1062 files changed, 36161 insertions, 40788 deletions

diff --git a/arch/powerpc/Kbuild b/arch/powerpc/Kbuild
index 22cd0d55a892..b010ccb071b6 100644
--- a/arch/powerpc/Kbuild
+++ b/arch/powerpc/Kbuild
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror -Wa,--fatal-warnings
+subdir-asflags-$(CONFIG_PPC_WERROR) := -Wa,--fatal-warnings
 
 obj-y += kernel/
 obj-y += mm/
@@ -18,4 +19,4 @@ obj-$(CONFIG_KEXEC_CORE)  += kexec/
 obj-$(CONFIG_KEXEC_FILE)  += purgatory/
 
 # for cleaning
-subdir- += boot
+subdir- += boot tools
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 539d1f03ff42..9537a61ebae0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -90,8 +90,7 @@ config NMI_IPI
 
 config PPC_WATCHDOG
 	bool
-	depends on HARDLOCKUP_DETECTOR
-	depends on HAVE_HARDLOCKUP_DETECTOR_ARCH
+	depends on HARDLOCKUP_DETECTOR_ARCH
 	default y
 	help
 	  This is a placeholder when the powerpc hardlockup detector
@@ -123,6 +122,7 @@ config PPC
 	# Please keep this list sorted alphabetically.
 	#
 	select ARCH_32BIT_OFF_T if PPC32
+	select ARCH_NEEDS_DEFER_KASAN		if PPC_RADIX_MMU
 	select ARCH_DISABLE_KASAN_INLINE	if PPC_RADIX_MMU
 	select ARCH_DMA_DEFAULT_COHERENT	if !NOT_COHERENT_CACHE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
@@ -134,10 +134,12 @@ config PPC
 	select ARCH_HAS_DEBUG_WX		if STRICT_KERNEL_RWX
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_DMA_MAP_DIRECT 		if PPC_PSERIES
+	select ARCH_HAS_DMA_OPS			if PPC64
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_HAS_HUGEPD			if HUGETLB_PAGE
+	select ARCH_HAS_GIGANTIC_PAGE		if ARCH_SUPPORTS_HUGETLBFS
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_KERNEL_FPU_SUPPORT	if PPC64 && PPC_FPU
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MEMREMAP_COMPAT_ALIGN	if PPC_64S_HASH_MMU
@@ -145,19 +147,23 @@ config PPC
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API
-	select ARCH_HAS_PTE_DEVMAP		if PPC_BOOK3S_64
+	select ARCH_HAS_PREEMPT_LAZY
+	select ARCH_HAS_PTDUMP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
 	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_STRICT_KERNEL_RWX	if (PPC_BOOK3S || PPC_8xx || 40x) && !HIBERNATION
+	select ARCH_HAS_STRICT_KERNEL_RWX	if (PPC_BOOK3S || PPC_8xx) && !HIBERNATION
 	select ARCH_HAS_STRICT_KERNEL_RWX	if PPC_85xx && !HIBERNATION && !RANDOMIZE_BASE
 	select ARCH_HAS_STRICT_MODULE_RWX	if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_SYSCALL_WRAPPER		if !SPU_BASE && !COMPAT
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
-	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_UBSAN
+	select ARCH_HAS_VDSO_ARCH_DATA
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_HAVE_EXTRA_ELF_NOTES        if SPU_BASE
 	select ARCH_KEEP_MEMBLOCK
+	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE	if PPC_RADIX_MMU
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
@@ -165,7 +171,10 @@ config PPC
 	select ARCH_SPLIT_ARG64			if PPC32
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_DEBUG_PAGEALLOC	if PPC_BOOK3S || PPC_8xx || 40x
+	select ARCH_SUPPORTS_DEBUG_PAGEALLOC	if PPC_BOOK3S || PPC_8xx
+	select ARCH_SUPPORTS_SCHED_MC		if SMP
+	select ARCH_SUPPORTS_SCHED_SMT		if PPC64 && SMP
+	select SCHED_MC				if ARCH_SUPPORTS_SCHED_MC
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
 	select ARCH_USE_MEMTEST
@@ -175,6 +184,7 @@ config PPC
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 	select ARCH_WANT_LD_ORPHAN_WARN
+	select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP	if PPC_RADIX_MMU
 	select ARCH_WANTS_MODULES_DATA_IN_VMALLOC	if PPC_BOOK3S_32 || PPC_8xx
 	select ARCH_WEAK_RELEASE_ACQUIRE
 	select BINFMT_ELF
@@ -183,10 +193,11 @@ config PPC
 	select CPUMASK_OFFSTACK			if NR_CPUS >= 8192
 	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
 	select DMA_OPS_BYPASS			if PPC64
-	select DMA_OPS				if PPC64
 	select DYNAMIC_FTRACE			if FUNCTION_TRACER
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
+	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+	select FUNCTION_ALIGNMENT_4B
 	select GENERIC_ATOMIC64			if PPC32
 	select GENERIC_CLOCKEVENTS_BROADCAST	if SMP
 	select GENERIC_CMOS_UPDATE
@@ -194,24 +205,24 @@ config PPC
 	select GENERIC_CPU_VULNERABILITIES	if PPC_BARRIER_NOSPEC
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_GETTIMEOFDAY
+	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IOREMAP
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_PCI_IOMAP		if PCI
-	select GENERIC_PTDUMP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
-	select GENERIC_VDSO_TIME_NS
 	select HAS_IOPORT			if PCI
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMALLOC		if HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_HUGE_VMAP		if PPC_RADIX_MMU || PPC_8xx
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
-	select HAVE_ARCH_KASAN			if PPC32 && PPC_PAGE_SHIFT <= 14
+	select HAVE_ARCH_KASAN			if PPC32 && PAGE_SHIFT <= 14
 	select HAVE_ARCH_KASAN			if PPC_RADIX_MMU
 	select HAVE_ARCH_KASAN			if PPC_BOOK3E_64
 	select HAVE_ARCH_KASAN_VMALLOC		if HAVE_ARCH_KASAN
-	select HAVE_ARCH_KCSAN            	if PPC_BOOK3S_64
+	select HAVE_ARCH_KCSAN
 	select HAVE_ARCH_KFENCE			if ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_WITHIN_STACK_FRAMES
@@ -227,20 +238,25 @@ config PPC
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_DYNAMIC_FTRACE_WITH_ARGS	if MPROFILE_KERNEL || PPC32
-	select HAVE_DYNAMIC_FTRACE_WITH_REGS	if MPROFILE_KERNEL || PPC32
+	select HAVE_DYNAMIC_FTRACE_WITH_ARGS	if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
+	select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if PPC_FTRACE_OUT_OF_LINE || (PPC32 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
+	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS if HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS	if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select HAVE_FAST_GUP
-	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_GUP_FAST
+	select HAVE_FTRACE_GRAPH_FUNC
+	select HAVE_FTRACE_REGS_HAVING_PT_REGS
+	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_DESCRIPTORS	if PPC64_ELF_ABI_V1
 	select HAVE_FUNCTION_ERROR_INJECTION
+	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_TRACER
-	select HAVE_GCC_PLUGINS			if GCC_VERSION >= 50200   # plugin support on gcc <= 5.1 is buggy on PPC
+	select HAVE_FUNCTION_TRACER		if !COMPILE_TEST && (PPC64 || (PPC32 && CC_IS_GCC))
+	select HAVE_GCC_PLUGINS
 	select HAVE_GENERIC_VDSO
 	select HAVE_HARDLOCKUP_DETECTOR_ARCH	if PPC_BOOK3S_64 && SMP
-	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_HW_BREAKPOINT		if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
 	select HAVE_IOREMAP_PROT
 	select HAVE_IRQ_TIME_ACCOUNTING
@@ -251,33 +267,41 @@ config PPC
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
-	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT
+	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT && (!ARCH_USING_PATCHABLE_FUNCTION_ENTRY || (!CC_IS_GCC || GCC_VERSION >= 110100))
 	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI				if PERF_EVENTS || (PPC64 && PPC_BOOK3S)
 	select HAVE_OPTPROBES
-	select HAVE_OBJTOOL			if PPC32 || MPROFILE_KERNEL
+	select HAVE_OBJTOOL			if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
 	select HAVE_OBJTOOL_MCOUNT		if HAVE_OBJTOOL
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI		if PPC64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_DYNAMIC_KEY
+	select HAVE_RETHOOK			if KPROBES
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_RSEQ
+	select HAVE_SAMPLE_FTRACE_DIRECT	if HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_SETUP_PER_CPU_AREA		if PPC64
 	select HAVE_SOFTIRQ_ON_OWN_STACK
-	select HAVE_STACKPROTECTOR		if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
-	select HAVE_STACKPROTECTOR		if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
+	select HAVE_STACKPROTECTOR		if PPC32 && $(cc-option,$(m32-flag) -mstack-protector-guard=tls -mstack-protector-guard-reg=r2 -mstack-protector-guard-offset=0)
+	select HAVE_STACKPROTECTOR		if PPC64 && $(cc-option,$(m64-flag) -mstack-protector-guard=tls -mstack-protector-guard-reg=r13 -mstack-protector-guard-offset=0)
 	select HAVE_STATIC_CALL			if PPC32
+	select HAVE_STATIC_CALL_INLINE		if PPC32
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN
+	select HOTPLUG_SMT			if HOTPLUG_CPU
+	select SMT_NUM_THREADS_DYNAMIC
 	select HUGETLB_PAGE_SIZE_VARIABLE	if PPC_BOOK3S_64 && HUGETLB_PAGE
 	select IOMMU_HELPER			if PPC64
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
-	select KASAN_VMALLOC			if KASAN && MODULES
+	select KASAN_VMALLOC			if KASAN && EXECMEM
+	select LOCK_MM_AND_FIND_VMA
 	select MMU_GATHER_PAGE_SIZE
 	select MMU_GATHER_RCU_TABLE_FREE
 	select MMU_GATHER_MERGE_VMAS
@@ -301,6 +325,7 @@ config PPC
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
 	select TRACE_IRQFLAGS_SUPPORT
+	select VDSO_GETRANDOM
 	#
 	# Please keep this list sorted alphabetically.
 	#
@@ -324,7 +349,6 @@ config PANIC_TIMEOUT
 config COMPAT
 	bool "Enable support for 32bit binaries"
 	depends on PPC64
-	depends on !CC_IS_CLANG || CLANG_VERSION >= 120000
 	default y if !CPU_LITTLE_ENDIAN
 	select ARCH_WANT_OLD_COMPAT_IPC
 	select COMPAT_OLD_SIGACTION
@@ -379,7 +403,7 @@ config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 	depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx || \
 		   (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \
-		   || 44x || 40x
+		   || 44x
 
 config ARCH_SUSPEND_NONZERO_CPU
 	def_bool y
@@ -392,12 +416,9 @@ config ARCH_HAS_ADD_PAGES
 config PPC_DCR_NATIVE
 	bool
 
-config PPC_DCR_MMIO
-	bool
-
 config PPC_DCR
 	bool
-	depends on PPC_DCR_NATIVE || PPC_DCR_MMIO
+	depends on PPC_DCR_NATIVE
 	default y
 
 config PPC_PCI_OF_BUS_MAP
@@ -423,17 +444,12 @@ config PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
 	  PCI domain dependent and each PCI controller on own domain can have
 	  256 PCI buses, like it is on other Linux architectures.
 
-config PPC_OF_PLATFORM_PCI
-	bool
-	depends on PCI
-	depends on PPC64 # not supported on 32 bits yet
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
 config PPC_ADV_DEBUG_REGS
 	bool
-	depends on 40x || BOOKE
+	depends on BOOKE
 	default y
 
 config PPC_ADV_DEBUG_IACS
@@ -480,7 +496,7 @@ source "kernel/Kconfig.hz"
 
 config MATH_EMULATION
 	bool "Math emulation"
-	depends on 4xx || PPC_8xx || PPC_MPC832x || BOOKE || PPC_MICROWATT
+	depends on 44x || PPC_8xx || PPC_MPC832x || BOOKE || PPC_MICROWATT
 	select PPC_FPU_REGS
 	help
 	  Some PowerPC chips designed for embedded applications do not have
@@ -547,8 +563,32 @@ config LD_HEAD_STUB_CATCH
 	  If unsure, say "N".
 
 config MPROFILE_KERNEL
-	depends on PPC64 && CPU_LITTLE_ENDIAN && FUNCTION_TRACER
-	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-mprofile-kernel.sh $(CC) -I$(srctree)/include -D__KERNEL__)
+	depends on PPC64_ELF_ABI_V2 && FUNCTION_TRACER
+	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-mprofile-kernel.sh $(CC) -mlittle-endian) if CPU_LITTLE_ENDIAN
+	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-mprofile-kernel.sh $(CC) -mbig-endian) if CPU_BIG_ENDIAN
+
+config ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+	depends on FUNCTION_TRACER && (PPC32 || PPC64_ELF_ABI_V2)
+	depends on $(cc-option,-fpatchable-function-entry=2)
+	def_bool y if PPC32
+	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN
+	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN
+
+config PPC_FTRACE_OUT_OF_LINE
+	def_bool PPC64 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+	select ARCH_WANTS_PRE_LINK_VMLINUX
+
+config PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE
+	int "Number of ftrace out-of-line stubs to reserve within .text"
+	depends on PPC_FTRACE_OUT_OF_LINE
+	default 32768
+	help
+	  Number of stubs to reserve for use by ftrace. This space is
+	  reserved within .text, and is distinct from any additional space
+	  added at the end of .text before the final vmlinux link. Set to
+	  zero to have stubs only be generated at the end of vmlinux (only
+	  if the size of vmlinux is less than 32MB). Set to a higher value
+	  if building vmlinux larger than 48MB.
 
 config HOTPLUG_CPU
 	bool "Support for enabling/disabling CPUs"
@@ -588,46 +628,28 @@ config PPC64_SUPPORTS_MEMORY_FAILURE
 	default "y" if PPC_POWERNV
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 
-config KEXEC
-	bool "kexec system call"
-	depends on PPC_BOOK3S || PPC_E500 || (44x && !SMP)
-	select KEXEC_CORE
-	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.
-
-	  It is an ongoing process to be certain the hardware in a machine
-	  is properly shutdown, so do not be surprised if this code does not
-	  initially work for you.  As of this writing the exact hardware
-	  interface is strongly in flux, so no good recommendation can be
-	  made.
-
-config KEXEC_FILE
-	bool "kexec file based system call"
-	select KEXEC_CORE
-	select HAVE_IMA_KEXEC if IMA
-	select KEXEC_ELF
-	depends on PPC64
-	depends on CRYPTO=y
-	depends on CRYPTO_SHA256=y
-	help
-	  This is a new version of the kexec system call. This call is
-	  file based and takes in file descriptors as system call arguments
-	  for kernel and initramfs as opposed to a list of segments as is the
-	  case for the older kexec call.
+config ARCH_SUPPORTS_KEXEC
+	def_bool PPC_BOOK3S || PPC_E500 || (44x && !SMP)
+
+config ARCH_SUPPORTS_KEXEC_FILE
+	def_bool PPC64
+
+config ARCH_SUPPORTS_KEXEC_PURGATORY
+	def_bool y
 
-config ARCH_HAS_KEXEC_PURGATORY
-	def_bool KEXEC_FILE
+config ARCH_SELECTS_KEXEC_FILE
+	def_bool y
+	depends on KEXEC_FILE
+	select KEXEC_ELF
+	select HAVE_IMA_KEXEC if IMA
 
 config PPC64_BIG_ENDIAN_ELF_ABI_V2
-	bool "Build big-endian kernel using ELF ABI V2 (EXPERIMENTAL)"
+	# Option is available to BFD, but LLD does not support ELFv1 so this is
+	# always true there.
+	prompt "Build big-endian kernel using ELF ABI V2" if LD_IS_BFD && EXPERT
+	def_bool y
 	depends on PPC64 && CPU_BIG_ENDIAN
 	depends on CC_HAS_ELFV2
-	depends on LD_VERSION >= 22400 || LLD_VERSION >= 150000
 	help
 	  This builds the kernel image using the "Power Architecture 64-Bit ELF
 	  V2 ABI Specification", which has a reduced stack overhead and faster
@@ -638,8 +660,6 @@ config PPC64_BIG_ENDIAN_ELF_ABI_V2
 	  it is less well tested by kernel and toolchain. However some distros
 	  build userspace this way, and it can produce a functioning kernel.
 
-	  This requires GCC and binutils 2.24 or newer.
-
 config RELOCATABLE
 	bool "Build a relocatable kernel"
 	depends on PPC64 || (FLATMEM && (44x || PPC_85xx))
@@ -682,20 +702,28 @@ config RELOCATABLE_TEST
 	  loaded at, which tends to be non-zero and therefore test the
 	  relocation code.
 
-config CRASH_DUMP
-	bool "Build a dump capture kernel"
-	depends on PPC64 || PPC_BOOK3S_32 || PPC_85xx || (44x && !SMP)
+config ARCH_SUPPORTS_CRASH_DUMP
+	def_bool PPC64 || PPC_BOOK3S_32 || PPC_85xx || (44x && !SMP)
+
+config ARCH_DEFAULT_CRASH_DUMP
+	bool
+	default y if !PPC_BOOK3S_32
+
+config ARCH_SELECTS_CRASH_DUMP
+	def_bool y
+	depends on CRASH_DUMP
 	select RELOCATABLE if PPC64 || 44x || PPC_85xx
-	help
-	  Build a kernel suitable for use as a dump capture kernel.
-	  The same kernel binary can be used as production kernel and dump
-	  capture kernel.
+
+config ARCH_SUPPORTS_CRASH_HOTPLUG
+	def_bool y
+	depends on PPC64
+
+config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+	def_bool CRASH_RESERVE
 
 config FA_DUMP
 	bool "Firmware-assisted dump"
-	depends on PPC64 && (PPC_RTAS || PPC_POWERNV)
-	select CRASH_CORE
-	select CRASH_DUMP
+	depends on CRASH_DUMP && PPC64 && (PPC_RTAS || PPC_POWERNV)
 	help
 	  A robust mechanism to get reliable kernel crash dump with
 	  assistance from firmware. This approach does not use kexec,
@@ -813,19 +841,23 @@ choice
 config PPC_4K_PAGES
 	bool "4k page size"
 	select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
+	select HAVE_PAGE_SIZE_4KB
 
 config PPC_16K_PAGES
 	bool "16k page size"
 	depends on 44x || PPC_8xx
+	select HAVE_PAGE_SIZE_16KB
 
 config PPC_64K_PAGES
 	bool "64k page size"
 	depends on 44x || PPC_BOOK3S_64
 	select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
+	select HAVE_PAGE_SIZE_64KB
 
 config PPC_256K_PAGES
 	bool "256k page size (Requires non-standard binutils settings)"
 	depends on 44x && !PPC_47x
+	select HAVE_PAGE_SIZE_256KB
 	help
 	  Make the page size 256k.
 
@@ -836,33 +868,11 @@ config PPC_256K_PAGES
 
 endchoice
 
-config PAGE_SIZE_4KB
-	def_bool y
-	depends on PPC_4K_PAGES
-
-config PAGE_SIZE_16KB
-	def_bool y
-	depends on PPC_16K_PAGES
-
-config PAGE_SIZE_64KB
-	def_bool y
-	depends on PPC_64K_PAGES
-
-config PAGE_SIZE_256KB
-	def_bool y
-	depends on PPC_256K_PAGES
-
-config PPC_PAGE_SHIFT
-	int
-	default 18 if PPC_256K_PAGES
-	default 16 if PPC_64K_PAGES
-	default 14 if PPC_16K_PAGES
-	default 12
-
 config THREAD_SHIFT
 	int "Thread shift" if EXPERT
 	range 13 15
 	default "15" if PPC_256K_PAGES
+	default "15" if PPC_PSERIES || PPC_POWERNV
 	default "14" if PPC64
 	default "13"
 	help
@@ -873,8 +883,8 @@ config DATA_SHIFT_BOOL
 	bool "Set custom data alignment"
 	depends on ADVANCED_OPTIONS
 	depends on STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE
-	depends on PPC_BOOK3S_32 || (PPC_8xx && !PIN_TLB_DATA && !STRICT_KERNEL_RWX) || \
-		   PPC_85xx
+	depends on (PPC_8xx && !PIN_TLB_DATA && (!STRICT_KERNEL_RWX || !PIN_TLB_TEXT)) || \
+		   PPC_BOOK3S_32 || PPC_85xx
 	help
 	  This option allows you to set the kernel data alignment. When
 	  RAM is mapped by blocks, the alignment needs to fit the size and
@@ -886,35 +896,41 @@ config DATA_SHIFT
 	int "Data shift" if DATA_SHIFT_BOOL
 	default 24 if STRICT_KERNEL_RWX && PPC64
 	range 17 28 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32
-	range 19 23 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
+	range 14 23 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
 	range 20 24 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_85xx
 	default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
 	default 18 if (DEBUG_PAGEALLOC || KFENCE) && PPC_BOOK3S_32
-	default 23 if STRICT_KERNEL_RWX && PPC_8xx
-	default 23 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx && PIN_TLB_DATA
-	default 19 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
+	default 23 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx && \
+		      (PIN_TLB_DATA || PIN_TLB_TEXT)
+	default 19 if (STRICT_KERNEL_RWX || DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
 	default 24 if STRICT_KERNEL_RWX && PPC_85xx
-	default PPC_PAGE_SHIFT
+	default PAGE_SHIFT
 	help
 	  On Book3S 32 (603+), DBATs are used to map kernel text and rodata RO.
 	  Smaller is the alignment, greater is the number of necessary DBATs.
 
-	  On 8xx, large pages (512kb or 8M) are used to map kernel linear
-	  memory. Aligning to 8M reduces TLB misses as only 8M pages are used
-	  in that case. If PIN_TLB is selected, it must be aligned to 8M as
-	  8M pages will be pinned.
+	  On 8xx, large pages (16kb or 512kb or 8M) are used to map kernel
+	  linear memory. Aligning to 8M reduces TLB misses as only 8M pages
+	  are used in that case. If PIN_TLB is selected, it must be aligned
+	  to 8M as 8M pages will be pinned.
 
 config ARCH_FORCE_MAX_ORDER
 	int "Order of maximal physically contiguous allocations"
+	range 7 8 if PPC64 && PPC_64K_PAGES
 	default "8" if PPC64 && PPC_64K_PAGES
+	range 12 12 if PPC64 && !PPC_64K_PAGES
 	default "12" if PPC64 && !PPC_64K_PAGES
+	range 8 10 if PPC32 && PPC_16K_PAGES
 	default "8" if PPC32 && PPC_16K_PAGES
+	range 6 10 if PPC32 && PPC_64K_PAGES
 	default "6" if PPC32 && PPC_64K_PAGES
+	range 4 10 if PPC32 && PPC_256K_PAGES
 	default "4" if PPC32 && PPC_256K_PAGES
+	range 10 12
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
@@ -952,14 +968,6 @@ config PPC_PROT_SAO_LPAR
 config PPC_COPRO_BASE
 	bool
 
-config SCHED_SMT
-	bool "SMT (Hyperthreading) scheduler support"
-	depends on PPC64 && SMP
-	help
-	  SMT scheduler support improves the CPU scheduler's decision making
-	  when dealing with POWER5 cpus at a cost of slightly increased
-	  overhead in some places. If unsure say N here.
-
 config PPC_DENORMALISATION
 	bool "PowerPC denormalisation exception handling"
 	depends on PPC_BOOK3S_64
@@ -978,7 +986,8 @@ config CMDLINE
 	  most cases you will need to specify the root device here.
 
 choice
-	prompt "Kernel command line type" if CMDLINE != ""
+	prompt "Kernel command line type"
+	depends on CMDLINE != ""
 	default CMDLINE_FROM_BOOTLOADER
 
 config CMDLINE_FROM_BOOTLOADER
@@ -1039,6 +1048,10 @@ config PPC_MEM_KEYS
 
 	  If unsure, say y.
 
+config ARCH_PKEY_BITS
+	int
+	default 5
+
 config PPC_SECURE_BOOT
 	prompt "Enable secure boot support"
 	bool
@@ -1090,7 +1103,7 @@ config GENERIC_ISA_DMA
 config PPC_INDIRECT_PCI
 	bool
 	depends on PCI
-	default y if 40x || 44x
+	default y if 44x
 
 config SBUS
 	bool
@@ -1115,15 +1128,12 @@ config FSL_PMC
 config PPC4xx_CPM
 	bool
 	default y
-	depends on SUSPEND && (44x || 40x)
+	depends on SUSPEND && 44x
 	help
 	  PPC4xx Clock Power Management (CPM) support (suspend/resume).
 	  It also enables support for two different idle states (idle-wait
 	  and idle-doze).
 
-config 4xx_SOC
-	bool
-
 config FSL_LBC
 	bool "Freescale Local Bus support"
 	help
@@ -1137,12 +1147,6 @@ config FSL_GTM
 	help
 	  Freescale General-purpose Timers support
 
-config PCI_8260
-	bool
-	depends on PCI && 8260
-	select PPC_INDIRECT_PCI
-	default y
-
 config FSL_RIO
 	bool "Freescale Embedded SRIO Controller support"
 	depends on RAPIDIO = y && HAVE_RAPIDIO
@@ -1291,10 +1295,37 @@ config TASK_SIZE_BOOL
 config TASK_SIZE
 	hex "Size of user task space" if TASK_SIZE_BOOL
 	default "0x80000000" if PPC_8xx
-	default "0xb0000000" if PPC_BOOK3S_32
+	default "0xb0000000" if PPC_BOOK3S_32 && EXECMEM
 	default "0xc0000000"
+
+config MODULES_SIZE_BOOL
+	bool "Set custom size for modules/execmem area"
+	depends on EXECMEM && ADVANCED_OPTIONS
+	help
+	  This option allows you to set the size of kernel virtual address
+	  space dedicated for modules/execmem.
+	  For the time being it is only for 8xx and book3s/32. Other
+	  platform share it with vmalloc space.
+
+	  Say N here unless you know what you are doing.
+
+config MODULES_SIZE
+	int "Size of modules/execmem area (In Mbytes)" if MODULES_SIZE_BOOL
+	range 1 256 if EXECMEM
+	default 64 if EXECMEM && PPC_BOOK3S_32
+	default 32 if EXECMEM && PPC_8xx
+	default 0
+
 endmenu
 
+config PPC64_PROC_SYSTEMCFG
+	def_bool y
+	depends on PPC64 && PROC_FS
+	help
+	  This option enables the presence of /proc/ppc64/systemcfg through
+	  which the systemcfg page can be accessed.
+	  This interface only exists for backwards-compatibility.
+
 if PPC64
 # This value must have zeroes in the bottom 60 bits otherwise lots will break
 config PAGE_OFFSET
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 6aaf8dc60610..f15e5920080b 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -82,6 +82,18 @@ config MSI_BITMAP_SELFTEST
 	bool "Run self-tests of the MSI bitmap code"
 	depends on DEBUG_KERNEL
 
+config GUEST_STATE_BUFFER_TEST
+	def_tristate n
+	prompt "Enable Guest State Buffer unit tests"
+	depends on KUNIT
+	depends on KVM_BOOK3S_HV_POSSIBLE
+	default KUNIT_ALL_TESTS
+	help
+	  The Guest State Buffer is a data format specified in the PAPR.
+	  It is by hcalls to communicate the state of L2 guests between
+	  the L1 and L0 hypervisors. Enable unit tests for the library
+	  used to create and use guest state buffers.
+
 config PPC_IRQ_SOFT_MASK_DEBUG
 	bool "Include extra checks for powerpc irq soft masking"
 	depends on PPC64
@@ -147,6 +159,8 @@ config BDI_SWITCH
 config BOOTX_TEXT
 	bool "Support for early boot text console (BootX or OpenFirmware only)"
 	depends on PPC_BOOK3S
+	select FONT_SUN8x16
+	select FONT_SUPPORT
 	help
 	  Say Y here to see progress messages from the boot firmware in text
 	  mode. Requires either BootX or Open Firmware.
@@ -202,19 +216,6 @@ config PPC_EARLY_DEBUG_RTAS_PANEL
 	help
 	  Select this to enable early debugging via the RTAS panel.
 
-config PPC_EARLY_DEBUG_RTAS_CONSOLE
-	bool "RTAS Console"
-	depends on PPC_RTAS
-	select UDBG_RTAS_CONSOLE
-	help
-	  Select this to enable early debugging via the RTAS console.
-
-config PPC_EARLY_DEBUG_MAPLE
-	bool "Maple real mode"
-	depends on PPC_MAPLE
-	help
-	  Select this to enable early debugging for Maple.
-
 config PPC_EARLY_DEBUG_PAS_REALMODE
 	bool "PA Semi real mode"
 	depends on PPC_PASEMI
@@ -230,17 +231,9 @@ config PPC_EARLY_DEBUG_44x
 	  inbuilt serial port.  If you enable this, ensure you set
 	  PPC_EARLY_DEBUG_44x_PHYSLOW below to suit your target board.
 
-config PPC_EARLY_DEBUG_40x
-	bool "Early serial debugging for IBM/AMCC 40x CPUs"
-	depends on 40x
-	help
-	  Select this to enable early debugging for IBM 40x chips via the
-	  inbuilt serial port. This works on chips with a 16550 compatible
-	  UART.
-
 config PPC_EARLY_DEBUG_CPM
 	bool "Early serial debugging for Freescale CPM-based serial ports"
-	depends on SERIAL_CPM
+	depends on SERIAL_CPM=y
 	help
 	  Select this to enable early debugging for Freescale chips
 	  using a CPM-based serial port.  This assumes that the bootwrapper
@@ -257,7 +250,6 @@ config PPC_EARLY_DEBUG_USBGECKO
 config PPC_EARLY_DEBUG_PS3GELIC
 	bool "Early debugging through the PS3 Ethernet port"
 	depends on PPC_PS3
-	select PS3GELIC_UDBG
 	help
 	  Select this to enable early debugging for the PlayStation3 via
 	  UDP broadcasts sent out through the Ethernet port.
@@ -343,11 +335,6 @@ config PPC_EARLY_DEBUG_44x_PHYSHIGH
 	depends on PPC_EARLY_DEBUG_44x
 	default "0x1"
 
-config PPC_EARLY_DEBUG_40x_PHYSADDR
-	hex "Early debug UART physical address"
-	depends on PPC_EARLY_DEBUG_40x
-	default "0xef600300"
-
 config PPC_EARLY_DEBUG_CPM_ADDR
 	hex "CPM UART early debug transmit descriptor address"
 	depends on PPC_EARLY_DEBUG_CPM
@@ -379,12 +366,6 @@ config FAIL_IOMMU
 
 	  If you are unsure, say N.
 
-config PPC_FAST_ENDIAN_SWITCH
-	bool "Deprecated fast endian-switch syscall"
-	depends on DEBUG_KERNEL && PPC_BOOK3S_64
-	help
-	  If you're unsure what this is, say N.
-
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index dca73f673d70..a58b1029592c 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -10,15 +10,26 @@
 # Rewritten by Cort Dougan and Paul Mackerras
 #
 
+ifdef cross_compiling
+  ifeq ($(CROSS_COMPILE),)
+    # Auto detect cross compiler prefix.
+    # Look for: (powerpc(64(le)?)?)(-unknown)?-linux(-gnu)?-
+    CC_ARCHES := powerpc powerpc64 powerpc64le
+    CC_SUFFIXES := linux linux-gnu unknown-linux-gnu
+    CROSS_COMPILE := $(call cc-cross-prefix, $(foreach a,$(CC_ARCHES), \
+                       $(foreach s,$(CC_SUFFIXES),$(a)-$(s)-)))
+  endif
+endif
+
 HAS_BIARCH	:= $(call cc-option-yn, -m32)
 
 # Set default 32 bits cross compilers for vdso and boot wrapper
 CROSS32_COMPILE ?=
 
 # If we're on a ppc/ppc64/ppc64le machine use that defconfig, otherwise just use
-# ppc64_defconfig because we have nothing better to go on.
+# ppc64le_defconfig because we have nothing better to go on.
 uname := $(shell uname -m)
-KBUILD_DEFCONFIG := $(if $(filter ppc%,$(uname)),$(uname),ppc64)_defconfig
+KBUILD_DEFCONFIG := $(if $(filter ppc%,$(uname)),$(uname),ppc64le)_defconfig
 
 new_nm := $(shell if $(NM) --help 2>&1 | grep -- '--synthetic' > /dev/null; then echo y; else echo n; fi)
 
@@ -42,28 +53,23 @@ machine-$(CONFIG_PPC64) += 64
 machine-$(CONFIG_CPU_LITTLE_ENDIAN) += le
 UTS_MACHINE := $(subst $(space),,$(machine-y))
 
-# XXX This needs to be before we override LD below
-ifdef CONFIG_PPC32
-KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
-else
-ifeq ($(call ld-ifversion, -ge, 22500, y),y)
+ifeq ($(CONFIG_PPC64)$(CONFIG_LD_IS_BFD),yy)
 # Have the linker provide sfpr if possible.
 # There is a corresponding test in arch/powerpc/lib/Makefile
 KBUILD_LDFLAGS_MODULE += --save-restore-funcs
 else
-KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
-endif
+KBUILD_LDFLAGS_MODULE += $(objtree)/arch/powerpc/lib/crtsavres.o
 endif
 
 ifdef CONFIG_CPU_LITTLE_ENDIAN
-KBUILD_CFLAGS	+= -mlittle-endian
+KBUILD_CPPFLAGS	+= -mlittle-endian
 KBUILD_LDFLAGS	+= -EL
 LDEMULATION	:= lppc
 GNUTARGET	:= powerpcle
 MULTIPLEWORD	:= -mno-multiple
 KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-save-toc-indirect)
 else
-KBUILD_CFLAGS += $(call cc-option,-mbig-endian)
+KBUILD_CPPFLAGS	+= $(call cc-option,-mbig-endian)
 KBUILD_LDFLAGS	+= -EB
 LDEMULATION	:= ppc
 GNUTARGET	:= powerpc
@@ -89,26 +95,18 @@ aflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
 aflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mlittle-endian
 
 ifeq ($(HAS_BIARCH),y)
-KBUILD_CFLAGS	+= -m$(BITS)
+KBUILD_CPPFLAGS	+= -m$(BITS)
 KBUILD_AFLAGS	+= -m$(BITS)
 KBUILD_LDFLAGS	+= -m elf$(BITS)$(LDEMULATION)
 endif
 
-cflags-$(CONFIG_STACKPROTECTOR)	+= -mstack-protector-guard=tls
-ifdef CONFIG_PPC64
-cflags-$(CONFIG_STACKPROTECTOR)	+= -mstack-protector-guard-reg=r13
-else
-cflags-$(CONFIG_STACKPROTECTOR)	+= -mstack-protector-guard-reg=r2
-endif
-
 LDFLAGS_vmlinux-y := -Bstatic
-LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie
+LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie --no-dynamic-linker
 LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) += -z notext
 LDFLAGS_vmlinux	:= $(LDFLAGS_vmlinux-y)
 
 ifdef CONFIG_PPC64
 ifndef CONFIG_PPC_KERNEL_PCREL
-ifeq ($(call cc-option-yn,-mcmodel=medium),y)
 	# -mcmodel=medium breaks modules because it uses 32bit offsets from
 	# the TOC pointer to create pointers where possible. Pointers into the
 	# percpu data area are created by this method.
@@ -118,9 +116,6 @@ ifeq ($(call cc-option-yn,-mcmodel=medium),y)
 	# kernel percpu data space (starting with 0xc...). We need a full
 	# 64bit relocation for this to work, hence -mcmodel=large.
 	KBUILD_CFLAGS_MODULE += -mcmodel=large
-else
-	export NO_MINIMAL_TOC := -mno-minimal-toc
-endif
 endif
 endif
 
@@ -133,41 +128,54 @@ CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcall-aixdesc)
 endif
 endif
-CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
+CFLAGS-$(CONFIG_PPC64)	+= -mcmodel=medium
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mlong-double-128)
 
 # Clang unconditionally reserves r2 on ppc32 and does not support the flag
-# https://bugs.llvm.org/show_bug.cgi?id=39555
+# https://llvm.org/pr39555
 CFLAGS-$(CONFIG_PPC32)	:= $(call cc-option, -ffixed-r2)
 
 # Clang doesn't support -mmultiple / -mno-multiple
-# https://bugs.llvm.org/show_bug.cgi?id=39556
+# https://llvm.org/pr39556
 CFLAGS-$(CONFIG_PPC32)	+= $(call cc-option, $(MULTIPLEWORD))
 
 CFLAGS-$(CONFIG_PPC32)	+= $(call cc-option,-mno-readonly-in-sdata)
 
+CC_FLAGS_FPU		:= $(call cc-option,-mhard-float)
+CC_FLAGS_NO_FPU		:= $(call cc-option,-msoft-float)
+
 ifdef CONFIG_FUNCTION_TRACER
+ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+KBUILD_CPPFLAGS	+= -DCC_USING_PATCHABLE_FUNCTION_ENTRY
+ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+CC_FLAGS_FTRACE := -fpatchable-function-entry=1
+else
+ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS # PPC32 only
+CC_FLAGS_FTRACE := -fpatchable-function-entry=3,1
+else
+CC_FLAGS_FTRACE := -fpatchable-function-entry=2
+endif
+endif
+else
 CC_FLAGS_FTRACE := -pg
 ifdef CONFIG_MPROFILE_KERNEL
 CC_FLAGS_FTRACE += -mprofile-kernel
 endif
 endif
+endif
 
 CFLAGS-$(CONFIG_TARGET_CPU_BOOL) += -mcpu=$(CONFIG_TARGET_CPU)
 AFLAGS-$(CONFIG_TARGET_CPU_BOOL) += -mcpu=$(CONFIG_TARGET_CPU)
 
-CFLAGS-$(CONFIG_POWERPC64_CPU) += $(call cc-option,-mtune=power10,	\
-				  $(call cc-option,-mtune=power9,	\
-				  $(call cc-option,-mtune=power8)))
+CFLAGS-y += $(CONFIG_TUNE_CPU)
 
 asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
 
-KBUILD_CPPFLAGS	+= -I $(srctree)/arch/$(ARCH) $(asinstr)
+KBUILD_CPPFLAGS	+= -I $(srctree)/arch/powerpc $(asinstr)
 KBUILD_AFLAGS	+= $(AFLAGS-y)
-KBUILD_CFLAGS	+= $(call cc-option,-msoft-float)
-KBUILD_CFLAGS	+= -pipe $(CFLAGS-y)
-CPP		= $(CC) -E $(KBUILD_CFLAGS)
+KBUILD_CFLAGS	+= $(CC_FLAGS_NO_FPU)
+KBUILD_CFLAGS	+= $(CFLAGS-y)
 
 CHECKFLAGS	+= -m$(BITS) -D__powerpc__ -D__powerpc$(BITS)__
 ifdef CONFIG_CPU_BIG_ENDIAN
@@ -210,18 +218,6 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 # often slow when they are implemented at all
 KBUILD_CFLAGS		+= $(call cc-option,-mno-string)
 
-cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
-
-# When using '-many -mpower4' gas will first try and find a matching power4
-# mnemonic and failing that it will allow any valid mnemonic that GAS knows
-# about. GCC will pass -many to GAS when assembling, clang does not.
-# LLVM IAS doesn't understand either flag: https://github.com/ClangBuiltLinux/linux/issues/675
-# but LLVM IAS only supports ISA >= 2.06 for Book3S 64 anyway...
-cpu-as-$(CONFIG_PPC_BOOK3S_64)	+= $(call as-option,-Wa$(comma)-mpower4) $(call as-option,-Wa$(comma)-many)
-
-KBUILD_AFLAGS += $(cpu-as-y)
-KBUILD_CFLAGS += $(cpu-as-y)
-
 KBUILD_AFLAGS += $(aflags-y)
 KBUILD_CFLAGS += $(cflags-y)
 
@@ -234,7 +230,7 @@ BOOT_TARGETS2 := zImage% dtbImage% treeImage.% cuImage.% simpleImage.% uImage.%
 
 PHONY += $(BOOT_TARGETS1) $(BOOT_TARGETS2)
 
-boot := arch/$(ARCH)/boot
+boot := arch/powerpc/boot
 
 $(BOOT_TARGETS1): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
@@ -305,6 +301,21 @@ ppc32_allmodconfig:
 	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/book3s_32.config \
 		-f $(srctree)/Makefile allmodconfig
 
+generated_configs += ppc44x_allmodconfig
+ppc44x_allmodconfig:
+	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/44x.config \
+		-f $(srctree)/Makefile allmodconfig
+
+generated_configs += ppc8xx_allmodconfig
+ppc8xx_allmodconfig:
+	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/8xx.config \
+		-f $(srctree)/Makefile allmodconfig
+
+generated_configs += ppc85xx_allmodconfig
+ppc85xx_allmodconfig:
+	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/85xx-32bit.config \
+		-f $(srctree)/Makefile allmodconfig
+
 generated_configs += ppc_defconfig
 ppc_defconfig:
 	$(call merge_into_defconfig,book3s_32.config,)
@@ -338,7 +349,7 @@ PHONY += $(generated_configs)
 
 define archhelp
   echo '* zImage          - Build default images selected by kernel config'
-  echo '  zImage.*        - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)'
+  echo '  zImage.*        - Compressed kernel image (arch/powerpc/boot/zImage.*)'
   echo '  uImage          - U-Boot native image format'
   echo '  cuImage.<dt>    - Backwards compatible U-Boot image for older'
   echo '                    versions which do not support device trees'
@@ -348,13 +359,13 @@ define archhelp
   echo '  install         - Install kernel using'
   echo '                    (your) ~/bin/$(INSTALLKERNEL) or'
   echo '                    (distribution) /sbin/$(INSTALLKERNEL) or'
-  echo '                    install to $$(INSTALL_PATH) and run lilo'
-  echo '  *_defconfig     - Select default config from arch/$(ARCH)/configs'
+  echo '                    install to $$(INSTALL_PATH)'
+  echo '  *_defconfig     - Select default config from arch/powerpc/configs'
   echo ''
   echo '  Targets with <dt> embed a device tree blob inside the image'
   echo '  These targets support board with firmware that does not'
   echo '  support passing a device tree directly.  Replace <dt> with the'
-  echo '  name of a dts file from the arch/$(ARCH)/boot/dts/ directory'
+  echo '  name of a dts file from the arch/powerpc/boot/dts/ directory'
   echo '  (minus the .dts extension).'
   echo
   $(foreach cfg,$(generated_configs),
@@ -391,21 +402,23 @@ prepare: stack_protector_prepare
 PHONY += stack_protector_prepare
 stack_protector_prepare: prepare0
 ifdef CONFIG_PPC64
-	$(eval KBUILD_CFLAGS += -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "PACA_CANARY") print $$3;}' include/generated/asm-offsets.h))
+	$(eval KBUILD_CFLAGS += -mstack-protector-guard=tls -mstack-protector-guard-reg=r13 \
+				-mstack-protector-guard-offset=$(shell awk '{if ($$2 == "PACA_CANARY") print $$3;}' \
+				$(objtree)/include/generated/asm-offsets.h))
 else
-	$(eval KBUILD_CFLAGS += -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "TASK_CANARY") print $$3;}' include/generated/asm-offsets.h))
+	$(eval KBUILD_CFLAGS += -mstack-protector-guard=tls -mstack-protector-guard-reg=r2 \
+				-mstack-protector-guard-offset=$(shell awk '{if ($$2 == "TASK_CANARY") print $$3;}' \
+				$(objtree)/include/generated/asm-offsets.h))
 endif
 endif
 
 PHONY += checkbin
-# Check toolchain versions:
-# - gcc-4.6 is the minimum kernel-wide version so nothing required.
 checkbin:
-	@if test "x${CONFIG_LD_IS_LLD}" != "xy" -a \
-		"x$(call ld-ifversion, -le, 22400, y)" = "xy" ; then \
-		echo -n '*** binutils 2.24 miscompiles weak symbols ' ; \
-		echo 'in some circumstances.' ; \
-		echo    '*** binutils 2.23 do not define the TOC symbol ' ; \
-		echo -n '*** Please use a different binutils version.' ; \
+	@if test "x${CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT}" = "xy" -a \
+		"x${CONFIG_LD_IS_BFD}" = "xy" -a \
+		"${CONFIG_LD_VERSION}" = "23700" ; then \
+		echo -n '*** binutils 2.37 drops unused section symbols, which recordmcount ' ; \
+		echo 'is unable to handle.' ; \
+		echo '*** Please use a different binutils version.' ; \
 		false ; \
 	fi
diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink
index 1f860b3c9bec..bb601be36173 100644
--- a/arch/powerpc/Makefile.postlink
+++ b/arch/powerpc/Makefile.postlink
@@ -24,6 +24,9 @@ else
 	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@"
 endif
 
+quiet_cmd_ftrace_check = CHKFTRC $@
+      cmd_ftrace_check = $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/ftrace_check.sh "$(NM)" "$@"
+
 # `@true` prevents complaint when there is nothing to be done
 
 vmlinux: FORCE
@@ -34,9 +37,11 @@ endif
 ifdef CONFIG_RELOCATABLE
 	$(call if_changed,relocs_check)
 endif
-
-%.ko: FORCE
-	@true
+ifdef CONFIG_FUNCTION_TRACER
+ifndef CONFIG_PPC64_ELF_ABI_V1
+	$(call cmd,ftrace_check)
+endif
+endif
 
 clean:
 	rm -f .tmp_symbols.txt
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index a4716d138cfc..5a867f23fe7f 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -30,7 +30,6 @@ zImage.coff
 zImage.epapr
 zImage.holly
 zImage.*lds
-zImage.maple
 zImage.miboot
 zImage.pmac
 zImage.pseries
diff --git a/arch/powerpc/boot/4xx.c b/arch/powerpc/boot/4xx.c
index 00c4d843a023..682ca3827892 100644
--- a/arch/powerpc/boot/4xx.c
+++ b/arch/powerpc/boot/4xx.c
@@ -253,7 +253,6 @@ void ibm4xx_denali_fixup_memsize(void)
 	dt_fixup_memory(0, memsize);
 }
 
-#define SPRN_DBCR0_40X 0x3F2
 #define SPRN_DBCR0_44X 0x134
 #define DBCR0_RST_SYSTEM 0x30000000
 
@@ -270,18 +269,6 @@ void ibm44x_dbcr_reset(void)
 
 }
 
-void ibm40x_dbcr_reset(void)
-{
-	unsigned long tmp;
-
-	asm volatile (
-		"mfspr	%0,%1\n"
-		"oris	%0,%0,%2@h\n"
-		"mtspr	%1,%0"
-		: "=&r"(tmp) : "i"(SPRN_DBCR0_40X), "i"(DBCR0_RST_SYSTEM)
-		);
-}
-
 #define EMAC_RESET 0x20000000
 void ibm4xx_quiesce_eth(u32 *emac0, u32 *emac1)
 {
@@ -544,256 +531,3 @@ void ibm440spe_fixup_clocks(unsigned int sys_clk,
 	eplike_fixup_uart_clk(1, "/plb/opb/serial@f0000300", ser_clk, plb_clk);
 	eplike_fixup_uart_clk(2, "/plb/opb/serial@f0000600", ser_clk, plb_clk);
 }
-
-void ibm405gp_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk)
-{
-	u32 pllmr = mfdcr(DCRN_CPC0_PLLMR);
-	u32 cpc0_cr0 = mfdcr(DCRN_405_CPC0_CR0);
-	u32 cpc0_cr1 = mfdcr(DCRN_405_CPC0_CR1);
-	u32 psr = mfdcr(DCRN_405_CPC0_PSR);
-	u32 cpu, plb, opb, ebc, tb, uart0, uart1, m;
-	u32 fwdv, fwdvb, fbdv, cbdv, opdv, epdv, ppdv, udiv;
-
-	fwdv = (8 - ((pllmr & 0xe0000000) >> 29));
-	fbdv = (pllmr & 0x1e000000) >> 25;
-	if (fbdv == 0)
-		fbdv = 16;
-	cbdv = ((pllmr & 0x00060000) >> 17) + 1; /* CPU:PLB */
-	opdv = ((pllmr & 0x00018000) >> 15) + 1; /* PLB:OPB */
-	ppdv = ((pllmr & 0x00006000) >> 13) + 1; /* PLB:PCI */
-	epdv = ((pllmr & 0x00001800) >> 11) + 2; /* PLB:EBC */
-	udiv = ((cpc0_cr0 & 0x3e) >> 1) + 1;
-
-	/* check for 405GPr */
-	if ((mfpvr() & 0xfffffff0) == (0x50910951 & 0xfffffff0)) {
-		fwdvb = 8 - (pllmr & 0x00000007);
-		if (!(psr & 0x00001000)) /* PCI async mode enable == 0 */
-			if (psr & 0x00000020) /* New mode enable */
-				m = fwdvb * 2 * ppdv;
-			else
-				m = fwdvb * cbdv * ppdv;
-		else if (psr & 0x00000020) /* New mode enable */
-			if (psr & 0x00000800) /* PerClk synch mode */
-				m = fwdvb * 2 * epdv;
-			else
-				m = fbdv * fwdv;
-		else if (epdv == fbdv)
-			m = fbdv * cbdv * epdv;
-		else
-			m = fbdv * fwdvb * cbdv;
-
-		cpu = sys_clk * m / fwdv;
-		plb = sys_clk * m / (fwdvb * cbdv);
-	} else {
-		m = fwdv * fbdv * cbdv;
-		cpu = sys_clk * m / fwdv;
-		plb = cpu / cbdv;
-	}
-	opb = plb / opdv;
-	ebc = plb / epdv;
-
-	if (cpc0_cr0 & 0x80)
-		/* uart0 uses the external clock */
-		uart0 = ser_clk;
-	else
-		uart0 = cpu / udiv;
-
-	if (cpc0_cr0 & 0x40)
-		/* uart1 uses the external clock */
-		uart1 = ser_clk;
-	else
-		uart1 = cpu / udiv;
-
-	/* setup the timebase clock to tick at the cpu frequency */
-	cpc0_cr1 = cpc0_cr1 & ~0x00800000;
-	mtdcr(DCRN_405_CPC0_CR1, cpc0_cr1);
-	tb = cpu;
-
-	dt_fixup_cpu_clocks(cpu, tb, 0);
-	dt_fixup_clock("/plb", plb);
-	dt_fixup_clock("/plb/opb", opb);
-	dt_fixup_clock("/plb/ebc", ebc);
-	dt_fixup_clock("/plb/opb/serial@ef600300", uart0);
-	dt_fixup_clock("/plb/opb/serial@ef600400", uart1);
-}
-
-
-void ibm405ep_fixup_clocks(unsigned int sys_clk)
-{
-	u32 pllmr0 = mfdcr(DCRN_CPC0_PLLMR0);
-	u32 pllmr1 = mfdcr(DCRN_CPC0_PLLMR1);
-	u32 cpc0_ucr = mfdcr(DCRN_CPC0_UCR);
-	u32 cpu, plb, opb, ebc, uart0, uart1;
-	u32 fwdva, fwdvb, fbdv, cbdv, opdv, epdv;
-	u32 pllmr0_ccdv, tb, m;
-
-	fwdva = 8 - ((pllmr1 & 0x00070000) >> 16);
-	fwdvb = 8 - ((pllmr1 & 0x00007000) >> 12);
-	fbdv = (pllmr1 & 0x00f00000) >> 20;
-	if (fbdv == 0)
-		fbdv = 16;
-
-	cbdv = ((pllmr0 & 0x00030000) >> 16) + 1; /* CPU:PLB */
-	epdv = ((pllmr0 & 0x00000300) >> 8) + 2;  /* PLB:EBC */
-	opdv = ((pllmr0 & 0x00003000) >> 12) + 1; /* PLB:OPB */
-
-	m = fbdv * fwdvb;
-
-	pllmr0_ccdv = ((pllmr0 & 0x00300000) >> 20) + 1;
-	if (pllmr1 & 0x80000000)
-		cpu = sys_clk * m / (fwdva * pllmr0_ccdv);
-	else
-		cpu = sys_clk / pllmr0_ccdv;
-
-	plb = cpu / cbdv;
-	opb = plb / opdv;
-	ebc = plb / epdv;
-	tb = cpu;
-	uart0 = cpu / (cpc0_ucr & 0x0000007f);
-	uart1 = cpu / ((cpc0_ucr & 0x00007f00) >> 8);
-
-	dt_fixup_cpu_clocks(cpu, tb, 0);
-	dt_fixup_clock("/plb", plb);
-	dt_fixup_clock("/plb/opb", opb);
-	dt_fixup_clock("/plb/ebc", ebc);
-	dt_fixup_clock("/plb/opb/serial@ef600300", uart0);
-	dt_fixup_clock("/plb/opb/serial@ef600400", uart1);
-}
-
-static u8 ibm405ex_fwdv_multi_bits[] = {
-	/* values for:  1 - 16 */
-	0x01, 0x02, 0x0e, 0x09, 0x04, 0x0b, 0x10, 0x0d, 0x0c, 0x05,
-	0x06, 0x0f, 0x0a, 0x07, 0x08, 0x03
-};
-
-u32 ibm405ex_get_fwdva(unsigned long cpr_fwdv)
-{
-	u32 index;
-
-	for (index = 0; index < ARRAY_SIZE(ibm405ex_fwdv_multi_bits); index++)
-		if (cpr_fwdv == (u32)ibm405ex_fwdv_multi_bits[index])
-			return index + 1;
-
-	return 0;
-}
-
-static u8 ibm405ex_fbdv_multi_bits[] = {
-	/* values for:  1 - 100 */
-	0x00, 0xff, 0x7e, 0xfd, 0x7a, 0xf5, 0x6a, 0xd5, 0x2a, 0xd4,
-	0x29, 0xd3, 0x26, 0xcc, 0x19, 0xb3, 0x67, 0xce, 0x1d, 0xbb,
-	0x77, 0xee, 0x5d, 0xba, 0x74, 0xe9, 0x52, 0xa5, 0x4b, 0x96,
-	0x2c, 0xd8, 0x31, 0xe3, 0x46, 0x8d, 0x1b, 0xb7, 0x6f, 0xde,
-	0x3d, 0xfb, 0x76, 0xed, 0x5a, 0xb5, 0x6b, 0xd6, 0x2d, 0xdb,
-	0x36, 0xec, 0x59, 0xb2, 0x64, 0xc9, 0x12, 0xa4, 0x48, 0x91,
-	0x23, 0xc7, 0x0e, 0x9c, 0x38, 0xf0, 0x61, 0xc2, 0x05, 0x8b,
-	0x17, 0xaf, 0x5f, 0xbe, 0x7c, 0xf9, 0x72, 0xe5, 0x4a, 0x95,
-	0x2b, 0xd7, 0x2e, 0xdc, 0x39, 0xf3, 0x66, 0xcd, 0x1a, 0xb4,
-	0x68, 0xd1, 0x22, 0xc4, 0x09, 0x93, 0x27, 0xcf, 0x1e, 0xbc,
-	/* values for:  101 - 200 */
-	0x78, 0xf1, 0x62, 0xc5, 0x0a, 0x94, 0x28, 0xd0, 0x21, 0xc3,
-	0x06, 0x8c, 0x18, 0xb0, 0x60, 0xc1, 0x02, 0x84, 0x08, 0x90,
-	0x20, 0xc0, 0x01, 0x83, 0x07, 0x8f, 0x1f, 0xbf, 0x7f, 0xfe,
-	0x7d, 0xfa, 0x75, 0xea, 0x55, 0xaa, 0x54, 0xa9, 0x53, 0xa6,
-	0x4c, 0x99, 0x33, 0xe7, 0x4e, 0x9d, 0x3b, 0xf7, 0x6e, 0xdd,
-	0x3a, 0xf4, 0x69, 0xd2, 0x25, 0xcb, 0x16, 0xac, 0x58, 0xb1,
-	0x63, 0xc6, 0x0d, 0x9b, 0x37, 0xef, 0x5e, 0xbd, 0x7b, 0xf6,
-	0x6d, 0xda, 0x35, 0xeb, 0x56, 0xad, 0x5b, 0xb6, 0x6c, 0xd9,
-	0x32, 0xe4, 0x49, 0x92, 0x24, 0xc8, 0x11, 0xa3, 0x47, 0x8e,
-	0x1c, 0xb8, 0x70, 0xe1, 0x42, 0x85, 0x0b, 0x97, 0x2f, 0xdf,
-	/* values for:  201 - 255 */
-	0x3e, 0xfc, 0x79, 0xf2, 0x65, 0xca, 0x15, 0xab, 0x57, 0xae,
-	0x5c, 0xb9, 0x73, 0xe6, 0x4d, 0x9a, 0x34, 0xe8, 0x51, 0xa2,
-	0x44, 0x89, 0x13, 0xa7, 0x4f, 0x9e, 0x3c, 0xf8, 0x71, 0xe2,
-	0x45, 0x8a, 0x14, 0xa8, 0x50, 0xa1, 0x43, 0x86, 0x0c, 0x98,
-	0x30, 0xe0, 0x41, 0x82, 0x04, 0x88, 0x10, 0xa0, 0x40, 0x81,
-	0x03, 0x87, 0x0f, 0x9f, 0x3f  /* END */
-};
-
-u32 ibm405ex_get_fbdv(unsigned long cpr_fbdv)
-{
-	u32 index;
-
-	for (index = 0; index < ARRAY_SIZE(ibm405ex_fbdv_multi_bits); index++)
-		if (cpr_fbdv == (u32)ibm405ex_fbdv_multi_bits[index])
-			return index + 1;
-
-	return 0;
-}
-
-void ibm405ex_fixup_clocks(unsigned int sys_clk, unsigned int uart_clk)
-{
-	/* PLL config */
-	u32 pllc  = CPR0_READ(DCRN_CPR0_PLLC);
-	u32 plld  = CPR0_READ(DCRN_CPR0_PLLD);
-	u32 cpud  = CPR0_READ(DCRN_CPR0_PRIMAD);
-	u32 plbd  = CPR0_READ(DCRN_CPR0_PRIMBD);
-	u32 opbd  = CPR0_READ(DCRN_CPR0_OPBD);
-	u32 perd  = CPR0_READ(DCRN_CPR0_PERD);
-
-	/* Dividers */
-	u32 fbdv   = ibm405ex_get_fbdv(__fix_zero((plld >> 24) & 0xff, 1));
-
-	u32 fwdva  = ibm405ex_get_fwdva(__fix_zero((plld >> 16) & 0x0f, 1));
-
-	u32 cpudv0 = __fix_zero((cpud >> 24) & 7, 8);
-
-	/* PLBDV0 is hardwared to 010. */
-	u32 plbdv0 = 2;
-	u32 plb2xdv0 = __fix_zero((plbd >> 16) & 7, 8);
-
-	u32 opbdv0 = __fix_zero((opbd >> 24) & 3, 4);
-
-	u32 perdv0 = __fix_zero((perd >> 24) & 3, 4);
-
-	/* Resulting clocks */
-	u32 cpu, plb, opb, ebc, vco, tb, uart0, uart1;
-
-	/* PLL's VCO is the source for primary forward ? */
-	if (pllc & 0x40000000) {
-		u32 m;
-
-		/* Feedback path */
-		switch ((pllc >> 24) & 7) {
-		case 0:
-			/* PLLOUTx */
-			m = fbdv;
-			break;
-		case 1:
-			/* CPU */
-			m = fbdv * fwdva * cpudv0;
-			break;
-		case 5:
-			/* PERClk */
-			m = fbdv * fwdva * plb2xdv0 * plbdv0 * opbdv0 * perdv0;
-			break;
-		default:
-			printf("WARNING ! Invalid PLL feedback source !\n");
-			goto bypass;
-		}
-
-		vco = (unsigned int)(sys_clk * m);
-	} else {
-bypass:
-		/* Bypass system PLL */
-		vco = 0;
-	}
-
-	/* CPU = VCO / ( FWDVA x CPUDV0) */
-	cpu = vco / (fwdva * cpudv0);
-	/* PLB = VCO / ( FWDVA x PLB2XDV0 x PLBDV0) */
-	plb = vco / (fwdva * plb2xdv0 * plbdv0);
-	/* OPB = PLB / OPBDV0 */
-	opb = plb / opbdv0;
-	/* EBC = OPB / PERDV0 */
-	ebc = opb / perdv0;
-
-	tb = cpu;
-	uart0 = uart1 = uart_clk;
-
-	dt_fixup_cpu_clocks(cpu, tb, 0);
-	dt_fixup_clock("/plb", plb);
-	dt_fixup_clock("/plb/opb", opb);
-	dt_fixup_clock("/plb/opb/ebc", ebc);
-	dt_fixup_clock("/plb/opb/serial@ef600200", uart0);
-	dt_fixup_clock("/plb/opb/serial@ef600300", uart1);
-}
diff --git a/arch/powerpc/boot/4xx.h b/arch/powerpc/boot/4xx.h
index 77f15d124c81..62df496b7ba6 100644
--- a/arch/powerpc/boot/4xx.h
+++ b/arch/powerpc/boot/4xx.h
@@ -12,13 +12,9 @@ void ibm4xx_sdram_fixup_memsize(void);
 void ibm440spe_fixup_memsize(void);
 void ibm4xx_denali_fixup_memsize(void);
 void ibm44x_dbcr_reset(void);
-void ibm40x_dbcr_reset(void);
 void ibm4xx_quiesce_eth(u32 *emac0, u32 *emac1);
 void ibm4xx_fixup_ebc_ranges(const char *ebc);
 
-void ibm405gp_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk);
-void ibm405ep_fixup_clocks(unsigned int sys_clk);
-void ibm405ex_fixup_clocks(unsigned int sys_clk, unsigned int uart_clk);
 void ibm440gp_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk);
 void ibm440ep_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk,
 			   unsigned int tmr_clk);
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 85cde5bf04b7..f1a4761ebd44 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -32,47 +32,61 @@ else
     BOOTAR := $(AR)
 endif
 
-BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
-		 -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \
-		 $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \
-		 $(call cc-option,-mno-mma) \
-		 $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \
-		 -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
-		 $(LINUXINCLUDE)
-
 ifdef CONFIG_PPC64_BOOT_WRAPPER
-BOOTCFLAGS	+= -m64
+BOOTTARGETFLAGS	+= -m64
+BOOTTARGETFLAGS	+= -mabi=elfv2
 ifdef CONFIG_PPC64_ELF_ABI_V2
-BOOTCFLAGS	+= $(call cc-option,-mabi=elfv2)
+BOOTTARGETFLAGS	+= $(call cc-option,-mabi=elfv2)
 endif
 else
-BOOTCFLAGS	+= -m32
+BOOTTARGETFLAGS	:= -m32
 endif
 
 ifdef CONFIG_TARGET_CPU_BOOL
-BOOTCFLAGS	+= -mcpu=$(CONFIG_TARGET_CPU)
+BOOTTARGETFLAGS	+= -mcpu=$(CONFIG_TARGET_CPU)
 else ifdef CONFIG_PPC64_BOOT_WRAPPER
 ifdef CONFIG_CPU_LITTLE_ENDIAN
-BOOTCFLAGS	+= -mcpu=powerpc64le
+BOOTTARGETFLAGS	+= -mcpu=powerpc64le
 else
-BOOTCFLAGS	+= -mcpu=powerpc64
+BOOTTARGETFLAGS	+= -mcpu=powerpc64
 endif
 endif
 
-BOOTCFLAGS	+= -isystem $(shell $(BOOTCC) -print-file-name=include)
+$(obj)/4xx.o: BOOTTARGETFLAGS += -mcpu=405
+$(obj)/ebony.o: BOOTTARGETFLAGS += -mcpu=440
+$(obj)/cuboot-taishan.o: BOOTTARGETFLAGS += -mcpu=440
+$(obj)/cuboot-katmai.o: BOOTTARGETFLAGS += -mcpu=440
+$(obj)/treeboot-iss4xx.o: BOOTTARGETFLAGS += -mcpu=405
+$(obj)/treeboot-currituck.o: BOOTTARGETFLAGS += -mcpu=405
+$(obj)/treeboot-akebono.o: BOOTTARGETFLAGS += -mcpu=405
 
 ifdef CONFIG_CPU_BIG_ENDIAN
-BOOTCFLAGS	+= -mbig-endian
+BOOTTARGETFLAGS	+= -mbig-endian
 else
-BOOTCFLAGS	+= -mlittle-endian
+BOOTTARGETFLAGS	+= -mlittle-endian
 endif
 
-BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc
+BOOTCPPFLAGS	:= -nostdinc $(LINUXINCLUDE)
+BOOTCPPFLAGS	+= -isystem $(shell $(BOOTCC) -print-file-name=include)
+
+BOOTCFLAGS	:= $(BOOTTARGETFLAGS) \
+		   -std=gnu11 -fms-extensions \
+		   -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
+		   -fno-strict-aliasing -O2 \
+		   -msoft-float -mno-altivec -mno-vsx \
+		   $(call cc-option,-mno-prefixed) \
+		   $(call cc-option,-mno-pcrel) \
+		   $(call cc-option,-mno-mma) \
+		   $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \
+		   -fomit-frame-pointer -fno-builtin -fPIC
+
+BOOTAFLAGS	:= $(BOOTTARGETFLAGS) -D__ASSEMBLY__
 
 BOOTARFLAGS	:= -crD
 
 ifdef CONFIG_CC_IS_CLANG
 BOOTCFLAGS += $(CLANG_FLAGS)
+BOOTCFLAGS += -Wno-microsoft-anon-tag
 BOOTAFLAGS += $(CLANG_FLAGS)
 endif
 
@@ -89,23 +103,13 @@ BOOTCFLAGS	+= -I$(objtree)/$(obj) -I$(srctree)/$(obj)
 
 DTC_FLAGS	?= -p 1024
 
-$(obj)/4xx.o: BOOTCFLAGS += -mcpu=405
-$(obj)/ebony.o: BOOTCFLAGS += -mcpu=440
-$(obj)/cuboot-hotfoot.o: BOOTCFLAGS += -mcpu=405
-$(obj)/cuboot-taishan.o: BOOTCFLAGS += -mcpu=440
-$(obj)/cuboot-katmai.o: BOOTCFLAGS += -mcpu=440
-$(obj)/cuboot-acadia.o: BOOTCFLAGS += -mcpu=405
-$(obj)/treeboot-iss4xx.o: BOOTCFLAGS += -mcpu=405
-$(obj)/treeboot-currituck.o: BOOTCFLAGS += -mcpu=405
-$(obj)/treeboot-akebono.o: BOOTCFLAGS += -mcpu=405
-
 # The pre-boot decompressors pull in a lot of kernel headers and other source
 # files. This creates a bit of a dependency headache since we need to copy
 # these files into the build dir, fix up any includes and ensure that dependent
 # files are copied in the right order.
 
-# these need to be seperate variables because they are copied out of different
-# directories in the kernel tree. Sure you COULd merge them, but it's a
+# these need to be separate variables because they are copied out of different
+# directories in the kernel tree. Sure you COULD merge them, but it's a
 # cure-is-worse-than-disease situation.
 zlib-decomp-$(CONFIG_KERNEL_GZIP) := decompress_inflate.c
 zlib-$(CONFIG_KERNEL_GZIP) := inffast.c inflate.c inftrees.c
@@ -142,7 +146,6 @@ src-wlib-$(CONFIG_PPC_POWERNV) += opal-calls.S opal.c
 ifndef CONFIG_PPC64_BOOT_WRAPPER
 src-wlib-y += crtsavres.S
 endif
-src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c
 src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c
 src-wlib-$(CONFIG_PPC_8xx) += mpc8xx.c planetcore.c fsl-soc.c
 src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c
@@ -150,9 +153,6 @@ src-wlib-$(CONFIG_EMBEDDED6xx) += ugecon.c fsl-soc.c
 src-wlib-$(CONFIG_CPM) += cpm-serial.c
 
 src-plat-y := of.c epapr.c
-src-plat-$(CONFIG_40x) += fixed-head.S cuboot-hotfoot.c \
-				cuboot-acadia.c \
-				cuboot-kilauea.c simpleboot.c
 src-plat-$(CONFIG_44x) += treeboot-ebony.c cuboot-ebony.c treeboot-bamboo.c \
 				cuboot-bamboo.c cuboot-sam440ep.c \
 				cuboot-sequoia.c cuboot-rainier.c \
@@ -175,7 +175,6 @@ src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c
 src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c
 src-plat-$(CONFIG_PPC_PSERIES) += pseries-head.S
 src-plat-$(CONFIG_PPC_POWERNV) += pseries-head.S
-src-plat-$(CONFIG_PPC_IBM_CELL_BLADE) += pseries-head.S
 src-plat-$(CONFIG_MVME7100) += motload-head.S mvme7100.c
 
 src-plat-$(CONFIG_PPC_MICROWATT) += fixed-head.S microwatt.c
@@ -214,7 +213,7 @@ $(addprefix $(obj)/,$(libfdt) $(libfdtheader)): $(obj)/%: $(srctree)/scripts/dtc
 $(obj)/empty.c:
 	$(Q)touch $@
 
-$(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(srctree)/$(src)/%.S
+$(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(src)/%.S
 	$(Q)cp $< $@
 
 clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \
@@ -222,10 +221,10 @@ clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \
 		empty.c zImage.coff.lds zImage.ps3.lds zImage.lds
 
 quiet_cmd_bootcc = BOOTCC  $@
-      cmd_bootcc = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $<
+      cmd_bootcc = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTCPPFLAGS) $(BOOTCFLAGS) -c -o $@ $<
 
 quiet_cmd_bootas = BOOTAS  $@
-      cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $<
+      cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTCPPFLAGS) $(BOOTAFLAGS) -c -o $@ $<
 
 quiet_cmd_bootar = BOOTAR  $@
       cmd_bootar = $(BOOTAR) $(BOOTARFLAGS) $@.$$$$ $(real-prereqs); mv $@.$$$$ $@
@@ -245,13 +244,13 @@ $(obj)/wrapper.a: $(obj-wlib) FORCE
 hostprogs	:= addnote hack-coff mktree
 
 targets		+= $(patsubst $(obj)/%,%,$(obj-boot) wrapper.a) zImage.lds
-extra-y		:= $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \
+always-y	:= $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \
 		   $(obj)/zImage.lds $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds
 
-dtstree		:= $(srctree)/$(src)/dts
+dtstree		:= $(src)/dts
 
-wrapper		:=$(srctree)/$(src)/wrapper
-wrapperbits	:= $(extra-y) $(addprefix $(obj)/,addnote hack-coff mktree) \
+wrapper		:= $(src)/wrapper
+wrapperbits	:= $(always-y) $(addprefix $(obj)/,addnote hack-coff mktree) \
 			$(wrapper) FORCE
 
 #############
@@ -278,8 +277,6 @@ quiet_cmd_wrap	= WRAP    $@
 
 image-$(CONFIG_PPC_PSERIES)		+= zImage.pseries
 image-$(CONFIG_PPC_POWERNV)		+= zImage.pseries
-image-$(CONFIG_PPC_MAPLE)		+= zImage.maple
-image-$(CONFIG_PPC_IBM_CELL_BLADE)	+= zImage.pseries
 image-$(CONFIG_PPC_PS3)			+= dtbImage.ps3
 image-$(CONFIG_PPC_CHRP)		+= zImage.chrp
 image-$(CONFIG_PPC_EFIKA)		+= zImage.chrp
@@ -296,11 +293,6 @@ image-$(CONFIG_EPAPR_BOOT)		+= zImage.epapr
 # Boards with newish u-boot firmware can use the uImage target above
 #
 
-# Board ports in arch/powerpc/platform/40x/Kconfig
-image-$(CONFIG_HOTFOOT)			+= cuImage.hotfoot
-image-$(CONFIG_ACADIA)			+= cuImage.acadia
-image-$(CONFIG_OBS600)			+= uImage.obs600
-
 # Board ports in arch/powerpc/platform/44x/Kconfig
 image-$(CONFIG_EBONY)			+= treeImage.ebony cuImage.ebony
 image-$(CONFIG_BAMBOO)			+= treeImage.bamboo cuImage.bamboo
@@ -338,11 +330,6 @@ image-$(CONFIG_MPC834x_ITX)		+= cuImage.mpc8349emitx \
 image-$(CONFIG_ASP834x)			+= dtbImage.asp834x-redboot
 
 # Board ports in arch/powerpc/platform/85xx/Kconfig
-image-$(CONFIG_MPC8540_ADS)		+= cuImage.mpc8540ads
-image-$(CONFIG_MPC8560_ADS)		+= cuImage.mpc8560ads
-image-$(CONFIG_MPC85xx_CDS)		+= cuImage.mpc8541cds \
-					   cuImage.mpc8548cds_32b \
-					   cuImage.mpc8555cds
 image-$(CONFIG_MPC85xx_MDS)		+= cuImage.mpc8568mds
 image-$(CONFIG_MPC85xx_DS)		+= cuImage.mpc8544ds \
 					   cuImage.mpc8572ds
@@ -456,7 +443,7 @@ $(obj)/zImage.initrd:	$(addprefix $(obj)/, $(initrd-y))
 clean-files += $(image-) $(initrd-) cuImage.* dtbImage.* treeImage.* \
 	zImage zImage.initrd zImage.chrp zImage.coff zImage.holly \
 	zImage.miboot zImage.pmac zImage.pseries \
-	zImage.maple simpleImage.* otheros.bld
+	simpleImage.* otheros.bld
 
 # clean up files cached by wrapper
 clean-kernel-base := vmlinux.strip vmlinux.bin
@@ -470,7 +457,7 @@ WRAPPER_DTSDIR := /usr/lib/kernel-wrapper/dts
 WRAPPER_BINDIR := /usr/sbin
 INSTALL := install
 
-extra-installed		:= $(patsubst $(obj)/%, $(DESTDIR)$(WRAPPER_OBJDIR)/%, $(extra-y))
+extra-installed		:= $(patsubst $(obj)/%, $(DESTDIR)$(WRAPPER_OBJDIR)/%, $(always-y))
 hostprogs-installed	:= $(patsubst %, $(DESTDIR)$(WRAPPER_BINDIR)/%, $(hostprogs))
 wrapper-installed	:= $(DESTDIR)$(WRAPPER_BINDIR)/wrapper
 dts-installed		:= $(patsubst $(dtstree)/%, $(DESTDIR)$(WRAPPER_DTSDIR)/%, $(wildcard $(dtstree)/*.dts))
diff --git a/arch/powerpc/boot/addnote.c b/arch/powerpc/boot/addnote.c
index 53b3b2621457..78704927453a 100644
--- a/arch/powerpc/boot/addnote.c
+++ b/arch/powerpc/boot/addnote.c
@@ -68,8 +68,8 @@ static int e_class = ELFCLASS32;
 #define PUT_16BE(off, v)(buf[off] = ((v) >> 8) & 0xff, \
 			 buf[(off) + 1] = (v) & 0xff)
 #define PUT_32BE(off, v)(PUT_16BE((off), (v) >> 16L), PUT_16BE((off) + 2, (v)))
-#define PUT_64BE(off, v)((PUT_32BE((off), (v) >> 32L), \
-			  PUT_32BE((off) + 4, (v))))
+#define PUT_64BE(off, v)((PUT_32BE((off), (unsigned long long)(v) >> 32L), \
+			  PUT_32BE((off) + 4, (unsigned long long)(v))))
 
 #define GET_16LE(off)	((buf[off]) + (buf[(off)+1] << 8))
 #define GET_32LE(off)	(GET_16LE(off) + (GET_16LE((off)+2U) << 16U))
@@ -78,7 +78,8 @@ static int e_class = ELFCLASS32;
 #define PUT_16LE(off, v) (buf[off] = (v) & 0xff, \
 			  buf[(off) + 1] = ((v) >> 8) & 0xff)
 #define PUT_32LE(off, v) (PUT_16LE((off), (v)), PUT_16LE((off) + 2, (v) >> 16L))
-#define PUT_64LE(off, v) (PUT_32LE((off), (v)), PUT_32LE((off) + 4, (v) >> 32L))
+#define PUT_64LE(off, v) (PUT_32LE((off), (unsigned long long)(v)), \
+			  PUT_32LE((off) + 4, (unsigned long long)(v) >> 32L))
 
 #define GET_16(off)	(e_data == ELFDATA2MSB ? GET_16BE(off) : GET_16LE(off))
 #define GET_32(off)	(e_data == ELFDATA2MSB ? GET_32BE(off) : GET_32LE(off))
diff --git a/arch/powerpc/boot/cuboot-acadia.c b/arch/powerpc/boot/cuboot-acadia.c
deleted file mode 100644
index 46e96756cfe1..000000000000
--- a/arch/powerpc/boot/cuboot-acadia.c
+++ /dev/null
@@ -1,171 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Old U-boot compatibility for Acadia
- *
- * Author: Josh Boyer <jwboyer@linux.vnet.ibm.com>
- *
- * Copyright 2008 IBM Corporation
- */
-
-#include "ops.h"
-#include "io.h"
-#include "dcr.h"
-#include "stdio.h"
-#include "4xx.h"
-#include "44x.h"
-#include "cuboot.h"
-
-#define TARGET_4xx
-#include "ppcboot.h"
-
-static bd_t bd;
-
-#define CPR_PERD0_SPIDV_MASK   0x000F0000     /* SPI Clock Divider */
-
-#define PLLC_SRC_MASK	       0x20000000     /* PLL feedback source */
-
-#define PLLD_FBDV_MASK	       0x1F000000     /* PLL feedback divider value */
-#define PLLD_FWDVA_MASK        0x000F0000     /* PLL forward divider A value */
-#define PLLD_FWDVB_MASK        0x00000700     /* PLL forward divider B value */
-
-#define PRIMAD_CPUDV_MASK      0x0F000000     /* CPU Clock Divisor Mask */
-#define PRIMAD_PLBDV_MASK      0x000F0000     /* PLB Clock Divisor Mask */
-#define PRIMAD_OPBDV_MASK      0x00000F00     /* OPB Clock Divisor Mask */
-#define PRIMAD_EBCDV_MASK      0x0000000F     /* EBC Clock Divisor Mask */
-
-#define PERD0_PWMDV_MASK       0xFF000000     /* PWM Divider Mask */
-#define PERD0_SPIDV_MASK       0x000F0000     /* SPI Divider Mask */
-#define PERD0_U0DV_MASK        0x0000FF00     /* UART 0 Divider Mask */
-#define PERD0_U1DV_MASK        0x000000FF     /* UART 1 Divider Mask */
-
-static void get_clocks(void)
-{
-	unsigned long sysclk, cpr_plld, cpr_pllc, cpr_primad, plloutb, i;
-	unsigned long pllFwdDiv, pllFwdDivB, pllFbkDiv, pllPlbDiv, pllExtBusDiv;
-	unsigned long pllOpbDiv, freqEBC, freqUART, freqOPB;
-	unsigned long div;		/* total divisor udiv * bdiv */
-	unsigned long umin;		/* minimum udiv	*/
-	unsigned short diff;		/* smallest diff */
-	unsigned long udiv;		/* best udiv */
-	unsigned short idiff;		/* current diff */
-	unsigned short ibdiv;		/* current bdiv */
-	unsigned long est;		/* current estimate */
-	unsigned long baud;
-	void *np;
-
-	/* read the sysclk value from the CPLD */
-	sysclk = (in_8((unsigned char *)0x80000000) == 0xc) ? 66666666 : 33333000;
-
-	/*
-	 * Read PLL Mode registers
-	 */
-	cpr_plld = CPR0_READ(DCRN_CPR0_PLLD);
-	cpr_pllc = CPR0_READ(DCRN_CPR0_PLLC);
-
-	/*
-	 * Determine forward divider A
-	 */
-	pllFwdDiv = ((cpr_plld & PLLD_FWDVA_MASK) >> 16);
-
-	/*
-	 * Determine forward divider B
-	 */
-	pllFwdDivB = ((cpr_plld & PLLD_FWDVB_MASK) >> 8);
-	if (pllFwdDivB == 0)
-		pllFwdDivB = 8;
-
-	/*
-	 * Determine FBK_DIV.
-	 */
-	pllFbkDiv = ((cpr_plld & PLLD_FBDV_MASK) >> 24);
-	if (pllFbkDiv == 0)
-		pllFbkDiv = 256;
-
-	/*
-	 * Read CPR_PRIMAD register
-	 */
-	cpr_primad = CPR0_READ(DCRN_CPR0_PRIMAD);
-
-	/*
-	 * Determine PLB_DIV.
-	 */
-	pllPlbDiv = ((cpr_primad & PRIMAD_PLBDV_MASK) >> 16);
-	if (pllPlbDiv == 0)
-		pllPlbDiv = 16;
-
-	/*
-	 * Determine EXTBUS_DIV.
-	 */
-	pllExtBusDiv = (cpr_primad & PRIMAD_EBCDV_MASK);
-	if (pllExtBusDiv == 0)
-		pllExtBusDiv = 16;
-
-	/*
-	 * Determine OPB_DIV.
-	 */
-	pllOpbDiv = ((cpr_primad & PRIMAD_OPBDV_MASK) >> 8);
-	if (pllOpbDiv == 0)
-		pllOpbDiv = 16;
-
-	/* There is a bug in U-Boot that prevents us from using
-	 * bd.bi_opbfreq because U-Boot doesn't populate it for
-	 * 405EZ.  We get to calculate it, yay!
-	 */
-	freqOPB = (sysclk *pllFbkDiv) /pllOpbDiv;
-
-	freqEBC = (sysclk * pllFbkDiv) / pllExtBusDiv;
-
-	plloutb = ((sysclk * ((cpr_pllc & PLLC_SRC_MASK) ?
-					   pllFwdDivB : pllFwdDiv) *
-		    pllFbkDiv) / pllFwdDivB);
-
-	np = find_node_by_alias("serial0");
-	if (getprop(np, "current-speed", &baud, sizeof(baud)) != sizeof(baud))
-		fatal("no current-speed property\n\r");
-
-	udiv = 256;			/* Assume lowest possible serial clk */
-	div = plloutb / (16 * baud); /* total divisor */
-	umin = (plloutb / freqOPB) << 1;	/* 2 x OPB divisor */
-	diff = 256;			/* highest possible */
-
-	/* i is the test udiv value -- start with the largest
-	 * possible (256) to minimize serial clock and constrain
-	 * search to umin.
-	 */
-	for (i = 256; i > umin; i--) {
-		ibdiv = div / i;
-		est = i * ibdiv;
-		idiff = (est > div) ? (est-div) : (div-est);
-		if (idiff == 0) {
-			udiv = i;
-			break;      /* can't do better */
-		} else if (idiff < diff) {
-			udiv = i;       /* best so far */
-			diff = idiff;   /* update lowest diff*/
-		}
-	}
-	freqUART = plloutb / udiv;
-
-	dt_fixup_cpu_clocks(bd.bi_procfreq, bd.bi_intfreq, bd.bi_plb_busfreq);
-	dt_fixup_clock("/plb/ebc", freqEBC);
-	dt_fixup_clock("/plb/opb", freqOPB);
-	dt_fixup_clock("/plb/opb/serial@ef600300", freqUART);
-	dt_fixup_clock("/plb/opb/serial@ef600400", freqUART);
-}
-
-static void acadia_fixups(void)
-{
-	dt_fixup_memory(bd.bi_memstart, bd.bi_memsize);
-	get_clocks();
-	dt_fixup_mac_address_by_alias("ethernet0", bd.bi_enetaddr);
-}
-	
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
-		unsigned long r6, unsigned long r7)
-{
-	CUBOOT_INIT();
-	platform_ops.fixups = acadia_fixups;
-	platform_ops.exit = ibm40x_dbcr_reset;
-	fdt_init(_dtb_start);
-	serial_console_init();
-}
diff --git a/arch/powerpc/boot/cuboot-hotfoot.c b/arch/powerpc/boot/cuboot-hotfoot.c
deleted file mode 100644
index 0e5532f855d6..000000000000
--- a/arch/powerpc/boot/cuboot-hotfoot.c
+++ /dev/null
@@ -1,139 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Old U-boot compatibility for Esteem 195E Hotfoot CPU Board
- *
- * Author: Solomon Peachy <solomon@linux-wlan.com>
- */
-
-#include "ops.h"
-#include "stdio.h"
-#include "reg.h"
-#include "dcr.h"
-#include "4xx.h"
-#include "cuboot.h"
-
-#define TARGET_4xx
-#define TARGET_HOTFOOT
-
-#include "ppcboot-hotfoot.h"
-
-static bd_t bd;
-
-#define NUM_REGS 3
-
-static void hotfoot_fixups(void)
-{
-	u32 uart = mfdcr(DCRN_CPC0_UCR) & 0x7f;
-
-	dt_fixup_memory(bd.bi_memstart, bd.bi_memsize); 
-
-	dt_fixup_cpu_clocks(bd.bi_procfreq, bd.bi_procfreq, 0);
-	dt_fixup_clock("/plb", bd.bi_plb_busfreq);
-	dt_fixup_clock("/plb/opb", bd.bi_opbfreq);
-	dt_fixup_clock("/plb/ebc", bd.bi_pci_busfreq);
-	dt_fixup_clock("/plb/opb/serial@ef600300", bd.bi_procfreq / uart); 
-	dt_fixup_clock("/plb/opb/serial@ef600400", bd.bi_procfreq / uart); 
-	
-	dt_fixup_mac_address_by_alias("ethernet0", bd.bi_enetaddr);
-	dt_fixup_mac_address_by_alias("ethernet1", bd.bi_enet1addr);
-
-	/* Is this a single eth/serial board? */
-	if ((bd.bi_enet1addr[0] == 0) && 
-	    (bd.bi_enet1addr[1] == 0) &&
-	    (bd.bi_enet1addr[2] == 0) &&
-	    (bd.bi_enet1addr[3] == 0) &&
-	    (bd.bi_enet1addr[4] == 0) &&
-	    (bd.bi_enet1addr[5] == 0)) {
-		void *devp;
-
-		printf("Trimming devtree for single serial/eth board\n");
-
-		devp = finddevice("/plb/opb/serial@ef600300");
-		if (!devp)
-			fatal("Can't find node for /plb/opb/serial@ef600300");
-		del_node(devp);
-
-		devp = finddevice("/plb/opb/ethernet@ef600900");
-		if (!devp)
-			fatal("Can't find node for /plb/opb/ethernet@ef600900");
-		del_node(devp);
-	}
-
-	ibm4xx_quiesce_eth((u32 *)0xef600800, (u32 *)0xef600900);
-
-	/* Fix up flash size in fdt for 4M boards. */
-	if (bd.bi_flashsize < 0x800000) {
-		u32 regs[NUM_REGS];
-		void *devp = finddevice("/plb/ebc/nor_flash@0");
-		if (!devp)
-			fatal("Can't find FDT node for nor_flash!??");
-
-		printf("Fixing devtree for 4M Flash\n");
-		
-		/* First fix up the base address */
-		getprop(devp, "reg", regs, sizeof(regs));
-		regs[0] = 0;
-		regs[1] = 0xffc00000;
-		regs[2] = 0x00400000;
-		setprop(devp, "reg", regs, sizeof(regs));
-		
-		/* Then the offsets */
-		devp = finddevice("/plb/ebc/nor_flash@0/partition@0");
-		if (!devp)
-			fatal("Can't find FDT node for partition@0");
-		getprop(devp, "reg", regs, 2*sizeof(u32));
-		regs[0] -= 0x400000;
-		setprop(devp, "reg", regs,  2*sizeof(u32));
-
-		devp = finddevice("/plb/ebc/nor_flash@0/partition@1");
-		if (!devp)
-			fatal("Can't find FDT node for partition@1");
-		getprop(devp, "reg", regs, 2*sizeof(u32));
-		regs[0] -= 0x400000;
-		setprop(devp, "reg", regs,  2*sizeof(u32));
-
-		devp = finddevice("/plb/ebc/nor_flash@0/partition@2");
-		if (!devp)
-			fatal("Can't find FDT node for partition@2");
-		getprop(devp, "reg", regs, 2*sizeof(u32));
-		regs[0] -= 0x400000;
-		setprop(devp, "reg", regs,  2*sizeof(u32));
-
-		devp = finddevice("/plb/ebc/nor_flash@0/partition@3");
-		if (!devp)
-			fatal("Can't find FDT node for partition@3");
-		getprop(devp, "reg", regs, 2*sizeof(u32));
-		regs[0] -= 0x400000;
-		setprop(devp, "reg", regs,  2*sizeof(u32));
-
-		devp = finddevice("/plb/ebc/nor_flash@0/partition@4");
-		if (!devp)
-			fatal("Can't find FDT node for partition@4");
-		getprop(devp, "reg", regs, 2*sizeof(u32));
-		regs[0] -= 0x400000;
-		setprop(devp, "reg", regs,  2*sizeof(u32));
-
-		devp = finddevice("/plb/ebc/nor_flash@0/partition@6");
-		if (!devp)
-			fatal("Can't find FDT node for partition@6");
-		getprop(devp, "reg", regs, 2*sizeof(u32));
-		regs[0] -= 0x400000;
-		setprop(devp, "reg", regs,  2*sizeof(u32));
-
-		/* Delete the FeatFS node */
-		devp = finddevice("/plb/ebc/nor_flash@0/partition@5");
-		if (!devp)
-			fatal("Can't find FDT node for partition@5");
-		del_node(devp);
-	}
-}
-
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
-		   unsigned long r6, unsigned long r7)
-{
-	CUBOOT_INIT();
-	platform_ops.fixups = hotfoot_fixups;
-        platform_ops.exit = ibm40x_dbcr_reset;
-	fdt_init(_dtb_start);
-	serial_console_init();
-}
diff --git a/arch/powerpc/boot/cuboot-kilauea.c b/arch/powerpc/boot/cuboot-kilauea.c
deleted file mode 100644
index fda182f518a2..000000000000
--- a/arch/powerpc/boot/cuboot-kilauea.c
+++ /dev/null
@@ -1,46 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Old U-boot compatibility for PPC405EX. This image is already included
- * a dtb.
- *
- * Author: Tiejun Chen <tiejun.chen@windriver.com>
- *
- * Copyright (C) 2009 Wind River Systems, Inc.
- */
-
-#include "ops.h"
-#include "io.h"
-#include "dcr.h"
-#include "stdio.h"
-#include "4xx.h"
-#include "44x.h"
-#include "cuboot.h"
-
-#define TARGET_4xx
-#define TARGET_44x
-#include "ppcboot.h"
-
-#define KILAUEA_SYS_EXT_SERIAL_CLOCK     11059200        /* ext. 11.059MHz clk */
-
-static bd_t bd;
-
-static void kilauea_fixups(void)
-{
-	unsigned long sysclk = 33333333;
-
-	ibm405ex_fixup_clocks(sysclk, KILAUEA_SYS_EXT_SERIAL_CLOCK);
-	dt_fixup_memory(bd.bi_memstart, bd.bi_memsize);
-	ibm4xx_fixup_ebc_ranges("/plb/opb/ebc");
-	dt_fixup_mac_address_by_alias("ethernet0", bd.bi_enetaddr);
-	dt_fixup_mac_address_by_alias("ethernet1", bd.bi_enet1addr);
-}
-
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
-		unsigned long r6, unsigned long r7)
-{
-	CUBOOT_INIT();
-	platform_ops.fixups = kilauea_fixups;
-	platform_ops.exit = ibm40x_dbcr_reset;
-	fdt_init(_dtb_start);
-	serial_console_init();
-}
diff --git a/arch/powerpc/boot/dcr.h b/arch/powerpc/boot/dcr.h
index 334ab8b5a668..91dc3a302cc8 100644
--- a/arch/powerpc/boot/dcr.h
+++ b/arch/powerpc/boot/dcr.h
@@ -153,17 +153,6 @@ static const unsigned long sdram_bxcr[] = { SDRAM0_B0CR, SDRAM0_B1CR,
 #define CPR0_SCPID	0x120
 #define CPR0_PLLC0	0x40
 
-/* 405GP Clocking/Power Management/Chip Control regs */
-#define DCRN_CPC0_PLLMR 0xb0
-#define DCRN_405_CPC0_CR0 0xb1
-#define DCRN_405_CPC0_CR1 0xb2
-#define DCRN_405_CPC0_PSR 0xb4
-
-/* 405EP Clocking/Power Management/Chip Control regs */
-#define DCRN_CPC0_PLLMR0  0xf0
-#define DCRN_CPC0_PLLMR1  0xf4
-#define DCRN_CPC0_UCR     0xf5
-
 /* 440GX/405EX Clock Control reg */
 #define DCRN_CPR0_CLKUPD				0x020
 #define DCRN_CPR0_PLLC					0x040
diff --git a/arch/powerpc/boot/decompress.c b/arch/powerpc/boot/decompress.c
index 977eb15a6d17..6835cb53f034 100644
--- a/arch/powerpc/boot/decompress.c
+++ b/arch/powerpc/boot/decompress.c
@@ -101,7 +101,7 @@ static void print_err(char *s)
  * @input_size:  length of the input buffer
  * @outbuf:      output buffer
  * @output_size: length of the output buffer
- * @skip         number of output bytes to ignore
+ * @_skip:       number of output bytes to ignore
  *
  * This function takes compressed data from inbuf, decompresses and write it to
  * outbuf. Once output_size bytes are written to the output buffer, or the
diff --git a/arch/powerpc/boot/dts/Makefile b/arch/powerpc/boot/dts/Makefile
index fb335d05aae8..0cd0d8558b47 100644
--- a/arch/powerpc/boot/dts/Makefile
+++ b/arch/powerpc/boot/dts/Makefile
@@ -2,5 +2,4 @@
 
 subdir-y += fsl
 
-dtstree		:= $(srctree)/$(src)
-dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
+dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
diff --git a/arch/powerpc/boot/dts/acadia.dts b/arch/powerpc/boot/dts/acadia.dts
deleted file mode 100644
index deb52e41ab84..000000000000
--- a/arch/powerpc/boot/dts/acadia.dts
+++ /dev/null
@@ -1,224 +0,0 @@
-/*
- * Device Tree Source for AMCC Acadia (405EZ)
- *
- * Copyright IBM Corp. 2008
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	model = "amcc,acadia";
-	compatible = "amcc,acadia";
-	dcr-parent = <&{/cpus/cpu@0}>;
-
-	aliases {
-		ethernet0 = &EMAC0;
-		serial0 = &UART0;
-		serial1 = &UART1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu@0 {
-			device_type = "cpu";
-			model = "PowerPC,405EZ";
-			reg = <0x0>;
-			clock-frequency = <0>; /* Filled in by wrapper */
-			timebase-frequency = <0>; /* Filled in by wrapper */
-			i-cache-line-size = <32>;
-			d-cache-line-size = <32>;
-			i-cache-size = <16384>;
-			d-cache-size = <16384>;
-			dcr-controller;
-			dcr-access-method = "native";
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x0 0x0>; /* Filled in by wrapper */
-	};
-
-	UIC0: interrupt-controller {
-		compatible = "ibm,uic-405ez", "ibm,uic";
-		interrupt-controller;
-		dcr-reg = <0x0c0 0x009>;
-		cell-index = <0>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-	};
-
-	plb {
-		compatible = "ibm,plb-405ez", "ibm,plb3";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-		clock-frequency = <0>; /* Filled in by wrapper */
-
-		MAL0: mcmal {
-			compatible = "ibm,mcmal-405ez", "ibm,mcmal";
-			dcr-reg = <0x380 0x62>;
-			num-tx-chans = <1>;
-			num-rx-chans = <1>;
-			interrupt-parent = <&UIC0>;
-			/* 405EZ has only 3 interrupts to the UIC, as
-			 * SERR, TXDE, and RXDE are or'd together into
-			 * one UIC bit
-			 */
-			interrupts = <
-				0x13 0x4 /* TXEOB */
-				0x15 0x4 /* RXEOB */
-				0x12 0x4 /* SERR, TXDE, RXDE */>;
-		};
-
-		POB0: opb {
-			compatible = "ibm,opb-405ez", "ibm,opb";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges;
-			dcr-reg = <0x0a 0x05>;
-			clock-frequency = <0>; /* Filled in by wrapper */
-
-			UART0: serial@ef600300 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600300 0x8>;
-				virtual-reg = <0xef600300>;
-				clock-frequency = <0>; /* Filled in by wrapper */
-				current-speed = <115200>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x5 0x4>;
-			};
-
-			UART1: serial@ef600400 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600400 0x8>;
-				clock-frequency = <0>; /* Filled in by wrapper */
-				current-speed = <115200>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x6 0x4>;
-			};
-
-			IIC: i2c@ef600500 {
-				compatible = "ibm,iic-405ez", "ibm,iic";
-				reg = <0xef600500 0x11>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0xa 0x4>;
-			};
-
-			GPIO0: gpio@ef600700 {
-				compatible = "ibm,gpio-405ez";
-				reg = <0xef600700 0x20>;
-			};
-
-			GPIO1: gpio@ef600800 {
-				compatible = "ibm,gpio-405ez";
-				reg = <0xef600800 0x20>;
-			};
-
-			EMAC0: ethernet@ef600900 {
-				device_type = "network";
-				compatible = "ibm,emac-405ez", "ibm,emac";
-				interrupt-parent = <&UIC0>;
-				interrupts = <
-					0x10 0x4 /* Ethernet */
-					0x11 0x4 /* Ethernet Wake up */>;
-				local-mac-address = [000000000000]; /* Filled in by wrapper */
-				reg = <0xef600900 0x70>;
-				mal-device = <&MAL0>;
-				mal-tx-channel = <0>;
-				mal-rx-channel = <0>;
-				cell-index = <0>;
-				max-frame-size = <1500>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-				phy-mode = "mii";
-				phy-map = <0x0>;
-			};
-
-			CAN0: can@ef601000 {
-				compatible = "amcc,can-405ez";
-				reg = <0xef601000 0x620>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x7 0x4>;
-			};
-
-			CAN1: can@ef601800 {
-				compatible = "amcc,can-405ez";
-				reg = <0xef601800 0x620>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x8 0x4>;
-			};
-
-			cameleon@ef602000 {
-				compatible = "amcc,cameleon-405ez";
-				reg = <0xef602000 0x800>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0xb 0x4 0xc 0x4>;
-			};
-
-			ieee1588@ef602800 {
-				compatible = "amcc,ieee1588-405ez";
-				reg = <0xef602800 0x60>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x4 0x4>;
-				/* This thing is a bit weird.  It has it's own UIC
-				 * that it uses to generate snapshot triggers.  We
-				 * don't really support this device yet, and it needs
-				 * work to figure this out.
-				 */
-				dcr-reg = <0xe0 0x9>;
-			};
-
-			usb@ef603000 {
-				compatible = "ohci-be";
-				reg = <0xef603000 0x80>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0xd 0x4 0xe 0x4>;
-			};
-
-			dac@ef603300 {
-				compatible = "amcc,dac-405ez";
-				reg = <0xef603300 0x40>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x18 0x4>;
-			};
-
-			adc@ef603400 {
-				compatible = "amcc,adc-405ez";
-				reg = <0xef603400 0x40>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x17 0x4>;
-			};
-
-			spi@ef603500 {
-				compatible = "amcc,spi-405ez";
-				reg = <0xef603500 0x100>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x9 0x4>;
-			};
-		};
-
-		EBC0: ebc {
-			compatible = "ibm,ebc-405ez", "ibm,ebc";
-			dcr-reg = <0x12 0x2>;
-			#address-cells = <2>;
-			#size-cells = <1>;
-			clock-frequency = <0>; /* Filled in by wrapper */
-		};
-	};
-
-	chosen {
-		stdout-path = "/plb/opb/serial@ef600300";
-	};
-};
diff --git a/arch/powerpc/boot/dts/akebono.dts b/arch/powerpc/boot/dts/akebono.dts
index df18f8dc4642..343326c30380 100644
--- a/arch/powerpc/boot/dts/akebono.dts
+++ b/arch/powerpc/boot/dts/akebono.dts
@@ -126,7 +126,7 @@
 			interrupts = <93 2>;
 		};
 
-		EHCI0: ehci@30010000000 {
+		EHCI0: usb@30010000000 {
 			compatible = "ibm,476gtr-ehci", "generic-ehci";
 			reg = <0x300 0x10000000 0x0 0x10000>;
 			interrupt-parent = <&MPIC>;
@@ -140,14 +140,14 @@
 			interrupt-parent = <&MPIC>;
 		};
 
-		OHCI0: ohci@30010010000 {
+		OHCI0: usb@30010010000 {
 			compatible = "ibm,476gtr-ohci", "generic-ohci";
 			reg = <0x300 0x10010000 0x0 0x10000>;
 			interrupt-parent = <&MPIC>;
 			interrupts = <89 1>;
 			};
 
-		OHCI1: ohci@30010020000 {
+		OHCI1: usb@30010020000 {
 			compatible = "ibm,476gtr-ohci", "generic-ohci";
 			reg = <0x300 0x10020000 0x0 0x10000>;
 			interrupt-parent = <&MPIC>;
diff --git a/arch/powerpc/boot/dts/asp834x-redboot.dts b/arch/powerpc/boot/dts/asp834x-redboot.dts
index 52a84561c4f0..33ddb17d1876 100644
--- a/arch/powerpc/boot/dts/asp834x-redboot.dts
+++ b/arch/powerpc/boot/dts/asp834x-redboot.dts
@@ -72,7 +72,7 @@
 		reg = <0xff000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/fsl/Makefile b/arch/powerpc/boot/dts/fsl/Makefile
index 3bae982641e9..d3ecdf14bc42 100644
--- a/arch/powerpc/boot/dts/fsl/Makefile
+++ b/arch/powerpc/boot/dts/fsl/Makefile
@@ -1,4 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 
-dtstree		:= $(srctree)/$(src)
-dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
+dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
index 4f044b41a776..fb3200b006ad 100644
--- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
@@ -50,7 +50,7 @@
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
-	compatible = "fsl,ifc", "simple-bus";
+	compatible = "fsl,ifc";
 	interrupts = <25 2 0 0>;
 };
 
diff --git a/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts b/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts
index 8da984251abc..0ba86a6dce1b 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts
@@ -15,7 +15,7 @@
 		device_type = "memory";
 	};
 
-	board_ifc: ifc: ifc@ff71e000 {
+	board_ifc: ifc: memory-controller@ff71e000 {
 		/* NAND Flash on board */
 		ranges = <0x0 0x0 0x0 0xff800000 0x00004000>;
 		reg = <0x0 0xff71e000 0x0 0x2000>;
diff --git a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
index 2a677fd323eb..5c53cee8755f 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
@@ -35,7 +35,7 @@
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
-	compatible = "fsl,ifc", "simple-bus";
+	compatible = "fsl,ifc";
 	interrupts = <16 2 0 0 20 2 0 0>;
 };
 
diff --git a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts
index 7cb2158dfe58..ce642e879a1b 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts
+++ b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts
@@ -15,7 +15,7 @@
 		device_type = "memory";
 	};
 
-	ifc: ifc@ff71e000 {
+	ifc: memory-controller@ff71e000 {
 		/* NOR, NAND Flash on board */
 		ranges = <0x0 0x0 0x0 0x88000000 0x08000000
 			  0x1 0x0 0x0 0xff800000 0x00010000>;
diff --git a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi
index b8e0edd1ac69..4da451e000d9 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi
@@ -35,7 +35,7 @@
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
-	compatible = "fsl,ifc", "simple-bus";
+	compatible = "fsl,ifc";
 	/* FIXME: Test whether interrupts are split */
 	interrupts = <16 2 0 0 20 2 0 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/c293pcie.dts b/arch/powerpc/boot/dts/fsl/c293pcie.dts
index 5e905e0857cf..e2fdac2ed420 100644
--- a/arch/powerpc/boot/dts/fsl/c293pcie.dts
+++ b/arch/powerpc/boot/dts/fsl/c293pcie.dts
@@ -42,7 +42,7 @@
 		device_type = "memory";
 	};
 
-	ifc: ifc@fffe1e000 {
+	ifc: memory-controller@fffe1e000 {
 		reg = <0xf 0xffe1e000 0 0x2000>;
 		ranges = <0x0 0x0 0xf 0xec000000 0x04000000
 			  0x1 0x0 0xf 0xff800000 0x00010000
diff --git a/arch/powerpc/boot/dts/fsl/c293si-post.dtsi b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi
index bec0fc36849d..2d443d519274 100644
--- a/arch/powerpc/boot/dts/fsl/c293si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi
@@ -35,7 +35,7 @@
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
-	compatible = "fsl,ifc", "simple-bus";
+	compatible = "fsl,ifc";
 	interrupts = <19 2 0 0>;
 };
 
@@ -124,10 +124,10 @@
 		reg = <0x80000 0x20000>;
 		ranges = <0x0 0x80000 0x20000>;
 
-		jr@1000{
+		jr@1000 {
 			interrupts = <45 2 0 0>;
 		};
-		jr@2000{
+		jr@2000 {
 			interrupts = <57 2 0 0>;
 		};
 	};
@@ -140,10 +140,10 @@
 		reg = <0xa0000 0x20000>;
 		ranges = <0x0 0xa0000 0x20000>;
 
-		jr@1000{
+		jr@1000 {
 			interrupts = <49 2 0 0>;
 		};
-		jr@2000{
+		jr@2000 {
 			interrupts = <50 2 0 0>;
 		};
 	};
@@ -156,10 +156,10 @@
 		reg = <0xc0000 0x20000>;
 		ranges = <0x0 0xc0000 0x20000>;
 
-		jr@1000{
+		jr@1000 {
 			interrupts = <55 2 0 0>;
 		};
-		jr@2000{
+		jr@2000 {
 			interrupts = <56 2 0 0>;
 		};
 	};
diff --git a/arch/powerpc/boot/dts/fsl/ge_imp3a.dts b/arch/powerpc/boot/dts/fsl/ge_imp3a.dts
index da3de8e2b7d2..9e5c01cfac2f 100644
--- a/arch/powerpc/boot/dts/fsl/ge_imp3a.dts
+++ b/arch/powerpc/boot/dts/fsl/ge_imp3a.dts
@@ -94,7 +94,7 @@
 			gpio-controller;
 		};
 
-		wdt@4,800 {
+		watchdog@4,800 {
 			compatible = "ge,imp3a-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x800 0x8>;
@@ -103,7 +103,7 @@
 		};
 
 		/* Second watchdog available, driver currently supports one.
-		wdt@4,808 {
+		watchdog@4,808 {
 			compatible = "gef,imp3a-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x808 0x8>;
diff --git a/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts b/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts
index fc92bb032c51..48a81430a8a3 100644
--- a/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts
+++ b/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts
@@ -82,7 +82,7 @@
 			reg = <0x4 0x0 0x40>;
 		};
 
-		wdt@4,2000 {
+		watchdog@4,2000 {
 			compatible = "gef,ppc9a-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x2000 0x8>;
@@ -90,7 +90,7 @@
 			interrupt-parent = <&gef_pic>;
 		};
 		/* Second watchdog available, driver currently supports one.
-		wdt@4,2010 {
+		watchdog@4,2010 {
 			compatible = "gef,ppc9a-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x2010 0x8>;
diff --git a/arch/powerpc/boot/dts/fsl/gef_sbc310.dts b/arch/powerpc/boot/dts/fsl/gef_sbc310.dts
index 47ae85c34635..8eb254b1738d 100644
--- a/arch/powerpc/boot/dts/fsl/gef_sbc310.dts
+++ b/arch/powerpc/boot/dts/fsl/gef_sbc310.dts
@@ -79,7 +79,7 @@
 			reg = <0x4 0x0 0x40>;
 		};
 
-		wdt@4,2000 {
+		watchdog@4,2000 {
 			compatible = "gef,sbc310-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x2000 0x8>;
@@ -87,7 +87,7 @@
 			interrupt-parent = <&gef_pic>;
 		};
 /*
-		wdt@4,2010 {
+		watchdog@4,2010 {
 			compatible = "gef,sbc310-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x2010 0x8>;
diff --git a/arch/powerpc/boot/dts/fsl/gef_sbc610.dts b/arch/powerpc/boot/dts/fsl/gef_sbc610.dts
index 5322be44b62e..02edbb262b8f 100644
--- a/arch/powerpc/boot/dts/fsl/gef_sbc610.dts
+++ b/arch/powerpc/boot/dts/fsl/gef_sbc610.dts
@@ -82,14 +82,14 @@
 			reg = <0x4 0x0 0x40>;
 		};
 
-		wdt@4,2000 {
+		watchdog@4,2000 {
 			compatible = "gef,fpga-wdt";
 			reg = <0x4 0x2000 0x8>;
 			interrupts = <0x1a 0x4>;
 			interrupt-parent = <&gef_pic>;
 		};
 		/* Second watchdog available, driver currently supports one.
-		wdt@4,2010 {
+		watchdog@4,2010 {
 			compatible = "gef,fpga-wdt";
 			reg = <0x4 0x2010 0x8>;
 			interrupts = <0x1b 0x4>;
diff --git a/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi
index 41935709ebe8..fba40a1bccc0 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi
@@ -199,6 +199,10 @@
 
 /include/ "pq3-dma-0.dtsi"
 /include/ "pq3-etsec1-0.dtsi"
+	enet0: ethernet@24000 {
+		fsl,wake-on-filer;
+		fsl,pmc-handle = <&etsec1_clk>;
+	};
 /include/ "pq3-etsec1-timer-0.dtsi"
 
 	usb@22000 {
@@ -222,9 +226,10 @@
 	};
 
 /include/ "pq3-etsec1-2.dtsi"
-
-	ethernet@26000 {
+	enet2: ethernet@26000 {
 		cell-index = <1>;
+		fsl,wake-on-filer;
+		fsl,pmc-handle = <&etsec3_clk>;
 	};
 
 	usb@2b000 {
@@ -249,4 +254,9 @@
 		reg = <0xe0000 0x1000>;
 		fsl,has-rstcr;
 	};
+
+/include/ "pq3-power.dtsi"
+	power@e0070 {
+		compatible = "fsl,mpc8536-pmc", "fsl,mpc8548-pmc";
+	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/mpc8540ads.dts b/arch/powerpc/boot/dts/fsl/mpc8540ads.dts
deleted file mode 100644
index e03ae130162b..000000000000
--- a/arch/powerpc/boot/dts/fsl/mpc8540ads.dts
+++ /dev/null
@@ -1,355 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * MPC8540 ADS Device Tree Source
- *
- * Copyright 2006, 2008 Freescale Semiconductor Inc.
- */
-
-/dts-v1/;
-
-/include/ "e500v1_power_isa.dtsi"
-
-/ {
-	model = "MPC8540ADS";
-	compatible = "MPC8540ADS", "MPC85xxADS";
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	aliases {
-		ethernet0 = &enet0;
-		ethernet1 = &enet1;
-		ethernet2 = &enet2;
-		serial0 = &serial0;
-		serial1 = &serial1;
-		pci0 = &pci0;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		PowerPC,8540@0 {
-			device_type = "cpu";
-			reg = <0x0>;
-			d-cache-line-size = <32>;	// 32 bytes
-			i-cache-line-size = <32>;	// 32 bytes
-			d-cache-size = <0x8000>;		// L1, 32K
-			i-cache-size = <0x8000>;		// L1, 32K
-			timebase-frequency = <0>;	//  33 MHz, from uboot
-			bus-frequency = <0>;	// 166 MHz
-			clock-frequency = <0>;	// 825 MHz, from uboot
-			next-level-cache = <&L2>;
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x0 0x8000000>;	// 128M at 0x0
-	};
-
-	soc8540@e0000000 {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		device_type = "soc";
-		compatible = "simple-bus";
-		ranges = <0x0 0xe0000000 0x100000>;
-		bus-frequency = <0>;
-
-		ecm-law@0 {
-			compatible = "fsl,ecm-law";
-			reg = <0x0 0x1000>;
-			fsl,num-laws = <8>;
-		};
-
-		ecm@1000 {
-			compatible = "fsl,mpc8540-ecm", "fsl,ecm";
-			reg = <0x1000 0x1000>;
-			interrupts = <17 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		memory-controller@2000 {
-			compatible = "fsl,mpc8540-memory-controller";
-			reg = <0x2000 0x1000>;
-			interrupt-parent = <&mpic>;
-			interrupts = <18 2>;
-		};
-
-		L2: l2-cache-controller@20000 {
-			compatible = "fsl,mpc8540-l2-cache-controller";
-			reg = <0x20000 0x1000>;
-			cache-line-size = <32>;	// 32 bytes
-			cache-size = <0x40000>;	// L2, 256K
-			interrupt-parent = <&mpic>;
-			interrupts = <16 2>;
-		};
-
-		i2c@3000 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <0>;
-			compatible = "fsl-i2c";
-			reg = <0x3000 0x100>;
-			interrupts = <43 2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
-		};
-
-		dma@21300 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8540-dma", "fsl,eloplus-dma";
-			reg = <0x21300 0x4>;
-			ranges = <0x0 0x21100 0x200>;
-			cell-index = <0>;
-			dma-channel@0 {
-				compatible = "fsl,mpc8540-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x0 0x80>;
-				cell-index = <0>;
-				interrupt-parent = <&mpic>;
-				interrupts = <20 2>;
-			};
-			dma-channel@80 {
-				compatible = "fsl,mpc8540-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x80 0x80>;
-				cell-index = <1>;
-				interrupt-parent = <&mpic>;
-				interrupts = <21 2>;
-			};
-			dma-channel@100 {
-				compatible = "fsl,mpc8540-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x100 0x80>;
-				cell-index = <2>;
-				interrupt-parent = <&mpic>;
-				interrupts = <22 2>;
-			};
-			dma-channel@180 {
-				compatible = "fsl,mpc8540-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x180 0x80>;
-				cell-index = <3>;
-				interrupt-parent = <&mpic>;
-				interrupts = <23 2>;
-			};
-		};
-
-		enet0: ethernet@24000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <0>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x24000 0x1000>;
-			ranges = <0x0 0x24000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <29 2 30 2 34 2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi0>;
-			phy-handle = <&phy0>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-mdio";
-				reg = <0x520 0x20>;
-
-				phy0: ethernet-phy@0 {
-					interrupt-parent = <&mpic>;
-					interrupts = <5 1>;
-					reg = <0x0>;
-				};
-				phy1: ethernet-phy@1 {
-					interrupt-parent = <&mpic>;
-					interrupts = <5 1>;
-					reg = <0x1>;
-				};
-				phy3: ethernet-phy@3 {
-					interrupt-parent = <&mpic>;
-					interrupts = <7 1>;
-					reg = <0x3>;
-				};
-				tbi0: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		enet1: ethernet@25000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <1>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x25000 0x1000>;
-			ranges = <0x0 0x25000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <35 2 36 2 40 2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi1>;
-			phy-handle = <&phy1>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-tbi";
-				reg = <0x520 0x20>;
-
-				tbi1: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		enet2: ethernet@26000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <2>;
-			device_type = "network";
-			model = "FEC";
-			compatible = "gianfar";
-			reg = <0x26000 0x1000>;
-			ranges = <0x0 0x26000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <41 2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi2>;
-			phy-handle = <&phy3>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-tbi";
-				reg = <0x520 0x20>;
-
-				tbi2: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		serial0: serial@4500 {
-			cell-index = <0>;
-			device_type = "serial";
-			compatible = "fsl,ns16550", "ns16550";
-			reg = <0x4500 0x100>; 	// reg base, size
-			clock-frequency = <0>; 	// should we fill in in uboot?
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		serial1: serial@4600 {
-			cell-index = <1>;
-			device_type = "serial";
-			compatible = "fsl,ns16550", "ns16550";
-			reg = <0x4600 0x100>;	// reg base, size
-			clock-frequency = <0>; 	// should we fill in in uboot?
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
-		};
-		mpic: pic@40000 {
-			interrupt-controller;
-			#address-cells = <0>;
-			#interrupt-cells = <2>;
-			reg = <0x40000 0x40000>;
-			compatible = "chrp,open-pic";
-			device_type = "open-pic";
-		};
-	};
-
-	pci0: pci@e0008000 {
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x02 */
-			0x1000 0x0 0x0 0x1 &mpic 0x1 0x1
-			0x1000 0x0 0x0 0x2 &mpic 0x2 0x1
-			0x1000 0x0 0x0 0x3 &mpic 0x3 0x1
-			0x1000 0x0 0x0 0x4 &mpic 0x4 0x1
-
-			/* IDSEL 0x03 */
-			0x1800 0x0 0x0 0x1 &mpic 0x4 0x1
-			0x1800 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x1800 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x1800 0x0 0x0 0x4 &mpic 0x3 0x1
-
-			/* IDSEL 0x04 */
-			0x2000 0x0 0x0 0x1 &mpic 0x3 0x1
-			0x2000 0x0 0x0 0x2 &mpic 0x4 0x1
-			0x2000 0x0 0x0 0x3 &mpic 0x1 0x1
-			0x2000 0x0 0x0 0x4 &mpic 0x2 0x1
-
-			/* IDSEL 0x05 */
-			0x2800 0x0 0x0 0x1 &mpic 0x2 0x1
-			0x2800 0x0 0x0 0x2 &mpic 0x3 0x1
-			0x2800 0x0 0x0 0x3 &mpic 0x4 0x1
-			0x2800 0x0 0x0 0x4 &mpic 0x1 0x1
-
-			/* IDSEL 0x0c */
-			0x6000 0x0 0x0 0x1 &mpic 0x1 0x1
-			0x6000 0x0 0x0 0x2 &mpic 0x2 0x1
-			0x6000 0x0 0x0 0x3 &mpic 0x3 0x1
-			0x6000 0x0 0x0 0x4 &mpic 0x4 0x1
-
-			/* IDSEL 0x0d */
-			0x6800 0x0 0x0 0x1 &mpic 0x4 0x1
-			0x6800 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x6800 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x6800 0x0 0x0 0x4 &mpic 0x3 0x1
-
-			/* IDSEL 0x0e */
-			0x7000 0x0 0x0 0x1 &mpic 0x3 0x1
-			0x7000 0x0 0x0 0x2 &mpic 0x4 0x1
-			0x7000 0x0 0x0 0x3 &mpic 0x1 0x1
-			0x7000 0x0 0x0 0x4 &mpic 0x2 0x1
-
-			/* IDSEL 0x0f */
-			0x7800 0x0 0x0 0x1 &mpic 0x2 0x1
-			0x7800 0x0 0x0 0x2 &mpic 0x3 0x1
-			0x7800 0x0 0x0 0x3 &mpic 0x4 0x1
-			0x7800 0x0 0x0 0x4 &mpic 0x1 0x1
-
-			/* IDSEL 0x12 */
-			0x9000 0x0 0x0 0x1 &mpic 0x1 0x1
-			0x9000 0x0 0x0 0x2 &mpic 0x2 0x1
-			0x9000 0x0 0x0 0x3 &mpic 0x3 0x1
-			0x9000 0x0 0x0 0x4 &mpic 0x4 0x1
-
-			/* IDSEL 0x13 */
-			0x9800 0x0 0x0 0x1 &mpic 0x4 0x1
-			0x9800 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x9800 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x9800 0x0 0x0 0x4 &mpic 0x3 0x1
-
-			/* IDSEL 0x14 */
-			0xa000 0x0 0x0 0x1 &mpic 0x3 0x1
-			0xa000 0x0 0x0 0x2 &mpic 0x4 0x1
-			0xa000 0x0 0x0 0x3 &mpic 0x1 0x1
-			0xa000 0x0 0x0 0x4 &mpic 0x2 0x1
-
-			/* IDSEL 0x15 */
-			0xa800 0x0 0x0 0x1 &mpic 0x2 0x1
-			0xa800 0x0 0x0 0x2 &mpic 0x3 0x1
-			0xa800 0x0 0x0 0x3 &mpic 0x4 0x1
-			0xa800 0x0 0x0 0x4 &mpic 0x1 0x1>;
-		interrupt-parent = <&mpic>;
-		interrupts = <24 2>;
-		bus-range = <0 0>;
-		ranges = <0x2000000 0x0 0x80000000 0x80000000 0x0 0x20000000
-			  0x1000000 0x0 0x0 0xe2000000 0x0 0x100000>;
-		clock-frequency = <66666666>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		reg = <0xe0008000 0x1000>;
-		compatible = "fsl,mpc8540-pcix", "fsl,mpc8540-pci";
-		device_type = "pci";
-	};
-};
diff --git a/arch/powerpc/boot/dts/fsl/mpc8541cds.dts b/arch/powerpc/boot/dts/fsl/mpc8541cds.dts
deleted file mode 100644
index a2a6c5cf852e..000000000000
--- a/arch/powerpc/boot/dts/fsl/mpc8541cds.dts
+++ /dev/null
@@ -1,375 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * MPC8541 CDS Device Tree Source
- *
- * Copyright 2006, 2008 Freescale Semiconductor Inc.
- */
-
-/dts-v1/;
-
-/include/ "e500v1_power_isa.dtsi"
-
-/ {
-	model = "MPC8541CDS";
-	compatible = "MPC8541CDS", "MPC85xxCDS";
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	aliases {
-		ethernet0 = &enet0;
-		ethernet1 = &enet1;
-		serial0 = &serial0;
-		serial1 = &serial1;
-		pci0 = &pci0;
-		pci1 = &pci1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		PowerPC,8541@0 {
-			device_type = "cpu";
-			reg = <0x0>;
-			d-cache-line-size = <32>;	// 32 bytes
-			i-cache-line-size = <32>;	// 32 bytes
-			d-cache-size = <0x8000>;		// L1, 32K
-			i-cache-size = <0x8000>;		// L1, 32K
-			timebase-frequency = <0>;	//  33 MHz, from uboot
-			bus-frequency = <0>;	// 166 MHz
-			clock-frequency = <0>;	// 825 MHz, from uboot
-			next-level-cache = <&L2>;
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x0 0x8000000>;	// 128M at 0x0
-	};
-
-	soc8541@e0000000 {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		device_type = "soc";
-		compatible = "simple-bus";
-		ranges = <0x0 0xe0000000 0x100000>;
-		bus-frequency = <0>;
-
-		ecm-law@0 {
-			compatible = "fsl,ecm-law";
-			reg = <0x0 0x1000>;
-			fsl,num-laws = <8>;
-		};
-
-		ecm@1000 {
-			compatible = "fsl,mpc8541-ecm", "fsl,ecm";
-			reg = <0x1000 0x1000>;
-			interrupts = <17 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		memory-controller@2000 {
-			compatible = "fsl,mpc8541-memory-controller";
-			reg = <0x2000 0x1000>;
-			interrupt-parent = <&mpic>;
-			interrupts = <18 2>;
-		};
-
-		L2: l2-cache-controller@20000 {
-			compatible = "fsl,mpc8541-l2-cache-controller";
-			reg = <0x20000 0x1000>;
-			cache-line-size = <32>;	// 32 bytes
-			cache-size = <0x40000>;	// L2, 256K
-			interrupt-parent = <&mpic>;
-			interrupts = <16 2>;
-		};
-
-		i2c@3000 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <0>;
-			compatible = "fsl-i2c";
-			reg = <0x3000 0x100>;
-			interrupts = <43 2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
-		};
-
-		dma@21300 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8541-dma", "fsl,eloplus-dma";
-			reg = <0x21300 0x4>;
-			ranges = <0x0 0x21100 0x200>;
-			cell-index = <0>;
-			dma-channel@0 {
-				compatible = "fsl,mpc8541-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x0 0x80>;
-				cell-index = <0>;
-				interrupt-parent = <&mpic>;
-				interrupts = <20 2>;
-			};
-			dma-channel@80 {
-				compatible = "fsl,mpc8541-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x80 0x80>;
-				cell-index = <1>;
-				interrupt-parent = <&mpic>;
-				interrupts = <21 2>;
-			};
-			dma-channel@100 {
-				compatible = "fsl,mpc8541-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x100 0x80>;
-				cell-index = <2>;
-				interrupt-parent = <&mpic>;
-				interrupts = <22 2>;
-			};
-			dma-channel@180 {
-				compatible = "fsl,mpc8541-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x180 0x80>;
-				cell-index = <3>;
-				interrupt-parent = <&mpic>;
-				interrupts = <23 2>;
-			};
-		};
-
-		enet0: ethernet@24000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <0>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x24000 0x1000>;
-			ranges = <0x0 0x24000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <29 2 30 2 34 2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi0>;
-			phy-handle = <&phy0>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-mdio";
-				reg = <0x520 0x20>;
-
-				phy0: ethernet-phy@0 {
-					interrupt-parent = <&mpic>;
-					interrupts = <5 1>;
-					reg = <0x0>;
-				};
-				phy1: ethernet-phy@1 {
-					interrupt-parent = <&mpic>;
-					interrupts = <5 1>;
-					reg = <0x1>;
-				};
-				tbi0: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		enet1: ethernet@25000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <1>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x25000 0x1000>;
-			ranges = <0x0 0x25000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <35 2 36 2 40 2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi1>;
-			phy-handle = <&phy1>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-tbi";
-				reg = <0x520 0x20>;
-
-				tbi1: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		serial0: serial@4500 {
-			cell-index = <0>;
-			device_type = "serial";
-			compatible = "fsl,ns16550", "ns16550";
-			reg = <0x4500 0x100>; 	// reg base, size
-			clock-frequency = <0>; 	// should we fill in in uboot?
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		serial1: serial@4600 {
-			cell-index = <1>;
-			device_type = "serial";
-			compatible = "fsl,ns16550", "ns16550";
-			reg = <0x4600 0x100>;	// reg base, size
-			clock-frequency = <0>; 	// should we fill in in uboot?
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		crypto@30000 {
-			compatible = "fsl,sec2.0";
-			reg = <0x30000 0x10000>;
-			interrupts = <45 2>;
-			interrupt-parent = <&mpic>;
-			fsl,num-channels = <4>;
-			fsl,channel-fifo-len = <24>;
-			fsl,exec-units-mask = <0x7e>;
-			fsl,descriptor-types-mask = <0x01010ebf>;
-		};
-
-		mpic: pic@40000 {
-			interrupt-controller;
-			#address-cells = <0>;
-			#interrupt-cells = <2>;
-			reg = <0x40000 0x40000>;
-			compatible = "chrp,open-pic";
-			device_type = "open-pic";
-		};
-
-		cpm@919c0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8541-cpm", "fsl,cpm2";
-			reg = <0x919c0 0x30>;
-			ranges;
-
-			muram@80000 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				ranges = <0x0 0x80000 0x10000>;
-
-				data@0 {
-					compatible = "fsl,cpm-muram-data";
-					reg = <0x0 0x2000 0x9000 0x1000>;
-				};
-			};
-
-			brg@919f0 {
-				compatible = "fsl,mpc8541-brg",
-				             "fsl,cpm2-brg",
-				             "fsl,cpm-brg";
-				reg = <0x919f0 0x10 0x915f0 0x10>;
-			};
-
-			cpmpic: pic@90c00 {
-				interrupt-controller;
-				#address-cells = <0>;
-				#interrupt-cells = <2>;
-				interrupts = <46 2>;
-				interrupt-parent = <&mpic>;
-				reg = <0x90c00 0x80>;
-				compatible = "fsl,mpc8541-cpm-pic", "fsl,cpm2-pic";
-			};
-		};
-	};
-
-	pci0: pci@e0008000 {
-		interrupt-map-mask = <0x1f800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x10 */
-			0x8000 0x0 0x0 0x1 &mpic 0x0 0x1
-			0x8000 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x8000 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x8000 0x0 0x0 0x4 &mpic 0x3 0x1
-
-			/* IDSEL 0x11 */
-			0x8800 0x0 0x0 0x1 &mpic 0x0 0x1
-			0x8800 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x8800 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x8800 0x0 0x0 0x4 &mpic 0x3 0x1
-
-			/* IDSEL 0x12 (Slot 1) */
-			0x9000 0x0 0x0 0x1 &mpic 0x0 0x1
-			0x9000 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x9000 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x9000 0x0 0x0 0x4 &mpic 0x3 0x1
-
-			/* IDSEL 0x13 (Slot 2) */
-			0x9800 0x0 0x0 0x1 &mpic 0x1 0x1
-			0x9800 0x0 0x0 0x2 &mpic 0x2 0x1
-			0x9800 0x0 0x0 0x3 &mpic 0x3 0x1
-			0x9800 0x0 0x0 0x4 &mpic 0x0 0x1
-
-			/* IDSEL 0x14 (Slot 3) */
-			0xa000 0x0 0x0 0x1 &mpic 0x2 0x1
-			0xa000 0x0 0x0 0x2 &mpic 0x3 0x1
-			0xa000 0x0 0x0 0x3 &mpic 0x0 0x1
-			0xa000 0x0 0x0 0x4 &mpic 0x1 0x1
-
-			/* IDSEL 0x15 (Slot 4) */
-			0xa800 0x0 0x0 0x1 &mpic 0x3 0x1
-			0xa800 0x0 0x0 0x2 &mpic 0x0 0x1
-			0xa800 0x0 0x0 0x3 &mpic 0x1 0x1
-			0xa800 0x0 0x0 0x4 &mpic 0x2 0x1
-
-			/* Bus 1 (Tundra Bridge) */
-			/* IDSEL 0x12 (ISA bridge) */
-			0x19000 0x0 0x0 0x1 &mpic 0x0 0x1
-			0x19000 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x19000 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x19000 0x0 0x0 0x4 &mpic 0x3 0x1>;
-		interrupt-parent = <&mpic>;
-		interrupts = <24 2>;
-		bus-range = <0 0>;
-		ranges = <0x2000000 0x0 0x80000000 0x80000000 0x0 0x20000000
-			  0x1000000 0x0 0x0 0xe2000000 0x0 0x100000>;
-		clock-frequency = <66666666>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		reg = <0xe0008000 0x1000>;
-		compatible = "fsl,mpc8540-pci";
-		device_type = "pci";
-
-		i8259@19000 {
-			interrupt-controller;
-			device_type = "interrupt-controller";
-			reg = <0x19000 0x0 0x0 0x0 0x1>;
-			#address-cells = <0>;
-			#interrupt-cells = <2>;
-			compatible = "chrp,iic";
-			interrupts = <1>;
-			interrupt-parent = <&pci0>;
-		};
-	};
-
-	pci1: pci@e0009000 {
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x15 */
-			0xa800 0x0 0x0 0x1 &mpic 0xb 0x1
-			0xa800 0x0 0x0 0x2 &mpic 0xb 0x1
-			0xa800 0x0 0x0 0x3 &mpic 0xb 0x1
-			0xa800 0x0 0x0 0x4 &mpic 0xb 0x1>;
-		interrupt-parent = <&mpic>;
-		interrupts = <25 2>;
-		bus-range = <0 0>;
-		ranges = <0x2000000 0x0 0xa0000000 0xa0000000 0x0 0x20000000
-			  0x1000000 0x0 0x0 0xe3000000 0x0 0x100000>;
-		clock-frequency = <66666666>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		reg = <0xe0009000 0x1000>;
-		compatible = "fsl,mpc8540-pci";
-		device_type = "pci";
-	};
-};
diff --git a/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi
index b68eb119faef..ea7416af7ee3 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi
@@ -188,4 +188,6 @@
 		reg = <0xe0000 0x1000>;
 		fsl,has-rstcr;
 	};
+
+/include/ "pq3-power.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/mpc8548cds.dtsi b/arch/powerpc/boot/dts/fsl/mpc8548cds.dtsi
deleted file mode 100644
index 3bc7d4711220..000000000000
--- a/arch/powerpc/boot/dts/fsl/mpc8548cds.dtsi
+++ /dev/null
@@ -1,302 +0,0 @@
-/*
- * MPC8548CDS Device Tree Source stub (no addresses or top-level ranges)
- *
- * Copyright 2012 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-&board_lbc {
-	nor@0,0 {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		compatible = "cfi-flash";
-		reg = <0x0 0x0 0x01000000>;
-		bank-width = <2>;
-		device-width = <2>;
-
-		partition@0 {
-			reg = <0x0 0x0b00000>;
-			label = "ramdisk-nor";
-		};
-
-		partition@300000 {
-			reg = <0x0b00000 0x0400000>;
-			label = "kernel-nor";
-		};
-
-		partition@700000 {
-			reg = <0x0f00000 0x060000>;
-			label = "dtb-nor";
-		};
-
-		partition@760000 {
-			reg = <0x0f60000 0x020000>;
-			label = "env-nor";
-			read-only;
-		};
-
-		partition@780000 {
-			reg = <0x0f80000 0x080000>;
-			label = "u-boot-nor";
-			read-only;
-		};
-	};
-
-	board-control@1,0 {
-		compatible = "fsl,mpc8548cds-fpga";
-		reg = <0x1 0x0 0x1000>;
-	};
-};
-
-&board_soc {
-	i2c@3000 {
-		eeprom@50 {
-			compatible = "atmel,24c64";
-			reg = <0x50>;
-		};
-
-		eeprom@56 {
-			compatible = "atmel,24c64";
-			reg = <0x56>;
-		};
-
-		eeprom@57 {
-			compatible = "atmel,24c64";
-			reg = <0x57>;
-		};
-	};
-
-	i2c@3100 {
-		eeprom@50 {
-			compatible = "atmel,24c64";
-			reg = <0x50>;
-		};
-	};
-
-	enet0: ethernet@24000 {
-		tbi-handle = <&tbi0>;
-		phy-handle = <&phy0>;
-	};
-
-	mdio@24520 {
-		phy0: ethernet-phy@0 {
-			interrupts = <5 1 0 0>;
-			reg = <0x0>;
-		};
-		phy1: ethernet-phy@1 {
-			interrupts = <5 1 0 0>;
-			reg = <0x1>;
-		};
-		phy2: ethernet-phy@2 {
-			interrupts = <5 1 0 0>;
-			reg = <0x2>;
-		};
-		phy3: ethernet-phy@3 {
-			interrupts = <5 1 0 0>;
-			reg = <0x3>;
-		};
-		tbi0: tbi-phy@11 {
-			reg = <0x11>;
-			device_type = "tbi-phy";
-		};
-	};
-
-	enet1: ethernet@25000 {
-		tbi-handle = <&tbi1>;
-		phy-handle = <&phy1>;
-	};
-
-	mdio@25520 {
-		tbi1: tbi-phy@11 {
-			reg = <0x11>;
-			device_type = "tbi-phy";
-		};
-	};
-
-	enet2: ethernet@26000 {
-		tbi-handle = <&tbi2>;
-		phy-handle = <&phy2>;
-	};
-
-	mdio@26520 {
-		tbi2: tbi-phy@11 {
-			reg = <0x11>;
-			device_type = "tbi-phy";
-		};
-	};
-
-	enet3: ethernet@27000 {
-		tbi-handle = <&tbi3>;
-		phy-handle = <&phy3>;
-	};
-
-	mdio@27520 {
-		tbi3: tbi-phy@11 {
-			reg = <0x11>;
-			device_type = "tbi-phy";
-		};
-	};
-};
-
-&board_pci0 {
-	interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-	interrupt-map = <
-		/* IDSEL 0x4 (PCIX Slot 2) */
-		0x2000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-		0x2000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-		0x2000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-		0x2000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-		/* IDSEL 0x5 (PCIX Slot 3) */
-		0x2800 0x0 0x0 0x1 &mpic 0x1 0x1 0 0
-		0x2800 0x0 0x0 0x2 &mpic 0x2 0x1 0 0
-		0x2800 0x0 0x0 0x3 &mpic 0x3 0x1 0 0
-		0x2800 0x0 0x0 0x4 &mpic 0x0 0x1 0 0
-
-		/* IDSEL 0x6 (PCIX Slot 4) */
-		0x3000 0x0 0x0 0x1 &mpic 0x2 0x1 0 0
-		0x3000 0x0 0x0 0x2 &mpic 0x3 0x1 0 0
-		0x3000 0x0 0x0 0x3 &mpic 0x0 0x1 0 0
-		0x3000 0x0 0x0 0x4 &mpic 0x1 0x1 0 0
-
-		/* IDSEL 0x8 (PCIX Slot 5) */
-		0x4000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-		0x4000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-		0x4000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-		0x4000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-		/* IDSEL 0xC (Tsi310 bridge) */
-		0x6000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-		0x6000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-		0x6000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-		0x6000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-		/* IDSEL 0x14 (Slot 2) */
-		0xa000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-		0xa000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-		0xa000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-		0xa000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-		/* IDSEL 0x15 (Slot 3) */
-		0xa800 0x0 0x0 0x1 &mpic 0x1 0x1 0 0
-		0xa800 0x0 0x0 0x2 &mpic 0x2 0x1 0 0
-		0xa800 0x0 0x0 0x3 &mpic 0x3 0x1 0 0
-		0xa800 0x0 0x0 0x4 &mpic 0x0 0x1 0 0
-
-		/* IDSEL 0x16 (Slot 4) */
-		0xb000 0x0 0x0 0x1 &mpic 0x2 0x1 0 0
-		0xb000 0x0 0x0 0x2 &mpic 0x3 0x1 0 0
-		0xb000 0x0 0x0 0x3 &mpic 0x0 0x1 0 0
-		0xb000 0x0 0x0 0x4 &mpic 0x1 0x1 0 0
-
-		/* IDSEL 0x18 (Slot 5) */
-		0xc000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-		0xc000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-		0xc000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-		0xc000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-		/* IDSEL 0x1C (Tsi310 bridge PCI primary) */
-		0xe000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-		0xe000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-		0xe000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-		0xe000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0>;
-
-	pci_bridge@1c {
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x00 (PrPMC Site) */
-			0000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-			0000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-			0000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-			0000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-			/* IDSEL 0x04 (VIA chip) */
-			0x2000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-			0x2000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-			0x2000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-			0x2000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-			/* IDSEL 0x05 (8139) */
-			0x2800 0x0 0x0 0x1 &mpic 0x1 0x1 0 0
-
-			/* IDSEL 0x06 (Slot 6) */
-			0x3000 0x0 0x0 0x1 &mpic 0x2 0x1 0 0
-			0x3000 0x0 0x0 0x2 &mpic 0x3 0x1 0 0
-			0x3000 0x0 0x0 0x3 &mpic 0x0 0x1 0 0
-			0x3000 0x0 0x0 0x4 &mpic 0x1 0x1 0 0
-
-			/* IDESL 0x07 (Slot 7) */
-			0x3800 0x0 0x0 0x1 &mpic 0x3 0x1 0 0
-			0x3800 0x0 0x0 0x2 &mpic 0x0 0x1 0 0
-			0x3800 0x0 0x0 0x3 &mpic 0x1 0x1 0 0
-			0x3800 0x0 0x0 0x4 &mpic 0x2 0x1 0 0>;
-
-		reg = <0xe000 0x0 0x0 0x0 0x0>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		ranges = <0x2000000 0x0 0x80000000
-			  0x2000000 0x0 0x80000000
-			  0x0 0x20000000
-			  0x1000000 0x0 0x0
-			  0x1000000 0x0 0x0
-			  0x0 0x80000>;
-		clock-frequency = <33333333>;
-
-		isa@4 {
-			device_type = "isa";
-			#interrupt-cells = <2>;
-			#size-cells = <1>;
-			#address-cells = <2>;
-			reg = <0x2000 0x0 0x0 0x0 0x0>;
-			ranges = <0x1 0x0 0x1000000 0x0 0x0 0x1000>;
-			interrupt-parent = <&i8259>;
-
-			i8259: interrupt-controller@20 {
-				interrupt-controller;
-				device_type = "interrupt-controller";
-				reg = <0x1 0x20 0x2
-				       0x1 0xa0 0x2
-				       0x1 0x4d0 0x2>;
-				#address-cells = <0>;
-				#interrupt-cells = <2>;
-				compatible = "chrp,iic";
-				interrupts = <0 1 0 0>;
-				interrupt-parent = <&mpic>;
-			};
-
-			rtc@70 {
-				compatible = "pnpPNP,b00";
-				reg = <0x1 0x70 0x2>;
-			};
-		};
-	};
-};
diff --git a/arch/powerpc/boot/dts/fsl/mpc8548cds_32b.dts b/arch/powerpc/boot/dts/fsl/mpc8548cds_32b.dts
deleted file mode 100644
index f6ba4a982766..000000000000
--- a/arch/powerpc/boot/dts/fsl/mpc8548cds_32b.dts
+++ /dev/null
@@ -1,82 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * MPC8548 CDS Device Tree Source (32-bit address map)
- *
- * Copyright 2006, 2008, 2011-2012 Freescale Semiconductor Inc.
- */
-
-/include/ "mpc8548si-pre.dtsi"
-
-/ {
-	model = "MPC8548CDS";
-	compatible = "MPC8548CDS", "MPC85xxCDS";
-
-	memory {
-		device_type = "memory";
-		reg = <0 0 0x0 0x8000000>;	// 128M at 0x0
-	};
-
-	board_lbc: lbc: localbus@e0005000 {
-		reg = <0 0xe0005000 0 0x1000>;
-
-		ranges = <0x0 0x0 0x0 0xff000000 0x01000000
-			  0x1 0x0 0x0 0xf8004000 0x00001000>;
-
-	};
-
-	board_soc: soc: soc8548@e0000000 {
-		ranges = <0 0x0 0xe0000000 0x100000>;
-	};
-
-	board_pci0: pci0: pci@e0008000 {
-		reg = <0 0xe0008000 0 0x1000>;
-		ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x10000000
-			  0x1000000 0x0 0x00000000 0 0xe2000000 0x0 0x800000>;
-		clock-frequency = <66666666>;
-	};
-
-	pci1: pci@e0009000 {
-		reg = <0 0xe0009000 0 0x1000>;
-		ranges = <0x2000000 0x0 0x90000000 0 0x90000000 0x0 0x10000000
-			  0x1000000 0x0 0x00000000 0 0xe2800000 0x0 0x800000>;
-		clock-frequency = <66666666>;
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x15 */
-			0xa800 0x0 0x0 0x1 &mpic 0xb 0x1 0 0
-			0xa800 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-			0xa800 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-			0xa800 0x0 0x0 0x4 &mpic 0x3 0x1 0 0>;
-	};
-
-	pci2: pcie@e000a000 {
-		reg = <0 0xe000a000 0 0x1000>;
-		ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xe3000000 0x0 0x100000>;
-		pcie@0 {
-			ranges = <0x2000000 0x0 0xa0000000
-				  0x2000000 0x0 0xa0000000
-				  0x0 0x20000000
-
-				  0x1000000 0x0 0x0
-				  0x1000000 0x0 0x0
-				  0x0 0x100000>;
-		};
-	};
-
-	rio: rapidio@e00c0000 {
-		reg = <0x0 0xe00c0000 0x0 0x20000>;
-		port1 {
-			ranges = <0x0 0x0 0x0 0xc0000000 0x0 0x20000000>;
-		};
-	};
-};
-
-/*
- * mpc8548cds.dtsi must be last to ensure board_pci0 overrides pci0 settings
- * for interrupt-map & interrupt-map-mask.
- */
-
-/include/ "mpc8548si-post.dtsi"
-/include/ "mpc8548cds.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8548cds_36b.dts b/arch/powerpc/boot/dts/fsl/mpc8548cds_36b.dts
deleted file mode 100644
index 32e9076375ae..000000000000
--- a/arch/powerpc/boot/dts/fsl/mpc8548cds_36b.dts
+++ /dev/null
@@ -1,82 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * MPC8548 CDS Device Tree Source (36-bit address map)
- *
- * Copyright 2012 Freescale Semiconductor Inc.
- */
-
-/include/ "mpc8548si-pre.dtsi"
-
-/ {
-	model = "MPC8548CDS";
-	compatible = "MPC8548CDS", "MPC85xxCDS";
-
-	memory {
-		device_type = "memory";
-		reg = <0 0 0x0 0x8000000>;	// 128M at 0x0
-	};
-
-	board_lbc: lbc: localbus@fe0005000 {
-		reg = <0xf 0xe0005000 0 0x1000>;
-
-		ranges = <0x0 0x0 0xf 0xff000000 0x01000000
-			  0x1 0x0 0xf 0xf8004000 0x00001000>;
-
-	};
-
-	board_soc: soc: soc8548@fe0000000 {
-		ranges = <0 0xf 0xe0000000 0x100000>;
-	};
-
-	board_pci0: pci0: pci@fe0008000 {
-		reg = <0xf 0xe0008000 0 0x1000>;
-		ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x10000000
-			  0x1000000 0x0 0x00000000 0xf 0xe2000000 0x0 0x800000>;
-		clock-frequency = <66666666>;
-	};
-
-	pci1: pci@fe0009000 {
-		reg = <0xf 0xe0009000 0 0x1000>;
-		ranges = <0x2000000 0x0 0xe0000000 0xc 0x10000000 0x0 0x10000000
-			  0x1000000 0x0 0x00000000 0xf 0xe2800000 0x0 0x800000>;
-		clock-frequency = <66666666>;
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x15 */
-			0xa800 0x0 0x0 0x1 &mpic 0xb 0x1 0 0
-			0xa800 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-			0xa800 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-			0xa800 0x0 0x0 0x4 &mpic 0x3 0x1 0 0>;
-	};
-
-	pci2: pcie@fe000a000 {
-		reg = <0xf 0xe000a000 0 0x1000>;
-		ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0xf 0xe3000000 0x0 0x100000>;
-		pcie@0 {
-			ranges = <0x2000000 0x0 0xa0000000
-				  0x2000000 0x0 0xa0000000
-				  0x0 0x20000000
-
-				  0x1000000 0x0 0x0
-				  0x1000000 0x0 0x0
-				  0x0 0x100000>;
-		};
-	};
-
-	rio: rapidio@fe00c0000 {
-		reg = <0xf 0xe00c0000 0x0 0x20000>;
-		port1 {
-			ranges = <0x0 0x0 0xc 0x40000000 0x0 0x20000000>;
-		};
-	};
-};
-
-/*
- * mpc8548cds.dtsi must be last to ensure board_pci0 overrides pci0 settings
- * for interrupt-map & interrupt-map-mask.
- */
-
-/include/ "mpc8548si-post.dtsi"
-/include/ "mpc8548cds.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi
index 579d76cb8e32..dddb7374508d 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi
@@ -156,4 +156,6 @@
 		reg = <0xe0000 0x1000>;
 		fsl,has-rstcr;
 	};
+
+/include/ "pq3-power.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/mpc8555cds.dts b/arch/powerpc/boot/dts/fsl/mpc8555cds.dts
deleted file mode 100644
index 901b6ff06dfb..000000000000
--- a/arch/powerpc/boot/dts/fsl/mpc8555cds.dts
+++ /dev/null
@@ -1,375 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * MPC8555 CDS Device Tree Source
- *
- * Copyright 2006, 2008 Freescale Semiconductor Inc.
- */
-
-/dts-v1/;
-
-/include/ "e500v1_power_isa.dtsi"
-
-/ {
-	model = "MPC8555CDS";
-	compatible = "MPC8555CDS", "MPC85xxCDS";
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	aliases {
-		ethernet0 = &enet0;
-		ethernet1 = &enet1;
-		serial0 = &serial0;
-		serial1 = &serial1;
-		pci0 = &pci0;
-		pci1 = &pci1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		PowerPC,8555@0 {
-			device_type = "cpu";
-			reg = <0x0>;
-			d-cache-line-size = <32>;	// 32 bytes
-			i-cache-line-size = <32>;	// 32 bytes
-			d-cache-size = <0x8000>;		// L1, 32K
-			i-cache-size = <0x8000>;		// L1, 32K
-			timebase-frequency = <0>;	//  33 MHz, from uboot
-			bus-frequency = <0>;	// 166 MHz
-			clock-frequency = <0>;	// 825 MHz, from uboot
-			next-level-cache = <&L2>;
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x0 0x8000000>;	// 128M at 0x0
-	};
-
-	soc8555@e0000000 {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		device_type = "soc";
-		compatible = "simple-bus";
-		ranges = <0x0 0xe0000000 0x100000>;
-		bus-frequency = <0>;
-
-		ecm-law@0 {
-			compatible = "fsl,ecm-law";
-			reg = <0x0 0x1000>;
-			fsl,num-laws = <8>;
-		};
-
-		ecm@1000 {
-			compatible = "fsl,mpc8555-ecm", "fsl,ecm";
-			reg = <0x1000 0x1000>;
-			interrupts = <17 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		memory-controller@2000 {
-			compatible = "fsl,mpc8555-memory-controller";
-			reg = <0x2000 0x1000>;
-			interrupt-parent = <&mpic>;
-			interrupts = <18 2>;
-		};
-
-		L2: l2-cache-controller@20000 {
-			compatible = "fsl,mpc8555-l2-cache-controller";
-			reg = <0x20000 0x1000>;
-			cache-line-size = <32>;	// 32 bytes
-			cache-size = <0x40000>;	// L2, 256K
-			interrupt-parent = <&mpic>;
-			interrupts = <16 2>;
-		};
-
-		i2c@3000 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <0>;
-			compatible = "fsl-i2c";
-			reg = <0x3000 0x100>;
-			interrupts = <43 2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
-		};
-
-		dma@21300 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8555-dma", "fsl,eloplus-dma";
-			reg = <0x21300 0x4>;
-			ranges = <0x0 0x21100 0x200>;
-			cell-index = <0>;
-			dma-channel@0 {
-				compatible = "fsl,mpc8555-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x0 0x80>;
-				cell-index = <0>;
-				interrupt-parent = <&mpic>;
-				interrupts = <20 2>;
-			};
-			dma-channel@80 {
-				compatible = "fsl,mpc8555-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x80 0x80>;
-				cell-index = <1>;
-				interrupt-parent = <&mpic>;
-				interrupts = <21 2>;
-			};
-			dma-channel@100 {
-				compatible = "fsl,mpc8555-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x100 0x80>;
-				cell-index = <2>;
-				interrupt-parent = <&mpic>;
-				interrupts = <22 2>;
-			};
-			dma-channel@180 {
-				compatible = "fsl,mpc8555-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x180 0x80>;
-				cell-index = <3>;
-				interrupt-parent = <&mpic>;
-				interrupts = <23 2>;
-			};
-		};
-
-		enet0: ethernet@24000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <0>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x24000 0x1000>;
-			ranges = <0x0 0x24000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <29 2 30 2 34 2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi0>;
-			phy-handle = <&phy0>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-mdio";
-				reg = <0x520 0x20>;
-
-				phy0: ethernet-phy@0 {
-					interrupt-parent = <&mpic>;
-					interrupts = <5 1>;
-					reg = <0x0>;
-				};
-				phy1: ethernet-phy@1 {
-					interrupt-parent = <&mpic>;
-					interrupts = <5 1>;
-					reg = <0x1>;
-				};
-				tbi0: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		enet1: ethernet@25000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <1>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x25000 0x1000>;
-			ranges = <0x0 0x25000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <35 2 36 2 40 2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi1>;
-			phy-handle = <&phy1>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-tbi";
-				reg = <0x520 0x20>;
-
-				tbi1: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		serial0: serial@4500 {
-			cell-index = <0>;
-			device_type = "serial";
-			compatible = "fsl,ns16550", "ns16550";
-			reg = <0x4500 0x100>; 	// reg base, size
-			clock-frequency = <0>; 	// should we fill in in uboot?
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		serial1: serial@4600 {
-			cell-index = <1>;
-			device_type = "serial";
-			compatible = "fsl,ns16550", "ns16550";
-			reg = <0x4600 0x100>;	// reg base, size
-			clock-frequency = <0>; 	// should we fill in in uboot?
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		crypto@30000 {
-			compatible = "fsl,sec2.0";
-			reg = <0x30000 0x10000>;
-			interrupts = <45 2>;
-			interrupt-parent = <&mpic>;
-			fsl,num-channels = <4>;
-			fsl,channel-fifo-len = <24>;
-			fsl,exec-units-mask = <0x7e>;
-			fsl,descriptor-types-mask = <0x01010ebf>;
-		};
-
-		mpic: pic@40000 {
-			interrupt-controller;
-			#address-cells = <0>;
-			#interrupt-cells = <2>;
-			reg = <0x40000 0x40000>;
-			compatible = "chrp,open-pic";
-			device_type = "open-pic";
-		};
-
-		cpm@919c0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8555-cpm", "fsl,cpm2";
-			reg = <0x919c0 0x30>;
-			ranges;
-
-			muram@80000 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				ranges = <0x0 0x80000 0x10000>;
-
-				data@0 {
-					compatible = "fsl,cpm-muram-data";
-					reg = <0x0 0x2000 0x9000 0x1000>;
-				};
-			};
-
-			brg@919f0 {
-				compatible = "fsl,mpc8555-brg",
-				             "fsl,cpm2-brg",
-				             "fsl,cpm-brg";
-				reg = <0x919f0 0x10 0x915f0 0x10>;
-			};
-
-			cpmpic: pic@90c00 {
-				interrupt-controller;
-				#address-cells = <0>;
-				#interrupt-cells = <2>;
-				interrupts = <46 2>;
-				interrupt-parent = <&mpic>;
-				reg = <0x90c00 0x80>;
-				compatible = "fsl,mpc8555-cpm-pic", "fsl,cpm2-pic";
-			};
-		};
-	};
-
-	pci0: pci@e0008000 {
-		interrupt-map-mask = <0x1f800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x10 */
-			0x8000 0x0 0x0 0x1 &mpic 0x0 0x1
-			0x8000 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x8000 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x8000 0x0 0x0 0x4 &mpic 0x3 0x1
-
-			/* IDSEL 0x11 */
-			0x8800 0x0 0x0 0x1 &mpic 0x0 0x1
-			0x8800 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x8800 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x8800 0x0 0x0 0x4 &mpic 0x3 0x1
-
-			/* IDSEL 0x12 (Slot 1) */
-			0x9000 0x0 0x0 0x1 &mpic 0x0 0x1
-			0x9000 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x9000 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x9000 0x0 0x0 0x4 &mpic 0x3 0x1
-
-			/* IDSEL 0x13 (Slot 2) */
-			0x9800 0x0 0x0 0x1 &mpic 0x1 0x1
-			0x9800 0x0 0x0 0x2 &mpic 0x2 0x1
-			0x9800 0x0 0x0 0x3 &mpic 0x3 0x1
-			0x9800 0x0 0x0 0x4 &mpic 0x0 0x1
-
-			/* IDSEL 0x14 (Slot 3) */
-			0xa000 0x0 0x0 0x1 &mpic 0x2 0x1
-			0xa000 0x0 0x0 0x2 &mpic 0x3 0x1
-			0xa000 0x0 0x0 0x3 &mpic 0x0 0x1
-			0xa000 0x0 0x0 0x4 &mpic 0x1 0x1
-
-			/* IDSEL 0x15 (Slot 4) */
-			0xa800 0x0 0x0 0x1 &mpic 0x3 0x1
-			0xa800 0x0 0x0 0x2 &mpic 0x0 0x1
-			0xa800 0x0 0x0 0x3 &mpic 0x1 0x1
-			0xa800 0x0 0x0 0x4 &mpic 0x2 0x1
-
-			/* Bus 1 (Tundra Bridge) */
-			/* IDSEL 0x12 (ISA bridge) */
-			0x19000 0x0 0x0 0x1 &mpic 0x0 0x1
-			0x19000 0x0 0x0 0x2 &mpic 0x1 0x1
-			0x19000 0x0 0x0 0x3 &mpic 0x2 0x1
-			0x19000 0x0 0x0 0x4 &mpic 0x3 0x1>;
-		interrupt-parent = <&mpic>;
-		interrupts = <24 2>;
-		bus-range = <0 0>;
-		ranges = <0x2000000 0x0 0x80000000 0x80000000 0x0 0x20000000
-			  0x1000000 0x0 0x0 0xe2000000 0x0 0x100000>;
-		clock-frequency = <66666666>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		reg = <0xe0008000 0x1000>;
-		compatible = "fsl,mpc8540-pci";
-		device_type = "pci";
-
-		i8259@19000 {
-			interrupt-controller;
-			device_type = "interrupt-controller";
-			reg = <0x19000 0x0 0x0 0x0 0x1>;
-			#address-cells = <0>;
-			#interrupt-cells = <2>;
-			compatible = "chrp,iic";
-			interrupts = <1>;
-			interrupt-parent = <&pci0>;
-		};
-	};
-
-	pci1: pci@e0009000 {
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x15 */
-			0xa800 0x0 0x0 0x1 &mpic 0xb 0x1
-			0xa800 0x0 0x0 0x2 &mpic 0xb 0x1
-			0xa800 0x0 0x0 0x3 &mpic 0xb 0x1
-			0xa800 0x0 0x0 0x4 &mpic 0xb 0x1>;
-		interrupt-parent = <&mpic>;
-		interrupts = <25 2>;
-		bus-range = <0 0>;
-		ranges = <0x2000000 0x0 0xa0000000 0xa0000000 0x0 0x20000000
-			  0x1000000 0x0 0x0 0xe3000000 0x0 0x100000>;
-		clock-frequency = <66666666>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		reg = <0xe0009000 0x1000>;
-		compatible = "fsl,mpc8540-pci";
-		device_type = "pci";
-	};
-};
diff --git a/arch/powerpc/boot/dts/fsl/mpc8560ads.dts b/arch/powerpc/boot/dts/fsl/mpc8560ads.dts
deleted file mode 100644
index c2f9aea78b29..000000000000
--- a/arch/powerpc/boot/dts/fsl/mpc8560ads.dts
+++ /dev/null
@@ -1,388 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * MPC8560 ADS Device Tree Source
- *
- * Copyright 2006, 2008 Freescale Semiconductor Inc.
- */
-
-/dts-v1/;
-
-/include/ "e500v1_power_isa.dtsi"
-
-/ {
-	model = "MPC8560ADS";
-	compatible = "MPC8560ADS", "MPC85xxADS";
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	aliases {
-		ethernet0 = &enet0;
-		ethernet1 = &enet1;
-		ethernet2 = &enet2;
-		ethernet3 = &enet3;
-		serial0 = &serial0;
-		serial1 = &serial1;
-		pci0 = &pci0;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		PowerPC,8560@0 {
-			device_type = "cpu";
-			reg = <0x0>;
-			d-cache-line-size = <32>;	// 32 bytes
-			i-cache-line-size = <32>;	// 32 bytes
-			d-cache-size = <0x8000>;		// L1, 32K
-			i-cache-size = <0x8000>;		// L1, 32K
-			timebase-frequency = <82500000>;
-			bus-frequency = <330000000>;
-			clock-frequency = <825000000>;
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x0 0x10000000>;
-	};
-
-	soc8560@e0000000 {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		device_type = "soc";
-		compatible = "simple-bus";
-		ranges = <0x0 0xe0000000 0x100000>;
-		bus-frequency = <330000000>;
-
-		ecm-law@0 {
-			compatible = "fsl,ecm-law";
-			reg = <0x0 0x1000>;
-			fsl,num-laws = <8>;
-		};
-
-		ecm@1000 {
-			compatible = "fsl,mpc8560-ecm", "fsl,ecm";
-			reg = <0x1000 0x1000>;
-			interrupts = <17 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		memory-controller@2000 {
-			compatible = "fsl,mpc8540-memory-controller";
-			reg = <0x2000 0x1000>;
-			interrupt-parent = <&mpic>;
-			interrupts = <18 2>;
-		};
-
-		L2: l2-cache-controller@20000 {
-			compatible = "fsl,mpc8540-l2-cache-controller";
-			reg = <0x20000 0x1000>;
-			cache-line-size = <32>;	// 32 bytes
-			cache-size = <0x40000>;	// L2, 256K
-			interrupt-parent = <&mpic>;
-			interrupts = <16 2>;
-		};
-
-		dma@21300 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8560-dma", "fsl,eloplus-dma";
-			reg = <0x21300 0x4>;
-			ranges = <0x0 0x21100 0x200>;
-			cell-index = <0>;
-			dma-channel@0 {
-				compatible = "fsl,mpc8560-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x0 0x80>;
-				cell-index = <0>;
-				interrupt-parent = <&mpic>;
-				interrupts = <20 2>;
-			};
-			dma-channel@80 {
-				compatible = "fsl,mpc8560-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x80 0x80>;
-				cell-index = <1>;
-				interrupt-parent = <&mpic>;
-				interrupts = <21 2>;
-			};
-			dma-channel@100 {
-				compatible = "fsl,mpc8560-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x100 0x80>;
-				cell-index = <2>;
-				interrupt-parent = <&mpic>;
-				interrupts = <22 2>;
-			};
-			dma-channel@180 {
-				compatible = "fsl,mpc8560-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x180 0x80>;
-				cell-index = <3>;
-				interrupt-parent = <&mpic>;
-				interrupts = <23 2>;
-			};
-		};
-
-		enet0: ethernet@24000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <0>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x24000 0x1000>;
-			ranges = <0x0 0x24000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <29 2 30 2 34 2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi0>;
-			phy-handle = <&phy0>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-mdio";
-				reg = <0x520 0x20>;
-
-				phy0: ethernet-phy@0 {
-					interrupt-parent = <&mpic>;
-					interrupts = <5 1>;
-					reg = <0x0>;
-				};
-				phy1: ethernet-phy@1 {
-					interrupt-parent = <&mpic>;
-					interrupts = <5 1>;
-					reg = <0x1>;
-				};
-				phy2: ethernet-phy@2 {
-					interrupt-parent = <&mpic>;
-					interrupts = <7 1>;
-					reg = <0x2>;
-				};
-				phy3: ethernet-phy@3 {
-					interrupt-parent = <&mpic>;
-					interrupts = <7 1>;
-					reg = <0x3>;
-				};
-				tbi0: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		enet1: ethernet@25000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <1>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x25000 0x1000>;
-			ranges = <0x0 0x25000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <35 2 36 2 40 2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi1>;
-			phy-handle = <&phy1>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-tbi";
-				reg = <0x520 0x20>;
-
-				tbi1: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		mpic: pic@40000 {
-			interrupt-controller;
-			#address-cells = <0>;
-			#interrupt-cells = <2>;
-			reg = <0x40000 0x40000>;
-			compatible = "chrp,open-pic";
-			device_type = "open-pic";
-		};
-
-		cpm@919c0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8560-cpm", "fsl,cpm2";
-			reg = <0x919c0 0x30>;
-			ranges;
-
-			muram@80000 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				ranges = <0x0 0x80000 0x10000>;
-
-				data@0 {
-					compatible = "fsl,cpm-muram-data";
-					reg = <0x0 0x4000 0x9000 0x2000>;
-				};
-			};
-
-			brg@919f0 {
-				compatible = "fsl,mpc8560-brg",
-				             "fsl,cpm2-brg",
-				             "fsl,cpm-brg";
-				reg = <0x919f0 0x10 0x915f0 0x10>;
-				clock-frequency = <165000000>;
-			};
-
-			cpmpic: pic@90c00 {
-				interrupt-controller;
-				#address-cells = <0>;
-				#interrupt-cells = <2>;
-				interrupts = <46 2>;
-				interrupt-parent = <&mpic>;
-				reg = <0x90c00 0x80>;
-				compatible = "fsl,mpc8560-cpm-pic", "fsl,cpm2-pic";
-			};
-
-			serial0: serial@91a00 {
-				device_type = "serial";
-				compatible = "fsl,mpc8560-scc-uart",
-				             "fsl,cpm2-scc-uart";
-				reg = <0x91a00 0x20 0x88000 0x100>;
-				fsl,cpm-brg = <1>;
-				fsl,cpm-command = <0x800000>;
-				current-speed = <115200>;
-				interrupts = <40 8>;
-				interrupt-parent = <&cpmpic>;
-			};
-
-			serial1: serial@91a20 {
-				device_type = "serial";
-				compatible = "fsl,mpc8560-scc-uart",
-				             "fsl,cpm2-scc-uart";
-				reg = <0x91a20 0x20 0x88100 0x100>;
-				fsl,cpm-brg = <2>;
-				fsl,cpm-command = <0x4a00000>;
-				current-speed = <115200>;
-				interrupts = <41 8>;
-				interrupt-parent = <&cpmpic>;
-			};
-
-			enet2: ethernet@91320 {
-				device_type = "network";
-				compatible = "fsl,mpc8560-fcc-enet",
-				             "fsl,cpm2-fcc-enet";
-				reg = <0x91320 0x20 0x88500 0x100 0x913b0 0x1>;
-				local-mac-address = [ 00 00 00 00 00 00 ];
-				fsl,cpm-command = <0x16200300>;
-				interrupts = <33 8>;
-				interrupt-parent = <&cpmpic>;
-				phy-handle = <&phy2>;
-			};
-
-			enet3: ethernet@91340 {
-				device_type = "network";
-				compatible = "fsl,mpc8560-fcc-enet",
-				             "fsl,cpm2-fcc-enet";
-				reg = <0x91340 0x20 0x88600 0x100 0x913d0 0x1>;
-				local-mac-address = [ 00 00 00 00 00 00 ];
-				fsl,cpm-command = <0x1a400300>;
-				interrupts = <34 8>;
-				interrupt-parent = <&cpmpic>;
-				phy-handle = <&phy3>;
-			};
-		};
-	};
-
-	pci0: pci@e0008000 {
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		compatible = "fsl,mpc8540-pcix", "fsl,mpc8540-pci";
-		device_type = "pci";
-		reg = <0xe0008000 0x1000>;
-		clock-frequency = <66666666>;
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-				/* IDSEL 0x2 */
-				 0x1000 0x0 0x0 0x1 &mpic 0x1 0x1
-				 0x1000 0x0 0x0 0x2 &mpic 0x2 0x1
-				 0x1000 0x0 0x0 0x3 &mpic 0x3 0x1
-				 0x1000 0x0 0x0 0x4 &mpic 0x4 0x1
-
-				/* IDSEL 0x3 */
-				 0x1800 0x0 0x0 0x1 &mpic 0x4 0x1
-				 0x1800 0x0 0x0 0x2 &mpic 0x1 0x1
-				 0x1800 0x0 0x0 0x3 &mpic 0x2 0x1
-				 0x1800 0x0 0x0 0x4 &mpic 0x3 0x1
-
-				/* IDSEL 0x4 */
-				 0x2000 0x0 0x0 0x1 &mpic 0x3 0x1
-				 0x2000 0x0 0x0 0x2 &mpic 0x4 0x1
-				 0x2000 0x0 0x0 0x3 &mpic 0x1 0x1
-				 0x2000 0x0 0x0 0x4 &mpic 0x2 0x1
-
-				/* IDSEL 0x5  */
-				 0x2800 0x0 0x0 0x1 &mpic 0x2 0x1
-				 0x2800 0x0 0x0 0x2 &mpic 0x3 0x1
-				 0x2800 0x0 0x0 0x3 &mpic 0x4 0x1
-				 0x2800 0x0 0x0 0x4 &mpic 0x1 0x1
-
-				/* IDSEL 12 */
-				 0x6000 0x0 0x0 0x1 &mpic 0x1 0x1
-				 0x6000 0x0 0x0 0x2 &mpic 0x2 0x1
-				 0x6000 0x0 0x0 0x3 &mpic 0x3 0x1
-				 0x6000 0x0 0x0 0x4 &mpic 0x4 0x1
-
-				/* IDSEL 13 */
-				 0x6800 0x0 0x0 0x1 &mpic 0x4 0x1
-				 0x6800 0x0 0x0 0x2 &mpic 0x1 0x1
-				 0x6800 0x0 0x0 0x3 &mpic 0x2 0x1
-				 0x6800 0x0 0x0 0x4 &mpic 0x3 0x1
-
-				/* IDSEL 14*/
-				 0x7000 0x0 0x0 0x1 &mpic 0x3 0x1
-				 0x7000 0x0 0x0 0x2 &mpic 0x4 0x1
-				 0x7000 0x0 0x0 0x3 &mpic 0x1 0x1
-				 0x7000 0x0 0x0 0x4 &mpic 0x2 0x1
-
-				/* IDSEL 15 */
-				 0x7800 0x0 0x0 0x1 &mpic 0x2 0x1
-				 0x7800 0x0 0x0 0x2 &mpic 0x3 0x1
-				 0x7800 0x0 0x0 0x3 &mpic 0x4 0x1
-				 0x7800 0x0 0x0 0x4 &mpic 0x1 0x1
-
-				/* IDSEL 18 */
-				 0x9000 0x0 0x0 0x1 &mpic 0x1 0x1
-				 0x9000 0x0 0x0 0x2 &mpic 0x2 0x1
-				 0x9000 0x0 0x0 0x3 &mpic 0x3 0x1
-				 0x9000 0x0 0x0 0x4 &mpic 0x4 0x1
-
-				/* IDSEL 19 */
-				 0x9800 0x0 0x0 0x1 &mpic 0x4 0x1
-				 0x9800 0x0 0x0 0x2 &mpic 0x1 0x1
-				 0x9800 0x0 0x0 0x3 &mpic 0x2 0x1
-				 0x9800 0x0 0x0 0x4 &mpic 0x3 0x1
-
-				/* IDSEL 20 */
-				 0xa000 0x0 0x0 0x1 &mpic 0x3 0x1
-				 0xa000 0x0 0x0 0x2 &mpic 0x4 0x1
-				 0xa000 0x0 0x0 0x3 &mpic 0x1 0x1
-				 0xa000 0x0 0x0 0x4 &mpic 0x2 0x1
-
-				/* IDSEL 21 */
-				 0xa800 0x0 0x0 0x1 &mpic 0x2 0x1
-				 0xa800 0x0 0x0 0x2 &mpic 0x3 0x1
-				 0xa800 0x0 0x0 0x3 &mpic 0x4 0x1
-				 0xa800 0x0 0x0 0x4 &mpic 0x1 0x1>;
-
-		interrupt-parent = <&mpic>;
-		interrupts = <24 2>;
-		bus-range = <0 0>;
-		ranges = <0x2000000 0x0 0x80000000 0x80000000 0x0 0x20000000
-			  0x1000000 0x0 0x0 0xe2000000 0x0 0x1000000>;
-	};
-};
diff --git a/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi
index 49294cf36b4e..40a6cff77032 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi
@@ -193,4 +193,6 @@
 		reg = <0xe0000 0x1000>;
 		fsl,has-rstcr;
 	};
+
+/include/ "pq3-power.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts b/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts
index 3a94acbb3c03..ce3346d77858 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts
@@ -29,3 +29,19 @@
 };
 
 /include/ "p1010si-post.dtsi"
+
+&pci0 {
+	pcie@0 {
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			/*
+			 *irq[4:5] are active-high
+			 *irq[6:7] are active-low
+			 */
+			0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0
+			0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0
+			0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0
+			0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0
+			>;
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts b/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts
index 4cf255fedc96..83590354f9a0 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts
@@ -56,3 +56,19 @@
 };
 
 /include/ "p1010si-post.dtsi"
+
+&pci0 {
+	pcie@0 {
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			/*
+			 *irq[4:5] are active-high
+			 *irq[6:7] are active-low
+			 */
+			0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0
+			0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0
+			0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0
+			0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0
+			>;
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi
index 2ca9cee2ddeb..ef49a7d6c69d 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi
@@ -215,19 +215,3 @@
 		phy-connection-type = "sgmii";
 	};
 };
-
-&pci0 {
-	pcie@0 {
-		interrupt-map = <
-			/* IDSEL 0x0 */
-			/*
-			 *irq[4:5] are active-high
-			 *irq[6:7] are active-low
-			 */
-			0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0
-			0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0
-			0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0
-			0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0
-			>;
-	};
-};
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi
index fdc19aab2f70..583a6cd05079 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi
@@ -36,7 +36,7 @@ memory {
 	device_type = "memory";
 };
 
-board_ifc: ifc: ifc@ffe1e000 {
+board_ifc: ifc: memory-controller@ffe1e000 {
 	/* NOR, NAND Flashes and CPLD on board */
 	ranges = <0x0 0x0 0x0 0xee000000 0x02000000
 		  0x1 0x0 0x0 0xff800000 0x00010000
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi
index de2fceed4f79..4d41efe0038f 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi
@@ -36,7 +36,7 @@ memory {
 	device_type = "memory";
 };
 
-board_ifc: ifc: ifc@fffe1e000 {
+board_ifc: ifc: memory-controller@fffe1e000 {
 	/* NOR, NAND Flashes and CPLD on board */
 	ranges = <0x0 0x0 0xf 0xee000000 0x02000000
 		  0x1 0x0 0xf 0xff800000 0x00010000
diff --git a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
index ccda0a91abf0..2d2550729dcc 100644
--- a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
@@ -35,7 +35,7 @@
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
-	compatible = "fsl,ifc", "simple-bus";
+	compatible = "fsl,ifc";
 	interrupts = <16 2 0 0 19 2 0 0>;
 };
 
@@ -183,9 +183,23 @@
 /include/ "pq3-etsec2-1.dtsi"
 /include/ "pq3-etsec2-2.dtsi"
 
+	enet0: ethernet@b0000 {
+		fsl,pmc-handle = <&etsec1_clk>;
+	};
+
+	enet1: ethernet@b1000 {
+		fsl,pmc-handle = <&etsec2_clk>;
+	};
+
+	enet2: ethernet@b2000 {
+		fsl,pmc-handle = <&etsec3_clk>;
+	};
+
 	global-utilities@e0000 {
 		compatible = "fsl,p1010-guts";
 		reg = <0xe0000 0x1000>;
 		fsl,has-rstcr;
 	};
+
+/include/ "pq3-power.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi
index 642dc3a83d0e..cc4c7461003b 100644
--- a/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi
@@ -163,14 +163,17 @@
 
 /include/ "pq3-etsec2-0.dtsi"
 	enet0: enet0_grp2: ethernet@b0000 {
+		fsl,pmc-handle = <&etsec1_clk>;
 	};
 
 /include/ "pq3-etsec2-1.dtsi"
 	enet1: enet1_grp2: ethernet@b1000 {
+		fsl,pmc-handle = <&etsec2_clk>;
 	};
 
 /include/ "pq3-etsec2-2.dtsi"
 	enet2: enet2_grp2: ethernet@b2000 {
+		fsl,pmc-handle = <&etsec3_clk>;
 	};
 
 	global-utilities@e0000 {
@@ -178,6 +181,8 @@
 		reg = <0xe0000 0x1000>;
 		fsl,has-rstcr;
 	};
+
+/include/ "pq3-power.dtsi"
 };
 
 /include/ "pq3-etsec2-grp2-0.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
index 407cb5fd0f5b..378195db9fca 100644
--- a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
@@ -159,14 +159,17 @@
 
 /include/ "pq3-etsec2-0.dtsi"
 	enet0: enet0_grp2: ethernet@b0000 {
+		fsl,pmc-handle = <&etsec1_clk>;
 	};
 
 /include/ "pq3-etsec2-1.dtsi"
 	enet1: enet1_grp2: ethernet@b1000 {
+		fsl,pmc-handle = <&etsec2_clk>;
 	};
 
 /include/ "pq3-etsec2-2.dtsi"
 	enet2: enet2_grp2: ethernet@b2000 {
+		fsl,pmc-handle = <&etsec3_clk>;
 	};
 
 	global-utilities@e0000 {
@@ -174,6 +177,8 @@
 		reg = <0xe0000 0x1000>;
 		fsl,has-rstcr;
 	};
+
+/include/ "pq3-power.dtsi"
 };
 
 &qe {
diff --git a/arch/powerpc/boot/dts/fsl/p1022rdk.dts b/arch/powerpc/boot/dts/fsl/p1022rdk.dts
index 29e8af1e3711..4261c2f7e4b3 100644
--- a/arch/powerpc/boot/dts/fsl/p1022rdk.dts
+++ b/arch/powerpc/boot/dts/fsl/p1022rdk.dts
@@ -60,23 +60,23 @@
 				compatible = "st,m41t62";
 				reg = <0x68>;
 			};
-			adt7461@4c{
+			adt7461@4c {
 				compatible = "adi,adt7461";
 				reg = <0x4c>;
 			};
-			zl6100@21{
+			zl6100@21 {
 				compatible = "isil,zl6100";
 				reg = <0x21>;
 			};
-			zl6100@24{
+			zl6100@24 {
 				compatible = "isil,zl6100";
 				reg = <0x24>;
 			};
-			zl6100@26{
+			zl6100@26 {
 				compatible = "isil,zl6100";
 				reg = <0x26>;
 			};
-			zl6100@29{
+			zl6100@29 {
 				compatible = "isil,zl6100";
 				reg = <0x29>;
 			};
diff --git a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
index 5f51b7bfc064..6ac21e81344a 100644
--- a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
@@ -225,11 +225,13 @@
 /include/ "pq3-etsec2-0.dtsi"
 	enet0: enet0_grp2: ethernet@b0000 {
 		fsl,wake-on-filer;
+		fsl,pmc-handle = <&etsec1_clk>;
 	};
 
 /include/ "pq3-etsec2-1.dtsi"
 	enet1: enet1_grp2: ethernet@b1000 {
 		fsl,wake-on-filer;
+		fsl,pmc-handle = <&etsec2_clk>;
 	};
 
 	global-utilities@e0000 {
@@ -238,9 +240,10 @@
 		fsl,has-rstcr;
 	};
 
-	power@e0070{
-		compatible = "fsl,mpc8536-pmc", "fsl,mpc8548-pmc";
-		reg = <0xe0070 0x20>;
+/include/ "pq3-power.dtsi"
+	power@e0070 {
+		compatible = "fsl,p1022-pmc", "fsl,mpc8536-pmc",
+				"fsl,mpc8548-pmc";
 	};
 
 };
diff --git a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi
index 81b9ab2119be..d410082d21c0 100644
--- a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi
@@ -178,6 +178,10 @@
 		compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
 	};
 /include/ "pq3-etsec1-0.dtsi"
+	enet0: ethernet@24000 {
+		fsl,pmc-handle = <&etsec1_clk>;
+
+	};
 /include/ "pq3-etsec1-timer-0.dtsi"
 
 	ptp_clock@24e00 {
@@ -186,7 +190,15 @@
 
 
 /include/ "pq3-etsec1-1.dtsi"
+	enet1: ethernet@25000 {
+		fsl,pmc-handle = <&etsec2_clk>;
+	};
+
 /include/ "pq3-etsec1-2.dtsi"
+	enet2: ethernet@26000 {
+		fsl,pmc-handle = <&etsec3_clk>;
+	};
+
 /include/ "pq3-esdhc-0.dtsi"
 	sdhc@2e000 {
 		compatible = "fsl,p2020-esdhc", "fsl,esdhc";
@@ -202,8 +214,5 @@
 		fsl,has-rstcr;
 	};
 
-	pmc: power@e0070 {
-		compatible = "fsl,mpc8548-pmc";
-		reg = <0xe0070 0x20>;
-	};
+/include/ "pq3-power.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/p3041ds.dts b/arch/powerpc/boot/dts/fsl/p3041ds.dts
index 6f5f7283c533..ca0e0272ac62 100644
--- a/arch/powerpc/boot/dts/fsl/p3041ds.dts
+++ b/arch/powerpc/boot/dts/fsl/p3041ds.dts
@@ -41,7 +41,7 @@
 	#size-cells = <2>;
 	interrupt-parent = <&mpic>;
 
-	aliases{
+	aliases {
 		phy_rgmii_0 = &phy_rgmii_0;
 		phy_rgmii_1 = &phy_rgmii_1;
 		phy_sgmii_1c = &phy_sgmii_1c;
@@ -165,7 +165,7 @@
 			};
 		};
 
-		fman@400000{
+		fman@400000 {
 			ethernet@e0000 {
 				phy-handle = <&phy_sgmii_1c>;
 				phy-connection-type = "sgmii";
diff --git a/arch/powerpc/boot/dts/fsl/p5040ds.dts b/arch/powerpc/boot/dts/fsl/p5040ds.dts
index 30850b3228e0..5cfc689ee474 100644
--- a/arch/powerpc/boot/dts/fsl/p5040ds.dts
+++ b/arch/powerpc/boot/dts/fsl/p5040ds.dts
@@ -41,7 +41,7 @@
 	#size-cells = <2>;
 	interrupt-parent = <&mpic>;
 
-	aliases{
+	aliases {
 		phy_sgmii_slot2_1c = &phy_sgmii_slot2_1c;
 		phy_sgmii_slot2_1d = &phy_sgmii_slot2_1d;
 		phy_sgmii_slot2_1e = &phy_sgmii_slot2_1e;
diff --git a/arch/powerpc/boot/dts/fsl/pq3-power.dtsi b/arch/powerpc/boot/dts/fsl/pq3-power.dtsi
new file mode 100644
index 000000000000..6af12401004d
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/pq3-power.dtsi
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: (GPL-2.0+)
+/*
+ * Copyright 2024 NXP
+ */
+
+power@e0070 {
+	compatible = "fsl,mpc8548-pmc";
+	reg = <0xe0070 0x20>;
+
+	etsec1_clk: soc-clk@24 {
+		fsl,pmcdr-mask = <0x00000080>;
+	};
+	etsec2_clk: soc-clk@25 {
+		fsl,pmcdr-mask = <0x00000040>;
+	};
+	etsec3_clk: soc-clk@26 {
+		fsl,pmcdr-mask = <0x00000020>;
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
index d552044c5afc..8ef0c020206b 100644
--- a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
@@ -52,7 +52,7 @@
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
-	compatible = "fsl,ifc", "simple-bus";
+	compatible = "fsl,ifc";
 	interrupts = <25 2 0 0>;
 };
 
@@ -367,45 +367,46 @@
 		reg = <0xf0000 0x1000>;
 		interrupts = <18 2 0 0>;
 		fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x30061>;
-		fsl,tmu-calibration = <0x00000000 0x0000000f
-				       0x00000001 0x00000017
-				       0x00000002 0x0000001e
-				       0x00000003 0x00000026
-				       0x00000004 0x0000002e
-				       0x00000005 0x00000035
-				       0x00000006 0x0000003d
-				       0x00000007 0x00000044
-				       0x00000008 0x0000004c
-				       0x00000009 0x00000053
-				       0x0000000a 0x0000005b
-				       0x0000000b 0x00000064
-
-				       0x00010000 0x00000011
-				       0x00010001 0x0000001c
-				       0x00010002 0x00000024
-				       0x00010003 0x0000002b
-				       0x00010004 0x00000034
-				       0x00010005 0x00000039
-				       0x00010006 0x00000042
-				       0x00010007 0x0000004c
-				       0x00010008 0x00000051
-				       0x00010009 0x0000005a
-				       0x0001000a 0x00000063
-
-				       0x00020000 0x00000013
-				       0x00020001 0x00000019
-				       0x00020002 0x00000024
-				       0x00020003 0x0000002c
-				       0x00020004 0x00000035
-				       0x00020005 0x0000003d
-				       0x00020006 0x00000046
-				       0x00020007 0x00000050
-				       0x00020008 0x00000059
-
-				       0x00030000 0x00000002
-				       0x00030001 0x0000000d
-				       0x00030002 0x00000019
-				       0x00030003 0x00000024>;
+		fsl,tmu-calibration =
+				<0x00000000 0x0000000f>,
+				<0x00000001 0x00000017>,
+				<0x00000002 0x0000001e>,
+				<0x00000003 0x00000026>,
+				<0x00000004 0x0000002e>,
+				<0x00000005 0x00000035>,
+				<0x00000006 0x0000003d>,
+				<0x00000007 0x00000044>,
+				<0x00000008 0x0000004c>,
+				<0x00000009 0x00000053>,
+				<0x0000000a 0x0000005b>,
+				<0x0000000b 0x00000064>,
+
+				<0x00010000 0x00000011>,
+				<0x00010001 0x0000001c>,
+				<0x00010002 0x00000024>,
+				<0x00010003 0x0000002b>,
+				<0x00010004 0x00000034>,
+				<0x00010005 0x00000039>,
+				<0x00010006 0x00000042>,
+				<0x00010007 0x0000004c>,
+				<0x00010008 0x00000051>,
+				<0x00010009 0x0000005a>,
+				<0x0001000a 0x00000063>,
+
+				<0x00020000 0x00000013>,
+				<0x00020001 0x00000019>,
+				<0x00020002 0x00000024>,
+				<0x00020003 0x0000002c>,
+				<0x00020004 0x00000035>,
+				<0x00020005 0x0000003d>,
+				<0x00020006 0x00000046>,
+				<0x00020007 0x00000050>,
+				<0x00020008 0x00000059>,
+
+				<0x00030000 0x00000002>,
+				<0x00030001 0x0000000d>,
+				<0x00030002 0x00000019>,
+				<0x00030003 0x00000024>;
 		#thermal-sensor-cells = <1>;
 	};
 
diff --git a/arch/powerpc/boot/dts/fsl/t1024rdb.dts b/arch/powerpc/boot/dts/fsl/t1024rdb.dts
index 270aaf631f2a..7d003e07a9fb 100644
--- a/arch/powerpc/boot/dts/fsl/t1024rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1024rdb.dts
@@ -91,7 +91,7 @@
 		board-control@2,0 {
 			#address-cells = <1>;
 			#size-cells = <1>;
-			compatible = "fsl,t1024-cpld";
+			compatible = "fsl,t1024-cpld", "fsl,deepsleep-cpld";
 			reg = <3 0 0x300>;
 			ranges = <0 3 0 0x300>;
 			bank-width = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
index dd3aab81e9de..4347924e9aa7 100644
--- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
@@ -104,7 +104,7 @@
 
 	ifc: localbus@ffe124000 {
 		cpld@3,0 {
-			compatible = "fsl,t1040rdb-cpld";
+			compatible = "fsl,t104xrdb-cpld", "fsl,deepsleep-cpld";
 		};
 	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index ad0ab33336b8..c9542b73bd7f 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -52,7 +52,7 @@
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
-	compatible = "fsl,ifc", "simple-bus";
+	compatible = "fsl,ifc";
 	interrupts = <25 2 0 0>;
 };
 
@@ -447,41 +447,42 @@
 		reg = <0xf0000 0x1000>;
 		interrupts = <18 2 0 0>;
 		fsl,tmu-range = <0xa0000 0x90026 0x8004a 0x1006a>;
-		fsl,tmu-calibration = <0x00000000 0x00000025
-				       0x00000001 0x00000028
-				       0x00000002 0x0000002d
-				       0x00000003 0x00000031
-				       0x00000004 0x00000036
-				       0x00000005 0x0000003a
-				       0x00000006 0x00000040
-				       0x00000007 0x00000044
-				       0x00000008 0x0000004a
-				       0x00000009 0x0000004f
-				       0x0000000a 0x00000054
-
-				       0x00010000 0x0000000d
-				       0x00010001 0x00000013
-				       0x00010002 0x00000019
-				       0x00010003 0x0000001f
-				       0x00010004 0x00000025
-				       0x00010005 0x0000002d
-				       0x00010006 0x00000033
-				       0x00010007 0x00000043
-				       0x00010008 0x0000004b
-				       0x00010009 0x00000053
-
-				       0x00020000 0x00000010
-				       0x00020001 0x00000017
-				       0x00020002 0x0000001f
-				       0x00020003 0x00000029
-				       0x00020004 0x00000031
-				       0x00020005 0x0000003c
-				       0x00020006 0x00000042
-				       0x00020007 0x0000004d
-				       0x00020008 0x00000056
-
-				       0x00030000 0x00000012
-				       0x00030001 0x0000001d>;
+		fsl,tmu-calibration =
+				<0x00000000 0x00000025>,
+				<0x00000001 0x00000028>,
+				<0x00000002 0x0000002d>,
+				<0x00000003 0x00000031>,
+				<0x00000004 0x00000036>,
+				<0x00000005 0x0000003a>,
+				<0x00000006 0x00000040>,
+				<0x00000007 0x00000044>,
+				<0x00000008 0x0000004a>,
+				<0x00000009 0x0000004f>,
+				<0x0000000a 0x00000054>,
+
+				<0x00010000 0x0000000d>,
+				<0x00010001 0x00000013>,
+				<0x00010002 0x00000019>,
+				<0x00010003 0x0000001f>,
+				<0x00010004 0x00000025>,
+				<0x00010005 0x0000002d>,
+				<0x00010006 0x00000033>,
+				<0x00010007 0x00000043>,
+				<0x00010008 0x0000004b>,
+				<0x00010009 0x00000053>,
+
+				<0x00020000 0x00000010>,
+				<0x00020001 0x00000017>,
+				<0x00020002 0x0000001f>,
+				<0x00020003 0x00000029>,
+				<0x00020004 0x00000031>,
+				<0x00020005 0x0000003c>,
+				<0x00020006 0x00000042>,
+				<0x00020007 0x0000004d>,
+				<0x00020008 0x00000056>,
+
+				<0x00030000 0x00000012>,
+				<0x00030001 0x0000001d>;
 		#thermal-sensor-cells = <1>;
 	};
 
diff --git a/arch/powerpc/boot/dts/fsl/t1042rdb.dts b/arch/powerpc/boot/dts/fsl/t1042rdb.dts
index 3ebb712224cb..099764322b33 100644
--- a/arch/powerpc/boot/dts/fsl/t1042rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1042rdb.dts
@@ -68,7 +68,7 @@
 
 	ifc: localbus@ffe124000 {
 		cpld@3,0 {
-			compatible = "fsl,t1042rdb-cpld";
+			compatible = "fsl,t104xrdb-cpld", "fsl,deepsleep-cpld";
 		};
 	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts b/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts
index 8ec3ff45e6fc..b10cab1a347b 100644
--- a/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts
+++ b/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts
@@ -41,7 +41,7 @@
 
 	ifc: localbus@ffe124000 {
 		cpld@3,0 {
-			compatible = "fsl,t1042rdb_pi-cpld";
+			compatible = "fsl,t104xrdb-cpld", "fsl,deepsleep-cpld";
 		};
 	};
 
diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
index 27714dc2f04a..6bb95878d39d 100644
--- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
@@ -50,7 +50,7 @@
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
-	compatible = "fsl,ifc", "simple-bus";
+	compatible = "fsl,ifc";
 	interrupts = <25 2 0 0>;
 };
 
diff --git a/arch/powerpc/boot/dts/fsl/t4240qds.dts b/arch/powerpc/boot/dts/fsl/t4240qds.dts
index c0913ac5aaad..128b5798bb97 100644
--- a/arch/powerpc/boot/dts/fsl/t4240qds.dts
+++ b/arch/powerpc/boot/dts/fsl/t4240qds.dts
@@ -41,7 +41,7 @@
 	#size-cells = <2>;
 	interrupt-parent = <&mpic>;
 
-	aliases{
+	aliases {
 		phy_rgmii1 = &phyrgmii1;
 		phy_rgmii2 = &phyrgmii2;
 		phy_sgmii3 = &phy3;
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
index fcac73486d48..65f3e17c0d41 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
@@ -50,7 +50,7 @@
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
-	compatible = "fsl,ifc", "simple-bus";
+	compatible = "fsl,ifc";
 	interrupts = <25 2 0 0>;
 };
 
diff --git a/arch/powerpc/boot/dts/haleakala.dts b/arch/powerpc/boot/dts/haleakala.dts
deleted file mode 100644
index f81ce8786d59..000000000000
--- a/arch/powerpc/boot/dts/haleakala.dts
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * Device Tree Source for AMCC Haleakala (405EXr)
- *
- * Copyright 2008 DENX Software Engineering, Stefan Roese <sr@denx.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	model = "amcc,haleakala";
-	compatible = "amcc,haleakala", "amcc,kilauea";
-	dcr-parent = <&{/cpus/cpu@0}>;
-
-	aliases {
-		ethernet0 = &EMAC0;
-		serial0 = &UART0;
-		serial1 = &UART1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu@0 {
-			device_type = "cpu";
-			model = "PowerPC,405EXr";
-			reg = <0x00000000>;
-			clock-frequency = <0>; /* Filled in by U-Boot */
-			timebase-frequency = <0>; /* Filled in by U-Boot */
-			i-cache-line-size = <32>;
-			d-cache-line-size = <32>;
-			i-cache-size = <16384>; /* 16 kB */
-			d-cache-size = <16384>; /* 16 kB */
-			dcr-controller;
-			dcr-access-method = "native";
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x00000000 0x00000000>; /* Filled in by U-Boot */
-	};
-
-	UIC0: interrupt-controller {
-		compatible = "ibm,uic-405exr", "ibm,uic";
-		interrupt-controller;
-		cell-index = <0>;
-		dcr-reg = <0x0c0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-	};
-
-	UIC1: interrupt-controller1 {
-		compatible = "ibm,uic-405exr","ibm,uic";
-		interrupt-controller;
-		cell-index = <1>;
-		dcr-reg = <0x0d0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	UIC2: interrupt-controller2 {
-		compatible = "ibm,uic-405exr","ibm,uic";
-		interrupt-controller;
-		cell-index = <2>;
-		dcr-reg = <0x0e0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x1c 0x4 0x1d 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	plb {
-		compatible = "ibm,plb-405exr", "ibm,plb4";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-		clock-frequency = <0>; /* Filled in by U-Boot */
-
-		SDRAM0: memory-controller {
-			compatible = "ibm,sdram-405exr", "ibm,sdram-4xx-ddr2";
-			dcr-reg = <0x010 0x002>;
-			interrupt-parent = <&UIC2>;
-			interrupts = <0x5 0x4	/* ECC DED Error */ 
-				      0x6 0x4>;	/* ECC SEC Error */ 
-		};
-
-		MAL0: mcmal {
-			compatible = "ibm,mcmal-405exr", "ibm,mcmal2";
-			dcr-reg = <0x180 0x062>;
-			num-tx-chans = <2>;
-			num-rx-chans = <2>;
-			interrupt-parent = <&MAL0>;
-			interrupts = <0x0 0x1 0x2 0x3 0x4>;
-			#interrupt-cells = <1>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			interrupt-map = </*TXEOB*/ 0x0 &UIC0 0xa 0x4
-					/*RXEOB*/ 0x1 &UIC0 0xb 0x4
-					/*SERR*/  0x2 &UIC1 0x0 0x4
-					/*TXDE*/  0x3 &UIC1 0x1 0x4
-					/*RXDE*/  0x4 &UIC1 0x2 0x4>;
-			interrupt-map-mask = <0xffffffff>;
-		};
-
-		POB0: opb {
-			compatible = "ibm,opb-405exr", "ibm,opb";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0x80000000 0x80000000 0x10000000
-				  0xef600000 0xef600000 0x00a00000
-				  0xf0000000 0xf0000000 0x10000000>;
-			dcr-reg = <0x0a0 0x005>;
-			clock-frequency = <0>; /* Filled in by U-Boot */
-
-			EBC0: ebc {
-				compatible = "ibm,ebc-405exr", "ibm,ebc";
-				dcr-reg = <0x012 0x002>;
-				#address-cells = <2>;
-				#size-cells = <1>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				/* ranges property is supplied by U-Boot */
-				interrupts = <0x5 0x1>;
-				interrupt-parent = <&UIC1>;
-
-				nor_flash@0,0 {
-					compatible = "amd,s29gl512n", "cfi-flash";
-					bank-width = <2>;
-					reg = <0x00000000 0x00000000 0x04000000>;
-					#address-cells = <1>;
-					#size-cells = <1>;
-					partition@0 {
-						label = "kernel";
-						reg = <0x00000000 0x00200000>;
-					};
-					partition@200000 {
-						label = "root";
-						reg = <0x00200000 0x00200000>;
-					};
-					partition@400000 {
-						label = "user";
-						reg = <0x00400000 0x03b60000>;
-					};
-					partition@3f60000 {
-						label = "env";
-						reg = <0x03f60000 0x00040000>;
-					};
-					partition@3fa0000 {
-						label = "u-boot";
-						reg = <0x03fa0000 0x00060000>;
-					};
-				};
-			};
-
-			UART0: serial@ef600200 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600200 0x00000008>;
-				virtual-reg = <0xef600200>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x1a 0x4>;
-			};
-
-			UART1: serial@ef600300 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600300 0x00000008>;
-				virtual-reg = <0xef600300>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x1 0x4>;
-			};
-
-			IIC0: i2c@ef600400 {
-				compatible = "ibm,iic-405exr", "ibm,iic";
-				reg = <0xef600400 0x00000014>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x2 0x4>;
-			};
-
-			IIC1: i2c@ef600500 {
-				compatible = "ibm,iic-405exr", "ibm,iic";
-				reg = <0xef600500 0x00000014>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x7 0x4>;
-			};
-
-
-			RGMII0: emac-rgmii@ef600b00 {
-				compatible = "ibm,rgmii-405exr", "ibm,rgmii";
-				reg = <0xef600b00 0x00000104>;
-				has-mdio;
-			};
-
-			EMAC0: ethernet@ef600900 {
-				linux,network-index = <0x0>;
-				device_type = "network";
-				compatible = "ibm,emac-405exr", "ibm,emac4sync";
-				interrupt-parent = <&EMAC0>;
-				interrupts = <0x0 0x1>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = </*Status*/ 0x0 &UIC0 0x18 0x4
-						/*Wake*/  0x1 &UIC1 0x1d 0x4>;
-				reg = <0xef600900 0x000000c4>;
-				local-mac-address = [000000000000]; /* Filled in by U-Boot */
-				mal-device = <&MAL0>;
-				mal-tx-channel = <0>;
-				mal-rx-channel = <0>;
-				cell-index = <0>;
-				max-frame-size = <9000>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-				rx-fifo-size-gige = <16384>;
-				tx-fifo-size-gige = <16384>;
-				phy-mode = "rgmii";
-				phy-map = <0x00000000>;
-				rgmii-device = <&RGMII0>;
-				rgmii-channel = <0>;
-				has-inverted-stacr-oc;
-				has-new-stacr-staopc;
-			};
-		};
-
-		PCIE0: pcie@a0000000 {
-			device_type = "pci";
-			#interrupt-cells = <1>;
-			#size-cells = <2>;
-			#address-cells = <3>;
-			compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
-			primary;
-			port = <0x0>; /* port number */
-			reg = <0xa0000000 0x20000000	/* Config space access */
-			       0xef000000 0x00001000>;	/* Registers */
-			dcr-reg = <0x040 0x020>;
-			sdr-base = <0x400>;
-
-			/* Outbound ranges, one memory and one IO,
-			 * later cannot be changed
-			 */
-			ranges = <0x02000000 0x00000000 0x80000000 0x90000000 0x00000000 0x08000000
-				  0x01000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00010000>;
-
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
-			/* This drives busses 0x00 to 0x3f */
-			bus-range = <0x0 0x3f>;
-
-			/* Legacy interrupts (note the weird polarity, the bridge seems
-			 * to invert PCIe legacy interrupts).
-			 * We are de-swizzling here because the numbers are actually for
-			 * port of the root complex virtual P2P bridge. But I want
-			 * to avoid putting a node for it in the tree, so the numbers
-			 * below are basically de-swizzled numbers.
-			 * The real slot is on idsel 0, so the swizzling is 1:1
-			 */
-			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
-			interrupt-map = <
-				0x0 0x0 0x0 0x1 &UIC2 0x0 0x4 /* swizzled int A */
-				0x0 0x0 0x0 0x2 &UIC2 0x1 0x4 /* swizzled int B */
-				0x0 0x0 0x0 0x3 &UIC2 0x2 0x4 /* swizzled int C */
-				0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
-		};
-	};
-};
diff --git a/arch/powerpc/boot/dts/hotfoot.dts b/arch/powerpc/boot/dts/hotfoot.dts
deleted file mode 100644
index b93bf2d9dd5b..000000000000
--- a/arch/powerpc/boot/dts/hotfoot.dts
+++ /dev/null
@@ -1,296 +0,0 @@
-/*
- * Device Tree Source for ESTeem 195E Hotfoot
- *
- * Copyright 2009 AbsoluteValue Systems <solomon@linux-wlan.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	model = "est,hotfoot";
-	compatible = "est,hotfoot";
-	dcr-parent = <&{/cpus/cpu@0}>;
-
-	aliases {
-		ethernet0 = &EMAC0;
-		ethernet1 = &EMAC1;
-		serial0 = &UART0;
-		serial1 = &UART1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu@0 {
-			device_type = "cpu";
-			model = "PowerPC,405EP";
-			reg = <0x00000000>;
-			clock-frequency = <0>; /* Filled in by zImage */
-			timebase-frequency = <0>; /* Filled in by zImage */
-			i-cache-line-size = <0x20>;
-			d-cache-line-size = <0x20>;
-			i-cache-size = <0x4000>;
-			d-cache-size = <0x4000>;
-			dcr-controller;
-			dcr-access-method = "native";
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x00000000 0x00000000>; /* Filled in by zImage */
-	};
-
-	UIC0: interrupt-controller {
-		compatible = "ibm,uic";
-		interrupt-controller;
-		cell-index = <0>;
-		dcr-reg = <0x0c0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-	};
-
-	plb {
-		compatible = "ibm,plb3";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-		clock-frequency = <0>; /* Filled in by zImage */
-
-		SDRAM0: memory-controller {
-			compatible = "ibm,sdram-405ep";
-			dcr-reg = <0x010 0x002>;
-		};
-
-		MAL: mcmal {
-			compatible = "ibm,mcmal-405ep", "ibm,mcmal";
-			dcr-reg = <0x180 0x062>;
-			num-tx-chans = <4>;
-			num-rx-chans = <2>;
-			interrupt-parent = <&UIC0>;
-			interrupts = <
-				0xb 0x4 /* TXEOB */
-				0xc 0x4 /* RXEOB */
-				0xa 0x4 /* SERR */
-				0xd 0x4 /* TXDE */
-				0xe 0x4 /* RXDE */>;
-		};
-
-		POB0: opb {
-			compatible = "ibm,opb-405ep", "ibm,opb";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0xef600000 0xef600000 0x00a00000>;
-			dcr-reg = <0x0a0 0x005>;
-			clock-frequency = <0>; /* Filled in by zImage */
-
-			/* Hotfoot has UART0/UART1 swapped */
-
-			UART0: serial@ef600400 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600400 0x00000008>;
-				virtual-reg = <0xef600400>;
-				clock-frequency = <0>; /* Filled in by zImage */
-				current-speed = <0x9600>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x1 0x4>;
-			};
-
-			UART1: serial@ef600300 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600300 0x00000008>;
-				virtual-reg = <0xef600300>;
-				clock-frequency = <0>; /* Filled in by zImage */
-				current-speed = <0x9600>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x0 0x4>;
-			};
-
-			IIC: i2c@ef600500 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "ibm,iic-405ep", "ibm,iic";
-				reg = <0xef600500 0x00000011>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x2 0x4>;
-
-				rtc@68 {
-					/* Actually a DS1339 */
-					compatible = "dallas,ds1307";
-					reg = <0x68>;
-				};
-
-				temp@4a {
-					/* Not present on all boards */
-					compatible = "national,lm75";
-					reg = <0x4a>;
-				};
-			};
-
-			GPIO: gpio@ef600700 {
-				#gpio-cells = <2>;
-				compatible = "ibm,ppc4xx-gpio";
-				reg = <0xef600700 0x00000020>;
-				gpio-controller;
-			};
-
-			gpio-leds {
-				compatible = "gpio-leds";
-				status {
-					label = "Status";
-					gpios = <&GPIO 1 0>;
-				};
-				radiorx {
-					label = "Rx";
-					gpios = <&GPIO 0xe 0>;
-				};
-			};
-
-			EMAC0: ethernet@ef600800 {
-				linux,network-index = <0x0>;
-				device_type = "network";
-				compatible = "ibm,emac-405ep", "ibm,emac";
-				interrupt-parent = <&UIC0>;
-				interrupts = <
-					0xf 0x4 /* Ethernet */
-					0x9 0x4 /* Ethernet Wake Up */>;
-				local-mac-address = [000000000000]; /* Filled in by zImage */
-				reg = <0xef600800 0x00000070>;
-				mal-device = <&MAL>;
-				mal-tx-channel = <0>;
-				mal-rx-channel = <0>;
-				cell-index = <0>;
-				max-frame-size = <0x5dc>;
-				rx-fifo-size = <0x1000>;
-				tx-fifo-size = <0x800>;
-				phy-mode = "mii";
-				phy-map = <0x00000000>;
-			};
-
-			EMAC1: ethernet@ef600900 {
-				linux,network-index = <0x1>;
-				device_type = "network";
-				compatible = "ibm,emac-405ep", "ibm,emac";
-				interrupt-parent = <&UIC0>;
-				interrupts = <
-					0x11 0x4 /* Ethernet */
-					0x9 0x4 /* Ethernet Wake Up */>;
-				local-mac-address = [000000000000]; /* Filled in by zImage */
-				reg = <0xef600900 0x00000070>;
-				mal-device = <&MAL>;
-				mal-tx-channel = <2>;
-				mal-rx-channel = <1>;
-				cell-index = <1>;
-				max-frame-size = <0x5dc>;
-				rx-fifo-size = <0x1000>;
-				tx-fifo-size = <0x800>;
-				mdio-device = <&EMAC0>;
-				phy-mode = "mii";
-				phy-map = <0x0000001>;
-			};
-		};
-
-		EBC0: ebc {
-			compatible = "ibm,ebc-405ep", "ibm,ebc";
-			dcr-reg = <0x012 0x002>;
-			#address-cells = <2>;
-			#size-cells = <1>;
-
-			/* The ranges property is supplied by the bootwrapper
-			 * and is based on the firmware's configuration of the
-			 * EBC bridge
-			 */
-			clock-frequency = <0>; /* Filled in by zImage */
-
-			nor_flash@0 {
-				compatible = "cfi-flash";
-				bank-width = <2>;
-				reg = <0x0 0xff800000 0x00800000>;
-				#address-cells = <1>;
-				#size-cells = <1>;
-
-				/* This mapping is for the 8M flash
-				   4M flash has all ofssets -= 4M,
-				   and FeatFS partition is not present */
-				partition@0 {
-					label = "Bootloader";
-					reg = <0x7c0000 0x40000>;
-					/* read-only; */
-				};
-				partition@1 {
-					label = "Env_and_Config_Primary";
-					reg = <0x400000 0x10000>;
-				};
-				partition@2 {
-					label = "Kernel";
-					reg = <0x420000 0x100000>;
-				};
-				partition@3 {
-					label = "Filesystem";
-					reg = <0x520000 0x2a0000>;
-				};
-				partition@4 {
-					label = "Env_and_Config_Secondary";
-					reg = <0x410000 0x10000>;
-				};
-				partition@5 {
-					label = "FeatFS";
-					reg = <0x000000 0x400000>;
-				};
-				partition@6 {
-					label = "Bootloader_Env";
-					reg = <0x7d0000 0x10000>;
-				};
-			};
-		};
-
-		PCI0: pci@ec000000 {
-			device_type = "pci";
-			#interrupt-cells = <1>;
-			#size-cells = <2>;
-			#address-cells = <3>;
-			compatible = "ibm,plb405ep-pci", "ibm,plb-pci";
-			primary;
-			reg = <0xeec00000 0x00000008    /* Config space access */
-				0xeed80000 0x00000004    /* IACK */
-				0xeed80000 0x00000004    /* Special cycle */
-				0xef480000 0x00000040>;  /* Internal registers */
-
-			/* Outbound ranges, one memory and one IO,
-			 * later cannot be changed. Chip supports a second
-			 * IO range but we don't use it for now
-			 */
-			ranges = <0x02000000 0x00000000 0x80000000 0x80000000 0x00000000 0x20000000
-				0x01000000 0x00000000 0x00000000 0xe8000000 0x00000000 0x00010000>;
-
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
-			interrupt-parent = <&UIC0>;
-			interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-			interrupt-map = <
-				/* IDSEL 3 -- slot1 (optional) 27/29 A/B IRQ2/4 */
-				0x1800 0x0 0x0 0x1 &UIC0 0x1b 0x8
-				0x1800 0x0 0x0 0x2 &UIC0 0x1d 0x8
-
-				/* IDSEL 4 -- slot0, 26/28 A/B IRQ1/3 */
-				0x2000 0x0 0x0 0x1 &UIC0 0x1a 0x8
-				0x2000 0x0 0x0 0x2 &UIC0 0x1c 0x8
-				>;
-		};
-	};
-
-	chosen {
-		stdout-path = &UART0;
-	};
-};
diff --git a/arch/powerpc/boot/dts/kilauea.dts b/arch/powerpc/boot/dts/kilauea.dts
deleted file mode 100644
index c07a7525a72c..000000000000
--- a/arch/powerpc/boot/dts/kilauea.dts
+++ /dev/null
@@ -1,407 +0,0 @@
-/*
- * Device Tree Source for AMCC Kilauea (405EX)
- *
- * Copyright 2007-2009 DENX Software Engineering, Stefan Roese <sr@denx.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	model = "amcc,kilauea";
-	compatible = "amcc,kilauea";
-	dcr-parent = <&{/cpus/cpu@0}>;
-
-	aliases {
-		ethernet0 = &EMAC0;
-		ethernet1 = &EMAC1;
-		serial0 = &UART0;
-		serial1 = &UART1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu@0 {
-			device_type = "cpu";
-			model = "PowerPC,405EX";
-			reg = <0x00000000>;
-			clock-frequency = <0>; /* Filled in by U-Boot */
-			timebase-frequency = <0>; /* Filled in by U-Boot */
-			i-cache-line-size = <32>;
-			d-cache-line-size = <32>;
-			i-cache-size = <16384>; /* 16 kB */
-			d-cache-size = <16384>; /* 16 kB */
-			dcr-controller;
-			dcr-access-method = "native";
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x00000000 0x00000000>; /* Filled in by U-Boot */
-	};
-
-	UIC0: interrupt-controller {
-		compatible = "ibm,uic-405ex", "ibm,uic";
-		interrupt-controller;
-		cell-index = <0>;
-		dcr-reg = <0x0c0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-	};
-
-	UIC1: interrupt-controller1 {
-		compatible = "ibm,uic-405ex","ibm,uic";
-		interrupt-controller;
-		cell-index = <1>;
-		dcr-reg = <0x0d0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	UIC2: interrupt-controller2 {
-		compatible = "ibm,uic-405ex","ibm,uic";
-		interrupt-controller;
-		cell-index = <2>;
-		dcr-reg = <0x0e0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x1c 0x4 0x1d 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	CPM0: cpm {
-		compatible = "ibm,cpm";
-		dcr-access-method = "native";
-		dcr-reg = <0x0b0 0x003>;
-		unused-units = <0x00000000>;
-		idle-doze = <0x02000000>;
-		standby = <0xe3e74800>;
-	};
-
-	plb {
-		compatible = "ibm,plb-405ex", "ibm,plb4";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-		clock-frequency = <0>; /* Filled in by U-Boot */
-
-		SDRAM0: memory-controller {
-			compatible = "ibm,sdram-405ex", "ibm,sdram-4xx-ddr2";
-			dcr-reg = <0x010 0x002>;
-			interrupt-parent = <&UIC2>;
-			interrupts = <0x5 0x4	/* ECC DED Error */ 
-				      0x6 0x4>;	/* ECC SEC Error */ 
-		};
-
-		CRYPTO: crypto@ef700000 {
-			compatible = "amcc,ppc405ex-crypto", "amcc,ppc4xx-crypto";
-			reg = <0xef700000 0x80400>;
-			interrupt-parent = <&UIC0>;
-			interrupts = <0x17 0x2>;
-		};
-
-		MAL0: mcmal {
-			compatible = "ibm,mcmal-405ex", "ibm,mcmal2";
-			dcr-reg = <0x180 0x062>;
-			num-tx-chans = <2>;
-			num-rx-chans = <2>;
-			interrupt-parent = <&MAL0>;
-			interrupts = <0x0 0x1 0x2 0x3 0x4>;
-			#interrupt-cells = <1>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			interrupt-map = </*TXEOB*/ 0x0 &UIC0 0xa 0x4
-					/*RXEOB*/ 0x1 &UIC0 0xb 0x4
-					/*SERR*/  0x2 &UIC1 0x0 0x4
-					/*TXDE*/  0x3 &UIC1 0x1 0x4
-					/*RXDE*/  0x4 &UIC1 0x2 0x4>;
-			interrupt-map-mask = <0xffffffff>;
-		};
-
-		POB0: opb {
-			compatible = "ibm,opb-405ex", "ibm,opb";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0x80000000 0x80000000 0x10000000
-				  0xef600000 0xef600000 0x00a00000
-				  0xf0000000 0xf0000000 0x10000000>;
-			dcr-reg = <0x0a0 0x005>;
-			clock-frequency = <0>; /* Filled in by U-Boot */
-
-			EBC0: ebc {
-				compatible = "ibm,ebc-405ex", "ibm,ebc";
-				dcr-reg = <0x012 0x002>;
-				#address-cells = <2>;
-				#size-cells = <1>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				/* ranges property is supplied by U-Boot */
-				interrupts = <0x5 0x1>;
-				interrupt-parent = <&UIC1>;
-
-				nor_flash@0,0 {
-					compatible = "amd,s29gl512n", "cfi-flash";
-					bank-width = <2>;
-					reg = <0x00000000 0x00000000 0x04000000>;
-					#address-cells = <1>;
-					#size-cells = <1>;
-					partition@0 {
-						label = "kernel";
-						reg = <0x00000000 0x001e0000>;
-					};
-					partition@1e0000 {
-						label = "dtb";
-						reg = <0x001e0000 0x00020000>;
-					};
-					partition@200000 {
-						label = "root";
-						reg = <0x00200000 0x00200000>;
-					};
-					partition@400000 {
-						label = "user";
-						reg = <0x00400000 0x03b60000>;
-					};
-					partition@3f60000 {
-						label = "env";
-						reg = <0x03f60000 0x00040000>;
-					};
-					partition@3fa0000 {
-						label = "u-boot";
-						reg = <0x03fa0000 0x00060000>;
-					};
-				};
-
-				ndfc@1,0 {
-					compatible = "ibm,ndfc";
-					reg = <0x00000001 0x00000000 0x00002000>;
-					ccr = <0x00001000>;
-					bank-settings = <0x80002222>;
-					#address-cells = <1>;
-					#size-cells = <1>;
-
-					nand {
-						#address-cells = <1>;
-						#size-cells = <1>;
-
-						partition@0 {
-							label = "u-boot";
-							reg = <0x00000000 0x00100000>;
-						};
-						partition@100000 {
-							label = "user";
-							reg = <0x00000000 0x03f00000>;
-						};
-					};
-				};
-			};
-
-			UART0: serial@ef600200 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600200 0x00000008>;
-				virtual-reg = <0xef600200>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x1a 0x4>;
-			};
-
-			UART1: serial@ef600300 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600300 0x00000008>;
-				virtual-reg = <0xef600300>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x1 0x4>;
-			};
-
-			IIC0: i2c@ef600400 {
-				compatible = "ibm,iic-405ex", "ibm,iic";
-				reg = <0xef600400 0x00000014>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x2 0x4>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				rtc@68 {
-					compatible = "dallas,ds1338";
-					reg = <0x68>;
-				};
-
-				dtt@48 {
-					compatible = "dallas,ds1775";
-					reg = <0x48>;
-				};
-			};
-
-			IIC1: i2c@ef600500 {
-				compatible = "ibm,iic-405ex", "ibm,iic";
-				reg = <0xef600500 0x00000014>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x7 0x4>;
-			};
-
-			RGMII0: emac-rgmii@ef600b00 {
-				compatible = "ibm,rgmii-405ex", "ibm,rgmii";
-				reg = <0xef600b00 0x00000104>;
-				has-mdio;
-			};
-
-			EMAC0: ethernet@ef600900 {
-				linux,network-index = <0x0>;
-				device_type = "network";
-				compatible = "ibm,emac-405ex", "ibm,emac4sync";
-				interrupt-parent = <&EMAC0>;
-				interrupts = <0x0 0x1>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = </*Status*/ 0x0 &UIC0 0x18 0x4
-						/*Wake*/  0x1 &UIC1 0x1d 0x4>;
-				reg = <0xef600900 0x000000c4>;
-				local-mac-address = [000000000000]; /* Filled in by U-Boot */
-				mal-device = <&MAL0>;
-				mal-tx-channel = <0>;
-				mal-rx-channel = <0>;
-				cell-index = <0>;
-				max-frame-size = <9000>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-				rx-fifo-size-gige = <16384>;
-				tx-fifo-size-gige = <16384>;
-				phy-mode = "rgmii";
-				phy-map = <0x00000000>;
-				rgmii-device = <&RGMII0>;
-				rgmii-channel = <0>;
-				has-inverted-stacr-oc;
-				has-new-stacr-staopc;
-			};
-
-			EMAC1: ethernet@ef600a00 {
-				linux,network-index = <0x1>;
-				device_type = "network";
-				compatible = "ibm,emac-405ex", "ibm,emac4sync";
-				interrupt-parent = <&EMAC1>;
-				interrupts = <0x0 0x1>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = </*Status*/ 0x0 &UIC0 0x19 0x4
-						/*Wake*/  0x1 &UIC1 0x1f 0x4>;
-				reg = <0xef600a00 0x000000c4>;
-				local-mac-address = [000000000000]; /* Filled in by U-Boot */
-				mal-device = <&MAL0>;
-				mal-tx-channel = <1>;
-				mal-rx-channel = <1>;
-				cell-index = <1>;
-				max-frame-size = <9000>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-				rx-fifo-size-gige = <16384>;
-				tx-fifo-size-gige = <16384>;
-				phy-mode = "rgmii";
-				phy-map = <0x00000000>;
-				rgmii-device = <&RGMII0>;
-				rgmii-channel = <1>;
-				has-inverted-stacr-oc;
-				has-new-stacr-staopc;
-			};
-		};
-
-		PCIE0: pcie@a0000000 {
-			device_type = "pci";
-			#interrupt-cells = <1>;
-			#size-cells = <2>;
-			#address-cells = <3>;
-			compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
-			primary;
-			port = <0x0>; /* port number */
-			reg = <0xa0000000 0x20000000	/* Config space access */
-			       0xef000000 0x00001000>;	/* Registers */
-			dcr-reg = <0x040 0x020>;
-			sdr-base = <0x400>;
-
-			/* Outbound ranges, one memory and one IO,
-			 * later cannot be changed
-			 */
-			ranges = <0x02000000 0x00000000 0x80000000 0x90000000 0x00000000 0x08000000
-				  0x01000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00010000>;
-
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
-			/* This drives busses 0x00 to 0x3f */
-			bus-range = <0x0 0x3f>;
-
-			/* Legacy interrupts (note the weird polarity, the bridge seems
-			 * to invert PCIe legacy interrupts).
-			 * We are de-swizzling here because the numbers are actually for
-			 * port of the root complex virtual P2P bridge. But I want
-			 * to avoid putting a node for it in the tree, so the numbers
-			 * below are basically de-swizzled numbers.
-			 * The real slot is on idsel 0, so the swizzling is 1:1
-			 */
-			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
-			interrupt-map = <
-				0x0 0x0 0x0 0x1 &UIC2 0x0 0x4 /* swizzled int A */
-				0x0 0x0 0x0 0x2 &UIC2 0x1 0x4 /* swizzled int B */
-				0x0 0x0 0x0 0x3 &UIC2 0x2 0x4 /* swizzled int C */
-				0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
-		};
-
-		PCIE1: pcie@c0000000 {
-			device_type = "pci";
-			#interrupt-cells = <1>;
-			#size-cells = <2>;
-			#address-cells = <3>;
-			compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
-			primary;
-			port = <0x1>; /* port number */
-			reg = <0xc0000000 0x20000000	/* Config space access */
-			       0xef001000 0x00001000>;	/* Registers */
-			dcr-reg = <0x060 0x020>;
-			sdr-base = <0x440>;
-
-			/* Outbound ranges, one memory and one IO,
-			 * later cannot be changed
-			 */
-			ranges = <0x02000000 0x00000000 0x80000000 0x98000000 0x00000000 0x08000000
-				  0x01000000 0x00000000 0x00000000 0xe0010000 0x00000000 0x00010000>;
-
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
-			/* This drives busses 0x40 to 0x7f */
-			bus-range = <0x40 0x7f>;
-
-			/* Legacy interrupts (note the weird polarity, the bridge seems
-			 * to invert PCIe legacy interrupts).
-			 * We are de-swizzling here because the numbers are actually for
-			 * port of the root complex virtual P2P bridge. But I want
-			 * to avoid putting a node for it in the tree, so the numbers
-			 * below are basically de-swizzled numbers.
-			 * The real slot is on idsel 0, so the swizzling is 1:1
-			 */
-			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
-			interrupt-map = <
-				0x0 0x0 0x0 0x1 &UIC2 0xb 0x4 /* swizzled int A */
-				0x0 0x0 0x0 0x2 &UIC2 0xc 0x4 /* swizzled int B */
-				0x0 0x0 0x0 0x3 &UIC2 0xd 0x4 /* swizzled int C */
-				0x0 0x0 0x0 0x4 &UIC2 0xe 0x4 /* swizzled int D */>;
-		};
-	};
-};
diff --git a/arch/powerpc/boot/dts/klondike.dts b/arch/powerpc/boot/dts/klondike.dts
deleted file mode 100644
index 97432177892a..000000000000
--- a/arch/powerpc/boot/dts/klondike.dts
+++ /dev/null
@@ -1,212 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Device Tree for Klondike (APM8018X) board.
- *
- * Copyright (c) 2010, Applied Micro Circuits Corporation
- * Author: Tanmay Inamdar <tinamdar@apm.com>
- */
-
-/dts-v1/;
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	model = "apm,klondike";
-	compatible = "apm,klondike";
-	dcr-parent = <&{/cpus/cpu@0}>;
-
-	aliases {
-		ethernet0 = &EMAC0;
-		ethernet1 = &EMAC1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu@0 {
-			device_type = "cpu";
-			model = "PowerPC,apm8018x";
-			reg = <0x00000000>;
-			clock-frequency = <300000000>; /* Filled in by U-Boot */
-			timebase-frequency = <300000000>; /* Filled in by U-Boot */
-			i-cache-line-size = <32>;
-			d-cache-line-size = <32>;
-			i-cache-size = <16384>; /* 16 kB */
-			d-cache-size = <16384>; /* 16 kB */
-			dcr-controller;
-			dcr-access-method = "native";
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x00000000 0x20000000>; /* Filled in by U-Boot */
-	};
-
-	UIC0: interrupt-controller {
-		compatible = "ibm,uic";
-		interrupt-controller;
-		cell-index = <0>;
-		dcr-reg = <0x0c0 0x010>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-	};
-
-	UIC1: interrupt-controller1 {
-		compatible = "ibm,uic";
-		interrupt-controller;
-		cell-index = <1>;
-		dcr-reg = <0x0d0 0x010>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	UIC2: interrupt-controller2 {
-		compatible = "ibm,uic";
-		interrupt-controller;
-		cell-index = <2>;
-		dcr-reg = <0x0e0 0x010>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x0a 0x4 0x0b 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	UIC3: interrupt-controller3 {
-		compatible = "ibm,uic";
-		interrupt-controller;
-		cell-index = <3>;
-		dcr-reg = <0x0f0 0x010>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x10 0x4 0x11 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	plb {
-		compatible = "ibm,plb4";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-		clock-frequency = <0>; /* Filled in by U-Boot */
-
-		SDRAM0: memory-controller {
-			compatible = "ibm,sdram-apm8018x";
-			dcr-reg = <0x010 0x002>;
-		};
-
-		MAL0: mcmal {
-			compatible = "ibm,mcmal2";
-			dcr-reg = <0x180 0x062>;
-			num-tx-chans = <2>;
-			num-rx-chans = <16>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			interrupt-parent = <&UIC1>;
-			interrupts = </*TXEOB*/   0x6 0x4
-					/*RXEOB*/ 0x7 0x4
-					/*SERR*/  0x1 0x4
-					/*TXDE*/  0x2 0x4
-					/*RXDE*/  0x3 0x4>;
-		};
-
-		POB0: opb {
-			compatible = "ibm,opb";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0x20000000 0x20000000 0x30000000
-				  0x50000000 0x50000000 0x10000000
-				  0x60000000 0x60000000 0x10000000
-				  0xFE000000 0xFE000000 0x00010000>;
-			dcr-reg = <0x100 0x020>;
-			clock-frequency = <300000000>; /* Filled in by U-Boot */
-
-			RGMII0: emac-rgmii@400a2000 {
-				compatible = "ibm,rgmii";
-				reg = <0x400a2000 0x00000010>;
-				has-mdio;
-			};
-
-			TAH0: emac-tah@400a3000 {
-				compatible = "ibm,tah";
-				reg = <0x400a3000 0x100>;
-			};
-
-			TAH1: emac-tah@400a4000 {
-				compatible = "ibm,tah";
-				reg = <0x400a4000 0x100>;
-			};
-
-			EMAC0: ethernet@400a0000 {
-				compatible = "ibm,emac4", "ibm-emac4sync";
-				interrupt-parent = <&EMAC0>;
-				interrupts = <0x0>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = </*Status*/ 0x0 &UIC0 0x13 0x4>;
-				reg = <0x400a0000 0x00000100>;
-				local-mac-address = [000000000000]; /* Filled in by U-Boot */
-				mal-device = <&MAL0>;
-				mal-tx-channel = <0x0>;
-				mal-rx-channel = <0x0>;
-				cell-index = <0>;
-				max-frame-size = <9000>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-				phy-mode = "rgmii";
-				phy-address = <0x2>;
-				turbo = "no";
-				phy-map = <0x00000000>;
-				rgmii-device = <&RGMII0>;
-				rgmii-channel = <0>;
-				tah-device = <&TAH0>;
-				tah-channel = <0>;
-				has-inverted-stacr-oc;
-				has-new-stacr-staopc;
-			};
-
-			EMAC1: ethernet@400a1000 {
-				compatible = "ibm,emac4", "ibm-emac4sync";
-				status = "disabled";
-				interrupt-parent = <&EMAC1>;
-				interrupts = <0x0>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = </*Status*/ 0x0 &UIC0 0x14 0x4>;
-				reg = <0x400a1000 0x00000100>;
-				local-mac-address = [000000000000]; /* Filled in by U-Boot */
-				mal-device = <&MAL0>;
-				mal-tx-channel = <1>;
-				mal-rx-channel = <8>;
-				cell-index = <1>;
-				max-frame-size = <9000>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-				phy-mode = "rgmii";
-				phy-address = <0x3>;
-				turbo = "no";
-				phy-map = <0x00000000>;
-				rgmii-device = <&RGMII0>;
-				rgmii-channel = <1>;
-				tah-device = <&TAH1>;
-				tah-channel = <0>;
-				has-inverted-stacr-oc;
-				has-new-stacr-staopc;
-				mdio-device = <&EMAC0>;
-			};
-		};
-	};
-
-	chosen {
-		stdout-path = "/plb/opb/serial@50001000";
-	};
-};
diff --git a/arch/powerpc/boot/dts/makalu.dts b/arch/powerpc/boot/dts/makalu.dts
deleted file mode 100644
index c473cd911bca..000000000000
--- a/arch/powerpc/boot/dts/makalu.dts
+++ /dev/null
@@ -1,353 +0,0 @@
-/*
- * Device Tree Source for AMCC Makalu (405EX)
- *
- * Copyright 2007 DENX Software Engineering, Stefan Roese <sr@denx.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	model = "amcc,makalu";
-	compatible = "amcc,makalu";
-	dcr-parent = <&{/cpus/cpu@0}>;
-
-	aliases {
-		ethernet0 = &EMAC0;
-		ethernet1 = &EMAC1;
-		serial0 = &UART0;
-		serial1 = &UART1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu@0 {
-			device_type = "cpu";
-			model = "PowerPC,405EX";
-			reg = <0x00000000>;
-			clock-frequency = <0>; /* Filled in by U-Boot */
-			timebase-frequency = <0>; /* Filled in by U-Boot */
-			i-cache-line-size = <32>;
-			d-cache-line-size = <32>;
-			i-cache-size = <16384>; /* 16 kB */
-			d-cache-size = <16384>; /* 16 kB */
-			dcr-controller;
-			dcr-access-method = "native";
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x00000000 0x00000000>; /* Filled in by U-Boot */
-	};
-
-	UIC0: interrupt-controller {
-		compatible = "ibm,uic-405ex", "ibm,uic";
-		interrupt-controller;
-		cell-index = <0>;
-		dcr-reg = <0x0c0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-	};
-
-	UIC1: interrupt-controller1 {
-		compatible = "ibm,uic-405ex","ibm,uic";
-		interrupt-controller;
-		cell-index = <1>;
-		dcr-reg = <0x0d0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	UIC2: interrupt-controller2 {
-		compatible = "ibm,uic-405ex","ibm,uic";
-		interrupt-controller;
-		cell-index = <2>;
-		dcr-reg = <0x0e0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x1c 0x4 0x1d 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	plb {
-		compatible = "ibm,plb-405ex", "ibm,plb4";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-		clock-frequency = <0>; /* Filled in by U-Boot */
-
-		SDRAM0: memory-controller {
-			compatible = "ibm,sdram-405ex", "ibm,sdram-4xx-ddr2";
-			dcr-reg = <0x010 0x002>;
-			interrupt-parent = <&UIC2>;
-			interrupts = <0x5 0x4 /* ECC DED Error */
-			              0x6 0x4 /* ECC SEC Error */ >;
-		};
-
-		MAL0: mcmal {
-			compatible = "ibm,mcmal-405ex", "ibm,mcmal2";
-			dcr-reg = <0x180 0x062>;
-			num-tx-chans = <2>;
-			num-rx-chans = <2>;
-			interrupt-parent = <&MAL0>;
-			interrupts = <0x0 0x1 0x2 0x3 0x4>;
-			#interrupt-cells = <1>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			interrupt-map = </*TXEOB*/ 0x0 &UIC0 0xa 0x4
-					/*RXEOB*/ 0x1 &UIC0 0xb 0x4
-					/*SERR*/  0x2 &UIC1 0x0 0x4
-					/*TXDE*/  0x3 &UIC1 0x1 0x4
-					/*RXDE*/  0x4 &UIC1 0x2 0x4>;
-			interrupt-map-mask = <0xffffffff>;
-		};
-
-		POB0: opb {
-			compatible = "ibm,opb-405ex", "ibm,opb";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0x80000000 0x80000000 0x10000000
-				  0xef600000 0xef600000 0x00a00000
-				  0xf0000000 0xf0000000 0x10000000>;
-			dcr-reg = <0x0a0 0x005>;
-			clock-frequency = <0>; /* Filled in by U-Boot */
-
-			EBC0: ebc {
-				compatible = "ibm,ebc-405ex", "ibm,ebc";
-				dcr-reg = <0x012 0x002>;
-				#address-cells = <2>;
-				#size-cells = <1>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				/* ranges property is supplied by U-Boot */
-				interrupts = <0x5 0x1>;
-				interrupt-parent = <&UIC1>;
-
-				nor_flash@0,0 {
-					compatible = "amd,s29gl512n", "cfi-flash";
-					bank-width = <2>;
-					reg = <0x00000000 0x00000000 0x04000000>;
-					#address-cells = <1>;
-					#size-cells = <1>;
-					partition@0 {
-						label = "kernel";
-						reg = <0x00000000 0x00200000>;
-					};
-					partition@200000 {
-						label = "root";
-						reg = <0x00200000 0x00200000>;
-					};
-					partition@400000 {
-						label = "user";
-						reg = <0x00400000 0x03b60000>;
-					};
-					partition@3f60000 {
-						label = "env";
-						reg = <0x03f60000 0x00040000>;
-					};
-					partition@3fa0000 {
-						label = "u-boot";
-						reg = <0x03fa0000 0x00060000>;
-					};
-				};
-			};
-
-			UART0: serial@ef600200 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600200 0x00000008>;
-				virtual-reg = <0xef600200>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x1a 0x4>;
-			};
-
-			UART1: serial@ef600300 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600300 0x00000008>;
-				virtual-reg = <0xef600300>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x1 0x4>;
-			};
-
-			IIC0: i2c@ef600400 {
-				compatible = "ibm,iic-405ex", "ibm,iic";
-				reg = <0xef600400 0x00000014>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x2 0x4>;
-			};
-
-			IIC1: i2c@ef600500 {
-				compatible = "ibm,iic-405ex", "ibm,iic";
-				reg = <0xef600500 0x00000014>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x7 0x4>;
-			};
-
-
-			RGMII0: emac-rgmii@ef600b00 {
-				compatible = "ibm,rgmii-405ex", "ibm,rgmii";
-				reg = <0xef600b00 0x00000104>;
-				has-mdio;
-			};
-
-			EMAC0: ethernet@ef600900 {
-				linux,network-index = <0x0>;
-				device_type = "network";
-				compatible = "ibm,emac-405ex", "ibm,emac4sync";
-				interrupt-parent = <&EMAC0>;
-				interrupts = <0x0 0x1>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = </*Status*/ 0x0 &UIC0 0x18 0x4
-						/*Wake*/  0x1 &UIC1 0x1d 0x4>;
-				reg = <0xef600900 0x000000c4>;
-				local-mac-address = [000000000000]; /* Filled in by U-Boot */
-				mal-device = <&MAL0>;
-				mal-tx-channel = <0>;
-				mal-rx-channel = <0>;
-				cell-index = <0>;
-				max-frame-size = <9000>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-				rx-fifo-size-gige = <16384>;
-				tx-fifo-size-gige = <16384>;
-				phy-mode = "rgmii";
-				phy-map = <0x0000003f>;	/* Start at 6 */
-				rgmii-device = <&RGMII0>;
-				rgmii-channel = <0>;
-				has-inverted-stacr-oc;
-				has-new-stacr-staopc;
-			};
-
-			EMAC1: ethernet@ef600a00 {
-				linux,network-index = <0x1>;
-				device_type = "network";
-				compatible = "ibm,emac-405ex", "ibm,emac4sync";
-				interrupt-parent = <&EMAC1>;
-				interrupts = <0x0 0x1>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = </*Status*/ 0x0 &UIC0 0x19 0x4
-						/*Wake*/  0x1 &UIC1 0x1f 0x4>;
-				reg = <0xef600a00 0x000000c4>;
-				local-mac-address = [000000000000]; /* Filled in by U-Boot */
-				mal-device = <&MAL0>;
-				mal-tx-channel = <1>;
-				mal-rx-channel = <1>;
-				cell-index = <1>;
-				max-frame-size = <9000>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-                                rx-fifo-size-gige = <16384>;
-                                tx-fifo-size-gige = <16384>;
-				phy-mode = "rgmii";
-				phy-map = <0x00000000>;
-				rgmii-device = <&RGMII0>;
-				rgmii-channel = <1>;
-				has-inverted-stacr-oc;
-				has-new-stacr-staopc;
-			};
-		};
-
-		PCIE0: pcie@a0000000 {
-			device_type = "pci";
-			#interrupt-cells = <1>;
-			#size-cells = <2>;
-			#address-cells = <3>;
-			compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
-			primary;
-			port = <0x0>; /* port number */
-			reg = <0xa0000000 0x20000000	/* Config space access */
-			       0xef000000 0x00001000>;	/* Registers */
-			dcr-reg = <0x040 0x020>;
-			sdr-base = <0x400>;
-
-			/* Outbound ranges, one memory and one IO,
-			 * later cannot be changed
-			 */
-			ranges = <0x02000000 0x00000000 0x80000000 0x90000000 0x00000000 0x08000000
-				  0x01000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00010000>;
-
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
-			/* This drives busses 0x00 to 0x3f */
-			bus-range = <0x0 0x3f>;
-
-			/* Legacy interrupts (note the weird polarity, the bridge seems
-			 * to invert PCIe legacy interrupts).
-			 * We are de-swizzling here because the numbers are actually for
-			 * port of the root complex virtual P2P bridge. But I want
-			 * to avoid putting a node for it in the tree, so the numbers
-			 * below are basically de-swizzled numbers.
-			 * The real slot is on idsel 0, so the swizzling is 1:1
-			 */
-			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
-			interrupt-map = <
-				0x0 0x0 0x0 0x1 &UIC2 0x0 0x4 /* swizzled int A */
-				0x0 0x0 0x0 0x2 &UIC2 0x1 0x4 /* swizzled int B */
-				0x0 0x0 0x0 0x3 &UIC2 0x2 0x4 /* swizzled int C */
-				0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>;
-		};
-
-		PCIE1: pcie@c0000000 {
-			device_type = "pci";
-			#interrupt-cells = <1>;
-			#size-cells = <2>;
-			#address-cells = <3>;
-			compatible = "ibm,plb-pciex-405ex", "ibm,plb-pciex";
-			primary;
-			port = <0x1>; /* port number */
-			reg = <0xc0000000 0x20000000	/* Config space access */
-			       0xef001000 0x00001000>;	/* Registers */
-			dcr-reg = <0x060 0x020>;
-			sdr-base = <0x440>;
-
-			/* Outbound ranges, one memory and one IO,
-			 * later cannot be changed
-			 */
-			ranges = <0x02000000 0x00000000 0x80000000 0x98000000 0x00000000 0x08000000
-				  0x01000000 0x00000000 0x00000000 0xe0010000 0x00000000 0x00010000>;
-
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x80000000>;
-
-			/* This drives busses 0x40 to 0x7f */
-			bus-range = <0x40 0x7f>;
-
-			/* Legacy interrupts (note the weird polarity, the bridge seems
-			 * to invert PCIe legacy interrupts).
-			 * We are de-swizzling here because the numbers are actually for
-			 * port of the root complex virtual P2P bridge. But I want
-			 * to avoid putting a node for it in the tree, so the numbers
-			 * below are basically de-swizzled numbers.
-			 * The real slot is on idsel 0, so the swizzling is 1:1
-			 */
-			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
-			interrupt-map = <
-				0x0 0x0 0x0 0x1 &UIC2 0xb 0x4 /* swizzled int A */
-				0x0 0x0 0x0 0x2 &UIC2 0xc 0x4 /* swizzled int B */
-				0x0 0x0 0x0 0x3 &UIC2 0xd 0x4 /* swizzled int C */
-				0x0 0x0 0x0 0x4 &UIC2 0xe 0x4 /* swizzled int D */>;
-		};
-	};
-};
diff --git a/arch/powerpc/boot/dts/microwatt.dts b/arch/powerpc/boot/dts/microwatt.dts
index 269e930b3b0b..292b909ca9ce 100644
--- a/arch/powerpc/boot/dts/microwatt.dts
+++ b/arch/powerpc/boot/dts/microwatt.dts
@@ -1,13 +1,15 @@
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	#size-cells = <0x02>;
 	#address-cells = <0x02>;
-	model-name = "microwatt";
+	model = "microwatt";
 	compatible = "microwatt-soc";
 
 	aliases {
 		serial0 = &UART0;
+		ethernet = &enet0;
 	};
 
 	reserved-memory {
@@ -35,40 +37,79 @@
 
 		ibm,powerpc-cpu-features {
 			display-name = "Microwatt";
-			isa = <3000>;
+			isa = <3100>;
 			device_type = "cpu-features";
 			compatible = "ibm,powerpc-cpu-features";
 
 			mmu-radix {
 				isa = <3000>;
-				usable-privilege = <2>;
+				usable-privilege = <6>;
+				os-support = <0>;
 			};
 
 			little-endian {
-				isa = <2050>;
-				usable-privilege = <3>;
+				isa = <0>;
+				usable-privilege = <7>;
+				os-support = <0>;
 				hwcap-bit-nr = <1>;
 			};
 
 			cache-inhibited-large-page {
-				isa = <2040>;
-				usable-privilege = <2>;
+				isa = <0>;
+				usable-privilege = <6>;
+				os-support = <0>;
 			};
 
 			fixed-point-v3 {
 				isa = <3000>;
-				usable-privilege = <3>;
+				usable-privilege = <7>;
 			};
 
 			no-execute {
-				isa = <2010>;
+				isa = <0x00>;
 				usable-privilege = <2>;
+				os-support = <0>;
 			};
 
 			floating-point {
+				hfscr-bit-nr = <0>;
 				hwcap-bit-nr = <27>;
 				isa = <0>;
-				usable-privilege = <3>;
+				usable-privilege = <7>;
+				hv-support = <1>;
+				os-support = <0>;
+			};
+
+			prefixed-instructions {
+				hfscr-bit-nr = <13>;
+				fscr-bit-nr = <13>;
+				isa = <3010>;
+				usable-privilege = <7>;
+				os-support = <1>;
+				hv-support = <1>;
+			};
+
+			tar {
+				hfscr-bit-nr = <8>;
+				fscr-bit-nr = <8>;
+				isa = <2070>;
+				usable-privilege = <7>;
+				os-support = <1>;
+				hv-support = <1>;
+				hwcap-bit-nr = <58>;
+			};
+
+			control-register {
+				isa = <0>;
+				usable-privilege = <7>;
+			};
+
+			system-call-vectored {
+				isa = <3000>;
+				usable-privilege = <7>;
+				os-support = <1>;
+				fscr-bit-nr = <12>;
+				hwcap-bit-nr = <52>;
 			};
 		};
 
@@ -101,6 +142,36 @@
 			ibm,mmu-lpid-bits = <12>;
 			ibm,mmu-pid-bits = <20>;
 		};
+
+		PowerPC,Microwatt@1 {
+			i-cache-sets = <2>;
+			ibm,dec-bits = <64>;
+			reservation-granule-size = <64>;
+			clock-frequency = <100000000>;
+			timebase-frequency = <100000000>;
+			i-tlb-sets = <1>;
+			ibm,ppc-interrupt-server#s = <1>;
+			i-cache-block-size = <64>;
+			d-cache-block-size = <64>;
+			d-cache-sets = <2>;
+			i-tlb-size = <64>;
+			cpu-version = <0x990000>;
+			status = "okay";
+			i-cache-size = <0x1000>;
+			ibm,processor-radix-AP-encodings = <0x0c 0xa0000010 0x20000015 0x4000001e>;
+			tlb-size = <0>;
+			tlb-sets = <0>;
+			device_type = "cpu";
+			d-tlb-size = <128>;
+			d-tlb-sets = <2>;
+			reg = <1>;
+			general-purpose;
+			64-bit;
+			d-cache-size = <0x1000>;
+			ibm,chip-id = <0>;
+			ibm,mmu-lpid-bits = <12>;
+			ibm,mmu-pid-bits = <20>;
+		};
 	};
 
 	soc@c0000000 {
@@ -113,8 +184,8 @@
 
 		interrupt-controller@4000 {
 			compatible = "openpower,xics-presentation", "ibm,ppc-xicp";
-			ibm,interrupt-server-ranges = <0x0 0x1>;
-			reg = <0x4000 0x100>;
+			ibm,interrupt-server-ranges = <0x0 0x2>;
+			reg = <0x4000 0x10 0x4010 0x10>;
 		};
 
 		ICS: interrupt-controller@5000 {
@@ -138,7 +209,18 @@
 			interrupts = <0x10 0x1>;
 		};
 
-		ethernet@8020000 {
+		gpio: gpio@7000 {
+			device_type = "gpio";
+			compatible = "faraday,ftgpio010";
+			gpio-controller;
+			#gpio-cells = <2>;
+			reg = <0x7000 0x80>;
+			interrupts = <0x14 1>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+
+		enet0: ethernet@8020000 {
 			compatible = "litex,liteeth";
 			reg = <0x8021000 0x100
 				0x8020800 0x100
@@ -160,7 +242,6 @@
 			reg-names = "phy", "core", "reader", "writer", "irq";
 			bus-width = <4>;
 			interrupts = <0x13 1>;
-			cap-sd-highspeed;
 			clocks = <&sys_clk>;
 		};
 	};
diff --git a/arch/powerpc/boot/dts/mpc5121.dtsi b/arch/powerpc/boot/dts/mpc5121.dtsi
index 3f66b91a8e3c..a278fb7b9e71 100644
--- a/arch/powerpc/boot/dts/mpc5121.dtsi
+++ b/arch/powerpc/boot/dts/mpc5121.dtsi
@@ -112,7 +112,7 @@
 		};
 
 		/* Watchdog timer */
-		wdt@900 {
+		watchdog@900 {
 			compatible = "fsl,mpc5121-wdt";
 			reg = <0x900 0x100>;
 		};
@@ -140,7 +140,7 @@
 		};
 
 		/* Power Management Controller */
-		pmc@1000{
+		pmc@1000 {
 			compatible = "fsl,mpc5121-pmc";
 			reg = <0x1000 0x100>;
 			interrupts = <83 0x8>;
diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts
index 0bd2acc0401d..ee090709aa3a 100644
--- a/arch/powerpc/boot/dts/mpc5125twr.dts
+++ b/arch/powerpc/boot/dts/mpc5125twr.dts
@@ -104,7 +104,7 @@
 			clock-names = "osc";
 		};
 
-		pmc@1000{  // Power Management Controller
+		pmc@1000 {  // Power Management Controller
 			compatible = "fsl,mpc5121-pmc";
 			reg = <0x1000 0x100>;
 			interrupts = <83 0x2>;
diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts
index a8315795b2c9..09508b4c8c73 100644
--- a/arch/powerpc/boot/dts/mpc8313erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8313erdb.dts
@@ -99,7 +99,7 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index e09b37d7489d..a8f68d6e50b0 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -6,6 +6,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/interrupt-controller/irq.h>
 
 / {
 	compatible = "fsl,mpc8315erdb";
@@ -99,7 +100,7 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
@@ -358,6 +359,15 @@
 			interrupt-parent = <&ipic>;
 			fsl,mpc8313-wakeup-timer = <&gtm1>;
 		};
+
+		gpio: gpio-controller@c00 {
+			compatible = "fsl,mpc8314-gpio";
+			reg = <0xc00 0x100>;
+			interrupts = <74 IRQ_TYPE_LEVEL_LOW>;
+			interrupt-parent = <&ipic>;
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
 	};
 
 	pci0: pci@e0008500 {
diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts
index ecebc27a2898..ba7caaf98fd5 100644
--- a/arch/powerpc/boot/dts/mpc832x_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts
@@ -52,7 +52,7 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts
index d4ebbb93de0b..13f17232ba83 100644
--- a/arch/powerpc/boot/dts/mpc8349emitx.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitx.dts
@@ -53,7 +53,7 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;                    // from bootloader
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
index bcf68a0a7b55..eae0afd5abbc 100644
--- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
@@ -51,7 +51,7 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;                    // from bootloader
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc836x_rdk.dts b/arch/powerpc/boot/dts/mpc836x_rdk.dts
index a0cc1953484d..4ff38e1a2185 100644
--- a/arch/powerpc/boot/dts/mpc836x_rdk.dts
+++ b/arch/powerpc/boot/dts/mpc836x_rdk.dts
@@ -62,7 +62,7 @@
 		/* filled by u-boot */
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
 		};
diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts
index 7df452efa957..f137ccb8cfde 100644
--- a/arch/powerpc/boot/dts/mpc8377_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts
@@ -99,7 +99,7 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8377_wlan.dts b/arch/powerpc/boot/dts/mpc8377_wlan.dts
index d8e7d40aeae4..ce254dd74dd0 100644
--- a/arch/powerpc/boot/dts/mpc8377_wlan.dts
+++ b/arch/powerpc/boot/dts/mpc8377_wlan.dts
@@ -89,7 +89,7 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts
index bdcfe83a561e..19e5473d4161 100644
--- a/arch/powerpc/boot/dts/mpc8378_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts
@@ -99,7 +99,7 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts
index a5f702304a35..61519acca228 100644
--- a/arch/powerpc/boot/dts/mpc8379_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts
@@ -97,7 +97,7 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/obs600.dts b/arch/powerpc/boot/dts/obs600.dts
deleted file mode 100644
index d10b0411809b..000000000000
--- a/arch/powerpc/boot/dts/obs600.dts
+++ /dev/null
@@ -1,314 +0,0 @@
-/*
- * Device Tree Source for PlatHome OpenBlockS 600 (405EX)
- *
- * Copyright 2011 Ben Herrenschmidt, IBM Corp.
- *
- * Based on Kilauea by:
- *
- * Copyright 2007-2009 DENX Software Engineering, Stefan Roese <sr@denx.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without
- * any warranty of any kind, whether express or implied.
- */
-
-/dts-v1/;
-
-/ {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	model = "PlatHome,OpenBlockS 600";
-	compatible = "plathome,obs600";
-	dcr-parent = <&{/cpus/cpu@0}>;
-
-	aliases {
-		ethernet0 = &EMAC0;
-		ethernet1 = &EMAC1;
-		serial0 = &UART0;
-		serial1 = &UART1;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu@0 {
-			device_type = "cpu";
-			model = "PowerPC,405EX";
-			reg = <0x00000000>;
-			clock-frequency = <0>; /* Filled in by U-Boot */
-			timebase-frequency = <0>; /* Filled in by U-Boot */
-			i-cache-line-size = <32>;
-			d-cache-line-size = <32>;
-			i-cache-size = <16384>; /* 16 kB */
-			d-cache-size = <16384>; /* 16 kB */
-			dcr-controller;
-			dcr-access-method = "native";
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x00000000 0x00000000>; /* Filled in by U-Boot */
-	};
-
-	UIC0: interrupt-controller {
-		compatible = "ibm,uic-405ex", "ibm,uic";
-		interrupt-controller;
-		cell-index = <0>;
-		dcr-reg = <0x0c0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-	};
-
-	UIC1: interrupt-controller1 {
-		compatible = "ibm,uic-405ex","ibm,uic";
-		interrupt-controller;
-		cell-index = <1>;
-		dcr-reg = <0x0d0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	UIC2: interrupt-controller2 {
-		compatible = "ibm,uic-405ex","ibm,uic";
-		interrupt-controller;
-		cell-index = <2>;
-		dcr-reg = <0x0e0 0x009>;
-		#address-cells = <0>;
-		#size-cells = <0>;
-		#interrupt-cells = <2>;
-		interrupts = <0x1c 0x4 0x1d 0x4>; /* cascade */
-		interrupt-parent = <&UIC0>;
-	};
-
-	CPM0: cpm {
-		compatible = "ibm,cpm";
-		dcr-access-method = "native";
-		dcr-reg = <0x0b0 0x003>;
-		unused-units = <0x00000000>;
-		idle-doze = <0x02000000>;
-		standby = <0xe3e74800>;
-	};
-
-	plb {
-		compatible = "ibm,plb-405ex", "ibm,plb4";
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-		clock-frequency = <0>; /* Filled in by U-Boot */
-
-		SDRAM0: memory-controller {
-			compatible = "ibm,sdram-405ex", "ibm,sdram-4xx-ddr2";
-			dcr-reg = <0x010 0x002>;
-			interrupt-parent = <&UIC2>;
-			interrupts = <0x5 0x4	/* ECC DED Error */
-				      0x6 0x4>;	/* ECC SEC Error */
-		};
-
-		CRYPTO: crypto@ef700000 {
-			compatible = "amcc,ppc405ex-crypto", "amcc,ppc4xx-crypto";
-			reg = <0xef700000 0x80400>;
-			interrupt-parent = <&UIC0>;
-			interrupts = <0x17 0x2>;
-		};
-
-		MAL0: mcmal {
-			compatible = "ibm,mcmal-405ex", "ibm,mcmal2";
-			dcr-reg = <0x180 0x062>;
-			num-tx-chans = <2>;
-			num-rx-chans = <2>;
-			interrupt-parent = <&MAL0>;
-			interrupts = <0x0 0x1 0x2 0x3 0x4>;
-			#interrupt-cells = <1>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			interrupt-map = </*TXEOB*/ 0x0 &UIC0 0xa 0x4
-					/*RXEOB*/ 0x1 &UIC0 0xb 0x4
-					/*SERR*/  0x2 &UIC1 0x0 0x4
-					/*TXDE*/  0x3 &UIC1 0x1 0x4
-					/*RXDE*/  0x4 &UIC1 0x2 0x4>;
-			interrupt-map-mask = <0xffffffff>;
-		};
-
-		POB0: opb {
-			compatible = "ibm,opb-405ex", "ibm,opb";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0x80000000 0x80000000 0x10000000
-				  0xef600000 0xef600000 0x00a00000
-				  0xf0000000 0xf0000000 0x10000000>;
-			dcr-reg = <0x0a0 0x005>;
-			clock-frequency = <0>; /* Filled in by U-Boot */
-
-			EBC0: ebc {
-				compatible = "ibm,ebc-405ex", "ibm,ebc";
-				dcr-reg = <0x012 0x002>;
-				#address-cells = <2>;
-				#size-cells = <1>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				/* ranges property is supplied by U-Boot */
-				interrupts = <0x5 0x1>;
-				interrupt-parent = <&UIC1>;
-
-				nor_flash@0,0 {
-					compatible = "amd,s29gl512n", "cfi-flash";
-					bank-width = <2>;
-					reg = <0x00000000 0x00000000 0x08000000>;
-					#address-cells = <1>;
-					#size-cells = <1>;
-					partition@0 {
-						label = "kernel + initrd";
-						reg = <0x00000000 0x03de0000>;
-					};
-					partition@3de0000 {
-						label = "user config area";
-						reg = <0x03de0000 0x00080000>;
-					};
-					partition@3e60000 {
-						label = "user program area";
-						reg = <0x03e60000 0x04000000>;
-					};
-					partition@7e60000 {
-						label = "flat device tree";
-						reg = <0x07e60000 0x00080000>;
-					};
-					partition@7ee0000 {
-						label = "test program";
-						reg = <0x07ee0000 0x00080000>;
-					};
-					partition@7f60000 {
-						label = "u-boot env";
-						reg = <0x07f60000 0x00040000>;
-					};
-					partition@7fa0000 {
-						label = "u-boot";
-						reg = <0x07fa0000 0x00060000>;
-					};
-				};
-			};
-
-			UART0: serial@ef600200 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600200 0x00000008>;
-				virtual-reg = <0xef600200>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x1a 0x4>;
-			};
-
-			UART1: serial@ef600300 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600300 0x00000008>;
-				virtual-reg = <0xef600300>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x1 0x4>;
-			};
-
-			IIC0: i2c@ef600400 {
-				compatible = "ibm,iic-405ex", "ibm,iic";
-				reg = <0xef600400 0x00000014>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x2 0x4>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				rtc@68 {
-					compatible = "dallas,ds1340";
-					reg = <0x68>;
-				};
-			};
-
-			IIC1: i2c@ef600500 {
-				compatible = "ibm,iic-405ex", "ibm,iic";
-				reg = <0xef600500 0x00000014>;
-				interrupt-parent = <&UIC0>;
-				interrupts = <0x7 0x4>;
-			};
-
-			RGMII0: emac-rgmii@ef600b00 {
-				compatible = "ibm,rgmii-405ex", "ibm,rgmii";
-				reg = <0xef600b00 0x00000104>;
-				has-mdio;
-			};
-
-			EMAC0: ethernet@ef600900 {
-				linux,network-index = <0x0>;
-				device_type = "network";
-				compatible = "ibm,emac-405ex", "ibm,emac4sync";
-				interrupt-parent = <&EMAC0>;
-				interrupts = <0x0 0x1>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = </*Status*/ 0x0 &UIC0 0x18 0x4
-						/*Wake*/  0x1 &UIC1 0x1d 0x4>;
-				reg = <0xef600900 0x000000c4>;
-				local-mac-address = [000000000000]; /* Filled in by U-Boot */
-				mal-device = <&MAL0>;
-				mal-tx-channel = <0>;
-				mal-rx-channel = <0>;
-				cell-index = <0>;
-				max-frame-size = <9000>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-				rx-fifo-size-gige = <16384>;
-				tx-fifo-size-gige = <16384>;
-				phy-mode = "rgmii";
-				phy-map = <0x00000000>;
-				rgmii-device = <&RGMII0>;
-				rgmii-channel = <0>;
-				has-inverted-stacr-oc;
-				has-new-stacr-staopc;
-			};
-
-			EMAC1: ethernet@ef600a00 {
-				linux,network-index = <0x1>;
-				device_type = "network";
-				compatible = "ibm,emac-405ex", "ibm,emac4sync";
-				interrupt-parent = <&EMAC1>;
-				interrupts = <0x0 0x1>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = </*Status*/ 0x0 &UIC0 0x19 0x4
-						/*Wake*/  0x1 &UIC1 0x1f 0x4>;
-				reg = <0xef600a00 0x000000c4>;
-				local-mac-address = [000000000000]; /* Filled in by U-Boot */
-				mal-device = <&MAL0>;
-				mal-tx-channel = <1>;
-				mal-rx-channel = <1>;
-				cell-index = <1>;
-				max-frame-size = <9000>;
-				rx-fifo-size = <4096>;
-				tx-fifo-size = <2048>;
-				rx-fifo-size-gige = <16384>;
-				tx-fifo-size-gige = <16384>;
-				phy-mode = "rgmii";
-				phy-map = <0x00000000>;
-				rgmii-device = <&RGMII0>;
-				rgmii-channel = <1>;
-				has-inverted-stacr-oc;
-				has-new-stacr-staopc;
-			};
-
-			GPIO: gpio@ef600800 {
-				device_type = "gpio";
-				compatible = "ibm,gpio-405ex", "ibm,ppc4xx-gpio";
-				reg = <0xef600800 0x50>;
-			};
-		};
-	};
-        chosen {
-                stdout-path = "/plb/opb/serial@ef600200";
-        };
-};
diff --git a/arch/powerpc/boot/dts/turris1x.dts b/arch/powerpc/boot/dts/turris1x.dts
index 6612160c19d5..dff1ea074d9d 100644
--- a/arch/powerpc/boot/dts/turris1x.dts
+++ b/arch/powerpc/boot/dts/turris1x.dts
@@ -476,12 +476,12 @@
 		 * channel 1 (but only USB 2.0 subset) to USB 2.0 pins on mPCIe
 		 * slot 1 (CN5), channels 2 and 3 to connector P600.
 		 *
-		 * P2020 PCIe Root Port uses 1MB of PCIe MEM and xHCI controller
+		 * P2020 PCIe Root Port does not use PCIe MEM and xHCI controller
 		 * uses 64kB + 8kB of PCIe MEM. No PCIe IO is used or required.
-		 * So allocate 2MB of PCIe MEM for this PCIe bus.
+		 * So allocate 128kB of PCIe MEM for this PCIe bus.
 		 */
 		reg = <0 0xffe08000 0 0x1000>;
-		ranges = <0x02000000 0x0 0xc0000000 0 0xc0000000 0x0 0x00200000>, /* MEM */
+		ranges = <0x02000000 0x0 0xc0000000 0 0xc0000000 0x0 0x00020000>, /* MEM */
 			 <0x01000000 0x0 0x00000000 0 0xffc20000 0x0 0x00010000>; /* IO */
 
 		pcie@0 {
diff --git a/arch/powerpc/boot/install.sh b/arch/powerpc/boot/install.sh
index 461902c8a46d..c3df6c27ce75 100755
--- a/arch/powerpc/boot/install.sh
+++ b/arch/powerpc/boot/install.sh
@@ -19,15 +19,19 @@
 set -e
 
 # this should work for both the pSeries zImage and the iSeries vmlinux.sm
-image_name=`basename $2`
+image_name=$(basename "$2")
 
-if [ -f $4/$image_name ]; then
-	mv $4/$image_name $4/$image_name.old
+
+echo "Warning: '${INSTALLKERNEL}' command not available... Copying" \
+     "directly to $4/$image_name-$1" >&2
+
+if [ -f "$4"/"$image_name"-"$1" ]; then
+	mv "$4"/"$image_name"-"$1" "$4"/"$image_name"-"$1".old
 fi
 
-if [ -f $4/System.map ]; then
-	mv $4/System.map $4/System.old
+if [ -f "$4"/System.map-"$1" ]; then
+	mv "$4"/System.map-"$1" "$4"/System-"$1".old
 fi
 
-cat $2 > $4/$image_name
-cp $3 $4/System.map
+cat "$2" > "$4"/"$image_name"-"$1"
+cp "$3" "$4"/System.map-"$1"
diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c
index cae31a6e8f02..2c0e2a1cab01 100644
--- a/arch/powerpc/boot/main.c
+++ b/arch/powerpc/boot/main.c
@@ -188,7 +188,7 @@ static inline void prep_esm_blob(struct addr_range vmlinux, void *chosen) { }
 
 /* A buffer that may be edited by tools operating on a zImage binary so as to
  * edit the command line passed to vmlinux (by setting /chosen/bootargs).
- * The buffer is put in it's own section so that tools may locate it easier.
+ * The buffer is put in its own section so that tools may locate it easier.
  */
 static char cmdline[BOOT_COMMAND_LINE_SIZE]
 	__attribute__((__section__("__builtin_cmdline")));
diff --git a/arch/powerpc/boot/page.h b/arch/powerpc/boot/page.h
index c3d55fc8f34c..e44a3119720d 100644
--- a/arch/powerpc/boot/page.h
+++ b/arch/powerpc/boot/page.h
@@ -5,7 +5,7 @@
  * Copyright (C) 2001 PPC64 Team, IBM Corp
  */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define ASM_CONST(x) x
 #else
 #define __ASM_CONST(x) x##UL
diff --git a/arch/powerpc/boot/ppcboot-hotfoot.h b/arch/powerpc/boot/ppcboot-hotfoot.h
deleted file mode 100644
index 4728db95f58a..000000000000
--- a/arch/powerpc/boot/ppcboot-hotfoot.h
+++ /dev/null
@@ -1,119 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * This interface is used for compatibility with old U-boots *ONLY*.
- * Please do not imitate or extend this.
- */
-
-/* 
- * Unfortunately, the ESTeem Hotfoot board uses a mangled version of 
- * ppcboot.h for historical reasons, and in the interest of having a 
- * mainline kernel boot on the production board+bootloader, this was the 
- * least-offensive solution.  Please direct all flames to:
- *
- *  Solomon Peachy <solomon@linux-wlan.com>
- *
- * (This header is identical to ppcboot.h except for the 
- *  TARGET_HOTFOOT bits)
- */
-
-/*
- * (C) Copyright 2000, 2001
- * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
- */
-
-#ifndef __PPCBOOT_H__
-#define __PPCBOOT_H__
-
-/*
- * Board information passed to kernel from PPCBoot
- *
- * include/asm-ppc/ppcboot.h
- */
-
-#include "types.h"
-
-typedef struct bd_info {
-	unsigned long	bi_memstart;	/* start of DRAM memory */
-	unsigned long	bi_memsize;	/* size	 of DRAM memory in bytes */
-	unsigned long	bi_flashstart;	/* start of FLASH memory */
-	unsigned long	bi_flashsize;	/* size	 of FLASH memory */
-	unsigned long	bi_flashoffset; /* reserved area for startup monitor */
-	unsigned long	bi_sramstart;	/* start of SRAM memory */
-	unsigned long	bi_sramsize;	/* size	 of SRAM memory */
-#if defined(TARGET_8xx) || defined(TARGET_CPM2) || defined(TARGET_85xx) ||\
-	defined(TARGET_83xx)
-	unsigned long	bi_immr_base;	/* base of IMMR register */
-#endif
-#if defined(TARGET_PPC_MPC52xx)
-	unsigned long   bi_mbar_base;   /* base of internal registers */
-#endif
-	unsigned long	bi_bootflags;	/* boot / reboot flag (for LynxOS) */
-	unsigned long	bi_ip_addr;	/* IP Address */
-	unsigned char	bi_enetaddr[6];	/* Ethernet address */
-#if defined(TARGET_HOTFOOT)
-	/* second onboard ethernet port */
-	unsigned char	bi_enet1addr[6];
-#define HAVE_ENET1ADDR
-#endif /* TARGET_HOOTFOOT */
-	unsigned short	bi_ethspeed;	/* Ethernet speed in Mbps */
-	unsigned long	bi_intfreq;	/* Internal Freq, in MHz */
-	unsigned long	bi_busfreq;	/* Bus Freq, in MHz */
-#if defined(TARGET_CPM2)
-	unsigned long	bi_cpmfreq;	/* CPM_CLK Freq, in MHz */
-	unsigned long	bi_brgfreq;	/* BRG_CLK Freq, in MHz */
-	unsigned long	bi_sccfreq;	/* SCC_CLK Freq, in MHz */
-	unsigned long	bi_vco;		/* VCO Out from PLL, in MHz */
-#endif
-#if defined(TARGET_PPC_MPC52xx)
-	unsigned long   bi_ipbfreq;     /* IPB Bus Freq, in MHz */
-	unsigned long   bi_pcifreq;     /* PCI Bus Freq, in MHz */
-#endif
-	unsigned long	bi_baudrate;	/* Console Baudrate */
-#if defined(TARGET_4xx)
-	unsigned char	bi_s_version[4];	/* Version of this structure */
-	unsigned char	bi_r_version[32];	/* Version of the ROM (IBM) */
-	unsigned int	bi_procfreq;	/* CPU (Internal) Freq, in Hz */
-	unsigned int	bi_plb_busfreq;	/* PLB Bus speed, in Hz */
-	unsigned int	bi_pci_busfreq;	/* PCI Bus speed, in Hz */
-	unsigned char	bi_pci_enetaddr[6];	/* PCI Ethernet MAC address */
-#endif
-#if defined(TARGET_HOTFOOT)
-	unsigned int     bi_pllouta_freq;       /* PLL OUTA speed, in Hz */
-#endif
-#if defined(TARGET_HYMOD)
-	hymod_conf_t	bi_hymod_conf;	/* hymod configuration information */
-#endif
-#if defined(TARGET_EVB64260) || defined(TARGET_405EP) || defined(TARGET_44x) || \
-	defined(TARGET_85xx) ||	defined(TARGET_83xx) || defined(TARGET_HAS_ETH1)
-	/* second onboard ethernet port */
-	unsigned char	bi_enet1addr[6];
-#define HAVE_ENET1ADDR
-#endif
-#if defined(TARGET_EVB64260) || defined(TARGET_440GX) || \
-    defined(TARGET_85xx) || defined(TARGET_HAS_ETH2)
-	/* third onboard ethernet ports */
-	unsigned char	bi_enet2addr[6];
-#define HAVE_ENET2ADDR
-#endif
-#if defined(TARGET_440GX) || defined(TARGET_HAS_ETH3)
-	/* fourth onboard ethernet ports */
-	unsigned char	bi_enet3addr[6];
-#define HAVE_ENET3ADDR
-#endif
-#if defined(TARGET_HOTFOOT)
-        int             bi_phynum[2];           /* Determines phy mapping */
-        int             bi_phymode[2];          /* Determines phy mode */
-#endif
-#if defined(TARGET_4xx)
-	unsigned int	bi_opbfreq;		/* OB clock in Hz */
-	int		bi_iic_fast[2];		/* Use fast i2c mode */
-#endif
-#if defined(TARGET_440GX)
-	int		bi_phynum[4];		/* phy mapping */
-	int		bi_phymode[4];		/* phy mode */
-#endif
-} bd_t;
-
-#define bi_tbfreq	bi_intfreq
-
-#endif	/* __PPCBOOT_H__ */
diff --git a/arch/powerpc/boot/ppcboot.h b/arch/powerpc/boot/ppcboot.h
index a78b0b257698..90c8f452fe6e 100644
--- a/arch/powerpc/boot/ppcboot.h
+++ b/arch/powerpc/boot/ppcboot.h
@@ -63,7 +63,7 @@ typedef struct bd_info {
 #if defined(TARGET_HYMOD)
 	hymod_conf_t	bi_hymod_conf;	/* hymod configuration information */
 #endif
-#if defined(TARGET_EVB64260) || defined(TARGET_405EP) || defined(TARGET_44x) || \
+#if defined(TARGET_EVB64260) || defined(TARGET_44x) || \
 	defined(TARGET_85xx) ||	defined(TARGET_83xx) || defined(TARGET_HAS_ETH1)
 	/* second onboard ethernet port */
 	unsigned char	bi_enet1addr[6];
diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c
index f157717ae814..89ff46b8b225 100644
--- a/arch/powerpc/boot/ps3.c
+++ b/arch/powerpc/boot/ps3.c
@@ -25,7 +25,7 @@ BSS_STACK(4096);
 
 /* A buffer that may be edited by tools operating on a zImage binary so as to
  * edit the command line passed to vmlinux (by setting /chosen/bootargs).
- * The buffer is put in it's own section so that tools may locate it easier.
+ * The buffer is put in its own section so that tools may locate it easier.
  */
 
 static char cmdline[BOOT_COMMAND_LINE_SIZE]
diff --git a/arch/powerpc/boot/rs6000.h b/arch/powerpc/boot/rs6000.h
index a9d879155ef9..16df8f3c43f1 100644
--- a/arch/powerpc/boot/rs6000.h
+++ b/arch/powerpc/boot/rs6000.h
@@ -1,11 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* IBM RS/6000 "XCOFF" file definitions for BFD.
    Copyright (C) 1990, 1991 Free Software Foundation, Inc.
-   FIXME: Can someone provide a transliteration of this name into ASCII?
-   Using the following chars caused a compiler warning on HIUX (so I replaced
-   them with octal escapes), and isn't useful without an understanding of what
-   character set it is.
-   Written by Mimi Ph\373\364ng-Th\345o V\365 of IBM
+   Written by Mimi Phuong-Thao Vo of IBM
    and John Gilmore of Cygnus Support.  */
 
 /********************** FILE HEADER **********************/
diff --git a/arch/powerpc/boot/simple_alloc.c b/arch/powerpc/boot/simple_alloc.c
index 267d6524caac..d07796fdf91a 100644
--- a/arch/powerpc/boot/simple_alloc.c
+++ b/arch/powerpc/boot/simple_alloc.c
@@ -112,8 +112,11 @@ static void *simple_realloc(void *ptr, unsigned long size)
 		return ptr;
 
 	new = simple_malloc(size);
-	memcpy(new, ptr, p->size);
-	simple_free(ptr);
+	if (new) {
+		memcpy(new, ptr, p->size);
+		simple_free(ptr);
+	}
+
 	return new;
 }
 
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 352d7de24018..1efd1206fcab 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -21,7 +21,7 @@
 #		(default ./arch/powerpc/boot)
 # -W dir	specify working directory for temporary files (default .)
 # -z		use gzip (legacy)
-# -Z zsuffix    compression to use (gz, xz or none)
+# -Z zsuffix    compression to use (gz, xz, lzma, lzo or none)
 
 # Stop execution if any command fails
 set -e
@@ -69,7 +69,7 @@ usage() {
     echo 'Usage: wrapper [-o output] [-p platform] [-i initrd]' >&2
     echo '       [-d devtree] [-s tree.dts] [-e esm_blob]' >&2
     echo '       [-c] [-C cross-prefix] [-D datadir] [-W workingdir]' >&2
-    echo '       [-Z (gz|xz|none)] [--no-compression] [vmlinux]' >&2
+    echo '       [-Z (gz|xz|lzma|lzo|none)] [--no-compression] [vmlinux]' >&2
     exit 1
 }
 
@@ -226,18 +226,12 @@ ld_is_lld()
 
 # Do not include PT_INTERP segment when linking pie. Non-pie linking
 # just ignores this option.
-LD_VERSION=$(${CROSS}ld --version | ld_version)
-LD_NO_DL_MIN_VERSION=$(echo 2.26 | ld_version)
-if [ "$LD_VERSION" -ge "$LD_NO_DL_MIN_VERSION" ] ; then
-	nodl="--no-dynamic-linker"
-fi
+nodl="--no-dynamic-linker"
 
 # suppress some warnings in recent ld versions
 nowarn="-z noexecstack"
-if ! ld_is_lld; then
-	if [ "$LD_VERSION" -ge "$(echo 2.39 | ld_version)" ]; then
-		nowarn="$nowarn --no-warn-rwx-segments"
-	fi
+if "${CROSS}ld" -v --no-warn-rwx-segments >/dev/null 2>&1; then
+	nowarn="$nowarn --no-warn-rwx-segments"
 fi
 
 platformo=$object/"$platform".o
@@ -271,11 +265,6 @@ pseries)
     fi
     make_space=n
     ;;
-maple)
-    platformo="$object/of.o $object/epapr.o"
-    link_address='0x400000'
-    make_space=n
-    ;;
 pmac|chrp)
     platformo="$object/of.o $object/epapr.o"
     make_space=n
@@ -337,7 +326,7 @@ ps3)
     make_space=n
     pie=
     ;;
-ep88xc|ep405|ep8248e)
+ep88xc|ep8248e)
     platformo="$object/fixed-head.o $object/$platform.o"
     binary=y
     ;;
@@ -468,26 +457,6 @@ uboot)
     fi
     exit 0
     ;;
-uboot-obs600)
-    rm -f "$ofile"
-    # obs600 wants a multi image with an initrd, so we need to put a fake
-    # one in even when building a "normal" image.
-    if [ -n "$initrd" ]; then
-	real_rd="$initrd"
-    else
-	real_rd=`mktemp`
-	echo "\0" >>"$real_rd"
-    fi
-    ${MKIMAGE} -A ppc -O linux -T multi -C gzip -a $membase -e $membase \
-	$uboot_version -d "$vmz":"$real_rd":"$dtb" "$ofile"
-    if [ -z "$initrd" ]; then
-	rm -f "$real_rd"
-    fi
-    if [ -z "$cacheit" ]; then
-	rm -f "$vmz"
-    fi
-    exit 0
-    ;;
 esac
 
 addsec() {
@@ -537,7 +506,7 @@ fi
 
 # post-processing needed for some platforms
 case "$platform" in
-pseries|chrp|maple)
+pseries|chrp)
     $objbin/addnote "$ofile"
     ;;
 coff)
diff --git a/arch/powerpc/boot/xz_config.h b/arch/powerpc/boot/xz_config.h
index ebfadd39e192..9506a96ebbcc 100644
--- a/arch/powerpc/boot/xz_config.h
+++ b/arch/powerpc/boot/xz_config.h
@@ -50,11 +50,8 @@ static inline void put_unaligned_be32(u32 val, void *p)
 /* prevent the inclusion of the xz-preboot MM headers */
 #define DECOMPR_MM_H
 #define memmove memmove
-#define XZ_EXTERN static
 
 /* xz.h needs to be included directly since we need enum xz_mode */
 #include "../../../include/linux/xz.h"
 
-#undef XZ_EXTERN
-
 #endif
diff --git a/arch/powerpc/configs/40x/acadia_defconfig b/arch/powerpc/configs/40x/acadia_defconfig
deleted file mode 100644
index 25eed86ec528..000000000000
--- a/arch/powerpc/configs/40x/acadia_defconfig
+++ /dev/null
@@ -1,61 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_ACADIA=y
-CONFIG_PCI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-CONFIG_IBM_EMAC_RXB=256
-CONFIG_IBM_EMAC_TXB=256
-CONFIG_IBM_EMAC_DEBUG=y
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_THERMAL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig
deleted file mode 100644
index 3549c9e950e8..000000000000
--- a/arch/powerpc/configs/40x/kilauea_defconfig
+++ /dev/null
@@ -1,69 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_KILAUEA=y
-CONFIG_PCI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_RAW_NAND=y
-CONFIG_MTD_NAND_NDFC=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-CONFIG_IBM_EMAC_RXB=256
-CONFIG_IBM_EMAC_TXB=256
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_IBM_IIC=y
-CONFIG_SENSORS_LM75=y
-CONFIG_THERMAL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1307=y
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/40x/klondike_defconfig b/arch/powerpc/configs/40x/klondike_defconfig
deleted file mode 100644
index 6a735ee75715..000000000000
--- a/arch/powerpc/configs/40x/klondike_defconfig
+++ /dev/null
@@ -1,44 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EMBEDDED=y
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_APM8018X=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_MATH_EMULATION=y
-# CONFIG_SUSPEND is not set
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_SAS_ATTRS=y
-# 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_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-# CONFIG_USB_SUPPORT is not set
-# CONFIG_IOMMU_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT4_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-CONFIG_MAGIC_SYSRQ=y
-# CONFIG_SCHED_DEBUG is not set
-# CONFIG_DEBUG_BUGVERBOSE is not set
-# CONFIG_FTRACE is not set
diff --git a/arch/powerpc/configs/40x/makalu_defconfig b/arch/powerpc/configs/40x/makalu_defconfig
deleted file mode 100644
index 4563f88acf0c..000000000000
--- a/arch/powerpc/configs/40x/makalu_defconfig
+++ /dev/null
@@ -1,59 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_MAKALU=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-CONFIG_IBM_EMAC_RXB=256
-CONFIG_IBM_EMAC_TXB=256
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_THERMAL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/40x/obs600_defconfig b/arch/powerpc/configs/40x/obs600_defconfig
deleted file mode 100644
index 2a2bb3f46847..000000000000
--- a/arch/powerpc/configs/40x/obs600_defconfig
+++ /dev/null
@@ -1,69 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_OBS600=y
-CONFIG_MATH_EMULATION=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_RAW_NAND=y
-CONFIG_MTD_NAND_NDFC=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-CONFIG_IBM_EMAC_RXB=256
-CONFIG_IBM_EMAC_TXB=256
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_IBM_IIC=y
-CONFIG_SENSORS_LM75=y
-CONFIG_THERMAL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1307=y
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/40x/walnut_defconfig b/arch/powerpc/configs/40x/walnut_defconfig
deleted file mode 100644
index 9eaaf1a1d2c6..000000000000
--- a/arch/powerpc/configs/40x/walnut_defconfig
+++ /dev/null
@@ -1,55 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_THERMAL=y
-CONFIG_EXT2_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/44x.config b/arch/powerpc/configs/44x.config
new file mode 100644
index 000000000000..79b7b1962995
--- /dev/null
+++ b/arch/powerpc/configs/44x.config
@@ -0,0 +1,2 @@
+CONFIG_PPC64=n
+CONFIG_44x=y
diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig
index fde4824f235e..02e88648a2e6 100644
--- a/arch/powerpc/configs/44x/akebono_defconfig
+++ b/arch/powerpc/configs/44x/akebono_defconfig
@@ -85,7 +85,6 @@ CONFIG_IBM_EMAC=y
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
 CONFIG_SERIAL_8250=y
-# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y
@@ -128,6 +127,5 @@ CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW=0x00010000
 CONFIG_PPC_EARLY_DEBUG_44x_PHYSHIGH=0x33f
 CONFIG_CRYPTO_PCBC=y
 CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_SHA1_PPC=y
 CONFIG_CRYPTO_DES=y
 # CONFIG_CRYPTO_HW is not set
diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig
index 3fdfbb29b854..5492537f4c6c 100644
--- a/arch/powerpc/configs/44x/fsp2_defconfig
+++ b/arch/powerpc/configs/44x/fsp2_defconfig
@@ -15,7 +15,7 @@ CONFIG_BLK_DEV_INITRD=y
 # CONFIG_RD_LZ4 is not set
 CONFIG_KALLSYMS_ALL=y
 CONFIG_BPF_SYSCALL=y
-CONFIG_EMBEDDED=y
+CONFIG_EXPERT=y
 CONFIG_PROFILING=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig
index ef09786d49b9..98221bda380d 100644
--- a/arch/powerpc/configs/44x/sam440ep_defconfig
+++ b/arch/powerpc/configs/44x/sam440ep_defconfig
@@ -78,8 +78,7 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS=y
-CONFIG_AUTOFS4_FS=y
+CONFIG_AUTOFS_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_ZISOFS=y
@@ -92,5 +91,4 @@ CONFIG_AFFS_FS=m
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig
index 20891c413149..5757625469c4 100644
--- a/arch/powerpc/configs/44x/warp_defconfig
+++ b/arch/powerpc/configs/44x/warp_defconfig
@@ -85,8 +85,6 @@ CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_15=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_FS=y
diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig
index 789622ffd844..88fbe0d42e11 100644
--- a/arch/powerpc/configs/52xx/pcm030_defconfig
+++ b/arch/powerpc/configs/52xx/pcm030_defconfig
@@ -10,7 +10,6 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
 # CONFIG_VM_EVENT_COUNTERS is not set
-CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/powerpc/configs/52xx/tqm5200_defconfig b/arch/powerpc/configs/52xx/tqm5200_defconfig
index e6735b945327..688f703d8e22 100644
--- a/arch/powerpc/configs/52xx/tqm5200_defconfig
+++ b/arch/powerpc/configs/52xx/tqm5200_defconfig
@@ -3,7 +3,7 @@ CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_KALLSYMS is not set
 # CONFIG_EPOLL is not set
-CONFIG_EMBEDDED=y
+CONFIG_EXPERT=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
diff --git a/arch/powerpc/configs/83xx/kmeter1_defconfig b/arch/powerpc/configs/83xx/kmeter1_defconfig
index 24bf1bde1bb4..487e5e1bbf4c 100644
--- a/arch/powerpc/configs/83xx/kmeter1_defconfig
+++ b/arch/powerpc/configs/83xx/kmeter1_defconfig
@@ -5,7 +5,6 @@ CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
-CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
index 1715ff547442..b99caba8724a 100644
--- a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
@@ -73,6 +73,5 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_932=y
 CONFIG_NLS_ISO8859_8=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
index e65c0057147f..11163052fdba 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
@@ -80,5 +80,4 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
index 17714bf0ed40..312d39e4242c 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
@@ -72,5 +72,4 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
index 4e3373381ab6..ac27f99faab8 100644
--- a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
@@ -2,7 +2,6 @@ CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
-CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -76,6 +75,5 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/85xx-32bit.config b/arch/powerpc/configs/85xx-32bit.config
index 6b8894d727a2..a85310bcb1fd 100644
--- a/arch/powerpc/configs/85xx-32bit.config
+++ b/arch/powerpc/configs/85xx-32bit.config
@@ -1,3 +1,4 @@
+CONFIG_PPC64=n
 CONFIG_HIGHMEM=y
 CONFIG_KEXEC=y
 CONFIG_PPC_85xx=y
diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config
index 524db76f47b7..8aff83217397 100644
--- a/arch/powerpc/configs/85xx-hw.config
+++ b/arch/powerpc/configs/85xx-hw.config
@@ -24,6 +24,7 @@ CONFIG_FS_ENET=y
 CONFIG_FSL_CORENET_CF=y
 CONFIG_FSL_DMA=y
 CONFIG_FSL_HV_MANAGER=y
+CONFIG_FSL_IFC=y
 CONFIG_FSL_PQ_MDIO=y
 CONFIG_FSL_RIO=y
 CONFIG_FSL_XGMAC_MDIO=y
@@ -58,6 +59,7 @@ CONFIG_INPUT_FF_MEMLESS=m
 CONFIG_MARVELL_PHY=y
 CONFIG_MDIO_BUS_MUX_GPIO=y
 CONFIG_MDIO_BUS_MUX_MMIOREG=y
+CONFIG_MEMORY=y
 CONFIG_MMC_SDHCI_OF_ESDHC=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI=y
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
index 6cb7e90d52c1..7beb36a41d45 100644
--- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -17,7 +17,6 @@ CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_PERF_EVENTS=y
-CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -222,9 +221,6 @@ CONFIG_NLS_ISO8859_15=y
 CONFIG_NLS_KOI8_R=m
 CONFIG_NLS_KOI8_U=m
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
-CONFIG_LIBCRC32C=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_CRYPTO_CBC=y
 CONFIG_CRYPTO_MD5=y
diff --git a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig b/arch/powerpc/configs/85xx/mpc8540_ads_defconfig
deleted file mode 100644
index 618e03e0706d..000000000000
--- a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig
+++ /dev/null
@@ -1,47 +0,0 @@
-CONFIG_PPC_85xx=y
-CONFIG_SYSVIPC=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-# CONFIG_MSDOS_PARTITION is not set
-CONFIG_MPC8540_ADS=y
-CONFIG_GEN_RTC=y
-CONFIG_BINFMT_MISC=y
-CONFIG_MATH_EMULATION=y
-# CONFIG_SECCOMP is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_SYN_COOKIES=y
-# CONFIG_IPV6 is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_NETDEVICES=y
-CONFIG_GIANFAR=y
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT4_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig b/arch/powerpc/configs/85xx/mpc8560_ads_defconfig
deleted file mode 100644
index 9bc6283f2fb2..000000000000
--- a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig
+++ /dev/null
@@ -1,50 +0,0 @@
-CONFIG_PPC_85xx=y
-CONFIG_SYSVIPC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-# CONFIG_MSDOS_PARTITION is not set
-CONFIG_MPC8560_ADS=y
-CONFIG_GEN_RTC=y
-CONFIG_BINFMT_MISC=y
-CONFIG_MATH_EMULATION=y
-# CONFIG_SECCOMP is not set
-CONFIG_PCI=y
-CONFIG_PCI_DEBUG=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_SYN_COOKIES=y
-# CONFIG_IPV6 is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_NETDEVICES=y
-CONFIG_FS_ENET=y
-# CONFIG_FS_ENET_HAS_SCC is not set
-CONFIG_GIANFAR=y
-CONFIG_E1000=y
-CONFIG_DAVICOM_PHY=y
-CONFIG_MARVELL_PHY=y
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_CPM=y
-CONFIG_SERIAL_CPM_CONSOLE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT4_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig
deleted file mode 100644
index cea72e85ed26..000000000000
--- a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig
+++ /dev/null
@@ -1,52 +0,0 @@
-CONFIG_PPC_85xx=y
-CONFIG_SYSVIPC=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-# CONFIG_MSDOS_PARTITION is not set
-CONFIG_MPC85xx_CDS=y
-CONFIG_GEN_RTC=y
-CONFIG_BINFMT_MISC=y
-CONFIG_MATH_EMULATION=y
-# CONFIG_SECCOMP is not set
-CONFIG_PCI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_SYN_COOKIES=y
-# CONFIG_IPV6 is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_ATA=y
-CONFIG_ATA_GENERIC=y
-CONFIG_PATA_VIA=y
-CONFIG_NETDEVICES=y
-CONFIG_GIANFAR=y
-CONFIG_E1000=y
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT4_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/85xx/stx_gp3_defconfig b/arch/powerpc/configs/85xx/stx_gp3_defconfig
index ecbcc853307d..0a42072fa23c 100644
--- a/arch/powerpc/configs/85xx/stx_gp3_defconfig
+++ b/arch/powerpc/configs/85xx/stx_gp3_defconfig
@@ -50,7 +50,7 @@ CONFIG_DRM=m
 CONFIG_SOUND=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-CONFIG_AUTOFS4_FS=y
+CONFIG_AUTOFS_FS=y
 CONFIG_ISO9660_FS=m
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
@@ -60,8 +60,6 @@ CONFIG_CRAMFS=m
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
 CONFIG_NLS=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=m
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_BDI_SWITCH=y
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index 3a6381aa9fdc..488d03ae6d6c 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -132,7 +132,6 @@ CONFIG_ROOT_NFS=y
 CONFIG_NFSD=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_T10DIF=y
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_CRYPTO_HMAC=y
diff --git a/arch/powerpc/configs/86xx-hw.config b/arch/powerpc/configs/86xx-hw.config
index 0cb24b33c88e..e7bd265fae5a 100644
--- a/arch/powerpc/configs/86xx-hw.config
+++ b/arch/powerpc/configs/86xx-hw.config
@@ -5,7 +5,6 @@ CONFIG_BROADCOM_PHY=y
 # CONFIG_CARDBUS is not set
 CONFIG_CHR_DEV_SG=y
 CONFIG_CHR_DEV_ST=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_HMAC=y
 CONFIG_DS1682=y
 CONFIG_EEPROM_LEGACY=y
diff --git a/arch/powerpc/configs/8xx.config b/arch/powerpc/configs/8xx.config
new file mode 100644
index 000000000000..7eb3ffbbd667
--- /dev/null
+++ b/arch/powerpc/configs/8xx.config
@@ -0,0 +1,2 @@
+CONFIG_PPC64=n
+CONFIG_PPC_8xx=y
diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig
index 7f35d5bc1229..3c6445c98a85 100644
--- a/arch/powerpc/configs/adder875_defconfig
+++ b/arch/powerpc/configs/adder875_defconfig
@@ -4,7 +4,7 @@ CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
 # CONFIG_FUTEX is not set
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_BLK_DEV_BSG is not set
@@ -44,7 +44,6 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC32_SLICEBY4=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig
index 200bb1ecb560..69ef3dc31c4b 100644
--- a/arch/powerpc/configs/amigaone_defconfig
+++ b/arch/powerpc/configs/amigaone_defconfig
@@ -106,7 +106,6 @@ CONFIG_TMPFS=y
 CONFIG_AFFS_FS=m
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 06391cc2af3a..7a31b52e92e1 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -25,7 +25,6 @@ CONFIG_PS3_DISK=y
 CONFIG_PS3_ROM=m
 CONFIG_PS3_FLASH=m
 CONFIG_PS3_LPM=m
-CONFIG_PPC_IBM_CELL_BLADE=y
 CONFIG_RTAS_FLASH=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
@@ -63,7 +62,6 @@ CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
@@ -133,7 +131,6 @@ CONFIG_SKGE=m
 CONFIG_SKY2=m
 CONFIG_GELIC_NET=m
 CONFIG_GELIC_WIRELESS=y
-CONFIG_SPIDER_NET=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO_I8042 is not set
@@ -168,11 +165,10 @@ CONFIG_INFINIBAND_MTHCA=m
 CONFIG_INFINIBAND_IPOIB=m
 CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
 CONFIG_EDAC=y
-CONFIG_EDAC_CELL=y
 CONFIG_UIO=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
 CONFIG_UDF_FS=m
diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig
index fb314f75ad4b..b799c95480ae 100644
--- a/arch/powerpc/configs/chrp32_defconfig
+++ b/arch/powerpc/configs/chrp32_defconfig
@@ -110,7 +110,6 @@ CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/debug.config b/arch/powerpc/configs/debug.config
index a14ae1f20d60..bcc1fcf25e10 100644
--- a/arch/powerpc/configs/debug.config
+++ b/arch/powerpc/configs/debug.config
@@ -1 +1,5 @@
+CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG=y
+CONFIG_PPC_IRQ_SOFT_MASK_DEBUG=y
+CONFIG_PPC_KUAP_DEBUG=y
+CONFIG_PPC_RFI_SRR_DEBUG=y
 CONFIG_SCOM_DEBUGFS=y
diff --git a/arch/powerpc/configs/disable-werror.config b/arch/powerpc/configs/disable-werror.config
index 6ea12a12432c..7776b91da37f 100644
--- a/arch/powerpc/configs/disable-werror.config
+++ b/arch/powerpc/configs/disable-werror.config
@@ -1 +1,2 @@
+# Help: Disable -Werror
 CONFIG_PPC_DISABLE_WERROR=y
diff --git a/arch/powerpc/configs/ep8248e_defconfig b/arch/powerpc/configs/ep8248e_defconfig
index 8df6d3a293e3..0d8d3f41f194 100644
--- a/arch/powerpc/configs/ep8248e_defconfig
+++ b/arch/powerpc/configs/ep8248e_defconfig
@@ -4,7 +4,6 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
 CONFIG_KALLSYMS_ALL=y
-CONFIG_SLAB=y
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_PPC_CHRP is not set
 # CONFIG_PPC_PMAC is not set
@@ -48,7 +47,7 @@ CONFIG_SERIAL_CPM_CONSOLE=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
-CONFIG_AUTOFS4_FS=y
+CONFIG_AUTOFS_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig
index a98ef6a4abef..354180ab94bc 100644
--- a/arch/powerpc/configs/ep88xc_defconfig
+++ b/arch/powerpc/configs/ep88xc_defconfig
@@ -6,7 +6,7 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
 # CONFIG_FUTEX is not set
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_BLK_DEV_BSG is not set
@@ -47,7 +47,6 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC32_SLICEBY4=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
index 3009b0efaf34..2f81bc2d819e 100644
--- a/arch/powerpc/configs/fsl-emb-nonhw.config
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -15,7 +15,6 @@ CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_CGROUPS=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_CPUSETS=y
 CONFIG_CRAMFS=y
 CONFIG_CRYPTO_MD4=y
@@ -112,7 +111,6 @@ CONFIG_QNX4FS_FS=m
 CONFIG_RCU_TRACE=y
 CONFIG_RESET_CONTROLLER=y
 CONFIG_ROOT_NFS=y
-CONFIG_SYSV_FS=m
 CONFIG_SYSVIPC=y
 CONFIG_TMPFS=y
 CONFIG_UBIFS_FS=y
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 71d9d112c0b6..428f17b45513 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -202,10 +202,6 @@ CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
-CONFIG_REISERFS_FS=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_POSIX_ACL=y
 CONFIG_FS_DAX=y
@@ -235,12 +231,11 @@ CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_15=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
 CONFIG_BOOTX_TEXT=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig
index 91a1b99f4e8f..cdd99657b71b 100644
--- a/arch/powerpc/configs/gamecube_defconfig
+++ b/arch/powerpc/configs/gamecube_defconfig
@@ -8,7 +8,6 @@ CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
-CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -83,7 +82,6 @@ CONFIG_ROOT_NFS=y
 CONFIG_CIFS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_SPINLOCK=y
 CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/powerpc/configs/hardening.config b/arch/powerpc/configs/hardening.config
new file mode 100644
index 000000000000..4e9bba327e8f
--- /dev/null
+++ b/arch/powerpc/configs/hardening.config
@@ -0,0 +1,10 @@
+# PowerPC specific hardening options
+
+# Block kernel from unexpectedly reading userspace memory.
+CONFIG_PPC_KUAP=y
+
+# Attack surface reduction.
+# CONFIG_SCOM_DEBUGFS is not set
+
+# Disable internal kernel debugger.
+# CONFIG_XMON is not set
diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig
index fa707de761be..b564f9e33a0d 100644
--- a/arch/powerpc/configs/linkstation_defconfig
+++ b/arch/powerpc/configs/linkstation_defconfig
@@ -125,8 +125,6 @@ CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_CODEPAGE_932=m
 CONFIG_NLS_ISO8859_1=m
 CONFIG_NLS_UTF8=m
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig
deleted file mode 100644
index c821a97f4a89..000000000000
--- a/arch/powerpc/configs/maple_defconfig
+++ /dev/null
@@ -1,111 +0,0 @@
-CONFIG_PPC64=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=4
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_KPROBES=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
-# CONFIG_PPC_POWERNV is not set
-# CONFIG_PPC_PSERIES is not set
-# CONFIG_PPC_PMAC is not set
-CONFIG_PPC_MAPLE=y
-CONFIG_UDBG_RTAS_CONSOLE=y
-CONFIG_GEN_RTC=y
-CONFIG_KEXEC=y
-CONFIG_IRQ_ALL_CPUS=y
-CONFIG_PPC_4K_PAGES=y
-CONFIG_PCI_MSI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_IPV6 is not set
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=8192
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_IPR=y
-CONFIG_ATA=y
-CONFIG_PATA_AMD=y
-CONFIG_ATA_GENERIC=y
-CONFIG_NETDEVICES=y
-CONFIG_AMD8111_ETH=y
-CONFIG_TIGON3=y
-CONFIG_E1000=y
-CONFIG_USB_PEGASUS=y
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_HVC_RTAS=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_AMD8111=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_HID_GYRATION=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_USB=y
-CONFIG_USB_MON=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_ROOT_HUB_TT=y
-# CONFIG_USB_EHCI_HCD_PPC_OF is not set
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_UHCI_HCD=y
-CONFIG_USB_SERIAL=y
-CONFIG_USB_SERIAL_GENERIC=y
-CONFIG_USB_SERIAL_CYPRESS_M8=m
-CONFIG_USB_SERIAL_GARMIN=m
-CONFIG_USB_SERIAL_IPW=m
-CONFIG_USB_SERIAL_KEYSPAN=y
-CONFIG_USB_SERIAL_TI=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT4_FS=y
-CONFIG_FS_DAX=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_HUGETLBFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_DEFAULT="utf-8"
-CONFIG_NLS_UTF8=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC_T10DIF=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_STACK_USAGE=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_XMON=y
-CONFIG_XMON_DEFAULT=y
-CONFIG_BOOTX_TEXT=y
-CONFIG_CRYPTO_ECB=m
-CONFIG_CRYPTO_PCBC=m
-# CONFIG_CRYPTO_HW is not set
-CONFIG_PRINTK_TIME=y
diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig
index 498d35db7833..f65001e7877f 100644
--- a/arch/powerpc/configs/mgcoge_defconfig
+++ b/arch/powerpc/configs/mgcoge_defconfig
@@ -9,8 +9,7 @@ CONFIG_BLK_DEV_INITRD=y
 # CONFIG_RD_GZIP is not set
 CONFIG_KALLSYMS_ALL=y
 # CONFIG_PCSPKR_PLATFORM is not set
-CONFIG_EMBEDDED=y
-CONFIG_SLAB=y
+CONFIG_EXPERT=y
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_82xx=y
@@ -61,7 +60,7 @@ CONFIG_USB_FSL_USB2=y
 CONFIG_USB_G_SERIAL=y
 CONFIG_UIO=y
 CONFIG_EXT2_FS=y
-CONFIG_AUTOFS4_FS=y
+CONFIG_AUTOFS_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/powerpc/configs/microwatt_defconfig b/arch/powerpc/configs/microwatt_defconfig
index 795a127908e7..d81989a6f59b 100644
--- a/arch/powerpc/configs/microwatt_defconfig
+++ b/arch/powerpc/configs/microwatt_defconfig
@@ -8,7 +8,7 @@ CONFIG_CGROUPS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_KALLSYMS_ALL=y
-CONFIG_EMBEDDED=y
+CONFIG_EXPERT=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
@@ -62,7 +62,6 @@ CONFIG_LITEX_LITEETH=y
 # CONFIG_VT is not set
 # CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_8250=y
-# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_NONSTANDARD=y
diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig
index 10fe061c5e6d..d24457bc5791 100644
--- a/arch/powerpc/configs/mpc512x_defconfig
+++ b/arch/powerpc/configs/mpc512x_defconfig
@@ -4,7 +4,6 @@ CONFIG_NO_HZ=y
 CONFIG_LOG_BUF_SHIFT=16
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_COMPAT_BRK is not set
-CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig
index 8779f03bced1..a815d9e5e3e8 100644
--- a/arch/powerpc/configs/mpc83xx_defconfig
+++ b/arch/powerpc/configs/mpc83xx_defconfig
@@ -2,7 +2,6 @@ CONFIG_SYSVIPC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
-CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -98,7 +97,6 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_SHA512=y
diff --git a/arch/powerpc/configs/mpc85xx_base.config b/arch/powerpc/configs/mpc85xx_base.config
index 85907b776908..a1e4d72ed39d 100644
--- a/arch/powerpc/configs/mpc85xx_base.config
+++ b/arch/powerpc/configs/mpc85xx_base.config
@@ -1,8 +1,5 @@
 CONFIG_MATH_EMULATION=y
 CONFIG_MPC8536_DS=y
-CONFIG_MPC8540_ADS=y
-CONFIG_MPC8560_ADS=y
-CONFIG_MPC85xx_CDS=y
 CONFIG_MPC85xx_DS=y
 CONFIG_MPC85xx_MDS=y
 CONFIG_MPC85xx_RDB=y
diff --git a/arch/powerpc/configs/mpc866_ads_defconfig b/arch/powerpc/configs/mpc866_ads_defconfig
index 5c56d36cdfc5..dfbdd5e8e108 100644
--- a/arch/powerpc/configs/mpc866_ads_defconfig
+++ b/arch/powerpc/configs/mpc866_ads_defconfig
@@ -6,7 +6,7 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
 # CONFIG_BUG is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
 # CONFIG_EPOLL is not set
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_BLK_DEV_BSG is not set
@@ -38,5 +38,3 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC_CCITT=y
-CONFIG_CRC32_SLICEBY4=y
diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig
index 56b876e418e9..9bc2758a6a9a 100644
--- a/arch/powerpc/configs/mpc885_ads_defconfig
+++ b/arch/powerpc/configs/mpc885_ads_defconfig
@@ -7,7 +7,7 @@ CONFIG_VIRT_CPU_ACCOUNTING_NATIVE=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
 # CONFIG_FUTEX is not set
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
@@ -70,7 +70,6 @@ CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
 CONFIG_CRYPTO=y
 CONFIG_CRYPTO_DEV_TALITOS=y
-CONFIG_CRC32_SLICEBY4=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
@@ -78,4 +77,4 @@ CONFIG_DEBUG_VM_PGTABLE=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_BDI_SWITCH=y
 CONFIG_PPC_EARLY_DEBUG=y
-CONFIG_GENERIC_PTDUMP=y
+CONFIG_PTDUMP_DEBUGFS=y
diff --git a/arch/powerpc/configs/mvme5100_defconfig b/arch/powerpc/configs/mvme5100_defconfig
index d1c7fd5bf34b..fa2b3b9c5945 100644
--- a/arch/powerpc/configs/mvme5100_defconfig
+++ b/arch/powerpc/configs/mvme5100_defconfig
@@ -107,8 +107,6 @@ CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_CODEPAGE_932=m
 CONFIG_NLS_ISO8859_1=m
 CONFIG_NLS_UTF8=m
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 96aa5355911f..8bbf51b38480 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -143,7 +143,7 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT4_FS=y
-CONFIG_AUTOFS4_FS=y
+CONFIG_AUTOFS_FS=y
 CONFIG_ISO9660_FS=y
 CONFIG_UDF_FS=y
 CONFIG_MSDOS_FS=y
@@ -159,7 +159,6 @@ CONFIG_NFSD=y
 CONFIG_NFSD_V4=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index 019163c2571e..ae45f70b29f0 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -87,7 +87,6 @@ CONFIG_IP_NF_RAW=m
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_IP_DCCP=m
 CONFIG_BT=m
 CONFIG_BT_RFCOMM=m
 CONFIG_BT_RFCOMM_TTY=y
@@ -138,7 +137,6 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_ZERO=m
 CONFIG_ADB=y
-CONFIG_ADB_CUDA=y
 CONFIG_ADB_PMU=y
 CONFIG_ADB_PMU_LED=y
 CONFIG_ADB_PMU_LED_DISK=y
@@ -176,10 +174,12 @@ CONFIG_MOUSE_APPLETOUCH=y
 # CONFIG_SERIO_I8042 is not set
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIAL_8250=m
-CONFIG_SERIAL_PMACZILOG=m
+CONFIG_SERIAL_PMACZILOG=y
 CONFIG_SERIAL_PMACZILOG_TTYS=y
+CONFIG_SERIAL_PMACZILOG_CONSOLE=y
 CONFIG_NVRAM=y
 CONFIG_I2C_CHARDEV=m
+CONFIG_POWER_RESET=y
 CONFIG_APM_POWER=y
 CONFIG_BATTERY_PMU=y
 CONFIG_HWMON=m
@@ -207,6 +207,7 @@ CONFIG_FB_ATY=y
 CONFIG_FB_ATY_CT=y
 CONFIG_FB_ATY_GX=y
 CONFIG_FB_3DFX=y
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
@@ -254,7 +255,7 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
@@ -274,7 +275,6 @@ CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index e02ab94a09bf..bd4685612de6 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -46,7 +46,7 @@ CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 CONFIG_CPU_IDLE=y
-CONFIG_HZ_100=y
+CONFIG_HZ_1000=y
 CONFIG_BINFMT_MISC=m
 CONFIG_PPC_TRANSACTIONAL_MEM=y
 CONFIG_PPC_UV=y
@@ -270,7 +270,7 @@ CONFIG_BTRFS_FS=m
 CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_NILFS2_FS=m
 CONFIG_FANOTIFY=y
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_OVERLAY_FS=m
 CONFIG_ISO9660_FS=y
@@ -317,14 +317,10 @@ CONFIG_CODE_PATCHING_SELFTEST=y
 CONFIG_FTR_FIXUP_SELFTEST=y
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_CRC32C_VPMSUM=m
-CONFIG_CRYPTO_CRCT10DIF_VPMSUM=m
-CONFIG_CRYPTO_MD5_PPC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_SHA1_PPC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
@@ -343,3 +339,4 @@ CONFIG_KVM_BOOK3S_64_HV=m
 CONFIG_VHOST_NET=m
 CONFIG_PRINTK_TIME=y
 CONFIG_PRINTK_CALLER=y
+CONFIG_KALLSYMS_ALL=y
diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig
deleted file mode 100644
index 7e48693775f4..000000000000
--- a/arch/powerpc/configs/ppc40x_defconfig
+++ /dev/null
@@ -1,74 +0,0 @@
-CONFIG_40x=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PPC4xx_GPIO=y
-CONFIG_ACADIA=y
-CONFIG_HOTFOOT=y
-CONFIG_KILAUEA=y
-CONFIG_MAKALU=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_UBI=m
-CONFIG_MTD_UBI_GLUEBI=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_IBM_EMAC=y
-# CONFIG_INPUT is not set
-CONFIG_SERIO=m
-# CONFIG_SERIO_I8042 is not set
-# CONFIG_SERIO_SERPORT is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_I2C_IBM_IIC=m
-# CONFIG_HWMON is not set
-CONFIG_THERMAL=y
-CONFIG_FB=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT4_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=m
-CONFIG_UBIFS_FS=m
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index 8b595f67068c..41c930f74ed4 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -90,7 +90,6 @@ CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
 CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_ISO8859_1=m
-CONFIG_CRC_T10DIF=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_CRYPTO_ECB=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 268fa361a06d..2d92c11eea7e 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -44,7 +44,6 @@ CONFIG_PPC_SMLPAR=y
 CONFIG_IBMEBUS=y
 CONFIG_PAPR_SCM=m
 CONFIG_PPC_SVM=y
-CONFIG_PPC_MAPLE=y
 CONFIG_PPC_PASEMI=y
 CONFIG_PPC_PASEMI_IOMMU=y
 CONFIG_PPC_PS3=y
@@ -52,14 +51,13 @@ CONFIG_PS3_DISK=m
 CONFIG_PS3_ROM=m
 CONFIG_PS3_FLASH=m
 CONFIG_PS3_LPM=m
-CONFIG_PPC_IBM_CELL_BLADE=y
 CONFIG_RTAS_FLASH=m
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 CONFIG_CPU_FREQ_PMAC64=y
-CONFIG_HZ_100=y
+CONFIG_HZ_1000=y
 CONFIG_PPC_TRANSACTIONAL_MEM=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
@@ -81,7 +79,6 @@ CONFIG_MODULE_SIG_SHA512=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_BINFMT_MISC=m
 CONFIG_ZSWAP=y
-CONFIG_Z3FOLD=y
 CONFIG_ZSMALLOC=y
 # CONFIG_SLAB_MERGE_DEFAULT is not set
 CONFIG_SLAB_FREELIST_RANDOM=y
@@ -92,6 +89,8 @@ CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_MEM_SOFT_DIRTY=y
+CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_ZONE_DEVICE=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -228,7 +227,6 @@ CONFIG_NETXEN_NIC=m
 CONFIG_SUNGEM=y
 CONFIG_GELIC_NET=m
 CONFIG_GELIC_WIRELESS=y
-CONFIG_SPIDER_NET=m
 CONFIG_BROADCOM_PHY=m
 CONFIG_MARVELL_PHY=y
 CONFIG_PPP=m
@@ -327,7 +325,7 @@ CONFIG_BTRFS_FS=m
 CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_NILFS2_FS=m
 CONFIG_FS_DAX=y
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_OVERLAY_FS=m
 CONFIG_ISO9660_FS=y
@@ -379,7 +377,7 @@ CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
 CONFIG_IMA_ARCH_POLICY=y
 CONFIG_IMA_APPRAISE_MODSIG=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_SERPENT=m
@@ -389,9 +387,7 @@ CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_LZO=m
-CONFIG_CRYPTO_CRC32C_VPMSUM=m
-CONFIG_CRYPTO_MD5_PPC=m
-CONFIG_CRYPTO_SHA1_PPC=m
+CONFIG_CRYPTO_AES_GCM_P10=m
 CONFIG_CRYPTO_DEV_NX=y
 CONFIG_CRYPTO_DEV_NX_ENCRYPT=m
 CONFIG_CRYPTO_DEV_VMX=y
@@ -468,3 +464,4 @@ CONFIG_TEST_MEMCAT_P=m
 CONFIG_TEST_MEMINIT=m
 CONFIG_TEST_FREE_PAGES=m
 CONFIG_MEMTEST=y
+CONFIG_KALLSYMS_ALL=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 776c32964e12..90247b2a0ab0 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -175,17 +175,13 @@ CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
-CONFIG_REISERFS_FS=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_JFS_FS=y
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_POSIX_ACL=y
 CONFIG_FS_DAX=y
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_ISO9660_FS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=y
@@ -211,7 +207,6 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
@@ -225,7 +220,7 @@ CONFIG_CODE_PATCHING_SELFTEST=y
 CONFIG_FTR_FIXUP_SELFTEST=y
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_CCM=m
 CONFIG_CRYPTO_GCM=m
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index f21170b8fa11..b082c1fae13c 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -12,7 +12,6 @@ CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_CGROUPS=y
 CONFIG_CGROUP_SCHED=y
-CONFIG_RT_GROUP_SCHED=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_USER_NS=y
@@ -183,7 +182,6 @@ CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -227,7 +225,6 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
-CONFIG_IP_DCCP=m
 CONFIG_TIPC=m
 CONFIG_ATM=m
 CONFIG_ATM_CLIP=m
@@ -255,7 +252,6 @@ CONFIG_NET_SCH_DSMARK=m
 CONFIG_NET_SCH_NETEM=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
 CONFIG_NET_CLS_U32=m
@@ -275,7 +271,6 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@@ -489,7 +484,6 @@ CONFIG_VIA_VELOCITY=m
 CONFIG_PCMCIA_XIRC2PS=m
 CONFIG_FDDI=y
 CONFIG_SKFP=m
-CONFIG_NET_SB1000=m
 CONFIG_BROADCOM_PHY=m
 CONFIG_CICADA_PHY=m
 CONFIG_DAVICOM_PHY=m
@@ -720,6 +714,7 @@ CONFIG_FB_TRIDENT=m
 CONFIG_FB_SM501=m
 CONFIG_FB_IBM_GXT4500=y
 CONFIG_LCD_PLATFORM=m
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_LOGO=y
@@ -955,11 +950,6 @@ CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 CONFIG_JBD2_DEBUG=y
-CONFIG_REISERFS_FS=m
-CONFIG_REISERFS_PROC_INFO=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
@@ -969,7 +959,7 @@ CONFIG_XFS_POSIX_ACL=y
 CONFIG_GFS2_FS=m
 CONFIG_FS_DAX=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
@@ -994,7 +984,6 @@ CONFIG_MINIX_FS=m
 CONFIG_OMFS_FS=m
 CONFIG_QNX4FS_FS=m
 CONFIG_ROMFS_FS=m
-CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=m
 CONFIG_NFS_V3_ACL=y
@@ -1083,7 +1072,7 @@ CONFIG_SECURITY_NETWORK_XFRM=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_DISABLE=y
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 52a8c5450ecb..0b48d2b776c4 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -3,7 +3,7 @@ CONFIG_POSIX_MQUEUE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-CONFIG_EMBEDDED=y
+CONFIG_EXPERT=y
 # CONFIG_PERF_EVENTS is not set
 CONFIG_PROFILING=y
 CONFIG_PPC64=y
@@ -33,7 +33,6 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=y
-CONFIG_SLAB=y
 # CONFIG_COMPAT_BRK is not set
 # CONFIG_SPARSEMEM_VMEMMAP is not set
 # CONFIG_COMPACTION is not set
@@ -130,7 +129,7 @@ CONFIG_EXT2_FS=m
 CONFIG_EXT4_FS=y
 CONFIG_QUOTA=y
 CONFIG_QFMT_V2=y
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_ISO9660_FS=m
 CONFIG_JOLIET=y
 CONFIG_UDF_FS=m
@@ -149,8 +148,6 @@ CONFIG_NLS_ISO8859_1=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_LZO=m
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/powerpc/configs/security.config b/arch/powerpc/configs/security.config
index 1c91a35c6a73..0d54e29e2cdf 100644
--- a/arch/powerpc/configs/security.config
+++ b/arch/powerpc/configs/security.config
@@ -1,3 +1,5 @@
+# Help: Common security options for PowerPC builds
+
 # This is the equivalent of booting with lockdown=integrity
 CONFIG_SECURITY=y
 CONFIG_SECURITYFS=y
@@ -12,4 +14,4 @@ CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y
 
 # UBSAN bounds checking is very cheap and good for hardening
 CONFIG_UBSAN=y
-# CONFIG_UBSAN_MISC is not set
\ No newline at end of file
+# CONFIG_UBSAN_MISC is not set
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 71cfb990a74f..2b71a6dc399e 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -78,7 +78,6 @@ CONFIG_VIRTIO_BLK=m
 CONFIG_BLK_DEV_NVME=m
 CONFIG_NVME_MULTIPATH=y
 CONFIG_EEPROM_AT24=m
-# CONFIG_CXL is not set
 # CONFIG_OCXL is not set
 CONFIG_BLK_DEV_SD=m
 CONFIG_BLK_DEV_SR=m
@@ -279,9 +278,6 @@ CONFIG_LOCK_DOWN_KERNEL_FORCE_INTEGRITY=y
 # CONFIG_INTEGRITY is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC16=y
-CONFIG_CRC_ITU_T=y
-CONFIG_LIBCRC32C=y
 # CONFIG_XZ_DEC_X86 is not set
 # CONFIG_XZ_DEC_IA64 is not set
 # CONFIG_XZ_DEC_ARM is not set
@@ -289,7 +285,6 @@ CONFIG_LIBCRC32C=y
 # CONFIG_XZ_DEC_SPARC is not set
 CONFIG_PRINTK_TIME=y
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_SLUB_DEBUG_ON=y
 CONFIG_SCHED_STACK_END_CHECK=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_PANIC_ON_OOPS=y
@@ -302,7 +297,6 @@ CONFIG_WQ_WATCHDOG=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_DEBUG_CREDENTIALS=y
 # CONFIG_FTRACE is not set
 CONFIG_XMON=y
 # CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig
index 7a978d396991..e415222bd839 100644
--- a/arch/powerpc/configs/storcenter_defconfig
+++ b/arch/powerpc/configs/storcenter_defconfig
@@ -75,4 +75,3 @@ CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig
index 083c2e57520a..425f10837a18 100644
--- a/arch/powerpc/configs/tqm8xx_defconfig
+++ b/arch/powerpc/configs/tqm8xx_defconfig
@@ -6,7 +6,7 @@ CONFIG_HIGH_RES_TIMERS=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
-# CONFIG_BASE_FULL is not set
+CONFIG_BASE_SMALL=y
 # CONFIG_FUTEX is not set
 # CONFIG_VM_EVENT_COUNTERS is not set
 CONFIG_MODULES=y
@@ -54,7 +54,6 @@ CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
-CONFIG_CRC32_SLICEBY4=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DETECT_HUNG_TASK=y
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index 0ab78c51455d..7c714a19221e 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -9,7 +9,6 @@ CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
-CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_PPC_CHRP is not set
@@ -115,7 +114,6 @@ CONFIG_ROOT_NFS=y
 CONFIG_CIFS=m
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=y
 CONFIG_PRINTK_TIME=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_SPINLOCK=y
diff --git a/arch/powerpc/crypto/.gitignore b/arch/powerpc/crypto/.gitignore
new file mode 100644
index 000000000000..e9fe73aac8b6
--- /dev/null
+++ b/arch/powerpc/crypto/.gitignore
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+aesp10-ppc.S
+aesp8-ppc.S
+ghashp10-ppc.S
+ghashp8-ppc.S
diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig
index 7113f9355165..662aed46f9c7 100644
--- a/arch/powerpc/crypto/Kconfig
+++ b/arch/powerpc/crypto/Kconfig
@@ -2,79 +2,9 @@
 
 menu "Accelerated Cryptographic Algorithms for CPU (powerpc)"
 
-config CRYPTO_CRC32C_VPMSUM
-	tristate "CRC32c"
-	depends on PPC64 && ALTIVEC
-	select CRYPTO_HASH
-	select CRC32
-	help
-	  CRC32c CRC algorithm with the iSCSI polynomial (RFC 3385 and RFC 3720)
-
-	  Architecture: powerpc64 using
-	  - AltiVec extensions
-
-	  Enable on POWER8 and newer processors for improved performance.
-
-config CRYPTO_CRCT10DIF_VPMSUM
-	tristate "CRC32T10DIF"
-	depends on PPC64 && ALTIVEC && CRC_T10DIF
-	select CRYPTO_HASH
-	help
-	  CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF)
-
-	  Architecture: powerpc64 using
-	  - AltiVec extensions
-
-	  Enable on POWER8 and newer processors for improved performance.
-
-config CRYPTO_VPMSUM_TESTER
-	tristate "CRC32c and CRC32T10DIF hardware acceleration tester"
-	depends on CRYPTO_CRCT10DIF_VPMSUM && CRYPTO_CRC32C_VPMSUM
-	help
-	  Stress test for CRC32c and CRCT10DIF algorithms implemented with
-	  powerpc64 AltiVec extensions (POWER8 vpmsum instructions).
-	  Unless you are testing these algorithms, you don't need this.
-
-config CRYPTO_MD5_PPC
-	tristate "Digests: MD5"
-	depends on PPC
-	select CRYPTO_HASH
-	help
-	  MD5 message digest algorithm (RFC1321)
-
-	  Architecture: powerpc
-
-config CRYPTO_SHA1_PPC
-	tristate "Hash functions: SHA-1"
-	depends on PPC
-	help
-	  SHA-1 secure hash algorithm (FIPS 180)
-
-	  Architecture: powerpc
-
-config CRYPTO_SHA1_PPC_SPE
-	tristate "Hash functions: SHA-1 (SPE)"
-	depends on PPC && SPE
-	help
-	  SHA-1 secure hash algorithm (FIPS 180)
-
-	  Architecture: powerpc using
-	  - SPE (Signal Processing Engine) extensions
-
-config CRYPTO_SHA256_PPC_SPE
-	tristate "Hash functions: SHA-224 and SHA-256 (SPE)"
-	depends on PPC && SPE
-	select CRYPTO_SHA256
-	select CRYPTO_HASH
-	help
-	  SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
-	  Architecture: powerpc using
-	  - SPE (Signal Processing Engine) extensions
-
 config CRYPTO_AES_PPC_SPE
 	tristate "Ciphers: AES, modes: ECB/CBC/CTR/XTS (SPE)"
-	depends on PPC && SPE
+	depends on SPE
 	select CRYPTO_SKCIPHER
 	help
 	  Block ciphers: AES cipher algorithms (FIPS-197)
@@ -96,11 +26,12 @@ config CRYPTO_AES_PPC_SPE
 
 config CRYPTO_AES_GCM_P10
 	tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)"
-	depends on PPC64 && CPU_LITTLE_ENDIAN
+	depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
 	select CRYPTO_LIB_AES
 	select CRYPTO_ALGAPI
 	select CRYPTO_AEAD
-	default m
+	select CRYPTO_SKCIPHER
+	select CRYPTO_SIMD
 	help
 	  AEAD cipher: AES cipher algorithms (FIPS-197)
 	  GCM (Galois/Counter Mode) authenticated encryption mode (NIST SP800-38D)
@@ -111,4 +42,24 @@ config CRYPTO_AES_GCM_P10
 	  Support for cryptographic acceleration instructions on Power10 or
 	  later CPU. This module supports stitched acceleration for AES/GCM.
 
+config CRYPTO_DEV_VMX
+        bool "Support for VMX cryptographic acceleration instructions"
+        depends on PPC64 && VSX
+        help
+          Support for VMX cryptographic acceleration instructions.
+
+config CRYPTO_DEV_VMX_ENCRYPT
+	tristate "Encryption acceleration support on P8 CPU"
+	depends on CRYPTO_DEV_VMX
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_CTR
+	select CRYPTO_GHASH
+	select CRYPTO_XTS
+	default m
+	help
+	  Support for VMX cryptographic acceleration instructions on Power8 CPU.
+	  This module supports acceleration for AES and GHASH in hardware. If you
+	  choose 'M' here, this module will be called vmx-crypto.
+
 endmenu
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 05c7486f42c5..5960e5300db7 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -6,31 +6,35 @@
 #
 
 obj-$(CONFIG_CRYPTO_AES_PPC_SPE) += aes-ppc-spe.o
-obj-$(CONFIG_CRYPTO_MD5_PPC) += md5-ppc.o
-obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
-obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
-obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
-obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o
-obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o
-obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o
 obj-$(CONFIG_CRYPTO_AES_GCM_P10) += aes-gcm-p10-crypto.o
+obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o
 
 aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
-md5-ppc-y := md5-asm.o md5-glue.o
-sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
-sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
-sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
-crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
-crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
-aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp8-ppc.o aesp8-ppc.o
+aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp10-ppc.o aesp10-ppc.o
+vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o
+
+ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
+override flavour := linux-ppc64le
+else
+ifdef CONFIG_PPC64_ELF_ABI_V2
+override flavour := linux-ppc64-elfv2
+else
+override flavour := linux-ppc64
+endif
+endif
 
 quiet_cmd_perl = PERL    $@
-      cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@
+      cmd_perl = $(PERL) $< $(flavour) > $@
+
+targets += aesp10-ppc.S ghashp10-ppc.S aesp8-ppc.S ghashp8-ppc.S
 
-targets += aesp8-ppc.S ghashp8-ppc.S
+$(obj)/aesp10-ppc.S $(obj)/ghashp10-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
+	$(call if_changed,perl)
 
 $(obj)/aesp8-ppc.S $(obj)/ghashp8-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE
 	$(call if_changed,perl)
 
+OBJECT_FILES_NON_STANDARD_aesp10-ppc.o := y
+OBJECT_FILES_NON_STANDARD_ghashp10-ppc.o := y
 OBJECT_FILES_NON_STANDARD_aesp8-ppc.o := y
 OBJECT_FILES_NON_STANDARD_ghashp8-ppc.o := y
diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c
index bd3475f5348d..85f4fd4b1bdc 100644
--- a/arch/powerpc/crypto/aes-gcm-p10-glue.c
+++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c
@@ -5,9 +5,10 @@
  * Copyright 2022- IBM Inc. All rights reserved
  */
 
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <asm/simd.h>
 #include <asm/switch_to.h>
+#include <crypto/gcm.h>
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <crypto/b128ops.h>
@@ -24,22 +25,24 @@
 
 #define	PPC_ALIGN		16
 #define GCM_IV_SIZE		12
+#define RFC4106_NONCE_SIZE	4
 
 MODULE_DESCRIPTION("PPC64le AES-GCM with Stitched implementation");
 MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_CRYPTO("aes");
 
-asmlinkage int aes_p8_set_encrypt_key(const u8 *userKey, const int bits,
-				      void *key);
-asmlinkage void aes_p8_encrypt(const u8 *in, u8 *out, const void *key);
-asmlinkage void aes_p10_gcm_encrypt(u8 *in, u8 *out, size_t len,
+asmlinkage int aes_p10_set_encrypt_key(const u8 *userKey, const int bits,
+				       void *key);
+asmlinkage void aes_p10_encrypt(const u8 *in, u8 *out, const void *key);
+asmlinkage void aes_p10_gcm_encrypt(const u8 *in, u8 *out, size_t len,
 				    void *rkey, u8 *iv, void *Xi);
-asmlinkage void aes_p10_gcm_decrypt(u8 *in, u8 *out, size_t len,
+asmlinkage void aes_p10_gcm_decrypt(const u8 *in, u8 *out, size_t len,
 				    void *rkey, u8 *iv, void *Xi);
-asmlinkage void gcm_init_htable(unsigned char htable[256], unsigned char Xi[16]);
-asmlinkage void gcm_ghash_p8(unsigned char *Xi, unsigned char *Htable,
-		unsigned char *aad, unsigned int alen);
+asmlinkage void gcm_init_htable(unsigned char htable[], unsigned char Xi[]);
+asmlinkage void gcm_ghash_p10(unsigned char *Xi, unsigned char *Htable,
+			      unsigned char *aad, unsigned int alen);
+asmlinkage void gcm_update(u8 *iv, void *Xi);
 
 struct aes_key {
 	u8 key[AES_MAX_KEYLENGTH];
@@ -52,6 +55,7 @@ struct gcm_ctx {
 	u8 aad_hash[16];
 	u64 aadLen;
 	u64 Plen;	/* offset 56 - used in aes_p10_gcm_{en/de}crypt */
+	u8 pblock[16];
 };
 struct Hash_ctx {
 	u8 H[16];	/* subkey */
@@ -60,17 +64,20 @@ struct Hash_ctx {
 
 struct p10_aes_gcm_ctx {
 	struct aes_key enc_key;
+	u8 nonce[RFC4106_NONCE_SIZE];
 };
 
 static void vsx_begin(void)
 {
 	preempt_disable();
+	pagefault_disable();
 	enable_kernel_vsx();
 }
 
 static void vsx_end(void)
 {
 	disable_kernel_vsx();
+	pagefault_enable();
 	preempt_enable();
 }
 
@@ -93,7 +100,7 @@ static void set_aad(struct gcm_ctx *gctx, struct Hash_ctx *hash,
 	gctx->aadLen = alen;
 	i = alen & ~0xf;
 	if (i) {
-		gcm_ghash_p8(nXi, hash->Htable+32, aad, i);
+		gcm_ghash_p10(nXi, hash->Htable+32, aad, i);
 		aad += i;
 		alen -= i;
 	}
@@ -102,7 +109,7 @@ static void set_aad(struct gcm_ctx *gctx, struct Hash_ctx *hash,
 			nXi[i] ^= aad[i];
 
 		memset(gctx->aad_hash, 0, 16);
-		gcm_ghash_p8(gctx->aad_hash, hash->Htable+32, nXi, 16);
+		gcm_ghash_p10(gctx->aad_hash, hash->Htable+32, nXi, 16);
 	} else {
 		memcpy(gctx->aad_hash, nXi, 16);
 	}
@@ -115,7 +122,7 @@ static void gcmp10_init(struct gcm_ctx *gctx, u8 *iv, unsigned char *rdkey,
 {
 	__be32 counter = cpu_to_be32(1);
 
-	aes_p8_encrypt(hash->H, hash->H, rdkey);
+	aes_p10_encrypt(hash->H, hash->H, rdkey);
 	set_subkey(hash->H);
 	gcm_init_htable(hash->Htable+32, hash->H);
 
@@ -126,7 +133,7 @@ static void gcmp10_init(struct gcm_ctx *gctx, u8 *iv, unsigned char *rdkey,
 	/*
 	 * Encrypt counter vector as iv tag and increment counter.
 	 */
-	aes_p8_encrypt(iv, gctx->ivtag, rdkey);
+	aes_p10_encrypt(iv, gctx->ivtag, rdkey);
 
 	counter = cpu_to_be32(2);
 	*((__be32 *)(iv+12)) = counter;
@@ -160,7 +167,7 @@ static void finish_tag(struct gcm_ctx *gctx, struct Hash_ctx *hash, int len)
 	/*
 	 * hash (AAD len and len)
 	 */
-	gcm_ghash_p8(hash->Htable, hash->Htable+32, aclen, 16);
+	gcm_ghash_p10(hash->Htable, hash->Htable+32, aclen, 16);
 
 	for (i = 0; i < 16; i++)
 		hash->Htable[i] ^= gctx->ivtag[i];
@@ -185,20 +192,21 @@ static int set_authsize(struct crypto_aead *tfm, unsigned int authsize)
 }
 
 static int p10_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key,
-			     unsigned int keylen)
+			      unsigned int keylen)
 {
 	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
 	struct p10_aes_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
 	int ret;
 
 	vsx_begin();
-	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	ret = aes_p10_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
 	vsx_end();
 
 	return ret ? -EINVAL : 0;
 }
 
-static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
+static int p10_aes_gcm_crypt(struct aead_request *req, u8 *riv,
+			     int assoclen, int enc)
 {
 	struct crypto_tfm *tfm = req->base.tfm;
 	struct p10_aes_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -206,11 +214,9 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
 	struct gcm_ctx *gctx = PTR_ALIGN((void *)databuf, PPC_ALIGN);
 	u8 hashbuf[sizeof(struct Hash_ctx) + PPC_ALIGN];
 	struct Hash_ctx *hash = PTR_ALIGN((void *)hashbuf, PPC_ALIGN);
-	struct scatter_walk assoc_sg_walk;
 	struct skcipher_walk walk;
 	u8 *assocmem = NULL;
 	u8 *assoc;
-	unsigned int assoclen = req->assoclen;
 	unsigned int cryptlen = req->cryptlen;
 	unsigned char ivbuf[AES_BLOCK_SIZE+PPC_ALIGN];
 	unsigned char *iv = PTR_ALIGN((void *)ivbuf, PPC_ALIGN);
@@ -218,16 +224,16 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
 	unsigned long auth_tag_len = crypto_aead_authsize(__crypto_aead_cast(tfm));
 	u8 otag[16];
 	int total_processed = 0;
+	int nbytes;
 
 	memset(databuf, 0, sizeof(databuf));
 	memset(hashbuf, 0, sizeof(hashbuf));
 	memset(ivbuf, 0, sizeof(ivbuf));
-	memcpy(iv, req->iv, GCM_IV_SIZE);
+	memcpy(iv, riv, GCM_IV_SIZE);
 
 	/* Linearize assoc, if not already linear */
 	if (req->src->length >= assoclen && req->src->length) {
-		scatterwalk_start(&assoc_sg_walk, req->src);
-		assoc = scatterwalk_map(&assoc_sg_walk);
+		assoc = sg_virt(req->src); /* ppc64 is !HIGHMEM */
 	} else {
 		gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 			      GFP_KERNEL : GFP_ATOMIC;
@@ -245,10 +251,7 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
 	gcmp10_init(gctx, iv, (unsigned char *) &ctx->enc_key, hash, assoc, assoclen);
 	vsx_end();
 
-	if (!assocmem)
-		scatterwalk_unmap(assoc);
-	else
-		kfree(assocmem);
+	kfree(assocmem);
 
 	if (enc)
 		ret = skcipher_walk_aead_encrypt(&walk, req, false);
@@ -257,19 +260,25 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
 	if (ret)
 		return ret;
 
-	while (walk.nbytes > 0 && ret == 0) {
+	while ((nbytes = walk.nbytes) > 0 && ret == 0) {
+		const u8 *src = walk.src.virt.addr;
+		u8 *dst = walk.dst.virt.addr;
+		u8 buf[AES_BLOCK_SIZE];
+
+		if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE))
+			src = dst = memcpy(buf, src, nbytes);
 
 		vsx_begin();
 		if (enc)
-			aes_p10_gcm_encrypt(walk.src.virt.addr,
-					    walk.dst.virt.addr,
-					    walk.nbytes,
+			aes_p10_gcm_encrypt(src, dst, nbytes,
 					    &ctx->enc_key, gctx->iv, hash->Htable);
 		else
-			aes_p10_gcm_decrypt(walk.src.virt.addr,
-					    walk.dst.virt.addr,
-					    walk.nbytes,
+			aes_p10_gcm_decrypt(src, dst, nbytes,
 					    &ctx->enc_key, gctx->iv, hash->Htable);
+
+		if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE))
+			memcpy(walk.dst.virt.addr, buf, nbytes);
+
 		vsx_end();
 
 		total_processed += walk.nbytes;
@@ -281,6 +290,7 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
 
 	/* Finalize hash */
 	vsx_begin();
+	gcm_update(gctx->iv, hash->Htable);
 	finish_tag(gctx, hash, total_processed);
 	vsx_end();
 
@@ -302,17 +312,63 @@ static int p10_aes_gcm_crypt(struct aead_request *req, int enc)
 	return 0;
 }
 
+static int rfc4106_setkey(struct crypto_aead *tfm, const u8 *inkey,
+			  unsigned int keylen)
+{
+	struct p10_aes_gcm_ctx *ctx = crypto_aead_ctx(tfm);
+	int err;
+
+	keylen -= RFC4106_NONCE_SIZE;
+	err = p10_aes_gcm_setkey(tfm, inkey, keylen);
+	if (err)
+		return err;
+
+	memcpy(ctx->nonce, inkey + keylen, RFC4106_NONCE_SIZE);
+	return 0;
+}
+
+static int rfc4106_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	return crypto_rfc4106_check_authsize(authsize);
+}
+
+static int rfc4106_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct p10_aes_gcm_ctx *ctx = crypto_aead_ctx(aead);
+	u8 iv[AES_BLOCK_SIZE];
+
+	memcpy(iv, ctx->nonce, RFC4106_NONCE_SIZE);
+	memcpy(iv + RFC4106_NONCE_SIZE, req->iv, GCM_RFC4106_IV_SIZE);
+
+	return crypto_ipsec_check_assoclen(req->assoclen) ?:
+	       p10_aes_gcm_crypt(req, iv, req->assoclen - GCM_RFC4106_IV_SIZE, 1);
+}
+
+static int rfc4106_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct p10_aes_gcm_ctx *ctx = crypto_aead_ctx(aead);
+	u8 iv[AES_BLOCK_SIZE];
+
+	memcpy(iv, ctx->nonce, RFC4106_NONCE_SIZE);
+	memcpy(iv + RFC4106_NONCE_SIZE, req->iv, GCM_RFC4106_IV_SIZE);
+
+	return crypto_ipsec_check_assoclen(req->assoclen) ?:
+	       p10_aes_gcm_crypt(req, iv, req->assoclen - GCM_RFC4106_IV_SIZE, 0);
+}
+
 static int p10_aes_gcm_encrypt(struct aead_request *req)
 {
-	return p10_aes_gcm_crypt(req, 1);
+	return p10_aes_gcm_crypt(req, req->iv, req->assoclen, 1);
 }
 
 static int p10_aes_gcm_decrypt(struct aead_request *req)
 {
-	return p10_aes_gcm_crypt(req, 0);
+	return p10_aes_gcm_crypt(req, req->iv, req->assoclen, 0);
 }
 
-static struct aead_alg gcm_aes_alg = {
+static struct aead_alg gcm_aes_algs[] = {{
 	.ivsize			= GCM_IV_SIZE,
 	.maxauthsize		= 16,
 
@@ -321,23 +377,57 @@ static struct aead_alg gcm_aes_alg = {
 	.encrypt		= p10_aes_gcm_encrypt,
 	.decrypt		= p10_aes_gcm_decrypt,
 
-	.base.cra_name		= "gcm(aes)",
-	.base.cra_driver_name	= "aes_gcm_p10",
+	.base.cra_name		= "__gcm(aes)",
+	.base.cra_driver_name	= "__aes_gcm_p10",
 	.base.cra_priority	= 2100,
 	.base.cra_blocksize	= 1,
-	.base.cra_ctxsize	= sizeof(struct p10_aes_gcm_ctx),
+	.base.cra_ctxsize	= sizeof(struct p10_aes_gcm_ctx)+
+				  4 * sizeof(u64[2]),
 	.base.cra_module	= THIS_MODULE,
-};
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+}, {
+	.ivsize			= GCM_RFC4106_IV_SIZE,
+	.maxauthsize		= 16,
+	.setkey			= rfc4106_setkey,
+	.setauthsize		= rfc4106_setauthsize,
+	.encrypt		= rfc4106_encrypt,
+	.decrypt		= rfc4106_decrypt,
+
+	.base.cra_name		= "__rfc4106(gcm(aes))",
+	.base.cra_driver_name	= "__rfc4106_aes_gcm_p10",
+	.base.cra_priority	= 2100,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct p10_aes_gcm_ctx) +
+				  4 * sizeof(u64[2]),
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+}};
+
+static struct simd_aead_alg *p10_simd_aeads[ARRAY_SIZE(gcm_aes_algs)];
 
 static int __init p10_init(void)
 {
-	return crypto_register_aead(&gcm_aes_alg);
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_31))
+		return 0;
+
+	ret = simd_register_aeads_compat(gcm_aes_algs,
+					 ARRAY_SIZE(gcm_aes_algs),
+					 p10_simd_aeads);
+	if (ret) {
+		simd_unregister_aeads(gcm_aes_algs, ARRAY_SIZE(gcm_aes_algs),
+				      p10_simd_aeads);
+		return ret;
+	}
+	return 0;
 }
 
 static void __exit p10_exit(void)
 {
-	crypto_unregister_aead(&gcm_aes_alg);
+	simd_unregister_aeads(gcm_aes_algs, ARRAY_SIZE(gcm_aes_algs),
+			      p10_simd_aeads);
 }
 
-module_cpu_feature_match(PPC_MODULE_FEATURE_P10, p10_init);
+module_init(p10_init);
 module_exit(p10_exit);
diff --git a/arch/powerpc/crypto/aes-gcm-p10.S b/arch/powerpc/crypto/aes-gcm-p10.S
index a51f4b265308..89f50eef3512 100644
--- a/arch/powerpc/crypto/aes-gcm-p10.S
+++ b/arch/powerpc/crypto/aes-gcm-p10.S
@@ -1,42 +1,42 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
- #
- # Accelerated AES-GCM stitched implementation for ppc64le.
- #
- # Copyright 2022- IBM Inc. All rights reserved
- #
- #===================================================================================
- # Written by Danny Tsen <dtsen@linux.ibm.com>
- #
- # GHASH is based on the Karatsuba multiplication method.
- #
- #    Xi xor X1
- #
- #    X1 * H^4 + X2 * H^3 + x3 * H^2 + X4 * H =
- #      (X1.h * H4.h + xX.l * H4.l + X1 * H4) +
- #      (X2.h * H3.h + X2.l * H3.l + X2 * H3) +
- #      (X3.h * H2.h + X3.l * H2.l + X3 * H2) +
- #      (X4.h * H.h + X4.l * H.l + X4 * H)
- #
- # Xi = v0
- # H Poly = v2
- # Hash keys = v3 - v14
- #     ( H.l, H, H.h)
- #     ( H^2.l, H^2, H^2.h)
- #     ( H^3.l, H^3, H^3.h)
- #     ( H^4.l, H^4, H^4.h)
- #
- # v30 is IV
- # v31 - counter 1
- #
- # AES used,
- #     vs0 - vs14 for round keys
- #     v15, v16, v17, v18, v19, v20, v21, v22 for 8 blocks (encrypted)
- #
- # This implementation uses stitched AES-GCM approach to improve overall performance.
- # AES is implemented with 8x blocks and GHASH is using 2 4x blocks.
- #
- # ===================================================================================
- #
+#
+# Accelerated AES-GCM stitched implementation for ppc64le.
+#
+# Copyright 2024- IBM Inc.
+#
+#===================================================================================
+# Written by Danny Tsen <dtsen@us.ibm.com>
+#
+# GHASH is based on the Karatsuba multiplication method.
+#
+#    Xi xor X1
+#
+#    X1 * H^4 + X2 * H^3 + x3 * H^2 + X4 * H =
+#      (X1.h * H4.h + xX.l * H4.l + X1 * H4) +
+#      (X2.h * H3.h + X2.l * H3.l + X2 * H3) +
+#      (X3.h * H2.h + X3.l * H2.l + X3 * H2) +
+#      (X4.h * H.h + X4.l * H.l + X4 * H)
+#
+# Xi = v0
+# H Poly = v2
+# Hash keys = v3 - v14
+#     ( H.l, H, H.h)
+#     ( H^2.l, H^2, H^2.h)
+#     ( H^3.l, H^3, H^3.h)
+#     ( H^4.l, H^4, H^4.h)
+#
+# v30 is IV
+# v31 - counter 1
+#
+# AES used,
+#     vs0 - round key 0
+#     v15, v16, v17, v18, v19, v20, v21, v22 for 8 blocks (encrypted)
+#
+# This implementation uses stitched AES-GCM approach to improve overall performance.
+# AES is implemented with 8x blocks and GHASH is using 2 4x blocks.
+#
+# ===================================================================================
+#
 
 #include <asm/ppc_asm.h>
 #include <linux/linkage.h>
@@ -44,483 +44,224 @@
 .machine        "any"
 .text
 
- # 4x loops
- # v15 - v18 - input states
- # vs1 - vs9 - round keys
- #
-.macro Loop_aes_middle4x
-	xxlor	19+32, 1, 1
-	xxlor	20+32, 2, 2
-	xxlor	21+32, 3, 3
-	xxlor	22+32, 4, 4
-
-	vcipher	15, 15, 19
-	vcipher	16, 16, 19
-	vcipher	17, 17, 19
-	vcipher	18, 18, 19
-
-	vcipher	15, 15, 20
-	vcipher	16, 16, 20
-	vcipher	17, 17, 20
-	vcipher	18, 18, 20
-
-	vcipher	15, 15, 21
-	vcipher	16, 16, 21
-	vcipher	17, 17, 21
-	vcipher	18, 18, 21
-
-	vcipher	15, 15, 22
-	vcipher	16, 16, 22
-	vcipher	17, 17, 22
-	vcipher	18, 18, 22
-
-	xxlor	19+32, 5, 5
-	xxlor	20+32, 6, 6
-	xxlor	21+32, 7, 7
-	xxlor	22+32, 8, 8
-
-	vcipher	15, 15, 19
-	vcipher	16, 16, 19
-	vcipher	17, 17, 19
-	vcipher	18, 18, 19
-
-	vcipher	15, 15, 20
-	vcipher	16, 16, 20
-	vcipher	17, 17, 20
-	vcipher	18, 18, 20
-
-	vcipher	15, 15, 21
-	vcipher	16, 16, 21
-	vcipher	17, 17, 21
-	vcipher	18, 18, 21
-
-	vcipher	15, 15, 22
-	vcipher	16, 16, 22
-	vcipher	17, 17, 22
-	vcipher	18, 18, 22
-
-	xxlor	23+32, 9, 9
-	vcipher	15, 15, 23
-	vcipher	16, 16, 23
-	vcipher	17, 17, 23
-	vcipher	18, 18, 23
+.macro	SAVE_GPR GPR OFFSET FRAME
+	std	\GPR,\OFFSET(\FRAME)
 .endm
 
- # 8x loops
- # v15 - v22 - input states
- # vs1 - vs9 - round keys
- #
-.macro Loop_aes_middle8x
-	xxlor	23+32, 1, 1
-	xxlor	24+32, 2, 2
-	xxlor	25+32, 3, 3
-	xxlor	26+32, 4, 4
-
-	vcipher	15, 15, 23
-	vcipher	16, 16, 23
-	vcipher	17, 17, 23
-	vcipher	18, 18, 23
-	vcipher	19, 19, 23
-	vcipher	20, 20, 23
-	vcipher	21, 21, 23
-	vcipher	22, 22, 23
-
-	vcipher	15, 15, 24
-	vcipher	16, 16, 24
-	vcipher	17, 17, 24
-	vcipher	18, 18, 24
-	vcipher	19, 19, 24
-	vcipher	20, 20, 24
-	vcipher	21, 21, 24
-	vcipher	22, 22, 24
-
-	vcipher	15, 15, 25
-	vcipher	16, 16, 25
-	vcipher	17, 17, 25
-	vcipher	18, 18, 25
-	vcipher	19, 19, 25
-	vcipher	20, 20, 25
-	vcipher	21, 21, 25
-	vcipher	22, 22, 25
-
-	vcipher	15, 15, 26
-	vcipher	16, 16, 26
-	vcipher	17, 17, 26
-	vcipher	18, 18, 26
-	vcipher	19, 19, 26
-	vcipher	20, 20, 26
-	vcipher	21, 21, 26
-	vcipher	22, 22, 26
-
-	xxlor	23+32, 5, 5
-	xxlor	24+32, 6, 6
-	xxlor	25+32, 7, 7
-	xxlor	26+32, 8, 8
-
-	vcipher	15, 15, 23
-	vcipher	16, 16, 23
-	vcipher	17, 17, 23
-	vcipher	18, 18, 23
-	vcipher	19, 19, 23
-	vcipher	20, 20, 23
-	vcipher	21, 21, 23
-	vcipher	22, 22, 23
-
-	vcipher	15, 15, 24
-	vcipher	16, 16, 24
-	vcipher	17, 17, 24
-	vcipher	18, 18, 24
-	vcipher	19, 19, 24
-	vcipher	20, 20, 24
-	vcipher	21, 21, 24
-	vcipher	22, 22, 24
-
-	vcipher	15, 15, 25
-	vcipher	16, 16, 25
-	vcipher	17, 17, 25
-	vcipher	18, 18, 25
-	vcipher	19, 19, 25
-	vcipher	20, 20, 25
-	vcipher	21, 21, 25
-	vcipher	22, 22, 25
-
-	vcipher	15, 15, 26
-	vcipher	16, 16, 26
-	vcipher	17, 17, 26
-	vcipher	18, 18, 26
-	vcipher	19, 19, 26
-	vcipher	20, 20, 26
-	vcipher	21, 21, 26
-	vcipher	22, 22, 26
-
-	xxlor	23+32, 9, 9
-	vcipher	15, 15, 23
-	vcipher	16, 16, 23
-	vcipher	17, 17, 23
-	vcipher	18, 18, 23
-	vcipher	19, 19, 23
-	vcipher	20, 20, 23
-	vcipher	21, 21, 23
-	vcipher	22, 22, 23
+.macro	SAVE_VRS VRS OFFSET FRAME
+	stxv	\VRS+32, \OFFSET(\FRAME)
 .endm
 
-.macro Loop_aes_middle_1x
-	xxlor	19+32, 1, 1
-	xxlor	20+32, 2, 2
-	xxlor	21+32, 3, 3
-	xxlor	22+32, 4, 4
-
-	vcipher 15, 15, 19
-	vcipher 15, 15, 20
-	vcipher 15, 15, 21
-	vcipher 15, 15, 22
-
-	xxlor	19+32, 5, 5
-	xxlor	20+32, 6, 6
-	xxlor	21+32, 7, 7
-	xxlor	22+32, 8, 8
-
-	vcipher 15, 15, 19
-	vcipher 15, 15, 20
-	vcipher 15, 15, 21
-	vcipher 15, 15, 22
-
-	xxlor	19+32, 9, 9
-	vcipher 15, 15, 19
+.macro	RESTORE_GPR GPR OFFSET FRAME
+	ld	\GPR,\OFFSET(\FRAME)
 .endm
 
- #
- # Compute 4x hash values based on Karatsuba method.
- #
-.macro ppc_aes_gcm_ghash
-	vxor		15, 15, 0
-
-	vpmsumd		23, 12, 15		# H4.L * X.L
-	vpmsumd		24, 9, 16
-	vpmsumd		25, 6, 17
-	vpmsumd		26, 3, 18
-
-	vxor		23, 23, 24
-	vxor		23, 23, 25
-	vxor		23, 23, 26		# L
-
-	vpmsumd		24, 13, 15		# H4.L * X.H + H4.H * X.L
-	vpmsumd		25, 10, 16		# H3.L * X1.H + H3.H * X1.L
-	vpmsumd		26, 7, 17
-	vpmsumd		27, 4, 18
-
-	vxor		24, 24, 25
-	vxor		24, 24, 26
-	vxor		24, 24, 27		# M
-
-	# sum hash and reduction with H Poly
-	vpmsumd		28, 23, 2		# reduction
-
-	vxor		29, 29, 29
-	vsldoi		26, 24, 29, 8		# mL
-	vsldoi		29, 29, 24, 8		# mH
-	vxor		23, 23, 26		# mL + L
-
-	vsldoi		23, 23, 23, 8		# swap
-	vxor		23, 23, 28
-
-	vpmsumd		24, 14, 15		# H4.H * X.H
-	vpmsumd		25, 11, 16
-	vpmsumd		26, 8, 17
-	vpmsumd		27, 5, 18
-
-	vxor		24, 24, 25
-	vxor		24, 24, 26
-	vxor		24, 24, 27
-
-	vxor		24, 24, 29
-
-	# sum hash and reduction with H Poly
-	vsldoi		27, 23, 23, 8		# swap
-	vpmsumd		23, 23, 2
-	vxor		27, 27, 24
-	vxor		23, 23, 27
-
-	xxlor		32, 23+32, 23+32		# update hash
-
+.macro	RESTORE_VRS VRS OFFSET FRAME
+	lxv	\VRS+32, \OFFSET(\FRAME)
 .endm
 
- #
- # Combine two 4x ghash
- # v15 - v22 - input blocks
- #
-.macro ppc_aes_gcm_ghash2_4x
-	# first 4x hash
-	vxor		15, 15, 0		# Xi + X
-
-	vpmsumd		23, 12, 15		# H4.L * X.L
-	vpmsumd		24, 9, 16
-	vpmsumd		25, 6, 17
-	vpmsumd		26, 3, 18
-
-	vxor		23, 23, 24
-	vxor		23, 23, 25
-	vxor		23, 23, 26		# L
-
-	vpmsumd		24, 13, 15		# H4.L * X.H + H4.H * X.L
-	vpmsumd		25, 10, 16		# H3.L * X1.H + H3.H * X1.L
-	vpmsumd		26, 7, 17
-	vpmsumd		27, 4, 18
-
-	vxor		24, 24, 25
-	vxor		24, 24, 26
-
-	# sum hash and reduction with H Poly
-	vpmsumd		28, 23, 2		# reduction
-
-	vxor		29, 29, 29
-
-	vxor		24, 24, 27		# M
-	vsldoi		26, 24, 29, 8		# mL
-	vsldoi		29, 29, 24, 8		# mH
-	vxor		23, 23, 26		# mL + L
-
-	vsldoi		23, 23, 23, 8		# swap
-	vxor		23, 23, 28
+.macro SAVE_REGS
+	mflr 0
+	std 0, 16(1)
+	stdu 1,-512(1)
+
+	SAVE_GPR 14, 112, 1
+	SAVE_GPR 15, 120, 1
+	SAVE_GPR 16, 128, 1
+	SAVE_GPR 17, 136, 1
+	SAVE_GPR 18, 144, 1
+	SAVE_GPR 19, 152, 1
+	SAVE_GPR 20, 160, 1
+	SAVE_GPR 21, 168, 1
+	SAVE_GPR 22, 176, 1
+	SAVE_GPR 23, 184, 1
+	SAVE_GPR 24, 192, 1
+
+	addi	9, 1, 256
+	SAVE_VRS 20, 0, 9
+	SAVE_VRS 21, 16, 9
+	SAVE_VRS 22, 32, 9
+	SAVE_VRS 23, 48, 9
+	SAVE_VRS 24, 64, 9
+	SAVE_VRS 25, 80, 9
+	SAVE_VRS 26, 96, 9
+	SAVE_VRS 27, 112, 9
+	SAVE_VRS 28, 128, 9
+	SAVE_VRS 29, 144, 9
+	SAVE_VRS 30, 160, 9
+	SAVE_VRS 31, 176, 9
+.endm # SAVE_REGS
 
-	vpmsumd		24, 14, 15		# H4.H * X.H
-	vpmsumd		25, 11, 16
-	vpmsumd		26, 8, 17
-	vpmsumd		27, 5, 18
+.macro RESTORE_REGS
+	addi	9, 1, 256
+	RESTORE_VRS 20, 0, 9
+	RESTORE_VRS 21, 16, 9
+	RESTORE_VRS 22, 32, 9
+	RESTORE_VRS 23, 48, 9
+	RESTORE_VRS 24, 64, 9
+	RESTORE_VRS 25, 80, 9
+	RESTORE_VRS 26, 96, 9
+	RESTORE_VRS 27, 112, 9
+	RESTORE_VRS 28, 128, 9
+	RESTORE_VRS 29, 144, 9
+	RESTORE_VRS 30, 160, 9
+	RESTORE_VRS 31, 176, 9
+
+	RESTORE_GPR 14, 112, 1
+	RESTORE_GPR 15, 120, 1
+	RESTORE_GPR 16, 128, 1
+	RESTORE_GPR 17, 136, 1
+	RESTORE_GPR 18, 144, 1
+	RESTORE_GPR 19, 152, 1
+	RESTORE_GPR 20, 160, 1
+	RESTORE_GPR 21, 168, 1
+	RESTORE_GPR 22, 176, 1
+	RESTORE_GPR 23, 184, 1
+	RESTORE_GPR 24, 192, 1
+
+	addi    1, 1, 512
+	ld 0, 16(1)
+	mtlr 0
+.endm # RESTORE_REGS
+
+# 4x loops
+.macro AES_CIPHER_4x _VCIPHER ST r
+	\_VCIPHER	\ST, \ST, \r
+	\_VCIPHER	\ST+1, \ST+1, \r
+	\_VCIPHER	\ST+2, \ST+2, \r
+	\_VCIPHER	\ST+3, \ST+3, \r
+.endm
 
-	vxor		24, 24, 25
-	vxor		24, 24, 26
-	vxor		24, 24, 27		# H
+# 8x loops
+.macro AES_CIPHER_8x _VCIPHER ST r
+	\_VCIPHER	\ST, \ST, \r
+	\_VCIPHER	\ST+1, \ST+1, \r
+	\_VCIPHER	\ST+2, \ST+2, \r
+	\_VCIPHER	\ST+3, \ST+3, \r
+	\_VCIPHER	\ST+4, \ST+4, \r
+	\_VCIPHER	\ST+5, \ST+5, \r
+	\_VCIPHER	\ST+6, \ST+6, \r
+	\_VCIPHER	\ST+7, \ST+7, \r
+.endm
 
-	vxor		24, 24, 29		# H + mH
+.macro LOOP_8AES_STATE
+	xxlor	32+23, 1, 1
+	xxlor	32+24, 2, 2
+	xxlor	32+25, 3, 3
+	xxlor	32+26, 4, 4
+	AES_CIPHER_8x vcipher, 15, 23
+	AES_CIPHER_8x vcipher, 15, 24
+	AES_CIPHER_8x vcipher, 15, 25
+	AES_CIPHER_8x vcipher, 15, 26
+	xxlor	32+23, 5, 5
+	xxlor	32+24, 6, 6
+	xxlor	32+25, 7, 7
+	xxlor	32+26, 8, 8
+	AES_CIPHER_8x vcipher, 15, 23
+	AES_CIPHER_8x vcipher, 15, 24
+	AES_CIPHER_8x vcipher, 15, 25
+	AES_CIPHER_8x vcipher, 15, 26
+.endm
 
-	# sum hash and reduction with H Poly
-	vsldoi		27, 23, 23, 8		# swap
-	vpmsumd		23, 23, 2
-	vxor		27, 27, 24
-	vxor		27, 23, 27		# 1st Xi
-
-	# 2nd 4x hash
-	vpmsumd		24, 9, 20
-	vpmsumd		25, 6, 21
-	vpmsumd		26, 3, 22
-	vxor		19, 19, 27		# Xi + X
-	vpmsumd		23, 12, 19		# H4.L * X.L
-
-	vxor		23, 23, 24
-	vxor		23, 23, 25
-	vxor		23, 23, 26		# L
-
-	vpmsumd		24, 13, 19		# H4.L * X.H + H4.H * X.L
-	vpmsumd		25, 10, 20		# H3.L * X1.H + H3.H * X1.L
-	vpmsumd		26, 7, 21
-	vpmsumd		27, 4, 22
-
-	vxor		24, 24, 25
-	vxor		24, 24, 26
+#
+# PPC_GHASH4x(H, S1, S2, S3, S4): Compute 4x hash values based on Karatsuba method.
+# H: returning digest
+# S#: states
+#
+# S1 should xor with the previous digest
+#
+# Xi = v0
+# H Poly = v2
+# Hash keys = v3 - v14
+# Scratch: v23 - v29
+#
+.macro PPC_GHASH4x H S1 S2 S3 S4
+
+	vpmsumd	23, 12, \S1		# H4.L * X.L
+	vpmsumd	24, 9, \S2
+	vpmsumd	25, 6, \S3
+	vpmsumd	26, 3, \S4
+
+	vpmsumd	27, 13, \S1		# H4.L * X.H + H4.H * X.L
+	vpmsumd	28, 10, \S2		# H3.L * X1.H + H3.H * X1.L
+
+	vxor	23, 23, 24
+	vxor	23, 23, 25
+	vxor	23, 23, 26		# L
+
+	vxor	24, 27, 28
+	vpmsumd	25, 7, \S3
+	vpmsumd	26, 4, \S4
+
+	vxor	24, 24, 25
+	vxor	24, 24, 26		# M
 
 	# sum hash and reduction with H Poly
-	vpmsumd		28, 23, 2		# reduction
-
-	vxor		29, 29, 29
+	vpmsumd	28, 23, 2		# reduction
 
-	vxor		24, 24, 27		# M
-	vsldoi		26, 24, 29, 8		# mL
-	vsldoi		29, 29, 24, 8		# mH
-	vxor		23, 23, 26		# mL + L
+	vxor	1, 1, 1
+	vsldoi	25, 24, 1, 8		# mL
+	vsldoi	1, 1, 24, 8		# mH
+	vxor	23, 23, 25		# mL + L
 
-	vsldoi		23, 23, 23, 8		# swap
-	vxor		23, 23, 28
+	# This performs swap and xor like,
+	#   vsldoi	23, 23, 23, 8		# swap
+	#   vxor	23, 23, 28
+	xxlor	32+25, 10, 10
+	vpermxor 23, 23, 28, 25
 
-	vpmsumd		24, 14, 19		# H4.H * X.H
-	vpmsumd		25, 11, 20
-	vpmsumd		26, 8, 21
-	vpmsumd		27, 5, 22
+	vpmsumd	26, 14, \S1		# H4.H * X.H
+	vpmsumd	27, 11, \S2
+	vpmsumd	28, 8, \S3
+	vpmsumd	29, 5, \S4
 
-	vxor		24, 24, 25
-	vxor		24, 24, 26
-	vxor		24, 24, 27		# H
+	vxor	24, 26, 27
+	vxor	24, 24, 28
+	vxor	24, 24, 29
 
-	vxor		24, 24, 29		# H + mH
+	vxor	24, 24, 1
 
 	# sum hash and reduction with H Poly
-	vsldoi		27, 23, 23, 8		# swap
-	vpmsumd		23, 23, 2
-	vxor		27, 27, 24
-	vxor		23, 23, 27
-
-	xxlor		32, 23+32, 23+32		# update hash
-
+	vsldoi	25, 23, 23, 8		# swap
+	vpmsumd	23, 23, 2
+	vxor	27, 25, 24
+	vxor	\H, 23, 27
 .endm
 
- #
- # Compute update single hash
- #
-.macro ppc_update_hash_1x
-	vxor		28, 28, 0
-
-	vxor		19, 19, 19
+#
+# Compute update single ghash
+# scratch: v1, v22..v27
+#
+.macro PPC_GHASH1x H S1
 
-	vpmsumd		22, 3, 28		# L
-	vpmsumd		23, 4, 28		# M
-	vpmsumd		24, 5, 28		# H
+	vxor	1, 1, 1
 
-	vpmsumd		27, 22, 2		# reduction
+	vpmsumd	22, 3, \S1		# L
+	vpmsumd	23, 4, \S1		# M
+	vpmsumd	24, 5, \S1		# H
 
-	vsldoi		25, 23, 19, 8		# mL
-	vsldoi		26, 19, 23, 8		# mH
-	vxor		22, 22, 25		# LL + LL
-	vxor		24, 24, 26		# HH + HH
+	vpmsumd	27, 22, 2		# reduction
 
-	vsldoi		22, 22, 22, 8		# swap
-	vxor		22, 22, 27
+	vsldoi	25, 23, 1, 8		# mL
+	vsldoi	26, 1, 23, 8		# mH
+	vxor	22, 22, 25		# LL + LL
+	vxor	24, 24, 26		# HH + HH
 
-	vsldoi		20, 22, 22, 8		# swap
-	vpmsumd		22, 22, 2		# reduction
-	vxor		20, 20, 24
-	vxor		22, 22, 20
+	xxlor	32+25, 10, 10
+	vpermxor 22, 22, 27, 25
 
-	vmr		0, 22			# update hash
-
-.endm
-
-.macro SAVE_REGS
-	stdu 1,-640(1)
-	mflr 0
-
-	std	14,112(1)
-	std	15,120(1)
-	std	16,128(1)
-	std	17,136(1)
-	std	18,144(1)
-	std	19,152(1)
-	std	20,160(1)
-	std	21,168(1)
-	li	9, 256
-	stvx	20, 9, 1
-	addi	9, 9, 16
-	stvx	21, 9, 1
-	addi	9, 9, 16
-	stvx	22, 9, 1
-	addi	9, 9, 16
-	stvx	23, 9, 1
-	addi	9, 9, 16
-	stvx	24, 9, 1
-	addi	9, 9, 16
-	stvx	25, 9, 1
-	addi	9, 9, 16
-	stvx	26, 9, 1
-	addi	9, 9, 16
-	stvx	27, 9, 1
-	addi	9, 9, 16
-	stvx	28, 9, 1
-	addi	9, 9, 16
-	stvx	29, 9, 1
-	addi	9, 9, 16
-	stvx	30, 9, 1
-	addi	9, 9, 16
-	stvx	31, 9, 1
-	stxv	14, 464(1)
-	stxv	15, 480(1)
-	stxv	16, 496(1)
-	stxv	17, 512(1)
-	stxv	18, 528(1)
-	stxv	19, 544(1)
-	stxv	20, 560(1)
-	stxv	21, 576(1)
-	stxv	22, 592(1)
-	std	0, 656(1)
-.endm
-
-.macro RESTORE_REGS
-	lxv	14, 464(1)
-	lxv	15, 480(1)
-	lxv	16, 496(1)
-	lxv	17, 512(1)
-	lxv	18, 528(1)
-	lxv	19, 544(1)
-	lxv	20, 560(1)
-	lxv	21, 576(1)
-	lxv	22, 592(1)
-	li	9, 256
-	lvx	20, 9, 1
-	addi	9, 9, 16
-	lvx	21, 9, 1
-	addi	9, 9, 16
-	lvx	22, 9, 1
-	addi	9, 9, 16
-	lvx	23, 9, 1
-	addi	9, 9, 16
-	lvx	24, 9, 1
-	addi	9, 9, 16
-	lvx	25, 9, 1
-	addi	9, 9, 16
-	lvx	26, 9, 1
-	addi	9, 9, 16
-	lvx	27, 9, 1
-	addi	9, 9, 16
-	lvx	28, 9, 1
-	addi	9, 9, 16
-	lvx	29, 9, 1
-	addi	9, 9, 16
-	lvx	30, 9, 1
-	addi	9, 9, 16
-	lvx	31, 9, 1
-
-	ld	0, 656(1)
-	ld      14,112(1)
-	ld      15,120(1)
-	ld      16,128(1)
-	ld      17,136(1)
-	ld      18,144(1)
-	ld      19,152(1)
-	ld      20,160(1)
-	ld	21,168(1)
-
-	mtlr	0
-	addi	1, 1, 640
+	vsldoi	23, 22, 22, 8		# swap
+	vpmsumd	22, 22, 2		# reduction
+	vxor	23, 23, 24
+	vxor	\H, 22, 23
 .endm
 
+#
+# LOAD_HASH_TABLE
+# Xi = v0
+# H Poly = v2
+# Hash keys = v3 - v14
+#
 .macro LOAD_HASH_TABLE
 	# Load Xi
 	lxvb16x	32, 0, 8	# load Xi
@@ -557,657 +298,434 @@
 	lxvd2x	14+32, 10, 8	# H^4h
 .endm
 
- #
- # aes_p10_gcm_encrypt (const void *inp, void *out, size_t len,
- #               const char *rk, unsigned char iv[16], void *Xip);
- #
- #    r3 - inp
- #    r4 - out
- #    r5 - len
- #    r6 - AES round keys
- #    r7 - iv and other data
- #    r8 - Xi, HPoli, hash keys
- #
- #    rounds is at offset 240 in rk
- #    Xi is at 0 in gcm_table (Xip).
- #
-_GLOBAL(aes_p10_gcm_encrypt)
-.align 5
-
-	SAVE_REGS
-
-	LOAD_HASH_TABLE
-
-	# initialize ICB: GHASH( IV ), IV - r7
-	lxvb16x	30+32, 0, 7	# load IV  - v30
-
-	mr	12, 5		# length
-	li	11, 0		# block index
-
-	# counter 1
-	vxor	31, 31, 31
-	vspltisb 22, 1
-	vsldoi	31, 31, 22,1	# counter 1
-
-	# load round key to VSR
-	lxv	0, 0(6)
-	lxv	1, 0x10(6)
-	lxv	2, 0x20(6)
-	lxv	3, 0x30(6)
-	lxv	4, 0x40(6)
-	lxv	5, 0x50(6)
-	lxv	6, 0x60(6)
-	lxv	7, 0x70(6)
-	lxv	8, 0x80(6)
-	lxv	9, 0x90(6)
-	lxv	10, 0xa0(6)
-
-	# load rounds - 10 (128), 12 (192), 14 (256)
-	lwz	9,240(6)
-
-	#
-	# vxor	state, state, w # addroundkey
-	xxlor	32+29, 0, 0
-	vxor	15, 30, 29	# IV + round key - add round key 0
-
-	cmpdi	9, 10
-	beq	Loop_aes_gcm_8x
-
-	# load 2 more round keys (v11, v12)
-	lxv	11, 0xb0(6)
-	lxv	12, 0xc0(6)
-
-	cmpdi	9, 12
-	beq	Loop_aes_gcm_8x
-
-	# load 2 more round keys (v11, v12, v13, v14)
-	lxv	13, 0xd0(6)
-	lxv	14, 0xe0(6)
-	cmpdi	9, 14
-	beq	Loop_aes_gcm_8x
-
-	b	aes_gcm_out
-
-.align 5
-Loop_aes_gcm_8x:
-	mr	14, 3
-	mr	9, 4
-
-	#
-	# check partial block
-	#
-Continue_partial_check:
-	ld	15, 56(7)
-	cmpdi	15, 0
-	beq	Continue
-	bgt	Final_block
-	cmpdi	15, 16
-	blt	Final_block
-
-Continue:
-	# n blcoks
-	li	10, 128
-	divdu	10, 12, 10	# n 128 bytes-blocks
-	cmpdi	10, 0
-	beq	Loop_last_block
-
-	vaddudm	30, 30, 31	# IV + counter
-	vxor	16, 30, 29
-	vaddudm	30, 30, 31
-	vxor	17, 30, 29
-	vaddudm	30, 30, 31
-	vxor	18, 30, 29
-	vaddudm	30, 30, 31
-	vxor	19, 30, 29
-	vaddudm	30, 30, 31
-	vxor	20, 30, 29
-	vaddudm	30, 30, 31
-	vxor	21, 30, 29
-	vaddudm	30, 30, 31
-	vxor	22, 30, 29
-
-	mtctr	10
-
-	li	15, 16
-	li	16, 32
-	li	17, 48
-	li	18, 64
-	li	19, 80
-	li	20, 96
-	li	21, 112
-
-	lwz	10, 240(6)
-
-Loop_8x_block:
-
-	lxvb16x		15, 0, 14	# load block
-	lxvb16x		16, 15, 14	# load block
-	lxvb16x		17, 16, 14	# load block
-	lxvb16x		18, 17, 14	# load block
-	lxvb16x		19, 18, 14	# load block
-	lxvb16x		20, 19, 14	# load block
-	lxvb16x		21, 20, 14	# load block
-	lxvb16x		22, 21, 14	# load block
-	addi		14, 14, 128
-
-	Loop_aes_middle8x
-
-	xxlor	23+32, 10, 10
-
-	cmpdi	10, 10
-	beq	Do_next_ghash
-
-	# 192 bits
-	xxlor	24+32, 11, 11
-
-	vcipher	15, 15, 23
-	vcipher	16, 16, 23
-	vcipher	17, 17, 23
-	vcipher	18, 18, 23
-	vcipher	19, 19, 23
-	vcipher	20, 20, 23
-	vcipher	21, 21, 23
-	vcipher	22, 22, 23
-
-	vcipher	15, 15, 24
-	vcipher	16, 16, 24
-	vcipher	17, 17, 24
-	vcipher	18, 18, 24
-	vcipher	19, 19, 24
-	vcipher	20, 20, 24
-	vcipher	21, 21, 24
-	vcipher	22, 22, 24
-
-	xxlor	23+32, 12, 12
-
-	cmpdi	10, 12
-	beq	Do_next_ghash
-
-	# 256 bits
-	xxlor	24+32, 13, 13
-
-	vcipher	15, 15, 23
-	vcipher	16, 16, 23
-	vcipher	17, 17, 23
-	vcipher	18, 18, 23
-	vcipher	19, 19, 23
-	vcipher	20, 20, 23
-	vcipher	21, 21, 23
-	vcipher	22, 22, 23
-
-	vcipher	15, 15, 24
-	vcipher	16, 16, 24
-	vcipher	17, 17, 24
-	vcipher	18, 18, 24
-	vcipher	19, 19, 24
-	vcipher	20, 20, 24
-	vcipher	21, 21, 24
-	vcipher	22, 22, 24
-
-	xxlor	23+32, 14, 14
-
-	cmpdi	10, 14
-	beq	Do_next_ghash
-	b	aes_gcm_out
-
-Do_next_ghash:
-
-	#
-	# last round
-	vcipherlast     15, 15, 23
-	vcipherlast     16, 16, 23
-
-	xxlxor		47, 47, 15
-	stxvb16x        47, 0, 9	# store output
-	xxlxor		48, 48, 16
-	stxvb16x        48, 15, 9	# store output
-
-	vcipherlast     17, 17, 23
-	vcipherlast     18, 18, 23
-
-	xxlxor		49, 49, 17
-	stxvb16x        49, 16, 9	# store output
-	xxlxor		50, 50, 18
-	stxvb16x        50, 17, 9	# store output
-
-	vcipherlast     19, 19, 23
-	vcipherlast     20, 20, 23
-
-	xxlxor		51, 51, 19
-	stxvb16x        51, 18, 9	# store output
-	xxlxor		52, 52, 20
-	stxvb16x        52, 19, 9	# store output
-
-	vcipherlast     21, 21, 23
-	vcipherlast     22, 22, 23
-
-	xxlxor		53, 53, 21
-	stxvb16x        53, 20, 9	# store output
-	xxlxor		54, 54, 22
-	stxvb16x        54, 21, 9	# store output
-
-	addi		9, 9, 128
-
-	# ghash here
-	ppc_aes_gcm_ghash2_4x
-
-	xxlor	27+32, 0, 0
-	vaddudm 30, 30, 31		# IV + counter
-	vmr	29, 30
-	vxor    15, 30, 27		# add round key
-	vaddudm 30, 30, 31
-	vxor    16, 30, 27
-	vaddudm 30, 30, 31
-	vxor    17, 30, 27
-	vaddudm 30, 30, 31
-	vxor    18, 30, 27
-	vaddudm 30, 30, 31
-	vxor    19, 30, 27
-	vaddudm 30, 30, 31
-	vxor    20, 30, 27
-	vaddudm 30, 30, 31
-	vxor    21, 30, 27
-	vaddudm 30, 30, 31
-	vxor    22, 30, 27
-
-	addi    12, 12, -128
-	addi    11, 11, 128
-
-	bdnz	Loop_8x_block
-
-	vmr	30, 29
-	stxvb16x 30+32, 0, 7		# update IV
-
-Loop_last_block:
-	cmpdi   12, 0
-	beq     aes_gcm_out
-
-	# loop last few blocks
+################################################################################
+# Compute AES and ghash one block at a time.
+# r23: AES rounds
+# v30: current IV
+# vs0: roundkey 0
+#
+################################################################################
+SYM_FUNC_START_LOCAL(aes_gcm_crypt_1x)
+
+	cmpdi	5, 16
+	bge	__More_1x
+	blr
+__More_1x:
 	li      10, 16
-	divdu   10, 12, 10
-
-	mtctr   10
-
-	lwz	10, 240(6)
-
-	cmpdi   12, 16
-	blt     Final_block
-
-Next_rem_block:
-	lxvb16x 15, 0, 14		# load block
-
-	Loop_aes_middle_1x
-
-	xxlor	23+32, 10, 10
-
-	cmpdi	10, 10
-	beq	Do_next_1x
-
-	# 192 bits
-	xxlor	24+32, 11, 11
-
-	vcipher	15, 15, 23
-	vcipher	15, 15, 24
-
-	xxlor	23+32, 12, 12
+	divdu   12, 5, 10
+
+	xxlxor	32+15, 32+30, 0
+
+	# Pre-load 8 AES rounds to scratch vectors.
+	xxlor	32+16, 1, 1
+	xxlor	32+17, 2, 2
+	xxlor	32+18, 3, 3
+	xxlor	32+19, 4, 4
+	xxlor	32+20, 5, 5
+	xxlor	32+21, 6, 6
+	xxlor	32+28, 7, 7
+	xxlor	32+29, 8, 8
+	lwz	23, 240(6)	# n rounds
+	addi	22, 23, -9	# remaing AES rounds
 
-	cmpdi	10, 12
-	beq	Do_next_1x
-
-	# 256 bits
-	xxlor	24+32, 13, 13
-
-	vcipher	15, 15, 23
-	vcipher	15, 15, 24
-
-	xxlor	23+32, 14, 14
-
-	cmpdi	10, 14
-	beq	Do_next_1x
-
-Do_next_1x:
-	vcipherlast     15, 15, 23
-
-	xxlxor		47, 47, 15
-	stxvb16x	47, 0, 9	# store output
-	addi		14, 14, 16
-	addi		9, 9, 16
-
-	vmr		28, 15
-	ppc_update_hash_1x
-
-	addi		12, 12, -16
-	addi		11, 11, 16
-	xxlor		19+32, 0, 0
-	vaddudm		30, 30, 31		# IV + counter
-	vxor		15, 30, 19		# add round key
-
-	bdnz	Next_rem_block
-
-	li	15, 0
-	std	15, 56(7)		# clear partial?
-	stxvb16x 30+32, 0, 7		# update IV
 	cmpdi	12, 0
-	beq	aes_gcm_out
-
-Final_block:
-	lwz	10, 240(6)
-	Loop_aes_middle_1x
-
-	xxlor	23+32, 10, 10
-
-	cmpdi	10, 10
-	beq	Do_final_1x
-
-	# 192 bits
-	xxlor	24+32, 11, 11
-
-	vcipher	15, 15, 23
-	vcipher	15, 15, 24
-
-	xxlor	23+32, 12, 12
-
-	cmpdi	10, 12
-	beq	Do_final_1x
-
-	# 256 bits
-	xxlor	24+32, 13, 13
-
-	vcipher	15, 15, 23
-	vcipher	15, 15, 24
+	bgt	__Loop_1x
+	blr
 
-	xxlor	23+32, 14, 14
+__Loop_1x:
+	mtctr	22
+	addi	10, 6, 144
+	vcipher	15, 15, 16
+	vcipher	15, 15, 17
+	vcipher	15, 15, 18
+	vcipher	15, 15, 19
+	vcipher	15, 15, 20
+	vcipher	15, 15, 21
+	vcipher	15, 15, 28
+	vcipher	15, 15, 29
 
-	cmpdi	10, 14
-	beq	Do_final_1x
+__Loop_aes_1state:
+	lxv	32+1, 0(10)
+	vcipher	15, 15, 1
+	addi	10, 10, 16
+	bdnz	__Loop_aes_1state
+	lxv	32+1, 0(10)		# last round key
+	lxvb16x 11, 0, 14		# load input block
+	vcipherlast 15, 15, 1
+
+	xxlxor	32+15, 32+15, 11
+	stxvb16x 32+15, 0, 9	# store output
+	addi	14, 14, 16
+	addi	9, 9, 16
 
-Do_final_1x:
-	vcipherlast     15, 15, 23
+	cmpdi	24, 0	# decrypt?
+	bne	__Encrypt_1x
+	xxlor	15+32, 11, 11
+__Encrypt_1x:
+	vxor	15, 15, 0
+	PPC_GHASH1x 0, 15
 
-	# check partial block
-	li	21, 0			# encrypt
-	ld	15, 56(7)		# partial?
-	cmpdi	15, 0
-	beq	Normal_block
-	bl	Do_partial_block
+	addi	5, 5, -16
+	addi	11, 11, 16
 
+	vadduwm 30, 30, 31		# IV + counter
+	xxlxor	32+15, 32+30, 0
+	addi	12, 12, -1
 	cmpdi	12, 0
-	ble aes_gcm_out
+	bgt	__Loop_1x
 
-	b Continue_partial_check
-
-Normal_block:
-	lxvb16x	15, 0, 14		# load last block
-	xxlxor	47, 47, 15
-
-	# create partial block mask
-	li	15, 16
-	sub	15, 15, 12		# index to the mask
-
-	vspltisb	16, -1		# first 16 bytes - 0xffff...ff
-	vspltisb	17, 0		# second 16 bytes - 0x0000...00
-	li	10, 192
-	stvx	16, 10, 1
+	stxvb16x 32+30, 0, 7		# update IV
+	stxvb16x 32+0, 0, 8		# update Xi
+	blr
+SYM_FUNC_END(aes_gcm_crypt_1x)
+
+################################################################################
+# Process a normal partial block when we come here.
+#  Compute partial mask, Load and store partial block to stack.
+#  Update partial_len and pblock.
+#  pblock is (encrypted ^ AES state) for encrypt
+#        and (input ^ AES state) for decrypt.
+#
+################################################################################
+SYM_FUNC_START_LOCAL(__Process_partial)
+
+	# create partial mask
+	vspltisb 16, -1
+	li	12, 16
+	sub	12, 12, 5
+	sldi	12, 12, 3
+	mtvsrdd	32+17, 0, 12
+	vslo	16, 16, 17		# partial block mask
+
+	lxvb16x 11, 0, 14		# load partial block
+	xxland	11, 11, 32+16
+
+	# AES crypt partial
+	xxlxor	32+15, 32+30, 0
+	lwz	23, 240(6)		# n rounds
+	addi	22, 23, -1		# loop - 1
+	mtctr	22
+	addi	10, 6, 16
+
+__Loop_aes_pstate:
+	lxv	32+1, 0(10)
+	vcipher	15, 15, 1
 	addi	10, 10, 16
-	stvx	17, 10, 1
-
-	addi	10, 1, 192
-	lxvb16x	16, 15, 10		# load partial block mask
-	xxland	47, 47, 16
-
-	vmr	28, 15
-	ppc_update_hash_1x
+	bdnz	__Loop_aes_pstate
+	lxv	32+1, 0(10)		# last round key
+	vcipherlast 15, 15, 1
 
-	# * should store only the remaining bytes.
-	bl	Write_partial_block
-
-	stxvb16x 30+32, 0, 7		# update IV
-	std	12, 56(7)		# update partial?
-	li	16, 16
+	xxlxor	32+15, 32+15, 11
+	vand	15, 15, 16
 
-	stxvb16x	32, 0, 8		# write out Xi
-	stxvb16x	32, 16, 8		# write out Xi
-	b aes_gcm_out
-
- #
- # Compute data mask
- #
-.macro GEN_MASK _mask _start _end
-	vspltisb	16, -1		# first 16 bytes - 0xffff...ff
-	vspltisb	17, 0		# second 16 bytes - 0x0000...00
-	li	10, 192
-	stxvb16x	17+32, 10, 1
-	add	10, 10, \_start
-	stxvb16x	16+32, 10, 1
-	add	10, 10, \_end
-	stxvb16x	17+32, 10, 1
-
-	addi	10, 1, 192
-	lxvb16x	\_mask, 0, 10		# load partial block mask
-.endm
+	# AES crypt output v15
+	# Write partial
+	li	10, 224
+	stxvb16x 15+32, 10, 1		# write v15 to stack
+	addi	10, 1, 223
+	addi	12, 9, -1
+        mtctr	5			# partial block len
+__Write_partial:
+        lbzu	22, 1(10)
+	stbu	22, 1(12)
+        bdnz	__Write_partial
+
+	cmpdi	24, 0			# decrypt?
+	bne	__Encrypt_partial
+	xxlor	32+15, 11, 11		# decrypt using the input block
+__Encrypt_partial:
+	#vxor	15, 15, 0		# ^ previous hash
+	#PPC_GHASH1x 0, 15
+
+	add	14, 14, 5
+	add	9, 9, 5
+	std	5, 56(7)		# update partial
+	sub	11, 11, 5
+	li	5, 0			# done last byte
 
- #
- # Handle multiple partial blocks for encrypt and decrypt
- #   operations.
- #
-SYM_FUNC_START_LOCAL(Do_partial_block)
-	add	17, 15, 5
-	cmpdi	17, 16
-	bgt	Big_block
-	GEN_MASK 18, 15, 5
-	b	_Partial
-SYM_FUNC_END(Do_partial_block)
-Big_block:
+	#
+	# Don't increase IV since this is the last partial.
+	# It should get updated in gcm_update if no more data blocks.
+	#vadduwm	30, 30, 31		# increase IV
+	stxvb16x 32+30, 0, 7		# update IV
+	li	10, 64
+	stxvb16x 32+0, 0, 8		# Update X1
+	stxvb16x 32+15, 10, 7		# Update pblock
+	blr
+SYM_FUNC_END(__Process_partial)
+
+################################################################################
+# Combine partial blocks and ghash when we come here.
+#
+# The partial block has to be shifted to the right location to encrypt/decrypt
+# and compute ghash if combing the previous partial block is needed.
+# - Compute ghash for a full block. Clear Partial_len and pblock. Update IV.
+#   Write Xi.
+# - Don't compute ghash if not full block.  gcm_update will take care of it
+#   is the last block. Update Partial_len and pblock.
+#
+################################################################################
+SYM_FUNC_START_LOCAL(__Combine_partial)
+
+	ld	12, 56(7)
+	mr	21, 5			# these bytes to be processed
+
+	li	17, 0
 	li	16, 16
-	GEN_MASK 18, 15, 16
-
-_Partial:
-	lxvb16x	17+32, 0, 14		# load last block
-	sldi	16, 15, 3
-	mtvsrdd	32+16, 0, 16
-	vsro	17, 17, 16
-	xxlxor	47, 47, 17+32
-	xxland	47, 47, 18
-
-	vxor	0, 0, 0			# clear Xi
-	vmr	28, 15
-
-	cmpdi	21, 0			# encrypt/decrypt ops?
-	beq	Skip_decrypt
-	xxland	32+28, 32+17, 18
-
-Skip_decrypt:
-
-	ppc_update_hash_1x
+	sub	22, 16, 12		# bytes to complete a block
+	sub	17, 22, 5		# remaining bytes in a block
+	cmpdi	5, 16
+	ble	__Inp_msg_less16
+	li	17, 0
+	mr	21, 22
+	b	__Combine_continue
+__Inp_msg_less16:
+	cmpd	22, 5
+	bgt	__Combine_continue
+	li	17, 0
+	mr	21, 22			# these bytes to be processed
+
+__Combine_continue:
+	# load msg and shift to the proper location and mask
+	vspltisb 16, -1
+	sldi	15, 12, 3
+	mtvsrdd	32+17, 0, 15
+	vslo	16, 16, 17
+	vsro	16, 16, 17
+	sldi	15, 17, 3
+	mtvsrdd	32+17, 0, 15
+	vsro	16, 16, 17
+	vslo	16, 16, 17		# mask
+
+	lxvb16x 32+19, 0, 14		# load partial block
+	sldi	15, 12, 3
+	mtvsrdd	32+17, 0, 15
+	vsro	19, 19, 17		# 0x00..xxxx??..??
+	sldi	15, 17, 3
+	mtvsrdd	32+17, 0, 15
+	vsro	19, 19, 17		# 0x00..xxxx
+	vslo	19, 19, 17		# shift back to form 0x00..xxxx00..00
+
+	# AES crypt partial
+	xxlxor	32+15, 32+30, 0
+	lwz	23, 240(6)	# n rounds
+	addi	22, 23, -1	# loop - 1
+	mtctr	22
+	addi	10, 6, 16
+
+__Loop_aes_cpstate:
+	lxv	32+1, 0(10)
+	vcipher	15, 15, 1
+	addi	10, 10, 16
+	bdnz	__Loop_aes_cpstate
+	lxv	32+1, 0(10)		# last round key
+	vcipherlast 15, 15, 1
 
-	li	16, 16
-	lxvb16x 32+29, 16, 8
-	vxor	0, 0, 29
-	stxvb16x 32, 0, 8		# save Xi
-	stxvb16x 32, 16, 8		# save Xi
-
-	# store partial block
-	# loop the rest of the stream if any
-	sldi	16, 15, 3
-	mtvsrdd	32+16, 0, 16
-	vslo	15, 15, 16
-	#stxvb16x 15+32, 0, 9		# last block
+	vxor	15, 15, 19
+	vand	15, 15, 16
 
-	li	16, 16
-	sub	17, 16, 15		# 16 - partial
-
-	add	16, 15, 5
-	cmpdi	16, 16
-	bgt	Larger_16
-	mr	17, 5
-Larger_16:
-
-	# write partial
-	li		10, 192
-	stxvb16x	15+32, 10, 1	# save current block
-
-	addi		10, 9, -1
-	addi		16, 1, 191
-	mtctr		17		# move partial byte count
-
-Write_last_partial:
-        lbzu		18, 1(16)
-	stbu		18, 1(10)
-        bdnz		Write_last_partial
-	# Complete loop partial
-
-	add	14, 14, 17
-	add	9, 9, 17
-	sub	12, 12, 17
-	add	11, 11, 17
-
-	add	15, 15, 5
-	cmpdi	15, 16
-	blt	Save_partial
-
-	vaddudm	30, 30, 31
-	stxvb16x 30+32, 0, 7		# update IV
-	xxlor	32+29, 0, 0
-	vxor	15, 30, 29		# IV + round key - add round key 0
-	li	15, 0
-	std	15, 56(7)		# partial done - clear
-	b	Partial_done
-Save_partial:
-	std	15, 56(7)		# partial
-
-Partial_done:
+	# AES crypt output v15
+	# Write partial
+	li	10, 224
+	stxvb16x 15+32, 10, 1		# write v15 to stack
+	addi	10, 1, 223
+	add	10, 10, 12		# add offset
+	addi	15, 9, -1
+        mtctr	21			# partial block len
+__Write_combine_partial:
+        lbzu	22, 1(10)
+	stbu	22, 1(15)
+        bdnz	__Write_combine_partial
+
+	add	14, 14, 21
+	add	11, 11, 21
+	add	9, 9, 21
+	sub	5, 5, 21
+
+	# Encrypt/Decrypt?
+	cmpdi	24, 0			# decrypt?
+	bne	__Encrypt_combine_partial
+	vmr	15, 19		# decrypt using the input block
+
+__Encrypt_combine_partial:
+	#
+	# Update partial flag and combine ghash.
+__Update_partial_ghash:
+	li	10, 64
+	lxvb16x 32+17, 10, 7		# load previous pblock
+	add	12, 12, 21		# combined pprocessed
+	vxor	15, 15, 17		# combined pblock
+
+	cmpdi	12, 16
+	beq	__Clear_partial_flag
+	std	12, 56(7)		# update partial len
+	stxvb16x 32+15, 10, 7		# Update current pblock
 	blr
 
- #
- # Write partial block
- # r9 - output
- # r12 - remaining bytes
- # v15 - partial input data
- #
-SYM_FUNC_START_LOCAL(Write_partial_block)
-	li		10, 192
-	stxvb16x	15+32, 10, 1		# last block
-
-	addi		10, 9, -1
-	addi		16, 1, 191
-
-        mtctr		12			# remaining bytes
-	li		15, 0
-
-Write_last_byte:
-        lbzu		14, 1(16)
-	stbu		14, 1(10)
-        bdnz		Write_last_byte
+__Clear_partial_flag:
+	li	12, 0
+	std	12, 56(7)
+	# Update IV and ghash here
+	vadduwm	30, 30, 31		# increase IV
+	stxvb16x 32+30, 0, 7		# update IV
+
+	# v15 either is either (input blockor encrypted)^(AES state)
+	vxor	15, 15, 0
+	PPC_GHASH1x 0, 15
+	stxvb16x 32+0, 10, 7		# update pblock for debug?
+	stxvb16x 32+0, 0, 8		# update Xi
 	blr
-SYM_FUNC_END(Write_partial_block)
+SYM_FUNC_END(__Combine_partial)
 
-aes_gcm_out:
-	# out = state
-	stxvb16x	32, 0, 8		# write out Xi
-	add	3, 11, 12		# return count
+################################################################################
+# gcm_update(iv, Xi) - compute last hash
+#
+################################################################################
+SYM_FUNC_START(gcm_update)
 
-	RESTORE_REGS
-	blr
+	ld	10, 56(3)
+	cmpdi	10, 0
+	beq	__no_update
 
- #
- # 8x Decrypt
- #
-_GLOBAL(aes_p10_gcm_decrypt)
-.align 5
+	lxvb16x	32, 0, 4	# load Xi
+	# load Hash - h^4, h^3, h^2, h
+	li	10, 32
+	lxvd2x	2+32, 10, 4	# H Poli
+	li	10, 48
+	lxvd2x	3+32, 10, 4	# Hl
+	li	10, 64
+	lxvd2x	4+32, 10, 4	# H
+	li	10, 80
+	lxvd2x	5+32, 10, 4	# Hh
+
+	addis	11, 2, permx@toc@ha
+	addi	11, 11, permx@toc@l
+	lxv	10, 0(11)	# vs10: vpermxor vector
+
+	li	9, 64
+	lxvb16x 32+6, 9, 3		# load pblock
+	vxor	6, 6, 0
+
+	vxor	1, 1, 1
+	vpmsumd	12, 3, 6		# L
+	vpmsumd	13, 4, 6		# M
+	vpmsumd	14, 5, 6		# H
+	vpmsumd	17, 12, 2		# reduction
+	vsldoi	15, 13, 1, 8		# mL
+	vsldoi	16, 1, 13, 8		# mH
+	vxor	12, 12, 15		# LL + LL
+	vxor	14, 14, 16		# HH + HH
+	xxlor	32+15, 10, 10
+	vpermxor 12, 12, 17, 15
+	vsldoi	13, 12, 12, 8		# swap
+	vpmsumd	12, 12, 2		# reduction
+	vxor	13, 13, 14
+	vxor	7, 12, 13
+
+	#vxor	0, 0, 0
+	#stxvb16x 32+0, 9, 3
+	li	10, 0
+	std	10, 56(3)
+	stxvb16x 32+7, 0, 4
+
+__no_update:
+	blr
+SYM_FUNC_END(gcm_update)
+
+################################################################################
+# aes_p10_gcm_encrypt (const void *inp, void *out, size_t len,
+#               const char *rk, unsigned char iv[16], void *Xip);
+#
+#    r3 - inp
+#    r4 - out
+#    r5 - len
+#    r6 - AES round keys
+#    r7 - iv and other data
+#    r8 - Xi, HPoli, hash keys
+#
+#    rounds is at offset 240 in rk
+#    Xi is at 0 in gcm_table (Xip).
+#
+################################################################################
+SYM_FUNC_START(aes_p10_gcm_encrypt)
+
+	cmpdi	5, 0
+	ble	__Invalid_msg_len
 
 	SAVE_REGS
-
 	LOAD_HASH_TABLE
 
 	# initialize ICB: GHASH( IV ), IV - r7
 	lxvb16x	30+32, 0, 7	# load IV  - v30
 
-	mr	12, 5		# length
-	li	11, 0		# block index
+	mr	14, 3
+	mr	9, 4
 
 	# counter 1
 	vxor	31, 31, 31
 	vspltisb 22, 1
 	vsldoi	31, 31, 22,1	# counter 1
 
-	# load round key to VSR
-	lxv	0, 0(6)
-	lxv	1, 0x10(6)
-	lxv	2, 0x20(6)
-	lxv	3, 0x30(6)
-	lxv	4, 0x40(6)
-	lxv	5, 0x50(6)
-	lxv	6, 0x60(6)
-	lxv	7, 0x70(6)
-	lxv	8, 0x80(6)
-	lxv	9, 0x90(6)
-	lxv	10, 0xa0(6)
+	addis	11, 2, permx@toc@ha
+	addi	11, 11, permx@toc@l
+	lxv	10, 0(11)	# vs10: vpermxor vector
+	li	11, 0
+
+	# load 9 round keys to VSR
+	lxv	0, 0(6)			# round key 0
+	lxv	1, 16(6)		# round key 1
+	lxv	2, 32(6)		# round key 2
+	lxv	3, 48(6)		# round key 3
+	lxv	4, 64(6)		# round key 4
+	lxv	5, 80(6)		# round key 5
+	lxv	6, 96(6)		# round key 6
+	lxv	7, 112(6)		# round key 7
+	lxv	8, 128(6)		# round key 8
 
 	# load rounds - 10 (128), 12 (192), 14 (256)
-	lwz	9,240(6)
+	lwz	23, 240(6)		# n rounds
+	li	24, 1			# encrypt
 
+__Process_encrypt:
 	#
-	# vxor	state, state, w # addroundkey
-	xxlor	32+29, 0, 0
-	vxor	15, 30, 29	# IV + round key - add round key 0
-
-	cmpdi	9, 10
-	beq	Loop_aes_gcm_8x_dec
-
-	# load 2 more round keys (v11, v12)
-	lxv	11, 0xb0(6)
-	lxv	12, 0xc0(6)
-
-	cmpdi	9, 12
-	beq	Loop_aes_gcm_8x_dec
-
-	# load 2 more round keys (v11, v12, v13, v14)
-	lxv	13, 0xd0(6)
-	lxv	14, 0xe0(6)
-	cmpdi	9, 14
-	beq	Loop_aes_gcm_8x_dec
+	# Process different blocks
+	#
+	ld	12, 56(7)
+	cmpdi	12, 0
+	bgt	__Do_combine_enc
+	cmpdi	5, 128
+	blt	__Process_more_enc
+
+#
+# Process 8x AES/GCM blocks
+#
+__Process_8x_enc:
+	# 8x blcoks
+	li	10, 128
+	divdu	12, 5, 10	# n 128 bytes-blocks
 
-	b	aes_gcm_out
+	addi	12, 12, -1	# loop - 1
 
-.align 5
-Loop_aes_gcm_8x_dec:
-	mr	14, 3
-	mr	9, 4
+	vmr	15, 30		# first state: IV
+	vadduwm	16, 15, 31	# state + counter
+	vadduwm	17, 16, 31
+	vadduwm	18, 17, 31
+	vadduwm	19, 18, 31
+	vadduwm	20, 19, 31
+	vadduwm	21, 20, 31
+	vadduwm	22, 21, 31
+	xxlor	9, 32+22, 32+22	# save last state
 
-	#
-	# check partial block
-	#
-Continue_partial_check_dec:
-	ld	15, 56(7)
-	cmpdi	15, 0
-	beq	Continue_dec
-	bgt	Final_block_dec
-	cmpdi	15, 16
-	blt	Final_block_dec
-
-Continue_dec:
-	# n blcoks
-	li	10, 128
-	divdu	10, 12, 10	# n 128 bytes-blocks
-	cmpdi	10, 0
-	beq	Loop_last_block_dec
-
-	vaddudm	30, 30, 31	# IV + counter
-	vxor	16, 30, 29
-	vaddudm	30, 30, 31
-	vxor	17, 30, 29
-	vaddudm	30, 30, 31
-	vxor	18, 30, 29
-	vaddudm	30, 30, 31
-	vxor	19, 30, 29
-	vaddudm	30, 30, 31
-	vxor	20, 30, 29
-	vaddudm	30, 30, 31
-	vxor	21, 30, 29
-	vaddudm	30, 30, 31
-	vxor	22, 30, 29
-
-	mtctr	10
+	# vxor  state, state, w # addroundkey
+	xxlor	32+29, 0, 0
+        vxor    15, 15, 29      # IV + round key - add round key 0
+	vxor	16, 16, 29
+	vxor	17, 17, 29
+	vxor	18, 18, 29
+	vxor	19, 19, 29
+	vxor	20, 20, 29
+	vxor	21, 21, 29
+	vxor	22, 22, 29
 
 	li	15, 16
 	li	16, 32
@@ -1217,305 +735,502 @@ Continue_dec:
 	li	20, 96
 	li	21, 112
 
-	lwz	10, 240(6)
-
-Loop_8x_block_dec:
-
-	lxvb16x		15, 0, 14	# load block
-	lxvb16x		16, 15, 14	# load block
-	lxvb16x		17, 16, 14	# load block
-	lxvb16x		18, 17, 14	# load block
-	lxvb16x		19, 18, 14	# load block
-	lxvb16x		20, 19, 14	# load block
-	lxvb16x		21, 20, 14	# load block
-	lxvb16x		22, 21, 14	# load block
-	addi		14, 14, 128
-
-	Loop_aes_middle8x
-
-	xxlor	23+32, 10, 10
-
-	cmpdi	10, 10
-	beq	Do_next_ghash_dec
-
-	# 192 bits
-	xxlor	24+32, 11, 11
-
-	vcipher	15, 15, 23
-	vcipher	16, 16, 23
-	vcipher	17, 17, 23
-	vcipher	18, 18, 23
-	vcipher	19, 19, 23
-	vcipher	20, 20, 23
-	vcipher	21, 21, 23
-	vcipher	22, 22, 23
-
-	vcipher	15, 15, 24
-	vcipher	16, 16, 24
-	vcipher	17, 17, 24
-	vcipher	18, 18, 24
-	vcipher	19, 19, 24
-	vcipher	20, 20, 24
-	vcipher	21, 21, 24
-	vcipher	22, 22, 24
-
-	xxlor	23+32, 12, 12
-
-	cmpdi	10, 12
-	beq	Do_next_ghash_dec
-
-	# 256 bits
-	xxlor	24+32, 13, 13
-
-	vcipher	15, 15, 23
-	vcipher	16, 16, 23
-	vcipher	17, 17, 23
-	vcipher	18, 18, 23
-	vcipher	19, 19, 23
-	vcipher	20, 20, 23
-	vcipher	21, 21, 23
-	vcipher	22, 22, 23
-
-	vcipher	15, 15, 24
-	vcipher	16, 16, 24
-	vcipher	17, 17, 24
-	vcipher	18, 18, 24
-	vcipher	19, 19, 24
-	vcipher	20, 20, 24
-	vcipher	21, 21, 24
-	vcipher	22, 22, 24
-
-	xxlor	23+32, 14, 14
-
-	cmpdi	10, 14
-	beq	Do_next_ghash_dec
-	b	aes_gcm_out
+	#
+	# Pre-compute first 8 AES state and leave 1/3/5 more rounds
+	# for the loop.
+	#
+	addi	22, 23, -9		# process 8 keys
+	mtctr	22			# AES key loop
+	addi	10, 6, 144
 
-Do_next_ghash_dec:
+	LOOP_8AES_STATE			# process 8 AES keys
 
-	#
-	# last round
-	vcipherlast     15, 15, 23
-	vcipherlast     16, 16, 23
-
-	xxlxor		47, 47, 15
-	stxvb16x        47, 0, 9	# store output
-	xxlxor		48, 48, 16
-	stxvb16x        48, 15, 9	# store output
-
-	vcipherlast     17, 17, 23
-	vcipherlast     18, 18, 23
-
-	xxlxor		49, 49, 17
-	stxvb16x        49, 16, 9	# store output
-	xxlxor		50, 50, 18
-	stxvb16x        50, 17, 9	# store output
-
-	vcipherlast     19, 19, 23
-	vcipherlast     20, 20, 23
-
-	xxlxor		51, 51, 19
-	stxvb16x        51, 18, 9	# store output
-	xxlxor		52, 52, 20
-	stxvb16x        52, 19, 9	# store output
-
-	vcipherlast     21, 21, 23
-	vcipherlast     22, 22, 23
-
-	xxlxor		53, 53, 21
-	stxvb16x        53, 20, 9	# store output
-	xxlxor		54, 54, 22
-	stxvb16x        54, 21, 9	# store output
-
-	addi		9, 9, 128
-
-	xxlor           15+32, 15, 15
-	xxlor           16+32, 16, 16
-	xxlor           17+32, 17, 17
-	xxlor           18+32, 18, 18
-	xxlor           19+32, 19, 19
-	xxlor           20+32, 20, 20
-	xxlor           21+32, 21, 21
-	xxlor           22+32, 22, 22
+__PreLoop_aes_state:
+	lxv	32+1, 0(10)		# round key
+	AES_CIPHER_8x vcipher 15 1
+	addi	10, 10, 16
+	bdnz	__PreLoop_aes_state
+	lxv	32+1, 0(10)		# last round key (v1)
+
+	cmpdi	12, 0			# Only one loop (8 block)
+	beq	__Finish_ghash
+
+#
+# Loop 8x blocks and compute ghash
+#
+__Loop_8x_block_enc:
+	vcipherlast     15, 15, 1
+	vcipherlast     16, 16, 1
+	vcipherlast     17, 17, 1
+	vcipherlast     18, 18, 1
+	vcipherlast     19, 19, 1
+	vcipherlast     20, 20, 1
+	vcipherlast     21, 21, 1
+	vcipherlast     22, 22, 1
+
+	lxvb16x	32+23, 0, 14	# load block
+	lxvb16x	32+24, 15, 14	# load block
+	lxvb16x	32+25, 16, 14	# load block
+	lxvb16x	32+26, 17, 14	# load block
+	lxvb16x	32+27, 18, 14	# load block
+	lxvb16x	32+28, 19, 14	# load block
+	lxvb16x	32+29, 20, 14	# load block
+	lxvb16x	32+30, 21, 14	# load block
+	addi	14, 14, 128
+
+	vxor	15, 15, 23
+	vxor	16, 16, 24
+	vxor	17, 17, 25
+	vxor	18, 18, 26
+	vxor	19, 19, 27
+	vxor	20, 20, 28
+	vxor	21, 21, 29
+	vxor	22, 22, 30
+
+	stxvb16x 47, 0, 9	# store output
+	stxvb16x 48, 15, 9	# store output
+	stxvb16x 49, 16, 9	# store output
+	stxvb16x 50, 17, 9	# store output
+	stxvb16x 51, 18, 9	# store output
+	stxvb16x 52, 19, 9	# store output
+	stxvb16x 53, 20, 9	# store output
+	stxvb16x 54, 21, 9	# store output
+	addi	9, 9, 128
 
 	# ghash here
-	ppc_aes_gcm_ghash2_4x
-
-	xxlor	27+32, 0, 0
-	vaddudm 30, 30, 31		# IV + counter
-	vmr	29, 30
-	vxor    15, 30, 27		# add round key
-	vaddudm 30, 30, 31
-	vxor    16, 30, 27
-	vaddudm 30, 30, 31
-	vxor    17, 30, 27
-	vaddudm 30, 30, 31
-	vxor    18, 30, 27
-	vaddudm 30, 30, 31
-	vxor    19, 30, 27
-	vaddudm 30, 30, 31
-	vxor    20, 30, 27
-	vaddudm 30, 30, 31
-	vxor    21, 30, 27
-	vaddudm 30, 30, 31
-	vxor    22, 30, 27
-
-	addi    12, 12, -128
+	vxor	15, 15, 0
+	PPC_GHASH4x 0, 15, 16, 17, 18
+
+	vxor	19, 19, 0
+	PPC_GHASH4x 0, 19, 20, 21, 22
+
+	xxlor	32+15, 9, 9		# last state
+	vadduwm 15, 15, 31		# state + counter
+	vadduwm 16, 15, 31
+	vadduwm 17, 16, 31
+	vadduwm 18, 17, 31
+	vadduwm 19, 18, 31
+	vadduwm 20, 19, 31
+	vadduwm 21, 20, 31
+	vadduwm 22, 21, 31
+	xxlor	9, 32+22, 32+22		# save last state
+
+	xxlor	32+27, 0, 0		# restore roundkey 0
+        vxor    15, 15, 27		# IV + round key - add round key 0
+	vxor	16, 16, 27
+	vxor	17, 17, 27
+	vxor	18, 18, 27
+	vxor	19, 19, 27
+	vxor	20, 20, 27
+	vxor	21, 21, 27
+	vxor	22, 22, 27
+
+	addi    5, 5, -128
 	addi    11, 11, 128
 
-	bdnz	Loop_8x_block_dec
-
-	vmr	30, 29
-	stxvb16x 30+32, 0, 7		# update IV
-
-Loop_last_block_dec:
-	cmpdi   12, 0
-	beq     aes_gcm_out
-
-	# loop last few blocks
-	li      10, 16
-	divdu   10, 12, 10
-
-	mtctr   10
-
-	lwz	10, 240(6)
-
-	cmpdi   12, 16
-	blt     Final_block_dec
-
-Next_rem_block_dec:
-	lxvb16x 15, 0, 14		# load block
-
-	Loop_aes_middle_1x
-
-	xxlor	23+32, 10, 10
+	LOOP_8AES_STATE			# process 8 AES keys
+	mtctr	22			# AES key loop
+	addi	10, 6, 144
+__LastLoop_aes_state:
+	lxv	32+1, 0(10)		# round key
+	AES_CIPHER_8x vcipher 15 1
+	addi	10, 10, 16
+	bdnz	__LastLoop_aes_state
+	lxv	32+1, 0(10)		# last round key (v1)
 
-	cmpdi	10, 10
-	beq	Do_next_1x_dec
+	addi	12, 12, -1
+	cmpdi	12, 0
+	bne	__Loop_8x_block_enc
+
+__Finish_ghash:
+	vcipherlast     15, 15, 1
+	vcipherlast     16, 16, 1
+	vcipherlast     17, 17, 1
+	vcipherlast     18, 18, 1
+	vcipherlast     19, 19, 1
+	vcipherlast     20, 20, 1
+	vcipherlast     21, 21, 1
+	vcipherlast     22, 22, 1
+
+	lxvb16x	32+23, 0, 14	# load block
+	lxvb16x	32+24, 15, 14	# load block
+	lxvb16x	32+25, 16, 14	# load block
+	lxvb16x	32+26, 17, 14	# load block
+	lxvb16x	32+27, 18, 14	# load block
+	lxvb16x	32+28, 19, 14	# load block
+	lxvb16x	32+29, 20, 14	# load block
+	lxvb16x	32+30, 21, 14	# load block
+	addi	14, 14, 128
+
+	vxor	15, 15, 23
+	vxor	16, 16, 24
+	vxor	17, 17, 25
+	vxor	18, 18, 26
+	vxor	19, 19, 27
+	vxor	20, 20, 28
+	vxor	21, 21, 29
+	vxor	22, 22, 30
+
+	stxvb16x 47, 0, 9	# store output
+	stxvb16x 48, 15, 9	# store output
+	stxvb16x 49, 16, 9	# store output
+	stxvb16x 50, 17, 9	# store output
+	stxvb16x 51, 18, 9	# store output
+	stxvb16x 52, 19, 9	# store output
+	stxvb16x 53, 20, 9	# store output
+	stxvb16x 54, 21, 9	# store output
+	addi	9, 9, 128
+
+	vxor	15, 15, 0
+	PPC_GHASH4x 0, 15, 16, 17, 18
+
+	vxor	19, 19, 0
+	PPC_GHASH4x 0, 19, 20, 21, 22
+
+	xxlor	30+32, 9, 9		# last ctr
+	vadduwm	30, 30, 31		# increase ctr
+	stxvb16x 32+30, 0, 7		# update IV
+	stxvb16x 32+0, 0, 8		# update Xi
+
+	addi    5, 5, -128
+	addi    11, 11, 128
 
-	# 192 bits
-	xxlor	24+32, 11, 11
+	#
+	# Done 8x blocks
+	#
 
-	vcipher	15, 15, 23
-	vcipher	15, 15, 24
+	cmpdi   5, 0
+	beq     aes_gcm_out
 
-	xxlor	23+32, 12, 12
+__Process_more_enc:
+	li	24, 1			# encrypt
+	bl	aes_gcm_crypt_1x
+	cmpdi   5, 0
+	beq     aes_gcm_out
 
-	cmpdi	10, 12
-	beq	Do_next_1x_dec
+	bl	__Process_partial
+	cmpdi   5, 0
+	beq     aes_gcm_out
+__Do_combine_enc:
+	bl	__Combine_partial
+	cmpdi	5, 0
+	bgt	__Process_encrypt
+	b	aes_gcm_out
 
-	# 256 bits
-	xxlor	24+32, 13, 13
+SYM_FUNC_END(aes_p10_gcm_encrypt)
 
-	vcipher	15, 15, 23
-	vcipher	15, 15, 24
+################################################################################
+# aes_p10_gcm_decrypt (const void *inp, void *out, size_t len,
+#               const char *rk, unsigned char iv[16], void *Xip);
+# 8x Decrypt
+#
+################################################################################
+SYM_FUNC_START(aes_p10_gcm_decrypt)
 
-	xxlor	23+32, 14, 14
+	cmpdi	5, 0
+	ble	__Invalid_msg_len
 
-	cmpdi	10, 14
-	beq	Do_next_1x_dec
+	SAVE_REGS
+	LOAD_HASH_TABLE
 
-Do_next_1x_dec:
-	vcipherlast     15, 15, 23
+	# initialize ICB: GHASH( IV ), IV - r7
+	lxvb16x	30+32, 0, 7	# load IV  - v30
 
-	xxlxor		47, 47, 15
-	stxvb16x	47, 0, 9	# store output
-	addi		14, 14, 16
-	addi		9, 9, 16
+	mr	14, 3
+	mr	9, 4
 
-	xxlor           28+32, 15, 15
-	#vmr		28, 15
-	ppc_update_hash_1x
+	# counter 1
+	vxor	31, 31, 31
+	vspltisb 22, 1
+	vsldoi	31, 31, 22,1	# counter 1
 
-	addi		12, 12, -16
-	addi		11, 11, 16
-	xxlor		19+32, 0, 0
-	vaddudm		30, 30, 31		# IV + counter
-	vxor		15, 30, 19		# add round key
+	addis	11, 2, permx@toc@ha
+	addi	11, 11, permx@toc@l
+	lxv	10, 0(11)	# vs10: vpermxor vector
+	li	11, 0
+
+	# load 9 round keys to VSR
+	lxv	0, 0(6)			# round key 0
+	lxv	1, 16(6)		# round key 1
+	lxv	2, 32(6)		# round key 2
+	lxv	3, 48(6)		# round key 3
+	lxv	4, 64(6)		# round key 4
+	lxv	5, 80(6)		# round key 5
+	lxv	6, 96(6)		# round key 6
+	lxv	7, 112(6)		# round key 7
+	lxv	8, 128(6)		# round key 8
 
-	bdnz	Next_rem_block_dec
+	# load rounds - 10 (128), 12 (192), 14 (256)
+	lwz	23, 240(6)		# n rounds
+	li	24, 0			# decrypt
 
-	li	15, 0
-	std	15, 56(7)		# clear partial?
-	stxvb16x 30+32, 0, 7		# update IV
+__Process_decrypt:
+	#
+	# Process different blocks
+	#
+	ld	12, 56(7)
 	cmpdi	12, 0
-	beq	aes_gcm_out
-
-Final_block_dec:
-	lwz	10, 240(6)
-	Loop_aes_middle_1x
-
-	xxlor	23+32, 10, 10
-
-	cmpdi	10, 10
-	beq	Do_final_1x_dec
+	bgt	__Do_combine_dec
+	cmpdi	5, 128
+	blt	__Process_more_dec
+
+#
+# Process 8x AES/GCM blocks
+#
+__Process_8x_dec:
+	# 8x blcoks
+	li	10, 128
+	divdu	12, 5, 10	# n 128 bytes-blocks
 
-	# 192 bits
-	xxlor	24+32, 11, 11
+	addi	12, 12, -1	# loop - 1
 
-	vcipher	15, 15, 23
-	vcipher	15, 15, 24
+	vmr	15, 30		# first state: IV
+	vadduwm	16, 15, 31	# state + counter
+	vadduwm	17, 16, 31
+	vadduwm	18, 17, 31
+	vadduwm	19, 18, 31
+	vadduwm	20, 19, 31
+	vadduwm	21, 20, 31
+	vadduwm	22, 21, 31
+	xxlor	9, 32+22, 32+22	# save last state
 
-	xxlor	23+32, 12, 12
+	# vxor  state, state, w # addroundkey
+	xxlor	32+29, 0, 0
+        vxor    15, 15, 29      # IV + round key - add round key 0
+	vxor	16, 16, 29
+	vxor	17, 17, 29
+	vxor	18, 18, 29
+	vxor	19, 19, 29
+	vxor	20, 20, 29
+	vxor	21, 21, 29
+	vxor	22, 22, 29
 
-	cmpdi	10, 12
-	beq	Do_final_1x_dec
+	li	15, 16
+	li	16, 32
+	li	17, 48
+	li	18, 64
+	li	19, 80
+	li	20, 96
+	li	21, 112
 
-	# 256 bits
-	xxlor	24+32, 13, 13
+	#
+	# Pre-compute first 8 AES state and leave 1/3/5 more rounds
+	# for the loop.
+	#
+	addi	22, 23, -9		# process 8 keys
+	mtctr	22			# AES key loop
+	addi	10, 6, 144
 
-	vcipher	15, 15, 23
-	vcipher	15, 15, 24
+	LOOP_8AES_STATE			# process 8 AES keys
 
-	xxlor	23+32, 14, 14
+__PreLoop_aes_state_dec:
+	lxv	32+1, 0(10)		# round key
+	AES_CIPHER_8x vcipher 15 1
+	addi	10, 10, 16
+	bdnz	__PreLoop_aes_state_dec
+	lxv	32+1, 0(10)		# last round key (v1)
+
+	cmpdi	12, 0			# Only one loop (8 block)
+	beq	__Finish_ghash_dec
+
+#
+# Loop 8x blocks and compute ghash
+#
+__Loop_8x_block_dec:
+	vcipherlast     15, 15, 1
+	vcipherlast     16, 16, 1
+	vcipherlast     17, 17, 1
+	vcipherlast     18, 18, 1
+	vcipherlast     19, 19, 1
+	vcipherlast     20, 20, 1
+	vcipherlast     21, 21, 1
+	vcipherlast     22, 22, 1
+
+	lxvb16x	32+23, 0, 14	# load block
+	lxvb16x	32+24, 15, 14	# load block
+	lxvb16x	32+25, 16, 14	# load block
+	lxvb16x	32+26, 17, 14	# load block
+	lxvb16x	32+27, 18, 14	# load block
+	lxvb16x	32+28, 19, 14	# load block
+	lxvb16x	32+29, 20, 14	# load block
+	lxvb16x	32+30, 21, 14	# load block
+	addi	14, 14, 128
+
+	vxor	15, 15, 23
+	vxor	16, 16, 24
+	vxor	17, 17, 25
+	vxor	18, 18, 26
+	vxor	19, 19, 27
+	vxor	20, 20, 28
+	vxor	21, 21, 29
+	vxor	22, 22, 30
+
+	stxvb16x 47, 0, 9	# store output
+	stxvb16x 48, 15, 9	# store output
+	stxvb16x 49, 16, 9	# store output
+	stxvb16x 50, 17, 9	# store output
+	stxvb16x 51, 18, 9	# store output
+	stxvb16x 52, 19, 9	# store output
+	stxvb16x 53, 20, 9	# store output
+	stxvb16x 54, 21, 9	# store output
+
+	addi	9, 9, 128
+
+	vmr	15, 23
+	vmr	16, 24
+	vmr	17, 25
+	vmr	18, 26
+	vmr	19, 27
+	vmr	20, 28
+	vmr	21, 29
+	vmr	22, 30
 
-	cmpdi	10, 14
-	beq	Do_final_1x_dec
+	# ghash here
+	vxor	15, 15, 0
+	PPC_GHASH4x 0, 15, 16, 17, 18
+
+	vxor	19, 19, 0
+	PPC_GHASH4x 0, 19, 20, 21, 22
+
+	xxlor	32+15, 9, 9		# last state
+	vadduwm 15, 15, 31		# state + counter
+	vadduwm 16, 15, 31
+	vadduwm 17, 16, 31
+	vadduwm 18, 17, 31
+	vadduwm 19, 18, 31
+	vadduwm 20, 19, 31
+	vadduwm 21, 20, 31
+	vadduwm 22, 21, 31
+	xxlor	9, 32+22, 32+22		# save last state
+
+	xxlor	32+27, 0, 0		# restore roundkey 0
+        vxor    15, 15, 27		# IV + round key - add round key 0
+	vxor	16, 16, 27
+	vxor	17, 17, 27
+	vxor	18, 18, 27
+	vxor	19, 19, 27
+	vxor	20, 20, 27
+	vxor	21, 21, 27
+	vxor	22, 22, 27
+
+	addi    5, 5, -128
+	addi    11, 11, 128
 
-Do_final_1x_dec:
-	vcipherlast     15, 15, 23
+	LOOP_8AES_STATE			# process 8 AES keys
+	mtctr	22			# AES key loop
+	addi	10, 6, 144
+__LastLoop_aes_state_dec:
+	lxv	32+1, 0(10)		# round key
+	AES_CIPHER_8x vcipher 15 1
+	addi	10, 10, 16
+	bdnz	__LastLoop_aes_state_dec
+	lxv	32+1, 0(10)		# last round key (v1)
 
-	# check partial block
-	li	21, 1			# decrypt
-	ld	15, 56(7)		# partial?
-	cmpdi	15, 0
-	beq	Normal_block_dec
-	bl	Do_partial_block
+	addi	12, 12, -1
 	cmpdi	12, 0
-	ble aes_gcm_out
-
-	b Continue_partial_check_dec
+	bne	__Loop_8x_block_dec
+
+__Finish_ghash_dec:
+	vcipherlast     15, 15, 1
+	vcipherlast     16, 16, 1
+	vcipherlast     17, 17, 1
+	vcipherlast     18, 18, 1
+	vcipherlast     19, 19, 1
+	vcipherlast     20, 20, 1
+	vcipherlast     21, 21, 1
+	vcipherlast     22, 22, 1
+
+	lxvb16x	32+23, 0, 14	# load block
+	lxvb16x	32+24, 15, 14	# load block
+	lxvb16x	32+25, 16, 14	# load block
+	lxvb16x	32+26, 17, 14	# load block
+	lxvb16x	32+27, 18, 14	# load block
+	lxvb16x	32+28, 19, 14	# load block
+	lxvb16x	32+29, 20, 14	# load block
+	lxvb16x	32+30, 21, 14	# load block
+	addi	14, 14, 128
+
+	vxor	15, 15, 23
+	vxor	16, 16, 24
+	vxor	17, 17, 25
+	vxor	18, 18, 26
+	vxor	19, 19, 27
+	vxor	20, 20, 28
+	vxor	21, 21, 29
+	vxor	22, 22, 30
+
+	stxvb16x 47, 0, 9	# store output
+	stxvb16x 48, 15, 9	# store output
+	stxvb16x 49, 16, 9	# store output
+	stxvb16x 50, 17, 9	# store output
+	stxvb16x 51, 18, 9	# store output
+	stxvb16x 52, 19, 9	# store output
+	stxvb16x 53, 20, 9	# store output
+	stxvb16x 54, 21, 9	# store output
+	addi	9, 9, 128
+
+	#vmr	15, 23
+	vxor	15, 23, 0
+	vmr	16, 24
+	vmr	17, 25
+	vmr	18, 26
+	vmr	19, 27
+	vmr	20, 28
+	vmr	21, 29
+	vmr	22, 30
+
+	#vxor	15, 15, 0
+	PPC_GHASH4x 0, 15, 16, 17, 18
+
+	vxor	19, 19, 0
+	PPC_GHASH4x 0, 19, 20, 21, 22
+
+	xxlor	30+32, 9, 9		# last ctr
+	vadduwm	30, 30, 31		# increase ctr
+	stxvb16x 32+30, 0, 7		# update IV
+	stxvb16x 32+0, 0, 8		# update Xi
+
+	addi    5, 5, -128
+	addi    11, 11, 128
 
-Normal_block_dec:
-	lxvb16x	15, 0, 14		# load last block
-	xxlxor	47, 47, 15
+	#
+	# Done 8x blocks
+	#
 
-	# create partial block mask
-	li	15, 16
-	sub	15, 15, 12		# index to the mask
+	cmpdi   5, 0
+	beq     aes_gcm_out
 
-	vspltisb	16, -1		# first 16 bytes - 0xffff...ff
-	vspltisb	17, 0		# second 16 bytes - 0x0000...00
-	li	10, 192
-	stvx	16, 10, 1
-	addi	10, 10, 16
-	stvx	17, 10, 1
+__Process_more_dec:
+	li	24, 0			# decrypt
+	bl	aes_gcm_crypt_1x
+	cmpdi   5, 0
+	beq     aes_gcm_out
 
-	addi	10, 1, 192
-	lxvb16x	16, 15, 10		# load partial block mask
-	xxland	47, 47, 16
+	bl	__Process_partial
+	cmpdi   5, 0
+	beq     aes_gcm_out
+__Do_combine_dec:
+	bl	__Combine_partial
+	cmpdi	5, 0
+	bgt	__Process_decrypt
+	b	aes_gcm_out
+SYM_FUNC_END(aes_p10_gcm_decrypt)
 
-	xxland	32+28, 15, 16
-	#vmr	28, 15
-	ppc_update_hash_1x
+SYM_FUNC_START_LOCAL(aes_gcm_out)
 
-	# * should store only the remaining bytes.
-	bl	Write_partial_block
+	mr	3, 11			# return count
 
-	stxvb16x 30+32, 0, 7		# update IV
-	std	12, 56(7)		# update partial?
-	li	16, 16
+	RESTORE_REGS
+	blr
 
-	stxvb16x	32, 0, 8		# write out Xi
-	stxvb16x	32, 16, 8		# write out Xi
-	b aes_gcm_out
+__Invalid_msg_len:
+	li	3, 0
+	blr
+SYM_FUNC_END(aes_gcm_out)
+
+SYM_DATA_START_LOCAL(PERMX)
+.align 4
+# for vector permute and xor
+permx:
+.long 0x4c5d6e7f, 0x08192a3b, 0xc4d5e6f7, 0x8091a2b3
+SYM_DATA_END(permx)
diff --git a/arch/powerpc/crypto/aes.c b/arch/powerpc/crypto/aes.c
new file mode 100644
index 000000000000..3f1e5e894902
--- /dev/null
+++ b/arch/powerpc/crypto/aes.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AES routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ */
+
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/internal/cipher.h>
+#include <crypto/internal/simd.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_ctx {
+	struct crypto_cipher *fallback;
+	struct aes_key enc_key;
+	struct aes_key dec_key;
+};
+
+static int p8_aes_init(struct crypto_tfm *tfm)
+{
+	const char *alg = crypto_tfm_alg_name(tfm);
+	struct crypto_cipher *fallback;
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	fallback = crypto_alloc_cipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+		       "Failed to allocate transformation for '%s': %ld\n",
+		       alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+
+	crypto_cipher_set_flags(fallback,
+				crypto_cipher_get_flags((struct
+							 crypto_cipher *)
+							tfm));
+	ctx->fallback = fallback;
+
+	return 0;
+}
+
+static void p8_aes_exit(struct crypto_tfm *tfm)
+{
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (ctx->fallback) {
+		crypto_free_cipher(ctx->fallback);
+		ctx->fallback = NULL;
+	}
+}
+
+static int p8_aes_setkey(struct crypto_tfm *tfm, const u8 *key,
+			 unsigned int keylen)
+{
+	int ret;
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_vsx();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	ret |= aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	disable_kernel_vsx();
+	pagefault_enable();
+	preempt_enable();
+
+	ret |= crypto_cipher_setkey(ctx->fallback, key, keylen);
+
+	return ret ? -EINVAL : 0;
+}
+
+static void p8_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!crypto_simd_usable()) {
+		crypto_cipher_encrypt_one(ctx->fallback, dst, src);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_vsx();
+		aes_p8_encrypt(src, dst, &ctx->enc_key);
+		disable_kernel_vsx();
+		pagefault_enable();
+		preempt_enable();
+	}
+}
+
+static void p8_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!crypto_simd_usable()) {
+		crypto_cipher_decrypt_one(ctx->fallback, dst, src);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_vsx();
+		aes_p8_decrypt(src, dst, &ctx->dec_key);
+		disable_kernel_vsx();
+		pagefault_enable();
+		preempt_enable();
+	}
+}
+
+struct crypto_alg p8_aes_alg = {
+	.cra_name = "aes",
+	.cra_driver_name = "p8_aes",
+	.cra_module = THIS_MODULE,
+	.cra_priority = 1000,
+	.cra_type = NULL,
+	.cra_flags = CRYPTO_ALG_TYPE_CIPHER | CRYPTO_ALG_NEED_FALLBACK,
+	.cra_alignmask = 0,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct p8_aes_ctx),
+	.cra_init = p8_aes_init,
+	.cra_exit = p8_aes_exit,
+	.cra_cipher = {
+		       .cia_min_keysize = AES_MIN_KEY_SIZE,
+		       .cia_max_keysize = AES_MAX_KEY_SIZE,
+		       .cia_setkey = p8_aes_setkey,
+		       .cia_encrypt = p8_aes_encrypt,
+		       .cia_decrypt = p8_aes_decrypt,
+	},
+};
diff --git a/arch/powerpc/crypto/aes_cbc.c b/arch/powerpc/crypto/aes_cbc.c
new file mode 100644
index 000000000000..5f2a4f375eef
--- /dev/null
+++ b/arch/powerpc/crypto/aes_cbc.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AES CBC routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ */
+
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_cbc_ctx {
+	struct crypto_skcipher *fallback;
+	struct aes_key enc_key;
+	struct aes_key dec_key;
+};
+
+static int p8_aes_cbc_init(struct crypto_skcipher *tfm)
+{
+	struct p8_aes_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *fallback;
+
+	fallback = crypto_alloc_skcipher("cbc(aes)", 0,
+					 CRYPTO_ALG_NEED_FALLBACK |
+					 CRYPTO_ALG_ASYNC);
+	if (IS_ERR(fallback)) {
+		pr_err("Failed to allocate cbc(aes) fallback: %ld\n",
+		       PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+				    crypto_skcipher_reqsize(fallback));
+	ctx->fallback = fallback;
+	return 0;
+}
+
+static void p8_aes_cbc_exit(struct crypto_skcipher *tfm)
+{
+	struct p8_aes_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	crypto_free_skcipher(ctx->fallback);
+}
+
+static int p8_aes_cbc_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			     unsigned int keylen)
+{
+	struct p8_aes_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int ret;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_vsx();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	ret |= aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	disable_kernel_vsx();
+	pagefault_enable();
+	preempt_enable();
+
+	ret |= crypto_skcipher_setkey(ctx->fallback, key, keylen);
+
+	return ret ? -EINVAL : 0;
+}
+
+static int p8_aes_cbc_crypt(struct skcipher_request *req, int enc)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct p8_aes_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int ret;
+
+	if (!crypto_simd_usable()) {
+		struct skcipher_request *subreq = skcipher_request_ctx(req);
+
+		*subreq = *req;
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		return enc ? crypto_skcipher_encrypt(subreq) :
+			     crypto_skcipher_decrypt(subreq);
+	}
+
+	ret = skcipher_walk_virt(&walk, req, false);
+	while ((nbytes = walk.nbytes) != 0) {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_vsx();
+		aes_p8_cbc_encrypt(walk.src.virt.addr,
+				   walk.dst.virt.addr,
+				   round_down(nbytes, AES_BLOCK_SIZE),
+				   enc ? &ctx->enc_key : &ctx->dec_key,
+				   walk.iv, enc);
+		disable_kernel_vsx();
+		pagefault_enable();
+		preempt_enable();
+
+		ret = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
+	}
+	return ret;
+}
+
+static int p8_aes_cbc_encrypt(struct skcipher_request *req)
+{
+	return p8_aes_cbc_crypt(req, 1);
+}
+
+static int p8_aes_cbc_decrypt(struct skcipher_request *req)
+{
+	return p8_aes_cbc_crypt(req, 0);
+}
+
+struct skcipher_alg p8_aes_cbc_alg = {
+	.base.cra_name = "cbc(aes)",
+	.base.cra_driver_name = "p8_aes_cbc",
+	.base.cra_module = THIS_MODULE,
+	.base.cra_priority = 2000,
+	.base.cra_flags = CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize = AES_BLOCK_SIZE,
+	.base.cra_ctxsize = sizeof(struct p8_aes_cbc_ctx),
+	.setkey = p8_aes_cbc_setkey,
+	.encrypt = p8_aes_cbc_encrypt,
+	.decrypt = p8_aes_cbc_decrypt,
+	.init = p8_aes_cbc_init,
+	.exit = p8_aes_cbc_exit,
+	.min_keysize = AES_MIN_KEY_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
+};
diff --git a/arch/powerpc/crypto/aes_ctr.c b/arch/powerpc/crypto/aes_ctr.c
new file mode 100644
index 000000000000..e27c4036e711
--- /dev/null
+++ b/arch/powerpc/crypto/aes_ctr.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AES CTR routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ */
+
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_ctr_ctx {
+	struct crypto_skcipher *fallback;
+	struct aes_key enc_key;
+};
+
+static int p8_aes_ctr_init(struct crypto_skcipher *tfm)
+{
+	struct p8_aes_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *fallback;
+
+	fallback = crypto_alloc_skcipher("ctr(aes)", 0,
+					 CRYPTO_ALG_NEED_FALLBACK |
+					 CRYPTO_ALG_ASYNC);
+	if (IS_ERR(fallback)) {
+		pr_err("Failed to allocate ctr(aes) fallback: %ld\n",
+		       PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+				    crypto_skcipher_reqsize(fallback));
+	ctx->fallback = fallback;
+	return 0;
+}
+
+static void p8_aes_ctr_exit(struct crypto_skcipher *tfm)
+{
+	struct p8_aes_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	crypto_free_skcipher(ctx->fallback);
+}
+
+static int p8_aes_ctr_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			     unsigned int keylen)
+{
+	struct p8_aes_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int ret;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_vsx();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	disable_kernel_vsx();
+	pagefault_enable();
+	preempt_enable();
+
+	ret |= crypto_skcipher_setkey(ctx->fallback, key, keylen);
+
+	return ret ? -EINVAL : 0;
+}
+
+static void p8_aes_ctr_final(const struct p8_aes_ctr_ctx *ctx,
+			     struct skcipher_walk *walk)
+{
+	const u8 *src = walk->src.virt.addr;
+	u8 *ctrblk = walk->iv;
+	u8 keystream[AES_BLOCK_SIZE];
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_vsx();
+	aes_p8_encrypt(ctrblk, keystream, &ctx->enc_key);
+	disable_kernel_vsx();
+	pagefault_enable();
+	preempt_enable();
+
+	crypto_xor_cpy(dst, keystream, src, nbytes);
+	crypto_inc(ctrblk, AES_BLOCK_SIZE);
+}
+
+static int p8_aes_ctr_crypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct p8_aes_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	int ret;
+
+	if (!crypto_simd_usable()) {
+		struct skcipher_request *subreq = skcipher_request_ctx(req);
+
+		*subreq = *req;
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		return crypto_skcipher_encrypt(subreq);
+	}
+
+	ret = skcipher_walk_virt(&walk, req, false);
+	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_vsx();
+		aes_p8_ctr32_encrypt_blocks(walk.src.virt.addr,
+					    walk.dst.virt.addr,
+					    nbytes / AES_BLOCK_SIZE,
+					    &ctx->enc_key, walk.iv);
+		disable_kernel_vsx();
+		pagefault_enable();
+		preempt_enable();
+
+		do {
+			crypto_inc(walk.iv, AES_BLOCK_SIZE);
+		} while ((nbytes -= AES_BLOCK_SIZE) >= AES_BLOCK_SIZE);
+
+		ret = skcipher_walk_done(&walk, nbytes);
+	}
+	if (nbytes) {
+		p8_aes_ctr_final(ctx, &walk);
+		ret = skcipher_walk_done(&walk, 0);
+	}
+	return ret;
+}
+
+struct skcipher_alg p8_aes_ctr_alg = {
+	.base.cra_name = "ctr(aes)",
+	.base.cra_driver_name = "p8_aes_ctr",
+	.base.cra_module = THIS_MODULE,
+	.base.cra_priority = 2000,
+	.base.cra_flags = CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize = 1,
+	.base.cra_ctxsize = sizeof(struct p8_aes_ctr_ctx),
+	.setkey = p8_aes_ctr_setkey,
+	.encrypt = p8_aes_ctr_crypt,
+	.decrypt = p8_aes_ctr_crypt,
+	.init = p8_aes_ctr_init,
+	.exit = p8_aes_ctr_exit,
+	.min_keysize = AES_MIN_KEY_SIZE,
+	.max_keysize = AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
+	.chunksize = AES_BLOCK_SIZE,
+};
diff --git a/arch/powerpc/crypto/aes_xts.c b/arch/powerpc/crypto/aes_xts.c
new file mode 100644
index 000000000000..9440e771cede
--- /dev/null
+++ b/arch/powerpc/crypto/aes_xts.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AES XTS routines supporting VMX In-core instructions on Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Leonidas S. Barbosa <leosilva@linux.vnet.ibm.com>
+ */
+
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/xts.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_xts_ctx {
+	struct crypto_skcipher *fallback;
+	struct aes_key enc_key;
+	struct aes_key dec_key;
+	struct aes_key tweak_key;
+};
+
+static int p8_aes_xts_init(struct crypto_skcipher *tfm)
+{
+	struct p8_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *fallback;
+
+	fallback = crypto_alloc_skcipher("xts(aes)", 0,
+					 CRYPTO_ALG_NEED_FALLBACK |
+					 CRYPTO_ALG_ASYNC);
+	if (IS_ERR(fallback)) {
+		pr_err("Failed to allocate xts(aes) fallback: %ld\n",
+		       PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct skcipher_request) +
+				    crypto_skcipher_reqsize(fallback));
+	ctx->fallback = fallback;
+	return 0;
+}
+
+static void p8_aes_xts_exit(struct crypto_skcipher *tfm)
+{
+	struct p8_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	crypto_free_skcipher(ctx->fallback);
+}
+
+static int p8_aes_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			     unsigned int keylen)
+{
+	struct p8_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int ret;
+
+	ret = xts_verify_key(tfm, key, keylen);
+	if (ret)
+		return ret;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_vsx();
+	ret = aes_p8_set_encrypt_key(key + keylen/2, (keylen/2) * 8, &ctx->tweak_key);
+	ret |= aes_p8_set_encrypt_key(key, (keylen/2) * 8, &ctx->enc_key);
+	ret |= aes_p8_set_decrypt_key(key, (keylen/2) * 8, &ctx->dec_key);
+	disable_kernel_vsx();
+	pagefault_enable();
+	preempt_enable();
+
+	ret |= crypto_skcipher_setkey(ctx->fallback, key, keylen);
+
+	return ret ? -EINVAL : 0;
+}
+
+static int p8_aes_xts_crypt(struct skcipher_request *req, int enc)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct p8_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	unsigned int nbytes;
+	u8 tweak[AES_BLOCK_SIZE];
+	int ret;
+
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	if (!crypto_simd_usable() || (req->cryptlen % XTS_BLOCK_SIZE) != 0) {
+		struct skcipher_request *subreq = skcipher_request_ctx(req);
+
+		*subreq = *req;
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		return enc ? crypto_skcipher_encrypt(subreq) :
+			     crypto_skcipher_decrypt(subreq);
+	}
+
+	ret = skcipher_walk_virt(&walk, req, false);
+	if (ret)
+		return ret;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_vsx();
+
+	aes_p8_encrypt(walk.iv, tweak, &ctx->tweak_key);
+
+	disable_kernel_vsx();
+	pagefault_enable();
+	preempt_enable();
+
+	while ((nbytes = walk.nbytes) != 0) {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_vsx();
+		if (enc)
+			aes_p8_xts_encrypt(walk.src.virt.addr,
+					   walk.dst.virt.addr,
+					   round_down(nbytes, AES_BLOCK_SIZE),
+					   &ctx->enc_key, NULL, tweak);
+		else
+			aes_p8_xts_decrypt(walk.src.virt.addr,
+					   walk.dst.virt.addr,
+					   round_down(nbytes, AES_BLOCK_SIZE),
+					   &ctx->dec_key, NULL, tweak);
+		disable_kernel_vsx();
+		pagefault_enable();
+		preempt_enable();
+
+		ret = skcipher_walk_done(&walk, nbytes % AES_BLOCK_SIZE);
+	}
+	return ret;
+}
+
+static int p8_aes_xts_encrypt(struct skcipher_request *req)
+{
+	return p8_aes_xts_crypt(req, 1);
+}
+
+static int p8_aes_xts_decrypt(struct skcipher_request *req)
+{
+	return p8_aes_xts_crypt(req, 0);
+}
+
+struct skcipher_alg p8_aes_xts_alg = {
+	.base.cra_name = "xts(aes)",
+	.base.cra_driver_name = "p8_aes_xts",
+	.base.cra_module = THIS_MODULE,
+	.base.cra_priority = 2000,
+	.base.cra_flags = CRYPTO_ALG_NEED_FALLBACK,
+	.base.cra_blocksize = AES_BLOCK_SIZE,
+	.base.cra_ctxsize = sizeof(struct p8_aes_xts_ctx),
+	.setkey = p8_aes_xts_setkey,
+	.encrypt = p8_aes_xts_encrypt,
+	.decrypt = p8_aes_xts_decrypt,
+	.init = p8_aes_xts_init,
+	.exit = p8_aes_xts_exit,
+	.min_keysize = 2 * AES_MIN_KEY_SIZE,
+	.max_keysize = 2 * AES_MAX_KEY_SIZE,
+	.ivsize = AES_BLOCK_SIZE,
+};
diff --git a/arch/powerpc/crypto/aesp10-ppc.pl b/arch/powerpc/crypto/aesp10-ppc.pl
new file mode 100644
index 000000000000..2c06ce2a2c7c
--- /dev/null
+++ b/arch/powerpc/crypto/aesp10-ppc.pl
@@ -0,0 +1,585 @@
+#! /usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from CRYPTOGAMs[1] and is included here using the option
+# in the license to distribute the code under the GPL. Therefore 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.
+#
+# [1] https://www.openssl.org/~appro/cryptogams/
+
+# Copyright (c) 2006-2017, CRYPTOGAMS by <appro@openssl.org>
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#
+#       * Redistributions of source code must retain copyright notices,
+#         this list of conditions and the following disclaimer.
+#
+#       * Redistributions in binary form must reproduce the above
+#         copyright notice, this list of conditions and the following
+#         disclaimer in the documentation and/or other materials
+#         provided with the distribution.
+#
+#       * Neither the name of the CRYPTOGAMS nor the names of its
+#         copyright holder and contributors may be used to endorse or
+#         promote products derived from this software without specific
+#         prior written permission.
+#
+# ALTERNATIVELY, provided that this notice is retained in full, this
+# product may be distributed under the terms of the GNU General Public
+# License (GPL), in which case the provisions of the GPL apply INSTEAD OF
+# those given above.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see https://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# This module implements support for AES instructions as per PowerISA
+# specification version 2.07, first implemented by POWER8 processor.
+# The module is endian-agnostic in sense that it supports both big-
+# and little-endian cases. Data alignment in parallelizable modes is
+# handled with VSX loads and stores, which implies MSR.VSX flag being
+# set. It should also be noted that ISA specification doesn't prohibit
+# alignment exceptions for these instructions on page boundaries.
+# Initially alignment was handled in pure AltiVec/VMX way [when data
+# is aligned programmatically, which in turn guarantees exception-
+# free execution], but it turned to hamper performance when vcipher
+# instructions are interleaved. It's reckoned that eventual
+# misalignment penalties at page boundaries are in average lower
+# than additional overhead in pure AltiVec approach.
+#
+# May 2016
+#
+# Add XTS subroutine, 9x on little- and 12x improvement on big-endian
+# systems were measured.
+#
+######################################################################
+# Current large-block performance in cycles per byte processed with
+# 128-bit key (less is better).
+#
+#		CBC en-/decrypt	CTR	XTS
+# POWER8[le]	3.96/0.72	0.74	1.1
+# POWER8[be]	3.75/0.65	0.66	1.0
+
+$flavour = shift;
+
+if ($flavour =~ /64/) {
+	$SIZE_T	=8;
+	$LRSAVE	=2*$SIZE_T;
+	$STU	="stdu";
+	$POP	="ld";
+	$PUSH	="std";
+	$UCMP	="cmpld";
+	$SHL	="sldi";
+} elsif ($flavour =~ /32/) {
+	$SIZE_T	=4;
+	$LRSAVE	=$SIZE_T;
+	$STU	="stwu";
+	$POP	="lwz";
+	$PUSH	="stw";
+	$UCMP	="cmplw";
+	$SHL	="slwi";
+} else { die "nonsense $flavour"; }
+
+$LITTLE_ENDIAN = ($flavour=~/le$/) ? $SIZE_T : 0;
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}ppc-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/ppc-xlate.pl" and -f $xlate) or
+die "can't locate ppc-xlate.pl";
+
+open STDOUT,"| $^X $xlate $flavour ".shift || die "can't call $xlate: $!";
+
+$FRAME=8*$SIZE_T;
+$prefix="aes_p10";
+
+$sp="r1";
+$vrsave="r12";
+
+#########################################################################
+{{{	# Key setup procedures						#
+my ($inp,$bits,$out,$ptr,$cnt,$rounds)=map("r$_",(3..8));
+my ($zero,$in0,$in1,$key,$rcon,$mask,$tmp)=map("v$_",(0..6));
+my ($stage,$outperm,$outmask,$outhead,$outtail)=map("v$_",(7..11));
+
+$code.=<<___;
+.machine	"any"
+
+.text
+
+.align	7
+rcon:
+.long	0x01000000, 0x01000000, 0x01000000, 0x01000000	?rev
+.long	0x1b000000, 0x1b000000, 0x1b000000, 0x1b000000	?rev
+.long	0x0d0e0f0c, 0x0d0e0f0c, 0x0d0e0f0c, 0x0d0e0f0c	?rev
+.long	0,0,0,0						?asis
+Lconsts:
+	mflr	r0
+	bcl	20,31,\$+4
+	mflr	$ptr	 #vvvvv "distance between . and rcon
+	addi	$ptr,$ptr,-0x48
+	mtlr	r0
+	blr
+	.long	0
+	.byte	0,12,0x14,0,0,0,0,0
+.asciz	"AES for PowerISA 2.07, CRYPTOGAMS by <appro\@openssl.org>"
+
+.globl	.${prefix}_set_encrypt_key
+Lset_encrypt_key:
+	mflr		r11
+	$PUSH		r11,$LRSAVE($sp)
+
+	li		$ptr,-1
+	${UCMP}i	$inp,0
+	beq-		Lenc_key_abort		# if ($inp==0) return -1;
+	${UCMP}i	$out,0
+	beq-		Lenc_key_abort		# if ($out==0) return -1;
+	li		$ptr,-2
+	cmpwi		$bits,128
+	blt-		Lenc_key_abort
+	cmpwi		$bits,256
+	bgt-		Lenc_key_abort
+	andi.		r0,$bits,0x3f
+	bne-		Lenc_key_abort
+
+	lis		r0,0xfff0
+	mfspr		$vrsave,256
+	mtspr		256,r0
+
+	bl		Lconsts
+	mtlr		r11
+
+	neg		r9,$inp
+	lvx		$in0,0,$inp
+	addi		$inp,$inp,15		# 15 is not typo
+	lvsr		$key,0,r9		# borrow $key
+	li		r8,0x20
+	cmpwi		$bits,192
+	lvx		$in1,0,$inp
+	le?vspltisb	$mask,0x0f		# borrow $mask
+	lvx		$rcon,0,$ptr
+	le?vxor		$key,$key,$mask		# adjust for byte swap
+	lvx		$mask,r8,$ptr
+	addi		$ptr,$ptr,0x10
+	vperm		$in0,$in0,$in1,$key	# align [and byte swap in LE]
+	li		$cnt,8
+	vxor		$zero,$zero,$zero
+	mtctr		$cnt
+
+	?lvsr		$outperm,0,$out
+	vspltisb	$outmask,-1
+	lvx		$outhead,0,$out
+	?vperm		$outmask,$zero,$outmask,$outperm
+
+	blt		Loop128
+	addi		$inp,$inp,8
+	beq		L192
+	addi		$inp,$inp,8
+	b		L256
+
+.align	4
+Loop128:
+	vperm		$key,$in0,$in0,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in0,$in0,$key
+	bdnz		Loop128
+
+	lvx		$rcon,0,$ptr		# last two round keys
+
+	vperm		$key,$in0,$in0,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in0,$in0,$key
+
+	vperm		$key,$in0,$in0,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vxor		$in0,$in0,$key
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+
+	addi		$inp,$out,15		# 15 is not typo
+	addi		$out,$out,0x50
+
+	li		$rounds,10
+	b		Ldone
+
+.align	4
+L192:
+	lvx		$tmp,0,$inp
+	li		$cnt,4
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+	vperm		$in1,$in1,$tmp,$key	# align [and byte swap in LE]
+	vspltisb	$key,8			# borrow $key
+	mtctr		$cnt
+	vsububm		$mask,$mask,$key	# adjust the mask
+
+Loop192:
+	vperm		$key,$in1,$in1,$mask	# roate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	vcipherlast	$key,$key,$rcon
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+
+	 vsldoi		$stage,$zero,$in1,8
+	vspltw		$tmp,$in0,3
+	vxor		$tmp,$tmp,$in1
+	vsldoi		$in1,$zero,$in1,12	# >>32
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in1,$in1,$tmp
+	vxor		$in0,$in0,$key
+	vxor		$in1,$in1,$key
+	 vsldoi		$stage,$stage,$in0,8
+
+	vperm		$key,$in1,$in1,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$stage,$stage,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	 vsldoi		$stage,$in0,$in1,8
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	 vperm		$outtail,$stage,$stage,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vspltw		$tmp,$in0,3
+	vxor		$tmp,$tmp,$in1
+	vsldoi		$in1,$zero,$in1,12	# >>32
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in1,$in1,$tmp
+	vxor		$in0,$in0,$key
+	vxor		$in1,$in1,$key
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+	 addi		$inp,$out,15		# 15 is not typo
+	 addi		$out,$out,16
+	bdnz		Loop192
+
+	li		$rounds,12
+	addi		$out,$out,0x20
+	b		Ldone
+
+.align	4
+L256:
+	lvx		$tmp,0,$inp
+	li		$cnt,7
+	li		$rounds,14
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+	vperm		$in1,$in1,$tmp,$key	# align [and byte swap in LE]
+	mtctr		$cnt
+
+Loop256:
+	vperm		$key,$in1,$in1,$mask	# rotate-n-splat
+	vsldoi		$tmp,$zero,$in0,12	# >>32
+	 vperm		$outtail,$in1,$in1,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	vcipherlast	$key,$key,$rcon
+	 stvx		$stage,0,$out
+	 addi		$out,$out,16
+
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in0,$in0,$tmp
+	 vadduwm	$rcon,$rcon,$rcon
+	vxor		$in0,$in0,$key
+	 vperm		$outtail,$in0,$in0,$outperm	# rotate
+	 vsel		$stage,$outhead,$outtail,$outmask
+	 vmr		$outhead,$outtail
+	 stvx		$stage,0,$out
+	 addi		$inp,$out,15		# 15 is not typo
+	 addi		$out,$out,16
+	bdz		Ldone
+
+	vspltw		$key,$in0,3		# just splat
+	vsldoi		$tmp,$zero,$in1,12	# >>32
+	vsbox		$key,$key
+
+	vxor		$in1,$in1,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in1,$in1,$tmp
+	vsldoi		$tmp,$zero,$tmp,12	# >>32
+	vxor		$in1,$in1,$tmp
+
+	vxor		$in1,$in1,$key
+	b		Loop256
+
+.align	4
+Ldone:
+	lvx		$in1,0,$inp		# redundant in aligned case
+	vsel		$in1,$outhead,$in1,$outmask
+	stvx		$in1,0,$inp
+	li		$ptr,0
+	mtspr		256,$vrsave
+	stw		$rounds,0($out)
+
+Lenc_key_abort:
+	mr		r3,$ptr
+	blr
+	.long		0
+	.byte		0,12,0x14,1,0,0,3,0
+	.long		0
+.size	.${prefix}_set_encrypt_key,.-.${prefix}_set_encrypt_key
+
+.globl	.${prefix}_set_decrypt_key
+	$STU		$sp,-$FRAME($sp)
+	mflr		r10
+	$PUSH		r10,$FRAME+$LRSAVE($sp)
+	bl		Lset_encrypt_key
+	mtlr		r10
+
+	cmpwi		r3,0
+	bne-		Ldec_key_abort
+
+	slwi		$cnt,$rounds,4
+	subi		$inp,$out,240		# first round key
+	srwi		$rounds,$rounds,1
+	add		$out,$inp,$cnt		# last round key
+	mtctr		$rounds
+
+Ldeckey:
+	lwz		r0, 0($inp)
+	lwz		r6, 4($inp)
+	lwz		r7, 8($inp)
+	lwz		r8, 12($inp)
+	addi		$inp,$inp,16
+	lwz		r9, 0($out)
+	lwz		r10,4($out)
+	lwz		r11,8($out)
+	lwz		r12,12($out)
+	stw		r0, 0($out)
+	stw		r6, 4($out)
+	stw		r7, 8($out)
+	stw		r8, 12($out)
+	subi		$out,$out,16
+	stw		r9, -16($inp)
+	stw		r10,-12($inp)
+	stw		r11,-8($inp)
+	stw		r12,-4($inp)
+	bdnz		Ldeckey
+
+	xor		r3,r3,r3		# return value
+Ldec_key_abort:
+	addi		$sp,$sp,$FRAME
+	blr
+	.long		0
+	.byte		0,12,4,1,0x80,0,3,0
+	.long		0
+.size	.${prefix}_set_decrypt_key,.-.${prefix}_set_decrypt_key
+___
+}}}
+#########################################################################
+{{{	# Single block en- and decrypt procedures			#
+sub gen_block () {
+my $dir = shift;
+my $n   = $dir eq "de" ? "n" : "";
+my ($inp,$out,$key,$rounds,$idx)=map("r$_",(3..7));
+
+$code.=<<___;
+.globl	.${prefix}_${dir}crypt
+	lwz		$rounds,240($key)
+	lis		r0,0xfc00
+	mfspr		$vrsave,256
+	li		$idx,15			# 15 is not typo
+	mtspr		256,r0
+
+	lvx		v0,0,$inp
+	neg		r11,$out
+	lvx		v1,$idx,$inp
+	lvsl		v2,0,$inp		# inpperm
+	le?vspltisb	v4,0x0f
+	?lvsl		v3,0,r11		# outperm
+	le?vxor		v2,v2,v4
+	li		$idx,16
+	vperm		v0,v0,v1,v2		# align [and byte swap in LE]
+	lvx		v1,0,$key
+	?lvsl		v5,0,$key		# keyperm
+	srwi		$rounds,$rounds,1
+	lvx		v2,$idx,$key
+	addi		$idx,$idx,16
+	subi		$rounds,$rounds,1
+	?vperm		v1,v1,v2,v5		# align round key
+
+	vxor		v0,v0,v1
+	lvx		v1,$idx,$key
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+Loop_${dir}c:
+	?vperm		v2,v2,v1,v5
+	v${n}cipher	v0,v0,v2
+	lvx		v2,$idx,$key
+	addi		$idx,$idx,16
+	?vperm		v1,v1,v2,v5
+	v${n}cipher	v0,v0,v1
+	lvx		v1,$idx,$key
+	addi		$idx,$idx,16
+	bdnz		Loop_${dir}c
+
+	?vperm		v2,v2,v1,v5
+	v${n}cipher	v0,v0,v2
+	lvx		v2,$idx,$key
+	?vperm		v1,v1,v2,v5
+	v${n}cipherlast	v0,v0,v1
+
+	vspltisb	v2,-1
+	vxor		v1,v1,v1
+	li		$idx,15			# 15 is not typo
+	?vperm		v2,v1,v2,v3		# outmask
+	le?vxor		v3,v3,v4
+	lvx		v1,0,$out		# outhead
+	vperm		v0,v0,v0,v3		# rotate [and byte swap in LE]
+	vsel		v1,v1,v0,v2
+	lvx		v4,$idx,$out
+	stvx		v1,0,$out
+	vsel		v0,v0,v4,v2
+	stvx		v0,$idx,$out
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,3,0
+	.long		0
+.size	.${prefix}_${dir}crypt,.-.${prefix}_${dir}crypt
+___
+}
+&gen_block("en");
+&gen_block("de");
+}}}
+
+my $consts=1;
+foreach(split("\n",$code)) {
+        s/\`([^\`]*)\`/eval($1)/geo;
+
+	# constants table endian-specific conversion
+	if ($consts && m/\.(long|byte)\s+(.+)\s+(\?[a-z]*)$/o) {
+	    my $conv=$3;
+	    my @bytes=();
+
+	    # convert to endian-agnostic format
+	    if ($1 eq "long") {
+	      foreach (split(/,\s*/,$2)) {
+		my $l = /^0/?oct:int;
+		push @bytes,($l>>24)&0xff,($l>>16)&0xff,($l>>8)&0xff,$l&0xff;
+	      }
+	    } else {
+		@bytes = map(/^0/?oct:int,split(/,\s*/,$2));
+	    }
+
+	    # little-endian conversion
+	    if ($flavour =~ /le$/o) {
+		SWITCH: for($conv)  {
+		    /\?inv/ && do   { @bytes=map($_^0xf,@bytes); last; };
+		    /\?rev/ && do   { @bytes=reverse(@bytes);    last; };
+		}
+	    }
+
+	    #emit
+	    print ".byte\t",join(',',map (sprintf("0x%02x",$_),@bytes)),"\n";
+	    next;
+	}
+	$consts=0 if (m/Lconsts:/o);	# end of table
+
+	# instructions prefixed with '?' are endian-specific and need
+	# to be adjusted accordingly...
+	if ($flavour =~ /le$/o) {	# little-endian
+	    s/le\?//o		or
+	    s/be\?/#be#/o	or
+	    s/\?lvsr/lvsl/o	or
+	    s/\?lvsl/lvsr/o	or
+	    s/\?(vperm\s+v[0-9]+,\s*)(v[0-9]+,\s*)(v[0-9]+,\s*)(v[0-9]+)/$1$3$2$4/o or
+	    s/\?(vsldoi\s+v[0-9]+,\s*)(v[0-9]+,)\s*(v[0-9]+,\s*)([0-9]+)/$1$3$2 16-$4/o or
+	    s/\?(vspltw\s+v[0-9]+,\s*)(v[0-9]+,)\s*([0-9])/$1$2 3-$3/o;
+	} else {			# big-endian
+	    s/le\?/#le#/o	or
+	    s/be\?//o		or
+	    s/\?([a-z]+)/$1/o;
+	}
+
+        print $_,"\n";
+}
+
+close STDOUT;
diff --git a/arch/powerpc/crypto/aesp8-ppc.h b/arch/powerpc/crypto/aesp8-ppc.h
new file mode 100644
index 000000000000..5764d4438388
--- /dev/null
+++ b/arch/powerpc/crypto/aesp8-ppc.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/types.h>
+#include <crypto/aes.h>
+
+struct aes_key {
+	u8 key[AES_MAX_KEYLENGTH];
+	int rounds;
+};
+
+extern struct shash_alg p8_ghash_alg;
+extern struct crypto_alg p8_aes_alg;
+extern struct skcipher_alg p8_aes_cbc_alg;
+extern struct skcipher_alg p8_aes_ctr_alg;
+extern struct skcipher_alg p8_aes_xts_alg;
+
+int aes_p8_set_encrypt_key(const u8 *userKey, const int bits,
+			   struct aes_key *key);
+int aes_p8_set_decrypt_key(const u8 *userKey, const int bits,
+			   struct aes_key *key);
+void aes_p8_encrypt(const u8 *in, u8 *out, const struct aes_key *key);
+void aes_p8_decrypt(const u8 *in, u8 *out, const struct aes_key *key);
+void aes_p8_cbc_encrypt(const u8 *in, u8 *out, size_t len,
+			const struct aes_key *key, u8 *iv, const int enc);
+void aes_p8_ctr32_encrypt_blocks(const u8 *in, u8 *out,
+				 size_t len, const struct aes_key *key,
+				 const u8 *iv);
+void aes_p8_xts_encrypt(const u8 *in, u8 *out, size_t len,
+			const struct aes_key *key1, const struct aes_key *key2, u8 *iv);
+void aes_p8_xts_decrypt(const u8 *in, u8 *out, size_t len,
+			const struct aes_key *key1, const struct aes_key *key2, u8 *iv);
diff --git a/arch/powerpc/crypto/aesp8-ppc.pl b/arch/powerpc/crypto/aesp8-ppc.pl
index 1f22aec27d79..f729589d792e 100644
--- a/arch/powerpc/crypto/aesp8-ppc.pl
+++ b/arch/powerpc/crypto/aesp8-ppc.pl
@@ -132,11 +132,12 @@ rcon:
 .long	0x1b000000, 0x1b000000, 0x1b000000, 0x1b000000	?rev
 .long	0x0d0e0f0c, 0x0d0e0f0c, 0x0d0e0f0c, 0x0d0e0f0c	?rev
 .long	0,0,0,0						?asis
+.long	0x0f102132, 0x43546576, 0x8798a9ba, 0xcbdcedfe
 Lconsts:
 	mflr	r0
 	bcl	20,31,\$+4
 	mflr	$ptr	 #vvvvv "distance between . and rcon
-	addi	$ptr,$ptr,-0x48
+	addi	$ptr,$ptr,-0x58
 	mtlr	r0
 	blr
 	.long	0
@@ -529,6 +530,3309 @@ ___
 &gen_block("en");
 &gen_block("de");
 }}}
+#########################################################################
+{{{	# CBC en- and decrypt procedures				#
+my ($inp,$out,$len,$key,$ivp,$enc,$rounds,$idx)=map("r$_",(3..10));
+my ($rndkey0,$rndkey1,$inout,$tmp)=		map("v$_",(0..3));
+my ($ivec,$inptail,$inpperm,$outhead,$outperm,$outmask,$keyperm)=
+						map("v$_",(4..10));
+$code.=<<___;
+.globl	.${prefix}_cbc_encrypt
+	${UCMP}i	$len,16
+	bltlr-
+
+	cmpwi		$enc,0			# test direction
+	lis		r0,0xffe0
+	mfspr		$vrsave,256
+	mtspr		256,r0
+
+	li		$idx,15
+	vxor		$rndkey0,$rndkey0,$rndkey0
+	le?vspltisb	$tmp,0x0f
+
+	lvx		$ivec,0,$ivp		# load [unaligned] iv
+	lvsl		$inpperm,0,$ivp
+	lvx		$inptail,$idx,$ivp
+	le?vxor		$inpperm,$inpperm,$tmp
+	vperm		$ivec,$ivec,$inptail,$inpperm
+
+	neg		r11,$inp
+	?lvsl		$keyperm,0,$key		# prepare for unaligned key
+	lwz		$rounds,240($key)
+
+	lvsr		$inpperm,0,r11		# prepare for unaligned load
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,15		# 15 is not typo
+	le?vxor		$inpperm,$inpperm,$tmp
+
+	?lvsr		$outperm,0,$out		# prepare for unaligned store
+	vspltisb	$outmask,-1
+	lvx		$outhead,0,$out
+	?vperm		$outmask,$rndkey0,$outmask,$outperm
+	le?vxor		$outperm,$outperm,$tmp
+
+	srwi		$rounds,$rounds,1
+	li		$idx,16
+	subi		$rounds,$rounds,1
+	beq		Lcbc_dec
+
+Lcbc_enc:
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+	mtctr		$rounds
+	subi		$len,$len,16		# len-=16
+
+	lvx		$rndkey0,0,$key
+	 vperm		$inout,$inout,$inptail,$inpperm
+	lvx		$rndkey1,$idx,$key
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key
+	addi		$idx,$idx,16
+	vxor		$inout,$inout,$ivec
+
+Loop_cbc_enc:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key
+	addi		$idx,$idx,16
+	bdnz		Loop_cbc_enc
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipherlast	$ivec,$inout,$rndkey0
+	${UCMP}i	$len,16
+
+	vperm		$tmp,$ivec,$ivec,$outperm
+	vsel		$inout,$outhead,$tmp,$outmask
+	vmr		$outhead,$tmp
+	stvx		$inout,0,$out
+	addi		$out,$out,16
+	bge		Lcbc_enc
+
+	b		Lcbc_done
+
+.align	4
+Lcbc_dec:
+	${UCMP}i	$len,128
+	bge		_aesp8_cbc_decrypt8x
+	vmr		$tmp,$inptail
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+	mtctr		$rounds
+	subi		$len,$len,16		# len-=16
+
+	lvx		$rndkey0,0,$key
+	 vperm		$tmp,$tmp,$inptail,$inpperm
+	lvx		$rndkey1,$idx,$key
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$tmp,$rndkey0
+	lvx		$rndkey0,$idx,$key
+	addi		$idx,$idx,16
+
+Loop_cbc_dec:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vncipher	$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key
+	addi		$idx,$idx,16
+	bdnz		Loop_cbc_dec
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vncipherlast	$inout,$inout,$rndkey0
+	${UCMP}i	$len,16
+
+	vxor		$inout,$inout,$ivec
+	vmr		$ivec,$tmp
+	vperm		$tmp,$inout,$inout,$outperm
+	vsel		$inout,$outhead,$tmp,$outmask
+	vmr		$outhead,$tmp
+	stvx		$inout,0,$out
+	addi		$out,$out,16
+	bge		Lcbc_dec
+
+Lcbc_done:
+	addi		$out,$out,-1
+	lvx		$inout,0,$out		# redundant in aligned case
+	vsel		$inout,$outhead,$inout,$outmask
+	stvx		$inout,0,$out
+
+	neg		$enc,$ivp		# write [unaligned] iv
+	li		$idx,15			# 15 is not typo
+	vxor		$rndkey0,$rndkey0,$rndkey0
+	vspltisb	$outmask,-1
+	le?vspltisb	$tmp,0x0f
+	?lvsl		$outperm,0,$enc
+	?vperm		$outmask,$rndkey0,$outmask,$outperm
+	le?vxor		$outperm,$outperm,$tmp
+	lvx		$outhead,0,$ivp
+	vperm		$ivec,$ivec,$ivec,$outperm
+	vsel		$inout,$outhead,$ivec,$outmask
+	lvx		$inptail,$idx,$ivp
+	stvx		$inout,0,$ivp
+	vsel		$inout,$ivec,$inptail,$outmask
+	stvx		$inout,$idx,$ivp
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,6,0
+	.long		0
+___
+#########################################################################
+{{	# Optimized CBC decrypt procedure				#
+my $key_="r11";
+my ($x00,$x10,$x20,$x30,$x40,$x50,$x60,$x70)=map("r$_",(0,8,26..31));
+my ($in0, $in1, $in2, $in3, $in4, $in5, $in6, $in7 )=map("v$_",(0..3,10..13));
+my ($out0,$out1,$out2,$out3,$out4,$out5,$out6,$out7)=map("v$_",(14..21));
+my $rndkey0="v23";	# v24-v25 rotating buffer for first found keys
+			# v26-v31 last 6 round keys
+my ($tmp,$keyperm)=($in3,$in4);	# aliases with "caller", redundant assignment
+
+$code.=<<___;
+.align	5
+_aesp8_cbc_decrypt8x:
+	$STU		$sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+	li		r10,`$FRAME+8*16+15`
+	li		r11,`$FRAME+8*16+31`
+	stvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	stvx		v21,r11,$sp
+	addi		r11,r11,32
+	stvx		v22,r10,$sp
+	addi		r10,r10,32
+	stvx		v23,r11,$sp
+	addi		r11,r11,32
+	stvx		v24,r10,$sp
+	addi		r10,r10,32
+	stvx		v25,r11,$sp
+	addi		r11,r11,32
+	stvx		v26,r10,$sp
+	addi		r10,r10,32
+	stvx		v27,r11,$sp
+	addi		r11,r11,32
+	stvx		v28,r10,$sp
+	addi		r10,r10,32
+	stvx		v29,r11,$sp
+	addi		r11,r11,32
+	stvx		v30,r10,$sp
+	stvx		v31,r11,$sp
+	li		r0,-1
+	stw		$vrsave,`$FRAME+21*16-4`($sp)	# save vrsave
+	li		$x10,0x10
+	$PUSH		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	li		$x20,0x20
+	$PUSH		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	li		$x30,0x30
+	$PUSH		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	li		$x40,0x40
+	$PUSH		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	li		$x50,0x50
+	$PUSH		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	li		$x60,0x60
+	$PUSH		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	li		$x70,0x70
+	mtspr		256,r0
+
+	subi		$rounds,$rounds,3	# -4 in total
+	subi		$len,$len,128		# bias
+
+	lvx		$rndkey0,$x00,$key	# load key schedule
+	lvx		v30,$x10,$key
+	addi		$key,$key,0x20
+	lvx		v31,$x00,$key
+	?vperm		$rndkey0,$rndkey0,v30,$keyperm
+	addi		$key_,$sp,$FRAME+15
+	mtctr		$rounds
+
+Load_cbc_dec_key:
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v30,$x10,$key
+	addi		$key,$key,0x20
+	stvx		v24,$x00,$key_		# off-load round[1]
+	?vperm		v25,v31,v30,$keyperm
+	lvx		v31,$x00,$key
+	stvx		v25,$x10,$key_		# off-load round[2]
+	addi		$key_,$key_,0x20
+	bdnz		Load_cbc_dec_key
+
+	lvx		v26,$x10,$key
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v27,$x20,$key
+	stvx		v24,$x00,$key_		# off-load round[3]
+	?vperm		v25,v31,v26,$keyperm
+	lvx		v28,$x30,$key
+	stvx		v25,$x10,$key_		# off-load round[4]
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	?vperm		v26,v26,v27,$keyperm
+	lvx		v29,$x40,$key
+	?vperm		v27,v27,v28,$keyperm
+	lvx		v30,$x50,$key
+	?vperm		v28,v28,v29,$keyperm
+	lvx		v31,$x60,$key
+	?vperm		v29,v29,v30,$keyperm
+	lvx		$out0,$x70,$key		# borrow $out0
+	?vperm		v30,v30,v31,$keyperm
+	lvx		v24,$x00,$key_		# pre-load round[1]
+	?vperm		v31,v31,$out0,$keyperm
+	lvx		v25,$x10,$key_		# pre-load round[2]
+
+	#lvx		$inptail,0,$inp		# "caller" already did this
+	#addi		$inp,$inp,15		# 15 is not typo
+	subi		$inp,$inp,15		# undo "caller"
+
+	 le?li		$idx,8
+	lvx_u		$in0,$x00,$inp		# load first 8 "words"
+	 le?lvsl	$inpperm,0,$idx
+	 le?vspltisb	$tmp,0x0f
+	lvx_u		$in1,$x10,$inp
+	 le?vxor	$inpperm,$inpperm,$tmp	# transform for lvx_u/stvx_u
+	lvx_u		$in2,$x20,$inp
+	 le?vperm	$in0,$in0,$in0,$inpperm
+	lvx_u		$in3,$x30,$inp
+	 le?vperm	$in1,$in1,$in1,$inpperm
+	lvx_u		$in4,$x40,$inp
+	 le?vperm	$in2,$in2,$in2,$inpperm
+	vxor		$out0,$in0,$rndkey0
+	lvx_u		$in5,$x50,$inp
+	 le?vperm	$in3,$in3,$in3,$inpperm
+	vxor		$out1,$in1,$rndkey0
+	lvx_u		$in6,$x60,$inp
+	 le?vperm	$in4,$in4,$in4,$inpperm
+	vxor		$out2,$in2,$rndkey0
+	lvx_u		$in7,$x70,$inp
+	addi		$inp,$inp,0x80
+	 le?vperm	$in5,$in5,$in5,$inpperm
+	vxor		$out3,$in3,$rndkey0
+	 le?vperm	$in6,$in6,$in6,$inpperm
+	vxor		$out4,$in4,$rndkey0
+	 le?vperm	$in7,$in7,$in7,$inpperm
+	vxor		$out5,$in5,$rndkey0
+	vxor		$out6,$in6,$rndkey0
+	vxor		$out7,$in7,$rndkey0
+
+	mtctr		$rounds
+	b		Loop_cbc_dec8x
+.align	5
+Loop_cbc_dec8x:
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+	vncipher	$out6,$out6,v24
+	vncipher	$out7,$out7,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+	vncipher	$out6,$out6,v25
+	vncipher	$out7,$out7,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_cbc_dec8x
+
+	subic		$len,$len,128		# $len-=128
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+	vncipher	$out6,$out6,v24
+	vncipher	$out7,$out7,v24
+
+	subfe.		r0,r0,r0		# borrow?-1:0
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+	vncipher	$out6,$out6,v25
+	vncipher	$out7,$out7,v25
+
+	and		r0,r0,$len
+	vncipher	$out0,$out0,v26
+	vncipher	$out1,$out1,v26
+	vncipher	$out2,$out2,v26
+	vncipher	$out3,$out3,v26
+	vncipher	$out4,$out4,v26
+	vncipher	$out5,$out5,v26
+	vncipher	$out6,$out6,v26
+	vncipher	$out7,$out7,v26
+
+	add		$inp,$inp,r0		# $inp is adjusted in such
+						# way that at exit from the
+						# loop inX-in7 are loaded
+						# with last "words"
+	vncipher	$out0,$out0,v27
+	vncipher	$out1,$out1,v27
+	vncipher	$out2,$out2,v27
+	vncipher	$out3,$out3,v27
+	vncipher	$out4,$out4,v27
+	vncipher	$out5,$out5,v27
+	vncipher	$out6,$out6,v27
+	vncipher	$out7,$out7,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	vncipher	$out1,$out1,v28
+	vncipher	$out2,$out2,v28
+	vncipher	$out3,$out3,v28
+	vncipher	$out4,$out4,v28
+	vncipher	$out5,$out5,v28
+	vncipher	$out6,$out6,v28
+	vncipher	$out7,$out7,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vncipher	$out0,$out0,v29
+	vncipher	$out1,$out1,v29
+	vncipher	$out2,$out2,v29
+	vncipher	$out3,$out3,v29
+	vncipher	$out4,$out4,v29
+	vncipher	$out5,$out5,v29
+	vncipher	$out6,$out6,v29
+	vncipher	$out7,$out7,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+
+	vncipher	$out0,$out0,v30
+	 vxor		$ivec,$ivec,v31		# xor with last round key
+	vncipher	$out1,$out1,v30
+	 vxor		$in0,$in0,v31
+	vncipher	$out2,$out2,v30
+	 vxor		$in1,$in1,v31
+	vncipher	$out3,$out3,v30
+	 vxor		$in2,$in2,v31
+	vncipher	$out4,$out4,v30
+	 vxor		$in3,$in3,v31
+	vncipher	$out5,$out5,v30
+	 vxor		$in4,$in4,v31
+	vncipher	$out6,$out6,v30
+	 vxor		$in5,$in5,v31
+	vncipher	$out7,$out7,v30
+	 vxor		$in6,$in6,v31
+
+	vncipherlast	$out0,$out0,$ivec
+	vncipherlast	$out1,$out1,$in0
+	 lvx_u		$in0,$x00,$inp		# load next input block
+	vncipherlast	$out2,$out2,$in1
+	 lvx_u		$in1,$x10,$inp
+	vncipherlast	$out3,$out3,$in2
+	 le?vperm	$in0,$in0,$in0,$inpperm
+	 lvx_u		$in2,$x20,$inp
+	vncipherlast	$out4,$out4,$in3
+	 le?vperm	$in1,$in1,$in1,$inpperm
+	 lvx_u		$in3,$x30,$inp
+	vncipherlast	$out5,$out5,$in4
+	 le?vperm	$in2,$in2,$in2,$inpperm
+	 lvx_u		$in4,$x40,$inp
+	vncipherlast	$out6,$out6,$in5
+	 le?vperm	$in3,$in3,$in3,$inpperm
+	 lvx_u		$in5,$x50,$inp
+	vncipherlast	$out7,$out7,$in6
+	 le?vperm	$in4,$in4,$in4,$inpperm
+	 lvx_u		$in6,$x60,$inp
+	vmr		$ivec,$in7
+	 le?vperm	$in5,$in5,$in5,$inpperm
+	 lvx_u		$in7,$x70,$inp
+	 addi		$inp,$inp,0x80
+
+	le?vperm	$out0,$out0,$out0,$inpperm
+	le?vperm	$out1,$out1,$out1,$inpperm
+	stvx_u		$out0,$x00,$out
+	 le?vperm	$in6,$in6,$in6,$inpperm
+	 vxor		$out0,$in0,$rndkey0
+	le?vperm	$out2,$out2,$out2,$inpperm
+	stvx_u		$out1,$x10,$out
+	 le?vperm	$in7,$in7,$in7,$inpperm
+	 vxor		$out1,$in1,$rndkey0
+	le?vperm	$out3,$out3,$out3,$inpperm
+	stvx_u		$out2,$x20,$out
+	 vxor		$out2,$in2,$rndkey0
+	le?vperm	$out4,$out4,$out4,$inpperm
+	stvx_u		$out3,$x30,$out
+	 vxor		$out3,$in3,$rndkey0
+	le?vperm	$out5,$out5,$out5,$inpperm
+	stvx_u		$out4,$x40,$out
+	 vxor		$out4,$in4,$rndkey0
+	le?vperm	$out6,$out6,$out6,$inpperm
+	stvx_u		$out5,$x50,$out
+	 vxor		$out5,$in5,$rndkey0
+	le?vperm	$out7,$out7,$out7,$inpperm
+	stvx_u		$out6,$x60,$out
+	 vxor		$out6,$in6,$rndkey0
+	stvx_u		$out7,$x70,$out
+	addi		$out,$out,0x80
+	 vxor		$out7,$in7,$rndkey0
+
+	mtctr		$rounds
+	beq		Loop_cbc_dec8x		# did $len-=128 borrow?
+
+	addic.		$len,$len,128
+	beq		Lcbc_dec8x_done
+	nop
+	nop
+
+Loop_cbc_dec8x_tail:				# up to 7 "words" tail...
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+	vncipher	$out6,$out6,v24
+	vncipher	$out7,$out7,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+	vncipher	$out6,$out6,v25
+	vncipher	$out7,$out7,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_cbc_dec8x_tail
+
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+	vncipher	$out6,$out6,v24
+	vncipher	$out7,$out7,v24
+
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+	vncipher	$out6,$out6,v25
+	vncipher	$out7,$out7,v25
+
+	vncipher	$out1,$out1,v26
+	vncipher	$out2,$out2,v26
+	vncipher	$out3,$out3,v26
+	vncipher	$out4,$out4,v26
+	vncipher	$out5,$out5,v26
+	vncipher	$out6,$out6,v26
+	vncipher	$out7,$out7,v26
+
+	vncipher	$out1,$out1,v27
+	vncipher	$out2,$out2,v27
+	vncipher	$out3,$out3,v27
+	vncipher	$out4,$out4,v27
+	vncipher	$out5,$out5,v27
+	vncipher	$out6,$out6,v27
+	vncipher	$out7,$out7,v27
+
+	vncipher	$out1,$out1,v28
+	vncipher	$out2,$out2,v28
+	vncipher	$out3,$out3,v28
+	vncipher	$out4,$out4,v28
+	vncipher	$out5,$out5,v28
+	vncipher	$out6,$out6,v28
+	vncipher	$out7,$out7,v28
+
+	vncipher	$out1,$out1,v29
+	vncipher	$out2,$out2,v29
+	vncipher	$out3,$out3,v29
+	vncipher	$out4,$out4,v29
+	vncipher	$out5,$out5,v29
+	vncipher	$out6,$out6,v29
+	vncipher	$out7,$out7,v29
+
+	vncipher	$out1,$out1,v30
+	 vxor		$ivec,$ivec,v31		# last round key
+	vncipher	$out2,$out2,v30
+	 vxor		$in1,$in1,v31
+	vncipher	$out3,$out3,v30
+	 vxor		$in2,$in2,v31
+	vncipher	$out4,$out4,v30
+	 vxor		$in3,$in3,v31
+	vncipher	$out5,$out5,v30
+	 vxor		$in4,$in4,v31
+	vncipher	$out6,$out6,v30
+	 vxor		$in5,$in5,v31
+	vncipher	$out7,$out7,v30
+	 vxor		$in6,$in6,v31
+
+	cmplwi		$len,32			# switch($len)
+	blt		Lcbc_dec8x_one
+	nop
+	beq		Lcbc_dec8x_two
+	cmplwi		$len,64
+	blt		Lcbc_dec8x_three
+	nop
+	beq		Lcbc_dec8x_four
+	cmplwi		$len,96
+	blt		Lcbc_dec8x_five
+	nop
+	beq		Lcbc_dec8x_six
+
+Lcbc_dec8x_seven:
+	vncipherlast	$out1,$out1,$ivec
+	vncipherlast	$out2,$out2,$in1
+	vncipherlast	$out3,$out3,$in2
+	vncipherlast	$out4,$out4,$in3
+	vncipherlast	$out5,$out5,$in4
+	vncipherlast	$out6,$out6,$in5
+	vncipherlast	$out7,$out7,$in6
+	vmr		$ivec,$in7
+
+	le?vperm	$out1,$out1,$out1,$inpperm
+	le?vperm	$out2,$out2,$out2,$inpperm
+	stvx_u		$out1,$x00,$out
+	le?vperm	$out3,$out3,$out3,$inpperm
+	stvx_u		$out2,$x10,$out
+	le?vperm	$out4,$out4,$out4,$inpperm
+	stvx_u		$out3,$x20,$out
+	le?vperm	$out5,$out5,$out5,$inpperm
+	stvx_u		$out4,$x30,$out
+	le?vperm	$out6,$out6,$out6,$inpperm
+	stvx_u		$out5,$x40,$out
+	le?vperm	$out7,$out7,$out7,$inpperm
+	stvx_u		$out6,$x50,$out
+	stvx_u		$out7,$x60,$out
+	addi		$out,$out,0x70
+	b		Lcbc_dec8x_done
+
+.align	5
+Lcbc_dec8x_six:
+	vncipherlast	$out2,$out2,$ivec
+	vncipherlast	$out3,$out3,$in2
+	vncipherlast	$out4,$out4,$in3
+	vncipherlast	$out5,$out5,$in4
+	vncipherlast	$out6,$out6,$in5
+	vncipherlast	$out7,$out7,$in6
+	vmr		$ivec,$in7
+
+	le?vperm	$out2,$out2,$out2,$inpperm
+	le?vperm	$out3,$out3,$out3,$inpperm
+	stvx_u		$out2,$x00,$out
+	le?vperm	$out4,$out4,$out4,$inpperm
+	stvx_u		$out3,$x10,$out
+	le?vperm	$out5,$out5,$out5,$inpperm
+	stvx_u		$out4,$x20,$out
+	le?vperm	$out6,$out6,$out6,$inpperm
+	stvx_u		$out5,$x30,$out
+	le?vperm	$out7,$out7,$out7,$inpperm
+	stvx_u		$out6,$x40,$out
+	stvx_u		$out7,$x50,$out
+	addi		$out,$out,0x60
+	b		Lcbc_dec8x_done
+
+.align	5
+Lcbc_dec8x_five:
+	vncipherlast	$out3,$out3,$ivec
+	vncipherlast	$out4,$out4,$in3
+	vncipherlast	$out5,$out5,$in4
+	vncipherlast	$out6,$out6,$in5
+	vncipherlast	$out7,$out7,$in6
+	vmr		$ivec,$in7
+
+	le?vperm	$out3,$out3,$out3,$inpperm
+	le?vperm	$out4,$out4,$out4,$inpperm
+	stvx_u		$out3,$x00,$out
+	le?vperm	$out5,$out5,$out5,$inpperm
+	stvx_u		$out4,$x10,$out
+	le?vperm	$out6,$out6,$out6,$inpperm
+	stvx_u		$out5,$x20,$out
+	le?vperm	$out7,$out7,$out7,$inpperm
+	stvx_u		$out6,$x30,$out
+	stvx_u		$out7,$x40,$out
+	addi		$out,$out,0x50
+	b		Lcbc_dec8x_done
+
+.align	5
+Lcbc_dec8x_four:
+	vncipherlast	$out4,$out4,$ivec
+	vncipherlast	$out5,$out5,$in4
+	vncipherlast	$out6,$out6,$in5
+	vncipherlast	$out7,$out7,$in6
+	vmr		$ivec,$in7
+
+	le?vperm	$out4,$out4,$out4,$inpperm
+	le?vperm	$out5,$out5,$out5,$inpperm
+	stvx_u		$out4,$x00,$out
+	le?vperm	$out6,$out6,$out6,$inpperm
+	stvx_u		$out5,$x10,$out
+	le?vperm	$out7,$out7,$out7,$inpperm
+	stvx_u		$out6,$x20,$out
+	stvx_u		$out7,$x30,$out
+	addi		$out,$out,0x40
+	b		Lcbc_dec8x_done
+
+.align	5
+Lcbc_dec8x_three:
+	vncipherlast	$out5,$out5,$ivec
+	vncipherlast	$out6,$out6,$in5
+	vncipherlast	$out7,$out7,$in6
+	vmr		$ivec,$in7
+
+	le?vperm	$out5,$out5,$out5,$inpperm
+	le?vperm	$out6,$out6,$out6,$inpperm
+	stvx_u		$out5,$x00,$out
+	le?vperm	$out7,$out7,$out7,$inpperm
+	stvx_u		$out6,$x10,$out
+	stvx_u		$out7,$x20,$out
+	addi		$out,$out,0x30
+	b		Lcbc_dec8x_done
+
+.align	5
+Lcbc_dec8x_two:
+	vncipherlast	$out6,$out6,$ivec
+	vncipherlast	$out7,$out7,$in6
+	vmr		$ivec,$in7
+
+	le?vperm	$out6,$out6,$out6,$inpperm
+	le?vperm	$out7,$out7,$out7,$inpperm
+	stvx_u		$out6,$x00,$out
+	stvx_u		$out7,$x10,$out
+	addi		$out,$out,0x20
+	b		Lcbc_dec8x_done
+
+.align	5
+Lcbc_dec8x_one:
+	vncipherlast	$out7,$out7,$ivec
+	vmr		$ivec,$in7
+
+	le?vperm	$out7,$out7,$out7,$inpperm
+	stvx_u		$out7,0,$out
+	addi		$out,$out,0x10
+
+Lcbc_dec8x_done:
+	le?vperm	$ivec,$ivec,$ivec,$inpperm
+	stvx_u		$ivec,0,$ivp		# write [unaligned] iv
+
+	li		r10,`$FRAME+15`
+	li		r11,`$FRAME+31`
+	stvx		$inpperm,r10,$sp	# wipe copies of round keys
+	addi		r10,r10,32
+	stvx		$inpperm,r11,$sp
+	addi		r11,r11,32
+	stvx		$inpperm,r10,$sp
+	addi		r10,r10,32
+	stvx		$inpperm,r11,$sp
+	addi		r11,r11,32
+	stvx		$inpperm,r10,$sp
+	addi		r10,r10,32
+	stvx		$inpperm,r11,$sp
+	addi		r11,r11,32
+	stvx		$inpperm,r10,$sp
+	addi		r10,r10,32
+	stvx		$inpperm,r11,$sp
+	addi		r11,r11,32
+
+	mtspr		256,$vrsave
+	lvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	lvx		v21,r11,$sp
+	addi		r11,r11,32
+	lvx		v22,r10,$sp
+	addi		r10,r10,32
+	lvx		v23,r11,$sp
+	addi		r11,r11,32
+	lvx		v24,r10,$sp
+	addi		r10,r10,32
+	lvx		v25,r11,$sp
+	addi		r11,r11,32
+	lvx		v26,r10,$sp
+	addi		r10,r10,32
+	lvx		v27,r11,$sp
+	addi		r11,r11,32
+	lvx		v28,r10,$sp
+	addi		r10,r10,32
+	lvx		v29,r11,$sp
+	addi		r11,r11,32
+	lvx		v30,r10,$sp
+	lvx		v31,r11,$sp
+	$POP		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	$POP		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	$POP		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	$POP		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	$POP		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	$POP		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	addi		$sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0x80,6,6,0
+	.long		0
+.size	.${prefix}_cbc_encrypt,.-.${prefix}_cbc_encrypt
+___
+}}	}}}
+
+#########################################################################
+{{{	# CTR procedure[s]						#
+
+####################### WARNING: Here be dragons! #######################
+#
+# This code is written as 'ctr32', based on a 32-bit counter used
+# upstream. The kernel does *not* use a 32-bit counter. The kernel uses
+# a 128-bit counter.
+#
+# This leads to subtle changes from the upstream code: the counter
+# is incremented with vaddu_q_m rather than vaddu_w_m. This occurs in
+# both the bulk (8 blocks at a time) path, and in the individual block
+# path. Be aware of this when doing updates.
+#
+# See:
+# 1d4aa0b4c181 ("crypto: vmx - Fixing AES-CTR counter bug")
+# 009b30ac7444 ("crypto: vmx - CTR: always increment IV as quadword")
+# https://github.com/openssl/openssl/pull/8942
+#
+#########################################################################
+my ($inp,$out,$len,$key,$ivp,$x10,$rounds,$idx)=map("r$_",(3..10));
+my ($rndkey0,$rndkey1,$inout,$tmp)=		map("v$_",(0..3));
+my ($ivec,$inptail,$inpperm,$outhead,$outperm,$outmask,$keyperm,$one)=
+						map("v$_",(4..11));
+my $dat=$tmp;
+
+$code.=<<___;
+.globl	.${prefix}_ctr32_encrypt_blocks
+	${UCMP}i	$len,1
+	bltlr-
+
+	lis		r0,0xfff0
+	mfspr		$vrsave,256
+	mtspr		256,r0
+
+	li		$idx,15
+	vxor		$rndkey0,$rndkey0,$rndkey0
+	le?vspltisb	$tmp,0x0f
+
+	lvx		$ivec,0,$ivp		# load [unaligned] iv
+	lvsl		$inpperm,0,$ivp
+	lvx		$inptail,$idx,$ivp
+	 vspltisb	$one,1
+	le?vxor		$inpperm,$inpperm,$tmp
+	vperm		$ivec,$ivec,$inptail,$inpperm
+	 vsldoi		$one,$rndkey0,$one,1
+
+	neg		r11,$inp
+	?lvsl		$keyperm,0,$key		# prepare for unaligned key
+	lwz		$rounds,240($key)
+
+	lvsr		$inpperm,0,r11		# prepare for unaligned load
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,15		# 15 is not typo
+	le?vxor		$inpperm,$inpperm,$tmp
+
+	srwi		$rounds,$rounds,1
+	li		$idx,16
+	subi		$rounds,$rounds,1
+
+	${UCMP}i	$len,8
+	bge		_aesp8_ctr32_encrypt8x
+
+	?lvsr		$outperm,0,$out		# prepare for unaligned store
+	vspltisb	$outmask,-1
+	lvx		$outhead,0,$out
+	?vperm		$outmask,$rndkey0,$outmask,$outperm
+	le?vxor		$outperm,$outperm,$tmp
+
+	lvx		$rndkey0,0,$key
+	mtctr		$rounds
+	lvx		$rndkey1,$idx,$key
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$ivec,$rndkey0
+	lvx		$rndkey0,$idx,$key
+	addi		$idx,$idx,16
+	b		Loop_ctr32_enc
+
+.align	5
+Loop_ctr32_enc:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key
+	addi		$idx,$idx,16
+	bdnz		Loop_ctr32_enc
+
+	vadduqm		$ivec,$ivec,$one	# Kernel change for 128-bit
+	 vmr		$dat,$inptail
+	 lvx		$inptail,0,$inp
+	 addi		$inp,$inp,16
+	 subic.		$len,$len,1		# blocks--
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key
+	 vperm		$dat,$dat,$inptail,$inpperm
+	 li		$idx,16
+	?vperm		$rndkey1,$rndkey0,$rndkey1,$keyperm
+	 lvx		$rndkey0,0,$key
+	vxor		$dat,$dat,$rndkey1	# last round key
+	vcipherlast	$inout,$inout,$dat
+
+	 lvx		$rndkey1,$idx,$key
+	 addi		$idx,$idx,16
+	vperm		$inout,$inout,$inout,$outperm
+	vsel		$dat,$outhead,$inout,$outmask
+	 mtctr		$rounds
+	 ?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vmr		$outhead,$inout
+	 vxor		$inout,$ivec,$rndkey0
+	 lvx		$rndkey0,$idx,$key
+	 addi		$idx,$idx,16
+	stvx		$dat,0,$out
+	addi		$out,$out,16
+	bne		Loop_ctr32_enc
+
+	addi		$out,$out,-1
+	lvx		$inout,0,$out		# redundant in aligned case
+	vsel		$inout,$outhead,$inout,$outmask
+	stvx		$inout,0,$out
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,6,0
+	.long		0
+___
+#########################################################################
+{{	# Optimized CTR procedure					#
+my $key_="r11";
+my ($x00,$x10,$x20,$x30,$x40,$x50,$x60,$x70)=map("r$_",(0,8,26..31));
+my ($in0, $in1, $in2, $in3, $in4, $in5, $in6, $in7 )=map("v$_",(0..3,10,12..14));
+my ($out0,$out1,$out2,$out3,$out4,$out5,$out6,$out7)=map("v$_",(15..22));
+my $rndkey0="v23";	# v24-v25 rotating buffer for first found keys
+			# v26-v31 last 6 round keys
+my ($tmp,$keyperm)=($in3,$in4);	# aliases with "caller", redundant assignment
+my ($two,$three,$four)=($outhead,$outperm,$outmask);
+
+$code.=<<___;
+.align	5
+_aesp8_ctr32_encrypt8x:
+	$STU		$sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+	li		r10,`$FRAME+8*16+15`
+	li		r11,`$FRAME+8*16+31`
+	stvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	stvx		v21,r11,$sp
+	addi		r11,r11,32
+	stvx		v22,r10,$sp
+	addi		r10,r10,32
+	stvx		v23,r11,$sp
+	addi		r11,r11,32
+	stvx		v24,r10,$sp
+	addi		r10,r10,32
+	stvx		v25,r11,$sp
+	addi		r11,r11,32
+	stvx		v26,r10,$sp
+	addi		r10,r10,32
+	stvx		v27,r11,$sp
+	addi		r11,r11,32
+	stvx		v28,r10,$sp
+	addi		r10,r10,32
+	stvx		v29,r11,$sp
+	addi		r11,r11,32
+	stvx		v30,r10,$sp
+	stvx		v31,r11,$sp
+	li		r0,-1
+	stw		$vrsave,`$FRAME+21*16-4`($sp)	# save vrsave
+	li		$x10,0x10
+	$PUSH		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	li		$x20,0x20
+	$PUSH		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	li		$x30,0x30
+	$PUSH		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	li		$x40,0x40
+	$PUSH		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	li		$x50,0x50
+	$PUSH		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	li		$x60,0x60
+	$PUSH		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	li		$x70,0x70
+	mtspr		256,r0
+
+	subi		$rounds,$rounds,3	# -4 in total
+
+	lvx		$rndkey0,$x00,$key	# load key schedule
+	lvx		v30,$x10,$key
+	addi		$key,$key,0x20
+	lvx		v31,$x00,$key
+	?vperm		$rndkey0,$rndkey0,v30,$keyperm
+	addi		$key_,$sp,$FRAME+15
+	mtctr		$rounds
+
+Load_ctr32_enc_key:
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v30,$x10,$key
+	addi		$key,$key,0x20
+	stvx		v24,$x00,$key_		# off-load round[1]
+	?vperm		v25,v31,v30,$keyperm
+	lvx		v31,$x00,$key
+	stvx		v25,$x10,$key_		# off-load round[2]
+	addi		$key_,$key_,0x20
+	bdnz		Load_ctr32_enc_key
+
+	lvx		v26,$x10,$key
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v27,$x20,$key
+	stvx		v24,$x00,$key_		# off-load round[3]
+	?vperm		v25,v31,v26,$keyperm
+	lvx		v28,$x30,$key
+	stvx		v25,$x10,$key_		# off-load round[4]
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	?vperm		v26,v26,v27,$keyperm
+	lvx		v29,$x40,$key
+	?vperm		v27,v27,v28,$keyperm
+	lvx		v30,$x50,$key
+	?vperm		v28,v28,v29,$keyperm
+	lvx		v31,$x60,$key
+	?vperm		v29,v29,v30,$keyperm
+	lvx		$out0,$x70,$key		# borrow $out0
+	?vperm		v30,v30,v31,$keyperm
+	lvx		v24,$x00,$key_		# pre-load round[1]
+	?vperm		v31,v31,$out0,$keyperm
+	lvx		v25,$x10,$key_		# pre-load round[2]
+
+	vadduqm		$two,$one,$one
+	subi		$inp,$inp,15		# undo "caller"
+	$SHL		$len,$len,4
+
+	vadduqm		$out1,$ivec,$one	# counter values ...
+	vadduqm		$out2,$ivec,$two	# (do all ctr adds as 128-bit)
+	vxor		$out0,$ivec,$rndkey0	# ... xored with rndkey[0]
+	 le?li		$idx,8
+	vadduqm		$out3,$out1,$two
+	vxor		$out1,$out1,$rndkey0
+	 le?lvsl	$inpperm,0,$idx
+	vadduqm		$out4,$out2,$two
+	vxor		$out2,$out2,$rndkey0
+	 le?vspltisb	$tmp,0x0f
+	vadduqm		$out5,$out3,$two
+	vxor		$out3,$out3,$rndkey0
+	 le?vxor	$inpperm,$inpperm,$tmp	# transform for lvx_u/stvx_u
+	vadduqm		$out6,$out4,$two
+	vxor		$out4,$out4,$rndkey0
+	vadduqm		$out7,$out5,$two
+	vxor		$out5,$out5,$rndkey0
+	vadduqm		$ivec,$out6,$two	# next counter value
+	vxor		$out6,$out6,$rndkey0
+	vxor		$out7,$out7,$rndkey0
+
+	mtctr		$rounds
+	b		Loop_ctr32_enc8x
+.align	5
+Loop_ctr32_enc8x:
+	vcipher 	$out0,$out0,v24
+	vcipher 	$out1,$out1,v24
+	vcipher 	$out2,$out2,v24
+	vcipher 	$out3,$out3,v24
+	vcipher 	$out4,$out4,v24
+	vcipher 	$out5,$out5,v24
+	vcipher 	$out6,$out6,v24
+	vcipher 	$out7,$out7,v24
+Loop_ctr32_enc8x_middle:
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher 	$out0,$out0,v25
+	vcipher 	$out1,$out1,v25
+	vcipher 	$out2,$out2,v25
+	vcipher 	$out3,$out3,v25
+	vcipher 	$out4,$out4,v25
+	vcipher 	$out5,$out5,v25
+	vcipher 	$out6,$out6,v25
+	vcipher 	$out7,$out7,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_ctr32_enc8x
+
+	subic		r11,$len,256		# $len-256, borrow $key_
+	vcipher 	$out0,$out0,v24
+	vcipher 	$out1,$out1,v24
+	vcipher 	$out2,$out2,v24
+	vcipher 	$out3,$out3,v24
+	vcipher 	$out4,$out4,v24
+	vcipher 	$out5,$out5,v24
+	vcipher 	$out6,$out6,v24
+	vcipher 	$out7,$out7,v24
+
+	subfe		r0,r0,r0		# borrow?-1:0
+	vcipher 	$out0,$out0,v25
+	vcipher 	$out1,$out1,v25
+	vcipher 	$out2,$out2,v25
+	vcipher 	$out3,$out3,v25
+	vcipher 	$out4,$out4,v25
+	vcipher		$out5,$out5,v25
+	vcipher		$out6,$out6,v25
+	vcipher		$out7,$out7,v25
+
+	and		r0,r0,r11
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vcipher		$out0,$out0,v26
+	vcipher		$out1,$out1,v26
+	vcipher		$out2,$out2,v26
+	vcipher		$out3,$out3,v26
+	vcipher		$out4,$out4,v26
+	vcipher		$out5,$out5,v26
+	vcipher		$out6,$out6,v26
+	vcipher		$out7,$out7,v26
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	subic		$len,$len,129		# $len-=129
+	vcipher		$out0,$out0,v27
+	addi		$len,$len,1		# $len-=128 really
+	vcipher		$out1,$out1,v27
+	vcipher		$out2,$out2,v27
+	vcipher		$out3,$out3,v27
+	vcipher		$out4,$out4,v27
+	vcipher		$out5,$out5,v27
+	vcipher		$out6,$out6,v27
+	vcipher		$out7,$out7,v27
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+
+	vcipher		$out0,$out0,v28
+	 lvx_u		$in0,$x00,$inp		# load input
+	vcipher		$out1,$out1,v28
+	 lvx_u		$in1,$x10,$inp
+	vcipher		$out2,$out2,v28
+	 lvx_u		$in2,$x20,$inp
+	vcipher		$out3,$out3,v28
+	 lvx_u		$in3,$x30,$inp
+	vcipher		$out4,$out4,v28
+	 lvx_u		$in4,$x40,$inp
+	vcipher		$out5,$out5,v28
+	 lvx_u		$in5,$x50,$inp
+	vcipher		$out6,$out6,v28
+	 lvx_u		$in6,$x60,$inp
+	vcipher		$out7,$out7,v28
+	 lvx_u		$in7,$x70,$inp
+	 addi		$inp,$inp,0x80
+
+	vcipher		$out0,$out0,v29
+	 le?vperm	$in0,$in0,$in0,$inpperm
+	vcipher		$out1,$out1,v29
+	 le?vperm	$in1,$in1,$in1,$inpperm
+	vcipher		$out2,$out2,v29
+	 le?vperm	$in2,$in2,$in2,$inpperm
+	vcipher		$out3,$out3,v29
+	 le?vperm	$in3,$in3,$in3,$inpperm
+	vcipher		$out4,$out4,v29
+	 le?vperm	$in4,$in4,$in4,$inpperm
+	vcipher		$out5,$out5,v29
+	 le?vperm	$in5,$in5,$in5,$inpperm
+	vcipher		$out6,$out6,v29
+	 le?vperm	$in6,$in6,$in6,$inpperm
+	vcipher		$out7,$out7,v29
+	 le?vperm	$in7,$in7,$in7,$inpperm
+
+	add		$inp,$inp,r0		# $inp is adjusted in such
+						# way that at exit from the
+						# loop inX-in7 are loaded
+						# with last "words"
+	subfe.		r0,r0,r0		# borrow?-1:0
+	vcipher		$out0,$out0,v30
+	 vxor		$in0,$in0,v31		# xor with last round key
+	vcipher		$out1,$out1,v30
+	 vxor		$in1,$in1,v31
+	vcipher		$out2,$out2,v30
+	 vxor		$in2,$in2,v31
+	vcipher		$out3,$out3,v30
+	 vxor		$in3,$in3,v31
+	vcipher		$out4,$out4,v30
+	 vxor		$in4,$in4,v31
+	vcipher		$out5,$out5,v30
+	 vxor		$in5,$in5,v31
+	vcipher		$out6,$out6,v30
+	 vxor		$in6,$in6,v31
+	vcipher		$out7,$out7,v30
+	 vxor		$in7,$in7,v31
+
+	bne		Lctr32_enc8x_break	# did $len-129 borrow?
+
+	vcipherlast	$in0,$out0,$in0
+	vcipherlast	$in1,$out1,$in1
+	 vadduqm	$out1,$ivec,$one	# counter values ...
+	vcipherlast	$in2,$out2,$in2
+	 vadduqm	$out2,$ivec,$two
+	 vxor		$out0,$ivec,$rndkey0	# ... xored with rndkey[0]
+	vcipherlast	$in3,$out3,$in3
+	 vadduqm	$out3,$out1,$two
+	 vxor		$out1,$out1,$rndkey0
+	vcipherlast	$in4,$out4,$in4
+	 vadduqm	$out4,$out2,$two
+	 vxor		$out2,$out2,$rndkey0
+	vcipherlast	$in5,$out5,$in5
+	 vadduqm	$out5,$out3,$two
+	 vxor		$out3,$out3,$rndkey0
+	vcipherlast	$in6,$out6,$in6
+	 vadduqm	$out6,$out4,$two
+	 vxor		$out4,$out4,$rndkey0
+	vcipherlast	$in7,$out7,$in7
+	 vadduqm	$out7,$out5,$two
+	 vxor		$out5,$out5,$rndkey0
+	le?vperm	$in0,$in0,$in0,$inpperm
+	 vadduqm	$ivec,$out6,$two	# next counter value
+	 vxor		$out6,$out6,$rndkey0
+	le?vperm	$in1,$in1,$in1,$inpperm
+	 vxor		$out7,$out7,$rndkey0
+	mtctr		$rounds
+
+	 vcipher	$out0,$out0,v24
+	stvx_u		$in0,$x00,$out
+	le?vperm	$in2,$in2,$in2,$inpperm
+	 vcipher	$out1,$out1,v24
+	stvx_u		$in1,$x10,$out
+	le?vperm	$in3,$in3,$in3,$inpperm
+	 vcipher	$out2,$out2,v24
+	stvx_u		$in2,$x20,$out
+	le?vperm	$in4,$in4,$in4,$inpperm
+	 vcipher	$out3,$out3,v24
+	stvx_u		$in3,$x30,$out
+	le?vperm	$in5,$in5,$in5,$inpperm
+	 vcipher	$out4,$out4,v24
+	stvx_u		$in4,$x40,$out
+	le?vperm	$in6,$in6,$in6,$inpperm
+	 vcipher	$out5,$out5,v24
+	stvx_u		$in5,$x50,$out
+	le?vperm	$in7,$in7,$in7,$inpperm
+	 vcipher	$out6,$out6,v24
+	stvx_u		$in6,$x60,$out
+	 vcipher	$out7,$out7,v24
+	stvx_u		$in7,$x70,$out
+	addi		$out,$out,0x80
+
+	b		Loop_ctr32_enc8x_middle
+
+.align	5
+Lctr32_enc8x_break:
+	cmpwi		$len,-0x60
+	blt		Lctr32_enc8x_one
+	nop
+	beq		Lctr32_enc8x_two
+	cmpwi		$len,-0x40
+	blt		Lctr32_enc8x_three
+	nop
+	beq		Lctr32_enc8x_four
+	cmpwi		$len,-0x20
+	blt		Lctr32_enc8x_five
+	nop
+	beq		Lctr32_enc8x_six
+	cmpwi		$len,0x00
+	blt		Lctr32_enc8x_seven
+
+Lctr32_enc8x_eight:
+	vcipherlast	$out0,$out0,$in0
+	vcipherlast	$out1,$out1,$in1
+	vcipherlast	$out2,$out2,$in2
+	vcipherlast	$out3,$out3,$in3
+	vcipherlast	$out4,$out4,$in4
+	vcipherlast	$out5,$out5,$in5
+	vcipherlast	$out6,$out6,$in6
+	vcipherlast	$out7,$out7,$in7
+
+	le?vperm	$out0,$out0,$out0,$inpperm
+	le?vperm	$out1,$out1,$out1,$inpperm
+	stvx_u		$out0,$x00,$out
+	le?vperm	$out2,$out2,$out2,$inpperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$inpperm
+	stvx_u		$out2,$x20,$out
+	le?vperm	$out4,$out4,$out4,$inpperm
+	stvx_u		$out3,$x30,$out
+	le?vperm	$out5,$out5,$out5,$inpperm
+	stvx_u		$out4,$x40,$out
+	le?vperm	$out6,$out6,$out6,$inpperm
+	stvx_u		$out5,$x50,$out
+	le?vperm	$out7,$out7,$out7,$inpperm
+	stvx_u		$out6,$x60,$out
+	stvx_u		$out7,$x70,$out
+	addi		$out,$out,0x80
+	b		Lctr32_enc8x_done
+
+.align	5
+Lctr32_enc8x_seven:
+	vcipherlast	$out0,$out0,$in1
+	vcipherlast	$out1,$out1,$in2
+	vcipherlast	$out2,$out2,$in3
+	vcipherlast	$out3,$out3,$in4
+	vcipherlast	$out4,$out4,$in5
+	vcipherlast	$out5,$out5,$in6
+	vcipherlast	$out6,$out6,$in7
+
+	le?vperm	$out0,$out0,$out0,$inpperm
+	le?vperm	$out1,$out1,$out1,$inpperm
+	stvx_u		$out0,$x00,$out
+	le?vperm	$out2,$out2,$out2,$inpperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$inpperm
+	stvx_u		$out2,$x20,$out
+	le?vperm	$out4,$out4,$out4,$inpperm
+	stvx_u		$out3,$x30,$out
+	le?vperm	$out5,$out5,$out5,$inpperm
+	stvx_u		$out4,$x40,$out
+	le?vperm	$out6,$out6,$out6,$inpperm
+	stvx_u		$out5,$x50,$out
+	stvx_u		$out6,$x60,$out
+	addi		$out,$out,0x70
+	b		Lctr32_enc8x_done
+
+.align	5
+Lctr32_enc8x_six:
+	vcipherlast	$out0,$out0,$in2
+	vcipherlast	$out1,$out1,$in3
+	vcipherlast	$out2,$out2,$in4
+	vcipherlast	$out3,$out3,$in5
+	vcipherlast	$out4,$out4,$in6
+	vcipherlast	$out5,$out5,$in7
+
+	le?vperm	$out0,$out0,$out0,$inpperm
+	le?vperm	$out1,$out1,$out1,$inpperm
+	stvx_u		$out0,$x00,$out
+	le?vperm	$out2,$out2,$out2,$inpperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$inpperm
+	stvx_u		$out2,$x20,$out
+	le?vperm	$out4,$out4,$out4,$inpperm
+	stvx_u		$out3,$x30,$out
+	le?vperm	$out5,$out5,$out5,$inpperm
+	stvx_u		$out4,$x40,$out
+	stvx_u		$out5,$x50,$out
+	addi		$out,$out,0x60
+	b		Lctr32_enc8x_done
+
+.align	5
+Lctr32_enc8x_five:
+	vcipherlast	$out0,$out0,$in3
+	vcipherlast	$out1,$out1,$in4
+	vcipherlast	$out2,$out2,$in5
+	vcipherlast	$out3,$out3,$in6
+	vcipherlast	$out4,$out4,$in7
+
+	le?vperm	$out0,$out0,$out0,$inpperm
+	le?vperm	$out1,$out1,$out1,$inpperm
+	stvx_u		$out0,$x00,$out
+	le?vperm	$out2,$out2,$out2,$inpperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$inpperm
+	stvx_u		$out2,$x20,$out
+	le?vperm	$out4,$out4,$out4,$inpperm
+	stvx_u		$out3,$x30,$out
+	stvx_u		$out4,$x40,$out
+	addi		$out,$out,0x50
+	b		Lctr32_enc8x_done
+
+.align	5
+Lctr32_enc8x_four:
+	vcipherlast	$out0,$out0,$in4
+	vcipherlast	$out1,$out1,$in5
+	vcipherlast	$out2,$out2,$in6
+	vcipherlast	$out3,$out3,$in7
+
+	le?vperm	$out0,$out0,$out0,$inpperm
+	le?vperm	$out1,$out1,$out1,$inpperm
+	stvx_u		$out0,$x00,$out
+	le?vperm	$out2,$out2,$out2,$inpperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$inpperm
+	stvx_u		$out2,$x20,$out
+	stvx_u		$out3,$x30,$out
+	addi		$out,$out,0x40
+	b		Lctr32_enc8x_done
+
+.align	5
+Lctr32_enc8x_three:
+	vcipherlast	$out0,$out0,$in5
+	vcipherlast	$out1,$out1,$in6
+	vcipherlast	$out2,$out2,$in7
+
+	le?vperm	$out0,$out0,$out0,$inpperm
+	le?vperm	$out1,$out1,$out1,$inpperm
+	stvx_u		$out0,$x00,$out
+	le?vperm	$out2,$out2,$out2,$inpperm
+	stvx_u		$out1,$x10,$out
+	stvx_u		$out2,$x20,$out
+	addi		$out,$out,0x30
+	b		Lctr32_enc8x_done
+
+.align	5
+Lctr32_enc8x_two:
+	vcipherlast	$out0,$out0,$in6
+	vcipherlast	$out1,$out1,$in7
+
+	le?vperm	$out0,$out0,$out0,$inpperm
+	le?vperm	$out1,$out1,$out1,$inpperm
+	stvx_u		$out0,$x00,$out
+	stvx_u		$out1,$x10,$out
+	addi		$out,$out,0x20
+	b		Lctr32_enc8x_done
+
+.align	5
+Lctr32_enc8x_one:
+	vcipherlast	$out0,$out0,$in7
+
+	le?vperm	$out0,$out0,$out0,$inpperm
+	stvx_u		$out0,0,$out
+	addi		$out,$out,0x10
+
+Lctr32_enc8x_done:
+	li		r10,`$FRAME+15`
+	li		r11,`$FRAME+31`
+	stvx		$inpperm,r10,$sp	# wipe copies of round keys
+	addi		r10,r10,32
+	stvx		$inpperm,r11,$sp
+	addi		r11,r11,32
+	stvx		$inpperm,r10,$sp
+	addi		r10,r10,32
+	stvx		$inpperm,r11,$sp
+	addi		r11,r11,32
+	stvx		$inpperm,r10,$sp
+	addi		r10,r10,32
+	stvx		$inpperm,r11,$sp
+	addi		r11,r11,32
+	stvx		$inpperm,r10,$sp
+	addi		r10,r10,32
+	stvx		$inpperm,r11,$sp
+	addi		r11,r11,32
+
+	mtspr		256,$vrsave
+	lvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	lvx		v21,r11,$sp
+	addi		r11,r11,32
+	lvx		v22,r10,$sp
+	addi		r10,r10,32
+	lvx		v23,r11,$sp
+	addi		r11,r11,32
+	lvx		v24,r10,$sp
+	addi		r10,r10,32
+	lvx		v25,r11,$sp
+	addi		r11,r11,32
+	lvx		v26,r10,$sp
+	addi		r10,r10,32
+	lvx		v27,r11,$sp
+	addi		r11,r11,32
+	lvx		v28,r10,$sp
+	addi		r10,r10,32
+	lvx		v29,r11,$sp
+	addi		r11,r11,32
+	lvx		v30,r10,$sp
+	lvx		v31,r11,$sp
+	$POP		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	$POP		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	$POP		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	$POP		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	$POP		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	$POP		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	addi		$sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0x80,6,6,0
+	.long		0
+.size	.${prefix}_ctr32_encrypt_blocks,.-.${prefix}_ctr32_encrypt_blocks
+___
+}}	}}}
+
+#########################################################################
+{{{	# XTS procedures						#
+# int aes_p8_xts_[en|de]crypt(const char *inp, char *out, size_t len,	#
+#                             const AES_KEY *key1, const AES_KEY *key2,	#
+#                             [const] unsigned char iv[16]);		#
+# If $key2 is NULL, then a "tweak chaining" mode is engaged, in which	#
+# input tweak value is assumed to be encrypted already, and last tweak	#
+# value, one suitable for consecutive call on same chunk of data, is	#
+# written back to original buffer. In addition, in "tweak chaining"	#
+# mode only complete input blocks are processed.			#
+
+my ($inp,$out,$len,$key1,$key2,$ivp,$rounds,$idx) =	map("r$_",(3..10));
+my ($rndkey0,$rndkey1,$inout) =				map("v$_",(0..2));
+my ($output,$inptail,$inpperm,$leperm,$keyperm) =	map("v$_",(3..7));
+my ($tweak,$seven,$eighty7,$tmp,$tweak1) =		map("v$_",(8..12));
+my $taillen = $key2;
+
+   ($inp,$idx) = ($idx,$inp);				# reassign
+
+$code.=<<___;
+.globl	.${prefix}_xts_encrypt
+	mr		$inp,r3				# reassign
+	li		r3,-1
+	${UCMP}i	$len,16
+	bltlr-
+
+	lis		r0,0xfff0
+	mfspr		r12,256				# save vrsave
+	li		r11,0
+	mtspr		256,r0
+
+	vspltisb	$seven,0x07			# 0x070707..07
+	le?lvsl		$leperm,r11,r11
+	le?vspltisb	$tmp,0x0f
+	le?vxor		$leperm,$leperm,$seven
+
+	li		$idx,15
+	lvx		$tweak,0,$ivp			# load [unaligned] iv
+	lvsl		$inpperm,0,$ivp
+	lvx		$inptail,$idx,$ivp
+	le?vxor		$inpperm,$inpperm,$tmp
+	vperm		$tweak,$tweak,$inptail,$inpperm
+
+	neg		r11,$inp
+	lvsr		$inpperm,0,r11			# prepare for unaligned load
+	lvx		$inout,0,$inp
+	addi		$inp,$inp,15			# 15 is not typo
+	le?vxor		$inpperm,$inpperm,$tmp
+
+	${UCMP}i	$key2,0				# key2==NULL?
+	beq		Lxts_enc_no_key2
+
+	?lvsl		$keyperm,0,$key2		# prepare for unaligned key
+	lwz		$rounds,240($key2)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	lvx		$rndkey0,0,$key2
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+Ltweak_xts_enc:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	bdnz		Ltweak_xts_enc
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipherlast	$tweak,$tweak,$rndkey0
+
+	li		$ivp,0				# don't chain the tweak
+	b		Lxts_enc
+
+Lxts_enc_no_key2:
+	li		$idx,-16
+	and		$len,$len,$idx			# in "tweak chaining"
+							# mode only complete
+							# blocks are processed
+Lxts_enc:
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+
+	?lvsl		$keyperm,0,$key1		# prepare for unaligned key
+	lwz		$rounds,240($key1)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	vslb		$eighty7,$seven,$seven		# 0x808080..80
+	vor		$eighty7,$eighty7,$seven	# 0x878787..87
+	vspltisb	$tmp,1				# 0x010101..01
+	vsldoi		$eighty7,$eighty7,$tmp,15	# 0x870101..01
+
+	${UCMP}i	$len,96
+	bge		_aesp8_xts_encrypt6x
+
+	andi.		$taillen,$len,15
+	subic		r0,$len,32
+	subi		$taillen,$taillen,16
+	subfe		r0,r0,r0
+	and		r0,r0,$taillen
+	add		$inp,$inp,r0
+
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	mtctr		$rounds
+	b		Loop_xts_enc
+
+.align	5
+Loop_xts_enc:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	bdnz		Loop_xts_enc
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$rndkey0,$rndkey0,$tweak
+	vcipherlast	$output,$inout,$rndkey0
+
+	le?vperm	$tmp,$output,$output,$leperm
+	be?nop
+	le?stvx_u	$tmp,0,$out
+	be?stvx_u	$output,0,$out
+	addi		$out,$out,16
+
+	subic.		$len,$len,16
+	beq		Lxts_enc_done
+
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+
+	subic		r0,$len,32
+	subfe		r0,r0,r0
+	and		r0,r0,$taillen
+	add		$inp,$inp,r0
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$output,$output,$rndkey0	# just in case $len<16
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+
+	mtctr		$rounds
+	${UCMP}i	$len,16
+	bge		Loop_xts_enc
+
+	vxor		$output,$output,$tweak
+	lvsr		$inpperm,0,$len			# $inpperm is no longer needed
+	vxor		$inptail,$inptail,$inptail	# $inptail is no longer needed
+	vspltisb	$tmp,-1
+	vperm		$inptail,$inptail,$tmp,$inpperm
+	vsel		$inout,$inout,$output,$inptail
+
+	subi		r11,$out,17
+	subi		$out,$out,16
+	mtctr		$len
+	li		$len,16
+Loop_xts_enc_steal:
+	lbzu		r0,1(r11)
+	stb		r0,16(r11)
+	bdnz		Loop_xts_enc_steal
+
+	mtctr		$rounds
+	b		Loop_xts_enc			# one more time...
+
+Lxts_enc_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_enc_ret
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_enc_ret:
+	mtspr		256,r12				# restore vrsave
+	li		r3,0
+	blr
+	.long		0
+	.byte		0,12,0x04,0,0x80,6,6,0
+	.long		0
+.size	.${prefix}_xts_encrypt,.-.${prefix}_xts_encrypt
+
+.globl	.${prefix}_xts_decrypt
+	mr		$inp,r3				# reassign
+	li		r3,-1
+	${UCMP}i	$len,16
+	bltlr-
+
+	lis		r0,0xfff8
+	mfspr		r12,256				# save vrsave
+	li		r11,0
+	mtspr		256,r0
+
+	andi.		r0,$len,15
+	neg		r0,r0
+	andi.		r0,r0,16
+	sub		$len,$len,r0
+
+	vspltisb	$seven,0x07			# 0x070707..07
+	le?lvsl		$leperm,r11,r11
+	le?vspltisb	$tmp,0x0f
+	le?vxor		$leperm,$leperm,$seven
+
+	li		$idx,15
+	lvx		$tweak,0,$ivp			# load [unaligned] iv
+	lvsl		$inpperm,0,$ivp
+	lvx		$inptail,$idx,$ivp
+	le?vxor		$inpperm,$inpperm,$tmp
+	vperm		$tweak,$tweak,$inptail,$inpperm
+
+	neg		r11,$inp
+	lvsr		$inpperm,0,r11			# prepare for unaligned load
+	lvx		$inout,0,$inp
+	addi		$inp,$inp,15			# 15 is not typo
+	le?vxor		$inpperm,$inpperm,$tmp
+
+	${UCMP}i	$key2,0				# key2==NULL?
+	beq		Lxts_dec_no_key2
+
+	?lvsl		$keyperm,0,$key2		# prepare for unaligned key
+	lwz		$rounds,240($key2)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	lvx		$rndkey0,0,$key2
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+Ltweak_xts_dec:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	bdnz		Ltweak_xts_dec
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipherlast	$tweak,$tweak,$rndkey0
+
+	li		$ivp,0				# don't chain the tweak
+	b		Lxts_dec
+
+Lxts_dec_no_key2:
+	neg		$idx,$len
+	andi.		$idx,$idx,15
+	add		$len,$len,$idx			# in "tweak chaining"
+							# mode only complete
+							# blocks are processed
+Lxts_dec:
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+
+	?lvsl		$keyperm,0,$key1		# prepare for unaligned key
+	lwz		$rounds,240($key1)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	vslb		$eighty7,$seven,$seven		# 0x808080..80
+	vor		$eighty7,$eighty7,$seven	# 0x878787..87
+	vspltisb	$tmp,1				# 0x010101..01
+	vsldoi		$eighty7,$eighty7,$tmp,15	# 0x870101..01
+
+	${UCMP}i	$len,96
+	bge		_aesp8_xts_decrypt6x
+
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+	${UCMP}i	$len,16
+	blt		Ltail_xts_dec
+	be?b		Loop_xts_dec
+
+.align	5
+Loop_xts_dec:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vncipher	$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	bdnz		Loop_xts_dec
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$rndkey0,$rndkey0,$tweak
+	vncipherlast	$output,$inout,$rndkey0
+
+	le?vperm	$tmp,$output,$output,$leperm
+	be?nop
+	le?stvx_u	$tmp,0,$out
+	be?stvx_u	$output,0,$out
+	addi		$out,$out,16
+
+	subic.		$len,$len,16
+	beq		Lxts_dec_done
+
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+
+	mtctr		$rounds
+	${UCMP}i	$len,16
+	bge		Loop_xts_dec
+
+Ltail_xts_dec:
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak1,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak1,$tweak1,$tmp
+
+	subi		$inp,$inp,16
+	add		$inp,$inp,$len
+
+	vxor		$inout,$inout,$tweak		# :-(
+	vxor		$inout,$inout,$tweak1		# :-)
+
+Loop_xts_dec_short:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vncipher	$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	bdnz		Loop_xts_dec_short
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$rndkey0,$rndkey0,$tweak1
+	vncipherlast	$output,$inout,$rndkey0
+
+	le?vperm	$tmp,$output,$output,$leperm
+	be?nop
+	le?stvx_u	$tmp,0,$out
+	be?stvx_u	$output,0,$out
+
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	#addi		$inp,$inp,16
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+
+	lvsr		$inpperm,0,$len			# $inpperm is no longer needed
+	vxor		$inptail,$inptail,$inptail	# $inptail is no longer needed
+	vspltisb	$tmp,-1
+	vperm		$inptail,$inptail,$tmp,$inpperm
+	vsel		$inout,$inout,$output,$inptail
+
+	vxor		$rndkey0,$rndkey0,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+
+	subi		r11,$out,1
+	mtctr		$len
+	li		$len,16
+Loop_xts_dec_steal:
+	lbzu		r0,1(r11)
+	stb		r0,16(r11)
+	bdnz		Loop_xts_dec_steal
+
+	mtctr		$rounds
+	b		Loop_xts_dec			# one more time...
+
+Lxts_dec_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_dec_ret
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_dec_ret:
+	mtspr		256,r12				# restore vrsave
+	li		r3,0
+	blr
+	.long		0
+	.byte		0,12,0x04,0,0x80,6,6,0
+	.long		0
+.size	.${prefix}_xts_decrypt,.-.${prefix}_xts_decrypt
+___
+#########################################################################
+{{	# Optimized XTS procedures					#
+my $key_=$key2;
+my ($x00,$x10,$x20,$x30,$x40,$x50,$x60,$x70)=map("r$_",(0,3,26..31));
+    $x00=0 if ($flavour =~ /osx/);
+my ($in0,  $in1,  $in2,  $in3,  $in4,  $in5 )=map("v$_",(0..5));
+my ($out0, $out1, $out2, $out3, $out4, $out5)=map("v$_",(7,12..16));
+my ($twk0, $twk1, $twk2, $twk3, $twk4, $twk5)=map("v$_",(17..22));
+my $rndkey0="v23";	# v24-v25 rotating buffer for first found keys
+			# v26-v31 last 6 round keys
+my ($keyperm)=($out0);	# aliases with "caller", redundant assignment
+my $taillen=$x70;
+
+$code.=<<___;
+.align	5
+_aesp8_xts_encrypt6x:
+	$STU		$sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+	mflr		r11
+	li		r7,`$FRAME+8*16+15`
+	li		r3,`$FRAME+8*16+31`
+	$PUSH		r11,`$FRAME+21*16+6*$SIZE_T+$LRSAVE`($sp)
+	stvx		v20,r7,$sp		# ABI says so
+	addi		r7,r7,32
+	stvx		v21,r3,$sp
+	addi		r3,r3,32
+	stvx		v22,r7,$sp
+	addi		r7,r7,32
+	stvx		v23,r3,$sp
+	addi		r3,r3,32
+	stvx		v24,r7,$sp
+	addi		r7,r7,32
+	stvx		v25,r3,$sp
+	addi		r3,r3,32
+	stvx		v26,r7,$sp
+	addi		r7,r7,32
+	stvx		v27,r3,$sp
+	addi		r3,r3,32
+	stvx		v28,r7,$sp
+	addi		r7,r7,32
+	stvx		v29,r3,$sp
+	addi		r3,r3,32
+	stvx		v30,r7,$sp
+	stvx		v31,r3,$sp
+	li		r0,-1
+	stw		$vrsave,`$FRAME+21*16-4`($sp)	# save vrsave
+	li		$x10,0x10
+	$PUSH		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	li		$x20,0x20
+	$PUSH		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	li		$x30,0x30
+	$PUSH		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	li		$x40,0x40
+	$PUSH		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	li		$x50,0x50
+	$PUSH		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	li		$x60,0x60
+	$PUSH		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	li		$x70,0x70
+	mtspr		256,r0
+
+	xxlor		2, 32+$eighty7, 32+$eighty7
+	vsldoi		$eighty7,$tmp,$eighty7,1        # 0x010101..87
+	xxlor		1, 32+$eighty7, 32+$eighty7
+
+	# Load XOR Lconsts.
+	mr		$x70, r6
+	bl		Lconsts
+	lxvw4x		0, $x40, r6		# load XOR contents
+	mr		r6, $x70
+	li		$x70,0x70
+
+	subi		$rounds,$rounds,3	# -4 in total
+
+	lvx		$rndkey0,$x00,$key1	# load key schedule
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	lvx		v31,$x00,$key1
+	?vperm		$rndkey0,$rndkey0,v30,$keyperm
+	addi		$key_,$sp,$FRAME+15
+	mtctr		$rounds
+
+Load_xts_enc_key:
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	stvx		v24,$x00,$key_		# off-load round[1]
+	?vperm		v25,v31,v30,$keyperm
+	lvx		v31,$x00,$key1
+	stvx		v25,$x10,$key_		# off-load round[2]
+	addi		$key_,$key_,0x20
+	bdnz		Load_xts_enc_key
+
+	lvx		v26,$x10,$key1
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v27,$x20,$key1
+	stvx		v24,$x00,$key_		# off-load round[3]
+	?vperm		v25,v31,v26,$keyperm
+	lvx		v28,$x30,$key1
+	stvx		v25,$x10,$key_		# off-load round[4]
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	?vperm		v26,v26,v27,$keyperm
+	lvx		v29,$x40,$key1
+	?vperm		v27,v27,v28,$keyperm
+	lvx		v30,$x50,$key1
+	?vperm		v28,v28,v29,$keyperm
+	lvx		v31,$x60,$key1
+	?vperm		v29,v29,v30,$keyperm
+	lvx		$twk5,$x70,$key1	# borrow $twk5
+	?vperm		v30,v30,v31,$keyperm
+	lvx		v24,$x00,$key_		# pre-load round[1]
+	?vperm		v31,v31,$twk5,$keyperm
+	lvx		v25,$x10,$key_		# pre-load round[2]
+
+	# Switch to use the following codes with 0x010101..87 to generate tweak.
+	#     eighty7 = 0x010101..87
+	# vsrab         tmp, tweak, seven       # next tweak value, right shift 7 bits
+	# vand          tmp, tmp, eighty7       # last byte with carry
+	# vaddubm       tweak, tweak, tweak     # left shift 1 bit (x2)
+	# xxlor         vsx, 0, 0
+	# vpermxor      tweak, tweak, tmp, vsx
+
+	 vperm		$in0,$inout,$inptail,$inpperm
+	 subi		$inp,$inp,31		# undo "caller"
+	vxor		$twk0,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out0,$in0,$twk0
+	xxlor		32+$in1, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in1
+
+	 lvx_u		$in1,$x10,$inp
+	vxor		$twk1,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in1,$in1,$in1,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out1,$in1,$twk1
+	xxlor		32+$in2, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in2
+
+	 lvx_u		$in2,$x20,$inp
+	 andi.		$taillen,$len,15
+	vxor		$twk2,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in2,$in2,$in2,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out2,$in2,$twk2
+	xxlor		32+$in3, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in3
+
+	 lvx_u		$in3,$x30,$inp
+	 sub		$len,$len,$taillen
+	vxor		$twk3,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in3,$in3,$in3,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out3,$in3,$twk3
+	xxlor		32+$in4, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in4
+
+	 lvx_u		$in4,$x40,$inp
+	 subi		$len,$len,0x60
+	vxor		$twk4,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in4,$in4,$in4,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out4,$in4,$twk4
+	xxlor		32+$in5, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in5
+
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	vxor		$twk5,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in5,$in5,$in5,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out5,$in5,$twk5
+	xxlor		32+$in0, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in0
+
+	vxor		v31,v31,$rndkey0
+	mtctr		$rounds
+	b		Loop_xts_enc6x
+
+.align	5
+Loop_xts_enc6x:
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+	vcipher		$out5,$out5,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	vcipher		$out4,$out4,v25
+	vcipher		$out5,$out5,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_enc6x
+
+	xxlor		32+$eighty7, 1, 1	# 0x010101..87
+
+	subic		$len,$len,96		# $len-=96
+	 vxor		$in0,$twk0,v31		# xor with last round key
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk0,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+	vcipher		$out5,$out5,v24
+
+	subfe.		r0,r0,r0		# borrow?-1:0
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	 xxlor		32+$in1, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in1
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	 vxor		$in1,$twk1,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk1,$tweak,$rndkey0
+	vcipher		$out4,$out4,v25
+	vcipher		$out5,$out5,v25
+
+	and		r0,r0,$len
+	 vaddubm	$tweak,$tweak,$tweak
+	vcipher		$out0,$out0,v26
+	vcipher		$out1,$out1,v26
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out2,$out2,v26
+	vcipher		$out3,$out3,v26
+	 xxlor		32+$in2, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in2
+	vcipher		$out4,$out4,v26
+	vcipher		$out5,$out5,v26
+
+	add		$inp,$inp,r0		# $inp is adjusted in such
+						# way that at exit from the
+						# loop inX-in5 are loaded
+						# with last "words"
+	 vxor		$in2,$twk2,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk2,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vcipher		$out0,$out0,v27
+	vcipher		$out1,$out1,v27
+	vcipher		$out2,$out2,v27
+	vcipher		$out3,$out3,v27
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out4,$out4,v27
+	vcipher		$out5,$out5,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	 xxlor		32+$in3, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in3
+	vcipher		$out0,$out0,v28
+	vcipher		$out1,$out1,v28
+	 vxor		$in3,$twk3,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk3,$tweak,$rndkey0
+	vcipher		$out2,$out2,v28
+	vcipher		$out3,$out3,v28
+	 vaddubm	$tweak,$tweak,$tweak
+	vcipher		$out4,$out4,v28
+	vcipher		$out5,$out5,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vand		$tmp,$tmp,$eighty7
+
+	vcipher		$out0,$out0,v29
+	vcipher		$out1,$out1,v29
+	 xxlor		32+$in4, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in4
+	vcipher		$out2,$out2,v29
+	vcipher		$out3,$out3,v29
+	 vxor		$in4,$twk4,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk4,$tweak,$rndkey0
+	vcipher		$out4,$out4,v29
+	vcipher		$out5,$out5,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vaddubm	$tweak,$tweak,$tweak
+
+	vcipher		$out0,$out0,v30
+	vcipher		$out1,$out1,v30
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out2,$out2,v30
+	vcipher		$out3,$out3,v30
+	 xxlor		32+$in5, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in5
+	vcipher		$out4,$out4,v30
+	vcipher		$out5,$out5,v30
+	 vxor		$in5,$twk5,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk5,$tweak,$rndkey0
+
+	vcipherlast	$out0,$out0,$in0
+	 lvx_u		$in0,$x00,$inp		# load next input block
+	 vaddubm	$tweak,$tweak,$tweak
+	vcipherlast	$out1,$out1,$in1
+	 lvx_u		$in1,$x10,$inp
+	vcipherlast	$out2,$out2,$in2
+	 le?vperm	$in0,$in0,$in0,$leperm
+	 lvx_u		$in2,$x20,$inp
+	 vand		$tmp,$tmp,$eighty7
+	vcipherlast	$out3,$out3,$in3
+	 le?vperm	$in1,$in1,$in1,$leperm
+	 lvx_u		$in3,$x30,$inp
+	vcipherlast	$out4,$out4,$in4
+	 le?vperm	$in2,$in2,$in2,$leperm
+	 lvx_u		$in4,$x40,$inp
+	 xxlor		10, 32+$in0, 32+$in0
+	 xxlor		32+$in0, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in0
+	 xxlor		32+$in0, 10, 10
+	vcipherlast	$tmp,$out5,$in5		# last block might be needed
+						# in stealing mode
+	 le?vperm	$in3,$in3,$in3,$leperm
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	 le?vperm	$in4,$in4,$in4,$leperm
+	 le?vperm	$in5,$in5,$in5,$leperm
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	 vxor		$out0,$in0,$twk0
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	 vxor		$out1,$in1,$twk1
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	 vxor		$out2,$in2,$twk2
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	 vxor		$out3,$in3,$twk3
+	le?vperm	$out5,$tmp,$tmp,$leperm
+	stvx_u		$out4,$x40,$out
+	 vxor		$out4,$in4,$twk4
+	le?stvx_u	$out5,$x50,$out
+	be?stvx_u	$tmp, $x50,$out
+	 vxor		$out5,$in5,$twk5
+	addi		$out,$out,0x60
+
+	mtctr		$rounds
+	beq		Loop_xts_enc6x		# did $len-=96 borrow?
+
+	xxlor		32+$eighty7, 2, 2	# 0x010101..87
+
+	addic.		$len,$len,0x60
+	beq		Lxts_enc6x_zero
+	cmpwi		$len,0x20
+	blt		Lxts_enc6x_one
+	nop
+	beq		Lxts_enc6x_two
+	cmpwi		$len,0x40
+	blt		Lxts_enc6x_three
+	nop
+	beq		Lxts_enc6x_four
+
+Lxts_enc6x_five:
+	vxor		$out0,$in1,$twk0
+	vxor		$out1,$in2,$twk1
+	vxor		$out2,$in3,$twk2
+	vxor		$out3,$in4,$twk3
+	vxor		$out4,$in5,$twk4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk5		# unused tweak
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	vxor		$tmp,$out4,$twk5	# last block prep for stealing
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	stvx_u		$out4,$x40,$out
+	addi		$out,$out,0x50
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_four:
+	vxor		$out0,$in2,$twk0
+	vxor		$out1,$in3,$twk1
+	vxor		$out2,$in4,$twk2
+	vxor		$out3,$in5,$twk3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk4		# unused tweak
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	vxor		$tmp,$out3,$twk4	# last block prep for stealing
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	stvx_u		$out3,$x30,$out
+	addi		$out,$out,0x40
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_three:
+	vxor		$out0,$in3,$twk0
+	vxor		$out1,$in4,$twk1
+	vxor		$out2,$in5,$twk2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk3		# unused tweak
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$tmp,$out2,$twk3	# last block prep for stealing
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	stvx_u		$out2,$x20,$out
+	addi		$out,$out,0x30
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_two:
+	vxor		$out0,$in4,$twk0
+	vxor		$out1,$in5,$twk1
+	vxor		$out2,$out2,$out2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk2		# unused tweak
+	vxor		$tmp,$out1,$twk2	# last block prep for stealing
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	stvx_u		$out1,$x10,$out
+	addi		$out,$out,0x20
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_one:
+	vxor		$out0,$in5,$twk0
+	nop
+Loop_xts_enc1x:
+	vcipher		$out0,$out0,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher		$out0,$out0,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_enc1x
+
+	add		$inp,$inp,$taillen
+	cmpwi		$taillen,0
+	vcipher		$out0,$out0,v24
+
+	subi		$inp,$inp,16
+	vcipher		$out0,$out0,v25
+
+	lvsr		$inpperm,0,$taillen
+	vcipher		$out0,$out0,v26
+
+	lvx_u		$in0,0,$inp
+	vcipher		$out0,$out0,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vcipher		$out0,$out0,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vcipher		$out0,$out0,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$twk0,$twk0,v31
+
+	le?vperm	$in0,$in0,$in0,$leperm
+	vcipher		$out0,$out0,v30
+
+	vperm		$in0,$in0,$in0,$inpperm
+	vcipherlast	$out0,$out0,$twk0
+
+	vmr		$twk0,$twk1		# unused tweak
+	vxor		$tmp,$out0,$twk1	# last block prep for stealing
+	le?vperm	$out0,$out0,$out0,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	addi		$out,$out,0x10
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_zero:
+	cmpwi		$taillen,0
+	beq		Lxts_enc6x_done
+
+	add		$inp,$inp,$taillen
+	subi		$inp,$inp,16
+	lvx_u		$in0,0,$inp
+	lvsr		$inpperm,0,$taillen	# $in5 is no more
+	le?vperm	$in0,$in0,$in0,$leperm
+	vperm		$in0,$in0,$in0,$inpperm
+	vxor		$tmp,$tmp,$twk0
+Lxts_enc6x_steal:
+	vxor		$in0,$in0,$twk0
+	vxor		$out0,$out0,$out0
+	vspltisb	$out1,-1
+	vperm		$out0,$out0,$out1,$inpperm
+	vsel		$out0,$in0,$tmp,$out0	# $tmp is last block, remember?
+
+	subi		r30,$out,17
+	subi		$out,$out,16
+	mtctr		$taillen
+Loop_xts_enc6x_steal:
+	lbzu		r0,1(r30)
+	stb		r0,16(r30)
+	bdnz		Loop_xts_enc6x_steal
+
+	li		$taillen,0
+	mtctr		$rounds
+	b		Loop_xts_enc1x		# one more time...
+
+.align	4
+Lxts_enc6x_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_enc6x_ret
+
+	vxor		$tweak,$twk0,$rndkey0
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_enc6x_ret:
+	mtlr		r11
+	li		r10,`$FRAME+15`
+	li		r11,`$FRAME+31`
+	stvx		$seven,r10,$sp		# wipe copies of round keys
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+
+	mtspr		256,$vrsave
+	lvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	lvx		v21,r11,$sp
+	addi		r11,r11,32
+	lvx		v22,r10,$sp
+	addi		r10,r10,32
+	lvx		v23,r11,$sp
+	addi		r11,r11,32
+	lvx		v24,r10,$sp
+	addi		r10,r10,32
+	lvx		v25,r11,$sp
+	addi		r11,r11,32
+	lvx		v26,r10,$sp
+	addi		r10,r10,32
+	lvx		v27,r11,$sp
+	addi		r11,r11,32
+	lvx		v28,r10,$sp
+	addi		r10,r10,32
+	lvx		v29,r11,$sp
+	addi		r11,r11,32
+	lvx		v30,r10,$sp
+	lvx		v31,r11,$sp
+	$POP		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	$POP		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	$POP		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	$POP		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	$POP		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	$POP		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	addi		$sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+	blr
+	.long		0
+	.byte		0,12,0x04,1,0x80,6,6,0
+	.long		0
+
+.align	5
+_aesp8_xts_enc5x:
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	vcipher		$out4,$out4,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		_aesp8_xts_enc5x
+
+	add		$inp,$inp,$taillen
+	cmpwi		$taillen,0
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+
+	subi		$inp,$inp,16
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	vcipher		$out4,$out4,v25
+	 vxor		$twk0,$twk0,v31
+
+	vcipher		$out0,$out0,v26
+	lvsr		$inpperm,r0,$taillen	# $in5 is no more
+	vcipher		$out1,$out1,v26
+	vcipher		$out2,$out2,v26
+	vcipher		$out3,$out3,v26
+	vcipher		$out4,$out4,v26
+	 vxor		$in1,$twk1,v31
+
+	vcipher		$out0,$out0,v27
+	lvx_u		$in0,0,$inp
+	vcipher		$out1,$out1,v27
+	vcipher		$out2,$out2,v27
+	vcipher		$out3,$out3,v27
+	vcipher		$out4,$out4,v27
+	 vxor		$in2,$twk2,v31
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vcipher		$out0,$out0,v28
+	vcipher		$out1,$out1,v28
+	vcipher		$out2,$out2,v28
+	vcipher		$out3,$out3,v28
+	vcipher		$out4,$out4,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vxor		$in3,$twk3,v31
+
+	vcipher		$out0,$out0,v29
+	le?vperm	$in0,$in0,$in0,$leperm
+	vcipher		$out1,$out1,v29
+	vcipher		$out2,$out2,v29
+	vcipher		$out3,$out3,v29
+	vcipher		$out4,$out4,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$in4,$twk4,v31
+
+	vcipher		$out0,$out0,v30
+	vperm		$in0,$in0,$in0,$inpperm
+	vcipher		$out1,$out1,v30
+	vcipher		$out2,$out2,v30
+	vcipher		$out3,$out3,v30
+	vcipher		$out4,$out4,v30
+
+	vcipherlast	$out0,$out0,$twk0
+	vcipherlast	$out1,$out1,$in1
+	vcipherlast	$out2,$out2,$in2
+	vcipherlast	$out3,$out3,$in3
+	vcipherlast	$out4,$out4,$in4
+	blr
+        .long   	0
+        .byte   	0,12,0x14,0,0,0,0,0
+
+.align	5
+_aesp8_xts_decrypt6x:
+	$STU		$sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+	mflr		r11
+	li		r7,`$FRAME+8*16+15`
+	li		r3,`$FRAME+8*16+31`
+	$PUSH		r11,`$FRAME+21*16+6*$SIZE_T+$LRSAVE`($sp)
+	stvx		v20,r7,$sp		# ABI says so
+	addi		r7,r7,32
+	stvx		v21,r3,$sp
+	addi		r3,r3,32
+	stvx		v22,r7,$sp
+	addi		r7,r7,32
+	stvx		v23,r3,$sp
+	addi		r3,r3,32
+	stvx		v24,r7,$sp
+	addi		r7,r7,32
+	stvx		v25,r3,$sp
+	addi		r3,r3,32
+	stvx		v26,r7,$sp
+	addi		r7,r7,32
+	stvx		v27,r3,$sp
+	addi		r3,r3,32
+	stvx		v28,r7,$sp
+	addi		r7,r7,32
+	stvx		v29,r3,$sp
+	addi		r3,r3,32
+	stvx		v30,r7,$sp
+	stvx		v31,r3,$sp
+	li		r0,-1
+	stw		$vrsave,`$FRAME+21*16-4`($sp)	# save vrsave
+	li		$x10,0x10
+	$PUSH		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	li		$x20,0x20
+	$PUSH		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	li		$x30,0x30
+	$PUSH		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	li		$x40,0x40
+	$PUSH		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	li		$x50,0x50
+	$PUSH		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	li		$x60,0x60
+	$PUSH		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	li		$x70,0x70
+	mtspr		256,r0
+
+	xxlor		2, 32+$eighty7, 32+$eighty7
+	vsldoi		$eighty7,$tmp,$eighty7,1        # 0x010101..87
+	xxlor		1, 32+$eighty7, 32+$eighty7
+
+	# Load XOR Lconsts.
+	mr		$x70, r6
+	bl		Lconsts
+	lxvw4x		0, $x40, r6		# load XOR contents
+	mr		r6, $x70
+	li		$x70,0x70
+
+	subi		$rounds,$rounds,3	# -4 in total
+
+	lvx		$rndkey0,$x00,$key1	# load key schedule
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	lvx		v31,$x00,$key1
+	?vperm		$rndkey0,$rndkey0,v30,$keyperm
+	addi		$key_,$sp,$FRAME+15
+	mtctr		$rounds
+
+Load_xts_dec_key:
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	stvx		v24,$x00,$key_		# off-load round[1]
+	?vperm		v25,v31,v30,$keyperm
+	lvx		v31,$x00,$key1
+	stvx		v25,$x10,$key_		# off-load round[2]
+	addi		$key_,$key_,0x20
+	bdnz		Load_xts_dec_key
+
+	lvx		v26,$x10,$key1
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v27,$x20,$key1
+	stvx		v24,$x00,$key_		# off-load round[3]
+	?vperm		v25,v31,v26,$keyperm
+	lvx		v28,$x30,$key1
+	stvx		v25,$x10,$key_		# off-load round[4]
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	?vperm		v26,v26,v27,$keyperm
+	lvx		v29,$x40,$key1
+	?vperm		v27,v27,v28,$keyperm
+	lvx		v30,$x50,$key1
+	?vperm		v28,v28,v29,$keyperm
+	lvx		v31,$x60,$key1
+	?vperm		v29,v29,v30,$keyperm
+	lvx		$twk5,$x70,$key1	# borrow $twk5
+	?vperm		v30,v30,v31,$keyperm
+	lvx		v24,$x00,$key_		# pre-load round[1]
+	?vperm		v31,v31,$twk5,$keyperm
+	lvx		v25,$x10,$key_		# pre-load round[2]
+
+	 vperm		$in0,$inout,$inptail,$inpperm
+	 subi		$inp,$inp,31		# undo "caller"
+	vxor		$twk0,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out0,$in0,$twk0
+	xxlor		32+$in1, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in1
+
+	 lvx_u		$in1,$x10,$inp
+	vxor		$twk1,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in1,$in1,$in1,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out1,$in1,$twk1
+	xxlor		32+$in2, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in2
+
+	 lvx_u		$in2,$x20,$inp
+	 andi.		$taillen,$len,15
+	vxor		$twk2,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in2,$in2,$in2,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out2,$in2,$twk2
+	xxlor		32+$in3, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in3
+
+	 lvx_u		$in3,$x30,$inp
+	 sub		$len,$len,$taillen
+	vxor		$twk3,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in3,$in3,$in3,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out3,$in3,$twk3
+	xxlor		32+$in4, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in4
+
+	 lvx_u		$in4,$x40,$inp
+	 subi		$len,$len,0x60
+	vxor		$twk4,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in4,$in4,$in4,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out4,$in4,$twk4
+	xxlor		32+$in5, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in5
+
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	vxor		$twk5,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	 le?vperm	$in5,$in5,$in5,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out5,$in5,$twk5
+	xxlor		32+$in0, 0, 0
+	vpermxor	$tweak, $tweak, $tmp, $in0
+
+	vxor		v31,v31,$rndkey0
+	mtctr		$rounds
+	b		Loop_xts_dec6x
+
+.align	5
+Loop_xts_dec6x:
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_dec6x
+
+	xxlor		32+$eighty7, 1, 1	# 0x010101..87
+
+	subic		$len,$len,96		# $len-=96
+	 vxor		$in0,$twk0,v31		# xor with last round key
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk0,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+
+	subfe.		r0,r0,r0		# borrow?-1:0
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	 xxlor		32+$in1, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in1
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	 vxor		$in1,$twk1,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk1,$tweak,$rndkey0
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+
+	and		r0,r0,$len
+	 vaddubm	$tweak,$tweak,$tweak
+	vncipher	$out0,$out0,v26
+	vncipher	$out1,$out1,v26
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out2,$out2,v26
+	vncipher	$out3,$out3,v26
+	 xxlor		32+$in2, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in2
+	vncipher	$out4,$out4,v26
+	vncipher	$out5,$out5,v26
+
+	add		$inp,$inp,r0		# $inp is adjusted in such
+						# way that at exit from the
+						# loop inX-in5 are loaded
+						# with last "words"
+	 vxor		$in2,$twk2,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk2,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vncipher	$out0,$out0,v27
+	vncipher	$out1,$out1,v27
+	vncipher	$out2,$out2,v27
+	vncipher	$out3,$out3,v27
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out4,$out4,v27
+	vncipher	$out5,$out5,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	 xxlor		32+$in3, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in3
+	vncipher	$out0,$out0,v28
+	vncipher	$out1,$out1,v28
+	 vxor		$in3,$twk3,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk3,$tweak,$rndkey0
+	vncipher	$out2,$out2,v28
+	vncipher	$out3,$out3,v28
+	 vaddubm	$tweak,$tweak,$tweak
+	vncipher	$out4,$out4,v28
+	vncipher	$out5,$out5,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vand		$tmp,$tmp,$eighty7
+
+	vncipher	$out0,$out0,v29
+	vncipher	$out1,$out1,v29
+	 xxlor		32+$in4, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in4
+	vncipher	$out2,$out2,v29
+	vncipher	$out3,$out3,v29
+	 vxor		$in4,$twk4,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk4,$tweak,$rndkey0
+	vncipher	$out4,$out4,v29
+	vncipher	$out5,$out5,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vaddubm	$tweak,$tweak,$tweak
+
+	vncipher	$out0,$out0,v30
+	vncipher	$out1,$out1,v30
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out2,$out2,v30
+	vncipher	$out3,$out3,v30
+	 xxlor		32+$in5, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in5
+	vncipher	$out4,$out4,v30
+	vncipher	$out5,$out5,v30
+	 vxor		$in5,$twk5,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk5,$tweak,$rndkey0
+
+	vncipherlast	$out0,$out0,$in0
+	 lvx_u		$in0,$x00,$inp		# load next input block
+	 vaddubm	$tweak,$tweak,$tweak
+	vncipherlast	$out1,$out1,$in1
+	 lvx_u		$in1,$x10,$inp
+	vncipherlast	$out2,$out2,$in2
+	 le?vperm	$in0,$in0,$in0,$leperm
+	 lvx_u		$in2,$x20,$inp
+	 vand		$tmp,$tmp,$eighty7
+	vncipherlast	$out3,$out3,$in3
+	 le?vperm	$in1,$in1,$in1,$leperm
+	 lvx_u		$in3,$x30,$inp
+	vncipherlast	$out4,$out4,$in4
+	 le?vperm	$in2,$in2,$in2,$leperm
+	 lvx_u		$in4,$x40,$inp
+	 xxlor		10, 32+$in0, 32+$in0
+	 xxlor		32+$in0, 0, 0
+	 vpermxor	$tweak, $tweak, $tmp, $in0
+	 xxlor		32+$in0, 10, 10
+	vncipherlast	$out5,$out5,$in5
+	 le?vperm	$in3,$in3,$in3,$leperm
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	 le?vperm	$in4,$in4,$in4,$leperm
+	 le?vperm	$in5,$in5,$in5,$leperm
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	 vxor		$out0,$in0,$twk0
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	 vxor		$out1,$in1,$twk1
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	 vxor		$out2,$in2,$twk2
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	 vxor		$out3,$in3,$twk3
+	le?vperm	$out5,$out5,$out5,$leperm
+	stvx_u		$out4,$x40,$out
+	 vxor		$out4,$in4,$twk4
+	stvx_u		$out5,$x50,$out
+	 vxor		$out5,$in5,$twk5
+	addi		$out,$out,0x60
+
+	mtctr		$rounds
+	beq		Loop_xts_dec6x		# did $len-=96 borrow?
+
+	xxlor		32+$eighty7, 2, 2	# 0x010101..87
+
+	addic.		$len,$len,0x60
+	beq		Lxts_dec6x_zero
+	cmpwi		$len,0x20
+	blt		Lxts_dec6x_one
+	nop
+	beq		Lxts_dec6x_two
+	cmpwi		$len,0x40
+	blt		Lxts_dec6x_three
+	nop
+	beq		Lxts_dec6x_four
+
+Lxts_dec6x_five:
+	vxor		$out0,$in1,$twk0
+	vxor		$out1,$in2,$twk1
+	vxor		$out2,$in3,$twk2
+	vxor		$out3,$in4,$twk3
+	vxor		$out4,$in5,$twk4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk5		# unused tweak
+	vxor		$twk1,$tweak,$rndkey0
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk1
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	stvx_u		$out4,$x40,$out
+	addi		$out,$out,0x50
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_four:
+	vxor		$out0,$in2,$twk0
+	vxor		$out1,$in3,$twk1
+	vxor		$out2,$in4,$twk2
+	vxor		$out3,$in5,$twk3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk4		# unused tweak
+	vmr		$twk1,$twk5
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk5
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	stvx_u		$out3,$x30,$out
+	addi		$out,$out,0x40
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_three:
+	vxor		$out0,$in3,$twk0
+	vxor		$out1,$in4,$twk1
+	vxor		$out2,$in5,$twk2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk3		# unused tweak
+	vmr		$twk1,$twk4
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk4
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	stvx_u		$out2,$x20,$out
+	addi		$out,$out,0x30
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_two:
+	vxor		$out0,$in4,$twk0
+	vxor		$out1,$in5,$twk1
+	vxor		$out2,$out2,$out2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk2		# unused tweak
+	vmr		$twk1,$twk3
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk3
+	stvx_u		$out1,$x10,$out
+	addi		$out,$out,0x20
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_one:
+	vxor		$out0,$in5,$twk0
+	nop
+Loop_xts_dec1x:
+	vncipher	$out0,$out0,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_dec1x
+
+	subi		r0,$taillen,1
+	vncipher	$out0,$out0,v24
+
+	andi.		r0,r0,16
+	cmpwi		$taillen,0
+	vncipher	$out0,$out0,v25
+
+	sub		$inp,$inp,r0
+	vncipher	$out0,$out0,v26
+
+	lvx_u		$in0,0,$inp
+	vncipher	$out0,$out0,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vncipher	$out0,$out0,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$twk0,$twk0,v31
+
+	le?vperm	$in0,$in0,$in0,$leperm
+	vncipher	$out0,$out0,v30
+
+	mtctr		$rounds
+	vncipherlast	$out0,$out0,$twk0
+
+	vmr		$twk0,$twk1		# unused tweak
+	vmr		$twk1,$twk2
+	le?vperm	$out0,$out0,$out0,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	addi		$out,$out,0x10
+	vxor		$out0,$in0,$twk2
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_zero:
+	cmpwi		$taillen,0
+	beq		Lxts_dec6x_done
+
+	lvx_u		$in0,0,$inp
+	le?vperm	$in0,$in0,$in0,$leperm
+	vxor		$out0,$in0,$twk1
+Lxts_dec6x_steal:
+	vncipher	$out0,$out0,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Lxts_dec6x_steal
+
+	add		$inp,$inp,$taillen
+	vncipher	$out0,$out0,v24
+
+	cmpwi		$taillen,0
+	vncipher	$out0,$out0,v25
+
+	lvx_u		$in0,0,$inp
+	vncipher	$out0,$out0,v26
+
+	lvsr		$inpperm,0,$taillen	# $in5 is no more
+	vncipher	$out0,$out0,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vncipher	$out0,$out0,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$twk1,$twk1,v31
+
+	le?vperm	$in0,$in0,$in0,$leperm
+	vncipher	$out0,$out0,v30
+
+	vperm		$in0,$in0,$in0,$inpperm
+	vncipherlast	$tmp,$out0,$twk1
+
+	le?vperm	$out0,$tmp,$tmp,$leperm
+	le?stvx_u	$out0,0,$out
+	be?stvx_u	$tmp,0,$out
+
+	vxor		$out0,$out0,$out0
+	vspltisb	$out1,-1
+	vperm		$out0,$out0,$out1,$inpperm
+	vsel		$out0,$in0,$tmp,$out0
+	vxor		$out0,$out0,$twk0
+
+	subi		r30,$out,1
+	mtctr		$taillen
+Loop_xts_dec6x_steal:
+	lbzu		r0,1(r30)
+	stb		r0,16(r30)
+	bdnz		Loop_xts_dec6x_steal
+
+	li		$taillen,0
+	mtctr		$rounds
+	b		Loop_xts_dec1x		# one more time...
+
+.align	4
+Lxts_dec6x_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_dec6x_ret
+
+	vxor		$tweak,$twk0,$rndkey0
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_dec6x_ret:
+	mtlr		r11
+	li		r10,`$FRAME+15`
+	li		r11,`$FRAME+31`
+	stvx		$seven,r10,$sp		# wipe copies of round keys
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+
+	mtspr		256,$vrsave
+	lvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	lvx		v21,r11,$sp
+	addi		r11,r11,32
+	lvx		v22,r10,$sp
+	addi		r10,r10,32
+	lvx		v23,r11,$sp
+	addi		r11,r11,32
+	lvx		v24,r10,$sp
+	addi		r10,r10,32
+	lvx		v25,r11,$sp
+	addi		r11,r11,32
+	lvx		v26,r10,$sp
+	addi		r10,r10,32
+	lvx		v27,r11,$sp
+	addi		r11,r11,32
+	lvx		v28,r10,$sp
+	addi		r10,r10,32
+	lvx		v29,r11,$sp
+	addi		r11,r11,32
+	lvx		v30,r10,$sp
+	lvx		v31,r11,$sp
+	$POP		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	$POP		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	$POP		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	$POP		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	$POP		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	$POP		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	addi		$sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+	blr
+	.long		0
+	.byte		0,12,0x04,1,0x80,6,6,0
+	.long		0
+
+.align	5
+_aesp8_xts_dec5x:
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		_aesp8_xts_dec5x
+
+	subi		r0,$taillen,1
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+
+	andi.		r0,r0,16
+	cmpwi		$taillen,0
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	 vxor		$twk0,$twk0,v31
+
+	sub		$inp,$inp,r0
+	vncipher	$out0,$out0,v26
+	vncipher	$out1,$out1,v26
+	vncipher	$out2,$out2,v26
+	vncipher	$out3,$out3,v26
+	vncipher	$out4,$out4,v26
+	 vxor		$in1,$twk1,v31
+
+	vncipher	$out0,$out0,v27
+	lvx_u		$in0,0,$inp
+	vncipher	$out1,$out1,v27
+	vncipher	$out2,$out2,v27
+	vncipher	$out3,$out3,v27
+	vncipher	$out4,$out4,v27
+	 vxor		$in2,$twk2,v31
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	vncipher	$out1,$out1,v28
+	vncipher	$out2,$out2,v28
+	vncipher	$out3,$out3,v28
+	vncipher	$out4,$out4,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vxor		$in3,$twk3,v31
+
+	vncipher	$out0,$out0,v29
+	le?vperm	$in0,$in0,$in0,$leperm
+	vncipher	$out1,$out1,v29
+	vncipher	$out2,$out2,v29
+	vncipher	$out3,$out3,v29
+	vncipher	$out4,$out4,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$in4,$twk4,v31
+
+	vncipher	$out0,$out0,v30
+	vncipher	$out1,$out1,v30
+	vncipher	$out2,$out2,v30
+	vncipher	$out3,$out3,v30
+	vncipher	$out4,$out4,v30
+
+	vncipherlast	$out0,$out0,$twk0
+	vncipherlast	$out1,$out1,$in1
+	vncipherlast	$out2,$out2,$in2
+	vncipherlast	$out3,$out3,$in3
+	vncipherlast	$out4,$out4,$in4
+	mtctr		$rounds
+	blr
+        .long   	0
+        .byte   	0,12,0x14,0,0,0,0,0
+___
+}}	}}}
 
 my $consts=1;
 foreach(split("\n",$code)) {
diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c
deleted file mode 100644
index c61a874a3a5c..000000000000
--- a/arch/powerpc/crypto/crc-vpmsum_test.c
+++ /dev/null
@@ -1,133 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * CRC vpmsum tester
- * Copyright 2017 Daniel Axtens, IBM Corporation.
- */
-
-#include <linux/crc-t10dif.h>
-#include <linux/crc32.h>
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/random.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/cpufeature.h>
-#include <asm/switch_to.h>
-
-static unsigned long iterations = 10000;
-
-#define MAX_CRC_LENGTH 65535
-
-
-static int __init crc_test_init(void)
-{
-	u16 crc16 = 0, verify16 = 0;
-	__le32 verify32le = 0;
-	unsigned char *data;
-	u32 verify32 = 0;
-	unsigned long i;
-	__le32 crc32;
-	int ret;
-
-	struct crypto_shash *crct10dif_tfm;
-	struct crypto_shash *crc32c_tfm;
-
-	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
-		return -ENODEV;
-
-	data = kmalloc(MAX_CRC_LENGTH, GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
-
-	if (IS_ERR(crct10dif_tfm)) {
-		pr_err("Error allocating crc-t10dif\n");
-		goto free_buf;
-	}
-
-	crc32c_tfm = crypto_alloc_shash("crc32c", 0, 0);
-
-	if (IS_ERR(crc32c_tfm)) {
-		pr_err("Error allocating crc32c\n");
-		goto free_16;
-	}
-
-	do {
-		SHASH_DESC_ON_STACK(crct10dif_shash, crct10dif_tfm);
-		SHASH_DESC_ON_STACK(crc32c_shash, crc32c_tfm);
-
-		crct10dif_shash->tfm = crct10dif_tfm;
-		ret = crypto_shash_init(crct10dif_shash);
-
-		if (ret) {
-			pr_err("Error initing crc-t10dif\n");
-			goto free_32;
-		}
-
-
-		crc32c_shash->tfm = crc32c_tfm;
-		ret = crypto_shash_init(crc32c_shash);
-
-		if (ret) {
-			pr_err("Error initing crc32c\n");
-			goto free_32;
-		}
-
-		pr_info("crc-vpmsum_test begins, %lu iterations\n", iterations);
-		for (i=0; i<iterations; i++) {
-			size_t offset = get_random_u32_below(16);
-			size_t len = get_random_u32_below(MAX_CRC_LENGTH);
-
-			if (len <= offset)
-				continue;
-			get_random_bytes(data, len);
-			len -= offset;
-
-			crypto_shash_update(crct10dif_shash, data+offset, len);
-			crypto_shash_final(crct10dif_shash, (u8 *)(&crc16));
-			verify16 = crc_t10dif_generic(verify16, data+offset, len);
-
-
-			if (crc16 != verify16) {
-				pr_err("FAILURE in CRC16: got 0x%04x expected 0x%04x (len %lu)\n",
-				       crc16, verify16, len);
-				break;
-			}
-
-			crypto_shash_update(crc32c_shash, data+offset, len);
-			crypto_shash_final(crc32c_shash, (u8 *)(&crc32));
-			verify32 = le32_to_cpu(verify32le);
-		        verify32le = ~cpu_to_le32(__crc32c_le(~verify32, data+offset, len));
-			if (crc32 != verify32le) {
-				pr_err("FAILURE in CRC32: got 0x%08x expected 0x%08x (len %lu)\n",
-				       crc32, verify32, len);
-				break;
-			}
-		cond_resched();
-		}
-		pr_info("crc-vpmsum_test done, completed %lu iterations\n", i);
-	} while (0);
-
-free_32:
-	crypto_free_shash(crc32c_tfm);
-
-free_16:
-	crypto_free_shash(crct10dif_tfm);
-
-free_buf:
-	kfree(data);
-
-	return 0;
-}
-
-static void __exit crc_test_exit(void) {}
-
-module_init(crc_test_init);
-module_exit(crc_test_exit);
-module_param(iterations, long, 0400);
-
-MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
-MODULE_DESCRIPTION("Vector polynomial multiply-sum CRC tester");
-MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/crypto/crc32-vpmsum_core.S
deleted file mode 100644
index b0f87f595b26..000000000000
--- a/arch/powerpc/crypto/crc32-vpmsum_core.S
+++ /dev/null
@@ -1,746 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Core of the accelerated CRC algorithm.
- * In your file, define the constants and CRC_FUNCTION_NAME
- * Then include this file.
- *
- * Calculate the checksum of data that is 16 byte aligned and a multiple of
- * 16 bytes.
- *
- * The first step is to reduce it to 1024 bits. We do this in 8 parallel
- * chunks in order to mask the latency of the vpmsum instructions. If we
- * have more than 32 kB of data to checksum we repeat this step multiple
- * times, passing in the previous 1024 bits.
- *
- * The next step is to reduce the 1024 bits to 64 bits. This step adds
- * 32 bits of 0s to the end - this matches what a CRC does. We just
- * calculate constants that land the data in this 32 bits.
- *
- * We then use fixed point Barrett reduction to compute a mod n over GF(2)
- * for n = CRC using POWER8 instructions. We use x = 32.
- *
- * https://en.wikipedia.org/wiki/Barrett_reduction
- *
- * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
-*/
-
-#include <asm/ppc_asm.h>
-#include <asm/ppc-opcode.h>
-
-#define MAX_SIZE	32768
-
-	.text
-
-#if defined(__BIG_ENDIAN__) && defined(REFLECT)
-#define BYTESWAP_DATA
-#elif defined(__LITTLE_ENDIAN__) && !defined(REFLECT)
-#define BYTESWAP_DATA
-#else
-#undef BYTESWAP_DATA
-#endif
-
-#define off16		r25
-#define off32		r26
-#define off48		r27
-#define off64		r28
-#define off80		r29
-#define off96		r30
-#define off112		r31
-
-#define const1		v24
-#define const2		v25
-
-#define byteswap	v26
-#define	mask_32bit	v27
-#define	mask_64bit	v28
-#define zeroes		v29
-
-#ifdef BYTESWAP_DATA
-#define VPERM(A, B, C, D) vperm	A, B, C, D
-#else
-#define VPERM(A, B, C, D)
-#endif
-
-/* unsigned int CRC_FUNCTION_NAME(unsigned int crc, void *p, unsigned long len) */
-FUNC_START(CRC_FUNCTION_NAME)
-	std	r31,-8(r1)
-	std	r30,-16(r1)
-	std	r29,-24(r1)
-	std	r28,-32(r1)
-	std	r27,-40(r1)
-	std	r26,-48(r1)
-	std	r25,-56(r1)
-
-	li	off16,16
-	li	off32,32
-	li	off48,48
-	li	off64,64
-	li	off80,80
-	li	off96,96
-	li	off112,112
-	li	r0,0
-
-	/* Enough room for saving 10 non volatile VMX registers */
-	subi	r6,r1,56+10*16
-	subi	r7,r1,56+2*16
-
-	stvx	v20,0,r6
-	stvx	v21,off16,r6
-	stvx	v22,off32,r6
-	stvx	v23,off48,r6
-	stvx	v24,off64,r6
-	stvx	v25,off80,r6
-	stvx	v26,off96,r6
-	stvx	v27,off112,r6
-	stvx	v28,0,r7
-	stvx	v29,off16,r7
-
-	mr	r10,r3
-
-	vxor	zeroes,zeroes,zeroes
-	vspltisw v0,-1
-
-	vsldoi	mask_32bit,zeroes,v0,4
-	vsldoi	mask_64bit,zeroes,v0,8
-
-	/* Get the initial value into v8 */
-	vxor	v8,v8,v8
-	MTVRD(v8, R3)
-#ifdef REFLECT
-	vsldoi	v8,zeroes,v8,8	/* shift into bottom 32 bits */
-#else
-	vsldoi	v8,v8,zeroes,4	/* shift into top 32 bits */
-#endif
-
-#ifdef BYTESWAP_DATA
-	LOAD_REG_ADDR(r3, .byteswap_constant)
-	lvx	byteswap,0,r3
-	addi	r3,r3,16
-#endif
-
-	cmpdi	r5,256
-	blt	.Lshort
-
-	rldicr	r6,r5,0,56
-
-	/* Checksum in blocks of MAX_SIZE */
-1:	lis	r7,MAX_SIZE@h
-	ori	r7,r7,MAX_SIZE@l
-	mr	r9,r7
-	cmpd	r6,r7
-	bgt	2f
-	mr	r7,r6
-2:	subf	r6,r7,r6
-
-	/* our main loop does 128 bytes at a time */
-	srdi	r7,r7,7
-
-	/*
-	 * Work out the offset into the constants table to start at. Each
-	 * constant is 16 bytes, and it is used against 128 bytes of input
-	 * data - 128 / 16 = 8
-	 */
-	sldi	r8,r7,4
-	srdi	r9,r9,3
-	subf	r8,r8,r9
-
-	/* We reduce our final 128 bytes in a separate step */
-	addi	r7,r7,-1
-	mtctr	r7
-
-	LOAD_REG_ADDR(r3, .constants)
-
-	/* Find the start of our constants */
-	add	r3,r3,r8
-
-	/* zero v0-v7 which will contain our checksums */
-	vxor	v0,v0,v0
-	vxor	v1,v1,v1
-	vxor	v2,v2,v2
-	vxor	v3,v3,v3
-	vxor	v4,v4,v4
-	vxor	v5,v5,v5
-	vxor	v6,v6,v6
-	vxor	v7,v7,v7
-
-	lvx	const1,0,r3
-
-	/*
-	 * If we are looping back to consume more data we use the values
-	 * already in v16-v23.
-	 */
-	cmpdi	r0,1
-	beq	2f
-
-	/* First warm up pass */
-	lvx	v16,0,r4
-	lvx	v17,off16,r4
-	VPERM(v16,v16,v16,byteswap)
-	VPERM(v17,v17,v17,byteswap)
-	lvx	v18,off32,r4
-	lvx	v19,off48,r4
-	VPERM(v18,v18,v18,byteswap)
-	VPERM(v19,v19,v19,byteswap)
-	lvx	v20,off64,r4
-	lvx	v21,off80,r4
-	VPERM(v20,v20,v20,byteswap)
-	VPERM(v21,v21,v21,byteswap)
-	lvx	v22,off96,r4
-	lvx	v23,off112,r4
-	VPERM(v22,v22,v22,byteswap)
-	VPERM(v23,v23,v23,byteswap)
-	addi	r4,r4,8*16
-
-	/* xor in initial value */
-	vxor	v16,v16,v8
-
-2:	bdz	.Lfirst_warm_up_done
-
-	addi	r3,r3,16
-	lvx	const2,0,r3
-
-	/* Second warm up pass */
-	VPMSUMD(v8,v16,const1)
-	lvx	v16,0,r4
-	VPERM(v16,v16,v16,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v9,v17,const1)
-	lvx	v17,off16,r4
-	VPERM(v17,v17,v17,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v10,v18,const1)
-	lvx	v18,off32,r4
-	VPERM(v18,v18,v18,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v11,v19,const1)
-	lvx	v19,off48,r4
-	VPERM(v19,v19,v19,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v12,v20,const1)
-	lvx	v20,off64,r4
-	VPERM(v20,v20,v20,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v13,v21,const1)
-	lvx	v21,off80,r4
-	VPERM(v21,v21,v21,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v14,v22,const1)
-	lvx	v22,off96,r4
-	VPERM(v22,v22,v22,byteswap)
-	ori	r2,r2,0
-
-	VPMSUMD(v15,v23,const1)
-	lvx	v23,off112,r4
-	VPERM(v23,v23,v23,byteswap)
-
-	addi	r4,r4,8*16
-
-	bdz	.Lfirst_cool_down
-
-	/*
-	 * main loop. We modulo schedule it such that it takes three iterations
-	 * to complete - first iteration load, second iteration vpmsum, third
-	 * iteration xor.
-	 */
-	.balign	16
-4:	lvx	const1,0,r3
-	addi	r3,r3,16
-	ori	r2,r2,0
-
-	vxor	v0,v0,v8
-	VPMSUMD(v8,v16,const2)
-	lvx	v16,0,r4
-	VPERM(v16,v16,v16,byteswap)
-	ori	r2,r2,0
-
-	vxor	v1,v1,v9
-	VPMSUMD(v9,v17,const2)
-	lvx	v17,off16,r4
-	VPERM(v17,v17,v17,byteswap)
-	ori	r2,r2,0
-
-	vxor	v2,v2,v10
-	VPMSUMD(v10,v18,const2)
-	lvx	v18,off32,r4
-	VPERM(v18,v18,v18,byteswap)
-	ori	r2,r2,0
-
-	vxor	v3,v3,v11
-	VPMSUMD(v11,v19,const2)
-	lvx	v19,off48,r4
-	VPERM(v19,v19,v19,byteswap)
-	lvx	const2,0,r3
-	ori	r2,r2,0
-
-	vxor	v4,v4,v12
-	VPMSUMD(v12,v20,const1)
-	lvx	v20,off64,r4
-	VPERM(v20,v20,v20,byteswap)
-	ori	r2,r2,0
-
-	vxor	v5,v5,v13
-	VPMSUMD(v13,v21,const1)
-	lvx	v21,off80,r4
-	VPERM(v21,v21,v21,byteswap)
-	ori	r2,r2,0
-
-	vxor	v6,v6,v14
-	VPMSUMD(v14,v22,const1)
-	lvx	v22,off96,r4
-	VPERM(v22,v22,v22,byteswap)
-	ori	r2,r2,0
-
-	vxor	v7,v7,v15
-	VPMSUMD(v15,v23,const1)
-	lvx	v23,off112,r4
-	VPERM(v23,v23,v23,byteswap)
-
-	addi	r4,r4,8*16
-
-	bdnz	4b
-
-.Lfirst_cool_down:
-	/* First cool down pass */
-	lvx	const1,0,r3
-	addi	r3,r3,16
-
-	vxor	v0,v0,v8
-	VPMSUMD(v8,v16,const1)
-	ori	r2,r2,0
-
-	vxor	v1,v1,v9
-	VPMSUMD(v9,v17,const1)
-	ori	r2,r2,0
-
-	vxor	v2,v2,v10
-	VPMSUMD(v10,v18,const1)
-	ori	r2,r2,0
-
-	vxor	v3,v3,v11
-	VPMSUMD(v11,v19,const1)
-	ori	r2,r2,0
-
-	vxor	v4,v4,v12
-	VPMSUMD(v12,v20,const1)
-	ori	r2,r2,0
-
-	vxor	v5,v5,v13
-	VPMSUMD(v13,v21,const1)
-	ori	r2,r2,0
-
-	vxor	v6,v6,v14
-	VPMSUMD(v14,v22,const1)
-	ori	r2,r2,0
-
-	vxor	v7,v7,v15
-	VPMSUMD(v15,v23,const1)
-	ori	r2,r2,0
-
-.Lsecond_cool_down:
-	/* Second cool down pass */
-	vxor	v0,v0,v8
-	vxor	v1,v1,v9
-	vxor	v2,v2,v10
-	vxor	v3,v3,v11
-	vxor	v4,v4,v12
-	vxor	v5,v5,v13
-	vxor	v6,v6,v14
-	vxor	v7,v7,v15
-
-#ifdef REFLECT
-	/*
-	 * vpmsumd produces a 96 bit result in the least significant bits
-	 * of the register. Since we are bit reflected we have to shift it
-	 * left 32 bits so it occupies the least significant bits in the
-	 * bit reflected domain.
-	 */
-	vsldoi	v0,v0,zeroes,4
-	vsldoi	v1,v1,zeroes,4
-	vsldoi	v2,v2,zeroes,4
-	vsldoi	v3,v3,zeroes,4
-	vsldoi	v4,v4,zeroes,4
-	vsldoi	v5,v5,zeroes,4
-	vsldoi	v6,v6,zeroes,4
-	vsldoi	v7,v7,zeroes,4
-#endif
-
-	/* xor with last 1024 bits */
-	lvx	v8,0,r4
-	lvx	v9,off16,r4
-	VPERM(v8,v8,v8,byteswap)
-	VPERM(v9,v9,v9,byteswap)
-	lvx	v10,off32,r4
-	lvx	v11,off48,r4
-	VPERM(v10,v10,v10,byteswap)
-	VPERM(v11,v11,v11,byteswap)
-	lvx	v12,off64,r4
-	lvx	v13,off80,r4
-	VPERM(v12,v12,v12,byteswap)
-	VPERM(v13,v13,v13,byteswap)
-	lvx	v14,off96,r4
-	lvx	v15,off112,r4
-	VPERM(v14,v14,v14,byteswap)
-	VPERM(v15,v15,v15,byteswap)
-
-	addi	r4,r4,8*16
-
-	vxor	v16,v0,v8
-	vxor	v17,v1,v9
-	vxor	v18,v2,v10
-	vxor	v19,v3,v11
-	vxor	v20,v4,v12
-	vxor	v21,v5,v13
-	vxor	v22,v6,v14
-	vxor	v23,v7,v15
-
-	li	r0,1
-	cmpdi	r6,0
-	addi	r6,r6,128
-	bne	1b
-
-	/* Work out how many bytes we have left */
-	andi.	r5,r5,127
-
-	/* Calculate where in the constant table we need to start */
-	subfic	r6,r5,128
-	add	r3,r3,r6
-
-	/* How many 16 byte chunks are in the tail */
-	srdi	r7,r5,4
-	mtctr	r7
-
-	/*
-	 * Reduce the previously calculated 1024 bits to 64 bits, shifting
-	 * 32 bits to include the trailing 32 bits of zeros
-	 */
-	lvx	v0,0,r3
-	lvx	v1,off16,r3
-	lvx	v2,off32,r3
-	lvx	v3,off48,r3
-	lvx	v4,off64,r3
-	lvx	v5,off80,r3
-	lvx	v6,off96,r3
-	lvx	v7,off112,r3
-	addi	r3,r3,8*16
-
-	VPMSUMW(v0,v16,v0)
-	VPMSUMW(v1,v17,v1)
-	VPMSUMW(v2,v18,v2)
-	VPMSUMW(v3,v19,v3)
-	VPMSUMW(v4,v20,v4)
-	VPMSUMW(v5,v21,v5)
-	VPMSUMW(v6,v22,v6)
-	VPMSUMW(v7,v23,v7)
-
-	/* Now reduce the tail (0 - 112 bytes) */
-	cmpdi	r7,0
-	beq	1f
-
-	lvx	v16,0,r4
-	lvx	v17,0,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off16,r4
-	lvx	v17,off16,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off32,r4
-	lvx	v17,off32,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off48,r4
-	lvx	v17,off48,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off64,r4
-	lvx	v17,off64,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off80,r4
-	lvx	v17,off80,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-	bdz	1f
-
-	lvx	v16,off96,r4
-	lvx	v17,off96,r3
-	VPERM(v16,v16,v16,byteswap)
-	VPMSUMW(v16,v16,v17)
-	vxor	v0,v0,v16
-
-	/* Now xor all the parallel chunks together */
-1:	vxor	v0,v0,v1
-	vxor	v2,v2,v3
-	vxor	v4,v4,v5
-	vxor	v6,v6,v7
-
-	vxor	v0,v0,v2
-	vxor	v4,v4,v6
-
-	vxor	v0,v0,v4
-
-.Lbarrett_reduction:
-	/* Barrett constants */
-	LOAD_REG_ADDR(r3, .barrett_constants)
-
-	lvx	const1,0,r3
-	lvx	const2,off16,r3
-
-	vsldoi	v1,v0,v0,8
-	vxor	v0,v0,v1		/* xor two 64 bit results together */
-
-#ifdef REFLECT
-	/* shift left one bit */
-	vspltisb v1,1
-	vsl	v0,v0,v1
-#endif
-
-	vand	v0,v0,mask_64bit
-#ifndef REFLECT
-	/*
-	 * Now for the Barrett reduction algorithm. The idea is to calculate q,
-	 * the multiple of our polynomial that we need to subtract. By
-	 * doing the computation 2x bits higher (ie 64 bits) and shifting the
-	 * result back down 2x bits, we round down to the nearest multiple.
-	 */
-	VPMSUMD(v1,v0,const1)	/* ma */
-	vsldoi	v1,zeroes,v1,8	/* q = floor(ma/(2^64)) */
-	VPMSUMD(v1,v1,const2)	/* qn */
-	vxor	v0,v0,v1	/* a - qn, subtraction is xor in GF(2) */
-
-	/*
-	 * Get the result into r3. We need to shift it left 8 bytes:
-	 * V0 [ 0 1 2 X ]
-	 * V0 [ 0 X 2 3 ]
-	 */
-	vsldoi	v0,v0,zeroes,8	/* shift result into top 64 bits */
-#else
-	/*
-	 * The reflected version of Barrett reduction. Instead of bit
-	 * reflecting our data (which is expensive to do), we bit reflect our
-	 * constants and our algorithm, which means the intermediate data in
-	 * our vector registers goes from 0-63 instead of 63-0. We can reflect
-	 * the algorithm because we don't carry in mod 2 arithmetic.
-	 */
-	vand	v1,v0,mask_32bit	/* bottom 32 bits of a */
-	VPMSUMD(v1,v1,const1)		/* ma */
-	vand	v1,v1,mask_32bit	/* bottom 32bits of ma */
-	VPMSUMD(v1,v1,const2)		/* qn */
-	vxor	v0,v0,v1		/* a - qn, subtraction is xor in GF(2) */
-
-	/*
-	 * Since we are bit reflected, the result (ie the low 32 bits) is in
-	 * the high 32 bits. We just need to shift it left 4 bytes
-	 * V0 [ 0 1 X 3 ]
-	 * V0 [ 0 X 2 3 ]
-	 */
-	vsldoi	v0,v0,zeroes,4		/* shift result into top 64 bits of */
-#endif
-
-	/* Get it into r3 */
-	MFVRD(R3, v0)
-
-.Lout:
-	subi	r6,r1,56+10*16
-	subi	r7,r1,56+2*16
-
-	lvx	v20,0,r6
-	lvx	v21,off16,r6
-	lvx	v22,off32,r6
-	lvx	v23,off48,r6
-	lvx	v24,off64,r6
-	lvx	v25,off80,r6
-	lvx	v26,off96,r6
-	lvx	v27,off112,r6
-	lvx	v28,0,r7
-	lvx	v29,off16,r7
-
-	ld	r31,-8(r1)
-	ld	r30,-16(r1)
-	ld	r29,-24(r1)
-	ld	r28,-32(r1)
-	ld	r27,-40(r1)
-	ld	r26,-48(r1)
-	ld	r25,-56(r1)
-
-	blr
-
-.Lfirst_warm_up_done:
-	lvx	const1,0,r3
-	addi	r3,r3,16
-
-	VPMSUMD(v8,v16,const1)
-	VPMSUMD(v9,v17,const1)
-	VPMSUMD(v10,v18,const1)
-	VPMSUMD(v11,v19,const1)
-	VPMSUMD(v12,v20,const1)
-	VPMSUMD(v13,v21,const1)
-	VPMSUMD(v14,v22,const1)
-	VPMSUMD(v15,v23,const1)
-
-	b	.Lsecond_cool_down
-
-.Lshort:
-	cmpdi	r5,0
-	beq	.Lzero
-
-	LOAD_REG_ADDR(r3, .short_constants)
-
-	/* Calculate where in the constant table we need to start */
-	subfic	r6,r5,256
-	add	r3,r3,r6
-
-	/* How many 16 byte chunks? */
-	srdi	r7,r5,4
-	mtctr	r7
-
-	vxor	v19,v19,v19
-	vxor	v20,v20,v20
-
-	lvx	v0,0,r4
-	lvx	v16,0,r3
-	VPERM(v0,v0,v16,byteswap)
-	vxor	v0,v0,v8	/* xor in initial value */
-	VPMSUMW(v0,v0,v16)
-	bdz	.Lv0
-
-	lvx	v1,off16,r4
-	lvx	v17,off16,r3
-	VPERM(v1,v1,v17,byteswap)
-	VPMSUMW(v1,v1,v17)
-	bdz	.Lv1
-
-	lvx	v2,off32,r4
-	lvx	v16,off32,r3
-	VPERM(v2,v2,v16,byteswap)
-	VPMSUMW(v2,v2,v16)
-	bdz	.Lv2
-
-	lvx	v3,off48,r4
-	lvx	v17,off48,r3
-	VPERM(v3,v3,v17,byteswap)
-	VPMSUMW(v3,v3,v17)
-	bdz	.Lv3
-
-	lvx	v4,off64,r4
-	lvx	v16,off64,r3
-	VPERM(v4,v4,v16,byteswap)
-	VPMSUMW(v4,v4,v16)
-	bdz	.Lv4
-
-	lvx	v5,off80,r4
-	lvx	v17,off80,r3
-	VPERM(v5,v5,v17,byteswap)
-	VPMSUMW(v5,v5,v17)
-	bdz	.Lv5
-
-	lvx	v6,off96,r4
-	lvx	v16,off96,r3
-	VPERM(v6,v6,v16,byteswap)
-	VPMSUMW(v6,v6,v16)
-	bdz	.Lv6
-
-	lvx	v7,off112,r4
-	lvx	v17,off112,r3
-	VPERM(v7,v7,v17,byteswap)
-	VPMSUMW(v7,v7,v17)
-	bdz	.Lv7
-
-	addi	r3,r3,128
-	addi	r4,r4,128
-
-	lvx	v8,0,r4
-	lvx	v16,0,r3
-	VPERM(v8,v8,v16,byteswap)
-	VPMSUMW(v8,v8,v16)
-	bdz	.Lv8
-
-	lvx	v9,off16,r4
-	lvx	v17,off16,r3
-	VPERM(v9,v9,v17,byteswap)
-	VPMSUMW(v9,v9,v17)
-	bdz	.Lv9
-
-	lvx	v10,off32,r4
-	lvx	v16,off32,r3
-	VPERM(v10,v10,v16,byteswap)
-	VPMSUMW(v10,v10,v16)
-	bdz	.Lv10
-
-	lvx	v11,off48,r4
-	lvx	v17,off48,r3
-	VPERM(v11,v11,v17,byteswap)
-	VPMSUMW(v11,v11,v17)
-	bdz	.Lv11
-
-	lvx	v12,off64,r4
-	lvx	v16,off64,r3
-	VPERM(v12,v12,v16,byteswap)
-	VPMSUMW(v12,v12,v16)
-	bdz	.Lv12
-
-	lvx	v13,off80,r4
-	lvx	v17,off80,r3
-	VPERM(v13,v13,v17,byteswap)
-	VPMSUMW(v13,v13,v17)
-	bdz	.Lv13
-
-	lvx	v14,off96,r4
-	lvx	v16,off96,r3
-	VPERM(v14,v14,v16,byteswap)
-	VPMSUMW(v14,v14,v16)
-	bdz	.Lv14
-
-	lvx	v15,off112,r4
-	lvx	v17,off112,r3
-	VPERM(v15,v15,v17,byteswap)
-	VPMSUMW(v15,v15,v17)
-
-.Lv15:	vxor	v19,v19,v15
-.Lv14:	vxor	v20,v20,v14
-.Lv13:	vxor	v19,v19,v13
-.Lv12:	vxor	v20,v20,v12
-.Lv11:	vxor	v19,v19,v11
-.Lv10:	vxor	v20,v20,v10
-.Lv9:	vxor	v19,v19,v9
-.Lv8:	vxor	v20,v20,v8
-.Lv7:	vxor	v19,v19,v7
-.Lv6:	vxor	v20,v20,v6
-.Lv5:	vxor	v19,v19,v5
-.Lv4:	vxor	v20,v20,v4
-.Lv3:	vxor	v19,v19,v3
-.Lv2:	vxor	v20,v20,v2
-.Lv1:	vxor	v19,v19,v1
-.Lv0:	vxor	v20,v20,v0
-
-	vxor	v0,v19,v20
-
-	b	.Lbarrett_reduction
-
-.Lzero:
-	mr	r3,r10
-	b	.Lout
-
-FUNC_END(CRC_FUNCTION_NAME)
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
deleted file mode 100644
index bf442004ea1f..000000000000
--- a/arch/powerpc/crypto/crc32c-vpmsum_asm.S
+++ /dev/null
@@ -1,842 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Calculate a crc32c with vpmsum acceleration
- *
- * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
- */
-	.section	.rodata
-.balign 16
-
-.byteswap_constant:
-	/* byte reverse permute constant */
-	.octa 0x0F0E0D0C0B0A09080706050403020100
-
-.constants:
-
-	/* Reduce 262144 kbits to 1024 bits */
-	/* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */
-	.octa 0x00000000b6ca9e20000000009c37c408
-
-	/* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */
-	.octa 0x00000000350249a800000001b51df26c
-
-	/* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */
-	.octa 0x00000001862dac54000000000724b9d0
-
-	/* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */
-	.octa 0x00000001d87fb48c00000001c00532fe
-
-	/* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */
-	.octa 0x00000001f39b699e00000000f05a9362
-
-	/* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */
-	.octa 0x0000000101da11b400000001e1007970
-
-	/* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */
-	.octa 0x00000001cab571e000000000a57366ee
-
-	/* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */
-	.octa 0x00000000c7020cfe0000000192011284
-
-	/* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */
-	.octa 0x00000000cdaed1ae0000000162716d9a
-
-	/* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */
-	.octa 0x00000001e804effc00000000cd97ecde
-
-	/* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */
-	.octa 0x0000000077c3ea3a0000000058812bc0
-
-	/* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */
-	.octa 0x0000000068df31b40000000088b8c12e
-
-	/* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */
-	.octa 0x00000000b059b6c200000001230b234c
-
-	/* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */
-	.octa 0x0000000145fb8ed800000001120b416e
-
-	/* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */
-	.octa 0x00000000cbc0916800000001974aecb0
-
-	/* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */
-	.octa 0x000000005ceeedc2000000008ee3f226
-
-	/* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */
-	.octa 0x0000000047d74e8600000001089aba9a
-
-	/* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */
-	.octa 0x00000001407e9e220000000065113872
-
-	/* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */
-	.octa 0x00000001da967bda000000005c07ec10
-
-	/* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */
-	.octa 0x000000006c8983680000000187590924
-
-	/* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */
-	.octa 0x00000000f2d14c9800000000e35da7c6
-
-	/* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */
-	.octa 0x00000001993c6ad4000000000415855a
-
-	/* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */
-	.octa 0x000000014683d1ac0000000073617758
-
-	/* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */
-	.octa 0x00000001a7c93e6c0000000176021d28
-
-	/* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */
-	.octa 0x000000010211e90a00000001c358fd0a
-
-	/* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */
-	.octa 0x000000001119403e00000001ff7a2c18
-
-	/* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */
-	.octa 0x000000001c3261aa00000000f2d9f7e4
-
-	/* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */
-	.octa 0x000000014e37a634000000016cf1f9c8
-
-	/* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */
-	.octa 0x0000000073786c0c000000010af9279a
-
-	/* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */
-	.octa 0x000000011dc037f80000000004f101e8
-
-	/* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */
-	.octa 0x0000000031433dfc0000000070bcf184
-
-	/* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */
-	.octa 0x000000009cde8348000000000a8de642
-
-	/* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */
-	.octa 0x0000000038d3c2a60000000062ea130c
-
-	/* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */
-	.octa 0x000000011b25f26000000001eb31cbb2
-
-	/* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */
-	.octa 0x000000001629e6f00000000170783448
-
-	/* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */
-	.octa 0x0000000160838b4c00000001a684b4c6
-
-	/* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */
-	.octa 0x000000007a44011c00000000253ca5b4
-
-	/* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */
-	.octa 0x00000000226f417a0000000057b4b1e2
-
-	/* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */
-	.octa 0x0000000045eb2eb400000000b6bd084c
-
-	/* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */
-	.octa 0x000000014459d70c0000000123c2d592
-
-	/* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */
-	.octa 0x00000001d406ed8200000000159dafce
-
-	/* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */
-	.octa 0x0000000160c8e1a80000000127e1a64e
-
-	/* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */
-	.octa 0x0000000027ba80980000000056860754
-
-	/* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */
-	.octa 0x000000006d92d01800000001e661aae8
-
-	/* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */
-	.octa 0x000000012ed7e3f200000000f82c6166
-
-	/* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */
-	.octa 0x000000002dc8778800000000c4f9c7ae
-
-	/* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */
-	.octa 0x0000000018240bb80000000074203d20
-
-	/* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */
-	.octa 0x000000001ad381580000000198173052
-
-	/* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */
-	.octa 0x00000001396b78f200000001ce8aba54
-
-	/* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */
-	.octa 0x000000011a68133400000001850d5d94
-
-	/* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */
-	.octa 0x000000012104732e00000001d609239c
-
-	/* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */
-	.octa 0x00000000a140d90c000000001595f048
-
-	/* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */
-	.octa 0x00000001b7215eda0000000042ccee08
-
-	/* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */
-	.octa 0x00000001aaf1df3c000000010a389d74
-
-	/* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */
-	.octa 0x0000000029d15b8a000000012a840da6
-
-	/* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */
-	.octa 0x00000000f1a96922000000001d181c0c
-
-	/* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */
-	.octa 0x00000001ac80d03c0000000068b7d1f6
-
-	/* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */
-	.octa 0x000000000f11d56a000000005b0f14fc
-
-	/* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */
-	.octa 0x00000001f1c022a20000000179e9e730
-
-	/* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */
-	.octa 0x0000000173d00ae200000001ce1368d6
-
-	/* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */
-	.octa 0x00000001d4ffe4ac0000000112c3a84c
-
-	/* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */
-	.octa 0x000000016edc5ae400000000de940fee
-
-	/* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */
-	.octa 0x00000001f1a0214000000000fe896b7e
-
-	/* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */
-	.octa 0x00000000ca0b28a000000001f797431c
-
-	/* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */
-	.octa 0x00000001928e30a20000000053e989ba
-
-	/* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */
-	.octa 0x0000000097b1b002000000003920cd16
-
-	/* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */
-	.octa 0x00000000b15bf90600000001e6f579b8
-
-	/* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */
-	.octa 0x00000000411c5d52000000007493cb0a
-
-	/* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */
-	.octa 0x00000001c36f330000000001bdd376d8
-
-	/* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */
-	.octa 0x00000001119227e0000000016badfee6
-
-	/* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */
-	.octa 0x00000000114d47020000000071de5c58
-
-	/* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */
-	.octa 0x00000000458b5b9800000000453f317c
-
-	/* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */
-	.octa 0x000000012e31fb8e0000000121675cce
-
-	/* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */
-	.octa 0x000000005cf619d800000001f409ee92
-
-	/* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */
-	.octa 0x0000000063f4d8b200000000f36b9c88
-
-	/* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */
-	.octa 0x000000004138dc8a0000000036b398f4
-
-	/* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */
-	.octa 0x00000001d29ee8e000000001748f9adc
-
-	/* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */
-	.octa 0x000000006a08ace800000001be94ec00
-
-	/* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */
-	.octa 0x0000000127d4201000000000b74370d6
-
-	/* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */
-	.octa 0x0000000019d76b6200000001174d0b98
-
-	/* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */
-	.octa 0x00000001b1471f6e00000000befc06a4
-
-	/* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */
-	.octa 0x00000001f64c19cc00000001ae125288
-
-	/* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */
-	.octa 0x00000000003c0ea00000000095c19b34
-
-	/* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */
-	.octa 0x000000014d73abf600000001a78496f2
-
-	/* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */
-	.octa 0x00000001620eb84400000001ac5390a0
-
-	/* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */
-	.octa 0x0000000147655048000000002a80ed6e
-
-	/* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */
-	.octa 0x0000000067b5077e00000001fa9b0128
-
-	/* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */
-	.octa 0x0000000010ffe20600000001ea94929e
-
-	/* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */
-	.octa 0x000000000fee8f1e0000000125f4305c
-
-	/* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */
-	.octa 0x00000001da26fbae00000001471e2002
-
-	/* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */
-	.octa 0x00000001b3a8bd880000000132d2253a
-
-	/* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */
-	.octa 0x00000000e8f3898e00000000f26b3592
-
-	/* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */
-	.octa 0x00000000b0d0d28c00000000bc8b67b0
-
-	/* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */
-	.octa 0x0000000030f2a798000000013a826ef2
-
-	/* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */
-	.octa 0x000000000fba10020000000081482c84
-
-	/* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */
-	.octa 0x00000000bdb9bd7200000000e77307c2
-
-	/* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */
-	.octa 0x0000000075d3bf5a00000000d4a07ec8
-
-	/* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */
-	.octa 0x00000000ef1f98a00000000017102100
-
-	/* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */
-	.octa 0x00000000689c760200000000db406486
-
-	/* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */
-	.octa 0x000000016d5fa5fe0000000192db7f88
-
-	/* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */
-	.octa 0x00000001d0d2b9ca000000018bf67b1e
-
-	/* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */
-	.octa 0x0000000041e7b470000000007c09163e
-
-	/* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */
-	.octa 0x00000001cbb6495e000000000adac060
-
-	/* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */
-	.octa 0x000000010052a0b000000000bd8316ae
-
-	/* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */
-	.octa 0x00000001d8effb5c000000019f09ab54
-
-	/* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */
-	.octa 0x00000001d969853c0000000125155542
-
-	/* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */
-	.octa 0x00000000523ccce2000000018fdb5882
-
-	/* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */
-	.octa 0x000000001e2436bc00000000e794b3f4
-
-	/* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */
-	.octa 0x00000000ddd1c3a2000000016f9bb022
-
-	/* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */
-	.octa 0x0000000019fcfe3800000000290c9978
-
-	/* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */
-	.octa 0x00000001ce95db640000000083c0f350
-
-	/* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */
-	.octa 0x00000000af5828060000000173ea6628
-
-	/* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */
-	.octa 0x00000001006388f600000001c8b4e00a
-
-	/* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */
-	.octa 0x0000000179eca00a00000000de95d6aa
-
-	/* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */
-	.octa 0x0000000122410a6a000000010b7f7248
-
-	/* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */
-	.octa 0x000000004288e87c00000001326e3a06
-
-	/* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */
-	.octa 0x000000016c5490da00000000bb62c2e6
-
-	/* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */
-	.octa 0x00000000d1c71f6e0000000156a4b2c2
-
-	/* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */
-	.octa 0x00000001b4ce08a6000000011dfe763a
-
-	/* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */
-	.octa 0x00000001466ba60c000000007bcca8e2
-
-	/* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */
-	.octa 0x00000001f6c488a40000000186118faa
-
-	/* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */
-	.octa 0x000000013bfb06820000000111a65a88
-
-	/* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */
-	.octa 0x00000000690e9e54000000003565e1c4
-
-	/* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */
-	.octa 0x00000000281346b6000000012ed02a82
-
-	/* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */
-	.octa 0x000000015646402400000000c486ecfc
-
-	/* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */
-	.octa 0x000000016063a8dc0000000001b951b2
-
-	/* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */
-	.octa 0x0000000116a663620000000048143916
-
-	/* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */
-	.octa 0x000000017e8aa4d200000001dc2ae124
-
-	/* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */
-	.octa 0x00000001728eb10c00000001416c58d6
-
-	/* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */
-	.octa 0x00000001b08fd7fa00000000a479744a
-
-	/* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */
-	.octa 0x00000001092a16e80000000096ca3a26
-
-	/* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */
-	.octa 0x00000000a505637c00000000ff223d4e
-
-	/* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */
-	.octa 0x00000000d94869b2000000010e84da42
-
-	/* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */
-	.octa 0x00000001c8b203ae00000001b61ba3d0
-
-	/* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */
-	.octa 0x000000005704aea000000000680f2de8
-
-	/* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */
-	.octa 0x000000012e295fa2000000008772a9a8
-
-	/* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */
-	.octa 0x000000011d0908bc0000000155f295bc
-
-	/* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */
-	.octa 0x0000000193ed97ea00000000595f9282
-
-	/* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */
-	.octa 0x000000013a0f1c520000000164b1c25a
-
-	/* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */
-	.octa 0x000000010c2c40c000000000fbd67c50
-
-	/* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */
-	.octa 0x00000000ff6fac3e0000000096076268
-
-	/* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */
-	.octa 0x000000017b3609c000000001d288e4cc
-
-	/* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */
-	.octa 0x0000000088c8c92200000001eaac1bdc
-
-	/* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */
-	.octa 0x00000001751baae600000001f1ea39e2
-
-	/* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */
-	.octa 0x000000010795297200000001eb6506fc
-
-	/* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */
-	.octa 0x0000000162b00abe000000010f806ffe
-
-	/* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */
-	.octa 0x000000000d7b404c000000010408481e
-
-	/* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */
-	.octa 0x00000000763b13d40000000188260534
-
-	/* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */
-	.octa 0x00000000f6dc22d80000000058fc73e0
-
-	/* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */
-	.octa 0x000000007daae06000000000391c59b8
-
-	/* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */
-	.octa 0x000000013359ab7c000000018b638400
-
-	/* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */
-	.octa 0x000000008add438a000000011738f5c4
-
-	/* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */
-	.octa 0x00000001edbefdea000000008cf7c6da
-
-	/* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */
-	.octa 0x000000004104e0f800000001ef97fb16
-
-	/* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */
-	.octa 0x00000000b48a82220000000102130e20
-
-	/* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */
-	.octa 0x00000001bcb4684400000000db968898
-
-	/* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */
-	.octa 0x000000013293ce0a00000000b5047b5e
-
-	/* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */
-	.octa 0x00000001710d0844000000010b90fdb2
-
-	/* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */
-	.octa 0x0000000117907f6e000000004834a32e
-
-	/* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */
-	.octa 0x0000000087ddf93e0000000059c8f2b0
-
-	/* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */
-	.octa 0x000000005970e9b00000000122cec508
-
-	/* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */
-	.octa 0x0000000185b2b7d0000000000a330cda
-
-	/* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */
-	.octa 0x00000001dcee0efc000000014a47148c
-
-	/* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */
-	.octa 0x0000000030da27220000000042c61cb8
-
-	/* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */
-	.octa 0x000000012f925a180000000012fe6960
-
-	/* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */
-	.octa 0x00000000dd2e357c00000000dbda2c20
-
-	/* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */
-	.octa 0x00000000071c80de000000011122410c
-
-	/* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */
-	.octa 0x000000011513140a00000000977b2070
-
-	/* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */
-	.octa 0x00000001df876e8e000000014050438e
-
-	/* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */
-	.octa 0x000000015f81d6ce0000000147c840e8
-
-	/* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */
-	.octa 0x000000019dd94dbe00000001cc7c88ce
-
-	/* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */
-	.octa 0x00000001373d206e00000001476b35a4
-
-	/* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */
-	.octa 0x00000000668ccade000000013d52d508
-
-	/* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */
-	.octa 0x00000001b192d268000000008e4be32e
-
-	/* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */
-	.octa 0x00000000e30f3a7800000000024120fe
-
-	/* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */
-	.octa 0x000000010ef1f7bc00000000ddecddb4
-
-	/* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */
-	.octa 0x00000001f5ac738000000000d4d403bc
-
-	/* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */
-	.octa 0x000000011822ea7000000001734b89aa
-
-	/* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */
-	.octa 0x00000000c3a33848000000010e7a58d6
-
-	/* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */
-	.octa 0x00000001bd151c2400000001f9f04e9c
-
-	/* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */
-	.octa 0x0000000056002d7600000000b692225e
-
-	/* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */
-	.octa 0x000000014657c4f4000000019b8d3f3e
-
-	/* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */
-	.octa 0x0000000113742d7c00000001a874f11e
-
-	/* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */
-	.octa 0x000000019c5920ba000000010d5a4254
-
-	/* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */
-	.octa 0x000000005216d2d600000000bbb2f5d6
-
-	/* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */
-	.octa 0x0000000136f5ad8a0000000179cc0e36
-
-	/* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */
-	.octa 0x000000018b07beb600000001dca1da4a
-
-	/* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */
-	.octa 0x00000000db1e93b000000000feb1a192
-
-	/* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */
-	.octa 0x000000000b96fa3a00000000d1eeedd6
-
-	/* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */
-	.octa 0x00000001d9968af0000000008fad9bb4
-
-	/* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */
-	.octa 0x000000000e4a77a200000001884938e4
-
-	/* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */
-	.octa 0x00000000508c2ac800000001bc2e9bc0
-
-	/* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */
-	.octa 0x0000000021572a8000000001f9658a68
-
-	/* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */
-	.octa 0x00000001b859daf2000000001b9224fc
-
-	/* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */
-	.octa 0x000000016f7884740000000055b2fb84
-
-	/* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */
-	.octa 0x00000001b438810e000000018b090348
-
-	/* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */
-	.octa 0x0000000095ddc6f2000000011ccbd5ea
-
-	/* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */
-	.octa 0x00000001d977c20c0000000007ae47f8
-
-	/* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */
-	.octa 0x00000000ebedb99a0000000172acbec0
-
-	/* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */
-	.octa 0x00000001df9e9e9200000001c6e3ff20
-
-	/* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */
-	.octa 0x00000001a4a3f95200000000e1b38744
-
-	/* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */
-	.octa 0x00000000e2f5122000000000791585b2
-
-	/* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */
-	.octa 0x000000004aa01f3e00000000ac53b894
-
-	/* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */
-	.octa 0x00000000b3e90a5800000001ed5f2cf4
-
-	/* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */
-	.octa 0x000000000c9ca2aa00000001df48b2e0
-
-	/* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */
-	.octa 0x000000015168231600000000049c1c62
-
-	/* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */
-	.octa 0x0000000036fce78c000000017c460c12
-
-	/* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */
-	.octa 0x000000009037dc10000000015be4da7e
-
-	/* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */
-	.octa 0x00000000d3298582000000010f38f668
-
-	/* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */
-	.octa 0x00000001b42e8ad60000000039f40a00
-
-	/* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */
-	.octa 0x00000000142a983800000000bd4c10c4
-
-	/* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */
-	.octa 0x0000000109c7f1900000000042db1d98
-
-	/* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */
-	.octa 0x0000000056ff931000000001c905bae6
-
-	/* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */
-	.octa 0x00000001594513aa00000000069d40ea
-
-	/* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */
-	.octa 0x00000001e3b5b1e8000000008e4fbad0
-
-	/* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */
-	.octa 0x000000011dd5fc080000000047bedd46
-
-	/* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */
-	.octa 0x00000001675f0cc20000000026396bf8
-
-	/* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */
-	.octa 0x00000000d1c8dd4400000000379beb92
-
-	/* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */
-	.octa 0x0000000115ebd3d8000000000abae54a
-
-	/* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */
-	.octa 0x00000001ecbd0dac0000000007e6a128
-
-	/* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */
-	.octa 0x00000000cdf67af2000000000ade29d2
-
-	/* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */
-	.octa 0x000000004c01ff4c00000000f974c45c
-
-	/* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */
-	.octa 0x00000000f2d8657e00000000e77ac60a
-
-	/* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */
-	.octa 0x000000006bae74c40000000145895816
-
-	/* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */
-	.octa 0x0000000152af8aa00000000038e362be
-
-	/* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */
-	.octa 0x0000000004663802000000007f991a64
-
-	/* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */
-	.octa 0x00000001ab2f5afc00000000fa366d3a
-
-	/* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */
-	.octa 0x0000000074a4ebd400000001a2bb34f0
-
-	/* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */
-	.octa 0x00000001d7ab3a4c0000000028a9981e
-
-	/* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */
-	.octa 0x00000001a8da60c600000001dbc672be
-
-	/* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */
-	.octa 0x000000013cf6382000000000b04d77f6
-
-	/* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */
-	.octa 0x00000000bec12e1e0000000124400d96
-
-	/* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */
-	.octa 0x00000001c6368010000000014ca4b414
-
-	/* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */
-	.octa 0x00000001e6e78758000000012fe2c938
-
-	/* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */
-	.octa 0x000000008d7f2b3c00000001faed01e6
-
-	/* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */
-	.octa 0x000000016b4a156e000000007e80ecfe
-
-	/* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */
-	.octa 0x00000001c63cfeb60000000098daee94
-
-	/* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */
-	.octa 0x000000015f902670000000010a04edea
-
-	/* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */
-	.octa 0x00000001cd5de11e00000001c00b4524
-
-	/* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */
-	.octa 0x000000001acaec540000000170296550
-
-	/* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */
-	.octa 0x000000002bd0ca780000000181afaa48
-
-	/* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */
-	.octa 0x0000000032d63d5c0000000185a31ffa
-
-	/* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */
-	.octa 0x000000001c6d4e4c000000002469f608
-
-	/* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */
-	.octa 0x0000000106a60b92000000006980102a
-
-	/* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */
-	.octa 0x00000000d3855e120000000111ea9ca8
-
-	/* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */
-	.octa 0x00000000e312563600000001bd1d29ce
-
-	/* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */
-	.octa 0x000000009e8f7ea400000001b34b9580
-
-	/* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */
-	.octa 0x00000001c82e562c000000003076054e
-
-	/* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */
-	.octa 0x00000000ca9f09ce000000012a608ea4
-
-	/* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */
-	.octa 0x00000000c63764e600000000784d05fe
-
-	/* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */
-	.octa 0x0000000168d2e49e000000016ef0d82a
-
-	/* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */
-	.octa 0x00000000e986c1480000000075bda454
-
-	/* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */
-	.octa 0x00000000cfb65894000000003dc0a1c4
-
-	/* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */
-	.octa 0x0000000111cadee400000000e9a5d8be
-
-	/* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */
-	.octa 0x0000000171fb63ce00000001609bc4b4
-
-.short_constants:
-
-	/* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */
-	/* x^1952 mod p(x)`, x^1984 mod p(x)`, x^2016 mod p(x)`, x^2048 mod p(x)` */
-	.octa 0x7fec2963e5bf80485cf015c388e56f72
-
-	/* x^1824 mod p(x)`, x^1856 mod p(x)`, x^1888 mod p(x)`, x^1920 mod p(x)` */
-	.octa 0x38e888d4844752a9963a18920246e2e6
-
-	/* x^1696 mod p(x)`, x^1728 mod p(x)`, x^1760 mod p(x)`, x^1792 mod p(x)` */
-	.octa 0x42316c00730206ad419a441956993a31
-
-	/* x^1568 mod p(x)`, x^1600 mod p(x)`, x^1632 mod p(x)`, x^1664 mod p(x)` */
-	.octa 0x543d5c543e65ddf9924752ba2b830011
-
-	/* x^1440 mod p(x)`, x^1472 mod p(x)`, x^1504 mod p(x)`, x^1536 mod p(x)` */
-	.octa 0x78e87aaf56767c9255bd7f9518e4a304
-
-	/* x^1312 mod p(x)`, x^1344 mod p(x)`, x^1376 mod p(x)`, x^1408 mod p(x)` */
-	.octa 0x8f68fcec1903da7f6d76739fe0553f1e
-
-	/* x^1184 mod p(x)`, x^1216 mod p(x)`, x^1248 mod p(x)`, x^1280 mod p(x)` */
-	.octa 0x3f4840246791d588c133722b1fe0b5c3
-
-	/* x^1056 mod p(x)`, x^1088 mod p(x)`, x^1120 mod p(x)`, x^1152 mod p(x)` */
-	.octa 0x34c96751b04de25a64b67ee0e55ef1f3
-
-	/* x^928 mod p(x)`, x^960 mod p(x)`, x^992 mod p(x)`, x^1024 mod p(x)` */
-	.octa 0x156c8e180b4a395b069db049b8fdb1e7
-
-	/* x^800 mod p(x)`, x^832 mod p(x)`, x^864 mod p(x)`, x^896 mod p(x)` */
-	.octa 0xe0b99ccbe661f7bea11bfaf3c9e90b9e
-
-	/* x^672 mod p(x)`, x^704 mod p(x)`, x^736 mod p(x)`, x^768 mod p(x)` */
-	.octa 0x041d37768cd75659817cdc5119b29a35
-
-	/* x^544 mod p(x)`, x^576 mod p(x)`, x^608 mod p(x)`, x^640 mod p(x)` */
-	.octa 0x3a0777818cfaa9651ce9d94b36c41f1c
-
-	/* x^416 mod p(x)`, x^448 mod p(x)`, x^480 mod p(x)`, x^512 mod p(x)` */
-	.octa 0x0e148e8252377a554f256efcb82be955
-
-	/* x^288 mod p(x)`, x^320 mod p(x)`, x^352 mod p(x)`, x^384 mod p(x)` */
-	.octa 0x9c25531d19e65ddeec1631edb2dea967
-
-	/* x^160 mod p(x)`, x^192 mod p(x)`, x^224 mod p(x)`, x^256 mod p(x)` */
-	.octa 0x790606ff9957c0a65d27e147510ac59a
-
-	/* x^32 mod p(x)`, x^64 mod p(x)`, x^96 mod p(x)`, x^128 mod p(x)` */
-	.octa 0x82f63b786ea2d55ca66805eb18b8ea18
-
-
-.barrett_constants:
-	/* 33 bit reflected Barrett constant m - (4^32)/n */
-	.octa 0x000000000000000000000000dea713f1	/* x^64 div p(x)` */
-	/* 33 bit reflected Barrett constant n */
-	.octa 0x00000000000000000000000105ec76f1
-
-#define CRC_FUNCTION_NAME __crc32c_vpmsum
-#define REFLECT
-#include "crc32-vpmsum_core.S"
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
deleted file mode 100644
index 63760b7dbb76..000000000000
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ /dev/null
@@ -1,173 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#include <linux/crc32.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/cpufeature.h>
-#include <asm/simd.h>
-#include <asm/switch_to.h>
-
-#define CHKSUM_BLOCK_SIZE	1
-#define CHKSUM_DIGEST_SIZE	4
-
-#define VMX_ALIGN		16
-#define VMX_ALIGN_MASK		(VMX_ALIGN-1)
-
-#define VECTOR_BREAKPOINT	512
-
-u32 __crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len);
-
-static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len)
-{
-	unsigned int prealign;
-	unsigned int tail;
-
-	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable())
-		return __crc32c_le(crc, p, len);
-
-	if ((unsigned long)p & VMX_ALIGN_MASK) {
-		prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
-		crc = __crc32c_le(crc, p, prealign);
-		len -= prealign;
-		p += prealign;
-	}
-
-	if (len & ~VMX_ALIGN_MASK) {
-		preempt_disable();
-		pagefault_disable();
-		enable_kernel_altivec();
-		crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
-		disable_kernel_altivec();
-		pagefault_enable();
-		preempt_enable();
-	}
-
-	tail = len & VMX_ALIGN_MASK;
-	if (tail) {
-		p += len & ~VMX_ALIGN_MASK;
-		crc = __crc32c_le(crc, p, tail);
-	}
-
-	return crc;
-}
-
-static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm)
-{
-	u32 *key = crypto_tfm_ctx(tfm);
-
-	*key = ~0;
-
-	return 0;
-}
-
-/*
- * Setting the seed allows arbitrary accumulators and flexible XOR policy
- * If your algorithm starts with ~0, then XOR with ~0 before you set
- * the seed.
- */
-static int crc32c_vpmsum_setkey(struct crypto_shash *hash, const u8 *key,
-			       unsigned int keylen)
-{
-	u32 *mctx = crypto_shash_ctx(hash);
-
-	if (keylen != sizeof(u32))
-		return -EINVAL;
-	*mctx = le32_to_cpup((__le32 *)key);
-	return 0;
-}
-
-static int crc32c_vpmsum_init(struct shash_desc *desc)
-{
-	u32 *mctx = crypto_shash_ctx(desc->tfm);
-	u32 *crcp = shash_desc_ctx(desc);
-
-	*crcp = *mctx;
-
-	return 0;
-}
-
-static int crc32c_vpmsum_update(struct shash_desc *desc, const u8 *data,
-			       unsigned int len)
-{
-	u32 *crcp = shash_desc_ctx(desc);
-
-	*crcp = crc32c_vpmsum(*crcp, data, len);
-
-	return 0;
-}
-
-static int __crc32c_vpmsum_finup(u32 *crcp, const u8 *data, unsigned int len,
-				u8 *out)
-{
-	*(__le32 *)out = ~cpu_to_le32(crc32c_vpmsum(*crcp, data, len));
-
-	return 0;
-}
-
-static int crc32c_vpmsum_finup(struct shash_desc *desc, const u8 *data,
-			      unsigned int len, u8 *out)
-{
-	return __crc32c_vpmsum_finup(shash_desc_ctx(desc), data, len, out);
-}
-
-static int crc32c_vpmsum_final(struct shash_desc *desc, u8 *out)
-{
-	u32 *crcp = shash_desc_ctx(desc);
-
-	*(__le32 *)out = ~cpu_to_le32p(crcp);
-
-	return 0;
-}
-
-static int crc32c_vpmsum_digest(struct shash_desc *desc, const u8 *data,
-			       unsigned int len, u8 *out)
-{
-	return __crc32c_vpmsum_finup(crypto_shash_ctx(desc->tfm), data, len,
-				     out);
-}
-
-static struct shash_alg alg = {
-	.setkey		= crc32c_vpmsum_setkey,
-	.init		= crc32c_vpmsum_init,
-	.update		= crc32c_vpmsum_update,
-	.final		= crc32c_vpmsum_final,
-	.finup		= crc32c_vpmsum_finup,
-	.digest		= crc32c_vpmsum_digest,
-	.descsize	= sizeof(u32),
-	.digestsize	= CHKSUM_DIGEST_SIZE,
-	.base		= {
-		.cra_name		= "crc32c",
-		.cra_driver_name	= "crc32c-vpmsum",
-		.cra_priority		= 200,
-		.cra_flags		= CRYPTO_ALG_OPTIONAL_KEY,
-		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(u32),
-		.cra_module		= THIS_MODULE,
-		.cra_init		= crc32c_vpmsum_cra_init,
-	}
-};
-
-static int __init crc32c_vpmsum_mod_init(void)
-{
-	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
-		return -ENODEV;
-
-	return crypto_register_shash(&alg);
-}
-
-static void __exit crc32c_vpmsum_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init);
-module_exit(crc32c_vpmsum_mod_fini);
-
-MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
-MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CRYPTO("crc32c");
-MODULE_ALIAS_CRYPTO("crc32c-vpmsum");
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S b/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
deleted file mode 100644
index f0b93a0fe168..000000000000
--- a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
+++ /dev/null
@@ -1,845 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Calculate a CRC T10DIF  with vpmsum acceleration
- *
- * Constants generated by crc32-vpmsum, available at
- * https://github.com/antonblanchard/crc32-vpmsum
- *
- * crc32-vpmsum is
- * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
- */
-	.section	.rodata
-.balign 16
-
-.byteswap_constant:
-	/* byte reverse permute constant */
-	.octa 0x0F0E0D0C0B0A09080706050403020100
-
-.constants:
-
-	/* Reduce 262144 kbits to 1024 bits */
-	/* x^261184 mod p(x), x^261120 mod p(x) */
-	.octa 0x0000000056d300000000000052550000
-
-	/* x^260160 mod p(x), x^260096 mod p(x) */
-	.octa 0x00000000ee67000000000000a1e40000
-
-	/* x^259136 mod p(x), x^259072 mod p(x) */
-	.octa 0x0000000060830000000000004ad10000
-
-	/* x^258112 mod p(x), x^258048 mod p(x) */
-	.octa 0x000000008cfe0000000000009ab40000
-
-	/* x^257088 mod p(x), x^257024 mod p(x) */
-	.octa 0x000000003e93000000000000fdb50000
-
-	/* x^256064 mod p(x), x^256000 mod p(x) */
-	.octa 0x000000003c2000000000000045480000
-
-	/* x^255040 mod p(x), x^254976 mod p(x) */
-	.octa 0x00000000b1fc0000000000008d690000
-
-	/* x^254016 mod p(x), x^253952 mod p(x) */
-	.octa 0x00000000f82b00000000000024ad0000
-
-	/* x^252992 mod p(x), x^252928 mod p(x) */
-	.octa 0x0000000044420000000000009f1a0000
-
-	/* x^251968 mod p(x), x^251904 mod p(x) */
-	.octa 0x00000000e88c00000000000066ec0000
-
-	/* x^250944 mod p(x), x^250880 mod p(x) */
-	.octa 0x00000000385c000000000000c87d0000
-
-	/* x^249920 mod p(x), x^249856 mod p(x) */
-	.octa 0x000000003227000000000000c8ff0000
-
-	/* x^248896 mod p(x), x^248832 mod p(x) */
-	.octa 0x00000000a9a900000000000033440000
-
-	/* x^247872 mod p(x), x^247808 mod p(x) */
-	.octa 0x00000000abaa00000000000066eb0000
-
-	/* x^246848 mod p(x), x^246784 mod p(x) */
-	.octa 0x000000001ac3000000000000c4ef0000
-
-	/* x^245824 mod p(x), x^245760 mod p(x) */
-	.octa 0x0000000063f000000000000056f30000
-
-	/* x^244800 mod p(x), x^244736 mod p(x) */
-	.octa 0x0000000032cc00000000000002050000
-
-	/* x^243776 mod p(x), x^243712 mod p(x) */
-	.octa 0x00000000f8b5000000000000568e0000
-
-	/* x^242752 mod p(x), x^242688 mod p(x) */
-	.octa 0x000000008db100000000000064290000
-
-	/* x^241728 mod p(x), x^241664 mod p(x) */
-	.octa 0x0000000059ca0000000000006b660000
-
-	/* x^240704 mod p(x), x^240640 mod p(x) */
-	.octa 0x000000005f5c00000000000018f80000
-
-	/* x^239680 mod p(x), x^239616 mod p(x) */
-	.octa 0x0000000061af000000000000b6090000
-
-	/* x^238656 mod p(x), x^238592 mod p(x) */
-	.octa 0x00000000e29e000000000000099a0000
-
-	/* x^237632 mod p(x), x^237568 mod p(x) */
-	.octa 0x000000000975000000000000a8360000
-
-	/* x^236608 mod p(x), x^236544 mod p(x) */
-	.octa 0x0000000043900000000000004f570000
-
-	/* x^235584 mod p(x), x^235520 mod p(x) */
-	.octa 0x00000000f9cd000000000000134c0000
-
-	/* x^234560 mod p(x), x^234496 mod p(x) */
-	.octa 0x000000007c29000000000000ec380000
-
-	/* x^233536 mod p(x), x^233472 mod p(x) */
-	.octa 0x000000004c6a000000000000b0d10000
-
-	/* x^232512 mod p(x), x^232448 mod p(x) */
-	.octa 0x00000000e7290000000000007d3e0000
-
-	/* x^231488 mod p(x), x^231424 mod p(x) */
-	.octa 0x00000000f1ab000000000000f0b20000
-
-	/* x^230464 mod p(x), x^230400 mod p(x) */
-	.octa 0x0000000039db0000000000009c270000
-
-	/* x^229440 mod p(x), x^229376 mod p(x) */
-	.octa 0x000000005e2800000000000092890000
-
-	/* x^228416 mod p(x), x^228352 mod p(x) */
-	.octa 0x00000000d44e000000000000d5ee0000
-
-	/* x^227392 mod p(x), x^227328 mod p(x) */
-	.octa 0x00000000cd0a00000000000041f50000
-
-	/* x^226368 mod p(x), x^226304 mod p(x) */
-	.octa 0x00000000c5b400000000000010520000
-
-	/* x^225344 mod p(x), x^225280 mod p(x) */
-	.octa 0x00000000fd2100000000000042170000
-
-	/* x^224320 mod p(x), x^224256 mod p(x) */
-	.octa 0x000000002f2500000000000095c20000
-
-	/* x^223296 mod p(x), x^223232 mod p(x) */
-	.octa 0x000000001b0100000000000001ce0000
-
-	/* x^222272 mod p(x), x^222208 mod p(x) */
-	.octa 0x000000000d430000000000002aca0000
-
-	/* x^221248 mod p(x), x^221184 mod p(x) */
-	.octa 0x0000000030a6000000000000385e0000
-
-	/* x^220224 mod p(x), x^220160 mod p(x) */
-	.octa 0x00000000e37b0000000000006f7a0000
-
-	/* x^219200 mod p(x), x^219136 mod p(x) */
-	.octa 0x00000000873600000000000024320000
-
-	/* x^218176 mod p(x), x^218112 mod p(x) */
-	.octa 0x00000000e9fb000000000000bd9c0000
-
-	/* x^217152 mod p(x), x^217088 mod p(x) */
-	.octa 0x000000003b9500000000000054bc0000
-
-	/* x^216128 mod p(x), x^216064 mod p(x) */
-	.octa 0x00000000133e000000000000a4660000
-
-	/* x^215104 mod p(x), x^215040 mod p(x) */
-	.octa 0x00000000784500000000000079930000
-
-	/* x^214080 mod p(x), x^214016 mod p(x) */
-	.octa 0x00000000b9800000000000001bb80000
-
-	/* x^213056 mod p(x), x^212992 mod p(x) */
-	.octa 0x00000000687600000000000024400000
-
-	/* x^212032 mod p(x), x^211968 mod p(x) */
-	.octa 0x00000000aff300000000000029e10000
-
-	/* x^211008 mod p(x), x^210944 mod p(x) */
-	.octa 0x0000000024b50000000000005ded0000
-
-	/* x^209984 mod p(x), x^209920 mod p(x) */
-	.octa 0x0000000017e8000000000000b12e0000
-
-	/* x^208960 mod p(x), x^208896 mod p(x) */
-	.octa 0x00000000128400000000000026d20000
-
-	/* x^207936 mod p(x), x^207872 mod p(x) */
-	.octa 0x000000002115000000000000a32a0000
-
-	/* x^206912 mod p(x), x^206848 mod p(x) */
-	.octa 0x000000009595000000000000a1210000
-
-	/* x^205888 mod p(x), x^205824 mod p(x) */
-	.octa 0x00000000281e000000000000ee8b0000
-
-	/* x^204864 mod p(x), x^204800 mod p(x) */
-	.octa 0x0000000006010000000000003d0d0000
-
-	/* x^203840 mod p(x), x^203776 mod p(x) */
-	.octa 0x00000000e2b600000000000034e90000
-
-	/* x^202816 mod p(x), x^202752 mod p(x) */
-	.octa 0x000000001bd40000000000004cdb0000
-
-	/* x^201792 mod p(x), x^201728 mod p(x) */
-	.octa 0x00000000df2800000000000030e90000
-
-	/* x^200768 mod p(x), x^200704 mod p(x) */
-	.octa 0x0000000049c200000000000042590000
-
-	/* x^199744 mod p(x), x^199680 mod p(x) */
-	.octa 0x000000009b97000000000000df950000
-
-	/* x^198720 mod p(x), x^198656 mod p(x) */
-	.octa 0x000000006184000000000000da7b0000
-
-	/* x^197696 mod p(x), x^197632 mod p(x) */
-	.octa 0x00000000461700000000000012510000
-
-	/* x^196672 mod p(x), x^196608 mod p(x) */
-	.octa 0x000000009b40000000000000f37e0000
-
-	/* x^195648 mod p(x), x^195584 mod p(x) */
-	.octa 0x00000000eeb2000000000000ecf10000
-
-	/* x^194624 mod p(x), x^194560 mod p(x) */
-	.octa 0x00000000b2e800000000000050f20000
-
-	/* x^193600 mod p(x), x^193536 mod p(x) */
-	.octa 0x00000000f59a000000000000e0b30000
-
-	/* x^192576 mod p(x), x^192512 mod p(x) */
-	.octa 0x00000000467f0000000000004d5a0000
-
-	/* x^191552 mod p(x), x^191488 mod p(x) */
-	.octa 0x00000000da92000000000000bb010000
-
-	/* x^190528 mod p(x), x^190464 mod p(x) */
-	.octa 0x000000001e1000000000000022a40000
-
-	/* x^189504 mod p(x), x^189440 mod p(x) */
-	.octa 0x0000000058fe000000000000836f0000
-
-	/* x^188480 mod p(x), x^188416 mod p(x) */
-	.octa 0x00000000b9ce000000000000d78d0000
-
-	/* x^187456 mod p(x), x^187392 mod p(x) */
-	.octa 0x0000000022210000000000004f8d0000
-
-	/* x^186432 mod p(x), x^186368 mod p(x) */
-	.octa 0x00000000744600000000000033760000
-
-	/* x^185408 mod p(x), x^185344 mod p(x) */
-	.octa 0x000000001c2e000000000000a1e50000
-
-	/* x^184384 mod p(x), x^184320 mod p(x) */
-	.octa 0x00000000dcc8000000000000a1a40000
-
-	/* x^183360 mod p(x), x^183296 mod p(x) */
-	.octa 0x00000000910f00000000000019a20000
-
-	/* x^182336 mod p(x), x^182272 mod p(x) */
-	.octa 0x0000000055d5000000000000f6ae0000
-
-	/* x^181312 mod p(x), x^181248 mod p(x) */
-	.octa 0x00000000c8ba000000000000a7ac0000
-
-	/* x^180288 mod p(x), x^180224 mod p(x) */
-	.octa 0x0000000031f8000000000000eea20000
-
-	/* x^179264 mod p(x), x^179200 mod p(x) */
-	.octa 0x000000001966000000000000c4d90000
-
-	/* x^178240 mod p(x), x^178176 mod p(x) */
-	.octa 0x00000000b9810000000000002b470000
-
-	/* x^177216 mod p(x), x^177152 mod p(x) */
-	.octa 0x000000008303000000000000f7cf0000
-
-	/* x^176192 mod p(x), x^176128 mod p(x) */
-	.octa 0x000000002ce500000000000035b30000
-
-	/* x^175168 mod p(x), x^175104 mod p(x) */
-	.octa 0x000000002fae0000000000000c7c0000
-
-	/* x^174144 mod p(x), x^174080 mod p(x) */
-	.octa 0x00000000f50c0000000000009edf0000
-
-	/* x^173120 mod p(x), x^173056 mod p(x) */
-	.octa 0x00000000714f00000000000004cd0000
-
-	/* x^172096 mod p(x), x^172032 mod p(x) */
-	.octa 0x00000000c161000000000000541b0000
-
-	/* x^171072 mod p(x), x^171008 mod p(x) */
-	.octa 0x0000000021c8000000000000e2700000
-
-	/* x^170048 mod p(x), x^169984 mod p(x) */
-	.octa 0x00000000b93d00000000000009a60000
-
-	/* x^169024 mod p(x), x^168960 mod p(x) */
-	.octa 0x00000000fbcf000000000000761c0000
-
-	/* x^168000 mod p(x), x^167936 mod p(x) */
-	.octa 0x0000000026350000000000009db30000
-
-	/* x^166976 mod p(x), x^166912 mod p(x) */
-	.octa 0x00000000b64f0000000000003e9f0000
-
-	/* x^165952 mod p(x), x^165888 mod p(x) */
-	.octa 0x00000000bd0e00000000000078590000
-
-	/* x^164928 mod p(x), x^164864 mod p(x) */
-	.octa 0x00000000d9360000000000008bc80000
-
-	/* x^163904 mod p(x), x^163840 mod p(x) */
-	.octa 0x000000002f140000000000008c9f0000
-
-	/* x^162880 mod p(x), x^162816 mod p(x) */
-	.octa 0x000000006a270000000000006af70000
-
-	/* x^161856 mod p(x), x^161792 mod p(x) */
-	.octa 0x000000006685000000000000e5210000
-
-	/* x^160832 mod p(x), x^160768 mod p(x) */
-	.octa 0x0000000062da00000000000008290000
-
-	/* x^159808 mod p(x), x^159744 mod p(x) */
-	.octa 0x00000000bb4b000000000000e4d00000
-
-	/* x^158784 mod p(x), x^158720 mod p(x) */
-	.octa 0x00000000d2490000000000004ae10000
-
-	/* x^157760 mod p(x), x^157696 mod p(x) */
-	.octa 0x00000000c85b00000000000000e70000
-
-	/* x^156736 mod p(x), x^156672 mod p(x) */
-	.octa 0x00000000c37a00000000000015650000
-
-	/* x^155712 mod p(x), x^155648 mod p(x) */
-	.octa 0x0000000018530000000000001c2f0000
-
-	/* x^154688 mod p(x), x^154624 mod p(x) */
-	.octa 0x00000000b46600000000000037bd0000
-
-	/* x^153664 mod p(x), x^153600 mod p(x) */
-	.octa 0x00000000439b00000000000012190000
-
-	/* x^152640 mod p(x), x^152576 mod p(x) */
-	.octa 0x00000000b1260000000000005ece0000
-
-	/* x^151616 mod p(x), x^151552 mod p(x) */
-	.octa 0x00000000d8110000000000002a5e0000
-
-	/* x^150592 mod p(x), x^150528 mod p(x) */
-	.octa 0x00000000099f00000000000052330000
-
-	/* x^149568 mod p(x), x^149504 mod p(x) */
-	.octa 0x00000000f9f9000000000000f9120000
-
-	/* x^148544 mod p(x), x^148480 mod p(x) */
-	.octa 0x000000005cc00000000000000ddc0000
-
-	/* x^147520 mod p(x), x^147456 mod p(x) */
-	.octa 0x00000000343b00000000000012200000
-
-	/* x^146496 mod p(x), x^146432 mod p(x) */
-	.octa 0x000000009222000000000000d12b0000
-
-	/* x^145472 mod p(x), x^145408 mod p(x) */
-	.octa 0x00000000d781000000000000eb2d0000
-
-	/* x^144448 mod p(x), x^144384 mod p(x) */
-	.octa 0x000000000bf400000000000058970000
-
-	/* x^143424 mod p(x), x^143360 mod p(x) */
-	.octa 0x00000000094200000000000013690000
-
-	/* x^142400 mod p(x), x^142336 mod p(x) */
-	.octa 0x00000000d55100000000000051950000
-
-	/* x^141376 mod p(x), x^141312 mod p(x) */
-	.octa 0x000000008f11000000000000954b0000
-
-	/* x^140352 mod p(x), x^140288 mod p(x) */
-	.octa 0x00000000140f000000000000b29e0000
-
-	/* x^139328 mod p(x), x^139264 mod p(x) */
-	.octa 0x00000000c6db000000000000db5d0000
-
-	/* x^138304 mod p(x), x^138240 mod p(x) */
-	.octa 0x00000000715b000000000000dfaf0000
-
-	/* x^137280 mod p(x), x^137216 mod p(x) */
-	.octa 0x000000000dea000000000000e3b60000
-
-	/* x^136256 mod p(x), x^136192 mod p(x) */
-	.octa 0x000000006f94000000000000ddaf0000
-
-	/* x^135232 mod p(x), x^135168 mod p(x) */
-	.octa 0x0000000024e1000000000000e4f70000
-
-	/* x^134208 mod p(x), x^134144 mod p(x) */
-	.octa 0x000000008810000000000000aa110000
-
-	/* x^133184 mod p(x), x^133120 mod p(x) */
-	.octa 0x0000000030c2000000000000a8e60000
-
-	/* x^132160 mod p(x), x^132096 mod p(x) */
-	.octa 0x00000000e6d0000000000000ccf30000
-
-	/* x^131136 mod p(x), x^131072 mod p(x) */
-	.octa 0x000000004da000000000000079bf0000
-
-	/* x^130112 mod p(x), x^130048 mod p(x) */
-	.octa 0x000000007759000000000000b3a30000
-
-	/* x^129088 mod p(x), x^129024 mod p(x) */
-	.octa 0x00000000597400000000000028790000
-
-	/* x^128064 mod p(x), x^128000 mod p(x) */
-	.octa 0x000000007acd000000000000b5820000
-
-	/* x^127040 mod p(x), x^126976 mod p(x) */
-	.octa 0x00000000e6e400000000000026ad0000
-
-	/* x^126016 mod p(x), x^125952 mod p(x) */
-	.octa 0x000000006d49000000000000985b0000
-
-	/* x^124992 mod p(x), x^124928 mod p(x) */
-	.octa 0x000000000f0800000000000011520000
-
-	/* x^123968 mod p(x), x^123904 mod p(x) */
-	.octa 0x000000002c7f000000000000846c0000
-
-	/* x^122944 mod p(x), x^122880 mod p(x) */
-	.octa 0x000000005ce7000000000000ae1d0000
-
-	/* x^121920 mod p(x), x^121856 mod p(x) */
-	.octa 0x00000000d4cb000000000000e21d0000
-
-	/* x^120896 mod p(x), x^120832 mod p(x) */
-	.octa 0x000000003a2300000000000019bb0000
-
-	/* x^119872 mod p(x), x^119808 mod p(x) */
-	.octa 0x000000000e1700000000000095290000
-
-	/* x^118848 mod p(x), x^118784 mod p(x) */
-	.octa 0x000000006e6400000000000050d20000
-
-	/* x^117824 mod p(x), x^117760 mod p(x) */
-	.octa 0x000000008d5c0000000000000cd10000
-
-	/* x^116800 mod p(x), x^116736 mod p(x) */
-	.octa 0x00000000ef310000000000007b570000
-
-	/* x^115776 mod p(x), x^115712 mod p(x) */
-	.octa 0x00000000645d00000000000053d60000
-
-	/* x^114752 mod p(x), x^114688 mod p(x) */
-	.octa 0x0000000018fc00000000000077510000
-
-	/* x^113728 mod p(x), x^113664 mod p(x) */
-	.octa 0x000000000cb3000000000000a7b70000
-
-	/* x^112704 mod p(x), x^112640 mod p(x) */
-	.octa 0x00000000991b000000000000d0780000
-
-	/* x^111680 mod p(x), x^111616 mod p(x) */
-	.octa 0x00000000845a000000000000be3c0000
-
-	/* x^110656 mod p(x), x^110592 mod p(x) */
-	.octa 0x00000000d3a9000000000000df020000
-
-	/* x^109632 mod p(x), x^109568 mod p(x) */
-	.octa 0x0000000017d7000000000000063e0000
-
-	/* x^108608 mod p(x), x^108544 mod p(x) */
-	.octa 0x000000007a860000000000008ab40000
-
-	/* x^107584 mod p(x), x^107520 mod p(x) */
-	.octa 0x00000000fd7c000000000000c7bd0000
-
-	/* x^106560 mod p(x), x^106496 mod p(x) */
-	.octa 0x00000000a56b000000000000efd60000
-
-	/* x^105536 mod p(x), x^105472 mod p(x) */
-	.octa 0x0000000010e400000000000071380000
-
-	/* x^104512 mod p(x), x^104448 mod p(x) */
-	.octa 0x00000000994500000000000004d30000
-
-	/* x^103488 mod p(x), x^103424 mod p(x) */
-	.octa 0x00000000b83c0000000000003b0e0000
-
-	/* x^102464 mod p(x), x^102400 mod p(x) */
-	.octa 0x00000000d6c10000000000008b020000
-
-	/* x^101440 mod p(x), x^101376 mod p(x) */
-	.octa 0x000000009efc000000000000da940000
-
-	/* x^100416 mod p(x), x^100352 mod p(x) */
-	.octa 0x000000005e87000000000000f9f70000
-
-	/* x^99392 mod p(x), x^99328 mod p(x) */
-	.octa 0x000000006c9b00000000000045e40000
-
-	/* x^98368 mod p(x), x^98304 mod p(x) */
-	.octa 0x00000000178a00000000000083940000
-
-	/* x^97344 mod p(x), x^97280 mod p(x) */
-	.octa 0x00000000f0c8000000000000f0a00000
-
-	/* x^96320 mod p(x), x^96256 mod p(x) */
-	.octa 0x00000000f699000000000000b74b0000
-
-	/* x^95296 mod p(x), x^95232 mod p(x) */
-	.octa 0x00000000316d000000000000c1cf0000
-
-	/* x^94272 mod p(x), x^94208 mod p(x) */
-	.octa 0x00000000987e00000000000072680000
-
-	/* x^93248 mod p(x), x^93184 mod p(x) */
-	.octa 0x00000000acff000000000000e0ab0000
-
-	/* x^92224 mod p(x), x^92160 mod p(x) */
-	.octa 0x00000000a1f6000000000000c5a80000
-
-	/* x^91200 mod p(x), x^91136 mod p(x) */
-	.octa 0x0000000061bd000000000000cf690000
-
-	/* x^90176 mod p(x), x^90112 mod p(x) */
-	.octa 0x00000000c9f2000000000000cbcc0000
-
-	/* x^89152 mod p(x), x^89088 mod p(x) */
-	.octa 0x000000005a33000000000000de050000
-
-	/* x^88128 mod p(x), x^88064 mod p(x) */
-	.octa 0x00000000e416000000000000ccd70000
-
-	/* x^87104 mod p(x), x^87040 mod p(x) */
-	.octa 0x0000000058930000000000002f670000
-
-	/* x^86080 mod p(x), x^86016 mod p(x) */
-	.octa 0x00000000a9d3000000000000152f0000
-
-	/* x^85056 mod p(x), x^84992 mod p(x) */
-	.octa 0x00000000c114000000000000ecc20000
-
-	/* x^84032 mod p(x), x^83968 mod p(x) */
-	.octa 0x00000000b9270000000000007c890000
-
-	/* x^83008 mod p(x), x^82944 mod p(x) */
-	.octa 0x000000002e6000000000000006ee0000
-
-	/* x^81984 mod p(x), x^81920 mod p(x) */
-	.octa 0x00000000dfc600000000000009100000
-
-	/* x^80960 mod p(x), x^80896 mod p(x) */
-	.octa 0x000000004911000000000000ad4e0000
-
-	/* x^79936 mod p(x), x^79872 mod p(x) */
-	.octa 0x00000000ae1b000000000000b04d0000
-
-	/* x^78912 mod p(x), x^78848 mod p(x) */
-	.octa 0x0000000005fa000000000000e9900000
-
-	/* x^77888 mod p(x), x^77824 mod p(x) */
-	.octa 0x0000000004a1000000000000cc6f0000
-
-	/* x^76864 mod p(x), x^76800 mod p(x) */
-	.octa 0x00000000af73000000000000ed110000
-
-	/* x^75840 mod p(x), x^75776 mod p(x) */
-	.octa 0x0000000082530000000000008f7e0000
-
-	/* x^74816 mod p(x), x^74752 mod p(x) */
-	.octa 0x00000000cfdc000000000000594f0000
-
-	/* x^73792 mod p(x), x^73728 mod p(x) */
-	.octa 0x00000000a6b6000000000000a8750000
-
-	/* x^72768 mod p(x), x^72704 mod p(x) */
-	.octa 0x00000000fd76000000000000aa0c0000
-
-	/* x^71744 mod p(x), x^71680 mod p(x) */
-	.octa 0x0000000006f500000000000071db0000
-
-	/* x^70720 mod p(x), x^70656 mod p(x) */
-	.octa 0x0000000037ca000000000000ab0c0000
-
-	/* x^69696 mod p(x), x^69632 mod p(x) */
-	.octa 0x00000000d7ab000000000000b7a00000
-
-	/* x^68672 mod p(x), x^68608 mod p(x) */
-	.octa 0x00000000440800000000000090d30000
-
-	/* x^67648 mod p(x), x^67584 mod p(x) */
-	.octa 0x00000000186100000000000054730000
-
-	/* x^66624 mod p(x), x^66560 mod p(x) */
-	.octa 0x000000007368000000000000a3a20000
-
-	/* x^65600 mod p(x), x^65536 mod p(x) */
-	.octa 0x0000000026d0000000000000f9040000
-
-	/* x^64576 mod p(x), x^64512 mod p(x) */
-	.octa 0x00000000fe770000000000009c0a0000
-
-	/* x^63552 mod p(x), x^63488 mod p(x) */
-	.octa 0x000000002cba000000000000d1e70000
-
-	/* x^62528 mod p(x), x^62464 mod p(x) */
-	.octa 0x00000000f8bd0000000000005ac10000
-
-	/* x^61504 mod p(x), x^61440 mod p(x) */
-	.octa 0x000000007372000000000000d68d0000
-
-	/* x^60480 mod p(x), x^60416 mod p(x) */
-	.octa 0x00000000f37f00000000000089f60000
-
-	/* x^59456 mod p(x), x^59392 mod p(x) */
-	.octa 0x00000000078400000000000008a90000
-
-	/* x^58432 mod p(x), x^58368 mod p(x) */
-	.octa 0x00000000d3e400000000000042360000
-
-	/* x^57408 mod p(x), x^57344 mod p(x) */
-	.octa 0x00000000eba800000000000092d50000
-
-	/* x^56384 mod p(x), x^56320 mod p(x) */
-	.octa 0x00000000afbe000000000000b4d50000
-
-	/* x^55360 mod p(x), x^55296 mod p(x) */
-	.octa 0x00000000d8ca000000000000c9060000
-
-	/* x^54336 mod p(x), x^54272 mod p(x) */
-	.octa 0x00000000c2d00000000000008f4f0000
-
-	/* x^53312 mod p(x), x^53248 mod p(x) */
-	.octa 0x00000000373200000000000028690000
-
-	/* x^52288 mod p(x), x^52224 mod p(x) */
-	.octa 0x0000000046ae000000000000c3b30000
-
-	/* x^51264 mod p(x), x^51200 mod p(x) */
-	.octa 0x00000000b243000000000000f8700000
-
-	/* x^50240 mod p(x), x^50176 mod p(x) */
-	.octa 0x00000000f7f500000000000029eb0000
-
-	/* x^49216 mod p(x), x^49152 mod p(x) */
-	.octa 0x000000000c7e000000000000fe730000
-
-	/* x^48192 mod p(x), x^48128 mod p(x) */
-	.octa 0x00000000c38200000000000096000000
-
-	/* x^47168 mod p(x), x^47104 mod p(x) */
-	.octa 0x000000008956000000000000683c0000
-
-	/* x^46144 mod p(x), x^46080 mod p(x) */
-	.octa 0x00000000422d0000000000005f1e0000
-
-	/* x^45120 mod p(x), x^45056 mod p(x) */
-	.octa 0x00000000ac0f0000000000006f810000
-
-	/* x^44096 mod p(x), x^44032 mod p(x) */
-	.octa 0x00000000ce30000000000000031f0000
-
-	/* x^43072 mod p(x), x^43008 mod p(x) */
-	.octa 0x000000003d43000000000000455a0000
-
-	/* x^42048 mod p(x), x^41984 mod p(x) */
-	.octa 0x000000007ebe000000000000a6050000
-
-	/* x^41024 mod p(x), x^40960 mod p(x) */
-	.octa 0x00000000976e00000000000077eb0000
-
-	/* x^40000 mod p(x), x^39936 mod p(x) */
-	.octa 0x000000000872000000000000389c0000
-
-	/* x^38976 mod p(x), x^38912 mod p(x) */
-	.octa 0x000000008979000000000000c7b20000
-
-	/* x^37952 mod p(x), x^37888 mod p(x) */
-	.octa 0x000000005c1e0000000000001d870000
-
-	/* x^36928 mod p(x), x^36864 mod p(x) */
-	.octa 0x00000000aebb00000000000045810000
-
-	/* x^35904 mod p(x), x^35840 mod p(x) */
-	.octa 0x000000004f7e0000000000006d4a0000
-
-	/* x^34880 mod p(x), x^34816 mod p(x) */
-	.octa 0x00000000ea98000000000000b9200000
-
-	/* x^33856 mod p(x), x^33792 mod p(x) */
-	.octa 0x00000000f39600000000000022f20000
-
-	/* x^32832 mod p(x), x^32768 mod p(x) */
-	.octa 0x000000000bc500000000000041ca0000
-
-	/* x^31808 mod p(x), x^31744 mod p(x) */
-	.octa 0x00000000786400000000000078500000
-
-	/* x^30784 mod p(x), x^30720 mod p(x) */
-	.octa 0x00000000be970000000000009e7e0000
-
-	/* x^29760 mod p(x), x^29696 mod p(x) */
-	.octa 0x00000000dd6d000000000000a53c0000
-
-	/* x^28736 mod p(x), x^28672 mod p(x) */
-	.octa 0x000000004c3f00000000000039340000
-
-	/* x^27712 mod p(x), x^27648 mod p(x) */
-	.octa 0x0000000093a4000000000000b58e0000
-
-	/* x^26688 mod p(x), x^26624 mod p(x) */
-	.octa 0x0000000050fb00000000000062d40000
-
-	/* x^25664 mod p(x), x^25600 mod p(x) */
-	.octa 0x00000000f505000000000000a26f0000
-
-	/* x^24640 mod p(x), x^24576 mod p(x) */
-	.octa 0x0000000064f900000000000065e60000
-
-	/* x^23616 mod p(x), x^23552 mod p(x) */
-	.octa 0x00000000e8c2000000000000aad90000
-
-	/* x^22592 mod p(x), x^22528 mod p(x) */
-	.octa 0x00000000720b000000000000a3b00000
-
-	/* x^21568 mod p(x), x^21504 mod p(x) */
-	.octa 0x00000000e992000000000000d2680000
-
-	/* x^20544 mod p(x), x^20480 mod p(x) */
-	.octa 0x000000009132000000000000cf4c0000
-
-	/* x^19520 mod p(x), x^19456 mod p(x) */
-	.octa 0x00000000608a00000000000076610000
-
-	/* x^18496 mod p(x), x^18432 mod p(x) */
-	.octa 0x000000009948000000000000fb9f0000
-
-	/* x^17472 mod p(x), x^17408 mod p(x) */
-	.octa 0x00000000173000000000000003770000
-
-	/* x^16448 mod p(x), x^16384 mod p(x) */
-	.octa 0x000000006fe300000000000004880000
-
-	/* x^15424 mod p(x), x^15360 mod p(x) */
-	.octa 0x00000000e15300000000000056a70000
-
-	/* x^14400 mod p(x), x^14336 mod p(x) */
-	.octa 0x0000000092d60000000000009dfd0000
-
-	/* x^13376 mod p(x), x^13312 mod p(x) */
-	.octa 0x0000000002fd00000000000074c80000
-
-	/* x^12352 mod p(x), x^12288 mod p(x) */
-	.octa 0x00000000c78b000000000000a3ec0000
-
-	/* x^11328 mod p(x), x^11264 mod p(x) */
-	.octa 0x000000009262000000000000b3530000
-
-	/* x^10304 mod p(x), x^10240 mod p(x) */
-	.octa 0x0000000084f200000000000047bf0000
-
-	/* x^9280 mod p(x), x^9216 mod p(x) */
-	.octa 0x0000000067ee000000000000e97c0000
-
-	/* x^8256 mod p(x), x^8192 mod p(x) */
-	.octa 0x00000000535b00000000000091e10000
-
-	/* x^7232 mod p(x), x^7168 mod p(x) */
-	.octa 0x000000007ebb00000000000055060000
-
-	/* x^6208 mod p(x), x^6144 mod p(x) */
-	.octa 0x00000000c6a1000000000000fd360000
-
-	/* x^5184 mod p(x), x^5120 mod p(x) */
-	.octa 0x000000001be500000000000055860000
-
-	/* x^4160 mod p(x), x^4096 mod p(x) */
-	.octa 0x00000000ae0e0000000000005bd00000
-
-	/* x^3136 mod p(x), x^3072 mod p(x) */
-	.octa 0x0000000022040000000000008db20000
-
-	/* x^2112 mod p(x), x^2048 mod p(x) */
-	.octa 0x00000000c9eb000000000000efe20000
-
-	/* x^1088 mod p(x), x^1024 mod p(x) */
-	.octa 0x0000000039b400000000000051d10000
-
-.short_constants:
-
-	/* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */
-	/* x^2048 mod p(x), x^2016 mod p(x), x^1984 mod p(x), x^1952 mod p(x) */
-	.octa 0xefe20000dccf00009440000033590000
-
-	/* x^1920 mod p(x), x^1888 mod p(x), x^1856 mod p(x), x^1824 mod p(x) */
-	.octa 0xee6300002f3f000062180000e0ed0000
-
-	/* x^1792 mod p(x), x^1760 mod p(x), x^1728 mod p(x), x^1696 mod p(x) */
-	.octa 0xcf5f000017ef0000ccbe000023d30000
-
-	/* x^1664 mod p(x), x^1632 mod p(x), x^1600 mod p(x), x^1568 mod p(x) */
-	.octa 0x6d0c0000a30e00000920000042630000
-
-	/* x^1536 mod p(x), x^1504 mod p(x), x^1472 mod p(x), x^1440 mod p(x) */
-	.octa 0x21d30000932b0000a7a00000efcc0000
-
-	/* x^1408 mod p(x), x^1376 mod p(x), x^1344 mod p(x), x^1312 mod p(x) */
-	.octa 0x10be00000b310000666f00000d1c0000
-
-	/* x^1280 mod p(x), x^1248 mod p(x), x^1216 mod p(x), x^1184 mod p(x) */
-	.octa 0x1f240000ce9e0000caad0000589e0000
-
-	/* x^1152 mod p(x), x^1120 mod p(x), x^1088 mod p(x), x^1056 mod p(x) */
-	.octa 0x29610000d02b000039b400007cf50000
-
-	/* x^1024 mod p(x), x^992 mod p(x), x^960 mod p(x), x^928 mod p(x) */
-	.octa 0x51d100009d9d00003c0e0000bfd60000
-
-	/* x^896 mod p(x), x^864 mod p(x), x^832 mod p(x), x^800 mod p(x) */
-	.octa 0xda390000ceae000013830000713c0000
-
-	/* x^768 mod p(x), x^736 mod p(x), x^704 mod p(x), x^672 mod p(x) */
-	.octa 0xb67800001e16000085c0000080a60000
-
-	/* x^640 mod p(x), x^608 mod p(x), x^576 mod p(x), x^544 mod p(x) */
-	.octa 0x0db40000f7f90000371d0000e6580000
-
-	/* x^512 mod p(x), x^480 mod p(x), x^448 mod p(x), x^416 mod p(x) */
-	.octa 0x87e70000044c0000aadb0000a4970000
-
-	/* x^384 mod p(x), x^352 mod p(x), x^320 mod p(x), x^288 mod p(x) */
-	.octa 0x1f990000ad180000d8b30000e7b50000
-
-	/* x^256 mod p(x), x^224 mod p(x), x^192 mod p(x), x^160 mod p(x) */
-	.octa 0xbe6c00006ee300004c1a000006df0000
-
-	/* x^128 mod p(x), x^96 mod p(x), x^64 mod p(x), x^32 mod p(x) */
-	.octa 0xfb0b00002d560000136800008bb70000
-
-
-.barrett_constants:
-	/* Barrett constant m - (4^32)/n */
-	.octa 0x000000000000000000000001f65a57f8	/* x^64 div p(x) */
-	/* Barrett constant n */
-	.octa 0x0000000000000000000000018bb70000
-
-#define CRC_FUNCTION_NAME __crct10dif_vpmsum
-#include "crc32-vpmsum_core.S"
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
deleted file mode 100644
index 1dc8b6915178..000000000000
--- a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
+++ /dev/null
@@ -1,126 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Calculate a CRC T10-DIF with vpmsum acceleration
- *
- * Copyright 2017, Daniel Axtens, IBM Corporation.
- * [based on crc32c-vpmsum_glue.c]
- */
-
-#include <linux/crc-t10dif.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/cpufeature.h>
-#include <asm/simd.h>
-#include <asm/switch_to.h>
-
-#define VMX_ALIGN		16
-#define VMX_ALIGN_MASK		(VMX_ALIGN-1)
-
-#define VECTOR_BREAKPOINT	64
-
-u32 __crct10dif_vpmsum(u32 crc, unsigned char const *p, size_t len);
-
-static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len)
-{
-	unsigned int prealign;
-	unsigned int tail;
-	u32 crc = crci;
-
-	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable())
-		return crc_t10dif_generic(crc, p, len);
-
-	if ((unsigned long)p & VMX_ALIGN_MASK) {
-		prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
-		crc = crc_t10dif_generic(crc, p, prealign);
-		len -= prealign;
-		p += prealign;
-	}
-
-	if (len & ~VMX_ALIGN_MASK) {
-		crc <<= 16;
-		preempt_disable();
-		pagefault_disable();
-		enable_kernel_altivec();
-		crc = __crct10dif_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
-		disable_kernel_altivec();
-		pagefault_enable();
-		preempt_enable();
-		crc >>= 16;
-	}
-
-	tail = len & VMX_ALIGN_MASK;
-	if (tail) {
-		p += len & ~VMX_ALIGN_MASK;
-		crc = crc_t10dif_generic(crc, p, tail);
-	}
-
-	return crc & 0xffff;
-}
-
-static int crct10dif_vpmsum_init(struct shash_desc *desc)
-{
-	u16 *crc = shash_desc_ctx(desc);
-
-	*crc = 0;
-	return 0;
-}
-
-static int crct10dif_vpmsum_update(struct shash_desc *desc, const u8 *data,
-			    unsigned int length)
-{
-	u16 *crc = shash_desc_ctx(desc);
-
-	*crc = crct10dif_vpmsum(*crc, data, length);
-
-	return 0;
-}
-
-
-static int crct10dif_vpmsum_final(struct shash_desc *desc, u8 *out)
-{
-	u16 *crcp = shash_desc_ctx(desc);
-
-	*(u16 *)out = *crcp;
-	return 0;
-}
-
-static struct shash_alg alg = {
-	.init		= crct10dif_vpmsum_init,
-	.update		= crct10dif_vpmsum_update,
-	.final		= crct10dif_vpmsum_final,
-	.descsize	= CRC_T10DIF_DIGEST_SIZE,
-	.digestsize	= CRC_T10DIF_DIGEST_SIZE,
-	.base		= {
-		.cra_name		= "crct10dif",
-		.cra_driver_name	= "crct10dif-vpmsum",
-		.cra_priority		= 200,
-		.cra_blocksize		= CRC_T10DIF_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	}
-};
-
-static int __init crct10dif_vpmsum_mod_init(void)
-{
-	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
-		return -ENODEV;
-
-	return crypto_register_shash(&alg);
-}
-
-static void __exit crct10dif_vpmsum_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crct10dif_vpmsum_mod_init);
-module_exit(crct10dif_vpmsum_mod_fini);
-
-MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
-MODULE_DESCRIPTION("CRCT10DIF using vector polynomial multiply-sum instructions");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CRYPTO("crct10dif");
-MODULE_ALIAS_CRYPTO("crct10dif-vpmsum");
diff --git a/arch/powerpc/crypto/ghash.c b/arch/powerpc/crypto/ghash.c
new file mode 100644
index 000000000000..7308735bdb33
--- /dev/null
+++ b/arch/powerpc/crypto/ghash.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * GHASH routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015, 2019 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ *
+ * Extended by Daniel Axtens <dja@axtens.net> to replace the fallback
+ * mechanism. The new approach is based on arm64 code, which is:
+ *   Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include "aesp8-ppc.h"
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/gf128mul.h>
+#include <crypto/ghash.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+
+void gcm_init_p8(u128 htable[16], const u64 Xi[2]);
+void gcm_gmult_p8(u64 Xi[2], const u128 htable[16]);
+void gcm_ghash_p8(u64 Xi[2], const u128 htable[16],
+		  const u8 *in, size_t len);
+
+struct p8_ghash_ctx {
+	/* key used by vector asm */
+	u128 htable[16];
+	/* key used by software fallback */
+	be128 key;
+};
+
+struct p8_ghash_desc_ctx {
+	u64 shash[2];
+};
+
+static int p8_ghash_init(struct shash_desc *desc)
+{
+	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	memset(dctx->shash, 0, GHASH_DIGEST_SIZE);
+	return 0;
+}
+
+static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
+			   unsigned int keylen)
+{
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(tfm));
+
+	if (keylen != GHASH_BLOCK_SIZE)
+		return -EINVAL;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_vsx();
+	gcm_init_p8(ctx->htable, (const u64 *) key);
+	disable_kernel_vsx();
+	pagefault_enable();
+	preempt_enable();
+
+	memcpy(&ctx->key, key, GHASH_BLOCK_SIZE);
+
+	return 0;
+}
+
+static inline void __ghash_block(struct p8_ghash_ctx *ctx,
+				 struct p8_ghash_desc_ctx *dctx,
+				 const u8 *src)
+{
+	if (crypto_simd_usable()) {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_vsx();
+		gcm_ghash_p8(dctx->shash, ctx->htable, src, GHASH_BLOCK_SIZE);
+		disable_kernel_vsx();
+		pagefault_enable();
+		preempt_enable();
+	} else {
+		crypto_xor((u8 *)dctx->shash, src, GHASH_BLOCK_SIZE);
+		gf128mul_lle((be128 *)dctx->shash, &ctx->key);
+	}
+}
+
+static inline int __ghash_blocks(struct p8_ghash_ctx *ctx,
+				 struct p8_ghash_desc_ctx *dctx,
+				 const u8 *src, unsigned int srclen)
+{
+	int remain = srclen - round_down(srclen, GHASH_BLOCK_SIZE);
+
+	srclen -= remain;
+	if (crypto_simd_usable()) {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_vsx();
+		gcm_ghash_p8(dctx->shash, ctx->htable,
+				src, srclen);
+		disable_kernel_vsx();
+		pagefault_enable();
+		preempt_enable();
+	} else {
+		do {
+			crypto_xor((u8 *)dctx->shash, src, GHASH_BLOCK_SIZE);
+			gf128mul_lle((be128 *)dctx->shash, &ctx->key);
+			srclen -= GHASH_BLOCK_SIZE;
+			src += GHASH_BLOCK_SIZE;
+		} while (srclen);
+	}
+
+	return remain;
+}
+
+static int p8_ghash_update(struct shash_desc *desc,
+			   const u8 *src, unsigned int srclen)
+{
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	return __ghash_blocks(ctx, dctx, src, srclen);
+}
+
+static int p8_ghash_finup(struct shash_desc *desc, const u8 *src,
+			  unsigned int len, u8 *out)
+{
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (len) {
+		u8 buf[GHASH_BLOCK_SIZE] = {};
+
+		memcpy(buf, src, len);
+		__ghash_block(ctx, dctx, buf);
+		memzero_explicit(buf, sizeof(buf));
+	}
+	memcpy(out, dctx->shash, GHASH_DIGEST_SIZE);
+	return 0;
+}
+
+struct shash_alg p8_ghash_alg = {
+	.digestsize = GHASH_DIGEST_SIZE,
+	.init = p8_ghash_init,
+	.update = p8_ghash_update,
+	.finup = p8_ghash_finup,
+	.setkey = p8_ghash_setkey,
+	.descsize = sizeof(struct p8_ghash_desc_ctx),
+	.base = {
+		 .cra_name = "ghash",
+		 .cra_driver_name = "p8_ghash",
+		 .cra_priority = 1000,
+		 .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
+		 .cra_blocksize = GHASH_BLOCK_SIZE,
+		 .cra_ctxsize = sizeof(struct p8_ghash_ctx),
+		 .cra_module = THIS_MODULE,
+	},
+};
diff --git a/arch/powerpc/crypto/ghashp10-ppc.pl b/arch/powerpc/crypto/ghashp10-ppc.pl
new file mode 100644
index 000000000000..27a6b0bec645
--- /dev/null
+++ b/arch/powerpc/crypto/ghashp10-ppc.pl
@@ -0,0 +1,370 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore 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.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see https://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# GHASH for PowerISA v2.07.
+#
+# July 2014
+#
+# Accurate performance measurements are problematic, because it's
+# always virtualized setup with possibly throttled processor.
+# Relative comparison is therefore more informative. This initial
+# version is ~2.1x slower than hardware-assisted AES-128-CTR, ~12x
+# faster than "4-bit" integer-only compiler-generated 64-bit code.
+# "Initial version" means that there is room for futher improvement.
+
+$flavour=shift;
+$output =shift;
+
+if ($flavour =~ /64/) {
+	$SIZE_T=8;
+	$LRSAVE=2*$SIZE_T;
+	$STU="stdu";
+	$POP="ld";
+	$PUSH="std";
+} elsif ($flavour =~ /32/) {
+	$SIZE_T=4;
+	$LRSAVE=$SIZE_T;
+	$STU="stwu";
+	$POP="lwz";
+	$PUSH="stw";
+} else { die "nonsense $flavour"; }
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}ppc-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/ppc-xlate.pl" and -f $xlate) or
+die "can't locate ppc-xlate.pl";
+
+open STDOUT,"| $^X $xlate $flavour $output" || die "can't call $xlate: $!";
+
+my ($Xip,$Htbl,$inp,$len)=map("r$_",(3..6));	# argument block
+
+my ($Xl,$Xm,$Xh,$IN)=map("v$_",(0..3));
+my ($zero,$t0,$t1,$t2,$xC2,$H,$Hh,$Hl,$lemask)=map("v$_",(4..12));
+my ($Xl1,$Xm1,$Xh1,$IN1,$H2,$H2h,$H2l)=map("v$_",(13..19));
+my $vrsave="r12";
+my ($t4,$t5,$t6) = ($Hl,$H,$Hh);
+
+$code=<<___;
+.machine	"any"
+
+.text
+
+.globl	.gcm_init_p10
+	lis		r0,0xfff0
+	li		r8,0x10
+	mfspr		$vrsave,256
+	li		r9,0x20
+	mtspr		256,r0
+	li		r10,0x30
+	lvx_u		$H,0,r4			# load H
+	le?xor		r7,r7,r7
+	le?addi		r7,r7,0x8		# need a vperm start with 08
+	le?lvsr		5,0,r7
+	le?vspltisb	6,0x0f
+	le?vxor		5,5,6			# set a b-endian mask
+	le?vperm	$H,$H,$H,5
+
+	vspltisb	$xC2,-16		# 0xf0
+	vspltisb	$t0,1			# one
+	vaddubm		$xC2,$xC2,$xC2		# 0xe0
+	vxor		$zero,$zero,$zero
+	vor		$xC2,$xC2,$t0		# 0xe1
+	vsldoi		$xC2,$xC2,$zero,15	# 0xe1...
+	vsldoi		$t1,$zero,$t0,1		# ...1
+	vaddubm		$xC2,$xC2,$xC2		# 0xc2...
+	vspltisb	$t2,7
+	vor		$xC2,$xC2,$t1		# 0xc2....01
+	vspltb		$t1,$H,0		# most significant byte
+	vsl		$H,$H,$t0		# H<<=1
+	vsrab		$t1,$t1,$t2		# broadcast carry bit
+	vand		$t1,$t1,$xC2
+	vxor		$H,$H,$t1		# twisted H
+
+	vsldoi		$H,$H,$H,8		# twist even more ...
+	vsldoi		$xC2,$zero,$xC2,8	# 0xc2.0
+	vsldoi		$Hl,$zero,$H,8		# ... and split
+	vsldoi		$Hh,$H,$zero,8
+
+	stvx_u		$xC2,0,r3		# save pre-computed table
+	stvx_u		$Hl,r8,r3
+	stvx_u		$H, r9,r3
+	stvx_u		$Hh,r10,r3
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,2,0
+	.long		0
+.size	.gcm_init_p10,.-.gcm_init_p10
+
+.globl	.gcm_init_htable
+	lis		r0,0xfff0
+	li		r8,0x10
+	mfspr		$vrsave,256
+	li		r9,0x20
+	mtspr		256,r0
+	li		r10,0x30
+	lvx_u		$H,0,r4			# load H
+
+	vspltisb	$xC2,-16		# 0xf0
+	vspltisb	$t0,1			# one
+	vaddubm		$xC2,$xC2,$xC2		# 0xe0
+	vxor		$zero,$zero,$zero
+	vor		$xC2,$xC2,$t0		# 0xe1
+	vsldoi		$xC2,$xC2,$zero,15	# 0xe1...
+	vsldoi		$t1,$zero,$t0,1		# ...1
+	vaddubm		$xC2,$xC2,$xC2		# 0xc2...
+	vspltisb	$t2,7
+	vor		$xC2,$xC2,$t1		# 0xc2....01
+	vspltb		$t1,$H,0		# most significant byte
+	vsl		$H,$H,$t0		# H<<=1
+	vsrab		$t1,$t1,$t2		# broadcast carry bit
+	vand		$t1,$t1,$xC2
+	vxor		$IN,$H,$t1		# twisted H
+
+	vsldoi		$H,$IN,$IN,8		# twist even more ...
+	vsldoi		$xC2,$zero,$xC2,8	# 0xc2.0
+	vsldoi		$Hl,$zero,$H,8		# ... and split
+	vsldoi		$Hh,$H,$zero,8
+
+	stvx_u		$xC2,0,r3		# save pre-computed table
+	stvx_u		$Hl,r8,r3
+	li		r8,0x40
+	stvx_u		$H, r9,r3
+	li		r9,0x50
+	stvx_u		$Hh,r10,r3
+	li		r10,0x60
+
+	vpmsumd		$Xl,$IN,$Hl		# H.lo·H.lo
+	vpmsumd		$Xm,$IN,$H		# H.hi·H.lo+H.lo·H.hi
+	vpmsumd		$Xh,$IN,$Hh		# H.hi·H.hi
+
+	vpmsumd		$t2,$Xl,$xC2		# 1st reduction phase
+
+	vsldoi		$t0,$Xm,$zero,8
+	vsldoi		$t1,$zero,$Xm,8
+	vxor		$Xl,$Xl,$t0
+	vxor		$Xh,$Xh,$t1
+
+	vsldoi		$Xl,$Xl,$Xl,8
+	vxor		$Xl,$Xl,$t2
+
+	vsldoi		$t1,$Xl,$Xl,8		# 2nd reduction phase
+	vpmsumd		$Xl,$Xl,$xC2
+	vxor		$t1,$t1,$Xh
+	vxor		$IN1,$Xl,$t1
+
+	vsldoi		$H2,$IN1,$IN1,8
+	vsldoi		$H2l,$zero,$H2,8
+	vsldoi		$H2h,$H2,$zero,8
+
+	stvx_u		$H2l,r8,r3		# save H^2
+	li		r8,0x70
+	stvx_u		$H2,r9,r3
+	li		r9,0x80
+	stvx_u		$H2h,r10,r3
+	li		r10,0x90
+
+	vpmsumd		$Xl,$IN,$H2l		# H.lo·H^2.lo
+	 vpmsumd	$Xl1,$IN1,$H2l		# H^2.lo·H^2.lo
+	vpmsumd		$Xm,$IN,$H2		# H.hi·H^2.lo+H.lo·H^2.hi
+	 vpmsumd	$Xm1,$IN1,$H2		# H^2.hi·H^2.lo+H^2.lo·H^2.hi
+	vpmsumd		$Xh,$IN,$H2h		# H.hi·H^2.hi
+	 vpmsumd	$Xh1,$IN1,$H2h		# H^2.hi·H^2.hi
+
+	vpmsumd		$t2,$Xl,$xC2		# 1st reduction phase
+	 vpmsumd	$t6,$Xl1,$xC2		# 1st reduction phase
+
+	vsldoi		$t0,$Xm,$zero,8
+	vsldoi		$t1,$zero,$Xm,8
+	 vsldoi		$t4,$Xm1,$zero,8
+	 vsldoi		$t5,$zero,$Xm1,8
+	vxor		$Xl,$Xl,$t0
+	vxor		$Xh,$Xh,$t1
+	 vxor		$Xl1,$Xl1,$t4
+	 vxor		$Xh1,$Xh1,$t5
+
+	vsldoi		$Xl,$Xl,$Xl,8
+	 vsldoi		$Xl1,$Xl1,$Xl1,8
+	vxor		$Xl,$Xl,$t2
+	 vxor		$Xl1,$Xl1,$t6
+
+	vsldoi		$t1,$Xl,$Xl,8		# 2nd reduction phase
+	 vsldoi		$t5,$Xl1,$Xl1,8		# 2nd reduction phase
+	vpmsumd		$Xl,$Xl,$xC2
+	 vpmsumd	$Xl1,$Xl1,$xC2
+	vxor		$t1,$t1,$Xh
+	 vxor		$t5,$t5,$Xh1
+	vxor		$Xl,$Xl,$t1
+	 vxor		$Xl1,$Xl1,$t5
+
+	vsldoi		$H,$Xl,$Xl,8
+	 vsldoi		$H2,$Xl1,$Xl1,8
+	vsldoi		$Hl,$zero,$H,8
+	vsldoi		$Hh,$H,$zero,8
+	 vsldoi		$H2l,$zero,$H2,8
+	 vsldoi		$H2h,$H2,$zero,8
+
+	stvx_u		$Hl,r8,r3		# save H^3
+	li		r8,0xa0
+	stvx_u		$H,r9,r3
+	li		r9,0xb0
+	stvx_u		$Hh,r10,r3
+	li		r10,0xc0
+	 stvx_u		$H2l,r8,r3		# save H^4
+	 stvx_u		$H2,r9,r3
+	 stvx_u		$H2h,r10,r3
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,2,0
+	.long		0
+.size	.gcm_init_htable,.-.gcm_init_htable
+
+.globl	.gcm_gmult_p10
+	lis		r0,0xfff8
+	li		r8,0x10
+	mfspr		$vrsave,256
+	li		r9,0x20
+	mtspr		256,r0
+	li		r10,0x30
+	lvx_u		$IN,0,$Xip		# load Xi
+
+	lvx_u		$Hl,r8,$Htbl		# load pre-computed table
+	 le?lvsl	$lemask,r0,r0
+	lvx_u		$H, r9,$Htbl
+	 le?vspltisb	$t0,0x07
+	lvx_u		$Hh,r10,$Htbl
+	 le?vxor	$lemask,$lemask,$t0
+	lvx_u		$xC2,0,$Htbl
+	 le?vperm	$IN,$IN,$IN,$lemask
+	vxor		$zero,$zero,$zero
+
+	vpmsumd		$Xl,$IN,$Hl		# H.lo·Xi.lo
+	vpmsumd		$Xm,$IN,$H		# H.hi·Xi.lo+H.lo·Xi.hi
+	vpmsumd		$Xh,$IN,$Hh		# H.hi·Xi.hi
+
+	vpmsumd		$t2,$Xl,$xC2		# 1st phase
+
+	vsldoi		$t0,$Xm,$zero,8
+	vsldoi		$t1,$zero,$Xm,8
+	vxor		$Xl,$Xl,$t0
+	vxor		$Xh,$Xh,$t1
+
+	vsldoi		$Xl,$Xl,$Xl,8
+	vxor		$Xl,$Xl,$t2
+
+	vsldoi		$t1,$Xl,$Xl,8		# 2nd phase
+	vpmsumd		$Xl,$Xl,$xC2
+	vxor		$t1,$t1,$Xh
+	vxor		$Xl,$Xl,$t1
+
+	le?vperm	$Xl,$Xl,$Xl,$lemask
+	stvx_u		$Xl,0,$Xip		# write out Xi
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,2,0
+	.long		0
+.size	.gcm_gmult_p10,.-.gcm_gmult_p10
+
+.globl	.gcm_ghash_p10
+	lis		r0,0xfff8
+	li		r8,0x10
+	mfspr		$vrsave,256
+	li		r9,0x20
+	mtspr		256,r0
+	li		r10,0x30
+	lvx_u		$Xl,0,$Xip		# load Xi
+
+	lvx_u		$Hl,r8,$Htbl		# load pre-computed table
+	 le?lvsl	$lemask,r0,r0
+	lvx_u		$H, r9,$Htbl
+	 le?vspltisb	$t0,0x07
+	lvx_u		$Hh,r10,$Htbl
+	 le?vxor	$lemask,$lemask,$t0
+	lvx_u		$xC2,0,$Htbl
+	 le?vperm	$Xl,$Xl,$Xl,$lemask
+	vxor		$zero,$zero,$zero
+
+	lvx_u		$IN,0,$inp
+	addi		$inp,$inp,16
+	subi		$len,$len,16
+	 le?vperm	$IN,$IN,$IN,$lemask
+	vxor		$IN,$IN,$Xl
+	b		Loop
+
+.align	5
+Loop:
+	 subic		$len,$len,16
+	vpmsumd		$Xl,$IN,$Hl		# H.lo·Xi.lo
+	 subfe.		r0,r0,r0		# borrow?-1:0
+	vpmsumd		$Xm,$IN,$H		# H.hi·Xi.lo+H.lo·Xi.hi
+	 and		r0,r0,$len
+	vpmsumd		$Xh,$IN,$Hh		# H.hi·Xi.hi
+	 add		$inp,$inp,r0
+
+	vpmsumd		$t2,$Xl,$xC2		# 1st phase
+
+	vsldoi		$t0,$Xm,$zero,8
+	vsldoi		$t1,$zero,$Xm,8
+	vxor		$Xl,$Xl,$t0
+	vxor		$Xh,$Xh,$t1
+
+	vsldoi		$Xl,$Xl,$Xl,8
+	vxor		$Xl,$Xl,$t2
+	 lvx_u		$IN,0,$inp
+	 addi		$inp,$inp,16
+
+	vsldoi		$t1,$Xl,$Xl,8		# 2nd phase
+	vpmsumd		$Xl,$Xl,$xC2
+	 le?vperm	$IN,$IN,$IN,$lemask
+	vxor		$t1,$t1,$Xh
+	vxor		$IN,$IN,$t1
+	vxor		$IN,$IN,$Xl
+	beq		Loop			# did $len-=16 borrow?
+
+	vxor		$Xl,$Xl,$t1
+	le?vperm	$Xl,$Xl,$Xl,$lemask
+	stvx_u		$Xl,0,$Xip		# write out Xi
+
+	mtspr		256,$vrsave
+	blr
+	.long		0
+	.byte		0,12,0x14,0,0,0,4,0
+	.long		0
+.size	.gcm_ghash_p10,.-.gcm_ghash_p10
+
+.asciz  "GHASH for PowerISA 2.07, CRYPTOGAMS by <appro\@openssl.org>"
+.align  2
+___
+
+foreach (split("\n",$code)) {
+	if ($flavour =~ /le$/o) {	# little-endian
+	    s/le\?//o		or
+	    s/be\?/#be#/o;
+	} else {
+	    s/le\?/#le#/o	or
+	    s/be\?//o;
+	}
+	print $_,"\n";
+}
+
+close STDOUT; # enforce flush
diff --git a/arch/powerpc/crypto/ghashp8-ppc.pl b/arch/powerpc/crypto/ghashp8-ppc.pl
index b56603b4a893..041e633c214f 100644
--- a/arch/powerpc/crypto/ghashp8-ppc.pl
+++ b/arch/powerpc/crypto/ghashp8-ppc.pl
@@ -55,9 +55,7 @@ my ($Xip,$Htbl,$inp,$len)=map("r$_",(3..6));	# argument block
 
 my ($Xl,$Xm,$Xh,$IN)=map("v$_",(0..3));
 my ($zero,$t0,$t1,$t2,$xC2,$H,$Hh,$Hl,$lemask)=map("v$_",(4..12));
-my ($Xl1,$Xm1,$Xh1,$IN1,$H2,$H2h,$H2l)=map("v$_",(13..19));
 my $vrsave="r12";
-my ($t4,$t5,$t6) = ($Hl,$H,$Hh);
 
 $code=<<___;
 .machine	"any"
@@ -112,131 +110,6 @@ $code=<<___;
 	.long		0
 .size	.gcm_init_p8,.-.gcm_init_p8
 
-.globl	.gcm_init_htable
-	lis		r0,0xfff0
-	li		r8,0x10
-	mfspr		$vrsave,256
-	li		r9,0x20
-	mtspr		256,r0
-	li		r10,0x30
-	lvx_u		$H,0,r4			# load H
-
-	vspltisb	$xC2,-16		# 0xf0
-	vspltisb	$t0,1			# one
-	vaddubm		$xC2,$xC2,$xC2		# 0xe0
-	vxor		$zero,$zero,$zero
-	vor		$xC2,$xC2,$t0		# 0xe1
-	vsldoi		$xC2,$xC2,$zero,15	# 0xe1...
-	vsldoi		$t1,$zero,$t0,1		# ...1
-	vaddubm		$xC2,$xC2,$xC2		# 0xc2...
-	vspltisb	$t2,7
-	vor		$xC2,$xC2,$t1		# 0xc2....01
-	vspltb		$t1,$H,0		# most significant byte
-	vsl		$H,$H,$t0		# H<<=1
-	vsrab		$t1,$t1,$t2		# broadcast carry bit
-	vand		$t1,$t1,$xC2
-	vxor		$IN,$H,$t1		# twisted H
-
-	vsldoi		$H,$IN,$IN,8		# twist even more ...
-	vsldoi		$xC2,$zero,$xC2,8	# 0xc2.0
-	vsldoi		$Hl,$zero,$H,8		# ... and split
-	vsldoi		$Hh,$H,$zero,8
-
-	stvx_u		$xC2,0,r3		# save pre-computed table
-	stvx_u		$Hl,r8,r3
-	li		r8,0x40
-	stvx_u		$H, r9,r3
-	li		r9,0x50
-	stvx_u		$Hh,r10,r3
-	li		r10,0x60
-
-	vpmsumd		$Xl,$IN,$Hl		# H.lo·H.lo
-	vpmsumd		$Xm,$IN,$H		# H.hi·H.lo+H.lo·H.hi
-	vpmsumd		$Xh,$IN,$Hh		# H.hi·H.hi
-
-	vpmsumd		$t2,$Xl,$xC2		# 1st reduction phase
-
-	vsldoi		$t0,$Xm,$zero,8
-	vsldoi		$t1,$zero,$Xm,8
-	vxor		$Xl,$Xl,$t0
-	vxor		$Xh,$Xh,$t1
-
-	vsldoi		$Xl,$Xl,$Xl,8
-	vxor		$Xl,$Xl,$t2
-
-	vsldoi		$t1,$Xl,$Xl,8		# 2nd reduction phase
-	vpmsumd		$Xl,$Xl,$xC2
-	vxor		$t1,$t1,$Xh
-	vxor		$IN1,$Xl,$t1
-
-	vsldoi		$H2,$IN1,$IN1,8
-	vsldoi		$H2l,$zero,$H2,8
-	vsldoi		$H2h,$H2,$zero,8
-
-	stvx_u		$H2l,r8,r3		# save H^2
-	li		r8,0x70
-	stvx_u		$H2,r9,r3
-	li		r9,0x80
-	stvx_u		$H2h,r10,r3
-	li		r10,0x90
-
-	vpmsumd		$Xl,$IN,$H2l		# H.lo·H^2.lo
-	 vpmsumd	$Xl1,$IN1,$H2l		# H^2.lo·H^2.lo
-	vpmsumd		$Xm,$IN,$H2		# H.hi·H^2.lo+H.lo·H^2.hi
-	 vpmsumd	$Xm1,$IN1,$H2		# H^2.hi·H^2.lo+H^2.lo·H^2.hi
-	vpmsumd		$Xh,$IN,$H2h		# H.hi·H^2.hi
-	 vpmsumd	$Xh1,$IN1,$H2h		# H^2.hi·H^2.hi
-
-	vpmsumd		$t2,$Xl,$xC2		# 1st reduction phase
-	 vpmsumd	$t6,$Xl1,$xC2		# 1st reduction phase
-
-	vsldoi		$t0,$Xm,$zero,8
-	vsldoi		$t1,$zero,$Xm,8
-	 vsldoi		$t4,$Xm1,$zero,8
-	 vsldoi		$t5,$zero,$Xm1,8
-	vxor		$Xl,$Xl,$t0
-	vxor		$Xh,$Xh,$t1
-	 vxor		$Xl1,$Xl1,$t4
-	 vxor		$Xh1,$Xh1,$t5
-
-	vsldoi		$Xl,$Xl,$Xl,8
-	 vsldoi		$Xl1,$Xl1,$Xl1,8
-	vxor		$Xl,$Xl,$t2
-	 vxor		$Xl1,$Xl1,$t6
-
-	vsldoi		$t1,$Xl,$Xl,8		# 2nd reduction phase
-	 vsldoi		$t5,$Xl1,$Xl1,8		# 2nd reduction phase
-	vpmsumd		$Xl,$Xl,$xC2
-	 vpmsumd	$Xl1,$Xl1,$xC2
-	vxor		$t1,$t1,$Xh
-	 vxor		$t5,$t5,$Xh1
-	vxor		$Xl,$Xl,$t1
-	 vxor		$Xl1,$Xl1,$t5
-
-	vsldoi		$H,$Xl,$Xl,8
-	 vsldoi		$H2,$Xl1,$Xl1,8
-	vsldoi		$Hl,$zero,$H,8
-	vsldoi		$Hh,$H,$zero,8
-	 vsldoi		$H2l,$zero,$H2,8
-	 vsldoi		$H2h,$H2,$zero,8
-
-	stvx_u		$Hl,r8,r3		# save H^3
-	li		r8,0xa0
-	stvx_u		$H,r9,r3
-	li		r9,0xb0
-	stvx_u		$Hh,r10,r3
-	li		r10,0xc0
-	 stvx_u		$H2l,r8,r3		# save H^4
-	 stvx_u		$H2,r9,r3
-	 stvx_u		$H2h,r10,r3
-
-	mtspr		256,$vrsave
-	blr
-	.long		0
-	.byte		0,12,0x14,0,0,0,2,0
-	.long		0
-.size	.gcm_init_htable,.-.gcm_init_htable
-
 .globl	.gcm_gmult_p8
 	lis		r0,0xfff8
 	li		r8,0x10
diff --git a/arch/powerpc/crypto/md5-asm.S b/arch/powerpc/crypto/md5-asm.S
deleted file mode 100644
index fa6bc440cf4a..000000000000
--- a/arch/powerpc/crypto/md5-asm.S
+++ /dev/null
@@ -1,235 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Fast MD5 implementation for PPC
- *
- * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- */
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/asm-compat.h>
-
-#define rHP	r3
-#define rWP	r4
-
-#define rH0	r0
-#define rH1	r6
-#define rH2	r7
-#define rH3	r5
-
-#define rW00	r8
-#define rW01	r9
-#define rW02	r10
-#define rW03	r11
-#define rW04	r12
-#define rW05	r14
-#define rW06	r15
-#define rW07	r16
-#define rW08	r17
-#define rW09	r18
-#define rW10	r19
-#define rW11	r20
-#define rW12	r21
-#define rW13	r22
-#define rW14	r23
-#define rW15	r24
-
-#define rT0	r25
-#define rT1	r26
-
-#define INITIALIZE \
-	PPC_STLU r1,-INT_FRAME_SIZE(r1); \
-	SAVE_GPRS(14, 26, r1)		/* push registers onto stack	*/
-
-#define FINALIZE \
-	REST_GPRS(14, 26, r1);		/* pop registers from stack	*/ \
-	addi	r1,r1,INT_FRAME_SIZE
-
-#ifdef __BIG_ENDIAN__
-#define LOAD_DATA(reg, off) \
-	lwbrx		reg,0,rWP;	/* load data			*/
-#define INC_PTR \
-	addi		rWP,rWP,4;	/* increment per word		*/
-#define NEXT_BLOCK			/* nothing to do		*/
-#else
-#define LOAD_DATA(reg, off) \
-	lwz		reg,off(rWP);	/* load data			*/
-#define INC_PTR				/* nothing to do		*/
-#define NEXT_BLOCK \
-	addi		rWP,rWP,64;	/* increment per block		*/
-#endif
-
-#define R_00_15(a, b, c, d, w0, w1, p, q, off, k0h, k0l, k1h, k1l) \
-	LOAD_DATA(w0, off)		/*    W				*/ \
-	and		rT0,b,c;	/* 1: f = b and c		*/ \
-	INC_PTR				/*    ptr++			*/ \
-	andc		rT1,d,b;	/* 1: f' = ~b and d		*/ \
-	LOAD_DATA(w1, off+4)		/*    W				*/ \
-	or		rT0,rT0,rT1;	/* 1: f = f or f'		*/ \
-	addi		w0,w0,k0l;	/* 1: wk = w + k		*/ \
-	add		a,a,rT0;	/* 1: a = a + f			*/ \
-	addis		w0,w0,k0h;	/* 1: wk = w + k'		*/ \
-	addis		w1,w1,k1h;	/* 2: wk = w + k		*/ \
-	add		a,a,w0;		/* 1: a = a + wk		*/ \
-	addi		w1,w1,k1l;	/* 2: wk = w + k'		*/ \
-	rotrwi		a,a,p;		/* 1: a = a rotl x		*/ \
-	add		d,d,w1;		/* 2: a = a + wk		*/ \
-	add		a,a,b;		/* 1: a = a + b			*/ \
-	and		rT0,a,b;	/* 2: f = b and c		*/ \
-	andc		rT1,c,a;	/* 2: f' = ~b and d		*/ \
-	or		rT0,rT0,rT1;	/* 2: f = f or f'		*/ \
-	add		d,d,rT0;	/* 2: a = a + f			*/ \
-	INC_PTR				/*    ptr++			*/ \
-	rotrwi		d,d,q;		/* 2: a = a rotl x		*/ \
-	add		d,d,a;		/* 2: a = a + b			*/
-
-#define R_16_31(a, b, c, d, w0, w1, p, q, k0h, k0l, k1h, k1l) \
-	andc		rT0,c,d;	/* 1: f = c and ~d		*/ \
-	and		rT1,b,d;	/* 1: f' = b and d		*/ \
-	addi		w0,w0,k0l;	/* 1: wk = w + k		*/ \
-	or		rT0,rT0,rT1;	/* 1: f = f or f'		*/ \
-	addis		w0,w0,k0h;	/* 1: wk = w + k'		*/ \
-	add		a,a,rT0;	/* 1: a = a + f			*/ \
-	addi		w1,w1,k1l;	/* 2: wk = w + k		*/ \
-	add		a,a,w0;		/* 1: a = a + wk		*/ \
-	addis		w1,w1,k1h;	/* 2: wk = w + k'		*/ \
-	andc		rT0,b,c;	/* 2: f = c and ~d		*/ \
-	rotrwi		a,a,p;		/* 1: a = a rotl x		*/ \
-	add		a,a,b;		/* 1: a = a + b			*/ \
-	add		d,d,w1;		/* 2: a = a + wk		*/ \
-	and		rT1,a,c;	/* 2: f' = b and d		*/ \
-	or		rT0,rT0,rT1;	/* 2: f = f or f'		*/ \
-	add		d,d,rT0;	/* 2: a = a + f			*/ \
-	rotrwi		d,d,q;		/* 2: a = a rotl x		*/ \
-	add		d,d,a;		/* 2: a = a +b			*/
-
-#define R_32_47(a, b, c, d, w0, w1, p, q, k0h, k0l, k1h, k1l) \
-	xor		rT0,b,c;	/* 1: f' = b xor c		*/ \
-	addi		w0,w0,k0l;	/* 1: wk = w + k		*/ \
-	xor		rT1,rT0,d;	/* 1: f = f xor f'		*/ \
-	addis		w0,w0,k0h;	/* 1: wk = w + k'		*/ \
-	add		a,a,rT1;	/* 1: a = a + f			*/ \
-	addi		w1,w1,k1l;	/* 2: wk = w + k		*/ \
-	add		a,a,w0;		/* 1: a = a + wk		*/ \
-	addis		w1,w1,k1h;	/* 2: wk = w + k'		*/ \
-	rotrwi		a,a,p;		/* 1: a = a rotl x		*/ \
-	add		d,d,w1;		/* 2: a = a + wk		*/ \
-	add		a,a,b;		/* 1: a = a + b			*/ \
-	xor		rT1,rT0,a;	/* 2: f = b xor f'		*/ \
-	add		d,d,rT1;	/* 2: a = a + f			*/ \
-	rotrwi		d,d,q;		/* 2: a = a rotl x		*/ \
-	add		d,d,a;		/* 2: a = a + b			*/
-
-#define R_48_63(a, b, c, d, w0, w1, p, q, k0h, k0l, k1h, k1l) \
-	addi		w0,w0,k0l;	/* 1: w = w + k			*/ \
-	orc		rT0,b,d;	/* 1: f = b or ~d		*/ \
-	addis		w0,w0,k0h;	/* 1: w = w + k'		*/ \
-	xor		rT0,rT0,c;	/* 1: f = f xor c		*/ \
-	add		a,a,w0;		/* 1: a = a + wk		*/ \
-	addi		w1,w1,k1l;	/* 2: w = w + k			*/ \
-	add		a,a,rT0;	/* 1: a = a + f			*/ \
-	addis		w1,w1,k1h;	/* 2: w = w + k'		*/ \
-	rotrwi		a,a,p;		/* 1: a = a rotl x		*/ \
-	add		a,a,b;		/* 1: a = a + b			*/ \
-	orc		rT0,a,c;	/* 2: f = b or ~d		*/ \
-	add		d,d,w1;		/* 2: a = a + wk		*/ \
-	xor		rT0,rT0,b;	/* 2: f = f xor c		*/ \
-	add		d,d,rT0;	/* 2: a = a + f			*/ \
-	rotrwi		d,d,q;		/* 2: a = a rotl x		*/ \
-	add		d,d,a;		/* 2: a = a + b			*/
-
-_GLOBAL(ppc_md5_transform)
-	INITIALIZE
-
-	mtctr		r5
-	lwz		rH0,0(rHP)
-	lwz		rH1,4(rHP)
-	lwz		rH2,8(rHP)
-	lwz		rH3,12(rHP)
-
-ppc_md5_main:
-	R_00_15(rH0, rH1, rH2, rH3, rW00, rW01, 25, 20, 0,
-		0xd76b, -23432, 0xe8c8, -18602)
-	R_00_15(rH2, rH3, rH0, rH1, rW02, rW03, 15, 10, 8,
-		0x2420, 0x70db, 0xc1be, -12562)
-	R_00_15(rH0, rH1, rH2, rH3, rW04, rW05, 25, 20, 16,
-		0xf57c, 0x0faf, 0x4788, -14806)
-	R_00_15(rH2, rH3, rH0, rH1, rW06, rW07, 15, 10, 24,
-		0xa830, 0x4613, 0xfd47, -27391)
-	R_00_15(rH0, rH1, rH2, rH3, rW08, rW09, 25, 20, 32,
-		0x6981, -26408, 0x8b45,  -2129)
-	R_00_15(rH2, rH3, rH0, rH1, rW10, rW11, 15, 10, 40,
-		0xffff, 0x5bb1, 0x895d, -10306)
-	R_00_15(rH0, rH1, rH2, rH3, rW12, rW13, 25, 20, 48,
-		0x6b90, 0x1122, 0xfd98, 0x7193)
-	R_00_15(rH2, rH3, rH0, rH1, rW14, rW15, 15, 10, 56,
-		0xa679, 0x438e, 0x49b4, 0x0821)
-
-	R_16_31(rH0, rH1, rH2, rH3, rW01, rW06, 27, 23,
-		0x0d56, 0x6e0c, 0x1810, 0x6d2d)
-	R_16_31(rH2, rH3, rH0, rH1, rW11, rW00, 18, 12,
-		0x9d02, -32109, 0x124c, 0x2332)
-	R_16_31(rH0, rH1, rH2, rH3, rW05, rW10, 27, 23,
-		0x8ea7, 0x4a33, 0x0245, -18270)
-	R_16_31(rH2, rH3, rH0, rH1, rW15, rW04, 18, 12,
-		0x8eee,  -8608, 0xf258,  -5095)
-	R_16_31(rH0, rH1, rH2, rH3, rW09, rW14, 27, 23,
-		0x969d, -10697, 0x1cbe, -15288)
-	R_16_31(rH2, rH3, rH0, rH1, rW03, rW08, 18, 12,
-		0x3317, 0x3e99, 0xdbd9, 0x7c15)
-	R_16_31(rH0, rH1, rH2, rH3, rW13, rW02, 27, 23,
-		0xac4b, 0x7772, 0xd8cf, 0x331d)
-	R_16_31(rH2, rH3, rH0, rH1, rW07, rW12, 18, 12,
-		0x6a28, 0x6dd8, 0x219a, 0x3b68)
-
-	R_32_47(rH0, rH1, rH2, rH3, rW05, rW08, 28, 21,
-		0x29cb, 0x28e5, 0x4218,  -7788)
-	R_32_47(rH2, rH3, rH0, rH1, rW11, rW14, 16,  9,
-		0x473f, 0x06d1, 0x3aae, 0x3036)
-	R_32_47(rH0, rH1, rH2, rH3, rW01, rW04, 28, 21,
-		0xaea1, -15134, 0x640b, -11295)
-	R_32_47(rH2, rH3, rH0, rH1, rW07, rW10, 16,  9,
-		0x8f4c, 0x4887, 0xbc7c, -22499)
-	R_32_47(rH0, rH1, rH2, rH3, rW13, rW00, 28, 21,
-		0x7eb8, -27199, 0x00ea, 0x6050)
-	R_32_47(rH2, rH3, rH0, rH1, rW03, rW06, 16,  9,
-		0xe01a, 0x22fe, 0x4447, 0x69c5)
-	R_32_47(rH0, rH1, rH2, rH3, rW09, rW12, 28, 21,
-		0xb7f3, 0x0253, 0x59b1, 0x4d5b)
-	R_32_47(rH2, rH3, rH0, rH1, rW15, rW02, 16,  9,
-		0x4701, -27017, 0xc7bd, -19859)
-
-	R_48_63(rH0, rH1, rH2, rH3, rW00, rW07, 26, 22,
-		0x0988,  -1462, 0x4c70, -19401)
-	R_48_63(rH2, rH3, rH0, rH1, rW14, rW05, 17, 11,
-		0xadaf,  -5221, 0xfc99, 0x66f7)
-	R_48_63(rH0, rH1, rH2, rH3, rW12, rW03, 26, 22,
-		0x7e80, -16418, 0xba1e, -25587)
-	R_48_63(rH2, rH3, rH0, rH1, rW10, rW01, 17, 11,
-		0x4130, 0x380d, 0xe0c5, 0x738d)
-	lwz		rW00,0(rHP)
-	R_48_63(rH0, rH1, rH2, rH3, rW08, rW15, 26, 22,
-		0xe837, -30770, 0xde8a, 0x69e8)
-	lwz		rW14,4(rHP)
-	R_48_63(rH2, rH3, rH0, rH1, rW06, rW13, 17, 11,
-		0x9e79, 0x260f, 0x256d, -27941)
-	lwz		rW12,8(rHP)
-	R_48_63(rH0, rH1, rH2, rH3, rW04, rW11, 26, 22,
-		0xab75, -20775, 0x4f9e, -28397)
-	lwz		rW10,12(rHP)
-	R_48_63(rH2, rH3, rH0, rH1, rW02, rW09, 17, 11,
-		0x662b, 0x7c56, 0x11b2, 0x0358)
-
-	add		rH0,rH0,rW00
-	stw		rH0,0(rHP)
-	add		rH1,rH1,rW14
-	stw		rH1,4(rHP)
-	add		rH2,rH2,rW12
-	stw		rH2,8(rHP)
-	add		rH3,rH3,rW10
-	stw		rH3,12(rHP)
-	NEXT_BLOCK
-
-	bdnz		ppc_md5_main
-
-	FINALIZE
-	blr
diff --git a/arch/powerpc/crypto/md5-glue.c b/arch/powerpc/crypto/md5-glue.c
deleted file mode 100644
index c24f605033bd..000000000000
--- a/arch/powerpc/crypto/md5-glue.c
+++ /dev/null
@@ -1,158 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Glue code for MD5 implementation for PPC assembler
- *
- * Based on generic implementation.
- *
- * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- */
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <crypto/md5.h>
-#include <asm/byteorder.h>
-
-extern void ppc_md5_transform(u32 *state, const u8 *src, u32 blocks);
-
-static inline void ppc_md5_clear_context(struct md5_state *sctx)
-{
-	int count = sizeof(struct md5_state) >> 2;
-	u32 *ptr = (u32 *)sctx;
-
-	/* make sure we can clear the fast way */
-	BUILD_BUG_ON(sizeof(struct md5_state) % 4);
-	do { *ptr++ = 0; } while (--count);
-}
-
-static int ppc_md5_init(struct shash_desc *desc)
-{
-	struct md5_state *sctx = shash_desc_ctx(desc);
-
-	sctx->hash[0] = MD5_H0;
-	sctx->hash[1] = MD5_H1;
-	sctx->hash[2] = MD5_H2;
-	sctx->hash[3] =	MD5_H3;
-	sctx->byte_count = 0;
-
-	return 0;
-}
-
-static int ppc_md5_update(struct shash_desc *desc, const u8 *data,
-			unsigned int len)
-{
-	struct md5_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->byte_count & 0x3f;
-	unsigned int avail = 64 - offset;
-	const u8 *src = data;
-
-	sctx->byte_count += len;
-
-	if (avail > len) {
-		memcpy((char *)sctx->block + offset, src, len);
-		return 0;
-	}
-
-	if (offset) {
-		memcpy((char *)sctx->block + offset, src, avail);
-		ppc_md5_transform(sctx->hash, (const u8 *)sctx->block, 1);
-		len -= avail;
-		src += avail;
-	}
-
-	if (len > 63) {
-		ppc_md5_transform(sctx->hash, src, len >> 6);
-		src += len & ~0x3f;
-		len &= 0x3f;
-	}
-
-	memcpy((char *)sctx->block, src, len);
-	return 0;
-}
-
-static int ppc_md5_final(struct shash_desc *desc, u8 *out)
-{
-	struct md5_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->byte_count & 0x3f;
-	const u8 *src = (const u8 *)sctx->block;
-	u8 *p = (u8 *)src + offset;
-	int padlen = 55 - offset;
-	__le64 *pbits = (__le64 *)((char *)sctx->block + 56);
-	__le32 *dst = (__le32 *)out;
-
-	*p++ = 0x80;
-
-	if (padlen < 0) {
-		memset(p, 0x00, padlen + sizeof (u64));
-		ppc_md5_transform(sctx->hash, src, 1);
-		p = (char *)sctx->block;
-		padlen = 56;
-	}
-
-	memset(p, 0, padlen);
-	*pbits = cpu_to_le64(sctx->byte_count << 3);
-	ppc_md5_transform(sctx->hash, src, 1);
-
-	dst[0] = cpu_to_le32(sctx->hash[0]);
-	dst[1] = cpu_to_le32(sctx->hash[1]);
-	dst[2] = cpu_to_le32(sctx->hash[2]);
-	dst[3] = cpu_to_le32(sctx->hash[3]);
-
-	ppc_md5_clear_context(sctx);
-	return 0;
-}
-
-static int ppc_md5_export(struct shash_desc *desc, void *out)
-{
-	struct md5_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int ppc_md5_import(struct shash_desc *desc, const void *in)
-{
-	struct md5_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
-}
-
-static struct shash_alg alg = {
-	.digestsize	=	MD5_DIGEST_SIZE,
-	.init		=	ppc_md5_init,
-	.update		=	ppc_md5_update,
-	.final		=	ppc_md5_final,
-	.export		=	ppc_md5_export,
-	.import		=	ppc_md5_import,
-	.descsize	=	sizeof(struct md5_state),
-	.statesize	=	sizeof(struct md5_state),
-	.base		=	{
-		.cra_name	=	"md5",
-		.cra_driver_name=	"md5-ppc",
-		.cra_priority	=	200,
-		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static int __init ppc_md5_mod_init(void)
-{
-	return crypto_register_shash(&alg);
-}
-
-static void __exit ppc_md5_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-module_init(ppc_md5_mod_init);
-module_exit(ppc_md5_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("MD5 Secure Hash Algorithm, PPC assembler");
-
-MODULE_ALIAS_CRYPTO("md5");
-MODULE_ALIAS_CRYPTO("md5-ppc");
diff --git a/arch/powerpc/crypto/sha1-powerpc-asm.S b/arch/powerpc/crypto/sha1-powerpc-asm.S
deleted file mode 100644
index f0d5ed557ab1..000000000000
--- a/arch/powerpc/crypto/sha1-powerpc-asm.S
+++ /dev/null
@@ -1,188 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * SHA-1 implementation for PowerPC.
- *
- * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
- */
-
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/asm-compat.h>
-
-#ifdef __BIG_ENDIAN__
-#define LWZ(rt, d, ra)	\
-	lwz	rt,d(ra)
-#else
-#define LWZ(rt, d, ra)	\
-	li	rt,d;	\
-	lwbrx	rt,rt,ra
-#endif
-
-/*
- * We roll the registers for T, A, B, C, D, E around on each
- * iteration; T on iteration t is A on iteration t+1, and so on.
- * We use registers 7 - 12 for this.
- */
-#define RT(t)	((((t)+5)%6)+7)
-#define RA(t)	((((t)+4)%6)+7)
-#define RB(t)	((((t)+3)%6)+7)
-#define RC(t)	((((t)+2)%6)+7)
-#define RD(t)	((((t)+1)%6)+7)
-#define RE(t)	((((t)+0)%6)+7)
-
-/* We use registers 16 - 31 for the W values */
-#define W(t)	(((t)%16)+16)
-
-#define LOADW(t)				\
-	LWZ(W(t),(t)*4,r4)
-
-#define STEPD0_LOAD(t)				\
-	andc	r0,RD(t),RB(t);		\
-	and	r6,RB(t),RC(t);		\
-	rotlwi	RT(t),RA(t),5;			\
-	or	r6,r6,r0;			\
-	add	r0,RE(t),r15;			\
-	add	RT(t),RT(t),r6;		\
-	add	r14,r0,W(t);			\
-	LWZ(W((t)+4),((t)+4)*4,r4);	\
-	rotlwi	RB(t),RB(t),30;			\
-	add	RT(t),RT(t),r14
-
-#define STEPD0_UPDATE(t)			\
-	and	r6,RB(t),RC(t);		\
-	andc	r0,RD(t),RB(t);		\
-	rotlwi	RT(t),RA(t),5;			\
-	rotlwi	RB(t),RB(t),30;			\
-	or	r6,r6,r0;			\
-	add	r0,RE(t),r15;			\
-	xor	r5,W((t)+4-3),W((t)+4-8);		\
-	add	RT(t),RT(t),r6;		\
-	xor	W((t)+4),W((t)+4-16),W((t)+4-14);	\
-	add	r0,r0,W(t);			\
-	xor	W((t)+4),W((t)+4),r5;			\
-	add	RT(t),RT(t),r0;		\
-	rotlwi	W((t)+4),W((t)+4),1
-
-#define STEPD1(t)				\
-	xor	r6,RB(t),RC(t);		\
-	rotlwi	RT(t),RA(t),5;			\
-	rotlwi	RB(t),RB(t),30;			\
-	xor	r6,r6,RD(t);			\
-	add	r0,RE(t),r15;			\
-	add	RT(t),RT(t),r6;		\
-	add	r0,r0,W(t);			\
-	add	RT(t),RT(t),r0
-
-#define STEPD1_UPDATE(t)				\
-	xor	r6,RB(t),RC(t);		\
-	rotlwi	RT(t),RA(t),5;			\
-	rotlwi	RB(t),RB(t),30;			\
-	xor	r6,r6,RD(t);			\
-	add	r0,RE(t),r15;			\
-	xor	r5,W((t)+4-3),W((t)+4-8);		\
-	add	RT(t),RT(t),r6;		\
-	xor	W((t)+4),W((t)+4-16),W((t)+4-14);	\
-	add	r0,r0,W(t);			\
-	xor	W((t)+4),W((t)+4),r5;			\
-	add	RT(t),RT(t),r0;		\
-	rotlwi	W((t)+4),W((t)+4),1
-
-#define STEPD2_UPDATE(t)			\
-	and	r6,RB(t),RC(t);		\
-	and	r0,RB(t),RD(t);		\
-	rotlwi	RT(t),RA(t),5;			\
-	or	r6,r6,r0;			\
-	rotlwi	RB(t),RB(t),30;			\
-	and	r0,RC(t),RD(t);		\
-	xor	r5,W((t)+4-3),W((t)+4-8);	\
-	or	r6,r6,r0;			\
-	xor	W((t)+4),W((t)+4-16),W((t)+4-14);	\
-	add	r0,RE(t),r15;			\
-	add	RT(t),RT(t),r6;		\
-	add	r0,r0,W(t);			\
-	xor	W((t)+4),W((t)+4),r5;		\
-	add	RT(t),RT(t),r0;		\
-	rotlwi	W((t)+4),W((t)+4),1
-
-#define STEP0LD4(t)				\
-	STEPD0_LOAD(t);				\
-	STEPD0_LOAD((t)+1);			\
-	STEPD0_LOAD((t)+2);			\
-	STEPD0_LOAD((t)+3)
-
-#define STEPUP4(t, fn)				\
-	STEP##fn##_UPDATE(t);			\
-	STEP##fn##_UPDATE((t)+1);		\
-	STEP##fn##_UPDATE((t)+2);		\
-	STEP##fn##_UPDATE((t)+3)
-
-#define STEPUP20(t, fn)				\
-	STEPUP4(t, fn);				\
-	STEPUP4((t)+4, fn);			\
-	STEPUP4((t)+8, fn);			\
-	STEPUP4((t)+12, fn);			\
-	STEPUP4((t)+16, fn)
-
-_GLOBAL(powerpc_sha_transform)
-	PPC_STLU r1,-INT_FRAME_SIZE(r1)
-	SAVE_GPRS(14, 31, r1)
-
-	/* Load up A - E */
-	lwz	RA(0),0(r3)	/* A */
-	lwz	RB(0),4(r3)	/* B */
-	lwz	RC(0),8(r3)	/* C */
-	lwz	RD(0),12(r3)	/* D */
-	lwz	RE(0),16(r3)	/* E */
-
-	LOADW(0)
-	LOADW(1)
-	LOADW(2)
-	LOADW(3)
-
-	lis	r15,0x5a82	/* K0-19 */
-	ori	r15,r15,0x7999
-	STEP0LD4(0)
-	STEP0LD4(4)
-	STEP0LD4(8)
-	STEPUP4(12, D0)
-	STEPUP4(16, D0)
-
-	lis	r15,0x6ed9	/* K20-39 */
-	ori	r15,r15,0xeba1
-	STEPUP20(20, D1)
-
-	lis	r15,0x8f1b	/* K40-59 */
-	ori	r15,r15,0xbcdc
-	STEPUP20(40, D2)
-
-	lis	r15,0xca62	/* K60-79 */
-	ori	r15,r15,0xc1d6
-	STEPUP4(60, D1)
-	STEPUP4(64, D1)
-	STEPUP4(68, D1)
-	STEPUP4(72, D1)
-	lwz	r20,16(r3)
-	STEPD1(76)
-	lwz	r19,12(r3)
-	STEPD1(77)
-	lwz	r18,8(r3)
-	STEPD1(78)
-	lwz	r17,4(r3)
-	STEPD1(79)
-
-	lwz	r16,0(r3)
-	add	r20,RE(80),r20
-	add	RD(0),RD(80),r19
-	add	RC(0),RC(80),r18
-	add	RB(0),RB(80),r17
-	add	RA(0),RA(80),r16
-	mr	RE(0),r20
-	stw	RA(0),0(r3)
-	stw	RB(0),4(r3)
-	stw	RC(0),8(r3)
-	stw	RD(0),12(r3)
-	stw	RE(0),16(r3)
-
-	REST_GPRS(14, 31, r1)
-	addi	r1,r1,INT_FRAME_SIZE
-	blr
diff --git a/arch/powerpc/crypto/sha1-spe-asm.S b/arch/powerpc/crypto/sha1-spe-asm.S
deleted file mode 100644
index 0f447523be5e..000000000000
--- a/arch/powerpc/crypto/sha1-spe-asm.S
+++ /dev/null
@@ -1,294 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Fast SHA-1 implementation for SPE instruction set (PPC)
- *
- * This code makes use of the SPE SIMD instruction set as defined in
- * http://cache.freescale.com/files/32bit/doc/ref_manual/SPEPIM.pdf
- * Implementation is based on optimization guide notes from
- * http://cache.freescale.com/files/32bit/doc/app_note/AN2665.pdf
- *
- * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- */
-
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-
-#define rHP	r3	/* pointer to hash value			*/
-#define rWP	r4	/* pointer to input				*/
-#define rKP	r5	/* pointer to constants				*/
-
-#define rW0	r14	/* 64 bit round words				*/
-#define rW1	r15
-#define rW2	r16
-#define rW3	r17
-#define rW4	r18
-#define rW5	r19
-#define rW6	r20
-#define rW7	r21
-
-#define rH0	r6	/* 32 bit hash values 				*/
-#define rH1	r7
-#define rH2	r8
-#define rH3	r9
-#define rH4	r10
-
-#define rT0	r22	/* 64 bit temporary				*/
-#define rT1	r0	/* 32 bit temporaries				*/
-#define rT2	r11
-#define rT3	r12
-
-#define rK	r23	/* 64 bit constant in volatile register		*/
-
-#define LOAD_K01
-
-#define LOAD_K11 \
-	evlwwsplat	rK,0(rKP);
-
-#define LOAD_K21 \
-	evlwwsplat	rK,4(rKP);
-
-#define LOAD_K31 \
-	evlwwsplat	rK,8(rKP);
-
-#define LOAD_K41 \
-	evlwwsplat	rK,12(rKP);
-
-#define INITIALIZE \
-	stwu		r1,-128(r1);	/* create stack frame		*/ \
-	evstdw		r14,8(r1);	/* We must save non volatile	*/ \
-	evstdw		r15,16(r1);	/* registers. Take the chance	*/ \
-	evstdw		r16,24(r1);	/* and save the SPE part too	*/ \
-	evstdw		r17,32(r1);					   \
-	evstdw		r18,40(r1);					   \
-	evstdw		r19,48(r1);					   \
-	evstdw		r20,56(r1);					   \
-	evstdw		r21,64(r1);					   \
-	evstdw		r22,72(r1);					   \
-	evstdw		r23,80(r1);
-
-
-#define FINALIZE \
-	evldw		r14,8(r1);	/* restore SPE registers	*/ \
-	evldw		r15,16(r1);					   \
-	evldw		r16,24(r1);					   \
-	evldw		r17,32(r1);					   \
-	evldw		r18,40(r1);					   \
-	evldw		r19,48(r1);					   \
-	evldw		r20,56(r1);					   \
-	evldw		r21,64(r1);					   \
-	evldw		r22,72(r1);					   \
-	evldw		r23,80(r1);					   \
-	xor		r0,r0,r0;					   \
-	stw		r0,8(r1);	/* Delete sensitive data	*/ \
-	stw		r0,16(r1);	/* that we might have pushed	*/ \
-	stw		r0,24(r1);	/* from other context that runs	*/ \
-	stw		r0,32(r1);	/* the same code. Assume that	*/ \
-	stw		r0,40(r1);	/* the lower part of the GPRs	*/ \
-	stw		r0,48(r1);	/* were already overwritten on	*/ \
-	stw		r0,56(r1);	/* the way down to here		*/ \
-	stw		r0,64(r1);					   \
-	stw		r0,72(r1);					   \
-	stw		r0,80(r1);					   \
-	addi		r1,r1,128;	/* cleanup stack frame		*/
-
-#ifdef __BIG_ENDIAN__
-#define LOAD_DATA(reg, off) \
-	lwz		reg,off(rWP);	/* load data			*/
-#define NEXT_BLOCK \
-	addi		rWP,rWP,64;	/* increment per block		*/
-#else
-#define LOAD_DATA(reg, off) \
-	lwbrx		reg,0,rWP;	/* load data			*/ \
-	addi		rWP,rWP,4;	/* increment per word		*/
-#define NEXT_BLOCK			/* nothing to do		*/
-#endif
-
-#define	R_00_15(a, b, c, d, e, w0, w1, k, off) \
-	LOAD_DATA(w0, off)		/* 1: W				*/ \
-	and		rT2,b,c;	/* 1: F' = B and C 		*/ \
-	LOAD_K##k##1							   \
-	andc		rT1,d,b;	/* 1: F" = ~B and D 		*/ \
-	rotrwi		rT0,a,27;	/* 1: A' = A rotl 5		*/ \
-	or		rT2,rT2,rT1;	/* 1: F = F' or F"		*/ \
-	add		e,e,rT0;	/* 1: E = E + A'		*/ \
-	rotrwi		b,b,2;		/* 1: B = B rotl 30		*/ \
-	add		e,e,w0;		/* 1: E = E + W			*/ \
-	LOAD_DATA(w1, off+4)		/* 2: W				*/ \
-	add		e,e,rT2;	/* 1: E = E + F			*/ \
-	and		rT1,a,b;	/* 2: F' = B and C 		*/ \
-	add		e,e,rK;		/* 1: E = E + K			*/ \
-	andc		rT2,c,a;	/* 2: F" = ~B and D 		*/ \
-	add		d,d,rK;		/* 2: E = E + K			*/ \
-	or		rT2,rT2,rT1;	/* 2: F = F' or F"		*/ \
-	rotrwi		rT0,e,27;	/* 2: A' = A rotl 5		*/ \
-	add		d,d,w1;		/* 2: E = E + W			*/ \
-	rotrwi		a,a,2;		/* 2: B = B rotl 30		*/ \
-	add		d,d,rT0;	/* 2: E = E + A'		*/ \
-	evmergelo	w1,w1,w0;	/*    mix W[0]/W[1]		*/ \
-	add		d,d,rT2		/* 2: E = E + F			*/
-
-#define R_16_19(a, b, c, d, e, w0, w1, w4, w6, w7, k) \
-	and		rT2,b,c;	/* 1: F' = B and C 		*/ \
-	evmergelohi	rT0,w7,w6;	/*    W[-3]			*/ \
-	andc		rT1,d,b;	/* 1: F" = ~B and D 		*/ \
-	evxor		w0,w0,rT0;	/*    W = W[-16] xor W[-3]	*/ \
-	or		rT1,rT1,rT2;	/* 1: F = F' or F"		*/ \
-	evxor		w0,w0,w4;	/*    W = W xor W[-8]		*/ \
-	add		e,e,rT1;	/* 1: E = E + F			*/ \
-	evxor		w0,w0,w1;	/*    W = W xor W[-14]		*/ \
-	rotrwi		rT2,a,27;	/* 1: A' = A rotl 5		*/ \
-	evrlwi		w0,w0,1;	/*    W = W rotl 1		*/ \
-	add		e,e,rT2;	/* 1: E = E + A'		*/ \
-	evaddw		rT0,w0,rK;	/*    WK = W + K		*/ \
-	rotrwi		b,b,2;		/* 1: B = B rotl 30		*/ \
-	LOAD_K##k##1							   \
-	evmergehi	rT1,rT1,rT0;	/*    WK1/WK2			*/ \
-	add		e,e,rT0;	/* 1: E = E + WK		*/ \
-	add		d,d,rT1;	/* 2: E = E + WK		*/ \
-	and		rT2,a,b;	/* 2: F' = B and C 		*/ \
-	andc		rT1,c,a;	/* 2: F" = ~B and D 		*/ \
-	rotrwi		rT0,e,27;	/* 2: A' = A rotl 5		*/ \
-	or		rT1,rT1,rT2;	/* 2: F = F' or F"		*/ \
-	add		d,d,rT0;	/* 2: E = E + A'		*/ \
-	rotrwi		a,a,2;		/* 2: B = B rotl 30		*/ \
-	add		d,d,rT1		/* 2: E = E + F			*/
-
-#define R_20_39(a, b, c, d, e, w0, w1, w4, w6, w7, k) \
-	evmergelohi	rT0,w7,w6;	/*    W[-3]			*/ \
-	xor		rT2,b,c;	/* 1: F' = B xor C		*/ \
-	evxor		w0,w0,rT0;	/*    W = W[-16] xor W[-3]	*/ \
-	xor		rT2,rT2,d;	/* 1: F = F' xor D		*/ \
-	evxor		w0,w0,w4;	/*    W = W xor W[-8]		*/ \
-	add		e,e,rT2;	/* 1: E = E + F			*/ \
-	evxor		w0,w0,w1;	/*    W = W xor W[-14]		*/ \
-	rotrwi		rT2,a,27;	/* 1: A' = A rotl 5		*/ \
-	evrlwi		w0,w0,1;	/*    W = W rotl 1		*/ \
-	add		e,e,rT2;	/* 1: E = E + A'		*/ \
-	evaddw		rT0,w0,rK;	/*    WK = W + K		*/ \
-	rotrwi		b,b,2;		/* 1: B = B rotl 30		*/ \
-	LOAD_K##k##1							   \
-	evmergehi	rT1,rT1,rT0;	/*    WK1/WK2			*/ \
-	add		e,e,rT0;	/* 1: E = E + WK		*/ \
-	xor		rT2,a,b;	/* 2: F' = B xor C		*/ \
-	add		d,d,rT1;	/* 2: E = E + WK		*/ \
-	xor		rT2,rT2,c;	/* 2: F = F' xor D		*/ \
-	rotrwi		rT0,e,27;	/* 2: A' = A rotl 5		*/ \
-	add		d,d,rT2;	/* 2: E = E + F			*/ \
-	rotrwi		a,a,2;		/* 2: B = B rotl 30		*/ \
-	add		d,d,rT0		/* 2: E = E + A'		*/
-
-#define R_40_59(a, b, c, d, e, w0, w1, w4, w6, w7, k) \
-	and		rT2,b,c;	/* 1: F' = B and C		*/ \
-	evmergelohi	rT0,w7,w6;	/*    W[-3]			*/ \
-	or		rT1,b,c;	/* 1: F" = B or C		*/ \
-	evxor		w0,w0,rT0;	/*    W = W[-16] xor W[-3]	*/ \
-	and		rT1,d,rT1;	/* 1: F" = F" and D		*/ \
-	evxor		w0,w0,w4;	/*    W = W xor W[-8]		*/ \
-	or		rT2,rT2,rT1;	/* 1: F = F' or F"		*/ \
-	evxor		w0,w0,w1;	/*    W = W xor W[-14]		*/ \
-	add		e,e,rT2;	/* 1: E = E + F			*/ \
-	evrlwi		w0,w0,1;	/*    W = W rotl 1		*/ \
-	rotrwi		rT2,a,27;	/* 1: A' = A rotl 5		*/ \
-	evaddw		rT0,w0,rK;	/*    WK = W + K		*/ \
-	add		e,e,rT2;	/* 1: E = E + A'		*/ \
-	LOAD_K##k##1							   \
-	evmergehi	rT1,rT1,rT0;	/*    WK1/WK2			*/ \
-	rotrwi		b,b,2;		/* 1: B = B rotl 30		*/ \
-	add		e,e,rT0;	/* 1: E = E + WK		*/ \
-	and		rT2,a,b;	/* 2: F' = B and C		*/ \
-	or		rT0,a,b;	/* 2: F" = B or C		*/ \
-	add		d,d,rT1;	/* 2: E = E + WK		*/ \
-	and		rT0,c,rT0;	/* 2: F" = F" and D		*/ \
-	rotrwi		a,a,2;		/* 2: B = B rotl 30		*/ \
-	or		rT2,rT2,rT0;	/* 2: F = F' or F"		*/ \
-	rotrwi		rT0,e,27;	/* 2: A' = A rotl 5		*/ \
-	add		d,d,rT2;	/* 2: E = E + F			*/ \
-	add		d,d,rT0		/* 2: E = E + A'		*/
-
-#define R_60_79(a, b, c, d, e, w0, w1, w4, w6, w7, k) \
-	R_20_39(a, b, c, d, e, w0, w1, w4, w6, w7, k)
-
-_GLOBAL(ppc_spe_sha1_transform)
-	INITIALIZE
-
-	lwz		rH0,0(rHP)
-	lwz		rH1,4(rHP)
-	mtctr		r5
-	lwz		rH2,8(rHP)
-	lis		rKP,PPC_SPE_SHA1_K@h
-	lwz		rH3,12(rHP)
-	ori		rKP,rKP,PPC_SPE_SHA1_K@l
-	lwz		rH4,16(rHP)
-
-ppc_spe_sha1_main:
-	R_00_15(rH0, rH1, rH2, rH3, rH4, rW1, rW0, 1, 0)
-	R_00_15(rH3, rH4, rH0, rH1, rH2, rW2, rW1, 0, 8)
-	R_00_15(rH1, rH2, rH3, rH4, rH0, rW3, rW2, 0, 16)
-	R_00_15(rH4, rH0, rH1, rH2, rH3, rW4, rW3, 0, 24)
-	R_00_15(rH2, rH3, rH4, rH0, rH1, rW5, rW4, 0, 32)
-	R_00_15(rH0, rH1, rH2, rH3, rH4, rW6, rW5, 0, 40)
-	R_00_15(rH3, rH4, rH0, rH1, rH2, rT3, rW6, 0, 48)
-	R_00_15(rH1, rH2, rH3, rH4, rH0, rT3, rW7, 0, 56)
-
-	R_16_19(rH4, rH0, rH1, rH2, rH3, rW0, rW1, rW4, rW6, rW7, 0)
-	R_16_19(rH2, rH3, rH4, rH0, rH1, rW1, rW2, rW5, rW7, rW0, 2)
-
-	R_20_39(rH0, rH1, rH2, rH3, rH4, rW2, rW3, rW6, rW0, rW1, 0)
-	R_20_39(rH3, rH4, rH0, rH1, rH2, rW3, rW4, rW7, rW1, rW2, 0)
-	R_20_39(rH1, rH2, rH3, rH4, rH0, rW4, rW5, rW0, rW2, rW3, 0)
-	R_20_39(rH4, rH0, rH1, rH2, rH3, rW5, rW6, rW1, rW3, rW4, 0)
-	R_20_39(rH2, rH3, rH4, rH0, rH1, rW6, rW7, rW2, rW4, rW5, 0)
-	R_20_39(rH0, rH1, rH2, rH3, rH4, rW7, rW0, rW3, rW5, rW6, 0)
-	R_20_39(rH3, rH4, rH0, rH1, rH2, rW0, rW1, rW4, rW6, rW7, 0)
-	R_20_39(rH1, rH2, rH3, rH4, rH0, rW1, rW2, rW5, rW7, rW0, 0)
-	R_20_39(rH4, rH0, rH1, rH2, rH3, rW2, rW3, rW6, rW0, rW1, 0)
-	R_20_39(rH2, rH3, rH4, rH0, rH1, rW3, rW4, rW7, rW1, rW2, 3)
-
-	R_40_59(rH0, rH1, rH2, rH3, rH4, rW4, rW5, rW0, rW2, rW3, 0)
-	R_40_59(rH3, rH4, rH0, rH1, rH2, rW5, rW6, rW1, rW3, rW4, 0)
-	R_40_59(rH1, rH2, rH3, rH4, rH0, rW6, rW7, rW2, rW4, rW5, 0)
-	R_40_59(rH4, rH0, rH1, rH2, rH3, rW7, rW0, rW3, rW5, rW6, 0)
-	R_40_59(rH2, rH3, rH4, rH0, rH1, rW0, rW1, rW4, rW6, rW7, 0)
-	R_40_59(rH0, rH1, rH2, rH3, rH4, rW1, rW2, rW5, rW7, rW0, 0)
-	R_40_59(rH3, rH4, rH0, rH1, rH2, rW2, rW3, rW6, rW0, rW1, 0)
-	R_40_59(rH1, rH2, rH3, rH4, rH0, rW3, rW4, rW7, rW1, rW2, 0)
-	R_40_59(rH4, rH0, rH1, rH2, rH3, rW4, rW5, rW0, rW2, rW3, 0)
-	R_40_59(rH2, rH3, rH4, rH0, rH1, rW5, rW6, rW1, rW3, rW4, 4)
-
-	R_60_79(rH0, rH1, rH2, rH3, rH4, rW6, rW7, rW2, rW4, rW5, 0)
-	R_60_79(rH3, rH4, rH0, rH1, rH2, rW7, rW0, rW3, rW5, rW6, 0)
-	R_60_79(rH1, rH2, rH3, rH4, rH0, rW0, rW1, rW4, rW6, rW7, 0)
-	R_60_79(rH4, rH0, rH1, rH2, rH3, rW1, rW2, rW5, rW7, rW0, 0)
-	R_60_79(rH2, rH3, rH4, rH0, rH1, rW2, rW3, rW6, rW0, rW1, 0)
-	R_60_79(rH0, rH1, rH2, rH3, rH4, rW3, rW4, rW7, rW1, rW2, 0)
-	R_60_79(rH3, rH4, rH0, rH1, rH2, rW4, rW5, rW0, rW2, rW3, 0)
-	lwz		rT3,0(rHP)
-	R_60_79(rH1, rH2, rH3, rH4, rH0, rW5, rW6, rW1, rW3, rW4, 0)
-	lwz		rW1,4(rHP)
-	R_60_79(rH4, rH0, rH1, rH2, rH3, rW6, rW7, rW2, rW4, rW5, 0)
-	lwz		rW2,8(rHP)
-	R_60_79(rH2, rH3, rH4, rH0, rH1, rW7, rW0, rW3, rW5, rW6, 0)
-	lwz		rW3,12(rHP)
-	NEXT_BLOCK
-	lwz		rW4,16(rHP)
-
-	add		rH0,rH0,rT3
-	stw		rH0,0(rHP)
-	add		rH1,rH1,rW1
-	stw		rH1,4(rHP)
-	add		rH2,rH2,rW2
-	stw		rH2,8(rHP)
-	add		rH3,rH3,rW3
-	stw		rH3,12(rHP)
-	add		rH4,rH4,rW4
-	stw		rH4,16(rHP)
-
-	bdnz		ppc_spe_sha1_main
-
-	FINALIZE
-	blr
-
-.data
-.align 4
-PPC_SPE_SHA1_K:
-	.long 0x5A827999,0x6ED9EBA1,0x8F1BBCDC,0xCA62C1D6
diff --git a/arch/powerpc/crypto/sha1-spe-glue.c b/arch/powerpc/crypto/sha1-spe-glue.c
deleted file mode 100644
index 9170892a8557..000000000000
--- a/arch/powerpc/crypto/sha1-spe-glue.c
+++ /dev/null
@@ -1,191 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Glue code for SHA-1 implementation for SPE instructions (PPC)
- *
- * Based on generic implementation.
- *
- * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- */
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <crypto/sha1.h>
-#include <crypto/sha1_base.h>
-#include <asm/byteorder.h>
-#include <asm/switch_to.h>
-#include <linux/hardirq.h>
-
-/*
- * MAX_BYTES defines the number of bytes that are allowed to be processed
- * between preempt_disable() and preempt_enable(). SHA1 takes ~1000
- * operations per 64 bytes. e500 cores can issue two arithmetic instructions
- * per clock cycle using one 32/64 bit unit (SU1) and one 32 bit unit (SU2).
- * Thus 2KB of input data will need an estimated maximum of 18,000 cycles.
- * Headroom for cache misses included. Even with the low end model clocked
- * at 667 MHz this equals to a critical time window of less than 27us.
- *
- */
-#define MAX_BYTES 2048
-
-extern void ppc_spe_sha1_transform(u32 *state, const u8 *src, u32 blocks);
-
-static void spe_begin(void)
-{
-	/* We just start SPE operations and will save SPE registers later. */
-	preempt_disable();
-	enable_kernel_spe();
-}
-
-static void spe_end(void)
-{
-	disable_kernel_spe();
-	/* reenable preemption */
-	preempt_enable();
-}
-
-static inline void ppc_sha1_clear_context(struct sha1_state *sctx)
-{
-	int count = sizeof(struct sha1_state) >> 2;
-	u32 *ptr = (u32 *)sctx;
-
-	/* make sure we can clear the fast way */
-	BUILD_BUG_ON(sizeof(struct sha1_state) % 4);
-	do { *ptr++ = 0; } while (--count);
-}
-
-static int ppc_spe_sha1_update(struct shash_desc *desc, const u8 *data,
-			unsigned int len)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->count & 0x3f;
-	const unsigned int avail = 64 - offset;
-	unsigned int bytes;
-	const u8 *src = data;
-
-	if (avail > len) {
-		sctx->count += len;
-		memcpy((char *)sctx->buffer + offset, src, len);
-		return 0;
-	}
-
-	sctx->count += len;
-
-	if (offset) {
-		memcpy((char *)sctx->buffer + offset, src, avail);
-
-		spe_begin();
-		ppc_spe_sha1_transform(sctx->state, (const u8 *)sctx->buffer, 1);
-		spe_end();
-
-		len -= avail;
-		src += avail;
-	}
-
-	while (len > 63) {
-		bytes = (len > MAX_BYTES) ? MAX_BYTES : len;
-		bytes = bytes & ~0x3f;
-
-		spe_begin();
-		ppc_spe_sha1_transform(sctx->state, src, bytes >> 6);
-		spe_end();
-
-		src += bytes;
-		len -= bytes;
-	}
-
-	memcpy((char *)sctx->buffer, src, len);
-	return 0;
-}
-
-static int ppc_spe_sha1_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->count & 0x3f;
-	char *p = (char *)sctx->buffer + offset;
-	int padlen;
-	__be64 *pbits = (__be64 *)(((char *)&sctx->buffer) + 56);
-	__be32 *dst = (__be32 *)out;
-
-	padlen = 55 - offset;
-	*p++ = 0x80;
-
-	spe_begin();
-
-	if (padlen < 0) {
-		memset(p, 0x00, padlen + sizeof (u64));
-		ppc_spe_sha1_transform(sctx->state, sctx->buffer, 1);
-		p = (char *)sctx->buffer;
-		padlen = 56;
-	}
-
-	memset(p, 0, padlen);
-	*pbits = cpu_to_be64(sctx->count << 3);
-	ppc_spe_sha1_transform(sctx->state, sctx->buffer, 1);
-
-	spe_end();
-
-	dst[0] = cpu_to_be32(sctx->state[0]);
-	dst[1] = cpu_to_be32(sctx->state[1]);
-	dst[2] = cpu_to_be32(sctx->state[2]);
-	dst[3] = cpu_to_be32(sctx->state[3]);
-	dst[4] = cpu_to_be32(sctx->state[4]);
-
-	ppc_sha1_clear_context(sctx);
-	return 0;
-}
-
-static int ppc_spe_sha1_export(struct shash_desc *desc, void *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int ppc_spe_sha1_import(struct shash_desc *desc, const void *in)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
-}
-
-static struct shash_alg alg = {
-	.digestsize	=	SHA1_DIGEST_SIZE,
-	.init		=	sha1_base_init,
-	.update		=	ppc_spe_sha1_update,
-	.final		=	ppc_spe_sha1_final,
-	.export		=	ppc_spe_sha1_export,
-	.import		=	ppc_spe_sha1_import,
-	.descsize	=	sizeof(struct sha1_state),
-	.statesize	=	sizeof(struct sha1_state),
-	.base		=	{
-		.cra_name	=	"sha1",
-		.cra_driver_name=	"sha1-ppc-spe",
-		.cra_priority	=	300,
-		.cra_blocksize	=	SHA1_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static int __init ppc_spe_sha1_mod_init(void)
-{
-	return crypto_register_shash(&alg);
-}
-
-static void __exit ppc_spe_sha1_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-module_init(ppc_spe_sha1_mod_init);
-module_exit(ppc_spe_sha1_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, SPE optimized");
-
-MODULE_ALIAS_CRYPTO("sha1");
-MODULE_ALIAS_CRYPTO("sha1-ppc-spe");
diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
deleted file mode 100644
index f283bbd3f121..000000000000
--- a/arch/powerpc/crypto/sha1.c
+++ /dev/null
@@ -1,139 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cryptographic API.
- *
- * powerpc implementation of the SHA1 Secure Hash Algorithm.
- *
- * Derived from cryptoapi implementation, adapted for in-place
- * scatterlist interface.
- *
- * Derived from "crypto/sha1.c"
- * Copyright (c) Alan Smithee.
- * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
- * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
- */
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <crypto/sha1.h>
-#include <crypto/sha1_base.h>
-#include <asm/byteorder.h>
-
-void powerpc_sha_transform(u32 *state, const u8 *src);
-
-static int powerpc_sha1_update(struct shash_desc *desc, const u8 *data,
-			       unsigned int len)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial, done;
-	const u8 *src;
-
-	partial = sctx->count & 0x3f;
-	sctx->count += len;
-	done = 0;
-	src = data;
-
-	if ((partial + len) > 63) {
-
-		if (partial) {
-			done = -partial;
-			memcpy(sctx->buffer + partial, data, done + 64);
-			src = sctx->buffer;
-		}
-
-		do {
-			powerpc_sha_transform(sctx->state, src);
-			done += 64;
-			src = data + done;
-		} while (done + 63 < len);
-
-		partial = 0;
-	}
-	memcpy(sctx->buffer + partial, src, len - done);
-
-	return 0;
-}
-
-
-/* Add padding and return the message digest. */
-static int powerpc_sha1_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-	__be32 *dst = (__be32 *)out;
-	u32 i, index, padlen;
-	__be64 bits;
-	static const u8 padding[64] = { 0x80, };
-
-	bits = cpu_to_be64(sctx->count << 3);
-
-	/* Pad out to 56 mod 64 */
-	index = sctx->count & 0x3f;
-	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
-	powerpc_sha1_update(desc, padding, padlen);
-
-	/* Append length */
-	powerpc_sha1_update(desc, (const u8 *)&bits, sizeof(bits));
-
-	/* Store state in digest */
-	for (i = 0; i < 5; i++)
-		dst[i] = cpu_to_be32(sctx->state[i]);
-
-	/* Wipe context */
-	memset(sctx, 0, sizeof *sctx);
-
-	return 0;
-}
-
-static int powerpc_sha1_export(struct shash_desc *desc, void *out)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int powerpc_sha1_import(struct shash_desc *desc, const void *in)
-{
-	struct sha1_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
-}
-
-static struct shash_alg alg = {
-	.digestsize	=	SHA1_DIGEST_SIZE,
-	.init		=	sha1_base_init,
-	.update		=	powerpc_sha1_update,
-	.final		=	powerpc_sha1_final,
-	.export		=	powerpc_sha1_export,
-	.import		=	powerpc_sha1_import,
-	.descsize	=	sizeof(struct sha1_state),
-	.statesize	=	sizeof(struct sha1_state),
-	.base		=	{
-		.cra_name	=	"sha1",
-		.cra_driver_name=	"sha1-powerpc",
-		.cra_blocksize	=	SHA1_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-};
-
-static int __init sha1_powerpc_mod_init(void)
-{
-	return crypto_register_shash(&alg);
-}
-
-static void __exit sha1_powerpc_mod_fini(void)
-{
-	crypto_unregister_shash(&alg);
-}
-
-module_init(sha1_powerpc_mod_init);
-module_exit(sha1_powerpc_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
-
-MODULE_ALIAS_CRYPTO("sha1");
-MODULE_ALIAS_CRYPTO("sha1-powerpc");
diff --git a/arch/powerpc/crypto/sha256-spe-asm.S b/arch/powerpc/crypto/sha256-spe-asm.S
deleted file mode 100644
index cd99d71dae34..000000000000
--- a/arch/powerpc/crypto/sha256-spe-asm.S
+++ /dev/null
@@ -1,318 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Fast SHA-256 implementation for SPE instruction set (PPC)
- *
- * This code makes use of the SPE SIMD instruction set as defined in
- * http://cache.freescale.com/files/32bit/doc/ref_manual/SPEPIM.pdf
- * Implementation is based on optimization guide notes from
- * http://cache.freescale.com/files/32bit/doc/app_note/AN2665.pdf
- *
- * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- */
-
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-
-#define rHP	r3	/* pointer to hash values in memory		*/
-#define rKP	r24	/* pointer to round constants			*/
-#define rWP	r4	/* pointer to input data			*/
-
-#define rH0	r5	/* 8 32 bit hash values in 8 registers		*/
-#define rH1	r6
-#define rH2	r7
-#define rH3	r8
-#define rH4	r9
-#define rH5	r10
-#define rH6	r11
-#define rH7	r12
-
-#define rW0	r14	/* 64 bit registers. 16 words in 8 registers	*/
-#define rW1	r15
-#define rW2	r16
-#define rW3	r17
-#define rW4	r18
-#define rW5	r19
-#define rW6	r20
-#define rW7	r21
-
-#define rT0	r22	/* 64 bit temporaries 				*/
-#define rT1	r23
-#define rT2	r0	/* 32 bit temporaries				*/
-#define rT3	r25
-
-#define CMP_KN_LOOP
-#define CMP_KC_LOOP \
-	cmpwi		rT1,0;
-
-#define INITIALIZE \
-	stwu		r1,-128(r1);	/* create stack frame		*/ \
-	evstdw		r14,8(r1);	/* We must save non volatile	*/ \
-	evstdw		r15,16(r1);	/* registers. Take the chance	*/ \
-	evstdw		r16,24(r1);	/* and save the SPE part too	*/ \
-	evstdw		r17,32(r1);					   \
-	evstdw		r18,40(r1);					   \
-	evstdw		r19,48(r1);					   \
-	evstdw		r20,56(r1);					   \
-	evstdw		r21,64(r1);					   \
-	evstdw		r22,72(r1);					   \
-	evstdw		r23,80(r1);					   \
-	stw		r24,88(r1);	/* save normal registers	*/ \
-	stw		r25,92(r1);
-
-
-#define FINALIZE \
-	evldw		r14,8(r1);	/* restore SPE registers	*/ \
-	evldw		r15,16(r1);					   \
-	evldw		r16,24(r1);					   \
-	evldw		r17,32(r1);					   \
-	evldw		r18,40(r1);					   \
-	evldw		r19,48(r1);					   \
-	evldw		r20,56(r1);					   \
-	evldw		r21,64(r1);					   \
-	evldw		r22,72(r1);					   \
-	evldw		r23,80(r1);					   \
-	lwz		r24,88(r1);	/* restore normal registers	*/ \
-	lwz		r25,92(r1);					   \
-	xor		r0,r0,r0;					   \
-	stw		r0,8(r1);	/* Delete sensitive data	*/ \
-	stw		r0,16(r1);	/* that we might have pushed	*/ \
-	stw		r0,24(r1);	/* from other context that runs	*/ \
-	stw		r0,32(r1);	/* the same code. Assume that	*/ \
-	stw		r0,40(r1);	/* the lower part of the GPRs	*/ \
-	stw		r0,48(r1);	/* was already overwritten on	*/ \
-	stw		r0,56(r1);	/* the way down to here		*/ \
-	stw		r0,64(r1);					   \
-	stw		r0,72(r1);					   \
-	stw		r0,80(r1);					   \
-	addi		r1,r1,128;	/* cleanup stack frame		*/
-
-#ifdef __BIG_ENDIAN__
-#define LOAD_DATA(reg, off) \
-	lwz		reg,off(rWP);	/* load data			*/
-#define NEXT_BLOCK \
-	addi		rWP,rWP,64;	/* increment per block		*/
-#else
-#define LOAD_DATA(reg, off) \
-	lwbrx		reg,0,rWP; 	/* load data			*/ \
-	addi		rWP,rWP,4;	/* increment per word		*/
-#define NEXT_BLOCK			/* nothing to do		*/
-#endif
-
-#define R_LOAD_W(a, b, c, d, e, f, g, h, w, off) \
-	LOAD_DATA(w, off)		/* 1: W				*/ \
-	rotrwi		rT0,e,6;	/* 1: S1 = e rotr 6		*/ \
-	rotrwi		rT1,e,11;	/* 1: S1' = e rotr 11		*/ \
-	rotrwi		rT2,e,25;	/* 1: S1" = e rotr 25		*/ \
-	xor		rT0,rT0,rT1;	/* 1: S1 = S1 xor S1'		*/ \
-	and		rT3,e,f;	/* 1: ch = e and f		*/ \
-	xor		rT0,rT0,rT2;	/* 1: S1 = S1 xor S1"		*/ \
-	andc		rT1,g,e;	/* 1: ch' = ~e and g		*/ \
-	lwz		rT2,off(rKP);	/* 1: K				*/ \
-	xor		rT3,rT3,rT1;	/* 1: ch = ch xor ch'		*/ \
-	add		h,h,rT0;	/* 1: temp1 = h + S1		*/ \
-	add		rT3,rT3,w;	/* 1: temp1' = ch + w		*/ \
-	rotrwi		rT0,a,2;	/* 1: S0 = a rotr 2		*/ \
-	add		h,h,rT3;	/* 1: temp1 = temp1 + temp1'	*/ \
-	rotrwi		rT1,a,13;	/* 1: S0' = a rotr 13		*/ \
-	add		h,h,rT2;	/* 1: temp1 = temp1 + K		*/ \
-	rotrwi		rT3,a,22;	/* 1: S0" = a rotr 22		*/ \
-	xor		rT0,rT0,rT1;	/* 1: S0 = S0 xor S0'		*/ \
-	add		d,d,h;		/* 1: d = d + temp1		*/ \
-	xor		rT3,rT0,rT3;	/* 1: S0 = S0 xor S0"		*/ \
-	evmergelo	w,w,w;		/*    shift W			*/ \
-	or		rT2,a,b;	/* 1: maj = a or b		*/ \
-	and		rT1,a,b;	/* 1: maj' = a and b		*/ \
-	and		rT2,rT2,c;	/* 1: maj = maj and c		*/ \
-	LOAD_DATA(w, off+4)		/* 2: W				*/ \
-	or		rT2,rT1,rT2;	/* 1: maj = maj or maj'		*/ \
-	rotrwi		rT0,d,6;	/* 2: S1 = e rotr 6		*/ \
-	add		rT3,rT3,rT2;	/* 1: temp2 = S0 + maj		*/ \
-	rotrwi		rT1,d,11;	/* 2: S1' = e rotr 11		*/ \
-	add		h,h,rT3;	/* 1: h = temp1 + temp2		*/ \
-	rotrwi		rT2,d,25;	/* 2: S1" = e rotr 25		*/ \
-	xor		rT0,rT0,rT1;	/* 2: S1 = S1 xor S1'		*/ \
-	and		rT3,d,e;	/* 2: ch = e and f		*/ \
-	xor		rT0,rT0,rT2;	/* 2: S1 = S1 xor S1"		*/ \
-	andc		rT1,f,d;	/* 2: ch' = ~e and g		*/ \
-	lwz		rT2,off+4(rKP);	/* 2: K				*/ \
-	xor		rT3,rT3,rT1;	/* 2: ch = ch xor ch'		*/ \
-	add		g,g,rT0;	/* 2: temp1 = h + S1		*/ \
-	add		rT3,rT3,w;	/* 2: temp1' = ch + w		*/ \
-	rotrwi		rT0,h,2;	/* 2: S0 = a rotr 2		*/ \
-	add		g,g,rT3;	/* 2: temp1 = temp1 + temp1'	*/ \
-	rotrwi		rT1,h,13;	/* 2: S0' = a rotr 13		*/ \
-	add		g,g,rT2;	/* 2: temp1 = temp1 + K		*/ \
-	rotrwi		rT3,h,22;	/* 2: S0" = a rotr 22		*/ \
-	xor		rT0,rT0,rT1;	/* 2: S0 = S0 xor S0'		*/ \
-	or		rT2,h,a;	/* 2: maj = a or b		*/ \
-	xor		rT3,rT0,rT3;	/* 2: S0 = S0 xor S0"		*/ \
-	and		rT1,h,a;	/* 2: maj' = a and b		*/ \
-	and		rT2,rT2,b;	/* 2: maj = maj and c		*/ \
-	add		c,c,g;		/* 2: d = d + temp1		*/ \
-	or		rT2,rT1,rT2;	/* 2: maj = maj or maj'		*/ \
-	add		rT3,rT3,rT2;	/* 2: temp2 = S0 + maj		*/ \
-	add		g,g,rT3		/* 2: h = temp1 + temp2		*/
-
-#define R_CALC_W(a, b, c, d, e, f, g, h, w0, w1, w4, w5, w7, k, off) \
-	rotrwi		rT2,e,6;	/* 1: S1 = e rotr 6		*/ \
-	evmergelohi	rT0,w0,w1;	/*    w[-15]			*/ \
-	rotrwi		rT3,e,11;	/* 1: S1' = e rotr 11		*/ \
-	evsrwiu		rT1,rT0,3;	/*    s0 = w[-15] >> 3		*/ \
-	xor		rT2,rT2,rT3;	/* 1: S1 = S1 xor S1'		*/ \
-	evrlwi		rT0,rT0,25;	/*    s0' = w[-15] rotr	7	*/ \
-	rotrwi		rT3,e,25;	/* 1: S1' = e rotr 25		*/ \
-	evxor		rT1,rT1,rT0;	/*    s0 = s0 xor s0'		*/ \
-	xor		rT2,rT2,rT3;	/* 1: S1 = S1 xor S1'		*/ \
-	evrlwi		rT0,rT0,21;	/*    s0' = w[-15] rotr 18	*/ \
-	add		h,h,rT2;	/* 1: temp1 = h + S1		*/ \
-	evxor		rT0,rT0,rT1;	/*    s0 = s0 xor s0'		*/ \
-	and		rT2,e,f;	/* 1: ch = e and f		*/ \
-	evaddw		w0,w0,rT0;	/*    w = w[-16] + s0		*/ \
-	andc		rT3,g,e;	/* 1: ch' = ~e and g		*/ \
-	evsrwiu		rT0,w7,10;	/*    s1 = w[-2] >> 10		*/ \
-	xor		rT2,rT2,rT3;	/* 1: ch = ch xor ch'		*/ \
-	evrlwi		rT1,w7,15;	/*    s1' = w[-2] rotr 17	*/ \
-	add		h,h,rT2;	/* 1: temp1 = temp1 + ch	*/ \
-	evxor		rT0,rT0,rT1;	/*    s1 = s1 xor s1'		*/ \
-	rotrwi		rT2,a,2;	/* 1: S0 = a rotr 2		*/ \
-	evrlwi		rT1,w7,13;	/*    s1' = w[-2] rotr 19	*/ \
-	rotrwi		rT3,a,13;	/* 1: S0' = a rotr 13		*/ \
-	evxor		rT0,rT0,rT1;	/*    s1 = s1 xor s1'		*/ \
-	xor		rT2,rT2,rT3;	/* 1: S0 = S0 xor S0'		*/ \
-	evldw		rT1,off(rKP);	/*    k				*/ \
-	rotrwi		rT3,a,22;	/* 1: S0' = a rotr 22		*/ \
-	evaddw		w0,w0,rT0;	/*    w = w + s1		*/ \
-	xor		rT2,rT2,rT3;	/* 1: S0 = S0 xor S0'		*/ \
-	evmergelohi	rT0,w4,w5;	/*    w[-7]			*/ \
-	and		rT3,a,b;	/* 1: maj = a and b		*/ \
-	evaddw		w0,w0,rT0;	/*    w = w + w[-7]		*/ \
-	CMP_K##k##_LOOP							   \
-	add		rT2,rT2,rT3;	/* 1: temp2 = S0 + maj		*/ \
-	evaddw		rT1,rT1,w0;	/*    wk = w + k		*/ \
-	xor		rT3,a,b;	/* 1: maj = a xor b		*/ \
-	evmergehi	rT0,rT1,rT1;	/*    wk1/wk2			*/ \
-	and		rT3,rT3,c;	/* 1: maj = maj and c		*/ \
-	add		h,h,rT0;	/* 1: temp1 = temp1 + wk	*/ \
-	add		rT2,rT2,rT3;	/* 1: temp2 = temp2 + maj	*/ \
-	add		g,g,rT1;	/* 2: temp1 = temp1 + wk	*/ \
-	add		d,d,h;		/* 1: d = d + temp1		*/ \
-	rotrwi		rT0,d,6;	/* 2: S1 = e rotr 6		*/ \
-	add		h,h,rT2;	/* 1: h = temp1 + temp2		*/ \
-	rotrwi		rT1,d,11;	/* 2: S1' = e rotr 11		*/ \
-	rotrwi		rT2,d,25;	/* 2: S" = e rotr 25		*/ \
-	xor		rT0,rT0,rT1;	/* 2: S1 = S1 xor S1'		*/ \
-	and		rT3,d,e;	/* 2: ch = e and f		*/ \
-	xor		rT0,rT0,rT2;	/* 2: S1 = S1 xor S1"		*/ \
-	andc		rT1,f,d;	/* 2: ch' = ~e and g		*/ \
-	add		g,g,rT0;	/* 2: temp1 = h + S1		*/ \
-	xor		rT3,rT3,rT1;	/* 2: ch = ch xor ch'		*/ \
-	rotrwi		rT0,h,2;	/* 2: S0 = a rotr 2		*/ \
-	add		g,g,rT3;	/* 2: temp1 = temp1 + ch	*/ \
-	rotrwi		rT1,h,13;	/* 2: S0' = a rotr 13		*/ \
-	rotrwi		rT3,h,22;	/* 2: S0" = a rotr 22		*/ \
-	xor		rT0,rT0,rT1;	/* 2: S0 = S0 xor S0'		*/ \
-	or		rT2,h,a;	/* 2: maj = a or b		*/ \
-	and		rT1,h,a;	/* 2: maj' = a and b		*/ \
-	and		rT2,rT2,b;	/* 2: maj = maj and c		*/ \
-	xor		rT3,rT0,rT3;	/* 2: S0 = S0 xor S0"		*/ \
-	or		rT2,rT1,rT2;	/* 2: maj = maj or maj'		*/ \
-	add		c,c,g;		/* 2: d = d + temp1		*/ \
-	add		rT3,rT3,rT2;	/* 2: temp2 = S0 + maj		*/ \
-	add		g,g,rT3		/* 2: h = temp1 + temp2		*/
-
-_GLOBAL(ppc_spe_sha256_transform)
-	INITIALIZE
-
-	mtctr		r5
-	lwz		rH0,0(rHP)
-	lwz		rH1,4(rHP)
-	lwz		rH2,8(rHP)
-	lwz		rH3,12(rHP)
-	lwz		rH4,16(rHP)
-	lwz		rH5,20(rHP)
-	lwz		rH6,24(rHP)
-	lwz		rH7,28(rHP)
-
-ppc_spe_sha256_main:
-	lis		rKP,PPC_SPE_SHA256_K@ha
-	addi		rKP,rKP,PPC_SPE_SHA256_K@l
-
-	R_LOAD_W(rH0, rH1, rH2, rH3, rH4, rH5, rH6, rH7, rW0, 0)
-	R_LOAD_W(rH6, rH7, rH0, rH1, rH2, rH3, rH4, rH5, rW1, 8)
-	R_LOAD_W(rH4, rH5, rH6, rH7, rH0, rH1, rH2, rH3, rW2, 16)
-	R_LOAD_W(rH2, rH3, rH4, rH5, rH6, rH7, rH0, rH1, rW3, 24)
-	R_LOAD_W(rH0, rH1, rH2, rH3, rH4, rH5, rH6, rH7, rW4, 32)
-	R_LOAD_W(rH6, rH7, rH0, rH1, rH2, rH3, rH4, rH5, rW5, 40)
-	R_LOAD_W(rH4, rH5, rH6, rH7, rH0, rH1, rH2, rH3, rW6, 48)
-	R_LOAD_W(rH2, rH3, rH4, rH5, rH6, rH7, rH0, rH1, rW7, 56)
-ppc_spe_sha256_16_rounds:
-	addi		rKP,rKP,64
-	R_CALC_W(rH0, rH1, rH2, rH3, rH4, rH5, rH6, rH7,
-		 rW0, rW1, rW4, rW5, rW7, N, 0)
-	R_CALC_W(rH6, rH7, rH0, rH1, rH2, rH3, rH4, rH5,
-		 rW1, rW2, rW5, rW6, rW0, N, 8)
-	R_CALC_W(rH4, rH5, rH6, rH7, rH0, rH1, rH2, rH3,
-		 rW2, rW3, rW6, rW7, rW1, N, 16)
-	R_CALC_W(rH2, rH3, rH4, rH5, rH6, rH7, rH0, rH1,
-		 rW3, rW4, rW7, rW0, rW2, N, 24)
-	R_CALC_W(rH0, rH1, rH2, rH3, rH4, rH5, rH6, rH7,
-		 rW4, rW5, rW0, rW1, rW3, N, 32)
-	R_CALC_W(rH6, rH7, rH0, rH1, rH2, rH3, rH4, rH5,
-		 rW5, rW6, rW1, rW2, rW4, N, 40)
-	R_CALC_W(rH4, rH5, rH6, rH7, rH0, rH1, rH2, rH3,
-		 rW6, rW7, rW2, rW3, rW5, N, 48)
-	R_CALC_W(rH2, rH3, rH4, rH5, rH6, rH7, rH0, rH1,
-		 rW7, rW0, rW3, rW4, rW6, C, 56)
-	bt		gt,ppc_spe_sha256_16_rounds
-
-	lwz		rW0,0(rHP)
-	NEXT_BLOCK
-	lwz		rW1,4(rHP)
-	lwz		rW2,8(rHP)
-	lwz		rW3,12(rHP)
-	lwz		rW4,16(rHP)
-	lwz		rW5,20(rHP)
-	lwz		rW6,24(rHP)
-	lwz		rW7,28(rHP)
-
-	add		rH0,rH0,rW0
-	stw		rH0,0(rHP)
-	add		rH1,rH1,rW1
-	stw		rH1,4(rHP)
-	add		rH2,rH2,rW2
-	stw		rH2,8(rHP)
-	add		rH3,rH3,rW3
-	stw		rH3,12(rHP)
-	add		rH4,rH4,rW4
-	stw		rH4,16(rHP)
-	add		rH5,rH5,rW5
-	stw		rH5,20(rHP)
-	add		rH6,rH6,rW6
-	stw		rH6,24(rHP)
-	add		rH7,rH7,rW7
-	stw		rH7,28(rHP)
-
-	bdnz		ppc_spe_sha256_main
-
-	FINALIZE
-	blr
-
-.data
-.align 5
-PPC_SPE_SHA256_K:
-	.long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
-	.long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
-	.long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
-	.long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
-	.long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
-	.long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
-	.long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
-	.long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
-	.long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
-	.long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
-	.long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
-	.long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
-	.long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
-	.long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
-	.long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
-	.long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
diff --git a/arch/powerpc/crypto/sha256-spe-glue.c b/arch/powerpc/crypto/sha256-spe-glue.c
deleted file mode 100644
index 2997d13236e0..000000000000
--- a/arch/powerpc/crypto/sha256-spe-glue.c
+++ /dev/null
@@ -1,235 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Glue code for SHA-256 implementation for SPE instructions (PPC)
- *
- * Based on generic implementation. The assembler module takes care 
- * about the SPE registers so it can run from interrupt context.
- *
- * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- */
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <asm/byteorder.h>
-#include <asm/switch_to.h>
-#include <linux/hardirq.h>
-
-/*
- * MAX_BYTES defines the number of bytes that are allowed to be processed
- * between preempt_disable() and preempt_enable(). SHA256 takes ~2,000
- * operations per 64 bytes. e500 cores can issue two arithmetic instructions
- * per clock cycle using one 32/64 bit unit (SU1) and one 32 bit unit (SU2).
- * Thus 1KB of input data will need an estimated maximum of 18,000 cycles.
- * Headroom for cache misses included. Even with the low end model clocked
- * at 667 MHz this equals to a critical time window of less than 27us.
- *
- */
-#define MAX_BYTES 1024
-
-extern void ppc_spe_sha256_transform(u32 *state, const u8 *src, u32 blocks);
-
-static void spe_begin(void)
-{
-	/* We just start SPE operations and will save SPE registers later. */
-	preempt_disable();
-	enable_kernel_spe();
-}
-
-static void spe_end(void)
-{
-	disable_kernel_spe();
-	/* reenable preemption */
-	preempt_enable();
-}
-
-static inline void ppc_sha256_clear_context(struct sha256_state *sctx)
-{
-	int count = sizeof(struct sha256_state) >> 2;
-	u32 *ptr = (u32 *)sctx;
-
-	/* make sure we can clear the fast way */
-	BUILD_BUG_ON(sizeof(struct sha256_state) % 4);
-	do { *ptr++ = 0; } while (--count);
-}
-
-static int ppc_spe_sha256_update(struct shash_desc *desc, const u8 *data,
-			unsigned int len)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->count & 0x3f;
-	const unsigned int avail = 64 - offset;
-	unsigned int bytes;
-	const u8 *src = data;
-
-	if (avail > len) {
-		sctx->count += len;
-		memcpy((char *)sctx->buf + offset, src, len);
-		return 0;
-	}
-
-	sctx->count += len;
-
-	if (offset) {
-		memcpy((char *)sctx->buf + offset, src, avail);
-
-		spe_begin();
-		ppc_spe_sha256_transform(sctx->state, (const u8 *)sctx->buf, 1);
-		spe_end();
-
-		len -= avail;
-		src += avail;
-	}
-
-	while (len > 63) {
-		/* cut input data into smaller blocks */
-		bytes = (len > MAX_BYTES) ? MAX_BYTES : len;
-		bytes = bytes & ~0x3f;
-
-		spe_begin();
-		ppc_spe_sha256_transform(sctx->state, src, bytes >> 6);
-		spe_end();
-
-		src += bytes;
-		len -= bytes;
-	}
-
-	memcpy((char *)sctx->buf, src, len);
-	return 0;
-}
-
-static int ppc_spe_sha256_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	const unsigned int offset = sctx->count & 0x3f;
-	char *p = (char *)sctx->buf + offset;
-	int padlen;
-	__be64 *pbits = (__be64 *)(((char *)&sctx->buf) + 56);
-	__be32 *dst = (__be32 *)out;
-
-	padlen = 55 - offset;
-	*p++ = 0x80;
-
-	spe_begin();
-
-	if (padlen < 0) {
-		memset(p, 0x00, padlen + sizeof (u64));
-		ppc_spe_sha256_transform(sctx->state, sctx->buf, 1);
-		p = (char *)sctx->buf;
-		padlen = 56;
-	}
-
-	memset(p, 0, padlen);
-	*pbits = cpu_to_be64(sctx->count << 3);
-	ppc_spe_sha256_transform(sctx->state, sctx->buf, 1);
-
-	spe_end();
-
-	dst[0] = cpu_to_be32(sctx->state[0]);
-	dst[1] = cpu_to_be32(sctx->state[1]);
-	dst[2] = cpu_to_be32(sctx->state[2]);
-	dst[3] = cpu_to_be32(sctx->state[3]);
-	dst[4] = cpu_to_be32(sctx->state[4]);
-	dst[5] = cpu_to_be32(sctx->state[5]);
-	dst[6] = cpu_to_be32(sctx->state[6]);
-	dst[7] = cpu_to_be32(sctx->state[7]);
-
-	ppc_sha256_clear_context(sctx);
-	return 0;
-}
-
-static int ppc_spe_sha224_final(struct shash_desc *desc, u8 *out)
-{
-	__be32 D[SHA256_DIGEST_SIZE >> 2];
-	__be32 *dst = (__be32 *)out;
-
-	ppc_spe_sha256_final(desc, (u8 *)D);
-
-	/* avoid bytewise memcpy */
-	dst[0] = D[0];
-	dst[1] = D[1];
-	dst[2] = D[2];
-	dst[3] = D[3];
-	dst[4] = D[4];
-	dst[5] = D[5];
-	dst[6] = D[6];
-
-	/* clear sensitive data */
-	memzero_explicit(D, SHA256_DIGEST_SIZE);
-	return 0;
-}
-
-static int ppc_spe_sha256_export(struct shash_desc *desc, void *out)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-	return 0;
-}
-
-static int ppc_spe_sha256_import(struct shash_desc *desc, const void *in)
-{
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-	return 0;
-}
-
-static struct shash_alg algs[2] = { {
-	.digestsize	=	SHA256_DIGEST_SIZE,
-	.init		=	sha256_base_init,
-	.update		=	ppc_spe_sha256_update,
-	.final		=	ppc_spe_sha256_final,
-	.export		=	ppc_spe_sha256_export,
-	.import		=	ppc_spe_sha256_import,
-	.descsize	=	sizeof(struct sha256_state),
-	.statesize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha256",
-		.cra_driver_name=	"sha256-ppc-spe",
-		.cra_priority	=	300,
-		.cra_blocksize	=	SHA256_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-}, {
-	.digestsize	=	SHA224_DIGEST_SIZE,
-	.init		=	sha224_base_init,
-	.update		=	ppc_spe_sha256_update,
-	.final		=	ppc_spe_sha224_final,
-	.export		=	ppc_spe_sha256_export,
-	.import		=	ppc_spe_sha256_import,
-	.descsize	=	sizeof(struct sha256_state),
-	.statesize	=	sizeof(struct sha256_state),
-	.base		=	{
-		.cra_name	=	"sha224",
-		.cra_driver_name=	"sha224-ppc-spe",
-		.cra_priority	=	300,
-		.cra_blocksize	=	SHA224_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int __init ppc_spe_sha256_mod_init(void)
-{
-	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit ppc_spe_sha256_mod_fini(void)
-{
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_init(ppc_spe_sha256_mod_init);
-module_exit(ppc_spe_sha256_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, SPE optimized");
-
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_ALIAS_CRYPTO("sha224-ppc-spe");
-MODULE_ALIAS_CRYPTO("sha256");
-MODULE_ALIAS_CRYPTO("sha256-ppc-spe");
diff --git a/arch/powerpc/crypto/vmx.c b/arch/powerpc/crypto/vmx.c
new file mode 100644
index 000000000000..0b725e826388
--- /dev/null
+++ b/arch/powerpc/crypto/vmx.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Routines supporting VMX instructions on the Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * Author: Marcelo Henrique Cerri <mhcerri@br.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <asm/cputable.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
+
+#include "aesp8-ppc.h"
+
+static int __init p8_init(void)
+{
+	int ret;
+
+	ret = crypto_register_shash(&p8_ghash_alg);
+	if (ret)
+		goto err;
+
+	ret = crypto_register_alg(&p8_aes_alg);
+	if (ret)
+		goto err_unregister_ghash;
+
+	ret = crypto_register_skcipher(&p8_aes_cbc_alg);
+	if (ret)
+		goto err_unregister_aes;
+
+	ret = crypto_register_skcipher(&p8_aes_ctr_alg);
+	if (ret)
+		goto err_unregister_aes_cbc;
+
+	ret = crypto_register_skcipher(&p8_aes_xts_alg);
+	if (ret)
+		goto err_unregister_aes_ctr;
+
+	return 0;
+
+err_unregister_aes_ctr:
+	crypto_unregister_skcipher(&p8_aes_ctr_alg);
+err_unregister_aes_cbc:
+	crypto_unregister_skcipher(&p8_aes_cbc_alg);
+err_unregister_aes:
+	crypto_unregister_alg(&p8_aes_alg);
+err_unregister_ghash:
+	crypto_unregister_shash(&p8_ghash_alg);
+err:
+	return ret;
+}
+
+static void __exit p8_exit(void)
+{
+	crypto_unregister_skcipher(&p8_aes_xts_alg);
+	crypto_unregister_skcipher(&p8_aes_ctr_alg);
+	crypto_unregister_skcipher(&p8_aes_cbc_alg);
+	crypto_unregister_alg(&p8_aes_alg);
+	crypto_unregister_shash(&p8_ghash_alg);
+}
+
+module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, p8_init);
+module_exit(p8_exit);
+
+MODULE_AUTHOR("Marcelo Cerri<mhcerri@br.ibm.com>");
+MODULE_DESCRIPTION("IBM VMX cryptographic acceleration instructions "
+		   "support on Power 8");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0.0");
+MODULE_IMPORT_NS("CRYPTO_INTERNAL");
diff --git a/arch/powerpc/include/asm/8xx_immap.h b/arch/powerpc/include/asm/8xx_immap.h
index bdf0563ba423..f9cac46a95cb 100644
--- a/arch/powerpc/include/asm/8xx_immap.h
+++ b/arch/powerpc/include/asm/8xx_immap.h
@@ -560,5 +560,7 @@ typedef struct immap {
 	cpm8xx_t	im_cpm;		/* Communication processor */
 } immap_t;
 
+extern immap_t __iomem *mpc8xx_immr;
+
 #endif /* __IMMAP_8XX__ */
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 419319c4963c..2e23533b67e3 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -3,9 +3,6 @@ generated-y += syscall_table_32.h
 generated-y += syscall_table_64.h
 generated-y += syscall_table_spu.h
 generic-y += agp.h
-generic-y += export.h
-generic-y += kvm_types.h
 generic-y += mcs_spinlock.h
 generic-y += qrwlock.h
-generic-y += vtime.h
 generic-y += early_ioremap.h
diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index 2bc53c646ccd..f48e644900a2 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -26,19 +26,23 @@
 #define PPC_MIN_STKFRM	112
 
 #ifdef __BIG_ENDIAN__
-#define LHZX_BE	stringify_in_c(lhzx)
 #define LWZX_BE	stringify_in_c(lwzx)
 #define LDX_BE	stringify_in_c(ldx)
 #define STWX_BE	stringify_in_c(stwx)
 #define STDX_BE	stringify_in_c(stdx)
 #else
-#define LHZX_BE	stringify_in_c(lhbrx)
 #define LWZX_BE	stringify_in_c(lwbrx)
 #define LDX_BE	stringify_in_c(ldbrx)
 #define STWX_BE	stringify_in_c(stwbrx)
 #define STDX_BE	stringify_in_c(stdbrx)
 #endif
 
+#ifdef CONFIG_CC_IS_CLANG
+#define DS_FORM_CONSTRAINT "Z<>"
+#else
+#define DS_FORM_CONSTRAINT "YZ<>"
+#endif
+
 #else /* 32-bit */
 
 /* operations for longs and pointers */
diff --git a/arch/powerpc/include/asm/asm-const.h b/arch/powerpc/include/asm/asm-const.h
index bfb3c3534877..392bdb1f104f 100644
--- a/arch/powerpc/include/asm/asm-const.h
+++ b/arch/powerpc/include/asm/asm-const.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_POWERPC_ASM_CONST_H
 #define _ASM_POWERPC_ASM_CONST_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #  define stringify_in_c(...)	__VA_ARGS__
 #  define ASM_CONST(x)		x
 #else
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 47228b177478..d1ea554c33ed 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -11,6 +11,7 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 #include <asm/asm-const.h>
+#include <asm/asm-compat.h>
 
 /*
  * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with
@@ -126,18 +127,6 @@ ATOMIC_OPS(xor, xor, "", K)
 #undef ATOMIC_OP_RETURN_RELAXED
 #undef ATOMIC_OP
 
-#define arch_atomic_cmpxchg(v, o, n) \
-	(arch_cmpxchg(&((v)->counter), (o), (n)))
-#define arch_atomic_cmpxchg_relaxed(v, o, n) \
-	arch_cmpxchg_relaxed(&((v)->counter), (o), (n))
-#define arch_atomic_cmpxchg_acquire(v, o, n) \
-	arch_cmpxchg_acquire(&((v)->counter), (o), (n))
-
-#define arch_atomic_xchg(v, new) \
-	(arch_xchg(&((v)->counter), new))
-#define arch_atomic_xchg_relaxed(v, new) \
-	arch_xchg_relaxed(&((v)->counter), (new))
-
 /**
  * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
@@ -209,7 +198,7 @@ static __inline__ s64 arch_atomic64_read(const atomic64_t *v)
 	if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
 		__asm__ __volatile__("ld %0,0(%1)" : "=r"(t) : "b"(&v->counter));
 	else
-		__asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter));
+		__asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : DS_FORM_CONSTRAINT (v->counter));
 
 	return t;
 }
@@ -220,7 +209,7 @@ static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i)
 	if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
 		__asm__ __volatile__("std %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter));
 	else
-		__asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i));
+		__asm__ __volatile__("std%U0%X0 %1,%0" : "=" DS_FORM_CONSTRAINT (v->counter) : "r"(i));
 }
 
 #define ATOMIC64_OP(op, asm_op)						\
@@ -396,18 +385,6 @@ static __inline__ s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 }
 #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
 
-#define arch_atomic64_cmpxchg(v, o, n) \
-	(arch_cmpxchg(&((v)->counter), (o), (n)))
-#define arch_atomic64_cmpxchg_relaxed(v, o, n) \
-	arch_cmpxchg_relaxed(&((v)->counter), (o), (n))
-#define arch_atomic64_cmpxchg_acquire(v, o, n) \
-	arch_cmpxchg_acquire(&((v)->counter), (o), (n))
-
-#define arch_atomic64_xchg(v, new) \
-	(arch_xchg(&((v)->counter), new))
-#define arch_atomic64_xchg_relaxed(v, new) \
-	arch_xchg_relaxed(&((v)->counter), (new))
-
 /**
  * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
diff --git a/arch/powerpc/include/asm/backlight.h b/arch/powerpc/include/asm/backlight.h
index 1b5eab62ed04..061a910d7492 100644
--- a/arch/powerpc/include/asm/backlight.h
+++ b/arch/powerpc/include/asm/backlight.h
@@ -10,15 +10,14 @@
 #define __ASM_POWERPC_BACKLIGHT_H
 #ifdef __KERNEL__
 
-#include <linux/fb.h>
 #include <linux/mutex.h>
 
+struct backlight_device;
+
 /* For locking instructions, see the implementation file */
 extern struct backlight_device *pmac_backlight;
 extern struct mutex pmac_backlight_mutex;
 
-extern int pmac_backlight_curve_lookup(struct fb_info *info, int value);
-
 extern int pmac_has_backlight_type(const char *type);
 
 extern void pmac_backlight_key(int direction);
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index b95b666f0374..9e9833faa4af 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -7,7 +7,7 @@
 
 #include <asm/asm-const.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/ppc-opcode.h>
 #endif
 
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 7e0f0322912b..0d0470cd5ac3 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -233,35 +233,24 @@ static inline int arch_test_and_change_bit(unsigned long nr,
 	return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
 }
 
-#ifdef CONFIG_PPC64
-static inline unsigned long
-clear_bit_unlock_return_word(int nr, volatile unsigned long *addr)
+static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
 {
 	unsigned long old, t;
-	unsigned long *p = (unsigned long *)addr + BIT_WORD(nr);
-	unsigned long mask = BIT_MASK(nr);
 
 	__asm__ __volatile__ (
 	PPC_RELEASE_BARRIER
 "1:"	PPC_LLARX "%0,0,%3,0\n"
-	"andc %1,%0,%2\n"
+	"xor %1,%0,%2\n"
 	PPC_STLCX "%1,0,%3\n"
 	"bne- 1b\n"
 	: "=&r" (old), "=&r" (t)
 	: "r" (mask), "r" (p)
 	: "cc", "memory");
 
-	return old;
+	return (old & BIT_MASK(7)) != 0;
 }
-
-/*
- * This is a special function for mm/filemap.c
- * Bit 7 corresponds to PG_waiters.
- */
-#define arch_clear_bit_unlock_is_negative_byte(nr, addr)		\
-	(clear_bit_unlock_return_word(nr, addr) & BIT_MASK(7))
-
-#endif /* CONFIG_PPC64 */
+#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte
 
 #include <asm-generic/bitops/non-atomic.h>
 
@@ -287,7 +276,7 @@ static inline void arch___clear_bit_unlock(int nr, volatile unsigned long *addr)
  * fls: find last (most-significant) bit set.
  * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
  */
-static __always_inline int fls(unsigned int x)
+static __always_inline __attribute_const__ int fls(unsigned int x)
 {
 	int lz;
 
@@ -305,7 +294,7 @@ static __always_inline int fls(unsigned int x)
  * 32-bit fls calls.
  */
 #ifdef CONFIG_PPC64
-static __always_inline int fls64(__u64 x)
+static __always_inline __attribute_const__ int fls64(__u64 x)
 {
 	int lz;
 
diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index 678f9c9d89b6..873c5146e326 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -7,81 +7,55 @@
 #include <asm/mmu.h>
 #include <asm/synch.h>
 
-#ifndef __ASSEMBLY__
-
-#include <linux/jump_label.h>
-
-extern struct static_key_false disable_kuap_key;
-
-static __always_inline bool kuep_is_disabled(void)
-{
-	return !IS_ENABLED(CONFIG_PPC_KUEP);
-}
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_PPC_KUAP
 
 #include <linux/sched.h>
 
 #define KUAP_NONE	(~0UL)
-#define KUAP_ALL	(~1UL)
 
-static __always_inline bool kuap_is_disabled(void)
-{
-	return static_branch_unlikely(&disable_kuap_key);
-}
-
-static inline void kuap_lock_one(unsigned long addr)
+static __always_inline void kuap_lock_one(unsigned long addr)
 {
 	mtsr(mfsr(addr) | SR_KS, addr);
 	isync();	/* Context sync required after mtsr() */
 }
 
-static inline void kuap_unlock_one(unsigned long addr)
+static __always_inline void kuap_unlock_one(unsigned long addr)
 {
 	mtsr(mfsr(addr) & ~SR_KS, addr);
 	isync();	/* Context sync required after mtsr() */
 }
 
-static inline void kuap_lock_all(void)
+static __always_inline void uaccess_begin_32s(unsigned long addr)
 {
-	update_user_segments(mfsr(0) | SR_KS);
-	isync();	/* Context sync required after mtsr() */
-}
+	unsigned long tmp;
 
-static inline void kuap_unlock_all(void)
-{
-	update_user_segments(mfsr(0) & ~SR_KS);
-	isync();	/* Context sync required after mtsr() */
+	asm volatile(ASM_MMU_FTR_IFSET(
+		"mfsrin %0, %1;"
+		"rlwinm %0, %0, 0, %2;"
+		"mtsrin %0, %1;"
+		"isync", "", %3)
+		: "=&r"(tmp)
+		: "r"(addr), "i"(~SR_KS), "i"(MMU_FTR_KUAP)
+		: "memory");
 }
 
-void kuap_lock_all_ool(void);
-void kuap_unlock_all_ool(void);
-
-static inline void kuap_lock_addr(unsigned long addr, bool ool)
+static __always_inline void uaccess_end_32s(unsigned long addr)
 {
-	if (likely(addr != KUAP_ALL))
-		kuap_lock_one(addr);
-	else if (!ool)
-		kuap_lock_all();
-	else
-		kuap_lock_all_ool();
-}
+	unsigned long tmp;
 
-static inline void kuap_unlock(unsigned long addr, bool ool)
-{
-	if (likely(addr != KUAP_ALL))
-		kuap_unlock_one(addr);
-	else if (!ool)
-		kuap_unlock_all();
-	else
-		kuap_unlock_all_ool();
+	asm volatile(ASM_MMU_FTR_IFSET(
+		"mfsrin %0, %1;"
+		"oris %0, %0, %2;"
+		"mtsrin %0, %1;"
+		"isync", "", %3)
+		: "=&r"(tmp)
+		: "r"(addr), "i"(SR_KS >> 16), "i"(MMU_FTR_KUAP)
+		: "memory");
 }
 
-static inline void __kuap_lock(void)
-{
-}
-
-static inline void __kuap_save_and_lock(struct pt_regs *regs)
+static __always_inline void __kuap_save_and_lock(struct pt_regs *regs)
 {
 	unsigned long kuap = current->thread.kuap;
 
@@ -90,18 +64,19 @@ static inline void __kuap_save_and_lock(struct pt_regs *regs)
 		return;
 
 	current->thread.kuap = KUAP_NONE;
-	kuap_lock_addr(kuap, false);
+	kuap_lock_one(kuap);
 }
+#define __kuap_save_and_lock __kuap_save_and_lock
 
-static inline void kuap_user_restore(struct pt_regs *regs)
+static __always_inline void kuap_user_restore(struct pt_regs *regs)
 {
 }
 
-static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
+static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
 {
 	if (unlikely(kuap != KUAP_NONE)) {
 		current->thread.kuap = KUAP_NONE;
-		kuap_lock_addr(kuap, false);
+		kuap_lock_one(kuap);
 	}
 
 	if (likely(regs->kuap == KUAP_NONE))
@@ -109,10 +84,10 @@ static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kua
 
 	current->thread.kuap = regs->kuap;
 
-	kuap_unlock(regs->kuap, false);
+	kuap_unlock_one(regs->kuap);
 }
 
-static inline unsigned long __kuap_get_and_assert_locked(void)
+static __always_inline unsigned long __kuap_get_and_assert_locked(void)
 {
 	unsigned long kuap = current->thread.kuap;
 
@@ -120,9 +95,10 @@ static inline unsigned long __kuap_get_and_assert_locked(void)
 
 	return kuap;
 }
+#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked
 
-static __always_inline void __allow_user_access(void __user *to, const void __user *from,
-						u32 size, unsigned long dir)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      u32 size, unsigned long dir)
 {
 	BUILD_BUG_ON(!__builtin_constant_p(dir));
 
@@ -130,10 +106,10 @@ static __always_inline void __allow_user_access(void __user *to, const void __us
 		return;
 
 	current->thread.kuap = (__force u32)to;
-	kuap_unlock_one((__force u32)to);
+	uaccess_begin_32s((__force u32)to);
 }
 
-static __always_inline void __prevent_user_access(unsigned long dir)
+static __always_inline void prevent_user_access(unsigned long dir)
 {
 	u32 kuap = current->thread.kuap;
 
@@ -143,48 +119,57 @@ static __always_inline void __prevent_user_access(unsigned long dir)
 		return;
 
 	current->thread.kuap = KUAP_NONE;
-	kuap_lock_addr(kuap, true);
+	uaccess_end_32s(kuap);
 }
 
-static inline unsigned long __prevent_user_access_return(void)
+static __always_inline unsigned long prevent_user_access_return(void)
 {
 	unsigned long flags = current->thread.kuap;
 
 	if (flags != KUAP_NONE) {
 		current->thread.kuap = KUAP_NONE;
-		kuap_lock_addr(flags, true);
+		uaccess_end_32s(flags);
 	}
 
 	return flags;
 }
 
-static inline void __restore_user_access(unsigned long flags)
+static __always_inline void restore_user_access(unsigned long flags)
 {
 	if (flags != KUAP_NONE) {
 		current->thread.kuap = flags;
-		kuap_unlock(flags, true);
+		uaccess_begin_32s(flags);
 	}
 }
 
-static inline bool
+static __always_inline bool
 __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	unsigned long kuap = regs->kuap;
 
-	if (!is_write || kuap == KUAP_ALL)
+	if (!is_write)
 		return false;
 	if (kuap == KUAP_NONE)
 		return true;
 
-	/* If faulting address doesn't match unlocked segment, unlock all */
-	if ((kuap ^ address) & 0xf0000000)
-		regs->kuap = KUAP_ALL;
+	/*
+	 * If faulting address doesn't match unlocked segment, change segment.
+	 * In case of unaligned store crossing two segments, emulate store.
+	 */
+	if ((kuap ^ address) & 0xf0000000) {
+		if (!(kuap & 0x0fffffff) && address > kuap - 4 && fix_alignment(regs)) {
+			regs_add_return_ip(regs, 4);
+			emulate_single_step(regs);
+		} else {
+			regs->kuap = address;
+		}
+	}
 
 	return false;
 }
 
 #endif /* CONFIG_PPC_KUAP */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_32_KUP_H */
diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h
index 78c6a5fde1d6..8435bf3cdabf 100644
--- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h
@@ -29,7 +29,7 @@
 #define BPP_RX	0x01		/* Read only */
 #define BPP_RW	0x02		/* Read/write */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /* Contort a phys_addr_t into the right format/bits for a BAT */
 #ifdef CONFIG_PHYS_64BIT
 #define BAT_PHYS_ADDR(x) ((u32)((x & 0x00000000fffe0000ULL) | \
@@ -47,7 +47,7 @@ struct ppc_bat {
 	u32 batu;
 	u32 batl;
 };
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * Hash table
@@ -64,7 +64,7 @@ struct ppc_bat {
 #define SR_KP	0x20000000	/* User key */
 #define SR_KS	0x40000000	/* Supervisor key */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/asm-offsets.h>
 
@@ -225,7 +225,7 @@ static __always_inline void update_user_segments(u32 val)
 
 int __init find_free_bat(void);
 unsigned int bat_block_size(unsigned long base, unsigned long top);
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* We happily ignore the smaller BATs on 601, we don't actually use
  * those definitions on hash32 at the moment anyway
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index dc5c039eb28e..f4390704d5ba 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -7,8 +7,14 @@
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
-			pgtable_gfp_flags(mm, GFP_KERNEL));
+	pgd_t *pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+				      pgtable_gfp_flags(mm, GFP_KERNEL));
+
+#ifdef CONFIG_PPC_BOOK3S_603
+	memcpy(pgd + USER_PTRS_PER_PGD, swapper_pg_dir + USER_PTRS_PER_PGD,
+	       (MAX_PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+#endif
+	return pgd;
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -47,8 +53,6 @@ static inline void pgtable_free(void *table, unsigned index_size)
 	}
 }
 
-#define get_hugepd_cache_index(x)  (x)
-
 static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 				    void *table, int shift)
 {
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 7bf1fe7297c6..87dcca962be7 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -20,7 +20,7 @@
 
 #define _PAGE_PRESENT	0x001	/* software: pte contains a translation */
 #define _PAGE_HASHPTE	0x002	/* hash_page has made an HPTE for this pte */
-#define _PAGE_USER	0x004	/* usermode access allowed */
+#define _PAGE_READ	0x004	/* software: read access allowed */
 #define _PAGE_GUARDED	0x008	/* G: prohibit speculative access */
 #define _PAGE_COHERENT	0x010	/* M: enforce memory coherence (SMP systems) */
 #define _PAGE_NO_CACHE	0x020	/* I: cache inhibit */
@@ -28,7 +28,7 @@
 #define _PAGE_DIRTY	0x080	/* C: page changed */
 #define _PAGE_ACCESSED	0x100	/* R: page referenced */
 #define _PAGE_EXEC	0x200	/* software: exec allowed */
-#define _PAGE_RW	0x400	/* software: user write access allowed */
+#define _PAGE_WRITE	0x400	/* software: user write access allowed */
 #define _PAGE_SPECIAL	0x800	/* software: Special page */
 
 #ifdef CONFIG_PTE_64BIT
@@ -42,26 +42,13 @@
 #define _PMD_PRESENT_MASK (PAGE_MASK)
 #define _PMD_BAD	(~PAGE_MASK)
 
-/* We borrow the _PAGE_USER bit to store the exclusive marker in swap PTEs. */
-#define _PAGE_SWP_EXCLUSIVE	_PAGE_USER
+/* We borrow the _PAGE_READ bit to store the exclusive marker in swap PTEs. */
+#define _PAGE_SWP_EXCLUSIVE	_PAGE_READ
 
 /* And here we include common definitions */
 
-#define _PAGE_KERNEL_RO		0
-#define _PAGE_KERNEL_ROX	(_PAGE_EXEC)
-#define _PAGE_KERNEL_RW		(_PAGE_DIRTY | _PAGE_RW)
-#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC)
-
 #define _PAGE_HPTEFLAGS _PAGE_HASHPTE
 
-#ifndef __ASSEMBLY__
-
-static inline bool pte_user(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_USER;
-}
-#endif /* __ASSEMBLY__ */
-
 /*
  * Location of the PFN in the PTE. Most 32-bit platforms use the same
  * as _PAGE_SHIFT here (ie, naturally aligned).
@@ -97,20 +84,7 @@ static inline bool pte_user(pte_t pte)
 #define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED)
 #define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
 
-/*
- * Permission masks used to generate the __P and __S table.
- *
- * Note:__pgprot is defined in arch/powerpc/include/asm/page.h
- *
- * Write permissions imply read permissions for now.
- */
-#define PAGE_NONE	__pgprot(_PAGE_BASE)
-#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
-#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC)
-#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+#include <asm/pgtable-masks.h>
 
 /* Permission masks used for kernel mappings */
 #define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW)
@@ -128,7 +102,7 @@ static inline bool pte_user(pte_t pte)
 #define PMD_CACHE_INDEX	PMD_INDEX_SIZE
 #define PUD_CACHE_INDEX	PUD_INDEX_SIZE
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
 #define PMD_TABLE_SIZE	0
 #define PUD_TABLE_SIZE	0
@@ -136,7 +110,7 @@ static inline bool pte_user(pte_t pte)
 
 /* Bits to mask out from a PMD to get to the PTE page */
 #define PMD_MASKED_BITS		(PTE_TABLE_SIZE - 1)
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
 #define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
@@ -158,19 +132,26 @@ static inline bool pte_user(pte_t pte)
 
 #define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
 void unmap_kernel_page(unsigned long va);
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
  * value (for now) on others, from where we can start layout kernel
  * virtual space that goes below PKMAP and FIXMAP
  */
-#include <asm/fixmap.h>
+
+#define FIXADDR_SIZE	0
+#ifdef CONFIG_KASAN
+#include <asm/kasan.h>
+#define FIXADDR_TOP	(KASAN_SHADOW_START - PAGE_SIZE)
+#else
+#define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
+#endif
 
 /*
  * ioremap_bot starts at that address. Early ioremaps move down from there,
@@ -215,18 +196,16 @@ void unmap_kernel_page(unsigned long va);
 #endif
 
 #define MODULES_END	ALIGN_DOWN(PAGE_OFFSET, SZ_256M)
-#define MODULES_VADDR	(MODULES_END - SZ_256M)
+#define MODULES_SIZE	(CONFIG_MODULES_SIZE * SZ_1M)
+#define MODULES_VADDR	(MODULES_END - MODULES_SIZE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/sched.h>
 #include <linux/threads.h>
 
 /* Bits to mask out from a PGD to get to the PUD page */
 #define PGD_MASKED_BITS		0
 
-#define pte_ERROR(e) \
-	pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
-		(unsigned long long)pte_val(e))
 #define pgd_ERROR(e) \
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 /*
@@ -343,7 +322,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
+	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
 }
 
 static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
@@ -386,7 +365,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
@@ -402,8 +381,16 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 }
 
 /* Generic accessors to PTE bits */
-static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_RW);}
-static inline int pte_read(pte_t pte)		{ return 1; }
+static inline bool pte_read(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_READ);
+}
+
+static inline bool pte_write(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_WRITE);
+}
+
 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); }
@@ -438,10 +425,10 @@ static inline bool pte_ci(pte_t pte)
 static inline bool pte_access_permitted(pte_t pte, bool write)
 {
 	/*
-	 * A read-only access is controlled by _PAGE_USER bit.
-	 * We have _PAGE_READ set for WRITE and EXECUTE
+	 * A read-only access is controlled by _PAGE_READ bit.
+	 * We have _PAGE_READ set for WRITE
 	 */
-	if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte))
+	if (!pte_present(pte) || !pte_read(pte))
 		return false;
 
 	if (write && !pte_write(pte))
@@ -462,15 +449,10 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
 		     pgprot_val(pgprot));
 }
 
-static inline unsigned long pte_pfn(pte_t pte)
-{
-	return pte_val(pte) >> PTE_RPN_SHIFT;
-}
-
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_RW);
+	return __pte(pte_val(pte) & ~_PAGE_WRITE);
 }
 
 static inline pte_t pte_exprotect(pte_t pte)
@@ -498,8 +480,11 @@ static inline pte_t pte_mkpte(pte_t pte)
 	return pte;
 }
 
-static inline pte_t pte_mkwrite(pte_t pte)
+static inline pte_t pte_mkwrite_novma(pte_t pte)
 {
+	/*
+	 * write implies read, hence set both
+	 */
 	return __pte(pte_val(pte) | _PAGE_RW);
 }
 
@@ -523,16 +508,6 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
-static inline pte_t pte_mkprivileged(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_USER);
-}
-
-static inline pte_t pte_mkuser(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_USER);
-}
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
@@ -541,58 +516,43 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 
 /* This low level function performs the actual PTE insertion
- * Setting the PTE depends on the MMU type and other factors. It's
- * an horrible mess that I'm not going to try to clean up now but
- * I'm keeping it in one place rather than spread around
+ * Setting the PTE depends on the MMU type and other factors.
+ *
+ * First case is 32-bit in UP mode with 32-bit PTEs, we need to preserve
+ * the _PAGE_HASHPTE bit since we may not have invalidated the previous
+ * translation in the hash yet (done in a subsequent flush_tlb_xxx())
+ * and see we need to keep track that this PTE needs invalidating.
+ *
+ * Second case is 32-bit with 64-bit PTE.  In this case, we
+ * can just store as long as we do the two halves in the right order
+ * with a barrier in between. This is possible because we take care,
+ * in the hash code, to pre-invalidate if the PTE was already hashed,
+ * which synchronizes us with any concurrent invalidation.
+ * In the percpu case, we fallback to the simple update preserving
+ * the hash bits (ie, same as the non-SMP case).
+ *
+ * Third case is 32-bit in SMP mode with 32-bit PTEs. We use the
+ * helper pte_update() which does an atomic update. We need to do that
+ * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
+ * per-CPU PTE such as a kmap_atomic, we also do a simple update preserving
+ * the hash bits instead.
  */
 static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, pte_t pte, int percpu)
 {
-#if defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT)
-	/* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the
-	 * helper pte_update() which does an atomic update. We need to do that
-	 * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
-	 * per-CPU PTE such as a kmap_atomic, we do a simple update preserving
-	 * the hash bits instead (ie, same as the non-SMP case)
-	 */
-	if (percpu)
-		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
-			      | (pte_val(pte) & ~_PAGE_HASHPTE));
-	else
-		pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0);
+	if ((!IS_ENABLED(CONFIG_SMP) && !IS_ENABLED(CONFIG_PTE_64BIT)) || percpu) {
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) |
+			      (pte_val(pte) & ~_PAGE_HASHPTE));
+	} else if (IS_ENABLED(CONFIG_PTE_64BIT)) {
+		if (pte_val(*ptep) & _PAGE_HASHPTE)
+			flush_hash_entry(mm, ptep, addr);
 
-#elif defined(CONFIG_PTE_64BIT)
-	/* Second case is 32-bit with 64-bit PTE.  In this case, we
-	 * can just store as long as we do the two halves in the right order
-	 * with a barrier in between. This is possible because we take care,
-	 * in the hash code, to pre-invalidate if the PTE was already hashed,
-	 * which synchronizes us with any concurrent invalidation.
-	 * In the percpu case, we also fallback to the simple update preserving
-	 * the hash bits
-	 */
-	if (percpu) {
-		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
-			      | (pte_val(pte) & ~_PAGE_HASHPTE));
-		return;
+		asm volatile("stw%X0 %2,%0; eieio; stw%X1 %L2,%1" :
+			     "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) :
+			     "r" (pte) : "memory");
+	} else {
+		pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0);
 	}
-	if (pte_val(*ptep) & _PAGE_HASHPTE)
-		flush_hash_entry(mm, ptep, addr);
-	__asm__ __volatile__("\
-		stw%X0 %2,%0\n\
-		eieio\n\
-		stw%X1 %L2,%1"
-	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
-	: "r" (pte) : "memory");
-
-#else
-	/* Third case is 32-bit hash table in UP mode, we need to preserve
-	 * the _PAGE_HASHPTE bit since we may not have invalidated the previous
-	 * translation in the hash yet (done in a subsequent flush_tlb_xxx())
-	 * and see we need to keep track that this PTE needs invalidating
-	 */
-	*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
-		      | (pte_val(pte) & ~_PAGE_HASHPTE));
-#endif
 }
 
 /*
@@ -642,6 +602,6 @@ static inline pgprot_t pgprot_writecombine(pgprot_t prot)
 	return pgprot_noncached_wc(prot);
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /*  _ASM_POWERPC_BOOK3S_32_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/book3s/32/tlbflush.h b/arch/powerpc/include/asm/book3s/32/tlbflush.h
index 4be572908124..4be2200a3c7e 100644
--- a/arch/powerpc/include/asm/book3s/32/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/32/tlbflush.h
@@ -11,6 +11,7 @@
 void hash__flush_tlb_mm(struct mm_struct *mm);
 void hash__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 void hash__flush_range(struct mm_struct *mm, unsigned long start, unsigned long end);
+void hash__flush_gather(struct mmu_gather *tlb);
 
 #ifdef CONFIG_SMP
 void _tlbie(unsigned long address);
@@ -29,7 +30,9 @@ void _tlbia(void);
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	/* 603 needs to flush the whole TLB here since it doesn't use a hash table. */
-	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE))
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		hash__flush_gather(tlb);
+	else
 		_tlbia();
 }
 
@@ -80,7 +83,7 @@ static inline void local_flush_tlb_page(struct vm_area_struct *vma,
 static inline void local_flush_tlb_page_psize(struct mm_struct *mm,
 					      unsigned long vmaddr, int psize)
 {
-	BUILD_BUG();
+	flush_range(mm, vmaddr, vmaddr);
 }
 
 static inline void local_flush_tlb_mm(struct mm_struct *mm)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index b6ac4f86c87b..8e5bd9902bed 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -32,7 +32,7 @@
  */
 #define H_KERN_VIRT_START	ASM_CONST(0xc0003d0000000000)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)
 #define H_PMD_TABLE_SIZE	(sizeof(pmd_t) << H_PMD_INDEX_SIZE)
 #define H_PUD_TABLE_SIZE	(sizeof(pud_t) << H_PUD_INDEX_SIZE)
@@ -74,20 +74,33 @@
 #define remap_4k_pfn(vma, addr, pfn, prot)	\
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
 
-#ifdef CONFIG_HUGETLB_PAGE
-static inline int hash__hugepd_ok(hugepd_t hpd)
+/*
+ * With 4K page size the real_pte machinery is all nops.
+ */
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset)
 {
-	unsigned long hpdval = hpd_val(hpd);
-	/*
-	 * if it is not a pte and have hugepd shift mask
-	 * set, then it is a hugepd directory pointer
-	 */
-	if (!(hpdval & _PAGE_PTE) && (hpdval & _PAGE_PRESENT) &&
-	    ((hpdval & HUGEPD_SHIFT_MASK) != 0))
-		return true;
-	return false;
+	return (real_pte_t){pte};
 }
-#endif
+
+#define __rpte_to_pte(r)	((r).pte)
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	return pte_val(__rpte_to_pte(rpte)) >> H_PAGE_F_GIX_SHIFT;
+}
+
+#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
+	do {							         \
+		index = 0;					         \
+		shift = mmu_psize_defs[psize].shift;		         \
+
+#define pte_iterate_hashed_end() } while(0)
+
+/*
+ * We expect this to be called only for user addresses or kernel virtual
+ * addresses other than the linear mapping.
+ */
+#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
 
 /*
  * 4K PTE format is different from 64K PTE format. Saving the hash_slot is just
@@ -136,12 +149,6 @@ static inline int hash__pmd_trans_huge(pmd_t pmd)
 	return 0;
 }
 
-static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b)
-{
-	BUG();
-	return 0;
-}
-
 static inline pmd_t hash__pmd_mkhuge(pmd_t pmd)
 {
 	BUG();
@@ -161,12 +168,6 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 extern int hash__has_transparent_hugepage(void);
 #endif
 
-static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
-{
-	BUG();
-	return pmd;
-}
-
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 338e62fbea0b..7deb3a66890b 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -79,7 +79,7 @@
 #endif
 #define H_PMD_FRAG_NR	(PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/errno.h>
 
 /*
@@ -259,15 +259,10 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
  */
 static inline int hash__pmd_trans_huge(pmd_t pmd)
 {
-	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) ==
+	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) ==
 		  (_PAGE_PTE | H_PAGE_THP_HUGE));
 }
 
-static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b)
-{
-	return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0);
-}
-
 static inline pmd_t hash__pmd_mkhuge(pmd_t pmd)
 {
 	return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE));
@@ -286,11 +281,6 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 extern int hash__has_transparent_hugepage(void);
 #endif /*  CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
-{
-	return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP));
-}
-
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-pkey.h b/arch/powerpc/include/asm/book3s/64/hash-pkey.h
index f1e60d579f6c..6c5564c4fae4 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-pkey.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-pkey.h
@@ -24,7 +24,7 @@ static inline u64 pte_to_hpte_pkey_bits(u64 pteflags, unsigned long flags)
 		    ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) |
 		    ((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL));
 
-	if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP) ||
+	if (mmu_has_feature(MMU_FTR_KUAP) ||
 	    mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
 		if ((pte_pkey == 0) && (flags & HPTE_USE_KERNEL_KEY))
 			return HASH_DEFAULT_KERNEL_KEY;
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 17e7a778c856..5a8cbd496731 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -4,6 +4,7 @@
 #ifdef __KERNEL__
 
 #include <asm/asm-const.h>
+#include <asm/book3s/64/slice.h>
 
 /*
  * Common bits between 4K and 64K pages in a linux-style PTE.
@@ -111,7 +112,7 @@
 #define H_PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
 #define H_PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 static inline int get_region_id(unsigned long ea)
 {
 	int region_id;
@@ -132,8 +133,22 @@ static inline int get_region_id(unsigned long ea)
 	return region_id;
 }
 
+static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0);
+}
+
 #define	hash__pmd_bad(pmd)		(pmd_val(pmd) & H_PMD_BAD_BITS)
+
+/*
+ * pud comparison that will work with both pte and page table pointer.
+ */
+static inline int hash__pud_same(pud_t pud_a, pud_t pud_b)
+{
+	return (((pud_raw(pud_a) ^ pud_raw(pud_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0);
+}
 #define	hash__pud_bad(pud)		(pud_val(pud) & H_PUD_BAD_BITS)
+
 static inline int hash__p4d_bad(p4d_t p4d)
 {
 	return (p4d_val(p4d) == 0);
@@ -147,14 +162,10 @@ extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, unsigned long pte, int huge);
 unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags);
 /* Atomic PTE updates */
-static inline unsigned long hash__pte_update(struct mm_struct *mm,
-					 unsigned long addr,
-					 pte_t *ptep, unsigned long clr,
-					 unsigned long set,
-					 int huge)
+static inline unsigned long hash__pte_update_one(pte_t *ptep, unsigned long clr,
+						 unsigned long set)
 {
 	__be64 old_be, tmp_be;
-	unsigned long old;
 
 	__asm__ __volatile__(
 	"1:	ldarx	%0,0,%3		# pte_update\n\
@@ -168,11 +179,40 @@ static inline unsigned long hash__pte_update(struct mm_struct *mm,
 	: "r" (ptep), "r" (cpu_to_be64(clr)), "m" (*ptep),
 	  "r" (cpu_to_be64(H_PAGE_BUSY)), "r" (cpu_to_be64(set))
 	: "cc" );
+
+	return be64_to_cpu(old_be);
+}
+
+static inline unsigned long hash__pte_update(struct mm_struct *mm,
+					 unsigned long addr,
+					 pte_t *ptep, unsigned long clr,
+					 unsigned long set,
+					 int huge)
+{
+	unsigned long old;
+
+	old = hash__pte_update_one(ptep, clr, set);
+
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && huge) {
+		unsigned int psize = get_slice_psize(mm, addr);
+		int nb, i;
+
+		if (psize == MMU_PAGE_16M)
+			nb = SZ_16M / PMD_SIZE;
+		else if (psize == MMU_PAGE_16G)
+			nb = SZ_16G / PUD_SIZE;
+		else
+			nb = 1;
+
+		WARN_ON_ONCE(nb == 1);	/* Should never happen */
+
+		for (i = 1; i < nb; i++)
+			hash__pte_update_one(ptep + i, clr, set);
+	}
 	/* huge pages use the old page table lock */
 	if (!huge)
 		assert_pte_locked(mm, addr);
 
-	old = be64_to_cpu(old_be);
 	if (old & H_PAGE_HASHPTE)
 		hpte_need_flush(mm, addr, ptep, old, huge);
 
@@ -255,8 +295,6 @@ int hash__create_section_mapping(unsigned long start, unsigned long end,
 				 int nid, pgprot_t prot);
 int hash__remove_section_mapping(unsigned long start, unsigned long end);
 
-void hash__kernel_map_pages(struct page *page, int numpages, int enable);
-
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index aa1c67c8bfc8..bb786694dd26 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -49,9 +49,6 @@ static inline bool gigantic_page_runtime_supported(void)
 	return true;
 }
 
-/* hugepd entry valid bit */
-#define HUGEPD_VAL_BITS		(0x8000000000000000UL)
-
 #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
 extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep);
@@ -60,29 +57,7 @@ extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep,
 					 pte_t old_pte, pte_t new_pte);
-/*
- * This should work for other subarchs too. But right now we use the
- * new format only for 64bit book3s
- */
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
-	BUG_ON(!hugepd_ok(hpd));
-	/*
-	 * We have only four bits to encode, MMU page size
-	 */
-	BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
-	return __va(hpd_val(hpd) & HUGEPD_ADDR_MASK);
-}
 
-static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)
-{
-	return (hpd_val(hpd) & HUGEPD_SHIFT_MASK) >> 2;
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
-	return mmu_psize_to_shift(hugepd_mmu_psize(hpd));
-}
 static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 				      unsigned long vmaddr)
 {
@@ -90,19 +65,6 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 		return radix__flush_hugetlb_page(vma, vmaddr);
 }
 
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
-				    unsigned int pdshift)
-{
-	unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd);
-
-	return hugepd_page(hpd) + idx;
-}
-
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
-	*hpdp = __hugepd(__pa(new) | HUGEPD_VAL_BITS | (shift_to_mmu_psize(pshift) << 2));
-}
-
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 
 static inline int check_and_get_huge_psize(int shift)
@@ -132,4 +94,10 @@ static inline int check_and_get_huge_psize(int shift)
 	return mmu_psize;
 }
 
+#define arch_has_huge_bootmem_alloc arch_has_huge_bootmem_alloc
+
+static inline bool arch_has_huge_bootmem_alloc(void)
+{
+	return (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled());
+}
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/kexec.h b/arch/powerpc/include/asm/book3s/64/kexec.h
index d4b9d476ecba..df37a76c1e9f 100644
--- a/arch/powerpc/include/asm/book3s/64/kexec.h
+++ b/arch/powerpc/include/asm/book3s/64/kexec.h
@@ -21,6 +21,11 @@ static inline void reset_sprs(void)
 			plpar_set_ciabr(0);
 	}
 
+	if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+		mtspr(SPRN_DEXCR, 0);
+		mtspr(SPRN_HASHKEYR, 0);
+	}
+
 	/*  Do we need isync()? We are going via a kexec reset */
 	isync();
 }
diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h
index 54cf46808157..03aec3c6c851 100644
--- a/arch/powerpc/include/asm/book3s/64/kup.h
+++ b/arch/powerpc/include/asm/book3s/64/kup.h
@@ -10,7 +10,7 @@
 #define AMR_KUEP_BLOCKED	UL(0x5455555555555555)
 #define AMR_KUAP_BLOCKED	(AMR_KUAP_BLOCK_READ | AMR_KUAP_BLOCK_WRITE)
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro kuap_user_restore gpr1, gpr2
 #if defined(CONFIG_PPC_PKEY)
@@ -31,7 +31,7 @@
 	mfspr	\gpr2, SPRN_AMR
 	cmpd	\gpr1, \gpr2
 	beq	99f
-	END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_BOOK3S_KUAP, 68)
+	END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_KUAP, 68)
 
 	isync
 	mtspr	SPRN_AMR, \gpr1
@@ -78,7 +78,7 @@
 	 * No need to restore IAMR when returning to kernel space.
 	 */
 100:
-	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 67)
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67)
 #endif
 .endm
 
@@ -91,7 +91,7 @@
 	LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED)
 999:	tdne	\gpr1, \gpr2
 	EMIT_WARN_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
-	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 67)
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67)
 #endif
 .endm
 #endif
@@ -130,7 +130,7 @@
 	 */
 	BEGIN_MMU_FTR_SECTION_NESTED(68)
 	b	100f  // skip_save_amr
-	END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY | MMU_FTR_BOOK3S_KUAP, 68)
+	END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY | MMU_FTR_KUAP, 68)
 
 	/*
 	 * if pkey is disabled and we are entering from userspace
@@ -166,7 +166,7 @@
 	mtspr	SPRN_AMR, \gpr2
 	isync
 102:
-	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUAP, 69)
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 69)
 
 	/*
 	 * if entering from kernel we don't need save IAMR
@@ -191,9 +191,10 @@
 #endif
 .endm
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 #include <linux/jump_label.h>
+#include <linux/sched.h>
 
 DECLARE_STATIC_KEY_FALSE(uaccess_flush_key);
 
@@ -212,14 +213,14 @@ extern u64 __ro_after_init default_iamr;
  * access restrictions. Because of this ignore AMR value when accessing
  * userspace via kernel thread.
  */
-static inline u64 current_thread_amr(void)
+static __always_inline u64 current_thread_amr(void)
 {
 	if (current->thread.regs)
 		return current->thread.regs->amr;
 	return default_amr;
 }
 
-static inline u64 current_thread_iamr(void)
+static __always_inline u64 current_thread_iamr(void)
 {
 	if (current->thread.regs)
 		return current->thread.regs->iamr;
@@ -229,12 +230,7 @@ static inline u64 current_thread_iamr(void)
 
 #ifdef CONFIG_PPC_KUAP
 
-static __always_inline bool kuap_is_disabled(void)
-{
-	return !mmu_has_feature(MMU_FTR_BOOK3S_KUAP);
-}
-
-static inline void kuap_user_restore(struct pt_regs *regs)
+static __always_inline void kuap_user_restore(struct pt_regs *regs)
 {
 	bool restore_amr = false, restore_iamr = false;
 	unsigned long amr, iamr;
@@ -242,7 +238,7 @@ static inline void kuap_user_restore(struct pt_regs *regs)
 	if (!mmu_has_feature(MMU_FTR_PKEY))
 		return;
 
-	if (!mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) {
+	if (!mmu_has_feature(MMU_FTR_KUAP)) {
 		amr = mfspr(SPRN_AMR);
 		if (amr != regs->amr)
 			restore_amr = true;
@@ -273,7 +269,7 @@ static inline void kuap_user_restore(struct pt_regs *regs)
 	 */
 }
 
-static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr)
+static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr)
 {
 	if (likely(regs->amr == amr))
 		return;
@@ -289,7 +285,7 @@ static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr
 	 */
 }
 
-static inline unsigned long __kuap_get_and_assert_locked(void)
+static __always_inline unsigned long __kuap_get_and_assert_locked(void)
 {
 	unsigned long amr = mfspr(SPRN_AMR);
 
@@ -297,22 +293,16 @@ static inline unsigned long __kuap_get_and_assert_locked(void)
 		WARN_ON_ONCE(amr != AMR_KUAP_BLOCKED);
 	return amr;
 }
+#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked
 
-/* Do nothing, book3s/64 does that in ASM */
-static inline void __kuap_lock(void)
-{
-}
-
-static inline void __kuap_save_and_lock(struct pt_regs *regs)
-{
-}
+/* __kuap_lock() not required, book3s/64 does that in ASM */
 
 /*
  * We support individually allowing read or write, but we don't support nesting
  * because that would require an expensive read/modify write of the AMR.
  */
 
-static inline unsigned long get_kuap(void)
+static __always_inline unsigned long get_kuap(void)
 {
 	/*
 	 * We return AMR_KUAP_BLOCKED when we don't support KUAP because
@@ -322,7 +312,7 @@ static inline unsigned long get_kuap(void)
 	 * This has no effect in terms of actually blocking things on hash,
 	 * so it doesn't break anything.
 	 */
-	if (!mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
+	if (!mmu_has_feature(MMU_FTR_KUAP))
 		return AMR_KUAP_BLOCKED;
 
 	return mfspr(SPRN_AMR);
@@ -330,7 +320,7 @@ static inline unsigned long get_kuap(void)
 
 static __always_inline void set_kuap(unsigned long value)
 {
-	if (!mmu_has_feature(MMU_FTR_BOOK3S_KUAP))
+	if (!mmu_has_feature(MMU_FTR_KUAP))
 		return;
 
 	/*
@@ -342,7 +332,8 @@ static __always_inline void set_kuap(unsigned long value)
 	isync();
 }
 
-static inline bool __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+static __always_inline bool
+__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	/*
 	 * For radix this will be a storage protection fault (DSISR_PROTFAULT).
@@ -385,12 +376,12 @@ static __always_inline void allow_user_access(void __user *to, const void __user
 
 #else /* CONFIG_PPC_KUAP */
 
-static inline unsigned long get_kuap(void)
+static __always_inline unsigned long get_kuap(void)
 {
 	return AMR_KUAP_BLOCKED;
 }
 
-static inline void set_kuap(unsigned long value) { }
+static __always_inline void set_kuap(unsigned long value) { }
 
 static __always_inline void allow_user_access(void __user *to, const void __user *from,
 					      unsigned long size, unsigned long dir)
@@ -405,7 +396,7 @@ static __always_inline void prevent_user_access(unsigned long dir)
 		do_uaccess_flush();
 }
 
-static inline unsigned long prevent_user_access_return(void)
+static __always_inline unsigned long prevent_user_access_return(void)
 {
 	unsigned long flags = get_kuap();
 
@@ -416,12 +407,12 @@ static inline unsigned long prevent_user_access_return(void)
 	return flags;
 }
 
-static inline void restore_user_access(unsigned long flags)
+static __always_inline void restore_user_access(unsigned long flags)
 {
 	set_kuap(flags);
 	if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED)
 		do_uaccess_flush();
 }
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_KUP_H */
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 1c4eebbc69c9..af12e2ba8eb8 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -130,7 +130,7 @@
 #define POWER9_TLB_SETS_HASH	256	/* # sets in POWER9 TLB Hash mode */
 #define POWER9_TLB_SETS_RADIX	128	/* # sets in POWER9 TLB Radix mode */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct mmu_hash_ops {
 	void            (*hpte_invalidate)(unsigned long slot,
@@ -220,7 +220,7 @@ static inline unsigned long get_sllp_encoding(int psize)
 	return sllp;
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * Segment sizes.
@@ -248,7 +248,7 @@ static inline unsigned long get_sllp_encoding(int psize)
 #define LP_BITS		8
 #define LP_MASK(i)	((0xFF >> (i)) << LP_SHIFT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 static inline int slb_vsid_shift(int ssize)
 {
@@ -524,7 +524,6 @@ void slb_save_contents(struct slb_entry *slb_ptr);
 void slb_dump_contents(struct slb_entry *slb_ptr);
 
 extern void slb_vmalloc_update(void);
-void preload_new_slb_context(unsigned long start, unsigned long sp);
 
 #ifdef CONFIG_PPC_64S_HASH_MMU
 void slb_set_size(u16 size);
@@ -532,7 +531,7 @@ void slb_set_size(u16 size);
 static inline void slb_set_size(u16 size) { }
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * VSID allocation (256MB segment)
@@ -668,7 +667,7 @@ static inline void slb_set_size(u16 size) { }
 #define SLICE_ARRAY_SIZE	(H_PGTABLE_RANGE >> 41)
 #define LOW_SLICE_ARRAY_SZ	(BITS_PER_LONG / BITS_PER_BYTE)
 #define TASK_SLICE_ARRAY_SZ(x)	((x)->hash_context->slb_addr_limit >> 41)
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_PPC_SUBPAGE_PROT
 /*
@@ -881,5 +880,5 @@ static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
 	return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags);
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ */
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 570a4960cf17..48631365b48c 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -4,7 +4,7 @@
 
 #include <asm/page.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Page size definition
  *
@@ -26,12 +26,12 @@ struct mmu_psize_def {
 	};
 };
 extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* 64-bit classic hash table MMU */
 #include <asm/book3s/64/mmu-hash.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * ISA 3.0 partition and process table entry format
  */
@@ -71,10 +71,7 @@ extern unsigned int mmu_pid_bits;
 /* Base PID to allocate from */
 extern unsigned int mmu_base_pid;
 
-/*
- * memory block size used with radix translation.
- */
-extern unsigned long __ro_after_init radix_mem_block_size;
+extern unsigned long __ro_after_init memory_block_size;
 
 #define PRTB_SIZE_SHIFT	(mmu_pid_bits + 4)
 #define PRTB_ENTRIES	(1ul << mmu_pid_bits)
@@ -261,7 +258,7 @@ static inline void radix_init_pseries(void) { }
 #define arch_clear_mm_cpumask_cpu(cpu, mm)				\
 	do {								\
 		if (cpumask_test_cpu(cpu, mm_cpumask(mm))) {		\
-			atomic_dec(&(mm)->context.active_cpus);		\
+			dec_mm_active_cpus(mm);				\
 			cpumask_clear_cpu(cpu, mm_cpumask(mm));		\
 		}							\
 	} while (0)
@@ -291,5 +288,5 @@ static inline unsigned long get_user_vsid(mm_context_t *ctx,
 }
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
deleted file mode 100644
index 48f21820afe2..000000000000
--- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H
-#define _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H
-/*
- * hash 4k can't share hugetlb and also doesn't support THP
- */
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_HUGETLB_PAGE
-static inline int pmd_huge(pmd_t pmd)
-{
-	/*
-	 * leaf pte for huge page
-	 */
-	if (radix_enabled())
-		return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
-	return 0;
-}
-
-static inline int pud_huge(pud_t pud)
-{
-	/*
-	 * leaf pte for huge page
-	 */
-	if (radix_enabled())
-		return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
-	return 0;
-}
-
-/*
- * With radix , we have hugepage ptes in the pud and pmd entries. We don't
- * need to setup hugepage directory for them. Our pte and page directory format
- * enable us to have this enabled.
- */
-static inline int hugepd_ok(hugepd_t hpd)
-{
-	if (radix_enabled())
-		return 0;
-	return hash__hugepd_ok(hpd);
-}
-#define is_hugepd(hpd)		(hugepd_ok(hpd))
-
-/*
- * 16M and 16G huge page directory tables are allocated from slab cache
- *
- */
-#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24)
-#define H_16G_CACHE_INDEX                                                      \
-	(PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34)
-
-static inline int get_hugepd_cache_index(int index)
-{
-	switch (index) {
-	case H_16M_CACHE_INDEX:
-		return HTLB_16M_INDEX;
-	case H_16G_CACHE_INDEX:
-		return HTLB_16G_INDEX;
-	default:
-		BUG();
-	}
-	/* should not reach */
-}
-
-#endif /* CONFIG_HUGETLB_PAGE */
-
-#endif /* __ASSEMBLY__ */
-
-#endif /*_ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
index 2fce3498b000..004a03e97e58 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
@@ -2,53 +2,8 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_64K_H
 #define _ASM_POWERPC_BOOK3S_64_PGTABLE_64K_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifdef CONFIG_HUGETLB_PAGE
-/*
- * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have
- * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD;
- *
- * Defined in such a way that we can optimize away code block at build time
- * if CONFIG_HUGETLB_PAGE=n.
- *
- * returns true for pmd migration entries, THP, devmap, hugetlb
- * But compile time dependent on CONFIG_HUGETLB_PAGE
- */
-static inline int pmd_huge(pmd_t pmd)
-{
-	/*
-	 * leaf pte for huge page
-	 */
-	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
-}
-
-static inline int pud_huge(pud_t pud)
-{
-	/*
-	 * leaf pte for huge page
-	 */
-	return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
-}
-
-/*
- * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't
- * need to setup hugepage directory for them. Our pte and page directory format
- * enable us to have this enabled.
- */
-static inline int hugepd_ok(hugepd_t hpd)
-{
-	return 0;
-}
-
-#define is_hugepd(pdep)			0
-
-/*
- * This should never get called
- */
-static inline int get_hugepd_cache_index(int index)
-{
-	BUG();
-}
 
 #endif /* CONFIG_HUGETLB_PAGE */
 
@@ -59,5 +14,5 @@ static inline int remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr,
 		BUG();
 	return hash__remap_4k_pfn(vma, addr, pfn, prot);
 }
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 #endif /*_ASM_POWERPC_BOOK3S_64_PGTABLE_64K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 4acc9690f599..aac8ce30cd3b 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -4,7 +4,7 @@
 
 #include <asm-generic/pgtable-nop4d.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/mmdebug.h>
 #include <linux/bug.h>
 #include <linux/sizes.h>
@@ -17,8 +17,6 @@
 #define _PAGE_EXEC		0x00001 /* execute permission */
 #define _PAGE_WRITE		0x00002 /* write access allowed */
 #define _PAGE_READ		0x00004	/* read access allowed */
-#define _PAGE_RW		(_PAGE_READ | _PAGE_WRITE)
-#define _PAGE_RWX		(_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 #define _PAGE_PRIVILEGED	0x00008 /* kernel access only */
 #define _PAGE_SAO		0x00010 /* Strong access order */
 #define _PAGE_NON_IDEMPOTENT	0x00020 /* non idempotent memory */
@@ -90,7 +88,6 @@
 
 #define _PAGE_SOFT_DIRTY	_RPAGE_SW3 /* software: software dirty tracking */
 #define _PAGE_SPECIAL		_RPAGE_SW2 /* software: special page */
-#define _PAGE_DEVMAP		_RPAGE_SW1 /* software: ZONE_DEVICE page */
 
 /*
  * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE
@@ -104,13 +101,14 @@
  * and every thing below PAGE_SHIFT;
  */
 #define PTE_RPN_MASK	(((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK))
+#define PTE_RPN_SHIFT	PAGE_SHIFT
 /*
  * set of bits not changed in pmd_modify. Even though we have hash specific bits
  * in here, on radix we expect them to be zero.
  */
 #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
 			 _PAGE_ACCESSED | H_PAGE_THP_HUGE | _PAGE_PTE | \
-			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
+			 _PAGE_SOFT_DIRTY)
 /*
  * user access blocked by key
  */
@@ -124,7 +122,7 @@
  */
 #define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
 			 _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE |	\
-			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
+			 _PAGE_SOFT_DIRTY)
 
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
@@ -135,23 +133,7 @@
 #define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED)
 #define _PAGE_BASE	(_PAGE_BASE_NC)
 
-/* Permission masks used to generate the __P and __S table,
- *
- * Note:__pgprot is defined in arch/powerpc/include/asm/page.h
- *
- * Write permissions imply read permissions for now (we could make write-only
- * pages on BookE but we don't bother for now). Execute permission control is
- * possible on platforms that define _PAGE_EXEC
- */
-#define PAGE_NONE	__pgprot(_PAGE_BASE | _PAGE_PRIVILEGED)
-#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_RW)
-#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_EXEC)
-#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_READ)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_READ)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
-/* Radix only, Hash uses PAGE_READONLY_X + execute-only pkey instead */
-#define PAGE_EXECONLY	__pgprot(_PAGE_BASE | _PAGE_EXEC)
+#include <asm/pgtable-masks.h>
 
 /* Permission masks used for kernel mappings */
 #define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW)
@@ -161,7 +143,7 @@
 #define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
 #define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * page table defines
  */
@@ -279,7 +261,37 @@ extern unsigned long __kernel_io_end;
 
 extern struct page *vmemmap;
 extern unsigned long pci_io_base;
-#endif /* __ASSEMBLY__ */
+
+#define pmd_leaf pmd_leaf
+static inline bool pmd_leaf(pmd_t pmd)
+{
+	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
+}
+
+#define pud_leaf pud_leaf
+static inline bool pud_leaf(pud_t pud)
+{
+	return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
+}
+
+#define pmd_leaf_size pmd_leaf_size
+static inline unsigned long pmd_leaf_size(pmd_t pmd)
+{
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled())
+		return SZ_16M;
+	else
+		return PMD_SIZE;
+}
+
+#define pud_leaf_size pud_leaf_size
+static inline unsigned long pud_leaf_size(pud_t pud)
+{
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled())
+		return SZ_16G;
+	else
+		return PUD_SIZE;
+}
+#endif /* __ASSEMBLER__ */
 
 #include <asm/book3s/64/hash.h>
 #include <asm/book3s/64/radix.h>
@@ -290,11 +302,9 @@ extern unsigned long pci_io_base;
 #define  MAX_PHYSMEM_BITS	R_MAX_PHYSMEM_BITS
 #endif
 
-
+/* hash 4k can't share hugetlb and also doesn't support THP */
 #ifdef CONFIG_PPC_64K_PAGES
 #include <asm/book3s/64/pgtable-64k.h>
-#else
-#include <asm/book3s/64/pgtable-4k.h>
 #endif
 
 #include <asm/barrier.h>
@@ -315,34 +325,9 @@ extern unsigned long pci_io_base;
 #define IOREMAP_START	(ioremap_bot)
 #define IOREMAP_END	(KERN_IO_END - FIXADDR_SIZE)
 #define FIXADDR_SIZE	SZ_32M
+#define FIXADDR_TOP	(IOREMAP_END + FIXADDR_SIZE)
 
-#ifndef __ASSEMBLY__
-
-/*
- * This is the default implementation of various PTE accessors, it's
- * used in all cases except Book3S with 64K pages where we have a
- * concept of sub-pages
- */
-#ifndef __real_pte
-
-#define __real_pte(e, p, o)		((real_pte_t){(e)})
-#define __rpte_to_pte(r)	((r).pte)
-#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)
-
-#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
-	do {							         \
-		index = 0;					         \
-		shift = mmu_psize_defs[psize].shift;		         \
-
-#define pte_iterate_hashed_end() } while(0)
-
-/*
- * We expect this to be called only for user addresses or kernel virtual
- * addresses other than the linear mapping.
- */
-#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
-
-#endif /* __real_pte */
+#ifndef __ASSEMBLER__
 
 static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr,
 				       pte_t *ptep, unsigned long clr,
@@ -542,8 +527,8 @@ static inline bool pte_user(pte_t pte)
 static inline bool pte_access_permitted(pte_t pte, bool write)
 {
 	/*
-	 * _PAGE_READ is needed for any access and will be
-	 * cleared for PROT_NONE
+	 * _PAGE_READ is needed for any access and will be cleared for
+	 * PROT_NONE. Execute-only mapping via PROT_EXEC also returns false.
 	 */
 	if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte))
 		return false;
@@ -569,11 +554,6 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
 	return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE);
 }
 
-static inline unsigned long pte_pfn(pte_t pte)
-{
-	return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT;
-}
-
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte)
 {
@@ -600,7 +580,7 @@ static inline pte_t pte_mkexec(pte_t pte)
 	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_EXEC));
 }
 
-static inline pte_t pte_mkwrite(pte_t pte)
+static inline pte_t pte_mkwrite_novma(pte_t pte)
 {
 	/*
 	 * write implies read, hence set both
@@ -628,34 +608,6 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
-static inline pte_t pte_mkdevmap(pte_t pte)
-{
-	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL | _PAGE_DEVMAP));
-}
-
-static inline pte_t pte_mkprivileged(pte_t pte)
-{
-	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED));
-}
-
-static inline pte_t pte_mkuser(pte_t pte)
-{
-	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED));
-}
-
-/*
- * This is potentially called with a pmd as the argument, in which case it's not
- * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set.
- * That's because the bit we use for _PAGE_DEVMAP is not reserved for software
- * use in page directory entries (ie. non-ptes).
- */
-static inline int pte_devmap(pte_t pte)
-{
-	u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE);
-
-	return (pte_raw(pte) & mask) == mask;
-}
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	/* FIXME!! check whether this need to be a conditional */
@@ -722,7 +674,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte)
 	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_EXCLUSIVE));
 }
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_EXCLUSIVE));
 }
@@ -921,8 +873,29 @@ static inline pud_t pte_pud(pte_t pte)
 {
 	return __pud_raw(pte_raw(pte));
 }
+
+static inline pte_t *pudp_ptep(pud_t *pud)
+{
+	return (pte_t *)pud;
+}
+
+#define pud_pfn(pud)		pte_pfn(pud_pte(pud))
+#define pud_dirty(pud)		pte_dirty(pud_pte(pud))
+#define pud_young(pud)		pte_young(pud_pte(pud))
+#define pud_mkold(pud)		pte_pud(pte_mkold(pud_pte(pud)))
+#define pud_wrprotect(pud)	pte_pud(pte_wrprotect(pud_pte(pud)))
+#define pud_mkdirty(pud)	pte_pud(pte_mkdirty(pud_pte(pud)))
+#define pud_mkclean(pud)	pte_pud(pte_mkclean(pud_pte(pud)))
+#define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
+#define pud_mkwrite(pud)	pte_pud(pte_mkwrite_novma(pud_pte(pud)))
 #define pud_write(pud)		pte_write(pud_pte(pud))
 
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+#define pud_soft_dirty(pmd)    pte_soft_dirty(pud_pte(pud))
+#define pud_mksoft_dirty(pmd)  pte_pud(pte_mksoft_dirty(pud_pte(pud)))
+#define pud_clear_soft_dirty(pmd) pte_pud(pte_clear_soft_dirty(pud_pte(pud)))
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
 static inline int pud_bad(pud_t pud)
 {
 	if (radix_enabled())
@@ -997,8 +970,6 @@ static inline pmd_t *pud_pgtable(pud_t pud)
 	return (pmd_t *)__va(pud_val(pud) & ~PUD_MASKED_BITS);
 }
 
-#define pte_ERROR(e) \
-	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
 #define pmd_ERROR(e) \
 	pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
 #define pud_ERROR(e) \
@@ -1039,16 +1010,6 @@ static inline void vmemmap_remove_mapping(unsigned long start,
 }
 #endif
 
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-static inline void __kernel_map_pages(struct page *page, int numpages, int enable)
-{
-	if (radix_enabled())
-		radix__kernel_map_pages(page, numpages, enable);
-	else
-		hash__kernel_map_pages(page, numpages, enable);
-}
-#endif
-
 static inline pte_t pmd_pte(pmd_t pmd)
 {
 	return __pte_raw(pmd_raw(pmd));
@@ -1071,7 +1032,7 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkwrite_novma(pmd)	pte_pmd(pte_mkwrite_novma(pmd_pte(pmd)))
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 #define pmd_soft_dirty(pmd)    pte_soft_dirty(pmd_pte(pmd))
@@ -1115,15 +1076,24 @@ static inline bool pmd_access_permitted(pmd_t pmd, bool write)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
-extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
+extern pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot);
 extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
+extern pud_t pud_modify(pud_t pud, pgprot_t newprot);
 extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t pmd);
+extern void set_pud_at(struct mm_struct *mm, unsigned long addr,
+		       pud_t *pudp, pud_t pud);
+
 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 					unsigned long addr, pmd_t *pmd)
 {
 }
 
+static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
+					unsigned long addr, pud_t *pud)
+{
+}
+
 extern int hash__has_transparent_hugepage(void);
 static inline int has_transparent_hugepage(void)
 {
@@ -1133,6 +1103,14 @@ static inline int has_transparent_hugepage(void)
 }
 #define has_transparent_hugepage has_transparent_hugepage
 
+static inline int has_transparent_pud_hugepage(void)
+{
+	if (radix_enabled())
+		return radix__has_transparent_pud_hugepage();
+	return 0;
+}
+#define has_transparent_pud_hugepage has_transparent_pud_hugepage
+
 static inline unsigned long
 pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp,
 		    unsigned long clr, unsigned long set)
@@ -1142,13 +1120,14 @@ pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp,
 	return hash__pmd_hugepage_update(mm, addr, pmdp, clr, set);
 }
 
-/*
- * returns true for pmd migration entries, THP, devmap, hugetlb
- * But compile time dependent on THP config
- */
-static inline int pmd_large(pmd_t pmd)
+static inline unsigned long
+pud_hugepage_update(struct mm_struct *mm, unsigned long addr, pud_t *pudp,
+		    unsigned long clr, unsigned long set)
 {
-	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
+	if (radix_enabled())
+		return radix__pud_hugepage_update(mm, addr, pudp, clr, set);
+	BUG();
+	return pud_val(*pudp);
 }
 
 /*
@@ -1166,6 +1145,17 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 	return ((old & _PAGE_ACCESSED) != 0);
 }
 
+static inline int __pudp_test_and_clear_young(struct mm_struct *mm,
+					      unsigned long addr, pud_t *pudp)
+{
+	unsigned long old;
+
+	if ((pud_raw(*pudp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
+		return 0;
+	old = pud_hugepage_update(mm, addr, pudp, _PAGE_ACCESSED, 0);
+	return ((old & _PAGE_ACCESSED) != 0);
+}
+
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
 static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pmd_t *pmdp)
@@ -1174,6 +1164,14 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 		pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
 }
 
+#define __HAVE_ARCH_PUDP_SET_WRPROTECT
+static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pud_t *pudp)
+{
+	if (pud_write(*pudp))
+		pud_hugepage_update(mm, addr, pudp, _PAGE_WRITE, 0);
+}
+
 /*
  * Only returns true for a THP. False for pmd migration entry.
  * We also need to return true when we come across a pte that
@@ -1195,6 +1193,17 @@ static inline int pmd_trans_huge(pmd_t pmd)
 	return hash__pmd_trans_huge(pmd);
 }
 
+static inline int pud_trans_huge(pud_t pud)
+{
+	if (!pud_present(pud))
+		return false;
+
+	if (radix_enabled())
+		return radix__pud_trans_huge(pud);
+	return 0;
+}
+
+
 #define __HAVE_ARCH_PMD_SAME
 static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 {
@@ -1203,6 +1212,15 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 	return hash__pmd_same(pmd_a, pmd_b);
 }
 
+#define pud_same pud_same
+static inline int pud_same(pud_t pud_a, pud_t pud_b)
+{
+	if (radix_enabled())
+		return radix__pud_same(pud_a, pud_b);
+	return hash__pud_same(pud_a, pud_b);
+}
+
+
 static inline pmd_t __pmd_mkhuge(pmd_t pmd)
 {
 	if (radix_enabled())
@@ -1210,6 +1228,14 @@ static inline pmd_t __pmd_mkhuge(pmd_t pmd)
 	return hash__pmd_mkhuge(pmd);
 }
 
+static inline pud_t __pud_mkhuge(pud_t pud)
+{
+	if (radix_enabled())
+		return radix__pud_mkhuge(pud);
+	BUG();
+	return pud;
+}
+
 /*
  * pfn_pmd return a pmd_t that can be used as pmd pte entry.
  */
@@ -1225,14 +1251,34 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 	return pmd;
 }
 
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+#ifdef CONFIG_DEBUG_VM
+	if (radix_enabled())
+		WARN_ON((pud_raw(pud) & cpu_to_be64(_PAGE_PTE)) == 0);
+	else
+		WARN_ON(1);
+#endif
+	return pud;
+}
+
+
 #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
 extern int pmdp_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp,
 				 pmd_t entry, int dirty);
+#define __HAVE_ARCH_PUDP_SET_ACCESS_FLAGS
+extern int pudp_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pud_t *pudp,
+				 pud_t entry, int dirty);
 
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
 extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 				     unsigned long address, pmd_t *pmdp);
+#define __HAVE_ARCH_PUDP_TEST_AND_CLEAR_YOUNG
+extern int pudp_test_and_clear_young(struct vm_area_struct *vma,
+				     unsigned long address, pud_t *pudp);
+
 
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
@@ -1243,6 +1289,16 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 	return hash__pmdp_huge_get_and_clear(mm, addr, pmdp);
 }
 
+#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
+static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pud_t *pudp)
+{
+	if (radix_enabled())
+		return radix__pudp_huge_get_and_clear(mm, addr, pudp);
+	BUG();
+	return *pudp;
+}
+
 static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
 					unsigned long address, pmd_t *pmdp)
 {
@@ -1257,6 +1313,11 @@ pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma,
 				   unsigned long addr,
 				   pmd_t *pmdp, int full);
 
+#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL
+pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma,
+				   unsigned long addr,
+				   pud_t *pudp, int full);
+
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
 static inline void pgtable_trans_huge_deposit(struct mm_struct *mm,
 					      pmd_t *pmdp, pgtable_t pgtable)
@@ -1278,6 +1339,8 @@ static inline pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm,
 #define __HAVE_ARCH_PMDP_INVALIDATE
 extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			     pmd_t *pmdp);
+extern pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			     pud_t *pudp);
 
 #define pmd_move_must_withdraw pmd_move_must_withdraw
 struct spinlock;
@@ -1297,40 +1360,8 @@ static inline bool arch_needs_pgtable_deposit(void)
 }
 extern void serialize_against_pte_lookup(struct mm_struct *mm);
 
-
-static inline pmd_t pmd_mkdevmap(pmd_t pmd)
-{
-	if (radix_enabled())
-		return radix__pmd_mkdevmap(pmd);
-	return hash__pmd_mkdevmap(pmd);
-}
-
-static inline int pmd_devmap(pmd_t pmd)
-{
-	return pte_devmap(pmd_pte(pmd));
-}
-
-static inline int pud_devmap(pud_t pud)
-{
-	return 0;
-}
-
-static inline int pgd_devmap(pgd_t pgd)
-{
-	return 0;
-}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline int pud_pfn(pud_t pud)
-{
-	/*
-	 * Currently all calls to pud_pfn() are gated around a pud_devmap()
-	 * check so this should never be used. If it grows another user we
-	 * want to know about it.
-	 */
-	BUILD_BUG();
-	return 0;
-}
 #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
 pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *);
 void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
@@ -1350,22 +1381,5 @@ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_va
 	return false;
 }
 
-/*
- * Like pmd_huge() and pmd_large(), but works regardless of config options
- */
-#define pmd_is_leaf pmd_is_leaf
-#define pmd_leaf pmd_is_leaf
-static inline bool pmd_is_leaf(pmd_t pmd)
-{
-	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
-}
-
-#define pud_is_leaf pud_is_leaf
-#define pud_leaf pud_is_leaf
-static inline bool pud_is_leaf(pud_t pud)
-{
-	return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
-}
-
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
diff --git a/arch/powerpc/include/asm/book3s/64/pkeys.h b/arch/powerpc/include/asm/book3s/64/pkeys.h
index 5b178139f3c0..ff911b4251d9 100644
--- a/arch/powerpc/include/asm/book3s/64/pkeys.h
+++ b/arch/powerpc/include/asm/book3s/64/pkeys.h
@@ -5,7 +5,7 @@
 
 #include <asm/book3s/64/hash-pkey.h>
 
-static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags)
+static inline u64 vmflag_to_pte_pkey_bits(vm_flags_t vm_flags)
 {
 	if (!mmu_has_feature(MMU_FTR_PKEY))
 		return 0x0UL;
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 686001eda936..da954e779744 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -4,7 +4,7 @@
 
 #include <asm/asm-const.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/cmpxchg.h>
 #endif
 
@@ -14,7 +14,7 @@
 #include <asm/book3s/64/radix-4k.h>
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/book3s/64/tlbflush-radix.h>
 #include <asm/cpu_has_feature.h>
 #endif
@@ -132,7 +132,7 @@
 #define RADIX_VMEMMAP_SIZE	RADIX_KERN_MAP_SIZE
 #define RADIX_VMEMMAP_END	(RADIX_VMEMMAP_START + RADIX_VMEMMAP_SIZE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #define RADIX_PTE_TABLE_SIZE	(sizeof(pte_t) << RADIX_PTE_INDEX_SIZE)
 #define RADIX_PMD_TABLE_SIZE	(sizeof(pmd_t) << RADIX_PMD_INDEX_SIZE)
 #define RADIX_PUD_TABLE_SIZE	(sizeof(pud_t) << RADIX_PUD_INDEX_SIZE)
@@ -250,6 +250,10 @@ static inline int radix__pud_bad(pud_t pud)
 	return !!(pud_val(pud) & RADIX_PUD_BAD_BITS);
 }
 
+static inline int radix__pud_same(pud_t pud_a, pud_t pud_b)
+{
+	return ((pud_raw(pud_a) ^ pud_raw(pud_b)) == 0);
+}
 
 static inline int radix__p4d_bad(p4d_t p4d)
 {
@@ -260,7 +264,7 @@ static inline int radix__p4d_bad(p4d_t p4d)
 
 static inline int radix__pmd_trans_huge(pmd_t pmd)
 {
-	return (pmd_val(pmd) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE;
+	return (pmd_val(pmd) & _PAGE_PTE) == _PAGE_PTE;
 }
 
 static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
@@ -268,9 +272,22 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
 	return __pmd(pmd_val(pmd) | _PAGE_PTE);
 }
 
+static inline int radix__pud_trans_huge(pud_t pud)
+{
+	return (pud_val(pud) & _PAGE_PTE) == _PAGE_PTE;
+}
+
+static inline pud_t radix__pud_mkhuge(pud_t pud)
+{
+	return __pud(pud_val(pud) | _PAGE_PTE);
+}
+
 extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
 					  pmd_t *pmdp, unsigned long clr,
 					  unsigned long set);
+extern unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr,
+						pud_t *pudp, unsigned long clr,
+						unsigned long set);
 extern pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma,
 				  unsigned long address, pmd_t *pmdp);
 extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
@@ -278,6 +295,9 @@ extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
 				      unsigned long addr, pmd_t *pmdp);
+pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pud_t *pudp);
+
 static inline int radix__has_transparent_hugepage(void)
 {
 	/* For radix 2M at PMD level means thp */
@@ -285,16 +305,25 @@ static inline int radix__has_transparent_hugepage(void)
 		return 1;
 	return 0;
 }
-#endif
 
-static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd)
+static inline int radix__has_transparent_pud_hugepage(void)
 {
-	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+	/* For radix 1G at PUD level means pud hugepage support */
+	if (mmu_psize_defs[MMU_PAGE_1G].shift == PUD_SHIFT)
+		return 1;
+	return 0;
 }
+#endif
 
+struct vmem_altmap;
+struct dev_pagemap;
 extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
 					     unsigned long page_size,
 					     unsigned long phys);
+int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end,
+				      int node, struct vmem_altmap *altmap);
+void __ref radix__vmemmap_free(unsigned long start, unsigned long end,
+			       struct vmem_altmap *altmap);
 extern void radix__vmemmap_remove_mapping(unsigned long start,
 				    unsigned long page_size);
 
@@ -323,7 +352,15 @@ int radix__create_section_mapping(unsigned long start, unsigned long end,
 int radix__remove_section_mapping(unsigned long start, unsigned long end);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-void radix__kernel_map_pages(struct page *page, int numpages, int enable);
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
+#define vmemmap_can_optimize vmemmap_can_optimize
+bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap);
+#endif
 
-#endif /* __ASSEMBLY__ */
+#define vmemmap_populate_compound_pages vmemmap_populate_compound_pages
+int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
+					      unsigned long start,
+					      unsigned long end, int node,
+					      struct dev_pagemap *pgmap);
+#endif /* __ASSEMBLER__ */
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/slice.h b/arch/powerpc/include/asm/book3s/64/slice.h
index 5fbe18544cbd..6e2f7a74cd75 100644
--- a/arch/powerpc/include/asm/book3s/64/slice.h
+++ b/arch/powerpc/include/asm/book3s/64/slice.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H
 #define _ASM_POWERPC_BOOK3S_64_SLICE_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_PPC_64S_HASH_MMU
 #ifdef CONFIG_HUGETLB_PAGE
@@ -37,6 +37,6 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 void slice_init_new_context_exec(struct mm_struct *mm);
 void slice_setup_new_exec(void);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 77797a2a82eb..a38542259fab 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -68,6 +68,8 @@ void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
 				      unsigned long end, int psize);
 extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
 				       unsigned long start, unsigned long end);
+extern void radix__flush_pud_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end);
 extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			    unsigned long end);
 extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end);
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index 0d0c1447ecf0..fd642b729775 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -5,6 +5,7 @@
 #define MMU_NO_CONTEXT	~0UL
 
 #include <linux/mm_types.h>
+#include <linux/mmu_notifier.h>
 #include <asm/book3s/64/tlbflush-hash.h>
 #include <asm/book3s/64/tlbflush-radix.h>
 
@@ -50,6 +51,14 @@ static inline void flush_pmd_tlb_range(struct vm_area_struct *vma,
 		radix__flush_pmd_tlb_range(vma, start, end);
 }
 
+#define __HAVE_ARCH_FLUSH_PUD_TLB_RANGE
+static inline void flush_pud_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end)
+{
+	if (radix_enabled())
+		radix__flush_pud_tlb_range(vma, start, end);
+}
+
 #define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
 static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 					   unsigned long start,
@@ -149,11 +158,6 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma,
 	 */
 }
 
-static inline bool __pte_protnone(unsigned long pte)
-{
-	return (pte & (pgprot_val(PAGE_NONE) | _PAGE_RWX)) == pgprot_val(PAGE_NONE);
-}
-
 static inline bool __pte_flags_need_flush(unsigned long oldval,
 					  unsigned long newval)
 {
@@ -170,8 +174,8 @@ static inline bool __pte_flags_need_flush(unsigned long oldval,
 	/*
 	 * We do not expect kernel mappings or non-PTEs or not-present PTEs.
 	 */
-	VM_WARN_ON_ONCE(!__pte_protnone(oldval) && oldval & _PAGE_PRIVILEGED);
-	VM_WARN_ON_ONCE(!__pte_protnone(newval) && newval & _PAGE_PRIVILEGED);
+	VM_WARN_ON_ONCE(oldval & _PAGE_PRIVILEGED);
+	VM_WARN_ON_ONCE(newval & _PAGE_PRIVILEGED);
 	VM_WARN_ON_ONCE(!(oldval & _PAGE_PTE));
 	VM_WARN_ON_ONCE(!(newval & _PAGE_PTE));
 	VM_WARN_ON_ONCE(!(oldval & _PAGE_PRESENT));
diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h
index d18b748ea3ae..f42d68c6b314 100644
--- a/arch/powerpc/include/asm/book3s/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/pgtable.h
@@ -8,42 +8,4 @@
 #include <asm/book3s/32/pgtable.h>
 #endif
 
-#ifndef __ASSEMBLY__
-/* Insert a PTE, top-level function is out of line. It uses an inline
- * low level function in the respective pgtable-* files
- */
-extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
-		       pte_t pte);
-
-
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
-				 pte_t *ptep, pte_t entry, int dirty);
-
-struct file;
-extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-				     unsigned long size, pgprot_t vma_prot);
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-
-void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep);
-
-/*
- * This gets called at the end of handling a page fault, when
- * the kernel has put a new PTE into the page table for the process.
- * We use it to ensure coherency between the i-cache and d-cache
- * for the page which has just been mapped in.
- * On machines which use an MMU hash table, we use this to put a
- * corresponding HPTE into the hash table ahead of time, instead of
- * waiting for the inevitable extra hash-table miss exception.
- */
-static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
-{
-	if (IS_ENABLED(CONFIG_PPC32) && !mmu_has_feature(MMU_FTR_HPTE_TABLE))
-		return;
-	if (radix_enabled())
-		return;
-	__update_mmu_cache(vma, address, ptep);
-}
-
-#endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index ef42adb44aa3..0db48977c70c 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -4,14 +4,13 @@
 #ifdef __KERNEL__
 
 #include <asm/asm-compat.h>
-#include <asm/extable.h>
 
 #ifdef CONFIG_BUG
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #include <asm/asm-offsets.h>
 #ifdef CONFIG_DEBUG_BUGVERBOSE
-.macro __EMIT_BUG_ENTRY addr,file,line,flags
+.macro EMIT_BUG_ENTRY addr,file,line,flags
 	 .section __bug_table,"aw"
 5001:	 .4byte \addr - .
 	 .4byte 5002f - .
@@ -23,7 +22,7 @@
 	 .previous
 .endm
 #else
-.macro __EMIT_BUG_ENTRY addr,file,line,flags
+.macro EMIT_BUG_ENTRY addr,file,line,flags
 	 .section __bug_table,"aw"
 5001:	 .4byte \addr - .
 	 .short \flags
@@ -32,19 +31,7 @@
 .endm
 #endif /* verbose */
 
-.macro EMIT_WARN_ENTRY addr,file,line,flags
-	EX_TABLE(\addr,\addr+4)
-	__EMIT_BUG_ENTRY \addr,\file,\line,\flags
-.endm
-
-.macro EMIT_BUG_ENTRY addr,file,line,flags
-	.if \flags & 1 /* BUGFLAG_WARNING */
-	.err /* Use EMIT_WARN_ENTRY for warnings */
-	.endif
-	__EMIT_BUG_ENTRY \addr,\file,\line,\flags
-.endm
-
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 /* _EMIT_BUG_ENTRY expects args %0,%1,%2,%3 to be FILE, LINE, flags and
    sizeof(struct bug_entry), respectively */
 #ifdef CONFIG_DEBUG_BUGVERBOSE
@@ -64,25 +51,15 @@
 	".previous\n"
 #endif
 
-#define BUG_ENTRY(insn, flags, ...)			\
+#define BUG_ENTRY(cond_str, insn, flags, ...)		\
 	__asm__ __volatile__(				\
 		"1:	" insn "\n"			\
 		_EMIT_BUG_ENTRY				\
-		: : "i" (__FILE__), "i" (__LINE__),	\
+		: : "i" (WARN_CONDITION_STR(cond_str) __FILE__), "i" (__LINE__),	\
 		  "i" (flags),				\
 		  "i" (sizeof(struct bug_entry)),	\
 		  ##__VA_ARGS__)
 
-#define WARN_ENTRY(insn, flags, label, ...)		\
-	asm_volatile_goto(				\
-		"1:	" insn "\n"			\
-		EX_TABLE(1b, %l[label])			\
-		_EMIT_BUG_ENTRY				\
-		: : "i" (__FILE__), "i" (__LINE__),	\
-		  "i" (flags),				\
-		  "i" (sizeof(struct bug_entry)),	\
-		  ##__VA_ARGS__ : : label)
-
 /*
  * BUG_ON() and WARN_ON() do their best to cooperate with compile-time
  * optimisations. However depending on the complexity of the condition
@@ -90,21 +67,12 @@
  */
 
 #define BUG() do {						\
-	BUG_ENTRY("twi 31, 0, 0", 0);				\
+	BUG_ENTRY("", "twi 31, 0, 0", 0);			\
 	unreachable();						\
 } while (0)
 #define HAVE_ARCH_BUG
 
-#define __WARN_FLAGS(flags) do {				\
-	__label__ __label_warn_on;				\
-								\
-	WARN_ENTRY("twi 31, 0, 0", BUGFLAG_WARNING | (flags), __label_warn_on); \
-	barrier_before_unreachable();				\
-	__builtin_unreachable();				\
-								\
-__label_warn_on:						\
-	break;							\
-} while (0)
+#define __WARN_FLAGS(cond_str, flags) BUG_ENTRY(cond_str, "twi 31, 0, 0", BUGFLAG_WARNING | (flags))
 
 #ifdef CONFIG_PPC64
 #define BUG_ON(x) do {						\
@@ -112,30 +80,20 @@ __label_warn_on:						\
 		if (x)						\
 			BUG();					\
 	} else {						\
-		BUG_ENTRY(PPC_TLNEI " %4, 0", 0, "r" ((__force long)(x)));	\
+		BUG_ENTRY(#x, PPC_TLNEI " %4, 0", 0, "r" ((__force long)(x)));	\
 	}							\
 } while (0)
 
 #define WARN_ON(x) ({						\
-	bool __ret_warn_on = false;				\
-	do {							\
-		if (__builtin_constant_p((x))) {		\
-			if (!(x)) 				\
-				break; 				\
+	int __ret_warn_on = !!(x);				\
+	if (__builtin_constant_p(__ret_warn_on)) {		\
+		if (__ret_warn_on)				\
 			__WARN();				\
-			__ret_warn_on = true;			\
-		} else {					\
-			__label__ __label_warn_on;		\
-								\
-			WARN_ENTRY(PPC_TLNEI " %4, 0",		\
-				   BUGFLAG_WARNING | BUGFLAG_TAINT(TAINT_WARN),	\
-				   __label_warn_on,		\
-				   "r" ((__force long)(x)));	\
-			break;					\
-__label_warn_on:						\
-			__ret_warn_on = true;			\
-		}						\
-	} while (0);						\
+	} else {						\
+		BUG_ENTRY(#x, PPC_TLNEI " %4, 0",			\
+			  BUGFLAG_WARNING | BUGFLAG_TAINT(TAINT_WARN),	\
+			  "r" (__ret_warn_on));	\
+	}							\
 	unlikely(__ret_warn_on);				\
 })
 
@@ -143,26 +101,26 @@ __label_warn_on:						\
 #define HAVE_ARCH_WARN_ON
 #endif
 
-#endif /* __ASSEMBLY __ */
+#endif /* __ASSEMBLER__ */
 #else
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 .macro EMIT_BUG_ENTRY addr,file,line,flags
 .endm
-.macro EMIT_WARN_ENTRY addr,file,line,flags
-.endm
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 #define _EMIT_BUG_ENTRY
-#define _EMIT_WARN_ENTRY
 #endif
 #endif /* CONFIG_BUG */
 
+#define EMIT_WARN_ENTRY EMIT_BUG_ENTRY
+
 #include <asm-generic/bug.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct pt_regs;
 void hash__do_page_fault(struct pt_regs *);
 void bad_page_fault(struct pt_regs *, int);
+void emulate_single_step(struct pt_regs *regs);
 extern void _exception(int, struct pt_regs *, int, unsigned long);
 extern void _exception_pkey(struct pt_regs *, unsigned long, int);
 extern void die(const char *, struct pt_regs *, long);
@@ -170,7 +128,7 @@ void die_mce(const char *str, struct pt_regs *regs, long err);
 extern bool die_will_crash(void);
 extern void panic_flush_kmsg_start(void);
 extern void panic_flush_kmsg_end(void);
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_BUG_H */
diff --git a/arch/powerpc/include/asm/bugs.h b/arch/powerpc/include/asm/bugs.h
deleted file mode 100644
index 01b8f6ca4dbb..000000000000
--- a/arch/powerpc/include/asm/bugs.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ASM_POWERPC_BUGS_H
-#define _ASM_POWERPC_BUGS_H
-
-/*
- */
-
-/*
- * This file is included by 'init/main.c' to check for
- * architecture-dependent bugs.
- */
-
-static inline void check_bugs(void) { }
-
-#endif	/* _ASM_POWERPC_BUGS_H */
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index ae0a68a838e8..6796babc4d31 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -33,7 +33,11 @@
 
 #define IFETCH_ALIGN_BYTES	(1 << IFETCH_ALIGN_SHIFT)
 
-#if !defined(__ASSEMBLY__)
+#ifdef CONFIG_NOT_COHERENT_CACHE
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+#endif
+
+#if !defined(__ASSEMBLER__)
 #ifdef CONFIG_PPC64
 
 struct ppc_cache_info {
@@ -141,6 +145,6 @@ static inline void iccci(void *addr)
 	asm volatile ("iccci 0, %0" : : "r"(addr) : "memory");
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_CACHE_H */
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 7564dd4fd12b..1fea42928f64 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -35,13 +35,19 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
  * It just marks the page as not i-cache clean.  We do the i-cache
  * flush later when the page is given to a user process, if necessary.
  */
-static inline void flush_dcache_page(struct page *page)
+static inline void flush_dcache_folio(struct folio *folio)
 {
 	if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
 		return;
 	/* avoid an atomic op if possible */
-	if (test_bit(PG_dcache_clean, &page->flags))
-		clear_bit(PG_dcache_clean, &page->flags);
+	if (test_bit(PG_dcache_clean, &folio->flags.f))
+		clear_bit(PG_dcache_clean, &folio->flags.f);
+}
+#define flush_dcache_folio flush_dcache_folio
+
+static inline void flush_dcache_page(struct page *page)
+{
+	flush_dcache_folio(page_folio(page));
 }
 
 void flush_icache_range(unsigned long start, unsigned long stop);
@@ -51,7 +57,7 @@ void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 		unsigned long addr, int len);
 #define flush_icache_user_page flush_icache_user_page
 
-void flush_dcache_icache_page(struct page *page);
+void flush_dcache_icache_folio(struct folio *folio);
 
 /**
  * flush_dcache_range(): Write any modified data cache blocks out to memory and
@@ -115,7 +121,7 @@ static inline void invalidate_dcache_range(unsigned long start,
 	mb();	/* sync */
 }
 
-#ifdef CONFIG_4xx
+#ifdef CONFIG_44x
 static inline void flush_instruction_cache(void)
 {
 	iccci((void *)KERNELBASE);
diff --git a/arch/powerpc/include/asm/cell-pmu.h b/arch/powerpc/include/asm/cell-pmu.h
index 6a79b5d1c44f..7fbefd64b4fb 100644
--- a/arch/powerpc/include/asm/cell-pmu.h
+++ b/arch/powerpc/include/asm/cell-pmu.h
@@ -20,36 +20,9 @@
 
 /* Macros for the pm_control register. */
 #define CBE_PM_16BIT_CTR(ctr)              (1 << (24 - ((ctr) & (NR_PHYS_CTRS - 1))))
-#define CBE_PM_ENABLE_PERF_MON             0x80000000
-#define CBE_PM_STOP_AT_MAX                 0x40000000
-#define CBE_PM_TRACE_MODE_GET(pm_control)  (((pm_control) >> 28) & 0x3)
-#define CBE_PM_TRACE_MODE_SET(mode)        (((mode)  & 0x3) << 28)
-#define CBE_PM_TRACE_BUF_OVFLW(bit)        (((bit) & 0x1) << 17)
-#define CBE_PM_COUNT_MODE_SET(count)       (((count) & 0x3) << 18)
-#define CBE_PM_FREEZE_ALL_CTRS             0x00100000
-#define CBE_PM_ENABLE_EXT_TRACE            0x00008000
-#define CBE_PM_SPU_ADDR_TRACE_SET(msk)     (((msk) & 0x3) << 9)
 
 /* Macros for the trace_address register. */
-#define CBE_PM_TRACE_BUF_FULL              0x00000800
 #define CBE_PM_TRACE_BUF_EMPTY             0x00000400
-#define CBE_PM_TRACE_BUF_DATA_COUNT(ta)    ((ta) & 0x3ff)
-#define CBE_PM_TRACE_BUF_MAX_COUNT         0x400
-
-/* Macros for the pm07_control registers. */
-#define CBE_PM_CTR_INPUT_MUX(pm07_control) (((pm07_control) >> 26) & 0x3f)
-#define CBE_PM_CTR_INPUT_CONTROL           0x02000000
-#define CBE_PM_CTR_POLARITY                0x01000000
-#define CBE_PM_CTR_COUNT_CYCLES            0x00800000
-#define CBE_PM_CTR_ENABLE                  0x00400000
-#define PM07_CTR_INPUT_MUX(x)              (((x) & 0x3F) << 26)
-#define PM07_CTR_INPUT_CONTROL(x)          (((x) & 1) << 25)
-#define PM07_CTR_POLARITY(x)               (((x) & 1) << 24)
-#define PM07_CTR_COUNT_CYCLES(x)           (((x) & 1) << 23)
-#define PM07_CTR_ENABLE(x)                 (((x) & 1) << 22)
-
-/* Macros for the pm_status register. */
-#define CBE_PM_CTR_OVERFLOW_INTR(ctr)      (1 << (31 - ((ctr) & 7)))
 
 enum pm_reg_name {
 	group_control,
@@ -62,33 +35,4 @@ enum pm_reg_name {
 	pm_start_stop,
 };
 
-/* Routines for reading/writing the PMU registers. */
-extern u32  cbe_read_phys_ctr(u32 cpu, u32 phys_ctr);
-extern void cbe_write_phys_ctr(u32 cpu, u32 phys_ctr, u32 val);
-extern u32  cbe_read_ctr(u32 cpu, u32 ctr);
-extern void cbe_write_ctr(u32 cpu, u32 ctr, u32 val);
-
-extern u32  cbe_read_pm07_control(u32 cpu, u32 ctr);
-extern void cbe_write_pm07_control(u32 cpu, u32 ctr, u32 val);
-extern u32  cbe_read_pm(u32 cpu, enum pm_reg_name reg);
-extern void cbe_write_pm(u32 cpu, enum pm_reg_name reg, u32 val);
-
-extern u32  cbe_get_ctr_size(u32 cpu, u32 phys_ctr);
-extern void cbe_set_ctr_size(u32 cpu, u32 phys_ctr, u32 ctr_size);
-
-extern void cbe_enable_pm(u32 cpu);
-extern void cbe_disable_pm(u32 cpu);
-
-extern void cbe_read_trace_buffer(u32 cpu, u64 *buf);
-
-extern void cbe_enable_pm_interrupts(u32 cpu, u32 thread, u32 mask);
-extern void cbe_disable_pm_interrupts(u32 cpu);
-extern u32  cbe_get_and_clear_pm_interrupts(u32 cpu);
-extern void cbe_sync_irq(int node);
-
-#define CBE_COUNT_SUPERVISOR_MODE       0
-#define CBE_COUNT_HYPERVISOR_MODE       1
-#define CBE_COUNT_PROBLEM_MODE          2
-#define CBE_COUNT_ALL_MODES             3
-
 #endif /* __ASM_CELL_PMU_H__ */
diff --git a/arch/powerpc/include/asm/cell-regs.h b/arch/powerpc/include/asm/cell-regs.h
index e1c431ef30e0..20f7339a3d4a 100644
--- a/arch/powerpc/include/asm/cell-regs.h
+++ b/arch/powerpc/include/asm/cell-regs.h
@@ -18,293 +18,6 @@
 
 #include <asm/cell-pmu.h>
 
-/*
- *
- * Some HID register definitions
- *
- */
-
-/* CBE specific HID0 bits */
-#define HID0_CBE_THERM_WAKEUP	0x0000020000000000ul
-#define HID0_CBE_SYSERR_WAKEUP	0x0000008000000000ul
-#define HID0_CBE_THERM_INT_EN	0x0000000400000000ul
-#define HID0_CBE_SYSERR_INT_EN	0x0000000200000000ul
-
-#define MAX_CBE		2
-
-/*
- *
- * Pervasive unit register definitions
- *
- */
-
-union spe_reg {
-	u64 val;
-	u8 spe[8];
-};
-
-union ppe_spe_reg {
-	u64 val;
-	struct {
-		u32 ppe;
-		u32 spe;
-	};
-};
-
-
-struct cbe_pmd_regs {
-	/* Debug Bus Control */
-	u64	pad_0x0000;					/* 0x0000 */
-
-	u64	group_control;					/* 0x0008 */
-
-	u8	pad_0x0010_0x00a8 [0x00a8 - 0x0010];		/* 0x0010 */
-
-	u64	debug_bus_control;				/* 0x00a8 */
-
-	u8	pad_0x00b0_0x0100 [0x0100 - 0x00b0];		/* 0x00b0 */
-
-	u64	trace_aux_data;					/* 0x0100 */
-	u64	trace_buffer_0_63;				/* 0x0108 */
-	u64	trace_buffer_64_127;				/* 0x0110 */
-	u64	trace_address;					/* 0x0118 */
-	u64	ext_tr_timer;					/* 0x0120 */
-
-	u8	pad_0x0128_0x0400 [0x0400 - 0x0128];		/* 0x0128 */
-
-	/* Performance Monitor */
-	u64	pm_status;					/* 0x0400 */
-	u64	pm_control;					/* 0x0408 */
-	u64	pm_interval;					/* 0x0410 */
-	u64	pm_ctr[4];					/* 0x0418 */
-	u64	pm_start_stop;					/* 0x0438 */
-	u64	pm07_control[8];				/* 0x0440 */
-
-	u8	pad_0x0480_0x0800 [0x0800 - 0x0480];		/* 0x0480 */
-
-	/* Thermal Sensor Registers */
-	union	spe_reg	ts_ctsr1;				/* 0x0800 */
-	u64	ts_ctsr2;					/* 0x0808 */
-	union	spe_reg	ts_mtsr1;				/* 0x0810 */
-	u64	ts_mtsr2;					/* 0x0818 */
-	union	spe_reg	ts_itr1;				/* 0x0820 */
-	u64	ts_itr2;					/* 0x0828 */
-	u64	ts_gitr;					/* 0x0830 */
-	u64	ts_isr;						/* 0x0838 */
-	u64	ts_imr;						/* 0x0840 */
-	union	spe_reg	tm_cr1;					/* 0x0848 */
-	u64	tm_cr2;						/* 0x0850 */
-	u64	tm_simr;					/* 0x0858 */
-	union	ppe_spe_reg tm_tpr;				/* 0x0860 */
-	union	spe_reg	tm_str1;				/* 0x0868 */
-	u64	tm_str2;					/* 0x0870 */
-	union	ppe_spe_reg tm_tsr;				/* 0x0878 */
-
-	/* Power Management */
-	u64	pmcr;						/* 0x0880 */
-#define CBE_PMD_PAUSE_ZERO_CONTROL	0x10000
-	u64	pmsr;						/* 0x0888 */
-
-	/* Time Base Register */
-	u64	tbr;						/* 0x0890 */
-
-	u8	pad_0x0898_0x0c00 [0x0c00 - 0x0898];		/* 0x0898 */
-
-	/* Fault Isolation Registers */
-	u64	checkstop_fir;					/* 0x0c00 */
-	u64	recoverable_fir;				/* 0x0c08 */
-	u64	spec_att_mchk_fir;				/* 0x0c10 */
-	u32	fir_mode_reg;					/* 0x0c18 */
-	u8	pad_0x0c1c_0x0c20 [4];				/* 0x0c1c */
-#define CBE_PMD_FIR_MODE_M8		0x00800
-	u64	fir_enable_mask;				/* 0x0c20 */
-
-	u8	pad_0x0c28_0x0ca8 [0x0ca8 - 0x0c28];		/* 0x0c28 */
-	u64	ras_esc_0;					/* 0x0ca8 */
-	u8	pad_0x0cb0_0x1000 [0x1000 - 0x0cb0];		/* 0x0cb0 */
-};
-
-extern struct cbe_pmd_regs __iomem *cbe_get_pmd_regs(struct device_node *np);
-extern struct cbe_pmd_regs __iomem *cbe_get_cpu_pmd_regs(int cpu);
-
-/*
- * PMU shadow registers
- *
- * Many of the registers in the performance monitoring unit are write-only,
- * so we need to save a copy of what we write to those registers.
- *
- * The actual data counters are read/write. However, writing to the counters
- * only takes effect if the PMU is enabled. Otherwise the value is stored in
- * a hardware latch until the next time the PMU is enabled. So we save a copy
- * of the counter values if we need to read them back while the PMU is
- * disabled. The counter_value_in_latch field is a bitmap indicating which
- * counters currently have a value waiting to be written.
- */
-
-struct cbe_pmd_shadow_regs {
-	u32 group_control;
-	u32 debug_bus_control;
-	u32 trace_address;
-	u32 ext_tr_timer;
-	u32 pm_status;
-	u32 pm_control;
-	u32 pm_interval;
-	u32 pm_start_stop;
-	u32 pm07_control[NR_CTRS];
-
-	u32 pm_ctr[NR_PHYS_CTRS];
-	u32 counter_value_in_latch;
-};
-
-extern struct cbe_pmd_shadow_regs *cbe_get_pmd_shadow_regs(struct device_node *np);
-extern struct cbe_pmd_shadow_regs *cbe_get_cpu_pmd_shadow_regs(int cpu);
-
-/*
- *
- * IIC unit register definitions
- *
- */
-
-struct cbe_iic_pending_bits {
-	u32 data;
-	u8 flags;
-	u8 class;
-	u8 source;
-	u8 prio;
-};
-
-#define CBE_IIC_IRQ_VALID	0x80
-#define CBE_IIC_IRQ_IPI		0x40
-
-struct cbe_iic_thread_regs {
-	struct cbe_iic_pending_bits pending;
-	struct cbe_iic_pending_bits pending_destr;
-	u64 generate;
-	u64 prio;
-};
-
-struct cbe_iic_regs {
-	u8	pad_0x0000_0x0400[0x0400 - 0x0000];		/* 0x0000 */
-
-	/* IIC interrupt registers */
-	struct	cbe_iic_thread_regs thread[2];			/* 0x0400 */
-
-	u64	iic_ir;						/* 0x0440 */
-#define CBE_IIC_IR_PRIO(x)      (((x) & 0xf) << 12)
-#define CBE_IIC_IR_DEST_NODE(x) (((x) & 0xf) << 4)
-#define CBE_IIC_IR_DEST_UNIT(x) ((x) & 0xf)
-#define CBE_IIC_IR_IOC_0        0x0
-#define CBE_IIC_IR_IOC_1S       0xb
-#define CBE_IIC_IR_PT_0         0xe
-#define CBE_IIC_IR_PT_1         0xf
-
-	u64	iic_is;						/* 0x0448 */
-#define CBE_IIC_IS_PMI		0x2
-
-	u8	pad_0x0450_0x0500[0x0500 - 0x0450];		/* 0x0450 */
-
-	/* IOC FIR */
-	u64	ioc_fir_reset;					/* 0x0500 */
-	u64	ioc_fir_set;					/* 0x0508 */
-	u64	ioc_checkstop_enable;				/* 0x0510 */
-	u64	ioc_fir_error_mask;				/* 0x0518 */
-	u64	ioc_syserr_enable;				/* 0x0520 */
-	u64	ioc_fir;					/* 0x0528 */
-
-	u8	pad_0x0530_0x1000[0x1000 - 0x0530];		/* 0x0530 */
-};
-
-extern struct cbe_iic_regs __iomem *cbe_get_iic_regs(struct device_node *np);
-extern struct cbe_iic_regs __iomem *cbe_get_cpu_iic_regs(int cpu);
-
-
-struct cbe_mic_tm_regs {
-	u8	pad_0x0000_0x0040[0x0040 - 0x0000];		/* 0x0000 */
-
-	u64	mic_ctl_cnfg2;					/* 0x0040 */
-#define CBE_MIC_ENABLE_AUX_TRC		0x8000000000000000LL
-#define CBE_MIC_DISABLE_PWR_SAV_2	0x0200000000000000LL
-#define CBE_MIC_DISABLE_AUX_TRC_WRAP	0x0100000000000000LL
-#define CBE_MIC_ENABLE_AUX_TRC_INT	0x0080000000000000LL
-
-	u64	pad_0x0048;					/* 0x0048 */
-
-	u64	mic_aux_trc_base;				/* 0x0050 */
-	u64	mic_aux_trc_max_addr;				/* 0x0058 */
-	u64	mic_aux_trc_cur_addr;				/* 0x0060 */
-	u64	mic_aux_trc_grf_addr;				/* 0x0068 */
-	u64	mic_aux_trc_grf_data;				/* 0x0070 */
-
-	u64	pad_0x0078;					/* 0x0078 */
-
-	u64	mic_ctl_cnfg_0;					/* 0x0080 */
-#define CBE_MIC_DISABLE_PWR_SAV_0	0x8000000000000000LL
-
-	u64	pad_0x0088;					/* 0x0088 */
-
-	u64	slow_fast_timer_0;				/* 0x0090 */
-	u64	slow_next_timer_0;				/* 0x0098 */
-
-	u8	pad_0x00a0_0x00f8[0x00f8 - 0x00a0];		/* 0x00a0 */
-	u64    	mic_df_ecc_address_0;				/* 0x00f8 */
-
-	u8	pad_0x0100_0x01b8[0x01b8 - 0x0100];		/* 0x0100 */
-	u64    	mic_df_ecc_address_1;				/* 0x01b8 */
-
-	u64	mic_ctl_cnfg_1;					/* 0x01c0 */
-#define CBE_MIC_DISABLE_PWR_SAV_1	0x8000000000000000LL
-
-	u64	pad_0x01c8;					/* 0x01c8 */
-
-	u64	slow_fast_timer_1;				/* 0x01d0 */
-	u64	slow_next_timer_1;				/* 0x01d8 */
-
-	u8	pad_0x01e0_0x0208[0x0208 - 0x01e0];		/* 0x01e0 */
-	u64	mic_exc;					/* 0x0208 */
-#define CBE_MIC_EXC_BLOCK_SCRUB		0x0800000000000000ULL
-#define CBE_MIC_EXC_FAST_SCRUB		0x0100000000000000ULL
-
-	u64	mic_mnt_cfg;					/* 0x0210 */
-#define CBE_MIC_MNT_CFG_CHAN_0_POP	0x0002000000000000ULL
-#define CBE_MIC_MNT_CFG_CHAN_1_POP	0x0004000000000000ULL
-
-	u64	mic_df_config;					/* 0x0218 */
-#define CBE_MIC_ECC_DISABLE_0		0x4000000000000000ULL
-#define CBE_MIC_ECC_REP_SINGLE_0	0x2000000000000000ULL
-#define CBE_MIC_ECC_DISABLE_1		0x0080000000000000ULL
-#define CBE_MIC_ECC_REP_SINGLE_1	0x0040000000000000ULL
-
-	u8	pad_0x0220_0x0230[0x0230 - 0x0220];		/* 0x0220 */
-	u64	mic_fir;					/* 0x0230 */
-#define CBE_MIC_FIR_ECC_SINGLE_0_ERR	0x0200000000000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_0_ERR	0x0100000000000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_1_ERR	0x0080000000000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_1_ERR	0x0040000000000000ULL
-#define CBE_MIC_FIR_ECC_ERR_MASK	0xffff000000000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_0_CTE	0x0000020000000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_0_CTE	0x0000010000000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_1_CTE	0x0000008000000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_1_CTE	0x0000004000000000ULL
-#define CBE_MIC_FIR_ECC_CTE_MASK	0x0000ffff00000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_0_RESET	0x0000000002000000ULL
-#define CBE_MIC_FIR_ECC_MULTI_0_RESET	0x0000000001000000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_1_RESET	0x0000000000800000ULL
-#define CBE_MIC_FIR_ECC_MULTI_1_RESET	0x0000000000400000ULL
-#define CBE_MIC_FIR_ECC_RESET_MASK	0x00000000ffff0000ULL
-#define CBE_MIC_FIR_ECC_SINGLE_0_SET	0x0000000000000200ULL
-#define CBE_MIC_FIR_ECC_MULTI_0_SET	0x0000000000000100ULL
-#define CBE_MIC_FIR_ECC_SINGLE_1_SET	0x0000000000000080ULL
-#define CBE_MIC_FIR_ECC_MULTI_1_SET	0x0000000000000040ULL
-#define CBE_MIC_FIR_ECC_SET_MASK	0x000000000000ffffULL
-	u64	mic_fir_debug;					/* 0x0238 */
-
-	u8	pad_0x0240_0x1000[0x1000 - 0x0240];		/* 0x0240 */
-};
-
-extern struct cbe_mic_tm_regs __iomem *cbe_get_mic_tm_regs(struct device_node *np);
-extern struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu);
-
-
 /* Cell page table entries */
 #define CBE_IOPTE_PP_W		0x8000000000000000ul /* protection: write */
 #define CBE_IOPTE_PP_R		0x4000000000000000ul /* protection: read */
@@ -315,13 +28,4 @@ extern struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu);
 #define CBE_IOPTE_H		0x0000000000000800ul /* cache hint */
 #define CBE_IOPTE_IOID_Mask	0x00000000000007fful /* ioid */
 
-/* some utility functions to deal with SMT */
-extern u32 cbe_get_hw_thread_id(int cpu);
-extern u32 cbe_cpu_to_node(int cpu);
-extern u32 cbe_node_to_cpu(int node);
-
-/* Init this module early */
-extern void cbe_regs_init(void);
-
-
 #endif /* CBE_REGS_H */
diff --git a/arch/powerpc/include/asm/copro.h b/arch/powerpc/include/asm/copro.h
index fd2e166ea02a..81bd176203ab 100644
--- a/arch/powerpc/include/asm/copro.h
+++ b/arch/powerpc/include/asm/copro.h
@@ -18,10 +18,4 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 
 int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb);
 
-
-#ifdef CONFIG_PPC_COPRO_BASE
-void copro_flush_all_slbs(struct mm_struct *mm);
-#else
-static inline void copro_flush_all_slbs(struct mm_struct *mm) {}
-#endif
 #endif /* _ASM_POWERPC_COPRO_H */
diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h
index 3bdd74739cb8..e3c6969853ef 100644
--- a/arch/powerpc/include/asm/cpm1.h
+++ b/arch/powerpc/include/asm/cpm1.h
@@ -49,11 +49,6 @@
  */
 extern cpm8xx_t __iomem *cpmp; /* Pointer to comm processor */
 
-#define cpm_dpalloc cpm_muram_alloc
-#define cpm_dpfree cpm_muram_free
-#define cpm_dpram_addr cpm_muram_addr
-#define cpm_dpram_phys cpm_muram_dma
-
 extern void cpm_setbrg(uint brg, uint rate);
 
 extern void __init cpm_load_patch(cpm8xx_t *cp);
diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h
index 9ee192a6c5d7..a22acc36eb9b 100644
--- a/arch/powerpc/include/asm/cpm2.h
+++ b/arch/powerpc/include/asm/cpm2.h
@@ -87,10 +87,6 @@
  */
 extern cpm_cpm2_t __iomem *cpmp; /* Pointer to comm processor */
 
-#define cpm_dpalloc cpm_muram_alloc
-#define cpm_dpfree cpm_muram_free
-#define cpm_dpram_addr cpm_muram_addr
-
 extern void cpm2_reset(void);
 
 /* Baud rate generators.
@@ -1080,6 +1076,9 @@ typedef struct im_idma {
 #define FCC2_MEM_OFFSET FCC_MEM_OFFSET(1)
 #define FCC3_MEM_OFFSET FCC_MEM_OFFSET(2)
 
+/* Pipeline Maximum Depth */
+#define MPC82XX_BCR_PLDP 0x00800000
+
 /* Clocks and GRG's */
 
 enum cpm_clk_dir {
diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index 727d4b321937..604fa3b6c33d 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_POWERPC_CPU_HAS_FEATURE_H
 #define __ASM_POWERPC_CPU_HAS_FEATURE_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bug.h>
 #include <asm/cputable.h>
@@ -24,12 +24,11 @@ static __always_inline bool cpu_has_feature(unsigned long feature)
 {
 	int i;
 
-#ifndef __clang__ /* clang can't cope with this */
 	BUILD_BUG_ON(!__builtin_constant_p(feature));
-#endif
+	BUILD_BUG_ON(__builtin_popcountl(feature) > 1);
 
 #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
-	if (!static_key_initialized) {
+	if (!static_key_feature_checks_initialized) {
 		printk("Warning! cpu_has_feature() used prior to jump label init!\n");
 		dump_stack();
 		return early_cpu_has_feature(feature);
@@ -52,5 +51,5 @@ static __always_inline bool cpu_has_feature(unsigned long feature)
 }
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_POWERPC_CPU_HAS_FEATURE_H */
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index 0cce5dc7fb1c..054cd2fcfd55 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -68,7 +68,7 @@
 #define ERR_EC_ESL_MISMATCH		-1
 #define ERR_DEEP_STATE_ESL_MISMATCH	-2
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define PNV_IDLE_NAME_LEN    16
 struct pnv_idle_states_t {
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 757dbded11dc..ec16c12296da 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -7,7 +7,7 @@
 #include <uapi/asm/cputable.h>
 #include <asm/asm-const.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /* This structure can grow, it's real size is used by head.S code
  * via the mkdefs mechanism.
@@ -103,7 +103,7 @@ extern void cpu_feature_keys_init(void);
 static inline void cpu_feature_keys_init(void) { }
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* CPU kernel features */
 
@@ -192,8 +192,10 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_P9_RADIX_PREFETCH_BUG	LONG_ASM_CONST(0x0002000000000000)
 #define CPU_FTR_ARCH_31			LONG_ASM_CONST(0x0004000000000000)
 #define CPU_FTR_DAWR1			LONG_ASM_CONST(0x0008000000000000)
+#define CPU_FTR_DEXCR_NPHIE		LONG_ASM_CONST(0x0010000000000000)
+#define CPU_FTR_P11_PVR			LONG_ASM_CONST(0x0020000000000000)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define CPU_FTR_PPCAS_ARCH_V2	(CPU_FTR_NOEXECUTE)
 
@@ -251,7 +253,7 @@ static inline void cpu_feature_keys_init(void) { }
  * This is also required by 52xx family.
  */
 #if defined(CONFIG_SMP) || defined(CONFIG_MPC10X_BRIDGE) \
-	|| defined(CONFIG_PPC_83xx) || defined(CONFIG_8260) \
+	|| defined(CONFIG_PPC_83xx) || defined(CONFIG_PPC_82xx) \
 	|| defined(CONFIG_PPC_MPC52xx)
 #define CPU_FTR_COMMON                  CPU_FTR_NEED_COHERENT
 #else
@@ -352,7 +354,6 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE  | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_CLASSIC32	(CPU_FTR_COMMON)
 #define CPU_FTRS_8XX	(CPU_FTR_NOEXECUTE)
-#define CPU_FTRS_40X	(CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_44X	(CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_440x6	(CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_INDEXED_DCR)
@@ -451,7 +452,11 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
 	    CPU_FTR_ARCH_300 | CPU_FTR_ARCH_31 | \
-	    CPU_FTR_DAWR | CPU_FTR_DAWR1)
+	    CPU_FTR_DAWR | CPU_FTR_DAWR1 | \
+	    CPU_FTR_DEXCR_NPHIE)
+
+#define CPU_FTRS_POWER11	(CPU_FTRS_POWER10 | CPU_FTR_P11_PVR)
+
 #define CPU_FTRS_CELL	(CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -471,7 +476,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    (CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \
 	     CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | CPU_FTRS_POWER9 | \
 	     CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \
-	     CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10)
+	     CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10 | CPU_FTRS_POWER11)
 #else
 #define CPU_FTRS_POSSIBLE	\
 	    (CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
@@ -479,7 +484,7 @@ static inline void cpu_feature_keys_init(void) { }
 	     CPU_FTRS_POWER8 | CPU_FTRS_CELL | CPU_FTRS_PA6T | \
 	     CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | CPU_FTRS_POWER9 | \
 	     CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \
-	     CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10)
+	     CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10 | CPU_FTRS_POWER11)
 #endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
 #else
@@ -502,9 +507,6 @@ enum {
 #ifdef CONFIG_PPC_8xx
 	    CPU_FTRS_8XX |
 #endif
-#ifdef CONFIG_40x
-	    CPU_FTRS_40X |
-#endif
 #ifdef CONFIG_PPC_47x
 	    CPU_FTRS_47X | CPU_FTR_476_DD2 |
 #elif defined(CONFIG_44x)
@@ -540,20 +542,21 @@ enum {
 #define CPU_FTRS_DT_CPU_BASE	(~0ul)
 #endif
 
+/* pseries may disable DBELL with ibm,pi-features */
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
 #define CPU_FTRS_ALWAYS \
-	    (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & CPU_FTRS_POWER7 & \
-	     CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & CPU_FTRS_POWER9 & \
-	     CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
-	     CPU_FTRS_POWER10 & CPU_FTRS_DT_CPU_BASE)
+	    (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & ~CPU_FTR_DBELL & \
+	     CPU_FTRS_POWER7 & CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & \
+	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
+	     CPU_FTRS_POWER10 & CPU_FTRS_POWER11 & CPU_FTRS_DT_CPU_BASE)
 #else
 #define CPU_FTRS_ALWAYS		\
 	    (CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \
 	     CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \
 	     CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \
-	     ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & CPU_FTRS_POWER9 & \
-	     CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
-	     CPU_FTRS_POWER10 & CPU_FTRS_DT_CPU_BASE)
+	     ~CPU_FTR_HVMODE & ~CPU_FTR_DBELL & CPU_FTRS_POSSIBLE & \
+	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
+	     CPU_FTRS_POWER10 & CPU_FTRS_POWER11 & CPU_FTRS_DT_CPU_BASE)
 #endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
 #else
@@ -576,9 +579,6 @@ enum {
 #ifdef CONFIG_PPC_8xx
 	    CPU_FTRS_8XX &
 #endif
-#ifdef CONFIG_40x
-	    CPU_FTRS_40X &
-#endif
 #ifdef CONFIG_PPC_47x
 	    CPU_FTRS_47X &
 #elif defined(CONFIG_44x)
@@ -602,6 +602,6 @@ enum {
  */
 #define HBP_NUM_MAX	2
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index f26c430f3982..d06f2b20b810 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_POWERPC_CPUTHREADS_H
 #define _ASM_POWERPC_CPUTHREADS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/cpumask.h>
 #include <asm/cpu_has_feature.h>
 
@@ -107,7 +107,7 @@ static inline u32 get_tensr(void)
 void book3e_start_thread(int thread, unsigned long addr);
 void book3e_stop_thread(int thread);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define INVALID_THREAD_HWID	0x0fff
 
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 4961fb38e438..aff858ca99c0 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -32,23 +32,10 @@
 #ifdef CONFIG_PPC64
 #define get_accounting(tsk)	(&get_paca()->accounting)
 #define raw_get_accounting(tsk)	(&local_paca->accounting)
-static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
 
 #else
 #define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
 #define raw_get_accounting(tsk)	get_accounting(tsk)
-/*
- * Called from the context switch with interrupts disabled, to charge all
- * accumulated times to the current process, and to prepare accounting on
- * the next process.
- */
-static inline void arch_vtime_task_switch(struct task_struct *prev)
-{
-	struct cpu_accounting_data *acct = get_accounting(current);
-	struct cpu_accounting_data *acct0 = get_accounting(prev);
-
-	acct->starttime = acct0->starttime;
-}
 #endif
 
 /*
diff --git a/arch/powerpc/include/asm/crash_reserve.h b/arch/powerpc/include/asm/crash_reserve.h
new file mode 100644
index 000000000000..d1b570ddbf98
--- /dev/null
+++ b/arch/powerpc/include/asm/crash_reserve.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CRASH_RESERVE_H
+#define _ASM_POWERPC_CRASH_RESERVE_H
+
+/* crash kernel regions are Page size agliged */
+#define CRASH_ALIGN             PAGE_SIZE
+
+#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+static inline bool arch_add_crash_res_to_iomem(void)
+{
+	return false;
+}
+#define arch_add_crash_res_to_iomem arch_add_crash_res_to_iomem
+#endif
+
+#endif /* _ASM_POWERPC_CRASH_RESERVE_H */
diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index 3e9da22a2779..0b9ef726f92c 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -40,12 +40,6 @@ static inline void _ppc_msgsnd(u32 msg)
 				: : "i" (CPU_FTR_HVMODE), "r" (msg));
 }
 
-/* sync before sending message */
-static inline void ppc_msgsnd_sync(void)
-{
-	__asm__ __volatile__ ("sync" : : : "memory");
-}
-
 /* sync after taking message interrupt */
 static inline void ppc_msgsync(void)
 {
@@ -76,12 +70,6 @@ static inline void _ppc_msgsnd(u32 msg)
 	__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
 }
 
-/* sync before sending message */
-static inline void ppc_msgsnd_sync(void)
-{
-	__asm__ __volatile__ ("sync" : : : "memory");
-}
-
 /* sync after taking message interrupt */
 static inline void ppc_msgsync(void)
 {
@@ -91,6 +79,12 @@ static inline void ppc_msgsync(void)
 
 extern void doorbell_exception(struct pt_regs *regs);
 
+/* sync before sending message */
+static inline void ppc_msgsnd_sync(void)
+{
+	__asm__ __volatile__ ("sync" : : : "memory");
+}
+
 static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag)
 {
 	u32 msg = PPC_DBELL_TYPE(type) | (flags & PPC_DBELL_MSG_BRDCAST) |
diff --git a/arch/powerpc/include/asm/dcr-generic.h b/arch/powerpc/include/asm/dcr-generic.h
deleted file mode 100644
index 099c28dd40b9..000000000000
--- a/arch/powerpc/include/asm/dcr-generic.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
- *                    <benh@kernel.crashing.org>
- */
-
-#ifndef _ASM_POWERPC_DCR_GENERIC_H
-#define _ASM_POWERPC_DCR_GENERIC_H
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-enum host_type_t {DCR_HOST_MMIO, DCR_HOST_NATIVE, DCR_HOST_INVALID};
-
-typedef struct {
-	enum host_type_t type;
-	union {
-		dcr_host_mmio_t mmio;
-		dcr_host_native_t native;
-	} host;
-} dcr_host_t;
-
-extern bool dcr_map_ok_generic(dcr_host_t host);
-
-extern dcr_host_t dcr_map_generic(struct device_node *dev, unsigned int dcr_n,
-			  unsigned int dcr_c);
-extern void dcr_unmap_generic(dcr_host_t host, unsigned int dcr_c);
-
-extern u32 dcr_read_generic(dcr_host_t host, unsigned int dcr_n);
-
-extern void dcr_write_generic(dcr_host_t host, unsigned int dcr_n, u32 value);
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_DCR_GENERIC_H */
-
-
diff --git a/arch/powerpc/include/asm/dcr-mmio.h b/arch/powerpc/include/asm/dcr-mmio.h
deleted file mode 100644
index fc6d93ef4a13..000000000000
--- a/arch/powerpc/include/asm/dcr-mmio.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
- *                    <benh@kernel.crashing.org>
- */
-
-#ifndef _ASM_POWERPC_DCR_MMIO_H
-#define _ASM_POWERPC_DCR_MMIO_H
-#ifdef __KERNEL__
-
-#include <asm/io.h>
-
-typedef struct {
-	void __iomem *token;
-	unsigned int stride;
-	unsigned int base;
-} dcr_host_mmio_t;
-
-static inline bool dcr_map_ok_mmio(dcr_host_mmio_t host)
-{
-	return host.token != NULL;
-}
-
-extern dcr_host_mmio_t dcr_map_mmio(struct device_node *dev,
-				    unsigned int dcr_n,
-				    unsigned int dcr_c);
-extern void dcr_unmap_mmio(dcr_host_mmio_t host, unsigned int dcr_c);
-
-static inline u32 dcr_read_mmio(dcr_host_mmio_t host, unsigned int dcr_n)
-{
-	return in_be32(host.token + ((host.base + dcr_n) * host.stride));
-}
-
-static inline void dcr_write_mmio(dcr_host_mmio_t host,
-				  unsigned int dcr_n,
-				  u32 value)
-{
-	out_be32(host.token + ((host.base + dcr_n) * host.stride), value);
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_DCR_MMIO_H */
-
-
diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h
index a92059964579..65b3fc2dc404 100644
--- a/arch/powerpc/include/asm/dcr-native.h
+++ b/arch/powerpc/include/asm/dcr-native.h
@@ -7,7 +7,7 @@
 #ifndef _ASM_POWERPC_DCR_NATIVE_H
 #define _ASM_POWERPC_DCR_NATIVE_H
 #ifdef __KERNEL__
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/spinlock.h>
 #include <asm/cputable.h>
@@ -139,6 +139,6 @@ static inline void __dcri_clrset(int base_addr, int base_data, int reg,
 							      DCRN_ ## base ## _CONFIG_DATA,	\
 							      reg, clr, set)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_DCR_NATIVE_H */
diff --git a/arch/powerpc/include/asm/dcr.h b/arch/powerpc/include/asm/dcr.h
index 64030e3a1f30..3c0fac2cc2b2 100644
--- a/arch/powerpc/include/asm/dcr.h
+++ b/arch/powerpc/include/asm/dcr.h
@@ -7,49 +7,17 @@
 #ifndef _ASM_POWERPC_DCR_H
 #define _ASM_POWERPC_DCR_H
 #ifdef __KERNEL__
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifdef CONFIG_PPC_DCR
 
-#ifdef CONFIG_PPC_DCR_NATIVE
 #include <asm/dcr-native.h>
-#endif
 
-#ifdef CONFIG_PPC_DCR_MMIO
-#include <asm/dcr-mmio.h>
-#endif
-
-
-/* Indirection layer for providing both NATIVE and MMIO support. */
-
-#if defined(CONFIG_PPC_DCR_NATIVE) && defined(CONFIG_PPC_DCR_MMIO)
-
-#include <asm/dcr-generic.h>
-
-#define DCR_MAP_OK(host)	dcr_map_ok_generic(host)
-#define dcr_map(dev, dcr_n, dcr_c) dcr_map_generic(dev, dcr_n, dcr_c)
-#define dcr_unmap(host, dcr_c) dcr_unmap_generic(host, dcr_c)
-#define dcr_read(host, dcr_n) dcr_read_generic(host, dcr_n)
-#define dcr_write(host, dcr_n, value) dcr_write_generic(host, dcr_n, value)
-
-#else
-
-#ifdef CONFIG_PPC_DCR_NATIVE
 typedef dcr_host_native_t dcr_host_t;
 #define DCR_MAP_OK(host)	dcr_map_ok_native(host)
 #define dcr_map(dev, dcr_n, dcr_c) dcr_map_native(dev, dcr_n, dcr_c)
 #define dcr_unmap(host, dcr_c) dcr_unmap_native(host, dcr_c)
 #define dcr_read(host, dcr_n) dcr_read_native(host, dcr_n)
 #define dcr_write(host, dcr_n, value) dcr_write_native(host, dcr_n, value)
-#else
-typedef dcr_host_mmio_t dcr_host_t;
-#define DCR_MAP_OK(host)	dcr_map_ok_mmio(host)
-#define dcr_map(dev, dcr_n, dcr_c) dcr_map_mmio(dev, dcr_n, dcr_c)
-#define dcr_unmap(host, dcr_c) dcr_unmap_mmio(host, dcr_c)
-#define dcr_read(host, dcr_n) dcr_read_mmio(host, dcr_n)
-#define dcr_write(host, dcr_n, value) dcr_write_mmio(host, dcr_n, value)
-#endif
-
-#endif /* defined(CONFIG_PPC_DCR_NATIVE) && defined(CONFIG_PPC_DCR_MMIO) */
 
 /*
  * additional helpers to read the DCR * base from the device-tree
@@ -60,6 +28,6 @@ extern unsigned int dcr_resource_start(const struct device_node *np,
 extern unsigned int dcr_resource_len(const struct device_node *np,
 				     unsigned int index);
 #endif /* CONFIG_PPC_DCR */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_DCR_H */
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 47ed639f3b8f..a4dc27655b3e 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -38,9 +38,6 @@ struct dev_archdata {
 #ifdef CONFIG_FAIL_IOMMU
 	int fail_iommu;
 #endif
-#ifdef CONFIG_CXL_BASE
-	struct cxl_context	*cxl_ctx;
-#endif
 #ifdef CONFIG_PCI_IOV
 	void *iov_data;
 #endif
diff --git a/arch/powerpc/include/asm/dtl.h b/arch/powerpc/include/asm/dtl.h
index 4bcb9f9ac764..a5c21bc623cb 100644
--- a/arch/powerpc/include/asm/dtl.h
+++ b/arch/powerpc/include/asm/dtl.h
@@ -1,8 +1,8 @@
 #ifndef _ASM_POWERPC_DTL_H
 #define _ASM_POWERPC_DTL_H
 
+#include <linux/rwsem.h>
 #include <asm/lppaca.h>
-#include <linux/spinlock_types.h>
 
 /*
  * Layout of entries in the hypervisor's dispatch trace log buffer.
@@ -35,10 +35,9 @@ struct dtl_entry {
 #define DTL_LOG_ALL		(DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT)
 
 extern struct kmem_cache *dtl_cache;
-extern rwlock_t dtl_access_lock;
+extern struct rw_semaphore dtl_access_lock;
 
 extern void register_dtl_buffer(int cpu);
 extern void alloc_dtl_buffers(unsigned long *time_limit);
-extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity);
 
 #endif /* _ASM_POWERPC_DTL_H */
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 514dd056c2c8..5e34611de9ef 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -82,7 +82,7 @@ struct eeh_pe {
 	int false_positives;		/* Times of reported #ff's	*/
 	atomic_t pass_dev_cnt;		/* Count of passed through devs	*/
 	struct eeh_pe *parent;		/* Parent PE			*/
-	void *data;			/* PE auxillary data		*/
+	void *data;			/* PE auxiliary data		*/
 	struct list_head child_list;	/* List of PEs below this PE	*/
 	struct list_head child;		/* Memb. child_list/eeh_phb_pe	*/
 	struct list_head edevs;		/* List of eeh_dev in this PE	*/
@@ -308,6 +308,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed);
 int eeh_pe_configure(struct eeh_pe *pe);
 int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
 		      unsigned long addr, unsigned long mask);
+int eeh_pe_inject_mmio_error(struct pci_dev *pdev);
 
 /**
  * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 79f1c480b5eb..bb4b94444d3e 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -127,8 +127,6 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 /* Notes used in ET_CORE. Note name is "SPU/<fd>/<filename>". */
 #define NT_SPU		1
 
-#define ARCH_HAVE_EXTRA_ELF_NOTES
-
 #endif /* CONFIG_SPU_BASE */
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index cdf3c6df5123..8fc5aaa4bbba 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -52,7 +52,7 @@
 
 #include <uapi/asm/epapr_hcalls.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <asm/byteorder.h>
@@ -571,5 +571,5 @@ static inline long epapr_hypercall4(unsigned int nr, unsigned long p1,
 	in[3] = p4;
 	return epapr_hypercall(in, out, nr);
 }
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _EPAPR_HCALLS_H */
diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h
index b1ef1e92c34a..1a83b1ff3578 100644
--- a/arch/powerpc/include/asm/exception-64e.h
+++ b/arch/powerpc/include/asm/exception-64e.h
@@ -149,7 +149,7 @@ exc_##label##_book3e:
 	addi	r11,r13,PACA_EXTLB;					    \
 	TLB_MISS_RESTORE(r11)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern unsigned int interrupt_base_book3e;
 #endif
 
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index bb6f78fcf981..a9437e89f69f 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -53,7 +53,7 @@
  */
 #define MAX_MCE_DEPTH	4
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define STF_ENTRY_BARRIER_SLOT						\
 	STF_ENTRY_BARRIER_FIXUP_SECTION;				\
@@ -170,9 +170,9 @@
 	RFSCV;								\
 	b	rfscv_flush_fallback
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 /* Prototype for function defined in exceptions-64s.S */
 void do_uaccess_flush(void);
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif	/* _ASM_POWERPC_EXCEPTION_H */
diff --git a/arch/powerpc/include/asm/extable.h b/arch/powerpc/include/asm/extable.h
index 26ce2e5c0fa8..d483a9c24ba9 100644
--- a/arch/powerpc/include/asm/extable.h
+++ b/arch/powerpc/include/asm/extable.h
@@ -17,7 +17,7 @@
 
 #define ARCH_HAS_RELATIVE_EXTABLE
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct exception_table_entry {
 	int insn;
diff --git a/arch/powerpc/include/asm/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h
index 27f9e11eda28..e83869a4eb6a 100644
--- a/arch/powerpc/include/asm/fadump-internal.h
+++ b/arch/powerpc/include/asm/fadump-internal.h
@@ -42,13 +42,38 @@ static inline u64 fadump_str_to_u64(const char *str)
 
 #define FADUMP_CPU_UNKNOWN		(~((u32)0))
 
-#define FADUMP_CRASH_INFO_MAGIC		fadump_str_to_u64("FADMPINF")
+/*
+ * The introduction of new fields in the fadump crash info header has
+ * led to a change in the magic key from `FADMPINF` to `FADMPSIG` for
+ * identifying a kernel crash from an old kernel.
+ *
+ * To prevent the need for further changes to the magic number in the
+ * event of future modifications to the fadump crash info header, a
+ * version field has been introduced to track the fadump crash info
+ * header version.
+ *
+ * Consider a few points before adding new members to the fadump crash info
+ * header structure:
+ *
+ *  - Append new members; avoid adding them in between.
+ *  - Non-primitive members should have a size member as well.
+ *  - For every change in the fadump header, increment the
+ *    fadump header version. This helps the updated kernel decide how to
+ *    handle kernel dumps from older kernels.
+ */
+#define FADUMP_CRASH_INFO_MAGIC_OLD	fadump_str_to_u64("FADMPINF")
+#define FADUMP_CRASH_INFO_MAGIC		fadump_str_to_u64("FADMPSIG")
+#define FADUMP_HEADER_VERSION		1
 
 /* fadump crash info structure */
 struct fadump_crash_info_header {
 	u64		magic_number;
-	u64		elfcorehdr_addr;
+	u32		version;
 	u32		crashing_cpu;
+	u64		vmcoreinfo_raddr;
+	u64		vmcoreinfo_size;
+	u32		pt_regs_sz;
+	u32		cpu_mask_sz;
 	struct pt_regs	regs;
 	struct cpumask	cpu_mask;
 };
@@ -94,9 +119,13 @@ struct fw_dump {
 	u64		boot_mem_regs_cnt;
 
 	unsigned long	fadumphdr_addr;
+	u64		elfcorehdr_addr;
+	u64		elfcorehdr_size;
 	unsigned long	cpu_notes_buf_vaddr;
 	unsigned long	cpu_notes_buf_size;
 
+	unsigned long	param_area;
+
 	/*
 	 * Maximum size supported by firmware to copy from source to
 	 * destination address per entry.
@@ -111,6 +140,7 @@ struct fw_dump {
 	unsigned long	dump_active:1;
 	unsigned long	dump_registered:1;
 	unsigned long	nocma:1;
+	unsigned long	param_area_supported:1;
 
 	struct fadump_ops	*ops;
 };
@@ -129,6 +159,7 @@ struct fadump_ops {
 				      struct seq_file *m);
 	void	(*fadump_trigger)(struct fadump_crash_info_header *fdh,
 				  const char *msg);
+	int	(*fadump_max_boot_mem_rgns)(void);
 };
 
 /* Helper functions */
@@ -136,7 +167,6 @@ s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus);
 void fadump_free_cpu_notes_buf(void);
 u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs);
 void __init fadump_update_elfcore_header(char *bufp);
-bool is_fadump_boot_mem_contiguous(void);
 bool is_fadump_reserved_mem_contiguous(void);
 
 #else /* !CONFIG_PRESERVE_FA_DUMP */
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 526a6a647312..a48f54dde4f6 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -19,12 +19,16 @@ extern int is_fadump_active(void);
 extern int should_fadump_crash(void);
 extern void crash_fadump(struct pt_regs *, const char *);
 extern void fadump_cleanup(void);
+void fadump_setup_param_area(void);
+extern void fadump_append_bootargs(void);
 
 #else	/* CONFIG_FA_DUMP */
 static inline int is_fadump_active(void) { return 0; }
 static inline int should_fadump_crash(void) { return 0; }
 static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
 static inline void fadump_cleanup(void) { }
+static inline void fadump_setup_param_area(void) { }
+static inline void fadump_append_bootargs(void) { }
 #endif /* !CONFIG_FA_DUMP */
 
 #if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
@@ -32,4 +36,11 @@ extern int early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
 				      int depth, void *data);
 extern int fadump_reserve_mem(void);
 #endif
+
+#if defined(CONFIG_FA_DUMP) && defined(CONFIG_CMA)
+void fadump_cma_init(void);
+#else
+static inline void fadump_cma_init(void) { }
+#endif
+
 #endif /* _ASM_POWERPC_FADUMP_H */
diff --git a/arch/powerpc/include/asm/fb.h b/arch/powerpc/include/asm/fb.h
deleted file mode 100644
index 6541ab77c5b9..000000000000
--- a/arch/powerpc/include/asm/fb.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-
-#include <linux/fb.h>
-#include <linux/fs.h>
-#include <asm/page.h>
-
-static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
-				unsigned long off)
-{
-	vma->vm_page_prot = phys_mem_access_prot(file, off >> PAGE_SHIFT,
-						 vma->vm_end - vma->vm_start,
-						 vma->vm_page_prot);
-}
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
-	return 0;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index ac605fc369c4..756a6c694018 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -168,7 +168,7 @@ label##5:							\
 #define ALT_FW_FTR_SECTION_END_IFCLR(msk)	\
 	ALT_FW_FTR_SECTION_END_NESTED_IFCLR(msk, 97)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define ASM_FTR_IF(section_if, section_else, msk, val)	\
 	stringify_in_c(BEGIN_FTR_SECTION)			\
@@ -196,7 +196,7 @@ label##5:							\
 #define ASM_MMU_FTR_IFCLR(section_if, section_else, msk)	\
 	ASM_MMU_FTR_IF(section_if, section_else, (msk), 0)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* LWSYNC feature sections */
 #define START_LWSYNC_SECTION(label)	label##1:
@@ -276,7 +276,7 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET 956b-957b;			\
 	.popsection;
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 extern long stf_barrier_fallback;
@@ -291,7 +291,10 @@ extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
 extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
 extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;
 
+extern bool static_key_feature_checks_initialized;
+
 void apply_feature_fixups(void);
+void update_mmu_feature_fixups(unsigned long mask);
 void setup_feature_keys(void);
 #endif
 
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 69ae9cf57d50..abd7c56f4d55 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -58,7 +58,7 @@
 #define FW_FEATURE_WATCHDOG	ASM_CONST(0x0000080000000000)
 #define FW_FEATURE_PLPKS	ASM_CONST(0x0000100000000000)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 enum {
 #ifdef CONFIG_PPC64
@@ -146,6 +146,6 @@ void pseries_probe_fw_features(void);
 static inline void pseries_probe_fw_features(void) { }
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_FIRMWARE_H */
diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index a832aeafe560..bc5109eab5b7 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -14,7 +14,7 @@
 #ifndef _ASM_FIXMAP_H
 #define _ASM_FIXMAP_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/sizes.h>
 #include <linux/pgtable.h>
 #include <asm/page.h>
@@ -23,18 +23,6 @@
 #include <asm/kmap_size.h>
 #endif
 
-#ifdef CONFIG_PPC64
-#define FIXADDR_TOP	(IOREMAP_END + FIXADDR_SIZE)
-#else
-#define FIXADDR_SIZE	0
-#ifdef CONFIG_KASAN
-#include <asm/kasan.h>
-#define FIXADDR_TOP	(KASAN_SHADOW_START - PAGE_SIZE)
-#else
-#define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
-#endif
-#endif
-
 /*
  * Here we define all the compile-time 'special' virtual
  * addresses. The point is to have a constant address at
@@ -119,5 +107,9 @@ static inline void __set_fixmap(enum fixed_addresses idx,
 
 #define __early_set_fixmap	__set_fixmap
 
-#endif /* !__ASSEMBLY__ */
+#ifdef CONFIG_PPC_8xx
+#define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE))
+#endif
+
+#endif /* !__ASSEMBLER__ */
 #endif
diff --git a/arch/powerpc/include/asm/floppy.h b/arch/powerpc/include/asm/floppy.h
index f8ce178b43b7..f4dc657638b3 100644
--- a/arch/powerpc/include/asm/floppy.h
+++ b/arch/powerpc/include/asm/floppy.h
@@ -144,9 +144,12 @@ static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
 		bus_addr = 0;
 	}
 
-	if (!bus_addr)	/* need to map it */
+	if (!bus_addr) {	/* need to map it */
 		bus_addr = dma_map_single(&isa_bridge_pcidev->dev, addr, size,
 					  dir);
+		if (dma_mapping_error(&isa_bridge_pcidev->dev, bus_addr))
+			return -ENOMEM;
+	}
 
 	/* remember this one as prev */
 	prev_addr = addr;
@@ -203,11 +206,6 @@ static int FDC2 = -1;
 #define N_FDC 2			/* Don't change this! */
 #define N_DRIVE 8
 
-/*
- * The PowerPC has no problems with floppy DMA crossing 64k borders.
- */
-#define CROSS_64KB(a,s)	(0)
-
 #define EXTRA_FLOPPY_PARAMS
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/fprobe.h b/arch/powerpc/include/asm/fprobe.h
new file mode 100644
index 000000000000..d64bc28fb3d3
--- /dev/null
+++ b/arch/powerpc/include/asm/fprobe.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_PPC_FPROBE_H
+#define _ASM_PPC_FPROBE_H
+
+#include <asm-generic/fprobe.h>
+
+#ifdef CONFIG_64BIT
+#undef FPROBE_HEADER_MSB_PATTERN
+#define FPROBE_HEADER_MSB_PATTERN	(PAGE_OFFSET & ~FPROBE_HEADER_MSB_MASK)
+#endif
+
+#endif /* _ASM_PPC_FPROBE_H */
diff --git a/arch/powerpc/include/asm/fpu.h b/arch/powerpc/include/asm/fpu.h
new file mode 100644
index 000000000000..ca584e4bc40f
--- /dev/null
+++ b/arch/powerpc/include/asm/fpu.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef _ASM_POWERPC_FPU_H
+#define _ASM_POWERPC_FPU_H
+
+#include <linux/preempt.h>
+
+#include <asm/cpu_has_feature.h>
+#include <asm/switch_to.h>
+
+#define kernel_fpu_available()	(!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE))
+
+static inline void kernel_fpu_begin(void)
+{
+	preempt_disable();
+	enable_kernel_fp();
+}
+
+static inline void kernel_fpu_end(void)
+{
+	disable_kernel_fp();
+	preempt_enable();
+}
+
+#endif /* ! _ASM_POWERPC_FPU_H */
diff --git a/arch/powerpc/include/asm/fs_pd.h b/arch/powerpc/include/asm/fs_pd.h
deleted file mode 100644
index 8def56ec05c6..000000000000
--- a/arch/powerpc/include/asm/fs_pd.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * Platform information definitions.
- *
- * 2006 (c) MontaVista Software, Inc.
- * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#ifndef FS_PD_H
-#define FS_PD_H
-#include <sysdev/fsl_soc.h>
-#include <asm/time.h>
-
-#ifdef CONFIG_CPM2
-#include <asm/cpm2.h>
-
-#if defined(CONFIG_8260)
-#include <asm/mpc8260.h>
-#endif
-
-#define cpm2_map(member) (&cpm2_immr->member)
-#define cpm2_map_size(member, size) (&cpm2_immr->member)
-#define cpm2_unmap(addr) do {} while(0)
-#endif
-
-#ifdef CONFIG_PPC_8xx
-#include <asm/8xx_immap.h>
-
-extern immap_t __iomem *mpc8xx_immr;
-
-#define immr_map(member) (&mpc8xx_immr->member)
-#define immr_map_size(member, size) (&mpc8xx_immr->member)
-#define immr_unmap(addr) do {} while (0)
-#endif
-
-static inline int uart_baudrate(void)
-{
-        return get_baudrate();
-}
-
-static inline int uart_clock(void)
-{
-        return ppc_proc_freq;
-}
-
-#endif
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 91c049d51d0e..5984eaa75ce8 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -8,82 +8,90 @@
 #define MCOUNT_ADDR		((unsigned long)(_mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
-#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
-
 /* Ignore unused weak functions which will have larger offsets */
-#ifdef CONFIG_MPROFILE_KERNEL
-#define FTRACE_MCOUNT_MAX_OFFSET	12
+#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
+#define FTRACE_MCOUNT_MAX_OFFSET	16
 #elif defined(CONFIG_PPC32)
 #define FTRACE_MCOUNT_MAX_OFFSET	8
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern void _mcount(void);
 
-static inline unsigned long ftrace_call_adjust(unsigned long addr)
-{
-       /* relocation of mcount call site is the same as the address */
-       return addr;
-}
-
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
 				    unsigned long sp);
 
+struct module;
+struct dyn_ftrace;
 struct dyn_arch_ftrace {
-	struct module *mod;
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	/* pointer to the associated out-of-line stub */
+	unsigned long ool_stub;
+#endif
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
-struct ftrace_regs {
-	struct pt_regs regs;
-};
+#define ftrace_need_init_nop()	(true)
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
+#define ftrace_init_nop ftrace_init_nop
+
+#include <linux/ftrace_regs.h>
 
 static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs)
 {
 	/* We clear regs.msr in ftrace_call */
-	return fregs->regs.msr ? &fregs->regs : NULL;
+	return arch_ftrace_regs(fregs)->regs.msr ? &arch_ftrace_regs(fregs)->regs : NULL;
+}
+
+#define arch_ftrace_fill_perf_regs(fregs, _regs) do {		\
+		(_regs)->result = 0;				\
+		(_regs)->nip = arch_ftrace_regs(fregs)->regs.nip;		\
+		(_regs)->gpr[1] = arch_ftrace_regs(fregs)->regs.gpr[1];		\
+		asm volatile("mfmsr %0" : "=r" ((_regs)->msr));	\
+	} while (0)
+
+#undef ftrace_regs_get_return_value
+static __always_inline unsigned long
+ftrace_regs_get_return_value(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->regs.gpr[3];
+}
+#define ftrace_regs_get_return_value ftrace_regs_get_return_value
+
+#undef ftrace_regs_get_frame_pointer
+static __always_inline unsigned long
+ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->regs.gpr[1];
 }
 
 static __always_inline void
 ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
 				    unsigned long ip)
 {
-	regs_set_return_ip(&fregs->regs, ip);
+	regs_set_return_ip(&arch_ftrace_regs(fregs)->regs, ip);
 }
 
 static __always_inline unsigned long
-ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs)
+ftrace_regs_get_return_address(struct ftrace_regs *fregs)
 {
-	return instruction_pointer(&fregs->regs);
+	return arch_ftrace_regs(fregs)->regs.link;
 }
 
-#define ftrace_regs_get_argument(fregs, n) \
-	regs_get_kernel_argument(&(fregs)->regs, n)
-#define ftrace_regs_get_stack_pointer(fregs) \
-	kernel_stack_pointer(&(fregs)->regs)
-#define ftrace_regs_return_value(fregs) \
-	regs_return_value(&(fregs)->regs)
-#define ftrace_regs_set_return_value(fregs, ret) \
-	regs_set_return_value(&(fregs)->regs, ret)
-#define ftrace_override_function_with_return(fregs) \
-	override_function_with_return(&(fregs)->regs)
-#define ftrace_regs_query_register_offset(name) \
-	regs_query_register_offset(name)
-
 struct ftrace_ops;
 
 #define ftrace_graph_func ftrace_graph_func
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs);
 #endif
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #endif
 #endif /* CONFIG_FUNCTION_TRACER */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifdef CONFIG_FTRACE_SYSCALLS
 /*
  * Some syscall entry functions on powerpc start with "ppc_" (fork and clone,
@@ -124,15 +132,49 @@ static inline u8 this_cpu_get_ftrace_enabled(void)
 {
 	return get_paca()->ftrace_enabled;
 }
-
-void ftrace_free_init_tramp(void);
 #else /* CONFIG_PPC64 */
 static inline void this_cpu_disable_ftrace(void) { }
 static inline void this_cpu_enable_ftrace(void) { }
 static inline void this_cpu_set_ftrace_enabled(u8 ftrace_enabled) { }
 static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; }
-static inline void ftrace_free_init_tramp(void) { }
 #endif /* CONFIG_PPC64 */
-#endif /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_FUNCTION_TRACER
+extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+struct ftrace_ool_stub {
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	struct ftrace_ops *ftrace_op;
+#endif
+	u32	insn[4];
+} __aligned(sizeof(unsigned long));
+extern struct ftrace_ool_stub ftrace_ool_stub_text_end[], ftrace_ool_stub_text[],
+			      ftrace_ool_stub_inittext[];
+extern unsigned int ftrace_ool_stub_text_end_count, ftrace_ool_stub_text_count,
+		    ftrace_ool_stub_inittext_count;
+#endif
+void ftrace_free_init_tramp(void);
+unsigned long ftrace_call_adjust(unsigned long addr);
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+/*
+ * When an ftrace registered caller is tracing a function that is also set by a
+ * register_ftrace_direct() call, it needs to be differentiated in the
+ * ftrace_caller trampoline so that the direct call can be invoked after the
+ * other ftrace ops. To do this, place the direct caller in the orig_gpr3 field
+ * of pt_regs. This tells ftrace_caller that there's a direct caller.
+ */
+static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr)
+{
+	struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs;
+
+	regs->orig_gpr3 = addr;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
+#else
+static inline void ftrace_free_init_tramp(void) { }
+static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; }
+#endif
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_FTRACE */
diff --git a/arch/powerpc/include/asm/guest-state-buffer.h b/arch/powerpc/include/asm/guest-state-buffer.h
new file mode 100644
index 000000000000..acd61eb36d59
--- /dev/null
+++ b/arch/powerpc/include/asm/guest-state-buffer.h
@@ -0,0 +1,1019 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Interface based on include/net/netlink.h
+ */
+#ifndef _ASM_POWERPC_GUEST_STATE_BUFFER_H
+#define _ASM_POWERPC_GUEST_STATE_BUFFER_H
+
+#include "asm/hvcall.h"
+#include <linux/gfp.h>
+#include <linux/bitmap.h>
+#include <asm/plpar_wrappers.h>
+
+/**************************************************************************
+ * Guest State Buffer Constants
+ **************************************************************************/
+/* Element without a value and any length */
+#define KVMPPC_GSID_BLANK			0x0000
+/* Size required for the L0's internal VCPU representation */
+#define KVMPPC_GSID_HOST_STATE_SIZE		0x0001
+ /* Minimum size for the H_GUEST_RUN_VCPU output buffer */
+#define KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE		0x0002
+ /* "Logical" PVR value as defined in the PAPR */
+#define KVMPPC_GSID_LOGICAL_PVR			0x0003
+ /* L0 relative timebase offset */
+#define KVMPPC_GSID_TB_OFFSET			0x0004
+ /* Partition Scoped Page Table Info */
+#define KVMPPC_GSID_PARTITION_TABLE		0x0005
+ /* Process Table Info */
+#define KVMPPC_GSID_PROCESS_TABLE		0x0006
+
+/* Guest Management Heap Size */
+#define KVMPPC_GSID_L0_GUEST_HEAP		0x0800
+
+/* Guest Management Heap Max Size */
+#define KVMPPC_GSID_L0_GUEST_HEAP_MAX		0x0801
+
+/* Guest Pagetable Size */
+#define KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE	0x0802
+
+/* Guest Pagetable Max Size */
+#define KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX	0x0803
+
+/* Guest Pagetable Reclaim in bytes */
+#define KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM	0x0804
+
+/* H_GUEST_RUN_VCPU input buffer Info */
+#define KVMPPC_GSID_RUN_INPUT			0x0C00
+/* H_GUEST_RUN_VCPU output buffer Info */
+#define KVMPPC_GSID_RUN_OUTPUT			0x0C01
+#define KVMPPC_GSID_VPA				0x0C02
+
+#define KVMPPC_GSID_GPR(x)			(0x1000 + (x))
+#define KVMPPC_GSID_HDEC_EXPIRY_TB		0x1020
+#define KVMPPC_GSID_NIA				0x1021
+#define KVMPPC_GSID_MSR				0x1022
+#define KVMPPC_GSID_LR				0x1023
+#define KVMPPC_GSID_XER				0x1024
+#define KVMPPC_GSID_CTR				0x1025
+#define KVMPPC_GSID_CFAR			0x1026
+#define KVMPPC_GSID_SRR0			0x1027
+#define KVMPPC_GSID_SRR1			0x1028
+#define KVMPPC_GSID_DAR				0x1029
+#define KVMPPC_GSID_DEC_EXPIRY_TB		0x102A
+#define KVMPPC_GSID_VTB				0x102B
+#define KVMPPC_GSID_LPCR			0x102C
+#define KVMPPC_GSID_HFSCR			0x102D
+#define KVMPPC_GSID_FSCR			0x102E
+#define KVMPPC_GSID_FPSCR			0x102F
+#define KVMPPC_GSID_DAWR0			0x1030
+#define KVMPPC_GSID_DAWR1			0x1031
+#define KVMPPC_GSID_CIABR			0x1032
+#define KVMPPC_GSID_PURR			0x1033
+#define KVMPPC_GSID_SPURR			0x1034
+#define KVMPPC_GSID_IC				0x1035
+#define KVMPPC_GSID_SPRG0			0x1036
+#define KVMPPC_GSID_SPRG1			0x1037
+#define KVMPPC_GSID_SPRG2			0x1038
+#define KVMPPC_GSID_SPRG3			0x1039
+#define KVMPPC_GSID_PPR				0x103A
+#define KVMPPC_GSID_MMCR(x)			(0x103B + (x))
+#define KVMPPC_GSID_MMCRA			0x103F
+#define KVMPPC_GSID_SIER(x)			(0x1040 + (x))
+#define KVMPPC_GSID_BESCR			0x1043
+#define KVMPPC_GSID_EBBHR			0x1044
+#define KVMPPC_GSID_EBBRR			0x1045
+#define KVMPPC_GSID_AMR				0x1046
+#define KVMPPC_GSID_IAMR			0x1047
+#define KVMPPC_GSID_AMOR			0x1048
+#define KVMPPC_GSID_UAMOR			0x1049
+#define KVMPPC_GSID_SDAR			0x104A
+#define KVMPPC_GSID_SIAR			0x104B
+#define KVMPPC_GSID_DSCR			0x104C
+#define KVMPPC_GSID_TAR				0x104D
+#define KVMPPC_GSID_DEXCR			0x104E
+#define KVMPPC_GSID_HDEXCR			0x104F
+#define KVMPPC_GSID_HASHKEYR			0x1050
+#define KVMPPC_GSID_HASHPKEYR			0x1051
+#define KVMPPC_GSID_CTRL			0x1052
+#define KVMPPC_GSID_DPDES			0x1053
+
+#define KVMPPC_GSID_CR				0x2000
+#define KVMPPC_GSID_PIDR			0x2001
+#define KVMPPC_GSID_DSISR			0x2002
+#define KVMPPC_GSID_VSCR			0x2003
+#define KVMPPC_GSID_VRSAVE			0x2004
+#define KVMPPC_GSID_DAWRX0			0x2005
+#define KVMPPC_GSID_DAWRX1			0x2006
+#define KVMPPC_GSID_PMC(x)			(0x2007 + (x))
+#define KVMPPC_GSID_WORT			0x200D
+#define KVMPPC_GSID_PSPB			0x200E
+
+#define KVMPPC_GSID_VSRS(x)			(0x3000 + (x))
+
+#define KVMPPC_GSID_HDAR			0xF000
+#define KVMPPC_GSID_HDSISR			0xF001
+#define KVMPPC_GSID_HEIR			0xF002
+#define KVMPPC_GSID_ASDR			0xF003
+
+#define KVMPPC_GSE_GUESTWIDE_START KVMPPC_GSID_BLANK
+#define KVMPPC_GSE_GUESTWIDE_END KVMPPC_GSID_PROCESS_TABLE
+#define KVMPPC_GSE_GUESTWIDE_COUNT \
+	(KVMPPC_GSE_GUESTWIDE_END - KVMPPC_GSE_GUESTWIDE_START + 1)
+
+#define KVMPPC_GSE_HOSTWIDE_START KVMPPC_GSID_L0_GUEST_HEAP
+#define KVMPPC_GSE_HOSTWIDE_END KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM
+#define KVMPPC_GSE_HOSTWIDE_COUNT \
+	(KVMPPC_GSE_HOSTWIDE_END - KVMPPC_GSE_HOSTWIDE_START + 1)
+
+#define KVMPPC_GSE_META_START KVMPPC_GSID_RUN_INPUT
+#define KVMPPC_GSE_META_END KVMPPC_GSID_VPA
+#define KVMPPC_GSE_META_COUNT (KVMPPC_GSE_META_END - KVMPPC_GSE_META_START + 1)
+
+#define KVMPPC_GSE_DW_REGS_START KVMPPC_GSID_GPR(0)
+#define KVMPPC_GSE_DW_REGS_END KVMPPC_GSID_DPDES
+#define KVMPPC_GSE_DW_REGS_COUNT \
+	(KVMPPC_GSE_DW_REGS_END - KVMPPC_GSE_DW_REGS_START + 1)
+
+#define KVMPPC_GSE_W_REGS_START KVMPPC_GSID_CR
+#define KVMPPC_GSE_W_REGS_END KVMPPC_GSID_PSPB
+#define KVMPPC_GSE_W_REGS_COUNT \
+	(KVMPPC_GSE_W_REGS_END - KVMPPC_GSE_W_REGS_START + 1)
+
+#define KVMPPC_GSE_VSRS_START KVMPPC_GSID_VSRS(0)
+#define KVMPPC_GSE_VSRS_END KVMPPC_GSID_VSRS(63)
+#define KVMPPC_GSE_VSRS_COUNT (KVMPPC_GSE_VSRS_END - KVMPPC_GSE_VSRS_START + 1)
+
+#define KVMPPC_GSE_INTR_REGS_START KVMPPC_GSID_HDAR
+#define KVMPPC_GSE_INTR_REGS_END KVMPPC_GSID_ASDR
+#define KVMPPC_GSE_INTR_REGS_COUNT \
+	(KVMPPC_GSE_INTR_REGS_END - KVMPPC_GSE_INTR_REGS_START + 1)
+
+#define KVMPPC_GSE_IDEN_COUNT                                 \
+	(KVMPPC_GSE_HOSTWIDE_COUNT + \
+	 KVMPPC_GSE_GUESTWIDE_COUNT + KVMPPC_GSE_META_COUNT + \
+	 KVMPPC_GSE_DW_REGS_COUNT + KVMPPC_GSE_W_REGS_COUNT + \
+	 KVMPPC_GSE_VSRS_COUNT + KVMPPC_GSE_INTR_REGS_COUNT)
+
+/**
+ * Ranges of guest state buffer elements
+ */
+enum {
+	KVMPPC_GS_CLASS_GUESTWIDE = 0x01,
+	KVMPPC_GS_CLASS_HOSTWIDE = 0x02,
+	KVMPPC_GS_CLASS_META = 0x04,
+	KVMPPC_GS_CLASS_DWORD_REG = 0x08,
+	KVMPPC_GS_CLASS_WORD_REG = 0x10,
+	KVMPPC_GS_CLASS_VECTOR = 0x18,
+	KVMPPC_GS_CLASS_INTR = 0x20,
+};
+
+/**
+ * Types of guest state buffer elements
+ */
+enum {
+	KVMPPC_GSE_BE32,
+	KVMPPC_GSE_BE64,
+	KVMPPC_GSE_VEC128,
+	KVMPPC_GSE_PARTITION_TABLE,
+	KVMPPC_GSE_PROCESS_TABLE,
+	KVMPPC_GSE_BUFFER,
+	__KVMPPC_GSE_TYPE_MAX,
+};
+
+/**
+ * Flags for guest state elements
+ */
+enum {
+	KVMPPC_GS_FLAGS_WIDE = 0x01,
+	KVMPPC_GS_FLAGS_HOST_WIDE = 0x02,
+};
+
+/**
+ * struct kvmppc_gs_part_table - deserialized partition table information
+ * element
+ * @address: start of the partition table
+ * @ea_bits: number of bits in the effective address
+ * @gpd_size: root page directory size
+ */
+struct kvmppc_gs_part_table {
+	u64 address;
+	u64 ea_bits;
+	u64 gpd_size;
+};
+
+/**
+ * struct kvmppc_gs_proc_table - deserialized process table information element
+ * @address: start of the process table
+ * @gpd_size: process table size
+ */
+struct kvmppc_gs_proc_table {
+	u64 address;
+	u64 gpd_size;
+};
+
+/**
+ * struct kvmppc_gs_buff_info - deserialized meta guest state buffer information
+ * @address: start of the guest state buffer
+ * @size: size of the guest state buffer
+ */
+struct kvmppc_gs_buff_info {
+	u64 address;
+	u64 size;
+};
+
+/**
+ * struct kvmppc_gs_header - serialized guest state buffer header
+ * @nelem: count of guest state elements in the buffer
+ * @data: start of the stream of elements in the buffer
+ */
+struct kvmppc_gs_header {
+	__be32 nelems;
+	char data[];
+} __packed;
+
+/**
+ * struct kvmppc_gs_elem - serialized guest state buffer element
+ * @iden: Guest State ID
+ * @len: length of data
+ * @data: the guest state buffer element's value
+ */
+struct kvmppc_gs_elem {
+	__be16 iden;
+	__be16 len;
+	char data[];
+} __packed;
+
+/**
+ * struct kvmppc_gs_buff - a guest state buffer with metadata.
+ * @capacity: total length of the buffer
+ * @len: current length of the elements and header
+ * @guest_id: guest id associated with the buffer
+ * @vcpu_id: vcpu_id associated with the buffer
+ * @hdr: the serialised guest state buffer
+ */
+struct kvmppc_gs_buff {
+	size_t capacity;
+	size_t len;
+	unsigned long guest_id;
+	unsigned long vcpu_id;
+	struct kvmppc_gs_header *hdr;
+};
+
+/**
+ * struct kvmppc_gs_bitmap - a bitmap for element ids
+ * @bitmap: a bitmap large enough for all Guest State IDs
+ */
+struct kvmppc_gs_bitmap {
+	/* private: */
+	DECLARE_BITMAP(bitmap, KVMPPC_GSE_IDEN_COUNT);
+};
+
+/**
+ * struct kvmppc_gs_parser - a map of element ids to locations in a buffer
+ * @iterator: bitmap used for iterating
+ * @gses: contains the pointers to elements
+ *
+ * A guest state parser is used for deserialising a guest state buffer.
+ * Given a buffer, it then allows looking up guest state elements using
+ * a guest state id.
+ */
+struct kvmppc_gs_parser {
+	/* private: */
+	struct kvmppc_gs_bitmap iterator;
+	struct kvmppc_gs_elem *gses[KVMPPC_GSE_IDEN_COUNT];
+};
+
+enum {
+	GSM_GUEST_WIDE = 0x1,
+	GSM_SEND = 0x2,
+	GSM_RECEIVE = 0x4,
+	GSM_GSB_OWNER = 0x8,
+};
+
+struct kvmppc_gs_msg;
+
+/**
+ * struct kvmppc_gs_msg_ops - guest state message behavior
+ * @get_size: maximum size required for the message data
+ * @fill_info: serializes to the guest state buffer format
+ * @refresh_info: dserializes from the guest state buffer format
+ */
+struct kvmppc_gs_msg_ops {
+	size_t (*get_size)(struct kvmppc_gs_msg *gsm);
+	int (*fill_info)(struct kvmppc_gs_buff *gsb, struct kvmppc_gs_msg *gsm);
+	int (*refresh_info)(struct kvmppc_gs_msg *gsm,
+			    struct kvmppc_gs_buff *gsb);
+};
+
+/**
+ * struct kvmppc_gs_msg - a guest state message
+ * @bitmap: the guest state ids that should be included
+ * @ops: modify message behavior for reading and writing to buffers
+ * @flags: host wide, guest wide or thread wide
+ * @data: location where buffer data will be written to or from.
+ *
+ * A guest state message is allows flexibility in sending in receiving data
+ * in a guest state buffer format.
+ */
+struct kvmppc_gs_msg {
+	struct kvmppc_gs_bitmap bitmap;
+	struct kvmppc_gs_msg_ops *ops;
+	unsigned long flags;
+	void *data;
+};
+
+/**************************************************************************
+ * Guest State IDs
+ **************************************************************************/
+
+u16 kvmppc_gsid_size(u16 iden);
+unsigned long kvmppc_gsid_flags(u16 iden);
+u64 kvmppc_gsid_mask(u16 iden);
+
+/**************************************************************************
+ * Guest State Buffers
+ **************************************************************************/
+struct kvmppc_gs_buff *kvmppc_gsb_new(size_t size, unsigned long guest_id,
+				      unsigned long vcpu_id, gfp_t flags);
+void kvmppc_gsb_free(struct kvmppc_gs_buff *gsb);
+void *kvmppc_gsb_put(struct kvmppc_gs_buff *gsb, size_t size);
+int kvmppc_gsb_send(struct kvmppc_gs_buff *gsb, unsigned long flags);
+int kvmppc_gsb_recv(struct kvmppc_gs_buff *gsb, unsigned long flags);
+
+/**
+ * kvmppc_gsb_header() - the header of a guest state buffer
+ * @gsb: guest state buffer
+ *
+ * Returns a pointer to the buffer header.
+ */
+static inline struct kvmppc_gs_header *
+kvmppc_gsb_header(struct kvmppc_gs_buff *gsb)
+{
+	return gsb->hdr;
+}
+
+/**
+ * kvmppc_gsb_data() - the elements of a guest state buffer
+ * @gsb: guest state buffer
+ *
+ * Returns a pointer to the first element of the buffer data.
+ */
+static inline struct kvmppc_gs_elem *kvmppc_gsb_data(struct kvmppc_gs_buff *gsb)
+{
+	return (struct kvmppc_gs_elem *)kvmppc_gsb_header(gsb)->data;
+}
+
+/**
+ * kvmppc_gsb_len() - the current length of a guest state buffer
+ * @gsb: guest state buffer
+ *
+ * Returns the length including the header of a buffer.
+ */
+static inline size_t kvmppc_gsb_len(struct kvmppc_gs_buff *gsb)
+{
+	return gsb->len;
+}
+
+/**
+ * kvmppc_gsb_capacity() - the capacity of a guest state buffer
+ * @gsb: guest state buffer
+ *
+ * Returns the capacity of a buffer.
+ */
+static inline size_t kvmppc_gsb_capacity(struct kvmppc_gs_buff *gsb)
+{
+	return gsb->capacity;
+}
+
+/**
+ * kvmppc_gsb_paddress() - the physical address of buffer
+ * @gsb: guest state buffer
+ *
+ * Returns the physical address of the buffer.
+ */
+static inline u64 kvmppc_gsb_paddress(struct kvmppc_gs_buff *gsb)
+{
+	return __pa(kvmppc_gsb_header(gsb));
+}
+
+/**
+ * kvmppc_gsb_nelems() - the number of elements in a buffer
+ * @gsb: guest state buffer
+ *
+ * Returns the number of elements in a buffer
+ */
+static inline u32 kvmppc_gsb_nelems(struct kvmppc_gs_buff *gsb)
+{
+	return be32_to_cpu(kvmppc_gsb_header(gsb)->nelems);
+}
+
+/**
+ * kvmppc_gsb_reset() - empty a guest state buffer
+ * @gsb: guest state buffer
+ *
+ * Reset the number of elements and length of buffer to empty.
+ */
+static inline void kvmppc_gsb_reset(struct kvmppc_gs_buff *gsb)
+{
+	kvmppc_gsb_header(gsb)->nelems = cpu_to_be32(0);
+	gsb->len = sizeof(struct kvmppc_gs_header);
+}
+
+/**
+ * kvmppc_gsb_data_len() - the length of a buffer excluding the header
+ * @gsb: guest state buffer
+ *
+ * Returns the length of a buffer excluding the header
+ */
+static inline size_t kvmppc_gsb_data_len(struct kvmppc_gs_buff *gsb)
+{
+	return gsb->len - sizeof(struct kvmppc_gs_header);
+}
+
+/**
+ * kvmppc_gsb_data_cap() - the capacity of a buffer excluding the header
+ * @gsb: guest state buffer
+ *
+ * Returns the capacity of a buffer excluding the header
+ */
+static inline size_t kvmppc_gsb_data_cap(struct kvmppc_gs_buff *gsb)
+{
+	return gsb->capacity - sizeof(struct kvmppc_gs_header);
+}
+
+/**
+ * kvmppc_gsb_for_each_elem - iterate over the elements in a buffer
+ * @i: loop counter
+ * @pos: set to current element
+ * @gsb: guest state buffer
+ * @rem: initialized to buffer capacity, holds bytes currently remaining in
+ *  stream
+ */
+#define kvmppc_gsb_for_each_elem(i, pos, gsb, rem)               \
+	kvmppc_gse_for_each_elem(i, kvmppc_gsb_nelems(gsb), pos, \
+				 kvmppc_gsb_data(gsb),           \
+				 kvmppc_gsb_data_cap(gsb), rem)
+
+/**************************************************************************
+ * Guest State Elements
+ **************************************************************************/
+
+/**
+ * kvmppc_gse_iden() - guest state ID of element
+ * @gse: guest state element
+ *
+ * Return the guest state ID in host endianness.
+ */
+static inline u16 kvmppc_gse_iden(const struct kvmppc_gs_elem *gse)
+{
+	return be16_to_cpu(gse->iden);
+}
+
+/**
+ * kvmppc_gse_len() - length of guest state element data
+ * @gse: guest state element
+ *
+ * Returns the length of guest state element data
+ */
+static inline u16 kvmppc_gse_len(const struct kvmppc_gs_elem *gse)
+{
+	return be16_to_cpu(gse->len);
+}
+
+/**
+ * kvmppc_gse_total_len() - total length of guest state element
+ * @gse: guest state element
+ *
+ * Returns the length of the data plus the ID and size header.
+ */
+static inline u16 kvmppc_gse_total_len(const struct kvmppc_gs_elem *gse)
+{
+	return be16_to_cpu(gse->len) + sizeof(*gse);
+}
+
+/**
+ * kvmppc_gse_total_size() - space needed for a given data length
+ * @size: data length
+ *
+ * Returns size plus the space needed for the ID and size header.
+ */
+static inline u16 kvmppc_gse_total_size(u16 size)
+{
+	return sizeof(struct kvmppc_gs_elem) + size;
+}
+
+/**
+ * kvmppc_gse_data() - pointer to data of a guest state element
+ * @gse: guest state element
+ *
+ * Returns a pointer to the beginning of guest state element data.
+ */
+static inline void *kvmppc_gse_data(const struct kvmppc_gs_elem *gse)
+{
+	return (void *)gse->data;
+}
+
+/**
+ * kvmppc_gse_ok() - checks space exists for guest state element
+ * @gse: guest state element
+ * @remaining: bytes of space remaining
+ *
+ * Returns true if the guest state element can fit in remaining space.
+ */
+static inline bool kvmppc_gse_ok(const struct kvmppc_gs_elem *gse,
+				 int remaining)
+{
+	return remaining >= kvmppc_gse_total_len(gse);
+}
+
+/**
+ * kvmppc_gse_next() - iterate to the next guest state element in a stream
+ * @gse: stream of guest state elements
+ * @remaining: length of the guest element stream
+ *
+ * Returns the next guest state element in a stream of elements. The length of
+ * the stream is updated in remaining.
+ */
+static inline struct kvmppc_gs_elem *
+kvmppc_gse_next(const struct kvmppc_gs_elem *gse, int *remaining)
+{
+	int len = sizeof(*gse) + kvmppc_gse_len(gse);
+
+	*remaining -= len;
+	return (struct kvmppc_gs_elem *)(gse->data + kvmppc_gse_len(gse));
+}
+
+/**
+ * kvmppc_gse_for_each_elem - iterate over a stream of guest state elements
+ * @i: loop counter
+ * @max: number of elements
+ * @pos: set to current element
+ * @head: head of elements
+ * @len: length of the stream
+ * @rem: initialized to len, holds bytes currently remaining elements
+ */
+#define kvmppc_gse_for_each_elem(i, max, pos, head, len, rem)                  \
+	for (i = 0, pos = head, rem = len; kvmppc_gse_ok(pos, rem) && i < max; \
+	     pos = kvmppc_gse_next(pos, &(rem)), i++)
+
+int __kvmppc_gse_put(struct kvmppc_gs_buff *gsb, u16 iden, u16 size,
+		     const void *data);
+int kvmppc_gse_parse(struct kvmppc_gs_parser *gsp, struct kvmppc_gs_buff *gsb);
+
+/**
+ * kvmppc_gse_put_be32() - add a be32 guest state element to a buffer
+ * @gsb: guest state buffer to add element to
+ * @iden: guest state ID
+ * @val: big endian value
+ */
+static inline int kvmppc_gse_put_be32(struct kvmppc_gs_buff *gsb, u16 iden,
+				      __be32 val)
+{
+	__be32 tmp;
+
+	tmp = val;
+	return __kvmppc_gse_put(gsb, iden, sizeof(__be32), &tmp);
+}
+
+/**
+ * kvmppc_gse_put_u32() - add a host endian 32bit int guest state element to a
+ * buffer
+ * @gsb: guest state buffer to add element to
+ * @iden: guest state ID
+ * @val: host endian value
+ */
+static inline int kvmppc_gse_put_u32(struct kvmppc_gs_buff *gsb, u16 iden,
+				     u32 val)
+{
+	__be32 tmp;
+
+	val &= kvmppc_gsid_mask(iden);
+	tmp = cpu_to_be32(val);
+	return kvmppc_gse_put_be32(gsb, iden, tmp);
+}
+
+/**
+ * kvmppc_gse_put_be64() - add a be64 guest state element to a buffer
+ * @gsb: guest state buffer to add element to
+ * @iden: guest state ID
+ * @val: big endian value
+ */
+static inline int kvmppc_gse_put_be64(struct kvmppc_gs_buff *gsb, u16 iden,
+				      __be64 val)
+{
+	__be64 tmp;
+
+	tmp = val;
+	return __kvmppc_gse_put(gsb, iden, sizeof(__be64), &tmp);
+}
+
+/**
+ * kvmppc_gse_put_u64() - add a host endian 64bit guest state element to a
+ * buffer
+ * @gsb: guest state buffer to add element to
+ * @iden: guest state ID
+ * @val: host endian value
+ */
+static inline int kvmppc_gse_put_u64(struct kvmppc_gs_buff *gsb, u16 iden,
+				     u64 val)
+{
+	__be64 tmp;
+
+	val &= kvmppc_gsid_mask(iden);
+	tmp = cpu_to_be64(val);
+	return kvmppc_gse_put_be64(gsb, iden, tmp);
+}
+
+/**
+ * __kvmppc_gse_put_reg() - add a register type guest state element to a buffer
+ * @gsb: guest state buffer to add element to
+ * @iden: guest state ID
+ * @val: host endian value
+ *
+ * Adds a register type guest state element. Uses the guest state ID for
+ * determining the length of the guest element. If the guest state ID has
+ * bits that can not be set they will be cleared.
+ */
+static inline int __kvmppc_gse_put_reg(struct kvmppc_gs_buff *gsb, u16 iden,
+				       u64 val)
+{
+	val &= kvmppc_gsid_mask(iden);
+	if (kvmppc_gsid_size(iden) == sizeof(u64))
+		return kvmppc_gse_put_u64(gsb, iden, val);
+
+	if (kvmppc_gsid_size(iden) == sizeof(u32)) {
+		u32 tmp;
+
+		tmp = (u32)val;
+		if (tmp != val)
+			return -EINVAL;
+
+		return kvmppc_gse_put_u32(gsb, iden, tmp);
+	}
+	return -EINVAL;
+}
+
+/**
+ * kvmppc_gse_put_vector128() - add a vector guest state element to a buffer
+ * @gsb: guest state buffer to add element to
+ * @iden: guest state ID
+ * @val: 16 byte vector value
+ */
+static inline int kvmppc_gse_put_vector128(struct kvmppc_gs_buff *gsb, u16 iden,
+					   vector128 *val)
+{
+	__be64 tmp[2] = { 0 };
+	union {
+		__vector128 v;
+		u64 dw[2];
+	} u;
+
+	u.v = *val;
+	tmp[0] = cpu_to_be64(u.dw[TS_FPROFFSET]);
+#ifdef CONFIG_VSX
+	tmp[1] = cpu_to_be64(u.dw[TS_VSRLOWOFFSET]);
+#endif
+	return __kvmppc_gse_put(gsb, iden, sizeof(tmp), &tmp);
+}
+
+/**
+ * kvmppc_gse_put_part_table() - add a partition table guest state element to a
+ * buffer
+ * @gsb: guest state buffer to add element to
+ * @iden: guest state ID
+ * @val: partition table value
+ */
+static inline int kvmppc_gse_put_part_table(struct kvmppc_gs_buff *gsb,
+					    u16 iden,
+					    struct kvmppc_gs_part_table val)
+{
+	__be64 tmp[3];
+
+	tmp[0] = cpu_to_be64(val.address);
+	tmp[1] = cpu_to_be64(val.ea_bits);
+	tmp[2] = cpu_to_be64(val.gpd_size);
+	return __kvmppc_gse_put(gsb, KVMPPC_GSID_PARTITION_TABLE, sizeof(tmp),
+				&tmp);
+}
+
+/**
+ * kvmppc_gse_put_proc_table() - add a process table guest state element to a
+ * buffer
+ * @gsb: guest state buffer to add element to
+ * @iden: guest state ID
+ * @val: process table value
+ */
+static inline int kvmppc_gse_put_proc_table(struct kvmppc_gs_buff *gsb,
+					    u16 iden,
+					    struct kvmppc_gs_proc_table val)
+{
+	__be64 tmp[2];
+
+	tmp[0] = cpu_to_be64(val.address);
+	tmp[1] = cpu_to_be64(val.gpd_size);
+	return __kvmppc_gse_put(gsb, KVMPPC_GSID_PROCESS_TABLE, sizeof(tmp),
+				&tmp);
+}
+
+/**
+ * kvmppc_gse_put_buff_info() - adds a GSB description guest state element to a
+ * buffer
+ * @gsb: guest state buffer to add element to
+ * @iden: guest state ID
+ * @val: guest state buffer description value
+ */
+static inline int kvmppc_gse_put_buff_info(struct kvmppc_gs_buff *gsb, u16 iden,
+					   struct kvmppc_gs_buff_info val)
+{
+	__be64 tmp[2];
+
+	tmp[0] = cpu_to_be64(val.address);
+	tmp[1] = cpu_to_be64(val.size);
+	return __kvmppc_gse_put(gsb, iden, sizeof(tmp), &tmp);
+}
+
+int __kvmppc_gse_put(struct kvmppc_gs_buff *gsb, u16 iden, u16 size,
+		     const void *data);
+
+/**
+ * kvmppc_gse_get_be32() - return the data of a be32 element
+ * @gse: guest state element
+ */
+static inline __be32 kvmppc_gse_get_be32(const struct kvmppc_gs_elem *gse)
+{
+	if (WARN_ON(kvmppc_gse_len(gse) != sizeof(__be32)))
+		return 0;
+	return *(__be32 *)kvmppc_gse_data(gse);
+}
+
+/**
+ * kvmppc_gse_get_u32() - return the data of a be32 element in host endianness
+ * @gse: guest state element
+ */
+static inline u32 kvmppc_gse_get_u32(const struct kvmppc_gs_elem *gse)
+{
+	return be32_to_cpu(kvmppc_gse_get_be32(gse));
+}
+
+/**
+ * kvmppc_gse_get_be64() - return the data of a be64 element
+ * @gse: guest state element
+ */
+static inline __be64 kvmppc_gse_get_be64(const struct kvmppc_gs_elem *gse)
+{
+	if (WARN_ON(kvmppc_gse_len(gse) != sizeof(__be64)))
+		return 0;
+	return *(__be64 *)kvmppc_gse_data(gse);
+}
+
+/**
+ * kvmppc_gse_get_u64() - return the data of a be64 element in host endianness
+ * @gse: guest state element
+ */
+static inline u64 kvmppc_gse_get_u64(const struct kvmppc_gs_elem *gse)
+{
+	return be64_to_cpu(kvmppc_gse_get_be64(gse));
+}
+
+/**
+ * kvmppc_gse_get_vector128() - return the data of a vector element
+ * @gse: guest state element
+ */
+static inline void kvmppc_gse_get_vector128(const struct kvmppc_gs_elem *gse,
+					    vector128 *v)
+{
+	union {
+		__vector128 v;
+		u64 dw[2];
+	} u = { 0 };
+	__be64 *src;
+
+	if (WARN_ON(kvmppc_gse_len(gse) != sizeof(__vector128)))
+		*v = u.v;
+
+	src = (__be64 *)kvmppc_gse_data(gse);
+	u.dw[TS_FPROFFSET] = be64_to_cpu(src[0]);
+#ifdef CONFIG_VSX
+	u.dw[TS_VSRLOWOFFSET] = be64_to_cpu(src[1]);
+#endif
+	*v = u.v;
+}
+
+/**************************************************************************
+ * Guest State Bitmap
+ **************************************************************************/
+
+bool kvmppc_gsbm_test(struct kvmppc_gs_bitmap *gsbm, u16 iden);
+void kvmppc_gsbm_set(struct kvmppc_gs_bitmap *gsbm, u16 iden);
+void kvmppc_gsbm_clear(struct kvmppc_gs_bitmap *gsbm, u16 iden);
+u16 kvmppc_gsbm_next(struct kvmppc_gs_bitmap *gsbm, u16 prev);
+
+/**
+ * kvmppc_gsbm_zero - zero the entire bitmap
+ * @gsbm: guest state buffer bitmap
+ */
+static inline void kvmppc_gsbm_zero(struct kvmppc_gs_bitmap *gsbm)
+{
+	bitmap_zero(gsbm->bitmap, KVMPPC_GSE_IDEN_COUNT);
+}
+
+/**
+ * kvmppc_gsbm_fill - fill the entire bitmap
+ * @gsbm: guest state buffer bitmap
+ */
+static inline void kvmppc_gsbm_fill(struct kvmppc_gs_bitmap *gsbm)
+{
+	bitmap_fill(gsbm->bitmap, KVMPPC_GSE_IDEN_COUNT);
+	clear_bit(0, gsbm->bitmap);
+}
+
+/**
+ * kvmppc_gsbm_for_each - iterate the present guest state IDs
+ * @gsbm: guest state buffer bitmap
+ * @iden: current guest state ID
+ */
+#define kvmppc_gsbm_for_each(gsbm, iden)                  \
+	for (iden = kvmppc_gsbm_next(gsbm, 0); iden != 0; \
+	     iden = kvmppc_gsbm_next(gsbm, iden))
+
+/**************************************************************************
+ * Guest State Parser
+ **************************************************************************/
+
+void kvmppc_gsp_insert(struct kvmppc_gs_parser *gsp, u16 iden,
+		       struct kvmppc_gs_elem *gse);
+struct kvmppc_gs_elem *kvmppc_gsp_lookup(struct kvmppc_gs_parser *gsp,
+					 u16 iden);
+
+/**
+ * kvmppc_gsp_for_each - iterate the <guest state IDs, guest state element>
+ * pairs
+ * @gsp: guest state buffer bitmap
+ * @iden: current guest state ID
+ * @gse: guest state element
+ */
+#define kvmppc_gsp_for_each(gsp, iden, gse)                              \
+	for (iden = kvmppc_gsbm_next(&(gsp)->iterator, 0),               \
+	    gse = kvmppc_gsp_lookup((gsp), iden);                        \
+	     iden != 0; iden = kvmppc_gsbm_next(&(gsp)->iterator, iden), \
+	    gse = kvmppc_gsp_lookup((gsp), iden))
+
+/**************************************************************************
+ * Guest State Message
+ **************************************************************************/
+
+/**
+ * kvmppc_gsm_for_each - iterate the guest state IDs included in a guest state
+ * message
+ * @gsp: guest state buffer bitmap
+ * @iden: current guest state ID
+ * @gse: guest state element
+ */
+#define kvmppc_gsm_for_each(gsm, iden)                            \
+	for (iden = kvmppc_gsbm_next(&gsm->bitmap, 0); iden != 0; \
+	     iden = kvmppc_gsbm_next(&gsm->bitmap, iden))
+
+int kvmppc_gsm_init(struct kvmppc_gs_msg *mgs, struct kvmppc_gs_msg_ops *ops,
+		    void *data, unsigned long flags);
+
+struct kvmppc_gs_msg *kvmppc_gsm_new(struct kvmppc_gs_msg_ops *ops, void *data,
+				     unsigned long flags, gfp_t gfp_flags);
+void kvmppc_gsm_free(struct kvmppc_gs_msg *gsm);
+size_t kvmppc_gsm_size(struct kvmppc_gs_msg *gsm);
+int kvmppc_gsm_fill_info(struct kvmppc_gs_msg *gsm, struct kvmppc_gs_buff *gsb);
+int kvmppc_gsm_refresh_info(struct kvmppc_gs_msg *gsm,
+			    struct kvmppc_gs_buff *gsb);
+
+/**
+ * kvmppc_gsm_include - indicate a guest state ID should be included when
+ * serializing
+ * @gsm: guest state message
+ * @iden: guest state ID
+ */
+static inline void kvmppc_gsm_include(struct kvmppc_gs_msg *gsm, u16 iden)
+{
+	kvmppc_gsbm_set(&gsm->bitmap, iden);
+}
+
+/**
+ * kvmppc_gsm_includes - check if a guest state ID will be included when
+ * serializing
+ * @gsm: guest state message
+ * @iden: guest state ID
+ */
+static inline bool kvmppc_gsm_includes(struct kvmppc_gs_msg *gsm, u16 iden)
+{
+	return kvmppc_gsbm_test(&gsm->bitmap, iden);
+}
+
+/**
+ * kvmppc_gsm_includes - indicate all guest state IDs should be included when
+ * serializing
+ * @gsm: guest state message
+ * @iden: guest state ID
+ */
+static inline void kvmppc_gsm_include_all(struct kvmppc_gs_msg *gsm)
+{
+	kvmppc_gsbm_fill(&gsm->bitmap);
+}
+
+/**
+ * kvmppc_gsm_include - clear the guest state IDs that should be included when
+ * serializing
+ * @gsm: guest state message
+ */
+static inline void kvmppc_gsm_reset(struct kvmppc_gs_msg *gsm)
+{
+	kvmppc_gsbm_zero(&gsm->bitmap);
+}
+
+/**
+ * kvmppc_gsb_receive_data - flexibly update values from a guest state buffer
+ * @gsb: guest state buffer
+ * @gsm: guest state message
+ *
+ * Requests updated values for the guest state values included in the guest
+ * state message. The guest state message will then deserialize the guest state
+ * buffer.
+ */
+static inline int kvmppc_gsb_receive_data(struct kvmppc_gs_buff *gsb,
+					  struct kvmppc_gs_msg *gsm)
+{
+	int rc;
+
+	kvmppc_gsb_reset(gsb);
+	rc = kvmppc_gsm_fill_info(gsm, gsb);
+	if (rc < 0)
+		return rc;
+
+	rc = kvmppc_gsb_recv(gsb, gsm->flags);
+	if (rc < 0)
+		return rc;
+
+	rc = kvmppc_gsm_refresh_info(gsm, gsb);
+	if (rc < 0)
+		return rc;
+	return 0;
+}
+
+/**
+ * kvmppc_gsb_recv - receive a single guest state ID
+ * @gsb: guest state buffer
+ * @gsm: guest state message
+ * @iden: guest state identity
+ */
+static inline int kvmppc_gsb_receive_datum(struct kvmppc_gs_buff *gsb,
+					   struct kvmppc_gs_msg *gsm, u16 iden)
+{
+	int rc;
+
+	kvmppc_gsm_include(gsm, iden);
+	rc = kvmppc_gsb_receive_data(gsb, gsm);
+	if (rc < 0)
+		return rc;
+	kvmppc_gsm_reset(gsm);
+	return 0;
+}
+
+/**
+ * kvmppc_gsb_send_data - flexibly send values from a guest state buffer
+ * @gsb: guest state buffer
+ * @gsm: guest state message
+ *
+ * Sends the guest state values included in the guest state message.
+ */
+static inline int kvmppc_gsb_send_data(struct kvmppc_gs_buff *gsb,
+				       struct kvmppc_gs_msg *gsm)
+{
+	int rc;
+
+	kvmppc_gsb_reset(gsb);
+	rc = kvmppc_gsm_fill_info(gsm, gsb);
+	if (rc < 0)
+		return rc;
+	rc = kvmppc_gsb_send(gsb, gsm->flags);
+
+	return rc;
+}
+
+/**
+ * kvmppc_gsb_recv - send a single guest state ID
+ * @gsb: guest state buffer
+ * @gsm: guest state message
+ * @iden: guest state identity
+ */
+static inline int kvmppc_gsb_send_datum(struct kvmppc_gs_buff *gsb,
+					struct kvmppc_gs_msg *gsm, u16 iden)
+{
+	int rc;
+
+	kvmppc_gsm_include(gsm, iden);
+	rc = kvmppc_gsb_send_data(gsb, gsm);
+	if (rc < 0)
+		return rc;
+	kvmppc_gsm_reset(gsm);
+	return 0;
+}
+
+#endif /* _ASM_POWERPC_GUEST_STATE_BUFFER_H */
diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h
index d73153b0275d..3966bd5810cb 100644
--- a/arch/powerpc/include/asm/head-64.h
+++ b/arch/powerpc/include/asm/head-64.h
@@ -4,7 +4,7 @@
 
 #include <asm/cache.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 /*
  * We can't do CPP stringification and concatination directly into the section
  * name for some reason, so these macros can do it for us.
@@ -167,6 +167,6 @@ name:
 // find label from _within_ sname
 #define ABS_ADDR(label, sname) (label - start_ ## sname + sname ## _start)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif	/* _ASM_POWERPC_HEAD_64_H */
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index ea71f7245a63..86326587e58d 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -15,6 +15,15 @@
 
 extern bool hugetlb_disabled;
 
+static inline bool hugepages_supported(void)
+{
+	if (hugetlb_disabled)
+		return false;
+
+	return HPAGE_SHIFT != 0;
+}
+#define hugepages_supported hugepages_supported
+
 void __init hugetlbpage_init_defaultsize(void);
 
 int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
@@ -30,14 +39,14 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 }
 #define is_hugepage_only_range is_hugepage_only_range
 
-#define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
-void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
-			    unsigned long end, unsigned long floor,
-			    unsigned long ceiling);
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
 }
@@ -47,8 +56,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_hugetlb_page(vma, addr);
 	return pte;
 }
@@ -67,14 +77,6 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 {
 }
 
-#define hugepd_shift(x) 0
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
-				    unsigned pdshift)
-{
-	return NULL;
-}
-
-
 static inline void __init gigantic_hugetlb_cma_reserve(void)
 {
 }
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index c099780385dd..9aef16149d92 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -100,6 +100,18 @@
 #define H_COP_HW	-74
 #define H_STATE		-75
 #define H_IN_USE	-77
+
+#define H_INVALID_ELEMENT_ID			-79
+#define H_INVALID_ELEMENT_SIZE			-80
+#define H_INVALID_ELEMENT_VALUE			-81
+#define H_INPUT_BUFFER_NOT_DEFINED		-82
+#define H_INPUT_BUFFER_TOO_SMALL		-83
+#define H_OUTPUT_BUFFER_NOT_DEFINED		-84
+#define H_OUTPUT_BUFFER_TOO_SMALL		-85
+#define H_PARTITION_PAGE_TABLE_NOT_DEFINED	-86
+#define H_GUEST_VCPU_STATE_NOT_HV_OWNED		-87
+
+
 #define H_UNSUPPORTED_FLAG_START	-256
 #define H_UNSUPPORTED_FLAG_END		-511
 #define H_MULTI_THREADS_ACTIVE	-9005
@@ -258,6 +270,7 @@
 #define H_QUERY_INT_STATE       0x1E4
 #define H_POLL_PENDING		0x1D8
 #define H_ILLAN_ATTRIBUTES	0x244
+#define H_ADD_LOGICAL_LAN_BUFFERS 0x248
 #define H_MODIFY_HEA_QP		0x250
 #define H_QUERY_HEA_QP		0x254
 #define H_QUERY_HEA		0x258
@@ -336,8 +349,18 @@
 #define H_SCM_FLUSH		0x44C
 #define H_GET_ENERGY_SCALE_INFO	0x450
 #define H_PKS_SIGNED_UPDATE	0x454
+#define H_HTM                   0x458
 #define H_WATCHDOG		0x45C
-#define MAX_HCALL_OPCODE	H_WATCHDOG
+#define H_GUEST_GET_CAPABILITIES 0x460
+#define H_GUEST_SET_CAPABILITIES 0x464
+#define H_GUEST_CREATE		0x470
+#define H_GUEST_CREATE_VCPU	0x474
+#define H_GUEST_GET_STATE	0x478
+#define H_GUEST_SET_STATE	0x47C
+#define H_GUEST_RUN_VCPU	0x480
+#define H_GUEST_COPY_MEMORY	0x484
+#define H_GUEST_DELETE		0x488
+#define MAX_HCALL_OPCODE	H_GUEST_DELETE
 
 /* Scope args for H_SCM_UNBIND_ALL */
 #define H_UNBIND_SCOPE_ALL (0x1)
@@ -467,7 +490,51 @@
 #define H_RPTI_PAGE_1G	0x08
 #define H_RPTI_PAGE_ALL (-1UL)
 
-#ifndef __ASSEMBLY__
+/* Flags for H_GUEST_{S,G}_STATE */
+#define H_GUEST_FLAGS_WIDE     (1UL << (63 - 0))
+#define H_GUEST_FLAGS_HOST_WIDE	(1UL << (63 - 1))
+
+/* Flag values used for H_{S,G}SET_GUEST_CAPABILITIES */
+#define H_GUEST_CAP_COPY_MEM	(1UL << (63 - 0))
+#define H_GUEST_CAP_POWER9	(1UL << (63 - 1))
+#define H_GUEST_CAP_POWER10	(1UL << (63 - 2))
+#define H_GUEST_CAP_POWER11	(1UL << (63 - 3))
+#define H_GUEST_CAP_BITMAP2	(1UL << (63 - 63))
+
+/*
+ * Defines for H_HTM - Macros for hardware trace macro (HTM) function.
+ */
+#define H_HTM_FLAGS_HARDWARE_TARGET    (1ul << 63)
+#define H_HTM_FLAGS_LOGICAL_TARGET     (1ul << 62)
+#define H_HTM_FLAGS_PROCID_TARGET      (1ul << 61)
+#define H_HTM_FLAGS_NOWRAP             (1ul << 60)
+
+#define H_HTM_OP_SHIFT                 (63-15)
+#define H_HTM_OP(x)                    ((unsigned long)(x)<<H_HTM_OP_SHIFT)
+#define H_HTM_OP_CAPABILITIES          0x01
+#define H_HTM_OP_STATUS                        0x02
+#define H_HTM_OP_SETUP                 0x03
+#define H_HTM_OP_CONFIGURE             0x04
+#define H_HTM_OP_START                 0x05
+#define H_HTM_OP_STOP                  0x06
+#define H_HTM_OP_DECONFIGURE           0x07
+#define H_HTM_OP_DUMP_DETAILS          0x08
+#define H_HTM_OP_DUMP_DATA             0x09
+#define H_HTM_OP_DUMP_SYSMEM_CONF      0x0a
+#define H_HTM_OP_DUMP_SYSPROC_CONF     0x0b
+
+#define H_HTM_TYPE_SHIFT               (63-31)
+#define H_HTM_TYPE(x)                  ((unsigned long)(x)<<H_HTM_TYPE_SHIFT)
+#define H_HTM_TYPE_NEST                        0x01
+#define H_HTM_TYPE_CORE                        0x02
+#define H_HTM_TYPE_LLAT                        0x03
+#define H_HTM_TYPE_GLOBAL              0xff
+
+#define H_HTM_TARGET_NODE_INDEX(x)             ((unsigned long)(x)<<(63-15))
+#define H_HTM_TARGET_NODAL_CHIP_INDEX(x)       ((unsigned long)(x)<<(63-31))
+#define H_HTM_TARGET_CORE_INDEX_ON_CHIP(x)     ((unsigned long)(x)<<(63-47))
+
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 /**
@@ -494,7 +561,7 @@ long plpar_hcall_norets_notrace(unsigned long opcode, ...);
  * Used for all but the craziest of phyp interfaces (see plpar_hcall9)
  */
 #define PLPAR_HCALL_BUFSIZE 4
-long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...);
+long plpar_hcall(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...);
 
 /**
  * plpar_hcall_raw: - Make a hypervisor call without calculating hcall stats
@@ -508,7 +575,7 @@ long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...);
  * plpar_hcall, but plpar_hcall_raw works in real mode and does not
  * calculate hypervisor call statistics.
  */
-long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...);
+long plpar_hcall_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...);
 
 /**
  * plpar_hcall9: - Make a pseries hypervisor call with up to 9 return arguments
@@ -519,8 +586,8 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...);
  * PLPAR_HCALL9_BUFSIZE to size the return argument buffer.
  */
 #define PLPAR_HCALL9_BUFSIZE 9
-long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...);
-long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...);
+long plpar_hcall9(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...);
+long plpar_hcall9_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...);
 
 /* pseries hcall tracing */
 extern struct static_key hcall_tracepoint_key;
@@ -540,7 +607,7 @@ struct hvcall_mpp_data {
 	unsigned long backing_mem;
 };
 
-int h_get_mpp(struct hvcall_mpp_data *);
+long h_get_mpp(struct hvcall_mpp_data *mpp_data);
 
 struct hvcall_mpp_x_data {
 	unsigned long coalesced_bytes;
@@ -668,6 +735,6 @@ struct hv_gpci_request_buffer {
 	uint8_t bytes[HGPCI_MAX_DATA_BYTES];
 } __packed;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_HVCALL_H */
diff --git a/arch/powerpc/include/asm/hvconsole.h b/arch/powerpc/include/asm/hvconsole.h
index ccb2034506f0..d841a97010a0 100644
--- a/arch/powerpc/include/asm/hvconsole.h
+++ b/arch/powerpc/include/asm/hvconsole.h
@@ -21,8 +21,8 @@
  * Vio firmware always attempts to fetch MAX_VIO_GET_CHARS chars.  The 'count'
  * parm is included to conform to put_chars() function pointer template
  */
-extern int hvc_get_chars(uint32_t vtermno, char *buf, int count);
-extern int hvc_put_chars(uint32_t vtermno, const char *buf, int count);
+extern ssize_t hvc_get_chars(uint32_t vtermno, u8 *buf, size_t count);
+extern ssize_t hvc_put_chars(uint32_t vtermno, const u8 *buf, size_t count);
 
 /* Provided by HVC VIO */
 void hvc_vio_init_early(void);
diff --git a/arch/powerpc/include/asm/hvsi.h b/arch/powerpc/include/asm/hvsi.h
index 464a7519ed64..9058edcb632b 100644
--- a/arch/powerpc/include/asm/hvsi.h
+++ b/arch/powerpc/include/asm/hvsi.h
@@ -64,7 +64,7 @@ struct hvsi_priv {
 	unsigned int	inbuf_len;	/* data in input buffer */
 	unsigned char	inbuf[HVSI_INBUF_SIZE];
 	unsigned int	inbuf_cur;	/* Cursor in input buffer */
-	unsigned int	inbuf_pktlen;	/* packet length from cursor */
+	size_t		inbuf_pktlen;	/* packet length from cursor */
 	atomic_t	seqno;		/* packet sequence number */
 	unsigned int	opened:1;	/* driver opened */
 	unsigned int	established:1;	/* protocol established */
@@ -72,24 +72,26 @@ struct hvsi_priv {
 	unsigned int	mctrl_update:1;	/* modem control updated */
 	unsigned short	mctrl;		/* modem control */
 	struct tty_struct *tty;		/* tty structure */
-	int (*get_chars)(uint32_t termno, char *buf, int count);
-	int (*put_chars)(uint32_t termno, const char *buf, int count);
+	ssize_t (*get_chars)(uint32_t termno, u8 *buf, size_t count);
+	ssize_t (*put_chars)(uint32_t termno, const u8 *buf, size_t count);
 	uint32_t	termno;
 };
 
 /* hvsi lib functions */
 struct hvc_struct;
 extern void hvsilib_init(struct hvsi_priv *pv,
-			 int (*get_chars)(uint32_t termno, char *buf, int count),
-			 int (*put_chars)(uint32_t termno, const char *buf,
-					  int count),
+			 ssize_t (*get_chars)(uint32_t termno, u8 *buf,
+					      size_t count),
+			 ssize_t (*put_chars)(uint32_t termno, const u8 *buf,
+					      size_t count),
 			 int termno, int is_console);
 extern int hvsilib_open(struct hvsi_priv *pv, struct hvc_struct *hp);
 extern void hvsilib_close(struct hvsi_priv *pv, struct hvc_struct *hp);
 extern int hvsilib_read_mctrl(struct hvsi_priv *pv);
 extern int hvsilib_write_mctrl(struct hvsi_priv *pv, int dtr);
 extern void hvsilib_establish(struct hvsi_priv *pv);
-extern int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count);
-extern int hvsilib_put_chars(struct hvsi_priv *pv, const char *buf, int count);
+extern ssize_t hvsilib_get_chars(struct hvsi_priv *pv, u8 *buf, size_t count);
+extern ssize_t hvsilib_put_chars(struct hvsi_priv *pv, const u8 *buf,
+				 size_t count);
 
 #endif /* _HVSI_H */
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 84d39fd42f71..66db0147d5b4 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -18,6 +18,7 @@ struct arch_hw_breakpoint {
 	u16		len; /* length of the target data symbol */
 	u16		hw_len; /* length programmed in hw */
 	u8		flags;
+	bool		perf_single_step; /* temporarily uninstalled for a perf single step */
 };
 
 /* Note: Don't change the first 6 bits below as they are in the same order
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 317659fdeacf..1078ba88efaf 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -59,11 +59,11 @@
 #define IRQS_PMI_DISABLED	2
 #define IRQS_ALL_DISABLED	(IRQS_DISABLED | IRQS_PMI_DISABLED)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 static inline void __hard_irq_enable(void)
 {
-	if (IS_ENABLED(CONFIG_BOOKE_OR_40x))
+	if (IS_ENABLED(CONFIG_BOOKE))
 		wrtee(MSR_EE);
 	else if (IS_ENABLED(CONFIG_PPC_8xx))
 		wrtspr(SPRN_EIE);
@@ -75,7 +75,7 @@ static inline void __hard_irq_enable(void)
 
 static inline void __hard_irq_disable(void)
 {
-	if (IS_ENABLED(CONFIG_BOOKE_OR_40x))
+	if (IS_ENABLED(CONFIG_BOOKE))
 		wrtee(0);
 	else if (IS_ENABLED(CONFIG_PPC_8xx))
 		wrtspr(SPRN_EID);
@@ -87,7 +87,7 @@ static inline void __hard_irq_disable(void)
 
 static inline void __hard_EE_RI_disable(void)
 {
-	if (IS_ENABLED(CONFIG_BOOKE_OR_40x))
+	if (IS_ENABLED(CONFIG_BOOKE))
 		wrtee(0);
 	else if (IS_ENABLED(CONFIG_PPC_8xx))
 		wrtspr(SPRN_NRI);
@@ -99,7 +99,7 @@ static inline void __hard_EE_RI_disable(void)
 
 static inline void __hard_RI_enable(void)
 {
-	if (IS_ENABLED(CONFIG_BOOKE_OR_40x))
+	if (IS_ENABLED(CONFIG_BOOKE))
 		return;
 
 	if (IS_ENABLED(CONFIG_PPC_8xx))
@@ -516,6 +516,6 @@ static inline unsigned long mtmsr_isync_irqsafe(unsigned long msr)
 
 #define ARCH_IRQ_INIT_FLAGS	IRQ_NOREQUEST
 
-#endif  /* __ASSEMBLY__ */
+#endif  /* __ASSEMBLER__ */
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_HW_IRQ_H */
diff --git a/arch/powerpc/include/asm/ibmebus.h b/arch/powerpc/include/asm/ibmebus.h
index 088f95b2e14f..46fe406f461c 100644
--- a/arch/powerpc/include/asm/ibmebus.h
+++ b/arch/powerpc/include/asm/ibmebus.h
@@ -46,7 +46,9 @@
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
 
-extern struct bus_type ibmebus_bus_type;
+struct platform_driver;
+
+extern const struct bus_type ibmebus_bus_type;
 
 int ibmebus_register_driver(struct platform_driver *drv);
 void ibmebus_unregister_driver(struct platform_driver *drv);
diff --git a/arch/powerpc/include/asm/ide.h b/arch/powerpc/include/asm/ide.h
deleted file mode 100644
index ce87a4441ca3..000000000000
--- a/arch/powerpc/include/asm/ide.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- *  Copyright (C) 1994-1996 Linus Torvalds & authors
- *
- *  This file contains the powerpc architecture specific IDE code.
- */
-#ifndef _ASM_POWERPC_IDE_H
-#define _ASM_POWERPC_IDE_H
-
-#include <linux/compiler.h>
-#include <asm/io.h>
-
-#define __ide_mm_insw(p, a, c)	readsw((void __iomem *)(p), (a), (c))
-#define __ide_mm_insl(p, a, c)	readsl((void __iomem *)(p), (a), (c))
-#define __ide_mm_outsw(p, a, c)	writesw((void __iomem *)(p), (a), (c))
-#define __ide_mm_outsl(p, a, c)	writesl((void __iomem *)(p), (a), (c))
-
-#endif /* _ASM_POWERPC_IDE_H */
diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h
index 699a88584ae1..a656635df386 100644
--- a/arch/powerpc/include/asm/imc-pmu.h
+++ b/arch/powerpc/include/asm/imc-pmu.h
@@ -74,14 +74,14 @@ struct imc_events {
  * The following is the data structure to hold trace imc data.
  */
 struct trace_imc_data {
-	u64 tb1;
-	u64 ip;
-	u64 val;
-	u64 cpmc1;
-	u64 cpmc2;
-	u64 cpmc3;
-	u64 cpmc4;
-	u64 tb2;
+	__be64 tb1;
+	__be64 ip;
+	__be64 val;
+	__be64 cpmc1;
+	__be64 cpmc2;
+	__be64 cpmc3;
+	__be64 cpmc4;
+	__be64 tb2;
 };
 
 /* Event attribute array index */
diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h
index 684d3f453282..ffa82167c860 100644
--- a/arch/powerpc/include/asm/inst.h
+++ b/arch/powerpc/include/asm/inst.h
@@ -143,10 +143,6 @@ static inline int __copy_inst_from_kernel_nofault(ppc_inst_t *inst, u32 *src)
 {
 	unsigned int val, suffix;
 
-/* See https://github.com/ClangBuiltLinux/linux/issues/1521 */
-#if defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 140000
-	val = suffix = 0;
-#endif
 	__get_kernel_nofault(&val, src, u32, Efault);
 	if (IS_ENABLED(CONFIG_PPC64) && get_op(val) == OP_PREFIX) {
 		__get_kernel_nofault(&suffix, src + 1, u32, Efault);
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index a4196ab1d016..eb0e4a20b818 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -64,7 +64,7 @@
 #define INTERRUPT_DATA_LOAD_TLB_MISS_603	0x1100
 #define INTERRUPT_DATA_STORE_TLB_MISS_603	0x1200
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/context_tracking.h>
 #include <linux/hardirq.h>
@@ -97,7 +97,7 @@ DECLARE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant);
 
 static inline bool is_implicit_soft_masked(struct pt_regs *regs)
 {
-	if (regs->msr & MSR_PR)
+	if (user_mode(regs))
 		return false;
 
 	if (regs->nip >= (unsigned long)__end_soft_masked)
@@ -177,7 +177,7 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs)
 
 	if (user_mode(regs)) {
 		kuap_lock();
-		CT_WARN_ON(ct_state() != CONTEXT_USER);
+		CT_WARN_ON(ct_state() != CT_STATE_USER);
 		user_exit_irqoff();
 
 		account_cpu_user_entry();
@@ -189,8 +189,8 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs)
 		 * so avoid recursion.
 		 */
 		if (TRAP(regs) != INTERRUPT_PROGRAM)
-			CT_WARN_ON(ct_state() != CONTEXT_KERNEL &&
-				   ct_state() != CONTEXT_IDLE);
+			CT_WARN_ON(ct_state() != CT_STATE_KERNEL &&
+				   ct_state() != CT_STATE_IDLE);
 		INT_SOFT_MASK_BUG_ON(regs, is_implicit_soft_masked(regs));
 		INT_SOFT_MASK_BUG_ON(regs, arch_irq_disabled_regs(regs) &&
 					   search_kernel_restart_table(regs->nip));
@@ -336,6 +336,14 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte
 	if (IS_ENABLED(CONFIG_KASAN))
 		return;
 
+	/*
+	 * Likewise, do not use it in real mode if percpu first chunk is not
+	 * embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there
+	 * are chances where percpu allocation can come from vmalloc area.
+	 */
+	if (percpu_first_chunk_is_paged)
+		return;
+
 	/* Otherwise, it should be safe to call it */
 	nmi_enter();
 }
@@ -351,6 +359,8 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
 		// no nmi_exit for a pseries hash guest taking a real mode exception
 	} else if (IS_ENABLED(CONFIG_KASAN)) {
 		// no nmi_exit for KASAN in real mode
+	} else if (percpu_first_chunk_is_paged) {
+		// no nmi_exit if percpu first chunk is not embedded
 	} else {
 		nmi_exit();
 	}
@@ -665,6 +675,6 @@ unsigned long interrupt_exit_user_restart(struct pt_regs *regs);
 unsigned long interrupt_exit_kernel_restart(struct pt_regs *regs);
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_INTERRUPT_H */
diff --git a/arch/powerpc/include/asm/io-defs.h b/arch/powerpc/include/asm/io-defs.h
index faf8617cc574..5c2be9b54a9d 100644
--- a/arch/powerpc/include/asm/io-defs.h
+++ b/arch/powerpc/include/asm/io-defs.h
@@ -1,61 +1,15 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* This file is meant to be include multiple times by other headers */
-/* last 2 argments are used by platforms/cell/io-workarounds.[ch] */
 
-DEF_PCI_AC_RET(readb, u8, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readw, u16, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readl, u32, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readw_be, u16, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readl_be, u32, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_NORET(writeb, (u8 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writew, (u16 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writel, (u32 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writew_be, (u16 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writel_be, (u32 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-
-#ifdef __powerpc64__
-DEF_PCI_AC_RET(readq, u64, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_RET(readq_be, u64, (const PCI_IO_ADDR addr), (addr), mem, addr)
-DEF_PCI_AC_NORET(writeq, (u64 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-DEF_PCI_AC_NORET(writeq_be, (u64 val, PCI_IO_ADDR addr), (val, addr), mem, addr)
-#endif /* __powerpc64__ */
-
-DEF_PCI_AC_RET(inb, u8, (unsigned long port), (port), pio, port)
-DEF_PCI_AC_RET(inw, u16, (unsigned long port), (port), pio, port)
-DEF_PCI_AC_RET(inl, u32, (unsigned long port), (port), pio, port)
-DEF_PCI_AC_NORET(outb, (u8 val, unsigned long port), (val, port), pio, port)
-DEF_PCI_AC_NORET(outw, (u16 val, unsigned long port), (val, port), pio, port)
-DEF_PCI_AC_NORET(outl, (u32 val, unsigned long port), (val, port), pio, port)
-
-DEF_PCI_AC_NORET(readsb, (const PCI_IO_ADDR a, void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(readsw, (const PCI_IO_ADDR a, void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(readsl, (const PCI_IO_ADDR a, void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(writesb, (PCI_IO_ADDR a, const void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(writesw, (PCI_IO_ADDR a, const void *b, unsigned long c),
-		 (a, b, c), mem, a)
-DEF_PCI_AC_NORET(writesl, (PCI_IO_ADDR a, const void *b, unsigned long c),
-		 (a, b, c), mem, a)
-
-DEF_PCI_AC_NORET(insb, (unsigned long p, void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(insw, (unsigned long p, void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(insl, (unsigned long p, void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(outsb, (unsigned long p, const void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(outsw, (unsigned long p, const void *b, unsigned long c),
-		 (p, b, c), pio, p)
-DEF_PCI_AC_NORET(outsl, (unsigned long p, const void *b, unsigned long c),
-		 (p, b, c), pio, p)
-
-DEF_PCI_AC_NORET(memset_io, (PCI_IO_ADDR a, int c, unsigned long n),
-		 (a, c, n), mem, a)
-DEF_PCI_AC_NORET(memcpy_fromio, (void *d, const PCI_IO_ADDR s, unsigned long n),
-		 (d, s, n), mem, s)
-DEF_PCI_AC_NORET(memcpy_toio, (PCI_IO_ADDR d, const void *s, unsigned long n),
-		 (d, s, n), mem, d)
+DEF_PCI_AC_RET(inb, u8, (unsigned long port), (port))
+DEF_PCI_AC_RET(inw, u16, (unsigned long port), (port))
+DEF_PCI_AC_RET(inl, u32, (unsigned long port), (port))
+DEF_PCI_AC_NORET(outb, (u8 val, unsigned long port), (val, port))
+DEF_PCI_AC_NORET(outw, (u16 val, unsigned long port), (val, port))
+DEF_PCI_AC_NORET(outl, (u32 val, unsigned long port), (val, port))
+DEF_PCI_AC_NORET(insb, (unsigned long p, void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(insw, (unsigned long p, void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(insl, (unsigned long p, void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(outsb, (unsigned long p, const void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(outsw, (unsigned long p, const void *b, unsigned long c), (p, b, c))
+DEF_PCI_AC_NORET(outsl, (unsigned long p, const void *b, unsigned long c), (p, b, c))
diff --git a/arch/powerpc/include/asm/io-workarounds.h b/arch/powerpc/include/asm/io-workarounds.h
deleted file mode 100644
index 3cce499fbe27..000000000000
--- a/arch/powerpc/include/asm/io-workarounds.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Support PCI IO workaround
- *
- * (C) Copyright 2007-2008 TOSHIBA CORPORATION
- */
-
-#ifndef _IO_WORKAROUNDS_H
-#define _IO_WORKAROUNDS_H
-
-#ifdef CONFIG_PPC_IO_WORKAROUNDS
-#include <linux/io.h>
-#include <asm/pci-bridge.h>
-
-/* Bus info */
-struct iowa_bus {
-	struct pci_controller *phb;
-	struct ppc_pci_io *ops;
-	void   *private;
-};
-
-void iowa_register_bus(struct pci_controller *, struct ppc_pci_io *,
-		       int (*)(struct iowa_bus *, void *), void *);
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR);
-struct iowa_bus *iowa_pio_find_bus(unsigned long);
-
-extern struct ppc_pci_io spiderpci_ops;
-extern int spiderpci_iowa_init(struct iowa_bus *, void *);
-
-#define SPIDER_PCI_REG_BASE		0xd000
-#define SPIDER_PCI_REG_SIZE		0x1000
-#define SPIDER_PCI_VCI_CNTL_STAT	0x0110
-#define SPIDER_PCI_DUMMY_READ		0x0810
-#define SPIDER_PCI_DUMMY_READ_BASE	0x0814
-
-#endif
-
-#if defined(CONFIG_PPC_IO_WORKAROUNDS) && defined(CONFIG_PPC_INDIRECT_MMIO)
-extern bool io_workaround_inited;
-
-static inline bool iowa_is_active(void)
-{
-	return unlikely(io_workaround_inited);
-}
-#else
-static inline bool iowa_is_active(void)
-{
-	return false;
-}
-#endif
-
-void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
-			   pgprot_t prot, void *caller);
-
-#endif /* _IO_WORKAROUNDS_H */
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index f1e657c9bbe8..7a89754842d6 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -3,11 +3,6 @@
 #define _ASM_POWERPC_IO_H
 #ifdef __KERNEL__
 
-#define ARCH_HAS_IOREMAP_WC
-#ifdef CONFIG_PPC32
-#define ARCH_HAS_IOREMAP_WT
-#endif
-
 /*
  */
 
@@ -42,7 +37,7 @@ extern struct pci_dev *isa_bridge_pcidev;
  * define properly based on the platform
  */
 #ifndef CONFIG_PCI
-#define _IO_BASE	0
+#define _IO_BASE	POISON_POINTER_DELTA
 #define _ISA_MEM_BASE	0
 #define PCI_DRAM_OFFSET 0
 #elif defined(CONFIG_PPC32)
@@ -70,8 +65,8 @@ extern resource_size_t isa_mem_base;
 extern bool isa_io_special;
 
 #ifdef CONFIG_PPC32
-#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
-#error CONFIG_PPC_INDIRECT_{PIO,MMIO} are not yet supported on 32 bits
+#ifdef CONFIG_PPC_INDIRECT_PIO
+#error CONFIG_PPC_INDIRECT_PIO is not yet supported on 32 bits
 #endif
 #endif
 
@@ -85,16 +80,12 @@ extern bool isa_io_special;
  *
  *	in_8, in_le16, in_be16, in_le32, in_be32, in_le64, in_be64
  *	out_8, out_le16, out_be16, out_le32, out_be32, out_le64, out_be64
- *	_insb, _insw_ns, _insl_ns, _outsb, _outsw_ns, _outsl_ns
+ *	_insb, _insw, _insl, _outsb, _outsw, _outsl
  *
  * Those operate directly on a kernel virtual address. Note that the prototype
  * for the out_* accessors has the arguments in opposite order from the usual
  * linux PCI accessors. Unlike those, they take the address first and the value
  * next.
- *
- * Note: I might drop the _ns suffix on the stream operations soon as it is
- * simply normal for stream operations to not swap in the first place.
- *
  */
 
 /* -mprefixed can generate offsets beyond range, fall back hack */
@@ -233,19 +224,10 @@ static inline void out_be64(volatile u64 __iomem *addr, u64 val)
  */
 extern void _insb(const volatile u8 __iomem *addr, void *buf, long count);
 extern void _outsb(volatile u8 __iomem *addr,const void *buf,long count);
-extern void _insw_ns(const volatile u16 __iomem *addr, void *buf, long count);
-extern void _outsw_ns(volatile u16 __iomem *addr, const void *buf, long count);
-extern void _insl_ns(const volatile u32 __iomem *addr, void *buf, long count);
-extern void _outsl_ns(volatile u32 __iomem *addr, const void *buf, long count);
-
-/* The _ns naming is historical and will be removed. For now, just #define
- * the non _ns equivalent names
- */
-#define _insw	_insw_ns
-#define _insl	_insl_ns
-#define _outsw	_outsw_ns
-#define _outsl	_outsl_ns
-
+extern void _insw(const volatile u16 __iomem *addr, void *buf, long count);
+extern void _outsw(volatile u16 __iomem *addr, const void *buf, long count);
+extern void _insl(const volatile u32 __iomem *addr, void *buf, long count);
+extern void _outsl(volatile u32 __iomem *addr, const void *buf, long count);
 
 /*
  * memset_io, memcpy_toio, memcpy_fromio base implementations are out of line
@@ -266,9 +248,9 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
  * for PowerPC is as close as possible to the x86 version of these, and thus
  * provides fairly heavy weight barriers for the non-raw versions
  *
- * In addition, they support a hook mechanism when CONFIG_PPC_INDIRECT_MMIO
- * or CONFIG_PPC_INDIRECT_PIO are set allowing the platform to provide its
- * own implementation of some or all of the accessors.
+ * In addition, they support a hook mechanism when CONFIG_PPC_INDIRECT_PIO
+ * is set allowing the platform to provide its own implementation of some
+ * of the accessors.
  */
 
 /*
@@ -279,116 +261,11 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src,
 #include <asm/eeh.h>
 #endif
 
-/* Shortcut to the MMIO argument pointer */
-#define PCI_IO_ADDR	volatile void __iomem *
-
-/* Indirect IO address tokens:
- *
- * When CONFIG_PPC_INDIRECT_MMIO is set, the platform can provide hooks
- * on all MMIOs. (Note that this is all 64 bits only for now)
- *
- * To help platforms who may need to differentiate MMIO addresses in
- * their hooks, a bitfield is reserved for use by the platform near the
- * top of MMIO addresses (not PIO, those have to cope the hard way).
- *
- * The highest address in the kernel virtual space are:
- *
- *  d0003fffffffffff	# with Hash MMU
- *  c00fffffffffffff	# with Radix MMU
- *
- * The top 4 bits are reserved as the region ID on hash, leaving us 8 bits
- * that can be used for the field.
- *
- * The direct IO mapping operations will then mask off those bits
- * before doing the actual access, though that only happen when
- * CONFIG_PPC_INDIRECT_MMIO is set, thus be careful when you use that
- * mechanism
- *
- * For PIO, there is a separate CONFIG_PPC_INDIRECT_PIO which makes
- * all PIO functions call through a hook.
- */
-
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-#define PCI_IO_IND_TOKEN_SHIFT	52
-#define PCI_IO_IND_TOKEN_MASK	(0xfful << PCI_IO_IND_TOKEN_SHIFT)
-#define PCI_FIX_ADDR(addr)						\
-	((PCI_IO_ADDR)(((unsigned long)(addr)) & ~PCI_IO_IND_TOKEN_MASK))
-#define PCI_GET_ADDR_TOKEN(addr)					\
-	(((unsigned long)(addr) & PCI_IO_IND_TOKEN_MASK) >> 		\
-		PCI_IO_IND_TOKEN_SHIFT)
-#define PCI_SET_ADDR_TOKEN(addr, token) 				\
-do {									\
-	unsigned long __a = (unsigned long)(addr);			\
-	__a &= ~PCI_IO_IND_TOKEN_MASK;					\
-	__a |= ((unsigned long)(token)) << PCI_IO_IND_TOKEN_SHIFT;	\
-	(addr) = (void __iomem *)__a;					\
-} while(0)
-#else
-#define PCI_FIX_ADDR(addr) (addr)
-#endif
-
-
-/*
- * Non ordered and non-swapping "raw" accessors
- */
-
-static inline unsigned char __raw_readb(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned char __force *)PCI_FIX_ADDR(addr);
-}
-#define __raw_readb __raw_readb
-
-static inline unsigned short __raw_readw(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned short __force *)PCI_FIX_ADDR(addr);
-}
-#define __raw_readw __raw_readw
-
-static inline unsigned int __raw_readl(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned int __force *)PCI_FIX_ADDR(addr);
-}
-#define __raw_readl __raw_readl
-
-static inline void __raw_writeb(unsigned char v, volatile void __iomem *addr)
-{
-	*(volatile unsigned char __force *)PCI_FIX_ADDR(addr) = v;
-}
-#define __raw_writeb __raw_writeb
-
-static inline void __raw_writew(unsigned short v, volatile void __iomem *addr)
-{
-	*(volatile unsigned short __force *)PCI_FIX_ADDR(addr) = v;
-}
-#define __raw_writew __raw_writew
-
-static inline void __raw_writel(unsigned int v, volatile void __iomem *addr)
-{
-	*(volatile unsigned int __force *)PCI_FIX_ADDR(addr) = v;
-}
-#define __raw_writel __raw_writel
+#define _IO_PORT(port)	((volatile void __iomem *)(_IO_BASE + (port)))
 
 #ifdef __powerpc64__
-static inline unsigned long __raw_readq(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned long __force *)PCI_FIX_ADDR(addr);
-}
-#define __raw_readq __raw_readq
-
-static inline void __raw_writeq(unsigned long v, volatile void __iomem *addr)
-{
-	*(volatile unsigned long __force *)PCI_FIX_ADDR(addr) = v;
-}
-#define __raw_writeq __raw_writeq
-
-static inline void __raw_writeq_be(unsigned long v, volatile void __iomem *addr)
-{
-	__raw_writeq((__force unsigned long)cpu_to_be64(v), addr);
-}
-#define __raw_writeq_be __raw_writeq_be
-
 /*
- * Real mode versions of the above. Those instructions are only supposed
+ * Real mode versions of raw accessors. Those instructions are only supposed
  * to be used in hypervisor real mode as per the architecture spec.
  */
 static inline void __raw_rm_writeb(u8 val, volatile void __iomem *paddr)
@@ -556,30 +433,23 @@ __do_out_asm(_rec_outl, "stwbrx")
  * possible to hook directly at the toplevel PIO operation if they have to
  * be handled differently
  */
-#define __do_writeb(val, addr)	out_8(PCI_FIX_ADDR(addr), val)
-#define __do_writew(val, addr)	out_le16(PCI_FIX_ADDR(addr), val)
-#define __do_writel(val, addr)	out_le32(PCI_FIX_ADDR(addr), val)
-#define __do_writeq(val, addr)	out_le64(PCI_FIX_ADDR(addr), val)
-#define __do_writew_be(val, addr) out_be16(PCI_FIX_ADDR(addr), val)
-#define __do_writel_be(val, addr) out_be32(PCI_FIX_ADDR(addr), val)
-#define __do_writeq_be(val, addr) out_be64(PCI_FIX_ADDR(addr), val)
 
 #ifdef CONFIG_EEH
-#define __do_readb(addr)	eeh_readb(PCI_FIX_ADDR(addr))
-#define __do_readw(addr)	eeh_readw(PCI_FIX_ADDR(addr))
-#define __do_readl(addr)	eeh_readl(PCI_FIX_ADDR(addr))
-#define __do_readq(addr)	eeh_readq(PCI_FIX_ADDR(addr))
-#define __do_readw_be(addr)	eeh_readw_be(PCI_FIX_ADDR(addr))
-#define __do_readl_be(addr)	eeh_readl_be(PCI_FIX_ADDR(addr))
-#define __do_readq_be(addr)	eeh_readq_be(PCI_FIX_ADDR(addr))
+#define __do_readb(addr)	eeh_readb(addr)
+#define __do_readw(addr)	eeh_readw(addr)
+#define __do_readl(addr)	eeh_readl(addr)
+#define __do_readq(addr)	eeh_readq(addr)
+#define __do_readw_be(addr)	eeh_readw_be(addr)
+#define __do_readl_be(addr)	eeh_readl_be(addr)
+#define __do_readq_be(addr)	eeh_readq_be(addr)
 #else /* CONFIG_EEH */
-#define __do_readb(addr)	in_8(PCI_FIX_ADDR(addr))
-#define __do_readw(addr)	in_le16(PCI_FIX_ADDR(addr))
-#define __do_readl(addr)	in_le32(PCI_FIX_ADDR(addr))
-#define __do_readq(addr)	in_le64(PCI_FIX_ADDR(addr))
-#define __do_readw_be(addr)	in_be16(PCI_FIX_ADDR(addr))
-#define __do_readl_be(addr)	in_be32(PCI_FIX_ADDR(addr))
-#define __do_readq_be(addr)	in_be64(PCI_FIX_ADDR(addr))
+#define __do_readb(addr)	in_8(addr)
+#define __do_readw(addr)	in_le16(addr)
+#define __do_readl(addr)	in_le32(addr)
+#define __do_readq(addr)	in_le64(addr)
+#define __do_readw_be(addr)	in_be16(addr)
+#define __do_readl_be(addr)	in_be32(addr)
+#define __do_readq_be(addr)	in_be64(addr)
 #endif /* !defined(CONFIG_EEH) */
 
 #ifdef CONFIG_PPC32
@@ -590,64 +460,185 @@ __do_out_asm(_rec_outl, "stwbrx")
 #define __do_inw(port)		_rec_inw(port)
 #define __do_inl(port)		_rec_inl(port)
 #else /* CONFIG_PPC32 */
-#define __do_outb(val, port)	writeb(val,(PCI_IO_ADDR)_IO_BASE+port);
-#define __do_outw(val, port)	writew(val,(PCI_IO_ADDR)_IO_BASE+port);
-#define __do_outl(val, port)	writel(val,(PCI_IO_ADDR)_IO_BASE+port);
-#define __do_inb(port)		readb((PCI_IO_ADDR)_IO_BASE + port);
-#define __do_inw(port)		readw((PCI_IO_ADDR)_IO_BASE + port);
-#define __do_inl(port)		readl((PCI_IO_ADDR)_IO_BASE + port);
+#define __do_outb(val, port)	writeb(val,_IO_PORT(port));
+#define __do_outw(val, port)	writew(val,_IO_PORT(port));
+#define __do_outl(val, port)	writel(val,_IO_PORT(port));
+#define __do_inb(port)		readb(_IO_PORT(port));
+#define __do_inw(port)		readw(_IO_PORT(port));
+#define __do_inl(port)		readl(_IO_PORT(port));
 #endif /* !CONFIG_PPC32 */
 
 #ifdef CONFIG_EEH
-#define __do_readsb(a, b, n)	eeh_readsb(PCI_FIX_ADDR(a), (b), (n))
-#define __do_readsw(a, b, n)	eeh_readsw(PCI_FIX_ADDR(a), (b), (n))
-#define __do_readsl(a, b, n)	eeh_readsl(PCI_FIX_ADDR(a), (b), (n))
+#define __do_readsb(a, b, n)	eeh_readsb(a, (b), (n))
+#define __do_readsw(a, b, n)	eeh_readsw(a, (b), (n))
+#define __do_readsl(a, b, n)	eeh_readsl(a, (b), (n))
 #else /* CONFIG_EEH */
-#define __do_readsb(a, b, n)	_insb(PCI_FIX_ADDR(a), (b), (n))
-#define __do_readsw(a, b, n)	_insw(PCI_FIX_ADDR(a), (b), (n))
-#define __do_readsl(a, b, n)	_insl(PCI_FIX_ADDR(a), (b), (n))
+#define __do_readsb(a, b, n)	_insb(a, (b), (n))
+#define __do_readsw(a, b, n)	_insw(a, (b), (n))
+#define __do_readsl(a, b, n)	_insl(a, (b), (n))
 #endif /* !CONFIG_EEH */
-#define __do_writesb(a, b, n)	_outsb(PCI_FIX_ADDR(a),(b),(n))
-#define __do_writesw(a, b, n)	_outsw(PCI_FIX_ADDR(a),(b),(n))
-#define __do_writesl(a, b, n)	_outsl(PCI_FIX_ADDR(a),(b),(n))
-
-#define __do_insb(p, b, n)	readsb((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
-#define __do_insw(p, b, n)	readsw((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
-#define __do_insl(p, b, n)	readsl((PCI_IO_ADDR)_IO_BASE+(p), (b), (n))
-#define __do_outsb(p, b, n)	writesb((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
-#define __do_outsw(p, b, n)	writesw((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
-#define __do_outsl(p, b, n)	writesl((PCI_IO_ADDR)_IO_BASE+(p),(b),(n))
-
-#define __do_memset_io(addr, c, n)	\
-				_memset_io(PCI_FIX_ADDR(addr), c, n)
-#define __do_memcpy_toio(dst, src, n)	\
-				_memcpy_toio(PCI_FIX_ADDR(dst), src, n)
+#define __do_writesb(a, b, n)	_outsb(a, (b), (n))
+#define __do_writesw(a, b, n)	_outsw(a, (b), (n))
+#define __do_writesl(a, b, n)	_outsl(a, (b), (n))
+
+#define __do_insb(p, b, n)	readsb(_IO_PORT(p), (b), (n))
+#define __do_insw(p, b, n)	readsw(_IO_PORT(p), (b), (n))
+#define __do_insl(p, b, n)	readsl(_IO_PORT(p), (b), (n))
+#define __do_outsb(p, b, n)	writesb(_IO_PORT(p),(b),(n))
+#define __do_outsw(p, b, n)	writesw(_IO_PORT(p),(b),(n))
+#define __do_outsl(p, b, n)	writesl(_IO_PORT(p),(b),(n))
 
 #ifdef CONFIG_EEH
 #define __do_memcpy_fromio(dst, src, n)	\
-				eeh_memcpy_fromio(dst, PCI_FIX_ADDR(src), n)
+				eeh_memcpy_fromio(dst, src, n)
 #else /* CONFIG_EEH */
 #define __do_memcpy_fromio(dst, src, n)	\
-				_memcpy_fromio(dst,PCI_FIX_ADDR(src),n)
+				_memcpy_fromio(dst, src, n)
 #endif /* !CONFIG_EEH */
 
-#ifdef CONFIG_PPC_INDIRECT_PIO
-#define DEF_PCI_HOOK_pio(x)	x
-#else
-#define DEF_PCI_HOOK_pio(x)	NULL
-#endif
+static inline u8 readb(const volatile void __iomem *addr)
+{
+	return __do_readb(addr);
+}
+#define readb readb
+
+static inline u16 readw(const volatile void __iomem *addr)
+{
+	return __do_readw(addr);
+}
+#define readw readw
+
+static inline u32 readl(const volatile void __iomem *addr)
+{
+	return __do_readl(addr);
+}
+#define readl readl
+
+static inline u16 readw_be(const volatile void __iomem *addr)
+{
+	return __do_readw_be(addr);
+}
+
+static inline u32 readl_be(const volatile void __iomem *addr)
+{
+	return __do_readl_be(addr);
+}
+
+static inline void writeb(u8 val, volatile void __iomem *addr)
+{
+	out_8(addr, val);
+}
+#define writeb writeb
+
+static inline void writew(u16 val, volatile void __iomem *addr)
+{
+	out_le16(addr, val);
+}
+#define writew writew
+
+static inline void writel(u32 val, volatile void __iomem *addr)
+{
+	out_le32(addr, val);
+}
+#define writel writel
+
+static inline void writew_be(u16 val, volatile void __iomem *addr)
+{
+	out_be16(addr, val);
+}
 
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-#define DEF_PCI_HOOK_mem(x)	x
+static inline void writel_be(u32 val, volatile void __iomem *addr)
+{
+	out_be32(addr, val);
+}
+
+static inline void readsb(const volatile void __iomem *a, void *b, unsigned long c)
+{
+	__do_readsb(a, b, c);
+}
+#define readsb readsb
+
+static inline void readsw(const volatile void __iomem *a, void *b, unsigned long c)
+{
+	__do_readsw(a, b, c);
+}
+#define readsw readsw
+
+static inline void readsl(const volatile void __iomem *a, void *b, unsigned long c)
+{
+	__do_readsl(a, b, c);
+}
+#define readsl readsl
+
+static inline void writesb(volatile void __iomem *a, const void *b, unsigned long c)
+{
+	__do_writesb(a, b, c);
+}
+#define writesb writesb
+
+static inline void writesw(volatile void __iomem *a, const void *b, unsigned long c)
+{
+	__do_writesw(a, b, c);
+}
+#define writesw writesw
+
+static inline void writesl(volatile void __iomem *a, const void *b, unsigned long c)
+{
+	__do_writesl(a, b, c);
+}
+#define writesl writesl
+
+static inline void memset_io(volatile void __iomem *a, int c, unsigned long n)
+{
+	_memset_io(a, c, n);
+}
+#define memset_io memset_io
+
+static inline void memcpy_fromio(void *d, const volatile void __iomem *s, unsigned long n)
+{
+	__do_memcpy_fromio(d, s, n);
+}
+#define memcpy_fromio memcpy_fromio
+
+static inline void memcpy_toio(volatile void __iomem *d, const void *s, unsigned long n)
+{
+	_memcpy_toio(d, s, n);
+}
+#define memcpy_toio memcpy_toio
+
+#ifdef __powerpc64__
+static inline u64 readq(const volatile void __iomem *addr)
+{
+	return __do_readq(addr);
+}
+
+static inline u64 readq_be(const volatile void __iomem *addr)
+{
+	return __do_readq_be(addr);
+}
+
+static inline void writeq(u64 val, volatile void __iomem *addr)
+{
+	out_le64(addr, val);
+}
+
+static inline void writeq_be(u64 val, volatile void __iomem *addr)
+{
+	out_be64(addr, val);
+}
+#endif /* __powerpc64__ */
+
+#ifdef CONFIG_PPC_INDIRECT_PIO
+#define DEF_PCI_HOOK(x)	x
 #else
-#define DEF_PCI_HOOK_mem(x)	NULL
+#define DEF_PCI_HOOK(x)	NULL
 #endif
 
 /* Structure containing all the hooks */
 extern struct ppc_pci_io {
 
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)	ret (*name) at;
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)	void (*name) at;
+#define DEF_PCI_AC_RET(name, ret, at, al)	ret (*name) at;
+#define DEF_PCI_AC_NORET(name, at, al)		void (*name) at;
 
 #include <asm/io-defs.h>
 
@@ -657,18 +648,18 @@ extern struct ppc_pci_io {
 } ppc_pci_io;
 
 /* The inline wrappers */
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
+#define DEF_PCI_AC_RET(name, ret, at, al)			\
 static inline ret name at					\
 {								\
-	if (DEF_PCI_HOOK_##space(ppc_pci_io.name) != NULL)	\
+	if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL)		\
 		return ppc_pci_io.name al;			\
 	return __do_##name al;					\
 }
 
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)		\
+#define DEF_PCI_AC_NORET(name, at, al)		\
 static inline void name at					\
 {								\
-	if (DEF_PCI_HOOK_##space(ppc_pci_io.name) != NULL)		\
+	if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL)		\
 		ppc_pci_io.name al;				\
 	else							\
 		__do_##name al;					\
@@ -679,21 +670,7 @@ static inline void name at					\
 #undef DEF_PCI_AC_RET
 #undef DEF_PCI_AC_NORET
 
-/* Some drivers check for the presence of readq & writeq with
- * a #ifdef, so we make them happy here.
- */
-#define readb readb
-#define readw readw
-#define readl readl
-#define writeb writeb
-#define writew writew
-#define writel writel
-#define readsb readsb
-#define readsw readsw
-#define readsl readsl
-#define writesb writesb
-#define writesw writesw
-#define writesl writesl
+// Signal to asm-generic/io.h that we have implemented these.
 #define inb inb
 #define inw inw
 #define inl inl
@@ -710,15 +687,6 @@ static inline void name at					\
 #define readq	readq
 #define writeq	writeq
 #endif
-#define memset_io memset_io
-#define memcpy_fromio memcpy_fromio
-#define memcpy_toio memcpy_toio
-
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
 
 /*
  * We don't do relaxed operations yet, at least not with this semantic
@@ -732,9 +700,7 @@ static inline void name at					\
 #define writel_relaxed(v, addr)	writel(v, addr)
 #define writeq_relaxed(v, addr)	writeq(v, addr)
 
-#ifdef CONFIG_GENERIC_IOMAP
-#include <asm-generic/iomap.h>
-#else
+#ifndef CONFIG_GENERIC_IOMAP
 /*
  * Here comes the implementation of the IOMAP interfaces.
  */
@@ -751,35 +717,11 @@ static inline unsigned int ioread32be(const void __iomem *addr)
 #define ioread32be ioread32be
 
 #ifdef __powerpc64__
-static inline u64 ioread64_lo_hi(const void __iomem *addr)
-{
-	return readq(addr);
-}
-#define ioread64_lo_hi ioread64_lo_hi
-
-static inline u64 ioread64_hi_lo(const void __iomem *addr)
-{
-	return readq(addr);
-}
-#define ioread64_hi_lo ioread64_hi_lo
-
 static inline u64 ioread64be(const void __iomem *addr)
 {
 	return readq_be(addr);
 }
 #define ioread64be ioread64be
-
-static inline u64 ioread64be_lo_hi(const void __iomem *addr)
-{
-	return readq_be(addr);
-}
-#define ioread64be_lo_hi ioread64be_lo_hi
-
-static inline u64 ioread64be_hi_lo(const void __iomem *addr)
-{
-	return readq_be(addr);
-}
-#define ioread64be_hi_lo ioread64be_hi_lo
 #endif /* __powerpc64__ */
 
 static inline void iowrite16be(u16 val, void __iomem *addr)
@@ -795,35 +737,11 @@ static inline void iowrite32be(u32 val, void __iomem *addr)
 #define iowrite32be iowrite32be
 
 #ifdef __powerpc64__
-static inline void iowrite64_lo_hi(u64 val, void __iomem *addr)
-{
-	writeq(val, addr);
-}
-#define iowrite64_lo_hi iowrite64_lo_hi
-
-static inline void iowrite64_hi_lo(u64 val, void __iomem *addr)
-{
-	writeq(val, addr);
-}
-#define iowrite64_hi_lo iowrite64_hi_lo
-
 static inline void iowrite64be(u64 val, void __iomem *addr)
 {
 	writeq_be(val, addr);
 }
 #define iowrite64be iowrite64be
-
-static inline void iowrite64be_lo_hi(u64 val, void __iomem *addr)
-{
-	writeq_be(val, addr);
-}
-#define iowrite64be_lo_hi iowrite64be_lo_hi
-
-static inline void iowrite64be_hi_lo(u64 val, void __iomem *addr)
-{
-	writeq_be(val, addr);
-}
-#define iowrite64be_hi_lo iowrite64be_hi_lo
 #endif /* __powerpc64__ */
 
 struct pci_dev;
@@ -896,8 +814,8 @@ static inline void iosync(void)
  *
  */
 extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
-extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size,
-				  unsigned long flags);
+#define ioremap ioremap
+#define ioremap_prot ioremap_prot
 extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size);
 #define ioremap_wc ioremap_wc
 
@@ -907,18 +825,15 @@ void __iomem *ioremap_wt(phys_addr_t address, unsigned long size);
 #endif
 
 void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
-#define ioremap_uc(addr, size)		ioremap((addr), (size))
 #define ioremap_cache(addr, size) \
-	ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL))
+	ioremap_prot((addr), (size), PAGE_KERNEL)
 
-extern void iounmap(volatile void __iomem *addr);
+#define iounmap iounmap
 
 void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size);
 
 int early_ioremap_range(unsigned long ea, phys_addr_t pa,
 			unsigned long size, pgprot_t prot);
-void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
-			 pgprot_t prot, void *caller);
 
 extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
 				      pgprot_t prot, void *caller);
@@ -959,7 +874,7 @@ extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
  *	almost all conceivable cases a device driver should not be using
  *	this function
  */
-static inline unsigned long virt_to_phys(volatile void * address)
+static inline unsigned long virt_to_phys(const volatile void * address)
 {
 	WARN_ON(IS_ENABLED(CONFIG_DEBUG_VIRTUAL) && !virt_addr_valid(address));
 
@@ -986,19 +901,7 @@ static inline void * phys_to_virt(unsigned long address)
 #define phys_to_virt phys_to_virt
 
 /*
- * Change "struct page" to physical address.
- */
-static inline phys_addr_t page_to_phys(struct page *page)
-{
-	unsigned long pfn = page_to_pfn(page);
-
-	WARN_ON(IS_ENABLED(CONFIG_DEBUG_VIRTUAL) && !pfn_valid(pfn));
-
-	return PFN_PHYS(pfn);
-}
-
-/*
- * 32 bits still uses virt_to_bus() for it's implementation of DMA
+ * 32 bits still uses virt_to_bus() for its implementation of DMA
  * mappings se we have to keep it defined here. We also have some old
  * drivers (shame shame shame) that use bus_to_virt() and haven't been
  * fixed yet so I need to define it here.
@@ -1058,6 +961,14 @@ static inline void * bus_to_virt(unsigned long address)
 
 #include <asm-generic/io.h>
 
+#ifdef __powerpc64__
+static inline void __raw_writeq_be(unsigned long v, volatile void __iomem *addr)
+{
+	__raw_writeq((__force unsigned long)cpu_to_be64(v), addr);
+}
+#define __raw_writeq_be __raw_writeq_be
+#endif // __powerpc64__
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_POWERPC_IO_H */
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 678b5bdc79b1..eafdd63cd6c4 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -28,6 +28,11 @@
 #define IOMMU_PAGE_MASK(tblptr) (~((1 << (tblptr)->it_page_shift) - 1))
 #define IOMMU_PAGE_ALIGN(addr, tblptr) ALIGN(addr, IOMMU_PAGE_SIZE(tblptr))
 
+#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info"
+#define DMA64_PROPNAME "linux,dma64-ddr-window-info"
+
+#define	MIN_DDW_VPMEM_DMA_WINDOW	SZ_2G
+
 /* Boot time flags */
 extern int iommu_is_off;
 extern int iommu_force_on;
@@ -153,6 +158,9 @@ extern int iommu_tce_table_put(struct iommu_table *tbl);
 extern struct iommu_table *iommu_init_table(struct iommu_table *tbl,
 		int nid, unsigned long res_start, unsigned long res_end);
 bool iommu_table_in_use(struct iommu_table *tbl);
+extern void iommu_table_reserve_pages(struct iommu_table *tbl,
+		unsigned long res_start, unsigned long res_end);
+extern void iommu_table_clear(struct iommu_table *tbl);
 
 #define IOMMU_TABLE_GROUP_MAX_TABLES	2
 
@@ -175,9 +183,9 @@ struct iommu_table_group_ops {
 	long (*unset_window)(struct iommu_table_group *table_group,
 			int num);
 	/* Switch ownership from platform code to external user (e.g. VFIO) */
-	long (*take_ownership)(struct iommu_table_group *table_group);
+	long (*take_ownership)(struct iommu_table_group *table_group, struct device *dev);
 	/* Switch ownership from external user (e.g. VFIO) back to core */
-	void (*release_ownership)(struct iommu_table_group *table_group);
+	void (*release_ownership)(struct iommu_table_group *table_group, struct device *dev);
 };
 
 struct iommu_table_group_link {
@@ -205,7 +213,6 @@ extern void iommu_register_group(struct iommu_table_group *table_group,
 				 int pci_domain_number, unsigned long pe_num);
 extern int iommu_add_device(struct iommu_table_group *table_group,
 		struct device *dev);
-extern void iommu_del_device(struct device *dev);
 extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction);
@@ -215,8 +222,8 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
 		enum dma_data_direction *direction);
 extern void iommu_tce_kill(struct iommu_table *tbl,
 		unsigned long entry, unsigned long pages);
+int dev_has_iommu_table(struct device *dev, void *data);
 
-extern struct iommu_table_group_ops spapr_tce_table_group_ops;
 #else
 static inline void iommu_register_group(struct iommu_table_group *table_group,
 					int pci_domain_number,
@@ -230,8 +237,9 @@ static inline int iommu_add_device(struct iommu_table_group *table_group,
 	return 0;
 }
 
-static inline void iommu_del_device(struct device *dev)
+static inline int dev_has_iommu_table(struct device *dev, void *data)
 {
+	return 0;
 }
 #endif /* !CONFIG_IOMMU_API */
 
@@ -266,12 +274,12 @@ extern void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 				  unsigned long mask, gfp_t flag, int node);
 extern void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 				void *vaddr, dma_addr_t dma_handle);
-extern dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
-				 struct page *page, unsigned long offset,
-				 size_t size, unsigned long mask,
+extern dma_addr_t iommu_map_phys(struct device *dev, struct iommu_table *tbl,
+				 phys_addr_t phys, size_t size,
+				 unsigned long mask,
 				 enum dma_data_direction direction,
 				 unsigned long attrs);
-extern void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
+extern void iommu_unmap_phys(struct iommu_table *tbl, dma_addr_t dma_handle,
 			     size_t size, enum dma_data_direction direction,
 			     unsigned long attrs);
 
@@ -309,12 +317,6 @@ extern void iommu_flush_tce(struct iommu_table *tbl);
 extern enum dma_data_direction iommu_tce_direction(unsigned long tce);
 extern unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir);
 
-#ifdef CONFIG_PPC_CELL_NATIVE
-extern bool iommu_fixed_is_weak;
-#else
-#define iommu_fixed_is_weak false
-#endif
-
 extern const struct dma_map_ops dma_iommu_ops;
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index deadd2149426..aa3751960ffd 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -33,7 +33,7 @@ extern int distribute_irqs;
 
 struct pt_regs;
 
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 /*
  * Per-cpu stacks for handling critical, debug and machine check
  * level interrupts.
@@ -50,9 +50,14 @@ extern void *hardirq_ctx[NR_CPUS];
 extern void *softirq_ctx[NR_CPUS];
 
 void __do_IRQ(struct pt_regs *regs);
-extern void __init init_IRQ(void);
 
 int irq_choose_cpu(const struct cpumask *mask);
 
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI)
+extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
+					   int exclude_cpu);
+#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
+#endif
+
 #endif /* _ASM_IRQ_H */
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h
index b8b0be8f1a07..c6d3078bd8c3 100644
--- a/arch/powerpc/include/asm/irq_work.h
+++ b/arch/powerpc/include/asm/irq_work.h
@@ -6,6 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void)
 {
 	return true;
 }
-extern void arch_irq_work_raise(void);
 
 #endif /* _ASM_POWERPC_IRQ_WORK_H */
diff --git a/arch/powerpc/include/asm/irqflags.h b/arch/powerpc/include/asm/irqflags.h
index 47d46712928a..1351fb40fe74 100644
--- a/arch/powerpc/include/asm/irqflags.h
+++ b/arch/powerpc/include/asm/irqflags.h
@@ -5,7 +5,7 @@
 #ifndef _ASM_IRQFLAGS_H
 #define _ASM_IRQFLAGS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Get definitions for arch_local_save_flags(x), etc.
  */
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 93ce3ec25387..d4eaba459a0e 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -6,7 +6,7 @@
  * Copyright 2010 Michael Ellerman, IBM Corp.
  */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 #include <asm/feature-fixups.h>
@@ -17,7 +17,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop # arch_static_branch\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
@@ -32,7 +32,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b %l[l_yes] # arch_static_branch_jump\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
index 365d2720097c..045804a86f98 100644
--- a/arch/powerpc/include/asm/kasan.h
+++ b/arch/powerpc/include/asm/kasan.h
@@ -12,14 +12,14 @@
 #define EXPORT_SYMBOL_KASAN(fn)
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/page.h>
 #include <linux/sizes.h>
 
 #define KASAN_SHADOW_SCALE_SHIFT	3
 
-#if defined(CONFIG_MODULES) && defined(CONFIG_PPC32)
+#if defined(CONFIG_EXECMEM) && defined(CONFIG_PPC32)
 #define KASAN_KERN_START	ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M)
 #else
 #define KASAN_KERN_START	PAGE_OFFSET
@@ -53,18 +53,6 @@
 #endif
 
 #ifdef CONFIG_KASAN
-#ifdef CONFIG_PPC_BOOK3S_64
-DECLARE_STATIC_KEY_FALSE(powerpc_kasan_enabled_key);
-
-static __always_inline bool kasan_arch_is_ready(void)
-{
-	if (static_branch_likely(&powerpc_kasan_enabled_key))
-		return true;
-	return false;
-}
-
-#define kasan_arch_is_ready kasan_arch_is_ready
-#endif
 
 void kasan_early_init(void);
 void kasan_mmu_init(void);
@@ -80,5 +68,5 @@ void kasan_update_early_region(unsigned long k_start, unsigned long k_end, pte_t
 int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end);
 int kasan_init_region(void *start, size_t size);
 
-#endif /* __ASSEMBLY */
+#endif /* __ASSEMBLER__ */
 #endif
diff --git a/arch/powerpc/include/asm/kdump.h b/arch/powerpc/include/asm/kdump.h
index fd128d1e52b3..802644178f43 100644
--- a/arch/powerpc/include/asm/kdump.h
+++ b/arch/powerpc/include/asm/kdump.h
@@ -31,7 +31,7 @@
 
 #endif /* CONFIG_CRASH_DUMP */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #if defined(CONFIG_CRASH_DUMP) && !defined(CONFIG_NONSTATIC_KERNEL)
 extern void reserve_kdump_trampoline(void);
@@ -42,6 +42,6 @@ static inline void reserve_kdump_trampoline(void) { ; }
 static inline void setup_kdump_trampoline(void) { ; }
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __PPC64_KDUMP_H */
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index a1ddba01e7d1..bd4a6c42a5f3 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -49,61 +49,23 @@
 #define KEXEC_STATE_IRQS_OFF 1
 #define KEXEC_STATE_REAL_MODE 2
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/reg.h>
 
 typedef void (*crash_shutdown_t)(void);
 
 #ifdef CONFIG_KEXEC_CORE
-
-/*
- * This function is responsible for capturing register states if coming
- * via panic or invoking dump using sysrq-trigger.
- */
-static inline void crash_setup_regs(struct pt_regs *newregs,
-					struct pt_regs *oldregs)
-{
-	if (oldregs)
-		memcpy(newregs, oldregs, sizeof(*newregs));
-	else
-		ppc_save_regs(newregs);
-}
+struct kimage;
+struct pt_regs;
 
 extern void kexec_smp_wait(void);	/* get and clear naca physid, wait for
 					  master to copy new code to 0 */
-extern int crashing_cpu;
-extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
-extern void crash_ipi_callback(struct pt_regs *);
-extern int crash_wake_offline;
-
-struct kimage;
-struct pt_regs;
 extern void default_machine_kexec(struct kimage *image);
-extern void default_machine_crash_shutdown(struct pt_regs *regs);
-extern int crash_shutdown_register(crash_shutdown_t handler);
-extern int crash_shutdown_unregister(crash_shutdown_t handler);
-
-extern void crash_kexec_prepare(void);
-extern void crash_kexec_secondary(struct pt_regs *regs);
-int __init overlaps_crashkernel(unsigned long start, unsigned long size);
-extern void reserve_crashkernel(void);
-extern void machine_kexec_mask_interrupts(void);
-
-static inline bool kdump_in_progress(void)
-{
-	return crashing_cpu >= 0;
-}
 
 void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_code_buffer,
 			 unsigned long start_address) __noreturn;
-
 void kexec_copy_flush(struct kimage *image);
 
-#if defined(CONFIG_CRASH_DUMP) && defined(CONFIG_PPC_RTAS)
-void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
-#define crash_free_reserved_phys_range crash_free_reserved_phys_range
-#endif
-
 #ifdef CONFIG_KEXEC_FILE
 extern const struct kexec_file_ops kexec_elf64_ops;
 
@@ -132,31 +94,85 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long
 int arch_kimage_file_post_load_cleanup(struct kimage *image);
 #define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup
 
-int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf);
-#define arch_kexec_locate_mem_hole arch_kexec_locate_mem_hole
+int arch_check_excluded_range(struct kimage *image, unsigned long start,
+			      unsigned long end);
+#define arch_check_excluded_range  arch_check_excluded_range
+
 
 int load_crashdump_segments_ppc64(struct kimage *image,
 				  struct kexec_buf *kbuf);
 int setup_purgatory_ppc64(struct kimage *image, const void *slave_code,
 			  const void *fdt, unsigned long kernel_load_addr,
 			  unsigned long fdt_load_addr);
-unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image);
-int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
-			unsigned long initrd_load_addr,
-			unsigned long initrd_len, const char *cmdline);
+unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image, struct crash_mem *rmem);
+int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem *rmem);
 #endif /* CONFIG_PPC64 */
 
 #endif /* CONFIG_KEXEC_FILE */
 
-#else /* !CONFIG_KEXEC_CORE */
-static inline void crash_kexec_secondary(struct pt_regs *regs) { }
+#endif /* CONFIG_KEXEC_CORE */
 
-static inline int overlaps_crashkernel(unsigned long start, unsigned long size)
+#ifdef CONFIG_CRASH_RESERVE
+int __init overlaps_crashkernel(unsigned long start, unsigned long size);
+extern void arch_reserve_crashkernel(void);
+extern void kdump_cma_reserve(void);
+#else
+static inline void arch_reserve_crashkernel(void) {}
+static inline int overlaps_crashkernel(unsigned long start, unsigned long size) { return 0; }
+static inline void kdump_cma_reserve(void) { }
+#endif
+
+#if defined(CONFIG_CRASH_DUMP)
+/*
+ * This function is responsible for capturing register states if coming
+ * via panic or invoking dump using sysrq-trigger.
+ */
+static inline void crash_setup_regs(struct pt_regs *newregs,
+					struct pt_regs *oldregs)
 {
-	return 0;
+	if (oldregs)
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	else
+		ppc_save_regs(newregs);
 }
 
-static inline void reserve_crashkernel(void) { ; }
+#ifdef CONFIG_CRASH_HOTPLUG
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg);
+#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
+
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags);
+#define arch_crash_hotplug_support arch_crash_hotplug_support
+
+unsigned int arch_crash_get_elfcorehdr_size(void);
+#define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size
+#endif /* CONFIG_CRASH_HOTPLUG */
+
+extern int crashing_cpu;
+extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
+extern void crash_ipi_callback(struct pt_regs *regs);
+extern int crash_wake_offline;
+
+extern int crash_shutdown_register(crash_shutdown_t handler);
+extern int crash_shutdown_unregister(crash_shutdown_t handler);
+extern void default_machine_crash_shutdown(struct pt_regs *regs);
+
+extern void crash_kexec_prepare(void);
+extern void crash_kexec_secondary(struct pt_regs *regs);
+
+static inline bool kdump_in_progress(void)
+{
+	return crashing_cpu >= 0;
+}
+
+bool is_kdump_kernel(void);
+#define is_kdump_kernel			is_kdump_kernel
+#if defined(CONFIG_PPC_RTAS)
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
+#define crash_free_reserved_phys_range crash_free_reserved_phys_range
+#endif /* CONFIG_PPC_RTAS */
+
+#else /* !CONFIG_CRASH_DUMP */
+static inline void crash_kexec_secondary(struct pt_regs *regs) { }
 
 static inline int crash_shutdown_register(crash_shutdown_t handler)
 {
@@ -179,7 +195,11 @@ static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 {
 }
 
-#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_CRASH_DUMP */
+
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
+int update_cpus_node(void *fdt);
+#endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/book3s/64/kexec.h>
@@ -192,6 +212,6 @@ static inline void reset_sprs(void)
 }
 #endif
 
-#endif /* ! __ASSEMBLY__ */
+#endif /* ! __ASSEMBLER__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_KEXEC_H */
diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h
index f83866a19e87..14055896cbcb 100644
--- a/arch/powerpc/include/asm/kexec_ranges.h
+++ b/arch/powerpc/include/asm/kexec_ranges.h
@@ -7,19 +7,9 @@
 void sort_memory_ranges(struct crash_mem *mrngs, bool merge);
 struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges);
 int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size);
-int add_tce_mem_ranges(struct crash_mem **mem_ranges);
-int add_initrd_mem_range(struct crash_mem **mem_ranges);
-#ifdef CONFIG_PPC_64S_HASH_MMU
-int add_htab_mem_range(struct crash_mem **mem_ranges);
-#else
-static inline int add_htab_mem_range(struct crash_mem **mem_ranges)
-{
-	return 0;
-}
-#endif
-int add_kernel_mem_range(struct crash_mem **mem_ranges);
-int add_rtas_mem_range(struct crash_mem **mem_ranges);
-int add_opal_mem_range(struct crash_mem **mem_ranges);
-int add_reserved_mem_ranges(struct crash_mem **mem_ranges);
-
+int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size);
+int get_exclude_memory_ranges(struct crash_mem **mem_ranges);
+int get_reserved_memory_ranges(struct crash_mem **mem_ranges);
+int get_crash_memory_ranges(struct crash_mem **mem_ranges);
+int get_usable_memory_ranges(struct crash_mem **mem_ranges);
 #endif /* _ASM_POWERPC_KEXEC_RANGES_H */
diff --git a/arch/powerpc/include/asm/kfence.h b/arch/powerpc/include/asm/kfence.h
index 6fd2b4d486c5..1f7cab58ab2c 100644
--- a/arch/powerpc/include/asm/kfence.h
+++ b/arch/powerpc/include/asm/kfence.h
@@ -15,15 +15,28 @@
 #define ARCH_FUNC_PREFIX "."
 #endif
 
+extern bool kfence_early_init;
+extern bool kfence_disabled;
+
+static inline void disable_kfence(void)
+{
+	kfence_disabled = true;
+}
+
 static inline bool arch_kfence_init_pool(void)
 {
-	return true;
+	return !kfence_disabled;
+}
+
+static inline bool kfence_early_init_enabled(void)
+{
+	return IS_ENABLED(CONFIG_KFENCE) && kfence_early_init;
 }
 
 #ifdef CONFIG_PPC64
 static inline bool kfence_protect_page(unsigned long addr, bool protect)
 {
-	struct page *page = virt_to_page(addr);
+	struct page *page = virt_to_page((void *)addr);
 
 	__kernel_map_pages(page, 1, !protect);
 
diff --git a/arch/powerpc/include/asm/kgdb.h b/arch/powerpc/include/asm/kgdb.h
index 715c18b75334..f39531903325 100644
--- a/arch/powerpc/include/asm/kgdb.h
+++ b/arch/powerpc/include/asm/kgdb.h
@@ -21,7 +21,7 @@
 #ifndef __POWERPC_KGDB_H__
 #define __POWERPC_KGDB_H__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define BREAK_INSTR_SIZE	4
 #define BUFMAX			((NUMREGBYTES * 2) + 512)
@@ -62,6 +62,6 @@ static inline void arch_kgdb_breakpoint(void)
 /* CR/LR, R1, R2, R13-R31 inclusive. */
 #define NUMCRITREGBYTES		(23 * sizeof(int))
 #endif /* 32/64 */
-#endif /* !(__ASSEMBLY__) */
+#endif /* !(__ASSEMBLER__) */
 #endif /* !__POWERPC_KGDB_H__ */
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index c8e4b4fd4e33..dfe2e5ad3b21 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -21,7 +21,7 @@
 #include <linux/percpu.h>
 #include <linux/module.h>
 #include <asm/probes.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 
 #ifdef CONFIG_KPROBES
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
@@ -84,8 +84,6 @@ struct arch_optimized_insn {
 	kprobe_opcode_t *insn;
 };
 
-extern int kprobe_exceptions_notify(struct notifier_block *self,
-					unsigned long val, void *data);
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_handler(struct pt_regs *regs);
 extern int kprobe_post_handler(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
index d751ddd08110..dab63b82a8d4 100644
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -6,6 +6,12 @@
 #define KUAP_WRITE	2
 #define KUAP_READ_WRITE	(KUAP_READ | KUAP_WRITE)
 
+#ifndef __ASSEMBLER__
+#include <linux/types.h>
+
+static __always_inline bool kuap_is_disabled(void);
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/book3s/64/kup.h>
 #endif
@@ -14,7 +20,7 @@
 #include <asm/nohash/32/kup-8xx.h>
 #endif
 
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 #include <asm/nohash/kup-booke.h>
 #endif
 
@@ -22,14 +28,14 @@
 #include <asm/book3s/32/kup.h>
 #endif
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #ifndef CONFIG_PPC_KUAP
 .macro kuap_check_amr	gpr1, gpr2
 .endm
 
 #endif
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 extern bool disable_kuep;
 extern bool disable_kuap;
@@ -41,26 +47,24 @@ void setup_kuep(bool disabled);
 
 #ifdef CONFIG_PPC_KUAP
 void setup_kuap(bool disabled);
+
+static __always_inline bool kuap_is_disabled(void)
+{
+	return !mmu_has_feature(MMU_FTR_KUAP);
+}
 #else
 static inline void setup_kuap(bool disabled) { }
 
 static __always_inline bool kuap_is_disabled(void) { return true; }
 
-static inline bool
+static __always_inline bool
 __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	return false;
 }
 
-static inline void __kuap_lock(void) { }
-static inline void __kuap_save_and_lock(struct pt_regs *regs) { }
-static inline void kuap_user_restore(struct pt_regs *regs) { }
-static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) { }
-
-static inline unsigned long __kuap_get_and_assert_locked(void)
-{
-	return 0;
-}
+static __always_inline void kuap_user_restore(struct pt_regs *regs) { }
+static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr) { }
 
 /*
  * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush
@@ -68,11 +72,11 @@ static inline unsigned long __kuap_get_and_assert_locked(void)
  * platforms.
  */
 #ifndef CONFIG_PPC_BOOK3S_64
-static inline void __allow_user_access(void __user *to, const void __user *from,
-				       unsigned long size, unsigned long dir) { }
-static inline void __prevent_user_access(unsigned long dir) { }
-static inline unsigned long __prevent_user_access_return(void) { return 0UL; }
-static inline void __restore_user_access(unsigned long flags) { }
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      unsigned long size, unsigned long dir) { }
+static __always_inline void prevent_user_access(unsigned long dir) { }
+static __always_inline unsigned long prevent_user_access_return(void) { return 0UL; }
+static __always_inline void restore_user_access(unsigned long flags) { }
 #endif /* CONFIG_PPC_BOOK3S_64 */
 #endif /* CONFIG_PPC_KUAP */
 
@@ -85,29 +89,24 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 	return __bad_kuap_fault(regs, address, is_write);
 }
 
-static __always_inline void kuap_assert_locked(void)
-{
-	if (kuap_is_disabled())
-		return;
-
-	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG))
-		__kuap_get_and_assert_locked();
-}
-
 static __always_inline void kuap_lock(void)
 {
+#ifdef __kuap_lock
 	if (kuap_is_disabled())
 		return;
 
 	__kuap_lock();
+#endif
 }
 
 static __always_inline void kuap_save_and_lock(struct pt_regs *regs)
 {
+#ifdef __kuap_save_and_lock
 	if (kuap_is_disabled())
 		return;
 
 	__kuap_save_and_lock(regs);
+#endif
 }
 
 static __always_inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long amr)
@@ -120,46 +119,18 @@ static __always_inline void kuap_kernel_restore(struct pt_regs *regs, unsigned l
 
 static __always_inline unsigned long kuap_get_and_assert_locked(void)
 {
-	if (kuap_is_disabled())
-		return 0;
-
-	return __kuap_get_and_assert_locked();
-}
-
-#ifndef CONFIG_PPC_BOOK3S_64
-static __always_inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size, unsigned long dir)
-{
-	if (kuap_is_disabled())
-		return;
-
-	__allow_user_access(to, from, size, dir);
-}
-
-static __always_inline void prevent_user_access(unsigned long dir)
-{
-	if (kuap_is_disabled())
-		return;
-
-	__prevent_user_access(dir);
-}
-
-static __always_inline unsigned long prevent_user_access_return(void)
-{
-	if (kuap_is_disabled())
-		return 0;
-
-	return __prevent_user_access_return();
+#ifdef __kuap_get_and_assert_locked
+	if (!kuap_is_disabled())
+		return __kuap_get_and_assert_locked();
+#endif
+	return 0;
 }
 
-static __always_inline void restore_user_access(unsigned long flags)
+static __always_inline void kuap_assert_locked(void)
 {
-	if (kuap_is_disabled())
-		return;
-
-	__restore_user_access(flags);
+	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG))
+		kuap_get_and_assert_locked();
 }
-#endif /* CONFIG_PPC_BOOK3S_64 */
 
 static __always_inline void allow_read_from_user(const void __user *from, unsigned long size)
 {
@@ -210,6 +181,6 @@ static __always_inline void prevent_current_write_to_user(void)
 	prevent_user_access(KUAP_WRITE);
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_KUAP_H_ */
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index d68d71987d5c..f9af8df09077 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -9,7 +9,7 @@
 #ifndef __POWERPC_KVM_ASM_H__
 #define __POWERPC_KVM_ASM_H__
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #ifdef CONFIG_64BIT
 #define PPC_STD(sreg, offset, areg)  std sreg, (offset)(areg)
 #define PPC_LD(treg, offset, areg)   ld treg, (offset)(areg)
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index bbf5e2c5fe09..e1ff291ba891 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_book3s_asm.h>
+#include <asm/guest-state-buffer.h>
 
 struct kvmppc_bat {
 	u64 raw;
@@ -191,23 +192,23 @@ extern int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
 extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 			struct kvmppc_pte *gpte, bool data, bool iswrite);
 extern void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
-				    unsigned int pshift, unsigned int lpid);
+				    unsigned int pshift, u64 lpid);
 extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
 			unsigned int shift,
 			const struct kvm_memory_slot *memslot,
-			unsigned int lpid);
+			u64 lpid);
 extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested,
 				    bool writing, unsigned long gpa,
-				    unsigned int lpid);
+				    u64 lpid);
 extern int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 				unsigned long gpa,
 				struct kvm_memory_slot *memslot,
-				bool writing, bool kvm_ro,
+				bool writing,
 				pte_t *inserted_pte, unsigned int *levelp);
 extern int kvmppc_init_vm_radix(struct kvm *kvm);
 extern void kvmppc_free_radix(struct kvm *kvm);
 extern void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd,
-				      unsigned int lpid);
+				      u64 lpid);
 extern int kvmppc_radix_init(void);
 extern void kvmppc_radix_exit(void);
 extern void kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
@@ -234,7 +235,7 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
 extern int kvmppc_emulate_paired_single(struct kvm_vcpu *vcpu);
 extern kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa,
-			bool writing, bool *writable);
+			bool writing, bool *writable, struct page **page);
 extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
 			unsigned long *rmap, long pte_index, int realmode);
 extern void kvmppc_update_dirty_map(const struct kvm_memory_slot *memslot,
@@ -295,12 +296,14 @@ static inline void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu) {}
 static inline void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu) {}
 #endif
 
+extern unsigned long nested_capabilities;
 long kvmhv_nested_init(void);
 void kvmhv_nested_exit(void);
 void kvmhv_vm_nested_init(struct kvm *kvm);
 long kvmhv_set_partition_table(struct kvm_vcpu *vcpu);
 long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu);
-void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1);
+void kvmhv_flush_lpid(u64 lpid);
+void kvmhv_set_ptbl_entry(u64 lpid, u64 dw0, u64 dw1);
 void kvmhv_release_all_nested(struct kvm *kvm);
 long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
 long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
@@ -316,6 +319,69 @@ long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu);
 
 void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
 
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+
+extern struct static_key_false __kvmhv_is_nestedv2;
+
+static inline bool kvmhv_is_nestedv2(void)
+{
+	return static_branch_unlikely(&__kvmhv_is_nestedv2);
+}
+
+static inline bool kvmhv_is_nestedv1(void)
+{
+	return !static_branch_likely(&__kvmhv_is_nestedv2);
+}
+
+#else
+
+static inline bool kvmhv_is_nestedv2(void)
+{
+	return false;
+}
+
+static inline bool kvmhv_is_nestedv1(void)
+{
+	return false;
+}
+
+#endif
+
+int __kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs);
+int __kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs);
+int __kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden);
+int __kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden);
+
+static inline int kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu,
+					       struct pt_regs *regs)
+{
+	if (kvmhv_is_nestedv2())
+		return __kvmhv_nestedv2_reload_ptregs(vcpu, regs);
+	return 0;
+}
+static inline int kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu,
+						   struct pt_regs *regs)
+{
+	if (kvmhv_is_nestedv2())
+		return __kvmhv_nestedv2_mark_dirty_ptregs(vcpu, regs);
+	return 0;
+}
+
+static inline int kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden)
+{
+	if (kvmhv_is_nestedv2())
+		return __kvmhv_nestedv2_mark_dirty(vcpu, iden);
+	return 0;
+}
+
+static inline int kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden)
+{
+	if (kvmhv_is_nestedv2())
+		return __kvmhv_nestedv2_cached_reload(vcpu, iden);
+	return 0;
+}
+
 extern int kvm_irq_bypass;
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
@@ -335,60 +401,72 @@ static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
 	vcpu->arch.regs.gpr[num] = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_GPR(num));
 }
 
 static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_GPR(num)) < 0);
 	return vcpu->arch.regs.gpr[num];
 }
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
 {
 	vcpu->arch.regs.ccr = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CR);
 }
 
 static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_CR) < 0);
 	return vcpu->arch.regs.ccr;
 }
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val)
 {
 	vcpu->arch.regs.xer = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_XER);
 }
 
 static inline ulong kvmppc_get_xer(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_XER) < 0);
 	return vcpu->arch.regs.xer;
 }
 
 static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
 {
 	vcpu->arch.regs.ctr = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CTR);
 }
 
 static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_CTR) < 0);
 	return vcpu->arch.regs.ctr;
 }
 
 static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
 {
 	vcpu->arch.regs.link = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LR);
 }
 
 static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_LR) < 0);
 	return vcpu->arch.regs.link;
 }
 
 static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
 {
 	vcpu->arch.regs.nip = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_NIA);
 }
 
 static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 {
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_NIA) < 0);
 	return vcpu->arch.regs.nip;
 }
 
@@ -403,10 +481,145 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 	return vcpu->arch.fault_dar;
 }
 
+static inline u64 kvmppc_get_fpr(struct kvm_vcpu *vcpu, int i)
+{
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(i)) < 0);
+	return vcpu->arch.fp.fpr[i][TS_FPROFFSET];
+}
+
+static inline void kvmppc_set_fpr(struct kvm_vcpu *vcpu, int i, u64 val)
+{
+	vcpu->arch.fp.fpr[i][TS_FPROFFSET] = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(i));
+}
+
+static inline u64 kvmppc_get_fpscr(struct kvm_vcpu *vcpu)
+{
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_FPSCR) < 0);
+	return vcpu->arch.fp.fpscr;
+}
+
+static inline void kvmppc_set_fpscr(struct kvm_vcpu *vcpu, u64 val)
+{
+	vcpu->arch.fp.fpscr = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_FPSCR);
+}
+
+
+static inline u64 kvmppc_get_vsx_fpr(struct kvm_vcpu *vcpu, int i, int j)
+{
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(i)) < 0);
+	return vcpu->arch.fp.fpr[i][j];
+}
+
+static inline void kvmppc_set_vsx_fpr(struct kvm_vcpu *vcpu, int i, int j,
+				      u64 val)
+{
+	vcpu->arch.fp.fpr[i][j] = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(i));
+}
+
+#ifdef CONFIG_ALTIVEC
+static inline void kvmppc_get_vsx_vr(struct kvm_vcpu *vcpu, int i, vector128 *v)
+{
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSRS(32 + i)) < 0);
+	*v =  vcpu->arch.vr.vr[i];
+}
+
+static inline void kvmppc_set_vsx_vr(struct kvm_vcpu *vcpu, int i,
+				     vector128 *val)
+{
+	vcpu->arch.vr.vr[i] = *val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSRS(32 + i));
+}
+
+static inline u32 kvmppc_get_vscr(struct kvm_vcpu *vcpu)
+{
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_VSCR) < 0);
+	return vcpu->arch.vr.vscr.u[3];
+}
+
+static inline void kvmppc_set_vscr(struct kvm_vcpu *vcpu, u32 val)
+{
+	vcpu->arch.vr.vscr.u[3] = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_VSCR);
+}
+#endif
+
+#define KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size, iden)		\
+static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val)	\
+{									\
+									\
+	vcpu->arch.reg = val;						\
+	kvmhv_nestedv2_mark_dirty(vcpu, iden);				\
+}
+
+#define KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size, iden)		\
+static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
+{									\
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0);		\
+	return vcpu->arch.reg;						\
+}
+
+#define KVMPPC_BOOK3S_VCPU_ACCESSOR(reg, size, iden)			\
+	KVMPPC_BOOK3S_VCPU_ACCESSOR_SET(reg, size, iden)		\
+	KVMPPC_BOOK3S_VCPU_ACCESSOR_GET(reg, size, iden)		\
+
+KVMPPC_BOOK3S_VCPU_ACCESSOR(pid, 32, KVMPPC_GSID_PIDR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(tar, 64, KVMPPC_GSID_TAR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbhr, 64, KVMPPC_GSID_EBBHR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(ebbrr, 64, KVMPPC_GSID_EBBRR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(bescr, 64, KVMPPC_GSID_BESCR)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(ic, 64, KVMPPC_GSID_IC)
+KVMPPC_BOOK3S_VCPU_ACCESSOR(vrsave, 64, KVMPPC_GSID_VRSAVE)
+
+
+#define KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size, iden)		\
+static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val)	\
+{									\
+	vcpu->arch.vcore->reg = val;					\
+	kvmhv_nestedv2_mark_dirty(vcpu, iden);				\
+}
+
+#define KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size, iden)		\
+static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
+{									\
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0);		\
+	return vcpu->arch.vcore->reg;					\
+}
+
+#define KVMPPC_BOOK3S_VCORE_ACCESSOR(reg, size, iden)			\
+	KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(reg, size, iden)		\
+	KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(reg, size, iden)		\
+
+
+KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64, KVMPPC_GSID_VTB)
+KVMPPC_BOOK3S_VCORE_ACCESSOR(dpdes, 64, KVMPPC_GSID_DPDES)
+KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(arch_compat, 32, KVMPPC_GSID_LOGICAL_PVR)
+KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(lpcr, 64, KVMPPC_GSID_LPCR)
+KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
+
+static inline u64 kvmppc_get_tb_offset(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.vcore->tb_offset;
+}
+
+static inline u64 kvmppc_get_dec_expires(struct kvm_vcpu *vcpu)
+{
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB) < 0);
+	return vcpu->arch.dec_expires;
+}
+
+static inline void kvmppc_set_dec_expires(struct kvm_vcpu *vcpu, u64 val)
+{
+	vcpu->arch.dec_expires = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_DEC_EXPIRY_TB);
+}
+
 /* Expiry time of vcpu DEC relative to host TB */
 static inline u64 kvmppc_dec_expires_host_tb(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.dec_expires - vcpu->arch.vcore->tb_offset;
+	return kvmppc_get_dec_expires(vcpu) - kvmppc_get_tb_offset(vcpu);
 }
 
 static inline bool is_kvmppc_resume_guest(int r)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index d49065af08e9..b936e174eefd 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -624,7 +624,7 @@ static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu)
 
 extern int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 			     unsigned long gpa, unsigned int level,
-			     unsigned long mmu_seq, unsigned int lpid,
+			     unsigned long mmu_seq, u64 lpid,
 			     unsigned long *rmapp, struct rmap_nested **n_rmap);
 extern void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
 				   struct rmap_nested **n_rmap);
@@ -677,6 +677,24 @@ static inline pte_t *find_kvm_host_pte(struct kvm *kvm, unsigned long mmu_seq,
 extern pte_t *find_kvm_nested_guest_pte(struct kvm *kvm, unsigned long lpid,
 					unsigned long ea, unsigned *hshift);
 
+int kvmhv_nestedv2_vcpu_create(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *io);
+void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu, struct kvmhv_nestedv2_io *io);
+int kvmhv_nestedv2_flush_vcpu(struct kvm_vcpu *vcpu, u64 time_limit);
+int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1);
+int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu);
+int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa);
+
+int kvmhv_counters_tracepoint_regfunc(void);
+void kvmhv_counters_tracepoint_unregfunc(void);
+int kvmhv_get_l2_counters_status(void);
+void kvmhv_set_l2_counters_status(int cpu, bool status);
+u64 kvmhv_get_l1_to_l2_cs_time(void);
+u64 kvmhv_get_l2_to_l1_cs_time(void);
+u64 kvmhv_get_l2_runtime_agg(void);
+u64 kvmhv_get_l1_to_l2_cs_time_vcpu(void);
+u64 kvmhv_get_l2_to_l1_cs_time_vcpu(void);
+u64 kvmhv_get_l2_runtime_agg_vcpu(void);
+
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index a36797938620..3435fe144908 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -20,7 +20,7 @@
 /* Maximum number of subcores per physical core */
 #define MAX_SUBCORES		4
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
 
@@ -58,7 +58,7 @@ kvmppc_resume_\intno:
 
 #endif /* CONFIG_KVM_BOOK3S_HANDLER */
 
-#else  /*__ASSEMBLY__ */
+#else  /*__ASSEMBLER__ */
 
 struct kvmppc_vcore;
 
@@ -150,7 +150,7 @@ struct kvmppc_book3s_shadow_vcpu {
 #endif
 };
 
-#endif /*__ASSEMBLY__ */
+#endif /*__ASSEMBLER__ */
 
 /* Values for kvm_state */
 #define KVM_HWTHREAD_IN_KERNEL	0
diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h
index 0c3401b2e19e..7c3291aa8922 100644
--- a/arch/powerpc/include/asm/kvm_booke.h
+++ b/arch/powerpc/include/asm/kvm_booke.h
@@ -89,6 +89,16 @@ static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 	return vcpu->arch.regs.nip;
 }
 
+static inline void kvmppc_set_fpr(struct kvm_vcpu *vcpu, int i, u64 val)
+{
+	vcpu->arch.fp.fpr[i][TS_FPROFFSET] = val;
+}
+
+static inline u64 kvmppc_get_fpr(struct kvm_vcpu *vcpu, int i)
+{
+	return vcpu->arch.fp.fpr[i][TS_FPROFFSET];
+}
+
 #ifdef CONFIG_BOOKE
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/powerpc/include/asm/kvm_booke_hv_asm.h b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
index 7487ef582121..3acf2995d364 100644
--- a/arch/powerpc/include/asm/kvm_booke_hv_asm.h
+++ b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
@@ -8,7 +8,7 @@
 
 #include <asm/feature-fixups.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 /*
  * All exceptions from guest state must go through KVM
@@ -64,5 +64,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 #endif
 .endm
 
-#endif /*__ASSEMBLY__ */
+#endif /*__ASSEMBLER__ */
 #endif /* ASM_KVM_BOOKE_HV_ASM_H */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 14ee0dece853..2d139c807577 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -25,6 +25,7 @@
 #include <asm/cacheflush.h>
 #include <asm/hvcall.h>
 #include <asm/mce.h>
+#include <asm/guest-state-buffer.h>
 
 #define __KVM_HAVE_ARCH_VCPU_DEBUGFS
 
@@ -62,8 +63,6 @@
 
 #include <linux/mmu_notifier.h>
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 #define HPTEG_CACHE_NUM			(1 << 15)
 #define HPTEG_HASH_BITS_PTE		13
 #define HPTEG_HASH_BITS_PTE_LONG	12
@@ -276,7 +275,7 @@ struct kvm_resize_hpt;
 #define KVMPPC_SECURE_INIT_ABORT 0x4 /* H_SVM_INIT_ABORT issued */
 
 struct kvm_arch {
-	unsigned int lpid;
+	u64 lpid;
 	unsigned int smt_mode;		/* # vcpus per virtual core */
 	unsigned int emul_smt_mode;	/* emualted SMT mode, on P9 */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -509,6 +508,23 @@ union xive_tma_w01 {
 	__be64 w01;
 };
 
+ /* Nestedv2 H_GUEST_RUN_VCPU configuration */
+struct kvmhv_nestedv2_config {
+	struct kvmppc_gs_buff_info vcpu_run_output_cfg;
+	struct kvmppc_gs_buff_info vcpu_run_input_cfg;
+	u64 vcpu_run_output_size;
+};
+
+ /* Nestedv2 L1<->L0 communication state */
+struct kvmhv_nestedv2_io {
+	struct kvmhv_nestedv2_config cfg;
+	struct kvmppc_gs_buff *vcpu_run_output;
+	struct kvmppc_gs_buff *vcpu_run_input;
+	struct kvmppc_gs_msg *vcpu_message;
+	struct kvmppc_gs_msg *vcore_message;
+	struct kvmppc_gs_bitmap valids;
+};
+
 struct kvm_vcpu_arch {
 	ulong host_stack;
 	u32 host_pid;
@@ -583,6 +599,9 @@ struct kvm_vcpu_arch {
 	ulong dawrx0;
 	ulong dawr1;
 	ulong dawrx1;
+	ulong dexcr;
+	ulong hashkeyr;
+	ulong hashpkeyr;
 	ulong ciabr;
 	ulong cfar;
 	ulong ppr;
@@ -829,6 +848,8 @@ struct kvm_vcpu_arch {
 	u64 nested_hfscr;	/* HFSCR that the L1 requested for the nested guest */
 	u32 nested_vcpu_id;
 	gpa_t nested_io_gpr;
+	/* For nested APIv2 guests*/
+	struct kvmhv_nestedv2_io nestedv2_io;
 #endif
 
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
@@ -850,6 +871,11 @@ struct kvm_vcpu_arch {
 	struct kvmhv_tb_accumulator cede_time;	/* time napping inside guest */
 #endif
 #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	u64 l1_to_l2_cs;
+	u64 l2_to_l1_cs;
+	u64 l2_runtime_agg;
+#endif
 };
 
 #define VCPU_FPR(vcpu, i)	(vcpu)->arch.fp.fpr[i][TS_FPROFFSET]
@@ -876,10 +902,8 @@ struct kvm_vcpu_arch {
 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE
 
-static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
 static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 79a9c0bb8bba..0953f2daa466 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -287,7 +287,6 @@ struct kvmppc_ops {
 	bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range);
 	bool (*age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
 	bool (*test_age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
-	bool (*set_spte_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
 	void (*free_memslot)(struct kvm_memory_slot *slot);
 	int (*init_vm)(struct kvm *kvm);
 	void (*destroy_vm)(struct kvm *kvm);
@@ -548,12 +547,12 @@ static inline void kvmppc_set_host_ipi(int cpu)
 	 * pairs with the barrier in kvmppc_clear_host_ipi()
 	 */
 	smp_mb();
-	paca_ptrs[cpu]->kvm_hstate.host_ipi = 1;
+	WRITE_ONCE(paca_ptrs[cpu]->kvm_hstate.host_ipi, 1);
 }
 
 static inline void kvmppc_clear_host_ipi(int cpu)
 {
-	paca_ptrs[cpu]->kvm_hstate.host_ipi = 0;
+	WRITE_ONCE(paca_ptrs[cpu]->kvm_hstate.host_ipi, 0);
 	/*
 	 * order clearing of host_ipi flag vs. processing of IPI messages
 	 *
@@ -615,6 +614,42 @@ static inline bool kvmhv_on_pseries(void)
 {
 	return false;
 }
+
+#endif
+
+#ifndef CONFIG_PPC_BOOK3S
+
+static inline bool kvmhv_is_nestedv2(void)
+{
+	return false;
+}
+
+static inline bool kvmhv_is_nestedv1(void)
+{
+	return false;
+}
+
+static inline int kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu,
+					       struct pt_regs *regs)
+{
+	return 0;
+}
+static inline int kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu,
+						   struct pt_regs *regs)
+{
+	return 0;
+}
+
+static inline int kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden)
+{
+	return 0;
+}
+
+static inline int kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden)
+{
+	return 0;
+}
+
 #endif
 
 #ifdef CONFIG_KVM_XICS
@@ -894,7 +929,7 @@ void kvmppc_init_lpid(unsigned long nr_lpids);
 
 static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
 {
-	struct page *page;
+	struct folio *folio;
 	/*
 	 * We can only access pages that the kernel maps
 	 * as memory. Bail out for unmapped ones.
@@ -903,10 +938,10 @@ static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn)
 		return;
 
 	/* Clear i-cache for new pages */
-	page = pfn_to_page(pfn);
-	if (!test_bit(PG_dcache_clean, &page->flags)) {
-		flush_dcache_icache_page(page);
-		set_bit(PG_dcache_clean, &page->flags);
+	folio = page_folio(pfn_to_page(pfn));
+	if (!test_bit(PG_dcache_clean, &folio->flags.f)) {
+		flush_dcache_icache_folio(folio);
+		set_bit(PG_dcache_clean, &folio->flags.f);
 	}
 }
 
@@ -927,79 +962,85 @@ static inline bool kvmppc_shared_big_endian(struct kvm_vcpu *vcpu)
 #endif
 }
 
-#define SPRNG_WRAPPER_GET(reg, bookehv_spr)				\
+#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_GET(reg, bookehv_spr)		\
 static inline ulong kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
 {									\
 	return mfspr(bookehv_spr);					\
 }									\
 
-#define SPRNG_WRAPPER_SET(reg, bookehv_spr)				\
+#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_SET(reg, bookehv_spr)		\
 static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, ulong val)	\
 {									\
 	mtspr(bookehv_spr, val);						\
 }									\
 
-#define SHARED_WRAPPER_GET(reg, size)					\
+#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(reg, size, iden)		\
 static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu)		\
 {									\
+	if (iden)							\
+		WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden) < 0);	\
 	if (kvmppc_shared_big_endian(vcpu))				\
-	       return be##size##_to_cpu(vcpu->arch.shared->reg);	\
+		return be##size##_to_cpu((__be##size __force)vcpu->arch.shared->reg);	\
 	else								\
-	       return le##size##_to_cpu(vcpu->arch.shared->reg);	\
+		return le##size##_to_cpu((__le##size __force)vcpu->arch.shared->reg);	\
 }									\
 
-#define SHARED_WRAPPER_SET(reg, size)					\
+#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR_SET(reg, size, iden)		\
 static inline void kvmppc_set_##reg(struct kvm_vcpu *vcpu, u##size val)	\
 {									\
 	if (kvmppc_shared_big_endian(vcpu))				\
-	       vcpu->arch.shared->reg = cpu_to_be##size(val);		\
+		vcpu->arch.shared->reg = (u##size __force)cpu_to_be##size(val);	\
 	else								\
-	       vcpu->arch.shared->reg = cpu_to_le##size(val);		\
+		vcpu->arch.shared->reg = (u##size __force)cpu_to_le##size(val);	\
+									\
+	if (iden)							\
+		kvmhv_nestedv2_mark_dirty(vcpu, iden);			\
 }									\
 
-#define SHARED_WRAPPER(reg, size)					\
-	SHARED_WRAPPER_GET(reg, size)					\
-	SHARED_WRAPPER_SET(reg, size)					\
+#define KVMPPC_VCPU_SHARED_REGS_ACCESSOR(reg, size, iden)		\
+	KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(reg, size, iden)		\
+	KVMPPC_VCPU_SHARED_REGS_ACCESSOR_SET(reg, size, iden)		\
 
-#define SPRNG_WRAPPER(reg, bookehv_spr)					\
-	SPRNG_WRAPPER_GET(reg, bookehv_spr)				\
-	SPRNG_WRAPPER_SET(reg, bookehv_spr)				\
+#define KVMPPC_BOOKE_HV_SPRNG_ACCESSOR(reg, bookehv_spr)		\
+	KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_GET(reg, bookehv_spr)		\
+	KVMPPC_BOOKE_HV_SPRNG_ACCESSOR_SET(reg, bookehv_spr)		\
 
 #ifdef CONFIG_KVM_BOOKE_HV
 
-#define SHARED_SPRNG_WRAPPER(reg, size, bookehv_spr)			\
-	SPRNG_WRAPPER(reg, bookehv_spr)					\
+#define KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(reg, size, bookehv_spr, iden)	\
+	KVMPPC_BOOKE_HV_SPRNG_ACCESSOR(reg, bookehv_spr)		\
 
 #else
 
-#define SHARED_SPRNG_WRAPPER(reg, size, bookehv_spr)			\
-	SHARED_WRAPPER(reg, size)					\
+#define KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(reg, size, bookehv_spr, iden)	\
+	KVMPPC_VCPU_SHARED_REGS_ACCESSOR(reg, size, iden)		\
 
 #endif
 
-SHARED_WRAPPER(critical, 64)
-SHARED_SPRNG_WRAPPER(sprg0, 64, SPRN_GSPRG0)
-SHARED_SPRNG_WRAPPER(sprg1, 64, SPRN_GSPRG1)
-SHARED_SPRNG_WRAPPER(sprg2, 64, SPRN_GSPRG2)
-SHARED_SPRNG_WRAPPER(sprg3, 64, SPRN_GSPRG3)
-SHARED_SPRNG_WRAPPER(srr0, 64, SPRN_GSRR0)
-SHARED_SPRNG_WRAPPER(srr1, 64, SPRN_GSRR1)
-SHARED_SPRNG_WRAPPER(dar, 64, SPRN_GDEAR)
-SHARED_SPRNG_WRAPPER(esr, 64, SPRN_GESR)
-SHARED_WRAPPER_GET(msr, 64)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(critical, 64, 0)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg0, 64, SPRN_GSPRG0, KVMPPC_GSID_SPRG0)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg1, 64, SPRN_GSPRG1, KVMPPC_GSID_SPRG1)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg2, 64, SPRN_GSPRG2, KVMPPC_GSID_SPRG2)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(sprg3, 64, SPRN_GSPRG3, KVMPPC_GSID_SPRG3)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(srr0, 64, SPRN_GSRR0, KVMPPC_GSID_SRR0)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(srr1, 64, SPRN_GSRR1, KVMPPC_GSID_SRR1)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(dar, 64, SPRN_GDEAR, KVMPPC_GSID_DAR)
+KVMPPC_BOOKE_HV_SPRNG_OR_VCPU_SHARED_REGS_ACCESSOR(esr, 64, SPRN_GESR, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR_GET(msr, 64, KVMPPC_GSID_MSR)
 static inline void kvmppc_set_msr_fast(struct kvm_vcpu *vcpu, u64 val)
 {
 	if (kvmppc_shared_big_endian(vcpu))
 	       vcpu->arch.shared->msr = cpu_to_be64(val);
 	else
 	       vcpu->arch.shared->msr = cpu_to_le64(val);
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_MSR);
 }
-SHARED_WRAPPER(dsisr, 32)
-SHARED_WRAPPER(int_pending, 32)
-SHARED_WRAPPER(sprg4, 64)
-SHARED_WRAPPER(sprg5, 64)
-SHARED_WRAPPER(sprg6, 64)
-SHARED_WRAPPER(sprg7, 64)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(dsisr, 32, KVMPPC_GSID_DSISR)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(int_pending, 32, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg4, 64, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg5, 64, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg6, 64, 0)
+KVMPPC_VCPU_SHARED_REGS_ACCESSOR(sprg7, 64, 0)
 
 static inline u32 kvmppc_get_sr(struct kvm_vcpu *vcpu, int nr)
 {
diff --git a/arch/powerpc/include/asm/kvm_types.h b/arch/powerpc/include/asm/kvm_types.h
new file mode 100644
index 000000000000..5d4bffea7d47
--- /dev/null
+++ b/arch/powerpc/include/asm/kvm_types.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_PPC_KVM_TYPES_H
+#define _ASM_PPC_KVM_TYPES_H
+
+#if IS_MODULE(CONFIG_KVM_BOOK3S_64_PR) && IS_MODULE(CONFIG_KVM_BOOK3S_64_HV)
+#define KVM_SUB_MODULES kvm-pr,kvm-hv
+#elif IS_MODULE(CONFIG_KVM_BOOK3S_64_PR)
+#define KVM_SUB_MODULES kvm-pr
+#elif IS_MODULE(CONFIG_KVM_BOOK3S_64_HV)
+#define KVM_SUB_MODULES kvm-hv
+#else
+#undef KVM_SUB_MODULES
+#endif
+
+#endif
diff --git a/arch/powerpc/include/asm/linkage.h b/arch/powerpc/include/asm/linkage.h
index b88d1d2cf304..b71b9582e754 100644
--- a/arch/powerpc/include/asm/linkage.h
+++ b/arch/powerpc/include/asm/linkage.h
@@ -4,9 +4,6 @@
 
 #include <asm/types.h>
 
-#define __ALIGN		.align 2
-#define __ALIGN_STR	".align 2"
-
 #ifdef CONFIG_PPC64_ELF_ABI_V1
 #define cond_syscall(x) \
 	asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n"		\
diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h
index 45492fb5bf22..ec6ced6d7ced 100644
--- a/arch/powerpc/include/asm/local.h
+++ b/arch/powerpc/include/asm/local.h
@@ -115,23 +115,23 @@ static __inline__ long local_xchg(local_t *l, long n)
 }
 
 /**
- * local_add_unless - add unless the number is a given value
+ * local_add_unless - add unless the number is already a given value
  * @l: pointer of type local_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
+ * Atomically adds @a to @l, if @v was not already @u.
+ * Returns true if the addition was done.
  */
-static __inline__ int local_add_unless(local_t *l, long a, long u)
+static __inline__ bool local_add_unless(local_t *l, long a, long u)
 {
 	unsigned long flags;
-	int ret = 0;
+	bool ret = false;
 
 	powerpc_local_irq_pmu_save(flags);
 	if (l->v != u) {
 		l->v += a;
-		ret = 1;
+		ret = true;
 	}
 	powerpc_local_irq_pmu_restore(flags);
 
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 34d44cb17c87..f40a646bee3c 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -6,28 +6,6 @@
 #ifndef _ASM_POWERPC_LPPACA_H
 #define _ASM_POWERPC_LPPACA_H
 
-/*
- * The below VPHN macros are outside the __KERNEL__ check since these are
- * used for compiling the vphn selftest in userspace
- */
-
-/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. */
-#define VPHN_REGISTER_COUNT 6
-
-/*
- * 6 64-bit registers unpacked into up to 24 be32 associativity values. To
- * form the complete property we have to add the length in the first cell.
- */
-#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1)
-
-/*
- * The H_HOME_NODE_ASSOCIATIVITY hcall takes two values for flags:
- * 1 for retrieving associativity information for a guest cpu
- * 2 for retrieving associativity information for a host/hypervisor cpu
- */
-#define VPHN_FLAG_VCPU	1
-#define VPHN_FLAG_PCPU	2
-
 #ifdef __KERNEL__
 
 /*
@@ -45,6 +23,7 @@
 #include <asm/types.h>
 #include <asm/mmu.h>
 #include <asm/firmware.h>
+#include <asm/paca.h>
 
 /*
  * The lppaca is the "virtual processor area" registered with the hypervisor,
@@ -83,7 +62,8 @@ struct lppaca {
 	u8	donate_dedicated_cpu;	/* Donate dedicated CPU cycles */
 	u8	fpregs_in_use;
 	u8	pmcregs_in_use;
-	u8	reserved8[28];
+	u8	l2_counters_enable;  /* Enable usage of counters for KVM guest */
+	u8	reserved8[27];
 	__be64	wait_state_cycles;	/* Wait cycles for this proc */
 	u8	reserved9[28];
 	__be16	slb_count;		/* # of SLBs to maintain */
@@ -113,9 +93,13 @@ struct lppaca {
 	/* cacheline 4-5 */
 
 	__be32	page_ins;		/* CMO Hint - # page ins by OS */
-	u8	reserved12[148];
+	u8	reserved12[28];
+	volatile __be64 l1_to_l2_cs_tb;
+	volatile __be64 l2_to_l1_cs_tb;
+	volatile __be64 l2_runtime_tb;
+	u8 reserved13[96];
 	volatile __be64 dtl_idx;	/* Dispatch Trace Log head index */
-	u8	reserved13[96];
+	u8	reserved14[96];
 } ____cacheline_aligned;
 
 #define lppaca_of(cpu)	(*paca_ptrs[cpu]->lppaca_ptr)
@@ -127,13 +111,23 @@ struct lppaca {
  */
 #define LPPACA_OLD_SHARED_PROC		2
 
-static inline bool lppaca_shared_proc(struct lppaca *l)
+#ifdef CONFIG_PPC_PSERIES
+/*
+ * All CPUs should have the same shared proc value, so directly access the PACA
+ * to avoid false positives from DEBUG_PREEMPT.
+ */
+static inline bool lppaca_shared_proc(void)
 {
+	struct lppaca *l = local_paca->lppaca_ptr;
+
 	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
 		return false;
 	return !!(l->__old_status & LPPACA_OLD_SHARED_PROC);
 }
 
+#define get_lppaca()	(get_paca()->lppaca_ptr)
+#endif
+
 /*
  * SLB shadow buffer structure as defined in the PAPR.  The save_area
  * contains adjacent ESID and VSID pairs for each shadowed SLB.  The
@@ -149,8 +143,6 @@ struct slb_shadow {
 	} save_area[SLB_NUM_BOLTED];
 } ____cacheline_aligned;
 
-extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity);
-
 #endif /* CONFIG_PPC_BOOK3S */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_LPPACA_H */
diff --git a/arch/powerpc/include/asm/lv1call.h b/arch/powerpc/include/asm/lv1call.h
index b11501b30193..ae70120953a8 100644
--- a/arch/powerpc/include/asm/lv1call.h
+++ b/arch/powerpc/include/asm/lv1call.h
@@ -10,7 +10,7 @@
 #if !defined(_ASM_POWERPC_LV1CALL_H)
 #define _ASM_POWERPC_LV1CALL_H
 
-#if !defined(__ASSEMBLY__)
+#if !defined(__ASSEMBLER__)
 
 #include <linux/types.h>
 #include <linux/export.h>
@@ -211,7 +211,7 @@
     {return _lv1_##name(LV1_##in##_IN_##out##_OUT_ARGS);}
 #endif
 
-#endif /* !defined(__ASSEMBLY__) */
+#endif /* !defined(__ASSEMBLER__) */
 
 /* lv1 call table */
 
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 4f6e7d7ee388..3298eec123a3 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -4,24 +4,29 @@
 #ifdef __KERNEL__
 
 #include <linux/compiler.h>
-#include <linux/seq_file.h>
 #include <linux/init.h>
-#include <linux/dma-mapping.h>
 #include <linux/export.h>
+#include <linux/time64.h>
+
+#include <asm/page.h>
 
 struct pt_regs;
-struct pci_bus;	
+struct pci_bus;
+struct device;
 struct device_node;
 struct iommu_table;
 struct rtc_time;
 struct file;
+struct pci_dev;
 struct pci_controller;
 struct kimage;
 struct pci_host_bridge;
+struct seq_file;
 
 struct machdep_calls {
 	const char	*name;
 	const char	*compatible;
+	const char * const *compatibles;
 #ifdef CONFIG_PPC64
 #ifdef CONFIG_PM
 	void		(*iommu_restore)(void);
@@ -78,8 +83,8 @@ struct machdep_calls {
 	unsigned char 	(*nvram_read_val)(int addr);
 	void		(*nvram_write_val)(int addr, unsigned char val);
 	ssize_t		(*nvram_write)(char *buf, size_t count, loff_t *index);
-	ssize_t		(*nvram_read)(char *buf, size_t count, loff_t *index);	
-	ssize_t		(*nvram_size)(void);		
+	ssize_t		(*nvram_read)(char *buf, size_t count, loff_t *index);
+	ssize_t		(*nvram_size)(void);
 	void		(*nvram_sync)(void);
 
 	/* Exception handlers */
@@ -102,12 +107,11 @@ struct machdep_calls {
 	 */
 	long	 	(*feature_call)(unsigned int feature, ...);
 
-	/* Get legacy PCI/IDE interrupt mapping */ 
+	/* Get legacy PCI/IDE interrupt mapping */
 	int		(*pci_get_legacy_ide_irq)(struct pci_dev *dev, int channel);
-	
+
 	/* Get access protection for /dev/mem */
-	pgprot_t	(*phys_mem_access_prot)(struct file *file,
-						unsigned long pfn,
+	pgprot_t	(*phys_mem_access_prot)(unsigned long pfn,
 						unsigned long size,
 						pgprot_t vma_prot);
 
diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h
index ff5fd82d9ff0..9203ff6acbf6 100644
--- a/arch/powerpc/include/asm/macio.h
+++ b/arch/powerpc/include/asm/macio.h
@@ -3,9 +3,10 @@
 #define __MACIO_ASIC_H__
 #ifdef __KERNEL__
 
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 
-extern struct bus_type macio_bus_type;
+extern const struct bus_type macio_bus_type;
 
 /* MacIO device driver is defined later */
 struct macio_driver;
@@ -125,7 +126,7 @@ static inline struct pci_dev *macio_get_pci_dev(struct macio_dev *mdev)
 struct macio_driver
 {
 	int	(*probe)(struct macio_dev* dev, const struct of_device_id *match);
-	int	(*remove)(struct macio_dev* dev);
+	void	(*remove)(struct macio_dev *dev);
 
 	int	(*suspend)(struct macio_dev* dev, pm_message_t state);
 	int	(*resume)(struct macio_dev* dev);
diff --git a/arch/powerpc/include/asm/mem_encrypt.h b/arch/powerpc/include/asm/mem_encrypt.h
index 2f26b8fc8d29..e355ca46fad9 100644
--- a/arch/powerpc/include/asm/mem_encrypt.h
+++ b/arch/powerpc/include/asm/mem_encrypt.h
@@ -9,6 +9,9 @@
 #define _ASM_POWERPC_MEM_ENCRYPT_H
 
 #include <asm/svm.h>
+#include <linux/types.h>
+
+struct device;
 
 static inline bool force_dma_unencrypted(struct device *dev)
 {
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 17a77d47ed6d..912f78a956a1 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -6,7 +6,7 @@
 
 #include <uapi/asm/mman.h>
 
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) && !defined(BUILD_VDSO)
 
 #include <asm/cputable.h>
 #include <linux/mm.h>
@@ -14,7 +14,7 @@
 #include <asm/cpu_has_feature.h>
 #include <asm/firmware.h>
 
-static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
+static inline vm_flags_t arch_calc_vm_prot_bits(unsigned long prot,
 		unsigned long pkey)
 {
 #ifdef CONFIG_PPC_MEM_KEYS
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 94b981152667..5f9c5d436e17 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -16,7 +16,6 @@
  */
 #define MMU_FTR_HPTE_TABLE		ASM_CONST(0x00000001)
 #define MMU_FTR_TYPE_8xx		ASM_CONST(0x00000002)
-#define MMU_FTR_TYPE_40x		ASM_CONST(0x00000004)
 #define MMU_FTR_TYPE_44x		ASM_CONST(0x00000008)
 #define MMU_FTR_TYPE_FSL_E		ASM_CONST(0x00000010)
 #define MMU_FTR_TYPE_47x		ASM_CONST(0x00000020)
@@ -33,7 +32,7 @@
  * key 0 controlling userspace addresses on radix
  * Key 3 on hash
  */
-#define MMU_FTR_BOOK3S_KUAP		ASM_CONST(0x00000200)
+#define MMU_FTR_KUAP		ASM_CONST(0x00000200)
 
 /*
  * Supports KUEP feature
@@ -133,22 +132,18 @@
 #define MMU_FTRS_POWER8		MMU_FTRS_POWER6
 #define MMU_FTRS_POWER9		MMU_FTRS_POWER6
 #define MMU_FTRS_POWER10	MMU_FTRS_POWER6
+#define MMU_FTRS_POWER11	MMU_FTRS_POWER6
 #define MMU_FTRS_CELL		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
 				MMU_FTR_CI_LARGE_PAGE
 #define MMU_FTRS_PA6T		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
 				MMU_FTR_CI_LARGE_PAGE | MMU_FTR_NO_SLBIE_B
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/bug.h>
 #include <asm/cputable.h>
 #include <asm/page.h>
 
 typedef pte_t *pgtable_t;
 
-#ifdef CONFIG_PPC_E500
-#include <asm/percpu.h>
-DECLARE_PER_CPU(int, next_tlbcam_idx);
-#endif
-
 enum {
 	MMU_FTRS_POSSIBLE =
 #if defined(CONFIG_PPC_BOOK3S_604)
@@ -157,9 +152,6 @@ enum {
 #ifdef CONFIG_PPC_8xx
 		MMU_FTR_TYPE_8xx |
 #endif
-#ifdef CONFIG_40x
-		MMU_FTR_TYPE_40x |
-#endif
 #ifdef CONFIG_PPC_47x
 		MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL |
 #elif defined(CONFIG_44x)
@@ -188,7 +180,7 @@ enum {
 #endif /* CONFIG_PPC_RADIX_MMU */
 #endif
 #ifdef CONFIG_PPC_KUAP
-	MMU_FTR_BOOK3S_KUAP |
+	MMU_FTR_KUAP |
 #endif /* CONFIG_PPC_KUAP */
 #ifdef CONFIG_PPC_MEM_KEYS
 	MMU_FTR_PKEY |
@@ -206,9 +198,6 @@ enum {
 #ifdef CONFIG_PPC_8xx
 #define MMU_FTRS_ALWAYS		MMU_FTR_TYPE_8xx
 #endif
-#ifdef CONFIG_40x
-#define MMU_FTRS_ALWAYS		MMU_FTR_TYPE_40x
-#endif
 #ifdef CONFIG_PPC_47x
 #define MMU_FTRS_ALWAYS		MMU_FTR_TYPE_47x
 #elif defined(CONFIG_44x)
@@ -250,12 +239,11 @@ static __always_inline bool mmu_has_feature(unsigned long feature)
 {
 	int i;
 
-#ifndef __clang__ /* clang can't cope with this */
 	BUILD_BUG_ON(!__builtin_constant_p(feature));
-#endif
+	BUILD_BUG_ON(__builtin_popcountl(feature) > 1);
 
 #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
-	if (!static_key_initialized) {
+	if (!static_key_feature_checks_initialized) {
 		printk("Warning! mmu_has_feature() used prior to jump label init!\n");
 		dump_stack();
 		return early_mmu_has_feature(feature);
@@ -335,23 +323,16 @@ static __always_inline bool early_radix_enabled(void)
 	return early_mmu_has_feature(MMU_FTR_TYPE_RADIX);
 }
 
-#ifdef CONFIG_STRICT_KERNEL_RWX
 static inline bool strict_kernel_rwx_enabled(void)
 {
-	return rodata_enabled;
+	return IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && rodata_enabled;
 }
-#else
-static inline bool strict_kernel_rwx_enabled(void)
-{
-	return false;
-}
-#endif
 
 static inline bool strict_module_rwx_enabled(void)
 {
 	return IS_ENABLED(CONFIG_STRICT_MODULE_RWX) && strict_kernel_rwx_enabled();
 }
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* The kernel use the constants below to index in the page sizes array.
  * The use of fixed constants for this purpose is better for performances
@@ -396,7 +377,7 @@ static inline bool strict_module_rwx_enabled(void)
 #include <asm/book3s/64/mmu.h>
 #else /* CONFIG_PPC_BOOK3S_64 */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /* MMU initialization */
 extern void early_init_mmu(void);
 extern void early_init_mmu_secondary(void);
@@ -407,7 +388,7 @@ static inline void mmu_early_init_devtree(void) { }
 static inline void pkey_early_init_devtree(void) {}
 
 extern void *abatron_pteptrs[2];
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif
 
 #if defined(CONFIG_PPC_BOOK3S_32)
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 57f5017111f4..a157ab513347 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -116,9 +116,6 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
 }
 #endif
 
-extern int use_cop(unsigned long acop, struct mm_struct *mm);
-extern void drop_cop(unsigned long acop, struct mm_struct *mm);
-
 #ifdef CONFIG_PPC_BOOK3S_64
 static inline void inc_mm_active_cpus(struct mm_struct *mm)
 {
@@ -127,6 +124,7 @@ static inline void inc_mm_active_cpus(struct mm_struct *mm)
 
 static inline void dec_mm_active_cpus(struct mm_struct *mm)
 {
+	VM_WARN_ON_ONCE(atomic_read(&mm->context.active_cpus) <= 0);
 	atomic_dec(&mm->context.active_cpus);
 }
 
@@ -259,15 +257,6 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
 
 extern void arch_exit_mmap(struct mm_struct *mm);
 
-static inline void arch_unmap(struct mm_struct *mm,
-			      unsigned long start, unsigned long end)
-{
-	unsigned long vdso_base = (unsigned long)mm->context.vdso;
-
-	if (start <= vdso_base && vdso_base < end)
-		mm->context.vdso = NULL;
-}
-
 #ifdef CONFIG_PPC_MEM_KEYS
 bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
 			       bool execute, bool foreign);
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index 4c6c6dbd182f..049152f8d597 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -20,12 +20,6 @@
 
 #ifdef CONFIG_NUMA
 
-extern struct pglist_data *node_data[];
-/*
- * Return a pointer to the node data for node n.
- */
-#define NODE_DATA(nid)		(node_data[nid])
-
 /*
  * Following are specific to this numa platform.
  */
@@ -35,6 +29,7 @@ extern cpumask_var_t node_to_cpumask_map[];
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern unsigned long max_pfn;
 u64 memory_hotplug_max(void);
+u64 hot_add_drconf_memory_max(void);
 #else
 #define memory_hotplug_max() memblock_end_of_DRAM()
 #endif
@@ -42,14 +37,6 @@ u64 memory_hotplug_max(void);
 #else
 #define memory_hotplug_max() memblock_end_of_DRAM()
 #endif /* CONFIG_NUMA */
-#ifdef CONFIG_FA_DUMP
-#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
-#endif
-
-#ifdef CONFIG_MEMORY_HOTPLUG
-extern int create_section_mapping(unsigned long start, unsigned long end,
-				  int nid, pgprot_t prot);
-#endif
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_MMZONE_H_ */
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index ac53606c2594..864e22deaa2c 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -27,6 +27,7 @@ struct ppc_plt_entry {
 struct mod_arch_specific {
 #ifdef __powerpc64__
 	unsigned int stubs_section;	/* Index of stubs section in module */
+	unsigned int stub_count;	/* Number of stubs used */
 #ifdef CONFIG_PPC_KERNEL_PCREL
 	unsigned int got_section;	/* What section is the GOT? */
 	unsigned int pcpu_section;	/* .data..percpu section */
@@ -35,9 +36,11 @@ struct mod_arch_specific {
 	bool toc_fixed;			/* Have we fixed up .TOC.? */
 #endif
 
+#ifdef CONFIG_PPC64_ELF_ABI_V1
 	/* For module function descriptor dereference */
 	unsigned long start_opd;
 	unsigned long end_opd;
+#endif
 #else /* powerpc64 */
 	/* Indices of PLT sections within module. */
 	unsigned int core_plt_section;
@@ -47,12 +50,12 @@ struct mod_arch_specific {
 #ifdef CONFIG_DYNAMIC_FTRACE
 	unsigned long tramp;
 	unsigned long tramp_regs;
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	struct ftrace_ool_stub *ool_stubs;
+	unsigned int ool_stub_count;
+	unsigned int ool_stub_index;
+#endif
 #endif
-
-	/* List of BUG addresses, source line numbers and filenames */
-	struct list_head bug_list;
-	struct bug_entry *bug_table;
-	unsigned int num_bugs;
 };
 
 /*
@@ -75,10 +78,6 @@ struct mod_arch_specific {
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-#    ifdef MODULE
-	asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous");
-#    endif	/* MODULE */
-
 int module_trampoline_target(struct module *mod, unsigned long trampoline,
 			     unsigned long *target);
 int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs);
diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h
index 5ea16a71c2f0..d7ffbd06797d 100644
--- a/arch/powerpc/include/asm/mpc52xx.h
+++ b/arch/powerpc/include/asm/mpc52xx.h
@@ -13,10 +13,10 @@
 #ifndef __ASM_POWERPC_MPC52xx_H__
 #define __ASM_POWERPC_MPC52xx_H__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/types.h>
 #include <asm/mpc5xxx.h>
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #include <linux/suspend.h>
 
@@ -30,7 +30,7 @@
 /* Structures mapping of some unit register set                             */
 /* ======================================================================== */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /* Memory Mapping Control */
 struct mpc52xx_mmap_ctl {
@@ -258,14 +258,14 @@ struct mpc52xx_intr {
 	u32 per_error;		/* INTR + 0x38 */
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 
 /* ========================================================================= */
 /* Prototypes for MPC52xx sysdev                                             */
 /* ========================================================================= */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct device_node;
 
@@ -285,47 +285,6 @@ extern int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period,
 extern u64 mpc52xx_gpt_timer_period(struct mpc52xx_gpt_priv *gpt);
 extern int mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt);
 
-/* mpc52xx_lpbfifo.c */
-#define MPC52XX_LPBFIFO_FLAG_READ		(0)
-#define MPC52XX_LPBFIFO_FLAG_WRITE		(1<<0)
-#define MPC52XX_LPBFIFO_FLAG_NO_INCREMENT	(1<<1)
-#define MPC52XX_LPBFIFO_FLAG_NO_DMA		(1<<2)
-#define MPC52XX_LPBFIFO_FLAG_POLL_DMA		(1<<3)
-
-struct mpc52xx_lpbfifo_request {
-	struct list_head list;
-
-	/* localplus bus address */
-	unsigned int cs;
-	size_t offset;
-
-	/* Memory address */
-	void *data;
-	phys_addr_t data_phys;
-
-	/* Details of transfer */
-	size_t size;
-	size_t pos;	/* current position of transfer */
-	int flags;
-	int defer_xfer_start;
-
-	/* What to do when finished */
-	void (*callback)(struct mpc52xx_lpbfifo_request *);
-
-	void *priv;		/* Driver private data */
-
-	/* statistics */
-	int irq_count;
-	int irq_ticks;
-	u8 last_byte;
-	int buffer_not_done_cnt;
-};
-
-extern int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req);
-extern void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req);
-extern void mpc52xx_lpbfifo_poll(void);
-extern int mpc52xx_lpbfifo_start_xfer(struct mpc52xx_lpbfifo_request *req);
-
 /* mpc52xx_pic.c */
 extern void mpc52xx_init_irq(void);
 extern unsigned int mpc52xx_get_irq(void);
@@ -338,7 +297,7 @@ extern void __init mpc52xx_setup_pci(void);
 static inline void mpc52xx_setup_pci(void) { }
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #ifdef CONFIG_PM
 struct mpc52xx_suspend {
diff --git a/arch/powerpc/include/asm/mpc8260.h b/arch/powerpc/include/asm/mpc8260.h
deleted file mode 100644
index 155114bbd1a2..000000000000
--- a/arch/powerpc/include/asm/mpc8260.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Since there are many different boards and no standard configuration,
- * we have a unique include file for each.  Rather than change every
- * file that has to include MPC8260 configuration, they all include
- * this one and the configuration switching is done here.
- */
-#ifdef __KERNEL__
-#ifndef __ASM_POWERPC_MPC8260_H__
-#define __ASM_POWERPC_MPC8260_H__
-
-#define MPC82XX_BCR_PLDP 0x00800000 /* Pipeline Maximum Depth */
-
-#ifdef CONFIG_8260
-
-#ifdef CONFIG_PCI_8260
-#include <platforms/82xx/m82xx_pci.h>
-#endif
-
-#endif /* CONFIG_8260 */
-#endif /* !__ASM_POWERPC_MPC8260_H__ */
-#endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index 58353c5bd3fb..0c03a98986cd 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -336,7 +336,7 @@ struct mpic
 #endif
 };
 
-extern struct bus_type mpic_subsys;
+extern const struct bus_type mpic_subsys;
 
 /*
  * MPIC flags (passed to mpic_alloc)
diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h
index c3c7adef74de..49a75340c3e0 100644
--- a/arch/powerpc/include/asm/nmi.h
+++ b/arch/powerpc/include/asm/nmi.h
@@ -3,18 +3,10 @@
 #define _ASM_NMI_H
 
 #ifdef CONFIG_PPC_WATCHDOG
-extern void arch_touch_nmi_watchdog(void);
 long soft_nmi_interrupt(struct pt_regs *regs);
-void watchdog_nmi_set_timeout_pct(u64 pct);
+void watchdog_hardlockup_set_timeout_pct(u64 pct);
 #else
-static inline void arch_touch_nmi_watchdog(void) {}
-static inline void watchdog_nmi_set_timeout_pct(u64 pct) {}
-#endif
-
-#ifdef CONFIG_NMI_IPI
-extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
-					   bool exclude_self);
-#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
+static inline void watchdog_hardlockup_set_timeout_pct(u64 pct) {}
 #endif
 
 extern void hv_nmi_check_nonrecoverable(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
index de092b04ee1a..014799557f60 100644
--- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -4,49 +4,28 @@
 
 #define PAGE_SHIFT_8M		23
 
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
-	BUG_ON(!hugepd_ok(hpd));
-
-	return (pte_t *)__va(hpd_val(hpd) & ~HUGEPD_SHIFT_MASK);
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
-	return PAGE_SHIFT_8M;
-}
-
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
-				    unsigned int pdshift)
-{
-	unsigned long idx = (addr & (SZ_4M - 1)) >> PAGE_SHIFT;
-
-	return hugepd_page(hpd) + idx;
-}
-
 static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 				      unsigned long vmaddr)
 {
 	flush_tlb_page(vma, vmaddr);
 }
 
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
-	*hpdp = __hugepd(__pa(new) | _PMD_USER | _PMD_PRESENT | _PMD_PAGE_8M);
-}
-
-static inline void hugepd_populate_kernel(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
-	*hpdp = __hugepd(__pa(new) | _PMD_PRESENT | _PMD_PAGE_8M);
-}
-
 static inline int check_and_get_huge_psize(int shift)
 {
 	return shift_to_mmu_psize(shift);
 }
 
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz);
+
+#define __HAVE_ARCH_HUGE_PTEP_GET
+static inline pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	if (ptep_is_8m_pmdp(mm, addr, ptep))
+		ptep = pte_offset_kernel((pmd_t *)ptep, ALIGN_DOWN(addr, SZ_8M));
+	return ptep_get(ptep);
+}
 
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
index c44d97751723..08486b15b207 100644
--- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
@@ -7,84 +7,82 @@
 
 #ifdef CONFIG_PPC_KUAP
 
-#ifndef __ASSEMBLY__
-
-#include <linux/jump_label.h>
+#ifndef __ASSEMBLER__
 
 #include <asm/reg.h>
 
-extern struct static_key_false disable_kuap_key;
-
-static __always_inline bool kuap_is_disabled(void)
-{
-	return static_branch_unlikely(&disable_kuap_key);
-}
-
-static inline void __kuap_lock(void)
-{
-}
-
-static inline void __kuap_save_and_lock(struct pt_regs *regs)
+static __always_inline void __kuap_save_and_lock(struct pt_regs *regs)
 {
 	regs->kuap = mfspr(SPRN_MD_AP);
 	mtspr(SPRN_MD_AP, MD_APG_KUAP);
 }
+#define __kuap_save_and_lock __kuap_save_and_lock
 
-static inline void kuap_user_restore(struct pt_regs *regs)
+static __always_inline void kuap_user_restore(struct pt_regs *regs)
 {
 }
 
-static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
+static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
 {
 	mtspr(SPRN_MD_AP, regs->kuap);
 }
 
-static inline unsigned long __kuap_get_and_assert_locked(void)
+#ifdef CONFIG_PPC_KUAP_DEBUG
+static __always_inline unsigned long __kuap_get_and_assert_locked(void)
 {
-	unsigned long kuap;
+	WARN_ON_ONCE(mfspr(SPRN_MD_AP) >> 16 != MD_APG_KUAP >> 16);
 
-	kuap = mfspr(SPRN_MD_AP);
+	return 0;
+}
+#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked
+#endif
 
-	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG))
-		WARN_ON_ONCE(kuap >> 16 != MD_APG_KUAP >> 16);
+static __always_inline void uaccess_begin_8xx(unsigned long val)
+{
+	asm(ASM_MMU_FTR_IFSET("mtspr %0, %1", "", %2) : :
+	    "i"(SPRN_MD_AP), "r"(val), "i"(MMU_FTR_KUAP) : "memory");
+}
 
-	return kuap;
+static __always_inline void uaccess_end_8xx(void)
+{
+	asm(ASM_MMU_FTR_IFSET("mtspr %0, %1", "", %2) : :
+	    "i"(SPRN_MD_AP), "r"(MD_APG_KUAP), "i"(MMU_FTR_KUAP) : "memory");
 }
 
-static inline void __allow_user_access(void __user *to, const void __user *from,
-				       unsigned long size, unsigned long dir)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      unsigned long size, unsigned long dir)
 {
-	mtspr(SPRN_MD_AP, MD_APG_INIT);
+	uaccess_begin_8xx(MD_APG_INIT);
 }
 
-static inline void __prevent_user_access(unsigned long dir)
+static __always_inline void prevent_user_access(unsigned long dir)
 {
-	mtspr(SPRN_MD_AP, MD_APG_KUAP);
+	uaccess_end_8xx();
 }
 
-static inline unsigned long __prevent_user_access_return(void)
+static __always_inline unsigned long prevent_user_access_return(void)
 {
 	unsigned long flags;
 
 	flags = mfspr(SPRN_MD_AP);
 
-	mtspr(SPRN_MD_AP, MD_APG_KUAP);
+	uaccess_end_8xx();
 
 	return flags;
 }
 
-static inline void __restore_user_access(unsigned long flags)
+static __always_inline void restore_user_access(unsigned long flags)
 {
-	mtspr(SPRN_MD_AP, flags);
+	uaccess_begin_8xx(flags);
 }
 
-static inline bool
+static __always_inline bool
 __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	return !((regs->kuap ^ MD_APG_KUAP) & 0xff000000);
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* CONFIG_PPC_KUAP */
 
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-40x.h b/arch/powerpc/include/asm/nohash/32/mmu-40x.h
deleted file mode 100644
index 8a8f13a22cf4..000000000000
--- a/arch/powerpc/include/asm/nohash/32/mmu-40x.h
+++ /dev/null
@@ -1,68 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_MMU_40X_H_
-#define _ASM_POWERPC_MMU_40X_H_
-
-/*
- * PPC40x support
- */
-
-#define PPC40X_TLB_SIZE 64
-
-/*
- * TLB entries are defined by a "high" tag portion and a "low" data
- * portion.  On all architectures, the data portion is 32-bits.
- *
- * TLB entries are managed entirely under software control by reading,
- * writing, and searchoing using the 4xx-specific tlbre, tlbwr, and tlbsx
- * instructions.
- */
-
-#define	TLB_LO          1
-#define	TLB_HI          0
-
-#define	TLB_DATA        TLB_LO
-#define	TLB_TAG         TLB_HI
-
-/* Tag portion */
-
-#define TLB_EPN_MASK    0xFFFFFC00      /* Effective Page Number */
-#define TLB_PAGESZ_MASK 0x00000380
-#define TLB_PAGESZ(x)   (((x) & 0x7) << 7)
-#define   PAGESZ_1K		0
-#define   PAGESZ_4K             1
-#define   PAGESZ_16K            2
-#define   PAGESZ_64K            3
-#define   PAGESZ_256K           4
-#define   PAGESZ_1M             5
-#define   PAGESZ_4M             6
-#define   PAGESZ_16M            7
-#define TLB_VALID       0x00000040      /* Entry is valid */
-
-/* Data portion */
-
-#define TLB_RPN_MASK    0xFFFFFC00      /* Real Page Number */
-#define TLB_PERM_MASK   0x00000300
-#define TLB_EX          0x00000200      /* Instruction execution allowed */
-#define TLB_WR          0x00000100      /* Writes permitted */
-#define TLB_ZSEL_MASK   0x000000F0
-#define TLB_ZSEL(x)     (((x) & 0xF) << 4)
-#define TLB_ATTR_MASK   0x0000000F
-#define TLB_W           0x00000008      /* Caching is write-through */
-#define TLB_I           0x00000004      /* Caching is inhibited */
-#define TLB_M           0x00000002      /* Memory is coherent */
-#define TLB_G           0x00000001      /* Memory is guarded from prefetch */
-
-#ifndef __ASSEMBLY__
-
-typedef struct {
-	unsigned int	id;
-	unsigned int	active;
-	void __user	*vdso;
-} mm_context_t;
-
-#endif /* !__ASSEMBLY__ */
-
-#define mmu_virtual_psize	MMU_PAGE_4K
-#define mmu_linear_psize	MMU_PAGE_256M
-
-#endif /* _ASM_POWERPC_MMU_40X_H_ */
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-44x.h b/arch/powerpc/include/asm/nohash/32/mmu-44x.h
index 2d92a39d8f2e..c3d192194324 100644
--- a/arch/powerpc/include/asm/nohash/32/mmu-44x.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-44x.h
@@ -100,7 +100,7 @@
 #define PPC47x_TLB2_S_RW	(PPC47x_TLB2_SW | PPC47x_TLB2_SR)
 #define PPC47x_TLB2_IMG		(PPC47x_TLB2_I | PPC47x_TLB2_M | PPC47x_TLB2_G)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 extern unsigned int tlb_44x_hwater;
 extern unsigned int tlb_44x_index;
@@ -114,7 +114,7 @@ typedef struct {
 /* patch sites */
 extern s32 patch__tlb_44x_hwater_D, patch__tlb_44x_hwater_I;
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #ifndef CONFIG_PPC_EARLY_DEBUG_44x
 #define PPC44x_EARLY_TLBS	1
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index 0e93a4728c9e..f19115db8072 100644
--- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
@@ -170,10 +170,11 @@
 
 #define mmu_linear_psize	MMU_PAGE_8M
 
-#define MODULES_VADDR	(PAGE_OFFSET - SZ_256M)
 #define MODULES_END	PAGE_OFFSET
+#define MODULES_SIZE	(CONFIG_MODULES_SIZE * SZ_1M)
+#define MODULES_VADDR	(MODULES_END - MODULES_SIZE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/mmdebug.h>
 #include <linux/sizes.h>
@@ -188,21 +189,15 @@ typedef struct {
 } mm_context_t;
 
 #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)
-#define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE))
 
-/* Page size definitions, common between 32 and 64-bit
+/*
+ * Page size definitions for 8xx
  *
  *    shift : is the "PAGE_SHIFT" value for that page size
- *    penc  : is the pte encoding mask
  *
  */
 struct mmu_psize_def {
 	unsigned int	shift;	/* number of bits */
-	unsigned int	enc;	/* PTE encoding */
-	unsigned int    ind;    /* Corresponding indirect page size shift */
-	unsigned int	flags;
-#define MMU_PAGE_SIZE_DIRECT	0x1	/* Supported as a direct size */
-#define MMU_PAGE_SIZE_INDIRECT	0x2	/* Supported as an indirect size */
 };
 
 extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
@@ -270,6 +265,6 @@ static inline int arch_vmap_pte_supported_shift(unsigned long size)
 extern s32 patch__itlbmiss_exit_1, patch__dtlbmiss_exit_1;
 extern s32 patch__itlbmiss_perf, patch__dtlbmiss_perf;
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_MMU_8XX_H_ */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index fec56d965f00..2d71e4b7cd09 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -4,16 +4,12 @@
 
 #include <asm-generic/pgtable-nopmd.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/sched.h>
 #include <linux/threads.h>
 #include <asm/mmu.h>			/* For sub-arch specific PPC_PIN_SIZE */
 
-#ifdef CONFIG_44x
-extern int icache_44x_need_flush;
-#endif
-
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define PTE_INDEX_SIZE	PTE_SHIFT
 #define PMD_INDEX_SIZE	0
@@ -23,14 +19,14 @@ extern int icache_44x_need_flush;
 #define PMD_CACHE_INDEX	PMD_INDEX_SIZE
 #define PUD_CACHE_INDEX	PUD_INDEX_SIZE
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
 #define PMD_TABLE_SIZE	0
 #define PUD_TABLE_SIZE	0
 #define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
 
 #define PMD_MASKED_BITS (PTE_TABLE_SIZE - 1)
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
 #define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
@@ -55,26 +51,22 @@ extern int icache_44x_need_flush;
 
 #define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
 
-#define pte_ERROR(e) \
-	pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
-		(unsigned long long)pte_val(e))
 #define pgd_ERROR(e) \
-	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
-
-#ifndef __ASSEMBLY__
-
-int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
-void unmap_kernel_page(unsigned long va);
-
-#endif /* !__ASSEMBLY__ */
-
+	pr_err("%s:%d: bad pgd %08llx.\n", __FILE__, __LINE__, (unsigned long long)pgd_val(e))
 
 /*
  * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
  * value (for now) on others, from where we can start layout kernel
  * virtual space that goes below PKMAP and FIXMAP
  */
-#include <asm/fixmap.h>
+
+#define FIXADDR_SIZE	0
+#ifdef CONFIG_KASAN
+#include <asm/kasan.h>
+#define FIXADDR_TOP	(KASAN_SHADOW_START - PAGE_SIZE)
+#else
+#define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
+#endif
 
 /*
  * ioremap_bot starts at that address. Early ioremaps move down from there,
@@ -126,9 +118,7 @@ void unmap_kernel_page(unsigned long va);
  * (hardware-defined) PowerPC PTE as closely as possible.
  */
 
-#if defined(CONFIG_40x)
-#include <asm/nohash/32/pte-40x.h>
-#elif defined(CONFIG_44x)
+#if defined(CONFIG_44x)
 #include <asm/nohash/32/pte-44x.h>
 #elif defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT)
 #include <asm/nohash/pte-e500.h>
@@ -151,7 +141,7 @@ void unmap_kernel_page(unsigned long va);
  * The mask covered by the RPN must be a ULL on 32-bit platforms with
  * 64-bit PTEs.
  */
-#if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
+#ifdef CONFIG_PTE_64BIT
 #define PTE_RPN_MASK	(~((1ULL << PTE_RPN_SHIFT) - 1))
 #define MAX_POSSIBLE_PHYSMEM_BITS 36
 #else
@@ -159,47 +149,7 @@ void unmap_kernel_page(unsigned long va);
 #define MAX_POSSIBLE_PHYSMEM_BITS 32
 #endif
 
-/*
- * _PAGE_CHG_MASK masks of bits that are to be preserved across
- * pgprot changes.
- */
-#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL)
-
-#ifndef __ASSEMBLY__
-
-#define pte_clear(mm, addr, ptep) \
-	do { pte_update(mm, addr, ptep, ~0, 0, 0); } while (0)
-
-#ifndef pte_mkwrite
-static inline pte_t pte_mkwrite(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_RW);
-}
-#endif
-
-static inline pte_t pte_mkdirty(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);
-}
-
-#ifndef pte_wrprotect
-static inline pte_t pte_wrprotect(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_RW);
-}
-#endif
-
-#ifndef pte_mkexec
-static inline pte_t pte_mkexec(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_EXEC);
-}
-#endif
+#ifndef __ASSEMBLER__
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
 #define	pmd_bad(pmd)		(pmd_val(pmd) & _PMD_BAD)
@@ -210,141 +160,6 @@ static inline void pmd_clear(pmd_t *pmdp)
 }
 
 /*
- * PTE updates. This function is called whenever an existing
- * valid PTE is updated. This does -not- include set_pte_at()
- * which nowadays only sets a new PTE.
- *
- * Depending on the type of MMU, we may need to use atomic updates
- * and the PTE may be either 32 or 64 bit wide. In the later case,
- * when using atomic updates, only the low part of the PTE is
- * accessed atomically.
- *
- * In addition, on 44x, we also maintain a global flag indicating
- * that an executable user mapping was modified, which is needed
- * to properly flush the virtually tagged instruction cache of
- * those implementations.
- *
- * On the 8xx, the page tables are a bit special. For 16k pages, we have
- * 4 identical entries. For 512k pages, we have 128 entries as if it was
- * 4k pages, but they are flagged as 512k pages for the hardware.
- * For other page sizes, we have a single entry in the table.
- */
-#ifdef CONFIG_PPC_8xx
-static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr);
-static int hugepd_ok(hugepd_t hpd);
-
-static int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge)
-{
-	if (!huge)
-		return PAGE_SIZE / SZ_4K;
-	else if (hugepd_ok(*((hugepd_t *)pmd)))
-		return 1;
-	else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE))
-		return SZ_16K / SZ_4K;
-	else
-		return SZ_512K / SZ_4K;
-}
-
-static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
-				     unsigned long clr, unsigned long set, int huge)
-{
-	pte_basic_t *entry = (pte_basic_t *)p;
-	pte_basic_t old = pte_val(*p);
-	pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
-	int num, i;
-	pmd_t *pmd = pmd_off(mm, addr);
-
-	num = number_of_cells_per_pte(pmd, new, huge);
-
-	for (i = 0; i < num; i += PAGE_SIZE / SZ_4K, new += PAGE_SIZE) {
-		*entry++ = new;
-		if (IS_ENABLED(CONFIG_PPC_16K_PAGES) && num != 1) {
-			*entry++ = new;
-			*entry++ = new;
-			*entry++ = new;
-		}
-	}
-
-	return old;
-}
-
-#ifdef CONFIG_PPC_16K_PAGES
-#define ptep_get ptep_get
-static inline pte_t ptep_get(pte_t *ptep)
-{
-	pte_basic_t val = READ_ONCE(ptep->pte);
-	pte_t pte = {val, val, val, val};
-
-	return pte;
-}
-#endif /* CONFIG_PPC_16K_PAGES */
-
-#else
-static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
-				     unsigned long clr, unsigned long set, int huge)
-{
-	pte_basic_t old = pte_val(*p);
-	pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
-
-	*p = __pte(new);
-
-#ifdef CONFIG_44x
-	if ((old & _PAGE_USER) && (old & _PAGE_EXEC))
-		icache_44x_need_flush = 1;
-#endif
-	return old;
-}
-#endif
-
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
-					      unsigned long addr, pte_t *ptep)
-{
-	unsigned long old;
-	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
-	return (old & _PAGE_ACCESSED) != 0;
-}
-#define ptep_test_and_clear_young(__vma, __addr, __ptep) \
-	__ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep)
-
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
-static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-				       pte_t *ptep)
-{
-	return __pte(pte_update(mm, addr, ptep, ~0, 0, 0));
-}
-
-#define __HAVE_ARCH_PTEP_SET_WRPROTECT
-#ifndef ptep_set_wrprotect
-static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
-				      pte_t *ptep)
-{
-	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
-}
-#endif
-
-#ifndef __ptep_set_access_flags
-static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
-					   pte_t *ptep, pte_t entry,
-					   unsigned long address,
-					   int psize)
-{
-	unsigned long set = pte_val(entry) &
-			    (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
-	int huge = psize > mmu_virtual_psize ? 1 : 0;
-
-	pte_update(vma->vm_mm, address, ptep, 0, set, huge);
-
-	flush_tlb_page(vma, address);
-}
-#endif
-
-static inline int pte_young(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_ACCESSED;
-}
-
-/*
  * Note that on Book E processors, the pmd contains the kernel virtual
  * (lowmem) address of the pte page.  The physical address is less useful
  * because everything runs with translation enabled (even the TLB miss
@@ -355,7 +170,7 @@ static inline int pte_young(pte_t pte)
 #define pmd_pfn(pmd)		(pmd_val(pmd) >> PAGE_SHIFT)
 #else
 #define pmd_page_vaddr(pmd)	\
-	((unsigned long)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1)))
+	((const void *)((unsigned long)pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1)))
 #define pmd_pfn(pmd)		(__pa(pmd_val(pmd)) >> PAGE_SHIFT)
 #endif
 
@@ -384,6 +199,6 @@ static inline int pte_young(pte_t pte)
 /* We borrow LSB 2 to store the exclusive marker in swap PTEs. */
 #define _PAGE_SWP_EXCLUSIVE	0x000004
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_POWERPC_NOHASH_32_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h
deleted file mode 100644
index 6fe46e754556..000000000000
--- a/arch/powerpc/include/asm/nohash/32/pte-40x.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_NOHASH_32_PTE_40x_H
-#define _ASM_POWERPC_NOHASH_32_PTE_40x_H
-#ifdef __KERNEL__
-
-/*
- * At present, all PowerPC 400-class processors share a similar TLB
- * architecture. The instruction and data sides share a unified,
- * 64-entry, fully-associative TLB which is maintained totally under
- * software control. In addition, the instruction side has a
- * hardware-managed, 4-entry, fully-associative TLB which serves as a
- * first level to the shared TLB. These two TLBs are known as the UTLB
- * and ITLB, respectively (see "mmu.h" for definitions).
- *
- * There are several potential gotchas here.  The 40x hardware TLBLO
- * field looks like this:
- *
- * 0  1  2  3  4  ... 18 19 20 21 22 23 24 25 26 27 28 29 30 31
- * RPN.....................  0  0 EX WR ZSEL.......  W  I  M  G
- *
- * Where possible we make the Linux PTE bits match up with this
- *
- * - bits 20 and 21 must be cleared, because we use 4k pages (40x can
- *   support down to 1k pages), this is done in the TLBMiss exception
- *   handler.
- * - We use only zones 0 (for kernel pages) and 1 (for user pages)
- *   of the 16 available.  Bit 24-26 of the TLB are cleared in the TLB
- *   miss handler.  Bit 27 is PAGE_USER, thus selecting the correct
- *   zone.
- * - PRESENT *must* be in the bottom two bits because swap PTEs
- *   use the top 30 bits.  Because 40x doesn't support SMP anyway, M is
- *   irrelevant so we borrow it for PAGE_PRESENT.  Bit 30
- *   is cleared in the TLB miss handler before the TLB entry is loaded.
- * - All other bits of the PTE are loaded into TLBLO without
- *   modification, leaving us only the bits 20, 21, 24, 25, 26, 30 for
- *   software PTE bits.  We actually use bits 21, 24, 25, and
- *   30 respectively for the software bits: ACCESSED, DIRTY, RW, and
- *   PRESENT.
- */
-
-#define	_PAGE_GUARDED	0x001	/* G: page is guarded from prefetch */
-#define _PAGE_PRESENT	0x002	/* software: PTE contains a translation */
-#define	_PAGE_NO_CACHE	0x004	/* I: caching is inhibited */
-#define	_PAGE_WRITETHRU	0x008	/* W: caching is write-through */
-#define	_PAGE_USER	0x010	/* matches one of the zone permission bits */
-#define	_PAGE_SPECIAL	0x020	/* software: Special page */
-#define	_PAGE_DIRTY	0x080	/* software: dirty page */
-#define _PAGE_RW	0x100	/* hardware: WR, anded with dirty in exception */
-#define _PAGE_EXEC	0x200	/* hardware: EX permission */
-#define _PAGE_ACCESSED	0x400	/* software: R: page referenced */
-
-/* No page size encoding in the linux PTE */
-#define _PAGE_PSIZE		0
-
-/* cache related flags non existing on 40x */
-#define _PAGE_COHERENT	0
-
-#define _PAGE_KERNEL_RO		0
-#define _PAGE_KERNEL_ROX	_PAGE_EXEC
-#define _PAGE_KERNEL_RW		(_PAGE_DIRTY | _PAGE_RW)
-#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC)
-
-#define _PMD_PRESENT	0x400	/* PMD points to page of PTEs */
-#define _PMD_PRESENT_MASK	_PMD_PRESENT
-#define _PMD_BAD	0x802
-#define _PMD_SIZE_4M	0x0c0
-#define _PMD_SIZE_16M	0x0e0
-#define _PMD_USER	0
-
-#define _PTE_NONE_MASK	0
-
-/* Until my rework is finished, 40x still needs atomic PTE updates */
-#define PTE_ATOMIC_UPDATES	1
-
-#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED)
-#define _PAGE_BASE	(_PAGE_BASE_NC)
-
-/* Permission masks used to generate the __P and __S table */
-#define PAGE_NONE	__pgprot(_PAGE_BASE)
-#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
-#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC)
-#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
-
-#endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_NOHASH_32_PTE_40x_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pte-44x.h b/arch/powerpc/include/asm/nohash/32/pte-44x.h
index b7ed13cee137..da0469928273 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-44x.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h
@@ -63,26 +63,18 @@
  */
 
 #define _PAGE_PRESENT	0x00000001		/* S: PTE valid */
-#define _PAGE_RW	0x00000002		/* S: Write permission */
+#define _PAGE_WRITE	0x00000002		/* S: Write permission */
 #define _PAGE_EXEC	0x00000004		/* H: Execute permission */
-#define _PAGE_ACCESSED	0x00000008		/* S: Page referenced */
+#define _PAGE_READ	0x00000008		/* S: Read permission */
 #define _PAGE_DIRTY	0x00000010		/* S: Page dirty */
 #define _PAGE_SPECIAL	0x00000020		/* S: Special page */
-#define _PAGE_USER	0x00000040		/* S: User page */
+#define _PAGE_ACCESSED	0x00000040		/* S: Page referenced */
 #define _PAGE_ENDIAN	0x00000080		/* H: E bit */
 #define _PAGE_GUARDED	0x00000100		/* H: G bit */
 #define _PAGE_COHERENT	0x00000200		/* H: M bit */
 #define _PAGE_NO_CACHE	0x00000400		/* H: I bit */
 #define _PAGE_WRITETHRU	0x00000800		/* H: W bit */
 
-/* No page size encoding in the linux PTE */
-#define _PAGE_PSIZE		0
-
-#define _PAGE_KERNEL_RO		0
-#define _PAGE_KERNEL_ROX	_PAGE_EXEC
-#define _PAGE_KERNEL_RW		(_PAGE_DIRTY | _PAGE_RW)
-#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC)
-
 /* TODO: Add large page lowmem mapping support */
 #define _PMD_PRESENT	0
 #define _PMD_PRESENT_MASK (PAGE_MASK)
@@ -105,14 +97,7 @@
 #define _PAGE_BASE	(_PAGE_BASE_NC)
 #endif
 
-/* Permission masks used to generate the __P and __S table */
-#define PAGE_NONE	__pgprot(_PAGE_BASE)
-#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
-#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC)
-#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+#include <asm/pgtable-masks.h>
 
 #endif /* __KERNEL__ */
 #endif /*  _ASM_POWERPC_NOHASH_32_PTE_44x_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pte-85xx.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h
index 16451df5ddb0..14d64b4f3f14 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-85xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-85xx.h
@@ -17,9 +17,9 @@
 */
 
 /* Definitions for FSL Book-E Cores */
-#define _PAGE_PRESENT	0x00001	/* S: PTE contains a translation */
-#define _PAGE_USER	0x00002	/* S: User page (maps to UR) */
-#define _PAGE_RW	0x00004	/* S: Write permission (SW) */
+#define _PAGE_READ	0x00001	/* H: Read permission (SR) */
+#define _PAGE_PRESENT	0x00002	/* S: PTE contains a translation */
+#define _PAGE_WRITE	0x00004	/* S: Write permission (SW) */
 #define _PAGE_DIRTY	0x00008	/* S: Page dirty */
 #define _PAGE_EXEC	0x00010	/* H: SX permission */
 #define _PAGE_ACCESSED	0x00020	/* S: Page referenced */
@@ -31,14 +31,6 @@
 #define _PAGE_WRITETHRU	0x00400	/* H: W bit */
 #define _PAGE_SPECIAL	0x00800 /* S: Special page */
 
-#define _PAGE_KERNEL_RO		0
-#define _PAGE_KERNEL_ROX	_PAGE_EXEC
-#define _PAGE_KERNEL_RW		(_PAGE_DIRTY | _PAGE_RW)
-#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC)
-
-/* No page size encoding in the linux PTE */
-#define _PAGE_PSIZE		0
-
 #define _PMD_PRESENT	0
 #define _PMD_PRESENT_MASK (PAGE_MASK)
 #define _PMD_BAD	(~PAGE_MASK)
@@ -61,14 +53,7 @@
 #define _PAGE_BASE	(_PAGE_BASE_NC)
 #endif
 
-/* Permission masks used to generate the __P and __S table */
-#define PAGE_NONE	__pgprot(_PAGE_BASE)
-#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
-#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC)
-#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC)
+#include <asm/pgtable-masks.h>
 
 #endif /* __KERNEL__ */
 #endif /*  _ASM_POWERPC_NOHASH_32_PTE_FSL_85xx_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 1a89ebdc3acc..e2ea8ba9f8ca 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -48,6 +48,11 @@
 
 #define _PAGE_HUGE	0x0800	/* Copied to L1 PS bit 29 */
 
+#define _PAGE_NAX	(_PAGE_NA | _PAGE_EXEC)
+#define _PAGE_ROX	(_PAGE_RO | _PAGE_EXEC)
+#define _PAGE_RW	0
+#define _PAGE_RWX	_PAGE_EXEC
+
 /* cache related flags non existing on 8xx */
 #define _PAGE_COHERENT	0
 #define _PAGE_WRITETHRU	0
@@ -69,24 +74,16 @@
 #define _PTE_NONE_MASK	0
 
 #ifdef CONFIG_PPC_16K_PAGES
-#define _PAGE_PSIZE	_PAGE_SPS
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_SPS)
 #else
-#define _PAGE_PSIZE		0
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED)
 #endif
 
-#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
 #define _PAGE_BASE	(_PAGE_BASE_NC)
 
-/* Permission masks used to generate the __P and __S table */
-#define PAGE_NONE	__pgprot(_PAGE_BASE | _PAGE_NA)
-#define PAGE_SHARED	__pgprot(_PAGE_BASE)
-#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_EXEC)
-#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_RO)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_RO | _PAGE_EXEC)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_RO)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_RO | _PAGE_EXEC)
+#include <asm/pgtable-masks.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 static inline pte_t pte_wrprotect(pte_t pte)
 {
 	return __pte(pte_val(pte) | _PAGE_RO);
@@ -94,40 +91,26 @@ static inline pte_t pte_wrprotect(pte_t pte)
 
 #define pte_wrprotect pte_wrprotect
 
-static inline int pte_write(pte_t pte)
-{
-	return !(pte_val(pte) & _PAGE_RO);
-}
-
-#define pte_write pte_write
-
-static inline pte_t pte_mkwrite(pte_t pte)
+static inline int pte_read(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_RO);
+	return (pte_val(pte) & _PAGE_RO) != _PAGE_NA;
 }
 
-#define pte_mkwrite pte_mkwrite
-
-static inline bool pte_user(pte_t pte)
-{
-	return !(pte_val(pte) & _PAGE_SH);
-}
+#define pte_read pte_read
 
-#define pte_user pte_user
-
-static inline pte_t pte_mkprivileged(pte_t pte)
+static inline int pte_write(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_SH);
+	return !(pte_val(pte) & _PAGE_RO);
 }
 
-#define pte_mkprivileged pte_mkprivileged
+#define pte_write pte_write
 
-static inline pte_t pte_mkuser(pte_t pte)
+static inline pte_t pte_mkwrite_novma(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_SH);
+	return __pte(pte_val(pte) & ~_PAGE_RO);
 }
 
-#define pte_mkuser pte_mkuser
+#define pte_mkwrite_novma pte_mkwrite_novma
 
 static inline pte_t pte_mkhuge(pte_t pte)
 {
@@ -136,7 +119,7 @@ static inline pte_t pte_mkhuge(pte_t pte)
 
 #define pte_mkhuge pte_mkhuge
 
-static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 				     unsigned long clr, unsigned long set, int huge);
 
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
@@ -158,19 +141,12 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, pte_t *pt
 }
 #define __ptep_set_access_flags __ptep_set_access_flags
 
-static inline unsigned long pgd_leaf_size(pgd_t pgd)
-{
-	if (pgd_val(pgd) & _PMD_PAGE_8M)
-		return SZ_8M;
-	return SZ_4M;
-}
-
-#define pgd_leaf_size pgd_leaf_size
-
-static inline unsigned long pte_leaf_size(pte_t pte)
+static inline unsigned long __pte_leaf_size(pmd_t pmd, pte_t pte)
 {
 	pte_basic_t val = pte_val(pte);
 
+	if (pmd_val(pmd) & _PMD_PAGE_8M)
+		return SZ_8M;
 	if (val & _PAGE_HUGE)
 		return SZ_512K;
 	if (val & _PAGE_SPS)
@@ -178,7 +154,86 @@ static inline unsigned long pte_leaf_size(pte_t pte)
 	return SZ_4K;
 }
 
-#define pte_leaf_size pte_leaf_size
+#define __pte_leaf_size __pte_leaf_size
+
+/*
+ * On the 8xx, the page tables are a bit special. For 16k pages, we have
+ * 4 identical entries. For 512k pages, we have 128 entries as if it was
+ * 4k pages, but they are flagged as 512k pages for the hardware.
+ * For 8M pages, we have 1024 entries as if it was 4M pages (PMD_SIZE)
+ * but they are flagged as 8M pages for the hardware.
+ * For 4k pages, we have a single entry in the table.
+ */
+static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr);
+static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address);
+
+static inline bool ptep_is_8m_pmdp(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	return (pmd_t *)ptep == pmd_off(mm, ALIGN_DOWN(addr, SZ_8M));
+}
+
+static inline int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge)
+{
+	if (!huge)
+		return PAGE_SIZE / SZ_4K;
+	else if ((pmd_val(*pmd) & _PMD_PAGE_MASK) == _PMD_PAGE_8M)
+		return SZ_4M / SZ_4K;
+	else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE))
+		return SZ_16K / SZ_4K;
+	else
+		return SZ_512K / SZ_4K;
+}
+
+static inline pte_basic_t __pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+				       unsigned long clr, unsigned long set, int huge)
+{
+	pte_basic_t *entry = (pte_basic_t *)p;
+	pte_basic_t old = pte_val(*p);
+	pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
+	int num, i;
+	pmd_t *pmd = pmd_off(mm, addr);
+
+	num = number_of_cells_per_pte(pmd, new, huge);
+
+	for (i = 0; i < num; i += PAGE_SIZE / SZ_4K, new += PAGE_SIZE) {
+		*entry++ = new;
+		if (IS_ENABLED(CONFIG_PPC_16K_PAGES)) {
+			*entry++ = new;
+			*entry++ = new;
+			*entry++ = new;
+		}
+	}
+
+	return old;
+}
+
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+				     unsigned long clr, unsigned long set, int huge)
+{
+	pte_basic_t old;
+
+	if (huge && ptep_is_8m_pmdp(mm, addr, ptep)) {
+		pmd_t *pmdp = (pmd_t *)ptep;
+
+		old = __pte_update(mm, addr, pte_offset_kernel(pmdp, 0), clr, set, huge);
+		__pte_update(mm, addr, pte_offset_kernel(pmdp + 1, 0), clr, set, huge);
+	} else {
+		old = __pte_update(mm, addr, ptep, clr, set, huge);
+	}
+	return old;
+}
+#define pte_update pte_update
+
+#ifdef CONFIG_PPC_16K_PAGES
+#define ptep_get ptep_get
+static inline pte_t ptep_get(pte_t *ptep)
+{
+	pte_basic_t val = READ_ONCE(ptep->pte);
+	pte_t pte = {val, val, val, val};
+
+	return pte;
+}
+#endif /* CONFIG_PPC_16K_PAGES */
 
 #endif
 
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
index 10f5cf444d72..fb6fa1d4e074 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable-4k.h
@@ -14,12 +14,12 @@
 #define PUD_INDEX_SIZE  9
 #define PGD_INDEX_SIZE  9
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
 #define PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
 #define PUD_TABLE_SIZE	(sizeof(pud_t) << PUD_INDEX_SIZE)
 #define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
 #define PTRS_PER_PMD	(1 << PMD_INDEX_SIZE)
@@ -57,7 +57,7 @@
 #define p4d_bad(p4d)		(p4d_val(p4d) == 0)
 #define p4d_present(p4d)	(p4d_val(p4d) != 0)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 static inline pud_t *p4d_pgtable(p4d_t p4d)
 {
@@ -80,7 +80,7 @@ static inline p4d_t pte_p4d(pte_t pte)
 }
 extern struct page *p4d_page(p4d_t p4d);
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #define pud_ERROR(e) \
 	pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e))
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 287e25864ffa..2deb955b7bc8 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -57,6 +57,7 @@
 #define IOREMAP_START	(ioremap_bot)
 #define IOREMAP_END	(KERN_IO_START + KERN_IO_SIZE - FIXADDR_SIZE)
 #define FIXADDR_SIZE	SZ_32M
+#define FIXADDR_TOP	(IOREMAP_END + FIXADDR_SIZE)
 
 /*
  * Defines the address of the vmemap area, in its own region on
@@ -74,37 +75,11 @@
 
 #define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
 
-/*
- * _PAGE_CHG_MASK masks of bits that are to be preserved across
- * pgprot changes.
- */
-#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL)
-
 #define H_PAGE_4K_PFN 0
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /* pte_clear moved to later in this file */
 
-static inline pte_t pte_mkwrite(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_RW);
-}
-
-static inline pte_t pte_mkdirty(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_wrprotect(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_RW);
-}
-
 #define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
 #define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
 
@@ -127,7 +102,7 @@ static inline pte_t pmd_pte(pmd_t pmd)
 #define	pmd_bad(pmd)		(!is_kernel_addr(pmd_val(pmd)) \
 				 || (pmd_val(pmd) & PMD_BAD_BITS))
 #define	pmd_present(pmd)	(!pmd_none(pmd))
-#define pmd_page_vaddr(pmd)	(pmd_val(pmd) & ~PMD_MASKED_BITS)
+#define pmd_page_vaddr(pmd)	((const void *)(pmd_val(pmd) & ~PMD_MASKED_BITS))
 extern struct page *pmd_page(pmd_t pmd);
 #define pmd_pfn(pmd)		(page_to_pfn(pmd_page(pmd)))
 
@@ -170,107 +145,20 @@ static inline void p4d_set(p4d_t *p4dp, unsigned long val)
 	*p4dp = __p4d(val);
 }
 
-/* Atomic PTE updates */
-static inline unsigned long pte_update(struct mm_struct *mm,
-				       unsigned long addr,
-				       pte_t *ptep, unsigned long clr,
-				       unsigned long set,
-				       int huge)
-{
-	unsigned long old = pte_val(*ptep);
-	*ptep = __pte((old & ~clr) | set);
-
-	/* huge pages use the old page table lock */
-	if (!huge)
-		assert_pte_locked(mm, addr);
-
-	return old;
-}
-
-static inline int pte_young(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_ACCESSED;
-}
-
-static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
-					      unsigned long addr, pte_t *ptep)
-{
-	unsigned long old;
-
-	if (pte_young(*ptep))
-		return 0;
-	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
-	return (old & _PAGE_ACCESSED) != 0;
-}
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-#define ptep_test_and_clear_young(__vma, __addr, __ptep)		   \
-({									   \
-	int __r;							   \
-	__r = __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \
-	__r;								   \
-})
-
-#define __HAVE_ARCH_PTEP_SET_WRPROTECT
-static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
-				      pte_t *ptep)
-{
-
-	if ((pte_val(*ptep) & _PAGE_RW) == 0)
-		return;
-
-	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
-}
-
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	if ((pte_val(*ptep) & _PAGE_RW) == 0)
-		return;
-
-	pte_update(mm, addr, ptep, _PAGE_RW, 0, 1);
+	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
 }
 
 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
 #define ptep_clear_flush_young(__vma, __address, __ptep)		\
 ({									\
-	int __young = __ptep_test_and_clear_young((__vma)->vm_mm, __address, \
-						  __ptep);		\
+	int __young = ptep_test_and_clear_young(__vma, __address, __ptep);\
 	__young;							\
 })
 
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
-static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
-				       unsigned long addr, pte_t *ptep)
-{
-	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0);
-	return __pte(old);
-}
-
-static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
-			     pte_t * ptep)
-{
-	pte_update(mm, addr, ptep, ~0UL, 0, 0);
-}
-
-
-/* Set the dirty and/or accessed bits atomically in a linux PTE */
-static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
-					   pte_t *ptep, pte_t entry,
-					   unsigned long address,
-					   int psize)
-{
-	unsigned long bits = pte_val(entry) &
-		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
-
-	unsigned long old = pte_val(*ptep);
-	*ptep = __pte(old | bits);
-
-	flush_tlb_page(vma, address);
-}
-
-#define pte_ERROR(e) \
-	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
 #define pmd_ERROR(e) \
 	pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
 #define pgd_ERROR(e) \
@@ -310,8 +198,6 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 /* We borrow MSB 56 (LSB 7) to store the exclusive marker in swap PTEs. */
 #define _PAGE_SWP_EXCLUSIVE	0x80
 
-int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot);
-void unmap_kernel_page(unsigned long va);
 extern int __meminit vmemmap_create_mapping(unsigned long start,
 					    unsigned long page_size,
 					    unsigned long phys);
@@ -323,6 +209,6 @@ void __patch_exception(int exc, unsigned long addr);
 	__patch_exception((exc), (unsigned long)&name); \
 } while (0)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_NOHASH_64_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/nohash/hugetlb-e500.h b/arch/powerpc/include/asm/nohash/hugetlb-e500.h
index 8f04ad20e040..cab0e1f1eea0 100644
--- a/arch/powerpc/include/asm/nohash/hugetlb-e500.h
+++ b/arch/powerpc/include/asm/nohash/hugetlb-e500.h
@@ -2,38 +2,8 @@
 #ifndef _ASM_POWERPC_NOHASH_HUGETLB_E500_H
 #define _ASM_POWERPC_NOHASH_HUGETLB_E500_H
 
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
-	if (WARN_ON(!hugepd_ok(hpd)))
-		return NULL;
-
-	return (pte_t *)((hpd_val(hpd) & ~HUGEPD_SHIFT_MASK) | PD_HUGE);
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
-	return hpd_val(hpd) & HUGEPD_SHIFT_MASK;
-}
-
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
-				    unsigned int pdshift)
-{
-	/*
-	 * On FSL BookE, we have multiple higher-level table entries that
-	 * point to the same hugepte.  Just use the first one since they're all
-	 * identical.  So for that case, idx=0.
-	 */
-	return hugepd_page(hpd);
-}
-
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
-	/* We use the old format for PPC_E500 */
-	*hpdp = __hugepd(((unsigned long)new & ~PD_HUGE) | pshift);
-}
-
 static inline int check_and_get_huge_psize(int shift)
 {
 	if (shift & 1)	/* Not a power of 4 */
@@ -42,4 +12,13 @@ static inline int check_and_get_huge_psize(int shift)
 	return shift_to_mmu_psize(shift);
 }
 
+static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
+{
+	unsigned int tsize = shift - _PAGE_PSIZE_SHIFT_OFFSET;
+	pte_basic_t val = (tsize << _PAGE_PSIZE_SHIFT) & _PAGE_PSIZE_MSK;
+
+	return __pte((pte_val(entry) & ~(pte_basic_t)_PAGE_PSIZE_MSK) | val);
+}
+#define arch_make_huge_pte arch_make_huge_pte
+
 #endif /* _ASM_POWERPC_NOHASH_HUGETLB_E500_H */
diff --git a/arch/powerpc/include/asm/nohash/kup-booke.h b/arch/powerpc/include/asm/nohash/kup-booke.h
index 49bb41ed0816..d6bbb6d78bbe 100644
--- a/arch/powerpc/include/asm/nohash/kup-booke.h
+++ b/arch/powerpc/include/asm/nohash/kup-booke.h
@@ -3,42 +3,37 @@
 #define _ASM_POWERPC_KUP_BOOKE_H_
 
 #include <asm/bug.h>
+#include <asm/mmu.h>
 
 #ifdef CONFIG_PPC_KUAP
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro kuap_check_amr	gpr1, gpr2
 .endm
 
 #else
 
-#include <linux/jump_label.h>
 #include <linux/sched.h>
 
 #include <asm/reg.h>
 
-extern struct static_key_false disable_kuap_key;
-
-static __always_inline bool kuap_is_disabled(void)
-{
-	return static_branch_unlikely(&disable_kuap_key);
-}
-
-static inline void __kuap_lock(void)
+static __always_inline void __kuap_lock(void)
 {
 	mtspr(SPRN_PID, 0);
 	isync();
 }
+#define __kuap_lock __kuap_lock
 
-static inline void __kuap_save_and_lock(struct pt_regs *regs)
+static __always_inline void __kuap_save_and_lock(struct pt_regs *regs)
 {
 	regs->kuap = mfspr(SPRN_PID);
 	mtspr(SPRN_PID, 0);
 	isync();
 }
+#define __kuap_save_and_lock __kuap_save_and_lock
 
-static inline void kuap_user_restore(struct pt_regs *regs)
+static __always_inline void kuap_user_restore(struct pt_regs *regs)
 {
 	if (kuap_is_disabled())
 		return;
@@ -48,7 +43,7 @@ static inline void kuap_user_restore(struct pt_regs *regs)
 	/* Context synchronisation is performed by rfi */
 }
 
-static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
+static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
 {
 	if (regs->kuap)
 		mtspr(SPRN_PID, current->thread.pid);
@@ -56,54 +51,61 @@ static inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kua
 	/* Context synchronisation is performed by rfi */
 }
 
-static inline unsigned long __kuap_get_and_assert_locked(void)
+#ifdef CONFIG_PPC_KUAP_DEBUG
+static __always_inline unsigned long __kuap_get_and_assert_locked(void)
 {
-	unsigned long kuap = mfspr(SPRN_PID);
+	WARN_ON_ONCE(mfspr(SPRN_PID));
 
-	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG))
-		WARN_ON_ONCE(kuap);
+	return 0;
+}
+#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked
+#endif
 
-	return kuap;
+static __always_inline void uaccess_begin_booke(unsigned long val)
+{
+	asm(ASM_MMU_FTR_IFSET("mtspr %0, %1; isync", "", %2) : :
+	    "i"(SPRN_PID), "r"(val), "i"(MMU_FTR_KUAP) : "memory");
 }
 
-static inline void __allow_user_access(void __user *to, const void __user *from,
-				       unsigned long size, unsigned long dir)
+static __always_inline void uaccess_end_booke(void)
 {
-	mtspr(SPRN_PID, current->thread.pid);
-	isync();
+	asm(ASM_MMU_FTR_IFSET("mtspr %0, %1; isync", "", %2) : :
+	    "i"(SPRN_PID), "r"(0), "i"(MMU_FTR_KUAP) : "memory");
 }
 
-static inline void __prevent_user_access(unsigned long dir)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      unsigned long size, unsigned long dir)
 {
-	mtspr(SPRN_PID, 0);
-	isync();
+	uaccess_begin_booke(current->thread.pid);
+}
+
+static __always_inline void prevent_user_access(unsigned long dir)
+{
+	uaccess_end_booke();
 }
 
-static inline unsigned long __prevent_user_access_return(void)
+static __always_inline unsigned long prevent_user_access_return(void)
 {
 	unsigned long flags = mfspr(SPRN_PID);
 
-	mtspr(SPRN_PID, 0);
-	isync();
+	uaccess_end_booke();
 
 	return flags;
 }
 
-static inline void __restore_user_access(unsigned long flags)
+static __always_inline void restore_user_access(unsigned long flags)
 {
-	if (flags) {
-		mtspr(SPRN_PID, current->thread.pid);
-		isync();
-	}
+	if (flags)
+		uaccess_begin_booke(current->thread.pid);
 }
 
-static inline bool
+static __always_inline bool
 __bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	return !regs->kuap;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* CONFIG_PPC_KUAP */
 
diff --git a/arch/powerpc/include/asm/nohash/mmu-e500.h b/arch/powerpc/include/asm/nohash/mmu-e500.h
index e43a418d3ccd..2fad5ff426a0 100644
--- a/arch/powerpc/include/asm/nohash/mmu-e500.h
+++ b/arch/powerpc/include/asm/nohash/mmu-e500.h
@@ -230,7 +230,7 @@
 #define MAS2_M_IF_NEEDED	0
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/bug.h>
 
 extern unsigned int tlbcam_index;
@@ -244,14 +244,11 @@ typedef struct {
 /* Page size definitions, common between 32 and 64-bit
  *
  *    shift : is the "PAGE_SHIFT" value for that page size
- *    penc  : is the pte encoding mask
  *
  */
 struct mmu_psize_def
 {
 	unsigned int	shift;	/* number of bits */
-	unsigned int	enc;	/* PTE encoding */
-	unsigned int    ind;    /* Corresponding indirect page size shift */
 	unsigned int	flags;
 #define MMU_PAGE_SIZE_DIRECT	0x1	/* Supported as a direct size */
 #define MMU_PAGE_SIZE_INDIRECT	0x2	/* Supported as an indirect size */
@@ -303,8 +300,7 @@ extern unsigned long linear_map_top;
 extern int book3e_htw_mode;
 
 #define PPC_HTW_NONE	0
-#define PPC_HTW_IBM	1
-#define PPC_HTW_E6500	2
+#define PPC_HTW_E6500	1
 
 /*
  * 64-bit booke platforms don't load the tlb in the tlb miss handler code.
@@ -319,6 +315,9 @@ extern int book3e_htw_mode;
 
 #endif
 
-#endif /* !__ASSEMBLY__ */
+#include <asm/percpu.h>
+DECLARE_PER_CPU(int, next_tlbcam_idx);
+
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_MMU_BOOK3E_H_ */
diff --git a/arch/powerpc/include/asm/nohash/mmu.h b/arch/powerpc/include/asm/nohash/mmu.h
index e264be219fdb..4cc795044103 100644
--- a/arch/powerpc/include/asm/nohash/mmu.h
+++ b/arch/powerpc/include/asm/nohash/mmu.h
@@ -2,10 +2,7 @@
 #ifndef _ASM_POWERPC_NOHASH_MMU_H_
 #define _ASM_POWERPC_NOHASH_MMU_H_
 
-#if defined(CONFIG_40x)
-/* 40x-style software loaded TLB */
-#include <asm/nohash/32/mmu-40x.h>
-#elif defined(CONFIG_44x)
+#if defined(CONFIG_44x)
 /* 44x-style software loaded TLB */
 #include <asm/nohash/32/mmu-44x.h>
 #elif defined(CONFIG_PPC_E500)
diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h
index 4b62376318e1..4ef780b291bc 100644
--- a/arch/powerpc/include/asm/nohash/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/pgalloc.h
@@ -19,8 +19,14 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+	pgd_t *pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
 			pgtable_gfp_flags(mm, GFP_KERNEL));
+
+#ifdef CONFIG_PPC_8xx
+	memcpy(pgd + USER_PTRS_PER_PGD, swapper_pg_dir + USER_PTRS_PER_PGD,
+	       (MAX_PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+#endif
+	return pgd;
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -44,8 +50,6 @@ static inline void pgtable_free(void *table, int shift)
 	}
 }
 
-#define get_hugepd_cache_index(x)	(x)
-
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
 {
 	unsigned long pgf = (unsigned long)table;
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index a6caaaab6f92..5af168b7f292 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -2,12 +2,23 @@
 #ifndef _ASM_POWERPC_NOHASH_PGTABLE_H
 #define _ASM_POWERPC_NOHASH_PGTABLE_H
 
+#ifndef __ASSEMBLER__
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+				     unsigned long clr, unsigned long set, int huge);
+#endif
+
 #if defined(CONFIG_PPC64)
 #include <asm/nohash/64/pgtable.h>
 #else
 #include <asm/nohash/32/pgtable.h>
 #endif
 
+/*
+ * _PAGE_CHG_MASK masks of bits that are to be preserved across
+ * pgprot changes.
+ */
+#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL)
+
 /* Permission masks used for kernel mappings */
 #define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW)
 #define PAGE_KERNEL_NC	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE)
@@ -16,16 +27,168 @@
 #define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
 #define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
+
+extern int icache_44x_need_flush;
+
+#ifndef pte_huge_size
+static inline unsigned long pte_huge_size(pte_t pte)
+{
+	return PAGE_SIZE;
+}
+#endif
+
+/*
+ * PTE updates. This function is called whenever an existing
+ * valid PTE is updated. This does -not- include set_pte_at()
+ * which nowadays only sets a new PTE.
+ *
+ * Depending on the type of MMU, we may need to use atomic updates
+ * and the PTE may be either 32 or 64 bit wide. In the later case,
+ * when using atomic updates, only the low part of the PTE is
+ * accessed atomically.
+ *
+ * In addition, on 44x, we also maintain a global flag indicating
+ * that an executable user mapping was modified, which is needed
+ * to properly flush the virtually tagged instruction cache of
+ * those implementations.
+ */
+#ifndef pte_update
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+				     unsigned long clr, unsigned long set, int huge)
+{
+	pte_basic_t old = pte_val(*p);
+	pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
+	unsigned long sz;
+	unsigned long pdsize;
+	int i;
+
+	if (new == old)
+		return old;
+
+	if (huge)
+		sz = pte_huge_size(__pte(old));
+	else
+		sz = PAGE_SIZE;
+
+	if (sz < PMD_SIZE)
+		pdsize = PAGE_SIZE;
+	else if (sz < PUD_SIZE)
+		pdsize = PMD_SIZE;
+	else if (sz < P4D_SIZE)
+		pdsize = PUD_SIZE;
+	else if (sz < PGDIR_SIZE)
+		pdsize = P4D_SIZE;
+	else
+		pdsize = PGDIR_SIZE;
+
+	for (i = 0; i < sz / pdsize; i++, p++) {
+		*p = __pte(new);
+		if (new)
+			new += (unsigned long long)(pdsize / PAGE_SIZE) << PTE_RPN_SHIFT;
+	}
+
+	if (IS_ENABLED(CONFIG_44x) && !is_kernel_addr(addr) && (old & _PAGE_EXEC))
+		icache_44x_need_flush = 1;
+
+	/* huge pages use the old page table lock */
+	if (!huge)
+		assert_pte_locked(mm, addr);
+
+	return old;
+}
+#endif
+
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long addr, pte_t *ptep)
+{
+	unsigned long old;
+
+	old = pte_update(vma->vm_mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
+
+	return (old & _PAGE_ACCESSED) != 0;
+}
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+
+#ifndef ptep_set_wrprotect
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep)
+{
+	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+}
+#endif
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				       pte_t *ptep)
+{
+	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 0));
+}
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+
+static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	pte_update(mm, addr, ptep, ~0UL, 0, 0);
+}
+
+/* Set the dirty and/or accessed bits atomically in a linux PTE */
+#ifndef __ptep_set_access_flags
+static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
+					   pte_t *ptep, pte_t entry,
+					   unsigned long address,
+					   int psize)
+{
+	unsigned long set = pte_val(entry) &
+			    (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
+	int huge = psize > mmu_virtual_psize ? 1 : 0;
+
+	pte_update(vma->vm_mm, address, ptep, 0, set, huge);
+
+	flush_tlb_page(vma, address);
+}
+#endif
 
 /* Generic accessors to PTE bits */
+#ifndef pte_mkwrite_novma
+static inline pte_t pte_mkwrite_novma(pte_t pte)
+{
+	/*
+	 * write implies read, hence set both
+	 */
+	return __pte(pte_val(pte) | _PAGE_RW);
+}
+#endif
+
+static inline pte_t pte_mkdirty(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);
+}
+
+#ifndef pte_wrprotect
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_WRITE);
+}
+#endif
+
+#ifndef pte_mkexec
+static inline pte_t pte_mkexec(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_EXEC);
+}
+#endif
+
 #ifndef pte_write
 static inline int pte_write(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_RW;
+	return pte_val(pte) & _PAGE_WRITE;
 }
 #endif
-static inline int pte_read(pte_t pte)		{ return 1; }
 static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_special(pte_t pte)	{ return pte_val(pte) & _PAGE_SPECIAL; }
 static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
@@ -33,23 +196,6 @@ static inline bool pte_hashpte(pte_t pte)	{ return false; }
 static inline bool pte_ci(pte_t pte)		{ return pte_val(pte) & _PAGE_NO_CACHE; }
 static inline bool pte_exec(pte_t pte)		{ return pte_val(pte) & _PAGE_EXEC; }
 
-#ifdef CONFIG_NUMA_BALANCING
-/*
- * These work without NUMA balancing but the kernel does not care. See the
- * comment in include/linux/pgtable.h . On powerpc, this will only
- * work for user pages and always return true for kernel pages.
- */
-static inline int pte_protnone(pte_t pte)
-{
-	return pte_present(pte) && !pte_user(pte);
-}
-
-static inline int pmd_protnone(pmd_t pmd)
-{
-	return pte_protnone(pmd_pte(pmd));
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 static inline int pte_present(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_PRESENT;
@@ -60,15 +206,20 @@ static inline bool pte_hw_valid(pte_t pte)
 	return pte_val(pte) & _PAGE_PRESENT;
 }
 
+static inline int pte_young(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_ACCESSED;
+}
+
 /*
- * Don't just check for any non zero bits in __PAGE_USER, since for book3e
+ * Don't just check for any non zero bits in __PAGE_READ, since for book3e
  * and PTE_64BIT, PAGE_KERNEL_X contains _PAGE_BAP_SR which is also in
- * _PAGE_USER.  Need to explicitly match _PAGE_BAP_UR bit in that case too.
+ * _PAGE_READ.  Need to explicitly match _PAGE_BAP_UR bit in that case too.
  */
-#ifndef pte_user
-static inline bool pte_user(pte_t pte)
+#ifndef pte_read
+static inline bool pte_read(pte_t pte)
 {
-	return (pte_val(pte) & _PAGE_USER) == _PAGE_USER;
+	return (pte_val(pte) & _PAGE_READ) == _PAGE_READ;
 }
 #endif
 
@@ -80,10 +231,10 @@ static inline bool pte_user(pte_t pte)
 static inline bool pte_access_permitted(pte_t pte, bool write)
 {
 	/*
-	 * A read-only access is controlled by _PAGE_USER bit.
-	 * We have _PAGE_READ set for WRITE and EXECUTE
+	 * A read-only access is controlled by _PAGE_READ bit.
+	 * We have _PAGE_READ set for WRITE
 	 */
-	if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte))
+	if (!pte_present(pte) || !pte_read(pte))
 		return false;
 
 	if (write && !pte_write(pte))
@@ -101,8 +252,6 @@ static inline bool pte_access_permitted(pte_t pte, bool write)
 static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) {
 	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
 		     pgprot_val(pgprot)); }
-static inline unsigned long pte_pfn(pte_t pte)	{
-	return pte_val(pte) >> PTE_RPN_SHIFT; }
 
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_exprotect(pte_t pte)
@@ -132,26 +281,12 @@ static inline pte_t pte_mkhuge(pte_t pte)
 }
 #endif
 
-#ifndef pte_mkprivileged
-static inline pte_t pte_mkprivileged(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_USER);
-}
-#endif
-
-#ifndef pte_mkuser
-static inline pte_t pte_mkuser(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_USER);
-}
-#endif
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
 }
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
@@ -166,12 +301,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 	return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE);
 }
 
-/* Insert a PTE, top-level function is out of line. It uses an inline
- * low level function in the respective pgtable-* files
- */
-extern void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
-		       pte_t pte);
-
 /* This low level function performs the actual PTE insertion
  * Setting the PTE depends on the MMU type and other factors. It's
  * an horrible mess that I'm not going to try to clean up now but
@@ -213,11 +342,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 		mb();
 }
 
-
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
-				 pte_t *ptep, pte_t entry, int dirty);
-
 /*
  * Macro to mark a page protection value as "uncacheable".
  */
@@ -246,47 +370,8 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addre
 
 #define pgprot_writecombine pgprot_noncached_wc
 
-struct file;
-extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-				     unsigned long size, pgprot_t vma_prot);
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-
-#ifdef CONFIG_HUGETLB_PAGE
-static inline int hugepd_ok(hugepd_t hpd)
-{
-#ifdef CONFIG_PPC_8xx
-	return ((hpd_val(hpd) & _PMD_PAGE_MASK) == _PMD_PAGE_8M);
-#else
-	/* We clear the top bit to indicate hugepd */
-	return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
-#endif
-}
-
-static inline int pmd_huge(pmd_t pmd)
-{
-	return 0;
-}
-
-static inline int pud_huge(pud_t pud)
-{
-	return 0;
-}
-
-#define is_hugepd(hpd)		(hugepd_ok(hpd))
-#endif
-
-/*
- * This gets called at the end of handling a page fault, when
- * the kernel has put a new PTE into the page table for the process.
- * We use it to ensure coherency between the i-cache and d-cache
- * for the page which has just been mapped in.
- */
-#if defined(CONFIG_PPC_E500) && defined(CONFIG_HUGETLB_PAGE)
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep);
-#else
-static inline
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {}
-#endif
+int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
+void unmap_kernel_page(unsigned long va);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif
diff --git a/arch/powerpc/include/asm/nohash/pte-e500.h b/arch/powerpc/include/asm/nohash/pte-e500.h
index d8924cbd61e4..b61efc3ee904 100644
--- a/arch/powerpc/include/asm/nohash/pte-e500.h
+++ b/arch/powerpc/include/asm/nohash/pte-e500.h
@@ -19,20 +19,7 @@
 #define _PAGE_BAP_SX	0x000040
 #define _PAGE_BAP_UX	0x000080
 #define _PAGE_PSIZE_MSK	0x000f00
-#define _PAGE_PSIZE_4K	0x000200
-#define _PAGE_PSIZE_8K	0x000300
-#define _PAGE_PSIZE_16K	0x000400
-#define _PAGE_PSIZE_32K	0x000500
-#define _PAGE_PSIZE_64K	0x000600
-#define _PAGE_PSIZE_128K	0x000700
-#define _PAGE_PSIZE_256K	0x000800
-#define _PAGE_PSIZE_512K	0x000900
-#define _PAGE_PSIZE_1M	0x000a00
-#define _PAGE_PSIZE_2M	0x000b00
-#define _PAGE_PSIZE_4M	0x000c00
-#define _PAGE_PSIZE_8M	0x000d00
-#define _PAGE_PSIZE_16M	0x000e00
-#define _PAGE_PSIZE_32M	0x000f00
+#define _PAGE_TSIZE_4K	0x000100
 #define _PAGE_DIRTY	0x001000 /* C: page changed */
 #define _PAGE_SW0	0x002000
 #define _PAGE_U3	0x004000
@@ -46,20 +33,28 @@
 #define _PAGE_NO_CACHE	0x400000 /* I: cache inhibit */
 #define _PAGE_WRITETHRU	0x800000 /* W: cache write-through */
 
+#define _PAGE_PSIZE_SHIFT		7
+#define _PAGE_PSIZE_SHIFT_OFFSET	10
+
 /* "Higher level" linux bit combinations */
 #define _PAGE_EXEC		(_PAGE_BAP_SX | _PAGE_BAP_UX) /* .. and was cache cleaned */
-#define _PAGE_RW		(_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */
+#define _PAGE_READ		(_PAGE_BAP_SR | _PAGE_BAP_UR) /* User read permission */
+#define _PAGE_WRITE		(_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */
+
 #define _PAGE_KERNEL_RW		(_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY)
 #define _PAGE_KERNEL_RO		(_PAGE_BAP_SR)
 #define _PAGE_KERNEL_RWX	(_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY | _PAGE_BAP_SX)
 #define _PAGE_KERNEL_ROX	(_PAGE_BAP_SR | _PAGE_BAP_SX)
-#define _PAGE_USER		(_PAGE_BAP_UR | _PAGE_BAP_SR) /* Can be read */
-#define _PAGE_PRIVILEGED	(_PAGE_BAP_SR)
+
+#define _PAGE_NA	0
+#define _PAGE_NAX	_PAGE_BAP_UX
+#define _PAGE_RO	_PAGE_READ
+#define _PAGE_ROX	(_PAGE_READ | _PAGE_BAP_UX)
+#define _PAGE_RW	(_PAGE_READ | _PAGE_WRITE)
+#define _PAGE_RWX	(_PAGE_READ | _PAGE_WRITE | _PAGE_BAP_UX)
 
 #define _PAGE_SPECIAL	_PAGE_SW0
 
-/* Base page size */
-#define _PAGE_PSIZE	_PAGE_PSIZE_4K
 #define	PTE_RPN_SHIFT	(24)
 
 #define PTE_WIMGE_SHIFT (19)
@@ -82,47 +77,64 @@
  * pages. We always set _PAGE_COHERENT when SMP is enabled or
  * the processor might need it for DMA coherency.
  */
-#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_TSIZE_4K)
 #if defined(CONFIG_SMP)
 #define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
 #else
 #define _PAGE_BASE	(_PAGE_BASE_NC)
 #endif
 
-/* Permission masks used to generate the __P and __S table */
-#define PAGE_NONE	__pgprot(_PAGE_BASE)
-#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW)
-#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_BAP_UX)
-#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_BAP_UX)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_BAP_UX)
-
-#ifndef __ASSEMBLY__
-static inline pte_t pte_mkprivileged(pte_t pte)
+#include <asm/pgtable-masks.h>
+
+#ifndef __ASSEMBLER__
+static inline pte_t pte_mkexec(pte_t pte)
 {
-	return __pte((pte_val(pte) & ~_PAGE_USER) | _PAGE_PRIVILEGED);
+	return __pte((pte_val(pte) & ~_PAGE_BAP_SX) | _PAGE_BAP_UX);
 }
+#define pte_mkexec pte_mkexec
 
-#define pte_mkprivileged pte_mkprivileged
+static inline unsigned long pte_huge_size(pte_t pte)
+{
+	pte_basic_t val = pte_val(pte);
 
-static inline pte_t pte_mkuser(pte_t pte)
+	return 1UL << (((val & _PAGE_PSIZE_MSK) >> _PAGE_PSIZE_SHIFT) + _PAGE_PSIZE_SHIFT_OFFSET);
+}
+#define pte_huge_size pte_huge_size
+
+static inline int pmd_leaf(pmd_t pmd)
 {
-	return __pte((pte_val(pte) & ~_PAGE_PRIVILEGED) | _PAGE_USER);
+	if (IS_ENABLED(CONFIG_PPC64))
+		return (long)pmd_val(pmd) > 0;
+	else
+		return pmd_val(pmd) & _PAGE_PSIZE_MSK;
 }
+#define pmd_leaf pmd_leaf
 
-#define pte_mkuser pte_mkuser
+static inline unsigned long pmd_leaf_size(pmd_t pmd)
+{
+	return pte_huge_size(__pte(pmd_val(pmd)));
+}
+#define pmd_leaf_size pmd_leaf_size
 
-static inline pte_t pte_mkexec(pte_t pte)
+#ifdef CONFIG_PPC64
+static inline int pud_leaf(pud_t pud)
 {
-	if (pte_val(pte) & _PAGE_BAP_UR)
-		return __pte((pte_val(pte) & ~_PAGE_BAP_SX) | _PAGE_BAP_UX);
+	if (IS_ENABLED(CONFIG_PPC64))
+		return (long)pud_val(pud) > 0;
 	else
-		return __pte((pte_val(pte) & ~_PAGE_BAP_UX) | _PAGE_BAP_SX);
+		return pud_val(pud) & _PAGE_PSIZE_MSK;
 }
-#define pte_mkexec pte_mkexec
+#define pud_leaf pud_leaf
+
+static inline unsigned long pud_leaf_size(pud_t pud)
+{
+	return pte_huge_size(__pte(pud_val(pud)));
+}
+#define pud_leaf_size pud_leaf_size
+
+#endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __KERNEL__ */
 #endif /*  _ASM_POWERPC_NOHASH_PTE_E500_H */
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index a2bc4b95e703..d3eaa3425797 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -246,7 +246,7 @@
 #define OPAL_CONFIG_IDLE_UNDO		0
 #define OPAL_CONFIG_IDLE_APPLY		1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /* Other enums */
 enum OpalFreezeState {
@@ -1027,10 +1027,10 @@ struct opal_i2c_request {
  * The host will pass on OPAL, a buffer of length OPAL_SYSEPOW_MAX
  * with individual elements being 16 bits wide to fetch the system
  * wide EPOW status. Each element in the buffer will contain the
- * EPOW status in it's bit representation for a particular EPOW sub
+ * EPOW status in its bit representation for a particular EPOW sub
  * class as defined here. So multiple detailed EPOW status bits
  * specific for any sub class can be represented in a single buffer
- * element as it's bit representation.
+ * element as its bit representation.
  */
 
 /* System EPOW type */
@@ -1183,6 +1183,6 @@ struct opal_mpipl_fadump {
 	struct	opal_mpipl_region region[];
 } __packed;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __OPAL_API_H */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 726125a534de..0a398265ba04 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -10,7 +10,7 @@
 
 #include <asm/opal-api.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/notifier.h>
 
@@ -112,9 +112,6 @@ int64_t opal_pci_set_pe(uint64_t phb_id, uint64_t pe_number, uint64_t bus_dev_fu
 			uint8_t pe_action);
 int64_t opal_pci_set_peltv(uint64_t phb_id, uint32_t parent_pe, uint32_t child_pe,
 			   uint8_t state);
-int64_t opal_pci_set_mve(uint64_t phb_id, uint32_t mve_number, uint32_t pe_number);
-int64_t opal_pci_set_mve_enable(uint64_t phb_id, uint32_t mve_number,
-				uint32_t state);
 int64_t opal_pci_get_xive_reissue(uint64_t phb_id, uint32_t xive_number,
 				  uint8_t *p_bit, uint8_t *q_bit);
 int64_t opal_pci_set_xive_reissue(uint64_t phb_id, uint32_t xive_number,
@@ -230,7 +227,7 @@ int64_t opal_pci_set_power_state(uint64_t async_token, uint64_t id,
 				 uint64_t data);
 int64_t opal_pci_poll2(uint64_t id, uint64_t data);
 
-int64_t opal_int_get_xirr(uint32_t *out_xirr, bool just_poll);
+int64_t opal_int_get_xirr(__be32 *out_xirr, bool just_poll);
 int64_t opal_int_set_cppr(uint8_t cppr);
 int64_t opal_int_eoi(uint32_t xirr);
 int64_t opal_int_set_mfrr(uint32_t cpu, uint8_t mfrr);
@@ -316,9 +313,11 @@ extern int early_init_dt_scan_recoverable_ranges(unsigned long node,
 				 const char *uname, int depth, void *data);
 void __init opal_configure_cores(void);
 
-extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
-extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
-extern int opal_put_chars_atomic(uint32_t vtermno, const char *buf, int total_len);
+extern ssize_t opal_get_chars(uint32_t vtermno, u8 *buf, size_t count);
+extern ssize_t opal_put_chars(uint32_t vtermno, const u8 *buf,
+			      size_t total_len);
+extern ssize_t opal_put_chars_atomic(uint32_t vtermno, const u8 *buf,
+				     size_t total_len);
 extern int opal_flush_chars(uint32_t vtermno, bool wait);
 extern int opal_flush_console(uint32_t vtermno);
 
@@ -391,6 +390,6 @@ void opal_powercap_init(void);
 void opal_psr_init(void);
 void opal_sensor_groups_init(void);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_OPAL_H */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index da0377f46597..1d58da946739 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -15,7 +15,6 @@
 #include <linux/cache.h>
 #include <linux/string.h>
 #include <asm/types.h>
-#include <asm/lppaca.h>
 #include <asm/mmu.h>
 #include <asm/page.h>
 #ifdef CONFIG_PPC_BOOK3E_64
@@ -47,14 +46,11 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
 #define get_paca()	local_paca
 #endif
 
-#ifdef CONFIG_PPC_PSERIES
-#define get_lppaca()	(get_paca()->lppaca_ptr)
-#endif
-
 #define get_slb_shadow()	(get_paca()->slb_shadow_ptr)
 
 struct task_struct;
 struct rtas_args;
+struct lppaca;
 
 /*
  * Defines the layout of the paca.
@@ -167,9 +163,7 @@ struct paca_struct {
 	u64 kstack;			/* Saved Kernel stack addr */
 	u64 saved_r1;			/* r1 save for RTAS calls or PM or EE=0 */
 	u64 saved_msr;			/* MSR saved here by enter_rtas */
-#ifdef CONFIG_PPC64
 	u64 exit_save_r1;		/* Syscall/interrupt R1 save */
-#endif
 #ifdef CONFIG_PPC_BOOK3E_64
 	u16 trap_save;			/* Used when bad stack is encountered */
 #endif
@@ -191,6 +185,7 @@ struct paca_struct {
 #ifdef CONFIG_PPC_POWERNV
 	/* PowerNV idle fields */
 	/* PNV_CORE_IDLE_* bits, all siblings work on thread 0 paca */
+	unsigned long idle_lock; /* A value of 1 means acquired */
 	unsigned long idle_state;
 	union {
 		/* P7/P8 specific fields */
@@ -217,8 +212,6 @@ struct paca_struct {
 	/* Non-maskable exceptions that are not performance critical */
 	u64 exnmi[EX_SIZE];	/* used for system reset (nmi) */
 	u64 exmc[EX_SIZE];	/* used for machine checks */
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
 	/* Exclusive stacks for system reset and machine check exception. */
 	void *nmi_emergency_sp;
 	void *mc_emergency_sp;
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index f2b6bf5687d0..b28fbb1d57eb 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -6,9 +6,10 @@
  * Copyright (C) 2001,2005 IBM Corporation.
  */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/bug.h>
 #else
 #include <asm/types.h>
 #endif
@@ -20,10 +21,9 @@
  * page size. When using 64K pages however, whether we are really supporting
  * 64K pages in HW or not is irrelevant to those definitions.
  */
-#define PAGE_SHIFT		CONFIG_PPC_PAGE_SHIFT
-#define PAGE_SIZE		(ASM_CONST(1) << PAGE_SHIFT)
+#include <vdso/page.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifndef CONFIG_HUGETLB_PAGE
 #define HPAGE_SHIFT PAGE_SHIFT
 #elif defined(CONFIG_PPC_BOOK3S_64)
@@ -41,13 +41,6 @@ extern unsigned int hpage_shift;
 #endif
 
 /*
- * Subtle: (1 << PAGE_SHIFT) is an int, not an unsigned long. So if we
- * assign PAGE_MASK to a larger type it gets extended the way we want
- * (i.e. with 1s in the high bits)
- */
-#define PAGE_MASK      (~((1 << PAGE_SHIFT) - 1))
-
-/*
  * KERNELBASE is the virtual address of the start of the kernel, it's often
  * the same as PAGE_OFFSET, but _might not be_.
  *
@@ -82,7 +75,7 @@ extern unsigned int hpage_shift;
 #define LOAD_OFFSET	ASM_CONST((CONFIG_KERNEL_START-CONFIG_PHYSICAL_START))
 
 #if defined(CONFIG_NONSTATIC_KERNEL)
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 extern phys_addr_t memstart_addr;
 extern phys_addr_t kernstart_addr;
@@ -91,7 +84,7 @@ extern phys_addr_t kernstart_addr;
 extern long long virt_phys_offset;
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #define PHYSICAL_START	kernstart_addr
 
 #else	/* !CONFIG_NONSTATIC_KERNEL */
@@ -119,16 +112,6 @@ extern long long virt_phys_offset;
 #define ARCH_PFN_OFFSET		((unsigned long)(MEMORY_START >> PAGE_SHIFT))
 #endif
 
-#define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
-#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
-
-#define virt_addr_valid(vaddr)	({					\
-	unsigned long _addr = (unsigned long)vaddr;			\
-	_addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory &&	\
-	pfn_valid(virt_to_pfn(_addr));					\
-})
-
 /*
  * On Book-E parts we need __va to parse the device tree and we can't
  * determine MEMORY_START until then.  However we can determine PHYSICAL_START
@@ -233,6 +216,25 @@ extern long long virt_phys_offset;
 #endif
 #endif
 
+#ifndef __ASSEMBLER__
+static inline unsigned long virt_to_pfn(const void *kaddr)
+{
+	return __pa(kaddr) >> PAGE_SHIFT;
+}
+
+static inline const void *pfn_to_kaddr(unsigned long pfn)
+{
+	return __va(pfn << PAGE_SHIFT);
+}
+#endif
+
+#define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
+#define virt_addr_valid(vaddr)	({					\
+	unsigned long _addr = (unsigned long)vaddr;			\
+	_addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory &&	\
+	pfn_valid(virt_to_pfn((void *)_addr));				\
+})
+
 /*
  * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI,
  * and needs to be executable.  This means the whole heap ends
@@ -259,39 +261,7 @@ extern long long virt_phys_offset;
 #define is_kernel_addr(x)	((x) >= TASK_SIZE)
 #endif
 
-#ifndef CONFIG_PPC_BOOK3S_64
-/*
- * Use the top bit of the higher-level page table entries to indicate whether
- * the entries we point to contain hugepages.  This works because we know that
- * the page tables live in kernel space.  If we ever decide to support having
- * page tables at arbitrary addresses, this breaks and will have to change.
- */
-#ifdef CONFIG_PPC64
-#define PD_HUGE 0x8000000000000000UL
-#else
-#define PD_HUGE 0x80000000
-#endif
-
-#else	/* CONFIG_PPC_BOOK3S_64 */
-/*
- * Book3S 64 stores real addresses in the hugepd entries to
- * avoid overlaps with _PAGE_PRESENT and _PAGE_PTE.
- */
-#define HUGEPD_ADDR_MASK	(0x0ffffffffffffffful & ~HUGEPD_SHIFT_MASK)
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-/*
- * Some number of bits at the level of the page table that points to
- * a hugepte are used to encode the size.  This masks those bits.
- * On 8xx, HW assistance requires 4k alignment for the hugepte.
- */
-#ifdef CONFIG_PPC_8xx
-#define HUGEPD_SHIFT_MASK     0xfff
-#else
-#define HUGEPD_SHIFT_MASK     0x3f
-#endif
-
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/pgtable-be-types.h>
@@ -320,6 +290,6 @@ static inline unsigned long kaslr_offset(void)
 }
 
 #include <asm-generic/memory_model.h>
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_PAGE_H */
diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h
index 56f217606327..25482405a811 100644
--- a/arch/powerpc/include/asm/page_32.h
+++ b/arch/powerpc/include/asm/page_32.h
@@ -12,10 +12,6 @@
 
 #define VM_DATA_DEFAULT_FLAGS	VM_DATA_DEFAULT_FLAGS32
 
-#ifdef CONFIG_NOT_COHERENT_CACHE
-#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
-#endif
-
 #if defined(CONFIG_PPC_256K_PAGES) || \
     (defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES))
 #define PTE_SHIFT	(PAGE_SHIFT - PTE_T_LOG2 - 2)	/* 1/4 of a page */
@@ -23,7 +19,7 @@
 #define PTE_SHIFT	(PAGE_SHIFT - PTE_T_LOG2)	/* full page */
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * The basic type of a PTE - 64 bits for those CPUs with > 32 bit
  * physical addressing.
@@ -57,6 +53,6 @@ extern void copy_page(void *to, void *from);
 #define PGD_T_LOG2	(__builtin_ffs(sizeof(pgd_t)) - 1)
 #define PTE_T_LOG2	(__builtin_ffs(sizeof(pte_t)) - 1)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_PAGE_32_H */
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 79a9b7c6a132..0f564a06bf68 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -35,7 +35,7 @@
 #define ESID_MASK_1T		0xffffff0000000000UL
 #define GET_ESID_1T(x)		(((x) >> SID_SHIFT_1T) & SID_MASK_1T)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/cache.h>
 
 typedef unsigned long pte_basic_t;
@@ -82,7 +82,7 @@ extern void copy_page(void *to, void *from);
 /* Log 2 of page table size */
 extern u64 ppc64_pft_size;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define VM_DATA_DEFAULT_FLAGS \
 	(is_32bit_task() ? \
diff --git a/arch/powerpc/include/asm/papr-sysparm.h b/arch/powerpc/include/asm/papr-sysparm.h
index f5fdbd8ae9db..a3b5a0d05db6 100644
--- a/arch/powerpc/include/asm/papr-sysparm.h
+++ b/arch/powerpc/include/asm/papr-sysparm.h
@@ -2,8 +2,10 @@
 #ifndef _ASM_POWERPC_PAPR_SYSPARM_H
 #define _ASM_POWERPC_PAPR_SYSPARM_H
 
+#include <uapi/asm/papr-sysparm.h>
+
 typedef struct {
-	const u32 token;
+	u32 token;
 } papr_sysparm_t;
 
 #define mk_papr_sysparm(x_) ((papr_sysparm_t){ .token = x_, })
@@ -19,15 +21,19 @@ typedef struct {
 #define PAPR_SYSPARM_COOP_MEM_OVERCOMMIT_ATTRS     mk_papr_sysparm(44)
 #define PAPR_SYSPARM_TLB_BLOCK_INVALIDATE_ATTRS    mk_papr_sysparm(50)
 #define PAPR_SYSPARM_LPAR_NAME                     mk_papr_sysparm(55)
+#define PAPR_SYSPARM_HVPIPE_ENABLE                 mk_papr_sysparm(64)
 
-enum {
-	PAPR_SYSPARM_MAX_INPUT  = 1024,
-	PAPR_SYSPARM_MAX_OUTPUT = 4000,
-};
-
+/**
+ * struct papr_sysparm_buf - RTAS work area layout for system parameter functions.
+ *
+ * This is the memory layout of the buffers passed to/from
+ * ibm,get-system-parameter and ibm,set-system-parameter. It is
+ * distinct from the papr_sysparm_io_block structure that is passed
+ * between user space and the kernel.
+ */
 struct papr_sysparm_buf {
 	__be16 len;
-	char val[PAPR_SYSPARM_MAX_OUTPUT];
+	u8 val[PAPR_SYSPARM_MAX_OUTPUT];
 };
 
 struct papr_sysparm_buf *papr_sysparm_buf_alloc(void);
diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h
index f5ba1a3c41f8..b78b82d66057 100644
--- a/arch/powerpc/include/asm/paravirt.h
+++ b/arch/powerpc/include/asm/paravirt.h
@@ -6,6 +6,7 @@
 #include <asm/smp.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
+#include <asm/lppaca.h>
 #include <asm/hvcall.h>
 #endif
 
@@ -70,6 +71,22 @@ static inline void yield_to_any(void)
 {
 	plpar_hcall_norets_notrace(H_CONFER, -1, 0);
 }
+
+static inline bool is_vcpu_idle(int vcpu)
+{
+	return lppaca_of(vcpu).idle;
+}
+
+static inline bool vcpu_is_dispatched(int vcpu)
+{
+	/*
+	 * This is the yield_count.  An "odd" value (low bit on) means that
+	 * the processor is yielded (either because of an OS yield or a
+	 * hypervisor preempt).  An even value implies that the processor is
+	 * currently executing.
+	 */
+	return (!(yield_count_of(vcpu) & 1));
+}
 #else
 static inline bool is_shared_processor(void)
 {
@@ -99,6 +116,14 @@ static inline void prod_cpu(int cpu)
 	___bad_prod_cpu(); /* This would be a bug */
 }
 
+static inline bool is_vcpu_idle(int vcpu)
+{
+	return false;
+}
+static inline bool vcpu_is_dispatched(int vcpu)
+{
+	return true;
+}
 #endif
 
 #define vcpu_is_preempted vcpu_is_preempted
@@ -120,9 +145,23 @@ static inline bool vcpu_is_preempted(int cpu)
 	if (!is_shared_processor())
 		return false;
 
+	/*
+	 * If the hypervisor has dispatched the target CPU on a physical
+	 * processor, then the target CPU is definitely not preempted.
+	 */
+	if (vcpu_is_dispatched(cpu))
+		return false;
+
+	/*
+	 * if the target CPU is not dispatched and the guest OS
+	 * has not marked the CPU idle, then it is hypervisor preempted.
+	 */
+	if (!is_vcpu_idle(cpu))
+		return true;
+
 #ifdef CONFIG_PPC_SPLPAR
 	if (!is_kvm_guest()) {
-		int first_cpu;
+		int first_cpu, i;
 
 		/*
 		 * The result of vcpu_is_preempted() is used in a
@@ -142,17 +181,37 @@ static inline bool vcpu_is_preempted(int cpu)
 
 		/*
 		 * The PowerVM hypervisor dispatches VMs on a whole core
-		 * basis. So we know that a thread sibling of the local CPU
+		 * basis. So we know that a thread sibling of the executing CPU
 		 * cannot have been preempted by the hypervisor, even if it
 		 * has called H_CONFER, which will set the yield bit.
 		 */
 		if (cpu_first_thread_sibling(cpu) == first_cpu)
 			return false;
+
+		/*
+		 * The specific target CPU was marked by guest OS as idle, but
+		 * then also check all other cpus in the core for PowerVM
+		 * because it does core scheduling and one of the vcpu
+		 * of the core getting preempted by hypervisor implies
+		 * other vcpus can also be considered preempted.
+		 */
+		first_cpu = cpu_first_thread_sibling(cpu);
+		for (i = first_cpu; i < first_cpu + threads_per_core; i++) {
+			if (i == cpu)
+				continue;
+			if (vcpu_is_dispatched(i))
+				return false;
+			if (!is_vcpu_idle(i))
+				return true;
+		}
 	}
 #endif
 
-	if (yield_count_of(cpu) & 1)
-		return true;
+	/*
+	 * None of the threads in target CPU's core are running but none of
+	 * them were preempted too. Hence assume the target CPU to be
+	 * non-preempted.
+	 */
 	return false;
 }
 
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 2aa3a091ef20..1dae53130782 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -133,8 +133,6 @@ struct pci_controller {
 
 	/* IRQ domain hierarchy */
 	struct irq_domain	*dev_domain;
-	struct irq_domain	*msi_domain;
-	struct fwnode_handle	*fwnode;
 
 	/* iommu_ops support */
 	struct iommu_device	iommu;
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 289f1ec85bc5..46a9c4491ed0 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -82,7 +82,8 @@ extern int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val,
 extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
 				      struct vm_area_struct *vma,
 				      enum pci_mmap_state mmap_state);
-
+extern void pci_adjust_legacy_attr(struct pci_bus *bus,
+				   enum pci_mmap_state mmap_type);
 #define HAVE_PCI_LEGACY	1
 
 extern void pcibios_claim_one_bus(struct pci_bus *b);
@@ -104,9 +105,7 @@ extern void of_scan_pci_bridge(struct pci_dev *dev);
 extern void of_scan_bus(struct device_node *node, struct pci_bus *bus);
 extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus);
 
-struct file;
-extern pgprot_t	pci_phys_mem_access_prot(struct file *file,
-					 unsigned long pfn,
+extern pgprot_t	pci_phys_mem_access_prot(unsigned long pfn,
 					 unsigned long size,
 					 pgprot_t prot);
 
diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h
index 8e5b7d0b851c..ecf5ac70cfae 100644
--- a/arch/powerpc/include/asm/percpu.h
+++ b/arch/powerpc/include/asm/percpu.h
@@ -15,6 +15,16 @@
 #endif /* CONFIG_SMP */
 #endif /* __powerpc64__ */
 
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) && defined(CONFIG_SMP)
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
+
+#define percpu_first_chunk_is_paged	\
+		(static_key_enabled(&__percpu_first_chunk_is_paged.key))
+#else
+#define percpu_first_chunk_is_paged	false
+#endif
+
 #include <asm-generic/percpu.h>
 
 #include <asm/paca.h>
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index e2221d29fdf9..af0f46e2373b 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -89,7 +89,8 @@ struct power_pmu {
 #define PPMU_NO_SIAR		0x00000100 /* Do not use SIAR */
 #define PPMU_ARCH_31		0x00000200 /* Has MMCR3, SIER2 and SIER3 */
 #define PPMU_P10_DD1		0x00000400 /* Is power10 DD1 processor version */
-#define PPMU_HAS_ATTR_CONFIG1	0x00000800 /* Using config1 attribute */
+#define PPMU_P10		0x00000800 /* For power10 pmu */
+#define PPMU_HAS_ATTR_CONFIG1	0x00001000 /* Using config1 attribute */
 
 /*
  * Values for flags to get_alternatives()
@@ -101,8 +102,8 @@ struct power_pmu {
 int __init register_power_pmu(struct power_pmu *pmu);
 
 struct pt_regs;
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_arch_misc_flags(struct pt_regs *regs);
+extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
 extern unsigned long int read_bhrb(int n);
 
 /*
@@ -110,7 +111,7 @@ extern unsigned long int read_bhrb(int n);
  * if we have hardware PMU support.
  */
 #ifdef CONFIG_PPC_PERF_CTRS
-#define perf_misc_flags(regs)	perf_misc_flags(regs)
+#define perf_arch_misc_flags(regs)	perf_arch_misc_flags(regs)
 #endif
 
 /*
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index 3360cad78ace..3a971e2a8c73 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -45,6 +45,10 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 	pte_fragment_free((unsigned long *)ptepage, 0);
 }
 
+/* arch use pte_free_defer() implementation in arch/powerpc/mm/pgtable-frag.c */
+#define pte_free_defer pte_free_defer
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);
+
 /*
  * Functions that deal with pagetables that could be at any level of
  * the table need to be passed an "index_size" so they know how to
diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h
index 82633200b500..6bd8f89b25dc 100644
--- a/arch/powerpc/include/asm/pgtable-be-types.h
+++ b/arch/powerpc/include/asm/pgtable-be-types.h
@@ -101,14 +101,4 @@ static inline bool pmd_xchg(pmd_t *pmdp, pmd_t old, pmd_t new)
 	return pmd_raw(old) == prev;
 }
 
-#ifdef CONFIG_ARCH_HAS_HUGEPD
-typedef struct { __be64 pdbe; } hugepd_t;
-#define __hugepd(x) ((hugepd_t) { cpu_to_be64(x) })
-
-static inline unsigned long hpd_val(hugepd_t x)
-{
-	return be64_to_cpu(x.pdbe);
-}
-#endif
-
 #endif /* _ASM_POWERPC_PGTABLE_BE_TYPES_H */
diff --git a/arch/powerpc/include/asm/pgtable-masks.h b/arch/powerpc/include/asm/pgtable-masks.h
new file mode 100644
index 000000000000..6e8e2db26a5a
--- /dev/null
+++ b/arch/powerpc/include/asm/pgtable-masks.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_PGTABLE_MASKS_H
+#define _ASM_POWERPC_PGTABLE_MASKS_H
+
+#ifndef _PAGE_NA
+#define _PAGE_NA	0
+#define _PAGE_NAX	_PAGE_EXEC
+#define _PAGE_RO	_PAGE_READ
+#define _PAGE_ROX	(_PAGE_READ | _PAGE_EXEC)
+#define _PAGE_RW	(_PAGE_READ | _PAGE_WRITE)
+#define _PAGE_RWX	(_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
+#endif
+
+/* Permission flags for kernel mappings */
+#ifndef _PAGE_KERNEL_RO
+#define _PAGE_KERNEL_RO		_PAGE_RO
+#define _PAGE_KERNEL_ROX	_PAGE_ROX
+#define _PAGE_KERNEL_RW		(_PAGE_RW | _PAGE_DIRTY)
+#define _PAGE_KERNEL_RWX	(_PAGE_RWX | _PAGE_DIRTY)
+#endif
+
+/* Permission masks used to generate the __P and __S table */
+#define PAGE_NONE	__pgprot(_PAGE_BASE | _PAGE_NA)
+#define PAGE_EXECONLY_X	__pgprot(_PAGE_BASE | _PAGE_NAX)
+#define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_RW)
+#define PAGE_SHARED_X	__pgprot(_PAGE_BASE | _PAGE_RWX)
+#define PAGE_COPY	__pgprot(_PAGE_BASE | _PAGE_RO)
+#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_ROX)
+#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_RO)
+#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_ROX)
+
+#endif /* _ASM_POWERPC_PGTABLE_MASKS_H */
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index 082c85cc09b1..f3086e39e7d2 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -49,12 +49,22 @@ static inline unsigned long pud_val(pud_t x)
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
+#if defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT)
+typedef struct { unsigned long long pgd; } pgd_t;
+
+static inline unsigned long long pgd_val(pgd_t x)
+{
+	return x.pgd;
+}
+#else
 typedef struct { unsigned long pgd; } pgd_t;
-#define __pgd(x)	((pgd_t) { (x) })
+
 static inline unsigned long pgd_val(pgd_t x)
 {
 	return x.pgd;
 }
+#endif
+#define __pgd(x)	((pgd_t) { (x) })
 
 /* Page protection bits */
 typedef struct { unsigned long pgprot; } pgprot_t;
@@ -83,13 +93,4 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new)
 }
 #endif
 
-#ifdef CONFIG_ARCH_HAS_HUGEPD
-typedef struct { unsigned long pd; } hugepd_t;
-#define __hugepd(x) ((hugepd_t) { (x) })
-static inline unsigned long hpd_val(hugepd_t x)
-{
-	return x.pd;
-}
-#endif
-
 #endif /* _ASM_POWERPC_PGTABLE_TYPES_H */
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 9972626ddaf6..17fd7ff6e535 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_POWERPC_PGTABLE_H
 #define _ASM_POWERPC_PGTABLE_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/mmdebug.h>
 #include <linux/mmzone.h>
 #include <asm/processor.h>		/* For TASK_SIZE */
@@ -12,7 +12,7 @@
 
 struct mm_struct;
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #ifdef CONFIG_PPC_BOOK3S
 #include <asm/book3s/pgtable.h>
@@ -20,18 +20,6 @@ struct mm_struct;
 #include <asm/nohash/pgtable.h>
 #endif /* !CONFIG_PPC_BOOK3S */
 
-/*
- * Protection used for kernel text. We want the debuggers to be able to
- * set breakpoints anywhere, so don't write protect the kernel text
- * on platforms where such control is possible.
- */
-#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) || \
-	defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE)
-#define PAGE_KERNEL_TEXT	PAGE_KERNEL_X
-#else
-#define PAGE_KERNEL_TEXT	PAGE_KERNEL_ROX
-#endif
-
 /* Make modules code happy. We don't set RO yet */
 #define PAGE_KERNEL_EXEC	PAGE_KERNEL_X
 
@@ -39,18 +27,32 @@ struct mm_struct;
 #define PAGE_AGP		(PAGE_KERNEL_NC)
 #define HAVE_PAGE_AGP
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
+
+#define PFN_PTE_SHIFT		PTE_RPN_SHIFT
+
+void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		pte_t pte, unsigned int nr);
+#define set_ptes set_ptes
+#define update_mmu_cache(vma, addr, ptep) \
+	update_mmu_cache_range(NULL, vma, addr, ptep, 1)
 
 #ifndef MAX_PTRS_PER_PGD
 #define MAX_PTRS_PER_PGD PTRS_PER_PGD
 #endif
 
-/* Keep these as a macros to avoid include dependency mess */
+/* Keep this as a macro to avoid include dependency mess */
 #define pte_page(x)		pfn_to_page(pte_pfn(x))
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return (pte_val(pte) & PTE_RPN_MASK) >> PTE_RPN_SHIFT;
+}
+
 /*
  * Select all bits except the pfn
  */
+#define pte_pgprot pte_pgprot
 static inline pgprot_t pte_pgprot(pte_t pte)
 {
 	unsigned long pte_flags;
@@ -59,10 +61,16 @@ static inline pgprot_t pte_pgprot(pte_t pte)
 	return __pgprot(pte_flags);
 }
 
+static inline pgprot_t pgprot_nx(pgprot_t prot)
+{
+	return pte_pgprot(pte_exprotect(__pte(pgprot_val(prot))));
+}
+#define pgprot_nx pgprot_nx
+
 #ifndef pmd_page_vaddr
-static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+static inline const void *pmd_page_vaddr(pmd_t pmd)
 {
-	return ((unsigned long)__va(pmd_val(pmd) & ~PMD_MASKED_BITS));
+	return __va(pmd_val(pmd) & ~PMD_MASKED_BITS);
 }
 #define pmd_page_vaddr pmd_page_vaddr
 #endif
@@ -81,15 +89,14 @@ void poking_init(void);
 extern unsigned long ioremap_bot;
 extern const pgprot_t protection_map[16];
 
-#ifndef CONFIG_TRANSPARENT_HUGEPAGE
-#define pmd_large(pmd)		0
-#endif
-
 /* can we use this in kvm */
 unsigned long vmalloc_to_phys(void *vmalloc_addr);
 
 void pgtable_cache_add(unsigned int shift);
 
+#ifdef CONFIG_PPC32
+void __init *early_alloc_pgtable(unsigned long size);
+#endif
 pte_t *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va);
 
 #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32)
@@ -98,6 +105,41 @@ void mark_initmem_nx(void);
 static inline void mark_initmem_nx(void) { }
 #endif
 
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+			  pte_t *ptep, pte_t entry, int dirty);
+
+pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size,
+				pgprot_t vma_prot);
+
+struct file;
+static inline pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+					    unsigned long size, pgprot_t vma_prot)
+{
+	return __phys_mem_access_prot(pfn, size, vma_prot);
+}
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+
+void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep);
+
+/*
+ * This gets called at the end of handling a page fault, when
+ * the kernel has put a new PTE into the page table for the process.
+ * We use it to ensure coherency between the i-cache and d-cache
+ * for the page which has just been mapped in.
+ * On machines which use an MMU hash table, we use this to put a
+ * corresponding HPTE into the hash table ahead of time, instead of
+ * waiting for the inevitable extra hash-table miss exception.
+ */
+static inline void update_mmu_cache_range(struct vm_fault *vmf,
+		struct vm_area_struct *vma, unsigned long address,
+		pte_t *ptep, unsigned int nr)
+{
+	if ((mmu_has_feature(MMU_FTR_HPTE_TABLE) && !radix_enabled()) ||
+	    (IS_ENABLED(CONFIG_PPC_E500) && IS_ENABLED(CONFIG_HUGETLB_PAGE)))
+		__update_mmu_cache(vma, address, ptep);
+}
+
 /*
  * When used, PTE_FRAG_NR is defined in subarch pgtable.h
  * so we are sure it is included when arriving here.
@@ -127,30 +169,6 @@ static inline void pte_frag_set(mm_context_t *ctx, void *p)
 }
 #endif
 
-#ifndef pmd_is_leaf
-#define pmd_is_leaf pmd_is_leaf
-static inline bool pmd_is_leaf(pmd_t pmd)
-{
-	return false;
-}
-#endif
-
-#ifndef pud_is_leaf
-#define pud_is_leaf pud_is_leaf
-static inline bool pud_is_leaf(pud_t pud)
-{
-	return false;
-}
-#endif
-
-#ifndef p4d_is_leaf
-#define p4d_is_leaf p4d_is_leaf
-static inline bool p4d_is_leaf(p4d_t p4d)
-{
-	return false;
-}
-#endif
-
 #define pmd_pgtable pmd_pgtable
 static inline pgtable_t pmd_pgtable(pmd_t pmd)
 {
@@ -158,18 +176,32 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd)
 }
 
 #ifdef CONFIG_PPC64
-#define is_ioremap_addr is_ioremap_addr
-static inline bool is_ioremap_addr(const void *x)
+int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size);
+bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start,
+			   unsigned long page_size);
+/*
+ * mm/memory_hotplug.c:mhp_supports_memmap_on_memory goes into details
+ * some of the restrictions. We don't check for PMD_SIZE because our
+ * vmemmap allocation code can fallback correctly. The pageblock
+ * alignment requirement is met using altmap->reserve blocks.
+ */
+#define arch_supports_memmap_on_memory arch_supports_memmap_on_memory
+static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size)
 {
-	unsigned long addr = (unsigned long)x;
-
-	return addr >= IOREMAP_BASE && addr < IOREMAP_END;
+	if (!radix_enabled())
+		return false;
+	/*
+	 * With 4K page size and 2M PMD_SIZE, we can align
+	 * things better with memory block size value
+	 * starting from 128MB. Hence align things with PMD_SIZE.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES))
+		return IS_ALIGNED(vmemmap_size, PMD_SIZE);
+	return true;
 }
 
-struct seq_file;
-void arch_report_meminfo(struct seq_file *m);
 #endif /* CONFIG_PPC64 */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/pkeys.h b/arch/powerpc/include/asm/pkeys.h
index 59a2c7dbc78f..28e752138996 100644
--- a/arch/powerpc/include/asm/pkeys.h
+++ b/arch/powerpc/include/asm/pkeys.h
@@ -30,9 +30,9 @@ extern u32 reserved_allocation_mask; /* bits set for reserved keys */
 #endif
 
 
-static inline u64 pkey_to_vmflag_bits(u16 pkey)
+static inline vm_flags_t pkey_to_vmflag_bits(u16 pkey)
 {
-	return (((u64)pkey << VM_PKEY_SHIFT) & ARCH_VM_PKEY_FLAGS);
+	return (((vm_flags_t)pkey << VM_PKEY_SHIFT) & ARCH_VM_PKEY_FLAGS);
 }
 
 static inline int vma_pkey(struct vm_area_struct *vma)
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index 8239c0af5eb2..f2b6cc4341bb 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -6,9 +6,11 @@
 
 #include <linux/string.h>
 #include <linux/irqflags.h>
+#include <linux/delay.h>
 
 #include <asm/hvcall.h>
 #include <asm/paca.h>
+#include <asm/lppaca.h>
 #include <asm/page.h>
 
 static inline long poll_pending(void)
@@ -16,16 +18,6 @@ static inline long poll_pending(void)
 	return plpar_hcall_norets(H_POLL_PENDING);
 }
 
-static inline u8 get_cede_latency_hint(void)
-{
-	return get_lppaca()->cede_latency_hint;
-}
-
-static inline void set_cede_latency_hint(u8 latency_hint)
-{
-	get_lppaca()->cede_latency_hint = latency_hint;
-}
-
 static inline long cede_processor(void)
 {
 	/*
@@ -35,24 +27,6 @@ static inline long cede_processor(void)
 	return plpar_hcall_norets_notrace(H_CEDE);
 }
 
-static inline long extended_cede_processor(unsigned long latency_hint)
-{
-	long rc;
-	u8 old_latency_hint = get_cede_latency_hint();
-
-	set_cede_latency_hint(latency_hint);
-
-	rc = cede_processor();
-
-	/* Ensure that H_CEDE returns with IRQs on */
-	if (WARN_ON(IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && !(mfmsr() & MSR_EE)))
-		__hard_irq_enable();
-
-	set_cede_latency_hint(old_latency_hint);
-
-	return rc;
-}
-
 static inline long vpa_call(unsigned long flags, unsigned long cpu,
 		unsigned long vpa)
 {
@@ -91,6 +65,35 @@ static inline long register_dtl(unsigned long cpu, unsigned long vpa)
 	return vpa_call(H_VPA_REG_DTL, cpu, vpa);
 }
 
+/*
+ * Invokes H_HTM hcall with parameters passed from htm_hcall_wrapper.
+ * flags: Set to hardwareTarget.
+ * target: Specifies target using node index, nodal chip index and core index.
+ * operation : action to perform ie configure, start, stop, deconfigure, trace
+ * based on the HTM type.
+ * param1, param2, param3: parameters for each action.
+ */
+static inline long htm_call(unsigned long flags, unsigned long target,
+               unsigned long operation, unsigned long param1,
+               unsigned long param2, unsigned long param3)
+{
+       return plpar_hcall_norets(H_HTM, flags, target, operation,
+                                 param1, param2, param3);
+}
+
+static inline long htm_hcall_wrapper(unsigned long flags, unsigned long nodeindex,
+               unsigned long nodalchipindex, unsigned long coreindexonchip,
+	       unsigned long type, unsigned long htm_op, unsigned long param1, unsigned long param2,
+	       unsigned long param3)
+{
+	return htm_call(H_HTM_FLAGS_HARDWARE_TARGET | flags,
+                       H_HTM_TARGET_NODE_INDEX(nodeindex) |
+                       H_HTM_TARGET_NODAL_CHIP_INDEX(nodalchipindex) |
+                       H_HTM_TARGET_CORE_INDEX_ON_CHIP(coreindexonchip),
+		       H_HTM_OP(htm_op) | H_HTM_TYPE(type),
+		       param1, param2, param3);
+}
+
 extern void vpa_init(int cpu);
 
 static inline long plpar_pte_enter(unsigned long flags,
@@ -342,6 +345,212 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
 	return rc;
 }
 
+static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	unsigned long token;
+	long rc;
+
+	token = -1UL;
+	do {
+		rc = plpar_hcall(H_GUEST_CREATE, retbuf, flags, token);
+		if (rc == H_SUCCESS)
+			*guest_id = retbuf[0];
+
+		if (rc == H_BUSY) {
+			token = retbuf[0];
+			cond_resched();
+		}
+
+		if (H_IS_LONG_BUSY(rc)) {
+			token = retbuf[0];
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_create_vcpu(unsigned long flags,
+					   unsigned long guest_id,
+					   unsigned long vcpu_id)
+{
+	long rc;
+
+	do {
+		rc = plpar_hcall_norets(H_GUEST_CREATE_VCPU, 0, guest_id, vcpu_id);
+
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_set_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	while (true) {
+		rc = plpar_hcall(H_GUEST_SET_STATE, retbuf, flags, guest_id,
+				 vcpu_id, data_buffer, data_size);
+
+		if (rc == H_BUSY) {
+			cpu_relax();
+			continue;
+		}
+
+		if (H_IS_LONG_BUSY(rc)) {
+			mdelay(get_longbusy_msecs(rc));
+			continue;
+		}
+
+		if (rc == H_INVALID_ELEMENT_ID)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_SIZE)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_VALUE)
+			*failed_index = retbuf[0];
+
+		break;
+	}
+
+	return rc;
+}
+
+static inline long plpar_guest_get_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	while (true) {
+		rc = plpar_hcall(H_GUEST_GET_STATE, retbuf, flags, guest_id,
+				 vcpu_id, data_buffer, data_size);
+
+		if (rc == H_BUSY) {
+			cpu_relax();
+			continue;
+		}
+
+		if (H_IS_LONG_BUSY(rc)) {
+			mdelay(get_longbusy_msecs(rc));
+			continue;
+		}
+
+		if (rc == H_INVALID_ELEMENT_ID)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_SIZE)
+			*failed_index = retbuf[0];
+		else if (rc == H_INVALID_ELEMENT_VALUE)
+			*failed_index = retbuf[0];
+
+		break;
+	}
+
+	return rc;
+}
+
+static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id,
+					unsigned long vcpu_id, int *trap,
+					unsigned long *failed_index)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	rc = plpar_hcall(H_GUEST_RUN_VCPU, retbuf, flags, guest_id, vcpu_id);
+	if (rc == H_SUCCESS)
+		*trap = retbuf[0];
+	else if (rc == H_INVALID_ELEMENT_ID)
+		*failed_index = retbuf[0];
+	else if (rc == H_INVALID_ELEMENT_SIZE)
+		*failed_index = retbuf[0];
+	else if (rc == H_INVALID_ELEMENT_VALUE)
+		*failed_index = retbuf[0];
+
+	return rc;
+}
+
+static inline long plpar_guest_delete(unsigned long flags, u64 guest_id)
+{
+	long rc;
+
+	do {
+		rc = plpar_hcall_norets(H_GUEST_DELETE, flags, guest_id);
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_set_capabilities(unsigned long flags,
+						unsigned long capabilities)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	do {
+		rc = plpar_hcall(H_GUEST_SET_CAPABILITIES, retbuf, flags, capabilities);
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+	} while (rc == H_BUSY);
+
+	return rc;
+}
+
+static inline long plpar_guest_get_capabilities(unsigned long flags,
+						unsigned long *capabilities)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	do {
+		rc = plpar_hcall(H_GUEST_GET_CAPABILITIES, retbuf, flags);
+		if (rc == H_BUSY)
+			cond_resched();
+
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		}
+	} while (rc == H_BUSY);
+
+	if (rc == H_SUCCESS)
+		*capabilities = retbuf[0];
+
+	return rc;
+}
+
 /*
  * Wrapper to H_RPT_INVALIDATE hcall that handles return values appropriately
  *
@@ -354,7 +563,7 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
  * error recovery of killing the process/guest will be eventually
  * needed.
  */
-static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type,
+static inline long pseries_rpt_invalidate(u64 pid, u64 target, u64 type,
 					  u64 page_sizes, u64 start, u64 end)
 {
 	long rc;
@@ -400,12 +609,68 @@ static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex,
 	return 0;
 }
 
-static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type,
+static inline long pseries_rpt_invalidate(u64 pid, u64 target, u64 type,
 					  u64 page_sizes, u64 start, u64 end)
 {
 	return 0;
 }
 
+static inline long plpar_guest_create_vcpu(unsigned long flags,
+					   unsigned long guest_id,
+					   unsigned long vcpu_id)
+{
+	return 0;
+}
+
+static inline long plpar_guest_get_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	return 0;
+}
+
+static inline long plpar_guest_set_state(unsigned long flags,
+					 unsigned long guest_id,
+					 unsigned long vcpu_id,
+					 unsigned long data_buffer,
+					 unsigned long data_size,
+					 unsigned long *failed_index)
+{
+	return 0;
+}
+
+static inline long plpar_guest_run_vcpu(unsigned long flags, unsigned long guest_id,
+					unsigned long vcpu_id, int *trap,
+					unsigned long *failed_index)
+{
+	return 0;
+}
+
+static inline long plpar_guest_create(unsigned long flags, unsigned long *guest_id)
+{
+	return 0;
+}
+
+static inline long plpar_guest_delete(unsigned long flags, u64 guest_id)
+{
+	return 0;
+}
+
+static inline long plpar_guest_get_capabilities(unsigned long flags,
+						unsigned long *capabilities)
+{
+	return 0;
+}
+
+static inline long plpar_guest_set_capabilities(unsigned long flags,
+						unsigned long capabilities)
+{
+	return 0;
+}
+
 #endif /* CONFIG_PPC_PSERIES */
 
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
diff --git a/arch/powerpc/include/asm/plpks.h b/arch/powerpc/include/asm/plpks.h
index 23b77027c916..7a84069759b0 100644
--- a/arch/powerpc/include/asm/plpks.h
+++ b/arch/powerpc/include/asm/plpks.h
@@ -44,9 +44,8 @@
 #define PLPKS_MAX_DATA_SIZE		4000
 
 // Timeouts for PLPKS operations
-#define PLPKS_MAX_TIMEOUT		5000 // msec
-#define PLPKS_FLUSH_SLEEP		10 // msec
-#define PLPKS_FLUSH_SLEEP_RANGE		400
+#define PLPKS_MAX_TIMEOUT		(5 * USEC_PER_SEC)
+#define PLPKS_FLUSH_SLEEP		10000 // usec
 
 struct plpks_var {
 	char *component;
diff --git a/arch/powerpc/include/asm/pmac_feature.h b/arch/powerpc/include/asm/pmac_feature.h
index 2495866f2e97..420e2878ae67 100644
--- a/arch/powerpc/include/asm/pmac_feature.h
+++ b/arch/powerpc/include/asm/pmac_feature.h
@@ -192,7 +192,7 @@ static inline long pmac_call_feature(int selector, struct device_node* node,
 
 /* PMAC_FTR_BMAC_ENABLE		(struct device_node* node, 0, int value)
  * enable/disable the bmac (ethernet) cell of a mac-io ASIC, also drive
- * it's reset line
+ * its reset line
  */
 #define PMAC_FTR_BMAC_ENABLE		PMAC_FTR_DEF(6)
 
diff --git a/arch/powerpc/include/asm/pmi.h b/arch/powerpc/include/asm/pmi.h
deleted file mode 100644
index 478f0a2fe7f4..000000000000
--- a/arch/powerpc/include/asm/pmi.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _POWERPC_PMI_H
-#define _POWERPC_PMI_H
-
-/*
- * Definitions for talking with PMI device on PowerPC
- *
- * PMI (Platform Management Interrupt) is a way to communicate
- * with the BMC (Baseboard Management Controller) via interrupts.
- * Unlike IPMI it is bidirectional and has a low latency.
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#ifdef __KERNEL__
-
-#define PMI_TYPE_FREQ_CHANGE	0x01
-#define PMI_TYPE_POWER_BUTTON	0x02
-#define PMI_READ_TYPE		0
-#define PMI_READ_DATA0		1
-#define PMI_READ_DATA1		2
-#define PMI_READ_DATA2		3
-#define PMI_WRITE_TYPE		4
-#define PMI_WRITE_DATA0		5
-#define PMI_WRITE_DATA1		6
-#define PMI_WRITE_DATA2		7
-
-#define PMI_ACK			0x80
-
-#define PMI_TIMEOUT		100
-
-typedef struct {
-	u8	type;
-	u8	data0;
-	u8	data1;
-	u8	data2;
-} pmi_message_t;
-
-struct pmi_handler {
-	struct list_head node;
-	u8 type;
-	void (*handle_pmi_message) (pmi_message_t);
-};
-
-int pmi_register_handler(struct pmi_handler *);
-void pmi_unregister_handler(struct pmi_handler *);
-
-int pmi_send_message(pmi_message_t);
-
-#endif /* __KERNEL__ */
-#endif /* _POWERPC_PMI_H */
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
index 8afc92860dbb..7e9a479951a3 100644
--- a/arch/powerpc/include/asm/pnv-pci.h
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -10,7 +10,6 @@
 #include <linux/pci_hotplug.h>
 #include <linux/irq.h>
 #include <linux/of.h>
-#include <misc/cxl-base.h>
 #include <asm/opal-api.h>
 
 #define PCI_SLOT_ID_PREFIX	(1UL << 63)
@@ -25,25 +24,9 @@ extern int pnv_pci_get_power_state(uint64_t id, uint8_t *state);
 extern int pnv_pci_set_power_state(uint64_t id, uint8_t state,
 				   struct opal_msg *msg);
 
-extern int pnv_pci_set_tunnel_bar(struct pci_dev *dev, uint64_t addr,
-				  int enable);
-int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode);
-int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
-			   unsigned int virq);
-int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num);
-void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num);
-int pnv_cxl_get_irq_count(struct pci_dev *dev);
-struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev);
 int64_t pnv_opal_pci_msi_eoi(struct irq_data *d);
 bool is_pnv_opal_msi(struct irq_chip *chip);
 
-#ifdef CONFIG_CXL_BASE
-int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
-			       struct pci_dev *dev, int num);
-void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
-				  struct pci_dev *dev);
-#endif
-
 struct pnv_php_slot {
 	struct hotplug_slot		slot;
 	uint64_t			id;
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index ca5a0da7df4e..55ca49d18319 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -222,6 +222,7 @@
 #define OP_31_XOP_STFSX	    663
 #define OP_31_XOP_STFSUX    695
 #define OP_31_XOP_STFDX     727
+#define OP_31_XOP_HASHCHK   754
 #define OP_31_XOP_STFDUX    759
 #define OP_31_XOP_LHBRX     790
 #define OP_31_XOP_LFIWAX    855
@@ -396,6 +397,7 @@
 #define PPC_RAW_RFCI			(0x4c000066)
 #define PPC_RAW_RFDI			(0x4c00004e)
 #define PPC_RAW_RFMCI			(0x4c00004c)
+#define PPC_RAW_TLBILX_LPID		(0x7c000024)
 #define PPC_RAW_TLBILX(t, a, b)		(0x7c000024 | __PPC_T_TLB(t) | 	__PPC_RA0(a) | __PPC_RB(b))
 #define PPC_RAW_WAIT_v203		(0x7c00007c)
 #define PPC_RAW_WAIT(w, p)		(0x7c00003c | __PPC_WC(w) | __PPC_PL(p))
@@ -423,6 +425,7 @@
 #define PPC_RAW_SC()			(0x44000002)
 #define PPC_RAW_SYNC()			(0x7c0004ac)
 #define PPC_RAW_ISYNC()			(0x4c00012c)
+#define PPC_RAW_LWSYNC()		(0x7c2004ac)
 
 /*
  * Define what the VSX XX1 form instructions will look like, then add
@@ -469,6 +472,7 @@
 #define PPC_RAW_VCMPEQUB_RC(vrt, vra, vrb) \
 	(0x10000006 | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | __PPC_RC21)
 #define PPC_RAW_LD(r, base, i)		(0xe8000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_DS(i))
+#define PPC_RAW_LWA(r, base, i)		(0xe8000002 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_DS(i))
 #define PPC_RAW_LWZ(r, base, i)		(0x80000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
 #define PPC_RAW_LWZX(t, a, b)		(0x7c00002e | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_STD(r, base, i)		(0xf8000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_DS(i))
@@ -508,6 +512,7 @@
 #define PPC_RAW_STB(r, base, i)		(0x98000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i))
 #define PPC_RAW_LBZ(r, base, i)		(0x88000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
 #define PPC_RAW_LDX(r, base, b)		(0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
+#define PPC_RAW_LHA(r, base, i)		(0xa8000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
 #define PPC_RAW_LHZ(r, base, i)		(0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i))
 #define PPC_RAW_LHBRX(r, base, b)	(0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
 #define PPC_RAW_LWBRX(r, base, b)	(0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b))
@@ -530,7 +535,9 @@
 #define PPC_RAW_MULW(d, a, b)		(0x7c0001d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_MULHWU(d, a, b)		(0x7c000016 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_MULI(d, a, i)		(0x1c000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i))
+#define PPC_RAW_DIVW(d, a, b)		(0x7c0003d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_DIVWU(d, a, b)		(0x7c000396 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_RAW_DIVD(d, a, b)		(0x7c0003d2 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_DIVDU(d, a, b)		(0x7c000392 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_DIVDE(t, a, b)		(0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_DIVDE_DOT(t, a, b)	(0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1)
@@ -548,6 +555,8 @@
 #define PPC_RAW_XOR(d, a, b)		(0x7c000278 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b))
 #define PPC_RAW_XORI(d, a, i)		(0x68000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i))
 #define PPC_RAW_XORIS(d, a, i)		(0x6c000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i))
+#define PPC_RAW_EXTSB(d, a)		(0x7c000774 | ___PPC_RA(d) | ___PPC_RS(a))
+#define PPC_RAW_EXTSH(d, a)		(0x7c000734 | ___PPC_RA(d) | ___PPC_RS(a))
 #define PPC_RAW_EXTSW(d, a)		(0x7c0007b4 | ___PPC_RA(d) | ___PPC_RS(a))
 #define PPC_RAW_SLW(d, a, s)		(0x7c000030 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s))
 #define PPC_RAW_SLD(d, a, s)		(0x7c000036 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s))
@@ -562,6 +571,7 @@
 					(0x54000001 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me))
 #define PPC_RAW_RLWIMI(d, a, i, mb, me) (0x50000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me))
 #define PPC_RAW_RLDICL(d, a, i, mb)     (0x78000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_MB64(mb))
+#define PPC_RAW_RLDICL_DOT(d, a, i, mb) (0x78000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_MB64(mb) | 0x1)
 #define PPC_RAW_RLDICR(d, a, i, me)     (0x78000004 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_ME64(me))
 
 /* slwi = rlwinm Rx, Ry, n, 0, 31-n */
@@ -579,12 +589,26 @@
 #define PPC_RAW_MTSPR(spr, d)		(0x7c0003a6 | ___PPC_RS(d) | __PPC_SPR(spr))
 #define PPC_RAW_EIEIO()			(0x7c0006ac)
 
+/* bcl 20,31,$+4 */
+#define PPC_RAW_BCL4()			(0x429f0005)
 #define PPC_RAW_BRANCH(offset)		(0x48000000 | PPC_LI(offset))
 #define PPC_RAW_BL(offset)		(0x48000001 | PPC_LI(offset))
 #define PPC_RAW_TW(t0, a, b)		(0x7c000008 | ___PPC_RS(t0) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_TRAP()			PPC_RAW_TW(31, 0, 0)
 #define PPC_RAW_SETB(t, bfa)		(0x7c000100 | ___PPC_RT(t) | ___PPC_RA((bfa) << 2))
 
+#ifdef CONFIG_PPC32
+#define PPC_RAW_STL		PPC_RAW_STW
+#define PPC_RAW_STLU		PPC_RAW_STWU
+#define PPC_RAW_LL		PPC_RAW_LWZ
+#define PPC_RAW_CMPLI		PPC_RAW_CMPWI
+#else
+#define PPC_RAW_STL		PPC_RAW_STD
+#define PPC_RAW_STLU		PPC_RAW_STDU
+#define PPC_RAW_LL		PPC_RAW_LD
+#define PPC_RAW_CMPLI		PPC_RAW_CMPDI
+#endif
+
 /* Deal with instructions that older assemblers aren't aware of */
 #define	PPC_BCCTR_FLUSH		stringify_in_c(.long PPC_INST_BCCTR_FLUSH)
 #define	PPC_CP_ABORT		stringify_in_c(.long PPC_RAW_CP_ABORT)
@@ -615,6 +639,7 @@
 #define PPC_TLBILX(t, a, b)	stringify_in_c(.long PPC_RAW_TLBILX(t, a, b))
 #define PPC_TLBILX_ALL(a, b)	PPC_TLBILX(0, a, b)
 #define PPC_TLBILX_PID(a, b)	PPC_TLBILX(1, a, b)
+#define PPC_TLBILX_LPID		stringify_in_c(.long PPC_RAW_TLBILX_LPID)
 #define PPC_TLBILX_VA(a, b)	PPC_TLBILX(3, a, b)
 #define PPC_WAIT_v203		stringify_in_c(.long PPC_RAW_WAIT_v203)
 #define PPC_WAIT(w, p)		stringify_in_c(.long PPC_RAW_WAIT(w, p))
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index d9fcff575027..a8b7e8682f5b 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -30,11 +30,24 @@ void *pci_traverse_device_nodes(struct device_node *start,
 				void *data);
 extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
 
+#if defined(CONFIG_IOMMU_API) && (defined(CONFIG_PPC_PSERIES) || \
+				  defined(CONFIG_PPC_POWERNV))
+extern void ppc_iommu_register_device(struct pci_controller *phb);
+extern void ppc_iommu_unregister_device(struct pci_controller *phb);
+#else
+static inline void ppc_iommu_register_device(struct pci_controller *phb) { }
+static inline void ppc_iommu_unregister_device(struct pci_controller *phb) { }
+#endif
+
+
 /* From rtas_pci.h */
 extern void init_pci_config_tokens (void);
 extern unsigned long get_phb_buid (struct device_node *);
 extern int rtas_setup_phb(struct pci_controller *phb);
 
+int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val);
+int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val);
+
 #ifdef CONFIG_EEH
 
 void eeh_addr_cache_insert_dev(struct pci_dev *dev);
@@ -44,8 +57,6 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity);
 int eeh_pci_enable(struct eeh_pe *pe, int function);
 int eeh_pe_reset_full(struct eeh_pe *pe, bool include_passed);
 void eeh_save_bars(struct eeh_dev *edev);
-int rtas_write_config(struct pci_dn *, int where, int size, u32 val);
-int rtas_read_config(struct pci_dn *, int where, int size, u32 *val);
 void eeh_pe_state_mark(struct eeh_pe *pe, int state);
 void eeh_pe_mark_isolated(struct eeh_pe *pe);
 void eeh_pe_state_clear(struct eeh_pe *pe, int state, bool include_passed);
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 5f05a984b103..46947c82a712 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -12,7 +12,7 @@
 #include <asm/feature-fixups.h>
 #include <asm/extable.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define SZL			(BITS_PER_LONG/8)
 
@@ -183,7 +183,7 @@
 /*
  * Used to name C functions called from asm
  */
-#ifdef CONFIG_PPC_KERNEL_PCREL
+#if defined(__powerpc64__) && defined(CONFIG_PPC_KERNEL_PCREL)
 #define CFUNC(name) name@notoc
 #else
 #define CFUNC(name) name
@@ -201,11 +201,13 @@
 
 #ifdef CONFIG_PPC64_ELF_ABI_V2
 #define STK_GOT		24
-#define __STK_PARAM(i)	(32 + ((i)-3)*8)
+#define STK_PARAM_AREA	32
 #else
 #define STK_GOT		40
-#define __STK_PARAM(i)	(48 + ((i)-3)*8)
+#define STK_PARAM_AREA	48
 #endif
+
+#define __STK_PARAM(i)	(STK_PARAM_AREA + ((i)-3)*8)
 #define STK_PARAM(i)	__STK_PARAM(__REG_##i)
 
 #ifdef CONFIG_PPC64_ELF_ABI_V2
@@ -406,6 +408,15 @@ n:
 /* offsets for stack frame layout */
 #define LRSAVE	16
 
+/*
+ * GCC stack frames follow a different pattern on 32 vs 64. This can be used
+ * to make asm frames be consistent with C.
+ */
+#define PPC_CREATE_STACK_FRAME(size)			\
+	mflr		r0;				\
+	std		r0,16(r1);			\
+	stdu		r1,-(size)(r1)
+
 #else /* 32-bit */
 
 #define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE_32 reg, expr
@@ -422,6 +433,11 @@ n:
 /* offsets for stack frame layout */
 #define LRSAVE	4
 
+#define PPC_CREATE_STACK_FRAME(size)			\
+	stwu		r1,-(size)(r1);			\
+	mflr		r0;				\
+	stw		r0,(size+4)(r1)
+
 #endif
 
 /* various errata or part fixups */
@@ -466,7 +482,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96)
  * and they must be used.
  */
 
-#if !defined(CONFIG_4xx) && !defined(CONFIG_PPC_8xx)
+#if !defined(CONFIG_44x) && !defined(CONFIG_PPC_8xx)
 #define tlbia					\
 	li	r4,1024;			\
 	mtctr	r4;				\
@@ -492,7 +508,25 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96)
  */
 #define DCBT_BOOK3S_STOP_ALL_STREAM_IDS(scratch)	\
        lis     scratch,0x60000000@h;			\
-       dcbt    0,scratch,0b01010
+       .machine push;					\
+       .machine power4;					\
+       dcbt    0,scratch,0b01010;			\
+       .machine pop;
+
+#define DCBT_SETUP_STREAMS(from, from_parms, to, to_parms, scratch)	\
+	lis	scratch,0x8000;	/* GO=1 */				\
+	clrldi	scratch,scratch,32;					\
+	.machine push;							\
+	.machine power4;						\
+	/* setup read stream 0 */					\
+	dcbt	0,from,0b01000;		/* addr from */			\
+	dcbt	0,from_parms,0b01010;	/* length and depth from */	\
+	/* setup write stream 1 */					\
+	dcbtst	0,to,0b01000;		/* addr to */			\
+	dcbtst	0,to_parms,0b01010;	/* length and depth to */	\
+	eieio;								\
+	dcbt	0,scratch,0b01010;	/* all streams GO */		\
+	.machine pop;
 
 /*
  * toreal/fromreal/tophys/tovirt macros. 32-bit BookE makes them
@@ -834,7 +868,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96)
 
 #endif /* !CONFIG_PPC_BOOK3E_64 */
 
-#endif /*  __ASSEMBLY__ */
+#endif /*  __ASSEMBLER__ */
 
 #define SOFT_MASK_TABLE(_start, _end)		\
 	stringify_in_c(.section __soft_mask_table,"a";)\
diff --git a/arch/powerpc/include/asm/preempt.h b/arch/powerpc/include/asm/preempt.h
new file mode 100644
index 000000000000..000e2b9681f3
--- /dev/null
+++ b/arch/powerpc/include/asm/preempt.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_POWERPC_PREEMPT_H
+#define __ASM_POWERPC_PREEMPT_H
+
+#include <asm-generic/preempt.h>
+
+#if defined(CONFIG_PREEMPT_DYNAMIC)
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+#define need_irq_preemption() \
+	(static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+#else
+#define need_irq_preemption()   (IS_ENABLED(CONFIG_PREEMPTION))
+#endif
+
+#endif /* __ASM_POWERPC_PREEMPT_H */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index e96c9b8c2a60..f156bdb43e2b 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -29,14 +29,14 @@
 #ifdef CONFIG_PPC64
 /* Default SMT priority is set to 3. Use 11- 13bits to save priority. */
 #define PPR_PRIORITY 3
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define DEFAULT_PPR (PPR_PRIORITY << 50)
 #else
 #define DEFAULT_PPR ((u64)PPR_PRIORITY << 50)
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* CONFIG_PPC64 */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #include <linux/thread_info.h>
 #include <asm/ptrace.h>
@@ -159,7 +159,7 @@ struct thread_struct {
 	unsigned long	sr0;
 #endif
 #endif /* CONFIG_PPC32 */
-#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP)
+#if defined(CONFIG_BOOKE) && defined(CONFIG_PPC_KUAP)
 	unsigned long	pid;	/* value written in PID reg. at interrupt exit */
 #endif
 	/* Debug Registers */
@@ -172,11 +172,6 @@ struct thread_struct {
 	unsigned int	align_ctl;	/* alignment handling control */
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	struct perf_event *ptrace_bps[HBP_NUM_MAX];
-	/*
-	 * Helps identify source of single-step exception and subsequent
-	 * hw-breakpoint enablement
-	 */
-	struct perf_event *last_hit_ubp[HBP_NUM_MAX];
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 	struct arch_hw_breakpoint hw_brk[HBP_NUM_MAX]; /* hardware breakpoint info */
 	unsigned long	trap_nr;	/* last trap # on this thread */
@@ -264,7 +259,9 @@ struct thread_struct {
 	unsigned long   mmcr3;
 	unsigned long   sier2;
 	unsigned long   sier3;
-
+	unsigned long	hashkeyr;
+	unsigned long	dexcr;
+	unsigned long	dexcr_onexec;	/* Reset value to load on exec */
 #endif
 };
 
@@ -337,6 +334,16 @@ extern int set_endian(struct task_struct *tsk, unsigned int val);
 extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr);
 extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+
+#define PPC_GET_DEXCR_ASPECT(tsk, asp) get_dexcr_prctl((tsk), (asp))
+#define PPC_SET_DEXCR_ASPECT(tsk, asp, val) set_dexcr_prctl((tsk), (asp), (val))
+
+int get_dexcr_prctl(struct task_struct *tsk, unsigned long asp);
+int set_dexcr_prctl(struct task_struct *tsk, unsigned long asp, unsigned long val);
+
+#endif
+
 extern void load_fp_state(struct thread_fp_state *fp);
 extern void store_fp_state(struct thread_fp_state *fp);
 extern void load_vr_state(struct thread_vr_state *vr);
@@ -392,7 +399,6 @@ int validate_sp_size(unsigned long sp, struct task_struct *p,
  */
 #define ARCH_HAS_PREFETCH
 #define ARCH_HAS_PREFETCHW
-#define ARCH_HAS_SPINLOCK_PREFETCH
 
 static inline void prefetch(const void *x)
 {
@@ -410,8 +416,6 @@ static inline void prefetchw(const void *x)
 	__asm__ __volatile__ ("dcbtst 0,%0" : : "r" (x));
 }
 
-#define spin_lock_prefetch(x)	prefetchw(x)
-
 /* asm stubs */
 extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
 extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
@@ -456,5 +460,5 @@ int enter_vmx_ops(void);
 void *exit_vmx_ops(void *dest);
 
 #endif /* __KERNEL__ */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_POWERPC_PROCESSOR_H */
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index c0107d8ddd8c..f679a11a7e7f 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -17,6 +17,8 @@
 struct device_node;
 struct property;
 
+#define MIN_RMA			768		/* Minimum RMA (in MB) for CAS negotiation */
+
 #define OF_DT_BEGIN_NODE	0x1		/* Start of node, full name */
 #define OF_DT_END_NODE		0x2		/* End node */
 #define OF_DT_PROP		0x3		/* Property: name off, size,
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index a5f36546a052..987e23a2bd28 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -390,11 +390,7 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev);
 int ps3_system_bus_driver_register(struct ps3_system_bus_driver *drv);
 void ps3_system_bus_driver_unregister(struct ps3_system_bus_driver *drv);
 
-static inline struct ps3_system_bus_driver *ps3_drv_to_system_bus_drv(
-	struct device_driver *_drv)
-{
-	return container_of(_drv, struct ps3_system_bus_driver, core);
-}
+#define ps3_drv_to_system_bus_drv(_drv) container_of_const(_drv, struct ps3_system_bus_driver, core)
 static inline struct ps3_system_bus_device *ps3_dev_to_system_bus_dev(
 	const struct device *_dev)
 {
@@ -514,4 +510,10 @@ u64 ps3_get_spe_id(void *arg);
 
 void ps3_early_mm_init(void);
 
+#ifdef CONFIG_PPC_EARLY_DEBUG_PS3GELIC
+void udbg_shutdown_ps3gelic(void);
+#else
+static inline void udbg_shutdown_ps3gelic(void) {}
+#endif
+
 #endif
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 0eb90a013346..94aa1de2b06e 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -24,7 +24,7 @@
 #include <asm/asm-const.h>
 #include <asm/reg.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct pt_regs
 {
 	union {
@@ -165,7 +165,7 @@ struct pt_regs
 #define STACK_INT_FRAME_SIZE	(KERNEL_REDZONE_SIZE + STACK_USER_INT_FRAME_SIZE)
 #define STACK_INT_FRAME_MARKER_LONGS	(STACK_INT_FRAME_MARKER/sizeof(long))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/paca.h>
 
 #ifdef CONFIG_SMP
@@ -180,8 +180,8 @@ void do_syscall_trace_leave(struct pt_regs *regs);
 static inline void set_return_regs_changed(void)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
-	local_paca->hsrr_valid = 0;
-	local_paca->srr_valid = 0;
+	WRITE_ONCE(local_paca->hsrr_valid, 0);
+	WRITE_ONCE(local_paca->srr_valid, 0);
 #endif
 }
 
@@ -310,7 +310,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
 
 static inline bool cpu_has_msr_ri(void)
 {
-	return !IS_ENABLED(CONFIG_BOOKE_OR_40x);
+	return !IS_ENABLED(CONFIG_BOOKE);
 }
 
 static inline bool regs_is_unrecoverable(struct pt_regs *regs)
@@ -397,7 +397,24 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 		return 0;
 }
 
-#endif /* __ASSEMBLY__ */
+/**
+ * regs_get_kernel_argument() - get Nth function argument in kernel
+ * @regs:	pt_regs of that context
+ * @n:		function argument number (start from 0)
+ *
+ * We support up to 8 arguments and assume they are sent in through the GPRs.
+ * This will fail for fp/vector arguments, but those aren't usually found in
+ * kernel code. This is expected to be called from kprobes or ftrace with regs.
+ */
+static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n)
+{
+#define NR_REG_ARGUMENTS 8
+	if (n < NR_REG_ARGUMENTS)
+		return regs_get_register(regs, offsetof(struct pt_regs, gpr[3 + n]));
+	return 0;
+}
+
+#endif /* __ASSEMBLER__ */
 
 #ifndef __powerpc64__
 /* We need PT_SOFTE defined at all time to avoid #ifdefs */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 6372e5f55ef0..3fe186635432 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -18,7 +18,7 @@
 #include <asm/feature-fixups.h>
 
 /* Pickup Book E specific registers. */
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 #include <asm/reg_booke.h>
 #endif
 
@@ -60,7 +60,7 @@
 #define MSR_RI_LG	1		/* Recoverable Exception */
 #define MSR_LE_LG	0 		/* Little Endian */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define __MASK(X)	(1<<(X))
 #else
 #define __MASK(X)	(1UL<<(X))
@@ -233,14 +233,10 @@
 
 /* Special Purpose Registers (SPRNs)*/
 
-#ifdef CONFIG_40x
-#define SPRN_PID	0x3B1	/* Process ID */
-#else
 #define SPRN_PID	0x030	/* Process ID */
 #ifdef CONFIG_BOOKE
 #define SPRN_PID0	SPRN_PID/* Process ID Register 0 */
 #endif
-#endif
 
 #define SPRN_CTR	0x009	/* Count Register */
 #define SPRN_DSCR	0x11
@@ -382,7 +378,17 @@
 #define SPRN_HIOR	0x137	/* 970 Hypervisor interrupt offset */
 #define SPRN_RMOR	0x138	/* Real mode offset register */
 #define SPRN_HRMOR	0x139	/* Real mode offset register */
+#define SPRN_HDEXCR_RO	0x1C7	/* Hypervisor DEXCR (non-privileged, readonly) */
+#define SPRN_HASHKEYR	0x1D4	/* Non-privileged hashst/hashchk key register */
+#define SPRN_HDEXCR	0x1D7	/* Hypervisor dynamic execution control register */
+#define SPRN_DEXCR_RO	0x32C	/* DEXCR (non-privileged, readonly) */
 #define SPRN_ASDR	0x330	/* Access segment descriptor register */
+#define SPRN_DEXCR	0x33C	/* Dynamic execution control register */
+#define   DEXCR_PR_SBHE	  0x80000000UL /* 0: Speculative Branch Hint Enable */
+#define   DEXCR_PR_IBRTPD 0x10000000UL /* 3: Indirect Branch Recurrent Target Prediction Disable */
+#define   DEXCR_PR_SRAPD  0x08000000UL /* 4: Subroutine Return Address Prediction Disable */
+#define   DEXCR_PR_NPHIE  0x04000000UL /* 5: Non-Privileged Hash Instruction Enable */
+#define   DEXCR_INIT	DEXCR_PR_NPHIE	/* Fixed DEXCR value to initialise all CPUs with */
 #define SPRN_IC		0x350	/* Virtual Instruction Count */
 #define SPRN_VTB	0x351	/* Virtual Time Base */
 #define SPRN_LDBAR	0x352	/* LD Base Address Register */
@@ -517,7 +523,7 @@
 #define SPRN_TSCR	0x399	/* Thread Switch Control Register */
 
 #define SPRN_DEC	0x016		/* Decrement Register */
-#define SPRN_PIT	0x3DB		/* Programmable Interval Timer (40x/BOOKE) */
+#define SPRN_PIT	0x3DB		/* Programmable Interval Timer (BOOKE) */
 
 #define SPRN_DER	0x095		/* Debug Enable Register */
 #define DER_RSTE	0x40000000	/* Reset Interrupt */
@@ -605,8 +611,10 @@
 #define HID1_ABE	(1<<10)		/* 7450 Address Broadcast Enable */
 #define HID1_PS		(1<<16)		/* 750FX PLL selection */
 #endif
-#define SPRN_HID2	0x3F8		/* Hardware Implementation Register 2 */
+#define SPRN_HID2_750FX	0x3F8		/* IBM 750FX HID2 Register */
 #define SPRN_HID2_GEKKO	0x398		/* Gekko HID2 Register */
+#define SPRN_HID2_G2_LE	0x3F3		/* G2_LE HID2 Register */
+#define  HID2_G2_LE_HBE	(1<<18)		/* High BAT Enable (G2_LE) */
 #define SPRN_IABR	0x3F2	/* Instruction Address Breakpoint Register */
 #define SPRN_IABR2	0x3FA		/* 83xx */
 #define SPRN_IBCR	0x135		/* 83xx Insn Breakpoint Control Reg */
@@ -1104,15 +1112,6 @@
  *	- SPRG2 indicator that we are in RTAS
  *	- SPRG4 (603 only) pseudo TLB LRU data
  *
- * 32-bit 40x:
- *	- SPRG0 scratch for exception vectors
- *	- SPRG1 scratch for exception vectors
- *	- SPRG2 scratch for exception vectors
- *	- SPRG4 scratch for exception vectors (not 403)
- *	- SPRG5 scratch for exception vectors (not 403)
- *	- SPRG6 scratch for exception vectors (not 403)
- *	- SPRG7 scratch for exception vectors (not 403)
- *
  * 32-bit 440 and FSL BookE:
  *	- SPRG0 scratch for exception vectors
  *	- SPRG1 scratch for exception vectors (*)
@@ -1204,16 +1203,6 @@
 #define SPRN_SPRG_603_LRU	SPRN_SPRG4
 #endif
 
-#ifdef CONFIG_40x
-#define SPRN_SPRG_SCRATCH0	SPRN_SPRG0
-#define SPRN_SPRG_SCRATCH1	SPRN_SPRG1
-#define SPRN_SPRG_SCRATCH2	SPRN_SPRG2
-#define SPRN_SPRG_SCRATCH3	SPRN_SPRG4
-#define SPRN_SPRG_SCRATCH4	SPRN_SPRG5
-#define SPRN_SPRG_SCRATCH5	SPRN_SPRG6
-#define SPRN_SPRG_SCRATCH6	SPRN_SPRG7
-#endif
-
 #ifdef CONFIG_BOOKE
 #define SPRN_SPRG_RSCRATCH0	SPRN_SPRG0
 #define SPRN_SPRG_WSCRATCH0	SPRN_SPRG0
@@ -1351,8 +1340,10 @@
 #define PVR_POWER8E	0x004B
 #define PVR_POWER8NVL	0x004C
 #define PVR_POWER8	0x004D
+#define PVR_HX_C2000	0x0066
 #define PVR_POWER9	0x004E
 #define PVR_POWER10	0x0080
+#define PVR_POWER11	0x0082
 #define PVR_BE		0x0070
 #define PVR_PA6T	0x0090
 
@@ -1364,9 +1355,10 @@
 #define PVR_ARCH_207	0x0f000004
 #define PVR_ARCH_300	0x0f000005
 #define PVR_ARCH_31	0x0f000006
+#define PVR_ARCH_31_P11	0x0f000007
 
 /* Macros for setting and retrieving special purpose registers */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #if defined(CONFIG_PPC64) || defined(__CHECKER__)
 typedef struct {
@@ -1404,11 +1396,9 @@ static inline void mtmsr_isync(unsigned long val)
 #define mfspr(rn)	({unsigned long rval; \
 			asm volatile("mfspr %0," __stringify(rn) \
 				: "=r" (rval)); rval;})
-#ifndef mtspr
 #define mtspr(rn, v)	asm volatile("mtspr " __stringify(rn) ",%0" : \
 				     : "r" ((unsigned long)(v)) \
 				     : "memory")
-#endif
 #define wrtspr(rn)	asm volatile("mtspr " __stringify(rn) ",2" : : : "memory")
 
 static inline void wrtee(unsigned long val)
@@ -1460,6 +1450,6 @@ extern void scom970_write(unsigned int address, unsigned long value);
 struct pt_regs;
 
 extern void ppc_save_regs(struct pt_regs *regs);
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_REG_H */
diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h
deleted file mode 100644
index 74fba29e9491..000000000000
--- a/arch/powerpc/include/asm/reg_a2.h
+++ /dev/null
@@ -1,154 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  Register definitions specific to the A2 core
- *
- *  Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
- */
-
-#ifndef __ASM_POWERPC_REG_A2_H__
-#define __ASM_POWERPC_REG_A2_H__
-
-#include <asm/asm-const.h>
-
-#define SPRN_TENSR	0x1b5
-#define SPRN_TENS	0x1b6	/* Thread ENable Set */
-#define SPRN_TENC	0x1b7	/* Thread ENable Clear */
-
-#define SPRN_A2_CCR0	0x3f0	/* Core Configuration Register 0 */
-#define SPRN_A2_CCR1	0x3f1	/* Core Configuration Register 1 */
-#define SPRN_A2_CCR2	0x3f2	/* Core Configuration Register 2 */
-#define SPRN_MMUCR0	0x3fc	/* MMU Control Register 0 */
-#define SPRN_MMUCR1	0x3fd	/* MMU Control Register 1 */
-#define SPRN_MMUCR2	0x3fe	/* MMU Control Register 2 */
-#define SPRN_MMUCR3	0x3ff	/* MMU Control Register 3 */
-
-#define SPRN_IAR	0x372
-
-#define SPRN_IUCR0	0x3f3
-#define IUCR0_ICBI_ACK	0x1000
-
-#define SPRN_XUCR0	0x3f6	/* Execution Unit Config Register 0 */
-
-#define A2_IERAT_SIZE	16
-#define A2_DERAT_SIZE	32
-
-/* A2 MMUCR0 bits */
-#define MMUCR0_ECL	0x80000000	/* Extended Class for TLB fills */
-#define MMUCR0_TID_NZ	0x40000000	/* TID is non-zero */
-#define MMUCR0_TS	0x10000000	/* Translation space for TLB fills */
-#define MMUCR0_TGS	0x20000000	/* Guest space for TLB fills */
-#define MMUCR0_TLBSEL	0x0c000000	/* TLB or ERAT target for TLB fills */
-#define MMUCR0_TLBSEL_U	0x00000000	/*  TLBSEL = UTLB */
-#define MMUCR0_TLBSEL_I	0x08000000	/*  TLBSEL = I-ERAT */
-#define MMUCR0_TLBSEL_D	0x0c000000	/*  TLBSEL = D-ERAT */
-#define MMUCR0_LOCKSRSH	0x02000000	/* Use TLB lock on tlbsx. */
-#define MMUCR0_TID_MASK	0x000000ff	/* TID field */
-
-/* A2 MMUCR1 bits */
-#define MMUCR1_IRRE		0x80000000	/* I-ERAT round robin enable */
-#define MMUCR1_DRRE		0x40000000	/* D-ERAT round robin enable */
-#define MMUCR1_REE		0x20000000	/* Reference Exception Enable*/
-#define MMUCR1_CEE		0x10000000	/* Change exception enable */
-#define MMUCR1_CSINV_ALL	0x00000000	/* Inval ERAT on all CS evts */
-#define MMUCR1_CSINV_NISYNC	0x04000000	/* Inval ERAT on all ex isync*/
-#define MMUCR1_CSINV_NEVER	0x0c000000	/* Don't inval ERAT on CS */
-#define MMUCR1_ICTID		0x00080000	/* IERAT class field as TID */
-#define MMUCR1_ITTID		0x00040000	/* IERAT thdid field as TID */
-#define MMUCR1_DCTID		0x00020000	/* DERAT class field as TID */
-#define MMUCR1_DTTID		0x00010000	/* DERAT thdid field as TID */
-#define MMUCR1_DCCD		0x00008000	/* DERAT class ignore */
-#define MMUCR1_TLBWE_BINV	0x00004000	/* back invalidate on tlbwe */
-
-/* A2 MMUCR2 bits */
-#define MMUCR2_PSSEL_SHIFT	4
-
-/* A2 MMUCR3 bits */
-#define MMUCR3_THID		0x0000000f	/* Thread ID */
-
-/* *** ERAT TLB bits definitions */
-#define TLB0_EPN_MASK		ASM_CONST(0xfffffffffffff000)
-#define TLB0_CLASS_MASK		ASM_CONST(0x0000000000000c00)
-#define TLB0_CLASS_00		ASM_CONST(0x0000000000000000)
-#define TLB0_CLASS_01		ASM_CONST(0x0000000000000400)
-#define TLB0_CLASS_10		ASM_CONST(0x0000000000000800)
-#define TLB0_CLASS_11		ASM_CONST(0x0000000000000c00)
-#define TLB0_V			ASM_CONST(0x0000000000000200)
-#define TLB0_X			ASM_CONST(0x0000000000000100)
-#define TLB0_SIZE_MASK		ASM_CONST(0x00000000000000f0)
-#define TLB0_SIZE_4K		ASM_CONST(0x0000000000000010)
-#define TLB0_SIZE_64K		ASM_CONST(0x0000000000000030)
-#define TLB0_SIZE_1M		ASM_CONST(0x0000000000000050)
-#define TLB0_SIZE_16M		ASM_CONST(0x0000000000000070)
-#define TLB0_SIZE_1G		ASM_CONST(0x00000000000000a0)
-#define TLB0_THDID_MASK		ASM_CONST(0x000000000000000f)
-#define TLB0_THDID_0		ASM_CONST(0x0000000000000001)
-#define TLB0_THDID_1		ASM_CONST(0x0000000000000002)
-#define TLB0_THDID_2		ASM_CONST(0x0000000000000004)
-#define TLB0_THDID_3		ASM_CONST(0x0000000000000008)
-#define TLB0_THDID_ALL		ASM_CONST(0x000000000000000f)
-
-#define TLB1_RESVATTR		ASM_CONST(0x00f0000000000000)
-#define TLB1_U0			ASM_CONST(0x0008000000000000)
-#define TLB1_U1			ASM_CONST(0x0004000000000000)
-#define TLB1_U2			ASM_CONST(0x0002000000000000)
-#define TLB1_U3			ASM_CONST(0x0001000000000000)
-#define TLB1_R			ASM_CONST(0x0000800000000000)
-#define TLB1_C			ASM_CONST(0x0000400000000000)
-#define TLB1_RPN_MASK		ASM_CONST(0x000003fffffff000)
-#define TLB1_W			ASM_CONST(0x0000000000000800)
-#define TLB1_I			ASM_CONST(0x0000000000000400)
-#define TLB1_M			ASM_CONST(0x0000000000000200)
-#define TLB1_G			ASM_CONST(0x0000000000000100)
-#define TLB1_E			ASM_CONST(0x0000000000000080)
-#define TLB1_VF			ASM_CONST(0x0000000000000040)
-#define TLB1_UX			ASM_CONST(0x0000000000000020)
-#define TLB1_SX			ASM_CONST(0x0000000000000010)
-#define TLB1_UW			ASM_CONST(0x0000000000000008)
-#define TLB1_SW			ASM_CONST(0x0000000000000004)
-#define TLB1_UR			ASM_CONST(0x0000000000000002)
-#define TLB1_SR			ASM_CONST(0x0000000000000001)
-
-/* A2 erativax attributes definitions */
-#define ERATIVAX_RS_IS_ALL		0x000
-#define ERATIVAX_RS_IS_TID		0x040
-#define ERATIVAX_RS_IS_CLASS		0x080
-#define ERATIVAX_RS_IS_FULLMATCH	0x0c0
-#define ERATIVAX_CLASS_00		0x000
-#define ERATIVAX_CLASS_01		0x010
-#define ERATIVAX_CLASS_10		0x020
-#define ERATIVAX_CLASS_11		0x030
-#define ERATIVAX_PSIZE_4K		(TLB_PSIZE_4K >> 1)
-#define ERATIVAX_PSIZE_64K		(TLB_PSIZE_64K >> 1)
-#define ERATIVAX_PSIZE_1M		(TLB_PSIZE_1M >> 1)
-#define ERATIVAX_PSIZE_16M		(TLB_PSIZE_16M >> 1)
-#define ERATIVAX_PSIZE_1G		(TLB_PSIZE_1G >> 1)
-
-/* A2 eratilx attributes definitions */
-#define ERATILX_T_ALL			0
-#define ERATILX_T_TID			1
-#define ERATILX_T_TGS			2
-#define ERATILX_T_FULLMATCH		3
-#define ERATILX_T_CLASS0		4
-#define ERATILX_T_CLASS1		5
-#define ERATILX_T_CLASS2		6
-#define ERATILX_T_CLASS3		7
-
-/* XUCR0 bits */
-#define XUCR0_TRACE_UM_T0		0x40000000	/* Thread 0 */
-#define XUCR0_TRACE_UM_T1		0x20000000	/* Thread 1 */
-#define XUCR0_TRACE_UM_T2		0x10000000	/* Thread 2 */
-#define XUCR0_TRACE_UM_T3		0x08000000	/* Thread 3 */
-
-/* A2 CCR0 register */
-#define A2_CCR0_PME_DISABLED		0x00000000
-#define A2_CCR0_PME_SLEEP		0x40000000
-#define A2_CCR0_PME_RVW			0x80000000
-#define A2_CCR0_PME_DISABLED2		0xc0000000
-
-/* A2 CCR2 register */
-#define A2_CCR2_ERAT_ONLY_MODE		0x00000001
-#define A2_CCR2_ENABLE_ICSWX		0x00000002
-#define A2_CCR2_ENABLE_PC		0x20000000
-#define A2_CCR2_ENABLE_TRACE		0x40000000
-
-#endif /* __ASM_POWERPC_REG_A2_H__ */
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index af56980b6cdb..56f9d3b1de85 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -1,10 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Contains register definitions common to the Book E PowerPC
- * specification.  Notice that while the IBM-40x series of CPUs
- * are not true Book E PowerPCs, they borrowed a number of features
- * before Book E was finalized, and are included here as well.  Unfortunately,
- * they sometimes used different locations than true Book E CPUs did.
+ * specification.
  *
  * Copyright 2009-2010 Freescale Semiconductor, Inc.
  */
@@ -42,9 +39,6 @@
 #define MSR_KERNEL	(MSR_ | MSR_64BIT)
 #define MSR_USER32	(MSR_ | MSR_PR | MSR_EE)
 #define MSR_USER64	(MSR_USER32 | MSR_64BIT)
-#elif defined (CONFIG_40x)
-#define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE)
-#define MSR_USER	(MSR_KERNEL|MSR_PR|MSR_EE)
 #else
 #define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_CE)
 #define MSR_USER	(MSR_KERNEL|MSR_PR|MSR_EE)
@@ -157,7 +151,6 @@
 #define SPRN_TLB3CFG	0x2B3	/* TLB 3 Config Register */
 #define SPRN_EPR	0x2BE	/* External Proxy Register */
 #define SPRN_CCR1	0x378	/* Core Configuration Register 1 */
-#define SPRN_ZPR	0x3B0	/* Zone Protection Register (40x) */
 #define SPRN_MAS7	0x3B0	/* MMU Assist Register 7 */
 #define SPRN_MMUCR	0x3B2	/* MMU Control Register */
 #define SPRN_CCR0	0x3B3	/* Core Configuration Register 0 */
@@ -166,7 +159,6 @@
 #define SPRN_SGR	0x3B9	/* Storage Guarded Register */
 #define SPRN_DCWR	0x3BA	/* Data Cache Write-thru Register */
 #define SPRN_SLER	0x3BB	/* Little-endian real mode */
-#define SPRN_SU0R	0x3BC	/* "User 0" real mode (40x) */
 #define SPRN_DCMP	0x3D1	/* Data TLB Compare Register */
 #define SPRN_ICDBDR	0x3D3	/* Instruction Cache Debug Data Register */
 #define SPRN_EVPR	0x3D6	/* Exception Vector Prefix Register */
@@ -183,10 +175,8 @@
 #define SPRN_SVR	0x3FF	/* System Version Register */
 
 /*
- * SPRs which have conflicting definitions on true Book E versus classic,
- * or IBM 40x.
+ * SPRs which have conflicting definitions on true Book E versus classic.
  */
-#ifdef CONFIG_BOOKE
 #define SPRN_CSRR0	0x03A	/* Critical Save and Restore Register 0 */
 #define SPRN_CSRR1	0x03B	/* Critical Save and Restore Register 1 */
 #define SPRN_DEAR	0x03D	/* Data Error Address Register */
@@ -201,22 +191,6 @@
 #define SPRN_DAC2	0x13D	/* Data Address Compare 2 */
 #define SPRN_TSR	0x150	/* Timer Status Register */
 #define SPRN_TCR	0x154	/* Timer Control Register */
-#endif /* Book E */
-#ifdef CONFIG_40x
-#define SPRN_DBCR1	0x3BD	/* Debug Control Register 1 */		
-#define SPRN_ESR	0x3D4	/* Exception Syndrome Register */
-#define SPRN_DEAR	0x3D5	/* Data Error Address Register */
-#define SPRN_TSR	0x3D8	/* Timer Status Register */
-#define SPRN_TCR	0x3DA	/* Timer Control Register */
-#define SPRN_SRR2	0x3DE	/* Save/Restore Register 2 */
-#define SPRN_SRR3	0x3DF	/* Save/Restore Register 3 */
-#define SPRN_DBSR	0x3F0	/* Debug Status Register */		
-#define SPRN_DBCR0	0x3F2	/* Debug Control Register 0 */
-#define SPRN_DAC1	0x3F6	/* Data Address Compare 1 */
-#define SPRN_DAC2	0x3F7	/* Data Address Compare 2 */
-#define SPRN_CSRR0	SPRN_SRR2 /* Critical Save and Restore Register 0 */
-#define SPRN_CSRR1	SPRN_SRR3 /* Critical Save and Restore Register 1 */
-#endif
 #define SPRN_HACOP	0x15F	/* Hypervisor Available Coprocessor Register */
 
 /* Bit definitions for CCR1. */
@@ -296,10 +270,6 @@
 #endif
 
 /* Bit definitions for the DBSR. */
-/*
- * DBSR bits which have conflicting definitions on true Book E versus IBM 40x.
- */
-#ifdef CONFIG_BOOKE
 #define DBSR_IDE	0x80000000	/* Imprecise Debug Event */
 #define DBSR_MRR	0x30000000	/* Most Recent Reset */
 #define DBSR_IC		0x08000000	/* Instruction Completion */
@@ -319,21 +289,6 @@
 #define DBSR_CRET	0x00000020	/* Critical Return Debug Event */
 #define DBSR_IAC12ATS	0x00000002	/* Instr Address Compare 1/2 Toggle */
 #define DBSR_IAC34ATS	0x00000001	/* Instr Address Compare 3/4 Toggle */
-#endif
-#ifdef CONFIG_40x
-#define DBSR_IC		0x80000000	/* Instruction Completion */
-#define DBSR_BT		0x40000000	/* Branch taken */
-#define DBSR_IRPT	0x20000000	/* Exception Debug Event */
-#define DBSR_TIE	0x10000000	/* Trap Instruction debug Event */
-#define DBSR_IAC1	0x04000000	/* Instruction Address Compare 1 Event */
-#define DBSR_IAC2	0x02000000	/* Instruction Address Compare 2 Event */
-#define DBSR_IAC3	0x00080000	/* Instruction Address Compare 3 Event */
-#define DBSR_IAC4	0x00040000	/* Instruction Address Compare 4 Event */
-#define DBSR_DAC1R	0x01000000	/* Data Address Compare 1 Read Event */
-#define DBSR_DAC1W	0x00800000	/* Data Address Compare 1 Write Event */
-#define DBSR_DAC2R	0x00400000	/* Data Address Compare 2 Read Event */
-#define DBSR_DAC2W	0x00200000	/* Data Address Compare 2 Write Event */
-#endif
 
 /* Bit definitions related to the ESR. */
 #define ESR_MCI		0x80000000	/* Machine Check - Instruction */
@@ -355,69 +310,6 @@
 #define ESR_SPV		0x00000080	/* Signal Processing operation */
 
 /* Bit definitions related to the DBCR0. */
-#if defined(CONFIG_40x)
-#define DBCR0_EDM	0x80000000	/* External Debug Mode */
-#define DBCR0_IDM	0x40000000	/* Internal Debug Mode */
-#define DBCR0_RST	0x30000000	/* all the bits in the RST field */
-#define DBCR0_RST_SYSTEM 0x30000000	/* System Reset */
-#define DBCR0_RST_CHIP	0x20000000	/* Chip Reset */
-#define DBCR0_RST_CORE	0x10000000	/* Core Reset */
-#define DBCR0_RST_NONE	0x00000000	/* No Reset */
-#define DBCR0_IC	0x08000000	/* Instruction Completion */
-#define DBCR0_ICMP	DBCR0_IC
-#define DBCR0_BT	0x04000000	/* Branch Taken */
-#define DBCR0_BRT	DBCR0_BT
-#define DBCR0_EDE	0x02000000	/* Exception Debug Event */
-#define DBCR0_IRPT	DBCR0_EDE
-#define DBCR0_TDE	0x01000000	/* TRAP Debug Event */
-#define DBCR0_IA1	0x00800000	/* Instr Addr compare 1 enable */
-#define DBCR0_IAC1	DBCR0_IA1
-#define DBCR0_IA2	0x00400000	/* Instr Addr compare 2 enable */
-#define DBCR0_IAC2	DBCR0_IA2
-#define DBCR0_IA12	0x00200000	/* Instr Addr 1-2 range enable */
-#define DBCR0_IA12X	0x00100000	/* Instr Addr 1-2 range eXclusive */
-#define DBCR0_IA3	0x00080000	/* Instr Addr compare 3 enable */
-#define DBCR0_IAC3	DBCR0_IA3
-#define DBCR0_IA4	0x00040000	/* Instr Addr compare 4 enable */
-#define DBCR0_IAC4	DBCR0_IA4
-#define DBCR0_IA34	0x00020000	/* Instr Addr 3-4 range Enable */
-#define DBCR0_IA34X	0x00010000	/* Instr Addr 3-4 range eXclusive */
-#define DBCR0_IA12T	0x00008000	/* Instr Addr 1-2 range Toggle */
-#define DBCR0_IA34T	0x00004000	/* Instr Addr 3-4 range Toggle */
-#define DBCR0_FT	0x00000001	/* Freeze Timers on debug event */
-
-#define dbcr_iac_range(task)	((task)->thread.debug.dbcr0)
-#define DBCR_IAC12I	DBCR0_IA12			/* Range Inclusive */
-#define DBCR_IAC12X	(DBCR0_IA12 | DBCR0_IA12X)	/* Range Exclusive */
-#define DBCR_IAC12MODE	(DBCR0_IA12 | DBCR0_IA12X)	/* IAC 1-2 Mode Bits */
-#define DBCR_IAC34I	DBCR0_IA34			/* Range Inclusive */
-#define DBCR_IAC34X	(DBCR0_IA34 | DBCR0_IA34X)	/* Range Exclusive */
-#define DBCR_IAC34MODE	(DBCR0_IA34 | DBCR0_IA34X)	/* IAC 3-4 Mode Bits */
-
-/* Bit definitions related to the DBCR1. */
-#define DBCR1_DAC1R	0x80000000	/* DAC1 Read Debug Event */
-#define DBCR1_DAC2R	0x40000000	/* DAC2 Read Debug Event */
-#define DBCR1_DAC1W	0x20000000	/* DAC1 Write Debug Event */
-#define DBCR1_DAC2W	0x10000000	/* DAC2 Write Debug Event */
-
-#define dbcr_dac(task)	((task)->thread.debug.dbcr1)
-#define DBCR_DAC1R	DBCR1_DAC1R
-#define DBCR_DAC1W	DBCR1_DAC1W
-#define DBCR_DAC2R	DBCR1_DAC2R
-#define DBCR_DAC2W	DBCR1_DAC2W
-
-/*
- * Are there any active Debug Events represented in the
- * Debug Control Registers?
- */
-#define DBCR0_ACTIVE_EVENTS	(DBCR0_ICMP | DBCR0_IAC1 | DBCR0_IAC2 | \
-				 DBCR0_IAC3 | DBCR0_IAC4)
-#define DBCR1_ACTIVE_EVENTS	(DBCR1_DAC1R | DBCR1_DAC2R | \
-				 DBCR1_DAC1W | DBCR1_DAC2W)
-#define DBCR_ACTIVE_EVENTS(dbcr0, dbcr1)  (((dbcr0) & DBCR0_ACTIVE_EVENTS) || \
-					   ((dbcr1) & DBCR1_ACTIVE_EVENTS))
-
-#elif defined(CONFIG_BOOKE)
 #define DBCR0_EDM	0x80000000	/* External Debug Mode */
 #define DBCR0_IDM	0x40000000	/* Internal Debug Mode */
 #define DBCR0_RST	0x30000000	/* all the bits in the RST field */
@@ -518,7 +410,6 @@
 
 #define DBCR_ACTIVE_EVENTS(dbcr0, dbcr1)  (((dbcr0) & DBCR0_ACTIVE_EVENTS) || \
 					   ((dbcr1) & DBCR1_ACTIVE_EVENTS))
-#endif /* #elif defined(CONFIG_BOOKE) */
 
 /* Bit definitions related to the TCR. */
 #define TCR_WP(x)	(((x)&0x3)<<30)	/* WDT Period */
@@ -685,7 +576,7 @@
 
 #define TEN_THREAD(x)	(1 << (x))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #define mftmr(rn)	({unsigned long rval; \
 			asm volatile(MFTMR(rn, %0) : "=r" (rval)); rval;})
 #define mttmr(rn, v)	asm volatile(MTTMR(rn, %0) : \
@@ -694,7 +585,7 @@
 
 extern unsigned long global_dbcr0[];
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_POWERPC_REG_BOOKE_H__ */
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h
index a21f529c43d9..ec459c3d9498 100644
--- a/arch/powerpc/include/asm/reg_fsl_emb.h
+++ b/arch/powerpc/include/asm/reg_fsl_emb.h
@@ -9,13 +9,30 @@
 
 #include <linux/stringify.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /* Performance Monitor Registers */
-#define mfpmr(rn)	({unsigned int rval; \
-			asm volatile("mfpmr %0," __stringify(rn) \
-				     : "=r" (rval)); rval;})
-#define mtpmr(rn, v)	asm volatile("mtpmr " __stringify(rn) ",%0" : : "r" (v))
-#endif /* __ASSEMBLY__ */
+static __always_inline unsigned int mfpmr(unsigned int rn)
+{
+	unsigned int rval;
+
+	asm (".machine push; "
+	     ".machine e300; "
+	     "mfpmr %[rval], %[rn];"
+	     ".machine pop;"
+	     : [rval] "=r" (rval) : [rn] "i" (rn));
+
+	return rval;
+}
+
+static __always_inline void mtpmr(unsigned int rn, unsigned int val)
+{
+	asm (".machine push; "
+	     ".machine e300; "
+	     "mtpmr %[rn], %[val];"
+	     ".machine pop;"
+	     : [val] "=r" (val) : [rn] "i" (rn));
+}
+#endif /* __ASSEMBLER__ */
 
 /* Freescale Book E Performance Monitor APU Registers */
 #define PMRN_PMC0	0x010	/* Performance Monitor Counter 0 */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 3abe15ac79db..d046bbd5017d 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -3,6 +3,7 @@
 #define _POWERPC_RTAS_H
 #ifdef __KERNEL__
 
+#include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <asm/page.h>
 #include <asm/rtas-types.h>
@@ -67,9 +68,11 @@ enum rtas_function_index {
 	RTAS_FNIDX__IBM_READ_PCI_CONFIG,
 	RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE,
 	RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2,
+	RTAS_FNIDX__IBM_RECEIVE_HVPIPE_MSG,
 	RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW,
-	RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS,
+	RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW,
 	RTAS_FNIDX__IBM_SCAN_LOG_DUMP,
+	RTAS_FNIDX__IBM_SEND_HVPIPE_MSG,
 	RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR,
 	RTAS_FNIDX__IBM_SET_EEH_OPTION,
 	RTAS_FNIDX__IBM_SET_SLOT_RESET,
@@ -162,9 +165,11 @@ typedef struct {
 #define RTAS_FN_IBM_READ_PCI_CONFIG               rtas_fn_handle(RTAS_FNIDX__IBM_READ_PCI_CONFIG)
 #define RTAS_FN_IBM_READ_SLOT_RESET_STATE         rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE)
 #define RTAS_FN_IBM_READ_SLOT_RESET_STATE2        rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2)
+#define RTAS_FN_IBM_RECEIVE_HVPIPE_MSG		  rtas_fn_handle(RTAS_FNIDX__IBM_RECEIVE_HVPIPE_MSG)
 #define RTAS_FN_IBM_REMOVE_PE_DMA_WINDOW          rtas_fn_handle(RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW)
-#define RTAS_FN_IBM_RESET_PE_DMA_WINDOWS          rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS)
+#define RTAS_FN_IBM_RESET_PE_DMA_WINDOW           rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW)
 #define RTAS_FN_IBM_SCAN_LOG_DUMP                 rtas_fn_handle(RTAS_FNIDX__IBM_SCAN_LOG_DUMP)
+#define RTAS_FN_IBM_SEND_HVPIPE_MSG		  rtas_fn_handle(RTAS_FNIDX__IBM_SEND_HVPIPE_MSG)
 #define RTAS_FN_IBM_SET_DYNAMIC_INDICATOR         rtas_fn_handle(RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR)
 #define RTAS_FN_IBM_SET_EEH_OPTION                rtas_fn_handle(RTAS_FNIDX__IBM_SET_EEH_OPTION)
 #define RTAS_FN_IBM_SET_SLOT_RESET                rtas_fn_handle(RTAS_FNIDX__IBM_SET_SLOT_RESET)
@@ -201,10 +206,26 @@ typedef struct {
 /* Memory set aside for sys_rtas to use with calls that need a work area. */
 #define RTAS_USER_REGION_SIZE (64 * 1024)
 
-/* RTAS return status codes */
-#define RTAS_BUSY		-2    /* RTAS Busy */
-#define RTAS_EXTENDED_DELAY_MIN	9900
-#define RTAS_EXTENDED_DELAY_MAX	9905
+/*
+ * Common RTAS function return values, derived from the table "RTAS
+ * Status Word Values" in PAPR+ v2.13 7.2.8: "Return Codes". If a
+ * function can return a value in this table then generally it has the
+ * meaning listed here. More extended commentary in the documentation
+ * for rtas_call().
+ *
+ * RTAS functions may use negative and positive numbers not in this
+ * set for function-specific error and success conditions,
+ * respectively.
+ */
+#define RTAS_SUCCESS                     0 /* Success. */
+#define RTAS_HARDWARE_ERROR             -1 /* Hardware or other unspecified error. */
+#define RTAS_BUSY                       -2 /* Retry immediately. */
+#define RTAS_INVALID_PARAMETER          -3 /* Invalid indicator/domain/sensor etc. */
+#define	RTAS_FUNC_NOT_SUPPORTED		-5 /* Function not supported */
+#define RTAS_UNEXPECTED_STATE_CHANGE    -7 /* Seems limited to EEH and slot reset. */
+#define RTAS_EXTENDED_DELAY_MIN       9900 /* Retry after delaying for ~1ms. */
+#define RTAS_EXTENDED_DELAY_MAX       9905 /* Retry after delaying for ~100s. */
+#define RTAS_ML_ISOLATION_ERROR      -9000 /* Multi-level isolation error. */
 
 /* statuses specific to ibm,suspend-me */
 #define RTAS_SUSPEND_ABORTED     9000 /* Suspension aborted */
@@ -217,6 +238,7 @@ typedef struct {
 #define RTAS_EPOW_WARNING		0x40000000 /* set bit 1 */
 #define RTAS_HOTPLUG_EVENTS		0x10000000 /* set bit 3 */
 #define RTAS_IO_EVENTS			0x08000000 /* set bit 4 */
+#define RTAS_HVPIPE_MSG_EVENTS		0x04000000 /* set bit 5 */
 #define RTAS_EVENT_SCAN_ALL_EVENTS	0xffffffff
 
 /* RTAS event severity */
@@ -266,7 +288,8 @@ typedef struct {
 #define RTAS_TYPE_DEALLOC		0xE3
 #define RTAS_TYPE_DUMP			0xE4
 #define RTAS_TYPE_HOTPLUG		0xE5
-/* I don't add PowerMGM events right now, this is a different topic */ 
+#define RTAS_TYPE_HVPIPE		0xE6
+/* I don't add PowerMGM events right now, this is a different topic */
 #define RTAS_TYPE_PMGM_POWER_SW_ON	0x60
 #define RTAS_TYPE_PMGM_POWER_SW_OFF	0x61
 #define RTAS_TYPE_PMGM_LID_OPEN		0x62
@@ -358,6 +381,7 @@ inline uint32_t rtas_ext_event_company_id(struct rtas_ext_event_log_v6 *ext_log)
 #define PSERIES_ELOG_SECT_ID_HMC_ID		(('H' << 8) | 'M')
 #define PSERIES_ELOG_SECT_ID_EPOW		(('E' << 8) | 'P')
 #define PSERIES_ELOG_SECT_ID_IO_EVENT		(('I' << 8) | 'E')
+#define PSERIES_ELOG_SECT_ID_HVPIPE_EVENT	(('P' << 8) | 'E')
 #define PSERIES_ELOG_SECT_ID_MANUFACT_INFO	(('M' << 8) | 'I')
 #define PSERIES_ELOG_SECT_ID_CALL_HOME		(('C' << 8) | 'H')
 #define PSERIES_ELOG_SECT_ID_USER_DEF		(('U' << 8) | 'D')
@@ -381,6 +405,7 @@ inline uint16_t pseries_errorlog_length(struct pseries_errorlog *sect)
 #define PSERIES_HP_ELOG_RESOURCE_SLOT	3
 #define PSERIES_HP_ELOG_RESOURCE_PHB	4
 #define PSERIES_HP_ELOG_RESOURCE_PMEM   6
+#define PSERIES_HP_ELOG_RESOURCE_DT	7
 
 #define PSERIES_HP_ELOG_ACTION_ADD	1
 #define PSERIES_HP_ELOG_ACTION_REMOVE	2
@@ -406,43 +431,41 @@ static inline bool rtas_function_implemented(const rtas_fn_handle_t handle)
 {
 	return rtas_function_token(handle) != RTAS_UNKNOWN_SERVICE;
 }
-extern int rtas_token(const char *service);
-extern int rtas_service_present(const char *service);
-extern int rtas_call(int token, int, int, int *, ...);
+int rtas_token(const char *service);
+int rtas_call(int token, int nargs, int nret, int *outputs, ...);
 void rtas_call_unlocked(struct rtas_args *args, int token, int nargs,
 			int nret, ...);
-extern void __noreturn rtas_restart(char *cmd);
-extern void rtas_power_off(void);
-extern void __noreturn rtas_halt(void);
-extern void rtas_os_term(char *str);
+void __noreturn rtas_restart(char *cmd);
+void rtas_power_off(void);
+void __noreturn rtas_halt(void);
+void rtas_os_term(char *str);
 void rtas_activate_firmware(void);
-extern int rtas_get_sensor(int sensor, int index, int *state);
-extern int rtas_get_sensor_fast(int sensor, int index, int *state);
-extern int rtas_get_power_level(int powerdomain, int *level);
-extern int rtas_set_power_level(int powerdomain, int level, int *setlevel);
-extern bool rtas_indicator_present(int token, int *maxindex);
-extern int rtas_set_indicator(int indicator, int index, int new_value);
-extern int rtas_set_indicator_fast(int indicator, int index, int new_value);
-extern void rtas_progress(char *s, unsigned short hex);
+int rtas_get_sensor(int sensor, int index, int *state);
+int rtas_get_sensor_fast(int sensor, int index, int *state);
+int rtas_get_power_level(int powerdomain, int *level);
+int rtas_set_power_level(int powerdomain, int level, int *setlevel);
+bool rtas_indicator_present(int token, int *maxindex);
+int rtas_set_indicator(int indicator, int index, int new_value);
+int rtas_set_indicator_fast(int indicator, int index, int new_value);
+void rtas_progress(char *s, unsigned short hex);
 int rtas_ibm_suspend_me(int *fw_status);
+int rtas_error_rc(int rtas_rc);
 
 struct rtc_time;
-extern time64_t rtas_get_boot_time(void);
-extern void rtas_get_rtc_time(struct rtc_time *rtc_time);
-extern int rtas_set_rtc_time(struct rtc_time *rtc_time);
+time64_t rtas_get_boot_time(void);
+void rtas_get_rtc_time(struct rtc_time *rtc_time);
+int rtas_set_rtc_time(struct rtc_time *rtc_time);
 
-extern unsigned int rtas_busy_delay_time(int status);
+unsigned int rtas_busy_delay_time(int status);
 bool rtas_busy_delay(int status);
 
-extern int early_init_dt_scan_rtas(unsigned long node,
-		const char *uname, int depth, void *data);
+int early_init_dt_scan_rtas(unsigned long node, const char *uname, int depth, void *data);
 
-extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
+void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
 
 #ifdef CONFIG_PPC_PSERIES
 extern time64_t last_rtas_event;
-extern int clobbering_unread_rtas_event(void);
-extern void post_mobility_fixup(void);
+int clobbering_unread_rtas_event(void);
 int rtas_syscall_dispatch_ibm_suspend_me(u64 handle);
 #else
 static inline int clobbering_unread_rtas_event(void) { return 0; }
@@ -453,14 +476,14 @@ static inline int rtas_syscall_dispatch_ibm_suspend_me(u64 handle)
 #endif
 
 #ifdef CONFIG_PPC_RTAS_DAEMON
-extern void rtas_cancel_event_scan(void);
+void rtas_cancel_event_scan(void);
 #else
 static inline void rtas_cancel_event_scan(void) { }
 #endif
 
 /* Error types logged.  */
 #define ERR_FLAG_ALREADY_LOGGED	0x0
-#define ERR_FLAG_BOOT		0x1 	/* log was pulled from NVRAM on boot */
+#define ERR_FLAG_BOOT		0x1	/* log was pulled from NVRAM on boot */
 #define ERR_TYPE_RTAS_LOG	0x2	/* from rtas event-scan */
 #define ERR_TYPE_KERNEL_PANIC	0x4	/* from die()/panic() */
 #define ERR_TYPE_KERNEL_PANIC_GZ 0x8	/* ditto, compressed */
@@ -470,7 +493,7 @@ static inline void rtas_cancel_event_scan(void) { }
 	(ERR_TYPE_RTAS_LOG | ERR_TYPE_KERNEL_PANIC | ERR_TYPE_KERNEL_PANIC_GZ)
 
 #define RTAS_DEBUG KERN_DEBUG "RTAS: "
- 
+
 #define RTAS_ERROR_LOG_MAX 2048
 
 /*
@@ -478,7 +501,7 @@ static inline void rtas_cancel_event_scan(void) { }
  *  for all rtas calls that require an error buffer argument.
  *  This includes 'check-exception' and 'rtas-last-error'.
  */
-extern int rtas_get_error_log_max(void);
+int rtas_get_error_log_max(void);
 
 /* Event Scan Parameters */
 #define EVENT_SCAN_ALL_EVENTS	0xf0000000
@@ -499,6 +522,13 @@ extern char rtas_data_buf[RTAS_DATA_BUF_SIZE];
 /* RMO buffer reserved for user-space RTAS use */
 extern unsigned long rtas_rmo_buf;
 
+extern struct mutex rtas_ibm_get_vpd_lock;
+extern struct mutex rtas_ibm_get_indices_lock;
+extern struct mutex rtas_ibm_set_dynamic_indicator_lock;
+extern struct mutex rtas_ibm_get_dynamic_sensor_state_lock;
+extern struct mutex rtas_ibm_physical_attestation_lock;
+extern struct mutex rtas_ibm_send_hvpipe_msg_lock;
+
 #define GLOBAL_INTERRUPT_QUEUE 9005
 
 /**
@@ -517,8 +547,8 @@ static inline u32 rtas_config_addr(int busno, int devfn, int reg)
 			(devfn << 8) | (reg & 0xff);
 }
 
-extern void rtas_give_timebase(void);
-extern void rtas_take_timebase(void);
+void rtas_give_timebase(void);
+void rtas_take_timebase(void);
 
 #ifdef CONFIG_PPC_RTAS
 static inline int page_is_rtas_user_buf(unsigned long pfn)
@@ -531,7 +561,7 @@ static inline int page_is_rtas_user_buf(unsigned long pfn)
 
 /* Not the best place to put pSeries_coalesce_init, will be fixed when we
  * move some of the rtas suspend-me stuff to pseries */
-extern void pSeries_coalesce_init(void);
+void pSeries_coalesce_init(void);
 void rtas_initialize(void);
 #else
 static inline int page_is_rtas_user_buf(unsigned long pfn) { return 0;}
@@ -539,8 +569,6 @@ static inline void pSeries_coalesce_init(void) { }
 static inline void rtas_initialize(void) { }
 #endif
 
-extern int call_rtas(const char *, int, int, unsigned long *, ...);
-
 #ifdef CONFIG_HV_PERF_CTRS
 void read_24x7_sys_info(void);
 #else
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 4e1f548c8d37..f43f3a6b0051 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -14,6 +14,7 @@ typedef struct func_desc func_desc_t;
 
 extern char __head_end[];
 extern char __srwx_boundary[];
+extern char __exittext_begin[], __exittext_end[];
 
 /* Patch sites */
 extern s32 patch__call_flush_branch_caches1;
@@ -74,6 +75,8 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
 		(unsigned long)_stext < end;
 }
 
+#else
+static inline unsigned long kernel_toc_addr(void) { BUILD_BUG(); return -1UL; }
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/set_memory.h b/arch/powerpc/include/asm/set_memory.h
index 7ebc807aa8cc..9c8d5747755d 100644
--- a/arch/powerpc/include/asm/set_memory.h
+++ b/arch/powerpc/include/asm/set_memory.h
@@ -8,37 +8,44 @@
 #define SET_MEMORY_X	3
 #define SET_MEMORY_NP	4	/* Set memory non present */
 #define SET_MEMORY_P	5	/* Set memory present */
+#define SET_MEMORY_ROX	6
 
 int change_memory_attr(unsigned long addr, int numpages, long action);
 
-static inline int set_memory_ro(unsigned long addr, int numpages)
+static inline int __must_check set_memory_ro(unsigned long addr, int numpages)
 {
 	return change_memory_attr(addr, numpages, SET_MEMORY_RO);
 }
 
-static inline int set_memory_rw(unsigned long addr, int numpages)
+static inline int __must_check set_memory_rw(unsigned long addr, int numpages)
 {
 	return change_memory_attr(addr, numpages, SET_MEMORY_RW);
 }
 
-static inline int set_memory_nx(unsigned long addr, int numpages)
+static inline int __must_check set_memory_nx(unsigned long addr, int numpages)
 {
 	return change_memory_attr(addr, numpages, SET_MEMORY_NX);
 }
 
-static inline int set_memory_x(unsigned long addr, int numpages)
+static inline int __must_check set_memory_x(unsigned long addr, int numpages)
 {
 	return change_memory_attr(addr, numpages, SET_MEMORY_X);
 }
 
-static inline int set_memory_np(unsigned long addr, int numpages)
+static inline int __must_check set_memory_np(unsigned long addr, int numpages)
 {
 	return change_memory_attr(addr, numpages, SET_MEMORY_NP);
 }
 
-static inline int set_memory_p(unsigned long addr, int numpages)
+static inline int __must_check set_memory_p(unsigned long addr, int numpages)
 {
 	return change_memory_attr(addr, numpages, SET_MEMORY_P);
 }
 
+static inline int __must_check set_memory_rox(unsigned long addr, int numpages)
+{
+	return change_memory_attr(addr, numpages, SET_MEMORY_ROX);
+}
+#define set_memory_rox set_memory_rox
+
 #endif
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index e29e83f8a89c..50a92b24628d 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -4,11 +4,10 @@
 
 #include <uapi/asm/setup.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern void ppc_printk_progress(char *s, unsigned short hex);
 
 extern unsigned long long memory_limit;
-extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
 struct device_node;
 
@@ -90,7 +89,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 
 extern struct seq_buf ppc_hw_desc;
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif	/* _ASM_POWERPC_SETUP_H */
 
diff --git a/arch/powerpc/include/asm/simple_spinlock.h b/arch/powerpc/include/asm/simple_spinlock.h
index 9dcc7e9993b9..4dd12dcb9ef8 100644
--- a/arch/powerpc/include/asm/simple_spinlock.h
+++ b/arch/powerpc/include/asm/simple_spinlock.h
@@ -15,6 +15,7 @@
  * (the type definitions are in asm/simple_spinlock_types.h)
  */
 #include <linux/irqflags.h>
+#include <linux/kcsan-checks.h>
 #include <asm/paravirt.h>
 #include <asm/paca.h>
 #include <asm/synch.h>
@@ -126,6 +127,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
+	kcsan_mb();
 	__asm__ __volatile__("# arch_spin_unlock\n\t"
 				PPC_RELEASE_BARRIER: : :"memory");
 	lock->slock = 0;
diff --git a/arch/powerpc/include/asm/simple_spinlock_types.h b/arch/powerpc/include/asm/simple_spinlock_types.h
index 08243338069d..391fc19f7272 100644
--- a/arch/powerpc/include/asm/simple_spinlock_types.h
+++ b/arch/powerpc/include/asm/simple_spinlock_types.h
@@ -3,7 +3,7 @@
 #define _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 typedef struct {
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index aaaa576d0e15..e41b9ea42122 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -18,7 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/irqreturn.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
@@ -27,6 +27,7 @@
 
 extern int boot_cpuid;
 extern int boot_cpu_hwid; /* PPC64 only */
+extern int boot_core_hwid;
 extern int spinning_secondaries;
 extern u32 *cpu_to_phys_id;
 extern bool coregroup_enabled;
@@ -265,7 +266,7 @@ extern char __secondary_hold;
 extern unsigned int booting_thread_hwid;
 
 extern void __early_start(void);
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_SMP_H) */
diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h
index 40b01446cf75..569765fa16bc 100644
--- a/arch/powerpc/include/asm/spinlock_types.h
+++ b/arch/powerpc/include/asm/spinlock_types.h
@@ -3,7 +3,7 @@
 #define _ASM_POWERPC_SPINLOCK_TYPES_H
 
 #ifndef __LINUX_SPINLOCK_TYPES_RAW_H
-# error "please don't include this file directly"
+# error "Please do not include this file directly."
 #endif
 
 #ifdef CONFIG_PPC_QUEUED_SPINLOCKS
diff --git a/arch/powerpc/include/asm/spu_csa.h b/arch/powerpc/include/asm/spu_csa.h
index c33df961c045..1b3271a03392 100644
--- a/arch/powerpc/include/asm/spu_csa.h
+++ b/arch/powerpc/include/asm/spu_csa.h
@@ -43,7 +43,7 @@
 #define SPU_DECR_STATUS_RUNNING 0x1
 #define SPU_DECR_STATUS_WRAPPED 0x2
 
-#ifndef  __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /**
  * spu_reg128 - generic 128-bit register definition.
  */
@@ -243,5 +243,5 @@ struct spu_state {
 
 #endif /* !__SPU__ */
 #endif /* __KERNEL__ */
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _SPU_CSA_H_ */
diff --git a/arch/powerpc/include/asm/spu_priv1.h b/arch/powerpc/include/asm/spu_priv1.h
index 2167d756e6d5..66b111fa1cd1 100644
--- a/arch/powerpc/include/asm/spu_priv1.h
+++ b/arch/powerpc/include/asm/spu_priv1.h
@@ -215,9 +215,6 @@ spu_disable_spu (struct spu_context *ctx)
  * and only intended to be used by the platform setup code.
  */
 
-extern const struct spu_priv1_ops spu_priv1_mmio_ops;
-extern const struct spu_priv1_ops spu_priv1_beat_ops;
-
 extern const struct spu_management_ops spu_management_of_ops;
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h
index 50950deedb87..e3d0e714ff28 100644
--- a/arch/powerpc/include/asm/sstep.h
+++ b/arch/powerpc/include/asm/sstep.h
@@ -173,9 +173,4 @@ int emulate_step(struct pt_regs *regs, ppc_inst_t instr);
  */
 extern int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op);
 
-extern void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
-			     const void *mem, bool cross_endian);
-extern void emulate_vsx_store(struct instruction_op *op,
-			      const union vsx_reg *reg, void *mem,
-			      bool cross_endian);
 extern int emulate_dcbz(unsigned long ea, struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h
index de1018cc522b..e3d5d3823dac 100644
--- a/arch/powerpc/include/asm/static_call.h
+++ b/arch/powerpc/include/asm/static_call.h
@@ -26,4 +26,6 @@
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)	__PPC_SCT(name, "blr")
 #define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name)	__PPC_SCT(name, "b .+20")
 
+#define CALL_INSN_SIZE		4
+
 #endif /* _ASM_POWERPC_STATIC_CALL_H */
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index aee25e3ebf96..fc933807ddc8 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -48,6 +48,10 @@ static inline void disable_kernel_fp(void)
 #else
 static inline void save_fpu(struct task_struct *t) { }
 static inline void flush_fp_to_thread(struct task_struct *t) { }
+static inline void enable_kernel_fp(void)
+{
+	BUILD_BUG();
+}
 #endif
 
 #ifdef CONFIG_ALTIVEC
diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h
index b0b4c64870d7..0d3ccb34adfb 100644
--- a/arch/powerpc/include/asm/synch.h
+++ b/arch/powerpc/include/asm/synch.h
@@ -7,7 +7,7 @@
 #include <asm/feature-fixups.h>
 #include <asm/ppc-opcode.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,
 			     void *fixup_end);
@@ -40,7 +40,7 @@ static inline void ppc_after_tlbiel_barrier(void)
 	 */
 	asm volatile(ASM_FTR_IFSET(PPC_CP_ABORT, "", %0) : : "i" (CPU_FTR_ARCH_31) : "memory");
 }
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #if defined(__powerpc64__)
 #    define LWSYNC	lwsync
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 3dd36c5e334a..4b3c52ed6e9d 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -39,6 +39,16 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 		return -1;
 }
 
+static inline void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr)
+{
+	/*
+	 * Unlike syscall_get_nr(), syscall_set_nr() can be called only when
+	 * the target task is stopped for tracing on entering syscall, so
+	 * there is no need to have the same check syscall_get_nr() has.
+	 */
+	regs->gpr[0] = nr;
+}
+
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
@@ -110,6 +120,16 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	}
 }
 
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 const unsigned long *args)
+{
+	memcpy(&regs->gpr[3], args, 6 * sizeof(args[0]));
+
+	/* Also copy the first argument into orig_gpr3 */
+	regs->orig_gpr3 = args[0];
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	if (is_tsk_32bit_task(task))
diff --git a/arch/powerpc/include/asm/systemcfg.h b/arch/powerpc/include/asm/systemcfg.h
new file mode 100644
index 000000000000..2f9b1d6a5c98
--- /dev/null
+++ b/arch/powerpc/include/asm/systemcfg.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _SYSTEMCFG_H
+#define _SYSTEMCFG_H
+
+/*
+ * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM
+ * Copyright (C) 2005 Benjamin Herrenschmidy <benh@kernel.crashing.org>,
+ * 		      IBM Corp.
+ */
+
+#ifdef CONFIG_PPC64
+
+/*
+ * If the major version changes we are incompatible.
+ * Minor version changes are a hint.
+ */
+#define SYSTEMCFG_MAJOR 1
+#define SYSTEMCFG_MINOR 1
+
+#include <linux/types.h>
+
+struct systemcfg {
+	__u8  eye_catcher[16];		/* Eyecatcher: SYSTEMCFG:PPC64	0x00 */
+	struct {			/* Systemcfg version numbers	     */
+		__u32 major;		/* Major number			0x10 */
+		__u32 minor;		/* Minor number			0x14 */
+	} version;
+
+	/* Note about the platform flags: it now only contains the lpar
+	 * bit. The actual platform number is dead and buried
+	 */
+	__u32 platform;			/* Platform flags		0x18 */
+	__u32 processor;		/* Processor type		0x1C */
+	__u64 processorCount;		/* # of physical processors	0x20 */
+	__u64 physicalMemorySize;	/* Size of real memory(B)	0x28 */
+	__u64 tb_orig_stamp;		/* (NU) Timebase at boot	0x30 */
+	__u64 tb_ticks_per_sec;		/* Timebase tics / sec		0x38 */
+	__u64 tb_to_xs;			/* (NU) Inverse of TB to 2^20	0x40 */
+	__u64 stamp_xsec;		/* (NU)				0x48 */
+	__u64 tb_update_count;		/* (NU) Timebase atomicity ctr	0x50 */
+	__u32 tz_minuteswest;		/* (NU) Min. west of Greenwich	0x58 */
+	__u32 tz_dsttime;		/* (NU) Type of dst correction	0x5C */
+	__u32 dcache_size;		/* L1 d-cache size		0x60 */
+	__u32 dcache_line_size;		/* L1 d-cache line size		0x64 */
+	__u32 icache_size;		/* L1 i-cache size		0x68 */
+	__u32 icache_line_size;		/* L1 i-cache line size		0x6C */
+};
+
+extern struct systemcfg *systemcfg;
+
+#endif /* CONFIG_PPC64 */
+#endif /* _SYSTEMCFG_H */
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/text-patching.h
index 3f881548fb61..e7f14720f630 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/text-patching.h
@@ -74,6 +74,44 @@ int create_cond_branch(ppc_inst_t *instr, const u32 *addr,
 int patch_branch(u32 *addr, unsigned long target, int flags);
 int patch_instruction(u32 *addr, ppc_inst_t instr);
 int raw_patch_instruction(u32 *addr, ppc_inst_t instr);
+int patch_instructions(u32 *addr, u32 *code, size_t len, bool repeat_instr);
+
+/*
+ * The data patching functions patch_uint() and patch_ulong(), etc., must be
+ * called on aligned addresses.
+ *
+ * The instruction patching functions patch_instruction() and similar must be
+ * called on addresses satisfying instruction alignment requirements.
+ */
+
+#ifdef CONFIG_PPC64
+
+int patch_uint(void *addr, unsigned int val);
+int patch_ulong(void *addr, unsigned long val);
+
+#define patch_u64 patch_ulong
+
+#else
+
+static inline int patch_uint(void *addr, unsigned int val)
+{
+	if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned int)))
+		return -EINVAL;
+
+	return patch_instruction(addr, ppc_inst(val));
+}
+
+static inline int patch_ulong(void *addr, unsigned long val)
+{
+	if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned long)))
+		return -EINVAL;
+
+	return patch_instruction(addr, ppc_inst(val));
+}
+
+#endif
+
+#define patch_u32 patch_uint
 
 static inline unsigned long patch_site_addr(s32 *site)
 {
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index bf5dde1a4114..b0f200aba2b3 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -14,7 +14,7 @@
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15
 #define MIN_THREAD_SHIFT	(CONFIG_THREAD_SHIFT + 1)
 #else
 #define MIN_THREAD_SHIFT	CONFIG_THREAD_SHIFT
@@ -41,7 +41,7 @@
 
 #define THREAD_ALIGN		(1 << THREAD_ALIGN_SHIFT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/cache.h>
 #include <asm/processor.h>
 #include <asm/accounting.h>
@@ -89,7 +89,7 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src
 void arch_setup_new_exec(void);
 #define arch_setup_new_exec arch_setup_new_exec
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * thread information flag bit numbers
@@ -103,6 +103,7 @@ void arch_setup_new_exec(void);
 #define TIF_PATCH_PENDING	6	/* pending live patching update */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SINGLESTEP		8	/* singlestepping active */
+#define TIF_NEED_RESCHED_LAZY	9       /* Scheduler driven lazy preemption */
 #define TIF_SECCOMP		10	/* secure computing */
 #define TIF_RESTOREALL		11	/* Restore all regs (implies NOERROR) */
 #define TIF_NOERROR		12	/* Force successful syscall return */
@@ -122,6 +123,7 @@ void arch_setup_new_exec(void);
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED_LAZY	(1<<TIF_NEED_RESCHED_LAZY)
 #define _TIF_NOTIFY_SIGNAL	(1<<TIF_NOTIFY_SIGNAL)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_32BIT		(1<<TIF_32BIT)
@@ -142,9 +144,10 @@ void arch_setup_new_exec(void);
 				 _TIF_SYSCALL_EMU)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
-				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
-				 _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \
-				 _TIF_NOTIFY_SIGNAL)
+				 _TIF_NEED_RESCHED_LAZY | _TIF_NOTIFY_RESUME | \
+				 _TIF_UPROBE | _TIF_RESTORE_TM | \
+				 _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL)
+
 #define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR)
 
 /* Bits in local_flags */
@@ -159,7 +162,7 @@ void arch_setup_new_exec(void);
 #define _TLF_LAZY_MMU		(1 << TLF_LAZY_MMU)
 #define _TLF_RUNLATCH		(1 << TLF_RUNLATCH)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 static inline void clear_thread_local_flags(unsigned int flags)
 {
@@ -226,7 +229,11 @@ static inline int arch_within_stack_frames(const void * const stack,
 	return BAD_STACK;
 }
 
-#endif	/* !__ASSEMBLY__ */
+#ifdef CONFIG_PPC32
+extern void *emergency_ctx[];
+#endif
+
+#endif	/* !__ASSEMBLER__ */
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 9f50766c4623..7991ab1d4cb8 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -29,6 +29,10 @@ extern u64 decrementer_max;
 
 extern void generic_calibrate_decr(void);
 
+#ifdef CONFIG_PPC_SPLPAR
+extern u64 get_boot_tb(void);
+#endif
+
 /* Some sane defaults: 125 MHz timebase, 1GHz processor */
 extern unsigned long ppc_proc_freq;
 #define DEFAULT_PROC_FREQ	(DEFAULT_TB_FREQ * 8)
@@ -58,9 +62,6 @@ static inline u64 get_vtb(void)
  */
 static inline u64 get_dec(void)
 {
-	if (IS_ENABLED(CONFIG_40x))
-		return mfspr(SPRN_PIT);
-
 	return mfspr(SPRN_DEC);
 }
 
@@ -71,9 +72,7 @@ static inline u64 get_dec(void)
  */
 static inline void set_dec(u64 val)
 {
-	if (IS_ENABLED(CONFIG_40x))
-		mtspr(SPRN_PIT, (u32)val);
-	else if (IS_ENABLED(CONFIG_BOOKE))
+	if (IS_ENABLED(CONFIG_BOOKE))
 		mtspr(SPRN_DEC, val);
 	else
 		mtspr(SPRN_DEC, val - 1);
@@ -91,12 +90,9 @@ static inline unsigned long tb_ticks_since(unsigned long tstamp)
 #define mulhdu(x,y) \
 ({unsigned long z; asm ("mulhdu %0,%1,%2" : "=r" (z) : "r" (x), "r" (y)); z;})
 #else
-extern u64 mulhdu(u64, u64);
+#define mulhdu(x, y)	mul_u64_u64_shr(x, y, 64)
 #endif
 
-extern void div128_by_32(u64 dividend_high, u64 dividend_low,
-			 unsigned divisor, struct div_result *dr);
-
 extern void secondary_cpu_time_init(void);
 extern void __init time_init(void);
 
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index b3de6102a907..2058e8d3e013 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -19,6 +19,8 @@
 
 #include <linux/pagemap.h>
 
+static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
+					  unsigned long address);
 #define __tlb_remove_tlb_entry	__tlb_remove_tlb_entry
 
 #define tlb_flush tlb_flush
@@ -35,6 +37,7 @@ extern void tlb_flush(struct mmu_gather *tlb);
  */
 #define tlb_needs_table_invalidate()	radix_enabled()
 
+#define __HAVE_ARCH_TLB_REMOVE_TABLE
 /* Get the generic bits... */
 #include <asm-generic/tlb.h>
 
diff --git a/arch/powerpc/include/asm/tm.h b/arch/powerpc/include/asm/tm.h
index e94f6db5e367..d700affba448 100644
--- a/arch/powerpc/include/asm/tm.h
+++ b/arch/powerpc/include/asm/tm.h
@@ -8,7 +8,7 @@
 
 #include <uapi/asm/tm.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 extern void tm_reclaim(struct thread_struct *thread,
 		       uint8_t cause);
@@ -19,4 +19,4 @@ extern void tm_restore_sprs(struct thread_struct *thread);
 
 extern bool tm_suspend_disabled;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8a4d4f4d9749..66ed5fe1b718 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -131,17 +131,51 @@ static inline int cpu_to_coregroup_id(int cpu)
 #ifdef CONFIG_SMP
 #include <asm/cputable.h>
 
+struct cpumask *cpu_coregroup_mask(int cpu);
+const struct cpumask *cpu_die_mask(int cpu);
+int cpu_die_id(int cpu);
+
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
 #define topology_physical_package_id(cpu)	(cpu_to_chip_id(cpu))
-
-#define topology_sibling_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
-#define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
-#define topology_core_id(cpu)		(cpu_to_core_id(cpu))
+#define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
+#define topology_core_id(cpu)			(cpu_to_core_id(cpu))
+#define topology_die_id(cpu)			(cpu_die_id(cpu))
+#define topology_die_cpumask(cpu)		(cpu_die_mask(cpu))
 
 #endif
 #endif
 
+#ifdef CONFIG_HOTPLUG_SMT
+#include <linux/cpu_smt.h>
+#include <linux/cpumask.h>
+#include <asm/cputhreads.h>
+
+static inline bool topology_is_primary_thread(unsigned int cpu)
+{
+	return cpu == cpu_first_thread_sibling(cpu);
+}
+#define topology_is_primary_thread topology_is_primary_thread
+
+static inline bool topology_smt_thread_allowed(unsigned int cpu)
+{
+	return cpu_thread_in_core(cpu) < cpu_smt_num_threads;
+}
+
+#define topology_is_core_online topology_is_core_online
+static inline bool topology_is_core_online(unsigned int cpu)
+{
+	int i, first_cpu = cpu_first_thread_sibling(cpu);
+
+	for (i = first_cpu; i < first_cpu + threads_per_core; ++i) {
+		if (cpu_online(i))
+			return true;
+	}
+	return false;
+}
+#endif
+
 #endif /* __KERNEL__ */
 #endif	/* _ASM_POWERPC_TOPOLOGY_H */
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index 82cc2c6704e6..a7b69b25296b 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -137,7 +137,7 @@ TRACE_EVENT(rtas_input,
 
 	TP_fast_assign(
 		__entry->nargs = be32_to_cpu(rtas_args->nargs);
-		__assign_str(name, name);
+		__assign_str(name);
 		be32_to_cpu_array(__get_dynamic_array(inputs), rtas_args->args, __entry->nargs);
 	),
 
@@ -162,7 +162,7 @@ TRACE_EVENT(rtas_output,
 	TP_fast_assign(
 		__entry->nr_other = be32_to_cpu(rtas_args->nret) - 1;
 		__entry->status = be32_to_cpu(rtas_args->rets[0]);
-		__assign_str(name, name);
+		__assign_str(name);
 		be32_to_cpu_array(__get_dynamic_array(other_outputs),
 				  &rtas_args->rets[1], __entry->nr_other);
 	),
@@ -267,6 +267,7 @@ TRACE_EVENT_FN(opal_exit,
 );
 #endif
 
+#ifdef CONFIG_PPC_64S_HASH_MMU
 TRACE_EVENT(hash_fault,
 
 	    TP_PROTO(unsigned long addr, unsigned long access, unsigned long trap),
@@ -286,7 +287,7 @@ TRACE_EVENT(hash_fault,
 	    TP_printk("hash fault with addr 0x%lx and access = 0x%lx trap = 0x%lx",
 		      __entry->addr, __entry->access, __entry->trap)
 );
-
+#endif
 
 TRACE_EVENT(tlbie,
 
diff --git a/arch/powerpc/include/asm/types.h b/arch/powerpc/include/asm/types.h
index 93157a661dcc..55d7ba6d910b 100644
--- a/arch/powerpc/include/asm/types.h
+++ b/arch/powerpc/include/asm/types.h
@@ -11,10 +11,10 @@
 
 #include <uapi/asm/types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 typedef __vector128 vector128;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_TYPES_H */
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index a2d255aa9627..784a00e681fa 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -6,6 +6,7 @@
 #include <asm/page.h>
 #include <asm/extable.h>
 #include <asm/kup.h>
+#include <asm/asm-compat.h>
 
 #ifdef __powerpc64__
 /* We use TASK_SIZE_USER64 as TASK_SIZE is not constant */
@@ -74,7 +75,7 @@ __pu_failed:							\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op " %0,0(%1)	# put_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -83,7 +84,7 @@ __pu_failed:							\
 		: label)
 #else
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op "%U1%X1 %0,%1	# put_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -93,11 +94,21 @@ __pu_failed:							\
 #endif
 
 #ifdef __powerpc64__
+#ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __put_user_asm2_goto(x, ptr, label)			\
 	__put_user_asm_goto(x, ptr, label, "std")
+#else
+#define __put_user_asm2_goto(x, addr, label)			\
+	asm goto ("1: std%U1%X1 %0,%1	# put_user\n"		\
+		EX_TABLE(1b, %l2)				\
+		:						\
+		: "r" (x), DS_FORM_CONSTRAINT (*addr)		\
+		:						\
+		: label)
+#endif // CONFIG_PPC_KERNEL_PREFIXED
 #else /* __powerpc64__ */
 #define __put_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	stw%X1 %0, %1\n"			\
 		"2:	stw%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
@@ -146,7 +157,7 @@ do {								\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op" %0,0(%1)	# get_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -155,7 +166,7 @@ do {								\
 		: label)
 #else
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op"%U1%X1 %0, %1	# get_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -165,11 +176,22 @@ do {								\
 #endif
 
 #ifdef __powerpc64__
+#ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __get_user_asm2_goto(x, addr, label)			\
 	__get_user_asm_goto(x, addr, label, "ld")
+#else
+#define __get_user_asm2_goto(x, addr, label)			\
+	asm_goto_output(					\
+		"1:	ld%U1%X1 %0, %1	# get_user\n"		\
+		EX_TABLE(1b, %l2)				\
+		: "=r" (x)					\
+		: DS_FORM_CONSTRAINT (*addr)			\
+		:						\
+		: label)
+#endif // CONFIG_PPC_KERNEL_PREFIXED
 #else /* __powerpc64__ */
 #define __get_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	lwz%X1 %0, %1\n"			\
 		"2:	lwz%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
@@ -374,7 +396,7 @@ copy_mc_to_user(void __user *to, const void *from, unsigned long n)
 	if (check_copy_size(from, n, true)) {
 		if (access_ok(to, n)) {
 			allow_write_to_user(to, n);
-			n = copy_mc_generic((void *)to, from, n);
+			n = copy_mc_generic((void __force *)to, from, n);
 			prevent_write_to_user(to, n);
 		}
 	}
@@ -386,7 +408,7 @@ copy_mc_to_user(void __user *to, const void *from, unsigned long n)
 extern long __copy_from_user_flushcache(void *dst, const void __user *src,
 		unsigned size);
 
-static __must_check inline bool user_access_begin(const void __user *ptr, size_t len)
+static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len)
 {
 	if (unlikely(!access_ok(ptr, len)))
 		return false;
@@ -401,7 +423,7 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t
 #define user_access_save	prevent_user_access_return
 #define user_access_restore	restore_user_access
 
-static __must_check inline bool
+static __must_check __always_inline bool
 user_read_access_begin(const void __user *ptr, size_t len)
 {
 	if (unlikely(!access_ok(ptr, len)))
@@ -415,7 +437,7 @@ user_read_access_begin(const void __user *ptr, size_t len)
 #define user_read_access_begin	user_read_access_begin
 #define user_read_access_end		prevent_current_read_from_user
 
-static __must_check inline bool
+static __must_check __always_inline bool
 user_write_access_begin(const void __user *ptr, size_t len)
 {
 	if (unlikely(!access_ok(ptr, len)))
@@ -429,7 +451,7 @@ user_write_access_begin(const void __user *ptr, size_t len)
 #define user_write_access_begin	user_write_access_begin
 #define user_write_access_end		prevent_current_write_to_user
 
-#define unsafe_get_user(x, p, e) do {					\
+#define arch_unsafe_get_user(x, p, e) do {			\
 	__long_type(*(p)) __gu_val;				\
 	__typeof__(*(p)) __user *__gu_addr = (p);		\
 								\
@@ -437,7 +459,7 @@ user_write_access_begin(const void __user *ptr, size_t len)
 	(x) = (__typeof__(*(p)))__gu_val;			\
 } while (0)
 
-#define unsafe_put_user(x, p, e) \
+#define arch_unsafe_put_user(x, p, e)				\
 	__put_user_size_goto((__typeof__(*(p)))(x), (p), sizeof(*(p)), e)
 
 #define unsafe_copy_from_user(d, s, l, e) \
@@ -482,11 +504,11 @@ do {									\
 		unsafe_put_user(*(u8*)(_src + _i), (u8 __user *)(_dst + _i), e); \
 } while (0)
 
-#define __get_kernel_nofault(dst, src, type, err_label)			\
+#define arch_get_kernel_nofault(dst, src, type, err_label)		\
 	__get_user_size_goto(*((type *)(dst)),				\
 		(__force type __user *)(src), sizeof(type), err_label)
 
-#define __put_kernel_nofault(dst, src, type, err_label)			\
+#define arch_put_kernel_nofault(dst, src, type, err_label)		\
 	__put_user_size_goto(*((type *)(src)),				\
 		(__force type __user *)(dst), sizeof(type), err_label)
 
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index b1f094728b35..a8681b12864f 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -38,13 +38,11 @@ void __init udbg_early_init(void);
 void __init udbg_init_debug_lpar(void);
 void __init udbg_init_debug_lpar_hvsi(void);
 void __init udbg_init_pmac_realmode(void);
-void __init udbg_init_maple_realmode(void);
 void __init udbg_init_pas_realmode(void);
 void __init udbg_init_rtas_panel(void);
 void __init udbg_init_rtas_console(void);
 void __init udbg_init_btext(void);
 void __init udbg_init_44x_as1(void);
-void __init udbg_init_40x_realmode(void);
 void __init udbg_init_cpm(void);
 void __init udbg_init_usbgecko(void);
 void __init udbg_init_memcons(void);
diff --git a/arch/powerpc/include/asm/uninorth.h b/arch/powerpc/include/asm/uninorth.h
index e278299b9b37..6949b5daa37d 100644
--- a/arch/powerpc/include/asm/uninorth.h
+++ b/arch/powerpc/include/asm/uninorth.h
@@ -144,7 +144,7 @@
 #define UNI_N_HWINIT_STATE_SLEEPING	0x01
 #define UNI_N_HWINIT_STATE_RUNNING	0x02
 /* This last bit appear to be used by the bootROM to know the second
- * CPU has started and will enter it's sleep loop with IP=0
+ * CPU has started and will enter its sleep loop with IP=0
  */
 #define UNI_N_HWINIT_STATE_CPU1_FLAG	0x10000000
 
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 659a996c75aa..b873fbb6d712 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -9,7 +9,7 @@
 
 #define NR_syscalls	__NR_syscalls
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/compiler.h>
@@ -51,7 +51,6 @@
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
-#define __ARCH_WANT_SYS_CLONE3
 
-#endif		/* __ASSEMBLY__ */
+#endif		/* __ASSEMBLER__ */
 #endif /* _ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index 7650b6ce14c8..07af32576072 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -3,8 +3,9 @@
 #define _ASM_POWERPC_VDSO_H
 
 #define VDSO_VERSION_STRING	LINUX_2.6.15
+#define __VDSO_PAGES		4
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_PPC64
 #include <generated/vdso64-offsets.h>
@@ -20,11 +21,12 @@
 
 int vdso_getcpu_init(void);
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #ifdef __VDSO64__
 #define V_FUNCTION_BEGIN(name)		\
 	.globl name;			\
+	.type name,@function; 		\
 	name:				\
 
 #define V_FUNCTION_END(name)		\
@@ -47,6 +49,6 @@ int vdso_getcpu_init(void);
 
 #endif /* __VDSO32__ */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_VDSO_H */
diff --git a/arch/powerpc/include/asm/vdso/arch_data.h b/arch/powerpc/include/asm/vdso/arch_data.h
new file mode 100644
index 000000000000..c240a6b87518
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/arch_data.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM
+ * Copyright (C) 2005 Benjamin Herrenschmidy <benh@kernel.crashing.org>,
+ * 		      IBM Corp.
+ */
+#ifndef _ASM_POWERPC_VDSO_ARCH_DATA_H
+#define _ASM_POWERPC_VDSO_ARCH_DATA_H
+
+#include <linux/unistd.h>
+#include <linux/types.h>
+
+#define SYSCALL_MAP_SIZE      ((NR_syscalls + 31) / 32)
+
+#ifdef CONFIG_PPC64
+
+struct vdso_arch_data {
+	__u64 tb_ticks_per_sec;			/* Timebase tics / sec */
+	__u32 dcache_block_size;		/* L1 d-cache block size     */
+	__u32 icache_block_size;		/* L1 i-cache block size     */
+	__u32 dcache_log_block_size;		/* L1 d-cache log block size */
+	__u32 icache_log_block_size;		/* L1 i-cache log block size */
+	__u32 syscall_map[SYSCALL_MAP_SIZE];	/* Map of syscalls  */
+	__u32 compat_syscall_map[SYSCALL_MAP_SIZE];	/* Map of compat syscalls */
+};
+
+#else /* CONFIG_PPC64 */
+
+struct vdso_arch_data {
+	__u64 tb_ticks_per_sec;		/* Timebase tics / sec */
+	__u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */
+	__u32 compat_syscall_map[0];	/* No compat syscalls on PPC32 */
+};
+
+#endif /* CONFIG_PPC64 */
+
+#endif /* _ASM_POWERPC_VDSO_ARCH_DATA_H */
diff --git a/arch/powerpc/include/asm/vdso/getrandom.h b/arch/powerpc/include/asm/vdso/getrandom.h
new file mode 100644
index 000000000000..4c24976061f4
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/getrandom.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+#ifndef _ASM_POWERPC_VDSO_GETRANDOM_H
+#define _ASM_POWERPC_VDSO_GETRANDOM_H
+
+#ifndef __ASSEMBLER__
+
+#include <asm/vdso_datapage.h>
+
+static __always_inline int do_syscall_3(const unsigned long _r0, const unsigned long _r3,
+					const unsigned long _r4, const unsigned long _r5)
+{
+	register long r0 asm("r0") = _r0;
+	register unsigned long r3 asm("r3") = _r3;
+	register unsigned long r4 asm("r4") = _r4;
+	register unsigned long r5 asm("r5") = _r5;
+	register int ret asm ("r3");
+
+	asm volatile(
+		"       sc\n"
+		"	bns+	1f\n"
+		"	neg	%0, %0\n"
+		"1:\n"
+	: "=r" (ret), "+r" (r4), "+r" (r5), "+r" (r0)
+	: "r" (r3)
+	: "memory", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "cr0", "ctr");
+
+	return ret;
+}
+
+/**
+ * getrandom_syscall - Invoke the getrandom() syscall.
+ * @buffer:	Destination buffer to fill with random bytes.
+ * @len:	Size of @buffer in bytes.
+ * @flags:	Zero or more GRND_* flags.
+ * Returns:	The number of bytes written to @buffer, or a negative value indicating an error.
+ */
+static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsigned int flags)
+{
+	return do_syscall_3(__NR_getrandom, (unsigned long)buffer,
+			    (unsigned long)len, (unsigned long)flags);
+}
+
+static __always_inline const struct vdso_rng_data *__arch_get_vdso_u_rng_data(void)
+{
+	struct vdso_rng_data *data;
+
+	asm (
+		"	bcl	20, 31, .+4 ;"
+		"0:	mflr	%0 ;"
+		"	addis	%0, %0, (vdso_u_rng_data - 0b)@ha ;"
+		"	addi	%0, %0, (vdso_u_rng_data - 0b)@l  ;"
+		: "=r" (data) : : "lr"
+	);
+
+	return data;
+}
+#define __arch_get_vdso_u_rng_data __arch_get_vdso_u_rng_data
+
+ssize_t __c_kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state,
+			     size_t opaque_len);
+
+#endif /* !__ASSEMBLER__ */
+
+#endif /* _ASM_POWERPC_VDSO_GETRANDOM_H */
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index f0a4cf01e85c..ab3df12c8d94 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -2,9 +2,8 @@
 #ifndef _ASM_POWERPC_VDSO_GETTIMEOFDAY_H
 #define _ASM_POWERPC_VDSO_GETTIMEOFDAY_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
-#include <asm/page.h>
 #include <asm/vdso/timebase.h>
 #include <asm/barrier.h>
 #include <asm/unistd.h>
@@ -14,6 +13,17 @@
 
 #define VDSO_HAS_TIME			1
 
+/*
+ * powerpc specific delta calculation.
+ *
+ * This variant removes the masking of the subtraction because the
+ * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX
+ * which would result in a pointless operation. The compiler cannot
+ * optimize it away as the mask comes from the vdso data and is not compile
+ * time constant.
+ */
+#define VDSO_DELTA_NOMASK		1
+
 static __always_inline int do_syscall_2(const unsigned long _r0, const unsigned long _r3,
 					const unsigned long _r4)
 {
@@ -84,42 +94,17 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
 #endif
 
 static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
-						 const struct vdso_data *vd)
+						 const struct vdso_time_data *vd)
 {
 	return get_tb();
 }
 
-const struct vdso_data *__arch_get_vdso_data(void);
-
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
-	return (void *)vd + PAGE_SIZE;
-}
-#endif
-
-static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+static inline bool vdso_clocksource_ok(const struct vdso_clock *vc)
 {
 	return true;
 }
 #define vdso_clocksource_ok vdso_clocksource_ok
 
-/*
- * powerpc specific delta calculation.
- *
- * This variant removes the masking of the subtraction because the
- * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX
- * which would result in a pointless operation. The compiler cannot
- * optimize it away as the mask comes from the vdso data and is not compile
- * time constant.
- */
-static __always_inline u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
-{
-	return (cycles - last) * mult;
-}
-#define vdso_calc_delta vdso_calc_delta
-
 #ifndef __powerpc64__
 static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift)
 {
@@ -140,21 +125,22 @@ static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift)
 
 #ifdef __powerpc64__
 int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
-			     const struct vdso_data *vd);
+			     const struct vdso_time_data *vd);
 int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
-			    const struct vdso_data *vd);
+			    const struct vdso_time_data *vd);
 #else
 int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
-			     const struct vdso_data *vd);
+			     const struct vdso_time_data *vd);
 int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
-			       const struct vdso_data *vd);
+			       const struct vdso_time_data *vd);
 int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
-			    const struct vdso_data *vd);
+			    const struct vdso_time_data *vd);
 #endif
 int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
-			    const struct vdso_data *vd);
+			    const struct vdso_time_data *vd);
 __kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time,
-				    const struct vdso_data *vd);
-#endif /* __ASSEMBLY__ */
+				    const struct vdso_time_data *vd);
+
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/powerpc/include/asm/vdso/processor.h b/arch/powerpc/include/asm/vdso/processor.h
index 80d13207c568..c1f3d7aaf3ee 100644
--- a/arch/powerpc/include/asm/vdso/processor.h
+++ b/arch/powerpc/include/asm/vdso/processor.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_POWERPC_VDSO_PROCESSOR_H
 #define _ASM_POWERPC_VDSO_PROCESSOR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /* Macros for adjusting thread priority (hardware multi-threading) */
 #ifdef CONFIG_PPC64
@@ -33,6 +33,6 @@
 #define cpu_relax()	barrier()
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_VDSO_PROCESSOR_H */
diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h
index 48cf23f1e273..bee18e8660a0 100644
--- a/arch/powerpc/include/asm/vdso/vsyscall.h
+++ b/arch/powerpc/include/asm/vdso/vsyscall.h
@@ -2,24 +2,13 @@
 #ifndef _ASM_POWERPC_VDSO_VSYSCALL_H
 #define _ASM_POWERPC_VDSO_VSYSCALL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
-#include <linux/timekeeper_internal.h>
 #include <asm/vdso_datapage.h>
 
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
-static __always_inline
-struct vdso_data *__arch_get_k_vdso_data(void)
-{
-	return vdso_data->data;
-}
-#define __arch_get_k_vdso_data __arch_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 /* !__ASSEMBLER__ */
 
 #endif /* _ASM_POWERPC_VDSO_VSYSCALL_H */
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index a585c8e538ff..441264af0e36 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -9,109 +9,21 @@
  * 		      IBM Corp.
  */
 
+#ifndef __ASSEMBLER__
 
-/*
- * Note about this structure:
- *
- * This structure was historically called systemcfg and exposed to
- * userland via /proc/ppc64/systemcfg. Unfortunately, this became an
- * ABI issue as some proprietary software started relying on being able
- * to mmap() it, thus we have to keep the base layout at least for a
- * few kernel versions.
- *
- * However, since ppc32 doesn't suffer from this backward handicap,
- * a simpler version of the data structure is used there with only the
- * fields actually used by the vDSO.
- *
- */
-
-/*
- * If the major version changes we are incompatible.
- * Minor version changes are a hint.
- */
-#define SYSTEMCFG_MAJOR 1
-#define SYSTEMCFG_MINOR 1
-
-#ifndef __ASSEMBLY__
-
-#include <linux/unistd.h>
-#include <linux/time.h>
 #include <vdso/datapage.h>
 
-#define SYSCALL_MAP_SIZE      ((NR_syscalls + 31) / 32)
-
-/*
- * So here is the ppc64 backward compatible version
- */
-
-#ifdef CONFIG_PPC64
-
-struct vdso_arch_data {
-	__u8  eye_catcher[16];		/* Eyecatcher: SYSTEMCFG:PPC64	0x00 */
-	struct {			/* Systemcfg version numbers	     */
-		__u32 major;		/* Major number			0x10 */
-		__u32 minor;		/* Minor number			0x14 */
-	} version;
-
-	/* Note about the platform flags: it now only contains the lpar
-	 * bit. The actual platform number is dead and buried
-	 */
-	__u32 platform;			/* Platform flags		0x18 */
-	__u32 processor;		/* Processor type		0x1C */
-	__u64 processorCount;		/* # of physical processors	0x20 */
-	__u64 physicalMemorySize;	/* Size of real memory(B)	0x28 */
-	__u64 tb_orig_stamp;		/* (NU) Timebase at boot	0x30 */
-	__u64 tb_ticks_per_sec;		/* Timebase tics / sec		0x38 */
-	__u64 tb_to_xs;			/* (NU) Inverse of TB to 2^20	0x40 */
-	__u64 stamp_xsec;		/* (NU)				0x48 */
-	__u64 tb_update_count;		/* (NU) Timebase atomicity ctr	0x50 */
-	__u32 tz_minuteswest;		/* (NU) Min. west of Greenwich	0x58 */
-	__u32 tz_dsttime;		/* (NU) Type of dst correction	0x5C */
-	__u32 dcache_size;		/* L1 d-cache size		0x60 */
-	__u32 dcache_line_size;		/* L1 d-cache line size		0x64 */
-	__u32 icache_size;		/* L1 i-cache size		0x68 */
-	__u32 icache_line_size;		/* L1 i-cache line size		0x6C */
-
-	/* those additional ones don't have to be located anywhere
-	 * special as they were not part of the original systemcfg
-	 */
-	__u32 dcache_block_size;		/* L1 d-cache block size     */
-	__u32 icache_block_size;		/* L1 i-cache block size     */
-	__u32 dcache_log_block_size;		/* L1 d-cache log block size */
-	__u32 icache_log_block_size;		/* L1 i-cache log block size */
-	__u32 syscall_map[SYSCALL_MAP_SIZE];	/* Map of syscalls  */
-	__u32 compat_syscall_map[SYSCALL_MAP_SIZE];	/* Map of compat syscalls */
-
-	struct vdso_data data[CS_BASES];
-};
-
-#else /* CONFIG_PPC64 */
-
-/*
- * And here is the simpler 32 bits version
- */
-struct vdso_arch_data {
-	__u64 tb_ticks_per_sec;		/* Timebase tics / sec		0x38 */
-	__u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */
-	__u32 compat_syscall_map[0];	/* No compat syscalls on PPC32 */
-	struct vdso_data data[CS_BASES];
-};
-
-#endif /* CONFIG_PPC64 */
-
-extern struct vdso_arch_data *vdso_data;
-
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
-.macro get_datapage ptr
+.macro get_datapage ptr symbol
 	bcl	20, 31, .+4
 999:
 	mflr	\ptr
-	addis	\ptr, \ptr, (_vdso_datapage - 999b)@ha
-	addi	\ptr, \ptr, (_vdso_datapage - 999b)@l
+	addis	\ptr, \ptr, (\symbol - 999b)@ha
+	addi	\ptr, \ptr, (\symbol - 999b)@l
 .endm
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __KERNEL__ */
 #endif /* _SYSTEMCFG_H */
diff --git a/arch/powerpc/include/asm/vermagic.h b/arch/powerpc/include/asm/vermagic.h
index b054a8576e5d..6f250fe506bd 100644
--- a/arch/powerpc/include/asm/vermagic.h
+++ b/arch/powerpc/include/asm/vermagic.h
@@ -2,7 +2,9 @@
 #ifndef _ASM_VERMAGIC_H
 #define _ASM_VERMAGIC_H
 
-#ifdef CONFIG_MPROFILE_KERNEL
+#ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+#define MODULE_ARCH_VERMAGIC_FTRACE	"patchable-function-entry "
+#elif defined(CONFIG_MPROFILE_KERNEL)
 #define MODULE_ARCH_VERMAGIC_FTRACE	"mprofile-kernel "
 #else
 #define MODULE_ARCH_VERMAGIC_FTRACE	""
diff --git a/arch/powerpc/include/asm/vga.h b/arch/powerpc/include/asm/vga.h
index fcf721682a71..f2dc40e1c52a 100644
--- a/arch/powerpc/include/asm/vga.h
+++ b/arch/powerpc/include/asm/vga.h
@@ -40,11 +40,6 @@ static inline void scr_memsetw(u16 *s, u16 v, unsigned int n)
 	memset16(s, cpu_to_le16(v), n / 2);
 }
 
-#define VT_BUF_HAVE_MEMCPYW
-#define VT_BUF_HAVE_MEMMOVEW
-#define scr_memcpyw	memcpy
-#define scr_memmovew	memmove
-
 #endif /* !CONFIG_VGA_CONSOLE && !CONFIG_MDA_CONSOLE */
 
 #ifdef __powerpc64__
diff --git a/arch/powerpc/include/asm/video.h b/arch/powerpc/include/asm/video.h
new file mode 100644
index 000000000000..e1770114ffc3
--- /dev/null
+++ b/arch/powerpc/include/asm/video.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_VIDEO_H_
+#define _ASM_VIDEO_H_
+
+#include <asm/page.h>
+
+static inline pgprot_t pgprot_framebuffer(pgprot_t prot,
+					  unsigned long vm_start, unsigned long vm_end,
+					  unsigned long offset)
+{
+	return __phys_mem_access_prot(PHYS_PFN(offset), vm_end - vm_start, prot);
+}
+#define pgprot_framebuffer pgprot_framebuffer
+
+#include <asm-generic/video.h>
+
+#endif /* _ASM_VIDEO_H_ */
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index cc9b787627ad..7c444150c5ad 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -39,7 +39,7 @@
  */
 #define VIO_CMO_MIN_ENT 1562624
 
-extern struct bus_type vio_bus_type;
+extern const struct bus_type vio_bus_type;
 
 struct iommu_table;
 
@@ -156,11 +156,7 @@ static inline int vio_enable_interrupts(struct vio_dev *dev)
 }
 #endif
 
-static inline struct vio_driver *to_vio_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct vio_driver, driver);
-}
-
+#define to_vio_driver(__drv)	container_of_const(__drv, struct vio_driver, driver)
 #define to_vio_dev(__dev)	container_of_const(__dev, struct vio_dev, dev)
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h
index 4c69ece52a31..59ed89890c90 100644
--- a/arch/powerpc/include/asm/vmalloc.h
+++ b/arch/powerpc/include/asm/vmalloc.h
@@ -7,14 +7,14 @@
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
 
 #define arch_vmap_pud_supported arch_vmap_pud_supported
-static inline bool arch_vmap_pud_supported(pgprot_t prot)
+static __always_inline bool arch_vmap_pud_supported(pgprot_t prot)
 {
 	/* HPT does not cope with large pages in the vmalloc area */
 	return radix_enabled();
 }
 
 #define arch_vmap_pmd_supported arch_vmap_pmd_supported
-static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+static __always_inline bool arch_vmap_pmd_supported(pgprot_t prot)
 {
 	return radix_enabled();
 }
diff --git a/arch/powerpc/include/asm/vphn.h b/arch/powerpc/include/asm/vphn.h
new file mode 100644
index 000000000000..8c2f795eea68
--- /dev/null
+++ b/arch/powerpc/include/asm/vphn.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_VPHN_H
+#define _ASM_POWERPC_VPHN_H
+
+/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. */
+#define VPHN_REGISTER_COUNT 6
+
+/*
+ * 6 64-bit registers unpacked into up to 24 be32 associativity values. To
+ * form the complete property we have to add the length in the first cell.
+ */
+#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1)
+
+/*
+ * The H_HOME_NODE_ASSOCIATIVITY hcall takes two values for flags:
+ * 1 for retrieving associativity information for a guest cpu
+ * 2 for retrieving associativity information for a host/hypervisor cpu
+ */
+#define VPHN_FLAG_VCPU	1
+#define VPHN_FLAG_PCPU	2
+
+long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity);
+
+#endif // _ASM_POWERPC_VPHN_H
diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h
index 46c31fb8748d..54653a863414 100644
--- a/arch/powerpc/include/asm/word-at-a-time.h
+++ b/arch/powerpc/include/asm/word-at-a-time.h
@@ -4,8 +4,8 @@
 /*
  * Word-at-a-time interfaces for PowerPC.
  */
-
-#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/wordpart.h>
 #include <asm/asm-compat.h>
 #include <asm/extable.h>
 
@@ -34,7 +34,7 @@ static inline long find_zero(unsigned long mask)
 	return leading_zero_bits >> 3;
 }
 
-static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
+static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
 {
 	unsigned long rhs = val | c->low_bits;
 	*data = rhs;
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 89090485bec1..60ef312dab05 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -31,7 +31,6 @@
 #ifdef CONFIG_PPC_ICP_NATIVE
 extern int icp_native_init(void);
 extern void icp_native_flush_interrupt(void);
-extern void icp_native_cause_ipi_rm(int cpu);
 #else
 static inline int icp_native_init(void) { return -ENODEV; }
 #endif
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
index 92930b0b5d0e..efb0f5effcc6 100644
--- a/arch/powerpc/include/asm/xive.h
+++ b/arch/powerpc/include/asm/xive.h
@@ -111,7 +111,6 @@ void xive_native_free_vp_block(u32 vp_base);
 int xive_native_populate_irq_data(u32 hw_irq,
 				  struct xive_irq_data *data);
 void xive_cleanup_irq_data(struct xive_irq_data *xd);
-void xive_irq_free_data(unsigned int virq);
 void xive_native_free_irq(u32 irq);
 int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq);
 
diff --git a/arch/powerpc/include/asm/xmon.h b/arch/powerpc/include/asm/xmon.h
index f2d44b44f46c..535cdb1e411a 100644
--- a/arch/powerpc/include/asm/xmon.h
+++ b/arch/powerpc/include/asm/xmon.h
@@ -12,13 +12,11 @@
 
 #ifdef CONFIG_XMON
 extern void xmon_setup(void);
-void __init xmon_register_spus(struct list_head *list);
 struct pt_regs;
 extern int xmon(struct pt_regs *excp);
 extern irqreturn_t xmon_irq(int, void *);
 #else
 static inline void xmon_setup(void) { }
-static inline void xmon_register_spus(struct list_head *list) { }
 #endif
 
 #if defined(CONFIG_XMON) && defined(CONFIG_SMP)
diff --git a/arch/powerpc/include/uapi/asm/bootx.h b/arch/powerpc/include/uapi/asm/bootx.h
index 6728c7e24e58..1b8c121071d9 100644
--- a/arch/powerpc/include/uapi/asm/bootx.h
+++ b/arch/powerpc/include/uapi/asm/bootx.h
@@ -108,7 +108,7 @@ typedef struct boot_infos
     /* ALL BELOW NEW (vers. 4) */
 
     /* This defines the physical memory. Valid with BOOT_ARCH_NUBUS flag
-       (non-PCI) only. On PCI, memory is contiguous and it's size is in the
+       (non-PCI) only. On PCI, memory is contiguous and its size is in the
        device-tree. */
     boot_info_map_entry_t
     	        physMemoryMap[MAX_MEM_MAP_SIZE]; /* Where the phys memory is */
diff --git a/arch/powerpc/include/uapi/asm/eeh.h b/arch/powerpc/include/uapi/asm/eeh.h
index 28186071fafc..3b5c47ff3fc4 100644
--- a/arch/powerpc/include/uapi/asm/eeh.h
+++ b/arch/powerpc/include/uapi/asm/eeh.h
@@ -1,18 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- *
  * Copyright IBM Corp. 2015
  *
  * Authors: Gavin Shan <gwshan@linux.vnet.ibm.com>
diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h
index dbc4a5b8d02d..a5377f494fa3 100644
--- a/arch/powerpc/include/uapi/asm/elf.h
+++ b/arch/powerpc/include/uapi/asm/elf.h
@@ -98,6 +98,8 @@
 #define ELF_NEBB	3	/* includes ebbrr, ebbhr, bescr */
 #define ELF_NPMU	5	/* includes siar, sdar, sier, mmcr2, mmcr0 */
 #define ELF_NPKEY	3	/* includes amr, iamr, uamor */
+#define ELF_NDEXCR	2	/* includes dexcr, hdexcr */
+#define ELF_NHASHKEYR	1	/* includes hashkeyr */
 
 typedef unsigned long elf_greg_t64;
 typedef elf_greg_t64 elf_gregset_t64[ELF_NGREG];
diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h
index 2c145da3b774..b5211e413829 100644
--- a/arch/powerpc/include/uapi/asm/ioctls.h
+++ b/arch/powerpc/include/uapi/asm/ioctls.h
@@ -23,10 +23,10 @@
 #define TCSETSW		_IOW('t', 21, struct termios)
 #define TCSETSF		_IOW('t', 22, struct termios)
 
-#define TCGETA		_IOR('t', 23, struct termio)
-#define TCSETA		_IOW('t', 24, struct termio)
-#define TCSETAW		_IOW('t', 25, struct termio)
-#define TCSETAF		_IOW('t', 28, struct termio)
+#define TCGETA		0x40147417 /* _IOR('t', 23, struct termio) */
+#define TCSETA		0x80147418 /* _IOW('t', 24, struct termio) */
+#define TCSETAW		0x80147419 /* _IOW('t', 25, struct termio) */
+#define TCSETAF		0x8014741c /* _IOW('t', 28, struct termio) */
 
 #define TCSBRK		_IO('t', 29)
 #define TCXONC		_IO('t', 30)
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 9f18fa090f1f..077c5437f521 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -1,18 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- *
  * Copyright IBM Corp. 2007
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>
@@ -28,7 +15,6 @@
 #define __KVM_HAVE_PPC_SMT
 #define __KVM_HAVE_IRQCHIP
 #define __KVM_HAVE_IRQ_LINE
-#define __KVM_HAVE_GUEST_DEBUG
 
 /* Not always available, but if it is, this is the correct offset.  */
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -646,6 +632,9 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_SIER3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3)
 #define KVM_REG_PPC_DAWR1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4)
 #define KVM_REG_PPC_DAWRX1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5)
+#define KVM_REG_PPC_DEXCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc6)
+#define KVM_REG_PPC_HASHKEYR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc7)
+#define KVM_REG_PPC_HASHPKEYR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc8)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
@@ -733,4 +722,48 @@ struct kvm_ppc_xive_eq {
 #define KVM_XIVE_TIMA_PAGE_OFFSET	0
 #define KVM_XIVE_ESB_PAGE_OFFSET	4
 
+/* for KVM_PPC_GET_PVINFO */
+
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
+
+struct kvm_ppc_pvinfo {
+	/* out */
+	__u32 flags;
+	__u32 hcall[4];
+	__u8  pad[108];
+};
+
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ	8
+
+struct kvm_ppc_one_page_size {
+	__u32 page_shift;	/* Page shift (or 0) */
+	__u32 pte_enc;		/* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+	__u32 page_shift;	/* Base page shift of segment (or 0) */
+	__u32 slb_enc;		/* SLB encoding for BookS */
+	struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL		0x00000001
+#define KVM_PPC_1T_SEGMENTS		0x00000002
+#define KVM_PPC_NO_HASH			0x00000004
+
+struct kvm_ppc_smmu_info {
+	__u64 flags;
+	__u32 slb_size;
+	__u16 data_keys;	/* # storage keys supported for data */
+	__u16 instr_keys;	/* # storage keys supported for instructions */
+	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
+struct kvm_ppc_resize_hpt {
+	__u64 flags;
+	__u32 shift;
+	__u32 pad;
+};
+
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/include/uapi/asm/kvm_para.h b/arch/powerpc/include/uapi/asm/kvm_para.h
index a809b1b44ddf..ac596064d4c7 100644
--- a/arch/powerpc/include/uapi/asm/kvm_para.h
+++ b/arch/powerpc/include/uapi/asm/kvm_para.h
@@ -1,18 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- *
  * Copyright IBM Corp. 2008
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>
diff --git a/arch/powerpc/include/uapi/asm/opal-prd.h b/arch/powerpc/include/uapi/asm/opal-prd.h
index 1869cf83a870..11abcf0192ca 100644
--- a/arch/powerpc/include/uapi/asm/opal-prd.h
+++ b/arch/powerpc/include/uapi/asm/opal-prd.h
@@ -40,7 +40,7 @@
 #define OPAL_PRD_SCOM_READ		_IOR('o', 0x02, struct opal_prd_scom)
 #define OPAL_PRD_SCOM_WRITE		_IOW('o', 0x03, struct opal_prd_scom)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct opal_prd_info {
 	__u64	version;
@@ -54,6 +54,6 @@ struct opal_prd_scom {
 	__s64	rc;
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_POWERPC_OPAL_PRD_H */
diff --git a/arch/powerpc/include/uapi/asm/papr-hvpipe.h b/arch/powerpc/include/uapi/asm/papr-hvpipe.h
new file mode 100644
index 000000000000..f8794139d06a
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-hvpipe.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_HVPIPE_H_
+#define _UAPI_PAPR_HVPIPE_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+/*
+ * This header is included in payload between OS and the user
+ * space.
+ * flags: OS notifies the user space whether the hvpipe is
+ *        closed or the buffer has the payload.
+ */
+struct papr_hvpipe_hdr {
+	__u8 version;
+	__u8 reserved[3];
+	__u32 flags;
+	__u8 reserved2[40];
+};
+
+/*
+ * ioctl for /dev/papr-hvpipe
+ */
+#define PAPR_HVPIPE_IOC_CREATE_HANDLE	_IOW(PAPR_MISCDEV_IOC_ID, 9, __u32)
+
+/*
+ * hvpipe_hdr flags used for read()
+ */
+#define HVPIPE_MSG_AVAILABLE	0x01 /* Payload is available */
+#define HVPIPE_LOST_CONNECTION	0x02 /* Pipe connection is closed/unavailable */
+
+#endif /* _UAPI_PAPR_HVPIPE_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-indices.h b/arch/powerpc/include/uapi/asm/papr-indices.h
new file mode 100644
index 000000000000..c2999d89d52a
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-indices.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_INDICES_H_
+#define _UAPI_PAPR_INDICES_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+#define LOC_CODE_SIZE			80
+#define RTAS_GET_INDICES_BUF_SIZE	SZ_4K
+
+struct papr_indices_io_block {
+	union {
+		struct {
+			__u8 is_sensor; /* 0 for indicator and 1 for sensor */
+			__u32 indice_type;
+		} indices;
+		struct {
+			__u32 token; /* Sensor or indicator token */
+			__u32 state; /* get / set state */
+			/*
+			 * PAPR+ 12.3.2.4 Converged Location Code Rules - Length
+			 * Restrictions. 79 characters plus null.
+			 */
+			char location_code_str[LOC_CODE_SIZE]; /* location code */
+		} dynamic_param;
+	};
+};
+
+/*
+ * ioctls for /dev/papr-indices.
+ * PAPR_INDICES_IOC_GET: Returns a get-indices handle fd to read data
+ * PAPR_DYNAMIC_SENSOR_IOC_GET: Gets the state of the input sensor
+ * PAPR_DYNAMIC_INDICATOR_IOC_SET: Sets the new state for the input indicator
+ */
+#define PAPR_INDICES_IOC_GET		_IOW(PAPR_MISCDEV_IOC_ID, 3, struct papr_indices_io_block)
+#define PAPR_DYNAMIC_SENSOR_IOC_GET	_IOWR(PAPR_MISCDEV_IOC_ID, 4, struct papr_indices_io_block)
+#define PAPR_DYNAMIC_INDICATOR_IOC_SET	_IOW(PAPR_MISCDEV_IOC_ID, 5, struct papr_indices_io_block)
+
+
+#endif /* _UAPI_PAPR_INDICES_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-miscdev.h b/arch/powerpc/include/uapi/asm/papr-miscdev.h
new file mode 100644
index 000000000000..49a2a270b7f3
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-miscdev.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_MISCDEV_H_
+#define _UAPI_PAPR_MISCDEV_H_
+
+enum {
+	PAPR_MISCDEV_IOC_ID = 0xb2,
+};
+
+#endif /* _UAPI_PAPR_MISCDEV_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-physical-attestation.h b/arch/powerpc/include/uapi/asm/papr-physical-attestation.h
new file mode 100644
index 000000000000..ea746837bb9a
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-physical-attestation.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_PHYSICAL_ATTESTATION_H_
+#define _UAPI_PAPR_PHYSICAL_ATTESTATION_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+#define PAPR_PHYATTEST_MAX_INPUT 4084 /* Max 4K buffer: 4K-12 */
+
+/*
+ * Defined in PAPR 2.13+ 21.6 Attestation Command Structures.
+ * User space pass this struct and the max size should be 4K.
+ */
+struct papr_phy_attest_io_block {
+	__u8 version;
+	__u8 command;
+	__u8 TCG_major_ver;
+	__u8 TCG_minor_ver;
+	__be32 length;
+	__be32 correlator;
+	__u8 payload[PAPR_PHYATTEST_MAX_INPUT];
+};
+
+/*
+ * ioctl for /dev/papr-physical-attestation. Returns a attestation
+ * command fd handle
+ */
+#define PAPR_PHY_ATTEST_IOC_HANDLE _IOW(PAPR_MISCDEV_IOC_ID, 8, struct papr_phy_attest_io_block)
+
+#endif /* _UAPI_PAPR_PHYSICAL_ATTESTATION_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-platform-dump.h b/arch/powerpc/include/uapi/asm/papr-platform-dump.h
new file mode 100644
index 000000000000..8a1c060e89a9
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-platform-dump.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_PLATFORM_DUMP_H_
+#define _UAPI_PAPR_PLATFORM_DUMP_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+/*
+ * ioctl for /dev/papr-platform-dump. Returns a platform-dump handle fd
+ * corresponding to dump tag.
+ */
+#define PAPR_PLATFORM_DUMP_IOC_CREATE_HANDLE _IOW(PAPR_MISCDEV_IOC_ID, 6, __u64)
+#define PAPR_PLATFORM_DUMP_IOC_INVALIDATE    _IOW(PAPR_MISCDEV_IOC_ID, 7, __u64)
+
+#endif /* _UAPI_PAPR_PLATFORM_DUMP_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-sysparm.h b/arch/powerpc/include/uapi/asm/papr-sysparm.h
new file mode 100644
index 000000000000..f733467b1534
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-sysparm.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_SYSPARM_H_
+#define _UAPI_PAPR_SYSPARM_H_
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+enum {
+	PAPR_SYSPARM_MAX_INPUT  = 1024,
+	PAPR_SYSPARM_MAX_OUTPUT = 4000,
+};
+
+struct papr_sysparm_io_block {
+	__u32 parameter;
+	__u16 length;
+	__u8 data[PAPR_SYSPARM_MAX_OUTPUT];
+};
+
+/**
+ * PAPR_SYSPARM_IOC_GET - Retrieve the value of a PAPR system parameter.
+ *
+ * Uses _IOWR because of one corner case: Retrieving the value of the
+ * "OS Service Entitlement Status" parameter (60) requires the caller
+ * to supply input data (a date string) in the buffer passed to
+ * firmware. So the @length and @data of the incoming
+ * papr_sysparm_io_block are always used to initialize the work area
+ * supplied to ibm,get-system-parameter. No other parameters are known
+ * to parameterize the result this way, and callers are encouraged
+ * (but not required) to zero-initialize @length and @data in the
+ * common case.
+ *
+ * On error the contents of the ioblock are indeterminate.
+ *
+ * Return:
+ * 0: Success; @length is the length of valid data in @data, not to exceed @PAPR_SYSPARM_MAX_OUTPUT.
+ * -EIO: Platform error. (-1)
+ * -EINVAL: Incorrect data length or format. (-9999)
+ * -EPERM: The calling partition is not allowed to access this parameter. (-9002)
+ * -EOPNOTSUPP: Parameter not supported on this platform (-3)
+ */
+#define PAPR_SYSPARM_IOC_GET _IOWR(PAPR_MISCDEV_IOC_ID, 1, struct papr_sysparm_io_block)
+
+/**
+ * PAPR_SYSPARM_IOC_SET - Update the value of a PAPR system parameter.
+ *
+ * The contents of the ioblock are unchanged regardless of success.
+ *
+ * Return:
+ * 0: Success; the parameter has been updated.
+ * -EIO: Platform error. (-1)
+ * -EINVAL: Incorrect data length or format. (-9999)
+ * -EPERM: The calling partition is not allowed to access this parameter. (-9002)
+ * -EOPNOTSUPP: Parameter not supported on this platform (-3)
+ */
+#define PAPR_SYSPARM_IOC_SET _IOW(PAPR_MISCDEV_IOC_ID, 2, struct papr_sysparm_io_block)
+
+#endif /* _UAPI_PAPR_SYSPARM_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr-vpd.h b/arch/powerpc/include/uapi/asm/papr-vpd.h
new file mode 100644
index 000000000000..1c88e87cb420
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/papr-vpd.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_PAPR_VPD_H_
+#define _UAPI_PAPR_VPD_H_
+
+#include <asm/ioctl.h>
+#include <asm/papr-miscdev.h>
+
+struct papr_location_code {
+	/*
+	 * PAPR+ v2.13 12.3.2.4 Converged Location Code Rules - Length
+	 * Restrictions. 79 characters plus nul.
+	 */
+	char str[80];
+};
+
+/*
+ * ioctl for /dev/papr-vpd. Returns a VPD handle fd corresponding to
+ * the location code.
+ */
+#define PAPR_VPD_IOC_CREATE_HANDLE _IOW(PAPR_MISCDEV_IOC_ID, 0, struct papr_location_code)
+
+#endif /* _UAPI_PAPR_VPD_H_ */
diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h
deleted file mode 100644
index 17439925045c..000000000000
--- a/arch/powerpc/include/uapi/asm/papr_pdsm.h
+++ /dev/null
@@ -1,165 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * PAPR nvDimm Specific Methods (PDSM) and structs for libndctl
- *
- * (C) Copyright IBM 2020
- *
- * Author: Vaibhav Jain <vaibhav at linux.ibm.com>
- */
-
-#ifndef _UAPI_ASM_POWERPC_PAPR_PDSM_H_
-#define _UAPI_ASM_POWERPC_PAPR_PDSM_H_
-
-#include <linux/types.h>
-#include <linux/ndctl.h>
-
-/*
- * PDSM Envelope:
- *
- * The ioctl ND_CMD_CALL exchange data between user-space and kernel via
- * envelope which consists of 2 headers sections and payload sections as
- * illustrated below:
- *  +-----------------+---------------+---------------------------+
- *  |   64-Bytes      |   8-Bytes     |       Max 184-Bytes       |
- *  +-----------------+---------------+---------------------------+
- *  | ND-HEADER       |  PDSM-HEADER  |      PDSM-PAYLOAD         |
- *  +-----------------+---------------+---------------------------+
- *  | nd_family       |               |                           |
- *  | nd_size_out     | cmd_status    |                           |
- *  | nd_size_in      | reserved      |     nd_pdsm_payload       |
- *  | nd_command      | payload   --> |                           |
- *  | nd_fw_size      |               |                           |
- *  | nd_payload ---> |               |                           |
- *  +---------------+-----------------+---------------------------+
- *
- * ND Header:
- * This is the generic libnvdimm header described as 'struct nd_cmd_pkg'
- * which is interpreted by libnvdimm before passed on to papr_scm. Important
- * member fields used are:
- * 'nd_family'		: (In) NVDIMM_FAMILY_PAPR_SCM
- * 'nd_size_in'		: (In) PDSM-HEADER + PDSM-IN-PAYLOAD (usually 0)
- * 'nd_size_out'        : (In) PDSM-HEADER + PDSM-RETURN-PAYLOAD
- * 'nd_command'         : (In) One of PAPR_PDSM_XXX
- * 'nd_fw_size'         : (Out) PDSM-HEADER + size of actual payload returned
- *
- * PDSM Header:
- * This is papr-scm specific header that precedes the payload. This is defined
- * as nd_cmd_pdsm_pkg.  Following fields aare available in this header:
- *
- * 'cmd_status'		: (Out) Errors if any encountered while servicing PDSM.
- * 'reserved'		: Not used, reserved for future and should be set to 0.
- * 'payload'            : A union of all the possible payload structs
- *
- * PDSM Payload:
- *
- * The layout of the PDSM Payload is defined by various structs shared between
- * papr_scm and libndctl so that contents of payload can be interpreted. As such
- * its defined as a union of all possible payload structs as
- * 'union nd_pdsm_payload'. Based on the value of 'nd_cmd_pkg.nd_command'
- * appropriate member of the union is accessed.
- */
-
-/* Max payload size that we can handle */
-#define ND_PDSM_PAYLOAD_MAX_SIZE 184
-
-/* Max payload size that we can handle */
-#define ND_PDSM_HDR_SIZE \
-	(sizeof(struct nd_pkg_pdsm) - ND_PDSM_PAYLOAD_MAX_SIZE)
-
-/* Various nvdimm health indicators */
-#define PAPR_PDSM_DIMM_HEALTHY       0
-#define PAPR_PDSM_DIMM_UNHEALTHY     1
-#define PAPR_PDSM_DIMM_CRITICAL      2
-#define PAPR_PDSM_DIMM_FATAL         3
-
-/* struct nd_papr_pdsm_health.extension_flags field flags */
-
-/* Indicate that the 'dimm_fuel_gauge' field is valid */
-#define PDSM_DIMM_HEALTH_RUN_GAUGE_VALID 1
-
-/* Indicate that the 'dimm_dsc' field is valid */
-#define PDSM_DIMM_DSC_VALID 2
-
-/*
- * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH
- * Various flags indicate the health status of the dimm.
- *
- * extension_flags	: Any extension fields present in the struct.
- * dimm_unarmed		: Dimm not armed. So contents wont persist.
- * dimm_bad_shutdown	: Previous shutdown did not persist contents.
- * dimm_bad_restore	: Contents from previous shutdown werent restored.
- * dimm_scrubbed	: Contents of the dimm have been scrubbed.
- * dimm_locked		: Contents of the dimm cant be modified until CEC reboot
- * dimm_encrypted	: Contents of dimm are encrypted.
- * dimm_health		: Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX
- * dimm_fuel_gauge	: Life remaining of DIMM as a percentage from 0-100
- */
-struct nd_papr_pdsm_health {
-	union {
-		struct {
-			__u32 extension_flags;
-			__u8 dimm_unarmed;
-			__u8 dimm_bad_shutdown;
-			__u8 dimm_bad_restore;
-			__u8 dimm_scrubbed;
-			__u8 dimm_locked;
-			__u8 dimm_encrypted;
-			__u16 dimm_health;
-
-			/* Extension flag PDSM_DIMM_HEALTH_RUN_GAUGE_VALID */
-			__u16 dimm_fuel_gauge;
-
-			/* Extension flag PDSM_DIMM_DSC_VALID */
-			__u64 dimm_dsc;
-		};
-		__u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
-	};
-};
-
-/* Flags for injecting specific smart errors */
-#define PDSM_SMART_INJECT_HEALTH_FATAL		(1 << 0)
-#define PDSM_SMART_INJECT_BAD_SHUTDOWN		(1 << 1)
-
-struct nd_papr_pdsm_smart_inject {
-	union {
-		struct {
-			/* One or more of PDSM_SMART_INJECT_ */
-			__u32 flags;
-			__u8 fatal_enable;
-			__u8 unsafe_shutdown_enable;
-		};
-		__u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
-	};
-};
-
-/*
- * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel
- * via 'nd_cmd_pkg.nd_command' member of the ioctl struct
- */
-enum papr_pdsm {
-	PAPR_PDSM_MIN = 0x0,
-	PAPR_PDSM_HEALTH,
-	PAPR_PDSM_SMART_INJECT,
-	PAPR_PDSM_MAX,
-};
-
-/* Maximal union that can hold all possible payload types */
-union nd_pdsm_payload {
-	struct nd_papr_pdsm_health health;
-	struct nd_papr_pdsm_smart_inject smart_inject;
-	__u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE];
-} __packed;
-
-/*
- * PDSM-header + payload expected with ND_CMD_CALL ioctl from libnvdimm
- * Valid member of union 'payload' is identified via 'nd_cmd_pkg.nd_command'
- * that should always precede this struct when sent to papr_scm via CMD_CALL
- * interface.
- */
-struct nd_pkg_pdsm {
-	__s32 cmd_status;	/* Out: Sub-cmd status returned back */
-	__u16 reserved[2];	/* Ignored and to be set as '0' */
-	union nd_pdsm_payload payload;
-} __packed;
-
-#endif /* _UAPI_ASM_POWERPC_PAPR_PDSM_H_ */
diff --git a/arch/powerpc/include/uapi/asm/ps3fb.h b/arch/powerpc/include/uapi/asm/ps3fb.h
index fd7e3a0d35d5..b1c6b0cd9e80 100644
--- a/arch/powerpc/include/uapi/asm/ps3fb.h
+++ b/arch/powerpc/include/uapi/asm/ps3fb.h
@@ -2,19 +2,6 @@
 /*
  * Copyright (C) 2006 Sony Computer Entertainment Inc.
  * Copyright 2006, 2007 Sony Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published
- * by the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef _ASM_POWERPC_PS3FB_H_
diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h
index 7004cfea3f5f..01e630149d48 100644
--- a/arch/powerpc/include/uapi/asm/ptrace.h
+++ b/arch/powerpc/include/uapi/asm/ptrace.h
@@ -27,7 +27,7 @@
 
 #include <linux/types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef __KERNEL__
 struct user_pt_regs
@@ -57,7 +57,7 @@ struct pt_regs
 	unsigned long result;		/* Result of a system call */
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 
 /*
@@ -200,7 +200,7 @@ struct pt_regs
 #define PPC_PTRACE_SETHWDEBUG	0x88
 #define PPC_PTRACE_DELHWDEBUG	0x87
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct ppc_debug_info {
 	__u32 version;			/* Only version 1 exists to date */
@@ -212,7 +212,7 @@ struct ppc_debug_info {
 	__u64 features;
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * features will have bits indication whether there is support for:
@@ -224,7 +224,7 @@ struct ppc_debug_info {
 #define PPC_DEBUG_FEATURE_DATA_BP_DAWR		0x0000000000000010
 #define PPC_DEBUG_FEATURE_DATA_BP_ARCH_31	0x0000000000000020
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct ppc_hw_breakpoint {
 	__u32 version;		/* currently, version must be 1 */
@@ -236,7 +236,7 @@ struct ppc_hw_breakpoint {
 	__u64 condition_value;	/* contents of the DVC register */
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * Trigger Type
diff --git a/arch/powerpc/include/uapi/asm/types.h b/arch/powerpc/include/uapi/asm/types.h
index 327616fb70e4..9dbf55e38ea5 100644
--- a/arch/powerpc/include/uapi/asm/types.h
+++ b/arch/powerpc/include/uapi/asm/types.h
@@ -28,14 +28,14 @@
 # include <asm-generic/int-ll64.h>
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 
 typedef struct {
 	__u32 u[4];
 } __attribute__((aligned(16))) __vector128;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 
 #endif /* _UAPI_ASM_POWERPC_TYPES_H */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 9bf2be123093..2f0a2e69c607 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -3,9 +3,6 @@
 # Makefile for the linux kernel.
 #
 
-ifdef CONFIG_PPC64
-CFLAGS_prom_init.o	+= $(NO_MINIMAL_TOC)
-endif
 ifdef CONFIG_PPC32
 CFLAGS_prom_init.o      += -fPIC
 CFLAGS_btext.o		+= -fPIC
@@ -55,7 +52,6 @@ CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
 endif
 
 KCSAN_SANITIZE_early_32.o := n
-KCSAN_SANITIZE_early_64.o := n
 KCSAN_SANITIZE_cputable.o := n
 KCSAN_SANITIZE_btext.o := n
 KCSAN_SANITIZE_paca.o := n
@@ -68,13 +64,13 @@ CFLAGS_REMOVE_syscall.o = -fstack-protector -fstack-protector-strong
 CFLAGS_syscall.o += -fno-stack-protector
 #endif
 
-obj-y				:= cputable.o syscalls.o \
+obj-y				:= cputable.o syscalls.o switch.o \
 				   irq.o align.o signal_$(BITS).o pmc.o vdso.o \
 				   process.o systbl.o idle.o \
 				   signal.o sysfs.o cacheinfo.o time.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o misc_$(BITS).o \
-				   of_platform.o prom_parse.o firmware.o \
+				   prom_parse.o firmware.o \
 				   hw_breakpoint_constraints.o interrupt.o \
 				   kdebugfs.o stacktrace.o syscall.o
 obj-y				+= ptrace/
@@ -88,6 +84,7 @@ obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_DAWR)		+= dawr.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= dexcr.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_64e.o
 obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
@@ -126,11 +123,10 @@ obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 
 obj-$(CONFIG_PPC64)		+= head_64.o
 obj-$(CONFIG_PPC_BOOK3S_32)	+= head_book3s_32.o
-obj-$(CONFIG_40x)		+= head_40x.o
 obj-$(CONFIG_44x)		+= head_44x.o
 obj-$(CONFIG_PPC_8xx)		+= head_8xx.o
 obj-$(CONFIG_PPC_85xx)		+= head_85xx.o
-extra-y				+= vmlinux.lds
+always-$(KBUILD_BUILTIN)	+= vmlinux.lds
 
 obj-$(CONFIG_RELOCATABLE)	+= reloc_$(BITS).o
 
@@ -143,6 +139,7 @@ obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_OPTPROBES)		+= optprobes.o optprobes_head.o
 obj-$(CONFIG_KPROBES_ON_FTRACE)	+= kprobes-ftrace.o
 obj-$(CONFIG_UPROBES)		+= uprobes.o
+obj-$(CONFIG_RETHOOK)           += rethook.o
 obj-$(CONFIG_PPC_UDBG_16550)	+= legacy_serial.o udbg_16550.o
 obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 obj-$(CONFIG_ARCH_HAS_DMA_SET_MASK) += dma-mask.o
@@ -155,8 +152,6 @@ obj-$(CONFIG_PCI_MSI)		+= msi.o
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
-obj-$(CONFIG_PPC_IO_WORKAROUNDS)	+= io-workarounds.o
-
 obj-y				+= trace/
 
 ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
@@ -165,12 +160,7 @@ endif
 
 obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM)	+= tm.o
 
-obj-$(CONFIG_PPC64)		+= $(obj64-y)
-obj-$(CONFIG_PPC32)		+= $(obj32-y)
-
-ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE)(CONFIG_PPC_BOOK3S),)
 obj-y				+= ppc_save_regs.o
-endif
 
 obj-$(CONFIG_EPAPR_PARAVIRT)	+= epapr_paravirt.o epapr_hcalls.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvm_emul.o
@@ -194,9 +184,6 @@ GCOV_PROFILE_kprobes-ftrace.o := n
 KCOV_INSTRUMENT_kprobes-ftrace.o := n
 KCSAN_SANITIZE_kprobes-ftrace.o := n
 UBSAN_SANITIZE_kprobes-ftrace.o := n
-GCOV_PROFILE_syscall_64.o := n
-KCOV_INSTRUMENT_syscall_64.o := n
-UBSAN_SANITIZE_syscall_64.o := n
 UBSAN_SANITIZE_vdso.o := n
 
 # Necessary for booting with kcov enabled on book3e machines
@@ -209,10 +196,15 @@ CFLAGS_paca.o			+= -fno-stack-protector
 
 obj-$(CONFIG_PPC_FPU)		+= fpu.o
 obj-$(CONFIG_ALTIVEC)		+= vector.o
-obj-$(CONFIG_PPC64)		+= entry_64.o
-obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE)	+= prom_init.o
 
-extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE)	+= prom_init_check
+obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o
+obj64-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_entry_64.o
+ifdef KBUILD_BUILTIN
+always-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check
+endif
+
+obj-$(CONFIG_PPC64)		+= $(obj64-y)
+obj-$(CONFIG_PPC32)		+= $(obj32-y)
 
 quiet_cmd_prom_init_check = PROMCHK $@
       cmd_prom_init_check = $(CONFIG_SHELL) $< "$(NM)" $(obj)/prom_init.o; touch $@
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 9f14d95b8b32..a4bc80b30410 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -8,6 +8,7 @@
  * compile this file to assembler, and then extract the
  * #defines from the assembly-language output.
  */
+#define COMPILE_OFFSETS
 
 #include <linux/compat.h>
 #include <linux/signal.h>
@@ -54,7 +55,7 @@
 #endif
 
 #ifdef CONFIG_PPC32
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 #include "head_booke.h"
 #endif
 #endif
@@ -246,9 +247,7 @@ int main(void)
 	OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
 	OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);
 	OFFSET(PACA_DSCR_DEFAULT, paca_struct, dscr_default);
-#ifdef CONFIG_PPC64
 	OFFSET(PACA_EXIT_SAVE_R1, paca_struct, exit_save_r1);
-#endif
 #ifdef CONFIG_PPC_BOOK3E_64
 	OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save);
 #endif
@@ -336,7 +335,6 @@ int main(void)
 #endif /* ! CONFIG_PPC64 */
 
 	/* datapage offsets for use by vdso */
-	OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data);
 	OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec);
 #ifdef CONFIG_PPC64
 	OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size);
@@ -596,7 +594,6 @@ int main(void)
 	HSTATE_FIELD(HSTATE_DABR, dabr);
 	HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
 	HSTATE_FIELD(HSTATE_SPLIT_MODE, kvm_split_mode);
-	DEFINE(IPI_PRIORITY, IPI_PRIORITY);
 	OFFSET(KVM_SPLIT_RPR, kvm_split_mode, rpr);
 	OFFSET(KVM_SPLIT_PMMAR, kvm_split_mode, pmmar);
 	OFFSET(KVM_SPLIT_LDBAR, kvm_split_mode, ldbar);
@@ -676,5 +673,16 @@ int main(void)
 	DEFINE(BPT_SIZE, BPT_SIZE);
 #endif
 
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	DEFINE(FTRACE_OOL_STUB_SIZE, sizeof(struct ftrace_ool_stub));
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	OFFSET(FTRACE_OPS_FUNC, ftrace_ops, func);
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	OFFSET(FTRACE_OPS_DIRECT_CALL, ftrace_ops, direct_call);
+#endif
+#endif
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/audit.c b/arch/powerpc/kernel/audit.c
index 1bcfca5fdf67..92298d6a3a37 100644
--- a/arch/powerpc/kernel/audit.c
+++ b/arch/powerpc/kernel/audit.c
@@ -4,6 +4,8 @@
 #include <linux/audit.h>
 #include <asm/unistd.h>
 
+#include "audit_32.h"
+
 static unsigned dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
 ~0U
@@ -41,7 +43,6 @@ int audit_classify_arch(int arch)
 int audit_classify_syscall(int abi, unsigned syscall)
 {
 #ifdef CONFIG_PPC64
-	extern int ppc32_classify_syscall(unsigned);
 	if (abi == AUDIT_ARCH_PPC)
 		return ppc32_classify_syscall(syscall);
 #endif
diff --git a/arch/powerpc/kernel/audit_32.h b/arch/powerpc/kernel/audit_32.h
new file mode 100644
index 000000000000..c6c79c3041ab
--- /dev/null
+++ b/arch/powerpc/kernel/audit_32.h
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __AUDIT_32_H__
+#define __AUDIT_32_H__
+
+extern int ppc32_classify_syscall(unsigned);
+
+#endif
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 19e46fd623b0..7f63f1cdc6c3 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -8,6 +8,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/export.h>
+#include <linux/font.h>
 #include <linux/memblock.h>
 #include <linux/pgtable.h>
 #include <linux/of.h>
@@ -41,10 +42,6 @@ static unsigned char *logicalDisplayBase __force_data;
 
 unsigned long disp_BAT[2] __initdata = {0, 0};
 
-#define cmapsz	(16*256)
-
-static unsigned char vga_font[cmapsz];
-
 static int boot_text_mapped __force_data;
 
 extern void rmci_on(void);
@@ -407,7 +404,7 @@ static unsigned int expand_bits_16[4] = {
 };
 
 
-static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
+static void draw_byte_32(const unsigned char *font, unsigned int *base, int rb)
 {
 	int l, bits;
 	int fg = 0xFFFFFFFFUL;
@@ -428,7 +425,7 @@ static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
 	}
 }
 
-static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
+static inline void draw_byte_16(const unsigned char *font, unsigned int *base, int rb)
 {
 	int l, bits;
 	int fg = 0xFFFFFFFFUL;
@@ -446,7 +443,7 @@ static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
 	}
 }
 
-static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
+static inline void draw_byte_8(const unsigned char *font, unsigned int *base, int rb)
 {
 	int l, bits;
 	int fg = 0x0F0F0F0FUL;
@@ -465,7 +462,8 @@ static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
 static noinline void draw_byte(unsigned char c, long locX, long locY)
 {
 	unsigned char *base	= calc_base(locX << 3, locY << 4);
-	unsigned char *font	= &vga_font[((unsigned int)c) * 16];
+	unsigned int font_index = c * 16;
+	const unsigned char *font	= font_sun_8x16.data + font_index;
 	int rb			= dispDeviceRowBytes;
 
 	rmci_maybe_on();
@@ -583,349 +581,3 @@ void __init udbg_init_btext(void)
 	 */
 	udbg_putc = btext_drawchar;
 }
-
-static unsigned char vga_font[cmapsz] = {
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x81, 0xa5, 0x81, 0x81, 0xbd,
-0x99, 0x81, 0x81, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xff,
-0xdb, 0xff, 0xff, 0xc3, 0xe7, 0xff, 0xff, 0x7e, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x6c, 0xfe, 0xfe, 0xfe, 0xfe, 0x7c, 0x38, 0x10,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x7c, 0xfe,
-0x7c, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18,
-0x3c, 0x3c, 0xe7, 0xe7, 0xe7, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x18, 0x3c, 0x7e, 0xff, 0xff, 0x7e, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c,
-0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
-0xff, 0xff, 0xe7, 0xc3, 0xc3, 0xe7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x42, 0x42, 0x66, 0x3c, 0x00,
-0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc3, 0x99, 0xbd,
-0xbd, 0x99, 0xc3, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x1e, 0x0e,
-0x1a, 0x32, 0x78, 0xcc, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x3c, 0x66, 0x66, 0x66, 0x66, 0x3c, 0x18, 0x7e, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x33, 0x3f, 0x30, 0x30, 0x30,
-0x30, 0x70, 0xf0, 0xe0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0x63,
-0x7f, 0x63, 0x63, 0x63, 0x63, 0x67, 0xe7, 0xe6, 0xc0, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x18, 0x18, 0xdb, 0x3c, 0xe7, 0x3c, 0xdb, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0xc0, 0xe0, 0xf0, 0xf8, 0xfe, 0xf8,
-0xf0, 0xe0, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x06, 0x0e,
-0x1e, 0x3e, 0xfe, 0x3e, 0x1e, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66,
-0x66, 0x00, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xdb,
-0xdb, 0xdb, 0x7b, 0x1b, 0x1b, 0x1b, 0x1b, 0x1b, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x7c, 0xc6, 0x60, 0x38, 0x6c, 0xc6, 0xc6, 0x6c, 0x38, 0x0c, 0xc6,
-0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0xfe, 0xfe, 0xfe, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c,
-0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x7e, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x18, 0x0c, 0xfe, 0x0c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x60, 0xfe, 0x60, 0x30, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0xc0,
-0xc0, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x24, 0x66, 0xff, 0x66, 0x24, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x38, 0x7c, 0x7c, 0xfe, 0xfe, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xfe, 0x7c, 0x7c,
-0x38, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x24, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6c,
-0x6c, 0xfe, 0x6c, 0x6c, 0x6c, 0xfe, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00,
-0x18, 0x18, 0x7c, 0xc6, 0xc2, 0xc0, 0x7c, 0x06, 0x06, 0x86, 0xc6, 0x7c,
-0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc2, 0xc6, 0x0c, 0x18,
-0x30, 0x60, 0xc6, 0x86, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c,
-0x6c, 0x38, 0x76, 0xdc, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x30, 0x30, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x30, 0x30, 0x30,
-0x30, 0x30, 0x18, 0x0c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x18,
-0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x3c, 0xff, 0x3c, 0x66, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e,
-0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x02, 0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xce, 0xde, 0xf6, 0xe6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x38, 0x78, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6,
-0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0x06, 0x06, 0x3c, 0x06, 0x06, 0x06, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x1c, 0x3c, 0x6c, 0xcc, 0xfe,
-0x0c, 0x0c, 0x0c, 0x1e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0,
-0xc0, 0xc0, 0xfc, 0x06, 0x06, 0x06, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x38, 0x60, 0xc0, 0xc0, 0xfc, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0x06, 0x06, 0x0c, 0x18,
-0x30, 0x30, 0x30, 0x30, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6,
-0xc6, 0xc6, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x06, 0x06, 0x0c, 0x78,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00,
-0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x18, 0x18, 0x00, 0x00, 0x00, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x06,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00,
-0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60,
-0x30, 0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0xc6, 0x0c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xde, 0xde,
-0xde, 0xdc, 0xc0, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38,
-0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x66, 0x66, 0x66, 0x66, 0xfc,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0xc2, 0xc0, 0xc0, 0xc0,
-0xc0, 0xc2, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x6c,
-0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x6c, 0xf8, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68, 0x60, 0x62, 0x66, 0xfe,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68,
-0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66,
-0xc2, 0xc0, 0xc0, 0xde, 0xc6, 0xc6, 0x66, 0x3a, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x0c,
-0x0c, 0x0c, 0x0c, 0x0c, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xe6, 0x66, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0x66, 0xe6,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, 0x60, 0x60, 0x60, 0x60, 0x60,
-0x60, 0x62, 0x66, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xe7,
-0xff, 0xff, 0xdb, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6, 0xc6,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66,
-0x66, 0x66, 0x7c, 0x60, 0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xd6, 0xde, 0x7c,
-0x0c, 0x0e, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x6c,
-0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6,
-0xc6, 0x60, 0x38, 0x0c, 0x06, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xff, 0xdb, 0x99, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3,
-0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x66,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x18,
-0x3c, 0x66, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3,
-0xc3, 0x66, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xff, 0xc3, 0x86, 0x0c, 0x18, 0x30, 0x60, 0xc1, 0xc3, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x30, 0x30, 0x30, 0x30, 0x30,
-0x30, 0x30, 0x30, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80,
-0xc0, 0xe0, 0x70, 0x38, 0x1c, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x3c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0x00,
-0x30, 0x30, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x78, 0x0c, 0x7c,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe0, 0x60,
-0x60, 0x78, 0x6c, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc0, 0xc0, 0xc0, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x0c, 0x0c, 0x3c, 0x6c, 0xcc,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xf0,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xcc, 0xcc,
-0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0xcc, 0x78, 0x00, 0x00, 0x00, 0xe0, 0x60,
-0x60, 0x6c, 0x76, 0x66, 0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x18, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x06, 0x00, 0x0e, 0x06, 0x06,
-0x06, 0x06, 0x06, 0x06, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0xe0, 0x60,
-0x60, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe6, 0xff, 0xdb,
-0xdb, 0xdb, 0xdb, 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x66, 0x66,
-0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x76, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0x0c, 0x1e, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x76, 0x66, 0x60, 0x60, 0x60, 0xf0,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0x60,
-0x38, 0x0c, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x30,
-0x30, 0xfc, 0x30, 0x30, 0x30, 0x30, 0x36, 0x1c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0xc3,
-0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0x3c, 0x66, 0xc3,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xfe, 0xcc, 0x18, 0x30, 0x60, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x0e, 0x18, 0x18, 0x18, 0x70, 0x18, 0x18, 0x18, 0x18, 0x0e,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x00, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0x18,
-0x18, 0x18, 0x0e, 0x18, 0x18, 0x18, 0x18, 0x70, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6,
-0xc6, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66,
-0xc2, 0xc0, 0xc0, 0xc0, 0xc2, 0x66, 0x3c, 0x0c, 0x06, 0x7c, 0x00, 0x00,
-0x00, 0x00, 0xcc, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x00, 0x7c, 0xc6, 0xfe,
-0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c,
-0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xcc, 0x00, 0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0x78, 0x0c, 0x7c,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38,
-0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x60, 0x60, 0x66, 0x3c, 0x0c, 0x06,
-0x3c, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xfe,
-0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00,
-0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x60, 0x30, 0x18, 0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x00, 0x00, 0x38, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, 0x66,
-0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x60, 0x30, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0xc6,
-0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38, 0x00,
-0x38, 0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00,
-0x18, 0x30, 0x60, 0x00, 0xfe, 0x66, 0x60, 0x7c, 0x60, 0x60, 0x66, 0xfe,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6e, 0x3b, 0x1b,
-0x7e, 0xd8, 0xdc, 0x77, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3e, 0x6c,
-0xcc, 0xcc, 0xfe, 0xcc, 0xcc, 0xcc, 0xcc, 0xce, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x00, 0x7c, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18,
-0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x30, 0x78, 0xcc, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0xcc, 0xcc, 0xcc,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00,
-0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0x78, 0x00,
-0x00, 0xc6, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
-0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e,
-0xc3, 0xc0, 0xc0, 0xc0, 0xc3, 0x7e, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xe6, 0xfc,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0xff, 0x18,
-0xff, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66,
-0x7c, 0x62, 0x66, 0x6f, 0x66, 0x66, 0x66, 0xf3, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x0e, 0x1b, 0x18, 0x18, 0x18, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18,
-0xd8, 0x70, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0x78, 0x0c, 0x7c,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30,
-0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x18, 0x30, 0x60, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0xcc, 0xcc, 0xcc,
-0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc,
-0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00,
-0x76, 0xdc, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x6c, 0x6c, 0x3e, 0x00, 0x7e, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c,
-0x38, 0x00, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x30, 0x30, 0x00, 0x30, 0x30, 0x60, 0xc0, 0xc6, 0xc6, 0x7c,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0,
-0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0xfe, 0x06, 0x06, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30, 0x60, 0xce, 0x9b, 0x06,
-0x0c, 0x1f, 0x00, 0x00, 0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30,
-0x66, 0xce, 0x96, 0x3e, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18,
-0x00, 0x18, 0x18, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x6c, 0xd8, 0x6c, 0x36, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd8, 0x6c, 0x36,
-0x6c, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x11, 0x44, 0x11, 0x44,
-0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44,
-0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa,
-0x55, 0xaa, 0x55, 0xaa, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77,
-0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x18, 0xf8,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36,
-0x36, 0xf6, 0x06, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x06, 0xf6,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0xf6, 0x06, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xfe, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0xf8, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x37,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x37, 0x30, 0x3f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xf7, 0x00, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xff, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x37, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36,
-0x36, 0xf7, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xff,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xff, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x3f,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x1f, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f,
-0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x36, 0x36, 0x36, 0xff, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
-0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x1f, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
-0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff,
-0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf0, 0xf0, 0xf0, 0xf0,
-0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0,
-0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
-0x0f, 0x0f, 0x0f, 0x0f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x76, 0xdc, 0xd8, 0xd8, 0xd8, 0xdc, 0x76, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x78, 0xcc, 0xcc, 0xcc, 0xd8, 0xcc, 0xc6, 0xc6, 0xc6, 0xcc,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0xc6, 0xc0, 0xc0, 0xc0,
-0xc0, 0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0xfe, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0xfe, 0xc6, 0x60, 0x30, 0x18, 0x30, 0x60, 0xc6, 0xfe,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xd8, 0xd8,
-0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x66, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xc0, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x18, 0x3c, 0x66, 0x66,
-0x66, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38,
-0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0x6c, 0x38, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x38, 0x6c, 0xc6, 0xc6, 0xc6, 0x6c, 0x6c, 0x6c, 0x6c, 0xee,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x30, 0x18, 0x0c, 0x3e, 0x66,
-0x66, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x7e, 0xdb, 0xdb, 0xdb, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x03, 0x06, 0x7e, 0xdb, 0xdb, 0xf3, 0x7e, 0x60, 0xc0,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x30, 0x60, 0x60, 0x7c, 0x60,
-0x60, 0x60, 0x30, 0x1c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c,
-0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, 0x18,
-0x18, 0x00, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30,
-0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x00, 0x7e,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0e, 0x1b, 0x1b, 0x1b, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
-0x18, 0x18, 0x18, 0x18, 0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x7e, 0x00, 0x18, 0x18, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x00,
-0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c,
-0x38, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0f, 0x0c, 0x0c,
-0x0c, 0x0c, 0x0c, 0xec, 0x6c, 0x6c, 0x3c, 0x1c, 0x00, 0x00, 0x00, 0x00,
-0x00, 0xd8, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0xd8, 0x30, 0x60, 0xc8, 0xf8, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-0x00, 0x00, 0x00, 0x00,
-};
-
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index f502337dd37d..0fcc463b02e2 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -735,7 +735,7 @@ static const struct sysfs_ops cache_index_ops = {
 	.show = cache_index_show,
 };
 
-static struct kobj_type cache_index_type = {
+static const struct kobj_type cache_index_type = {
 	.release = cache_index_release,
 	.sysfs_ops = &cache_index_ops,
 	.default_groups = cache_index_default_groups,
diff --git a/arch/powerpc/kernel/compat_audit.c b/arch/powerpc/kernel/compat_audit.c
index d92ffe4e5dc1..57b38c592b9f 100644
--- a/arch/powerpc/kernel/compat_audit.c
+++ b/arch/powerpc/kernel/compat_audit.c
@@ -3,6 +3,8 @@
 #include <linux/audit_arch.h>
 #include <asm/unistd.h>
 
+#include "audit_32.h"
+
 unsigned ppc32_dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
 ~0U
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index f29ce3dd6140..ab3ca74e6730 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -26,6 +26,15 @@ BEGIN_FTR_SECTION
 	bl	__init_fpu_registers
 END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
 	bl	setup_common_caches
+
+	/*
+	 * This assumes that all cores using __setup_cpu_603 with
+	 * MMU_FTR_USE_HIGH_BATS are G2_LE compatible
+	 */
+BEGIN_MMU_FTR_SECTION
+	bl      setup_g2_le_hid2
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
 	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_604)
@@ -115,6 +124,16 @@ SYM_FUNC_START_LOCAL(setup_604_hid0)
 	blr
 SYM_FUNC_END(setup_604_hid0)
 
+/* Enable high BATs for G2_LE and derivatives like e300cX */
+SYM_FUNC_START_LOCAL(setup_g2_le_hid2)
+	mfspr	r11,SPRN_HID2_G2_LE
+	oris	r11,r11,HID2_G2_LE_HBE@h
+	mtspr	SPRN_HID2_G2_LE,r11
+	sync
+	isync
+	blr
+SYM_FUNC_END(setup_g2_le_hid2)
+
 /* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
  * erratas we work around here.
  * Moto MPC710CE.pdf describes them, those are errata
@@ -382,7 +401,7 @@ _GLOBAL(__save_cpu_setup)
 	andi.	r3,r3,0xff00
 	cmpwi	cr0,r3,0x0200
 	bne	1f
-	mfspr	r4,SPRN_HID2
+	mfspr	r4,SPRN_HID2_750FX
 	stw	r4,CS_HID2(r5)
 1:
 	mtcr	r7
@@ -477,7 +496,7 @@ _GLOBAL(__restore_cpu_setup)
 	bne	4f
 	lwz	r4,CS_HID2(r5)
 	rlwinm	r4,r4,0,19,17
-	mtspr	SPRN_HID2,r4
+	mtspr	SPRN_HID2_750FX,r4
 	sync
 4:
 	lwz	r4,CS_HID1(r5)
@@ -495,4 +514,3 @@ _GLOBAL(__restore_cpu_setup)
 	mtcr	r7
 	blr
 _ASM_NOKPROBE_SYMBOL(__restore_cpu_setup)
-
diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c
index 097c033668f0..98bd4e6c1770 100644
--- a/arch/powerpc/kernel/cpu_setup_power.c
+++ b/arch/powerpc/kernel/cpu_setup_power.c
@@ -126,6 +126,12 @@ static void init_PMU_ISA31(void)
 	mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT);
 }
 
+static void init_DEXCR(void)
+{
+	mtspr(SPRN_DEXCR, DEXCR_INIT);
+	mtspr(SPRN_HASHKEYR, 0);
+}
+
 /*
  * Note that we can be called twice of pseudo-PVRs.
  * The parameter offset is not used.
@@ -241,6 +247,7 @@ void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t)
 	init_FSCR_power10();
 	init_PMU();
 	init_PMU_ISA31();
+	init_DEXCR();
 
 	if (!init_hvmode_206(t))
 		return;
@@ -263,6 +270,7 @@ void __restore_cpu_power10(void)
 	init_FSCR_power10();
 	init_PMU();
 	init_PMU_ISA31();
+	init_DEXCR();
 
 	msr = mfmsr();
 	if (!(msr & MSR_HV))
diff --git a/arch/powerpc/kernel/cpu_specs.h b/arch/powerpc/kernel/cpu_specs.h
index 85ded3f77204..5ea14605bb41 100644
--- a/arch/powerpc/kernel/cpu_specs.h
+++ b/arch/powerpc/kernel/cpu_specs.h
@@ -1,9 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 
-#ifdef CONFIG_40x
-#include "cpu_specs_40x.h"
-#endif
-
 #ifdef CONFIG_PPC_47x
 #include "cpu_specs_47x.h"
 #elif defined(CONFIG_44x)
diff --git a/arch/powerpc/kernel/cpu_specs_40x.h b/arch/powerpc/kernel/cpu_specs_40x.h
deleted file mode 100644
index a1362a75b8c8..000000000000
--- a/arch/powerpc/kernel/cpu_specs_40x.h
+++ /dev/null
@@ -1,280 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
- */
-
-static struct cpu_spec cpu_specs[] __initdata = {
-	{	/* STB 04xxx */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x41810000,
-		.cpu_name		= "STB04xxx",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* NP405L */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x41610000,
-		.cpu_name		= "NP405L",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* NP4GS3 */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x40B10000,
-		.cpu_name		= "NP4GS3",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{   /* NP405H */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x41410000,
-		.cpu_name		= "NP405H",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405GPr */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x50910000,
-		.cpu_name		= "405GPr",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{   /* STBx25xx */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x51510000,
-		.cpu_name		= "STBx25xx",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405LP */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x41F10000,
-		.cpu_name		= "405LP",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EP */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x51210000,
-		.cpu_name		= "405EP",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EX Rev. A/B with Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x12910007,
-		.cpu_name		= "405EX Rev. A/B",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EX Rev. C without Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x1291000d,
-		.cpu_name		= "405EX Rev. C",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EX Rev. C with Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x1291000f,
-		.cpu_name		= "405EX Rev. C",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EX Rev. D without Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x12910003,
-		.cpu_name		= "405EX Rev. D",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EX Rev. D with Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x12910005,
-		.cpu_name		= "405EX Rev. D",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EXr Rev. A/B without Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x12910001,
-		.cpu_name		= "405EXr Rev. A/B",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EXr Rev. C without Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x12910009,
-		.cpu_name		= "405EXr Rev. C",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EXr Rev. C with Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x1291000b,
-		.cpu_name		= "405EXr Rev. C",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EXr Rev. D without Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x12910000,
-		.cpu_name		= "405EXr Rev. D",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* 405EXr Rev. D with Security */
-		.pvr_mask		= 0xffff000f,
-		.pvr_value		= 0x12910002,
-		.cpu_name		= "405EXr Rev. D",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{
-		/* 405EZ */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x41510000,
-		.cpu_name		= "405EZ",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* APM8018X */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x7ff11432,
-		.cpu_name		= "APM8018X",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	},
-	{	/* default match */
-		.pvr_mask		= 0x00000000,
-		.pvr_value		= 0x00000000,
-		.cpu_name		= "(generic 40x PPC)",
-		.cpu_features		= CPU_FTRS_40X,
-		.cpu_user_features	= PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
-					  PPC_FEATURE_HAS_4xxMAC,
-		.mmu_features		= MMU_FTR_TYPE_40x,
-		.icache_bsize		= 32,
-		.dcache_bsize		= 32,
-		.machine_check		= machine_check_4xx,
-		.platform		= "ppc405",
-	}
-};
diff --git a/arch/powerpc/kernel/cpu_specs_book3s_64.h b/arch/powerpc/kernel/cpu_specs_book3s_64.h
index c370c1b804a9..98d4274a1b6b 100644
--- a/arch/powerpc/kernel/cpu_specs_book3s_64.h
+++ b/arch/powerpc/kernel/cpu_specs_book3s_64.h
@@ -60,6 +60,9 @@
 				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
 				 PPC_FEATURE2_VEC_CRYPTO)
 
+#define COMMON_USER_POWER11	COMMON_USER_POWER10
+#define COMMON_USER2_POWER11	COMMON_USER2_POWER10
+
 static struct cpu_spec cpu_specs[] __initdata = {
 	{	/* PPC970 */
 		.pvr_mask		= 0xffff0000,
@@ -238,6 +241,21 @@ static struct cpu_spec cpu_specs[] __initdata = {
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
+	{	/* 2.07-compliant processor, HeXin C2000 processor */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x00660000,
+		.cpu_name		= "HX-C2000",
+		.cpu_features		= CPU_FTRS_POWER8,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.machine_check_early	= __machine_check_early_realmode_p8,
+		.platform		= "power8",
+	},
 	{	/* 3.00-compliant processor, i.e. Power9 "architected" mode */
 		.pvr_mask		= 0xffffffff,
 		.pvr_value		= 0x0f000005,
@@ -266,6 +284,20 @@ static struct cpu_spec cpu_specs[] __initdata = {
 		.cpu_restore		= __restore_cpu_power10,
 		.platform		= "power10",
 	},
+	{	/* 3.1-compliant processor, i.e. Power11 "architected" mode */
+		.pvr_mask		= 0xffffffff,
+		.pvr_value		= 0x0f000007,
+		.cpu_name		= "Power11 (architected)",
+		.cpu_features		= CPU_FTRS_POWER11,
+		.cpu_user_features	= COMMON_USER_POWER11,
+		.cpu_user_features2	= COMMON_USER2_POWER11,
+		.mmu_features		= MMU_FTRS_POWER11,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.cpu_setup		= __setup_cpu_power10,
+		.cpu_restore		= __restore_cpu_power10,
+		.platform		= "power11",
+	},
 	{	/* Power7 */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x003f0000,
@@ -436,6 +468,23 @@ static struct cpu_spec cpu_specs[] __initdata = {
 		.machine_check_early	= __machine_check_early_realmode_p10,
 		.platform		= "power10",
 	},
+	{	/* Power11 */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x00820000,
+		.cpu_name		= "Power11 (raw)",
+		.cpu_features		= CPU_FTRS_POWER11,
+		.cpu_user_features	= COMMON_USER_POWER11,
+		.cpu_user_features2	= COMMON_USER2_POWER11,
+		.mmu_features		= MMU_FTRS_POWER11,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.cpu_setup		= __setup_cpu_power10,
+		.cpu_restore		= __restore_cpu_power10,
+		.machine_check_early	= __machine_check_early_realmode_p10,
+		.platform		= "power11",
+	},
 	{	/* Cell Broadband Engine */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x00700000,
diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h
index ceb06b109f83..2ae8e9a7b461 100644
--- a/arch/powerpc/kernel/cpu_specs_e500mc.h
+++ b/arch/powerpc/kernel/cpu_specs_e500mc.h
@@ -8,7 +8,8 @@
 
 #ifdef CONFIG_PPC64
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
-				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64)
+				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \
+				 PPC_FEATURE_BOOKE)
 #else
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
 				 PPC_FEATURE_BOOKE)
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 8a32bffefa5b..6f6801da9dc1 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -20,9 +20,9 @@
 #include <asm/setup.h>
 #include <asm/cpu_setup.h>
 
-static struct cpu_spec the_cpu_spec __read_mostly;
+static struct cpu_spec the_cpu_spec __ro_after_init;
 
-struct cpu_spec* cur_cpu_spec __read_mostly = NULL;
+struct cpu_spec *cur_cpu_spec __ro_after_init = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
 
 /* The platform string corresponding to the real PVR */
@@ -75,6 +75,10 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
 		t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG;
 	}
 
+	/* Set kuap ON at startup, will be disabled later if cmdline has 'nosmap' */
+	if (IS_ENABLED(CONFIG_PPC_KUAP) && IS_ENABLED(CONFIG_PPC32))
+		t->mmu_features |= MMU_FTR_KUAP;
+
 	*PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
 
 	/*
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 9a3b85bfc83f..103b6605dd68 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -13,12 +13,13 @@
 #include <linux/io.h>
 #include <linux/memblock.h>
 #include <linux/of.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/kdump.h>
 #include <asm/firmware.h>
 #include <linux/uio.h>
 #include <asm/rtas.h>
 #include <asm/inst.h>
+#include <asm/fadump.h>
 
 #ifdef DEBUG
 #include <asm/udbg.h>
@@ -92,6 +93,17 @@ ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
 	return csize;
 }
 
+/*
+ * Return true only when kexec based kernel dump capturing method is used.
+ * This ensures all restritions applied for kdump case are not automatically
+ * applied for fadump case.
+ */
+bool is_kdump_kernel(void)
+{
+	return !is_fadump_active() && elfcorehdr_addr != ELFCORE_ADDR_MAX;
+}
+EXPORT_SYMBOL_GPL(is_kdump_kernel);
+
 #ifdef CONFIG_PPC_RTAS
 /*
  * The crashkernel region will almost always overlap the RTAS region, so
diff --git a/arch/powerpc/kernel/dexcr.c b/arch/powerpc/kernel/dexcr.c
new file mode 100644
index 000000000000..3a0358e91c60
--- /dev/null
+++ b/arch/powerpc/kernel/dexcr.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/capability.h>
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/prctl.h>
+#include <linux/sched.h>
+
+#include <asm/cpu_has_feature.h>
+#include <asm/cputable.h>
+#include <asm/processor.h>
+#include <asm/reg.h>
+
+static int __init init_task_dexcr(void)
+{
+	if (!early_cpu_has_feature(CPU_FTR_ARCH_31))
+		return 0;
+
+	current->thread.dexcr_onexec = mfspr(SPRN_DEXCR);
+
+	return 0;
+}
+early_initcall(init_task_dexcr)
+
+/* Allow thread local configuration of these by default */
+#define DEXCR_PRCTL_EDITABLE ( \
+	DEXCR_PR_IBRTPD | \
+	DEXCR_PR_SRAPD | \
+	DEXCR_PR_NPHIE)
+
+static int prctl_to_aspect(unsigned long which, unsigned int *aspect)
+{
+	switch (which) {
+	case PR_PPC_DEXCR_SBHE:
+		*aspect = DEXCR_PR_SBHE;
+		break;
+	case PR_PPC_DEXCR_IBRTPD:
+		*aspect = DEXCR_PR_IBRTPD;
+		break;
+	case PR_PPC_DEXCR_SRAPD:
+		*aspect = DEXCR_PR_SRAPD;
+		break;
+	case PR_PPC_DEXCR_NPHIE:
+		*aspect = DEXCR_PR_NPHIE;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+int get_dexcr_prctl(struct task_struct *task, unsigned long which)
+{
+	unsigned int aspect;
+	int ret;
+
+	ret = prctl_to_aspect(which, &aspect);
+	if (ret)
+		return ret;
+
+	if (aspect & DEXCR_PRCTL_EDITABLE)
+		ret |= PR_PPC_DEXCR_CTRL_EDITABLE;
+
+	if (aspect & mfspr(SPRN_DEXCR))
+		ret |= PR_PPC_DEXCR_CTRL_SET;
+	else
+		ret |= PR_PPC_DEXCR_CTRL_CLEAR;
+
+	if (aspect & task->thread.dexcr_onexec)
+		ret |= PR_PPC_DEXCR_CTRL_SET_ONEXEC;
+	else
+		ret |= PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC;
+
+	return ret;
+}
+
+int set_dexcr_prctl(struct task_struct *task, unsigned long which, unsigned long ctrl)
+{
+	unsigned long dexcr;
+	unsigned int aspect;
+	int err = 0;
+
+	err = prctl_to_aspect(which, &aspect);
+	if (err)
+		return err;
+
+	if (!(aspect & DEXCR_PRCTL_EDITABLE))
+		return -EPERM;
+
+	if (ctrl & ~PR_PPC_DEXCR_CTRL_MASK)
+		return -EINVAL;
+
+	if (ctrl & PR_PPC_DEXCR_CTRL_SET && ctrl & PR_PPC_DEXCR_CTRL_CLEAR)
+		return -EINVAL;
+
+	if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC && ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC)
+		return -EINVAL;
+
+	/*
+	 * We do not want an unprivileged process being able to disable
+	 * a setuid process's hash check instructions
+	 */
+	if (aspect == DEXCR_PR_NPHIE &&
+	    ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC &&
+	    !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	dexcr = mfspr(SPRN_DEXCR);
+
+	if (ctrl & PR_PPC_DEXCR_CTRL_SET)
+		dexcr |= aspect;
+	else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR)
+		dexcr &= ~aspect;
+
+	if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC)
+		task->thread.dexcr_onexec |= aspect;
+	else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC)
+		task->thread.dexcr_onexec &= ~aspect;
+
+	mtspr(SPRN_DEXCR, dexcr);
+
+	return 0;
+}
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 038ce8d9061d..aa3689d61917 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -14,7 +14,7 @@
 #define can_map_direct(dev, addr) \
 	((dev)->bus_dma_limit >= phys_to_dma((dev), (addr)))
 
-bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
+bool arch_dma_map_phys_direct(struct device *dev, phys_addr_t addr)
 {
 	if (likely(!dev->bus_dma_limit))
 		return false;
@@ -24,7 +24,7 @@ bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
 
 #define is_direct_handle(dev, h) ((h) >= (dev)->archdata.dma_offset)
 
-bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle)
+bool arch_dma_unmap_phys_direct(struct device *dev, dma_addr_t dma_handle)
 {
 	if (likely(!dev->bus_dma_limit))
 		return false;
@@ -93,28 +93,26 @@ static void dma_iommu_free_coherent(struct device *dev, size_t size,
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
- * comprises a page address and offset into that page. The dma_addr_t
- * returned will point to the same byte within the page as was passed in.
+ * is a physical address to that page. The dma_addr_t returned will point
+ * to the same byte within the page as was passed in.
  */
-static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
-				     unsigned long offset, size_t size,
+static dma_addr_t dma_iommu_map_phys(struct device *dev, phys_addr_t phys,
+				     size_t size,
 				     enum dma_data_direction direction,
 				     unsigned long attrs)
 {
-	return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
-			      size, dma_get_mask(dev), direction, attrs);
+	return iommu_map_phys(dev, get_iommu_table_base(dev), phys, size,
+			      dma_get_mask(dev), direction, attrs);
 }
 
-
-static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
+static void dma_iommu_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 				 size_t size, enum dma_data_direction direction,
 				 unsigned long attrs)
 {
-	iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
+	iommu_unmap_phys(get_iommu_table_base(dev), dma_handle, size, direction,
 			 attrs);
 }
 
-
 static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 			    int nelems, enum dma_data_direction direction,
 			    unsigned long attrs)
@@ -136,7 +134,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct pci_controller *phb = pci_bus_to_host(pdev->bus);
 
-	if (iommu_fixed_is_weak || !phb->controller_ops.iommu_bypass_supported)
+	if (!phb->controller_ops.iommu_bypass_supported)
 		return false;
 	return phb->controller_ops.iommu_bypass_supported(pdev, mask);
 }
@@ -144,7 +142,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
 /* We support DMA to/from any memory page via the iommu */
 int dma_iommu_dma_supported(struct device *dev, u64 mask)
 {
-	struct iommu_table *tbl = get_iommu_table_base(dev);
+	struct iommu_table *tbl;
 
 	if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
 		/*
@@ -162,6 +160,8 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
 		return 1;
 	}
 
+	tbl = get_iommu_table_base(dev);
+
 	if (!tbl) {
 		dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask);
 		return 0;
@@ -209,11 +209,11 @@ const struct dma_map_ops dma_iommu_ops = {
 	.map_sg			= dma_iommu_map_sg,
 	.unmap_sg		= dma_iommu_unmap_sg,
 	.dma_supported		= dma_iommu_dma_supported,
-	.map_page		= dma_iommu_map_page,
-	.unmap_page		= dma_iommu_unmap_page,
+	.map_phys		= dma_iommu_map_phys,
+	.unmap_phys		= dma_iommu_unmap_phys,
 	.get_required_mask	= dma_iommu_get_required_mask,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
-	.alloc_pages		= dma_common_alloc_pages,
+	.alloc_pages_op		= dma_common_alloc_pages,
 	.free_pages		= dma_common_free_pages,
 };
diff --git a/arch/powerpc/kernel/dma-mask.c b/arch/powerpc/kernel/dma-mask.c
index ffbbbc432612..5b07ca7b73aa 100644
--- a/arch/powerpc/kernel/dma-mask.c
+++ b/arch/powerpc/kernel/dma-mask.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <asm/machdep.h>
 
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index c3fb9fdf5bd7..3af6c06af02f 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -458,6 +458,14 @@ static int __init feat_enable_mce_power10(struct dt_cpu_feature *f)
 	return 1;
 }
 
+static int __init feat_enable_mce_power11(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->platform = "power11";
+	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p10;
+
+	return 1;
+}
+
 static int __init feat_enable_tm(struct dt_cpu_feature *f)
 {
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -648,8 +656,10 @@ static struct dt_cpu_feature_match __initdata
 	{"pc-relative-addressing", feat_enable, 0},
 	{"machine-check-power9", feat_enable_mce_power9, 0},
 	{"machine-check-power10", feat_enable_mce_power10, 0},
+	{"machine-check-power11", feat_enable_mce_power11, 0},
 	{"performance-monitor-power9", feat_enable_pmu_power9, 0},
 	{"performance-monitor-power10", feat_enable_pmu_power10, 0},
+	{"performance-monitor-power11", feat_enable_pmu_power10, 0},
 	{"event-based-branch-v3", feat_enable, 0},
 	{"random-number-generator", feat_enable, 0},
 	{"system-call-vectored", feat_disable, 0},
@@ -857,7 +867,7 @@ bool __init dt_cpu_ftrs_init(void *fdt)
 	using_dt_cpu_ftrs = false;
 
 	/* Setup and verify the FDT, if it fails we just bail */
-	if (!early_init_dt_verify(fdt))
+	if (!early_init_dt_verify(fdt, __pa(fdt)))
 		return false;
 
 	if (!of_scan_flat_dt(fdt_find_cpu_features, NULL))
@@ -1077,12 +1087,10 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
 	/* Count and allocate space for cpu features */
 	of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes,
 						&nr_dt_cpu_features);
-	dt_cpu_features = memblock_alloc(sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, PAGE_SIZE);
-	if (!dt_cpu_features)
-		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
-		      __func__,
-		      sizeof(struct dt_cpu_feature) * nr_dt_cpu_features,
-		      PAGE_SIZE);
+	dt_cpu_features =
+		memblock_alloc_or_panic(
+			sizeof(struct dt_cpu_feature) * nr_dt_cpu_features,
+			PAGE_SIZE);
 
 	cpufeatures_setup_start(isa);
 
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index ab316e155ea9..bb836f02101c 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -506,9 +506,18 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	 * We will punt with the following conditions: Failure to get
 	 * PE's state, EEH not support and Permanently unavailable
 	 * state, PE is in good state.
+	 *
+	 * On the pSeries, after reaching the threshold, get_state might
+	 * return EEH_STATE_NOT_SUPPORT. However, it's possible that the
+	 * device state remains uncleared if the device is not marked
+	 * pci_channel_io_perm_failure. Therefore, consider logging the
+	 * event to let device removal happen.
+	 *
 	 */
 	if ((ret < 0) ||
-	    (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) {
+	    (ret == EEH_STATE_NOT_SUPPORT &&
+	     dev->error_state == pci_channel_io_perm_failure) ||
+	    eeh_state_active(ret)) {
 		eeh_stats.false_positives++;
 		pe->false_positives++;
 		rc = 0;
@@ -1130,6 +1139,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(eeh_unfreeze_pe);
 
 
 static struct pci_device_id eeh_reset_ids[] = {
@@ -1199,16 +1209,16 @@ int eeh_dev_open(struct pci_dev *pdev)
 	struct eeh_dev *edev;
 	int ret = -ENODEV;
 
-	mutex_lock(&eeh_dev_mutex);
+	guard(mutex)(&eeh_dev_mutex);
 
 	/* No PCI device ? */
 	if (!pdev)
-		goto out;
+		return ret;
 
 	/* No EEH device or PE ? */
 	edev = pci_dev_to_eeh_dev(pdev);
 	if (!edev || !edev->pe)
-		goto out;
+		return ret;
 
 	/*
 	 * The PE might have been put into frozen state, but we
@@ -1218,16 +1228,12 @@ int eeh_dev_open(struct pci_dev *pdev)
 	 */
 	ret = eeh_pe_change_owner(edev->pe);
 	if (ret)
-		goto out;
+		return ret;
 
 	/* Increase PE's pass through count */
 	atomic_inc(&edev->pe->pass_dev_cnt);
-	mutex_unlock(&eeh_dev_mutex);
 
 	return 0;
-out:
-	mutex_unlock(&eeh_dev_mutex);
-	return ret;
 }
 EXPORT_SYMBOL_GPL(eeh_dev_open);
 
@@ -1243,43 +1249,25 @@ void eeh_dev_release(struct pci_dev *pdev)
 {
 	struct eeh_dev *edev;
 
-	mutex_lock(&eeh_dev_mutex);
+	guard(mutex)(&eeh_dev_mutex);
 
 	/* No PCI device ? */
 	if (!pdev)
-		goto out;
+		return;
 
 	/* No EEH device ? */
 	edev = pci_dev_to_eeh_dev(pdev);
 	if (!edev || !edev->pe || !eeh_pe_passed(edev->pe))
-		goto out;
+		return;
 
 	/* Decrease PE's pass through count */
 	WARN_ON(atomic_dec_if_positive(&edev->pe->pass_dev_cnt) < 0);
 	eeh_pe_change_owner(edev->pe);
-out:
-	mutex_unlock(&eeh_dev_mutex);
 }
 EXPORT_SYMBOL(eeh_dev_release);
 
 #ifdef CONFIG_IOMMU_API
 
-static int dev_has_iommu_table(struct device *dev, void *data)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct pci_dev **ppdev = data;
-
-	if (!dev)
-		return 0;
-
-	if (device_iommu_mapped(dev)) {
-		*ppdev = pdev;
-		return 1;
-	}
-
-	return 0;
-}
-
 /**
  * eeh_iommu_group_to_pe - Convert IOMMU group to EEH PE
  * @group: IOMMU group
@@ -1516,6 +1504,8 @@ int eeh_pe_configure(struct eeh_pe *pe)
 	/* Invalid PE ? */
 	if (!pe)
 		return -ENODEV;
+	else
+		ret = eeh_ops->configure_bridge(pe);
 
 	return ret;
 }
@@ -1544,10 +1534,6 @@ int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
 	if (!eeh_ops || !eeh_ops->err_inject)
 		return -ENOENT;
 
-	/* Check on PCI error type */
-	if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
-		return -EINVAL;
-
 	/* Check on PCI error function */
 	if (func < EEH_ERR_FUNC_MIN || func > EEH_ERR_FUNC_MAX)
 		return -EINVAL;
@@ -1585,6 +1571,104 @@ static int proc_eeh_show(struct seq_file *m, void *v)
 }
 #endif /* CONFIG_PROC_FS */
 
+static int eeh_break_device(struct pci_dev *pdev)
+{
+	struct resource *bar = NULL;
+	void __iomem *mapped;
+	u16 old, bit;
+	int i, pos;
+
+	/* Do we have an MMIO BAR to disable? */
+	for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
+		struct resource *r = &pdev->resource[i];
+
+		if (!r->flags || !r->start)
+			continue;
+		if (r->flags & IORESOURCE_IO)
+			continue;
+		if (r->flags & IORESOURCE_UNSET)
+			continue;
+
+		bar = r;
+		break;
+	}
+
+	if (!bar) {
+		pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n");
+		return -ENXIO;
+	}
+
+	pci_err(pdev, "Going to break: %pR\n", bar);
+
+	if (pdev->is_virtfn) {
+#ifndef CONFIG_PCI_IOV
+		return -ENXIO;
+#else
+		/*
+		 * VFs don't have a per-function COMMAND register, so the best
+		 * we can do is clear the Memory Space Enable bit in the PF's
+		 * SRIOV control reg.
+		 *
+		 * Unfortunately, this requires that we have a PF (i.e doesn't
+		 * work for a passed-through VF) and it has the potential side
+		 * effect of also causing an EEH on every other VF under the
+		 * PF. Oh well.
+		 */
+		pdev = pdev->physfn;
+		if (!pdev)
+			return -ENXIO; /* passed through VFs have no PF */
+
+		pos  = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
+		pos += PCI_SRIOV_CTRL;
+		bit  = PCI_SRIOV_CTRL_MSE;
+#endif /* !CONFIG_PCI_IOV */
+	} else {
+		bit = PCI_COMMAND_MEMORY;
+		pos = PCI_COMMAND;
+	}
+
+	/*
+	 * Process here is:
+	 *
+	 * 1. Disable Memory space.
+	 *
+	 * 2. Perform an MMIO to the device. This should result in an error
+	 *    (CA  / UR) being raised by the device which results in an EEH
+	 *    PE freeze. Using the in_8() accessor skips the eeh detection hook
+	 *    so the freeze hook so the EEH Detection machinery won't be
+	 *    triggered here. This is to match the usual behaviour of EEH
+	 *    where the HW will asynchronously freeze a PE and it's up to
+	 *    the kernel to notice and deal with it.
+	 *
+	 * 3. Turn Memory space back on. This is more important for VFs
+	 *    since recovery will probably fail if we don't. For normal
+	 *    the COMMAND register is reset as a part of re-initialising
+	 *    the device.
+	 *
+	 * Breaking stuff is the point so who cares if it's racy ;)
+	 */
+	pci_read_config_word(pdev, pos, &old);
+
+	mapped = ioremap(bar->start, PAGE_SIZE);
+	if (!mapped) {
+		pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar);
+		return -ENXIO;
+	}
+
+	pci_write_config_word(pdev, pos, old & ~bit);
+	in_8(mapped);
+	pci_write_config_word(pdev, pos, old);
+
+	iounmap(mapped);
+
+	return 0;
+}
+
+int eeh_pe_inject_mmio_error(struct pci_dev *pdev)
+{
+	return eeh_break_device(pdev);
+}
+
 #ifdef CONFIG_DEBUG_FS
 
 
@@ -1689,7 +1773,6 @@ static ssize_t eeh_force_recover_write(struct file *filp,
 
 static const struct file_operations eeh_force_recover_fops = {
 	.open	= simple_open,
-	.llseek	= no_llseek,
 	.write	= eeh_force_recover_write,
 };
 
@@ -1733,104 +1816,10 @@ static ssize_t eeh_dev_check_write(struct file *filp,
 
 static const struct file_operations eeh_dev_check_fops = {
 	.open	= simple_open,
-	.llseek	= no_llseek,
 	.write	= eeh_dev_check_write,
 	.read   = eeh_debugfs_dev_usage,
 };
 
-static int eeh_debugfs_break_device(struct pci_dev *pdev)
-{
-	struct resource *bar = NULL;
-	void __iomem *mapped;
-	u16 old, bit;
-	int i, pos;
-
-	/* Do we have an MMIO BAR to disable? */
-	for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
-		struct resource *r = &pdev->resource[i];
-
-		if (!r->flags || !r->start)
-			continue;
-		if (r->flags & IORESOURCE_IO)
-			continue;
-		if (r->flags & IORESOURCE_UNSET)
-			continue;
-
-		bar = r;
-		break;
-	}
-
-	if (!bar) {
-		pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n");
-		return -ENXIO;
-	}
-
-	pci_err(pdev, "Going to break: %pR\n", bar);
-
-	if (pdev->is_virtfn) {
-#ifndef CONFIG_PCI_IOV
-		return -ENXIO;
-#else
-		/*
-		 * VFs don't have a per-function COMMAND register, so the best
-		 * we can do is clear the Memory Space Enable bit in the PF's
-		 * SRIOV control reg.
-		 *
-		 * Unfortunately, this requires that we have a PF (i.e doesn't
-		 * work for a passed-through VF) and it has the potential side
-		 * effect of also causing an EEH on every other VF under the
-		 * PF. Oh well.
-		 */
-		pdev = pdev->physfn;
-		if (!pdev)
-			return -ENXIO; /* passed through VFs have no PF */
-
-		pos  = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
-		pos += PCI_SRIOV_CTRL;
-		bit  = PCI_SRIOV_CTRL_MSE;
-#endif /* !CONFIG_PCI_IOV */
-	} else {
-		bit = PCI_COMMAND_MEMORY;
-		pos = PCI_COMMAND;
-	}
-
-	/*
-	 * Process here is:
-	 *
-	 * 1. Disable Memory space.
-	 *
-	 * 2. Perform an MMIO to the device. This should result in an error
-	 *    (CA  / UR) being raised by the device which results in an EEH
-	 *    PE freeze. Using the in_8() accessor skips the eeh detection hook
-	 *    so the freeze hook so the EEH Detection machinery won't be
-	 *    triggered here. This is to match the usual behaviour of EEH
-	 *    where the HW will asynchronously freeze a PE and it's up to
-	 *    the kernel to notice and deal with it.
-	 *
-	 * 3. Turn Memory space back on. This is more important for VFs
-	 *    since recovery will probably fail if we don't. For normal
-	 *    the COMMAND register is reset as a part of re-initialising
-	 *    the device.
-	 *
-	 * Breaking stuff is the point so who cares if it's racy ;)
-	 */
-	pci_read_config_word(pdev, pos, &old);
-
-	mapped = ioremap(bar->start, PAGE_SIZE);
-	if (!mapped) {
-		pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar);
-		return -ENXIO;
-	}
-
-	pci_write_config_word(pdev, pos, old & ~bit);
-	in_8(mapped);
-	pci_write_config_word(pdev, pos, old);
-
-	iounmap(mapped);
-
-	return 0;
-}
-
 static ssize_t eeh_dev_break_write(struct file *filp,
 				const char __user *user_buf,
 				size_t count, loff_t *ppos)
@@ -1842,7 +1831,7 @@ static ssize_t eeh_dev_break_write(struct file *filp,
 	if (IS_ERR(pdev))
 		return PTR_ERR(pdev);
 
-	ret = eeh_debugfs_break_device(pdev);
+	ret = eeh_break_device(pdev);
 	pci_dev_put(pdev);
 
 	if (ret < 0)
@@ -1853,7 +1842,6 @@ static ssize_t eeh_dev_break_write(struct file *filp,
 
 static const struct file_operations eeh_dev_break_fops = {
 	.open	= simple_open,
-	.llseek	= no_llseek,
 	.write	= eeh_dev_break_write,
 	.read   = eeh_debugfs_dev_usage,
 };
@@ -1900,7 +1888,6 @@ static ssize_t eeh_dev_can_recover(struct file *filp,
 
 static const struct file_operations eeh_dev_can_recover_fops = {
 	.open	= simple_open,
-	.llseek	= no_llseek,
 	.write	= eeh_dev_can_recover,
 	.read   = eeh_debugfs_dev_usage,
 };
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 438568a472d0..ef78ff77cf8f 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -39,7 +39,7 @@ static int eeh_result_priority(enum pci_ers_result result)
 	case PCI_ERS_RESULT_NEED_RESET:
 		return 6;
 	default:
-		WARN_ONCE(1, "Unknown pci_ers_result value: %d\n", (int)result);
+		WARN_ONCE(1, "Unknown pci_ers_result value: %d\n", result);
 		return 0;
 	}
 };
@@ -60,7 +60,7 @@ static const char *pci_ers_result_name(enum pci_ers_result result)
 	case PCI_ERS_RESULT_NO_AER_DRIVER:
 		return "no AER driver";
 	default:
-		WARN_ONCE(1, "Unknown result type: %d\n", (int)result);
+		WARN_ONCE(1, "Unknown result type: %d\n", result);
 		return "unknown";
 	}
 };
@@ -257,13 +257,12 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn,
 	struct pci_driver *driver;
 	enum pci_ers_result new_result;
 
-	pci_lock_rescan_remove();
 	pdev = edev->pdev;
 	if (pdev)
 		get_device(&pdev->dev);
-	pci_unlock_rescan_remove();
 	if (!pdev) {
 		eeh_edev_info(edev, "no device");
+		*result = PCI_ERS_RESULT_DISCONNECT;
 		return;
 	}
 	device_lock(&pdev->dev);
@@ -304,8 +303,9 @@ static void eeh_pe_report(const char *name, struct eeh_pe *root,
 	struct eeh_dev *edev, *tmp;
 
 	pr_info("EEH: Beginning: '%s'\n", name);
-	eeh_for_each_pe(root, pe) eeh_pe_for_each_dev(pe, edev, tmp)
-		eeh_pe_report_edev(edev, fn, result);
+	eeh_for_each_pe(root, pe)
+		eeh_pe_for_each_dev(pe, edev, tmp)
+			eeh_pe_report_edev(edev, fn, result);
 	if (result)
 		pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n",
 			name, pci_ers_result_name(*result));
@@ -334,7 +334,7 @@ static enum pci_ers_result eeh_report_error(struct eeh_dev *edev,
 	rc = driver->err_handler->error_detected(pdev, pci_channel_io_frozen);
 
 	edev->in_error = true;
-	pci_uevent_ers(pdev, PCI_ERS_RESULT_NONE);
+	pci_uevent_ers(pdev, rc);
 	return rc;
 }
 
@@ -383,6 +383,8 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
 	if (!edev)
 		return;
 
+	pci_lock_rescan_remove();
+
 	/*
 	 * The content in the config space isn't saved because
 	 * the blocked config space on some adapters. We have
@@ -393,14 +395,19 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
 		if (list_is_last(&edev->entry, &edev->pe->edevs))
 			eeh_pe_restore_bars(edev->pe);
 
+		pci_unlock_rescan_remove();
 		return;
 	}
 
 	pdev = eeh_dev_to_pci_dev(edev);
-	if (!pdev)
+	if (!pdev) {
+		pci_unlock_rescan_remove();
 		return;
+	}
 
 	pci_restore_state(pdev);
+
+	pci_unlock_rescan_remove();
 }
 
 /**
@@ -647,9 +654,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	if (any_passed || driver_eeh_aware || (pe->type & EEH_PE_VF)) {
 		eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
 	} else {
-		pci_lock_rescan_remove();
 		pci_hp_remove_devices(bus);
-		pci_unlock_rescan_remove();
 	}
 
 	/*
@@ -665,8 +670,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	if (rc)
 		return rc;
 
-	pci_lock_rescan_remove();
-
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
@@ -674,7 +677,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	/* Clear frozen state */
 	rc = eeh_clear_pe_frozen_state(pe, false);
 	if (rc) {
-		pci_unlock_rescan_remove();
 		return rc;
 	}
 
@@ -709,7 +711,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	pe->tstamp = tstamp;
 	pe->freeze_count = cnt;
 
-	pci_unlock_rescan_remove();
 	return 0;
 }
 
@@ -843,10 +844,13 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 		{LIST_HEAD_INIT(rmv_data.removed_vf_list), 0};
 	int devices = 0;
 
+	pci_lock_rescan_remove();
+
 	bus = eeh_pe_bus_get(pe);
 	if (!bus) {
 		pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
+		pci_unlock_rescan_remove();
 		return;
 	}
 
@@ -865,9 +869,18 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 				devices++;
 
 	if (!devices) {
-		pr_debug("EEH: Frozen PHB#%x-PE#%x is empty!\n",
+		pr_warn("EEH: Frozen PHB#%x-PE#%x is empty!\n",
 			pe->phb->global_number, pe->addr);
-		goto out; /* nothing to recover */
+		/*
+		 * The device is removed, tear down its state, on powernv
+		 * hotplug driver would take care of it but not on pseries,
+		 * permanently disable the card as it is hot removed.
+		 *
+		 * In the case of powernv, note that the removal of device
+		 * is covered by pci rescan lock, so no problem even if hotplug
+		 * driver attempts to remove the device.
+		 */
+		goto recover_failed;
 	}
 
 	/* Log the event */
@@ -898,7 +911,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 		/* FIXME: Use the same format as dump_stack() */
 		pr_err("EEH: Call Trace:\n");
 		for (i = 0; i < pe->trace_entries; i++)
-			pr_err("EEH: [%pK] %pS\n", ptrs[i], ptrs[i]);
+			pr_err("EEH: [%p] %pS\n", ptrs[i], ptrs[i]);
 
 		pe->trace_entries = 0;
 	}
@@ -1085,10 +1098,15 @@ recover_failed:
 		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
 		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
-		pci_lock_rescan_remove();
-		pci_hp_remove_devices(bus);
-		pci_unlock_rescan_remove();
+		bus = eeh_pe_bus_get(pe);
+		if (bus)
+			pci_hp_remove_devices(bus);
+		else
+			pr_err("%s: PCI bus for PHB#%x-PE#%x disappeared\n",
+				__func__, pe->phb->global_number, pe->addr);
+
 		/* The passed PE should no longer be used */
+		pci_unlock_rescan_remove();
 		return;
 	}
 
@@ -1105,6 +1123,8 @@ out:
 			eeh_clear_slot_attention(edev->pdev);
 
 	eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
+
+	pci_unlock_rescan_remove();
 }
 
 /**
@@ -1123,6 +1143,7 @@ void eeh_handle_special_event(void)
 	unsigned long flags;
 	int rc;
 
+	pci_lock_rescan_remove();
 
 	do {
 		rc = eeh_ops->next_error(&pe);
@@ -1162,10 +1183,12 @@ void eeh_handle_special_event(void)
 
 			break;
 		case EEH_NEXT_ERR_NONE:
+			pci_unlock_rescan_remove();
 			return;
 		default:
 			pr_warn("%s: Invalid value %d from next_error()\n",
 				__func__, rc);
+			pci_unlock_rescan_remove();
 			return;
 		}
 
@@ -1177,7 +1200,9 @@ void eeh_handle_special_event(void)
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
 			eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+			pci_unlock_rescan_remove();
 			eeh_handle_normal_event(pe);
+			pci_lock_rescan_remove();
 		} else {
 			eeh_for_each_pe(pe, tmp_pe)
 				eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
@@ -1190,7 +1215,6 @@ void eeh_handle_special_event(void)
 				eeh_report_failure, NULL);
 			eeh_set_channel_state(pe, pci_channel_io_perm_failure);
 
-			pci_lock_rescan_remove();
 			list_for_each_entry(hose, &hose_list, list_node) {
 				phb_pe = eeh_phb_pe_get(hose);
 				if (!phb_pe ||
@@ -1209,7 +1233,6 @@ void eeh_handle_special_event(void)
 				}
 				pci_hp_remove_devices(bus);
 			}
-			pci_unlock_rescan_remove();
 		}
 
 		/*
@@ -1219,4 +1242,6 @@ void eeh_handle_special_event(void)
 		if (rc == EEH_NEXT_ERR_DEAD_IOC)
 			break;
 	} while (rc != EEH_NEXT_ERR_NONE);
+
+	pci_unlock_rescan_remove();
 }
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index d2873d17d2b1..e740101fadf3 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -24,10 +24,10 @@ static int eeh_pe_aux_size = 0;
 static LIST_HEAD(eeh_phb_pe);
 
 /**
- * eeh_set_pe_aux_size - Set PE auxillary data size
- * @size: PE auxillary data size
+ * eeh_set_pe_aux_size - Set PE auxiliary data size
+ * @size: PE auxiliary data size in bytes
  *
- * Set PE auxillary data size
+ * Set PE auxiliary data size.
  */
 void eeh_set_pe_aux_size(int size)
 {
@@ -527,7 +527,7 @@ EXPORT_SYMBOL_GPL(eeh_pe_state_mark);
  * eeh_pe_mark_isolated
  * @pe: EEH PE
  *
- * Record that a PE has been isolated by marking the PE and it's children as
+ * Record that a PE has been isolated by marking the PE and its children as
  * EEH_PE_ISOLATED (and EEH_PE_CFG_BLOCKED, if required) and their PCI devices
  * as pci_channel_io_frozen.
  */
@@ -671,11 +671,12 @@ static void eeh_bridge_check_link(struct eeh_dev *edev)
 	eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val);
 
 	/* Check link */
-	eeh_ops->read_config(edev, cap + PCI_EXP_LNKCAP, 4, &val);
-	if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
-		eeh_edev_dbg(edev, "No link reporting capability (0x%08x) \n", val);
-		msleep(1000);
-		return;
+	if (edev->pdev) {
+		if (!edev->pdev->link_active_reporting) {
+			eeh_edev_dbg(edev, "No link reporting capability\n");
+			msleep(1000);
+			return;
+		}
 	}
 
 	/* Wait the link is up until timeout (5s) */
@@ -850,6 +851,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
 {
 	struct eeh_dev *edev;
 	struct pci_dev *pdev;
+	struct pci_bus *bus = NULL;
 
 	if (pe->type & EEH_PE_PHB)
 		return pe->phb->bus;
@@ -860,9 +862,11 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
 
 	/* Retrieve the parent PCI bus of first (top) PCI device */
 	edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry);
+	pci_lock_rescan_remove();
 	pdev = eeh_dev_to_pci_dev(edev);
 	if (pdev)
-		return pdev->bus;
+		bus = pdev->bus;
+	pci_unlock_rescan_remove();
 
-	return NULL;
+	return bus;
 }
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 47f0dd9a45ad..16f8ee6cb2cd 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -29,7 +29,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 #include <asm/ptrace.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 #include <asm/barrier.h>
 #include <asm/kup.h>
@@ -102,6 +101,17 @@ SYM_FUNC_END(__kuep_unlock)
 .endm
 #endif
 
+.macro	clr_ri trash
+#ifndef CONFIG_BOOKE
+#ifdef CONFIG_PPC_8xx
+	mtspr   SPRN_NRI, \trash
+#else
+	li	\trash, MSR_KERNEL & ~MSR_RI
+	mtmsr	\trash
+#endif
+#endif
+.endm
+
 	.globl	transfer_to_syscall
 transfer_to_syscall:
 	stw	r3, ORIG_GPR3(r1)
@@ -109,7 +119,7 @@ transfer_to_syscall:
 	stw	r11, 0(r1)
 	mflr	r12
 	stw	r12, _LINK(r1)
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
 #endif
 	lis	r12,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
@@ -138,8 +148,9 @@ ret_from_syscall:
 	lis	r4,icache_44x_need_flush@ha
 	lwz	r5,icache_44x_need_flush@l(r4)
 	cmplwi	cr0,r5,0
-	bne-	2f
+	bne-	.L44x_icache_flush
 #endif /* CONFIG_PPC_47x */
+.L44x_icache_flush_return:
 	kuep_unlock
 	lwz	r4,_LINK(r1)
 	lwz	r5,_CCR(r1)
@@ -149,6 +160,7 @@ ret_from_syscall:
 	cmpwi	r3,0
 	REST_GPR(3, r1)
 syscall_exit_finish:
+	clr_ri	r4
 	mtspr	SPRN_SRR0,r7
 	mtspr	SPRN_SRR1,r8
 
@@ -158,9 +170,6 @@ syscall_exit_finish:
 1:	REST_GPR(2, r1)
 	REST_GPR(1, r1)
 	rfi
-#ifdef CONFIG_40x
-	b .	/* Prevent prefetch past rfi */
-#endif
 
 3:	mtcr	r5
 	lwz	r4,_CTR(r1)
@@ -171,12 +180,14 @@ syscall_exit_finish:
 	REST_GPR(0, r1)
 	REST_GPRS(3, 12, r1)
 	b	1b
+_ASM_NOKPROBE_SYMBOL(syscall_exit_finish)
 
 #ifdef CONFIG_44x
-2:	li	r7,0
+.L44x_icache_flush:
+	li	r7,0
 	iccci	r0,r0
 	stw	r7,icache_44x_need_flush@l(r4)
-	b	1b
+	b	.L44x_icache_flush_return
 #endif  /* CONFIG_44x */
 
 	.globl	ret_from_fork
@@ -211,72 +222,14 @@ start_kernel_thread:
 100:	trap
 	EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0
 
-
-/*
- * This routine switches between two different tasks.  The process
- * state of one is saved on its kernel stack.  Then the state
- * of the other is restored from its kernel stack.  The memory
- * management hardware is updated to the second process's state.
- * Finally, we can return to the second process.
- * On entry, r3 points to the THREAD for the current task, r4
- * points to the THREAD for the new task.
- *
- * This routine is always called with interrupts disabled.
- *
- * Note: there are two ways to get to the "going out" portion
- * of this code; either by coming in via the entry (_switch)
- * or via "fork" which must set up an environment equivalent
- * to the "_switch" path.  If you change this , you'll have to
- * change the fork code also.
- *
- * The code which creates the new task context is in 'copy_thread'
- * in arch/ppc/kernel/process.c
- */
-_GLOBAL(_switch)
-	stwu	r1,-SWITCH_FRAME_SIZE(r1)
-	mflr	r0
-	stw	r0,SWITCH_FRAME_SIZE+4(r1)
-	/* r3-r12 are caller saved -- Cort */
-	SAVE_NVGPRS(r1)
-	stw	r0,_NIP(r1)	/* Return to switch caller */
-	mfcr	r10
-	stw	r10,_CCR(r1)
-	stw	r1,KSP(r3)	/* Set old stack pointer */
-
-#ifdef CONFIG_SMP
-	/* We need a sync somewhere here to make sure that if the
-	 * previous task gets rescheduled on another CPU, it sees all
-	 * stores it has performed on this one.
-	 */
-	sync
-#endif /* CONFIG_SMP */
-
-	tophys(r0,r4)
-	mtspr	SPRN_SPRG_THREAD,r0	/* Update current THREAD phys addr */
-	lwz	r1,KSP(r4)	/* Load new stack pointer */
-
-	/* save the old current 'last' for return value */
-	mr	r3,r2
-	addi	r2,r4,-THREAD	/* Update current */
-
-	lwz	r0,_CCR(r1)
-	mtcrf	0xFF,r0
-	/* r3-r12 are destroyed -- Cort */
-	REST_NVGPRS(r1)
-
-	lwz	r4,_NIP(r1)	/* Return to _switch caller in new task */
-	mtlr	r4
-	addi	r1,r1,SWITCH_FRAME_SIZE
-	blr
-
 	.globl	fast_exception_return
 fast_exception_return:
-#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+#ifndef CONFIG_BOOKE
 	andi.	r10,r9,MSR_RI		/* check for recoverable interrupt */
 	beq	3f			/* if not, we've got problems */
 #endif
 
-2:	lwz	r10,_CCR(r11)
+	lwz	r10,_CCR(r11)
 	REST_GPRS(1, 6, r11)
 	mtcr	r10
 	lwz	r10,_LINK(r11)
@@ -284,19 +237,14 @@ fast_exception_return:
 	/* Clear the exception marker on the stack to avoid confusing stacktrace */
 	li	r10, 0
 	stw	r10, 8(r11)
-	REST_GPR(10, r11)
-#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
-	mtspr	SPRN_NRI, r0
-#endif
+	clr_ri	r10
 	mtspr	SPRN_SRR1,r9
 	mtspr	SPRN_SRR0,r12
 	REST_GPR(9, r11)
+	REST_GPR(10, r11)
 	REST_GPR(12, r11)
 	REST_GPR(11, r11)
 	rfi
-#ifdef CONFIG_40x
-	b .	/* Prevent prefetch past rfi */
-#endif
 _ASM_NOKPROBE_SYMBOL(fast_exception_return)
 
 /* aargh, a nonrecoverable interrupt, panic */
@@ -322,14 +270,14 @@ interrupt_return:
 .Lfast_user_interrupt_return:
 	lwz	r11,_NIP(r1)
 	lwz	r12,_MSR(r1)
+	clr_ri	r4
 	mtspr	SPRN_SRR0,r11
 	mtspr	SPRN_SRR1,r12
 
 BEGIN_FTR_SECTION
+	lwarx   r0,0,r1
+END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	stwcx.	r0,0,r1		/* to clear the reservation */
-FTR_SECTION_ELSE
-	lwarx	r0,0,r1
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 	lwz	r3,_CCR(r1)
 	lwz	r4,_LINK(r1)
@@ -353,9 +301,6 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	REST_GPR(0, r1)
 	REST_GPR(1, r1)
 	rfi
-#ifdef CONFIG_40x
-	b .	/* Prevent prefetch past rfi */
-#endif
 
 .Lrestore_nvgprs:
 	REST_NVGPRS(r1)
@@ -368,14 +313,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	cmpwi	cr1,r3,0
 	lwz	r11,_NIP(r1)
 	lwz	r12,_MSR(r1)
+	clr_ri	r4
 	mtspr	SPRN_SRR0,r11
 	mtspr	SPRN_SRR1,r12
 
 BEGIN_FTR_SECTION
+	lwarx   r0,0,r1
+END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	stwcx.	r0,0,r1		/* to clear the reservation */
-FTR_SECTION_ELSE
-	lwarx	r0,0,r1
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 	lwz	r3,_LINK(r1)
 	lwz	r4,_CTR(r1)
@@ -403,9 +348,6 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	REST_GPR(0, r1)
 	REST_GPR(1, r1)
 	rfi
-#ifdef CONFIG_40x
-	b .	/* Prevent prefetch past rfi */
-#endif
 
 1:	/*
 	 * Emulate stack store with update. New r1 value was already calculated
@@ -432,12 +374,9 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	mfspr	r9, SPRN_SPRG_SCRATCH0
 #endif
 	rfi
-#ifdef CONFIG_40x
-	b .	/* Prevent prefetch past rfi */
-#endif
 _ASM_NOKPROBE_SYMBOL(interrupt_return)
 
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_BOOKE
 
 /*
  * Returning from a critical interrupt in user mode doesn't need
@@ -452,17 +391,6 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
  * time of the critical interrupt.
  *
  */
-#ifdef CONFIG_40x
-#define PPC_40x_TURN_OFF_MSR_DR						    \
-	/* avoid any possible TLB misses here by turning off MSR.DR, we	    \
-	 * assume the instructions here are mapped by a pinned TLB entry */ \
-	li	r10,MSR_IR;						    \
-	mtmsr	r10;							    \
-	isync;								    \
-	tophys(r1, r1);
-#else
-#define PPC_40x_TURN_OFF_MSR_DR
-#endif
 
 #define RET_FROM_EXC_LEVEL(exc_lvl_srr0, exc_lvl_srr1, exc_lvl_rfi)	\
 	REST_NVGPRS(r1);						\
@@ -480,7 +408,6 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
 	mtlr	r11;							\
 	lwz	r10,_CCR(r1);						\
 	mtcrf	0xff,r10;						\
-	PPC_40x_TURN_OFF_MSR_DR;					\
 	lwz	r9,_DEAR(r1);						\
 	lwz	r10,_ESR(r1);						\
 	mtspr	SPRN_DEAR,r9;						\
@@ -528,20 +455,6 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return)
 #define RESTORE_MMU_REGS
 #endif
 
-#ifdef CONFIG_40x
-	.globl	ret_from_crit_exc
-ret_from_crit_exc:
-	lis	r9,crit_srr0@ha;
-	lwz	r9,crit_srr0@l(r9);
-	lis	r10,crit_srr1@ha;
-	lwz	r10,crit_srr1@l(r10);
-	mtspr	SPRN_SRR0,r9;
-	mtspr	SPRN_SRR1,r10;
-	RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, PPC_RFCI)
-_ASM_NOKPROBE_SYMBOL(ret_from_crit_exc)
-#endif /* CONFIG_40x */
-
-#ifdef CONFIG_BOOKE
 	.globl	ret_from_crit_exc
 ret_from_crit_exc:
 	RESTORE_xSRR(SRR0,SRR1);
@@ -566,4 +479,3 @@ ret_from_mcheck_exc:
 	RET_FROM_EXC_LEVEL(SPRN_MCSRR0, SPRN_MCSRR1, PPC_RFMCI)
 _ASM_NOKPROBE_SYMBOL(ret_from_mcheck_exc)
 #endif /* CONFIG_BOOKE */
-#endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
index 033116e465d0..6a414ed5a411 100644
--- a/arch/powerpc/kernel/epapr_hcalls.S
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -3,6 +3,7 @@
  * Copyright (C) 2012 Freescale Semiconductor, Inc.
  */
 
+#include <linux/export.h>
 #include <linux/threads.h>
 #include <asm/epapr_hcalls.h>
 #include <asm/reg.h>
@@ -12,7 +13,6 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-compat.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 
 #ifndef CONFIG_PPC64
 /* epapr_ev_idle() was derived from e500_idle() */
@@ -21,7 +21,7 @@ _GLOBAL(epapr_ev_idle)
 	ori	r4, r4,_TLF_NAPPING	/* so when we take an exception */
 	PPC_STL	r4, TI_LOCAL_FLAGS(r2)	/* it will return to our caller */
 
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 	wrteei	1
 #else
 	mfmsr	r4
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index d4b8aff20815..247ab2acaccc 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -9,7 +9,7 @@
 #include <linux/of_fdt.h>
 #include <asm/epapr_hcalls.h>
 #include <asm/cacheflush.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/machdep.h>
 #include <asm/inst.h>
 
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 3f86091e68b3..63f6b9f513a4 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -5,6 +5,7 @@
  *  Copyright (C) 2007 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
  */
 
+#include <linux/linkage.h>
 #include <linux/threads.h>
 #include <asm/reg.h>
 #include <asm/page.h>
@@ -13,7 +14,6 @@
 #include <asm/cputable.h>
 #include <asm/setup.h>
 #include <asm/thread_info.h>
-#include <asm/reg_a2.h>
 #include <asm/exception-64e.h>
 #include <asm/bug.h>
 #include <asm/irqflags.h>
@@ -66,7 +66,7 @@
 #define SPECIAL_EXC_LOAD(reg, name) \
 	ld	reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1)
 
-special_reg_save:
+SYM_CODE_START_LOCAL(special_reg_save)
 	/*
 	 * We only need (or have stack space) to save this stuff if
 	 * we interrupted the kernel.
@@ -131,8 +131,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	SPECIAL_EXC_STORE(r10,CSRR1)
 
 	blr
+SYM_CODE_END(special_reg_save)
 
-ret_from_level_except:
+SYM_CODE_START_LOCAL(ret_from_level_except)
 	ld	r3,_MSR(r1)
 	andi.	r3,r3,MSR_PR
 	beq	1f
@@ -206,6 +207,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	mtxer	r11
 
 	blr
+SYM_CODE_END(ret_from_level_except)
 
 .macro ret_from_level srr0 srr1 paca_ex scratch
 	bl	ret_from_level_except
@@ -232,13 +234,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	mfspr	r13,\scratch
 .endm
 
-ret_from_crit_except:
+SYM_CODE_START_LOCAL(ret_from_crit_except)
 	ret_from_level SPRN_CSRR0 SPRN_CSRR1 PACA_EXCRIT SPRN_SPRG_CRIT_SCRATCH
 	rfci
+SYM_CODE_END(ret_from_crit_except)
 
-ret_from_mc_except:
+SYM_CODE_START_LOCAL(ret_from_mc_except)
 	ret_from_level SPRN_MCSRR0 SPRN_MCSRR1 PACA_EXMC SPRN_SPRG_MC_SCRATCH
 	rfmci
+SYM_CODE_END(ret_from_mc_except)
 
 /* Exception prolog code for all exceptions */
 #define EXCEPTION_PROLOG(n, intnum, type, addition)	    		    \
@@ -481,8 +485,8 @@ interrupt_base_book3e:					/* fake trap */
 	EXCEPTION_STUB(0x160, decrementer)		/* 0x0900 */
 	EXCEPTION_STUB(0x180, fixed_interval)		/* 0x0980 */
 	EXCEPTION_STUB(0x1a0, watchdog)			/* 0x09f0 */
-	EXCEPTION_STUB(0x1c0, data_tlb_miss)
-	EXCEPTION_STUB(0x1e0, instruction_tlb_miss)
+	EXCEPTION_STUB(0x1c0, data_tlb_miss_bolted)
+	EXCEPTION_STUB(0x1e0, instruction_tlb_miss_bolted)
 	EXCEPTION_STUB(0x200, altivec_unavailable)
 	EXCEPTION_STUB(0x220, altivec_assist)
 	EXCEPTION_STUB(0x260, perfmon)
@@ -978,20 +982,22 @@ masked_interrupt_book3e_0x2c0:
  * r14 and r15 containing the fault address and error code, with the
  * original values stashed away in the PACA
  */
-storage_fault_common:
+SYM_CODE_START_LOCAL(storage_fault_common)
 	addi	r3,r1,STACK_INT_FRAME_REGS
 	bl	do_page_fault
 	b	interrupt_return
+SYM_CODE_END(storage_fault_common)
 
 /*
  * Alignment exception doesn't fit entirely in the 0x100 bytes so it
  * continues here.
  */
-alignment_more:
+SYM_CODE_START_LOCAL(alignment_more)
 	addi	r3,r1,STACK_INT_FRAME_REGS
 	bl	alignment_exception
 	REST_NVGPRS(r1)
 	b	interrupt_return
+SYM_CODE_END(alignment_more)
 
 /*
  * Trampolines used when spotting a bad kernel stack pointer in
@@ -1030,8 +1036,7 @@ BAD_STACK_TRAMPOLINE(0xe00)
 BAD_STACK_TRAMPOLINE(0xf00)
 BAD_STACK_TRAMPOLINE(0xf20)
 
-	.globl	bad_stack_book3e
-bad_stack_book3e:
+_GLOBAL(bad_stack_book3e)
 	/* XXX: Needs to make SPRN_SPRG_GEN depend on exception type */
 	mfspr	r10,SPRN_SRR0;		  /* read SRR0 before touching stack */
 	ld	r1,PACAEMERGSP(r13)
@@ -1285,8 +1290,7 @@ have_hes:
 	 * ever takes any parameters, the SCOM code must also be updated to
 	 * provide them.
 	 */
-	.globl a2_tlbinit_code_start
-a2_tlbinit_code_start:
+_GLOBAL(a2_tlbinit_code_start)
 
 	ori	r11,r3,MAS0_WQ_ALLWAYS
 	oris	r11,r11,MAS0_ESEL(3)@h /* Use way 3: workaround A2 erratum 376 */
@@ -1479,8 +1483,7 @@ _GLOBAL(book3e_secondary_thread_init)
 	mflr	r28
 	b	3b
 
-	.globl init_core_book3e
-init_core_book3e:
+_GLOBAL(init_core_book3e)
 	/* Establish the interrupt vector base */
 	tovirt(r2,r2)
 	LOAD_REG_ADDR(r3, interrupt_base_book3e)
@@ -1488,7 +1491,7 @@ init_core_book3e:
 	sync
 	blr
 
-init_thread_book3e:
+SYM_CODE_START_LOCAL(init_thread_book3e)
 	lis	r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h
 	mtspr	SPRN_EPCR,r3
 
@@ -1502,6 +1505,7 @@ init_thread_book3e:
 	mtspr	SPRN_TSR,r3
 
 	blr
+SYM_CODE_END(init_thread_book3e)
 
 _GLOBAL(__setup_base_ivors)
 	SET_IVOR(0, 0x020) /* Critical Input */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index c33c8ebf8641..b7229430ca94 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -893,7 +893,7 @@ __start_interrupts:
  *
  * Call convention:
  *
- * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
+ * syscall register convention is in Documentation/arch/powerpc/syscall64-abi.rst
  */
 EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
 	/* SCV 0 */
@@ -1952,8 +1952,8 @@ EXC_VIRT_NONE(0x4b00, 0x100)
  * Call convention:
  *
  * syscall and hypercalls register conventions are documented in
- * Documentation/powerpc/syscall64-abi.rst and
- * Documentation/powerpc/papr_hcalls.rst respectively.
+ * Documentation/arch/powerpc/syscall64-abi.rst and
+ * Documentation/arch/powerpc/papr_hcalls.rst respectively.
  *
  * The intersection of volatile registers that don't contain possible
  * inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry
@@ -1989,13 +1989,6 @@ INT_DEFINE_END(system_call)
 	INTERRUPT_TO_KERNEL
 #endif
 
-#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
-BEGIN_FTR_SECTION
-	cmpdi	r0,0x1ebe
-	beq-	1f
-END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
-#endif
-
 	/* We reach here with PACA in r13, r13 in r9. */
 	mfspr	r11,SPRN_SRR0
 	mfspr	r12,SPRN_SRR1
@@ -2015,16 +2008,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	b	system_call_common
 #endif
 	.endif
-
-#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
-	/* Fast LE/BE switch system call */
-1:	mfspr	r12,SPRN_SRR1
-	xori	r12,r12,MSR_LE
-	mtspr	SPRN_SRR1,r12
-	mr	r13,r9
-	RFI_TO_USER	/* return to userspace */
-	b	.	/* prevent speculative execution */
-#endif
 .endm
 
 EXC_REAL_BEGIN(system_call, 0xc00, 0x100)
@@ -2554,27 +2537,8 @@ EXC_REAL_NONE(0x1000, 0x100)
 EXC_VIRT_NONE(0x5000, 0x100)
 EXC_REAL_NONE(0x1100, 0x100)
 EXC_VIRT_NONE(0x5100, 0x100)
-
-#ifdef CONFIG_CBE_RAS
-INT_DEFINE_BEGIN(cbe_system_error)
-	IVEC=0x1200
-	IHSRR=1
-INT_DEFINE_END(cbe_system_error)
-
-EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
-	GEN_INT_ENTRY cbe_system_error, virt=0
-EXC_REAL_END(cbe_system_error, 0x1200, 0x100)
-EXC_VIRT_NONE(0x5200, 0x100)
-EXC_COMMON_BEGIN(cbe_system_error_common)
-	GEN_COMMON cbe_system_error
-	addi	r3,r1,STACK_INT_FRAME_REGS
-	bl	CFUNC(cbe_system_error_exception)
-	b	interrupt_return_hsrr
-
-#else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1200, 0x100)
 EXC_VIRT_NONE(0x5200, 0x100)
-#endif
 
 /**
  * Interrupt 0x1300 - Instruction Address Breakpoint Interrupt.
@@ -2725,26 +2689,8 @@ EXC_COMMON_BEGIN(denorm_exception_common)
 	b	interrupt_return_hsrr
 
 
-#ifdef CONFIG_CBE_RAS
-INT_DEFINE_BEGIN(cbe_maintenance)
-	IVEC=0x1600
-	IHSRR=1
-INT_DEFINE_END(cbe_maintenance)
-
-EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
-	GEN_INT_ENTRY cbe_maintenance, virt=0
-EXC_REAL_END(cbe_maintenance, 0x1600, 0x100)
-EXC_VIRT_NONE(0x5600, 0x100)
-EXC_COMMON_BEGIN(cbe_maintenance_common)
-	GEN_COMMON cbe_maintenance
-	addi	r3,r1,STACK_INT_FRAME_REGS
-	bl	CFUNC(cbe_maintenance_exception)
-	b	interrupt_return_hsrr
-
-#else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1600, 0x100)
 EXC_VIRT_NONE(0x5600, 0x100)
-#endif
 
 
 INT_DEFINE_BEGIN(altivec_assist)
@@ -2772,26 +2718,8 @@ EXC_COMMON_BEGIN(altivec_assist_common)
 	b	interrupt_return_srr
 
 
-#ifdef CONFIG_CBE_RAS
-INT_DEFINE_BEGIN(cbe_thermal)
-	IVEC=0x1800
-	IHSRR=1
-INT_DEFINE_END(cbe_thermal)
-
-EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)
-	GEN_INT_ENTRY cbe_thermal, virt=0
-EXC_REAL_END(cbe_thermal, 0x1800, 0x100)
-EXC_VIRT_NONE(0x5800, 0x100)
-EXC_COMMON_BEGIN(cbe_thermal_common)
-	GEN_COMMON cbe_thermal
-	addi	r3,r1,STACK_INT_FRAME_REGS
-	bl	CFUNC(cbe_thermal_exception)
-	b	interrupt_return_hsrr
-
-#else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1800, 0x100)
 EXC_VIRT_NONE(0x5800, 0x100)
-#endif
 
 
 #ifdef CONFIG_PPC_WATCHDOG
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index ea0a073abd96..4ebc333dd786 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -33,6 +33,7 @@
 #include <asm/fadump-internal.h>
 #include <asm/setup.h>
 #include <asm/interrupt.h>
+#include <asm/prom.h>
 
 /*
  * The CPU who acquired the lock to trigger the fadump crash should
@@ -53,8 +54,6 @@ static struct kobject *fadump_kobj;
 static atomic_t cpus_in_fadump;
 static DEFINE_MUTEX(fadump_mutex);
 
-static struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0, false };
-
 #define RESERVED_RNGS_SZ	16384 /* 16K - 128 entries */
 #define RESERVED_RNGS_CNT	(RESERVED_RNGS_SZ / \
 				 sizeof(struct fadump_memory_range))
@@ -80,26 +79,38 @@ static struct cma *fadump_cma;
  * But for some reason even if it fails we still have the memory reservation
  * with us and we can still continue doing fadump.
  */
-static int __init fadump_cma_init(void)
+void __init fadump_cma_init(void)
 {
-	unsigned long long base, size;
+	unsigned long long base, size, end;
 	int rc;
 
-	if (!fw_dump.fadump_enabled)
-		return 0;
-
+	if (!fw_dump.fadump_supported || !fw_dump.fadump_enabled ||
+			fw_dump.dump_active)
+		return;
 	/*
 	 * Do not use CMA if user has provided fadump=nocma kernel parameter.
-	 * Return 1 to continue with fadump old behaviour.
 	 */
-	if (fw_dump.nocma)
-		return 1;
+	if (fw_dump.nocma || !fw_dump.boot_memory_size)
+		return;
 
+	/*
+	 * [base, end) should be reserved during early init in
+	 * fadump_reserve_mem(). No need to check this here as
+	 * cma_init_reserved_mem() already checks for overlap.
+	 * Here we give the aligned chunk of this reserved memory to CMA.
+	 */
 	base = fw_dump.reserve_dump_area_start;
 	size = fw_dump.boot_memory_size;
+	end = base + size;
 
-	if (!size)
-		return 0;
+	base = ALIGN(base, CMA_MIN_ALIGNMENT_BYTES);
+	end = ALIGN_DOWN(end, CMA_MIN_ALIGNMENT_BYTES);
+	size = end - base;
+
+	if (end <= base) {
+		pr_warn("%s: Too less memory to give to CMA\n", __func__);
+		return;
+	}
 
 	rc = cma_init_reserved_mem(base, size, 0, "fadump_cma", &fadump_cma);
 	if (rc) {
@@ -110,7 +121,7 @@ static int __init fadump_cma_init(void)
 		 * blocked from production system usage.  Hence return 1,
 		 * so that we can continue with fadump.
 		 */
-		return 1;
+		return;
 	}
 
 	/*
@@ -122,17 +133,50 @@ static int __init fadump_cma_init(void)
 	/*
 	 * So we now have successfully initialized cma area for fadump.
 	 */
-	pr_info("Initialized 0x%lx bytes cma area at %ldMB from 0x%lx "
+	pr_info("Initialized [0x%llx, %luMB] cma area from [0x%lx, %luMB] "
 		"bytes of memory reserved for firmware-assisted dump\n",
-		cma_get_size(fadump_cma),
-		(unsigned long)cma_get_base(fadump_cma) >> 20,
-		fw_dump.reserve_dump_area_size);
-	return 1;
+		cma_get_base(fadump_cma), cma_get_size(fadump_cma) >> 20,
+		fw_dump.reserve_dump_area_start,
+		fw_dump.boot_memory_size >> 20);
+	return;
 }
-#else
-static int __init fadump_cma_init(void) { return 1; }
 #endif /* CONFIG_CMA */
 
+/*
+ * Additional parameters meant for capture kernel are placed in a dedicated area.
+ * If this is capture kernel boot, append these parameters to bootargs.
+ */
+void __init fadump_append_bootargs(void)
+{
+	char *append_args;
+	size_t len;
+
+	if (!fw_dump.dump_active || !fw_dump.param_area_supported || !fw_dump.param_area)
+		return;
+
+	if (fw_dump.param_area < fw_dump.boot_mem_top) {
+		if (memblock_reserve(fw_dump.param_area, COMMAND_LINE_SIZE)) {
+			pr_warn("WARNING: Can't use additional parameters area!\n");
+			fw_dump.param_area = 0;
+			return;
+		}
+	}
+
+	append_args = (char *)fw_dump.param_area;
+	len = strlen(boot_command_line);
+
+	/*
+	 * Too late to fail even if cmdline size exceeds. Truncate additional parameters
+	 * to cmdline size and proceed anyway.
+	 */
+	if (len + strlen(append_args) >= COMMAND_LINE_SIZE - 1)
+		pr_warn("WARNING: Appending parameters exceeds cmdline size. Truncating!\n");
+
+	pr_debug("Cmdline: %s\n", boot_command_line);
+	snprintf(boot_command_line + len, COMMAND_LINE_SIZE - len, " %s", append_args);
+	pr_info("Updated cmdline: %s\n", boot_command_line);
+}
+
 /* Scan the Firmware Assisted dump configuration details. */
 int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
 				      int depth, void *data)
@@ -223,28 +267,6 @@ static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end)
 }
 
 /*
- * Returns true, if there are no holes in boot memory area,
- * false otherwise.
- */
-bool is_fadump_boot_mem_contiguous(void)
-{
-	unsigned long d_start, d_end;
-	bool ret = false;
-	int i;
-
-	for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
-		d_start = fw_dump.boot_mem_addr[i];
-		d_end   = d_start + fw_dump.boot_mem_sz[i];
-
-		ret = is_fadump_mem_area_contiguous(d_start, d_end);
-		if (!ret)
-			break;
-	}
-
-	return ret;
-}
-
-/*
  * Returns true, if there are no holes in reserved memory area,
  * false otherwise.
  */
@@ -268,10 +290,8 @@ static void __init fadump_show_config(void)
 	if (!fw_dump.fadump_supported)
 		return;
 
-	pr_debug("Fadump enabled    : %s\n",
-				(fw_dump.fadump_enabled ? "yes" : "no"));
-	pr_debug("Dump Active       : %s\n",
-				(fw_dump.dump_active ? "yes" : "no"));
+	pr_debug("Fadump enabled    : %s\n", str_yes_no(fw_dump.fadump_enabled));
+	pr_debug("Dump Active       : %s\n", str_yes_no(fw_dump.dump_active));
 	pr_debug("Dump section sizes:\n");
 	pr_debug("    CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
 	pr_debug("    HPTE region size   : %lx\n", fw_dump.hpte_region_size);
@@ -313,7 +333,7 @@ static __init u64 fadump_calculate_reserve_size(void)
 	 * memory at a predefined offset.
 	 */
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
-				&size, &base);
+				&size, &base, NULL, NULL, NULL);
 	if (ret == 0 && size > 0) {
 		unsigned long max_size;
 
@@ -373,12 +393,6 @@ static unsigned long __init get_fadump_area_size(void)
 	size = PAGE_ALIGN(size);
 	size += fw_dump.boot_memory_size;
 	size += sizeof(struct fadump_crash_info_header);
-	size += sizeof(struct elfhdr); /* ELF core header.*/
-	size += sizeof(struct elf_phdr); /* place holder for cpu notes */
-	/* Program headers for crash memory regions. */
-	size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
-
-	size = PAGE_ALIGN(size);
 
 	/* This is to hold kernel metadata on platforms that support it */
 	size += (fw_dump.ops->fadump_get_metadata_size ?
@@ -389,10 +403,11 @@ static unsigned long __init get_fadump_area_size(void)
 static int __init add_boot_mem_region(unsigned long rstart,
 				      unsigned long rsize)
 {
+	int max_boot_mem_rgns = fw_dump.ops->fadump_max_boot_mem_rgns();
 	int i = fw_dump.boot_mem_regs_cnt++;
 
-	if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) {
-		fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS;
+	if (fw_dump.boot_mem_regs_cnt > max_boot_mem_rgns) {
+		fw_dump.boot_mem_regs_cnt = max_boot_mem_rgns;
 		return 0;
 	}
 
@@ -552,13 +567,6 @@ int __init fadump_reserve_mem(void)
 	if (!fw_dump.dump_active) {
 		fw_dump.boot_memory_size =
 			PAGE_ALIGN(fadump_calculate_reserve_size());
-#ifdef CONFIG_CMA
-		if (!fw_dump.nocma) {
-			fw_dump.boot_memory_size =
-				ALIGN(fw_dump.boot_memory_size,
-				      CMA_MIN_ALIGNMENT_BYTES);
-		}
-#endif
 
 		bootmem_min = fw_dump.ops->fadump_get_bootmem_min();
 		if (fw_dump.boot_memory_size < bootmem_min) {
@@ -573,22 +581,6 @@ int __init fadump_reserve_mem(void)
 		}
 	}
 
-	/*
-	 * Calculate the memory boundary.
-	 * If memory_limit is less than actual memory boundary then reserve
-	 * the memory for fadump beyond the memory_limit and adjust the
-	 * memory_limit accordingly, so that the running kernel can run with
-	 * specified memory_limit.
-	 */
-	if (memory_limit && memory_limit < memblock_end_of_DRAM()) {
-		size = get_fadump_area_size();
-		if ((memory_limit + size) < memblock_end_of_DRAM())
-			memory_limit += size;
-		else
-			memory_limit = memblock_end_of_DRAM();
-		printk(KERN_INFO "Adjusted memory_limit for firmware-assisted"
-				" dump, now %#016llx\n", memory_limit);
-	}
 	if (memory_limit)
 		mem_boundary = memory_limit;
 	else
@@ -647,13 +639,12 @@ int __init fadump_reserve_mem(void)
 
 		pr_info("Reserved %lldMB of memory at %#016llx (System RAM: %lldMB)\n",
 			(size >> 20), base, (memblock_phys_mem_size() >> 20));
-
-		ret = fadump_cma_init();
 	}
 
 	return ret;
 error_out:
 	fw_dump.fadump_enabled = 0;
+	fw_dump.reserve_dump_area_size = 0;
 	return 0;
 }
 
@@ -704,7 +695,7 @@ void crash_fadump(struct pt_regs *regs, const char *str)
 	 * old_cpu == -1 means this is the first CPU which has come here,
 	 * go ahead and trigger fadump.
 	 *
-	 * old_cpu != -1 means some other CPU has already on it's way
+	 * old_cpu != -1 means some other CPU has already on its way
 	 * to trigger fadump, just keep looping here.
 	 */
 	this_cpu = smp_processor_id();
@@ -759,7 +750,7 @@ u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
 	 * prstatus.pr_pid = ????
 	 */
 	elf_core_copy_regs(&prstatus.pr_reg, regs);
-	buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+	buf = append_elf_note(buf, NN_PRSTATUS, NT_PRSTATUS,
 			      &prstatus, sizeof(prstatus));
 	return buf;
 }
@@ -930,36 +921,6 @@ static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info,
 	return 0;
 }
 
-static int fadump_exclude_reserved_area(u64 start, u64 end)
-{
-	u64 ra_start, ra_end;
-	int ret = 0;
-
-	ra_start = fw_dump.reserve_dump_area_start;
-	ra_end = ra_start + fw_dump.reserve_dump_area_size;
-
-	if ((ra_start < end) && (ra_end > start)) {
-		if ((start < ra_start) && (end > ra_end)) {
-			ret = fadump_add_mem_range(&crash_mrange_info,
-						   start, ra_start);
-			if (ret)
-				return ret;
-
-			ret = fadump_add_mem_range(&crash_mrange_info,
-						   ra_end, end);
-		} else if (start < ra_start) {
-			ret = fadump_add_mem_range(&crash_mrange_info,
-						   start, ra_start);
-		} else if (ra_end < end) {
-			ret = fadump_add_mem_range(&crash_mrange_info,
-						   ra_end, end);
-		}
-	} else
-		ret = fadump_add_mem_range(&crash_mrange_info, start, end);
-
-	return ret;
-}
-
 static int fadump_init_elfcore_header(char *bufp)
 {
 	struct elfhdr *elf;
@@ -997,52 +958,6 @@ static int fadump_init_elfcore_header(char *bufp)
 }
 
 /*
- * Traverse through memblock structure and setup crash memory ranges. These
- * ranges will be used create PT_LOAD program headers in elfcore header.
- */
-static int fadump_setup_crash_memory_ranges(void)
-{
-	u64 i, start, end;
-	int ret;
-
-	pr_debug("Setup crash memory ranges.\n");
-	crash_mrange_info.mem_range_cnt = 0;
-
-	/*
-	 * Boot memory region(s) registered with firmware are moved to
-	 * different location at the time of crash. Create separate program
-	 * header(s) for this memory chunk(s) with the correct offset.
-	 */
-	for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
-		start = fw_dump.boot_mem_addr[i];
-		end = start + fw_dump.boot_mem_sz[i];
-		ret = fadump_add_mem_range(&crash_mrange_info, start, end);
-		if (ret)
-			return ret;
-	}
-
-	for_each_mem_range(i, &start, &end) {
-		/*
-		 * skip the memory chunk that is already added
-		 * (0 through boot_memory_top).
-		 */
-		if (start < fw_dump.boot_mem_top) {
-			if (end > fw_dump.boot_mem_top)
-				start = fw_dump.boot_mem_top;
-			else
-				continue;
-		}
-
-		/* add this range excluding the reserved dump area. */
-		ret = fadump_exclude_reserved_area(start, end);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/*
  * If the given physical address falls within the boot memory region then
  * return the relocated address that points to the dump region reserved
  * for saving initial boot memory contents.
@@ -1072,36 +987,50 @@ static inline unsigned long fadump_relocate(unsigned long paddr)
 	return raddr;
 }
 
-static int fadump_create_elfcore_headers(char *bufp)
+static void __init populate_elf_pt_load(struct elf_phdr *phdr, u64 start,
+			     u64 size, unsigned long long offset)
 {
-	unsigned long long raddr, offset;
-	struct elf_phdr *phdr;
+	phdr->p_align	= 0;
+	phdr->p_memsz	= size;
+	phdr->p_filesz	= size;
+	phdr->p_paddr	= start;
+	phdr->p_offset	= offset;
+	phdr->p_type	= PT_LOAD;
+	phdr->p_flags	= PF_R|PF_W|PF_X;
+	phdr->p_vaddr	= (unsigned long)__va(start);
+}
+
+static void __init fadump_populate_elfcorehdr(struct fadump_crash_info_header *fdh)
+{
+	char *bufp;
 	struct elfhdr *elf;
-	int i, j;
+	struct elf_phdr *phdr;
+	u64 boot_mem_dest_offset;
+	unsigned long long i, ra_start, ra_end, ra_size, mstart, mend;
 
+	bufp = (char *) fw_dump.elfcorehdr_addr;
 	fadump_init_elfcore_header(bufp);
 	elf = (struct elfhdr *)bufp;
 	bufp += sizeof(struct elfhdr);
 
 	/*
-	 * setup ELF PT_NOTE, place holder for cpu notes info. The notes info
-	 * will be populated during second kernel boot after crash. Hence
-	 * this PT_NOTE will always be the first elf note.
+	 * Set up ELF PT_NOTE, a placeholder for CPU notes information.
+	 * The notes info will be populated later by platform-specific code.
+	 * Hence, this PT_NOTE will always be the first ELF note.
 	 *
 	 * NOTE: Any new ELF note addition should be placed after this note.
 	 */
 	phdr = (struct elf_phdr *)bufp;
 	bufp += sizeof(struct elf_phdr);
 	phdr->p_type = PT_NOTE;
-	phdr->p_flags = 0;
-	phdr->p_vaddr = 0;
-	phdr->p_align = 0;
-
-	phdr->p_offset = 0;
-	phdr->p_paddr = 0;
-	phdr->p_filesz = 0;
-	phdr->p_memsz = 0;
-
+	phdr->p_flags	= 0;
+	phdr->p_vaddr	= 0;
+	phdr->p_align	= 0;
+	phdr->p_offset	= 0;
+	phdr->p_paddr	= 0;
+	phdr->p_filesz	= 0;
+	phdr->p_memsz	= 0;
+	/* Increment number of program headers. */
 	(elf->e_phnum)++;
 
 	/* setup ELF PT_NOTE for vmcoreinfo */
@@ -1111,55 +1040,66 @@ static int fadump_create_elfcore_headers(char *bufp)
 	phdr->p_flags	= 0;
 	phdr->p_vaddr	= 0;
 	phdr->p_align	= 0;
-
-	phdr->p_paddr	= fadump_relocate(paddr_vmcoreinfo_note());
-	phdr->p_offset	= phdr->p_paddr;
-	phdr->p_memsz	= phdr->p_filesz = VMCOREINFO_NOTE_SIZE;
-
+	phdr->p_paddr	= phdr->p_offset = fdh->vmcoreinfo_raddr;
+	phdr->p_memsz	= phdr->p_filesz = fdh->vmcoreinfo_size;
 	/* Increment number of program headers. */
 	(elf->e_phnum)++;
 
-	/* setup PT_LOAD sections. */
-	j = 0;
-	offset = 0;
-	raddr = fw_dump.boot_mem_addr[0];
-	for (i = 0; i < crash_mrange_info.mem_range_cnt; i++) {
-		u64 mbase, msize;
-
-		mbase = crash_mrange_info.mem_ranges[i].base;
-		msize = crash_mrange_info.mem_ranges[i].size;
-		if (!msize)
-			continue;
-
+	/*
+	 * Setup PT_LOAD sections. first include boot memory regions
+	 * and then add rest of the memory regions.
+	 */
+	boot_mem_dest_offset = fw_dump.boot_mem_dest_addr;
+	for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
 		phdr = (struct elf_phdr *)bufp;
 		bufp += sizeof(struct elf_phdr);
-		phdr->p_type	= PT_LOAD;
-		phdr->p_flags	= PF_R|PF_W|PF_X;
-		phdr->p_offset	= mbase;
-
-		if (mbase == raddr) {
-			/*
-			 * The entire real memory region will be moved by
-			 * firmware to the specified destination_address.
-			 * Hence set the correct offset.
-			 */
-			phdr->p_offset = fw_dump.boot_mem_dest_addr + offset;
-			if (j < (fw_dump.boot_mem_regs_cnt - 1)) {
-				offset += fw_dump.boot_mem_sz[j];
-				raddr = fw_dump.boot_mem_addr[++j];
-			}
+		populate_elf_pt_load(phdr, fw_dump.boot_mem_addr[i],
+				     fw_dump.boot_mem_sz[i],
+				     boot_mem_dest_offset);
+		/* Increment number of program headers. */
+		(elf->e_phnum)++;
+		boot_mem_dest_offset += fw_dump.boot_mem_sz[i];
+	}
+
+	/* Memory reserved for fadump in first kernel */
+	ra_start = fw_dump.reserve_dump_area_start;
+	ra_size = get_fadump_area_size();
+	ra_end = ra_start + ra_size;
+
+	phdr = (struct elf_phdr *)bufp;
+	for_each_mem_range(i, &mstart, &mend) {
+		/* Boot memory regions already added, skip them now */
+		if (mstart < fw_dump.boot_mem_top) {
+			if (mend > fw_dump.boot_mem_top)
+				mstart = fw_dump.boot_mem_top;
+			else
+				continue;
 		}
 
-		phdr->p_paddr = mbase;
-		phdr->p_vaddr = (unsigned long)__va(mbase);
-		phdr->p_filesz = msize;
-		phdr->p_memsz = msize;
-		phdr->p_align = 0;
+		/* Handle memblock regions overlaps with fadump reserved area */
+		if ((ra_start < mend) && (ra_end > mstart)) {
+			if ((mstart < ra_start) && (mend > ra_end)) {
+				populate_elf_pt_load(phdr, mstart, ra_start - mstart, mstart);
+				/* Increment number of program headers. */
+				(elf->e_phnum)++;
+				bufp += sizeof(struct elf_phdr);
+				phdr = (struct elf_phdr *)bufp;
+				populate_elf_pt_load(phdr, ra_end, mend - ra_end, ra_end);
+			} else if (mstart < ra_start) {
+				populate_elf_pt_load(phdr, mstart, ra_start - mstart, mstart);
+			} else if (ra_end < mend) {
+				populate_elf_pt_load(phdr, ra_end, mend - ra_end, ra_end);
+			}
+		} else {
+		/* No overlap with fadump reserved memory region */
+			populate_elf_pt_load(phdr, mstart, mend - mstart, mstart);
+		}
 
 		/* Increment number of program headers. */
 		(elf->e_phnum)++;
+		bufp += sizeof(struct elf_phdr);
+		phdr = (struct elf_phdr *) bufp;
 	}
-	return 0;
 }
 
 static unsigned long init_fadump_header(unsigned long addr)
@@ -1174,14 +1114,25 @@ static unsigned long init_fadump_header(unsigned long addr)
 
 	memset(fdh, 0, sizeof(struct fadump_crash_info_header));
 	fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
-	fdh->elfcorehdr_addr = addr;
+	fdh->version = FADUMP_HEADER_VERSION;
 	/* We will set the crashing cpu id in crash_fadump() during crash. */
 	fdh->crashing_cpu = FADUMP_CPU_UNKNOWN;
+
+	/*
+	 * The physical address and size of vmcoreinfo are required in the
+	 * second kernel to prepare elfcorehdr.
+	 */
+	fdh->vmcoreinfo_raddr = fadump_relocate(paddr_vmcoreinfo_note());
+	fdh->vmcoreinfo_size = VMCOREINFO_NOTE_SIZE;
+
+
+	fdh->pt_regs_sz = sizeof(struct pt_regs);
 	/*
 	 * When LPAR is terminated by PYHP, ensure all possible CPUs'
 	 * register data is processed while exporting the vmcore.
 	 */
 	fdh->cpu_mask = *cpu_possible_mask;
+	fdh->cpu_mask_sz = sizeof(struct cpumask);
 
 	return addr;
 }
@@ -1189,8 +1140,6 @@ static unsigned long init_fadump_header(unsigned long addr)
 static int register_fadump(void)
 {
 	unsigned long addr;
-	void *vaddr;
-	int ret;
 
 	/*
 	 * If no memory is reserved then we can not register for firmware-
@@ -1199,18 +1148,10 @@ static int register_fadump(void)
 	if (!fw_dump.reserve_dump_area_size)
 		return -ENODEV;
 
-	ret = fadump_setup_crash_memory_ranges();
-	if (ret)
-		return ret;
-
 	addr = fw_dump.fadumphdr_addr;
 
 	/* Initialize fadump crash info header. */
 	addr = init_fadump_header(addr);
-	vaddr = __va(addr);
-
-	pr_debug("Creating ELF core headers at %#016lx\n", addr);
-	fadump_create_elfcore_headers(vaddr);
 
 	/* register the future kernel dump with firmware. */
 	pr_debug("Registering for firmware-assisted kernel dump...\n");
@@ -1229,7 +1170,6 @@ void fadump_cleanup(void)
 	} else if (fw_dump.dump_registered) {
 		/* Un-register Firmware-assisted dump if it was registered. */
 		fw_dump.ops->fadump_unregister(&fw_dump);
-		fadump_free_mem_ranges(&crash_mrange_info);
 	}
 
 	if (fw_dump.ops->fadump_cleanup)
@@ -1415,17 +1355,31 @@ static void fadump_release_memory(u64 begin, u64 end)
 		fadump_release_reserved_area(tstart, end);
 }
 
-static void fadump_invalidate_release_mem(void)
+static void fadump_free_elfcorehdr_buf(void)
 {
-	mutex_lock(&fadump_mutex);
-	if (!fw_dump.dump_active) {
-		mutex_unlock(&fadump_mutex);
+	if (fw_dump.elfcorehdr_addr == 0 || fw_dump.elfcorehdr_size == 0)
 		return;
-	}
 
-	fadump_cleanup();
-	mutex_unlock(&fadump_mutex);
+	/*
+	 * Before freeing the memory of `elfcorehdr`, reset the global
+	 * `elfcorehdr_addr` to prevent modules like `vmcore` from accessing
+	 * invalid memory.
+	 */
+	elfcorehdr_addr = ELFCORE_ADDR_ERR;
+	fadump_free_buffer(fw_dump.elfcorehdr_addr, fw_dump.elfcorehdr_size);
+	fw_dump.elfcorehdr_addr = 0;
+	fw_dump.elfcorehdr_size = 0;
+}
 
+static void fadump_invalidate_release_mem(void)
+{
+	scoped_guard(mutex, &fadump_mutex) {
+		if (!fw_dump.dump_active)
+			return;
+		fadump_cleanup();
+	}
+
+	fadump_free_elfcorehdr_buf();
 	fadump_release_memory(fw_dump.boot_mem_top, memblock_end_of_DRAM());
 	fadump_free_cpu_notes_buf();
 
@@ -1483,6 +1437,18 @@ static ssize_t enabled_show(struct kobject *kobj,
 	return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
 }
 
+/*
+ * /sys/kernel/fadump/hotplug_ready sysfs node returns 1, which inidcates
+ * to usersapce that fadump re-registration is not required on memory
+ * hotplug events.
+ */
+static ssize_t hotplug_ready_show(struct kobject *kobj,
+				      struct kobj_attribute *attr,
+				      char *buf)
+{
+	return sprintf(buf, "%d\n", 1);
+}
+
 static ssize_t mem_reserved_show(struct kobject *kobj,
 				 struct kobj_attribute *attr,
 				 char *buf)
@@ -1497,6 +1463,43 @@ static ssize_t registered_show(struct kobject *kobj,
 	return sprintf(buf, "%d\n", fw_dump.dump_registered);
 }
 
+static ssize_t bootargs_append_show(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   char *buf)
+{
+	return sprintf(buf, "%s\n", (char *)__va(fw_dump.param_area));
+}
+
+static ssize_t bootargs_append_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t count)
+{
+	char *params;
+
+	if (!fw_dump.fadump_enabled || fw_dump.dump_active)
+		return -EPERM;
+
+	if (count >= COMMAND_LINE_SIZE)
+		return -EINVAL;
+
+	/*
+	 * Fail here instead of handling this scenario with
+	 * some silly workaround in capture kernel.
+	 */
+	if (saved_command_line_len + count >= COMMAND_LINE_SIZE) {
+		pr_err("Appending parameters exceeds cmdline size!\n");
+		return -ENOSPC;
+	}
+
+	params = __va(fw_dump.param_area);
+	strscpy_pad(params, buf, COMMAND_LINE_SIZE);
+	/* Remove newline character at the end. */
+	if (params[count-1] == '\n')
+		params[count-1] = '\0';
+
+	return count;
+}
+
 static ssize_t registered_store(struct kobject *kobj,
 				struct kobj_attribute *attr,
 				const char *buf, size_t count)
@@ -1555,11 +1558,14 @@ static struct kobj_attribute release_attr = __ATTR_WO(release_mem);
 static struct kobj_attribute enable_attr = __ATTR_RO(enabled);
 static struct kobj_attribute register_attr = __ATTR_RW(registered);
 static struct kobj_attribute mem_reserved_attr = __ATTR_RO(mem_reserved);
+static struct kobj_attribute hotplug_ready_attr = __ATTR_RO(hotplug_ready);
+static struct kobj_attribute bootargs_append_attr = __ATTR_RW(bootargs_append);
 
 static struct attribute *fadump_attrs[] = {
 	&enable_attr.attr,
 	&register_attr.attr,
 	&mem_reserved_attr.attr,
+	&hotplug_ready_attr.attr,
 	NULL,
 };
 
@@ -1577,6 +1583,12 @@ static void __init fadump_init_files(void)
 		return;
 	}
 
+	if (fw_dump.param_area) {
+		rc = sysfs_create_file(fadump_kobj, &bootargs_append_attr.attr);
+		if (rc)
+			pr_err("unable to create bootargs_append sysfs file (%d)\n", rc);
+	}
+
 	debugfs_create_file("fadump_region", 0444, arch_debugfs_dir, NULL,
 			    &fadump_region_fops);
 
@@ -1631,6 +1643,153 @@ static void __init fadump_init_files(void)
 	return;
 }
 
+static int __init fadump_setup_elfcorehdr_buf(void)
+{
+	int elf_phdr_cnt;
+	unsigned long elfcorehdr_size;
+
+	/*
+	 * Program header for CPU notes comes first, followed by one for
+	 * vmcoreinfo, and the remaining program headers correspond to
+	 * memory regions.
+	 */
+	elf_phdr_cnt = 2 + fw_dump.boot_mem_regs_cnt + memblock_num_regions(memory);
+	elfcorehdr_size = sizeof(struct elfhdr) + (elf_phdr_cnt * sizeof(struct elf_phdr));
+	elfcorehdr_size = PAGE_ALIGN(elfcorehdr_size);
+
+	fw_dump.elfcorehdr_addr = (u64)fadump_alloc_buffer(elfcorehdr_size);
+	if (!fw_dump.elfcorehdr_addr) {
+		pr_err("Failed to allocate %lu bytes for elfcorehdr\n",
+		       elfcorehdr_size);
+		return -ENOMEM;
+	}
+	fw_dump.elfcorehdr_size = elfcorehdr_size;
+	return 0;
+}
+
+/*
+ * Check if the fadump header of crashed kernel is compatible with fadump kernel.
+ *
+ * It checks the magic number, endianness, and size of non-primitive type
+ * members of fadump header to ensure safe dump collection.
+ */
+static bool __init is_fadump_header_compatible(struct fadump_crash_info_header *fdh)
+{
+	if (fdh->magic_number == FADUMP_CRASH_INFO_MAGIC_OLD) {
+		pr_err("Old magic number, can't process the dump.\n");
+		return false;
+	}
+
+	if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
+		if (fdh->magic_number == swab64(FADUMP_CRASH_INFO_MAGIC))
+			pr_err("Endianness mismatch between the crashed and fadump kernels.\n");
+		else
+			pr_err("Fadump header is corrupted.\n");
+
+		return false;
+	}
+
+	/*
+	 * Dump collection is not safe if the size of non-primitive type members
+	 * of the fadump header do not match between crashed and fadump kernel.
+	 */
+	if (fdh->pt_regs_sz != sizeof(struct pt_regs) ||
+	    fdh->cpu_mask_sz != sizeof(struct cpumask)) {
+		pr_err("Fadump header size mismatch.\n");
+		return false;
+	}
+
+	return true;
+}
+
+static void __init fadump_process(void)
+{
+	struct fadump_crash_info_header *fdh;
+
+	fdh = (struct fadump_crash_info_header *) __va(fw_dump.fadumphdr_addr);
+	if (!fdh) {
+		pr_err("Crash info header is empty.\n");
+		goto err_out;
+	}
+
+	/* Avoid processing the dump if fadump header isn't compatible */
+	if (!is_fadump_header_compatible(fdh))
+		goto err_out;
+
+	/* Allocate buffer for elfcorehdr */
+	if (fadump_setup_elfcorehdr_buf())
+		goto err_out;
+
+	fadump_populate_elfcorehdr(fdh);
+
+	/* Let platform update the CPU notes in elfcorehdr */
+	if (fw_dump.ops->fadump_process(&fw_dump) < 0)
+		goto err_out;
+
+	/*
+	 * elfcorehdr is now ready to be exported.
+	 *
+	 * set elfcorehdr_addr so that vmcore module will export the
+	 * elfcorehdr through '/proc/vmcore'.
+	 */
+	elfcorehdr_addr = virt_to_phys((void *)fw_dump.elfcorehdr_addr);
+	return;
+
+err_out:
+	fadump_invalidate_release_mem();
+}
+
+/*
+ * Reserve memory to store additional parameters to be passed
+ * for fadump/capture kernel.
+ */
+void __init fadump_setup_param_area(void)
+{
+	phys_addr_t range_start, range_end;
+
+	if (!fw_dump.fadump_enabled)
+		return;
+
+	if (!fw_dump.param_area_supported || fw_dump.dump_active)
+		return;
+
+	/* This memory can't be used by PFW or bootloader as it is shared across kernels */
+	if (early_radix_enabled()) {
+		/*
+		 * Anywhere in the upper half should be good enough as all memory
+		 * is accessible in real mode.
+		 */
+		range_start = memblock_end_of_DRAM() / 2;
+		range_end = memblock_end_of_DRAM();
+	} else {
+		/*
+		 * Memory range for passing additional parameters for HASH MMU
+		 * must meet the following conditions:
+		 * 1. The first memory block size must be higher than the
+		 *    minimum RMA (MIN_RMA) size. Bootloader can use memory
+		 *    upto RMA size. So it should be avoided.
+		 * 2. The range should be between MIN_RMA and RMA size (ppc64_rma_size)
+		 * 3. It must not overlap with the fadump reserved area.
+		 */
+		if (ppc64_rma_size < MIN_RMA*1024*1024)
+			return;
+
+		range_start = MIN_RMA * 1024 * 1024;
+		range_end = min(ppc64_rma_size, fw_dump.boot_mem_top);
+	}
+
+	fw_dump.param_area = memblock_phys_alloc_range(COMMAND_LINE_SIZE,
+						       COMMAND_LINE_SIZE,
+						       range_start,
+						       range_end);
+	if (!fw_dump.param_area) {
+		pr_warn("WARNING: Could not setup area to pass additional parameters!\n");
+		return;
+	}
+
+	memset((void *)fw_dump.param_area, 0, COMMAND_LINE_SIZE);
+}
+
 /*
  * Prepare for firmware-assisted dump.
  */
@@ -1650,12 +1809,7 @@ int __init setup_fadump(void)
 	 * saving it to the disk.
 	 */
 	if (fw_dump.dump_active) {
-		/*
-		 * if dump process fails then invalidate the registration
-		 * and release memory before proceeding for re-registration.
-		 */
-		if (fw_dump.ops->fadump_process(&fw_dump) < 0)
-			fadump_invalidate_release_mem();
+		fadump_process();
 	}
 	/* Initialize the kernel dump memory structure and register with f/w */
 	else if (fw_dump.reserve_dump_area_size) {
@@ -1734,8 +1888,3 @@ static void __init fadump_reserve_crash_area(u64 base)
 		memblock_reserve(mstart, msize);
 	}
 }
-
-unsigned long __init arch_reserved_kernel_pages(void)
-{
-	return memblock_reserved_size() / PAGE_SIZE;
-}
diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
index 20328f72f9f2..8987eee33dc8 100644
--- a/arch/powerpc/kernel/firmware.c
+++ b/arch/powerpc/kernel/firmware.c
@@ -23,6 +23,8 @@ EXPORT_SYMBOL_GPL(powerpc_firmware_features);
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST)
 DEFINE_STATIC_KEY_FALSE(kvm_guest);
+EXPORT_SYMBOL_GPL(kvm_guest);
+
 int __init check_kvm_guest(void)
 {
 	struct device_node *hyper_node;
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index f71f2bbd4de6..2f8f3f93cbb6 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -9,6 +9,7 @@
  *    Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
  */
 
+#include <linux/export.h>
 #include <asm/reg.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -18,11 +19,19 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
-#include <asm/export.h>
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
 #ifdef CONFIG_VSX
+#define __REST_1FPVSR(n,c,base)						\
+BEGIN_FTR_SECTION							\
+	b	2f;							\
+END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
+	REST_FPR(n,base);						\
+	b	3f;							\
+2:	REST_VSR(n,c,base);						\
+3:
+
 #define __REST_32FPVSRS(n,c,base)					\
 BEGIN_FTR_SECTION							\
 	b	2f;							\
@@ -41,9 +50,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 2:	SAVE_32VSRS(n,c,base);						\
 3:
 #else
+#define __REST_1FPVSR(n,b,base)		REST_FPR(n, base)
 #define __REST_32FPVSRS(n,b,base)	REST_32FPRS(n, base)
 #define __SAVE_32FPVSRS(n,b,base)	SAVE_32FPRS(n, base)
 #endif
+#define REST_1FPVSR(n,c,base)   __REST_1FPVSR(n,__REG_##c,__REG_##base)
 #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
 #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
 
@@ -67,6 +78,7 @@ _GLOBAL(store_fp_state)
 	SAVE_32FPVSRS(0, R4, R3)
 	mffs	fr0
 	stfd	fr0,FPSTATE_FPSCR(r3)
+	REST_1FPVSR(0, R4, R3)
 	blr
 EXPORT_SYMBOL(store_fp_state)
 
@@ -138,4 +150,5 @@ _GLOBAL(save_fpu)
 2:	SAVE_32FPVSRS(0, R4, R6)
 	mffs	fr0
 	stfd	fr0,FPSTATE_FPSCR(r6)
+	REST_1FPVSR(0, R4, R6)
 	blr
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index f8e2911478a7..9cba7dbf58dd 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -21,17 +21,9 @@
 	mtspr	SPRN_SPRG_SCRATCH1,r11
 	mfspr	r10, SPRN_SPRG_THREAD
 	.if	\handle_dar_dsisr
-#ifdef CONFIG_40x
-	mfspr	r11, SPRN_DEAR
-#else
 	mfspr	r11, SPRN_DAR
-#endif
 	stw	r11, DAR(r10)
-#ifdef CONFIG_40x
-	mfspr	r11, SPRN_ESR
-#else
 	mfspr	r11, SPRN_DSISR
-#endif
 	stw	r11, DSISR(r10)
 	.endif
 	mfspr	r11, SPRN_SRR0
@@ -96,9 +88,7 @@
 	.endif
 	lwz	r9, SRR1(r12)
 	lwz	r12, SRR0(r12)
-#ifdef CONFIG_40x
-	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
-#elif defined(CONFIG_PPC_8xx)
+#ifdef CONFIG_PPC_8xx
 	mtspr	SPRN_EID, r2		/* Set MSR_RI */
 #else
 	li	r10, MSR_KERNEL		/* can take exceptions */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
deleted file mode 100644
index 3f68a1624646..000000000000
--- a/arch/powerpc/kernel/head_40x.S
+++ /dev/null
@@ -1,721 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *    Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
- *      Initial PowerPC version.
- *    Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu>
- *      Rewritten for PReP
- *    Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
- *      Low-level exception handers, MMU support, and rewrite.
- *    Copyright (c) 1997 Dan Malek <dmalek@jlc.net>
- *      PowerPC 8xx modifications.
- *    Copyright (c) 1998-1999 TiVo, Inc.
- *      PowerPC 403GCX modifications.
- *    Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
- *      PowerPC 403GCX/405GP modifications.
- *    Copyright 2000 MontaVista Software Inc.
- *	PPC405 modifications
- *      PowerPC 403GCX/405GP modifications.
- * 	Author: MontaVista Software, Inc.
- *         	frank_rowand@mvista.com or source@mvista.com
- * 	   	debbie_chu@mvista.com
- *
- *    Module name: head_4xx.S
- *
- *    Description:
- *      Kernel execution entry point code.
- */
-
-#include <linux/init.h>
-#include <linux/pgtable.h>
-#include <linux/sizes.h>
-#include <linux/linkage.h>
-
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/mmu.h>
-#include <asm/cputable.h>
-#include <asm/thread_info.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/ptrace.h>
-#include <asm/export.h>
-
-#include "head_32.h"
-
-/* As with the other PowerPC ports, it is expected that when code
- * execution begins here, the following registers contain valid, yet
- * optional, information:
- *
- *   r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.)
- *   r4 - Starting address of the init RAM disk
- *   r5 - Ending address of the init RAM disk
- *   r6 - Start of kernel command line string (e.g. "mem=96m")
- *   r7 - End of kernel command line string
- *
- * This is all going to change RSN when we add bi_recs.......  -- Dan
- */
-	__HEAD
-_GLOBAL(_stext);
-_GLOBAL(_start);
-
-	mr	r31,r3			/* save device tree ptr */
-
-	/* We have to turn on the MMU right away so we get cache modes
-	 * set correctly.
-	 */
-	bl	initial_mmu
-
-/* We now have the lower 16 Meg mapped into TLB entries, and the caches
- * ready to work.
- */
-turn_on_mmu:
-	lis	r0,MSR_KERNEL@h
-	ori	r0,r0,MSR_KERNEL@l
-	mtspr	SPRN_SRR1,r0
-	lis	r0,start_here@h
-	ori	r0,r0,start_here@l
-	mtspr	SPRN_SRR0,r0
-	rfi				/* enables MMU */
-	b	.			/* prevent prefetch past rfi */
-
-/*
- * This area is used for temporarily saving registers during the
- * critical exception prolog.
- */
-	. = 0xc0
-crit_save:
-_GLOBAL(crit_r10)
-	.space	4
-_GLOBAL(crit_r11)
-	.space	4
-_GLOBAL(crit_srr0)
-	.space	4
-_GLOBAL(crit_srr1)
-	.space	4
-_GLOBAL(crit_r1)
-	.space	4
-_GLOBAL(crit_dear)
-	.space	4
-_GLOBAL(crit_esr)
-	.space	4
-
-/*
- * Exception prolog for critical exceptions.  This is a little different
- * from the normal exception prolog above since a critical exception
- * can potentially occur at any point during normal exception processing.
- * Thus we cannot use the same SPRG registers as the normal prolog above.
- * Instead we use a couple of words of memory at low physical addresses.
- * This is OK since we don't support SMP on these processors.
- */
-.macro CRITICAL_EXCEPTION_PROLOG trapno name
-	stw	r10,crit_r10@l(0)	/* save two registers to work with */
-	stw	r11,crit_r11@l(0)
-	mfspr	r10,SPRN_SRR0
-	mfspr	r11,SPRN_SRR1
-	stw	r10,crit_srr0@l(0)
-	stw	r11,crit_srr1@l(0)
-	mfspr	r10,SPRN_DEAR
-	mfspr	r11,SPRN_ESR
-	stw	r10,crit_dear@l(0)
-	stw	r11,crit_esr@l(0)
-	mfcr	r10			/* save CR in r10 for now	   */
-	mfspr	r11,SPRN_SRR3		/* check whether user or kernel    */
-	andi.	r11,r11,MSR_PR
-	lis	r11,(critirq_ctx-PAGE_OFFSET)@ha
-	lwz	r11,(critirq_ctx-PAGE_OFFSET)@l(r11)
-	beq	1f
-	/* COMING FROM USER MODE */
-	mfspr	r11,SPRN_SPRG_THREAD	/* if from user, start at top of   */
-	lwz	r11,TASK_STACK-THREAD(r11) /* this thread's kernel stack */
-1:	stw	r1,crit_r1@l(0)
-	addi	r1,r11,THREAD_SIZE-INT_FRAME_SIZE /* Alloc an excpt frm  */
-	LOAD_REG_IMMEDIATE(r11, MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)) /* re-enable MMU */
-	mtspr	SPRN_SRR1, r11
-	lis	r11, 1f@h
-	ori	r11, r11, 1f@l
-	mtspr	SPRN_SRR0, r11
-	rfi
-
-	.text
-1:
-\name\()_virt:
-	lwz	r11,crit_r1@l(0)
-	stw	r11,GPR1(r1)
-	stw	r11,0(r1)
-	mr	r11,r1
-	stw	r10,_CCR(r11)		/* save various registers	   */
-	stw	r12,GPR12(r11)
-	stw	r9,GPR9(r11)
-	mflr	r10
-	stw	r10,_LINK(r11)
-	lis	r9,PAGE_OFFSET@ha
-	lwz	r10,crit_r10@l(r9)
-	lwz	r12,crit_r11@l(r9)
-	stw	r10,GPR10(r11)
-	stw	r12,GPR11(r11)
-	lwz	r12,crit_dear@l(r9)
-	lwz	r9,crit_esr@l(r9)
-	stw	r12,_DEAR(r11)		/* since they may have had stuff   */
-	stw	r9,_ESR(r11)		/* exception was taken		   */
-	mfspr	r12,SPRN_SRR2
-	mfspr	r9,SPRN_SRR3
-	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?)	   */
-	COMMON_EXCEPTION_PROLOG_END \trapno + 2
-_ASM_NOKPROBE_SYMBOL(\name\()_virt)
-.endm
-
-	/*
-	 * State at this point:
-	 * r9 saved in stack frame, now saved SRR3 & ~MSR_WE
-	 * r10 saved in crit_r10 and in stack frame, trashed
-	 * r11 saved in crit_r11 and in stack frame,
-	 *	now phys stack/exception frame pointer
-	 * r12 saved in stack frame, now saved SRR2
-	 * CR saved in stack frame, CR0.EQ = !SRR3.PR
-	 * LR, DEAR, ESR in stack frame
-	 * r1 saved in stack frame, now virt stack/excframe pointer
-	 * r0, r3-r8 saved in stack frame
-	 */
-
-/*
- * Exception vectors.
- */
-#define CRITICAL_EXCEPTION(n, label, hdlr)			\
-	START_EXCEPTION(n, label);				\
-	CRITICAL_EXCEPTION_PROLOG n label;				\
-	prepare_transfer_to_handler;				\
-	bl	hdlr;						\
-	b	ret_from_crit_exc
-
-/*
- * 0x0100 - Critical Interrupt Exception
- */
-	CRITICAL_EXCEPTION(0x0100, CriticalInterrupt, unknown_exception)
-
-/*
- * 0x0200 - Machine Check Exception
- */
-	CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
-
-/*
- * 0x0300 - Data Storage Exception
- * This happens for just a few reasons.  U0 set (but we don't do that),
- * or zone protection fault (user violation, write to protected page).
- * The other Data TLB exceptions bail out to this point
- * if they can't resolve the lightweight TLB fault.
- */
-	START_EXCEPTION(0x0300,	DataStorage)
-	EXCEPTION_PROLOG 0x300 DataStorage handle_dar_dsisr=1
-	prepare_transfer_to_handler
-	bl	do_page_fault
-	b	interrupt_return
-
-/*
- * 0x0400 - Instruction Storage Exception
- * This is caused by a fetch from non-execute or guarded pages.
- */
-	START_EXCEPTION(0x0400, InstructionAccess)
-	EXCEPTION_PROLOG 0x400 InstructionAccess
-	li	r5,0
-	stw	r5, _ESR(r11)		/* Zero ESR */
-	stw	r12, _DEAR(r11)		/* SRR0 as DEAR */
-	prepare_transfer_to_handler
-	bl	do_page_fault
-	b	interrupt_return
-
-/* 0x0500 - External Interrupt Exception */
-	EXCEPTION(0x0500, HardwareInterrupt, do_IRQ)
-
-/* 0x0600 - Alignment Exception */
-	START_EXCEPTION(0x0600, Alignment)
-	EXCEPTION_PROLOG 0x600 Alignment handle_dar_dsisr=1
-	prepare_transfer_to_handler
-	bl	alignment_exception
-	REST_NVGPRS(r1)
-	b	interrupt_return
-
-/* 0x0700 - Program Exception */
-	START_EXCEPTION(0x0700, ProgramCheck)
-	EXCEPTION_PROLOG 0x700 ProgramCheck handle_dar_dsisr=1
-	prepare_transfer_to_handler
-	bl	program_check_exception
-	REST_NVGPRS(r1)
-	b	interrupt_return
-
-	EXCEPTION(0x0800, Trap_08, unknown_exception)
-	EXCEPTION(0x0900, Trap_09, unknown_exception)
-	EXCEPTION(0x0A00, Trap_0A, unknown_exception)
-	EXCEPTION(0x0B00, Trap_0B, unknown_exception)
-
-/* 0x0C00 - System Call Exception */
-	START_EXCEPTION(0x0C00,	SystemCall)
-	SYSCALL_ENTRY	0xc00
-/*	Trap_0D is commented out to get more space for system call exception */
-
-/*	EXCEPTION(0x0D00, Trap_0D, unknown_exception) */
-	EXCEPTION(0x0E00, Trap_0E, unknown_exception)
-	EXCEPTION(0x0F00, Trap_0F, unknown_exception)
-
-/* 0x1000 - Programmable Interval Timer (PIT) Exception */
-	START_EXCEPTION(0x1000, DecrementerTrap)
-	b Decrementer
-
-/* 0x1010 - Fixed Interval Timer (FIT) Exception */
-	START_EXCEPTION(0x1010, FITExceptionTrap)
-	b FITException
-
-/* 0x1020 - Watchdog Timer (WDT) Exception */
-	START_EXCEPTION(0x1020, WDTExceptionTrap)
-	b WDTException
-
-/* 0x1100 - Data TLB Miss Exception
- * As the name implies, translation is not in the MMU, so search the
- * page tables and fix it.  The only purpose of this function is to
- * load TLB entries from the page table if they exist.
- */
-	START_EXCEPTION(0x1100,	DTLBMiss)
-	mtspr	SPRN_SPRG_SCRATCH5, r10 /* Save some working registers */
-	mtspr	SPRN_SPRG_SCRATCH6, r11
-	mtspr	SPRN_SPRG_SCRATCH3, r12
-	mtspr	SPRN_SPRG_SCRATCH4, r9
-	mfcr	r12
-	mfspr	r9, SPRN_PID
-	rlwimi	r12, r9, 0, 0xff
-	mfspr	r10, SPRN_DEAR		/* Get faulting address */
-
-	/* If we are faulting a kernel address, we have to use the
-	 * kernel page tables.
-	 */
-	lis	r11, PAGE_OFFSET@h
-	cmplw	r10, r11
-	blt+	3f
-	lis	r11, swapper_pg_dir@h
-	ori	r11, r11, swapper_pg_dir@l
-	li	r9, 0
-	mtspr	SPRN_PID, r9		/* TLB will have 0 TID */
-	b	4f
-
-	/* Get the PGD for the current thread.
-	 */
-3:
-	mfspr	r11,SPRN_SPRG_THREAD
-	lwz	r11,PGDIR(r11)
-#ifdef CONFIG_PPC_KUAP
-	rlwinm.	r9, r9, 0, 0xff
-	beq	5f			/* Kuap fault */
-#endif
-4:
-	tophys(r11, r11)
-	rlwimi	r11, r10, 12, 20, 29	/* Create L1 (pgdir/pmd) address */
-	lwz	r11, 0(r11)		/* Get L1 entry */
-	andi.	r9, r11, _PMD_PRESENT	/* Check if it points to a PTE page */
-	beq	2f			/* Bail if no table */
-
-	rlwimi	r11, r10, 22, 20, 29	/* Compute PTE address */
-	lwz	r11, 0(r11)		/* Get Linux PTE */
-	li	r9, _PAGE_PRESENT | _PAGE_ACCESSED
-	andc.	r9, r9, r11		/* Check permission */
-	bne	5f
-
-	rlwinm	r9, r11, 1, _PAGE_RW	/* dirty => rw */
-	and	r9, r9, r11		/* hwwrite = dirty & rw */
-	rlwimi	r11, r9, 0, _PAGE_RW	/* replace rw by hwwrite */
-
-	/* Create TLB tag.  This is the faulting address plus a static
-	 * set of bits.  These are size, valid, E, U0.
-	*/
-	li	r9, 0x00c0
-	rlwimi	r10, r9, 0, 20, 31
-
-	b	finish_tlb_load
-
-2:	/* Check for possible large-page pmd entry */
-	rlwinm.	r9, r11, 2, 22, 24
-	beq	5f
-
-	/* Create TLB tag.  This is the faulting address, plus a static
-	 * set of bits (valid, E, U0) plus the size from the PMD.
-	 */
-	ori	r9, r9, 0x40
-	rlwimi	r10, r9, 0, 20, 31
-
-	b	finish_tlb_load
-
-5:
-	/* The bailout.  Restore registers to pre-exception conditions
-	 * and call the heavyweights to help us out.
-	 */
-	mtspr	SPRN_PID, r12
-	mtcrf	0x80, r12
-	mfspr	r9, SPRN_SPRG_SCRATCH4
-	mfspr	r12, SPRN_SPRG_SCRATCH3
-	mfspr	r11, SPRN_SPRG_SCRATCH6
-	mfspr	r10, SPRN_SPRG_SCRATCH5
-	b	DataStorage
-
-/* 0x1200 - Instruction TLB Miss Exception
- * Nearly the same as above, except we get our information from different
- * registers and bailout to a different point.
- */
-	START_EXCEPTION(0x1200,	ITLBMiss)
-	mtspr	SPRN_SPRG_SCRATCH5, r10	 /* Save some working registers */
-	mtspr	SPRN_SPRG_SCRATCH6, r11
-	mtspr	SPRN_SPRG_SCRATCH3, r12
-	mtspr	SPRN_SPRG_SCRATCH4, r9
-	mfcr	r12
-	mfspr	r9, SPRN_PID
-	rlwimi	r12, r9, 0, 0xff
-	mfspr	r10, SPRN_SRR0		/* Get faulting address */
-
-	/* If we are faulting a kernel address, we have to use the
-	 * kernel page tables.
-	 */
-	lis	r11, PAGE_OFFSET@h
-	cmplw	r10, r11
-	blt+	3f
-	lis	r11, swapper_pg_dir@h
-	ori	r11, r11, swapper_pg_dir@l
-	li	r9, 0
-	mtspr	SPRN_PID, r9		/* TLB will have 0 TID */
-	b	4f
-
-	/* Get the PGD for the current thread.
-	 */
-3:
-	mfspr	r11,SPRN_SPRG_THREAD
-	lwz	r11,PGDIR(r11)
-#ifdef CONFIG_PPC_KUAP
-	rlwinm.	r9, r9, 0, 0xff
-	beq	5f			/* Kuap fault */
-#endif
-4:
-	tophys(r11, r11)
-	rlwimi	r11, r10, 12, 20, 29	/* Create L1 (pgdir/pmd) address */
-	lwz	r11, 0(r11)		/* Get L1 entry */
-	andi.	r9, r11, _PMD_PRESENT	/* Check if it points to a PTE page */
-	beq	2f			/* Bail if no table */
-
-	rlwimi	r11, r10, 22, 20, 29	/* Compute PTE address */
-	lwz	r11, 0(r11)		/* Get Linux PTE */
-	li	r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-	andc.	r9, r9, r11		/* Check permission */
-	bne	5f
-
-	rlwinm	r9, r11, 1, _PAGE_RW	/* dirty => rw */
-	and	r9, r9, r11		/* hwwrite = dirty & rw */
-	rlwimi	r11, r9, 0, _PAGE_RW	/* replace rw by hwwrite */
-
-	/* Create TLB tag.  This is the faulting address plus a static
-	 * set of bits.  These are size, valid, E, U0.
-	*/
-	li	r9, 0x00c0
-	rlwimi	r10, r9, 0, 20, 31
-
-	b	finish_tlb_load
-
-2:	/* Check for possible large-page pmd entry */
-	rlwinm.	r9, r11, 2, 22, 24
-	beq	5f
-
-	/* Create TLB tag.  This is the faulting address, plus a static
-	 * set of bits (valid, E, U0) plus the size from the PMD.
-	 */
-	ori	r9, r9, 0x40
-	rlwimi	r10, r9, 0, 20, 31
-
-	b	finish_tlb_load
-
-5:
-	/* The bailout.  Restore registers to pre-exception conditions
-	 * and call the heavyweights to help us out.
-	 */
-	mtspr	SPRN_PID, r12
-	mtcrf	0x80, r12
-	mfspr	r9, SPRN_SPRG_SCRATCH4
-	mfspr	r12, SPRN_SPRG_SCRATCH3
-	mfspr	r11, SPRN_SPRG_SCRATCH6
-	mfspr	r10, SPRN_SPRG_SCRATCH5
-	b	InstructionAccess
-
-	EXCEPTION(0x1300, Trap_13, unknown_exception)
-	EXCEPTION(0x1400, Trap_14, unknown_exception)
-	EXCEPTION(0x1500, Trap_15, unknown_exception)
-	EXCEPTION(0x1600, Trap_16, unknown_exception)
-	EXCEPTION(0x1700, Trap_17, unknown_exception)
-	EXCEPTION(0x1800, Trap_18, unknown_exception)
-	EXCEPTION(0x1900, Trap_19, unknown_exception)
-	EXCEPTION(0x1A00, Trap_1A, unknown_exception)
-	EXCEPTION(0x1B00, Trap_1B, unknown_exception)
-	EXCEPTION(0x1C00, Trap_1C, unknown_exception)
-	EXCEPTION(0x1D00, Trap_1D, unknown_exception)
-	EXCEPTION(0x1E00, Trap_1E, unknown_exception)
-	EXCEPTION(0x1F00, Trap_1F, unknown_exception)
-
-/* Check for a single step debug exception while in an exception
- * handler before state has been saved.  This is to catch the case
- * where an instruction that we are trying to single step causes
- * an exception (eg ITLB/DTLB miss) and thus the first instruction of
- * the exception handler generates a single step debug exception.
- *
- * If we get a debug trap on the first instruction of an exception handler,
- * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is
- * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR).
- * The exception handler was handling a non-critical interrupt, so it will
- * save (and later restore) the MSR via SPRN_SRR1, which will still have
- * the MSR_DE bit set.
- */
-	/* 0x2000 - Debug Exception */
-	START_EXCEPTION(0x2000, DebugTrap)
-	CRITICAL_EXCEPTION_PROLOG 0x2000 DebugTrap
-
-	/*
-	 * If this is a single step or branch-taken exception in an
-	 * exception entry sequence, it was probably meant to apply to
-	 * the code where the exception occurred (since exception entry
-	 * doesn't turn off DE automatically).  We simulate the effect
-	 * of turning off DE on entry to an exception handler by turning
-	 * off DE in the SRR3 value and clearing the debug status.
-	 */
-	mfspr	r10,SPRN_DBSR		/* check single-step/branch taken */
-	andis.	r10,r10,DBSR_IC@h
-	beq+	2f
-
-	andi.	r10,r9,MSR_IR|MSR_PR	/* check supervisor + MMU off */
-	beq	1f			/* branch and fix it up */
-
-	mfspr   r10,SPRN_SRR2		/* Faulting instruction address */
-	cmplwi  r10,0x2100
-	bgt+    2f			/* address above exception vectors */
-
-	/* here it looks like we got an inappropriate debug exception. */
-1:	rlwinm	r9,r9,0,~MSR_DE		/* clear DE in the SRR3 value */
-	lis	r10,DBSR_IC@h		/* clear the IC event */
-	mtspr	SPRN_DBSR,r10
-	/* restore state and get out */
-	lwz	r10,_CCR(r11)
-	lwz	r0,GPR0(r11)
-	lwz	r1,GPR1(r11)
-	mtcrf	0x80,r10
-	mtspr	SPRN_SRR2,r12
-	mtspr	SPRN_SRR3,r9
-	lwz	r9,GPR9(r11)
-	lwz	r12,GPR12(r11)
-	lwz	r10,crit_r10@l(0)
-	lwz	r11,crit_r11@l(0)
-	rfci
-	b	.
-
-	/* continue normal handling for a critical exception... */
-2:	mfspr	r4,SPRN_DBSR
-	stw	r4,_ESR(r11)		/* DebugException takes DBSR in _ESR */
-	prepare_transfer_to_handler
-	bl	DebugException
-	b	ret_from_crit_exc
-
-	/* Programmable Interval Timer (PIT) Exception. (from 0x1000) */
-	__HEAD
-Decrementer:
-	EXCEPTION_PROLOG 0x1000 Decrementer
-	lis	r0,TSR_PIS@h
-	mtspr	SPRN_TSR,r0		/* Clear the PIT exception */
-	prepare_transfer_to_handler
-	bl	timer_interrupt
-	b	interrupt_return
-
-	/* Fixed Interval Timer (FIT) Exception. (from 0x1010) */
-	__HEAD
-FITException:
-	EXCEPTION_PROLOG 0x1010 FITException
-	prepare_transfer_to_handler
-	bl	unknown_exception
-	b	interrupt_return
-
-	/* Watchdog Timer (WDT) Exception. (from 0x1020) */
-	__HEAD
-WDTException:
-	CRITICAL_EXCEPTION_PROLOG 0x1020 WDTException
-	prepare_transfer_to_handler
-	bl	WatchdogException
-	b	ret_from_crit_exc
-
-/* Other PowerPC processors, namely those derived from the 6xx-series
- * have vectors from 0x2100 through 0x2F00 defined, but marked as reserved.
- * However, for the 4xx-series processors these are neither defined nor
- * reserved.
- */
-
-	__HEAD
-	/* Damn, I came up one instruction too many to fit into the
-	 * exception space :-).  Both the instruction and data TLB
-	 * miss get to this point to load the TLB.
-	 * 	r10 - TLB_TAG value
-	 * 	r11 - Linux PTE
-	 *	r9 - available to use
-	 *	PID - loaded with proper value when we get here
-	 *	Upon exit, we reload everything and RFI.
-	 * Actually, it will fit now, but oh well.....a common place
-	 * to load the TLB.
-	 */
-tlb_4xx_index:
-	.long	0
-finish_tlb_load:
-	/*
-	 * Clear out the software-only bits in the PTE to generate the
-	 * TLB_DATA value.  These are the bottom 2 bits of the RPM, the
-	 * top 3 bits of the zone field, and M.
-	 */
-	li	r9, 0x0ce2
-	andc	r11, r11, r9
-
-	/* load the next available TLB index. */
-	lwz	r9, tlb_4xx_index@l(0)
-	addi	r9, r9, 1
-	andi.	r9, r9, PPC40X_TLB_SIZE - 1
-	stw	r9, tlb_4xx_index@l(0)
-
-	tlbwe	r11, r9, TLB_DATA		/* Load TLB LO */
-	tlbwe	r10, r9, TLB_TAG		/* Load TLB HI */
-
-	/* Done...restore registers and get out of here.
-	*/
-	mtspr	SPRN_PID, r12
-	mtcrf	0x80, r12
-	mfspr	r9, SPRN_SPRG_SCRATCH4
-	mfspr	r12, SPRN_SPRG_SCRATCH3
-	mfspr	r11, SPRN_SPRG_SCRATCH6
-	mfspr	r10, SPRN_SPRG_SCRATCH5
-	rfi			/* Should sync shadow TLBs */
-	b	.		/* prevent prefetch past rfi */
-
-/* This is where the main kernel code starts.
- */
-start_here:
-
-	/* ptr to current */
-	lis	r2,init_task@h
-	ori	r2,r2,init_task@l
-
-	/* ptr to phys current thread */
-	tophys(r4,r2)
-	addi	r4,r4,THREAD	/* init task's THREAD */
-	mtspr	SPRN_SPRG_THREAD,r4
-
-	/* stack */
-	lis	r1,init_thread_union@ha
-	addi	r1,r1,init_thread_union@l
-	li	r0,0
-	stwu	r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
-
-	bl	early_init	/* We have to do this with MMU on */
-
-/*
- * Decide what sort of machine this is and initialize the MMU.
- */
-#ifdef CONFIG_KASAN
-	bl	kasan_early_init
-#endif
-	li	r3,0
-	mr	r4,r31
-	bl	machine_init
-	bl	MMU_init
-
-/* Go back to running unmapped so we can load up new values
- * and change to using our exception vectors.
- * On the 4xx, all we have to do is invalidate the TLB to clear
- * the old 16M byte TLB mappings.
- */
-	lis	r4,2f@h
-	ori	r4,r4,2f@l
-	tophys(r4,r4)
-	lis	r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@h
-	ori	r3,r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@l
-	mtspr	SPRN_SRR0,r4
-	mtspr	SPRN_SRR1,r3
-	rfi
-	b	.		/* prevent prefetch past rfi */
-
-/* Load up the kernel context */
-2:
-	sync			/* Flush to memory before changing TLB */
-	tlbia
-	isync			/* Flush shadow TLBs */
-
-	/* set up the PTE pointers for the Abatron bdiGDB.
-	*/
-	lis	r6, swapper_pg_dir@h
-	ori	r6, r6, swapper_pg_dir@l
-	lis	r5, abatron_pteptrs@h
-	ori	r5, r5, abatron_pteptrs@l
-	stw	r5, 0xf0(0)	/* Must match your Abatron config file */
-	tophys(r5,r5)
-	stw	r6, 0(r5)
-
-/* Now turn on the MMU for real! */
-	lis	r4,MSR_KERNEL@h
-	ori	r4,r4,MSR_KERNEL@l
-	lis	r3,start_kernel@h
-	ori	r3,r3,start_kernel@l
-	mtspr	SPRN_SRR0,r3
-	mtspr	SPRN_SRR1,r4
-	rfi			/* enable MMU and jump to start_kernel */
-	b	.		/* prevent prefetch past rfi */
-
-/* Set up the initial MMU state so we can do the first level of
- * kernel initialization.  This maps the first 32 MBytes of memory 1:1
- * virtual to physical and more importantly sets the cache mode.
- */
-SYM_FUNC_START_LOCAL(initial_mmu)
-	tlbia			/* Invalidate all TLB entries */
-	isync
-
-	/* We should still be executing code at physical address 0x0000xxxx
-	 * at this point. However, start_here is at virtual address
-	 * 0xC000xxxx. So, set up a TLB mapping to cover this once
-	 * translation is enabled.
-	 */
-
-	lis	r3,KERNELBASE@h		/* Load the kernel virtual address */
-	ori	r3,r3,KERNELBASE@l
-	tophys(r4,r3)			/* Load the kernel physical address */
-
-	iccci	r0,r3			/* Invalidate the i-cache before use */
-
-	/* Load the kernel PID.
-	*/
-	li	r0,0
-	mtspr	SPRN_PID,r0
-	sync
-
-	/* Configure and load one entry into TLB slots 63 */
-	clrrwi	r4,r4,10		/* Mask off the real page number */
-	ori	r4,r4,(TLB_WR | TLB_EX)	/* Set the write and execute bits */
-
-	clrrwi	r3,r3,10		/* Mask off the effective page number */
-	ori	r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_16M))
-
-        li      r0,63                    /* TLB slot 63 */
-
-	tlbwe	r4,r0,TLB_DATA		/* Load the data portion of the entry */
-	tlbwe	r3,r0,TLB_TAG		/* Load the tag portion of the entry */
-
-	li	r0,62			/* TLB slot 62 */
-	addis	r4,r4,SZ_16M@h
-	addis	r3,r3,SZ_16M@h
-	tlbwe	r4,r0,TLB_DATA		/* Load the data portion of the entry */
-	tlbwe	r3,r0,TLB_TAG		/* Load the tag portion of the entry */
-
-	isync
-
-	/* Establish the exception vector base
-	*/
-	lis	r4,KERNELBASE@h		/* EVPR only uses the high 16-bits */
-	tophys(r0,r4)			/* Use the physical address */
-	mtspr	SPRN_EVPR,r0
-
-	blr
-SYM_FUNC_END(initial_mmu)
-
-_GLOBAL(abort)
-        mfspr   r13,SPRN_DBCR0
-        oris    r13,r13,DBCR0_RST_SYSTEM@h
-        mtspr   SPRN_DBCR0,r13
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 63a85c16fef4..25642e802ed3 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -35,7 +35,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 #include <asm/synch.h>
-#include <asm/export.h>
 #include <asm/code-patching-asm.h>
 #include "head_booke.h"
 
@@ -315,8 +314,8 @@ interrupt_base:
 	 * kernel page tables.
 	 */
 	lis	r11, PAGE_OFFSET@h
-	cmplw	r10, r11
-	blt+	3f
+	cmplw	cr7, r10, r11
+	blt+	cr7, 3f
 	lis	r11, swapper_pg_dir@h
 	ori	r11, r11, swapper_pg_dir@l
 
@@ -343,7 +342,7 @@ interrupt_base:
 	mtspr	SPRN_MMUCR,r12
 
 	/* Mask of required permission bits. Note that while we
-	 * do copy ESR:ST to _PAGE_RW position as trying to write
+	 * do copy ESR:ST to _PAGE_WRITE position as trying to write
 	 * to an RO page is pretty common, we don't do it with
 	 * _PAGE_DIRTY. We could do it, but it's a fairly rare
 	 * event so I'd rather take the overhead when it happens
@@ -356,7 +355,7 @@ interrupt_base:
 	 *       place or can we save a couple of instructions here ?
 	 */
 	mfspr	r12,SPRN_ESR
-	li	r13,_PAGE_PRESENT|_PAGE_ACCESSED
+	li	r13,_PAGE_PRESENT|_PAGE_ACCESSED|_PAGE_READ
 	rlwimi	r13,r12,10,30,30
 
 	/* Load the PTE */
@@ -429,8 +428,8 @@ interrupt_base:
 	 * kernel page tables.
 	 */
 	lis	r11, PAGE_OFFSET@h
-	cmplw	r10, r11
-	blt+	3f
+	cmplw	cr7, r10, r11
+	blt+	cr7, 3f
 	lis	r11, swapper_pg_dir@h
 	ori	r11, r11, swapper_pg_dir@l
 
@@ -516,6 +515,7 @@ interrupt_base:
  * 	r11 - PTE high word value
  *	r12 - PTE low word value
  *	r13 - TLB index
+ *	cr7 - Result of comparison with PAGE_OFFSET
  *	MMUCR - loaded with proper value when we get here
  *	Upon exit, we reload everything and RFI.
  */
@@ -534,11 +534,10 @@ finish_tlb_load_44x:
 	tlbwe	r10,r13,PPC44x_TLB_PAGEID	/* Write PAGEID */
 
 	/* And WS 2 */
-	li	r10,0xf85			/* Mask to apply from PTE */
-	rlwimi	r10,r12,29,30,30		/* DIRTY -> SW position */
+	li	r10,0xf84			/* Mask to apply from PTE */
+	rlwimi	r10,r12,29,30,31		/* DIRTY,READ -> SW,SR position */
 	and	r11,r12,r10			/* Mask PTE bits to keep */
-	andi.	r10,r12,_PAGE_USER		/* User page ? */
-	beq	1f				/* nope, leave U bits empty */
+	bge	cr7,1f			/* User page ? no, leave U bits empty */
 	rlwimi	r11,r11,3,26,28			/* yes, copy S bits to U */
 	rlwinm	r11,r11,0,~PPC44x_TLB_SX	/* Clear SX if User page */
 1:	tlbwe	r11,r13,PPC44x_TLB_ATTRIB	/* Write ATTRIB */
@@ -569,8 +568,8 @@ finish_tlb_load_44x:
 	 * kernel page tables.
 	 */
 	lis	r11,PAGE_OFFSET@h
-	cmplw	cr0,r10,r11
-	blt+	3f
+	cmplw	cr7,r10,r11
+	blt+	cr7,3f
 	lis	r11,swapper_pg_dir@h
 	ori	r11,r11, swapper_pg_dir@l
 	li	r12,0			/* MMUCR = 0 */
@@ -587,7 +586,7 @@ finish_tlb_load_44x:
 4:	mtspr	SPRN_MMUCR,r12		/* Set MMUCR */
 
 	/* Mask of required permission bits. Note that while we
-	 * do copy ESR:ST to _PAGE_RW position as trying to write
+	 * do copy ESR:ST to _PAGE_WRITE position as trying to write
 	 * to an RO page is pretty common, we don't do it with
 	 * _PAGE_DIRTY. We could do it, but it's a fairly rare
 	 * event so I'd rather take the overhead when it happens
@@ -600,7 +599,7 @@ finish_tlb_load_44x:
 	 *       place or can we save a couple of instructions here ?
 	 */
 	mfspr	r12,SPRN_ESR
-	li	r13,_PAGE_PRESENT|_PAGE_ACCESSED
+	li	r13,_PAGE_PRESENT|_PAGE_ACCESSED|_PAGE_READ
 	rlwimi	r13,r12,10,30,30
 
 	/* Load the PTE */
@@ -670,8 +669,8 @@ finish_tlb_load_44x:
 	 * kernel page tables.
 	 */
 	lis	r11,PAGE_OFFSET@h
-	cmplw	cr0,r10,r11
-	blt+	3f
+	cmplw	cr7,r10,r11
+	blt+	cr7,3f
 	lis	r11,swapper_pg_dir@h
 	ori	r11,r11, swapper_pg_dir@l
 	li	r12,0			/* MMUCR = 0 */
@@ -745,6 +744,7 @@ finish_tlb_load_44x:
  * 	r11 - PTE high word value
  *	r12 - PTE low word value
  *      r13 - free to use
+ *	cr7 - Result of comparison with PAGE_OFFSET
  *	MMUCR - loaded with proper value when we get here
  *	Upon exit, we reload everything and RFI.
  */
@@ -754,11 +754,10 @@ finish_tlb_load_47x:
 	tlbwe	r11,r13,1
 
 	/* And make up word 2 */
-	li	r10,0xf85			/* Mask to apply from PTE */
-	rlwimi	r10,r12,29,30,30		/* DIRTY -> SW position */
+	li	r10,0xf84			/* Mask to apply from PTE */
+	rlwimi	r10,r12,29,30,31		/* DIRTY,READ -> SW,SR position */
 	and	r11,r12,r10			/* Mask PTE bits to keep */
-	andi.	r10,r12,_PAGE_USER		/* User page ? */
-	beq	1f				/* nope, leave U bits empty */
+	bge	cr7,1f			/* User page ? no, leave U bits empty */
 	rlwimi	r11,r11,3,26,28			/* yes, copy S bits to U */
 	rlwinm	r11,r11,0,~PPC47x_TLB2_SX	/* Clear SX if User page */
 1:	tlbwe	r11,r13,2
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index f132d8704263..63432a33ec49 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -40,7 +40,6 @@
 #include <asm/hw_irq.h>
 #include <asm/cputhreads.h>
 #include <asm/ppc-opcode.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 #ifdef CONFIG_PPC_BOOK3S
 #include <asm/exception-64s.h>
@@ -375,8 +374,7 @@ _GLOBAL(generic_secondary_smp_init)
 	beq	20f
 
 	/* start the specified thread */
-	LOAD_REG_ADDR(r5, fsl_secondary_thread_init)
-	ld	r4, 0(r5)
+	LOAD_REG_ADDR(r5, DOTSYM(fsl_secondary_thread_init))
 	bl	book3e_start_thread
 
 	/* stop the current thread */
@@ -649,8 +647,9 @@ __after_prom_start:
  * Note: This process overwrites the OF exception vectors.
  */
 	LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET)
-	mr.	r4,r26			/* In some cases the loader may  */
-	beq	9f			/* have already put us at zero */
+	mr	r4,r26			/* Load the virtual source address into r4 */
+	cmpld	r3,r4			/* Check if source == dest */
+	beq	9f			/* If so skip the copy  */
 	li	r6,0x100		/* Start offset, the first 0x100 */
 					/* bytes were copied earlier.	 */
 
diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S
index fdbee1093e2b..f9a73fae6464 100644
--- a/arch/powerpc/kernel/head_85xx.S
+++ b/arch/powerpc/kernel/head_85xx.S
@@ -40,7 +40,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
 #include <asm/ptrace.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 #include "head_booke.h"
 
@@ -295,9 +294,10 @@ set_ivor:
 /* Macros to hide the PTE size differences
  *
  * FIND_PTE -- walks the page tables given EA & pgdir pointer
- *   r10 -- EA of fault
+ *   r10 -- free
  *   r11 -- PGDIR pointer
  *   r12 -- free
+ *   r13 -- EA of fault
  *   label 2: is the bailout case
  *
  * if we find the pte (fall through):
@@ -308,34 +308,34 @@ set_ivor:
 #ifdef CONFIG_PTE_64BIT
 #ifdef CONFIG_HUGETLB_PAGE
 #define FIND_PTE	\
-	rlwinm	r12, r10, 13, 19, 29;	/* Compute pgdir/pmd offset */	\
-	lwzx	r11, r12, r11;		/* Get pgd/pmd entry */		\
+	rlwinm	r12, r13, 14, 18, 28;	/* Compute pgdir/pmd offset */	\
+	add	r12, r11, r12;						\
+	lwz	r11, 4(r12);		/* Get pgd/pmd entry */		\
+	rlwinm.	r10, r11, 32 - _PAGE_PSIZE_SHIFT, 0x1e; /* get tsize*/	\
+	bne	1000f;			/* Huge page (leaf entry) */	\
 	rlwinm.	r12, r11, 0, 0, 20;	/* Extract pt base address */	\
-	blt	1000f;			/* Normal non-huge page */	\
 	beq	2f;			/* Bail if no table */		\
-	oris	r11, r11, PD_HUGE@h;	/* Put back address bit */	\
-	andi.	r10, r11, HUGEPD_SHIFT_MASK@l; /* extract size field */	\
-	xor	r12, r10, r11;		/* drop size bits from pointer */ \
-	b	1001f;							\
-1000:	rlwimi	r12, r10, 23, 20, 28;	/* Compute pte address */	\
+	rlwimi	r12, r13, 23, 20, 28;	/* Compute pte address */	\
 	li	r10, 0;			/* clear r10 */			\
-1001:	lwz	r11, 4(r12);		/* Get pte entry */
+	lwz	r11, 4(r12);		/* Get pte entry */		\
+1000:
 #else
 #define FIND_PTE	\
-	rlwinm	r12, r10, 13, 19, 29;	/* Compute pgdir/pmd offset */	\
-	lwzx	r11, r12, r11;		/* Get pgd/pmd entry */		\
+	rlwinm	r12, r13, 14, 18, 28;	/* Compute pgdir/pmd offset */	\
+	add	r12, r11, r12;						\
+	lwz	r11, 4(r12);		/* Get pgd/pmd entry */		\
 	rlwinm.	r12, r11, 0, 0, 20;	/* Extract pt base address */	\
 	beq	2f;			/* Bail if no table */		\
-	rlwimi	r12, r10, 23, 20, 28;	/* Compute pte address */	\
+	rlwimi	r12, r13, 23, 20, 28;	/* Compute pte address */	\
 	lwz	r11, 4(r12);		/* Get pte entry */
 #endif /* HUGEPAGE */
 #else /* !PTE_64BIT */
 #define FIND_PTE	\
-	rlwimi	r11, r10, 12, 20, 29;	/* Create L1 (pgdir/pmd) address */	\
+	rlwimi	r11, r13, 12, 20, 29;	/* Create L1 (pgdir/pmd) address */	\
 	lwz	r11, 0(r11);		/* Get L1 entry */			\
 	rlwinm.	r12, r11, 0, 0, 19;	/* Extract L2 (pte) base address */	\
 	beq	2f;			/* Bail if no table */			\
-	rlwimi	r12, r10, 22, 20, 29;	/* Compute PTE address */		\
+	rlwimi	r12, r13, 22, 20, 29;	/* Compute PTE address */		\
 	lwz	r11, 0(r12);		/* Get Linux PTE */
 #endif
 
@@ -396,7 +396,7 @@ interrupt_base:
 #ifdef CONFIG_PPC_FPU
 	FP_UNAVAILABLE_EXCEPTION
 #else
-	EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, unknown_exception)
+	EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, emulation_assist_interrupt)
 #endif
 
 	/* System Call Interrupt */
@@ -442,13 +442,13 @@ START_BTB_FLUSH_SECTION
 	BTB_FLUSH(r10)
 1:
 END_BTB_FLUSH_SECTION
-	mfspr	r10, SPRN_DEAR		/* Get faulting address */
+	mfspr	r13, SPRN_DEAR		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
 	lis	r11, PAGE_OFFSET@h
-	cmplw	5, r10, r11
+	cmplw	5, r13, r11
 	blt	5, 3f
 	lis	r11, swapper_pg_dir@h
 	ori	r11, r11, swapper_pg_dir@l
@@ -471,29 +471,14 @@ END_BTB_FLUSH_SECTION
 #endif
 
 4:
-	/* Mask of required permission bits. Note that while we
-	 * do copy ESR:ST to _PAGE_RW position as trying to write
-	 * to an RO page is pretty common, we don't do it with
-	 * _PAGE_DIRTY. We could do it, but it's a fairly rare
-	 * event so I'd rather take the overhead when it happens
-	 * rather than adding an instruction here. We should measure
-	 * whether the whole thing is worth it in the first place
-	 * as we could avoid loading SPRN_ESR completely in the first
-	 * place...
-	 *
-	 * TODO: Is it worth doing that mfspr & rlwimi in the first
-	 *       place or can we save a couple of instructions here ?
-	 */
-	mfspr	r12,SPRN_ESR
+	FIND_PTE
+
 #ifdef CONFIG_PTE_64BIT
-	li	r13,_PAGE_PRESENT
+	li	r13,_PAGE_PRESENT|_PAGE_BAP_SR
 	oris	r13,r13,_PAGE_ACCESSED@h
 #else
-	li	r13,_PAGE_PRESENT|_PAGE_ACCESSED
+	li	r13,_PAGE_PRESENT|_PAGE_READ|_PAGE_ACCESSED
 #endif
-	rlwimi	r13,r12,11,29,29
-
-	FIND_PTE
 	andc.	r13,r13,r11		/* Check permission */
 
 #ifdef CONFIG_PTE_64BIT
@@ -550,13 +535,13 @@ START_BTB_FLUSH_SECTION
 1:
 END_BTB_FLUSH_SECTION
 
-	mfspr	r10, SPRN_SRR0		/* Get faulting address */
+	mfspr	r13, SPRN_SRR0		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
 	lis	r11, PAGE_OFFSET@h
-	cmplw	5, r10, r11
+	cmplw	5, r13, r11
 	blt	5, 3f
 	lis	r11, swapper_pg_dir@h
 	ori	r11, r11, swapper_pg_dir@l
@@ -565,6 +550,7 @@ END_BTB_FLUSH_SECTION
 	rlwinm	r12,r12,0,16,1
 	mtspr	SPRN_MAS1,r12
 
+	FIND_PTE
 	/* Make up the required permissions for kernel code */
 #ifdef CONFIG_PTE_64BIT
 	li	r13,_PAGE_PRESENT | _PAGE_BAP_SX
@@ -585,6 +571,7 @@ END_BTB_FLUSH_SECTION
 	beq	2f			/* KUAP fault */
 #endif
 
+	FIND_PTE
 	/* Make up the required permissions for user code */
 #ifdef CONFIG_PTE_64BIT
 	li	r13,_PAGE_PRESENT | _PAGE_BAP_UX
@@ -594,7 +581,6 @@ END_BTB_FLUSH_SECTION
 #endif
 
 4:
-	FIND_PTE
 	andc.	r13,r13,r11		/* Check permission */
 
 #ifdef CONFIG_PTE_64BIT
@@ -747,17 +733,12 @@ finish_tlb_load:
 	lwz	r15, 0(r14)
 100:	stw	r15, 0(r17)
 
-	/*
-	 * Calc MAS1_TSIZE from r10 (which has pshift encoded)
-	 * tlb_enc = (pshift - 10).
-	 */
-	subi	r15, r10, 10
 	mfspr	r16, SPRN_MAS1
-	rlwimi	r16, r15, 7, 20, 24
+	rlwimi	r16, r10, MAS1_TSIZE_SHIFT, MAS1_TSIZE_MASK
 	mtspr	SPRN_MAS1, r16
 
 	/* copy the pshift for use later */
-	mr	r14, r10
+	addi	r14, r10, _PAGE_PSIZE_SHIFT_OFFSET
 
 	/* fall through */
 
@@ -784,15 +765,15 @@ BEGIN_MMU_FTR_SECTION
 	mtspr	SPRN_MAS7, r10
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
 #else
-	li	r10, (_PAGE_EXEC | _PAGE_PRESENT)
+	li	r10, (_PAGE_EXEC | _PAGE_READ)
 	mr	r13, r11
 	rlwimi	r10, r11, 31, 29, 29	/* extract _PAGE_DIRTY into SW */
 	and	r12, r11, r10
-	andi.	r10, r11, _PAGE_USER	/* Test for _PAGE_USER */
+	mcrf	cr0, cr5		/* Test for user page */
 	slwi	r10, r12, 1
 	or	r10, r10, r12
 	rlwinm	r10, r10, 0, ~_PAGE_EXEC	/* Clear SX on user pages */
-	iseleq	r12, r12, r10
+	isellt	r12, r10, r12
 	rlwimi	r13, r12, 0, 20, 31	/* Get RPN from PTE, merge w/ perms */
 	mtspr	SPRN_MAS3, r13
 #endif
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index a79751e05781..393e19ee1322 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -29,7 +29,6 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
-#include <asm/export.h>
 #include <asm/code-patching-asm.h>
 #include <asm/interrupt.h>
 
@@ -41,16 +40,6 @@
 
 #include "head_32.h"
 
-.macro compare_to_kernel_boundary scratch, addr
-#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
-/* By simply checking Address >= 0x80000000, we know if its a kernel address */
-	not.	\scratch, \addr
-#else
-	rlwinm	\scratch, \addr, 16, 0xfff8
-	cmpli	cr0, \scratch, PAGE_OFFSET@h
-#endif
-.endm
-
 #define PAGE_SHIFT_512K		19
 #define PAGE_SHIFT_8M		23
 
@@ -173,7 +162,7 @@ instruction_counter:
  * For the MPC8xx, this is a software tablewalk to load the instruction
  * TLB.  The task switch loads the M_TWB register with the pointer to the first
  * level table.
- * If we discover there is no second level table (value is zero) or if there
+ * If there is no second level table (value is zero) or if there
  * is an invalid pte, we load that into the TLB, which causes another fault
  * into the TLB Error interrupt where we can handle such problems.
  * We have to use the MD_xxx registers for the tablewalk because the
@@ -194,25 +183,11 @@ instruction_counter:
 	mtspr	SPRN_SPRG_SCRATCH2, r10
 	mtspr	SPRN_M_TW, r11
 
-	/* If we are faulting a kernel address, we have to use the
-	 * kernel page tables.
-	 */
 	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
 	INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11)
 	mtspr	SPRN_MD_EPN, r10
-#ifdef CONFIG_MODULES
-	mfcr	r11
-	compare_to_kernel_boundary r10, r10
-#endif
 	mfspr	r10, SPRN_M_TWB	/* Get level 1 table */
-#ifdef CONFIG_MODULES
-	blt+	3f
-	rlwinm	r10, r10, 0, 20, 31
-	oris	r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
-3:
-	mtcr	r11
-#endif
-	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
+	lwz	r11, 0(r10)	/* Get level 1 entry */
 	mtspr	SPRN_MD_TWC, r11
 	mfspr	r10, SPRN_MD_TWC
 	lwz	r10, 0(r10)	/* Get the pte */
@@ -249,20 +224,9 @@ instruction_counter:
 	START_EXCEPTION(INTERRUPT_DATA_TLB_MISS_8xx, DataStoreTLBMiss)
 	mtspr	SPRN_SPRG_SCRATCH2, r10
 	mtspr	SPRN_M_TW, r11
-	mfcr	r11
 
-	/* If we are faulting a kernel address, we have to use the
-	 * kernel page tables.
-	 */
-	mfspr	r10, SPRN_MD_EPN
-	compare_to_kernel_boundary r10, r10
 	mfspr	r10, SPRN_M_TWB	/* Get level 1 table */
-	blt+	3f
-	rlwinm	r10, r10, 0, 20, 31
-	oris	r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
-3:
-	mtcr	r11
-	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
+	lwz	r11, 0(r10)	/* Get level 1 entry */
 
 	mtspr	SPRN_MD_TWC, r11
 	mfspr	r10, SPRN_MD_TWC
@@ -333,15 +297,19 @@ instruction_counter:
 	cmpwi	cr1, r11, RPN_PATTERN
 	beq-	cr1, FixupDAR	/* must be a buggy dcbX, icbi insn. */
 DARFixed:/* Return from dcbx instruction bug workaround */
+	mfspr	r11, SPRN_DSISR
+	rlwinm	r11, r11, 0, DSISR_NOHPTE
+	cmpwi	cr1, r11, 0
+	beq+	cr1, .Ldtlbie
+	mfspr	r11, SPRN_DAR
+	tlbie	r11
+	rlwinm	r11, r11, 16, 0xffff
+	cmplwi	cr1, r11, TASK_SIZE@h
+	bge-	cr1, FixupPGD
+.Ldtlbie:
 	EXCEPTION_PROLOG_1
 	/* 0x300 is DataAccess exception, needed by bad_page_fault() */
 	EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataTLBError handle_dar_dsisr=1
-	lwz	r4, _DAR(r11)
-	lwz	r5, _DSISR(r11)
-	andis.	r10,r5,DSISR_NOHPTE@h
-	beq+	.Ldtlbie
-	tlbie	r4
-.Ldtlbie:
 	prepare_transfer_to_handler
 	bl	do_page_fault
 	b	interrupt_return
@@ -395,6 +363,30 @@ DARFixed:/* Return from dcbx instruction bug workaround */
 	__HEAD
 	. = 0x2000
 
+FixupPGD:
+	mtspr	SPRN_M_TW, r10
+	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_MD_EPN, r10
+	mfspr	r11, SPRN_M_TWB	/* Get level 1 table */
+	lwz	r10, 0(r11)	/* Get the level 1 entry */
+	cmpwi	cr1, r10, 0
+	bne	cr1, 1f
+
+	rlwinm	r10, r11, 0, 20, 31
+	oris	r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
+	lwz	r10, (swapper_pg_dir - PAGE_OFFSET)@l(r10)	/* Get the level 1 entry */
+	cmpwi	cr1, r10, 0
+	beq	cr1, 1f
+	stw	r10, 0(r11)	/* Set the level 1 entry */
+	mfspr	r10, SPRN_M_TW
+	mtcr	r10
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	rfi
+1:
+	mfspr	r10, SPRN_M_TW
+	b	.Ldtlbie
+
 /* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
  * by decoding the registers used by the dcbx instruction and adding them.
  * DAR is set to the calculated address.
@@ -405,7 +397,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	mfspr	r10, SPRN_SRR0
 	mtspr	SPRN_MD_EPN, r10
 	rlwinm	r11, r10, 16, 0xfff8
-	cmpli	cr1, r11, PAGE_OFFSET@h
+	cmpli	cr1, r11, TASK_SIZE@h
 	mfspr	r11, SPRN_M_TWB	/* Get level 1 table */
 	blt+	cr1, 3f
 
@@ -413,17 +405,17 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	tophys(r11, r10)
 	mfspr	r11, SPRN_M_TWB	/* Get level 1 table */
 	rlwinm	r11, r11, 0, 20, 31
-	oris	r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha
+	oris	r11, r11, (swapper_pg_dir - PAGE_OFFSET)@h
+	ori	r11, r11, (swapper_pg_dir - PAGE_OFFSET)@l
 3:
-	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
+	lwz	r11, 0(r11)	/* Get the level 1 entry */
+	rlwinm	r11, r11, 0, ~_PMD_PAGE_8M
 	mtspr	SPRN_MD_TWC, r11
-	mtcrf	0x01, r11
 	mfspr	r11, SPRN_MD_TWC
 	lwz	r11, 0(r11)	/* Get the pte */
-	bt	28,200f		/* bit 28 = Large page (8M) */
 	/* concat physical page address(r11) and page offset(r10) */
 	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT, 31
-201:	lwz	r11,0(r11)
+	lwz	r11,0(r11)
 /* Check if it really is a dcbx instruction. */
 /* dcbt and dcbtst does not generate DTLB Misses/Errors,
  * no need to include them here */
@@ -442,11 +434,6 @@ FixupDAR:/* Entry point for dcbx workaround. */
 141:	mfspr	r10,SPRN_M_TW
 	b	DARFixed	/* Nope, go back to normal TLB processing */
 
-200:
-	/* concat physical page address(r11) and page offset(r10) */
-	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT_8M, 31
-	b	201b
-
 144:	mfspr	r10, SPRN_DSISR
 	rlwinm	r10, r10,0,7,5	/* Clear store bit for buggy dcbst insn */
 	mtspr	SPRN_DSISR, r10
@@ -501,6 +488,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	bctr				/* jump into table */
 152:
 	mfdar	r11
+	mtdar	r10
 	mtctr	r11			/* restore ctr reg from DAR */
 	mfspr	r11, SPRN_SPRG_THREAD
 	stw	r10, DAR(r11)
@@ -541,7 +529,8 @@ start_here:
 	li	r0,0
 	stwu	r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
 
-	lis	r6, swapper_pg_dir@ha
+	lis	r6, swapper_pg_dir@h
+	ori	r6, r6, swapper_pg_dir@l
 	tophys(r6,r6)
 	mtspr	SPRN_M_TWB, r6
 
@@ -594,6 +583,10 @@ start_here:
 	lis	r0, (MD_TWAM | MD_RSV4I)@h
 	mtspr	SPRN_MD_CTR, r0
 #endif
+#ifndef CONFIG_PIN_TLB_TEXT
+	li	r0, 0
+	mtspr	SPRN_MI_CTR, r0
+#endif
 #if !defined(CONFIG_PIN_TLB_DATA) && !defined(CONFIG_PIN_TLB_IMMR)
 	lis	r0, MD_TWAM@h
 	mtspr	SPRN_MD_CTR, r0
@@ -690,6 +683,7 @@ SYM_FUNC_START_LOCAL(initial_mmu)
 	blr
 SYM_FUNC_END(initial_mmu)
 
+#ifdef CONFIG_PIN_TLB
 _GLOBAL(mmu_pin_tlb)
 	lis	r9, (1f - PAGE_OFFSET)@h
 	ori	r9, r9, (1f - PAGE_OFFSET)@l
@@ -711,6 +705,7 @@ _GLOBAL(mmu_pin_tlb)
 	mtspr	SPRN_MD_CTR, r6
 	tlbia
 
+#ifdef CONFIG_PIN_TLB_TEXT
 	LOAD_REG_IMMEDIATE(r5, 28 << 8)
 	LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
 	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
@@ -731,6 +726,7 @@ _GLOBAL(mmu_pin_tlb)
 	bdnzt	lt, 2b
 	lis	r0, MI_RSV4I@h
 	mtspr	SPRN_MI_CTR, r0
+#endif
 
 	LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM)
 #ifdef CONFIG_PIN_TLB_DATA
@@ -790,3 +786,4 @@ _GLOBAL(mmu_pin_tlb)
 	mtspr	SPRN_SRR1, r10
 	mtspr	SPRN_SRR0, r11
 	rfi
+#endif
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index c51f28b5abc0..cb2bca76be53 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -31,7 +31,6 @@
 #include <asm/ptrace.h>
 #include <asm/bug.h>
 #include <asm/kvm_book3s_asm.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 #include <asm/interrupt.h>
 
@@ -412,44 +411,34 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE)
  */
 	. = INTERRUPT_INST_TLB_MISS_603
 InstructionTLBMiss:
-/*
- * r0:	scratch
- * r1:	linux style pte ( later becomes ppc hardware pte )
- * r2:	ptr to linux-style pte
- * r3:	scratch
- */
 	/* Get PTE (linux-style) and check access */
-	mfspr	r3,SPRN_IMISS
-#ifdef CONFIG_MODULES
-	lis	r1, TASK_SIZE@h		/* check if kernel address */
-	cmplw	0,r1,r3
-#endif
+	mfspr	r0,SPRN_IMISS
 	mfspr	r2, SPRN_SDR1
-	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
-	rlwinm	r2, r2, 28, 0xfffff000
-#ifdef CONFIG_MODULES
-	bgt-	112f
-	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
-#endif
-112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
+	rlwinm	r2, r2, 28, 0xfffff000
+	rlwimi	r2,r0,12,20,29		/* insert top 10 bits of address */
 	lwz	r2,0(r2)		/* get pmd entry */
+#ifdef CONFIG_EXECMEM
+	rlwinm	r3, r0, 4, 0xf
+	subi	r3, r3, (TASK_SIZE >> 28) & 0xf
+#endif
 	rlwinm.	r2,r2,0,0,19		/* extract address of pte page */
 	beq-	InstructionAddressInvalid	/* return if no mapping */
-	rlwimi	r2,r3,22,20,29		/* insert next 10 bits of address */
-	lwz	r0,0(r2)		/* get linux-style pte */
-	andc.	r1,r1,r0		/* check access & ~permission */
+	rlwimi	r2,r0,22,20,29		/* insert next 10 bits of address */
+	lwz	r2,0(r2)		/* get linux-style pte */
+	andc.	r1,r1,r2		/* check access & ~permission */
 	bne-	InstructionAddressInvalid /* return if access not permitted */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
+#ifdef CONFIG_EXECMEM
+	rlwimi	r2, r3, 1, 31, 31	/* userspace ? -> PP lsb */
+#endif
 	ori	r1, r1, 0xe06		/* clear out reserved bits */
-	andc	r1, r0, r1		/* PP = user? 1 : 0 */
+	andc	r1, r2, r1		/* PP = user? 1 : 0 */
 BEGIN_FTR_SECTION
 	rlwinm	r1,r1,0,~_PAGE_COHERENT	/* clear M (coherence not required) */
 END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	mtspr	SPRN_RPA,r1
-	tlbli	r3
+	tlbli	r0
 	mfspr	r3,SPRN_SRR1		/* Need to restore CR0 */
 	mtcrf	0x80,r3
 	rfi
@@ -478,63 +467,62 @@ InstructionAddressInvalid:
  */
 	. = INTERRUPT_DATA_LOAD_TLB_MISS_603
 DataLoadTLBMiss:
-/*
- * r0:	scratch
- * r1:	linux style pte ( later becomes ppc hardware pte )
- * r2:	ptr to linux-style pte
- * r3:	scratch
- */
 	/* Get PTE (linux-style) and check access */
-	mfspr	r3,SPRN_DMISS
-	lis	r1, TASK_SIZE@h		/* check if kernel address */
-	cmplw	0,r1,r3
+	mfspr	r0,SPRN_DMISS
 	mfspr	r2, SPRN_SDR1
-	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
-	rlwinm	r2, r2, 28, 0xfffff000
-	bgt-	112f
-	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
-	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED
-	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
-112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
-	lwz	r2,0(r2)		/* get pmd entry */
+	rlwinm	r1, r2, 28, 0xfffff000
+	rlwimi	r1,r0,12,20,29		/* insert top 10 bits of address */
+	lwz	r2,0(r1)		/* get pmd entry */
+	rlwinm	r3, r0, 4, 0xf
 	rlwinm.	r2,r2,0,0,19		/* extract address of pte page */
-	beq-	DataAddressInvalid	/* return if no mapping */
-	rlwimi	r2,r3,22,20,29		/* insert next 10 bits of address */
-	lwz	r0,0(r2)		/* get linux-style pte */
-	andc.	r1,r1,r0		/* check access & ~permission */
+	subi	r3, r3, (TASK_SIZE >> 28) & 0xf
+	beq-	2f			/* bail if no mapping */
+1:	rlwimi	r2,r0,22,20,29		/* insert next 10 bits of address */
+	lwz	r2,0(r2)		/* get linux-style pte */
+	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_READ
+	andc.	r1,r1,r2		/* check access & ~permission */
 	bne-	DataAddressInvalid	/* return if access not permitted */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwinm	r1,r0,32-9,30,30	/* _PAGE_RW -> PP msb */
-	rlwimi	r0,r0,32-1,30,30	/* _PAGE_USER -> PP msb */
-	rlwimi	r1,r0,32-3,24,24	/* _PAGE_RW -> _PAGE_DIRTY */
-	rlwimi	r0,r0,32-1,31,31	/* _PAGE_USER -> PP lsb */
+	rlwinm	r1,r2,32-9,30,30	/* _PAGE_WRITE -> PP msb */
+	rlwimi	r2,r3,2,30,31		/* userspace ? -> PP */
+	rlwimi	r1,r2,32-3,24,24	/* _PAGE_WRITE -> _PAGE_DIRTY */
 	xori	r1,r1,_PAGE_DIRTY	/* clear dirty when not rw */
 	ori	r1,r1,0xe04		/* clear out reserved bits */
-	andc	r1,r0,r1		/* PP = user? rw? 1: 3: 0 */
+	andc	r1,r2,r1		/* PP = user? rw? 1: 3: 0 */
 BEGIN_FTR_SECTION
 	rlwinm	r1,r1,0,~_PAGE_COHERENT	/* clear M (coherence not required) */
 END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	mtspr	SPRN_RPA,r1
 BEGIN_MMU_FTR_SECTION
-	li	r0,1
+	li	r3,1
 	mfspr	r1,SPRN_SPRG_603_LRU
-	rlwinm	r2,r3,20,27,31		/* Get Address bits 15:19 */
-	slw	r0,r0,r2
-	xor	r1,r0,r1
-	srw	r0,r1,r2
+	rlwinm	r2,r0,20,27,31		/* Get Address bits 15:19 */
+	slw	r3,r3,r2
+	xor	r1,r3,r1
+	srw	r3,r1,r2
 	mtspr   SPRN_SPRG_603_LRU,r1
 	mfspr	r2,SPRN_SRR1
-	rlwimi	r2,r0,31-14,14,14
+	rlwimi	r2,r3,31-14,14,14
 	mtspr   SPRN_SRR1,r2
 	mtcrf	0x80,r2
-	tlbld	r3
+	tlbld	r0
 	rfi
 MMU_FTR_SECTION_ELSE
 	mfspr	r2,SPRN_SRR1		/* Need to restore CR0 */
 	mtcrf	0x80,r2
-	tlbld	r3
+	tlbld	r0
 	rfi
 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
+
+2:	lis     r2, (swapper_pg_dir - PAGE_OFFSET)@ha
+	addi    r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l        /* kernel page table */
+	rlwimi	r2,r0,12,20,29		/* insert top 10 bits of address */
+	lwz	r2,0(r2)		/* get pmd entry */
+	cmpwi	cr0,r2,0
+	beq-	DataAddressInvalid	/* return if no mapping */
+	stw	r2,0(r1)
+	rlwinm.	r2,r2,0,0,19		/* extract address of pte page */
+	b	1b
 DataAddressInvalid:
 	mfspr	r3,SPRN_SRR1
 	rlwinm	r1,r3,9,6,6	/* Get load/store bit */
@@ -558,35 +546,26 @@ DataAddressInvalid:
  */
 	. = INTERRUPT_DATA_STORE_TLB_MISS_603
 DataStoreTLBMiss:
-/*
- * r0:	scratch
- * r1:	linux style pte ( later becomes ppc hardware pte )
- * r2:	ptr to linux-style pte
- * r3:	scratch
- */
 	/* Get PTE (linux-style) and check access */
-	mfspr	r3,SPRN_DMISS
-	lis	r1, TASK_SIZE@h		/* check if kernel address */
-	cmplw	0,r1,r3
+	mfspr	r0,SPRN_DMISS
 	mfspr	r2, SPRN_SDR1
-	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
-	rlwinm	r2, r2, 28, 0xfffff000
-	bgt-	112f
-	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
-	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
-	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
-112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
-	lwz	r2,0(r2)		/* get pmd entry */
+	rlwinm	r1, r2, 28, 0xfffff000
+	rlwimi	r1,r0,12,20,29		/* insert top 10 bits of address */
+	lwz	r2,0(r1)		/* get pmd entry */
+	rlwinm	r3, r0, 4, 0xf
 	rlwinm.	r2,r2,0,0,19		/* extract address of pte page */
-	beq-	DataAddressInvalid	/* return if no mapping */
-	rlwimi	r2,r3,22,20,29		/* insert next 10 bits of address */
-	lwz	r0,0(r2)		/* get linux-style pte */
-	andc.	r1,r1,r0		/* check access & ~permission */
+	subi	r3, r3, (TASK_SIZE >> 28) & 0xf
+	beq-	2f			/* bail if no mapping */
+1:
+	rlwimi	r2,r0,22,20,29		/* insert next 10 bits of address */
+	lwz	r2,0(r2)		/* get linux-style pte */
+	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
+	andc.	r1,r1,r2		/* check access & ~permission */
 	bne-	DataAddressInvalid	/* return if access not permitted */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
+	rlwimi	r2,r3,1,31,31		/* userspace ? -> PP lsb */
 	li	r1,0xe06		/* clear out reserved bits & PP msb */
-	andc	r1,r0,r1		/* PP = user? 1: 0 */
+	andc	r1,r2,r1		/* PP = user? 1: 0 */
 BEGIN_FTR_SECTION
 	rlwinm	r1,r1,0,~_PAGE_COHERENT	/* clear M (coherence not required) */
 END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
@@ -594,26 +573,36 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	mfspr	r2,SPRN_SRR1		/* Need to restore CR0 */
 	mtcrf	0x80,r2
 BEGIN_MMU_FTR_SECTION
-	li	r0,1
+	li	r3,1
 	mfspr	r1,SPRN_SPRG_603_LRU
-	rlwinm	r2,r3,20,27,31		/* Get Address bits 15:19 */
-	slw	r0,r0,r2
-	xor	r1,r0,r1
-	srw	r0,r1,r2
+	rlwinm	r2,r0,20,27,31		/* Get Address bits 15:19 */
+	slw	r3,r3,r2
+	xor	r1,r3,r1
+	srw	r3,r1,r2
 	mtspr   SPRN_SPRG_603_LRU,r1
 	mfspr	r2,SPRN_SRR1
-	rlwimi	r2,r0,31-14,14,14
+	rlwimi	r2,r3,31-14,14,14
 	mtspr   SPRN_SRR1,r2
 	mtcrf	0x80,r2
-	tlbld	r3
+	tlbld	r0
 	rfi
 MMU_FTR_SECTION_ELSE
 	mfspr	r2,SPRN_SRR1		/* Need to restore CR0 */
 	mtcrf	0x80,r2
-	tlbld	r3
+	tlbld	r0
 	rfi
 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
 
+2:	lis     r2, (swapper_pg_dir - PAGE_OFFSET)@ha
+	addi    r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l        /* kernel page table */
+	rlwimi	r2,r0,12,20,29		/* insert top 10 bits of address */
+	lwz	r2,0(r2)		/* get pmd entry */
+	cmpwi	cr0,r2,0
+	beq-	DataAddressInvalid	/* return if no mapping */
+	stw	r2,0(r1)
+	rlwinm	r2,r2,0,0,19		/* extract address of pte page */
+	b	1b
+
 #ifndef CONFIG_ALTIVEC
 #define altivec_assist_exception	unknown_exception
 #endif
@@ -690,7 +679,8 @@ hash_page_dsi:
 	mfdar	r4
 	mfsrr0	r5
 	mfsrr1	r9
-	rlwinm	r3, r3, 32 - 15, _PAGE_RW	/* DSISR_STORE -> _PAGE_RW */
+	rlwinm	r3, r3, 32 - 15, _PAGE_WRITE	/* DSISR_STORE -> _PAGE_WRITE */
+	ori	r3, r3, _PAGE_PRESENT | _PAGE_READ
 	bl	hash_page
 	mfspr	r10, SPRN_SPRG_THREAD
 	restore_regs_thread r10
@@ -700,7 +690,7 @@ hash_page_isi:
 	mr	r11, r10
 	mfspr	r10, SPRN_SPRG_THREAD
 	save_regs_thread	r10
-	li	r3, 0
+	li	r3, _PAGE_PRESENT | _PAGE_EXEC
 	lwz	r4, SRR0(r10)
 	lwz	r9, SRR1(r10)
 	bl	hash_page
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index b6b5b01a173c..75471fb6fb10 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -7,7 +7,7 @@
 #include <asm/kvm_booke_hv_asm.h>
 #include <asm/thread_info.h>	/* for THREAD_SHIFT */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 /*
  * Macros used for common Book-e exception handling
@@ -145,10 +145,9 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 	b	transfer_to_syscall	/* jump to handler */
 .endm
 
-/* To handle the additional exception priority levels on 40x and Book-E
+/* To handle the additional exception priority levels on Book-E
  * processors we allocate a stack per additional priority level.
  *
- * On 40x critical is the only additional level
  * On 44x/e500 we have critical and machine check
  *
  * Additionally we reserve a SPRG for each priority level so we can free up a
@@ -523,5 +522,5 @@ label:
 	bl	kernel_fp_unavailable_exception;			      \
 	b	interrupt_return
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __HEAD_BOOKE_H__ */
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index e1b4e70c8fd0..a1318ce18d0e 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -43,16 +43,6 @@ int hw_breakpoint_slots(int type)
 	return 0;		/* no instruction breakpoints available */
 }
 
-static bool single_step_pending(void)
-{
-	int i;
-
-	for (i = 0; i < nr_wp_slots(); i++) {
-		if (current->thread.last_hit_ubp[i])
-			return true;
-	}
-	return false;
-}
 
 /*
  * Install a perf counter breakpoint.
@@ -84,7 +74,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	 * Do not install DABR values if the instruction must be single-stepped.
 	 * If so, DABR will be populated in single_step_dabr_instruction().
 	 */
-	if (!single_step_pending())
+	if (!info->perf_single_step)
 		__set_breakpoint(i, info);
 
 	return 0;
@@ -124,275 +114,6 @@ static bool is_ptrace_bp(struct perf_event *bp)
 	return bp->overflow_handler == ptrace_triggered;
 }
 
-struct breakpoint {
-	struct list_head list;
-	struct perf_event *bp;
-	bool ptrace_bp;
-};
-
-/*
- * While kernel/events/hw_breakpoint.c does its own synchronization, we cannot
- * rely on it safely synchronizing internals here; however, we can rely on it
- * not requesting more breakpoints than available.
- */
-static DEFINE_SPINLOCK(cpu_bps_lock);
-static DEFINE_PER_CPU(struct breakpoint *, cpu_bps[HBP_NUM_MAX]);
-static DEFINE_SPINLOCK(task_bps_lock);
-static LIST_HEAD(task_bps);
-
-static struct breakpoint *alloc_breakpoint(struct perf_event *bp)
-{
-	struct breakpoint *tmp;
-
-	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
-		return ERR_PTR(-ENOMEM);
-	tmp->bp = bp;
-	tmp->ptrace_bp = is_ptrace_bp(bp);
-	return tmp;
-}
-
-static bool bp_addr_range_overlap(struct perf_event *bp1, struct perf_event *bp2)
-{
-	__u64 bp1_saddr, bp1_eaddr, bp2_saddr, bp2_eaddr;
-
-	bp1_saddr = ALIGN_DOWN(bp1->attr.bp_addr, HW_BREAKPOINT_SIZE);
-	bp1_eaddr = ALIGN(bp1->attr.bp_addr + bp1->attr.bp_len, HW_BREAKPOINT_SIZE);
-	bp2_saddr = ALIGN_DOWN(bp2->attr.bp_addr, HW_BREAKPOINT_SIZE);
-	bp2_eaddr = ALIGN(bp2->attr.bp_addr + bp2->attr.bp_len, HW_BREAKPOINT_SIZE);
-
-	return (bp1_saddr < bp2_eaddr && bp1_eaddr > bp2_saddr);
-}
-
-static bool alternate_infra_bp(struct breakpoint *b, struct perf_event *bp)
-{
-	return is_ptrace_bp(bp) ? !b->ptrace_bp : b->ptrace_bp;
-}
-
-static bool can_co_exist(struct breakpoint *b, struct perf_event *bp)
-{
-	return !(alternate_infra_bp(b, bp) && bp_addr_range_overlap(b->bp, bp));
-}
-
-static int task_bps_add(struct perf_event *bp)
-{
-	struct breakpoint *tmp;
-
-	tmp = alloc_breakpoint(bp);
-	if (IS_ERR(tmp))
-		return PTR_ERR(tmp);
-
-	spin_lock(&task_bps_lock);
-	list_add(&tmp->list, &task_bps);
-	spin_unlock(&task_bps_lock);
-	return 0;
-}
-
-static void task_bps_remove(struct perf_event *bp)
-{
-	struct list_head *pos, *q;
-
-	spin_lock(&task_bps_lock);
-	list_for_each_safe(pos, q, &task_bps) {
-		struct breakpoint *tmp = list_entry(pos, struct breakpoint, list);
-
-		if (tmp->bp == bp) {
-			list_del(&tmp->list);
-			kfree(tmp);
-			break;
-		}
-	}
-	spin_unlock(&task_bps_lock);
-}
-
-/*
- * If any task has breakpoint from alternate infrastructure,
- * return true. Otherwise return false.
- */
-static bool all_task_bps_check(struct perf_event *bp)
-{
-	struct breakpoint *tmp;
-	bool ret = false;
-
-	spin_lock(&task_bps_lock);
-	list_for_each_entry(tmp, &task_bps, list) {
-		if (!can_co_exist(tmp, bp)) {
-			ret = true;
-			break;
-		}
-	}
-	spin_unlock(&task_bps_lock);
-	return ret;
-}
-
-/*
- * If same task has breakpoint from alternate infrastructure,
- * return true. Otherwise return false.
- */
-static bool same_task_bps_check(struct perf_event *bp)
-{
-	struct breakpoint *tmp;
-	bool ret = false;
-
-	spin_lock(&task_bps_lock);
-	list_for_each_entry(tmp, &task_bps, list) {
-		if (tmp->bp->hw.target == bp->hw.target &&
-		    !can_co_exist(tmp, bp)) {
-			ret = true;
-			break;
-		}
-	}
-	spin_unlock(&task_bps_lock);
-	return ret;
-}
-
-static int cpu_bps_add(struct perf_event *bp)
-{
-	struct breakpoint **cpu_bp;
-	struct breakpoint *tmp;
-	int i = 0;
-
-	tmp = alloc_breakpoint(bp);
-	if (IS_ERR(tmp))
-		return PTR_ERR(tmp);
-
-	spin_lock(&cpu_bps_lock);
-	cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
-	for (i = 0; i < nr_wp_slots(); i++) {
-		if (!cpu_bp[i]) {
-			cpu_bp[i] = tmp;
-			break;
-		}
-	}
-	spin_unlock(&cpu_bps_lock);
-	return 0;
-}
-
-static void cpu_bps_remove(struct perf_event *bp)
-{
-	struct breakpoint **cpu_bp;
-	int i = 0;
-
-	spin_lock(&cpu_bps_lock);
-	cpu_bp = per_cpu_ptr(cpu_bps, bp->cpu);
-	for (i = 0; i < nr_wp_slots(); i++) {
-		if (!cpu_bp[i])
-			continue;
-
-		if (cpu_bp[i]->bp == bp) {
-			kfree(cpu_bp[i]);
-			cpu_bp[i] = NULL;
-			break;
-		}
-	}
-	spin_unlock(&cpu_bps_lock);
-}
-
-static bool cpu_bps_check(int cpu, struct perf_event *bp)
-{
-	struct breakpoint **cpu_bp;
-	bool ret = false;
-	int i;
-
-	spin_lock(&cpu_bps_lock);
-	cpu_bp = per_cpu_ptr(cpu_bps, cpu);
-	for (i = 0; i < nr_wp_slots(); i++) {
-		if (cpu_bp[i] && !can_co_exist(cpu_bp[i], bp)) {
-			ret = true;
-			break;
-		}
-	}
-	spin_unlock(&cpu_bps_lock);
-	return ret;
-}
-
-static bool all_cpu_bps_check(struct perf_event *bp)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if (cpu_bps_check(cpu, bp))
-			return true;
-	}
-	return false;
-}
-
-int arch_reserve_bp_slot(struct perf_event *bp)
-{
-	int ret;
-
-	/* ptrace breakpoint */
-	if (is_ptrace_bp(bp)) {
-		if (all_cpu_bps_check(bp))
-			return -ENOSPC;
-
-		if (same_task_bps_check(bp))
-			return -ENOSPC;
-
-		return task_bps_add(bp);
-	}
-
-	/* perf breakpoint */
-	if (is_kernel_addr(bp->attr.bp_addr))
-		return 0;
-
-	if (bp->hw.target && bp->cpu == -1) {
-		if (same_task_bps_check(bp))
-			return -ENOSPC;
-
-		return task_bps_add(bp);
-	} else if (!bp->hw.target && bp->cpu != -1) {
-		if (all_task_bps_check(bp))
-			return -ENOSPC;
-
-		return cpu_bps_add(bp);
-	}
-
-	if (same_task_bps_check(bp))
-		return -ENOSPC;
-
-	ret = cpu_bps_add(bp);
-	if (ret)
-		return ret;
-	ret = task_bps_add(bp);
-	if (ret)
-		cpu_bps_remove(bp);
-
-	return ret;
-}
-
-void arch_release_bp_slot(struct perf_event *bp)
-{
-	if (!is_kernel_addr(bp->attr.bp_addr)) {
-		if (bp->hw.target)
-			task_bps_remove(bp);
-		if (bp->cpu != -1)
-			cpu_bps_remove(bp);
-	}
-}
-
-/*
- * Perform cleanup of arch-specific counters during unregistration
- * of the perf-event
- */
-void arch_unregister_hw_breakpoint(struct perf_event *bp)
-{
-	/*
-	 * If the breakpoint is unregistered between a hw_breakpoint_handler()
-	 * and the single_step_dabr_instruction(), then cleanup the breakpoint
-	 * restoration variables to prevent dangling pointers.
-	 * FIXME, this should not be using bp->ctx at all! Sayeth peterz.
-	 */
-	if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L)) {
-		int i;
-
-		for (i = 0; i < nr_wp_slots(); i++) {
-			if (bp->ctx->task->thread.last_hit_ubp[i] == bp)
-				bp->ctx->task->thread.last_hit_ubp[i] = NULL;
-		}
-	}
-}
-
 /*
  * Check for virtual address in kernel space.
  */
@@ -499,25 +220,36 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
  * Restores the breakpoint on the debug registers.
  * Invoke this function if it is known that the execution context is
  * about to change to cause loss of MSR_SE settings.
+ *
+ * The perf watchpoint will simply re-trigger once the thread is started again,
+ * and the watchpoint handler will set up MSR_SE and perf_single_step as
+ * needed.
  */
 void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
 {
 	struct arch_hw_breakpoint *info;
 	int i;
 
+	preempt_disable();
+
 	for (i = 0; i < nr_wp_slots(); i++) {
-		if (unlikely(tsk->thread.last_hit_ubp[i]))
+		struct perf_event *bp = __this_cpu_read(bp_per_reg[i]);
+
+		if (unlikely(bp && counter_arch_bp(bp)->perf_single_step))
 			goto reset;
 	}
-	return;
+	goto out;
 
 reset:
 	regs_set_return_msr(regs, regs->msr & ~MSR_SE);
 	for (i = 0; i < nr_wp_slots(); i++) {
 		info = counter_arch_bp(__this_cpu_read(bp_per_reg[i]));
 		__set_breakpoint(i, info);
-		tsk->thread.last_hit_ubp[i] = NULL;
+		info->perf_single_step = false;
 	}
+
+out:
+	preempt_enable();
 }
 
 static bool is_larx_stcx_instr(int type)
@@ -534,23 +266,22 @@ static bool is_octword_vsx_instr(int type, int size)
  * We've failed in reliably handling the hw-breakpoint. Unregister
  * it and throw a warning message to let the user know about it.
  */
-static void handler_error(struct perf_event *bp, struct arch_hw_breakpoint *info)
+static void handler_error(struct perf_event *bp)
 {
 	WARN(1, "Unable to handle hardware breakpoint. Breakpoint at 0x%lx will be disabled.",
-	     info->address);
+	     counter_arch_bp(bp)->address);
 	perf_event_disable_inatomic(bp);
 }
 
-static void larx_stcx_err(struct perf_event *bp, struct arch_hw_breakpoint *info)
+static void larx_stcx_err(struct perf_event *bp)
 {
 	printk_ratelimited("Breakpoint hit on instruction that can't be emulated. Breakpoint at 0x%lx will be disabled.\n",
-			   info->address);
+			   counter_arch_bp(bp)->address);
 	perf_event_disable_inatomic(bp);
 }
 
 static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
-			     struct arch_hw_breakpoint **info, int *hit,
-			     ppc_inst_t instr)
+			     int *hit, ppc_inst_t instr)
 {
 	int i;
 	int stepped;
@@ -560,8 +291,9 @@ static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
 		for (i = 0; i < nr_wp_slots(); i++) {
 			if (!hit[i])
 				continue;
-			current->thread.last_hit_ubp[i] = bp[i];
-			info[i] = NULL;
+
+			counter_arch_bp(bp[i])->perf_single_step = true;
+			bp[i] = NULL;
 		}
 		regs_set_return_msr(regs, regs->msr | MSR_SE);
 		return false;
@@ -572,15 +304,15 @@ static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
 		for (i = 0; i < nr_wp_slots(); i++) {
 			if (!hit[i])
 				continue;
-			handler_error(bp[i], info[i]);
-			info[i] = NULL;
+			handler_error(bp[i]);
+			bp[i] = NULL;
 		}
 		return false;
 	}
 	return true;
 }
 
-static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info,
+static void handle_p10dd1_spurious_exception(struct perf_event **bp,
 					     int *hit, unsigned long ea)
 {
 	int i;
@@ -592,10 +324,14 @@ static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info,
 	 * spurious exception.
 	 */
 	for (i = 0; i < nr_wp_slots(); i++) {
-		if (!info[i])
+		struct arch_hw_breakpoint *info;
+
+		if (!bp[i])
 			continue;
 
-		hw_end_addr = ALIGN(info[i]->address + info[i]->len, HW_BREAKPOINT_SIZE);
+		info = counter_arch_bp(bp[i]);
+
+		hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE);
 
 		/*
 		 * Ending address of DAWR range is less than starting
@@ -625,20 +361,24 @@ static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info,
 		return;
 
 	for (i = 0; i < nr_wp_slots(); i++) {
-		if (info[i]) {
+		if (bp[i]) {
 			hit[i] = 1;
-			info[i]->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+			counter_arch_bp(bp[i])->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
 		}
 	}
 }
 
+/*
+ * Handle a DABR or DAWR exception.
+ *
+ * Called in atomic context.
+ */
 int hw_breakpoint_handler(struct die_args *args)
 {
 	bool err = false;
 	int rc = NOTIFY_STOP;
 	struct perf_event *bp[HBP_NUM_MAX] = { NULL };
 	struct pt_regs *regs = args->regs;
-	struct arch_hw_breakpoint *info[HBP_NUM_MAX] = { NULL };
 	int i;
 	int hit[HBP_NUM_MAX] = {0};
 	int nr_hit = 0;
@@ -663,18 +403,20 @@ int hw_breakpoint_handler(struct die_args *args)
 		wp_get_instr_detail(regs, &instr, &type, &size, &ea);
 
 	for (i = 0; i < nr_wp_slots(); i++) {
+		struct arch_hw_breakpoint *info;
+
 		bp[i] = __this_cpu_read(bp_per_reg[i]);
 		if (!bp[i])
 			continue;
 
-		info[i] = counter_arch_bp(bp[i]);
-		info[i]->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
+		info = counter_arch_bp(bp[i]);
+		info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
 
-		if (wp_check_constraints(regs, instr, ea, type, size, info[i])) {
+		if (wp_check_constraints(regs, instr, ea, type, size, info)) {
 			if (!IS_ENABLED(CONFIG_PPC_8xx) &&
 			    ppc_inst_equal(instr, ppc_inst(0))) {
-				handler_error(bp[i], info[i]);
-				info[i] = NULL;
+				handler_error(bp[i]);
+				bp[i] = NULL;
 				err = 1;
 				continue;
 			}
@@ -693,7 +435,7 @@ int hw_breakpoint_handler(struct die_args *args)
 		/* Workaround for Power10 DD1 */
 		if (!IS_ENABLED(CONFIG_PPC_8xx) && mfspr(SPRN_PVR) == 0x800100 &&
 		    is_octword_vsx_instr(type, size)) {
-			handle_p10dd1_spurious_exception(info, hit, ea);
+			handle_p10dd1_spurious_exception(bp, hit, ea);
 		} else {
 			rc = NOTIFY_DONE;
 			goto out;
@@ -708,10 +450,10 @@ int hw_breakpoint_handler(struct die_args *args)
 	 */
 	if (ptrace_bp) {
 		for (i = 0; i < nr_wp_slots(); i++) {
-			if (!hit[i])
+			if (!hit[i] || !is_ptrace_bp(bp[i]))
 				continue;
 			perf_bp_event(bp[i], regs);
-			info[i] = NULL;
+			bp[i] = NULL;
 		}
 		rc = NOTIFY_DONE;
 		goto reset;
@@ -722,13 +464,13 @@ int hw_breakpoint_handler(struct die_args *args)
 			for (i = 0; i < nr_wp_slots(); i++) {
 				if (!hit[i])
 					continue;
-				larx_stcx_err(bp[i], info[i]);
-				info[i] = NULL;
+				larx_stcx_err(bp[i]);
+				bp[i] = NULL;
 			}
 			goto reset;
 		}
 
-		if (!stepping_handler(regs, bp, info, hit, instr))
+		if (!stepping_handler(regs, bp, hit, instr))
 			goto reset;
 	}
 
@@ -739,15 +481,15 @@ int hw_breakpoint_handler(struct die_args *args)
 	for (i = 0; i < nr_wp_slots(); i++) {
 		if (!hit[i])
 			continue;
-		if (!(info[i]->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
+		if (!(counter_arch_bp(bp[i])->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
 			perf_bp_event(bp[i], regs);
 	}
 
 reset:
 	for (i = 0; i < nr_wp_slots(); i++) {
-		if (!info[i])
+		if (!bp[i])
 			continue;
-		__set_breakpoint(i, info[i]);
+		__set_breakpoint(i, counter_arch_bp(bp[i]));
 	}
 
 out:
@@ -758,28 +500,34 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler);
 
 /*
  * Handle single-step exceptions following a DABR hit.
+ *
+ * Called in atomic context.
  */
 static int single_step_dabr_instruction(struct die_args *args)
 {
 	struct pt_regs *regs = args->regs;
-	struct perf_event *bp = NULL;
-	struct arch_hw_breakpoint *info;
-	int i;
 	bool found = false;
 
 	/*
 	 * Check if we are single-stepping as a result of a
 	 * previous HW Breakpoint exception
 	 */
-	for (i = 0; i < nr_wp_slots(); i++) {
-		bp = current->thread.last_hit_ubp[i];
+	for (int i = 0; i < nr_wp_slots(); i++) {
+		struct perf_event *bp;
+		struct arch_hw_breakpoint *info;
+
+		bp = __this_cpu_read(bp_per_reg[i]);
 
 		if (!bp)
 			continue;
 
-		found = true;
 		info = counter_arch_bp(bp);
 
+		if (!info->perf_single_step)
+			continue;
+
+		found = true;
+
 		/*
 		 * We shall invoke the user-defined callback function in the
 		 * single stepping handler to confirm to 'trigger-after-execute'
@@ -787,26 +535,16 @@ static int single_step_dabr_instruction(struct die_args *args)
 		 */
 		if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
 			perf_bp_event(bp, regs);
-		current->thread.last_hit_ubp[i] = NULL;
-	}
 
-	if (!found)
-		return NOTIFY_DONE;
-
-	for (i = 0; i < nr_wp_slots(); i++) {
-		bp = __this_cpu_read(bp_per_reg[i]);
-		if (!bp)
-			continue;
-
-		info = counter_arch_bp(bp);
-		__set_breakpoint(i, info);
+		info->perf_single_step = false;
+		__set_breakpoint(i, counter_arch_bp(bp));
 	}
 
 	/*
 	 * If the process was being single-stepped by ptrace, let the
 	 * other single-step actions occur (e.g. generate SIGTRAP).
 	 */
-	if (test_thread_flag(TIF_SINGLESTEP))
+	if (!found || test_thread_flag(TIF_SINGLESTEP))
 		return NOTIFY_DONE;
 
 	return NOTIFY_STOP;
@@ -815,6 +553,8 @@ NOKPROBE_SYMBOL(single_step_dabr_instruction);
 
 /*
  * Handle debug exception notifications.
+ *
+ * Called in atomic context.
  */
 int hw_breakpoint_exceptions_notify(
 		struct notifier_block *unused, unsigned long val, void *data)
diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c
index a74623025f3a..9e51801c4915 100644
--- a/arch/powerpc/kernel/hw_breakpoint_constraints.c
+++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c
@@ -131,8 +131,13 @@ void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr,
 			 int *type, int *size, unsigned long *ea)
 {
 	struct instruction_op op;
+	int err;
 
-	if (__get_user_instr(*instr, (void __user *)regs->nip))
+	pagefault_disable();
+	err = __get_user_instr(*instr, (void __user *)regs->nip);
+	pagefault_enable();
+
+	if (err)
 		return;
 
 	analyse_instr(&op, regs, *instr);
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index b1c0418b25c8..e527cd3ef128 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -97,7 +97,7 @@ void power4_idle(void)
 /*
  * Register the sysctl to set/clear powersave_nap.
  */
-static struct ctl_table powersave_nap_ctl_table[] = {
+static const struct ctl_table powersave_nap_ctl_table[] = {
 	{
 		.procname	= "powersave-nap",
 		.data		= &powersave_nap,
@@ -105,7 +105,6 @@ static struct ctl_table powersave_nap_ctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{}
 };
 
 static int __init
diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c
index 957abd592075..b7029beed847 100644
--- a/arch/powerpc/kernel/ima_arch.c
+++ b/arch/powerpc/kernel/ima_arch.c
@@ -23,9 +23,9 @@ bool arch_ima_get_secureboot(void)
  * is not enabled.
  */
 static const char *const secure_rules[] = {
-	"appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+	"appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig",
 #ifndef CONFIG_MODULE_SIG
-	"appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+	"appraise func=MODULE_CHECK appraise_type=imasig|modsig",
 #endif
 	NULL
 };
@@ -49,9 +49,9 @@ static const char *const trusted_rules[] = {
 static const char *const secure_and_trusted_rules[] = {
 	"measure func=KEXEC_KERNEL_CHECK template=ima-modsig",
 	"measure func=MODULE_CHECK template=ima-modsig",
-	"appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+	"appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig",
 #ifndef CONFIG_MODULE_SIG
-	"appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
+	"appraise func=MODULE_CHECK appraise_type=imasig|modsig",
 #endif
 	NULL
 };
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index e34c72285b4e..aea6f7e8e9c6 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -3,6 +3,7 @@
 #include <linux/context_tracking.h>
 #include <linux/err.h>
 #include <linux/compat.h>
+#include <linux/rseq.h>
 #include <linux/sched/debug.h> /* for show_regs */
 
 #include <asm/kup.h>
@@ -24,6 +25,10 @@
 unsigned long global_dbcr0[NR_CPUS];
 #endif
 
+#if defined(CONFIG_PREEMPT_DYNAMIC)
+DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S_64
 DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant);
 static inline bool exit_must_hard_disable(void)
@@ -33,7 +38,7 @@ static inline bool exit_must_hard_disable(void)
 #else
 static inline bool exit_must_hard_disable(void)
 {
-	return true;
+	return false;
 }
 #endif
 
@@ -125,7 +130,7 @@ static notrace void check_return_regs_valid(struct pt_regs *regs)
 	case 0x1600:
 	case 0x1800:
 		validp = &local_paca->hsrr_valid;
-		if (!*validp)
+		if (!READ_ONCE(*validp))
 			return;
 
 		srr0 = mfspr(SPRN_HSRR0);
@@ -135,7 +140,7 @@ static notrace void check_return_regs_valid(struct pt_regs *regs)
 		break;
 	default:
 		validp = &local_paca->srr_valid;
-		if (!*validp)
+		if (!READ_ONCE(*validp))
 			return;
 
 		srr0 = mfspr(SPRN_SRR0);
@@ -161,19 +166,17 @@ static notrace void check_return_regs_valid(struct pt_regs *regs)
 	 * such things will get caught most of the time, statistically
 	 * enough to be able to get a warning out.
 	 */
-	barrier();
-
-	if (!*validp)
+	if (!READ_ONCE(*validp))
 		return;
 
-	if (!warned) {
-		warned = true;
+	if (!data_race(warned)) {
+		data_race(warned = true);
 		printk("%sSRR0 was: %lx should be: %lx\n", h, srr0, regs->nip);
 		printk("%sSRR1 was: %lx should be: %lx\n", h, srr1, regs->msr);
 		show_regs(regs);
 	}
 
-	*validp = 0; /* fixup */
+	WRITE_ONCE(*validp, 0); /* fixup */
 #endif
 }
 
@@ -186,7 +189,7 @@ again:
 	ti_flags = read_thread_flags();
 	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
 		local_irq_enable();
-		if (ti_flags & _TIF_NEED_RESCHED) {
+		if (ti_flags & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) {
 			schedule();
 		} else {
 			/*
@@ -267,7 +270,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	unsigned long ret = 0;
 	bool is_not_scv = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !scv;
 
-	CT_WARN_ON(ct_state() == CONTEXT_USER);
+	CT_WARN_ON(ct_state() == CT_STATE_USER);
 
 	kuap_assert_locked();
 
@@ -345,7 +348,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs)
 
 	BUG_ON(regs_is_unrecoverable(regs));
 	BUG_ON(arch_irq_disabled_regs(regs));
-	CT_WARN_ON(ct_state() == CONTEXT_USER);
+	CT_WARN_ON(ct_state() == CT_STATE_USER);
 
 	/*
 	 * We don't need to restore AMR on the way back to userspace for KUAP.
@@ -368,7 +371,6 @@ void preempt_schedule_irq(void);
 
 notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 {
-	unsigned long flags;
 	unsigned long ret = 0;
 	unsigned long kuap;
 	bool stack_store = read_thread_flags() & _TIF_EMULATE_STACK_STORE;
@@ -388,17 +390,17 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 	if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
 	    TRAP(regs) != INTERRUPT_PROGRAM &&
 	    TRAP(regs) != INTERRUPT_PERFMON)
-		CT_WARN_ON(ct_state() == CONTEXT_USER);
+		CT_WARN_ON(ct_state() == CT_STATE_USER);
 
 	kuap = kuap_get_and_assert_locked();
 
-	local_irq_save(flags);
+	local_irq_disable();
 
 	if (!arch_irq_disabled_regs(regs)) {
 		/* Returning to a kernel context with local irqs enabled. */
 		WARN_ON_ONCE(!(regs->msr & MSR_EE));
 again:
-		if (IS_ENABLED(CONFIG_PREEMPT)) {
+		if (need_irq_preemption()) {
 			/* Return to preemptible kernel context */
 			if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) {
 				if (preempt_count() == 0)
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index bd863702d812..1ad059a9e2fe 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
-	std	r11,_NIP(r1)
+	std	r11,_LINK(r1)
+	std	r11,_NIP(r1)	/* Saved LR is also the next instruction */
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
@@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	std	r9,GPR13(r1)
 	SAVE_NVGPRS(r1)
 	std	r11,_XER(r1)
-	std	r11,_LINK(r1)
 	std	r11,_CTR(r1)
 
 	li	r11,\trapnr
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
deleted file mode 100644
index c877f074d174..000000000000
--- a/arch/powerpc/kernel/io-workarounds.c
+++ /dev/null
@@ -1,197 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Support PCI IO workaround
- *
- *  Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>
- *		       IBM, Corp.
- *  (C) Copyright 2007-2008 TOSHIBA CORPORATION
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/sched/mm.h>	/* for init_mm */
-#include <linux/pgtable.h>
-
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/ppc-pci.h>
-#include <asm/io-workarounds.h>
-#include <asm/pte-walk.h>
-
-
-#define IOWA_MAX_BUS	8
-
-static struct iowa_bus iowa_busses[IOWA_MAX_BUS];
-static unsigned int iowa_bus_count;
-
-static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
-{
-	int i, j;
-	struct resource *res;
-	unsigned long vstart, vend;
-
-	for (i = 0; i < iowa_bus_count; i++) {
-		struct iowa_bus *bus = &iowa_busses[i];
-		struct pci_controller *phb = bus->phb;
-
-		if (vaddr) {
-			vstart = (unsigned long)phb->io_base_virt;
-			vend = vstart + phb->pci_io_size - 1;
-			if ((vaddr >= vstart) && (vaddr <= vend))
-				return bus;
-		}
-
-		if (paddr)
-			for (j = 0; j < 3; j++) {
-				res = &phb->mem_resources[j];
-				if (paddr >= res->start && paddr <= res->end)
-					return bus;
-			}
-	}
-
-	return NULL;
-}
-
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
-{
-	struct iowa_bus *bus;
-	int token;
-
-	token = PCI_GET_ADDR_TOKEN(addr);
-
-	if (token && token <= iowa_bus_count)
-		bus = &iowa_busses[token - 1];
-	else {
-		unsigned long vaddr, paddr;
-
-		vaddr = (unsigned long)PCI_FIX_ADDR(addr);
-		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
-			return NULL;
-
-		paddr = ppc_find_vmap_phys(vaddr);
-
-		bus = iowa_pci_find(vaddr, paddr);
-
-		if (bus == NULL)
-			return NULL;
-	}
-
-	return bus;
-}
-#else /* CONFIG_PPC_INDIRECT_MMIO */
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
-{
-	return NULL;
-}
-#endif /* !CONFIG_PPC_INDIRECT_MMIO */
-
-#ifdef CONFIG_PPC_INDIRECT_PIO
-struct iowa_bus *iowa_pio_find_bus(unsigned long port)
-{
-	unsigned long vaddr = (unsigned long)pci_io_base + port;
-	return iowa_pci_find(vaddr, 0);
-}
-#else
-struct iowa_bus *iowa_pio_find_bus(unsigned long port)
-{
-	return NULL;
-}
-#endif
-
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
-static ret iowa_##name at					\
-{								\
-	struct iowa_bus *bus;					\
-	bus = iowa_##space##_find_bus(aa);			\
-	if (bus && bus->ops && bus->ops->name)			\
-		return bus->ops->name al;			\
-	return __do_##name al;					\
-}
-
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)		\
-static void iowa_##name at					\
-{								\
-	struct iowa_bus *bus;					\
-	bus = iowa_##space##_find_bus(aa);			\
-	if (bus && bus->ops && bus->ops->name) {		\
-		bus->ops->name al;				\
-		return;						\
-	}							\
-	__do_##name al;						\
-}
-
-#include <asm/io-defs.h>
-
-#undef DEF_PCI_AC_RET
-#undef DEF_PCI_AC_NORET
-
-static const struct ppc_pci_io iowa_pci_io = {
-
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)	.name = iowa_##name,
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)	.name = iowa_##name,
-
-#include <asm/io-defs.h>
-
-#undef DEF_PCI_AC_RET
-#undef DEF_PCI_AC_NORET
-
-};
-
-#ifdef CONFIG_PPC_INDIRECT_MMIO
-void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
-			   pgprot_t prot, void *caller)
-{
-	struct iowa_bus *bus;
-	void __iomem *res = __ioremap_caller(addr, size, prot, caller);
-	int busno;
-
-	bus = iowa_pci_find(0, (unsigned long)addr);
-	if (bus != NULL) {
-		busno = bus - iowa_busses;
-		PCI_SET_ADDR_TOKEN(res, busno + 1);
-	}
-	return res;
-}
-#endif /* !CONFIG_PPC_INDIRECT_MMIO */
-
-bool io_workaround_inited;
-
-/* Enable IO workaround */
-static void io_workaround_init(void)
-{
-	if (io_workaround_inited)
-		return;
-	ppc_pci_io = iowa_pci_io;
-	io_workaround_inited = true;
-}
-
-/* Register new bus to support workaround */
-void iowa_register_bus(struct pci_controller *phb, struct ppc_pci_io *ops,
-		       int (*initfunc)(struct iowa_bus *, void *), void *data)
-{
-	struct iowa_bus *bus;
-	struct device_node *np = phb->dn;
-
-	io_workaround_init();
-
-	if (iowa_bus_count >= IOWA_MAX_BUS) {
-		pr_err("IOWA:Too many pci bridges, "
-		       "workarounds disabled for %pOF\n", np);
-		return;
-	}
-
-	bus = &iowa_busses[iowa_bus_count];
-	bus->phb = phb;
-	bus->ops = ops;
-	bus->private = data;
-
-	if (initfunc)
-		if ((*initfunc)(bus, data))
-			return;
-
-	iowa_bus_count++;
-
-	pr_debug("IOWA:[%d]Add bus, %pOF.\n", iowa_bus_count-1, np);
-}
-
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index 2f29b7d432de..bcc201c01514 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -31,13 +31,14 @@ void _insb(const volatile u8 __iomem *port, void *buf, long count)
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
-		tmp = *port;
+		tmp = *(const volatile u8 __force *)port;
 		eieio();
 		*tbuf++ = tmp;
 	} while (--count != 0);
-	asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+	data_barrier(tmp);
 }
 EXPORT_SYMBOL(_insb);
 
@@ -47,75 +48,80 @@ void _outsb(volatile u8 __iomem *port, const void *buf, long count)
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
-		*port = *tbuf++;
+		*(volatile u8 __force *)port = *tbuf++;
 	} while (--count != 0);
-	asm volatile("sync");
+	mb();
 }
 EXPORT_SYMBOL(_outsb);
 
-void _insw_ns(const volatile u16 __iomem *port, void *buf, long count)
+void _insw(const volatile u16 __iomem *port, void *buf, long count)
 {
 	u16 *tbuf = buf;
 	u16 tmp;
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
-		tmp = *port;
+		tmp = *(const volatile u16 __force *)port;
 		eieio();
 		*tbuf++ = tmp;
 	} while (--count != 0);
-	asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+	data_barrier(tmp);
 }
-EXPORT_SYMBOL(_insw_ns);
+EXPORT_SYMBOL(_insw);
 
-void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count)
+void _outsw(volatile u16 __iomem *port, const void *buf, long count)
 {
 	const u16 *tbuf = buf;
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
-		*port = *tbuf++;
+		*(volatile u16 __force *)port = *tbuf++;
 	} while (--count != 0);
-	asm volatile("sync");
+	mb();
 }
-EXPORT_SYMBOL(_outsw_ns);
+EXPORT_SYMBOL(_outsw);
 
-void _insl_ns(const volatile u32 __iomem *port, void *buf, long count)
+void _insl(const volatile u32 __iomem *port, void *buf, long count)
 {
 	u32 *tbuf = buf;
 	u32 tmp;
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
-		tmp = *port;
+		tmp = *(const volatile u32 __force *)port;
 		eieio();
 		*tbuf++ = tmp;
 	} while (--count != 0);
-	asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+	data_barrier(tmp);
 }
-EXPORT_SYMBOL(_insl_ns);
+EXPORT_SYMBOL(_insl);
 
-void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count)
+void _outsl(volatile u32 __iomem *port, const void *buf, long count)
 {
 	const u32 *tbuf = buf;
 
 	if (unlikely(count <= 0))
 		return;
-	asm volatile("sync");
+
+	mb();
 	do {
-		*port = *tbuf++;
+		*(volatile u32 __force *)port = *tbuf++;
 	} while (--count != 0);
-	asm volatile("sync");
+	mb();
 }
-EXPORT_SYMBOL(_outsl_ns);
+EXPORT_SYMBOL(_outsl);
 
 #define IO_CHECK_ALIGN(v,a) ((((unsigned long)(v)) & ((a) - 1)) == 0)
 
@@ -127,7 +133,7 @@ _memset_io(volatile void __iomem *addr, int c, unsigned long n)
 	lc |= lc << 8;
 	lc |= lc << 16;
 
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 	while(n && !IO_CHECK_ALIGN(p, 4)) {
 		*((volatile u8 *)p) = c;
 		p++;
@@ -143,7 +149,7 @@ _memset_io(volatile void __iomem *addr, int c, unsigned long n)
 		p++;
 		n--;
 	}
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 }
 EXPORT_SYMBOL(_memset_io);
 
@@ -152,7 +158,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src,
 {
 	void *vsrc = (void __force *) src;
 
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 	while(n && (!IO_CHECK_ALIGN(vsrc, 4) || !IO_CHECK_ALIGN(dest, 4))) {
 		*((u8 *)dest) = *((volatile u8 *)vsrc);
 		eieio();
@@ -174,7 +180,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src,
 		dest++;
 		n--;
 	}
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 }
 EXPORT_SYMBOL(_memcpy_fromio);
 
@@ -182,7 +188,7 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
 {
 	void *vdest = (void __force *) dest;
 
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 	while(n && (!IO_CHECK_ALIGN(vdest, 4) || !IO_CHECK_ALIGN(src, 4))) {
 		*((volatile u8 *)vdest) = *((u8 *)src);
 		src++;
@@ -201,6 +207,6 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
 		vdest++;
 		n--;
 	}
-	__asm__ __volatile__ ("sync" : : : "memory");
+	mb();
 }
 EXPORT_SYMBOL(_memcpy_toio);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0089dd49b4cb..0ce71310b7d9 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -16,6 +16,7 @@
 #include <linux/mm.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/dma-mapping.h>
 #include <linux/bitmap.h>
 #include <linux/iommu-helper.h>
@@ -26,6 +27,7 @@
 #include <linux/iommu.h>
 #include <linux/sched.h>
 #include <linux/debugfs.h>
+#include <linux/vmalloc.h>
 #include <asm/io.h>
 #include <asm/iommu.h>
 #include <asm/pci-bridge.h>
@@ -172,17 +174,28 @@ static int fail_iommu_bus_notify(struct notifier_block *nb,
 	return 0;
 }
 
-static struct notifier_block fail_iommu_bus_notifier = {
+/*
+ * PCI and VIO buses need separate notifier_block structs, since they're linked
+ * list nodes.  Sharing a notifier_block would mean that any notifiers later
+ * registered for PCI buses would also get called by VIO buses and vice versa.
+ */
+static struct notifier_block fail_iommu_pci_bus_notifier = {
+	.notifier_call = fail_iommu_bus_notify
+};
+
+#ifdef CONFIG_IBMVIO
+static struct notifier_block fail_iommu_vio_bus_notifier = {
 	.notifier_call = fail_iommu_bus_notify
 };
+#endif
 
 static int __init fail_iommu_setup(void)
 {
 #ifdef CONFIG_PCI
-	bus_register_notifier(&pci_bus_type, &fail_iommu_bus_notifier);
+	bus_register_notifier(&pci_bus_type, &fail_iommu_pci_bus_notifier);
 #endif
 #ifdef CONFIG_IBMVIO
-	bus_register_notifier(&vio_bus_type, &fail_iommu_bus_notifier);
+	bus_register_notifier(&vio_bus_type, &fail_iommu_vio_bus_notifier);
 #endif
 
 	return 0;
@@ -518,7 +531,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		/* Convert entry to a dma_addr_t */
 		entry += tbl->it_offset;
 		dma_addr = entry << tbl->it_page_shift;
-		dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl));
+		dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl));
 
 		DBG("  - %lu pages, entry: %lx, dma_addr: %lx\n",
 			    npages, entry, dma_addr);
@@ -631,7 +644,7 @@ void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 		tbl->it_ops->flush(tbl);
 }
 
-static void iommu_table_clear(struct iommu_table *tbl)
+void iommu_table_clear(struct iommu_table *tbl)
 {
 	/*
 	 * In case of firmware assisted dump system goes through clean
@@ -672,10 +685,10 @@ static void iommu_table_clear(struct iommu_table *tbl)
 #endif
 }
 
-static void iommu_table_reserve_pages(struct iommu_table *tbl,
+void iommu_table_reserve_pages(struct iommu_table *tbl,
 		unsigned long res_start, unsigned long res_end)
 {
-	int i;
+	unsigned long i;
 
 	WARN_ON_ONCE(res_end < res_start);
 	/*
@@ -757,8 +770,8 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
 	iommu_table_clear(tbl);
 
 	if (!welcomed) {
-		printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n",
-		       novmerge ? "disabled" : "enabled");
+		pr_info("IOMMU table initialized, virtual merging %s\n",
+			str_disabled_enabled(novmerge));
 		welcomed = 1;
 	}
 
@@ -835,12 +848,12 @@ EXPORT_SYMBOL_GPL(iommu_tce_table_put);
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
- * comprises a page address and offset into that page. The dma_addr_t
- * returned will point to the same byte within the page as was passed in.
+ * is physical address into that page. The dma_addr_t returned will point
+ * to the same byte within the page as was passed in.
  */
-dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
-			  struct page *page, unsigned long offset, size_t size,
-			  unsigned long mask, enum dma_data_direction direction,
+dma_addr_t iommu_map_phys(struct device *dev, struct iommu_table *tbl,
+			  phys_addr_t phys, size_t size, unsigned long mask,
+			  enum dma_data_direction direction,
 			  unsigned long attrs)
 {
 	dma_addr_t dma_handle = DMA_MAPPING_ERROR;
@@ -850,7 +863,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 
 	BUG_ON(direction == DMA_NONE);
 
-	vaddr = page_address(page) + offset;
+	vaddr = phys_to_virt(phys);
 	uaddr = (unsigned long)vaddr;
 
 	if (tbl) {
@@ -877,7 +890,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 	return dma_handle;
 }
 
-void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
+void iommu_unmap_phys(struct iommu_table *tbl, dma_addr_t dma_handle,
 		      size_t size, enum dma_data_direction direction,
 		      unsigned long attrs)
 {
@@ -905,6 +918,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	unsigned int order;
 	unsigned int nio_pages, io_order;
 	struct page *page;
+	int tcesize = (1 << tbl->it_page_shift);
 
 	size = PAGE_ALIGN(size);
 	order = get_order(size);
@@ -931,7 +945,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	memset(ret, 0, size);
 
 	/* Set up tces to cover the allocated range */
-	nio_pages = size >> tbl->it_page_shift;
+	nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
+
 	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
 			      mask >> tbl->it_page_shift, io_order, 0);
@@ -939,7 +954,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 		free_pages((unsigned long)ret, order);
 		return NULL;
 	}
-	*dma_handle = mapping;
+
+	*dma_handle = mapping | ((u64)ret & (tcesize - 1));
 	return ret;
 }
 
@@ -950,7 +966,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 		unsigned int nio_pages;
 
 		size = PAGE_ALIGN(size);
-		nio_pages = size >> tbl->it_page_shift;
+		nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
 		iommu_free(tbl, dma_handle, nio_pages);
 		size = PAGE_ALIGN(size);
 		free_pages((unsigned long)vaddr, get_order(size));
@@ -973,6 +989,23 @@ unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir)
 EXPORT_SYMBOL_GPL(iommu_direction_to_tce_perm);
 
 #ifdef CONFIG_IOMMU_API
+
+int dev_has_iommu_table(struct device *dev, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_dev **ppdev = data;
+
+	if (!dev)
+		return 0;
+
+	if (device_iommu_mapped(dev)) {
+		*ppdev = pdev;
+		return 1;
+	}
+
+	return 0;
+}
+
 /*
  * SPAPR TCE API
  */
@@ -1060,10 +1093,10 @@ int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa)
 }
 EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
 
-extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
-		struct iommu_table *tbl,
-		unsigned long entry, unsigned long *hpa,
-		enum dma_data_direction *direction)
+long iommu_tce_xchg_no_kill(struct mm_struct *mm,
+			    struct iommu_table *tbl,
+			    unsigned long entry, unsigned long *hpa,
+			    enum dma_data_direction *direction)
 {
 	long ret;
 	unsigned long size = 0;
@@ -1087,57 +1120,6 @@ void iommu_tce_kill(struct iommu_table *tbl,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_kill);
 
-static int iommu_take_ownership(struct iommu_table *tbl)
-{
-	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
-	int ret = 0;
-
-	/*
-	 * VFIO does not control TCE entries allocation and the guest
-	 * can write new TCEs on top of existing ones so iommu_tce_build()
-	 * must be able to release old pages. This functionality
-	 * requires exchange() callback defined so if it is not
-	 * implemented, we disallow taking ownership over the table.
-	 */
-	if (!tbl->it_ops->xchg_no_kill)
-		return -EINVAL;
-
-	spin_lock_irqsave(&tbl->large_pool.lock, flags);
-	for (i = 0; i < tbl->nr_pools; i++)
-		spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
-	if (iommu_table_in_use(tbl)) {
-		pr_err("iommu_tce: it_map is not empty");
-		ret = -EBUSY;
-	} else {
-		memset(tbl->it_map, 0xff, sz);
-	}
-
-	for (i = 0; i < tbl->nr_pools; i++)
-		spin_unlock(&tbl->pools[i].lock);
-	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-
-	return ret;
-}
-
-static void iommu_release_ownership(struct iommu_table *tbl)
-{
-	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
-
-	spin_lock_irqsave(&tbl->large_pool.lock, flags);
-	for (i = 0; i < tbl->nr_pools; i++)
-		spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
-	memset(tbl->it_map, 0, sz);
-
-	iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
-			tbl->it_reserved_end);
-
-	for (i = 0; i < tbl->nr_pools; i++)
-		spin_unlock(&tbl->pools[i].lock);
-	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-}
-
 int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 {
 	/*
@@ -1168,146 +1150,70 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_add_device);
 
-void iommu_del_device(struct device *dev)
-{
-	/*
-	 * Some devices might not have IOMMU table and group
-	 * and we needn't detach them from the associated
-	 * IOMMU groups
-	 */
-	if (!device_iommu_mapped(dev)) {
-		pr_debug("iommu_tce: skipping device %s with no tbl\n",
-			 dev_name(dev));
-		return;
-	}
-
-	iommu_group_remove_device(dev);
-}
-EXPORT_SYMBOL_GPL(iommu_del_device);
-
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
- * A simple iommu_table_group_ops which only allows reusing the existing
- * iommu_table. This handles VFIO for POWER7 or the nested KVM.
- * The ops does not allow creating windows and only allows reusing the existing
- * one if it matches table_group->tce32_start/tce32_size/page_shift.
+ * A simple iommu_ops to allow less cruft in generic VFIO code.
  */
-static unsigned long spapr_tce_get_table_size(__u32 page_shift,
-					      __u64 window_size, __u32 levels)
+static int
+spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
+				    struct device *dev,
+				    struct iommu_domain *old)
 {
-	unsigned long size;
-
-	if (levels > 1)
-		return ~0U;
-	size = window_size >> (page_shift - 3);
-	return size;
-}
-
-static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
-				   __u32 page_shift, __u64 window_size, __u32 levels,
-				   struct iommu_table **ptbl)
-{
-	struct iommu_table *tbl = table_group->tables[0];
-
-	if (num > 0)
-		return -EPERM;
-
-	if (tbl->it_page_shift != page_shift ||
-	    tbl->it_size != (window_size >> page_shift) ||
-	    tbl->it_indirect_levels != levels - 1)
-		return -EINVAL;
-
-	*ptbl = iommu_tce_table_get(tbl);
-	return 0;
-}
-
-static long spapr_tce_set_window(struct iommu_table_group *table_group,
-				 int num, struct iommu_table *tbl)
-{
-	return tbl == table_group->tables[num] ? 0 : -EPERM;
-}
-
-static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
-{
-	return 0;
-}
-
-static long spapr_tce_take_ownership(struct iommu_table_group *table_group)
-{
-	int i, j, rc = 0;
-
-	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
-		struct iommu_table *tbl = table_group->tables[i];
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_table_group *table_group;
+	struct iommu_group *grp;
 
-		if (!tbl || !tbl->it_map)
-			continue;
+	/* At first attach the ownership is already set */
+	if (!domain)
+		return 0;
 
-		rc = iommu_take_ownership(tbl);
-		if (!rc)
-			continue;
+	grp = iommu_group_get(dev);
+	table_group = iommu_group_get_iommudata(grp);
+	/*
+	 * The domain being set to PLATFORM from earlier
+	 * BLOCKED. The table_group ownership has to be released.
+	 */
+	table_group->ops->release_ownership(table_group, dev);
+	iommu_group_put(grp);
 
-		for (j = 0; j < i; ++j)
-			iommu_release_ownership(table_group->tables[j]);
-		return rc;
-	}
 	return 0;
 }
 
-static void spapr_tce_release_ownership(struct iommu_table_group *table_group)
-{
-	int i;
-
-	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
-		struct iommu_table *tbl = table_group->tables[i];
-
-		if (!tbl)
-			continue;
-
-		iommu_table_clear(tbl);
-		if (tbl->it_map)
-			iommu_release_ownership(tbl);
-	}
-}
+static const struct iommu_domain_ops spapr_tce_platform_domain_ops = {
+	.attach_dev = spapr_tce_platform_iommu_attach_dev,
+};
 
-struct iommu_table_group_ops spapr_tce_table_group_ops = {
-	.get_table_size = spapr_tce_get_table_size,
-	.create_table = spapr_tce_create_table,
-	.set_window = spapr_tce_set_window,
-	.unset_window = spapr_tce_unset_window,
-	.take_ownership = spapr_tce_take_ownership,
-	.release_ownership = spapr_tce_release_ownership,
+static struct iommu_domain spapr_tce_platform_domain = {
+	.type = IOMMU_DOMAIN_PLATFORM,
+	.ops = &spapr_tce_platform_domain_ops,
 };
 
-/*
- * A simple iommu_ops to allow less cruft in generic VFIO code.
- */
-static int spapr_tce_blocking_iommu_attach_dev(struct iommu_domain *dom,
-					       struct device *dev)
+static int
+spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain,
+				   struct device *dev, struct iommu_domain *old)
 {
 	struct iommu_group *grp = iommu_group_get(dev);
 	struct iommu_table_group *table_group;
 	int ret = -EINVAL;
 
-	if (!grp)
-		return -ENODEV;
-
+	/*
+	 * FIXME: SPAPR mixes blocked and platform behaviors, the blocked domain
+	 * also sets the dma_api ops
+	 */
 	table_group = iommu_group_get_iommudata(grp);
-	ret = table_group->ops->take_ownership(table_group);
+	ret = table_group->ops->take_ownership(table_group, dev);
 	iommu_group_put(grp);
 
 	return ret;
 }
 
-static void spapr_tce_blocking_iommu_set_platform_dma(struct device *dev)
-{
-	struct iommu_group *grp = iommu_group_get(dev);
-	struct iommu_table_group *table_group;
-
-	table_group = iommu_group_get_iommudata(grp);
-	table_group->ops->release_ownership(table_group);
-}
+static const struct iommu_domain_ops spapr_tce_blocked_domain_ops = {
+	.attach_dev = spapr_tce_blocked_iommu_attach_dev,
+};
 
-static const struct iommu_domain_ops spapr_tce_blocking_domain_ops = {
-	.attach_dev = spapr_tce_blocking_iommu_attach_dev,
+static struct iommu_domain spapr_tce_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	.ops = &spapr_tce_blocked_domain_ops,
 };
 
 static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
@@ -1322,29 +1228,13 @@ static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
 	return false;
 }
 
-static struct iommu_domain *spapr_tce_iommu_domain_alloc(unsigned int type)
-{
-	struct iommu_domain *dom;
-
-	if (type != IOMMU_DOMAIN_BLOCKED)
-		return NULL;
-
-	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
-	if (!dom)
-		return NULL;
-
-	dom->ops = &spapr_tce_blocking_domain_ops;
-
-	return dom;
-}
-
 static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev)
 {
 	struct pci_dev *pdev;
 	struct pci_controller *hose;
 
 	if (!dev_is_pci(dev))
-		return ERR_PTR(-EPERM);
+		return ERR_PTR(-ENODEV);
 
 	pdev = to_pci_dev(dev);
 	hose = pdev->bus->sysdata;
@@ -1371,12 +1261,12 @@ static struct iommu_group *spapr_tce_iommu_device_group(struct device *dev)
 }
 
 static const struct iommu_ops spapr_tce_iommu_ops = {
+	.default_domain = &spapr_tce_platform_domain,
+	.blocked_domain = &spapr_tce_blocked_domain,
 	.capable = spapr_tce_iommu_capable,
-	.domain_alloc = spapr_tce_iommu_domain_alloc,
 	.probe_device = spapr_tce_iommu_probe_device,
 	.release_device = spapr_tce_iommu_release_device,
 	.device_group = spapr_tce_iommu_device_group,
-	.set_platform_dma_ops = spapr_tce_blocking_iommu_set_platform_dma,
 };
 
 static struct attribute *spapr_tce_iommu_attrs[] = {
@@ -1393,6 +1283,21 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = {
 	NULL,
 };
 
+void ppc_iommu_register_device(struct pci_controller *phb)
+{
+	iommu_device_sysfs_add(&phb->iommu, phb->parent,
+				spapr_tce_iommu_groups, "iommu-phb%04x",
+				phb->global_number);
+	iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops,
+				phb->parent);
+}
+
+void ppc_iommu_unregister_device(struct pci_controller *phb)
+{
+	iommu_device_unregister(&phb->iommu);
+	iommu_device_sysfs_remove(&phb->iommu);
+}
+
 /*
  * This registers IOMMU devices of PHBs. This needs to happen
  * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and
@@ -1403,14 +1308,11 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void)
 	struct pci_controller *hose;
 
 	list_for_each_entry(hose, &hose_list, list_node) {
-		iommu_device_sysfs_add(&hose->iommu, hose->parent,
-				       spapr_tce_iommu_groups, "iommu-phb%04x",
-				       hose->global_number);
-		iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops,
-				      hose->parent);
+		ppc_iommu_register_device(hose);
 	}
 	return 0;
 }
 postcore_initcall_sync(spapr_tce_setup_phb_iommus_initcall);
+#endif
 
 #endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 6f7d4edaa0bc..a0e8b998c9b5 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -89,69 +89,69 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 
 #if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT)
 	if (tau_initialized) {
-		seq_printf(p, "%*s: ", prec, "TAU");
+		seq_printf(p, "%*s:", prec, "TAU");
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", tau_interrupts(j));
+			seq_put_decimal_ull_width(p, " ", tau_interrupts(j), 10);
 		seq_puts(p, "  PowerPC             Thermal Assist (cpu temp)\n");
 	}
 #endif /* CONFIG_PPC32 && CONFIG_TAU_INT */
 
-	seq_printf(p, "%*s: ", prec, "LOC");
+	seq_printf(p, "%*s:", prec, "LOC");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event);
+		seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).timer_irqs_event, 10);
         seq_printf(p, "  Local timer interrupts for timer event device\n");
 
-	seq_printf(p, "%*s: ", prec, "BCT");
+	seq_printf(p, "%*s:", prec, "BCT");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat, j).broadcast_irqs_event);
+		seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).broadcast_irqs_event, 10);
 	seq_printf(p, "  Broadcast timer interrupts for timer event device\n");
 
-	seq_printf(p, "%*s: ", prec, "LOC");
+	seq_printf(p, "%*s:", prec, "LOC");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others);
+		seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).timer_irqs_others, 10);
         seq_printf(p, "  Local timer interrupts for others\n");
 
-	seq_printf(p, "%*s: ", prec, "SPU");
+	seq_printf(p, "%*s:", prec, "SPU");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
+		seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).spurious_irqs, 10);
 	seq_printf(p, "  Spurious interrupts\n");
 
-	seq_printf(p, "%*s: ", prec, "PMI");
+	seq_printf(p, "%*s:", prec, "PMI");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
+		seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).pmu_irqs, 10);
 	seq_printf(p, "  Performance monitoring interrupts\n");
 
-	seq_printf(p, "%*s: ", prec, "MCE");
+	seq_printf(p, "%*s:", prec, "MCE");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
+		seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).mce_exceptions, 10);
 	seq_printf(p, "  Machine check exceptions\n");
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (cpu_has_feature(CPU_FTR_HVMODE)) {
-		seq_printf(p, "%*s: ", prec, "HMI");
+		seq_printf(p, "%*s:", prec, "HMI");
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", paca_ptrs[j]->hmi_irqs);
+			seq_put_decimal_ull_width(p, " ", paca_ptrs[j]->hmi_irqs, 10);
 		seq_printf(p, "  Hypervisor Maintenance Interrupts\n");
 	}
 #endif
 
-	seq_printf(p, "%*s: ", prec, "NMI");
+	seq_printf(p, "%*s:", prec, "NMI");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat, j).sreset_irqs);
+		seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).sreset_irqs, 10);
 	seq_printf(p, "  System Reset interrupts\n");
 
 #ifdef CONFIG_PPC_WATCHDOG
-	seq_printf(p, "%*s: ", prec, "WDG");
+	seq_printf(p, "%*s:", prec, "WDG");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat, j).soft_nmi_irqs);
+		seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).soft_nmi_irqs, 10);
 	seq_printf(p, "  Watchdog soft-NMI interrupts\n");
 #endif
 
 #ifdef CONFIG_PPC_DOORBELL
 	if (cpu_has_feature(CPU_FTR_DBELL)) {
-		seq_printf(p, "%*s: ", prec, "DBL");
+		seq_printf(p, "%*s:", prec, "DBL");
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", per_cpu(irq_stat, j).doorbell_irqs);
+			seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, j).doorbell_irqs, 10);
 		seq_printf(p, "  Doorbell interrupts\n");
 	}
 #endif
@@ -284,15 +284,14 @@ static __always_inline void call_do_irq(struct pt_regs *regs, void *sp)
 void __do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	void *cursp, *irqsp, *sirqsp;
+	void *cursp, *irqsp;
 
 	/* Switch to the irq stack to handle this */
 	cursp = (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 	irqsp = hardirq_ctx[raw_smp_processor_id()];
-	sirqsp = softirq_ctx[raw_smp_processor_id()];
 
 	/* Already there ? If not switch stack and call */
-	if (unlikely(cursp == irqsp || cursp == sirqsp))
+	if (unlikely(cursp == irqsp))
 		__do_irq(regs, current_stack_pointer);
 	else
 		call_do_irq(regs, irqsp);
@@ -334,7 +333,7 @@ void __init init_IRQ(void)
 		static_call_update(ppc_get_irq, ppc_md.get_irq);
 }
 
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 void   *critirq_ctx[NR_CPUS] __read_mostly;
 void    *dbgirq_ctx[NR_CPUS] __read_mostly;
 void *mcheckirq_ctx[NR_CPUS] __read_mostly;
diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c
index 938e66829eae..d5c48d1b0a31 100644
--- a/arch/powerpc/kernel/irq_64.c
+++ b/arch/powerpc/kernel/irq_64.c
@@ -230,7 +230,7 @@ again:
 	 * This allows interrupts to be unmasked without hard disabling, and
 	 * also without new hard interrupts coming in ahead of pending ones.
 	 */
-	asm_volatile_goto(
+	asm goto(
 "1:					\n"
 "		lbz	9,%0(13)	\n"
 "		cmpwi	9,0		\n"
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index 85bdd7d3652f..5c064485197a 100644
--- a/arch/powerpc/kernel/isa-bridge.c
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -46,8 +46,8 @@ static void remap_isa_base(phys_addr_t pa, unsigned long size)
 	WARN_ON_ONCE(size & ~PAGE_MASK);
 
 	if (slab_is_available()) {
-		if (ioremap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
-				pgprot_noncached(PAGE_KERNEL)))
+		if (vmap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
+				    pgprot_noncached(PAGE_KERNEL)))
 			vunmap_range(ISA_IO_BASE, ISA_IO_BASE + size);
 	} else {
 		early_ioremap_range(ISA_IO_BASE, pa, size,
@@ -93,11 +93,12 @@ static int process_ISA_OF_ranges(struct device_node *isa_node,
 	}
 
 inval_range:
-	if (!phb_io_base_phys) {
+	if (phb_io_base_phys) {
 		pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n");
 		remap_isa_base(phb_io_base_phys, 0x10000);
+		return 0;
 	}
-	return 0;
+	return -EINVAL;
 }
 
 
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
index 5277cf582c16..2659e1ac8604 100644
--- a/arch/powerpc/kernel/jump_label.c
+++ b/arch/powerpc/kernel/jump_label.c
@@ -5,7 +5,7 @@
 
 #include <linux/kernel.h>
 #include <linux/jump_label.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/inst.h>
 
 void arch_jump_label_transform(struct jump_entry *entry,
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index ebe4d1645ca1..5081334b7bd2 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -21,7 +21,7 @@
 #include <asm/processor.h>
 #include <asm/machdep.h>
 #include <asm/debug.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <linux/slab.h>
 #include <asm/inst.h>
 
@@ -45,7 +45,7 @@ static struct hard_trap_info
 	{ 0x0800, 0x08 /* SIGFPE */  },		/* fp unavailable */
 	{ 0x0900, 0x0e /* SIGALRM */ },		/* decrementer */
 	{ 0x0c00, 0x14 /* SIGCHLD */ },		/* system call */
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 	{ 0x2002, 0x05 /* SIGTRAP */ },		/* debug */
 #if defined(CONFIG_PPC_85xx)
 	{ 0x2010, 0x08 /* SIGFPE */  },		/* spe unavailable */
@@ -64,7 +64,7 @@ static struct hard_trap_info
 	{ 0x2010, 0x08 /* SIGFPE */  },		/* fp unavailable */
 	{ 0x2020, 0x08 /* SIGFPE */  },		/* ap unavailable */
 #endif
-#else /* !CONFIG_BOOKE_OR_40x */
+#else /* !CONFIG_BOOKE */
 	{ 0x0d00, 0x05 /* SIGTRAP */ },		/* single-step */
 #if defined(CONFIG_PPC_8xx)
 	{ 0x1000, 0x04 /* SIGILL */  },		/* software emulation */
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 072ebe7f290b..f8208c027148 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 	struct pt_regs *regs;
 	int bit;
 
+	if (unlikely(kprobe_ftrace_disabled))
+		return;
+
 	bit = ftrace_test_recursion_trylock(nip, parent_nip);
 	if (bit < 0)
 		return;
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index b20ee72e873a..c0d9f12cb441 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -19,9 +19,9 @@
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/slab.h>
-#include <linux/moduleloader.h>
 #include <linux/set_memory.h>
-#include <asm/code-patching.h>
+#include <linux/execmem.h>
+#include <asm/text-patching.h>
 #include <asm/cacheflush.h>
 #include <asm/sstep.h>
 #include <asm/sections.h>
@@ -105,41 +105,25 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
 	return addr;
 }
 
-static bool arch_kprobe_on_func_entry(unsigned long offset)
+static bool arch_kprobe_on_func_entry(unsigned long addr, unsigned long offset)
 {
-#ifdef CONFIG_PPC64_ELF_ABI_V2
-#ifdef CONFIG_KPROBES_ON_FTRACE
-	return offset <= 16;
-#else
-	return offset <= 8;
-#endif
-#else
+	unsigned long ip = ftrace_location(addr);
+
+	if (ip)
+		return offset <= (ip - addr);
+	if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+		return offset <= 8;
 	return !offset;
-#endif
 }
 
 /* XXX try and fold the magic of kprobe_lookup_name() in this */
 kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
 					 bool *on_func_entry)
 {
-	*on_func_entry = arch_kprobe_on_func_entry(offset);
+	*on_func_entry = arch_kprobe_on_func_entry(addr, offset);
 	return (kprobe_opcode_t *)(addr + offset);
 }
 
-void *alloc_insn_page(void)
-{
-	void *page;
-
-	page = module_alloc(PAGE_SIZE);
-	if (!page)
-		return NULL;
-
-	if (strict_module_rwx_enabled())
-		set_memory_rox((unsigned long)page, 1);
-
-	return page;
-}
-
 int arch_prepare_kprobe(struct kprobe *p)
 {
 	int ret = 0;
@@ -242,16 +226,6 @@ static nokprobe_inline void set_current_kprobe(struct kprobe *p, struct pt_regs
 	kcb->kprobe_saved_msr = regs->msr;
 }
 
-void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
-{
-	ri->ret_addr = (kprobe_opcode_t *)regs->link;
-	ri->fp = NULL;
-
-	/* Replace the return addr with trampoline addr */
-	regs->link = (unsigned long)__kretprobe_trampoline;
-}
-NOKPROBE_SYMBOL(arch_prepare_kretprobe);
-
 static int try_to_emulate(struct kprobe *p, struct pt_regs *regs)
 {
 	int ret;
@@ -409,49 +383,6 @@ no_kprobe:
 NOKPROBE_SYMBOL(kprobe_handler);
 
 /*
- * Function return probe trampoline:
- * 	- init_kprobes() establishes a probepoint here
- * 	- When the probed function returns, this probe
- * 		causes the handlers to fire
- */
-asm(".global __kretprobe_trampoline\n"
-	".type __kretprobe_trampoline, @function\n"
-	"__kretprobe_trampoline:\n"
-	"nop\n"
-	"blr\n"
-	".size __kretprobe_trampoline, .-__kretprobe_trampoline\n");
-
-/*
- * Called when the probe at kretprobe trampoline is hit
- */
-static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	unsigned long orig_ret_address;
-
-	orig_ret_address = __kretprobe_trampoline_handler(regs, NULL);
-	/*
-	 * We get here through one of two paths:
-	 * 1. by taking a trap -> kprobe_handler() -> here
-	 * 2. by optprobe branch -> optimized_callback() -> opt_pre_handler() -> here
-	 *
-	 * When going back through (1), we need regs->nip to be setup properly
-	 * as it is used to determine the return address from the trap.
-	 * For (2), since nip is not honoured with optprobes, we instead setup
-	 * the link register properly so that the subsequent 'blr' in
-	 * __kretprobe_trampoline jumps back to the right instruction.
-	 *
-	 * For nip, we should set the address to the previous instruction since
-	 * we end up emulating it in kprobe_handler(), which increments the nip
-	 * again.
-	 */
-	regs_set_return_ip(regs, orig_ret_address - 4);
-	regs->link = orig_ret_address;
-
-	return 0;
-}
-NOKPROBE_SYMBOL(trampoline_probe_handler);
-
-/*
  * Called after single-stepping.  p->addr is the address of the
  * instruction whose first byte has been replaced by the "breakpoint"
  * instruction.  To avoid the SMP problems that can occur when we
@@ -553,19 +484,9 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 }
 NOKPROBE_SYMBOL(kprobe_fault_handler);
 
-static struct kprobe trampoline_p = {
-	.addr = (kprobe_opcode_t *) &__kretprobe_trampoline,
-	.pre_handler = trampoline_probe_handler
-};
-
-int __init arch_init_kprobes(void)
-{
-	return register_kprobe(&trampoline_p);
-}
-
 int arch_trampoline_kprobe(struct kprobe *p)
 {
-	if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline)
+	if (p->addr == (kprobe_opcode_t *)&arch_rethook_trampoline)
 		return 1;
 
 	return 0;
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 5b3c093611ba..7209d00a9c25 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -632,19 +632,19 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
 #endif
 	}
 
-	switch (inst_no_rt & ~KVM_MASK_RB) {
 #ifdef CONFIG_PPC_BOOK3S_32
+	switch (inst_no_rt & ~KVM_MASK_RB) {
 	case KVM_INST_MTSRIN:
 		if (features & KVM_MAGIC_FEAT_SR) {
 			u32 inst_rb = _inst & KVM_MASK_RB;
 			kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb);
 		}
 		break;
-#endif
 	}
+#endif
 
-	switch (_inst) {
 #ifdef CONFIG_BOOKE
+	switch (_inst) {
 	case KVM_INST_WRTEEI_0:
 		kvm_patch_ins_wrteei_0(inst);
 		break;
@@ -652,8 +652,8 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
 	case KVM_INST_WRTEEI_1:
 		kvm_patch_ins_wrtee(inst, 0, 1);
 		break;
-#endif
 	}
+#endif
 }
 
 extern u32 kvm_template_start[];
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index c9ad12461d44..ae1906bfe8a5 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -5,8 +5,8 @@
 #include <linux/serial_core.h>
 #include <linux/console.h>
 #include <linux/pci.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/serial_reg.h>
 #include <asm/io.h>
@@ -54,9 +54,10 @@ static int legacy_serial_console = -1;
 static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
 	UPF_SHARE_IRQ | UPF_FIXED_PORT;
 
-static unsigned int tsi_serial_in(struct uart_port *p, int offset)
+static u32 tsi_serial_in(struct uart_port *p, unsigned int offset)
 {
-	unsigned int tmp;
+	u32 tmp;
+
 	offset = offset << p->regshift;
 	if (offset == UART_IIR) {
 		tmp = readl(p->membase + (UART_IIR & ~3));
@@ -65,7 +66,7 @@ static unsigned int tsi_serial_in(struct uart_port *p, int offset)
 		return readb(p->membase + offset);
 }
 
-static void tsi_serial_out(struct uart_port *p, int offset, int value)
+static void tsi_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	offset = offset << p->regshift;
 	if (!((offset == UART_IER) && (value & UART_IER_UUE)))
@@ -77,6 +78,8 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
 				  phys_addr_t taddr, unsigned long irq,
 				  upf_t flags, int irq_check_parent)
 {
+	struct plat_serial8250_port *legacy_port;
+	struct legacy_serial_info *legacy_info;
 	const __be32 *clk, *spd, *rs;
 	u32 clock = BASE_BAUD * 16;
 	u32 shift = 0;
@@ -110,16 +113,17 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
 	if (index >= legacy_serial_count)
 		legacy_serial_count = index + 1;
 
+	legacy_port = &legacy_serial_ports[index];
+	legacy_info = &legacy_serial_infos[index];
+
 	/* Check if there is a port who already claimed our slot */
-	if (legacy_serial_infos[index].np != NULL) {
+	if (legacy_info->np != NULL) {
 		/* if we still have some room, move it, else override */
 		if (legacy_serial_count < MAX_LEGACY_SERIAL_PORTS) {
 			printk(KERN_DEBUG "Moved legacy port %d -> %d\n",
 			       index, legacy_serial_count);
-			legacy_serial_ports[legacy_serial_count] =
-				legacy_serial_ports[index];
-			legacy_serial_infos[legacy_serial_count] =
-				legacy_serial_infos[index];
+			legacy_serial_ports[legacy_serial_count] = *legacy_port;
+			legacy_serial_infos[legacy_serial_count] = *legacy_info;
 			legacy_serial_count++;
 		} else {
 			printk(KERN_DEBUG "Replacing legacy port %d\n", index);
@@ -127,36 +131,32 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
 	}
 
 	/* Now fill the entry */
-	memset(&legacy_serial_ports[index], 0,
-	       sizeof(struct plat_serial8250_port));
+	memset(legacy_port, 0, sizeof(*legacy_port));
 	if (iotype == UPIO_PORT)
-		legacy_serial_ports[index].iobase = base;
+		legacy_port->iobase = base;
 	else
-		legacy_serial_ports[index].mapbase = base;
-
-	legacy_serial_ports[index].iotype = iotype;
-	legacy_serial_ports[index].uartclk = clock;
-	legacy_serial_ports[index].irq = irq;
-	legacy_serial_ports[index].flags = flags;
-	legacy_serial_ports[index].regshift = shift;
-	legacy_serial_infos[index].taddr = taddr;
-	legacy_serial_infos[index].np = of_node_get(np);
-	legacy_serial_infos[index].clock = clock;
-	legacy_serial_infos[index].speed = spd ? be32_to_cpup(spd) : 0;
-	legacy_serial_infos[index].irq_check_parent = irq_check_parent;
+		legacy_port->mapbase = base;
+
+	legacy_port->iotype = iotype;
+	legacy_port->uartclk = clock;
+	legacy_port->irq = irq;
+	legacy_port->flags = flags;
+	legacy_port->regshift = shift;
+	legacy_info->taddr = taddr;
+	legacy_info->np = of_node_get(np);
+	legacy_info->clock = clock;
+	legacy_info->speed = spd ? be32_to_cpup(spd) : 0;
+	legacy_info->irq_check_parent = irq_check_parent;
 
 	if (iotype == UPIO_TSI) {
-		legacy_serial_ports[index].serial_in = tsi_serial_in;
-		legacy_serial_ports[index].serial_out = tsi_serial_out;
+		legacy_port->serial_in = tsi_serial_in;
+		legacy_port->serial_out = tsi_serial_out;
 	}
 
-	printk(KERN_DEBUG "Found legacy serial port %d for %pOF\n",
-	       index, np);
-	printk(KERN_DEBUG "  %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n",
+	printk(KERN_DEBUG "Found legacy serial port %d for %pOF\n", index, np);
+	printk(KERN_DEBUG "  %s=%pa, taddr=%pa, irq=%lx, clk=%d, speed=%d\n",
 	       (iotype == UPIO_PORT) ? "port" : "mem",
-	       (unsigned long long)base, (unsigned long long)taddr, irq,
-	       legacy_serial_ports[index].uartclk,
-	       legacy_serial_infos[index].speed);
+	       &base, &taddr, irq, legacy_port->uartclk, legacy_info->speed);
 
 	return index;
 }
@@ -508,12 +508,16 @@ static void __init fixup_port_irq(int index,
 
 	port->irq = virq;
 
-#ifdef CONFIG_SERIAL_8250_FSL
-	if (of_device_is_compatible(np, "fsl,ns16550")) {
-		port->handle_irq = fsl8250_handle_irq;
-		port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE);
+	if (IS_ENABLED(CONFIG_SERIAL_8250) &&
+	    of_device_is_compatible(np, "fsl,ns16550")) {
+		if (IS_REACHABLE(CONFIG_SERIAL_8250_FSL)) {
+			port->handle_irq = fsl8250_handle_irq;
+			port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE);
+		} else {
+			pr_warn_once("Not activating Freescale specific workaround for device %pOFP\n",
+				     np);
+		}
 	}
-#endif
 }
 
 static void __init fixup_port_pio(int index,
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index fb7de3543c03..29e1440d14cc 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -10,11 +10,11 @@
  *
  * setjmp/longjmp code by Paul Mackerras.
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
 #include <asm/unistd.h>
 #include <asm/asm-compat.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 
 	.text
 
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index daf8f87d2372..acb727f54e9d 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -8,6 +8,7 @@
  *
  */
 
+#include <linux/export.h>
 #include <linux/sys.h>
 #include <asm/unistd.h>
 #include <asm/errno.h>
@@ -22,38 +23,11 @@
 #include <asm/processor.h>
 #include <asm/bug.h>
 #include <asm/ptrace.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 
 	.text
 
 /*
- * This returns the high 64 bits of the product of two 64-bit numbers.
- */
-_GLOBAL(mulhdu)
-	cmpwi	r6,0
-	cmpwi	cr1,r3,0
-	mr	r10,r4
-	mulhwu	r4,r4,r5
-	beq	1f
-	mulhwu	r0,r10,r6
-	mullw	r7,r10,r5
-	addc	r7,r0,r7
-	addze	r4,r4
-1:	beqlr	cr1		/* all done if high part of A is 0 */
-	mullw	r9,r3,r5
-	mulhwu	r10,r3,r5
-	beq	2f
-	mullw	r0,r3,r6
-	mulhwu	r8,r3,r6
-	addc	r7,r0,r7
-	adde	r4,r4,r8
-	addze	r10,r10
-2:	addc	r4,r4,r9
-	addze	r3,r10
-	blr
-
-/*
  * reloc_got2 runs through the .got2 section adding an offset
  * to each entry.
  */
@@ -176,46 +150,6 @@ _GLOBAL(low_choose_7447a_dfs)
 
 #endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_PPC_BOOK3S_32 */
 
-#ifdef CONFIG_40x
-
-/*
- * Do an IO access in real mode
- */
-_GLOBAL(real_readb)
-	mfmsr	r7
-	rlwinm	r0,r7,0,~MSR_DR
-	sync
-	mtmsr	r0
-	sync
-	isync
-	lbz	r3,0(r3)
-	sync
-	mtmsr	r7
-	sync
-	isync
-	blr
-_ASM_NOKPROBE_SYMBOL(real_readb)
-
-	/*
- * Do an IO access in real mode
- */
-_GLOBAL(real_writeb)
-	mfmsr	r7
-	rlwinm	r0,r7,0,~MSR_DR
-	sync
-	mtmsr	r0
-	sync
-	isync
-	stb	r3,0(r4)
-	sync
-	mtmsr	r7
-	sync
-	isync
-	blr
-_ASM_NOKPROBE_SYMBOL(real_writeb)
-
-#endif /* CONFIG_40x */
-
 /*
  * Copy a whole page.  We use the dcbz instruction on the destination
  * to reduce memory traffic (it eliminates the unnecessary reads of
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 2c9ac70aaf0c..a997c7f43dc0 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -9,6 +9,7 @@
  * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
  */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <linux/sys.h>
 #include <asm/unistd.h>
@@ -23,7 +24,6 @@
 #include <asm/kexec.h>
 #include <asm/ptrace.h>
 #include <asm/mmu.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 
 	.text
@@ -74,7 +74,7 @@ _GLOBAL(rmci_off)
 	blr
 #endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
 
-#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
+#ifdef CONFIG_PPC_PMAC
 
 /*
  * Do an IO access in real mode
@@ -137,7 +137,7 @@ _GLOBAL(real_writeb)
 	sync
 	isync
 	blr
-#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) */
+#endif // CONFIG_PPC_PMAC
 
 #ifdef CONFIG_PPC_PASEMI
 
@@ -174,7 +174,7 @@ _GLOBAL(real_205_writeb)
 #endif /* CONFIG_PPC_PASEMI */
 
 
-#if defined(CONFIG_CPU_FREQ_PMAC64) || defined(CONFIG_CPU_FREQ_MAPLE)
+#ifdef CONFIG_CPU_FREQ_PMAC64
 /*
  * SCOM access functions for 970 (FX only for now)
  *
@@ -192,7 +192,7 @@ _GLOBAL(scom970_read)
 	xori	r0,r0,MSR_EE
 	mtmsrd	r0,1
 
-	/* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
+	/* rotate 24 bits SCOM address 8 bits left and mask out its low 8 bits
 	 * (including parity). On current CPUs they must be 0'd,
 	 * and finally or in RW bit
 	 */
@@ -226,7 +226,7 @@ _GLOBAL(scom970_write)
 	xori	r0,r0,MSR_EE
 	mtmsrd	r0,1
 
-	/* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
+	/* rotate 24 bits SCOM address 8 bits left and mask out its low 8 bits
 	 * (including parity). On current CPUs they must be 0'd.
 	 */
 
@@ -243,7 +243,7 @@ _GLOBAL(scom970_write)
 	/* restore interrupts */
 	mtmsrd	r5,1
 	blr
-#endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */
+#endif // CONFIG_CPU_FREQ_PMAC64
 
 /* kexec_wait(phys_cpu)
  *
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index f6d6ae0a1692..baeb24c102c8 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -7,7 +7,6 @@
 #include <linux/elf.h>
 #include <linux/moduleloader.h>
 #include <linux/err.h>
-#include <linux/vmalloc.h>
 #include <linux/mm.h>
 #include <linux/bug.h>
 #include <asm/module.h>
@@ -17,8 +16,6 @@
 #include <asm/setup.h>
 #include <asm/sections.h>
 
-static LIST_HEAD(module_bug_list);
-
 static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
 				    const Elf_Shdr *sechdrs,
 				    const char *name)
@@ -88,40 +85,3 @@ int module_finalize(const Elf_Ehdr *hdr,
 
 	return 0;
 }
-
-static __always_inline void *
-__module_alloc(unsigned long size, unsigned long start, unsigned long end, bool nowarn)
-{
-	pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
-	gfp_t gfp = GFP_KERNEL | (nowarn ? __GFP_NOWARN : 0);
-
-	/*
-	 * Don't do huge page allocations for modules yet until more testing
-	 * is done. STRICT_MODULE_RWX may require extra work to support this
-	 * too.
-	 */
-	return __vmalloc_node_range(size, 1, start, end, gfp, prot,
-				    VM_FLUSH_RESET_PERMS,
-				    NUMA_NO_NODE, __builtin_return_address(0));
-}
-
-void *module_alloc(unsigned long size)
-{
-#ifdef MODULES_VADDR
-	unsigned long limit = (unsigned long)_etext - SZ_32M;
-	void *ptr = NULL;
-
-	BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
-
-	/* First try within 32M limit from _etext to avoid branch trampolines */
-	if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit)
-		ptr = __module_alloc(size, limit, MODULES_END, true);
-
-	if (!ptr)
-		ptr = __module_alloc(size, MODULES_VADDR, MODULES_END, false);
-
-	return ptr;
-#else
-	return __module_alloc(size, VMALLOC_START, VMALLOC_END, false);
-#endif
-}
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 816a63fd71fb..f930e3395a7f 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -18,7 +18,7 @@
 #include <linux/bug.h>
 #include <linux/sort.h>
 #include <asm/setup.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 
 /* Count how many different relocations (different symbol, different
    addend) */
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 92570289ce08..2a44bc8e2439 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -17,7 +17,7 @@
 #include <linux/kernel.h>
 #include <asm/module.h>
 #include <asm/firmware.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <linux/sort.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -205,10 +205,11 @@ static int relacmp(const void *_x, const void *_y)
 
 /* Get size of potential trampolines required. */
 static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
-				    const Elf64_Shdr *sechdrs)
+				    const Elf64_Shdr *sechdrs,
+				    char *secstrings,
+				    struct module *me)
 {
-	/* One extra reloc so it's always 0-addr terminated */
-	unsigned long relocs = 1;
+	unsigned long relocs = 0;
 	unsigned i;
 
 	/* Every relocated section... */
@@ -241,13 +242,21 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 		}
 	}
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-	/* make the trampoline to the ftrace_caller */
-	relocs++;
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-	/* an additional one for ftrace_regs_caller */
-	relocs++;
-#endif
+	/* stubs for ftrace_caller and ftrace_regs_caller */
+	relocs += IS_ENABLED(CONFIG_DYNAMIC_FTRACE) + IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS);
+
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	/* stubs for the function tracer */
+	for (i = 1; i < hdr->e_shnum; i++) {
+		if (!strcmp(secstrings + sechdrs[i].sh_name, "__patchable_function_entries")) {
+			me->arch.ool_stub_count = sechdrs[i].sh_size / sizeof(unsigned long);
+			me->arch.ool_stub_index = 0;
+			relocs += roundup(me->arch.ool_stub_count * sizeof(struct ftrace_ool_stub),
+					  sizeof(struct ppc64_stub_entry)) /
+				  sizeof(struct ppc64_stub_entry);
+			break;
+		}
+	}
 #endif
 
 	pr_debug("Looks like a total of %lu stubs, max\n", relocs);
@@ -355,6 +364,24 @@ static void dedotify_versions(struct modversion_info *vers,
 		}
 }
 
+/* Same as normal versions, remove a leading dot if present. */
+static void dedotify_ext_version_names(char *str_seq, unsigned long size)
+{
+	unsigned long out = 0;
+	unsigned long in;
+	char last = '\0';
+
+	for (in = 0; in < size; in++) {
+		/* Skip one leading dot */
+		if (last == '\0' && str_seq[in] == '.')
+			in++;
+		last = str_seq[in];
+		str_seq[out++] = last;
+	}
+	/* Zero the trailing portion of the names table for robustness */
+	memset(&str_seq[out], 0, size - out);
+}
+
 /*
  * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC.
  * seem to be defined (value set later).
@@ -424,10 +451,12 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 			me->arch.toc_section = i;
 			if (sechdrs[i].sh_addralign < 8)
 				sechdrs[i].sh_addralign = 8;
-		}
-		else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0)
+		} else if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0)
 			dedotify_versions((void *)hdr + sechdrs[i].sh_offset,
 					  sechdrs[i].sh_size);
+		else if (strcmp(secstrings + sechdrs[i].sh_name, "__version_ext_names") == 0)
+			dedotify_ext_version_names((void *)hdr + sechdrs[i].sh_offset,
+						   sechdrs[i].sh_size);
 
 		if (sechdrs[i].sh_type == SHT_SYMTAB)
 			dedotify((void *)hdr + sechdrs[i].sh_offset,
@@ -460,12 +489,12 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 #endif
 
 	/* Override the stubs size */
-	sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs);
+	sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs, secstrings, me);
 
 	return 0;
 }
 
-#ifdef CONFIG_MPROFILE_KERNEL
+#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
 
 static u32 stub_insns[] = {
 #ifdef CONFIG_PPC_KERNEL_PCREL
@@ -651,12 +680,11 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
 	// func_desc_t is 8 bytes if ABIv2, else 16 bytes
 	desc = func_desc(addr);
 	for (i = 0; i < sizeof(func_desc_t) / sizeof(u32); i++) {
-		if (patch_instruction(((u32 *)&entry->funcdata) + i,
-				      ppc_inst(((u32 *)(&desc))[i])))
+		if (patch_u32(((u32 *)&entry->funcdata) + i, ((u32 *)&desc)[i]))
 			return 0;
 	}
 
-	if (patch_instruction(&entry->magic, ppc_inst(STUB_MAGIC)))
+	if (patch_u32(&entry->magic, STUB_MAGIC))
 		return 0;
 
 	return 1;
@@ -676,7 +704,7 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
 
 	/* Find this stub, or if that fails, the next avail. entry */
 	stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr;
-	for (i = 0; stub_func_addr(stubs[i].funcdata); i++) {
+	for (i = 0; i < me->arch.stub_count; i++) {
 		if (WARN_ON(i >= num_stubs))
 			return 0;
 
@@ -687,6 +715,7 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
 	if (!create_stub(sechdrs, &stubs[i], addr, me, name))
 		return 0;
 
+	me->arch.stub_count++;
 	return (unsigned long)&stubs[i];
 }
 
@@ -1086,6 +1115,27 @@ int module_trampoline_target(struct module *mod, unsigned long addr,
 	return 0;
 }
 
+static int setup_ftrace_ool_stubs(const Elf64_Shdr *sechdrs, unsigned long addr, struct module *me)
+{
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	unsigned int total_stubs, num_stubs;
+	struct ppc64_stub_entry *stub;
+
+	total_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stub);
+	num_stubs = roundup(me->arch.ool_stub_count * sizeof(struct ftrace_ool_stub),
+			    sizeof(struct ppc64_stub_entry)) / sizeof(struct ppc64_stub_entry);
+
+	if (WARN_ON(me->arch.stub_count + num_stubs > total_stubs))
+		return -1;
+
+	stub = (void *)sechdrs[me->arch.stubs_section].sh_addr;
+	me->arch.ool_stubs = (struct ftrace_ool_stub *)(stub + me->arch.stub_count);
+	me->arch.stub_count += num_stubs;
+#endif
+
+	return 0;
+}
+
 int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
 {
 	mod->arch.tramp = stub_for_addr(sechdrs,
@@ -1104,6 +1154,9 @@ int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
 	if (!mod->arch.tramp)
 		return -ENOENT;
 
+	if (setup_ftrace_ool_stubs(sechdrs, mod->arch.tramp, mod))
+		return -ENOENT;
+
 	return 0;
 }
 #endif
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index e385d3164648..f9c6568a9137 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -73,7 +73,7 @@ static const char *nvram_os_partitions[] = {
 };
 
 static void oops_to_nvram(struct kmsg_dumper *dumper,
-			  enum kmsg_dump_reason reason);
+			  struct kmsg_dump_detail *detail);
 
 static struct kmsg_dumper nvram_kmsg_dumper = {
 	.dump = oops_to_nvram
@@ -643,7 +643,7 @@ void __init nvram_init_oops_partition(int rtas_partition_exists)
  * partition.  If that's too much, go back and capture uncompressed text.
  */
 static void oops_to_nvram(struct kmsg_dumper *dumper,
-			  enum kmsg_dump_reason reason)
+			  struct kmsg_dump_detail *detail)
 {
 	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
 	static unsigned int oops_count = 0;
@@ -655,7 +655,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 	unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ;
 	int rc = -1;
 
-	switch (reason) {
+	switch (detail->reason) {
 	case KMSG_DUMP_SHUTDOWN:
 		/* These are almost always orderly shutdowns. */
 		return;
@@ -671,7 +671,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 		break;
 	default:
 		pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n",
-		       __func__, (int) reason);
+		       __func__, (int) detail->reason);
 		return;
 	}
 
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
deleted file mode 100644
index f89376ff633e..000000000000
--- a/arch/powerpc/kernel/of_platform.c
+++ /dev/null
@@ -1,104 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *    Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp.
- *			 <benh@kernel.crashing.org>
- *    and		 Arnd Bergmann, IBM Corp.
- */
-
-#undef DEBUG
-
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/export.h>
-#include <linux/mod_devicetable.h>
-#include <linux/pci.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_platform.h>
-#include <linux/atomic.h>
-
-#include <asm/errno.h>
-#include <asm/topology.h>
-#include <asm/pci-bridge.h>
-#include <asm/ppc-pci.h>
-#include <asm/eeh.h>
-
-#ifdef CONFIG_PPC_OF_PLATFORM_PCI
-
-/* The probing of PCI controllers from of_platform is currently
- * 64 bits only, mostly due to gratuitous differences between
- * the 32 and 64 bits PCI code on PowerPC and the 32 bits one
- * lacking some bits needed here.
- */
-
-static int of_pci_phb_probe(struct platform_device *dev)
-{
-	struct pci_controller *phb;
-
-	/* Check if we can do that ... */
-	if (ppc_md.pci_setup_phb == NULL)
-		return -ENODEV;
-
-	pr_info("Setting up PCI bus %pOF\n", dev->dev.of_node);
-
-	/* Alloc and setup PHB data structure */
-	phb = pcibios_alloc_controller(dev->dev.of_node);
-	if (!phb)
-		return -ENODEV;
-
-	/* Setup parent in sysfs */
-	phb->parent = &dev->dev;
-
-	/* Setup the PHB using arch provided callback */
-	if (ppc_md.pci_setup_phb(phb)) {
-		pcibios_free_controller(phb);
-		return -ENODEV;
-	}
-
-	/* Process "ranges" property */
-	pci_process_bridge_OF_ranges(phb, dev->dev.of_node, 0);
-
-	/* Init pci_dn data structures */
-	pci_devs_phb_init_dynamic(phb);
-
-	/* Create EEH PE for the PHB */
-	eeh_phb_pe_create(phb);
-
-	/* Scan the bus */
-	pcibios_scan_phb(phb);
-	if (phb->bus == NULL)
-		return -ENXIO;
-
-	/* Claim resources. This might need some rework as well depending
-	 * whether we are doing probe-only or not, like assigning unassigned
-	 * resources etc...
-	 */
-	pcibios_claim_one_bus(phb->bus);
-
-	/* Add probed PCI devices to the device model */
-	pci_bus_add_devices(phb->bus);
-
-	return 0;
-}
-
-static const struct of_device_id of_pci_phb_ids[] = {
-	{ .type = "pci", },
-	{ .type = "pcix", },
-	{ .type = "pcie", },
-	{ .type = "pciex", },
-	{ .type = "ht", },
-	{}
-};
-
-static struct platform_driver of_pci_phb_driver = {
-	.probe = of_pci_phb_probe,
-	.driver = {
-		.name = "of-pci",
-		.of_match_table = of_pci_phb_ids,
-	},
-};
-
-builtin_platform_driver(of_pci_phb_driver);
-
-#endif /* CONFIG_PPC_OF_PLATFORM_PCI */
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
index 004fae2044a3..2e83702bf9ba 100644
--- a/arch/powerpc/kernel/optprobes.c
+++ b/arch/powerpc/kernel/optprobes.c
@@ -13,7 +13,7 @@
 #include <asm/kprobes.h>
 #include <asm/ptrace.h>
 #include <asm/cacheflush.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/sstep.h>
 #include <asm/ppc-opcode.h>
 #include <asm/inst.h>
@@ -56,7 +56,7 @@ static unsigned long can_optimize(struct kprobe *p)
 	 * has a 'nop' instruction, which can be emulated.
 	 * So further checks can be skipped.
 	 */
-	if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline)
+	if (p->addr == (kprobe_opcode_t *)&arch_rethook_trampoline)
 		return addr + sizeof(kprobe_opcode_t);
 
 	/*
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index cda4e00b67c1..7502066c3c53 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -68,7 +68,7 @@ static void *__init alloc_shared_lppaca(unsigned long size, unsigned long limit,
 		memblock_set_bottom_up(true);
 
 		/*
-		 * See Documentation/powerpc/ultravisor.rst for more details.
+		 * See Documentation/arch/powerpc/ultravisor.rst for more details.
 		 *
 		 * UV/HV data sharing is in PAGE_SIZE granularity. In order to
 		 * minimize the number of pages shared, align the allocation to
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index e88d7c9feeec..eac84d687b53 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -125,7 +125,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 {
 	struct pci_controller *phb;
 
-	phb = zalloc_maybe_bootmem(sizeof(struct pci_controller), GFP_KERNEL);
+	phb = kzalloc(sizeof(struct pci_controller), GFP_KERNEL);
 	if (phb == NULL)
 		return NULL;
 
@@ -517,12 +517,11 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma)
 }
 
 /*
- * This one is used by /dev/mem and fbdev who have no clue about the
+ * This one is used by /dev/mem and video who have no clue about the
  * PCI device, it tries to find the PCI device first and calls the
  * above routine
  */
-pgprot_t pci_phys_mem_access_prot(struct file *file,
-				  unsigned long pfn,
+pgprot_t pci_phys_mem_access_prot(unsigned long pfn,
 				  unsigned long size,
 				  pgprot_t prot)
 {
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 0fe251c6ac2c..6f444d0822d8 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -93,6 +93,36 @@ void pci_hp_remove_devices(struct pci_bus *bus)
 }
 EXPORT_SYMBOL_GPL(pci_hp_remove_devices);
 
+static void traverse_siblings_and_scan_slot(struct device_node *start, struct pci_bus *bus)
+{
+	struct device_node *dn;
+	int slotno;
+
+	u32 class = 0;
+
+	if (!of_property_read_u32(start->child, "class-code", &class)) {
+		/* Call of pci_scan_slot for non-bridge/EP case */
+		if (!((class >> 8) == PCI_CLASS_BRIDGE_PCI)) {
+			slotno = PCI_SLOT(PCI_DN(start->child)->devfn);
+			pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+			return;
+		}
+	}
+
+	/* Iterate all siblings */
+	for_each_child_of_node(start, dn) {
+		class = 0;
+
+		if (!of_property_read_u32(start->child, "class-code", &class)) {
+			/* Call of pci_scan_slot on each sibling-nodes/bridge-ports */
+			if ((class >> 8) == PCI_CLASS_BRIDGE_PCI) {
+				slotno = PCI_SLOT(PCI_DN(dn)->devfn);
+				pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+			}
+		}
+	}
+}
+
 /**
  * pci_hp_add_devices - adds new pci devices to bus
  * @bus: the indicated PCI bus
@@ -106,11 +136,14 @@ EXPORT_SYMBOL_GPL(pci_hp_remove_devices);
  */
 void pci_hp_add_devices(struct pci_bus *bus)
 {
-	int slotno, mode, max;
+	int mode, max;
 	struct pci_dev *dev;
 	struct pci_controller *phb;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
+	if (!dn)
+		return;
+
 	phb = pci_bus_to_host(bus);
 
 	mode = PCI_PROBE_NORMAL;
@@ -129,8 +162,7 @@ void pci_hp_add_devices(struct pci_bus *bus)
 		 * order for fully rescan all the way down to pick them up.
 		 * They can have been removed during partial hotplug.
 		 */
-		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
-		pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+		traverse_siblings_and_scan_slot(dn, bus);
 		max = bus->busn_res.start;
 		/*
 		 * Scan bridges that are already configured. We don't touch
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index ce0c8623e563..f8a3bd8cfae4 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -213,11 +213,8 @@ pci_create_OF_bus_map(void)
 	struct property* of_prop;
 	struct device_node *dn;
 
-	of_prop = memblock_alloc(sizeof(struct property) + 256,
+	of_prop = memblock_alloc_or_panic(sizeof(struct property) + 256,
 				 SMP_CACHE_BYTES);
-	if (!of_prop)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(struct property) + 256);
 	dn = of_find_node_by_path("/");
 	if (dn) {
 		memset(of_prop, -1, sizeof(struct property) + 256);
diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c
index 15414c8a2837..9fabb4d9235e 100644
--- a/arch/powerpc/kernel/pmc.c
+++ b/arch/powerpc/kernel/pmc.c
@@ -74,7 +74,7 @@ void release_pmc_hardware(void)
 }
 EXPORT_SYMBOL_GPL(release_pmc_hardware);
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
 void power4_enable_pmcs(void)
 {
 	unsigned long hid0;
diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S
index 49813f982468..a9b9c32d0c1f 100644
--- a/arch/powerpc/kernel/ppc_save_regs.S
+++ b/arch/powerpc/kernel/ppc_save_regs.S
@@ -31,10 +31,10 @@ _GLOBAL(ppc_save_regs)
 	lbz	r0,PACAIRQSOFTMASK(r13)
 	PPC_STL	r0,SOFTE(r3)
 #endif
-	/* go up one stack frame for SP */
-	PPC_LL	r4,0(r1)
-	PPC_STL	r4,GPR1(r3)
+	/* store current SP */
+	PPC_STL	r1,GPR1(r3)
 	/* get caller's LR */
+	PPC_LL	r4,0(r1)
 	PPC_LL	r0,LRSAVE(r4)
 	PPC_STL	r0,_LINK(r3)
 	mflr	r0
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index b109cd7b5d01..d083b4517065 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -4,17 +4,20 @@
  */
 
 #include <linux/init.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/proc_fs.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
+#include <linux/string.h>
 
 #include <asm/machdep.h>
 #include <asm/vdso_datapage.h>
 #include <asm/rtas.h>
+#include <asm/systemcfg.h>
 #include <linux/uaccess.h>
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
 
 static loff_t page_map_seek(struct file *file, loff_t off, int whence)
 {
@@ -33,10 +36,9 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma )
 	if ((vma->vm_end - vma->vm_start) > PAGE_SIZE)
 		return -EINVAL;
 
-	remap_pfn_range(vma, vma->vm_start,
-			__pa(pde_data(file_inode(file))) >> PAGE_SHIFT,
-			PAGE_SIZE, vma->vm_page_prot);
-	return 0;
+	return remap_pfn_range(vma, vma->vm_start,
+			       __pa(pde_data(file_inode(file))) >> PAGE_SHIFT,
+			       PAGE_SIZE, vma->vm_page_prot);
 }
 
 static const struct proc_ops page_map_proc_ops = {
@@ -45,13 +47,35 @@ static const struct proc_ops page_map_proc_ops = {
 	.proc_mmap	= page_map_mmap,
 };
 
+static union {
+	struct systemcfg	data;
+	u8			page[PAGE_SIZE];
+} systemcfg_data_store __page_aligned_data;
+struct systemcfg *systemcfg = &systemcfg_data_store.data;
 
 static int __init proc_ppc64_init(void)
 {
 	struct proc_dir_entry *pde;
 
+	strscpy(systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
+	systemcfg->version.major = SYSTEMCFG_MAJOR;
+	systemcfg->version.minor = SYSTEMCFG_MINOR;
+	systemcfg->processor = mfspr(SPRN_PVR);
+	/*
+	 * Fake the old platform number for pSeries and add
+	 * in LPAR bit if necessary
+	 */
+	systemcfg->platform = 0x100;
+	if (firmware_has_feature(FW_FEATURE_LPAR))
+		systemcfg->platform |= 1;
+	systemcfg->physicalMemorySize = memblock_phys_mem_size();
+	systemcfg->dcache_size = ppc64_caches.l1d.size;
+	systemcfg->dcache_line_size = ppc64_caches.l1d.line_size;
+	systemcfg->icache_size = ppc64_caches.l1i.size;
+	systemcfg->icache_line_size = ppc64_caches.l1i.line_size;
+
 	pde = proc_create_data("powerpc/systemcfg", S_IFREG | 0444, NULL,
-			       &page_map_proc_ops, vdso_data);
+			       &page_map_proc_ops, systemcfg);
 	if (!pde)
 		return 1;
 	proc_set_size(pde, PAGE_SIZE);
@@ -60,7 +84,7 @@ static int __init proc_ppc64_init(void)
 }
 __initcall(proc_ppc64_init);
 
-#endif /* CONFIG_PPC64 */
+#endif /* CONFIG_PPC64_PROC_SYSTEMCFG */
 
 /*
  * Create the ppc64 and ppc64/rtas directories early. This allows us to
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 1fefafb2b29b..a45fe147868b 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -54,7 +54,7 @@
 #include <asm/firmware.h>
 #include <asm/hw_irq.h>
 #endif
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/exec.h>
 #include <asm/livepatch.h>
 #include <asm/cpu_has_feature.h>
@@ -72,8 +72,6 @@
 #define TM_DEBUG(x...) do { } while(0)
 #endif
 
-extern unsigned long _get_SP(void);
-
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 /*
  * Are we running in "Suspend disabled" mode? If so we have to block any
@@ -1002,7 +1000,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk)
 
 	WARN_ON(tm_suspend_disabled);
 
-	TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, "
+	TM_DEBUG("---- tm_reclaim on pid %d (NIP=%lx, "
 		 "ccr=%lx, msr=%lx, trap=%lx)\n",
 		 tsk->pid, thr->regs->nip,
 		 thr->regs->ccr, thr->regs->msr,
@@ -1010,7 +1008,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk)
 
 	tm_reclaim_thread(thr, TM_CAUSE_RESCHED);
 
-	TM_DEBUG("--- tm_reclaim on pid %d complete\n",
+	TM_DEBUG("---- tm_reclaim on pid %d complete\n",
 		 tsk->pid);
 
 out_and_saveregs:
@@ -1182,6 +1180,12 @@ static inline void save_sprs(struct thread_struct *t)
 		 */
 		t->tar = mfspr(SPRN_TAR);
 	}
+
+	if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE))
+		t->hashkeyr = mfspr(SPRN_HASHKEYR);
+
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		t->dexcr = mfspr(SPRN_DEXCR);
 #endif
 }
 
@@ -1195,11 +1199,11 @@ void kvmppc_save_user_regs(void)
 
 	usermsr = current->thread.regs->msr;
 
+	/* Caller has enabled FP/VEC/VSX/TM in MSR */
 	if (usermsr & MSR_FP)
-		save_fpu(current);
-
+		__giveup_fpu(current);
 	if (usermsr & MSR_VEC)
-		save_altivec(current);
+		__giveup_altivec(current);
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (usermsr & MSR_TM) {
@@ -1260,6 +1264,14 @@ static inline void restore_sprs(struct thread_struct *old_thread,
 	if (cpu_has_feature(CPU_FTR_P9_TIDR) &&
 	    old_thread->tidr != new_thread->tidr)
 		mtspr(SPRN_TIDR, new_thread->tidr);
+
+	if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) &&
+	    old_thread->hashkeyr != new_thread->hashkeyr)
+		mtspr(SPRN_HASHKEYR, new_thread->hashkeyr);
+
+	if (cpu_has_feature(CPU_FTR_ARCH_31) &&
+	    old_thread->dexcr != new_thread->dexcr)
+		mtspr(SPRN_DEXCR, new_thread->dexcr);
 #endif
 
 }
@@ -1559,7 +1571,7 @@ static void __show_regs(struct pt_regs *regs)
 	if (trap == INTERRUPT_MACHINE_CHECK ||
 	    trap == INTERRUPT_DATA_STORAGE ||
 	    trap == INTERRUPT_ALIGNMENT) {
-		if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
+		if (IS_ENABLED(CONFIG_BOOKE))
 			pr_cont("DEAR: "REG" ESR: "REG" ", regs->dear, regs->esr);
 		else
 			pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
@@ -1627,6 +1639,13 @@ void arch_setup_new_exec(void)
 	current->thread.regs->amr  = default_amr;
 	current->thread.regs->iamr  = default_iamr;
 #endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+		current->thread.dexcr = current->thread.dexcr_onexec;
+		mtspr(SPRN_DEXCR, current->thread.dexcr);
+	}
+#endif /* CONFIG_PPC_BOOK3S_64 */
 }
 
 #ifdef CONFIG_PPC64
@@ -1640,7 +1659,7 @@ void arch_setup_new_exec(void)
  * cases will happen:
  *
  * 1. The correct thread is running, the wrong thread is not
- * In this situation, the correct thread is woken and proceeds to pass it's
+ * In this situation, the correct thread is woken and proceeds to pass its
  * condition check.
  *
  * 2. Neither threads are running
@@ -1650,15 +1669,15 @@ void arch_setup_new_exec(void)
  * for the wrong thread, or they will execute the condition check immediately.
  *
  * 3. The wrong thread is running, the correct thread is not
- * The wrong thread will be woken, but will fail it's condition check and
+ * The wrong thread will be woken, but will fail its condition check and
  * re-execute wait. The correct thread, when scheduled, will execute either
- * it's condition check (which will pass), or wait, which returns immediately
- * when called the first time after the thread is scheduled, followed by it's
+ * its condition check (which will pass), or wait, which returns immediately
+ * when called the first time after the thread is scheduled, followed by its
  * condition check (which will pass).
  *
  * 4. Both threads are running
- * Both threads will be woken. The wrong thread will fail it's condition check
- * and execute another wait, while the correct thread will pass it's condition
+ * Both threads will be woken. The wrong thread will fail its condition check
+ * and execute another wait, while the correct thread will pass its condition
  * check.
  *
  * @t: the task to set the thread ID for
@@ -1786,7 +1805,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 			f = ret_from_kernel_user_thread;
 		} else {
 			struct pt_regs *regs = current_pt_regs();
-			unsigned long clone_flags = args->flags;
+			u64 clone_flags = args->flags;
 			unsigned long usp = args->stack;
 
 			/* Copy registers */
@@ -1854,7 +1873,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 #if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
 	p->thread.kuap = KUAP_NONE;
 #endif
-#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP)
+#if defined(CONFIG_BOOKE) && defined(CONFIG_PPC_KUAP)
 	p->thread.pid = MMU_NO_CONTEXT;
 #endif
 
@@ -1868,11 +1887,16 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 	p->thread.tidr = 0;
 #endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE))
+		p->thread.hashkeyr = current->thread.hashkeyr;
+
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		p->thread.dexcr = mfspr(SPRN_DEXCR);
+#endif
 	return 0;
 }
 
-void preload_new_slb_context(unsigned long start, unsigned long sp);
-
 /*
  * Set up a thread for executing a new program
  */
@@ -1880,9 +1904,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 {
 #ifdef CONFIG_PPC64
 	unsigned long load_addr = regs->gpr[2];	/* saved by ELF_PLAT_INIT */
-
-	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled())
-		preload_new_slb_context(start, sp);
 #endif
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1934,8 +1955,8 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 			 * address of _start and the second entry is the TOC
 			 * value we need to use.
 			 */
-			__get_user(entry, (unsigned long __user *)start);
-			__get_user(toc, (unsigned long __user *)start+1);
+			get_user(entry, (unsigned long __user *)start);
+			get_user(toc, (unsigned long __user *)start+1);
 
 			/* Check whether the e_entry function descriptor entries
 			 * need to be relocated before we can use them.
@@ -1984,6 +2005,12 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.tm_tfiar = 0;
 	current->thread.load_tm = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
+		current->thread.hashkeyr = get_random_long();
+		mtspr(SPRN_HASHKEYR, current->thread.hashkeyr);
+	}
+#endif /* CONFIG_PPC_BOOK3S_64 */
 }
 EXPORT_SYMBOL(start_thread);
 
@@ -2143,10 +2170,10 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
 	return 0;
 }
 
+#ifdef CONFIG_PPC64
 static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
 					unsigned long nbytes)
 {
-#ifdef CONFIG_PPC64
 	unsigned long stack_page;
 	unsigned long cpu = task_cpu(p);
 
@@ -2174,10 +2201,26 @@ static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
 	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
 		return 1;
 # endif
-#endif
 
 	return 0;
 }
+#else
+static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
+					unsigned long nbytes)
+{
+	unsigned long stack_page;
+	unsigned long cpu = task_cpu(p);
+
+	if (!IS_ENABLED(CONFIG_VMAP_STACK))
+		return 0;
+
+	stack_page = (unsigned long)emergency_ctx[cpu] - THREAD_SIZE;
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+		return 1;
+
+	return 0;
+}
+#endif
 
 /*
  * validate the stack frame of a particular minimum size, used for when we are
@@ -2241,6 +2284,22 @@ unsigned long __get_wchan(struct task_struct *p)
 	return ret;
 }
 
+static bool empty_user_regs(struct pt_regs *regs, struct task_struct *tsk)
+{
+	unsigned long stack_page;
+
+	// A non-empty pt_regs should never have a zero MSR or TRAP value.
+	if (regs->msr || regs->trap)
+		return false;
+
+	// Check it sits at the very base of the stack
+	stack_page = (unsigned long)task_stack_page(tsk);
+	if ((unsigned long)(regs + 1) != stack_page + THREAD_SIZE)
+		return false;
+
+	return true;
+}
+
 static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
 
 void __no_sanitize_address show_stack(struct task_struct *tsk,
@@ -2303,11 +2362,15 @@ void __no_sanitize_address show_stack(struct task_struct *tsk,
 				(sp + STACK_INT_FRAME_REGS);
 
 			lr = regs->link;
-			printk("%s--- interrupt: %lx at %pS\n",
+			printk("%s---- interrupt: %lx at %pS\n",
 			       loglvl, regs->trap, (void *)regs->nip);
-			__show_regs(regs);
-			printk("%s--- interrupt: %lx\n",
-			       loglvl, regs->trap);
+
+			// Detect the case of an empty pt_regs at the very base
+			// of the stack and suppress showing it in full.
+			if (!empty_user_regs(regs, tsk)) {
+				__show_regs(regs);
+				printk("%s---- interrupt: %lx\n", loglvl, regs->trap);
+			}
 
 			firstframe = 1;
 		}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 9d9ee4e9e1a1..9ed9dde7d231 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -151,6 +151,9 @@ static void __init move_device_tree(void)
  * pa-features property is missing, or a 1/0 to indicate if the feature
  * is supported/not supported.  Note that the bit numbers are
  * big-endian to match the definition in PAPR.
+ * Note: the 'clear' flag clears the feature if the bit is set in the
+ * ibm,pa/pi-features property, it does not set the feature if the
+ * bit is clear.
  */
 struct ibm_feature {
 	unsigned long	cpu_features;	/* CPU_FTR_xxx bit */
@@ -159,7 +162,7 @@ struct ibm_feature {
 	unsigned int	cpu_user_ftrs2;	/* PPC_FEATURE2_xxx bit */
 	unsigned char	pabyte;		/* byte number in ibm,pa/pi-features */
 	unsigned char	pabit;		/* bit number (big-endian) */
-	unsigned char	invert;		/* if 1, pa bit set => clear feature */
+	unsigned char	clear;		/* if 1, pa bit set => clear feature */
 };
 
 static struct ibm_feature ibm_pa_features[] __initdata = {
@@ -182,6 +185,7 @@ static struct ibm_feature ibm_pa_features[] __initdata = {
 	  .cpu_user_ftrs2 = PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_HTM_NOSC_COMP },
 
 	{ .pabyte = 64, .pabit = 0, .cpu_features = CPU_FTR_DAWR1 },
+	{ .pabyte = 68, .pabit = 5, .cpu_features = CPU_FTR_DEXCR_NPHIE },
 };
 
 /*
@@ -192,6 +196,7 @@ static struct ibm_feature ibm_pa_features[] __initdata = {
  */
 static struct ibm_feature ibm_pi_features[] __initdata = {
 	{ .pabyte = 0, .pabit = 3, .mmu_features  = MMU_FTR_NX_DSI },
+	{ .pabyte = 0, .pabit = 4, .cpu_features  = CPU_FTR_DBELL, .clear = 1 },
 };
 
 static void __init scan_features(unsigned long node, const unsigned char *ftrs,
@@ -219,12 +224,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs,
 		if (fp->pabyte >= ftrs[0])
 			continue;
 		bit = (ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1;
-		if (bit ^ fp->invert) {
+		if (bit && !fp->clear) {
 			cur_cpu_spec->cpu_features |= fp->cpu_features;
 			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
 			cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2;
 			cur_cpu_spec->mmu_features |= fp->mmu_features;
-		} else {
+		} else if (bit == fp->clear) {
 			cur_cpu_spec->cpu_features &= ~fp->cpu_features;
 			cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
 			cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2;
@@ -326,6 +331,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 					  void *data)
 {
 	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *cpu_version = NULL;
 	const __be32 *prop;
 	const __be32 *intserv;
 	int i, nthreads;
@@ -367,13 +373,31 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	if (found < 0)
 		return 0;
 
-	DBG("boot cpu: logical %d physical %d\n", found,
-	    be32_to_cpu(intserv[found_thread]));
 	boot_cpuid = found;
 
 	if (IS_ENABLED(CONFIG_PPC64))
 		boot_cpu_hwid = be32_to_cpu(intserv[found_thread]);
 
+	if (nr_cpu_ids % nthreads != 0) {
+		set_nr_cpu_ids(ALIGN(nr_cpu_ids, nthreads));
+		pr_warn("nr_cpu_ids was not a multiple of threads_per_core, adjusted to %d\n",
+			nr_cpu_ids);
+	}
+
+	if (boot_cpuid >= nr_cpu_ids) {
+		// Remember boot core for smp_setup_cpu_maps()
+		boot_core_hwid = be32_to_cpu(intserv[0]);
+
+		pr_warn("Boot CPU %d (core hwid %d) >= nr_cpu_ids, adjusted boot CPU to %d\n",
+			boot_cpuid, boot_core_hwid, found_thread);
+
+		// Adjust boot CPU to appear on logical core 0
+		boot_cpuid = found_thread;
+	}
+
+	DBG("boot cpu: logical %d physical %d\n", boot_cpuid,
+	    be32_to_cpu(intserv[found_thread]));
+
 	/*
 	 * PAPR defines "logical" PVR values for cpus that
 	 * meet various levels of the architecture:
@@ -397,7 +421,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
 		if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) {
 			identify_cpu(0, be32_to_cpup(prop));
-			seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(prop));
+			cpu_version = prop;
 		}
 
 		check_cpu_feature_properties(node);
@@ -408,6 +432,12 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	}
 
 	identical_pvr_fixup(node);
+
+	// We can now add the CPU name & PVR to the hardware description
+	seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR));
+	if (cpu_version)
+		seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(cpu_version));
+
 	init_mmu_slb_size(node);
 
 #ifdef CONFIG_PPC64
@@ -452,7 +482,7 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node,
 		tce_alloc_end = *lprop;
 #endif
 
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_RESERVE
 	lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL);
 	if (lprop)
 		crashk_res.start = *lprop;
@@ -756,12 +786,12 @@ static inline void save_fscr_to_task(void) {}
 
 void __init early_init_devtree(void *params)
 {
-	phys_addr_t limit;
+	phys_addr_t int_vector_size;
 
 	DBG(" -> early_init_devtree(%px)\n", params);
 
 	/* Too early to BUG_ON(), do it by hand */
-	if (!early_init_dt_verify(params))
+	if (!early_init_dt_verify(params, __pa(params)))
 		panic("BUG: Failed verifying flat device tree, bad version?");
 
 	of_scan_flat_dt(early_init_dt_scan_model, NULL);
@@ -790,6 +820,9 @@ void __init early_init_devtree(void *params)
 	 */
 	of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line);
 
+	/* Append additional parameters passed for fadump capture kernel */
+	fadump_append_bootargs();
+
 	/* Scan memory nodes and rebuild MEMBLOCKs */
 	early_init_dt_scan_root();
 	early_init_dt_scan_memory_ppc();
@@ -809,9 +842,16 @@ void __init early_init_devtree(void *params)
 	setup_initial_memory_limit(memstart_addr, first_memblock_size);
 	/* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */
 	memblock_reserve(PHYSICAL_START, __pa(_end) - PHYSICAL_START);
+#ifdef CONFIG_PPC64
+	/* If relocatable, reserve at least 32k for interrupt vectors etc. */
+	int_vector_size = __end_interrupts - _stext;
+	int_vector_size = max_t(phys_addr_t, SZ_32K, int_vector_size);
+#else
 	/* If relocatable, reserve first 32k for interrupt vectors etc. */
+	int_vector_size = SZ_32K;
+#endif
 	if (PHYSICAL_START > MEMORY_START)
-		memblock_reserve(MEMORY_START, 0x8000);
+		memblock_reserve(MEMORY_START, int_vector_size);
 	reserve_kdump_trampoline();
 #if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
 	/*
@@ -820,12 +860,15 @@ void __init early_init_devtree(void *params)
 	 */
 	if (fadump_reserve_mem() == 0)
 #endif
-		reserve_crashkernel();
+		arch_reserve_crashkernel();
 	early_reserve_mem();
 
-	/* Ensure that total memory size is page-aligned. */
-	limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE);
-	memblock_enforce_memory_limit(limit);
+	if (memory_limit > memblock_phys_mem_size())
+		memory_limit = 0;
+
+	/* Align down to 16 MB which is large page size with hash page translation */
+	memory_limit = ALIGN_DOWN(memory_limit ?: memblock_phys_mem_size(), SZ_16M);
+	memblock_enforce_memory_limit(memory_limit);
 
 #if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_4K_PAGES)
 	if (!early_radix_enabled())
@@ -845,9 +888,6 @@ void __init early_init_devtree(void *params)
 
 	dt_cpu_ftrs_scan();
 
-	// We can now add the CPU name & PVR to the hardware description
-	seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR));
-
 	/* Retrieve CPU related informations from the flat tree
 	 * (altivec support, boot CPU ID, ...)
 	 */
@@ -868,6 +908,9 @@ void __init early_init_devtree(void *params)
 
 	mmu_early_init_devtree();
 
+	/* Setup param area for passing additional parameters to fadump capture kernel. */
+	fadump_setup_param_area();
+
 #ifdef CONFIG_PPC_POWERNV
 	/* Scan and build the list of machine check recoverable ranges */
 	of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL);
diff --git a/arch/powerpc/kernel/prom_entry_64.S b/arch/powerpc/kernel/prom_entry_64.S
new file mode 100644
index 000000000000..f1b8793d28c6
--- /dev/null
+++ b/arch/powerpc/kernel/prom_entry_64.S
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *  PowerPC version 
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ *  Adapted for Power Macintosh by Paul Mackerras.
+ *  Low-level exception handlers and MMU support
+ *  rewritten by Paul Mackerras.
+ *    Copyright (C) 1996 Paul Mackerras.
+ *  MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
+ *  This file contains the 64-bit prom entry code.
+ */
+#include <asm/asm-offsets.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
+#include <asm/ppc_asm.h>
+
+.section ".text","ax",@progbits
+
+_GLOBAL(enter_prom)
+	mflr	r0
+	std	r0,16(r1)
+        stdu	r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space */
+
+	/* Because PROM is running in 32b mode, it clobbers the high order half
+	 * of all registers that it saves.  We therefore save those registers
+	 * PROM might touch to the stack.  (r0, r3-r13 are caller saved)
+   	 */
+	SAVE_GPR(2, r1)
+	SAVE_GPR(13, r1)
+	SAVE_NVGPRS(r1)
+	mfcr	r10
+	mfmsr	r11
+	std	r10,_CCR(r1)
+	std	r11,_MSR(r1)
+
+	/* Put PROM address in SRR0 */
+	mtsrr0	r4
+
+	/* Setup our trampoline return addr in LR */
+	bcl	20,31,$+4
+0:	mflr	r4
+	addi	r4,r4,(1f - 0b)
+       	mtlr	r4
+
+	/* Prepare a 32-bit mode big endian MSR
+	 */
+#ifdef CONFIG_PPC_BOOK3E_64
+	rlwinm	r11,r11,0,1,31
+	mtsrr1	r11
+	rfi
+#else /* CONFIG_PPC_BOOK3E_64 */
+	LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE)
+	andc	r11,r11,r12
+	mtsrr1	r11
+	RFI_TO_KERNEL
+#endif /* CONFIG_PPC_BOOK3E_64 */
+
+1:	/* Return from OF */
+	FIXUP_ENDIAN
+
+	/* Just make sure that r1 top 32 bits didn't get
+	 * corrupt by OF
+	 */
+	rldicl	r1,r1,0,32
+
+	/* Restore the MSR (back to 64 bits) */
+	ld	r0,_MSR(r1)
+	MTMSRD(r0)
+        isync
+
+	/* Restore other registers */
+	REST_GPR(2, r1)
+	REST_GPR(13, r1)
+	REST_NVGPRS(r1)
+	ld	r4,_CCR(r1)
+	mtcr	r4
+
+        addi	r1,r1,SWITCH_FRAME_SIZE
+	ld	r0,16(r1)
+	mtlr    r0
+        blr
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index d464ba412084..827c958677f8 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -817,8 +817,8 @@ static void __init early_cmdline_parse(void)
 		opt += 4;
 		prom_memory_limit = prom_memparse(opt, (const char **)&opt);
 #ifdef CONFIG_PPC64
-		/* Align to 16 MB == size of ppc64 large page */
-		prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
+		/* Align down to 16 MB which is large page size with hash page translation */
+		prom_memory_limit = ALIGN_DOWN(prom_memory_limit, SZ_16M);
 #endif
 	}
 
@@ -947,7 +947,7 @@ struct option_vector7 {
 } __packed;
 
 struct ibm_arch_vec {
-	struct { u32 mask, val; } pvrs[14];
+	struct { __be32 mask, val; } pvrs[16];
 
 	u8 num_vectors;
 
@@ -1008,6 +1008,14 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 			.val  = cpu_to_be32(0x00800000),
 		},
 		{
+			.mask = cpu_to_be32(0xffff0000), /* POWER11 */
+			.val  = cpu_to_be32(0x00820000),
+		},
+		{
+			.mask = cpu_to_be32(0xffffffff), /* P11 compliant */
+			.val  = cpu_to_be32(0x0f000007),
+		},
+		{
 			.mask = cpu_to_be32(0xffffffff), /* all 3.1-compliant */
 			.val  = cpu_to_be32(0x0f000006),
 		},
@@ -1053,7 +1061,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 		.virt_base = cpu_to_be32(0xffffffff),
 		.virt_size = cpu_to_be32(0xffffffff),
 		.load_base = cpu_to_be32(0xffffffff),
-		.min_rma = cpu_to_be32(512),		/* 512MB min RMA */
+		.min_rma = cpu_to_be32(MIN_RMA),
 		.min_load = cpu_to_be32(0xffffffff),	/* full client load */
 		.min_rma_percent = 0,	/* min RMA percentage of total RAM */
 		.max_pft_size = 48,	/* max log_2(hash table size) */
@@ -2784,91 +2792,6 @@ static void __init flatten_device_tree(void)
 		    dt_struct_start, dt_struct_end);
 }
 
-#ifdef CONFIG_PPC_MAPLE
-/* PIBS Version 1.05.0000 04/26/2005 has an incorrect /ht/isa/ranges property.
- * The values are bad, and it doesn't even have the right number of cells. */
-static void __init fixup_device_tree_maple(void)
-{
-	phandle isa;
-	u32 rloc = 0x01002000; /* IO space; PCI device = 4 */
-	u32 isa_ranges[6];
-	char *name;
-
-	name = "/ht@0/isa@4";
-	isa = call_prom("finddevice", 1, 1, ADDR(name));
-	if (!PHANDLE_VALID(isa)) {
-		name = "/ht@0/isa@6";
-		isa = call_prom("finddevice", 1, 1, ADDR(name));
-		rloc = 0x01003000; /* IO space; PCI device = 6 */
-	}
-	if (!PHANDLE_VALID(isa))
-		return;
-
-	if (prom_getproplen(isa, "ranges") != 12)
-		return;
-	if (prom_getprop(isa, "ranges", isa_ranges, sizeof(isa_ranges))
-		== PROM_ERROR)
-		return;
-
-	if (isa_ranges[0] != 0x1 ||
-		isa_ranges[1] != 0xf4000000 ||
-		isa_ranges[2] != 0x00010000)
-		return;
-
-	prom_printf("Fixing up bogus ISA range on Maple/Apache...\n");
-
-	isa_ranges[0] = 0x1;
-	isa_ranges[1] = 0x0;
-	isa_ranges[2] = rloc;
-	isa_ranges[3] = 0x0;
-	isa_ranges[4] = 0x0;
-	isa_ranges[5] = 0x00010000;
-	prom_setprop(isa, name, "ranges",
-			isa_ranges, sizeof(isa_ranges));
-}
-
-#define CPC925_MC_START		0xf8000000
-#define CPC925_MC_LENGTH	0x1000000
-/* The values for memory-controller don't have right number of cells */
-static void __init fixup_device_tree_maple_memory_controller(void)
-{
-	phandle mc;
-	u32 mc_reg[4];
-	char *name = "/hostbridge@f8000000";
-	u32 ac, sc;
-
-	mc = call_prom("finddevice", 1, 1, ADDR(name));
-	if (!PHANDLE_VALID(mc))
-		return;
-
-	if (prom_getproplen(mc, "reg") != 8)
-		return;
-
-	prom_getprop(prom.root, "#address-cells", &ac, sizeof(ac));
-	prom_getprop(prom.root, "#size-cells", &sc, sizeof(sc));
-	if ((ac != 2) || (sc != 2))
-		return;
-
-	if (prom_getprop(mc, "reg", mc_reg, sizeof(mc_reg)) == PROM_ERROR)
-		return;
-
-	if (mc_reg[0] != CPC925_MC_START || mc_reg[1] != CPC925_MC_LENGTH)
-		return;
-
-	prom_printf("Fixing up bogus hostbridge on Maple...\n");
-
-	mc_reg[0] = 0x0;
-	mc_reg[1] = CPC925_MC_START;
-	mc_reg[2] = 0x0;
-	mc_reg[3] = CPC925_MC_LENGTH;
-	prom_setprop(mc, name, "reg", mc_reg, sizeof(mc_reg));
-}
-#else
-#define fixup_device_tree_maple()
-#define fixup_device_tree_maple_memory_controller()
-#endif
-
-#ifdef CONFIG_PPC_CHRP
 /*
  * Pegasos and BriQ lacks the "ranges" property in the isa node
  * Pegasos needs decimal IRQ 14/15, not hexadecimal
@@ -2919,12 +2842,8 @@ static void __init fixup_device_tree_chrp(void)
 		}
 	}
 }
-#else
-#define fixup_device_tree_chrp()
-#endif
 
-#if defined(CONFIG_PPC64) && defined(CONFIG_PPC_PMAC)
-static void __init fixup_device_tree_pmac(void)
+static void __init fixup_device_tree_pmac64(void)
 {
 	phandle u3, i2c, mpic;
 	u32 u3_rev;
@@ -2963,11 +2882,27 @@ static void __init fixup_device_tree_pmac(void)
 	prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupt-parent",
 		     &parent, sizeof(parent));
 }
-#else
-#define fixup_device_tree_pmac()
-#endif
 
-#ifdef CONFIG_PPC_EFIKA
+static void __init fixup_device_tree_pmac(void)
+{
+	__be32 val = 1;
+	char type[8];
+	phandle node;
+
+	// Some pmacs are missing #size-cells on escc or i2s nodes
+	for (node = 0; prom_next_node(&node); ) {
+		type[0] = '\0';
+		prom_getprop(node, "device_type", type, sizeof(type));
+		if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s"))
+			continue;
+
+		if (prom_getproplen(node, "#size-cells") != PROM_ERROR)
+			continue;
+
+		prom_setprop(node, NULL, "#size-cells", &val, sizeof(val));
+	}
+}
+
 /*
  * The MPC5200 FEC driver requires an phy-handle property to tell it how
  * to talk to the phy.  If the phy-handle property is missing, then this
@@ -3099,11 +3034,7 @@ static void __init fixup_device_tree_efika(void)
 	/* Make sure ethernet phy-handle property exists */
 	fixup_device_tree_efika_add_phy();
 }
-#else
-#define fixup_device_tree_efika()
-#endif
 
-#ifdef CONFIG_PPC_PASEMI_NEMO
 /*
  * CFE supplied on Nemo is broken in several ways, biggest
  * problem is that it reassigns ISA interrupts to unused mpic ints.
@@ -3179,18 +3110,23 @@ static void __init fixup_device_tree_pasemi(void)
 
 	prom_setprop(iob, name, "device_type", "isa", sizeof("isa"));
 }
-#else	/* !CONFIG_PPC_PASEMI_NEMO */
-static inline void fixup_device_tree_pasemi(void) { }
-#endif
 
 static void __init fixup_device_tree(void)
 {
-	fixup_device_tree_maple();
-	fixup_device_tree_maple_memory_controller();
-	fixup_device_tree_chrp();
-	fixup_device_tree_pmac();
-	fixup_device_tree_efika();
-	fixup_device_tree_pasemi();
+	if (IS_ENABLED(CONFIG_PPC_CHRP))
+		fixup_device_tree_chrp();
+
+	if (IS_ENABLED(CONFIG_PPC_PMAC))
+		fixup_device_tree_pmac();
+
+	if (IS_ENABLED(CONFIG_PPC_PMAC) && IS_ENABLED(CONFIG_PPC64))
+		fixup_device_tree_pmac64();
+
+	if (IS_ENABLED(CONFIG_PPC_EFIKA))
+		fixup_device_tree_efika();
+
+	if (IS_ENABLED(CONFIG_PPC_PASEMI_NEMO))
+		fixup_device_tree_pasemi();
 }
 
 static void __init prom_find_boot_cpu(void)
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 69623b9045d5..3090b97258ae 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -15,8 +15,8 @@
 
 has_renamed_memintrinsics()
 {
-	grep -q "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} && \
-		! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" ${KCONFIG_CONFIG}
+	grep -q "^CONFIG_KASAN=y$" "${KCONFIG_CONFIG}" && \
+		! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" "${KCONFIG_CONFIG}"
 }
 
 if has_renamed_memintrinsics
@@ -42,15 +42,15 @@ check_section()
 {
     file=$1
     section=$2
-    size=$(objdump -h -j $section $file 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
+    size=$(objdump -h -j "$section" "$file" 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
     size=${size:-0}
-    if [ $size -ne 0 ]; then
+    if [ "$size" -ne 0 ]; then
 	ERROR=1
 	echo "Error: Section $section not empty in prom_init.c" >&2
     fi
 }
 
-for UNDEF in $($NM -u $OBJ | awk '{print $2}')
+for UNDEF in $($NM -u "$OBJ" | awk '{print $2}')
 do
 	# On 64-bit nm gives us the function descriptors, which have
 	# a leading . on the name, so strip it off here.
@@ -87,8 +87,8 @@ do
 	fi
 done
 
-check_section $OBJ .data
-check_section $OBJ .bss
-check_section $OBJ .init.data
+check_section "$OBJ" .data
+check_section "$OBJ" .bss
+check_section "$OBJ" .init.data
 
 exit $ERROR
diff --git a/arch/powerpc/kernel/ptrace/ptrace-decl.h b/arch/powerpc/kernel/ptrace/ptrace-decl.h
index eafe5f0f6289..4171a5727197 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-decl.h
+++ b/arch/powerpc/kernel/ptrace/ptrace-decl.h
@@ -1,5 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 
+#include <linux/regset.h>
+
 /*
  * Set of msr bits that gdb can change on behalf of a process.
  */
@@ -55,6 +57,10 @@ enum powerpc_regset {
 	REGSET_TAR,		/* TAR register */
 	REGSET_EBB,		/* EBB registers */
 	REGSET_PMR,		/* Performance Monitor Registers */
+	REGSET_DEXCR,		/* DEXCR registers */
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	REGSET_HASHKEYR,	/* HASHKEYR register */
+#endif
 #endif
 #ifdef CONFIG_PPC_MEM_KEYS
 	REGSET_PKEY,		/* AMR register */
diff --git a/arch/powerpc/kernel/ptrace/ptrace-tm.c b/arch/powerpc/kernel/ptrace/ptrace-tm.c
index 210ea834e603..447bff87fd21 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-tm.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-tm.c
@@ -12,7 +12,7 @@ void flush_tmregs_to_thread(struct task_struct *tsk)
 {
 	/*
 	 * If task is not current, it will have been flushed already to
-	 * it's thread_struct during __switch_to().
+	 * its thread_struct during __switch_to().
 	 *
 	 * A reclaim flushes ALL the state or if not in TM save TM SPRs
 	 * in the appropriate thread structures from live.
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
index 5fff0d04b23f..0310f9097e39 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -454,7 +454,60 @@ static int pmu_set(struct task_struct *target, const struct user_regset *regset,
 					 5 * sizeof(unsigned long));
 	return ret;
 }
-#endif
+
+static int dexcr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_31))
+		return -ENODEV;
+
+	return regset->n;
+}
+
+static int dexcr_get(struct task_struct *target, const struct user_regset *regset,
+		     struct membuf to)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_31))
+		return -ENODEV;
+
+	membuf_store(&to, (u64)lower_32_bits(target->thread.dexcr));
+
+	/*
+	 * Technically the HDEXCR is per-cpu, but a hypervisor can't reasonably
+	 * change it between CPUs of the same guest.
+	 */
+	return membuf_store(&to, (u64)lower_32_bits(mfspr(SPRN_HDEXCR_RO)));
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static int hashkeyr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_31))
+		return -ENODEV;
+
+	return regset->n;
+}
+
+static int hashkeyr_get(struct task_struct *target, const struct user_regset *regset,
+			struct membuf to)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_31))
+		return -ENODEV;
+
+	return membuf_store(&to, target->thread.hashkeyr);
+}
+
+static int hashkeyr_set(struct task_struct *target, const struct user_regset *regset,
+			unsigned int pos, unsigned int count, const void *kbuf,
+			const void __user *ubuf)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_31))
+		return -ENODEV;
+
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.hashkeyr,
+				  0, sizeof(unsigned long));
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+#endif /* CONFIG_PPC_BOOK3S_64 */
 
 #ifdef CONFIG_PPC_MEM_KEYS
 static int pkey_active(struct task_struct *target, const struct user_regset *regset)
@@ -515,110 +568,122 @@ static int pkey_set(struct task_struct *target, const struct user_regset *regset
 
 static const struct user_regset native_regsets[] = {
 	[REGSET_GPR] = {
-		.core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+		USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG,
 		.size = sizeof(long), .align = sizeof(long),
 		.regset_get = gpr_get, .set = gpr_set
 	},
 	[REGSET_FPR] = {
-		.core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+		USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG,
 		.size = sizeof(double), .align = sizeof(double),
 		.regset_get = fpr_get, .set = fpr_set
 	},
 #ifdef CONFIG_ALTIVEC
 	[REGSET_VMX] = {
-		.core_note_type = NT_PPC_VMX, .n = 34,
+		USER_REGSET_NOTE_TYPE(PPC_VMX), .n = 34,
 		.size = sizeof(vector128), .align = sizeof(vector128),
 		.active = vr_active, .regset_get = vr_get, .set = vr_set
 	},
 #endif
 #ifdef CONFIG_VSX
 	[REGSET_VSX] = {
-		.core_note_type = NT_PPC_VSX, .n = 32,
+		USER_REGSET_NOTE_TYPE(PPC_VSX), .n = 32,
 		.size = sizeof(double), .align = sizeof(double),
 		.active = vsr_active, .regset_get = vsr_get, .set = vsr_set
 	},
 #endif
 #ifdef CONFIG_SPE
 	[REGSET_SPE] = {
-		.core_note_type = NT_PPC_SPE, .n = 35,
+		USER_REGSET_NOTE_TYPE(PPC_SPE), .n = 35,
 		.size = sizeof(u32), .align = sizeof(u32),
 		.active = evr_active, .regset_get = evr_get, .set = evr_set
 	},
 #endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	[REGSET_TM_CGPR] = {
-		.core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CGPR), .n = ELF_NGREG,
 		.size = sizeof(long), .align = sizeof(long),
 		.active = tm_cgpr_active, .regset_get = tm_cgpr_get, .set = tm_cgpr_set
 	},
 	[REGSET_TM_CFPR] = {
-		.core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CFPR), .n = ELF_NFPREG,
 		.size = sizeof(double), .align = sizeof(double),
 		.active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set
 	},
 	[REGSET_TM_CVMX] = {
-		.core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CVMX), .n = ELF_NVMX,
 		.size = sizeof(vector128), .align = sizeof(vector128),
 		.active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set
 	},
 	[REGSET_TM_CVSX] = {
-		.core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CVSX), .n = ELF_NVSX,
 		.size = sizeof(double), .align = sizeof(double),
 		.active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set
 	},
 	[REGSET_TM_SPR] = {
-		.core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+		USER_REGSET_NOTE_TYPE(PPC_TM_SPR), .n = ELF_NTMSPRREG,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set
 	},
 	[REGSET_TM_CTAR] = {
-		.core_note_type = NT_PPC_TM_CTAR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CTAR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set
 	},
 	[REGSET_TM_CPPR] = {
-		.core_note_type = NT_PPC_TM_CPPR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CPPR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set
 	},
 	[REGSET_TM_CDSCR] = {
-		.core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CDSCR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set
 	},
 #endif
 #ifdef CONFIG_PPC64
 	[REGSET_PPR] = {
-		.core_note_type = NT_PPC_PPR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_PPR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.regset_get = ppr_get, .set = ppr_set
 	},
 	[REGSET_DSCR] = {
-		.core_note_type = NT_PPC_DSCR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_DSCR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.regset_get = dscr_get, .set = dscr_set
 	},
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	[REGSET_TAR] = {
-		.core_note_type = NT_PPC_TAR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_TAR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.regset_get = tar_get, .set = tar_set
 	},
 	[REGSET_EBB] = {
-		.core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+		USER_REGSET_NOTE_TYPE(PPC_EBB), .n = ELF_NEBB,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = ebb_active, .regset_get = ebb_get, .set = ebb_set
 	},
 	[REGSET_PMR] = {
-		.core_note_type = NT_PPC_PMU, .n = ELF_NPMU,
+		USER_REGSET_NOTE_TYPE(PPC_PMU), .n = ELF_NPMU,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = pmu_active, .regset_get = pmu_get, .set = pmu_set
 	},
+	[REGSET_DEXCR] = {
+		USER_REGSET_NOTE_TYPE(PPC_DEXCR), .n = ELF_NDEXCR,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = dexcr_active, .regset_get = dexcr_get
+	},
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	[REGSET_HASHKEYR] = {
+		USER_REGSET_NOTE_TYPE(PPC_HASHKEYR), .n = ELF_NHASHKEYR,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = hashkeyr_active, .regset_get = hashkeyr_get, .set = hashkeyr_set
+	},
+#endif
 #endif
 #ifdef CONFIG_PPC_MEM_KEYS
 	[REGSET_PKEY] = {
-		.core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY,
+		USER_REGSET_NOTE_TYPE(PPC_PKEY), .n = ELF_NPKEY,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = pkey_active, .regset_get = pkey_get, .set = pkey_set
 	},
@@ -646,69 +711,86 @@ int gpr32_get_common(struct task_struct *target,
 	return membuf_zero(&to, (ELF_NGREG - PT_REGS_COUNT) * sizeof(u32));
 }
 
-int gpr32_set_common(struct task_struct *target,
-		     const struct user_regset *regset,
-		     unsigned int pos, unsigned int count,
-		     const void *kbuf, const void __user *ubuf,
-		     unsigned long *regs)
+static int gpr32_set_common_kernel(struct task_struct *target,
+				   const struct user_regset *regset,
+				   unsigned int pos, unsigned int count,
+				   const void *kbuf, unsigned long *regs)
 {
 	const compat_ulong_t *k = kbuf;
+
+	pos /= sizeof(compat_ulong_t);
+	count /= sizeof(compat_ulong_t);
+
+	for (; count > 0 && pos < PT_MSR; --count)
+		regs[pos++] = *k++;
+
+	if (count > 0 && pos == PT_MSR) {
+		set_user_msr(target, *k++);
+		++pos;
+		--count;
+	}
+
+	for (; count > 0 && pos <= PT_MAX_PUT_REG; --count)
+		regs[pos++] = *k++;
+	for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+		++k;
+
+	if (count > 0 && pos == PT_TRAP) {
+		set_user_trap(target, *k++);
+		++pos;
+		--count;
+	}
+
+	kbuf = k;
+	pos *= sizeof(compat_ulong_t);
+	count *= sizeof(compat_ulong_t);
+	user_regset_copyin_ignore(&pos, &count, &kbuf, NULL,
+				  (PT_TRAP + 1) * sizeof(compat_ulong_t), -1);
+	return 0;
+}
+
+static int gpr32_set_common_user(struct task_struct *target,
+				 const struct user_regset *regset,
+				 unsigned int pos, unsigned int count,
+				 const void __user *ubuf, unsigned long *regs)
+{
 	const compat_ulong_t __user *u = ubuf;
+	const void *kbuf = NULL;
 	compat_ulong_t reg;
 
-	if (!kbuf && !user_read_access_begin(u, count))
+	if (!user_read_access_begin(u, count))
 		return -EFAULT;
 
 	pos /= sizeof(reg);
 	count /= sizeof(reg);
 
-	if (kbuf)
-		for (; count > 0 && pos < PT_MSR; --count)
-			regs[pos++] = *k++;
-	else
-		for (; count > 0 && pos < PT_MSR; --count) {
-			unsafe_get_user(reg, u++, Efault);
-			regs[pos++] = reg;
-		}
-
+	for (; count > 0 && pos < PT_MSR; --count) {
+		unsafe_get_user(reg, u++, Efault);
+		regs[pos++] = reg;
+	}
 
 	if (count > 0 && pos == PT_MSR) {
-		if (kbuf)
-			reg = *k++;
-		else
-			unsafe_get_user(reg, u++, Efault);
+		unsafe_get_user(reg, u++, Efault);
 		set_user_msr(target, reg);
 		++pos;
 		--count;
 	}
 
-	if (kbuf) {
-		for (; count > 0 && pos <= PT_MAX_PUT_REG; --count)
-			regs[pos++] = *k++;
-		for (; count > 0 && pos < PT_TRAP; --count, ++pos)
-			++k;
-	} else {
-		for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) {
-			unsafe_get_user(reg, u++, Efault);
-			regs[pos++] = reg;
-		}
-		for (; count > 0 && pos < PT_TRAP; --count, ++pos)
-			unsafe_get_user(reg, u++, Efault);
+	for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) {
+		unsafe_get_user(reg, u++, Efault);
+		regs[pos++] = reg;
 	}
+	for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+		unsafe_get_user(reg, u++, Efault);
 
 	if (count > 0 && pos == PT_TRAP) {
-		if (kbuf)
-			reg = *k++;
-		else
-			unsafe_get_user(reg, u++, Efault);
+		unsafe_get_user(reg, u++, Efault);
 		set_user_trap(target, reg);
 		++pos;
 		--count;
 	}
-	if (!kbuf)
-		user_read_access_end();
+	user_read_access_end();
 
-	kbuf = k;
 	ubuf = u;
 	pos *= sizeof(reg);
 	count *= sizeof(reg);
@@ -721,6 +803,18 @@ Efault:
 	return -EFAULT;
 }
 
+int gpr32_set_common(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf,
+		     unsigned long *regs)
+{
+	if (kbuf)
+		return gpr32_set_common_kernel(target, regset, pos, count, kbuf, regs);
+	else
+		return gpr32_set_common_user(target, regset, pos, count, ubuf, regs);
+}
+
 static int gpr32_get(struct task_struct *target,
 		     const struct user_regset *regset,
 		     struct membuf to)
@@ -749,92 +843,92 @@ static int gpr32_set(struct task_struct *target,
  */
 static const struct user_regset compat_regsets[] = {
 	[REGSET_GPR] = {
-		.core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+		USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG,
 		.size = sizeof(compat_long_t), .align = sizeof(compat_long_t),
 		.regset_get = gpr32_get, .set = gpr32_set
 	},
 	[REGSET_FPR] = {
-		.core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+		USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG,
 		.size = sizeof(double), .align = sizeof(double),
 		.regset_get = fpr_get, .set = fpr_set
 	},
 #ifdef CONFIG_ALTIVEC
 	[REGSET_VMX] = {
-		.core_note_type = NT_PPC_VMX, .n = 34,
+		USER_REGSET_NOTE_TYPE(PPC_VMX), .n = 34,
 		.size = sizeof(vector128), .align = sizeof(vector128),
 		.active = vr_active, .regset_get = vr_get, .set = vr_set
 	},
 #endif
 #ifdef CONFIG_SPE
 	[REGSET_SPE] = {
-		.core_note_type = NT_PPC_SPE, .n = 35,
+		USER_REGSET_NOTE_TYPE(PPC_SPE), .n = 35,
 		.size = sizeof(u32), .align = sizeof(u32),
 		.active = evr_active, .regset_get = evr_get, .set = evr_set
 	},
 #endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	[REGSET_TM_CGPR] = {
-		.core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CGPR), .n = ELF_NGREG,
 		.size = sizeof(long), .align = sizeof(long),
 		.active = tm_cgpr_active,
 		.regset_get = tm_cgpr32_get, .set = tm_cgpr32_set
 	},
 	[REGSET_TM_CFPR] = {
-		.core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CFPR), .n = ELF_NFPREG,
 		.size = sizeof(double), .align = sizeof(double),
 		.active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set
 	},
 	[REGSET_TM_CVMX] = {
-		.core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CVMX), .n = ELF_NVMX,
 		.size = sizeof(vector128), .align = sizeof(vector128),
 		.active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set
 	},
 	[REGSET_TM_CVSX] = {
-		.core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CVSX), .n = ELF_NVSX,
 		.size = sizeof(double), .align = sizeof(double),
 		.active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set
 	},
 	[REGSET_TM_SPR] = {
-		.core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+		USER_REGSET_NOTE_TYPE(PPC_TM_SPR), .n = ELF_NTMSPRREG,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set
 	},
 	[REGSET_TM_CTAR] = {
-		.core_note_type = NT_PPC_TM_CTAR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CTAR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set
 	},
 	[REGSET_TM_CPPR] = {
-		.core_note_type = NT_PPC_TM_CPPR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CPPR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set
 	},
 	[REGSET_TM_CDSCR] = {
-		.core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_TM_CDSCR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set
 	},
 #endif
 #ifdef CONFIG_PPC64
 	[REGSET_PPR] = {
-		.core_note_type = NT_PPC_PPR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_PPR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.regset_get = ppr_get, .set = ppr_set
 	},
 	[REGSET_DSCR] = {
-		.core_note_type = NT_PPC_DSCR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_DSCR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.regset_get = dscr_get, .set = dscr_set
 	},
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	[REGSET_TAR] = {
-		.core_note_type = NT_PPC_TAR, .n = 1,
+		USER_REGSET_NOTE_TYPE(PPC_TAR), .n = 1,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.regset_get = tar_get, .set = tar_set
 	},
 	[REGSET_EBB] = {
-		.core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+		USER_REGSET_NOTE_TYPE(PPC_EBB), .n = ELF_NEBB,
 		.size = sizeof(u64), .align = sizeof(u64),
 		.active = ebb_active, .regset_get = ebb_get, .set = ebb_set
 	},
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 5d7a72b41ae7..c6997df63287 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -9,10 +10,6 @@
  *
  * Modified by Cort Dougan (cort@hq.fsmlabs.com)
  * and Paul Mackerras (paulus@samba.org).
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file README.legal in the main directory of
- * this archive for more details.
  */
 
 #include <linux/regset.h>
@@ -218,7 +215,7 @@ static int do_seccomp(struct pt_regs *regs)
 	 * have already loaded -ENOSYS into r3, or seccomp has put
 	 * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
 	 */
-	if (__secure_computing(NULL))
+	if (__secure_computing())
 		return -1;
 
 	/*
diff --git a/arch/powerpc/kernel/rethook.c b/arch/powerpc/kernel/rethook.c
new file mode 100644
index 000000000000..5f5f47ae82cf
--- /dev/null
+++ b/arch/powerpc/kernel/rethook.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PowerPC implementation of rethook. This depends on kprobes.
+ */
+
+#include <linux/kprobes.h>
+#include <linux/rethook.h>
+
+/*
+ * Function return trampoline:
+ *     - init_kprobes() establishes a probepoint here
+ *     - When the probed function returns, this probe
+ *         causes the handlers to fire
+ */
+asm(".global arch_rethook_trampoline\n"
+	".type arch_rethook_trampoline, @function\n"
+	"arch_rethook_trampoline:\n"
+	"nop\n"
+	"blr\n"
+	".size arch_rethook_trampoline, .-arch_rethook_trampoline\n");
+
+/*
+ * Called when the probe at kretprobe trampoline is hit
+ */
+static int trampoline_rethook_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	return !rethook_trampoline_handler(regs, regs->gpr[1]);
+}
+NOKPROBE_SYMBOL(trampoline_rethook_handler);
+
+void arch_rethook_prepare(struct rethook_node *rh, struct pt_regs *regs, bool mcount)
+{
+	rh->ret_addr = regs->link;
+	rh->frame = regs->gpr[1];
+
+	/* Replace the return addr with trampoline addr */
+	regs->link = (unsigned long)arch_rethook_trampoline;
+}
+NOKPROBE_SYMBOL(arch_rethook_prepare);
+
+/* This is called from rethook_trampoline_handler(). */
+void arch_rethook_fixup_return(struct pt_regs *regs, unsigned long orig_ret_address)
+{
+	/*
+	 * We get here through one of two paths:
+	 * 1. by taking a trap -> kprobe_handler() -> here
+	 * 2. by optprobe branch -> optimized_callback() -> opt_pre_handler() -> here
+	 *
+	 * When going back through (1), we need regs->nip to be setup properly
+	 * as it is used to determine the return address from the trap.
+	 * For (2), since nip is not honoured with optprobes, we instead setup
+	 * the link register properly so that the subsequent 'blr' in
+	 * arch_rethook_trampoline jumps back to the right instruction.
+	 *
+	 * For nip, we should set the address to the previous instruction since
+	 * we end up emulating it in kprobe_handler(), which increments the nip
+	 * again.
+	 */
+	regs_set_return_ip(regs, orig_ret_address - 4);
+	regs->link = orig_ret_address;
+}
+NOKPROBE_SYMBOL(arch_rethook_fixup_return);
+
+static struct kprobe trampoline_p = {
+	.addr = (kprobe_opcode_t *) &arch_rethook_trampoline,
+	.pre_handler = trampoline_rethook_handler
+};
+
+/* rethook initializer */
+int __init arch_init_kprobes(void)
+{
+	return register_kprobe(&trampoline_p);
+}
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index 9454b8395b6a..f38df72e64b8 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -752,6 +752,8 @@ static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v)
 
 /**
  * ppc_rtas_rmo_buf_show() - Describe RTAS-addressable region for user space.
+ * @m: seq_file output target.
+ * @v: Unused.
  *
  * Base + size description of a range of RTAS-addressable memory set
  * aside for user space to use as work area(s) for certain RTAS
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index c087eeee320f..8d81c1e7a8db 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -18,6 +18,8 @@
 #include <linux/kernel.h>
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
+#include <linux/mutex.h>
+#include <linux/nospec.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/reboot.h>
@@ -70,14 +72,35 @@ struct rtas_filter {
  *                            ppc64le, and we want to keep it that way. It does
  *                            not make sense for this to be set when @filter
  *                            is NULL.
+ * @lock: Pointer to an optional dedicated per-function mutex. This
+ *        should be set for functions that require multiple calls in
+ *        sequence to complete a single operation, and such sequences
+ *        will disrupt each other if allowed to interleave. Users of
+ *        this function are required to hold the associated lock for
+ *        the duration of the call sequence. Add an explanatory
+ *        comment to the function table entry if setting this member.
  */
 struct rtas_function {
 	s32 token;
 	const bool banned_for_syscall_on_le:1;
 	const char * const name;
 	const struct rtas_filter *filter;
+	struct mutex *lock;
 };
 
+/*
+ * Per-function locks for sequence-based RTAS functions.
+ */
+static DEFINE_MUTEX(rtas_ibm_activate_firmware_lock);
+static DEFINE_MUTEX(rtas_ibm_lpar_perftools_lock);
+DEFINE_MUTEX(rtas_ibm_physical_attestation_lock);
+DEFINE_MUTEX(rtas_ibm_get_vpd_lock);
+DEFINE_MUTEX(rtas_ibm_get_indices_lock);
+DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock);
+DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock);
+DEFINE_MUTEX(rtas_ibm_receive_hvpipe_msg_lock);
+DEFINE_MUTEX(rtas_ibm_send_hvpipe_msg_lock);
+
 static struct rtas_function rtas_function_table[] __ro_after_init = {
 	[RTAS_FNIDX__CHECK_EXCEPTION] = {
 		.name = "check-exception",
@@ -125,6 +148,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = -1, .size_idx1 = -1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ as of v2.13 doesn't explicitly impose any
+		 * restriction, but this typically requires multiple
+		 * calls before success, and there's no reason to
+		 * allow sequences to interleave.
+		 */
+		.lock = &rtas_ibm_activate_firmware_lock,
 	},
 	[RTAS_FNIDX__IBM_CBE_START_PTCAL] = {
 		.name = "ibm,cbe-start-ptcal",
@@ -196,6 +226,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 1, .size_idx1 = -1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.19–3 is explicit that the OS
+		 * must not call ibm,get-dynamic-sensor-state with
+		 * different inputs until a non-retry status has been
+		 * returned.
+		 */
+		.lock = &rtas_ibm_get_dynamic_sensor_state_lock,
 	},
 	[RTAS_FNIDX__IBM_GET_INDICES] = {
 		.name = "ibm,get-indices",
@@ -203,6 +240,12 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 2, .size_idx1 = 3,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.17–2 says that the OS must not
+		 * interleave ibm,get-indices call sequences with
+		 * different inputs.
+		 */
+		.lock = &rtas_ibm_get_indices_lock,
 	},
 	[RTAS_FNIDX__IBM_GET_RIO_TOPOLOGY] = {
 		.name = "ibm,get-rio-topology",
@@ -220,6 +263,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 0, .size_idx1 = -1,
 			.buf_idx2 = 1, .size_idx2 = 2,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.20–4 indicates that sequences
+		 * should not be allowed to interleave.
+		 */
+		.lock = &rtas_ibm_get_vpd_lock,
 	},
 	[RTAS_FNIDX__IBM_GET_XIVE] = {
 		.name = "ibm,get-xive",
@@ -239,6 +287,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 2, .size_idx1 = 3,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.26–6 says the OS should allow
+		 * only one call sequence in progress at a time.
+		 */
+		.lock = &rtas_ibm_lpar_perftools_lock,
 	},
 	[RTAS_FNIDX__IBM_MANAGE_FLASH_IMAGE] = {
 		.name = "ibm,manage-flash-image",
@@ -277,6 +330,14 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 0, .size_idx1 = 1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * This follows a sequence-based pattern similar to
+		 * ibm,get-vpd et al. Since PAPR+ restricts
+		 * interleaving call sequences for other functions of
+		 * this style, assume the restriction applies here,
+		 * even though it's not explicit in the spec.
+		 */
+		.lock = &rtas_ibm_physical_attestation_lock,
 	},
 	[RTAS_FNIDX__IBM_PLATFORM_DUMP] = {
 		.name = "ibm,platform-dump",
@@ -284,6 +345,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx1 = 4, .size_idx1 = 5,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 7.3.3.4.1 indicates that concurrent
+		 * sequences of ibm,platform-dump are allowed if they
+		 * are operating on different dump tags. So leave the
+		 * lock pointer unset for now. This may need
+		 * reconsideration if kernel-internal users appear.
+		 */
 	},
 	[RTAS_FNIDX__IBM_POWER_OFF_UPS] = {
 		.name = "ibm,power-off-ups",
@@ -307,11 +375,27 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 	[RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2] = {
 		.name = "ibm,read-slot-reset-state2",
 	},
+	[RTAS_FNIDX__IBM_RECEIVE_HVPIPE_MSG] {
+		.name = "ibm,receive-hvpipe-msg",
+		.filter = &(const struct rtas_filter) {
+			.buf_idx1 = 0, .size_idx1 = 1,
+			.buf_idx2 = -1, .size_idx2 = -1,
+		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.32.1
+		 */
+		.lock = &rtas_ibm_receive_hvpipe_msg_lock,
+	},
 	[RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = {
 		.name = "ibm,remove-pe-dma-window",
 	},
-	[RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS] = {
-		.name = "ibm,reset-pe-dma-windows",
+	[RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = {
+		/*
+		 * Note: PAPR+ v2.13 7.3.31.4.1 spells this as
+		 * "ibm,reset-pe-dma-windows" (plural), but RTAS
+		 * implementations use the singular form in practice.
+		 */
+		.name = "ibm,reset-pe-dma-window",
 	},
 	[RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = {
 		.name = "ibm,scan-log-dump",
@@ -320,12 +404,29 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
 	},
+	[RTAS_FNIDX__IBM_SEND_HVPIPE_MSG] {
+		.name = "ibm,send-hvpipe-msg",
+		.filter = &(const struct rtas_filter) {
+			.buf_idx1 = 1, .size_idx1 = -1,
+			.buf_idx2 = -1, .size_idx2 = -1,
+		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.32.2
+		 */
+		.lock = &rtas_ibm_send_hvpipe_msg_lock,
+	},
 	[RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR] = {
 		.name = "ibm,set-dynamic-indicator",
 		.filter = &(const struct rtas_filter) {
 			.buf_idx1 = 2, .size_idx1 = -1,
 			.buf_idx2 = -1, .size_idx2 = -1,
 		},
+		/*
+		 * PAPR+ v2.13 R1–7.3.18–3 says the OS must not call
+		 * this function with different inputs until a
+		 * non-retry status has been returned.
+		 */
+		.lock = &rtas_ibm_set_dynamic_indicator_lock,
 	},
 	[RTAS_FNIDX__IBM_SET_EEH_OPTION] = {
 		.name = "ibm,set-eeh-option",
@@ -454,6 +555,11 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 	},
 };
 
+#define for_each_rtas_function(funcp)                                       \
+	for (funcp = &rtas_function_table[0];                               \
+	     funcp < &rtas_function_table[ARRAY_SIZE(rtas_function_table)]; \
+	     ++funcp)
+
 /*
  * Nearly all RTAS calls need to be serialized. All uses of the
  * default rtas_args block must hold rtas_lock.
@@ -525,10 +631,10 @@ static DEFINE_XARRAY(rtas_token_to_function_xarray);
 
 static int __init rtas_token_to_function_xarray_init(void)
 {
+	const struct rtas_function *func;
 	int err = 0;
 
-	for (size_t i = 0; i < ARRAY_SIZE(rtas_function_table); ++i) {
-		const struct rtas_function *func = &rtas_function_table[i];
+	for_each_rtas_function(func) {
 		const s32 token = func->token;
 
 		if (token == RTAS_UNKNOWN_SERVICE)
@@ -544,6 +650,21 @@ static int __init rtas_token_to_function_xarray_init(void)
 }
 arch_initcall(rtas_token_to_function_xarray_init);
 
+/*
+ * For use by sys_rtas(), where the token value is provided by user
+ * space and we don't want to warn on failed lookups.
+ */
+static const struct rtas_function *rtas_token_to_function_untrusted(s32 token)
+{
+	return xa_load(&rtas_token_to_function_xarray, token);
+}
+
+/*
+ * Reverse lookup for deriving the function descriptor from a
+ * known-good token value in contexts where the former is not already
+ * available. @token must be valid, e.g. derived from the result of a
+ * prior lookup against the function table.
+ */
 static const struct rtas_function *rtas_token_to_function(s32 token)
 {
 	const struct rtas_function *func;
@@ -551,12 +672,22 @@ static const struct rtas_function *rtas_token_to_function(s32 token)
 	if (WARN_ONCE(token < 0, "invalid token %d", token))
 		return NULL;
 
-	func = xa_load(&rtas_token_to_function_xarray, token);
-
-	if (WARN_ONCE(!func, "unexpected failed lookup for token %d", token))
-		return NULL;
+	func = rtas_token_to_function_untrusted(token);
+	if (func)
+		return func;
+	/*
+	 * Fall back to linear scan in case the reverse mapping hasn't
+	 * been initialized yet.
+	 */
+	if (xa_empty(&rtas_token_to_function_xarray)) {
+		for_each_rtas_function(func) {
+			if (func->token == token)
+				return func;
+		}
+	}
 
-	return func;
+	WARN_ONCE(true, "unexpected failed lookup for token %d", token);
+	return NULL;
 }
 
 /* This is here deliberately so it's only used in this file */
@@ -570,28 +701,25 @@ static void __do_enter_rtas(struct rtas_args *args)
 
 static void __do_enter_rtas_trace(struct rtas_args *args)
 {
-	const char *name = NULL;
+	const struct rtas_function *func = rtas_token_to_function(be32_to_cpu(args->token));
 
-	if (args == &rtas_args)
-		lockdep_assert_held(&rtas_lock);
 	/*
-	 * If the tracepoints that consume the function name aren't
-	 * active, avoid the lookup.
+	 * If there is a per-function lock, it must be held by the
+	 * caller.
 	 */
-	if ((trace_rtas_input_enabled() || trace_rtas_output_enabled())) {
-		const s32 token = be32_to_cpu(args->token);
-		const struct rtas_function *func = rtas_token_to_function(token);
+	if (func->lock)
+		lockdep_assert_held(func->lock);
 
-		name = func->name;
-	}
+	if (args == &rtas_args)
+		lockdep_assert_held(&rtas_lock);
 
-	trace_rtas_input(args, name);
+	trace_rtas_input(args, func->name);
 	trace_rtas_ll_entry(args);
 
 	__do_enter_rtas(args);
 
 	trace_rtas_ll_exit(args);
-	trace_rtas_output(args, name);
+	trace_rtas_output(args, func->name);
 }
 
 static void do_enter_rtas(struct rtas_args *args)
@@ -670,7 +798,7 @@ static void call_rtas_display_status_delay(char c)
 	static int pending_newline = 0;  /* did last write end with unprinted newline? */
 	static int width = 16;
 
-	if (c == '\n') {	
+	if (c == '\n') {
 		while (width-- > 0)
 			call_rtas_display_status(' ');
 		width = 16;
@@ -680,7 +808,7 @@ static void call_rtas_display_status_delay(char c)
 		if (pending_newline) {
 			call_rtas_display_status('\r');
 			call_rtas_display_status('\n');
-		} 
+		}
 		pending_newline = 0;
 		if (width--) {
 			call_rtas_display_status(c);
@@ -694,66 +822,6 @@ void __init udbg_init_rtas_panel(void)
 	udbg_putc = call_rtas_display_status_delay;
 }
 
-#ifdef CONFIG_UDBG_RTAS_CONSOLE
-
-/* If you think you're dying before early_init_dt_scan_rtas() does its
- * work, you can hard code the token values for your firmware here and
- * hardcode rtas.base/entry etc.
- */
-static unsigned int rtas_putchar_token = RTAS_UNKNOWN_SERVICE;
-static unsigned int rtas_getchar_token = RTAS_UNKNOWN_SERVICE;
-
-static void udbg_rtascon_putc(char c)
-{
-	int tries;
-
-	if (!rtas.base)
-		return;
-
-	/* Add CRs before LFs */
-	if (c == '\n')
-		udbg_rtascon_putc('\r');
-
-	/* if there is more than one character to be displayed, wait a bit */
-	for (tries = 0; tries < 16; tries++) {
-		if (rtas_call(rtas_putchar_token, 1, 1, NULL, c) == 0)
-			break;
-		udelay(1000);
-	}
-}
-
-static int udbg_rtascon_getc_poll(void)
-{
-	int c;
-
-	if (!rtas.base)
-		return -1;
-
-	if (rtas_call(rtas_getchar_token, 0, 2, &c))
-		return -1;
-
-	return c;
-}
-
-static int udbg_rtascon_getc(void)
-{
-	int c;
-
-	while ((c = udbg_rtascon_getc_poll()) == -1)
-		;
-
-	return c;
-}
-
-
-void __init udbg_init_rtas_console(void)
-{
-	udbg_putc = udbg_rtascon_putc;
-	udbg_getc = udbg_rtascon_getc;
-	udbg_getc_poll = udbg_rtascon_getc_poll;
-}
-#endif /* CONFIG_UDBG_RTAS_CONSOLE */
-
 void rtas_progress(char *s, unsigned short hex)
 {
 	struct device_node *root;
@@ -820,7 +888,7 @@ void rtas_progress(char *s, unsigned short hex)
 		else
 			rtas_call(display_character, 1, 1, NULL, '\r');
 	}
- 
+
 	if (row_width)
 		width = row_width[current_line];
 	else
@@ -840,9 +908,9 @@ void rtas_progress(char *s, unsigned short hex)
 				spin_unlock(&progress_lock);
 				return;
 			}
- 
+
 			/* RTAS wants CR-LF, not just LF */
- 
+
 			if (*os == '\n') {
 				rtas_call(display_character, 1, 1, NULL, '\r');
 				rtas_call(display_character, 1, 1, NULL, '\n');
@@ -852,7 +920,7 @@ void rtas_progress(char *s, unsigned short hex)
 				 */
 				rtas_call(display_character, 1, 1, NULL, *os);
 			}
- 
+
 			if (row_width)
 				width = row_width[current_line];
 			else
@@ -861,15 +929,15 @@ void rtas_progress(char *s, unsigned short hex)
 			width--;
 			rtas_call(display_character, 1, 1, NULL, *os);
 		}
- 
+
 		os++;
- 
+
 		/* if we overwrite the screen length */
 		if (width <= 0)
 			while ((*os != 0) && (*os != '\n') && (*os != '\r'))
 				os++;
 	}
- 
+
 	spin_unlock(&progress_lock);
 }
 EXPORT_SYMBOL_GPL(rtas_progress);		/* needed by rtas_flash module */
@@ -900,11 +968,6 @@ int rtas_token(const char *service)
 }
 EXPORT_SYMBOL_GPL(rtas_token);
 
-int rtas_service_present(const char *service)
-{
-	return rtas_token(service) != RTAS_UNKNOWN_SERVICE;
-}
-
 #ifdef CONFIG_RTAS_ERROR_LOGGING
 
 static u32 rtas_error_log_max __ro_after_init = RTAS_ERROR_LOG_MAX;
@@ -1291,21 +1354,14 @@ bool __ref rtas_busy_delay(int status)
 		 */
 		ms = clamp(ms, 1U, 1000U);
 		/*
-		 * The delay hint is an order-of-magnitude suggestion, not
-		 * a minimum. It is fine, possibly even advantageous, for
-		 * us to pause for less time than hinted. For small values,
-		 * use usleep_range() to ensure we don't sleep much longer
-		 * than actually needed.
-		 *
-		 * See Documentation/timers/timers-howto.rst for
-		 * explanation of the threshold used here. In effect we use
-		 * usleep_range() for 9900 and 9901, msleep() for
-		 * 9902-9905.
+		 * The delay hint is an order-of-magnitude suggestion, not a
+		 * minimum. It is fine, possibly even advantageous, for us to
+		 * pause for less time than hinted. To make sure pause time will
+		 * not be way longer than requested independent of HZ
+		 * configuration, use fsleep(). See fsleep() for details of
+		 * used sleeping functions.
 		 */
-		if (ms <= 20)
-			usleep_range(ms * 100, ms * 1000);
-		else
-			msleep(ms);
+		fsleep(ms * 1000);
 		break;
 	case RTAS_BUSY:
 		ret = true;
@@ -1330,33 +1386,34 @@ bool __ref rtas_busy_delay(int status)
 }
 EXPORT_SYMBOL_GPL(rtas_busy_delay);
 
-static int rtas_error_rc(int rtas_rc)
+int rtas_error_rc(int rtas_rc)
 {
 	int rc;
 
 	switch (rtas_rc) {
-		case -1: 		/* Hardware Error */
-			rc = -EIO;
-			break;
-		case -3:		/* Bad indicator/domain/etc */
-			rc = -EINVAL;
-			break;
-		case -9000:		/* Isolation error */
-			rc = -EFAULT;
-			break;
-		case -9001:		/* Outstanding TCE/PTE */
-			rc = -EEXIST;
-			break;
-		case -9002:		/* No usable slot */
-			rc = -ENODEV;
-			break;
-		default:
-			pr_err("%s: unexpected error %d\n", __func__, rtas_rc);
-			rc = -ERANGE;
-			break;
+	case RTAS_HARDWARE_ERROR:	/* Hardware Error */
+		rc = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER:	/* Bad indicator/domain/etc */
+		rc = -EINVAL;
+		break;
+	case -9000:			/* Isolation error */
+		rc = -EFAULT;
+		break;
+	case -9001:			/* Outstanding TCE/PTE */
+		rc = -EEXIST;
+		break;
+	case -9002:			/* No usable slot */
+		rc = -ENODEV;
+		break;
+	default:
+		pr_err("%s: unexpected error %d\n", __func__, rtas_rc);
+		rc = -ERANGE;
+		break;
 	}
 	return rc;
 }
+EXPORT_SYMBOL_GPL(rtas_error_rc);
 
 int rtas_get_power_level(int powerdomain, int *level)
 {
@@ -1587,6 +1644,7 @@ static bool ibm_extended_os_term;
 void rtas_os_term(char *str)
 {
 	s32 token = rtas_function_token(RTAS_FN_IBM_OS_TERM);
+	static struct rtas_args args;
 	int status;
 
 	/*
@@ -1607,7 +1665,8 @@ void rtas_os_term(char *str)
 	 * schedules.
 	 */
 	do {
-		status = rtas_call(token, 1, 1, NULL, __pa(rtas_os_term_buf));
+		rtas_call_unlocked(&args, token, 1, 1, NULL, __pa(rtas_os_term_buf));
+		status = be32_to_cpu(args.rets[0]);
 	} while (rtas_busy_delay_time(status));
 
 	if (status != 0)
@@ -1635,10 +1694,14 @@ void rtas_activate_firmware(void)
 		return;
 	}
 
+	mutex_lock(&rtas_ibm_activate_firmware_lock);
+
 	do {
 		fwrc = rtas_call(token, 0, 1, NULL);
 	} while (rtas_busy_delay(fwrc));
 
+	mutex_unlock(&rtas_ibm_activate_firmware_lock);
+
 	if (fwrc)
 		pr_err("ibm,activate-firmware failed (%i)\n", fwrc);
 }
@@ -1710,24 +1773,18 @@ static bool in_rmo_buf(u32 base, u32 end)
 		end < (rtas_rmo_buf + RTAS_USER_REGION_SIZE);
 }
 
-static bool block_rtas_call(int token, int nargs,
+static bool block_rtas_call(const struct rtas_function *func, int nargs,
 			    struct rtas_args *args)
 {
-	const struct rtas_function *func;
 	const struct rtas_filter *f;
-	const bool is_platform_dump = token == rtas_function_token(RTAS_FN_IBM_PLATFORM_DUMP);
-	const bool is_config_conn = token == rtas_function_token(RTAS_FN_IBM_CONFIGURE_CONNECTOR);
+	const bool is_platform_dump =
+		func == &rtas_function_table[RTAS_FNIDX__IBM_PLATFORM_DUMP];
+	const bool is_config_conn =
+		func == &rtas_function_table[RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR];
 	u32 base, size, end;
 
 	/*
-	 * If this token doesn't correspond to a function the kernel
-	 * understands, you're not allowed to call it.
-	 */
-	func = rtas_token_to_function(token);
-	if (!func)
-		goto err;
-	/*
-	 * And only functions with filters attached are allowed.
+	 * Only functions with filters attached are allowed.
 	 */
 	f = func->filter;
 	if (!f)
@@ -1784,14 +1841,15 @@ static bool block_rtas_call(int token, int nargs,
 	return false;
 err:
 	pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n");
-	pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n",
-			   token, nargs, current->comm);
+	pr_err_ratelimited("sys_rtas: %s nargs=%d (called by %s)\n",
+			   func->name, nargs, current->comm);
 	return true;
 }
 
 /* We assume to be passed big endian arguments */
 SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 {
+	const struct rtas_function *func;
 	struct pin_cookie cookie;
 	struct rtas_args args;
 	unsigned long flags;
@@ -1816,18 +1874,26 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 	    || nargs + nret > ARRAY_SIZE(args.args))
 		return -EINVAL;
 
+	nargs = array_index_nospec(nargs, ARRAY_SIZE(args.args));
+	nret = array_index_nospec(nret, ARRAY_SIZE(args.args) - nargs);
+
 	/* Copy in args. */
 	if (copy_from_user(args.args, uargs->args,
 			   nargs * sizeof(rtas_arg_t)) != 0)
 		return -EFAULT;
 
-	if (token == RTAS_UNKNOWN_SERVICE)
+	/*
+	 * If this token doesn't correspond to a function the kernel
+	 * understands, you're not allowed to call it.
+	 */
+	func = rtas_token_to_function_untrusted(token);
+	if (!func)
 		return -EINVAL;
 
 	args.rets = &args.args[nargs];
 	memset(args.rets, 0, nret * sizeof(rtas_arg_t));
 
-	if (block_rtas_call(token, nargs, &args))
+	if (block_rtas_call(func, nargs, &args))
 		return -EINVAL;
 
 	if (token_is_restricted_errinjct(token)) {
@@ -1860,6 +1926,15 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 
 	buff_copy = get_errorlog_buffer();
 
+	/*
+	 * If this function has a mutex assigned to it, we must
+	 * acquire it to avoid interleaving with any kernel-based uses
+	 * of the same function. Kernel-based sequences acquire the
+	 * appropriate mutex explicitly.
+	 */
+	if (func->lock)
+		mutex_lock(func->lock);
+
 	raw_spin_lock_irqsave(&rtas_lock, flags);
 	cookie = lockdep_pin_lock(&rtas_lock);
 
@@ -1875,6 +1950,9 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
 	lockdep_unpin_lock(&rtas_lock, cookie);
 	raw_spin_unlock_irqrestore(&rtas_lock, flags);
 
+	if (func->lock)
+		mutex_unlock(func->lock);
+
 	if (buff_copy) {
 		if (errbuf)
 			log_error(errbuf, ERR_TYPE_RTAS_LOG, 0);
@@ -2021,21 +2099,6 @@ int __init early_init_dt_scan_rtas(unsigned long node,
 		rtas.size = *sizep;
 	}
 
-#ifdef CONFIG_UDBG_RTAS_CONSOLE
-	basep = of_get_flat_dt_prop(node, "put-term-char", NULL);
-	if (basep)
-		rtas_putchar_token = *basep;
-
-	basep = of_get_flat_dt_prop(node, "get-term-char", NULL);
-	if (basep)
-		rtas_getchar_token = *basep;
-
-	if (rtas_putchar_token != RTAS_UNKNOWN_SERVICE &&
-	    rtas_getchar_token != RTAS_UNKNOWN_SERVICE)
-		udbg_init_rtas_console();
-
-#endif
-
 	/* break now */
 	return 1;
 }
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 4caf5e3079eb..583dc16e9d3c 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -312,13 +312,13 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
 {
 	struct rtas_update_flash_t *const uf = &rtas_update_flash_data;
 	char *p;
-	int next_free, rc;
+	int next_free;
 	struct flash_block_list *fl;
 
-	mutex_lock(&rtas_update_flash_mutex);
+	guard(mutex)(&rtas_update_flash_mutex);
 
 	if (uf->status == FLASH_AUTH || count == 0)
-		goto out;	/* discard data */
+		return count;	/* discard data */
 
 	/* In the case that the image is not ready for flashing, the memory
 	 * allocated for the block list will be freed upon the release of the 
@@ -327,7 +327,7 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
 	if (uf->flist == NULL) {
 		uf->flist = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL);
 		if (!uf->flist)
-			goto nomem;
+			return -ENOMEM;
 	}
 
 	fl = uf->flist;
@@ -338,7 +338,7 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
 		/* Need to allocate another block_list */
 		fl->next = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL);
 		if (!fl->next)
-			goto nomem;
+			return -ENOMEM;
 		fl = fl->next;
 		next_free = 0;
 	}
@@ -347,25 +347,17 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
 		count = RTAS_BLK_SIZE;
 	p = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL);
 	if (!p)
-		goto nomem;
+		return -ENOMEM;
 	
 	if(copy_from_user(p, buffer, count)) {
 		kmem_cache_free(flash_block_cache, p);
-		rc = -EFAULT;
-		goto error;
+		return -EFAULT;
 	}
 	fl->blocks[next_free].data = p;
 	fl->blocks[next_free].length = count;
 	fl->num_blocks++;
-out:
-	mutex_unlock(&rtas_update_flash_mutex);
-	return count;
 
-nomem:
-	rc = -ENOMEM;
-error:
-	mutex_unlock(&rtas_update_flash_mutex);
-	return rc;
+	return count;
 }
 
 /*
@@ -405,19 +397,18 @@ static ssize_t manage_flash_write(struct file *file, const char __user *buf,
 	static const char reject_str[] = "0";
 	static const char commit_str[] = "1";
 	char stkbuf[10];
-	int op, rc;
+	int op;
 
-	mutex_lock(&rtas_manage_flash_mutex);
+	guard(mutex)(&rtas_manage_flash_mutex);
 
 	if ((args_buf->status == MANAGE_AUTH) || (count == 0))
-		goto out;
+		return count;
 		
 	op = -1;
 	if (buf) {
 		if (count > 9) count = 9;
-		rc = -EFAULT;
 		if (copy_from_user (stkbuf, buf, count))
-			goto error;
+			return -EFAULT;
 		if (strncmp(stkbuf, reject_str, strlen(reject_str)) == 0) 
 			op = RTAS_REJECT_TMP_IMG;
 		else if (strncmp(stkbuf, commit_str, strlen(commit_str)) == 0) 
@@ -425,18 +416,11 @@ static ssize_t manage_flash_write(struct file *file, const char __user *buf,
 	}
 	
 	if (op == -1) {   /* buf is empty, or contains invalid string */
-		rc = -EINVAL;
-		goto error;
+		return -EINVAL;
 	}
 
 	manage_flash(args_buf, op);
-out:
-	mutex_unlock(&rtas_manage_flash_mutex);
 	return count;
-
-error:
-	mutex_unlock(&rtas_manage_flash_mutex);
-	return rc;
 }
 
 /*
@@ -499,16 +483,14 @@ static ssize_t validate_flash_write(struct file *file, const char __user *buf,
 {
 	struct rtas_validate_flash_t *const args_buf =
 		&rtas_validate_flash_data;
-	int rc;
 
-	mutex_lock(&rtas_validate_flash_mutex);
+	guard(mutex)(&rtas_validate_flash_mutex);
 
 	/* We are only interested in the first 4K of the
 	 * candidate image */
 	if ((*off >= VALIDATE_BUF_SIZE) || 
 		(args_buf->status == VALIDATE_AUTH)) {
 		*off += count;
-		mutex_unlock(&rtas_validate_flash_mutex);
 		return count;
 	}
 
@@ -519,20 +501,14 @@ static ssize_t validate_flash_write(struct file *file, const char __user *buf,
 		args_buf->status = VALIDATE_INCOMPLETE;
 	}
 
-	if (!access_ok(buf, count)) {
-		rc = -EFAULT;
-		goto done;
-	}
-	if (copy_from_user(args_buf->buf + *off, buf, count)) {
-		rc = -EFAULT;
-		goto done;
-	}
+	if (!access_ok(buf, count))
+		return -EFAULT;
+
+	if (copy_from_user(args_buf->buf + *off, buf, count))
+		return -EFAULT;
 
 	*off += count;
-	rc = count;
-done:
-	mutex_unlock(&rtas_validate_flash_mutex);
-	return rc;
+	return count;
 }
 
 static int validate_flash_release(struct inode *inode, struct file *file)
@@ -709,9 +685,9 @@ static int __init rtas_flash_init(void)
 	if (!rtas_validate_flash_data.buf)
 		return -ENOMEM;
 
-	flash_block_cache = kmem_cache_create("rtas_flash_cache",
-					      RTAS_BLK_SIZE, RTAS_BLK_SIZE, 0,
-					      NULL);
+	flash_block_cache = kmem_cache_create_usercopy("rtas_flash_cache",
+						       RTAS_BLK_SIZE, RTAS_BLK_SIZE,
+						       0, 0, RTAS_BLK_SIZE, NULL);
 	if (!flash_block_cache) {
 		printk(KERN_ERR "%s: failed to create block cache\n",
 				__func__);
@@ -773,4 +749,5 @@ static void __exit rtas_flash_cleanup(void)
 
 module_init(rtas_flash_init);
 module_exit(rtas_flash_cleanup);
+MODULE_DESCRIPTION("PPC procfs firmware flash interface");
 MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index e1fdc7473b72..fccf96e897f6 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -43,7 +43,7 @@ static inline int config_access_valid(struct pci_dn *dn, int where)
 	return 0;
 }
 
-int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
+int rtas_pci_dn_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
 {
 	int returnval = -1;
 	unsigned long buid, addr;
@@ -87,7 +87,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 	pdn = pci_get_pdn_by_devfn(bus, devfn);
 
 	/* Validity of pdn is checked in here */
-	ret = rtas_read_config(pdn, where, size, val);
+	ret = rtas_pci_dn_read_config(pdn, where, size, val);
 	if (*val == EEH_IO_ERROR_VALUE(size) &&
 	    eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
 		return PCIBIOS_DEVICE_NOT_FOUND;
@@ -95,7 +95,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 	return ret;
 }
 
-int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
+int rtas_pci_dn_write_config(struct pci_dn *pdn, int where, int size, u32 val)
 {
 	unsigned long buid, addr;
 	int ret;
@@ -134,7 +134,7 @@ static int rtas_pci_write_config(struct pci_bus *bus,
 	pdn = pci_get_pdn_by_devfn(bus, devfn);
 
 	/* Validity of pdn is checked in here. */
-	return rtas_write_config(pdn, where, size, val);
+	return rtas_pci_dn_write_config(pdn, where, size, val);
 }
 
 static struct pci_ops rtas_pci_ops = {
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 9bba469239fc..6336ec9aedd0 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -89,6 +89,8 @@ static char *rtas_event_type(int type)
 			return "Platform Resource Reassignment Event";
 		case RTAS_TYPE_HOTPLUG:
 			return "Hotplug Event";
+		case RTAS_TYPE_HVPIPE:
+			return "Hypervisor Pipe Notification event";
 	}
 
 	return rtas_type[0];
diff --git a/arch/powerpc/kernel/secure_boot.c b/arch/powerpc/kernel/secure_boot.c
index f9af305d9579..3a28795b4ed8 100644
--- a/arch/powerpc/kernel/secure_boot.c
+++ b/arch/powerpc/kernel/secure_boot.c
@@ -5,6 +5,7 @@
  */
 #include <linux/types.h>
 #include <linux/of.h>
+#include <linux/string_choices.h>
 #include <asm/secure_boot.h>
 
 static struct device_node *get_ppc_fw_sb_node(void)
@@ -32,11 +33,13 @@ bool is_ppc_secureboot_enabled(void)
 	if (enabled)
 		goto out;
 
-	if (!of_property_read_u32(of_root, "ibm,secure-boot", &secureboot))
+	node = of_find_node_by_path("/");
+	if (!of_property_read_u32(node, "ibm,secure-boot", &secureboot))
 		enabled = (secureboot > 1);
+	of_node_put(node);
 
 out:
-	pr_info("Secure boot mode %s\n", enabled ? "enabled" : "disabled");
+	pr_info("Secure boot mode %s\n", str_enabled_disabled(enabled));
 
 	return enabled;
 }
@@ -54,11 +57,13 @@ bool is_ppc_trustedboot_enabled(void)
 	if (enabled)
 		goto out;
 
-	if (!of_property_read_u32(of_root, "ibm,trusted-boot", &trustedboot))
+	node = of_find_node_by_path("/");
+	if (!of_property_read_u32(node, "ibm,trusted-boot", &trustedboot))
 		enabled = (trustedboot > 0);
+	of_node_put(node);
 
 out:
-	pr_info("Trusted boot mode %s\n", enabled ? "enabled" : "disabled");
+	pr_info("Trusted boot mode %s\n", str_enabled_disabled(enabled));
 
 	return enabled;
 }
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index 206475e3e0b4..fbb7ebd8aa08 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -14,7 +14,7 @@
 #include <linux/debugfs.h>
 
 #include <asm/asm-prototypes.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/security_features.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
@@ -364,26 +364,27 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *
 
 static int ssb_prctl_get(struct task_struct *task)
 {
+	/*
+	 * The STF_BARRIER feature is on by default, so if it's off that means
+	 * firmware has explicitly said the CPU is not vulnerable via either
+	 * the hypercall or device tree.
+	 */
+	if (!security_ftr_enabled(SEC_FTR_STF_BARRIER))
+		return PR_SPEC_NOT_AFFECTED;
+
+	/*
+	 * If the system's CPU has no known barrier (see setup_stf_barrier())
+	 * then assume that the CPU is not vulnerable.
+	 */
 	if (stf_enabled_flush_types == STF_BARRIER_NONE)
-		/*
-		 * We don't have an explicit signal from firmware that we're
-		 * vulnerable or not, we only have certain CPU revisions that
-		 * are known to be vulnerable.
-		 *
-		 * We assume that if we're on another CPU, where the barrier is
-		 * NONE, then we are not vulnerable.
-		 */
 		return PR_SPEC_NOT_AFFECTED;
-	else
-		/*
-		 * If we do have a barrier type then we are vulnerable. The
-		 * barrier is not a global or per-process mitigation, so the
-		 * only value we can report here is PR_SPEC_ENABLE, which
-		 * appears as "vulnerable" in /proc.
-		 */
-		return PR_SPEC_ENABLE;
-
-	return -EINVAL;
+
+	/*
+	 * Otherwise the CPU is vulnerable. The barrier is not a global or
+	 * per-process mitigation, so the only value that can be reported here
+	 * is PR_SPEC_ENABLE, which appears as "vulnerable" in /proc.
+	 */
+	return PR_SPEC_ENABLE;
 }
 
 int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c
index eb3c053f323f..ec900bce0257 100644
--- a/arch/powerpc/kernel/secvar-sysfs.c
+++ b/arch/powerpc/kernel/secvar-sysfs.c
@@ -52,7 +52,7 @@ static ssize_t size_show(struct kobject *kobj, struct kobj_attribute *attr,
 }
 
 static ssize_t data_read(struct file *filep, struct kobject *kobj,
-			 struct bin_attribute *attr, char *buf, loff_t off,
+			 const struct bin_attribute *attr, char *buf, loff_t off,
 			 size_t count)
 {
 	char *data;
@@ -85,7 +85,7 @@ data_fail:
 }
 
 static ssize_t update_write(struct file *filep, struct kobject *kobj,
-			    struct bin_attribute *attr, char *buf, loff_t off,
+			    const struct bin_attribute *attr, char *buf, loff_t off,
 			    size_t count)
 {
 	int rc;
@@ -104,11 +104,11 @@ static struct kobj_attribute format_attr = __ATTR_RO(format);
 
 static struct kobj_attribute size_attr = __ATTR_RO(size);
 
-static struct bin_attribute data_attr = __BIN_ATTR_RO(data, 0);
+static struct bin_attribute data_attr __ro_after_init = __BIN_ATTR_RO(data, 0);
 
-static struct bin_attribute update_attr = __BIN_ATTR_WO(update, 0);
+static struct bin_attribute update_attr __ro_after_init = __BIN_ATTR_WO(update, 0);
 
-static struct bin_attribute *secvar_bin_attrs[] = {
+static const struct bin_attribute *const secvar_bin_attrs[] = {
 	&data_attr,
 	&update_attr,
 	NULL,
@@ -125,12 +125,12 @@ static const struct attribute_group secvar_attr_group = {
 };
 __ATTRIBUTE_GROUPS(secvar_attr);
 
-static struct kobj_type secvar_ktype = {
+static const struct kobj_type secvar_ktype = {
 	.sysfs_ops	= &kobj_sysfs_ops,
 	.default_groups = secvar_attr_groups,
 };
 
-static int update_kobj_size(void)
+static __init int update_kobj_size(void)
 {
 
 	u64 varsize;
@@ -145,7 +145,7 @@ static int update_kobj_size(void)
 	return 0;
 }
 
-static int secvar_sysfs_config(struct kobject *kobj)
+static __init int secvar_sysfs_config(struct kobject *kobj)
 {
 	struct attribute_group config_group = {
 		.name = "config",
@@ -158,7 +158,7 @@ static int secvar_sysfs_config(struct kobject *kobj)
 	return 0;
 }
 
-static int add_var(const char *name)
+static __init int add_var(const char *name)
 {
 	struct kobject *kobj;
 	int rc;
@@ -181,7 +181,7 @@ static int add_var(const char *name)
 	return 0;
 }
 
-static int secvar_sysfs_load(void)
+static __init int secvar_sysfs_load(void)
 {
 	u64 namesize = 0;
 	char *name;
@@ -209,7 +209,7 @@ static int secvar_sysfs_load(void)
 	return rc;
 }
 
-static int secvar_sysfs_load_static(void)
+static __init int secvar_sysfs_load_static(void)
 {
 	const char * const *name_ptr = secvar_ops->var_names;
 	int rc;
@@ -224,7 +224,7 @@ static int secvar_sysfs_load_static(void)
 	return 0;
 }
 
-static int secvar_sysfs_init(void)
+static __init int secvar_sysfs_init(void)
 {
 	u64 max_size;
 	int rc;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index d2a446216444..c8c42b419742 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -22,7 +22,6 @@
 #include <linux/seq_file.h>
 #include <linux/ioport.h>
 #include <linux/console.h>
-#include <linux/screen_info.h>
 #include <linux/root_dev.h>
 #include <linux/cpu.h>
 #include <linux/unistd.h>
@@ -31,11 +30,12 @@
 #include <linux/serial_8250.h>
 #include <linux/percpu.h>
 #include <linux/memblock.h>
-#include <linux/of_irq.h>
+#include <linux/of.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
+#include <linux/of_irq.h>
 #include <linux/hugetlb.h>
 #include <linux/pgtable.h>
+#include <asm/kexec.h>
 #include <asm/io.h>
 #include <asm/paca.h>
 #include <asm/processor.h>
@@ -68,6 +68,7 @@
 #include <asm/cpu_has_feature.h>
 #include <asm/kasan.h>
 #include <asm/mce.h>
+#include <asm/systemcfg.h>
 
 #include "setup.h"
 
@@ -86,6 +87,7 @@ EXPORT_SYMBOL(machine_id);
 
 int boot_cpuid = -1;
 EXPORT_SYMBOL_GPL(boot_cpuid);
+int __initdata boot_core_hwid = -1;
 
 #ifdef CONFIG_PPC64
 int boot_cpu_hwid = -1;
@@ -98,21 +100,6 @@ int boot_cpu_hwid = -1;
 int dcache_bsize;
 int icache_bsize;
 
-/*
- * This still seems to be needed... -- paulus
- */ 
-struct screen_info screen_info = {
-	.orig_x = 0,
-	.orig_y = 25,
-	.orig_video_cols = 80,
-	.orig_video_lines = 25,
-	.orig_video_isVGA = 1,
-	.orig_video_points = 16
-};
-#if defined(CONFIG_FB_VGA16_MODULE)
-EXPORT_SYMBOL(screen_info);
-#endif
-
 /* Variables required to store legacy IO irq routing */
 int of_i8042_kbd_irq;
 EXPORT_SYMBOL_GPL(of_i8042_kbd_irq);
@@ -125,7 +112,7 @@ int ppc_do_canonicalize_irqs;
 EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
 #endif
 
-#ifdef CONFIG_CRASH_CORE
+#ifdef CONFIG_CRASH_DUMP
 /* This keeps a track of which one is the crashing cpu. */
 int crashing_cpu = -1;
 #endif
@@ -420,13 +407,32 @@ static void __init cpu_init_thread_core_maps(int tpc)
 		cpumask_set_cpu(i, &threads_core_mask);
 
 	printk(KERN_INFO "CPU maps initialized for %d thread%s per core\n",
-	       tpc, tpc > 1 ? "s" : "");
+	       tpc, str_plural(tpc));
 	printk(KERN_DEBUG " (thread shift is %d)\n", threads_shift);
 }
 
 
 u32 *cpu_to_phys_id = NULL;
 
+static int assign_threads(unsigned int cpu, unsigned int nthreads, bool present,
+			  const __be32 *hw_ids)
+{
+	for (int i = 0; i < nthreads && cpu < nr_cpu_ids; i++) {
+		__be32 hwid;
+
+		hwid = be32_to_cpu(hw_ids[i]);
+
+		DBG("    thread %d -> cpu %d (hard id %d)\n", i, cpu, hwid);
+
+		set_cpu_present(cpu, present);
+		set_cpu_possible(cpu, true);
+		cpu_to_phys_id[cpu] = hwid;
+		cpu++;
+	}
+
+	return cpu;
+}
+
 /**
  * setup_cpu_maps - initialize the following cpu maps:
  *                  cpu_possible_mask
@@ -453,16 +459,13 @@ void __init smp_setup_cpu_maps(void)
 
 	DBG("smp_setup_cpu_maps()\n");
 
-	cpu_to_phys_id = memblock_alloc(nr_cpu_ids * sizeof(u32),
+	cpu_to_phys_id = memblock_alloc_or_panic(nr_cpu_ids * sizeof(u32),
 					__alignof__(u32));
-	if (!cpu_to_phys_id)
-		panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
-		      __func__, nr_cpu_ids * sizeof(u32), __alignof__(u32));
 
 	for_each_node_by_type(dn, "cpu") {
 		const __be32 *intserv;
 		__be32 cpu_be;
-		int j, len;
+		int len;
 
 		DBG("  * %pOF...\n", dn);
 
@@ -484,27 +487,31 @@ void __init smp_setup_cpu_maps(void)
 
 		nthreads = len / sizeof(int);
 
-		for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
-			bool avail;
-
-			DBG("    thread %d -> cpu %d (hard id %d)\n",
-			    j, cpu, be32_to_cpu(intserv[j]));
+		bool avail = of_device_is_available(dn);
+		if (!avail)
+			avail = !of_property_match_string(dn,
+					"enable-method", "spin-table");
 
-			avail = of_device_is_available(dn);
-			if (!avail)
-				avail = !of_property_match_string(dn,
-						"enable-method", "spin-table");
-
-			set_cpu_present(cpu, avail);
-			set_cpu_possible(cpu, true);
-			cpu_to_phys_id[cpu] = be32_to_cpu(intserv[j]);
-			cpu++;
-		}
+		if (boot_core_hwid >= 0) {
+			if (cpu == 0) {
+				pr_info("Skipping CPU node %pOF to allow for boot core.\n", dn);
+				cpu = nthreads;
+				continue;
+			}
 
-		if (cpu >= nr_cpu_ids) {
+			if (be32_to_cpu(intserv[0]) == boot_core_hwid) {
+				pr_info("Renumbered boot core %pOF to logical 0\n", dn);
+				assign_threads(0, nthreads, avail, intserv);
+				of_node_put(dn);
+				break;
+			}
+		} else if (cpu >= nr_cpu_ids) {
 			of_node_put(dn);
 			break;
 		}
+
+		if (cpu < nr_cpu_ids)
+			cpu = assign_threads(cpu, nthreads, avail, intserv);
 	}
 
 	/* If no SMT supported, nthreads is forced to 1 */
@@ -552,7 +559,9 @@ void __init smp_setup_cpu_maps(void)
 	out:
 		of_node_put(dn);
 	}
-	vdso_data->processorCount = num_present_cpus();
+#endif
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->processorCount = num_present_cpus();
 #endif /* CONFIG_PPC64 */
 
         /* Initialize CPU <=> thread mapping/
@@ -601,7 +610,6 @@ struct seq_buf ppc_hw_desc __initdata = {
 	.buffer = ppc_hw_desc_buf,
 	.size = sizeof(ppc_hw_desc_buf),
 	.len = 0,
-	.readpos = 0,
 };
 
 static __init void probe_machine(void)
@@ -633,6 +641,8 @@ static __init void probe_machine(void)
 		DBG("  %s ...\n", machine_id->name);
 		if (machine_id->compatible && !of_machine_is_compatible(machine_id->compatible))
 			continue;
+		if (machine_id->compatibles && !of_machine_compatible_match(machine_id->compatibles))
+			continue;
 		memcpy(&ppc_md, machine_id, sizeof(struct machdep_calls));
 		if (ppc_md.probe && !ppc_md.probe())
 			continue;
@@ -822,8 +832,8 @@ static int __init check_cache_coherency(void)
 	if (devtree_coherency != KERNEL_COHERENCY) {
 		printk(KERN_ERR
 			"kernel coherency:%s != device tree_coherency:%s\n",
-			KERNEL_COHERENCY ? "on" : "off",
-			devtree_coherency ? "on" : "off");
+			str_on_off(KERNEL_COHERENCY),
+			str_on_off(devtree_coherency));
 		BUG();
 	}
 
@@ -948,6 +958,7 @@ void __init setup_arch(char **cmdline_p)
 
 	/* Parse memory topology */
 	mem_topology_setup();
+	high_memory = (void *)__va(max_low_pfn * PAGE_SIZE);
 
 	/*
 	 * Release secondary cpus out of their spinloops at 0x60 now that
@@ -969,8 +980,12 @@ void __init setup_arch(char **cmdline_p)
 	klp_init_thread_info(&init_task);
 
 	setup_initial_init_mm(_stext, _etext, _edata, _end);
-
+	/* sched_init() does the mmgrab(&init_mm) for the primary CPU */
+	VM_WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(&init_mm)));
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(&init_mm));
+	inc_mm_active_cpus(&init_mm);
 	mm_iommu_init(&init_mm);
+
 	irqstack_early_init();
 	exc_lvl_early_init();
 	emergency_stack_init();
@@ -981,9 +996,12 @@ void __init setup_arch(char **cmdline_p)
 	initmem_init();
 
 	/*
-	 * Reserve large chunks of memory for use by CMA for KVM and hugetlb. These must
-	 * be called after initmem_init(), so that pageblock_order is initialised.
+	 * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM and
+	 * hugetlb. These must be called after initmem_init(), so that
+	 * pageblock_order is initialised.
 	 */
+	fadump_cma_init();
+	kdump_cma_reserve();
 	kvm_cma_reserve();
 	gigantic_hugetlb_cma_reserve();
 
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
index 7912bb50a7cb..385a00a2e2ca 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -29,7 +29,7 @@ void setup_tlb_core_data(void);
 static inline void setup_tlb_core_data(void) { }
 #endif
 
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 void exc_lvl_early_init(void);
 #else
 static inline void exc_lvl_early_init(void) { }
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index b761cc1a403c..5a1bf501fbe1 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -40,7 +40,7 @@
 #include <asm/time.h>
 #include <asm/serial.h>
 #include <asm/udbg.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/cpu_has_feature.h>
 #include <asm/asm-prototypes.h>
 #include <asm/kdump.h>
@@ -140,13 +140,7 @@ arch_initcall(ppc_init);
 
 static void *__init alloc_stack(void)
 {
-	void *ptr = memblock_alloc(THREAD_SIZE, THREAD_ALIGN);
-
-	if (!ptr)
-		panic("cannot allocate %d bytes for stack at %pS\n",
-		      THREAD_SIZE, (void *)_RET_IP_);
-
-	return ptr;
+	return memblock_alloc_or_panic(THREAD_SIZE, THREAD_ALIGN);
 }
 
 void __init irqstack_early_init(void)
@@ -176,7 +170,7 @@ void __init emergency_stack_init(void)
 }
 #endif
 
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 void __init exc_lvl_early_init(void)
 {
 	unsigned int i, hw_cpu;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 246201d0d879..8fd7cbf3bd04 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -60,7 +60,7 @@
 #include <asm/xmon.h>
 #include <asm/udbg.h>
 #include <asm/kexec.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/ftrace.h>
 #include <asm/opal.h>
 #include <asm/cputhreads.h>
@@ -141,10 +141,7 @@ void __init check_smt_enabled(void)
 			smt_enabled_at_boot = 0;
 		else {
 			int smt;
-			int rc;
-
-			rc = kstrtoint(smt_enabled_cmdline, 10, &smt);
-			if (!rc)
+			if (!kstrtoint(smt_enabled_cmdline, 10, &smt))
 				smt_enabled_at_boot =
 					min(threads_per_core, smt);
 		}
@@ -364,7 +361,7 @@ void __init early_setup(unsigned long dt_ptr)
 	 */
 	initialise_paca(&boot_paca, 0);
 	fixup_boot_paca(&boot_paca);
-	WARN_ON(local_paca != 0);
+	WARN_ON(local_paca);
 	setup_paca(&boot_paca); /* install the paca into registers */
 
 	/* -------- printk is now safe to use ------- */
@@ -696,11 +693,7 @@ __init u64 ppc64_bolted_size(void)
 {
 #ifdef CONFIG_PPC_BOOK3E_64
 	/* Freescale BookE bolts the entire linear mapping */
-	/* XXX: BookE ppc64_rma_limit setup seems to disagree? */
-	if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E))
-		return linear_map_top;
-	/* Other BookE, we assume the first GB is bolted */
-	return 1ul << 30;
+	return linear_map_top;
 #else
 	/* BookS radix, does not take faults on linear mapping */
 	if (early_radix_enabled())
@@ -834,6 +827,7 @@ static __init int pcpu_cpu_to_node(int cpu)
 
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
+DEFINE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged);
 
 void __init setup_per_cpu_areas(void)
 {
@@ -876,6 +870,7 @@ void __init setup_per_cpu_areas(void)
 	if (rc < 0)
 		panic("cannot initialize percpu area (err=%d)", rc);
 
+	static_key_enable(&__percpu_first_chunk_is_paged.key);
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu) {
                 __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
@@ -894,7 +889,7 @@ unsigned long memory_block_size_bytes(void)
 }
 #endif
 
-#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
+#ifdef CONFIG_PPC_INDIRECT_PIO
 struct ppc_pci_io ppc_pci_io;
 EXPORT_SYMBOL(ppc_pci_io);
 #endif
@@ -922,6 +917,7 @@ static int __init disable_hardlockup_detector(void)
 	hardlockup_detector_disable();
 #else
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
+		check_kvm_guest();
 		if (is_kvm_guest())
 			hardlockup_detector_disable();
 	}
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 68a91e553e14..aa17e62f3754 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Common signal handling code for both 32 and 64 bits
  *
  *    Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation
  *    Extracted from signal_32.c and signal_64.c
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file README.legal in the main directory of
- * this archive for more details.
  */
 
 #include <linux/resume_user_mode.h>
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index a429c57ed433..58ecea1cdc27 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -1,10 +1,7 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0-or-later
+ *
  *    Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation
  *    Extracted from signal_32.c and signal_64.c
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file README.legal in the main directory of
- * this archive for more details.
  */
 
 #ifndef _POWERPC_ARCH_SIGNAL_H
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index c114c7f25645..7a718ed32b27 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -264,8 +264,9 @@ static void prepare_save_user_regs(int ctx_has_vsx_region)
 #endif
 }
 
-static int __unsafe_save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
-				   struct mcontext __user *tm_frame, int ctx_has_vsx_region)
+static __always_inline int
+__unsafe_save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
+			struct mcontext __user *tm_frame, int ctx_has_vsx_region)
 {
 	unsigned long msr = regs->msr;
 
@@ -364,8 +365,9 @@ static void prepare_save_tm_user_regs(void)
 		current->thread.ckvrsave = mfspr(SPRN_VRSAVE);
 }
 
-static int save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
-				    struct mcontext __user *tm_frame, unsigned long msr)
+static __always_inline int
+save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
+			 struct mcontext __user *tm_frame, unsigned long msr)
 {
 	/* Save both sets of general registers */
 	unsafe_save_general_regs(&current->thread.ckpt_regs, frame, failed);
@@ -444,8 +446,9 @@ failed:
 #else
 static void prepare_save_tm_user_regs(void) { }
 
-static int save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
-				    struct mcontext __user *tm_frame, unsigned long msr)
+static __always_inline int
+save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
+			 struct mcontext __user *tm_frame, unsigned long msr)
 {
 	return 0;
 }
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 265801a3e94c..292fee8809bc 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -47,6 +47,7 @@
 #include <asm/smp.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
+#include <asm/mmu_context.h>
 #include <asm/cputhreads.h>
 #include <asm/cputable.h>
 #include <asm/mpic.h>
@@ -60,6 +61,7 @@
 #include <asm/ftrace.h>
 #include <asm/kup.h>
 #include <asm/fadump.h>
+#include <asm/systemcfg.h>
 
 #include <trace/events/ipi.h>
 
@@ -76,10 +78,10 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 #endif
 
 struct task_struct *secondary_current;
-bool has_big_cores;
-bool coregroup_enabled;
-bool thread_group_shares_l2;
-bool thread_group_shares_l3;
+bool has_big_cores __ro_after_init;
+bool coregroup_enabled __ro_after_init;
+bool thread_group_shares_l2 __ro_after_init;
+bool thread_group_shares_l3 __ro_after_init;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
@@ -92,15 +94,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 EXPORT_SYMBOL_GPL(has_big_cores);
 
-enum {
-#ifdef CONFIG_SCHED_SMT
-	smt_idx,
-#endif
-	cache_idx,
-	mc_idx,
-	die_idx,
-};
-
 #define MAX_THREAD_LIST_SIZE	8
 #define THREAD_GROUP_SHARE_L1   1
 #define THREAD_GROUP_SHARE_L2_L3 2
@@ -291,7 +284,7 @@ void smp_muxed_ipi_set_message(int cpu, int msg)
 	 * Order previous accesses before accesses in the IPI handler.
 	 */
 	smp_mb();
-	message[msg] = 1;
+	WRITE_ONCE(message[msg], 1);
 }
 
 void smp_muxed_ipi_message_pass(int cpu, int msg)
@@ -350,7 +343,7 @@ irqreturn_t smp_ipi_demux_relaxed(void)
 		if (all & IPI_MESSAGE(PPC_MSG_NMI_IPI))
 			nmi_ipi_action(0, NULL);
 #endif
-	} while (info->messages);
+	} while (READ_ONCE(info->messages));
 
 	return IRQ_HANDLED;
 }
@@ -417,9 +410,9 @@ noinstr static void nmi_ipi_lock_start(unsigned long *flags)
 {
 	raw_local_irq_save(*flags);
 	hard_irq_disable();
-	while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
+	while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
 		raw_local_irq_restore(*flags);
-		spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0);
+		spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0);
 		raw_local_irq_save(*flags);
 		hard_irq_disable();
 	}
@@ -427,15 +420,15 @@ noinstr static void nmi_ipi_lock_start(unsigned long *flags)
 
 noinstr static void nmi_ipi_lock(void)
 {
-	while (arch_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
-		spin_until_cond(arch_atomic_read(&__nmi_ipi_lock) == 0);
+	while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
+		spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0);
 }
 
 noinstr static void nmi_ipi_unlock(void)
 {
 	smp_mb();
-	WARN_ON(arch_atomic_read(&__nmi_ipi_lock) != 1);
-	arch_atomic_set(&__nmi_ipi_lock, 0);
+	WARN_ON(raw_atomic_read(&__nmi_ipi_lock) != 1);
+	raw_atomic_set(&__nmi_ipi_lock, 0);
 }
 
 noinstr static void nmi_ipi_unlock_end(unsigned long *flags)
@@ -596,7 +589,7 @@ void smp_send_debugger_break(void)
 }
 #endif
 
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
 void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 {
 	int cpu;
@@ -639,7 +632,7 @@ void crash_smp_send_stop(void)
 
 	stopped = true;
 
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
 	if (kexec_crash_image) {
 		crash_kexec_prepare();
 		return;
@@ -986,13 +979,13 @@ static int __init init_thread_group_cache_map(int cpu, int cache_property)
 	return 0;
 }
 
-static bool shared_caches;
+static bool shared_caches __ro_after_init;
 
 #ifdef CONFIG_SCHED_SMT
 /* cpumask of CPUs with asymmetric SMT dependency */
 static int powerpc_smt_flags(void)
 {
-	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_LLC;
 
 	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
 		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
@@ -1003,6 +996,13 @@ static int powerpc_smt_flags(void)
 #endif
 
 /*
+ * On shared processor LPARs scheduled on a big core (which has two or more
+ * independent thread groups per core), prefer lower numbered CPUs, so
+ * that workload consolidates to lesser number of cores.
+ */
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack);
+
+/*
  * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
  * This topology makes it *much* cheaper to migrate tasks between adjacent cores
  * since the migrated task remains cache hot. We want to take advantage of this
@@ -1010,50 +1010,50 @@ static int powerpc_smt_flags(void)
  */
 static int powerpc_shared_cache_flags(void)
 {
-	return SD_SHARE_PKG_RESOURCES;
+	if (static_branch_unlikely(&splpar_asym_pack))
+		return SD_SHARE_LLC | SD_ASYM_PACKING;
+
+	return SD_SHARE_LLC;
+}
+
+static int powerpc_shared_proc_flags(void)
+{
+	if (static_branch_unlikely(&splpar_asym_pack))
+		return SD_ASYM_PACKING;
+
+	return 0;
 }
 
 /*
  * We can't just pass cpu_l2_cache_mask() directly because
  * returns a non-const pointer and the compiler barfs on that.
  */
-static const struct cpumask *shared_cache_mask(int cpu)
+static const struct cpumask *tl_cache_mask(struct sched_domain_topology_level *tl, int cpu)
 {
 	return per_cpu(cpu_l2_cache_map, cpu);
 }
 
 #ifdef CONFIG_SCHED_SMT
-static const struct cpumask *smallcore_smt_mask(int cpu)
+static const struct cpumask *tl_smallcore_smt_mask(struct sched_domain_topology_level *tl, int cpu)
 {
 	return cpu_smallcore_mask(cpu);
 }
 #endif
 
-static struct cpumask *cpu_coregroup_mask(int cpu)
+struct cpumask *cpu_coregroup_mask(int cpu)
 {
 	return per_cpu(cpu_coregroup_map, cpu);
 }
 
 static bool has_coregroup_support(void)
 {
-	return coregroup_enabled;
-}
+	/* Coregroup identification not available on shared systems */
+	if (is_shared_processor())
+		return 0;
 
-static const struct cpumask *cpu_mc_mask(int cpu)
-{
-	return cpu_coregroup_mask(cpu);
+	return coregroup_enabled;
 }
 
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
-	{ cpu_mc_mask, SD_INIT_NAME(MC) },
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
-	{ NULL, },
-};
-
 static int __init init_big_cores(void)
 {
 	int cpu;
@@ -1085,9 +1085,32 @@ static int __init init_big_cores(void)
 	return 0;
 }
 
+/*
+ * die_mask and die_id are only available on systems which support
+ * multiple coregroups within a same package. On all other systems, die_mask
+ * would be same as package mask and die_id would be set to -1.
+ */
+const struct cpumask *cpu_die_mask(int cpu)
+{
+	if (has_coregroup_support())
+		return per_cpu(cpu_coregroup_map, cpu);
+	else
+		return cpu_node_mask(cpu);
+}
+EXPORT_SYMBOL_GPL(cpu_die_mask);
+
+int cpu_die_id(int cpu)
+{
+	if (has_coregroup_support())
+		return cpu_to_coregroup_id(cpu);
+	else
+		return -1;
+}
+EXPORT_SYMBOL_GPL(cpu_die_id);
+
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned int cpu;
+	unsigned int cpu, num_threads;
 
 	DBG("smp_prepare_cpus\n");
 
@@ -1154,9 +1177,15 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 
 	if (smp_ops && smp_ops->probe)
 		smp_ops->probe();
+
+	// Initalise the generic SMT topology support
+	num_threads = 1;
+	if (smt_enabled_at_boot)
+		num_threads = smt_enabled_at_boot;
+	cpu_smt_set_num_threads(num_threads, threads_per_core);
 }
 
-void smp_prepare_boot_cpu(void)
+void __init smp_prepare_boot_cpu(void)
 {
 	BUG_ON(smp_processor_id() != boot_cpuid);
 #ifdef CONFIG_PPC64
@@ -1176,8 +1205,8 @@ int generic_cpu_disable(void)
 		return -EBUSY;
 
 	set_cpu_online(cpu, false);
-#ifdef CONFIG_PPC64
-	vdso_data->processorCount--;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->processorCount--;
 #endif
 	/* Update affinity of all IRQs previously aimed at this CPU */
 	irq_migrate_all_off_this_cpu();
@@ -1437,7 +1466,7 @@ static bool update_mask_by_l2(int cpu, cpumask_var_t *mask)
 		return false;
 	}
 
-	cpumask_and(*mask, cpu_online_mask, cpu_cpu_mask(cpu));
+	cpumask_and(*mask, cpu_online_mask, cpu_node_mask(cpu));
 
 	/* Update l2-cache mask with all the CPUs that are part of submask */
 	or_cpumasks_related(cpu, cpu, submask_fn, cpu_l2_cache_mask);
@@ -1527,7 +1556,7 @@ static void update_coregroup_mask(int cpu, cpumask_var_t *mask)
 		return;
 	}
 
-	cpumask_and(*mask, cpu_online_mask, cpu_cpu_mask(cpu));
+	cpumask_and(*mask, cpu_online_mask, cpu_node_mask(cpu));
 
 	/* Update coregroup mask with all the CPUs that are part of submask */
 	or_cpumasks_related(cpu, cpu, submask_fn, cpu_coregroup_mask);
@@ -1557,7 +1586,7 @@ static void add_cpu_to_masks(int cpu)
 
 	/*
 	 * This CPU will not be in the online mask yet so we need to manually
-	 * add it to it's own thread sibling mask.
+	 * add it to its own thread sibling mask.
 	 */
 	map_cpu_to_node(cpu, cpu_to_node(cpu));
 	cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
@@ -1588,9 +1617,9 @@ static void add_cpu_to_masks(int cpu)
 	/* Skip all CPUs already part of current CPU core mask */
 	cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu));
 
-	/* If chip_id is -1; limit the cpu_core_mask to within DIE*/
+	/* If chip_id is -1; limit the cpu_core_mask to within PKG */
 	if (chip_id == -1)
-		cpumask_and(mask, mask, cpu_cpu_mask(cpu));
+		cpumask_and(mask, mask, cpu_node_mask(cpu));
 
 	for_each_cpu(i, mask) {
 		if (chip_id == cpu_to_chip_id(i)) {
@@ -1605,6 +1634,7 @@ static void add_cpu_to_masks(int cpu)
 }
 
 /* Activate a secondary processor. */
+__no_stack_protector
 void start_secondary(void *unused)
 {
 	unsigned int cpu = raw_smp_processor_id();
@@ -1615,10 +1645,13 @@ void start_secondary(void *unused)
 
 	mmgrab_lazy_tlb(&init_mm);
 	current->active_mm = &init_mm;
+	VM_WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(&init_mm)));
+	cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
+	inc_mm_active_cpus(&init_mm);
 
 	smp_store_cpu_info(cpu);
 	set_dec(tb_ticks_per_jiffy);
-	rcu_cpu_starting(cpu);
+	rcutree_report_cpu_starting(cpu);
 	cpu_callin_map[cpu] = 1;
 
 	if (smp_ops->setup_cpu)
@@ -1628,10 +1661,12 @@ void start_secondary(void *unused)
 
 	secondary_cpu_time_init();
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
 	if (system_state == SYSTEM_RUNNING)
-		vdso_data->processorCount++;
+		systemcfg->processorCount++;
+#endif
 
+#ifdef CONFIG_PPC64
 	vdso_getcpu_init();
 #endif
 	set_numa_node(numa_cpu_lookup_table[cpu]);
@@ -1671,43 +1706,40 @@ void start_secondary(void *unused)
 	BUG();
 }
 
-static void __init fixup_topology(void)
+static struct sched_domain_topology_level powerpc_topology[6];
+
+static void __init build_sched_topology(void)
 {
-	int i;
+	int i = 0;
+
+	if (is_shared_processor() && has_big_cores)
+		static_branch_enable(&splpar_asym_pack);
 
 #ifdef CONFIG_SCHED_SMT
 	if (has_big_cores) {
 		pr_info("Big cores detected but using small core scheduling\n");
-		powerpc_topology[smt_idx].mask = smallcore_smt_mask;
+		powerpc_topology[i++] =
+			SDTL_INIT(tl_smallcore_smt_mask, powerpc_smt_flags, SMT);
+	} else {
+		powerpc_topology[i++] = SDTL_INIT(tl_smt_mask, powerpc_smt_flags, SMT);
 	}
 #endif
+	if (shared_caches) {
+		powerpc_topology[i++] =
+			SDTL_INIT(tl_cache_mask, powerpc_shared_cache_flags, CACHE);
+	}
 
-	if (!has_coregroup_support())
-		powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
-
-	/*
-	 * Try to consolidate topology levels here instead of
-	 * allowing scheduler to degenerate.
-	 * - Dont consolidate if masks are different.
-	 * - Dont consolidate if sd_flags exists and are different.
-	 */
-	for (i = 1; i <= die_idx; i++) {
-		if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
-			continue;
+	if (has_coregroup_support()) {
+		powerpc_topology[i++] =
+			SDTL_INIT(tl_mc_mask, powerpc_shared_proc_flags, MC);
+	}
 
-		if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
-				powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
-			continue;
+	powerpc_topology[i++] = SDTL_INIT(tl_pkg_mask, powerpc_shared_proc_flags, PKG);
 
-		if (!powerpc_topology[i - 1].sd_flags)
-			powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+	/* There must be one trailing NULL entry left.  */
+	BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1);
 
-		powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
-		powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
-#ifdef CONFIG_SCHED_DEBUG
-		powerpc_topology[i].name = powerpc_topology[i + 1].name;
-#endif
-	}
+	set_sched_topology(powerpc_topology);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -1722,9 +1754,20 @@ void __init smp_cpus_done(unsigned int max_cpus)
 		smp_ops->bringup_done();
 
 	dump_numa_cpu_topology();
+	build_sched_topology();
+}
 
-	fixup_topology();
-	set_sched_topology(powerpc_topology);
+/*
+ * For asym packing, by default lower numbered CPU has higher priority.
+ * On shared processors, pack to lower numbered core. However avoid moving
+ * between thread_groups within the same core.
+ */
+int arch_asym_cpu_priority(int cpu)
+{
+	if (static_branch_unlikely(&splpar_asym_pack))
+		return -cpu / threads_per_core;
+
+	return -cpu;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -1750,6 +1793,14 @@ int __cpu_disable(void)
 
 void __cpu_die(unsigned int cpu)
 {
+	/*
+	 * This could perhaps be a generic call in idlea_task_dead(), but
+	 * that requires testing from all archs, so first put it here to
+	 */
+	VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(&init_mm)));
+	dec_mm_active_cpus(&init_mm);
+	cpumask_clear_cpu(cpu, mm_cpumask(&init_mm));
+
 	if (smp_ops->cpu_die)
 		smp_ops->cpu_die(cpu);
 }
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 5de8597eaab8..90882b5175cd 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -21,6 +21,7 @@
 #include <asm/processor.h>
 #include <linux/ftrace.h>
 #include <asm/kprobes.h>
+#include <linux/rethook.h>
 
 #include <asm/paca.h>
 
@@ -73,29 +74,12 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum
 	bool firstframe;
 
 	stack_end = stack_page + THREAD_SIZE;
-	if (!is_idle_task(task)) {
-		/*
-		 * For user tasks, this is the SP value loaded on
-		 * kernel entry, see "PACAKSAVE(r13)" in _switch() and
-		 * system_call_common().
-		 *
-		 * Likewise for non-swapper kernel threads,
-		 * this also happens to be the top of the stack
-		 * as setup by copy_thread().
-		 *
-		 * Note that stack backlinks are not properly setup by
-		 * copy_thread() and thus, a forked task() will have
-		 * an unreliable stack trace until it's been
-		 * _switch()'ed to for the first time.
-		 */
-		stack_end -= STACK_USER_INT_FRAME_SIZE;
-	} else {
-		/*
-		 * idle tasks have a custom stack layout,
-		 * c.f. cpu_idle_thread_init().
-		 */
+
+	// See copy_thread() for details.
+	if (task->flags & PF_KTHREAD)
 		stack_end -= STACK_FRAME_MIN_SIZE;
-	}
+	else
+		stack_end -= STACK_USER_INT_FRAME_SIZE;
 
 	if (task == current)
 		sp = current_stack_frame();
@@ -150,12 +134,13 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum
 		 * arch-dependent code, they are generic.
 		 */
 		ip = ftrace_graph_ret_addr(task, &graph_idx, ip, stack);
-#ifdef CONFIG_KPROBES
+
 		/*
 		 * Mark stacktraces with kretprobed functions on them
 		 * as unreliable.
 		 */
-		if (ip == (unsigned long)__kretprobe_trampoline)
+#ifdef CONFIG_RETHOOK
+		if (ip == (unsigned long)arch_rethook_trampoline)
 			return -EINVAL;
 #endif
 
@@ -221,8 +206,8 @@ static void raise_backtrace_ipi(cpumask_t *mask)
 	}
 }
 
-void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu)
 {
-	nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi);
+	nmi_trigger_cpumask_backtrace(mask, exclude_cpu, raise_backtrace_ipi);
 }
 #endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */
diff --git a/arch/powerpc/kernel/static_call.c b/arch/powerpc/kernel/static_call.c
index 863a7aa24650..ec3101f95e53 100644
--- a/arch/powerpc/kernel/static_call.c
+++ b/arch/powerpc/kernel/static_call.c
@@ -2,32 +2,60 @@
 #include <linux/memory.h>
 #include <linux/static_call.h>
 
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 
 void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 {
 	int err;
 	bool is_ret0 = (func == __static_call_return0);
-	unsigned long target = (unsigned long)(is_ret0 ? tramp + PPC_SCT_RET0 : func);
-	bool is_short = is_offset_in_branch_range((long)target - (long)tramp);
-
-	if (!tramp)
-		return;
+	unsigned long _tramp = (unsigned long)tramp;
+	unsigned long _func = (unsigned long)func;
+	unsigned long _ret0 = _tramp + PPC_SCT_RET0;
+	bool is_short = is_offset_in_branch_range((long)func - (long)(site ? : tramp));
 
 	mutex_lock(&text_mutex);
 
-	if (func && !is_short) {
-		err = patch_instruction(tramp + PPC_SCT_DATA, ppc_inst(target));
-		if (err)
-			goto out;
+	if (site && tail) {
+		if (!func)
+			err = patch_instruction(site, ppc_inst(PPC_RAW_BLR()));
+		else if (is_ret0)
+			err = patch_branch(site, _ret0, 0);
+		else if (is_short)
+			err = patch_branch(site, _func, 0);
+		else if (tramp)
+			err = patch_branch(site, _tramp, 0);
+		else
+			err = 0;
+	} else if (site) {
+		if (!func)
+			err = patch_instruction(site, ppc_inst(PPC_RAW_NOP()));
+		else if (is_ret0)
+			err = patch_instruction(site, ppc_inst(PPC_RAW_LI(_R3, 0)));
+		else if (is_short)
+			err = patch_branch(site, _func, BRANCH_SET_LINK);
+		else if (tramp)
+			err = patch_branch(site, _tramp, BRANCH_SET_LINK);
+		else
+			err = 0;
+	} else if (tramp) {
+		if (func && !is_short) {
+			err = patch_ulong(tramp + PPC_SCT_DATA, _func);
+			if (err)
+				goto out;
+		}
+
+		if (!func)
+			err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR()));
+		else if (is_ret0)
+			err = patch_branch(tramp, _ret0, 0);
+		else if (is_short)
+			err = patch_branch(tramp, _func, 0);
+		else
+			err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP()));
+	} else {
+		err = 0;
 	}
 
-	if (!func)
-		err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR()));
-	else if (is_short)
-		err = patch_branch(tramp, target, 0);
-	else
-		err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP()));
 out:
 	mutex_unlock(&text_mutex);
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/switch.S
index 1bf1121e17f1..59e3ee99db0e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/switch.S
@@ -1,56 +1,21 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  PowerPC version 
- *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
- *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
- *  Adapted for Power Macintosh by Paul Mackerras.
- *  Low-level exception handlers and MMU support
- *  rewritten by Paul Mackerras.
- *    Copyright (C) 1996 Paul Mackerras.
- *  MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
- *
- *  This file contains the system call entry code, context switch
- *  code, and exception/interrupt return code for PowerPC.
- */
-
 #include <linux/objtool.h>
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <asm/cache.h>
-#include <asm/unistd.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/mmu.h>
-#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
 #include <asm/code-patching-asm.h>
+#include <asm/mmu.h>
 #include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/cputable.h>
-#include <asm/firmware.h>
-#include <asm/bug.h>
-#include <asm/ptrace.h>
-#include <asm/irqflags.h>
-#include <asm/hw_irq.h>
-#include <asm/context_tracking.h>
-#include <asm/ppc-opcode.h>
-#include <asm/barrier.h>
-#include <asm/export.h>
-#include <asm/asm-compat.h>
-#ifdef CONFIG_PPC_BOOK3S
-#include <asm/exception-64s.h>
-#else
-#include <asm/exception-64e.h>
-#endif
-#include <asm/feature-fixups.h>
 #include <asm/kup.h>
+#include <asm/thread_info.h>
 
-/*
- * System calls.
- */
-	.section	".text"
+.section ".text","ax",@progbits
 
 #ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * Cancel all explict user streams as they will have no use after context
+ * switch and will stop the HW from creating streams itself
+ */
+#define STOP_STREAMS		\
+	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6)
 
 #define FLUSH_COUNT_CACHE	\
 1:	nop;			\
@@ -74,7 +39,6 @@ flush_branch_caches:
 
 	// Flush the link stack
 	.rept 64
-	ANNOTATE_INTRA_FUNCTION_CALL
 	bl	.+4
 	.endr
 	b	1f
@@ -105,87 +69,13 @@ flush_branch_caches:
 	.endr
 
 	blr
-#else
-#define FLUSH_COUNT_CACHE
-#endif /* CONFIG_PPC_BOOK3S_64 */
 
+#ifdef CONFIG_PPC_64S_HASH_MMU
+.balign 32
 /*
- * This routine switches between two different tasks.  The process
- * state of one is saved on its kernel stack.  Then the state
- * of the other is restored from its kernel stack.  The memory
- * management hardware is updated to the second process's state.
- * Finally, we can return to the second process, via interrupt_return.
- * On entry, r3 points to the THREAD for the current task, r4
- * points to the THREAD for the new task.
- *
- * Note: there are two ways to get to the "going out" portion
- * of this code; either by coming in via the entry (_switch)
- * or via "fork" which must set up an environment equivalent
- * to the "_switch" path.  If you change this you'll have to change
- * the fork code also.
- *
- * The code which creates the new task context is in 'copy_thread'
- * in arch/powerpc/kernel/process.c 
+ * New stack pointer in r8, old stack pointer in r1, must not clobber r3
  */
-	.align	7
-_GLOBAL(_switch)
-	mflr	r0
-	std	r0,16(r1)
-	stdu	r1,-SWITCH_FRAME_SIZE(r1)
-	/* r3-r13 are caller saved -- Cort */
-	SAVE_NVGPRS(r1)
-	std	r0,_NIP(r1)	/* Return to switch caller */
-	mfcr	r23
-	std	r23,_CCR(r1)
-	std	r1,KSP(r3)	/* Set old stack pointer */
-
-	kuap_check_amr r9, r10
-
-	FLUSH_COUNT_CACHE	/* Clobbers r9, ctr */
-
-	/*
-	 * On SMP kernels, care must be taken because a task may be
-	 * scheduled off CPUx and on to CPUy. Memory ordering must be
-	 * considered.
-	 *
-	 * Cacheable stores on CPUx will be visible when the task is
-	 * scheduled on CPUy by virtue of the core scheduler barriers
-	 * (see "Notes on Program-Order guarantees on SMP systems." in
-	 * kernel/sched/core.c).
-	 *
-	 * Uncacheable stores in the case of involuntary preemption must
-	 * be taken care of. The smp_mb__after_spinlock() in __schedule()
-	 * is implemented as hwsync on powerpc, which orders MMIO too. So
-	 * long as there is an hwsync in the context switch path, it will
-	 * be executed on the source CPU after the task has performed
-	 * all MMIO ops on that CPU, and on the destination CPU before the
-	 * task performs any MMIO ops there.
-	 */
-
-	/*
-	 * The kernel context switch path must contain a spin_lock,
-	 * which contains larx/stcx, which will clear any reservation
-	 * of the task being switched.
-	 */
-#ifdef CONFIG_PPC_BOOK3S
-/* Cancel all explict user streams as they will have no use after context
- * switch and will stop the HW from creating streams itself
- */
-	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6)
-#endif
-
-	addi	r6,r4,-THREAD	/* Convert THREAD to 'current' */
-	std	r6,PACACURRENT(r13)	/* Set new 'current' */
-#if defined(CONFIG_STACKPROTECTOR)
-	ld	r6, TASK_CANARY(r6)
-	std	r6, PACA_CANARY(r13)
-#endif
-
-	ld	r8,KSP(r4)	/* new stack pointer */
-#ifdef CONFIG_PPC_64S_HASH_MMU
-BEGIN_MMU_FTR_SECTION
-	b	2f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
+pin_stack_slb:
 BEGIN_FTR_SECTION
 	clrrdi	r6,r8,28	/* get its ESID */
 	clrrdi	r9,r1,28	/* get current sp ESID */
@@ -233,15 +123,57 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	slbmte	r7,r0
 	isync
-2:
+2:	blr
+	.size pin_stack_slb,.-pin_stack_slb
 #endif /* CONFIG_PPC_64S_HASH_MMU */
 
-	clrrdi	r7, r8, THREAD_SHIFT	/* base of new stack */
-	/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
-	   because we don't need to leave the 288-byte ABI gap at the
-	   top of the kernel stack. */
+#else
+#define STOP_STREAMS
+#define FLUSH_COUNT_CACHE
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+/*
+ * do_switch_32/64 have the same calling convention as _switch, i.e., r3,r4
+ * are prev and next thread_struct *, and returns prev task_struct * in r3.
+
+ * This switches the stack, current, and does other task switch housekeeping.
+ */
+.macro do_switch_32
+	tophys(r0,r4)
+	mtspr	SPRN_SPRG_THREAD,r0	/* Update current THREAD phys addr */
+	lwz	r1,KSP(r4)	/* Load new stack pointer */
+
+	/* save the old current 'last' for return value */
+	mr	r3,r2
+	addi	r2,r4,-THREAD	/* Update current */
+.endm
+
+.macro do_switch_64
+	ld	r8,KSP(r4)	/* Load new stack pointer */
+
+	kuap_check_amr r9, r10
+
+	FLUSH_COUNT_CACHE	/* Clobbers r9, ctr */
+
+	STOP_STREAMS		/* Clobbers r6 */
+
+	addi	r3,r3,-THREAD	/* old thread -> task_struct for return value */
+	addi	r6,r4,-THREAD	/* new thread -> task_struct */
+	std	r6,PACACURRENT(r13)	/* Set new task_struct to 'current' */
+#if defined(CONFIG_STACKPROTECTOR)
+	ld	r6, TASK_CANARY(r6)
+	std	r6, PACA_CANARY(r13)
+#endif
+	/* Set new PACAKSAVE */
+	clrrdi	r7,r8,THREAD_SHIFT	/* base of new stack */
 	addi	r7,r7,THREAD_SIZE-SWITCH_FRAME_SIZE
+	std	r7,PACAKSAVE(r13)
 
+#ifdef CONFIG_PPC_64S_HASH_MMU
+BEGIN_MMU_FTR_SECTION
+	bl	pin_stack_slb
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
+#endif
 	/*
 	 * PMU interrupts in radix may come in here. They will use r1, not
 	 * PACAKSAVE, so this stack switch will not cause a problem. They
@@ -251,81 +183,75 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	 * active on the new CPU, will order those stores.
 	 */
 	mr	r1,r8		/* start using new stack pointer */
-	std	r7,PACAKSAVE(r13)
+.endm
+
+/*
+ * This routine switches between two different tasks.  The process
+ * state of one is saved on its kernel stack.  Then the state
+ * of the other is restored from its kernel stack.  The memory
+ * management hardware is updated to the second process's state.
+ * Finally, we can return to the second process.
+ * On entry, r3 points to the THREAD for the current task, r4
+ * points to the THREAD for the new task.
+ *
+ * This routine is always called with interrupts disabled.
+ *
+ * Note: there are two ways to get to the "going out" portion
+ * of this code; either by coming in via the entry (_switch)
+ * or via "fork" which must set up an environment equivalent
+ * to the "_switch" path.  If you change this , you'll have to
+ * change the fork code also.
+ *
+ * The code which creates the new task context is in 'copy_thread'
+ * in arch/ppc/kernel/process.c
+ *
+ * Note: this uses SWITCH_FRAME_SIZE rather than USER_INT_FRAME_SIZE
+ * because we don't need to leave the redzone ABI gap at the top of
+ * the kernel stack.
+ */
+_GLOBAL(_switch)
+	PPC_CREATE_STACK_FRAME(SWITCH_FRAME_SIZE)
+	PPC_STL		r1,KSP(r3)	/* Set old stack pointer */
+	SAVE_NVGPRS(r1)			/* volatiles are caller-saved -- Cort */
+	PPC_STL		r0,_NIP(r1)	/* Return to switch caller */
+	mfcr		r0
+	stw		r0,_CCR(r1)
 
-	ld	r6,_CCR(r1)
-	mtcrf	0xFF,r6
+	/*
+	 * On SMP kernels, care must be taken because a task may be
+	 * scheduled off CPUx and on to CPUy. Memory ordering must be
+	 * considered.
+	 *
+	 * Cacheable stores on CPUx will be visible when the task is
+	 * scheduled on CPUy by virtue of the core scheduler barriers
+	 * (see "Notes on Program-Order guarantees on SMP systems." in
+	 * kernel/sched/core.c).
+	 *
+	 * Uncacheable stores in the case of involuntary preemption must
+	 * be taken care of. The smp_mb__after_spinlock() in __schedule()
+	 * is implemented as hwsync on powerpc, which orders MMIO too. So
+	 * long as there is an hwsync in the context switch path, it will
+	 * be executed on the source CPU after the task has performed
+	 * all MMIO ops on that CPU, and on the destination CPU before the
+	 * task performs any MMIO ops there.
+	 */
+
+	/*
+	 * The kernel context switch path must contain a spin_lock,
+	 * which contains larx/stcx, which will clear any reservation
+	 * of the task being switched.
+	 */
 
-	/* r3-r13 are destroyed -- Cort */
-	REST_NVGPRS(r1)
+#ifdef CONFIG_PPC32
+	do_switch_32
+#else
+	do_switch_64
+#endif
 
-	/* convert old thread to its task_struct for return value */
-	addi	r3,r3,-THREAD
-	ld	r7,_NIP(r1)	/* Return to _switch caller in new task */
-	mtlr	r7
+	lwz	r0,_CCR(r1)
+	mtcrf	0xFF,r0
+	REST_NVGPRS(r1)		/* volatiles are destroyed -- Cort */
+	PPC_LL	r0,_NIP(r1)	/* Return to _switch caller in new task */
+	mtlr	r0
 	addi	r1,r1,SWITCH_FRAME_SIZE
 	blr
-
-_GLOBAL(enter_prom)
-	mflr	r0
-	std	r0,16(r1)
-        stdu	r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space */
-
-	/* Because PROM is running in 32b mode, it clobbers the high order half
-	 * of all registers that it saves.  We therefore save those registers
-	 * PROM might touch to the stack.  (r0, r3-r13 are caller saved)
-   	 */
-	SAVE_GPR(2, r1)
-	SAVE_GPR(13, r1)
-	SAVE_NVGPRS(r1)
-	mfcr	r10
-	mfmsr	r11
-	std	r10,_CCR(r1)
-	std	r11,_MSR(r1)
-
-	/* Put PROM address in SRR0 */
-	mtsrr0	r4
-
-	/* Setup our trampoline return addr in LR */
-	bcl	20,31,$+4
-0:	mflr	r4
-	addi	r4,r4,(1f - 0b)
-       	mtlr	r4
-
-	/* Prepare a 32-bit mode big endian MSR
-	 */
-#ifdef CONFIG_PPC_BOOK3E_64
-	rlwinm	r11,r11,0,1,31
-	mtsrr1	r11
-	rfi
-#else /* CONFIG_PPC_BOOK3E_64 */
-	LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE)
-	andc	r11,r11,r12
-	mtsrr1	r11
-	RFI_TO_KERNEL
-#endif /* CONFIG_PPC_BOOK3E_64 */
-
-1:	/* Return from OF */
-	FIXUP_ENDIAN
-
-	/* Just make sure that r1 top 32 bits didn't get
-	 * corrupt by OF
-	 */
-	rldicl	r1,r1,0,32
-
-	/* Restore the MSR (back to 64 bits) */
-	ld	r0,_MSR(r1)
-	MTMSRD(r0)
-        isync
-
-	/* Restore other registers */
-	REST_GPR(2, r1)
-	REST_GPR(13, r1)
-	REST_NVGPRS(r1)
-	ld	r4,_CCR(r1)
-	mtcr	r4
-
-        addi	r1,r1,SWITCH_FRAME_SIZE
-	ld	r0,16(r1)
-	mtlr    r0
-        blr
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
index 16ee3baaf09a..50fa8fc9ef95 100644
--- a/arch/powerpc/kernel/swsusp_64.c
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -11,6 +11,8 @@
 #include <linux/interrupt.h>
 #include <linux/nmi.h>
 
+void do_after_copyback(void);
+
 void do_after_copyback(void)
 {
 	iommu_restore();
diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index 18b9d325395f..be159ad4b77b 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.c
@@ -27,11 +27,11 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
 
 	trace_hardirqs_off(); /* finish reconciling */
 
-	CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
+	CT_WARN_ON(ct_state() == CT_STATE_KERNEL);
 	user_exit_irqoff();
 
 	BUG_ON(regs_is_unrecoverable(regs));
-	BUG_ON(!(regs->msr & MSR_PR));
+	BUG_ON(!user_mode(regs));
 	BUG_ON(arch_irq_disabled_regs(regs));
 
 #ifdef CONFIG_PPC_PKEY
@@ -46,7 +46,7 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
 		iamr = mfspr(SPRN_IAMR);
 		regs->amr  = amr;
 		regs->iamr = iamr;
-		if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) {
+		if (mmu_has_feature(MMU_FTR_KUAP)) {
 			mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
 			flush_needed = true;
 		}
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index a0be127475b1..ec4458cdb97b 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -230,8 +230,10 @@
 178	nospu 	rt_sigsuspend			sys_rt_sigsuspend		compat_sys_rt_sigsuspend
 179	32	pread64				sys_ppc_pread64			compat_sys_ppc_pread64
 179	64	pread64				sys_pread64
+179	spu	pread64				sys_pread64
 180	32	pwrite64			sys_ppc_pwrite64		compat_sys_ppc_pwrite64
 180	64	pwrite64			sys_pwrite64
+180	spu	pwrite64			sys_pwrite64
 181	common	chown				sys_chown
 182	common	getcwd				sys_getcwd
 183	common	capget				sys_capget
@@ -246,6 +248,7 @@
 190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
 191	32	readahead			sys_ppc_readahead		compat_sys_ppc_readahead
 191	64	readahead			sys_readahead
+191	spu	readahead			sys_readahead
 192	32	mmap2				sys_mmap2			compat_sys_mmap2
 193	32	truncate64			sys_ppc_truncate64		compat_sys_ppc_truncate64
 194	32	ftruncate64			sys_ppc_ftruncate64		compat_sys_ppc_ftruncate64
@@ -293,8 +296,9 @@
 232	nospu	set_tid_address			sys_set_tid_address
 233	32	fadvise64			sys_ppc32_fadvise64		compat_sys_ppc32_fadvise64
 233	64	fadvise64			sys_fadvise64
+233	spu	fadvise64			sys_fadvise64
 234	nospu	exit_group			sys_exit_group
-235	nospu	lookup_dcookie			sys_lookup_dcookie		compat_sys_lookup_dcookie
+235	nospu	lookup_dcookie			sys_ni_syscall
 236	common	epoll_create			sys_epoll_create
 237	common	epoll_ctl			sys_epoll_ctl
 238	common	epoll_wait			sys_epoll_wait
@@ -502,7 +506,7 @@
 412	32	utimensat_time64		sys_utimensat			sys_utimensat
 413	32	pselect6_time64			sys_pselect6			compat_sys_pselect6_time64
 414	32	ppoll_time64			sys_ppoll			compat_sys_ppoll_time64
-416	32	io_pgetevents_time64		sys_io_pgetevents		sys_io_pgetevents
+416	32	io_pgetevents_time64		sys_io_pgetevents		compat_sys_io_pgetevents_time64
 417	32	recvmmsg_time64			sys_recvmmsg			compat_sys_recvmmsg_time64
 418	32	mq_timedsend_time64		sys_mq_timedsend		sys_mq_timedsend
 419	32	mq_timedreceive_time64		sys_mq_timedreceive		sys_mq_timedreceive
@@ -537,3 +541,23 @@
 448	common	process_mrelease		sys_process_mrelease
 449	common  futex_waitv                     sys_futex_waitv
 450 	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
+453	common	map_shadow_stack		sys_ni_syscall
+454	common	futex_wake			sys_futex_wake
+455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
+462	common	mseal				sys_mseal
+463	common	setxattrat			sys_setxattrat
+464	common	getxattrat			sys_getxattrat
+465	common	listxattrat			sys_listxattrat
+466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
+470	common	listns				sys_listns
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 0f39a6b84132..6b3dd6decdf9 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -17,6 +17,7 @@
 #include <asm/hvcall.h>
 #include <asm/machdep.h>
 #include <asm/smp.h>
+#include <asm/time.h>
 #include <asm/pmc.h>
 #include <asm/firmware.h>
 #include <asm/idle.h>
@@ -139,7 +140,7 @@ static unsigned long dscr_default;
  * @val:	Returned cpu specific DSCR default value
  *
  * This function returns the per cpu DSCR default value
- * for any cpu which is contained in it's PACA structure.
+ * for any cpu which is contained in its PACA structure.
  */
 static void read_dscr(void *val)
 {
@@ -152,7 +153,7 @@ static void read_dscr(void *val)
  * @val:	New cpu specific DSCR default value to update
  *
  * This function updates the per cpu DSCR default value
- * for any cpu which is contained in it's PACA structure.
+ * for any cpu which is contained in its PACA structure.
  */
 static void write_dscr(void *val)
 {
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 828d0f4106d2..cba6dd15de3b 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -200,7 +200,7 @@ static int __init TAU_init(void)
 	tau_int_enable = IS_ENABLED(CONFIG_TAU_INT) &&
 			 !strcmp(cur_cpu_spec->platform, "ppc750");
 
-	tau_workq = alloc_workqueue("tau", WQ_UNBOUND, 1);
+	tau_workq = alloc_ordered_workqueue("tau", 0);
 	if (!tau_workq)
 		return -ENOMEM;
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index df20cf201f74..4bbeb8644d3d 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -71,11 +71,11 @@
 #include <asm/vdso_datapage.h>
 #include <asm/firmware.h>
 #include <asm/mce.h>
+#include <asm/systemcfg.h>
 
 /* powerpc clocksource/clockevent code */
 
 #include <linux/clockchips.h>
-#include <linux/timekeeper_internal.h>
 
 static u64 timebase_read(struct clocksource *);
 static struct clocksource clocksource_timebase = {
@@ -137,7 +137,7 @@ EXPORT_SYMBOL_GPL(rtc_lock);
 
 static u64 tb_to_ns_scale __read_mostly;
 static unsigned tb_to_ns_shift __read_mostly;
-static u64 boot_tb __read_mostly;
+static u64 boot_tb __ro_after_init;
 
 extern struct timezone sys_tz;
 static long timezone_offset;
@@ -354,6 +354,28 @@ void vtime_flush(struct task_struct *tsk)
 	acct->hardirq_time = 0;
 	acct->softirq_time = 0;
 }
+
+/*
+ * Called from the context switch with interrupts disabled, to charge all
+ * accumulated times to the current process, and to prepare accounting on
+ * the next process.
+ */
+void vtime_task_switch(struct task_struct *prev)
+{
+	if (is_idle_task(prev))
+		vtime_account_idle(prev);
+	else
+		vtime_account_kernel(prev);
+
+	vtime_flush(prev);
+
+	if (!IS_ENABLED(CONFIG_PPC64)) {
+		struct cpu_accounting_data *acct = get_accounting(current);
+		struct cpu_accounting_data *acct0 = get_accounting(prev);
+
+		acct->starttime = acct0->starttime;
+	}
+}
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 void __no_kcsan __delay(unsigned long loops)
@@ -617,6 +639,12 @@ notrace unsigned long long sched_clock(void)
 	return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
 }
 
+#ifdef CONFIG_PPC_SPLPAR
+u64 get_boot_tb(void)
+{
+	return boot_tb;
+}
+#endif
 
 #ifdef CONFIG_PPC_PSERIES
 
@@ -673,7 +701,7 @@ static int __init get_freq(char *name, int cells, unsigned long *val)
 
 static void start_cpu_decrementer(void)
 {
-#ifdef CONFIG_BOOKE_OR_40x
+#ifdef CONFIG_BOOKE
 	unsigned int tcr;
 
 	/* Clear any pending timer interrupts */
@@ -879,6 +907,38 @@ void secondary_cpu_time_init(void)
 	register_decrementer_clockevent(smp_processor_id());
 }
 
+/*
+ * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
+ * result.
+ */
+static __init void div128_by_32(u64 dividend_high, u64 dividend_low,
+				unsigned int divisor, struct div_result *dr)
+{
+	unsigned long a, b, c, d;
+	unsigned long w, x, y, z;
+	u64 ra, rb, rc;
+
+	a = dividend_high >> 32;
+	b = dividend_high & 0xffffffff;
+	c = dividend_low >> 32;
+	d = dividend_low & 0xffffffff;
+
+	w = a / divisor;
+	ra = ((u64)(a - (w * divisor)) << 32) + b;
+
+	rb = ((u64)do_div(ra, divisor) << 32) + c;
+	x = ra;
+
+	rc = ((u64)do_div(rb, divisor) << 32) + d;
+	y = rb;
+
+	do_div(rc, divisor);
+	z = rc;
+
+	dr->result_high = ((u64)w << 32) + x;
+	dr->result_low  = ((u64)y << 32) + z;
+}
+
 /* This function is only called on the boot processor */
 void __init time_init(void)
 {
@@ -928,7 +988,10 @@ void __init time_init(void)
 		sys_tz.tz_dsttime = 0;
 	}
 
-	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+	vdso_k_arch_data->tb_ticks_per_sec = tb_ticks_per_sec;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
+#endif
 
 	/* initialise and enable the large decrementer (if we have one) */
 	set_decrementer_max();
@@ -949,39 +1012,6 @@ void __init time_init(void)
 	enable_sched_clock_irqtime();
 }
 
-/*
- * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
- * result.
- */
-void div128_by_32(u64 dividend_high, u64 dividend_low,
-		  unsigned divisor, struct div_result *dr)
-{
-	unsigned long a, b, c, d;
-	unsigned long w, x, y, z;
-	u64 ra, rb, rc;
-
-	a = dividend_high >> 32;
-	b = dividend_high & 0xffffffff;
-	c = dividend_low >> 32;
-	d = dividend_low & 0xffffffff;
-
-	w = a / divisor;
-	ra = ((u64)(a - (w * divisor)) << 32) + b;
-
-	rb = ((u64) do_div(ra, divisor) << 32) + c;
-	x = ra;
-
-	rc = ((u64) do_div(rb, divisor) << 32) + d;
-	y = rb;
-
-	do_div(rc, divisor);
-	z = rc;
-
-	dr->result_high = ((u64)w << 32) + x;
-	dr->result_low  = ((u64)y << 32) + z;
-
-}
-
 /* We don't need to calibrate delay, we use the CPU timebase for that */
 void calibrate_delay(void)
 {
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 9feab5e0485b..a9cd6507163a 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -6,13 +6,13 @@
  * Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation.
  */
 
+#include <linux/export.h>
 #include <asm/asm-offsets.h>
 #include <asm/ppc_asm.h>
 #include <asm/ppc-opcode.h>
 #include <asm/ptrace.h>
 #include <asm/reg.h>
 #include <asm/bug.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 
 #ifdef CONFIG_VSX
diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
index b16a9f9c0b35..d6c3885453bd 100644
--- a/arch/powerpc/kernel/trace/Makefile
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -6,15 +6,18 @@
 ifdef CONFIG_FUNCTION_TRACER
 # do not trace tracer code
 CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace_64_pg.o = $(CC_FLAGS_FTRACE)
 endif
 
-obj32-$(CONFIG_FUNCTION_TRACER)		+= ftrace_mprofile.o
-ifdef CONFIG_MPROFILE_KERNEL
-obj64-$(CONFIG_FUNCTION_TRACER)		+= ftrace_mprofile.o
+ifdef CONFIG_FUNCTION_TRACER
+obj32-y					+= ftrace.o ftrace_entry.o
+ifeq ($(CONFIG_MPROFILE_KERNEL)$(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY),)
+obj64-y					+= ftrace_64_pg.o ftrace_64_pg_entry.o
 else
-obj64-$(CONFIG_FUNCTION_TRACER)		+= ftrace_64_pg.o
+obj64-y					+= ftrace.o ftrace_entry.o
+endif
 endif
-obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace_low.o ftrace.o
+
 obj-$(CONFIG_TRACING)			+= trace_clock.o
 
 obj-$(CONFIG_PPC64)			+= $(obj64-y)
@@ -25,3 +28,7 @@ GCOV_PROFILE_ftrace.o := n
 KCOV_INSTRUMENT_ftrace.o := n
 KCSAN_SANITIZE_ftrace.o := n
 UBSAN_SANITIZE_ftrace.o := n
+GCOV_PROFILE_ftrace_64_pg.o := n
+KCOV_INSTRUMENT_ftrace_64_pg.o := n
+KCSAN_SANITIZE_ftrace_64_pg.o := n
+UBSAN_SANITIZE_ftrace_64_pg.o := n
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index a47f30373423..841d077e2825 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -23,208 +23,85 @@
 #include <linux/list.h>
 
 #include <asm/cacheflush.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/ftrace.h>
 #include <asm/syscall.h>
 #include <asm/inst.h>
+#include <asm/sections.h>
 
-/*
- * We generally only have a single long_branch tramp and at most 2 or 3 plt
- * tramps generated. But, we don't use the plt tramps currently. We also allot
- * 2 tramps after .text and .init.text. So, we only end up with around 3 usable
- * tramps in total. Set aside 8 just to be sure.
- */
-#define	NUM_FTRACE_TRAMPS	8
+#define	NUM_FTRACE_TRAMPS	2
 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
 
-static ppc_inst_t
-ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
+unsigned long ftrace_call_adjust(unsigned long addr)
 {
-	ppc_inst_t op;
+	if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
+		return 0;
+
+	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) &&
+	    !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
+		addr += MCOUNT_INSN_SIZE;
+		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+			addr += MCOUNT_INSN_SIZE;
+	}
 
-	addr = ppc_function_entry((void *)addr);
+	return addr;
+}
+
+static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link)
+{
+	ppc_inst_t op;
 
-	/* if (link) set op to 'bl' else 'b' */
+	WARN_ON(!is_offset_in_branch_range(addr - ip));
 	create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0);
 
 	return op;
 }
 
-static inline int
-ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
+static inline int ftrace_read_inst(unsigned long ip, ppc_inst_t *op)
 {
-	ppc_inst_t replaced;
-
-	/*
-	 * Note:
-	 * We are paranoid about modifying text, as if a bug was to happen, it
-	 * could cause us to read or write to someplace that could cause harm.
-	 * Carefully read and modify the code with probe_kernel_*(), and make
-	 * sure what we read is what we expected it to be before modifying it.
-	 */
-
-	/* read the text we want to modify */
-	if (copy_inst_from_kernel_nofault(&replaced, (void *)ip))
+	if (copy_inst_from_kernel_nofault(op, (void *)ip)) {
+		pr_err("0x%lx: fetching instruction failed\n", ip);
 		return -EFAULT;
-
-	/* Make sure it is what we expect it to be */
-	if (!ppc_inst_equal(replaced, old)) {
-		pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip,
-		       ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old));
-		return -EINVAL;
 	}
 
-	/* replace the text with the new text */
-	return patch_instruction((u32 *)ip, new);
+	return 0;
 }
 
-/*
- * Helper functions that are the same for both PPC64 and PPC32.
- */
-static int test_24bit_addr(unsigned long ip, unsigned long addr)
+static inline int ftrace_validate_inst(unsigned long ip, ppc_inst_t inst)
 {
-	addr = ppc_function_entry((void *)addr);
-
-	return is_offset_in_branch_range(addr - ip);
-}
+	ppc_inst_t op;
+	int ret;
 
-static int is_bl_op(ppc_inst_t op)
-{
-	return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
-}
+	ret = ftrace_read_inst(ip, &op);
+	if (!ret && !ppc_inst_equal(op, inst)) {
+		pr_err("0x%lx: expected (%08lx) != found (%08lx)\n",
+		       ip, ppc_inst_as_ulong(inst), ppc_inst_as_ulong(op));
+		ret = -EINVAL;
+	}
 
-static int is_b_op(ppc_inst_t op)
-{
-	return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0);
+	return ret;
 }
 
-static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
+static inline int ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
 {
-	int offset;
+	int ret = ftrace_validate_inst(ip, old);
 
-	offset = PPC_LI(ppc_inst_val(op));
-	/* make it signed */
-	if (offset & 0x02000000)
-		offset |= 0xfe000000;
+	if (!ret && !ppc_inst_equal(old, new))
+		ret = patch_instruction((u32 *)ip, new);
 
-	return ip + (long)offset;
+	return ret;
 }
 
-#ifdef CONFIG_MODULES
-static int
-__ftrace_make_nop(struct module *mod,
-		  struct dyn_ftrace *rec, unsigned long addr)
-{
-	unsigned long entry, ptr, tramp;
-	unsigned long ip = rec->ip;
-	ppc_inst_t op, pop;
-
-	/* read where this goes */
-	if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
-		pr_err("Fetching opcode failed.\n");
-		return -EFAULT;
-	}
-
-	/* Make sure that this is still a 24bit jump */
-	if (!is_bl_op(op)) {
-		pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
-		return -EINVAL;
-	}
-
-	/* lets find where the pointer goes */
-	tramp = find_bl_target(ip, op);
-
-	pr_devel("ip:%lx jumps to %lx", ip, tramp);
-
-	if (module_trampoline_target(mod, tramp, &ptr)) {
-		pr_err("Failed to get trampoline target\n");
-		return -EFAULT;
-	}
-
-	pr_devel("trampoline target %lx", ptr);
-
-	entry = ppc_global_function_entry((void *)addr);
-	/* This should match what was called */
-	if (ptr != entry) {
-		pr_err("addr %lx does not match expected %lx\n", ptr, entry);
-		return -EINVAL;
-	}
-
-	if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
-		if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) {
-			pr_err("Fetching instruction at %lx failed.\n", ip - 4);
-			return -EFAULT;
-		}
-
-		/* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
-		if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) &&
-		    !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) {
-			pr_err("Unexpected instruction %08lx around bl _mcount\n",
-			       ppc_inst_as_ulong(op));
-			return -EINVAL;
-		}
-	} else if (IS_ENABLED(CONFIG_PPC64)) {
-		/*
-		 * Check what is in the next instruction. We can see ld r2,40(r1), but
-		 * on first pass after boot we will see mflr r0.
-		 */
-		if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) {
-			pr_err("Fetching op failed.\n");
-			return -EFAULT;
-		}
-
-		if (!ppc_inst_equal(op,  ppc_inst(PPC_INST_LD_TOC))) {
-			pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC,
-			       ppc_inst_as_ulong(op));
-			return -EINVAL;
-		}
-	}
-
-	/*
-	 * When using -mprofile-kernel or PPC32 there is no load to jump over.
-	 *
-	 * Otherwise our original call site looks like:
-	 *
-	 * bl <tramp>
-	 * ld r2,XX(r1)
-	 *
-	 * Milton Miller pointed out that we can not simply nop the branch.
-	 * If a task was preempted when calling a trace function, the nops
-	 * will remove the way to restore the TOC in r2 and the r2 TOC will
-	 * get corrupted.
-	 *
-	 * Use a b +8 to jump over the load.
-	 * XXX: could make PCREL depend on MPROFILE_KERNEL
-	 * XXX: check PCREL && MPROFILE_KERNEL calling sequence
-	 */
-	if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32))
-		pop = ppc_inst(PPC_RAW_NOP());
-	else
-		pop = ppc_inst(PPC_RAW_BRANCH(8));	/* b +8 */
-
-	if (patch_instruction((u32 *)ip, pop)) {
-		pr_err("Patching NOP failed.\n");
-		return -EPERM;
-	}
-
-	return 0;
-}
-#else
-static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
+static int is_bl_op(ppc_inst_t op)
 {
-	return 0;
+	return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
 }
-#endif /* CONFIG_MODULES */
 
 static unsigned long find_ftrace_tramp(unsigned long ip)
 {
 	int i;
 
-	/*
-	 * We have the compiler generated long_branch tramps at the end
-	 * and we prefer those
-	 */
-	for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--)
+	for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
 		if (!ftrace_tramps[i])
 			continue;
 		else if (is_offset_in_branch_range(ftrace_tramps[i] - ip))
@@ -233,449 +110,424 @@ static unsigned long find_ftrace_tramp(unsigned long ip)
 	return 0;
 }
 
-static int add_ftrace_tramp(unsigned long tramp)
+#ifdef CONFIG_MODULES
+static unsigned long ftrace_lookup_module_stub(unsigned long ip, unsigned long addr)
 {
-	int i;
+	struct module *mod = NULL;
 
-	for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
-		if (!ftrace_tramps[i]) {
-			ftrace_tramps[i] = tramp;
-			return 0;
-		}
+	scoped_guard(rcu)
+		mod = __module_text_address(ip);
+	if (!mod)
+		pr_err("No module loaded at addr=%lx\n", ip);
 
-	return -1;
+	return (addr == (unsigned long)ftrace_caller ? mod->arch.tramp : mod->arch.tramp_regs);
 }
-
-/*
- * If this is a compiler generated long_branch trampoline (essentially, a
- * trampoline that has a branch to _mcount()), we re-write the branch to
- * instead go to ftrace_[regs_]caller() and note down the location of this
- * trampoline.
- */
-static int setup_mcount_compiler_tramp(unsigned long tramp)
+#else
+static unsigned long ftrace_lookup_module_stub(unsigned long ip, unsigned long addr)
 {
-	int i;
-	ppc_inst_t op;
-	unsigned long ptr;
-
-	/* Is this a known long jump tramp? */
-	for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
-		if (ftrace_tramps[i] == tramp)
-			return 0;
-
-	/* New trampoline -- read where this goes */
-	if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) {
-		pr_debug("Fetching opcode failed.\n");
-		return -1;
-	}
+	return 0;
+}
+#endif
 
-	/* Is this a 24 bit branch? */
-	if (!is_b_op(op)) {
-		pr_debug("Trampoline is not a long branch tramp.\n");
-		return -1;
-	}
+static unsigned long ftrace_get_ool_stub(struct dyn_ftrace *rec)
+{
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	return rec->arch.ool_stub;
+#else
+	BUILD_BUG();
+#endif
+}
 
-	/* lets find where the pointer goes */
-	ptr = find_bl_target(tramp, op);
+static int ftrace_get_call_inst(struct dyn_ftrace *rec, unsigned long addr, ppc_inst_t *call_inst)
+{
+	unsigned long ip;
+	unsigned long stub;
 
-	if (ptr != ppc_global_function_entry((void *)_mcount)) {
-		pr_debug("Trampoline target %p is not _mcount\n", (void *)ptr);
-		return -1;
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+		ip = ftrace_get_ool_stub(rec) + MCOUNT_INSN_SIZE; /* second instruction in stub */
+	else
+		ip = rec->ip;
+
+	if (!is_offset_in_branch_range(addr - ip) && addr != FTRACE_ADDR &&
+	    addr != FTRACE_REGS_ADDR) {
+		/* This can only happen with ftrace direct */
+		if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS)) {
+			pr_err("0x%lx (0x%lx): Unexpected target address 0x%lx\n",
+			       ip, rec->ip, addr);
+			return -EINVAL;
+		}
+		addr = FTRACE_ADDR;
 	}
 
-	/* Let's re-write the tramp to go to ftrace_[regs_]caller */
-	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
-		ptr = ppc_global_function_entry((void *)ftrace_regs_caller);
+	if (is_offset_in_branch_range(addr - ip))
+		/* Within range */
+		stub = addr;
+	else if (core_kernel_text(ip))
+		/* We would be branching to one of our ftrace stubs */
+		stub = find_ftrace_tramp(ip);
 	else
-		ptr = ppc_global_function_entry((void *)ftrace_caller);
+		stub = ftrace_lookup_module_stub(ip, addr);
 
-	if (patch_branch((u32 *)tramp, ptr, 0)) {
-		pr_debug("REL24 out of range!\n");
-		return -1;
-	}
-
-	if (add_ftrace_tramp(tramp)) {
-		pr_debug("No tramp locations left\n");
-		return -1;
+	if (!stub) {
+		pr_err("0x%lx (0x%lx): No ftrace stubs reachable\n", ip, rec->ip);
+		return -EINVAL;
 	}
 
+	*call_inst = ftrace_create_branch_inst(ip, stub, 1);
 	return 0;
 }
 
-static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
+static int ftrace_init_ool_stub(struct module *mod, struct dyn_ftrace *rec)
 {
-	unsigned long tramp, ip = rec->ip;
-	ppc_inst_t op;
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	static int ool_stub_text_index, ool_stub_text_end_index, ool_stub_inittext_index;
+	int ret = 0, ool_stub_count, *ool_stub_index;
+	ppc_inst_t inst;
+	/*
+	 * See ftrace_entry.S if changing the below instruction sequence, as we rely on
+	 * decoding the last branch instruction here to recover the correct function ip.
+	 */
+	struct ftrace_ool_stub *ool_stub, ool_stub_template = {
+		.insn = {
+			PPC_RAW_MFLR(_R0),
+			PPC_RAW_NOP(),		/* bl ftrace_caller */
+			PPC_RAW_MTLR(_R0),
+			PPC_RAW_NOP()		/* b rec->ip + 4 */
+		}
+	};
 
-	/* Read where this goes */
-	if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
-		pr_err("Fetching opcode failed.\n");
-		return -EFAULT;
-	}
+	WARN_ON(rec->arch.ool_stub);
 
-	/* Make sure that this is still a 24bit jump */
-	if (!is_bl_op(op)) {
-		pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+	if (is_kernel_inittext(rec->ip)) {
+		ool_stub = ftrace_ool_stub_inittext;
+		ool_stub_index = &ool_stub_inittext_index;
+		ool_stub_count = ftrace_ool_stub_inittext_count;
+	} else if (is_kernel_text(rec->ip)) {
+		/*
+		 * ftrace records are sorted, so we first use up the stub area within .text
+		 * (ftrace_ool_stub_text) before using the area at the end of .text
+		 * (ftrace_ool_stub_text_end), unless the stub is out of range of the record.
+		 */
+		if (ool_stub_text_index >= ftrace_ool_stub_text_count ||
+		    !is_offset_in_branch_range((long)rec->ip -
+					       (long)&ftrace_ool_stub_text[ool_stub_text_index])) {
+			ool_stub = ftrace_ool_stub_text_end;
+			ool_stub_index = &ool_stub_text_end_index;
+			ool_stub_count = ftrace_ool_stub_text_end_count;
+		} else {
+			ool_stub = ftrace_ool_stub_text;
+			ool_stub_index = &ool_stub_text_index;
+			ool_stub_count = ftrace_ool_stub_text_count;
+		}
+#ifdef CONFIG_MODULES
+	} else if (mod) {
+		ool_stub = mod->arch.ool_stubs;
+		ool_stub_index = &mod->arch.ool_stub_index;
+		ool_stub_count = mod->arch.ool_stub_count;
+#endif
+	} else {
 		return -EINVAL;
 	}
 
-	/* Let's find where the pointer goes */
-	tramp = find_bl_target(ip, op);
+	ool_stub += (*ool_stub_index)++;
 
-	pr_devel("ip:%lx jumps to %lx", ip, tramp);
+	if (WARN_ON(*ool_stub_index > ool_stub_count))
+		return -EINVAL;
 
-	if (setup_mcount_compiler_tramp(tramp)) {
-		/* Are other trampolines reachable? */
-		if (!find_ftrace_tramp(ip)) {
-			pr_err("No ftrace trampolines reachable from %ps\n",
-					(void *)ip);
-			return -EINVAL;
-		}
+	if (!is_offset_in_branch_range((long)rec->ip - (long)&ool_stub->insn[0]) ||
+	    !is_offset_in_branch_range((long)(rec->ip + MCOUNT_INSN_SIZE) -
+				       (long)&ool_stub->insn[3])) {
+		pr_err("%s: ftrace ool stub out of range (%p -> %p).\n",
+					__func__, (void *)rec->ip, (void *)&ool_stub->insn[0]);
+		return -EINVAL;
 	}
 
-	if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) {
-		pr_err("Patching NOP failed.\n");
-		return -EPERM;
-	}
+	rec->arch.ool_stub = (unsigned long)&ool_stub->insn[0];
 
-	return 0;
+	/* bl ftrace_caller */
+	if (!mod)
+		ret = ftrace_get_call_inst(rec, (unsigned long)ftrace_caller, &inst);
+#ifdef CONFIG_MODULES
+	else
+		/*
+		 * We can't use ftrace_get_call_inst() since that uses
+		 * __module_text_address(rec->ip) to look up the module.
+		 * But, since the module is not fully formed at this stage,
+		 * the lookup fails. We know the target though, so generate
+		 * the branch inst directly.
+		 */
+		inst = ftrace_create_branch_inst(ftrace_get_ool_stub(rec) + MCOUNT_INSN_SIZE,
+						 mod->arch.tramp, 1);
+#endif
+	ool_stub_template.insn[1] = ppc_inst_val(inst);
+
+	/* b rec->ip + 4 */
+	if (!ret && create_branch(&inst, &ool_stub->insn[3], rec->ip + MCOUNT_INSN_SIZE, 0))
+		return -EINVAL;
+	ool_stub_template.insn[3] = ppc_inst_val(inst);
+
+	if (!ret)
+		ret = patch_instructions((u32 *)ool_stub, (u32 *)&ool_stub_template,
+					 sizeof(ool_stub_template), false);
+
+	return ret;
+#else /* !CONFIG_PPC_FTRACE_OUT_OF_LINE */
+	BUILD_BUG();
+#endif
 }
 
-int ftrace_make_nop(struct module *mod,
-		    struct dyn_ftrace *rec, unsigned long addr)
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+static const struct ftrace_ops *powerpc_rec_get_ops(struct dyn_ftrace *rec)
 {
-	unsigned long ip = rec->ip;
-	ppc_inst_t old, new;
+	const struct ftrace_ops *ops = NULL;
 
-	/*
-	 * If the calling address is more that 24 bits away,
-	 * then we had to use a trampoline to make the call.
-	 * Otherwise just update the call site.
-	 */
-	if (test_24bit_addr(ip, addr)) {
-		/* within range */
-		old = ftrace_call_replace(ip, addr, 1);
-		new = ppc_inst(PPC_RAW_NOP());
-		return ftrace_modify_code(ip, old, new);
-	} else if (core_kernel_text(ip)) {
-		return __ftrace_make_nop_kernel(rec, addr);
-	} else if (!IS_ENABLED(CONFIG_MODULES)) {
-		return -EINVAL;
+	if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
+		ops = ftrace_find_unique_ops(rec);
+		WARN_ON_ONCE(!ops);
 	}
 
-	/*
-	 * Out of range jumps are called from modules.
-	 * We should either already have a pointer to the module
-	 * or it has been passed in.
-	 */
-	if (!rec->arch.mod) {
-		if (!mod) {
-			pr_err("No module loaded addr=%lx\n", addr);
-			return -EFAULT;
-		}
-		rec->arch.mod = mod;
-	} else if (mod) {
-		if (mod != rec->arch.mod) {
-			pr_err("Record mod %p not equal to passed in mod %p\n",
-			       rec->arch.mod, mod);
-			return -EINVAL;
-		}
-		/* nothing to do if mod == rec->arch.mod */
-	} else
-		mod = rec->arch.mod;
+	if (!ops)
+		ops = &ftrace_list_ops;
 
-	return __ftrace_make_nop(mod, rec, addr);
+	return ops;
 }
 
-#ifdef CONFIG_MODULES
-/*
- * Examine the existing instructions for __ftrace_make_call.
- * They should effectively be a NOP, and follow formal constraints,
- * depending on the ABI. Return false if they don't.
- */
-static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1)
+static int ftrace_rec_set_ops(struct dyn_ftrace *rec, const struct ftrace_ops *ops)
 {
-	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
-		return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP()));
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+		return patch_ulong((void *)(ftrace_get_ool_stub(rec) - sizeof(unsigned long)),
+				   (unsigned long)ops);
 	else
-		return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) &&
-		       ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC));
+		return patch_ulong((void *)(rec->ip - MCOUNT_INSN_SIZE - sizeof(unsigned long)),
+				   (unsigned long)ops);
 }
 
-static int
-__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec)
 {
-	ppc_inst_t op[2];
-	void *ip = (void *)rec->ip;
-	unsigned long entry, ptr, tramp;
-	struct module *mod = rec->arch.mod;
-
-	/* read where this goes */
-	if (copy_inst_from_kernel_nofault(op, ip))
-		return -EFAULT;
-
-	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) &&
-	    copy_inst_from_kernel_nofault(op + 1, ip + 4))
-		return -EFAULT;
-
-	if (!expected_nop_sequence(ip, op[0], op[1])) {
-		pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip,
-		       ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1]));
-		return -EINVAL;
-	}
-
-	/* If we never set up ftrace trampoline(s), then bail */
-	if (!mod->arch.tramp ||
-	    (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) {
-		pr_err("No ftrace trampoline\n");
-		return -EINVAL;
-	}
-
-	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS)
-		tramp = mod->arch.tramp_regs;
-	else
-		tramp = mod->arch.tramp;
-
-	if (module_trampoline_target(mod, tramp, &ptr)) {
-		pr_err("Failed to get trampoline target\n");
-		return -EFAULT;
-	}
-
-	pr_devel("trampoline target %lx", ptr);
-
-	entry = ppc_global_function_entry((void *)addr);
-	/* This should match what was called */
-	if (ptr != entry) {
-		pr_err("addr %lx does not match expected %lx\n", ptr, entry);
-		return -EINVAL;
-	}
-
-	if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
-		pr_err("REL24 out of range!\n");
-		return -EINVAL;
-	}
+	return ftrace_rec_set_ops(rec, &ftrace_nop_ops);
+}
 
-	return 0;
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec)
+{
+	return ftrace_rec_set_ops(rec, powerpc_rec_get_ops(rec));
 }
 #else
-static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; }
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; }
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
 {
-	return 0;
+	/* This should never be called since we override ftrace_replace_code() */
+	WARN_ON(1);
+	return -EINVAL;
 }
-#endif /* CONFIG_MODULES */
+#endif
 
-static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	ppc_inst_t op;
-	void *ip = (void *)rec->ip;
-	unsigned long tramp, entry, ptr;
-
-	/* Make sure we're being asked to patch branch to a known ftrace addr */
-	entry = ppc_global_function_entry((void *)ftrace_caller);
-	ptr = ppc_global_function_entry((void *)addr);
-
-	if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
-		entry = ppc_global_function_entry((void *)ftrace_regs_caller);
+	ppc_inst_t old, new;
+	unsigned long ip = rec->ip;
+	int ret = 0;
 
-	if (ptr != entry) {
-		pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr);
+	/* This can only ever be called during module load */
+	if (WARN_ON(!IS_ENABLED(CONFIG_MODULES) || core_kernel_text(ip)))
 		return -EINVAL;
-	}
 
-	/* Make sure we have a nop */
-	if (copy_inst_from_kernel_nofault(&op, ip)) {
-		pr_err("Unable to read ftrace location %p\n", ip);
-		return -EFAULT;
+	old = ppc_inst(PPC_RAW_NOP());
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
+		ip = ftrace_get_ool_stub(rec) + MCOUNT_INSN_SIZE; /* second instruction in stub */
+		ret = ftrace_get_call_inst(rec, (unsigned long)ftrace_caller, &old);
 	}
 
-	if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) {
-		pr_err("Unexpected call sequence at %p: %08lx\n",
-		       ip, ppc_inst_as_ulong(op));
-		return -EINVAL;
-	}
+	ret |= ftrace_get_call_inst(rec, addr, &new);
 
-	tramp = find_ftrace_tramp((unsigned long)ip);
-	if (!tramp) {
-		pr_err("No ftrace trampolines reachable from %ps\n", ip);
-		return -EINVAL;
-	}
+	if (!ret)
+		ret = ftrace_modify_code(ip, old, new);
 
-	if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
-		pr_err("Error patching branch to ftrace tramp!\n");
-		return -EINVAL;
-	}
+	ret = ftrace_rec_update_ops(rec);
+	if (ret)
+		return ret;
 
-	return 0;
+	if (!ret && IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+		ret = ftrace_modify_code(rec->ip, ppc_inst(PPC_RAW_NOP()),
+			 ppc_inst(PPC_RAW_BRANCH((long)ftrace_get_ool_stub(rec) - (long)rec->ip)));
+
+	return ret;
 }
 
-int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned long ip = rec->ip;
-	ppc_inst_t old, new;
-
-	/*
-	 * If the calling address is more that 24 bits away,
-	 * then we had to use a trampoline to make the call.
-	 * Otherwise just update the call site.
-	 */
-	if (test_24bit_addr(ip, addr)) {
-		/* within range */
-		old = ppc_inst(PPC_RAW_NOP());
-		new = ftrace_call_replace(ip, addr, 1);
-		return ftrace_modify_code(ip, old, new);
-	} else if (core_kernel_text(ip)) {
-		return __ftrace_make_call_kernel(rec, addr);
-	} else if (!IS_ENABLED(CONFIG_MODULES)) {
-		/* We should not get here without modules */
-		return -EINVAL;
-	}
-
 	/*
-	 * Out of range jumps are called from modules.
-	 * Being that we are converting from nop, it had better
-	 * already have a module defined.
+	 * This should never be called since we override ftrace_replace_code(),
+	 * as well as ftrace_init_nop()
 	 */
-	if (!rec->arch.mod) {
-		pr_err("No module loaded\n");
-		return -EINVAL;
-	}
-
-	return __ftrace_make_call(rec, addr);
+	WARN_ON(1);
+	return -EINVAL;
 }
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-#ifdef CONFIG_MODULES
-static int
-__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
-					unsigned long addr)
+void ftrace_replace_code(int enable)
 {
-	ppc_inst_t op;
-	unsigned long ip = rec->ip;
-	unsigned long entry, ptr, tramp;
-	struct module *mod = rec->arch.mod;
+	ppc_inst_t old, new, call_inst, new_call_inst;
+	ppc_inst_t nop_inst = ppc_inst(PPC_RAW_NOP());
+	unsigned long ip, new_addr, addr;
+	struct ftrace_rec_iter *iter;
+	struct dyn_ftrace *rec;
+	int ret = 0, update;
 
-	/* If we never set up ftrace trampolines, then bail */
-	if (!mod->arch.tramp || !mod->arch.tramp_regs) {
-		pr_err("No ftrace trampoline\n");
-		return -EINVAL;
-	}
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+		ip = rec->ip;
 
-	/* read where this goes */
-	if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
-		pr_err("Fetching opcode failed.\n");
-		return -EFAULT;
-	}
-
-	/* Make sure that this is still a 24bit jump */
-	if (!is_bl_op(op)) {
-		pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
-		return -EINVAL;
-	}
-
-	/* lets find where the pointer goes */
-	tramp = find_bl_target(ip, op);
-	entry = ppc_global_function_entry((void *)old_addr);
-
-	pr_devel("ip:%lx jumps to %lx", ip, tramp);
-
-	if (tramp != entry) {
-		/* old_addr is not within range, so we must have used a trampoline */
-		if (module_trampoline_target(mod, tramp, &ptr)) {
-			pr_err("Failed to get trampoline target\n");
-			return -EFAULT;
-		}
+		if (rec->flags & FTRACE_FL_DISABLED && !(rec->flags & FTRACE_FL_ENABLED))
+			continue;
 
-		pr_devel("trampoline target %lx", ptr);
+		addr = ftrace_get_addr_curr(rec);
+		new_addr = ftrace_get_addr_new(rec);
+		update = ftrace_update_record(rec, enable);
 
-		/* This should match what was called */
-		if (ptr != entry) {
-			pr_err("addr %lx does not match expected %lx\n", ptr, entry);
-			return -EINVAL;
+		if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) && update != FTRACE_UPDATE_IGNORE) {
+			ip = ftrace_get_ool_stub(rec) + MCOUNT_INSN_SIZE;
+			ret = ftrace_get_call_inst(rec, (unsigned long)ftrace_caller, &nop_inst);
+			if (ret)
+				goto out;
 		}
-	}
 
-	/* The new target may be within range */
-	if (test_24bit_addr(ip, addr)) {
-		/* within range */
-		if (patch_branch((u32 *)ip, addr, BRANCH_SET_LINK)) {
-			pr_err("REL24 out of range!\n");
-			return -EINVAL;
+		switch (update) {
+		case FTRACE_UPDATE_IGNORE:
+		default:
+			continue;
+		case FTRACE_UPDATE_MODIFY_CALL:
+			ret = ftrace_get_call_inst(rec, new_addr, &new_call_inst);
+			ret |= ftrace_get_call_inst(rec, addr, &call_inst);
+			ret |= ftrace_rec_update_ops(rec);
+			old = call_inst;
+			new = new_call_inst;
+			break;
+		case FTRACE_UPDATE_MAKE_NOP:
+			ret = ftrace_get_call_inst(rec, addr, &call_inst);
+			ret |= ftrace_rec_set_nop_ops(rec);
+			old = call_inst;
+			new = nop_inst;
+			break;
+		case FTRACE_UPDATE_MAKE_CALL:
+			ret = ftrace_get_call_inst(rec, new_addr, &call_inst);
+			ret |= ftrace_rec_update_ops(rec);
+			old = nop_inst;
+			new = call_inst;
+			break;
 		}
 
-		return 0;
-	}
+		if (!ret)
+			ret = ftrace_modify_code(ip, old, new);
 
-	if (rec->flags & FTRACE_FL_REGS)
-		tramp = mod->arch.tramp_regs;
-	else
-		tramp = mod->arch.tramp;
+		if (!ret && IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) &&
+		    (update == FTRACE_UPDATE_MAKE_NOP || update == FTRACE_UPDATE_MAKE_CALL)) {
+			/* Update the actual ftrace location */
+			call_inst = ppc_inst(PPC_RAW_BRANCH((long)ftrace_get_ool_stub(rec) -
+							    (long)rec->ip));
+			nop_inst = ppc_inst(PPC_RAW_NOP());
+			ip = rec->ip;
 
-	if (module_trampoline_target(mod, tramp, &ptr)) {
-		pr_err("Failed to get trampoline target\n");
-		return -EFAULT;
-	}
-
-	pr_devel("trampoline target %lx", ptr);
+			if (update == FTRACE_UPDATE_MAKE_NOP)
+				ret = ftrace_modify_code(ip, call_inst, nop_inst);
+			else
+				ret = ftrace_modify_code(ip, nop_inst, call_inst);
 
-	entry = ppc_global_function_entry((void *)addr);
-	/* This should match what was called */
-	if (ptr != entry) {
-		pr_err("addr %lx does not match expected %lx\n", ptr, entry);
-		return -EINVAL;
-	}
+			if (ret)
+				goto out;
+		}
 
-	if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) {
-		pr_err("REL24 out of range!\n");
-		return -EINVAL;
+		if (ret)
+			goto out;
 	}
 
-	return 0;
-}
-#else
-static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
-{
-	return 0;
+out:
+	if (ret)
+		ftrace_bug(ret, rec);
+	return;
 }
-#endif
 
-int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
-			unsigned long addr)
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 {
-	unsigned long ip = rec->ip;
+	unsigned long addr, ip = rec->ip;
 	ppc_inst_t old, new;
+	int ret = 0;
+
+	/* Verify instructions surrounding the ftrace location */
+	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+		/* Expect nops */
+		if (!IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+			ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_NOP()));
+		if (!ret)
+			ret = ftrace_validate_inst(ip, ppc_inst(PPC_RAW_NOP()));
+	} else if (IS_ENABLED(CONFIG_PPC32)) {
+		/* Expected sequence: 'mflr r0', 'stw r0,4(r1)', 'bl _mcount' */
+		ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
+		if (ret)
+			return ret;
+		ret = ftrace_modify_code(ip - 4, ppc_inst(PPC_RAW_STW(_R0, _R1, 4)),
+					 ppc_inst(PPC_RAW_NOP()));
+	} else if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
+		/* Expected sequence: 'mflr r0', ['std r0,16(r1)'], 'bl _mcount' */
+		ret = ftrace_read_inst(ip - 4, &old);
+		if (!ret && !ppc_inst_equal(old, ppc_inst(PPC_RAW_MFLR(_R0)))) {
+			/* Gcc v5.x emit the additional 'std' instruction, gcc v6.x don't */
+			ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
+			if (ret)
+				return ret;
+			ret = ftrace_modify_code(ip - 4, ppc_inst(PPC_RAW_STD(_R0, _R1, 16)),
+						 ppc_inst(PPC_RAW_NOP()));
+		}
+	} else {
+		return -EINVAL;
+	}
 
-	/*
-	 * If the calling address is more that 24 bits away,
-	 * then we had to use a trampoline to make the call.
-	 * Otherwise just update the call site.
-	 */
-	if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) {
-		/* within range */
-		old = ftrace_call_replace(ip, old_addr, 1);
-		new = ftrace_call_replace(ip, addr, 1);
-		return ftrace_modify_code(ip, old, new);
-	} else if (core_kernel_text(ip)) {
+	if (ret)
+		return ret;
+
+	/* Set up out-of-line stub */
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
+		ret = ftrace_init_ool_stub(mod, rec);
+		goto out;
+	}
+
+	/* Nop-out the ftrace location */
+	new = ppc_inst(PPC_RAW_NOP());
+	addr = MCOUNT_ADDR;
+	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+		/* we instead patch-in the 'mflr r0' */
+		old = ppc_inst(PPC_RAW_NOP());
+		new = ppc_inst(PPC_RAW_MFLR(_R0));
+		ret = ftrace_modify_code(ip - 4, old, new);
+	} else if (is_offset_in_branch_range(addr - ip)) {
+		/* Within range */
+		old = ftrace_create_branch_inst(ip, addr, 1);
+		ret = ftrace_modify_code(ip, old, new);
+	} else if (core_kernel_text(ip) || (IS_ENABLED(CONFIG_MODULES) && mod)) {
 		/*
-		 * We always patch out of range locations to go to the regs
-		 * variant, so there is nothing to do here
+		 * We would be branching to a linker-generated stub, or to the module _mcount
+		 * stub. Let's just confirm we have a 'bl' here.
 		 */
-		return 0;
-	} else if (!IS_ENABLED(CONFIG_MODULES)) {
-		/* We should not get here without modules */
+		ret = ftrace_read_inst(ip, &old);
+		if (ret)
+			return ret;
+		if (!is_bl_op(old)) {
+			pr_err("0x%lx: expected (bl) != found (%08lx)\n", ip, ppc_inst_as_ulong(old));
+			return -EINVAL;
+		}
+		ret = patch_instruction((u32 *)ip, new);
+	} else {
 		return -EINVAL;
 	}
 
-	/*
-	 * Out of range jumps are called from modules.
-	 */
-	if (!rec->arch.mod) {
-		pr_err("No module loaded\n");
-		return -EINVAL;
-	}
+out:
+	if (!ret)
+		ret = ftrace_rec_set_nop_ops(rec);
 
-	return __ftrace_modify_call(rec, old_addr, addr);
+	return ret;
 }
-#endif
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
@@ -683,15 +535,22 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	ppc_inst_t old, new;
 	int ret;
 
+	/*
+	 * When using CALL_OPS, the function to call is associated with the
+	 * call site, and we don't have a global function pointer to update.
+	 */
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+		return 0;
+
 	old = ppc_inst_read((u32 *)&ftrace_call);
-	new = ftrace_call_replace(ip, (unsigned long)func, 1);
+	new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
 	ret = ftrace_modify_code(ip, old, new);
 
 	/* Also update the regs callback function */
 	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) {
 		ip = (unsigned long)(&ftrace_regs_call);
 		old = ppc_inst_read((u32 *)&ftrace_regs_call);
-		new = ftrace_call_replace(ip, (unsigned long)func, 1);
+		new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
 		ret = ftrace_modify_code(ip, old, new);
 	}
 
@@ -707,11 +566,6 @@ void arch_ftrace_update_code(int command)
 	ftrace_modify_all_code(command);
 }
 
-#ifdef CONFIG_PPC64
-#define PACATOC offsetof(struct paca_struct, kernel_toc)
-
-extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
-
 void ftrace_free_init_tramp(void)
 {
 	int i;
@@ -723,35 +577,43 @@ void ftrace_free_init_tramp(void)
 		}
 }
 
-int __init ftrace_dyn_arch_init(void)
+static void __init add_ftrace_tramp(unsigned long tramp)
 {
 	int i;
+
+	for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+		if (!ftrace_tramps[i]) {
+			ftrace_tramps[i] = tramp;
+			return;
+		}
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
 	unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
-#ifdef CONFIG_PPC_KERNEL_PCREL
+	unsigned long addr = FTRACE_REGS_ADDR;
+	long reladdr;
+	int i;
 	u32 stub_insns[] = {
+#ifdef CONFIG_PPC_KERNEL_PCREL
 		/* pla r12,addr */
 		PPC_PREFIX_MLS | __PPC_PRFX_R(1),
 		PPC_INST_PADDI | ___PPC_RT(_R12),
 		PPC_RAW_MTCTR(_R12),
 		PPC_RAW_BCTR()
-	};
-#else
-	u32 stub_insns[] = {
-		PPC_RAW_LD(_R12, _R13, PACATOC),
+#elif defined(CONFIG_PPC64)
+		PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernel_toc)),
 		PPC_RAW_ADDIS(_R12, _R12, 0),
 		PPC_RAW_ADDI(_R12, _R12, 0),
 		PPC_RAW_MTCTR(_R12),
 		PPC_RAW_BCTR()
-	};
+#else
+		PPC_RAW_LIS(_R12, 0),
+		PPC_RAW_ADDI(_R12, _R12, 0),
+		PPC_RAW_MTCTR(_R12),
+		PPC_RAW_BCTR()
 #endif
-
-	unsigned long addr;
-	long reladdr;
-
-	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
-		addr = ppc_global_function_entry((void *)ftrace_regs_caller);
-	else
-		addr = ppc_global_function_entry((void *)ftrace_caller);
+	};
 
 	if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
 		for (i = 0; i < 2; i++) {
@@ -768,10 +630,10 @@ int __init ftrace_dyn_arch_init(void)
 			tramp[i][1] |= IMM_L(reladdr);
 			add_ftrace_tramp((unsigned long)tramp[i]);
 		}
-	} else {
+	} else if (IS_ENABLED(CONFIG_PPC64)) {
 		reladdr = addr - kernel_toc_addr();
 
-		if (reladdr >= (long)SZ_2G || reladdr < -(long)SZ_2G) {
+		if (reladdr >= (long)SZ_2G || reladdr < -(long long)SZ_2G) {
 			pr_err("Address of %ps out of range of kernel_toc.\n",
 				(void *)addr);
 			return -1;
@@ -783,52 +645,23 @@ int __init ftrace_dyn_arch_init(void)
 			tramp[i][2] |= PPC_LO(reladdr);
 			add_ftrace_tramp((unsigned long)tramp[i]);
 		}
+	} else {
+		for (i = 0; i < 2; i++) {
+			memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+			tramp[i][0] |= PPC_HA(addr);
+			tramp[i][1] |= PPC_LO(addr);
+			add_ftrace_tramp((unsigned long)tramp[i]);
+		}
 	}
 
 	return 0;
 }
-#endif
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-extern void ftrace_graph_call(void);
-extern void ftrace_graph_stub(void);
-
-static int ftrace_modify_ftrace_graph_caller(bool enable)
-{
-	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	unsigned long addr = (unsigned long)(&ftrace_graph_caller);
-	unsigned long stub = (unsigned long)(&ftrace_graph_stub);
-	ppc_inst_t old, new;
-
-	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
-		return 0;
-
-	old = ftrace_call_replace(ip, enable ? stub : addr, 0);
-	new = ftrace_call_replace(ip, enable ? addr : stub, 0);
-
-	return ftrace_modify_code(ip, old, new);
-}
-
-int ftrace_enable_ftrace_graph_caller(void)
-{
-	return ftrace_modify_ftrace_graph_caller(true);
-}
-
-int ftrace_disable_ftrace_graph_caller(void)
-{
-	return ftrace_modify_ftrace_graph_caller(false);
-}
-
-/*
- * Hook the return address and push it in the stack of return addrs
- * in current thread info. Return the address we want to divert to.
- */
-static unsigned long
-__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp)
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	unsigned long return_hooker;
-	int bit;
+	unsigned long sp = arch_ftrace_regs(fregs)->regs.gpr[1];
 
 	if (unlikely(ftrace_graph_is_dead()))
 		goto out;
@@ -836,41 +669,10 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
 
-	bit = ftrace_test_recursion_trylock(ip, parent);
-	if (bit < 0)
-		goto out;
-
-	return_hooker = ppc_function_entry(return_to_handler);
-
-	if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
-		parent = return_hooker;
+	if (!function_graph_enter_regs(parent_ip, ip, 0, (unsigned long *)sp, fregs))
+		parent_ip = ppc_function_entry(return_to_handler);
 
-	ftrace_test_recursion_unlock(bit);
 out:
-	return parent;
-}
-
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
-void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
-		       struct ftrace_ops *op, struct ftrace_regs *fregs)
-{
-	fregs->regs.link = __prepare_ftrace_return(parent_ip, ip, fregs->regs.gpr[1]);
-}
-#else
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
-				    unsigned long sp)
-{
-	return __prepare_ftrace_return(parent, ip, sp);
+	arch_ftrace_regs(fregs)->regs.link = parent_ip;
 }
-#endif
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#ifdef CONFIG_PPC64_ELF_ABI_V1
-char *arch_ftrace_match_adjust(char *str, const char *search)
-{
-	if (str[0] == '.' && search[0] != '.')
-		return str + 1;
-	else
-		return str;
-}
-#endif /* CONFIG_PPC64_ELF_ABI_V1 */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.S b/arch/powerpc/kernel/trace/ftrace_64_pg.S
deleted file mode 100644
index 6708e24db0ab..000000000000
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.S
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Split from ftrace_64.S
- */
-
-#include <linux/magic.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/ftrace.h>
-#include <asm/ppc-opcode.h>
-#include <asm/export.h>
-
-_GLOBAL_TOC(ftrace_caller)
-	lbz	r3, PACA_FTRACE_ENABLED(r13)
-	cmpdi	r3, 0
-	beqlr
-
-	/* Taken from output of objdump from lib64/glibc */
-	mflr	r3
-	ld	r11, 0(r1)
-	stdu	r1, -112(r1)
-	std	r3, 128(r1)
-	ld	r4, 16(r11)
-	subi	r3, r3, MCOUNT_INSN_SIZE
-.globl ftrace_call
-ftrace_call:
-	bl	ftrace_stub
-	nop
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
-	b	ftrace_graph_stub
-_GLOBAL(ftrace_graph_stub)
-#endif
-	ld	r0, 128(r1)
-	mtlr	r0
-	addi	r1, r1, 112
-
-_GLOBAL(ftrace_stub)
-	blr
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-_GLOBAL(ftrace_graph_caller)
-	addi	r5, r1, 112
-	/* load r4 with local address */
-	ld	r4, 128(r1)
-	subi	r4, r4, MCOUNT_INSN_SIZE
-
-	/* Grab the LR out of the caller stack frame */
-	ld	r11, 112(r1)
-	ld	r3, 16(r11)
-
-	bl	prepare_ftrace_return
-	nop
-
-	/*
-	 * prepare_ftrace_return gives us the address we divert to.
-	 * Change the LR in the callers stack frame to this.
-	 */
-	ld	r11, 112(r1)
-	std	r3, 16(r11)
-
-	ld	r0, 128(r1)
-	mtlr	r0
-	addi	r1, r1, 112
-	blr
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
new file mode 100644
index 000000000000..5c6e545d1708
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -0,0 +1,832 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box.
+ *
+ * Added function graph tracer code, taken from x86 that was written
+ * by Frederic Weisbecker, and ported to PPC by Steven Rostedt.
+ *
+ */
+
+#define pr_fmt(fmt) "ftrace-powerpc: " fmt
+
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/list.h>
+
+#include <asm/cacheflush.h>
+#include <asm/text-patching.h>
+#include <asm/ftrace.h>
+#include <asm/syscall.h>
+#include <asm/inst.h>
+
+/*
+ * We generally only have a single long_branch tramp and at most 2 or 3 plt
+ * tramps generated. But, we don't use the plt tramps currently. We also allot
+ * 2 tramps after .text and .init.text. So, we only end up with around 3 usable
+ * tramps in total. Set aside 8 just to be sure.
+ */
+#define	NUM_FTRACE_TRAMPS	8
+static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
+
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
+static ppc_inst_t
+ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
+{
+	ppc_inst_t op;
+
+	addr = ppc_function_entry((void *)addr);
+
+	/* if (link) set op to 'bl' else 'b' */
+	create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0);
+
+	return op;
+}
+
+static inline int
+ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
+{
+	ppc_inst_t replaced;
+
+	/*
+	 * Note:
+	 * We are paranoid about modifying text, as if a bug was to happen, it
+	 * could cause us to read or write to someplace that could cause harm.
+	 * Carefully read and modify the code with probe_kernel_*(), and make
+	 * sure what we read is what we expected it to be before modifying it.
+	 */
+
+	/* read the text we want to modify */
+	if (copy_inst_from_kernel_nofault(&replaced, (void *)ip))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (!ppc_inst_equal(replaced, old)) {
+		pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip,
+		       ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old));
+		return -EINVAL;
+	}
+
+	/* replace the text with the new text */
+	return patch_instruction((u32 *)ip, new);
+}
+
+/*
+ * Helper functions that are the same for both PPC64 and PPC32.
+ */
+static int test_24bit_addr(unsigned long ip, unsigned long addr)
+{
+	addr = ppc_function_entry((void *)addr);
+
+	return is_offset_in_branch_range(addr - ip);
+}
+
+static int is_bl_op(ppc_inst_t op)
+{
+	return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
+}
+
+static int is_b_op(ppc_inst_t op)
+{
+	return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0);
+}
+
+static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
+{
+	int offset;
+
+	offset = PPC_LI(ppc_inst_val(op));
+	/* make it signed */
+	if (offset & 0x02000000)
+		offset |= 0xfe000000;
+
+	return ip + (long)offset;
+}
+
+#ifdef CONFIG_MODULES
+static struct module *ftrace_lookup_module(struct dyn_ftrace *rec)
+{
+	struct module *mod;
+
+	scoped_guard(rcu)
+		mod = __module_text_address(rec->ip);
+	if (!mod)
+		pr_err("No module loaded at addr=%lx\n", rec->ip);
+
+	return mod;
+}
+
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long entry, ptr, tramp;
+	unsigned long ip = rec->ip;
+	ppc_inst_t op, pop;
+
+	if (!mod) {
+		mod = ftrace_lookup_module(rec);
+		if (!mod)
+			return -EINVAL;
+	}
+
+	/* read where this goes */
+	if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+		pr_err("Fetching opcode failed.\n");
+		return -EFAULT;
+	}
+
+	/* Make sure that this is still a 24bit jump */
+	if (!is_bl_op(op)) {
+		pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, op);
+
+	pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+	if (module_trampoline_target(mod, tramp, &ptr)) {
+		pr_err("Failed to get trampoline target\n");
+		return -EFAULT;
+	}
+
+	pr_devel("trampoline target %lx", ptr);
+
+	entry = ppc_global_function_entry((void *)addr);
+	/* This should match what was called */
+	if (ptr != entry) {
+		pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+		return -EINVAL;
+	}
+
+	if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
+		if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) {
+			pr_err("Fetching instruction at %lx failed.\n", ip - 4);
+			return -EFAULT;
+		}
+
+		/* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
+		if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) &&
+		    !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) {
+			pr_err("Unexpected instruction %08lx around bl _mcount\n",
+			       ppc_inst_as_ulong(op));
+			return -EINVAL;
+		}
+	} else if (IS_ENABLED(CONFIG_PPC64)) {
+		/*
+		 * Check what is in the next instruction. We can see ld r2,40(r1), but
+		 * on first pass after boot we will see mflr r0.
+		 */
+		if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) {
+			pr_err("Fetching op failed.\n");
+			return -EFAULT;
+		}
+
+		if (!ppc_inst_equal(op,  ppc_inst(PPC_INST_LD_TOC))) {
+			pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC,
+			       ppc_inst_as_ulong(op));
+			return -EINVAL;
+		}
+	}
+
+	/*
+	 * When using -mprofile-kernel or PPC32 there is no load to jump over.
+	 *
+	 * Otherwise our original call site looks like:
+	 *
+	 * bl <tramp>
+	 * ld r2,XX(r1)
+	 *
+	 * Milton Miller pointed out that we can not simply nop the branch.
+	 * If a task was preempted when calling a trace function, the nops
+	 * will remove the way to restore the TOC in r2 and the r2 TOC will
+	 * get corrupted.
+	 *
+	 * Use a b +8 to jump over the load.
+	 */
+	if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32))
+		pop = ppc_inst(PPC_RAW_NOP());
+	else
+		pop = ppc_inst(PPC_RAW_BRANCH(8));	/* b +8 */
+
+	if (patch_instruction((u32 *)ip, pop)) {
+		pr_err("Patching NOP failed.\n");
+		return -EPERM;
+	}
+
+	return 0;
+}
+#else
+static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
+{
+	return 0;
+}
+#endif /* CONFIG_MODULES */
+
+static unsigned long find_ftrace_tramp(unsigned long ip)
+{
+	int i;
+
+	/*
+	 * We have the compiler generated long_branch tramps at the end
+	 * and we prefer those
+	 */
+	for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--)
+		if (!ftrace_tramps[i])
+			continue;
+		else if (is_offset_in_branch_range(ftrace_tramps[i] - ip))
+			return ftrace_tramps[i];
+
+	return 0;
+}
+
+static int add_ftrace_tramp(unsigned long tramp)
+{
+	int i;
+
+	for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+		if (!ftrace_tramps[i]) {
+			ftrace_tramps[i] = tramp;
+			return 0;
+		}
+
+	return -1;
+}
+
+/*
+ * If this is a compiler generated long_branch trampoline (essentially, a
+ * trampoline that has a branch to _mcount()), we re-write the branch to
+ * instead go to ftrace_[regs_]caller() and note down the location of this
+ * trampoline.
+ */
+static int setup_mcount_compiler_tramp(unsigned long tramp)
+{
+	int i;
+	ppc_inst_t op;
+	unsigned long ptr;
+
+	/* Is this a known long jump tramp? */
+	for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+		if (ftrace_tramps[i] == tramp)
+			return 0;
+
+	/* New trampoline -- read where this goes */
+	if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) {
+		pr_debug("Fetching opcode failed.\n");
+		return -1;
+	}
+
+	/* Is this a 24 bit branch? */
+	if (!is_b_op(op)) {
+		pr_debug("Trampoline is not a long branch tramp.\n");
+		return -1;
+	}
+
+	/* lets find where the pointer goes */
+	ptr = find_bl_target(tramp, op);
+
+	if (ptr != ppc_global_function_entry((void *)_mcount)) {
+		pr_debug("Trampoline target %p is not _mcount\n", (void *)ptr);
+		return -1;
+	}
+
+	/* Let's re-write the tramp to go to ftrace_[regs_]caller */
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+		ptr = ppc_global_function_entry((void *)ftrace_regs_caller);
+	else
+		ptr = ppc_global_function_entry((void *)ftrace_caller);
+
+	if (patch_branch((u32 *)tramp, ptr, 0)) {
+		pr_debug("REL24 out of range!\n");
+		return -1;
+	}
+
+	if (add_ftrace_tramp(tramp)) {
+		pr_debug("No tramp locations left\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long tramp, ip = rec->ip;
+	ppc_inst_t op;
+
+	/* Read where this goes */
+	if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+		pr_err("Fetching opcode failed.\n");
+		return -EFAULT;
+	}
+
+	/* Make sure that this is still a 24bit jump */
+	if (!is_bl_op(op)) {
+		pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+		return -EINVAL;
+	}
+
+	/* Let's find where the pointer goes */
+	tramp = find_bl_target(ip, op);
+
+	pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+	if (setup_mcount_compiler_tramp(tramp)) {
+		/* Are other trampolines reachable? */
+		if (!find_ftrace_tramp(ip)) {
+			pr_err("No ftrace trampolines reachable from %ps\n",
+					(void *)ip);
+			return -EINVAL;
+		}
+	}
+
+	if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) {
+		pr_err("Patching NOP failed.\n");
+		return -EPERM;
+	}
+
+	return 0;
+}
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	ppc_inst_t old, new;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ftrace_call_replace(ip, addr, 1);
+		new = ppc_inst(PPC_RAW_NOP());
+		return ftrace_modify_code(ip, old, new);
+	} else if (core_kernel_text(ip)) {
+		return __ftrace_make_nop_kernel(rec, addr);
+	} else if (!IS_ENABLED(CONFIG_MODULES)) {
+		return -EINVAL;
+	}
+
+	return __ftrace_make_nop(mod, rec, addr);
+}
+
+#ifdef CONFIG_MODULES
+/*
+ * Examine the existing instructions for __ftrace_make_call.
+ * They should effectively be a NOP, and follow formal constraints,
+ * depending on the ABI. Return false if they don't.
+ */
+static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1)
+{
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+		return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP()));
+	else
+		return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) &&
+		       ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC));
+}
+
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	ppc_inst_t op[2];
+	void *ip = (void *)rec->ip;
+	unsigned long entry, ptr, tramp;
+	struct module *mod = ftrace_lookup_module(rec);
+
+	if (!mod)
+		return -EINVAL;
+
+	/* read where this goes */
+	if (copy_inst_from_kernel_nofault(op, ip))
+		return -EFAULT;
+
+	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) &&
+	    copy_inst_from_kernel_nofault(op + 1, ip + 4))
+		return -EFAULT;
+
+	if (!expected_nop_sequence(ip, op[0], op[1])) {
+		pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip,
+		       ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1]));
+		return -EINVAL;
+	}
+
+	/* If we never set up ftrace trampoline(s), then bail */
+	if (!mod->arch.tramp ||
+	    (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) {
+		pr_err("No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS)
+		tramp = mod->arch.tramp_regs;
+	else
+		tramp = mod->arch.tramp;
+
+	if (module_trampoline_target(mod, tramp, &ptr)) {
+		pr_err("Failed to get trampoline target\n");
+		return -EFAULT;
+	}
+
+	pr_devel("trampoline target %lx", ptr);
+
+	entry = ppc_global_function_entry((void *)addr);
+	/* This should match what was called */
+	if (ptr != entry) {
+		pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+		return -EINVAL;
+	}
+
+	if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
+		pr_err("REL24 out of range!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+#else
+static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	return 0;
+}
+#endif /* CONFIG_MODULES */
+
+static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+	ppc_inst_t op;
+	void *ip = (void *)rec->ip;
+	unsigned long tramp, entry, ptr;
+
+	/* Make sure we're being asked to patch branch to a known ftrace addr */
+	entry = ppc_global_function_entry((void *)ftrace_caller);
+	ptr = ppc_global_function_entry((void *)addr);
+
+	if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+		entry = ppc_global_function_entry((void *)ftrace_regs_caller);
+
+	if (ptr != entry) {
+		pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr);
+		return -EINVAL;
+	}
+
+	/* Make sure we have a nop */
+	if (copy_inst_from_kernel_nofault(&op, ip)) {
+		pr_err("Unable to read ftrace location %p\n", ip);
+		return -EFAULT;
+	}
+
+	if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) {
+		pr_err("Unexpected call sequence at %p: %08lx\n",
+		       ip, ppc_inst_as_ulong(op));
+		return -EINVAL;
+	}
+
+	tramp = find_ftrace_tramp((unsigned long)ip);
+	if (!tramp) {
+		pr_err("No ftrace trampolines reachable from %ps\n", ip);
+		return -EINVAL;
+	}
+
+	if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
+		pr_err("Error patching branch to ftrace tramp!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	ppc_inst_t old, new;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ppc_inst(PPC_RAW_NOP());
+		new = ftrace_call_replace(ip, addr, 1);
+		return ftrace_modify_code(ip, old, new);
+	} else if (core_kernel_text(ip)) {
+		return __ftrace_make_call_kernel(rec, addr);
+	} else if (!IS_ENABLED(CONFIG_MODULES)) {
+		/* We should not get here without modules */
+		return -EINVAL;
+	}
+
+	return __ftrace_make_call(rec, addr);
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_MODULES
+static int
+__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+					unsigned long addr)
+{
+	ppc_inst_t op;
+	unsigned long ip = rec->ip;
+	unsigned long entry, ptr, tramp;
+	struct module *mod = ftrace_lookup_module(rec);
+
+	if (!mod)
+		return -EINVAL;
+
+	/* If we never set up ftrace trampolines, then bail */
+	if (!mod->arch.tramp || !mod->arch.tramp_regs) {
+		pr_err("No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* read where this goes */
+	if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+		pr_err("Fetching opcode failed.\n");
+		return -EFAULT;
+	}
+
+	/* Make sure that this is still a 24bit jump */
+	if (!is_bl_op(op)) {
+		pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, op);
+	entry = ppc_global_function_entry((void *)old_addr);
+
+	pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+	if (tramp != entry) {
+		/* old_addr is not within range, so we must have used a trampoline */
+		if (module_trampoline_target(mod, tramp, &ptr)) {
+			pr_err("Failed to get trampoline target\n");
+			return -EFAULT;
+		}
+
+		pr_devel("trampoline target %lx", ptr);
+
+		/* This should match what was called */
+		if (ptr != entry) {
+			pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+			return -EINVAL;
+		}
+	}
+
+	/* The new target may be within range */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		if (patch_branch((u32 *)ip, addr, BRANCH_SET_LINK)) {
+			pr_err("REL24 out of range!\n");
+			return -EINVAL;
+		}
+
+		return 0;
+	}
+
+	if (rec->flags & FTRACE_FL_REGS)
+		tramp = mod->arch.tramp_regs;
+	else
+		tramp = mod->arch.tramp;
+
+	if (module_trampoline_target(mod, tramp, &ptr)) {
+		pr_err("Failed to get trampoline target\n");
+		return -EFAULT;
+	}
+
+	pr_devel("trampoline target %lx", ptr);
+
+	entry = ppc_global_function_entry((void *)addr);
+	/* This should match what was called */
+	if (ptr != entry) {
+		pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+		return -EINVAL;
+	}
+
+	if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) {
+		pr_err("REL24 out of range!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+#else
+static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
+{
+	return 0;
+}
+#endif
+
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+			unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	ppc_inst_t old, new;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) {
+		/* within range */
+		old = ftrace_call_replace(ip, old_addr, 1);
+		new = ftrace_call_replace(ip, addr, 1);
+		return ftrace_modify_code(ip, old, new);
+	} else if (core_kernel_text(ip)) {
+		/*
+		 * We always patch out of range locations to go to the regs
+		 * variant, so there is nothing to do here
+		 */
+		return 0;
+	} else if (!IS_ENABLED(CONFIG_MODULES)) {
+		/* We should not get here without modules */
+		return -EINVAL;
+	}
+
+	return __ftrace_modify_call(rec, old_addr, addr);
+}
+#endif
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	ppc_inst_t old, new;
+	int ret;
+
+	old = ppc_inst_read((u32 *)&ftrace_call);
+	new = ftrace_call_replace(ip, (unsigned long)func, 1);
+	ret = ftrace_modify_code(ip, old, new);
+
+	/* Also update the regs callback function */
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) {
+		ip = (unsigned long)(&ftrace_regs_call);
+		old = ppc_inst_read((u32 *)&ftrace_regs_call);
+		new = ftrace_call_replace(ip, (unsigned long)func, 1);
+		ret = ftrace_modify_code(ip, old, new);
+	}
+
+	return ret;
+}
+
+/*
+ * Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
+void arch_ftrace_update_code(int command)
+{
+	ftrace_modify_all_code(command);
+}
+
+#ifdef CONFIG_PPC64
+#define PACATOC offsetof(struct paca_struct, kernel_toc)
+
+extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
+
+void ftrace_free_init_tramp(void)
+{
+	int i;
+
+	for (i = 0; i < NUM_FTRACE_TRAMPS && ftrace_tramps[i]; i++)
+		if (ftrace_tramps[i] == (unsigned long)ftrace_tramp_init) {
+			ftrace_tramps[i] = 0;
+			return;
+		}
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+	int i;
+	unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
+	u32 stub_insns[] = {
+		PPC_RAW_LD(_R12, _R13, PACATOC),
+		PPC_RAW_ADDIS(_R12, _R12, 0),
+		PPC_RAW_ADDI(_R12, _R12, 0),
+		PPC_RAW_MTCTR(_R12),
+		PPC_RAW_BCTR()
+	};
+	unsigned long addr;
+	long reladdr;
+
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+		addr = ppc_global_function_entry((void *)ftrace_regs_caller);
+	else
+		addr = ppc_global_function_entry((void *)ftrace_caller);
+
+	reladdr = addr - kernel_toc_addr();
+
+	if (reladdr >= SZ_2G || reladdr < -(long)SZ_2G) {
+		pr_err("Address of %ps out of range of kernel_toc.\n",
+				(void *)addr);
+		return -1;
+	}
+
+	for (i = 0; i < 2; i++) {
+		memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+		tramp[i][1] |= PPC_HA(reladdr);
+		tramp[i][2] |= PPC_LO(reladdr);
+		add_ftrace_tramp((unsigned long)tramp[i]);
+	}
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+extern void ftrace_graph_call(void);
+extern void ftrace_graph_stub(void);
+
+static int ftrace_modify_ftrace_graph_caller(bool enable)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+	unsigned long addr = (unsigned long)(&ftrace_graph_caller);
+	unsigned long stub = (unsigned long)(&ftrace_graph_stub);
+	ppc_inst_t old, new;
+
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
+		return 0;
+
+	old = ftrace_call_replace(ip, enable ? stub : addr, 0);
+	new = ftrace_call_replace(ip, enable ? addr : stub, 0);
+
+	return ftrace_modify_code(ip, old, new);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_ftrace_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_ftrace_graph_caller(false);
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info. Return the address we want to divert to.
+ */
+static unsigned long
+__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp,
+			struct ftrace_regs *fregs)
+{
+	unsigned long return_hooker;
+
+	if (unlikely(ftrace_graph_is_dead()))
+		goto out;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		goto out;
+
+	return_hooker = ppc_function_entry(return_to_handler);
+
+	if (!function_graph_enter_regs(parent, ip, 0, (unsigned long *)sp, fregs))
+		parent = return_hooker;
+
+out:
+	return parent;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip,
+						arch_ftrace_regs(fregs)->regs.gpr[1], fregs);
+}
+#else
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
+				    unsigned long sp)
+{
+	return __prepare_ftrace_return(parent, ip, sp, NULL);
+}
+#endif
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+char *arch_ftrace_match_adjust(char *str, const char *search)
+{
+	if (str[0] == '.' && search[0] != '.')
+		return str + 1;
+	else
+		return str;
+}
+#endif /* CONFIG_PPC64_ELF_ABI_V1 */
diff --git a/arch/powerpc/kernel/trace/ftrace_low.S b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S
index 294d1e05958a..a8a7f28404c8 100644
--- a/arch/powerpc/kernel/trace/ftrace_low.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S
@@ -1,28 +1,82 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * Split from entry_64.S
+ * Split from ftrace_64.S
  */
 
+#include <linux/export.h>
 #include <linux/magic.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/ftrace.h>
 #include <asm/ppc-opcode.h>
-#include <asm/export.h>
 
-#ifdef CONFIG_PPC64
+_GLOBAL_TOC(ftrace_caller)
+	lbz	r3, PACA_FTRACE_ENABLED(r13)
+	cmpdi	r3, 0
+	beqlr
+
+	/* Taken from output of objdump from lib64/glibc */
+	mflr	r3
+	ld	r11, 0(r1)
+	stdu	r1, -112(r1)
+	std	r3, 128(r1)
+	ld	r4, 16(r11)
+	subi	r3, r3, MCOUNT_INSN_SIZE
+.globl ftrace_call
+ftrace_call:
+	bl	ftrace_stub
+	nop
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+	b	ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+	ld	r0, 128(r1)
+	mtlr	r0
+	addi	r1, r1, 112
+
+_GLOBAL(ftrace_stub)
+	blr
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(ftrace_graph_caller)
+	addi	r5, r1, 112
+	/* load r4 with local address */
+	ld	r4, 128(r1)
+	subi	r4, r4, MCOUNT_INSN_SIZE
+
+	/* Grab the LR out of the caller stack frame */
+	ld	r11, 112(r1)
+	ld	r3, 16(r11)
+
+	bl	prepare_ftrace_return
+	nop
+
+	/*
+	 * prepare_ftrace_return gives us the address we divert to.
+	 * Change the LR in the callers stack frame to this.
+	 */
+	ld	r11, 112(r1)
+	std	r3, 16(r11)
+
+	ld	r0, 128(r1)
+	mtlr	r0
+	addi	r1, r1, 112
+	blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 .pushsection ".tramp.ftrace.text","aw",@progbits;
 .globl ftrace_tramp_text
 ftrace_tramp_text:
-	.space 64
+	.space 32
 .popsection
 
 .pushsection ".tramp.ftrace.init","aw",@progbits;
 .globl ftrace_tramp_init
 ftrace_tramp_init:
-	.space 64
+	.space 32
 .popsection
-#endif
 
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
new file mode 100644
index 000000000000..6599fe3c6234
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -0,0 +1,479 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Split from ftrace_64.S
+ */
+
+#include <linux/export.h>
+#include <linux/magic.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/ppc-opcode.h>
+#include <asm/thread_info.h>
+#include <asm/bug.h>
+#include <asm/ptrace.h>
+
+/*
+ *
+ * ftrace_caller()/ftrace_regs_caller() is the function that replaces _mcount()
+ * when ftrace is active.
+ *
+ * We arrive here after a function A calls function B, and we are the trace
+ * function for B. When we enter r1 points to A's stack frame, B has not yet
+ * had a chance to allocate one yet.
+ *
+ * Additionally r2 may point either to the TOC for A, or B, depending on
+ * whether B did a TOC setup sequence before calling us.
+ *
+ * On entry the LR points back to the _mcount() call site, and r0 holds the
+ * saved LR as it was on entry to B, ie. the original return address at the
+ * call site in A.
+ *
+ * Our job is to save the register state into a struct pt_regs (on the stack)
+ * and then arrange for the ftrace function to be called.
+ */
+.macro	ftrace_regs_entry allregs
+	/* Create a minimal stack frame for representing B */
+	PPC_STLU	r1, -STACK_FRAME_MIN_SIZE(r1)
+
+	/* Create our stack frame + pt_regs */
+	PPC_STLU	r1,-SWITCH_FRAME_SIZE(r1)
+
+	.if \allregs == 1
+	SAVE_GPRS(11, 12, r1)
+	.endif
+
+	/* Get the _mcount() call site out of LR */
+	mflr	r11
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	/* Load the ftrace_op */
+	PPC_LL	r12, -(MCOUNT_INSN_SIZE*2 + SZL)(r11)
+
+	/* Load direct_call from the ftrace_op */
+	PPC_LL	r12, FTRACE_OPS_DIRECT_CALL(r12)
+	PPC_LCMPI r12, 0
+	.if \allregs == 1
+	bne	.Lftrace_direct_call_regs
+	.else
+	bne	.Lftrace_direct_call
+	.endif
+#endif
+
+	/* Save the previous LR in pt_regs->link */
+	PPC_STL	r0, _LINK(r1)
+	/* Also save it in A's stack frame */
+	PPC_STL	r0, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE+LRSAVE(r1)
+
+	/* Save all gprs to pt_regs */
+	SAVE_GPR(0, r1)
+	SAVE_GPRS(3, 10, r1)
+
+#ifdef CONFIG_PPC64
+	/* Ok to continue? */
+	lbz	r3, PACA_FTRACE_ENABLED(r13)
+	cmpdi	r3, 0
+	beq	ftrace_no_trace
+#endif
+
+	.if \allregs == 1
+	SAVE_GPR(2, r1)
+	SAVE_GPRS(13, 31, r1)
+	.else
+#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
+	SAVE_GPR(14, r1)
+#endif
+	.endif
+
+	/* Save previous stack pointer (r1) */
+	addi	r8, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+	PPC_STL	r8, GPR1(r1)
+
+	.if \allregs == 1
+	/* Load special regs for save below */
+	mfcr	r7
+	mfmsr   r8
+	mfctr   r9
+	mfxer   r10
+	.else
+	/* Clear MSR to flag as ftrace_caller versus frace_regs_caller */
+	li	r8, 0
+	.endif
+
+#ifdef CONFIG_PPC64
+	/* Save callee's TOC in the ABI compliant location */
+	std	r2, STK_GOT(r1)
+	LOAD_PACA_TOC()		/* get kernel TOC in r2 */
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	/* r11 points to the instruction following the call to ftrace */
+	PPC_LL	r5, -(MCOUNT_INSN_SIZE*2 + SZL)(r11)
+	PPC_LL	r12, FTRACE_OPS_FUNC(r5)
+	mtctr	r12
+#else /* !CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS */
+#ifdef CONFIG_PPC64
+	LOAD_REG_ADDR(r3, function_trace_op)
+	ld	r5,0(r3)
+#else
+	lis	r3,function_trace_op@ha
+	lwz	r5,function_trace_op@l(r3)
+#endif
+#endif
+
+	/* Save special regs */
+	PPC_STL	r8, _MSR(r1)
+	.if \allregs == 1
+	PPC_STL	r7, _CCR(r1)
+	PPC_STL	r9, _CTR(r1)
+	PPC_STL	r10, _XER(r1)
+	.endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	/* Clear orig_gpr3 to later detect ftrace_direct call */
+	li	r7, 0
+	PPC_STL	r7, ORIG_GPR3(r1)
+#endif
+
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	/* Save our real return address in nvr for return */
+	.if \allregs == 0
+	SAVE_GPR(15, r1)
+	.endif
+	mr	r15, r11
+	/*
+	 * We want the ftrace location in the function, but our lr (in r11)
+	 * points at the 'mtlr r0' instruction in the out of line stub.  To
+	 * recover the ftrace location, we read the branch instruction in the
+	 * stub, and adjust our lr by the branch offset.
+	 *
+	 * See ftrace_init_ool_stub() for the profile sequence.
+	 */
+	lwz	r8, MCOUNT_INSN_SIZE(r11)
+	slwi	r8, r8, 6
+	srawi	r8, r8, 6
+	add	r3, r11, r8
+	/*
+	 * Override our nip to point past the branch in the original function.
+	 * This allows reliable stack trace and the ftrace stack tracer to work as-is.
+	 */
+	addi	r11, r3, MCOUNT_INSN_SIZE
+#else
+	/* Calculate ip from nip-4 into r3 for call below */
+	subi    r3, r11, MCOUNT_INSN_SIZE
+#endif
+
+	/* Save NIP as pt_regs->nip */
+	PPC_STL	r11, _NIP(r1)
+	/* Also save it in B's stackframe header for proper unwind */
+	PPC_STL	r11, LRSAVE+SWITCH_FRAME_SIZE(r1)
+#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
+	mr	r14, r11	/* remember old NIP */
+#endif
+
+	/* Put the original return address in r4 as parent_ip */
+	mr	r4, r0
+
+	/* Load &pt_regs in r6 for call below */
+	addi    r6, r1, STACK_INT_FRAME_REGS
+.endm
+
+.macro	ftrace_regs_exit allregs
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	/* Check orig_gpr3 to detect ftrace_direct call */
+	PPC_LL	r3, ORIG_GPR3(r1)
+	PPC_LCMPI cr1, r3, 0
+	mtctr	r3
+#endif
+
+	/* Restore possibly modified LR */
+	PPC_LL	r0, _LINK(r1)
+
+#ifndef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	/* Load ctr with the possibly modified NIP */
+	PPC_LL	r3, _NIP(r1)
+#ifdef CONFIG_LIVEPATCH_64
+	cmpd	r14, r3		/* has NIP been altered? */
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	beq	cr1,2f
+	mtlr	r3
+	b	3f
+#endif
+2:	mtctr	r3
+	mtlr	r0
+3:
+
+#else /* !CONFIG_PPC_FTRACE_OUT_OF_LINE */
+	/* Load LR with the possibly modified NIP */
+	PPC_LL	r3, _NIP(r1)
+	cmpd	r14, r3		/* has NIP been altered? */
+	bne-	1f
+
+	mr	r3, r15
+1:	mtlr	r3
+	.if \allregs == 0
+	REST_GPR(15, r1)
+	.endif
+#endif
+
+	/* Restore gprs */
+	.if \allregs == 1
+	REST_GPRS(2, 31, r1)
+	.else
+	REST_GPRS(3, 10, r1)
+#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
+	REST_GPR(14, r1)
+#endif
+	.endif
+
+#ifdef CONFIG_PPC64
+	/* Restore callee's TOC */
+	ld	r2, STK_GOT(r1)
+#endif
+
+	/* Pop our stack frame */
+	addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+
+#ifdef CONFIG_LIVEPATCH_64
+        /* Based on the cmpd above, if the NIP was altered handle livepatch */
+	bne-	livepatch_handler
+#endif
+
+	/* jump after _mcount site */
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	bnectr	cr1
+#endif
+	/*
+	 * Return with blr to keep the link stack balanced. The function profiling sequence
+	 * uses 'mtlr r0' to restore LR.
+	 */
+	blr
+#else
+	bctr
+#endif
+.endm
+
+.macro ftrace_regs_func allregs
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	bctrl
+#else
+	.if \allregs == 1
+.globl ftrace_regs_call
+ftrace_regs_call:
+	.else
+.globl ftrace_call
+ftrace_call:
+	.endif
+	/* ftrace_call(r3, r4, r5, r6) */
+	bl	ftrace_stub
+#endif
+.endm
+
+_GLOBAL(ftrace_regs_caller)
+	ftrace_regs_entry 1
+	ftrace_regs_func 1
+	ftrace_regs_exit 1
+
+_GLOBAL(ftrace_caller)
+	ftrace_regs_entry 0
+	ftrace_regs_func 0
+	ftrace_regs_exit 0
+
+_GLOBAL(ftrace_stub)
+	blr
+
+#ifdef CONFIG_PPC64
+ftrace_no_trace:
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	REST_GPR(3, r1)
+	addi	r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+	blr
+#else
+	mflr	r3
+	mtctr	r3
+	REST_GPR(3, r1)
+	addi	r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+	mtlr	r0
+	bctr
+#endif
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+.Lftrace_direct_call_regs:
+	mtctr	r12
+	REST_GPRS(11, 12, r1)
+	addi	r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+	bctr
+.Lftrace_direct_call:
+	mtctr	r12
+	addi	r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+	bctr
+SYM_FUNC_START(ftrace_stub_direct_tramp)
+	blr
+SYM_FUNC_END(ftrace_stub_direct_tramp)
+#endif
+
+#ifdef CONFIG_LIVEPATCH_64
+	/*
+	 * This function runs in the mcount context, between two functions. As
+	 * such it can only clobber registers which are volatile and used in
+	 * function linkage.
+	 *
+	 * We get here when a function A, calls another function B, but B has
+	 * been live patched with a new function C.
+	 *
+	 * On entry, we have no stack frame and can not allocate one.
+	 *
+	 * With PPC_FTRACE_OUT_OF_LINE=n, on entry:
+	 *  - LR points back to the original caller (in A)
+	 *  - CTR holds the new NIP in C
+	 *  - r0, r11 & r12 are free
+	 *
+	 * With PPC_FTRACE_OUT_OF_LINE=y, on entry:
+	 *  - r0 points back to the original caller (in A)
+	 *  - LR holds the new NIP in C
+	 *  - r11 & r12 are free
+	 */
+livepatch_handler:
+	ld	r12, PACA_THREAD_INFO(r13)
+
+	/* Allocate 3 x 8 bytes */
+	ld	r11, TI_livepatch_sp(r12)
+	addi	r11, r11, 24
+	std	r11, TI_livepatch_sp(r12)
+
+	/* Store stack end marker */
+	lis     r12, STACK_END_MAGIC@h
+	ori     r12, r12, STACK_END_MAGIC@l
+	std	r12, -8(r11)
+
+	/* Save toc & real LR on livepatch stack */
+	std	r2,  -24(r11)
+#ifndef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	mflr	r12
+	std	r12, -16(r11)
+	mfctr	r12
+#else
+	std	r0, -16(r11)
+	mflr	r12
+	/* Put ctr in r12 for global entry and branch there */
+	mtctr	r12
+#endif
+	bctrl
+
+	/*
+	 * Now we are returning from the patched function to the original
+	 * caller A. We are free to use r11, r12 and we can use r2 until we
+	 * restore it.
+	 */
+
+	ld	r12, PACA_THREAD_INFO(r13)
+
+	ld	r11, TI_livepatch_sp(r12)
+
+	/* Check stack marker hasn't been trashed */
+	lis     r2,  STACK_END_MAGIC@h
+	ori     r2,  r2, STACK_END_MAGIC@l
+	ld	r12, -8(r11)
+1:	tdne	r12, r2
+	EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
+
+	/* Restore LR & toc from livepatch stack */
+	ld	r12, -16(r11)
+	mtlr	r12
+	ld	r2,  -24(r11)
+
+	/* Pop livepatch stack frame */
+	ld	r12, PACA_THREAD_INFO(r13)
+	subi	r11, r11, 24
+	std	r11, TI_livepatch_sp(r12)
+
+	/* Return to original caller of live patched function */
+	blr
+#endif /* CONFIG_LIVEPATCH */
+
+#ifndef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+EXPORT_SYMBOL(_mcount)
+	mflr	r12
+	mtctr	r12
+	mtlr	r0
+	bctr
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(return_to_handler)
+	/* need to save return values */
+#ifdef CONFIG_PPC64
+	stdu	r1, -SWITCH_FRAME_SIZE(r1)
+	std	r4, GPR4(r1)
+	std	r3, GPR3(r1)
+	/* Save previous stack pointer (r1) */
+	addi	r3, r1, SWITCH_FRAME_SIZE
+	std	r3, GPR1(r1)
+	/* save TOC */
+	std	r2,  24(r1)
+	std	r31, 32(r1)
+	mr	r31, r1
+	/* pass ftrace_regs/pt_regs to ftrace_return_to_handler */
+	addi	r3, r1, STACK_INT_FRAME_REGS
+	/*
+	 * We might be called from a module.
+	 * Switch to our TOC to run inside the core kernel.
+	 */
+	LOAD_PACA_TOC()
+#else
+	stwu	r1, -SWITCH_FRAME_SIZE(r1)
+	stw	r4, GPR4(r1)
+	stw	r3, GPR3(r1)
+	addi	r3, r1, SWITCH_FRAME_SIZE
+	stw	r3, GPR1(r1)
+	/* pass ftrace_regs/pt_regs to ftrace_return_to_handler */
+	addi	r3, r1, STACK_INT_FRAME_REGS
+#endif
+
+	bl	ftrace_return_to_handler
+	nop
+
+	/* return value has real return address */
+	mtlr	r3
+
+#ifdef CONFIG_PPC64
+	ld	r4,  GPR4(r1)
+	ld	r3,  GPR3(r1)
+	ld	r2,  24(r1)
+	ld	r31, 32(r1)
+	ld	r1,  0(r1)
+#else
+	lwz	r3, GPR3(r1)
+	lwz	r4, GPR4(r1)
+	addi	r1, r1, SWITCH_FRAME_SIZE
+#endif
+
+	/* Jump back to real return address */
+	blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+SYM_DATA(ftrace_ool_stub_text_count, .long CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE)
+
+SYM_START(ftrace_ool_stub_text, SYM_L_GLOBAL, .balign SZL)
+	.space CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE * FTRACE_OOL_STUB_SIZE
+SYM_CODE_END(ftrace_ool_stub_text)
+#endif
+
+.pushsection ".tramp.ftrace.text","aw",@progbits;
+.globl ftrace_tramp_text
+ftrace_tramp_text:
+	.space 32
+.popsection
+
+.pushsection ".tramp.ftrace.init","aw",@progbits;
+.globl ftrace_tramp_init
+ftrace_tramp_init:
+	.space 32
+.popsection
diff --git a/arch/powerpc/kernel/trace/ftrace_mprofile.S b/arch/powerpc/kernel/trace/ftrace_mprofile.S
deleted file mode 100644
index ffb1db386849..000000000000
--- a/arch/powerpc/kernel/trace/ftrace_mprofile.S
+++ /dev/null
@@ -1,251 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Split from ftrace_64.S
- */
-
-#include <linux/magic.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/ftrace.h>
-#include <asm/ppc-opcode.h>
-#include <asm/export.h>
-#include <asm/thread_info.h>
-#include <asm/bug.h>
-#include <asm/ptrace.h>
-
-/*
- *
- * ftrace_caller()/ftrace_regs_caller() is the function that replaces _mcount()
- * when ftrace is active.
- *
- * We arrive here after a function A calls function B, and we are the trace
- * function for B. When we enter r1 points to A's stack frame, B has not yet
- * had a chance to allocate one yet.
- *
- * Additionally r2 may point either to the TOC for A, or B, depending on
- * whether B did a TOC setup sequence before calling us.
- *
- * On entry the LR points back to the _mcount() call site, and r0 holds the
- * saved LR as it was on entry to B, ie. the original return address at the
- * call site in A.
- *
- * Our job is to save the register state into a struct pt_regs (on the stack)
- * and then arrange for the ftrace function to be called.
- */
-.macro	ftrace_regs_entry allregs
-	/* Create our stack frame + pt_regs */
-	PPC_STLU	r1,-SWITCH_FRAME_SIZE(r1)
-
-	/* Save all gprs to pt_regs */
-	SAVE_GPR(0, r1)
-	SAVE_GPRS(3, 10, r1)
-
-#ifdef CONFIG_PPC64
-	/* Save the original return address in A's stack frame */
-	std	r0, LRSAVE+SWITCH_FRAME_SIZE(r1)
-	/* Ok to continue? */
-	lbz	r3, PACA_FTRACE_ENABLED(r13)
-	cmpdi	r3, 0
-	beq	ftrace_no_trace
-#endif
-
-	.if \allregs == 1
-	SAVE_GPR(2, r1)
-	SAVE_GPRS(11, 31, r1)
-	.else
-#ifdef CONFIG_LIVEPATCH_64
-	SAVE_GPR(14, r1)
-#endif
-	.endif
-
-	/* Save previous stack pointer (r1) */
-	addi	r8, r1, SWITCH_FRAME_SIZE
-	PPC_STL	r8, GPR1(r1)
-
-	.if \allregs == 1
-	/* Load special regs for save below */
-	mfmsr   r8
-	mfctr   r9
-	mfxer   r10
-	mfcr	r11
-	.else
-	/* Clear MSR to flag as ftrace_caller versus frace_regs_caller */
-	li	r8, 0
-	.endif
-
-	/* Get the _mcount() call site out of LR */
-	mflr	r7
-	/* Save it as pt_regs->nip */
-	PPC_STL	r7, _NIP(r1)
-	/* Save the read LR in pt_regs->link */
-	PPC_STL	r0, _LINK(r1)
-
-#ifdef CONFIG_PPC64
-	/* Save callee's TOC in the ABI compliant location */
-	std	r2, STK_GOT(r1)
-	LOAD_PACA_TOC()		/* get kernel TOC in r2 */
-	LOAD_REG_ADDR(r3, function_trace_op)
-	ld	r5,0(r3)
-#else
-	lis	r3,function_trace_op@ha
-	lwz	r5,function_trace_op@l(r3)
-#endif
-
-#ifdef CONFIG_LIVEPATCH_64
-	mr	r14, r7		/* remember old NIP */
-#endif
-
-	/* Calculate ip from nip-4 into r3 for call below */
-	subi    r3, r7, MCOUNT_INSN_SIZE
-
-	/* Put the original return address in r4 as parent_ip */
-	mr	r4, r0
-
-	/* Save special regs */
-	PPC_STL	r8, _MSR(r1)
-	.if \allregs == 1
-	PPC_STL	r9, _CTR(r1)
-	PPC_STL	r10, _XER(r1)
-	PPC_STL	r11, _CCR(r1)
-	.endif
-
-	/* Load &pt_regs in r6 for call below */
-	addi    r6, r1, STACK_INT_FRAME_REGS
-.endm
-
-.macro	ftrace_regs_exit allregs
-	/* Load ctr with the possibly modified NIP */
-	PPC_LL	r3, _NIP(r1)
-	mtctr	r3
-
-#ifdef CONFIG_LIVEPATCH_64
-	cmpd	r14, r3		/* has NIP been altered? */
-#endif
-
-	/* Restore gprs */
-	.if \allregs == 1
-	REST_GPRS(2, 31, r1)
-	.else
-	REST_GPRS(3, 10, r1)
-#ifdef CONFIG_LIVEPATCH_64
-	REST_GPR(14, r1)
-#endif
-	.endif
-
-	/* Restore possibly modified LR */
-	PPC_LL	r0, _LINK(r1)
-	mtlr	r0
-
-#ifdef CONFIG_PPC64
-	/* Restore callee's TOC */
-	ld	r2, STK_GOT(r1)
-#endif
-
-	/* Pop our stack frame */
-	addi r1, r1, SWITCH_FRAME_SIZE
-
-#ifdef CONFIG_LIVEPATCH_64
-        /* Based on the cmpd above, if the NIP was altered handle livepatch */
-	bne-	livepatch_handler
-#endif
-	bctr			/* jump after _mcount site */
-.endm
-
-_GLOBAL(ftrace_regs_caller)
-	ftrace_regs_entry 1
-	/* ftrace_call(r3, r4, r5, r6) */
-.globl ftrace_regs_call
-ftrace_regs_call:
-	bl	ftrace_stub
-	nop
-	ftrace_regs_exit 1
-
-_GLOBAL(ftrace_caller)
-	ftrace_regs_entry 0
-	/* ftrace_call(r3, r4, r5, r6) */
-.globl ftrace_call
-ftrace_call:
-	bl	ftrace_stub
-	nop
-	ftrace_regs_exit 0
-
-_GLOBAL(ftrace_stub)
-	blr
-
-#ifdef CONFIG_PPC64
-ftrace_no_trace:
-	mflr	r3
-	mtctr	r3
-	REST_GPR(3, r1)
-	addi	r1, r1, SWITCH_FRAME_SIZE
-	mtlr	r0
-	bctr
-#endif
-
-#ifdef CONFIG_LIVEPATCH_64
-	/*
-	 * This function runs in the mcount context, between two functions. As
-	 * such it can only clobber registers which are volatile and used in
-	 * function linkage.
-	 *
-	 * We get here when a function A, calls another function B, but B has
-	 * been live patched with a new function C.
-	 *
-	 * On entry:
-	 *  - we have no stack frame and can not allocate one
-	 *  - LR points back to the original caller (in A)
-	 *  - CTR holds the new NIP in C
-	 *  - r0, r11 & r12 are free
-	 */
-livepatch_handler:
-	ld	r12, PACA_THREAD_INFO(r13)
-
-	/* Allocate 3 x 8 bytes */
-	ld	r11, TI_livepatch_sp(r12)
-	addi	r11, r11, 24
-	std	r11, TI_livepatch_sp(r12)
-
-	/* Save toc & real LR on livepatch stack */
-	std	r2,  -24(r11)
-	mflr	r12
-	std	r12, -16(r11)
-
-	/* Store stack end marker */
-	lis     r12, STACK_END_MAGIC@h
-	ori     r12, r12, STACK_END_MAGIC@l
-	std	r12, -8(r11)
-
-	/* Put ctr in r12 for global entry and branch there */
-	mfctr	r12
-	bctrl
-
-	/*
-	 * Now we are returning from the patched function to the original
-	 * caller A. We are free to use r11, r12 and we can use r2 until we
-	 * restore it.
-	 */
-
-	ld	r12, PACA_THREAD_INFO(r13)
-
-	ld	r11, TI_livepatch_sp(r12)
-
-	/* Check stack marker hasn't been trashed */
-	lis     r2,  STACK_END_MAGIC@h
-	ori     r2,  r2, STACK_END_MAGIC@l
-	ld	r12, -8(r11)
-1:	tdne	r12, r2
-	EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
-
-	/* Restore LR & toc from livepatch stack */
-	ld	r12, -16(r11)
-	mtlr	r12
-	ld	r2,  -24(r11)
-
-	/* Pop livepatch stack frame */
-	ld	r12, PACA_THREAD_INFO(r13)
-	subi	r11, r11, 24
-	std	r11, TI_livepatch_sp(r12)
-
-	/* Return to original caller of live patched function */
-	blr
-#endif /* CONFIG_LIVEPATCH */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 9bdd79aa51cf..cb8e9357383e 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -121,7 +121,7 @@ static void pmac_backlight_unblank(void)
 
 		props = &pmac_backlight->props;
 		props->brightness = props->max_brightness;
-		props->power = FB_BLANK_UNBLANK;
+		props->power = BACKLIGHT_POWER_ON;
 		backlight_update_status(pmac_backlight);
 	}
 	mutex_unlock(&pmac_backlight_mutex);
@@ -157,7 +157,7 @@ static int die_owner = -1;
 static unsigned int die_nest_count;
 static int die_counter;
 
-extern void panic_flush_kmsg_start(void)
+void panic_flush_kmsg_start(void)
 {
 	/*
 	 * These are mostly taken from kernel/panic.c, but tries to do
@@ -170,7 +170,7 @@ extern void panic_flush_kmsg_start(void)
 	bust_spinlocks(1);
 }
 
-extern void panic_flush_kmsg_end(void)
+void panic_flush_kmsg_end(void)
 {
 	kmsg_dump(KMSG_DUMP_PANIC);
 	bust_spinlocks(0);
@@ -263,10 +263,9 @@ static int __die(const char *str, struct pt_regs *regs, long err)
 {
 	printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
 
-	printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n",
+	printk("%s PAGE_SIZE=%luK%s %s%s%s%s %s\n",
 	       IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
 	       PAGE_SIZE / 1024, get_mmu_str(),
-	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
 	       IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
 	       IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
 	       debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
@@ -404,7 +403,7 @@ noinstr void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
 		return;
 	if (!(regs->msr & MSR_HV))
 		return;
-	if (regs->msr & MSR_PR)
+	if (user_mode(regs))
 		return;
 
 	/*
@@ -1158,12 +1157,13 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception)
  * pretend we got a single-step exception.  This was pointed out
  * by Kumar Gala.  -- paulus
  */
-static void emulate_single_step(struct pt_regs *regs)
+void emulate_single_step(struct pt_regs *regs)
 {
 	if (single_stepping(regs))
 		__single_step_exception(regs);
 }
 
+#ifdef CONFIG_PPC_FPU_REGS
 static inline int __parse_fpscr(unsigned long fpscr)
 {
 	int ret = FPE_FLTUNK;
@@ -1190,6 +1190,7 @@ static inline int __parse_fpscr(unsigned long fpscr)
 
 	return ret;
 }
+#endif
 
 static void parse_fpe(struct pt_regs *regs)
 {
@@ -1437,10 +1438,12 @@ static int emulate_instruction(struct pt_regs *regs)
 	return -EINVAL;
 }
 
+#ifdef CONFIG_GENERIC_BUG
 int is_valid_bugaddr(unsigned long addr)
 {
 	return is_kernel_addr(addr);
 }
+#endif
 
 #ifdef CONFIG_MATH_EMULATION
 static int emulate_math(struct pt_regs *regs)
@@ -1506,18 +1509,17 @@ static void do_program_check(struct pt_regs *regs)
 		if (!is_kernel_addr(bugaddr) && !(regs->msr & MSR_IR))
 			bugaddr += PAGE_OFFSET;
 
-		if (!(regs->msr & MSR_PR) &&  /* not user-mode */
+		if (!user_mode(regs) &&
 		    report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
-			const struct exception_table_entry *entry;
+			regs_add_return_ip(regs, 4);
+			return;
+		}
 
-			entry = search_exception_tables(bugaddr);
-			if (entry) {
-				regs_set_return_ip(regs, extable_fixup(entry) + regs->nip - bugaddr);
-				return;
-			}
+		/* User mode considers other cases after enabling IRQs */
+		if (!user_mode(regs)) {
+			_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+			return;
 		}
-		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-		return;
 	}
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (reason & REASON_TM) {
@@ -1550,16 +1552,44 @@ static void do_program_check(struct pt_regs *regs)
 
 	/*
 	 * If we took the program check in the kernel skip down to sending a
-	 * SIGILL. The subsequent cases all relate to emulating instructions
-	 * which we should only do for userspace. We also do not want to enable
-	 * interrupts for kernel faults because that might lead to further
-	 * faults, and loose the context of the original exception.
+	 * SIGILL. The subsequent cases all relate to user space, such as
+	 * emulating instructions which we should only do for user space. We
+	 * also do not want to enable interrupts for kernel faults because that
+	 * might lead to further faults, and loose the context of the original
+	 * exception.
 	 */
 	if (!user_mode(regs))
 		goto sigill;
 
 	interrupt_cond_local_irq_enable(regs);
 
+	/*
+	 * (reason & REASON_TRAP) is mostly handled before enabling IRQs,
+	 * except get_user_instr() can sleep so we cannot reliably inspect the
+	 * current instruction in that context. Now that we know we are
+	 * handling a user space trap and can sleep, we can check if the trap
+	 * was a hashchk failure.
+	 */
+	if (reason & REASON_TRAP) {
+		if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
+			ppc_inst_t insn;
+
+			if (get_user_instr(insn, (void __user *)regs->nip)) {
+				_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+				return;
+			}
+
+			if (ppc_inst_primary_opcode(insn) == 31 &&
+			    get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
+				_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
+				return;
+			}
+		}
+
+		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+		return;
+	}
+
 	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
 	 * but there seems to be a hardware bug on the 405GP (RevD)
 	 * that means ESR is sometimes set incorrectly - either to
@@ -2213,22 +2243,11 @@ void __noreturn unrecoverable_exception(struct pt_regs *regs)
 		;
 }
 
-#if defined(CONFIG_BOOKE_WDT) || defined(CONFIG_40x)
-/*
- * Default handler for a Watchdog exception,
- * spins until a reboot occurs
- */
-void __attribute__ ((weak)) WatchdogHandler(struct pt_regs *regs)
-{
-	/* Generic WatchdogHandler, implement your own */
-	mtspr(SPRN_TCR, mfspr(SPRN_TCR)&(~TCR_WIE));
-	return;
-}
-
+#ifdef CONFIG_BOOKE_WDT
 DEFINE_INTERRUPT_HANDLER_NMI(WatchdogException)
 {
 	printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n");
-	WatchdogHandler(regs);
+	mtspr(SPRN_TCR, mfspr(SPRN_TCR) & ~TCR_WIE);
 	return 0;
 }
 #endif
diff --git a/arch/powerpc/kernel/ucall.S b/arch/powerpc/kernel/ucall.S
index 07296bc39166..80a1f9a4300a 100644
--- a/arch/powerpc/kernel/ucall.S
+++ b/arch/powerpc/kernel/ucall.S
@@ -5,8 +5,8 @@
  * Copyright 2019, IBM Corporation.
  *
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 
 _GLOBAL(ucall_norets)
 EXPORT_SYMBOL_GPL(ucall_norets)
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 92b3fc258d11..862b22b2b616 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -36,12 +36,6 @@ void __init udbg_early_init(void)
 #elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_PANEL)
 	/* RTAS panel debug */
 	udbg_init_rtas_panel();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_CONSOLE)
-	/* RTAS console debug */
-	udbg_init_rtas_console();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_MAPLE)
-	/* Maple real mode debug */
-	udbg_init_maple_realmode();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
 	udbg_init_pas_realmode();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX)
@@ -49,9 +43,6 @@ void __init udbg_early_init(void)
 #elif defined(CONFIG_PPC_EARLY_DEBUG_44x)
 	/* PPC44x debug */
 	udbg_init_44x_as1();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_40x)
-	/* PPC40x debug */
-	udbg_init_40x_realmode();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_CPM)
 	udbg_init_cpm();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_USBGECKO)
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 74ddf836f7a2..dfe8ed2192e8 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -7,7 +7,6 @@
 #include <linux/types.h>
 #include <asm/udbg.h>
 #include <asm/io.h>
-#include <asm/reg_a2.h>
 #include <asm/early_ioremap.h>
 
 extern u8 real_readb(volatile u8 __iomem  *addr);
@@ -206,29 +205,6 @@ void __init udbg_uart_init_mmio(void __iomem *addr, unsigned int stride)
 	udbg_use_uart();
 }
 
-#ifdef CONFIG_PPC_MAPLE
-
-#define UDBG_UART_MAPLE_ADDR	((void __iomem *)0xf40003f8)
-
-static u8 udbg_uart_in_maple(unsigned int reg)
-{
-	return real_readb(UDBG_UART_MAPLE_ADDR + reg);
-}
-
-static void udbg_uart_out_maple(unsigned int reg, u8 val)
-{
-	real_writeb(val, UDBG_UART_MAPLE_ADDR + reg);
-}
-
-void __init udbg_init_maple_realmode(void)
-{
-	udbg_uart_in = udbg_uart_in_maple;
-	udbg_uart_out = udbg_uart_out_maple;
-	udbg_use_uart();
-}
-
-#endif /* CONFIG_PPC_MAPLE */
-
 #ifdef CONFIG_PPC_PASEMI
 
 #define UDBG_UART_PAS_ADDR	((void __iomem *)0xfcff03f8UL)
@@ -275,29 +251,6 @@ void __init udbg_init_44x_as1(void)
 
 #endif /* CONFIG_PPC_EARLY_DEBUG_44x */
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_40x
-
-static u8 udbg_uart_in_40x(unsigned int reg)
-{
-	return real_readb((void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
-			  + reg);
-}
-
-static void udbg_uart_out_40x(unsigned int reg, u8 val)
-{
-	real_writeb(val, (void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
-		    + reg);
-}
-
-void __init udbg_init_40x_realmode(void)
-{
-	udbg_uart_in = udbg_uart_in_40x;
-	udbg_uart_out = udbg_uart_out_40x;
-	udbg_use_uart();
-}
-
-#endif /* CONFIG_PPC_EARLY_DEBUG_40x */
-
 #ifdef CONFIG_PPC_EARLY_DEBUG_16550
 
 static void __iomem *udbg_uart_early_addr;
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 7a2ff9010f17..ab7c4cc80943 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -16,12 +16,12 @@
 #include <linux/user.h>
 #include <linux/elf.h>
 #include <linux/security.h>
-#include <linux/memblock.h>
 #include <linux/syscalls.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 #include <vdso/datapage.h>
 
 #include <asm/syscall.h>
+#include <asm/syscalls.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
@@ -33,31 +33,14 @@
 #include <asm/vdso_datapage.h>
 #include <asm/setup.h>
 
+static_assert(__VDSO_PAGES == VDSO_NR_PAGES);
+
 /* The alignment of the vDSO */
 #define VDSO_ALIGNMENT	(1 << 16)
 
 extern char vdso32_start, vdso32_end;
 extern char vdso64_start, vdso64_end;
 
-long sys_ni_syscall(void);
-
-/*
- * The vdso data page (aka. systemcfg for old ppc64 fans) is here.
- * Once the early boot kernel code no longer needs to muck around
- * with it, it will become dynamically allocated
- */
-static union {
-	struct vdso_arch_data	data;
-	u8			page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_arch_data *vdso_data = &vdso_data_store.data;
-
-enum vvar_pages {
-	VVAR_DATA_PAGE_OFFSET,
-	VVAR_TIMENS_PAGE_OFFSET,
-	VVAR_NR_PAGES,
-};
-
 static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma,
 		       unsigned long text_size)
 {
@@ -81,88 +64,33 @@ static int vdso64_mremap(const struct vm_special_mapping *sm, struct vm_area_str
 	return vdso_mremap(sm, new_vma, &vdso64_end - &vdso64_start);
 }
 
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf);
+static void vdso_close(const struct vm_special_mapping *sm, struct vm_area_struct *vma)
+{
+	struct mm_struct *mm = vma->vm_mm;
 
-static struct vm_special_mapping vvar_spec __ro_after_init = {
-	.name = "[vvar]",
-	.fault = vvar_fault,
-};
+	/*
+	 * close() is called for munmap() but also for mremap(). In the mremap()
+	 * case the vdso pointer has already been updated by the mremap() hook
+	 * above, so it must not be set to NULL here.
+	 */
+	if (vma->vm_start != (unsigned long)mm->context.vdso)
+		return;
+
+	mm->context.vdso = NULL;
+}
 
 static struct vm_special_mapping vdso32_spec __ro_after_init = {
 	.name = "[vdso]",
 	.mremap = vdso32_mremap,
+	.close = vdso_close,
 };
 
 static struct vm_special_mapping vdso64_spec __ro_after_init = {
 	.name = "[vdso]",
 	.mremap = vdso64_mremap,
+	.close = vdso_close,
 };
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return ((struct vdso_arch_data *)vvar_page)->data;
-}
-
-/*
- * 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;
-	VMA_ITERATOR(vmi, mm, 0);
-	struct vm_area_struct *vma;
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vvar_spec))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#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 = virt_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 = virt_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
 /*
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
@@ -171,7 +99,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 {
 	unsigned long vdso_size, vdso_base, mappings_size;
 	struct vm_special_mapping *vdso_spec;
-	unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE;
+	unsigned long vvar_size = VDSO_NR_PAGES * PAGE_SIZE;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 
@@ -197,16 +125,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 	/* Add required alignment. */
 	vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
 
-	/*
-	 * Put vDSO base into mm struct. We need to do this before calling
-	 * install_special_mapping or the perf counter mmap tracking code
-	 * will fail to recognise it as a vDSO.
-	 */
-	mm->context.vdso = (void __user *)vdso_base + vvar_size;
-
-	vma = _install_special_mapping(mm, vdso_base, vvar_size,
-				       VM_READ | VM_MAYREAD | VM_IO |
-				       VM_DONTDUMP | VM_PFNMAP, &vvar_spec);
+	vma = vdso_install_vvar_mapping(mm, vdso_base);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -223,10 +142,15 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 	vma = _install_special_mapping(mm, vdso_base + vvar_size, vdso_size,
 				       VM_READ | VM_EXEC | VM_MAYREAD |
 				       VM_MAYWRITE | VM_MAYEXEC, vdso_spec);
-	if (IS_ERR(vma))
+	if (IS_ERR(vma)) {
 		do_munmap(mm, vdso_base, vvar_size, NULL);
+		return PTR_ERR(vma);
+	}
+
+	// Now that the mappings are in place, set the mm VDSO pointer
+	mm->context.vdso = (void __user *)vdso_base + vvar_size;
 
-	return PTR_ERR_OR_ZERO(vma);
+	return 0;
 }
 
 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
@@ -240,8 +164,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		return -EINTR;
 
 	rc = __arch_setup_additional_pages(bprm, uses_interp);
-	if (rc)
-		mm->context.vdso = NULL;
 
 	mmap_write_unlock(mm);
 	return rc;
@@ -283,10 +205,10 @@ static void __init vdso_setup_syscall_map(void)
 
 	for (i = 0; i < NR_syscalls; i++) {
 		if (sys_call_table[i] != (void *)&sys_ni_syscall)
-			vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+			vdso_k_arch_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
 		if (IS_ENABLED(CONFIG_COMPAT) &&
 		    compat_sys_call_table[i] != (void *)&sys_ni_syscall)
-			vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+			vdso_k_arch_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
 	}
 }
 
@@ -336,29 +258,10 @@ static struct page ** __init vdso_setup_pages(void *start, void *end)
 static int __init vdso_init(void)
 {
 #ifdef CONFIG_PPC64
-	/*
-	 * Fill up the "systemcfg" stuff for backward compatibility
-	 */
-	strcpy((char *)vdso_data->eye_catcher, "SYSTEMCFG:PPC64");
-	vdso_data->version.major = SYSTEMCFG_MAJOR;
-	vdso_data->version.minor = SYSTEMCFG_MINOR;
-	vdso_data->processor = mfspr(SPRN_PVR);
-	/*
-	 * Fake the old platform number for pSeries and add
-	 * in LPAR bit if necessary
-	 */
-	vdso_data->platform = 0x100;
-	if (firmware_has_feature(FW_FEATURE_LPAR))
-		vdso_data->platform |= 1;
-	vdso_data->physicalMemorySize = memblock_phys_mem_size();
-	vdso_data->dcache_size = ppc64_caches.l1d.size;
-	vdso_data->dcache_line_size = ppc64_caches.l1d.line_size;
-	vdso_data->icache_size = ppc64_caches.l1i.size;
-	vdso_data->icache_line_size = ppc64_caches.l1i.line_size;
-	vdso_data->dcache_block_size = ppc64_caches.l1d.block_size;
-	vdso_data->icache_block_size = ppc64_caches.l1i.block_size;
-	vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
-	vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
+	vdso_k_arch_data->dcache_block_size = ppc64_caches.l1d.block_size;
+	vdso_k_arch_data->icache_block_size = ppc64_caches.l1i.block_size;
+	vdso_k_arch_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
+	vdso_k_arch_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
 #endif /* CONFIG_PPC64 */
 
 	vdso_setup_syscall_map();
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index 4c3f34485f08..8834dfe9d727 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -3,35 +3,26 @@
 # List of files in the vdso, has to be asm only for now
 
 # Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
 
 obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o
 obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o
 
+obj-vdso32 += getrandom-32.o vgetrandom-chacha-32.o
+obj-vdso64 += getrandom-64.o vgetrandom-chacha-64.o
+
 ifneq ($(c-gettimeofday-y),)
   CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y)
-  CFLAGS_vgettimeofday-32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
-  CFLAGS_vgettimeofday-32.o += $(call cc-option, -fno-stack-protector)
-  CFLAGS_vgettimeofday-32.o += -DDISABLE_BRANCH_PROFILING
-  CFLAGS_vgettimeofday-32.o += -ffreestanding -fasynchronous-unwind-tables
-  CFLAGS_REMOVE_vgettimeofday-32.o = $(CC_FLAGS_FTRACE)
-  CFLAGS_REMOVE_vgettimeofday-32.o += -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc
-  # This flag is supported by clang for 64-bit but not 32-bit so it will cause
-  # an unused command line flag warning for this file.
-  ifdef CONFIG_CC_IS_CLANG
-  CFLAGS_REMOVE_vgettimeofday-32.o += -fno-stack-clash-protection
-  endif
-  CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y)
-  CFLAGS_vgettimeofday-64.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
-  CFLAGS_vgettimeofday-64.o += $(call cc-option, -fno-stack-protector)
-  CFLAGS_vgettimeofday-64.o += -DDISABLE_BRANCH_PROFILING
-  CFLAGS_vgettimeofday-64.o += -ffreestanding -fasynchronous-unwind-tables
-  CFLAGS_REMOVE_vgettimeofday-64.o = $(CC_FLAGS_FTRACE)
 # Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true
 # by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is
 # compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code
 # generation is minimal, it will just use r29 instead.
-  CFLAGS_vgettimeofday-64.o += $(call cc-option, -ffixed-r30)
+  CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y) $(call cc-option, -ffixed-r30)
+endif
+
+ifneq ($(c-getrandom-y),)
+  CFLAGS_vgetrandom-32.o += -include $(c-getrandom-y)
+  CFLAGS_vgetrandom-64.o += -include $(c-getrandom-y)
 endif
 
 # Build rules
@@ -42,24 +33,36 @@ else
     VDSOCC := $(CC)
 endif
 
-targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o
+targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o vgetrandom-32.o
+targets += crtsavres-32.o
 obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
-targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o
+targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o vgetrandom-64.o
 obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
 
-GCOV_PROFILE := n
-KCOV_INSTRUMENT := n
-UBSAN_SANITIZE := n
-KASAN_SANITIZE := n
-KCSAN_SANITIZE := n
-
-ccflags-y := -fno-common -fno-builtin
-ldflags-y := -Wl,--hash-style=both -nostdlib -shared -z noexecstack
+ccflags-y := -fno-common -fno-builtin -DBUILD_VDSO
+ccflags-y += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ccflags-y += $(call cc-option, -fno-stack-protector)
+ccflags-y += -DDISABLE_BRANCH_PROFILING
+ccflags-y += -ffreestanding -fasynchronous-unwind-tables
+ccflags-remove-y := $(CC_FLAGS_FTRACE)
+ldflags-y := -Wl,--hash-style=both -nostdlib -shared -z noexecstack $(CLANG_FLAGS)
 ldflags-$(CONFIG_LD_IS_LLD) += $(call cc-option,--ld-path=$(LD),-fuse-ld=lld)
+ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL)
+
 # Filter flags that clang will warn are unused for linking
-ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CFLAGS))
+ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 
 CC32FLAGS := -m32
+CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc -mpcrel
+ifdef CONFIG_CC_IS_CLANG
+# This flag is supported by clang for 64-bit but not 32-bit so it will cause
+# an unused command line flag warning for this file.
+CC32FLAGSREMOVE += -fno-stack-clash-protection
+# -mstack-protector-guard values from the 64-bit build are not valid for the
+# 32-bit one. clang validates the values passed to these arguments during
+# parsing, even when -fno-stack-protector is passed afterwards.
+CC32FLAGSREMOVE += -mstack-protector-guard%
+endif
 LD32FLAGS := -Wl,-soname=linux-vdso32.so.1
 AS32FLAGS := -D__VDSO32__
 
@@ -69,29 +72,35 @@ AS64FLAGS := -D__VDSO64__
 targets += vdso32.lds
 CPPFLAGS_vdso32.lds += -P -C -Upowerpc
 targets += vdso64.lds
-CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+CPPFLAGS_vdso64.lds += -P -C
 
 # link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE
+$(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o $(obj)/vgetrandom-32.o $(obj)/crtsavres-32.o FORCE
 	$(call if_changed,vdso32ld_and_check)
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE
+$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o $(obj)/vgetrandom-64.o FORCE
 	$(call if_changed,vdso64ld_and_check)
 
 # assembly rules for the .S files
 $(obj-vdso32): %-32.o: %.S FORCE
 	$(call if_changed_dep,vdso32as)
+$(obj)/crtsavres-32.o: %-32.o: $(srctree)/arch/powerpc/lib/crtsavres.S FORCE
+	$(call if_changed_dep,vdso32as)
 $(obj)/vgettimeofday-32.o: %-32.o: %.c FORCE
 	$(call if_changed_dep,vdso32cc)
+$(obj)/vgetrandom-32.o: %-32.o: %.c FORCE
+	$(call if_changed_dep,vdso32cc)
 $(obj-vdso64): %-64.o: %.S FORCE
 	$(call if_changed_dep,vdso64as)
 $(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE
 	$(call if_changed_dep,cc_o_c)
+$(obj)/vgetrandom-64.o: %-64.o: %.c FORCE
+	$(call if_changed_dep,cc_o_c)
 
 # Generate VDSO offsets using helper script
-gen-vdso32sym := $(srctree)/$(src)/gen_vdso32_offsets.sh
+gen-vdso32sym := $(src)/gen_vdso32_offsets.sh
 quiet_cmd_vdso32sym = VDSO32SYM $@
       cmd_vdso32sym = $(NM) $< | $(gen-vdso32sym) | LC_ALL=C sort > $@
-gen-vdso64sym := $(srctree)/$(src)/gen_vdso64_offsets.sh
+gen-vdso64sym := $(src)/gen_vdso64_offsets.sh
 quiet_cmd_vdso64sym = VDSO64SYM $@
       cmd_vdso64sym = $(NM) $< | $(gen-vdso64sym) | LC_ALL=C sort > $@
 
@@ -106,11 +115,9 @@ quiet_cmd_vdso32ld_and_check = VDSO32L $@
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) $(AS32FLAGS) -c -o $@ $<
 quiet_cmd_vdso32cc = VDSO32C $@
-      cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $<
+      cmd_vdso32cc = $(VDSOCC) $(filter-out $(CC32FLAGSREMOVE), $(c_flags)) $(CC32FLAGS) -c -o $@ $<
 
 quiet_cmd_vdso64ld_and_check = VDSO64L $@
       cmd_vdso64ld_and_check = $(VDSOCC) $(ldflags-y) $(LD64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
 quiet_cmd_vdso64as = VDSO64A $@
       cmd_vdso64as = $(VDSOCC) $(a_flags) $(AS64FLAGS) -c -o $@ $<
-
-OBJECT_FILES_NON_STANDARD := y
diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S
index 0085ae464dac..488d3ade11e6 100644
--- a/arch/powerpc/kernel/vdso/cacheflush.S
+++ b/arch/powerpc/kernel/vdso/cacheflush.S
@@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 #ifdef CONFIG_PPC64
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r10
+	get_datapage	r10 vdso_u_arch_data
 	mtlr	r12
   .cfi_restore	lr
 #endif
diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S
index db8e167f0166..d23b2e8e2a34 100644
--- a/arch/powerpc/kernel/vdso/datapage.S
+++ b/arch/powerpc/kernel/vdso/datapage.S
@@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	mflr	r12
   .cfi_register lr,r12
 	mr.	r4,r3
-	get_datapage	r3
+	get_datapage	r3 vdso_u_arch_data
 	mtlr	r12
 #ifdef __powerpc64__
 	addi	r3,r3,CFG_SYSCALL_MAP64
@@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	get_datapage	r3
+	get_datapage	r3 vdso_u_arch_data
 #ifndef __powerpc64__
 	lwz	r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
 #endif
diff --git a/arch/powerpc/kernel/vdso/getrandom.S b/arch/powerpc/kernel/vdso/getrandom.S
new file mode 100644
index 000000000000..a80d9fb436f7
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/getrandom.S
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Userland implementation of getrandom() for processes
+ * for use in the vDSO
+ *
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+/*
+ * The macro sets two stack frames, one for the caller and one for the callee
+ * because there are no requirement for the caller to set a stack frame when
+ * calling VDSO so it may have omitted to set one, especially on PPC64
+ */
+
+.macro cvdso_call funct
+  .cfi_startproc
+	PPC_STLU	r1, -PPC_MIN_STKFRM(r1)
+  .cfi_adjust_cfa_offset PPC_MIN_STKFRM
+	mflr		r0
+	PPC_STLU	r1, -PPC_MIN_STKFRM(r1)
+  .cfi_adjust_cfa_offset PPC_MIN_STKFRM
+	PPC_STL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+  .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF
+#ifdef __powerpc64__
+	PPC_STL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
+  .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
+#endif
+	bl		CFUNC(DOTSYM(\funct))
+	PPC_LL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+#ifdef __powerpc64__
+	PPC_LL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
+  .cfi_restore r2
+#endif
+	cmpwi		r3, 0
+	mtlr		r0
+	addi		r1, r1, 2 * PPC_MIN_STKFRM
+  .cfi_restore lr
+  .cfi_def_cfa_offset 0
+	crclr		so
+	bgelr+
+	crset		so
+	neg		r3, r3
+	blr
+  .cfi_endproc
+.endm
+
+	.text
+V_FUNCTION_BEGIN(__kernel_getrandom)
+	cvdso_call __c_kernel_getrandom
+V_FUNCTION_END(__kernel_getrandom)
diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S
index 48fc6658053a..79c967212444 100644
--- a/arch/powerpc/kernel/vdso/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso/gettimeofday.S
@@ -32,17 +32,12 @@
 	PPC_STL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
   .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
 #endif
-	get_datapage	r5
 	.ifeq	\call_time
-	addi		r5, r5, VDSO_DATA_OFFSET
+		get_datapage	r5 vdso_u_time_data
 	.else
-	addi		r4, r5, VDSO_DATA_OFFSET
+		get_datapage	r4 vdso_u_time_data
 	.endif
-#ifdef __powerpc64__
 	bl		CFUNC(DOTSYM(\funct))
-#else
-	bl		\funct
-#endif
 	PPC_LL		r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
 #ifdef __powerpc64__
 	PPC_LL		r2, PPC_MIN_STKFRM + STK_GOT(r1)
@@ -118,16 +113,3 @@ V_FUNCTION_END(__kernel_clock_getres)
 V_FUNCTION_BEGIN(__kernel_time)
 	cvdso_call __c_kernel_time call_time=1
 V_FUNCTION_END(__kernel_time)
-
-/* Routines for restoring integer registers, called by the compiler.  */
-/* Called with r11 pointing to the stack header word of the caller of the */
-/* function, just beyond the end of the integer restore area.  */
-#ifndef __powerpc64__
-_GLOBAL(_restgpr_31_x)
-_GLOBAL(_rest32gpr_31_x)
-	lwz	r0,4(r11)
-	lwz	r31,-4(r11)
-	mtlr	r0
-	mr	r1,r11
-	blr
-#endif
diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S
index bc0be274a9ac..72a1012b8a20 100644
--- a/arch/powerpc/kernel/vdso/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso32.lds.S
@@ -6,6 +6,7 @@
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 #ifdef __LITTLE_ENDIAN__
 OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common)
 
 SECTIONS
 {
-	PROVIDE(_vdso_datapage = . - 2 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash          	: { *(.hash) }			:text
@@ -74,6 +76,8 @@ SECTIONS
 	.got		: { *(.got) }			:text
 	.plt		: { *(.plt) }
 
+	.rela.dyn	: { *(.rela .rela*) }
+
 	_end = .;
 	__end = .;
 	PROVIDE(end = .);
@@ -83,9 +87,11 @@ SECTIONS
 
 	/DISCARD/	: {
 		*(.note.GNU-stack)
+		*(*.EMB.apuinfo)
+		*(.branch_lt)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
-		*(.got1)
+		*(.got1 .glink .iplt)
 	}
 }
 
@@ -126,6 +132,7 @@ VERSION
 #if defined(CONFIG_PPC64) || !defined(CONFIG_SMP)
 		__kernel_getcpu;
 #endif
+		__kernel_getrandom;
 
 	local: *;
 	};
diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S
index 744ae5363e6c..32102a05eaa7 100644
--- a/arch/powerpc/kernel/vdso/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso/vdso64.lds.S
@@ -6,6 +6,7 @@
 #include <asm/vdso.h>
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
+#include <vdso/datapage.h>
 
 #ifdef __LITTLE_ENDIAN__
 OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle")
@@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common64)
 
 SECTIONS
 {
-	PROVIDE(_vdso_datapage = . - 2 * PAGE_SIZE);
+	VDSO_VVAR_SYMS
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
@@ -32,7 +34,7 @@ SECTIONS
 	. = ALIGN(16);
 	.text		: {
 		*(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*)
-		*(.sfpr .glink)
+		*(.sfpr)
 	}						:text
 	PROVIDE(__etext = .);
 	PROVIDE(_etext = .);
@@ -69,7 +71,7 @@ SECTIONS
 	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
 	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
 	.gcc_except_table : { *(.gcc_except_table) }
-	.rela.dyn ALIGN(8) : { *(.rela.dyn) }
+	.rela.dyn ALIGN(8) : { *(.rela .rela*) }
 
 	.got ALIGN(8)	: { *(.got .toc) }
 
@@ -81,10 +83,12 @@ SECTIONS
 
 	/DISCARD/	: {
 		*(.note.GNU-stack)
+		*(*.EMB.apuinfo)
 		*(.branch_lt)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
 		*(.opd)
+		*(.glink .iplt .plt)
 	}
 }
 
@@ -121,6 +125,7 @@ VERSION
 		__kernel_sigtramp_rt64;
 		__kernel_getcpu;
 		__kernel_time;
+		__kernel_getrandom;
 
 	local: *;
 	};
diff --git a/arch/powerpc/kernel/vdso/vgetrandom-chacha.S b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S
new file mode 100644
index 000000000000..7f9061a9e8b4
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S
@@ -0,0 +1,365 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/ppc_asm.h>
+
+#define	dst_bytes	r3
+#define	key		r4
+#define	counter		r5
+#define	nblocks		r6
+
+#define	idx_r0		r0
+#define	val4		r4
+
+#define	const0		0x61707865
+#define	const1		0x3320646e
+#define	const2		0x79622d32
+#define	const3		0x6b206574
+
+#define	key0		r5
+#define	key1		r6
+#define	key2		r7
+#define	key3		r8
+#define	key4		r9
+#define	key5		r10
+#define	key6		r11
+#define	key7		r12
+
+#define	counter0	r14
+#define	counter1	r15
+
+#define	state0		r16
+#define	state1		r17
+#define	state2		r18
+#define	state3		r19
+#define	state4		r20
+#define	state5		r21
+#define	state6		r22
+#define	state7		r23
+#define	state8		r24
+#define	state9		r25
+#define	state10		r26
+#define	state11		r27
+#define	state12		r28
+#define	state13		r29
+#define	state14		r30
+#define	state15		r31
+
+.macro quarterround4 a1 b1 c1 d1 a2 b2 c2 d2 a3 b3 c3 d3 a4 b4 c4 d4
+	add	\a1, \a1, \b1
+	add	\a2, \a2, \b2
+	add	\a3, \a3, \b3
+	add	\a4, \a4, \b4
+	xor	\d1, \d1, \a1
+	xor	\d2, \d2, \a2
+	xor	\d3, \d3, \a3
+	xor	\d4, \d4, \a4
+	rotlwi	\d1, \d1, 16
+	rotlwi	\d2, \d2, 16
+	rotlwi	\d3, \d3, 16
+	rotlwi	\d4, \d4, 16
+	add	\c1, \c1, \d1
+	add	\c2, \c2, \d2
+	add	\c3, \c3, \d3
+	add	\c4, \c4, \d4
+	xor	\b1, \b1, \c1
+	xor	\b2, \b2, \c2
+	xor	\b3, \b3, \c3
+	xor	\b4, \b4, \c4
+	rotlwi	\b1, \b1, 12
+	rotlwi	\b2, \b2, 12
+	rotlwi	\b3, \b3, 12
+	rotlwi	\b4, \b4, 12
+	add	\a1, \a1, \b1
+	add	\a2, \a2, \b2
+	add	\a3, \a3, \b3
+	add	\a4, \a4, \b4
+	xor	\d1, \d1, \a1
+	xor	\d2, \d2, \a2
+	xor	\d3, \d3, \a3
+	xor	\d4, \d4, \a4
+	rotlwi	\d1, \d1, 8
+	rotlwi	\d2, \d2, 8
+	rotlwi	\d3, \d3, 8
+	rotlwi	\d4, \d4, 8
+	add	\c1, \c1, \d1
+	add	\c2, \c2, \d2
+	add	\c3, \c3, \d3
+	add	\c4, \c4, \d4
+	xor	\b1, \b1, \c1
+	xor	\b2, \b2, \c2
+	xor	\b3, \b3, \c3
+	xor	\b4, \b4, \c4
+	rotlwi	\b1, \b1, 7
+	rotlwi	\b2, \b2, 7
+	rotlwi	\b3, \b3, 7
+	rotlwi	\b4, \b4, 7
+.endm
+
+#define QUARTERROUND4(a1,b1,c1,d1,a2,b2,c2,d2,a3,b3,c3,d3,a4,b4,c4,d4) \
+	quarterround4 state##a1 state##b1 state##c1 state##d1 \
+		      state##a2 state##b2 state##c2 state##d2 \
+		      state##a3 state##b3 state##c3 state##d3 \
+		      state##a4 state##b4 state##c4 state##d4
+
+/*
+ * Very basic 32 bits implementation of ChaCha20. Produces a given positive number
+ * of blocks of output with a nonce of 0, taking an input key and 8-byte
+ * counter. Importantly does not spill to the stack. Its arguments are:
+ *
+ *	r3: output bytes
+ *	r4: 32-byte key input
+ *	r5: 8-byte counter input/output (saved on stack)
+ *	r6: number of 64-byte blocks to write to output
+ *
+ *	r0: counter of blocks (initialised with r6)
+ *	r4: Value '4' after key has been read.
+ *	r5-r12: key
+ *	r14-r15: counter
+ *	r16-r31: state
+ */
+SYM_FUNC_START(__arch_chacha20_blocks_nostack)
+#ifdef __powerpc64__
+	std	counter, -216(r1)
+
+	std	r14, -144(r1)
+	std	r15, -136(r1)
+	std	r16, -128(r1)
+	std	r17, -120(r1)
+	std	r18, -112(r1)
+	std	r19, -104(r1)
+	std	r20, -96(r1)
+	std	r21, -88(r1)
+	std	r22, -80(r1)
+	std	r23, -72(r1)
+	std	r24, -64(r1)
+	std	r25, -56(r1)
+	std	r26, -48(r1)
+	std	r27, -40(r1)
+	std	r28, -32(r1)
+	std	r29, -24(r1)
+	std	r30, -16(r1)
+	std	r31, -8(r1)
+#else
+	stwu	r1, -96(r1)
+	stw	counter, 20(r1)
+#ifdef __BIG_ENDIAN__
+	stmw	r14, 24(r1)
+#else
+	stw	r14, 24(r1)
+	stw	r15, 28(r1)
+	stw	r16, 32(r1)
+	stw	r17, 36(r1)
+	stw	r18, 40(r1)
+	stw	r19, 44(r1)
+	stw	r20, 48(r1)
+	stw	r21, 52(r1)
+	stw	r22, 56(r1)
+	stw	r23, 60(r1)
+	stw	r24, 64(r1)
+	stw	r25, 68(r1)
+	stw	r26, 72(r1)
+	stw	r27, 76(r1)
+	stw	r28, 80(r1)
+	stw	r29, 84(r1)
+	stw	r30, 88(r1)
+	stw	r31, 92(r1)
+#endif
+#endif	/* __powerpc64__ */
+
+	lwz	counter0, 0(counter)
+	lwz	counter1, 4(counter)
+#ifdef __powerpc64__
+	rldimi	counter0, counter1, 32, 0
+#endif
+	mr	idx_r0, nblocks
+	subi	dst_bytes, dst_bytes, 4
+
+	lwz	key0, 0(key)
+	lwz	key1, 4(key)
+	lwz	key2, 8(key)
+	lwz	key3, 12(key)
+	lwz	key4, 16(key)
+	lwz	key5, 20(key)
+	lwz	key6, 24(key)
+	lwz	key7, 28(key)
+
+	li	val4, 4
+.Lblock:
+	li	r31, 10
+
+	lis	state0, const0@ha
+	lis	state1, const1@ha
+	lis	state2, const2@ha
+	lis	state3, const3@ha
+	addi	state0, state0, const0@l
+	addi	state1, state1, const1@l
+	addi	state2, state2, const2@l
+	addi	state3, state3, const3@l
+
+	mtctr	r31
+
+	mr	state4, key0
+	mr	state5, key1
+	mr	state6, key2
+	mr	state7, key3
+	mr	state8, key4
+	mr	state9, key5
+	mr	state10, key6
+	mr	state11, key7
+
+	mr	state12, counter0
+	mr	state13, counter1
+
+	li	state14, 0
+	li	state15, 0
+
+.Lpermute:
+	QUARTERROUND4( 0, 4, 8,12, 1, 5, 9,13, 2, 6,10,14, 3, 7,11,15)
+	QUARTERROUND4( 0, 5,10,15, 1, 6,11,12, 2, 7, 8,13, 3, 4, 9,14)
+
+	bdnz	.Lpermute
+
+	addis	state0, state0, const0@ha
+	addis	state1, state1, const1@ha
+	addis	state2, state2, const2@ha
+	addis	state3, state3, const3@ha
+	addi	state0, state0, const0@l
+	addi	state1, state1, const1@l
+	addi	state2, state2, const2@l
+	addi	state3, state3, const3@l
+
+	add	state4, state4, key0
+	add	state5, state5, key1
+	add	state6, state6, key2
+	add	state7, state7, key3
+	add	state8, state8, key4
+	add	state9, state9, key5
+	add	state10, state10, key6
+	add	state11, state11, key7
+
+	add	state12, state12, counter0
+	add	state13, state13, counter1
+
+#ifdef __BIG_ENDIAN__
+	stwbrx	state0, val4, dst_bytes
+	addi	dst_bytes, dst_bytes, 8
+	stwbrx	state1, 0, dst_bytes
+	stwbrx	state2, val4, dst_bytes
+	addi	dst_bytes, dst_bytes, 8
+	stwbrx	state3, 0, dst_bytes
+	stwbrx	state4, val4, dst_bytes
+	addi	dst_bytes, dst_bytes, 8
+	stwbrx	state5, 0, dst_bytes
+	stwbrx	state6, val4, dst_bytes
+	addi	dst_bytes, dst_bytes, 8
+	stwbrx	state7, 0, dst_bytes
+	stwbrx	state8, val4, dst_bytes
+	addi	dst_bytes, dst_bytes, 8
+	stwbrx	state9, 0, dst_bytes
+	stwbrx	state10, val4, dst_bytes
+	addi	dst_bytes, dst_bytes, 8
+	stwbrx	state11, 0, dst_bytes
+	stwbrx	state12, val4, dst_bytes
+	addi	dst_bytes, dst_bytes, 8
+	stwbrx	state13, 0, dst_bytes
+	stwbrx	state14, val4, dst_bytes
+	addi	dst_bytes, dst_bytes, 8
+	stwbrx	state15, 0, dst_bytes
+#else
+	stw	state0, 4(dst_bytes)
+	stw	state1, 8(dst_bytes)
+	stw	state2, 12(dst_bytes)
+	stw	state3, 16(dst_bytes)
+	stw	state4, 20(dst_bytes)
+	stw	state5, 24(dst_bytes)
+	stw	state6, 28(dst_bytes)
+	stw	state7, 32(dst_bytes)
+	stw	state8, 36(dst_bytes)
+	stw	state9, 40(dst_bytes)
+	stw	state10, 44(dst_bytes)
+	stw	state11, 48(dst_bytes)
+	stw	state12, 52(dst_bytes)
+	stw	state13, 56(dst_bytes)
+	stw	state14, 60(dst_bytes)
+	stwu	state15, 64(dst_bytes)
+#endif
+
+	subic.	idx_r0, idx_r0, 1	/* subi. can't use r0 as source */
+
+#ifdef __powerpc64__
+	addi	counter0, counter0, 1
+	srdi	counter1, counter0, 32
+#else
+	addic	counter0, counter0, 1
+	addze	counter1, counter1
+#endif
+
+	bne	.Lblock
+
+#ifdef __powerpc64__
+	ld	counter, -216(r1)
+#else
+	lwz	counter, 20(r1)
+#endif
+	stw	counter0, 0(counter)
+	stw	counter1, 4(counter)
+
+	li	r6, 0
+	li	r7, 0
+	li	r8, 0
+	li	r9, 0
+	li	r10, 0
+	li	r11, 0
+	li	r12, 0
+
+#ifdef __powerpc64__
+	ld	r14, -144(r1)
+	ld	r15, -136(r1)
+	ld	r16, -128(r1)
+	ld	r17, -120(r1)
+	ld	r18, -112(r1)
+	ld	r19, -104(r1)
+	ld	r20, -96(r1)
+	ld	r21, -88(r1)
+	ld	r22, -80(r1)
+	ld	r23, -72(r1)
+	ld	r24, -64(r1)
+	ld	r25, -56(r1)
+	ld	r26, -48(r1)
+	ld	r27, -40(r1)
+	ld	r28, -32(r1)
+	ld	r29, -24(r1)
+	ld	r30, -16(r1)
+	ld	r31, -8(r1)
+#else
+#ifdef __BIG_ENDIAN__
+	lmw	r14, 24(r1)
+#else
+	lwz	r14, 24(r1)
+	lwz	r15, 28(r1)
+	lwz	r16, 32(r1)
+	lwz	r17, 36(r1)
+	lwz	r18, 40(r1)
+	lwz	r19, 44(r1)
+	lwz	r20, 48(r1)
+	lwz	r21, 52(r1)
+	lwz	r22, 56(r1)
+	lwz	r23, 60(r1)
+	lwz	r24, 64(r1)
+	lwz	r25, 68(r1)
+	lwz	r26, 72(r1)
+	lwz	r27, 76(r1)
+	lwz	r28, 80(r1)
+	lwz	r29, 84(r1)
+	lwz	r30, 88(r1)
+	lwz	r31, 92(r1)
+#endif
+	addi	r1, r1, 96
+#endif	/* __powerpc64__ */
+	blr
+SYM_FUNC_END(__arch_chacha20_blocks_nostack)
diff --git a/arch/powerpc/kernel/vdso/vgetrandom.c b/arch/powerpc/kernel/vdso/vgetrandom.c
new file mode 100644
index 000000000000..cc79b960a541
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/vgetrandom.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Powerpc userspace implementation of getrandom()
+ *
+ * Copyright (C) 2024 Christophe Leroy <christophe.leroy@csgroup.eu>, CS GROUP France
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+ssize_t __c_kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state,
+			     size_t opaque_len)
+{
+	return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len);
+}
diff --git a/arch/powerpc/kernel/vdso/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c
index 55a287c9a736..6f5167d81af5 100644
--- a/arch/powerpc/kernel/vdso/vgettimeofday.c
+++ b/arch/powerpc/kernel/vdso/vgettimeofday.c
@@ -7,43 +7,43 @@
 
 #ifdef __powerpc64__
 int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
-			     const struct vdso_data *vd)
+			     const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_getres_data(vd, clock_id, res);
 }
 #else
 int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
-			     const struct vdso_data *vd)
+			     const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime32_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
-			       const struct vdso_data *vd)
+			       const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_gettime_data(vd, clock, ts);
 }
 
 int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_clock_getres_time32_data(vd, clock_id, res);
 }
 #endif
 
 int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
-			    const struct vdso_data *vd)
+			    const struct vdso_time_data *vd)
 {
 	return __cvdso_gettimeofday_data(vd, tv, tz);
 }
 
-__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_time_data *vd)
 {
 	return __cvdso_time_data(vd, time);
 }
diff --git a/arch/powerpc/kernel/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32_wrapper.S
index 10f92f265d51..20bca3548b44 100644
--- a/arch/powerpc/kernel/vdso32_wrapper.S
+++ b/arch/powerpc/kernel/vdso32_wrapper.S
@@ -2,7 +2,7 @@
 #include <linux/linkage.h>
 #include <asm/page.h>
 
-	__PAGE_ALIGNED_DATA
+	.section ".data..ro_after_init", "aw"
 
 	.globl vdso32_start, vdso32_end
 	.balign PAGE_SIZE
diff --git a/arch/powerpc/kernel/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64_wrapper.S
index 839d1a61411d..1912936fa227 100644
--- a/arch/powerpc/kernel/vdso64_wrapper.S
+++ b/arch/powerpc/kernel/vdso64_wrapper.S
@@ -2,7 +2,7 @@
 #include <linux/linkage.h>
 #include <asm/page.h>
 
-	__PAGE_ALIGNED_DATA
+	.section ".data..ro_after_init", "aw"
 
 	.globl vdso64_start, vdso64_end
 	.balign PAGE_SIZE
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index fcc0ad6d9c7b..80b3f6e476b6 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
@@ -8,7 +9,6 @@
 #include <asm/thread_info.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
-#include <asm/export.h>
 #include <asm/asm-compat.h>
 
 /*
@@ -33,6 +33,7 @@ _GLOBAL(store_vr_state)
 	mfvscr	v0
 	li	r4, VRSTATE_VSCR
 	stvx	v0, r4, r3
+	lvx	v0, 0, r3
 	blr
 EXPORT_SYMBOL(store_vr_state)
 
@@ -109,6 +110,7 @@ _GLOBAL(save_altivec)
 	mfvscr	v0
 	li	r4,VRSTATE_VSCR
 	stvx	v0,r4,r7
+	lvx	v0,0,r7
 	blr
 
 #ifdef CONFIG_VSX
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 13614f0b269c..15850296c0a9 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -1,10 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifdef CONFIG_PPC64
-#define PROVIDE32(x)	PROVIDE(__unused__##x)
-#else
-#define PROVIDE32(x)	PROVIDE(x)
-#endif
-
 #define BSS_FIRST_SECTIONS *(.bss.prominit)
 #define EMITS_PT_NOTE
 #define RO_EXCEPTION_TABLE_ALIGN	0
@@ -107,9 +101,7 @@ SECTIONS
 #endif
 		/* careful! __ftr_alt_* sections need to be close to .text */
 		*(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text);
-#ifdef CONFIG_PPC64
 		*(.tramp.ftrace.text);
-#endif
 		NOINSTR_TEXT
 		SCHED_TEXT
 		LOCK_TEXT
@@ -125,13 +117,10 @@ SECTIONS
 		 */
 		*(.sfpr);
 		*(.text.asan.* .text.tsan.*)
-		MEM_KEEP(init.text)
-		MEM_KEEP(exit.text)
 	} :text
 
 	. = ALIGN(PAGE_SIZE);
 	_etext = .;
-	PROVIDE32 (etext = .);
 
 	/* Read-only data */
 	RO_DATA(PAGE_SIZE)
@@ -269,23 +258,22 @@ SECTIONS
 	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
 		_sinittext = .;
 		INIT_TEXT
-
+		*(.tramp.ftrace.init);
 		/*
 		 *.init.text might be RO so we must ensure this section ends on
 		 * a page boundary.
 		 */
 		. = ALIGN(PAGE_SIZE);
 		_einittext = .;
-#ifdef CONFIG_PPC64
-		*(.tramp.ftrace.init);
-#endif
 	} :text
 
 	/* .exit.text is discarded at runtime, not link time,
 	 * to deal with references from __bug_table
 	 */
 	.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+		__exittext_begin = .;
 		EXIT_TEXT
+		__exittext_end = .;
 	}
 
 	. = ALIGN(PAGE_SIZE);
@@ -342,7 +330,6 @@ SECTIONS
 	}
 	.hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) }
 	.gnu.hash : AT(ADDR(.gnu.hash) - LOAD_OFFSET) { *(.gnu.hash) }
-	.interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) }
 	.rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET)
 	{
 		__rela_dyn_start = .;
@@ -399,7 +386,6 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	_edata  =  .;
-	PROVIDE32 (edata = .);
 
 /*
  * And finally the bss
@@ -409,7 +395,6 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	_end = . ;
-	PROVIDE32 (end = .);
 
 	DWARF_DEBUG
 	ELF_DETAILS
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index dbcc4a793f0b..2429cb1c7baa 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -245,7 +245,7 @@ static void watchdog_smp_panic(int cpu)
 			__cpumask_clear_cpu(c, &wd_smp_cpus_ipi);
 		}
 	} else {
-		trigger_allbutself_cpu_backtrace();
+		trigger_allbutcpu_cpu_backtrace(cpu);
 		cpumask_clear(&wd_smp_cpus_ipi);
 	}
 
@@ -416,7 +416,7 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
 		xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi
 
 		if (sysctl_hardlockup_all_cpu_backtrace)
-			trigger_allbutself_cpu_backtrace();
+			trigger_allbutcpu_cpu_backtrace(cpu);
 
 		if (hardlockup_panic)
 			nmi_panic(regs, "Hard LOCKUP");
@@ -438,7 +438,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
 	int cpu = smp_processor_id();
 
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+	if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED))
 		return HRTIMER_NORESTART;
 
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
@@ -479,7 +479,7 @@ static void start_watchdog(void *arg)
 		return;
 	}
 
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+	if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED))
 		return;
 
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
@@ -495,8 +495,7 @@ static void start_watchdog(void *arg)
 
 	*this_cpu_ptr(&wd_timer_tb) = get_tb();
 
-	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtimer->function = watchdog_timer_fn;
+	hrtimer_setup(hrtimer, watchdog_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms),
 		      HRTIMER_MODE_REL_PINNED);
 }
@@ -546,7 +545,7 @@ static void watchdog_calc_timeouts(void)
 	wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5;
 }
 
-void watchdog_nmi_stop(void)
+void watchdog_hardlockup_stop(void)
 {
 	int cpu;
 
@@ -554,7 +553,7 @@ void watchdog_nmi_stop(void)
 		stop_watchdog_on_cpu(cpu);
 }
 
-void watchdog_nmi_start(void)
+void watchdog_hardlockup_start(void)
 {
 	int cpu;
 
@@ -566,7 +565,7 @@ void watchdog_nmi_start(void)
 /*
  * Invoked from core watchdog init.
  */
-int __init watchdog_nmi_probe(void)
+int __init watchdog_hardlockup_probe(void)
 {
 	int err;
 
@@ -582,7 +581,7 @@ int __init watchdog_nmi_probe(void)
 }
 
 #ifdef CONFIG_PPC_PSERIES
-void watchdog_nmi_set_timeout_pct(u64 pct)
+void watchdog_hardlockup_set_timeout_pct(u64 pct)
 {
 	pr_info("Set the NMI watchdog timeout factor to %llu%%\n", pct);
 	WRITE_ONCE(wd_timeout_pct, pct);
diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile
index 0c2abe7f9908..470eb0453e17 100644
--- a/arch/powerpc/kexec/Makefile
+++ b/arch/powerpc/kexec/Makefile
@@ -3,11 +3,13 @@
 # Makefile for the linux kernel.
 #
 
-obj-y				+= core.o crash.o core_$(BITS).o
+obj-y				+= core.o core_$(BITS).o ranges.o
 
 obj-$(CONFIG_PPC32)		+= relocate_32.o
 
-obj-$(CONFIG_KEXEC_FILE)	+= file_load.o ranges.o file_load_$(BITS).o elf_$(BITS).o
+obj-$(CONFIG_KEXEC_FILE)	+= file_load.o file_load_$(BITS).o elf_$(BITS).o
+obj-$(CONFIG_VMCORE_INFO)	+= vmcore_info.o
+obj-$(CONFIG_CRASH_DUMP)	+= crash.o
 
 # Disable GCOV, KCOV & sanitizers in odd or sensitive code
 GCOV_PROFILE_core_$(BITS).o := n
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index de64c7962991..104c05520bf0 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -22,61 +22,19 @@
 #include <asm/setup.h>
 #include <asm/firmware.h>
 
-void machine_kexec_mask_interrupts(void) {
-	unsigned int i;
-	struct irq_desc *desc;
-
-	for_each_irq_desc(i, desc) {
-		struct irq_chip *chip;
-
-		chip = irq_desc_get_chip(desc);
-		if (!chip)
-			continue;
-
-		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
-			chip->irq_eoi(&desc->irq_data);
-
-		if (chip->irq_mask)
-			chip->irq_mask(&desc->irq_data);
-
-		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
-			chip->irq_disable(&desc->irq_data);
-	}
-}
+#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG)
 
+#ifdef CONFIG_CRASH_DUMP
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	default_machine_crash_shutdown(regs);
 }
+#endif
 
 void machine_kexec_cleanup(struct kimage *image)
 {
 }
 
-void arch_crash_save_vmcoreinfo(void)
-{
-
-#ifdef CONFIG_NUMA
-	VMCOREINFO_SYMBOL(node_data);
-	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
-#endif
-#ifndef CONFIG_NUMA
-	VMCOREINFO_SYMBOL(contig_page_data);
-#endif
-#if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP)
-	VMCOREINFO_SYMBOL(vmemmap_list);
-	VMCOREINFO_SYMBOL(mmu_vmemmap_psize);
-	VMCOREINFO_SYMBOL(mmu_psize_defs);
-	VMCOREINFO_STRUCT_SIZE(vmemmap_backing);
-	VMCOREINFO_OFFSET(vmemmap_backing, list);
-	VMCOREINFO_OFFSET(vmemmap_backing, phys);
-	VMCOREINFO_OFFSET(vmemmap_backing, virt_addr);
-	VMCOREINFO_STRUCT_SIZE(mmu_psize_def);
-	VMCOREINFO_OFFSET(mmu_psize_def, shift);
-#endif
-	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
-}
-
 /*
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
@@ -101,38 +59,23 @@ void machine_kexec(struct kimage *image)
 	for(;;);
 }
 
-void __init reserve_crashkernel(void)
-{
-	unsigned long long crash_size, crash_base, total_mem_sz;
-	int ret;
-
-	total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
-	/* use common parsing */
-	ret = parse_crashkernel(boot_command_line, total_mem_sz,
-			&crash_size, &crash_base);
-	if (ret == 0 && crash_size > 0) {
-		crashk_res.start = crash_base;
-		crashk_res.end = crash_base + crash_size - 1;
-	}
-
-	if (crashk_res.end == crashk_res.start) {
-		crashk_res.start = crashk_res.end = 0;
-		return;
-	}
+#ifdef CONFIG_CRASH_RESERVE
 
-	/* We might have got these values via the command line or the
-	 * device tree, either way sanitise them now. */
+static unsigned long long crashk_cma_size;
 
-	crash_size = resource_size(&crashk_res);
+static unsigned long long __init get_crash_base(unsigned long long crash_base)
+{
 
 #ifndef CONFIG_NONSTATIC_KERNEL
-	if (crashk_res.start != KDUMP_KERNELBASE)
+	if (crash_base != KDUMP_KERNELBASE)
 		printk("Crash kernel location must be 0x%x\n",
 				KDUMP_KERNELBASE);
 
-	crashk_res.start = KDUMP_KERNELBASE;
+	return KDUMP_KERNELBASE;
 #else
-	if (!crashk_res.start) {
+	unsigned long long crash_base_align;
+
+	if (!crash_base) {
 #ifdef CONFIG_PPC64
 		/*
 		 * On the LPAR platform place the crash kernel to mid of
@@ -144,53 +87,57 @@ void __init reserve_crashkernel(void)
 		 * kernel starts at 128MB offset on other platforms.
 		 */
 		if (firmware_has_feature(FW_FEATURE_LPAR))
-			crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_512M);
+			crash_base = min_t(u64, ppc64_rma_size / 2, SZ_512M);
 		else
-			crashk_res.start = min_t(u64, ppc64_rma_size / 2, SZ_128M);
+			crash_base = min_t(u64, ppc64_rma_size / 2, SZ_128M);
 #else
-		crashk_res.start = KDUMP_KERNELBASE;
+		crash_base = KDUMP_KERNELBASE;
 #endif
 	}
 
-	crash_base = PAGE_ALIGN(crashk_res.start);
-	if (crash_base != crashk_res.start) {
-		printk("Crash kernel base must be aligned to 0x%lx\n",
-				PAGE_SIZE);
-		crashk_res.start = crash_base;
-	}
+	crash_base_align = PAGE_ALIGN(crash_base);
+	if (crash_base != crash_base_align)
+		pr_warn("Crash kernel base must be aligned to 0x%lx\n", PAGE_SIZE);
 
+	return crash_base_align;
 #endif
-	crash_size = PAGE_ALIGN(crash_size);
-	crashk_res.end = crashk_res.start + crash_size - 1;
+}
 
-	/* The crash region must not overlap the current kernel */
-	if (overlaps_crashkernel(__pa(_stext), _end - _stext)) {
-		printk(KERN_WARNING
-			"Crash kernel can not overlap current kernel\n");
-		crashk_res.start = crashk_res.end = 0;
+void __init arch_reserve_crashkernel(void)
+{
+	unsigned long long crash_size, crash_base, crash_end;
+	unsigned long long kernel_start, kernel_size;
+	unsigned long long total_mem_sz;
+	int ret;
+
+	total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size();
+
+	/* use common parsing */
+	ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size,
+				&crash_base, NULL, &crashk_cma_size, NULL);
+
+	if (ret)
 		return;
-	}
 
-	/* Crash kernel trumps memory limit */
-	if (memory_limit && memory_limit <= crashk_res.end) {
-		memory_limit = crashk_res.end + 1;
-		total_mem_sz = memory_limit;
-		printk("Adjusted memory limit for crashkernel, now 0x%llx\n",
-		       memory_limit);
-	}
+	crash_base = get_crash_base(crash_base);
+	crash_end = crash_base + crash_size - 1;
 
-	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
-			"for crashkernel (System RAM: %ldMB)\n",
-			(unsigned long)(crash_size >> 20),
-			(unsigned long)(crashk_res.start >> 20),
-			(unsigned long)(total_mem_sz >> 20));
+	kernel_start = __pa(_stext);
+	kernel_size = _end - _stext;
 
-	if (!memblock_is_region_memory(crashk_res.start, crash_size) ||
-	    memblock_reserve(crashk_res.start, crash_size)) {
-		pr_err("Failed to reserve memory for crashkernel!\n");
-		crashk_res.start = crashk_res.end = 0;
+	/* The crash region must not overlap the current kernel */
+	if ((kernel_start + kernel_size > crash_base) && (kernel_start <= crash_end)) {
+		pr_warn("Crash kernel can not overlap current kernel\n");
 		return;
 	}
+
+	reserve_crashkernel_generic(crash_size, crash_base, 0, false);
+}
+
+void __init kdump_cma_reserve(void)
+{
+	if (crashk_cma_size)
+		reserve_crashkernel_cma(crashk_cma_size);
 }
 
 int __init overlaps_crashkernel(unsigned long start, unsigned long size)
@@ -199,17 +146,10 @@ int __init overlaps_crashkernel(unsigned long start, unsigned long size)
 }
 
 /* Values we need to export to the second kernel via the device tree. */
-static phys_addr_t kernel_end;
 static phys_addr_t crashk_base;
 static phys_addr_t crashk_size;
 static unsigned long long mem_limit;
 
-static struct property kernel_end_prop = {
-	.name = "linux,kernel-end",
-	.length = sizeof(phys_addr_t),
-	.value = &kernel_end,
-};
-
 static struct property crashk_base_prop = {
 	.name = "linux,crashkernel-base",
 	.length = sizeof(phys_addr_t),
@@ -228,8 +168,6 @@ static struct property memory_limit_prop = {
 	.value = &mem_limit,
 };
 
-#define cpu_to_be_ulong	__PASTE(cpu_to_be, BITS_PER_LONG)
-
 static void __init export_crashk_values(struct device_node *node)
 {
 	/* There might be existing crash kernel properties, but we can't
@@ -253,6 +191,15 @@ static void __init export_crashk_values(struct device_node *node)
 	mem_limit = cpu_to_be_ulong(memory_limit);
 	of_update_property(node, &memory_limit_prop);
 }
+#endif /* CONFIG_CRASH_RESERVE */
+
+static phys_addr_t kernel_end;
+
+static struct property kernel_end_prop = {
+	.name = "linux,kernel-end",
+	.length = sizeof(phys_addr_t),
+	.value = &kernel_end,
+};
 
 static int __init kexec_setup(void)
 {
@@ -263,14 +210,16 @@ static int __init kexec_setup(void)
 		return -ENOENT;
 
 	/* remove any stale properties so ours can be found */
-	of_remove_property(node, of_find_property(node, kernel_end_prop.name, NULL));
+	of_remove_property(node, of_find_property(node, kernel_end_prop.name,
+						  NULL));
 
 	/* information needed by userspace when using default_machine_kexec */
 	kernel_end = cpu_to_be_ulong(__pa(_end));
 	of_add_property(node, &kernel_end_prop);
 
+#ifdef CONFIG_CRASH_RESERVE
 	export_crashk_values(node);
-
+#endif
 	of_node_put(node);
 	return 0;
 }
diff --git a/arch/powerpc/kexec/core_32.c b/arch/powerpc/kexec/core_32.c
index c95f96850c9e..deb28eb44f30 100644
--- a/arch/powerpc/kexec/core_32.c
+++ b/arch/powerpc/kexec/core_32.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2005 IBM Corporation.
  */
 
+#include <linux/irq.h>
 #include <linux/kexec.h>
 #include <linux/mm.h>
 #include <linux/string.h>
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index a79e28c91e2b..222aa326dace 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -17,6 +17,7 @@
 #include <linux/cpu.h>
 #include <linux/hardirq.h>
 #include <linux/of.h>
+#include <linux/libfdt.h>
 
 #include <asm/page.h>
 #include <asm/current.h>
@@ -26,10 +27,12 @@
 #include <asm/paca.h>
 #include <asm/mmu.h>
 #include <asm/sections.h>	/* _end */
+#include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/svm.h>
 #include <asm/ultravisor.h>
+#include <asm/crashdump-ppc64.h>
 
 int machine_kexec_prepare(struct kimage *image)
 {
@@ -283,8 +286,7 @@ static void kexec_prepare_cpus(void)
  * We could use a smaller stack if we don't care about anything using
  * current, but that audit has not been performed.
  */
-static union thread_union kexec_stack __init_task_data =
-	{ };
+static union thread_union kexec_stack = { };
 
 /*
  * For similar reasons to the stack above, the kexecing CPU needs to be on a
@@ -316,6 +318,16 @@ void default_machine_kexec(struct kimage *image)
 	if (!kdump_in_progress())
 		kexec_prepare_cpus();
 
+#ifdef CONFIG_PPC_PSERIES
+	/*
+	 * This must be done after other CPUs have shut down, otherwise they
+	 * could execute the 'scv' instruction, which is not supported with
+	 * reloc disabled (see configure_exceptions()).
+	 */
+	if (firmware_has_feature(FW_FEATURE_SET_MODE))
+		pseries_disable_reloc_on_exc();
+#endif
+
 	printk("kexec: Starting switchover sequence.\n");
 
 	/* switch to a staticly allocated stack.  Based on irq stack code.
@@ -379,8 +391,8 @@ void default_machine_kexec(struct kimage *image)
 
 #ifdef CONFIG_PPC_64S_HASH_MMU
 /* Values we need to export to the second kernel via the device tree. */
-static unsigned long htab_base;
-static unsigned long htab_size;
+static __be64 htab_base;
+static __be64 htab_size;
 
 static struct property htab_base_prop = {
 	.name = "linux,htab-base",
@@ -420,3 +432,113 @@ static int __init export_htab_values(void)
 }
 late_initcall(export_htab_values);
 #endif /* CONFIG_PPC_64S_HASH_MMU */
+
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
+/**
+ * add_node_props - Reads node properties from device node structure and add
+ *                  them to fdt.
+ * @fdt:            Flattened device tree of the kernel
+ * @node_offset:    offset of the node to add a property at
+ * @dn:             device node pointer
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int add_node_props(void *fdt, int node_offset, const struct device_node *dn)
+{
+	int ret = 0;
+	struct property *pp;
+
+	if (!dn)
+		return -EINVAL;
+
+	for_each_property_of_node(dn, pp) {
+		ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length);
+		if (ret < 0) {
+			pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret));
+			return ret;
+		}
+	}
+	return ret;
+}
+
+/**
+ * update_cpus_node - Update cpus node of flattened device tree using of_root
+ *                    device node.
+ * @fdt:              Flattened device tree of the kernel.
+ *
+ * Returns 0 on success, negative errno on error.
+ *
+ * Note: expecting no subnodes under /cpus/<node> with device_type == "cpu".
+ * If this changes, update this function to include them.
+ */
+int update_cpus_node(void *fdt)
+{
+	int prev_node_offset;
+	const char *device_type;
+	const struct fdt_property *prop;
+	struct device_node *cpus_node, *dn;
+	int cpus_offset, cpus_subnode_offset, ret = 0;
+
+	cpus_offset = fdt_path_offset(fdt, "/cpus");
+	if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) {
+		pr_err("Malformed device tree: error reading /cpus node: %s\n",
+		       fdt_strerror(cpus_offset));
+		return cpus_offset;
+	}
+
+	prev_node_offset = cpus_offset;
+	/* Delete sub-nodes of /cpus node with device_type == "cpu" */
+	for (cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset); cpus_subnode_offset >= 0;) {
+		/* Ignore nodes that do not have a device_type property or device_type != "cpu" */
+		prop = fdt_get_property(fdt, cpus_subnode_offset, "device_type", NULL);
+		if (!prop || strcmp(prop->data, "cpu")) {
+			prev_node_offset = cpus_subnode_offset;
+			goto next_node;
+		}
+
+		ret = fdt_del_node(fdt, cpus_subnode_offset);
+		if (ret < 0) {
+			pr_err("Failed to delete a cpus sub-node: %s\n", fdt_strerror(ret));
+			return ret;
+		}
+next_node:
+		if (prev_node_offset == cpus_offset)
+			cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset);
+		else
+			cpus_subnode_offset = fdt_next_subnode(fdt, prev_node_offset);
+	}
+
+	cpus_node = of_find_node_by_path("/cpus");
+	/* Fail here to avoid kexec/kdump kernel boot hung */
+	if (!cpus_node) {
+		pr_err("No /cpus node found\n");
+		return -EINVAL;
+	}
+
+	/* Add all /cpus sub-nodes of device_type == "cpu" to FDT */
+	for_each_child_of_node(cpus_node, dn) {
+		/* Ignore device nodes that do not have a device_type property
+		 * or device_type != "cpu".
+		 */
+		device_type = of_get_property(dn, "device_type", NULL);
+		if (!device_type || strcmp(device_type, "cpu"))
+			continue;
+
+		cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
+		if (cpus_subnode_offset < 0) {
+			pr_err("Unable to add %s subnode: %s\n", dn->full_name,
+			       fdt_strerror(cpus_subnode_offset));
+			ret = cpus_subnode_offset;
+			goto out;
+		}
+
+		ret = add_node_props(fdt, cpus_subnode_offset, dn);
+		if (ret < 0)
+			goto out;
+	}
+out:
+	of_node_put(cpus_node);
+	of_node_put(dn);
+	return ret;
+}
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c
index 252724ed666a..a325c1c02f96 100644
--- a/arch/powerpc/kexec/crash.c
+++ b/arch/powerpc/kexec/crash.c
@@ -16,6 +16,8 @@
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/types.h>
+#include <linux/libfdt.h>
+#include <linux/memory.h>
 
 #include <asm/processor.h>
 #include <asm/machdep.h>
@@ -24,6 +26,7 @@
 #include <asm/setjmp.h>
 #include <asm/debug.h>
 #include <asm/interrupt.h>
+#include <asm/kexec_ranges.h>
 
 /*
  * The primary CPU waits a while for all secondary CPUs to enter. This is to
@@ -350,13 +353,16 @@ EXPORT_SYMBOL(crash_shutdown_unregister);
 
 void default_machine_crash_shutdown(struct pt_regs *regs)
 {
-	unsigned int i;
+	volatile unsigned int i;
 	int (*old_handler)(struct pt_regs *regs);
 
 	if (TRAP(regs) == INTERRUPT_SYSTEM_RESET)
 		is_via_system_reset = 1;
 
-	crash_smp_send_stop();
+	if (IS_ENABLED(CONFIG_SMP))
+		crash_smp_send_stop();
+	else
+		crash_kexec_prepare();
 
 	crash_save_cpu(regs, crashing_cpu);
 
@@ -392,3 +398,195 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(1, 0);
 }
+
+#ifdef CONFIG_CRASH_HOTPLUG
+#undef pr_fmt
+#define pr_fmt(fmt) "crash hp: " fmt
+
+/*
+ * Advertise preferred elfcorehdr size to userspace via
+ * /sys/kernel/crash_elfcorehdr_size sysfs interface.
+ */
+unsigned int arch_crash_get_elfcorehdr_size(void)
+{
+	unsigned long phdr_cnt;
+
+	/* A program header for possible CPUs + vmcoreinfo */
+	phdr_cnt = num_possible_cpus() + 1;
+	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG))
+		phdr_cnt += CONFIG_CRASH_MAX_MEMORY_RANGES;
+
+	return sizeof(struct elfhdr) + (phdr_cnt * sizeof(Elf64_Phdr));
+}
+
+/**
+ * update_crash_elfcorehdr() - Recreate the elfcorehdr and replace it with old
+ *			       elfcorehdr in the kexec segment array.
+ * @image: the active struct kimage
+ * @mn: struct memory_notify data handler
+ */
+static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify *mn)
+{
+	int ret;
+	struct crash_mem *cmem = NULL;
+	struct kexec_segment *ksegment;
+	void *ptr, *mem, *elfbuf = NULL;
+	unsigned long elfsz, memsz, base_addr, size;
+
+	ksegment = &image->segment[image->elfcorehdr_index];
+	mem = (void *) ksegment->mem;
+	memsz = ksegment->memsz;
+
+	ret = get_crash_memory_ranges(&cmem);
+	if (ret) {
+		pr_err("Failed to get crash mem range\n");
+		return;
+	}
+
+	/*
+	 * The hot unplugged memory is part of crash memory ranges,
+	 * remove it here.
+	 */
+	if (image->hp_action == KEXEC_CRASH_HP_REMOVE_MEMORY) {
+		base_addr = PFN_PHYS(mn->start_pfn);
+		size = mn->nr_pages * PAGE_SIZE;
+		ret = remove_mem_range(&cmem, base_addr, size);
+		if (ret) {
+			pr_err("Failed to remove hot-unplugged memory from crash memory ranges\n");
+			goto out;
+		}
+	}
+
+	ret = crash_prepare_elf64_headers(cmem, false, &elfbuf, &elfsz);
+	if (ret) {
+		pr_err("Failed to prepare elf header\n");
+		goto out;
+	}
+
+	/*
+	 * It is unlikely that kernel hit this because elfcorehdr kexec
+	 * segment (memsz) is built with addition space to accommodate growing
+	 * number of crash memory ranges while loading the kdump kernel. It is
+	 * Just to avoid any unforeseen case.
+	 */
+	if (elfsz > memsz) {
+		pr_err("Updated crash elfcorehdr elfsz %lu > memsz %lu", elfsz, memsz);
+		goto out;
+	}
+
+	ptr = __va(mem);
+	if (ptr) {
+		/* Temporarily invalidate the crash image while it is replaced */
+		xchg(&kexec_crash_image, NULL);
+
+		/* Replace the old elfcorehdr with newly prepared elfcorehdr */
+		memcpy((void *)ptr, elfbuf, elfsz);
+
+		/* The crash image is now valid once again */
+		xchg(&kexec_crash_image, image);
+	}
+out:
+	kvfree(cmem);
+	kvfree(elfbuf);
+}
+
+/**
+ * get_fdt_index - Loop through the kexec segment array and find
+ *		   the index of the FDT segment.
+ * @image: a pointer to kexec_crash_image
+ *
+ * Returns the index of FDT segment in the kexec segment array
+ * if found; otherwise -1.
+ */
+static int get_fdt_index(struct kimage *image)
+{
+	void *ptr;
+	unsigned long mem;
+	int i, fdt_index = -1;
+
+	/* Find the FDT segment index in kexec segment array. */
+	for (i = 0; i < image->nr_segments; i++) {
+		mem = image->segment[i].mem;
+		ptr = __va(mem);
+
+		if (ptr && fdt_magic(ptr) == FDT_MAGIC) {
+			fdt_index = i;
+			break;
+		}
+	}
+
+	return fdt_index;
+}
+
+/**
+ * update_crash_fdt - updates the cpus node of the crash FDT.
+ *
+ * @image: a pointer to kexec_crash_image
+ */
+static void update_crash_fdt(struct kimage *image)
+{
+	void *fdt;
+	int fdt_index;
+
+	fdt_index = get_fdt_index(image);
+	if (fdt_index < 0) {
+		pr_err("Unable to locate FDT segment.\n");
+		return;
+	}
+
+	fdt = __va((void *)image->segment[fdt_index].mem);
+
+	/* Temporarily invalidate the crash image while it is replaced */
+	xchg(&kexec_crash_image, NULL);
+
+	/* update FDT to reflect changes in CPU resources */
+	if (update_cpus_node(fdt))
+		pr_err("Failed to update crash FDT");
+
+	/* The crash image is now valid once again */
+	xchg(&kexec_crash_image, image);
+}
+
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags)
+{
+#ifdef CONFIG_KEXEC_FILE
+	if (image->file_mode)
+		return 1;
+#endif
+	return kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT;
+}
+
+/**
+ * arch_crash_handle_hotplug_event - Handle crash CPU/Memory hotplug events to update the
+ *				     necessary kexec segments based on the hotplug event.
+ * @image: a pointer to kexec_crash_image
+ * @arg: struct memory_notify handler for memory hotplug case and NULL for CPU hotplug case.
+ *
+ * Update the kdump image based on the type of hotplug event, represented by image->hp_action.
+ * CPU add: Update the FDT segment to include the newly added CPU.
+ * CPU remove: No action is needed, with the assumption that it's okay to have offline CPUs
+ *	       part of the FDT.
+ * Memory add/remove: No action is taken as this is not yet supported.
+ */
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
+{
+	struct memory_notify *mn;
+
+	switch (image->hp_action) {
+	case KEXEC_CRASH_HP_REMOVE_CPU:
+		return;
+
+	case KEXEC_CRASH_HP_ADD_CPU:
+		update_crash_fdt(image);
+		break;
+
+	case KEXEC_CRASH_HP_REMOVE_MEMORY:
+	case KEXEC_CRASH_HP_ADD_MEMORY:
+		mn = (struct memory_notify *)arg;
+		update_crash_elfcorehdr(image, mn);
+		return;
+	default:
+		pr_warn_once("Unknown hotplug action\n");
+	}
+}
+#endif /* CONFIG_CRASH_HOTPLUG */
diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c
index eeb258002d1e..5d6d616404cf 100644
--- a/arch/powerpc/kexec/elf_64.c
+++ b/arch/powerpc/kexec/elf_64.c
@@ -23,6 +23,7 @@
 #include <linux/of_fdt.h>
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <asm/kexec_ranges.h>
 
 static void *elf64_load(struct kimage *image, char *kernel_buf,
 			unsigned long kernel_len, char *initrd,
@@ -36,6 +37,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	const void *slave_code;
 	struct elfhdr ehdr;
 	char *modified_cmdline = NULL;
+	struct crash_mem *rmem = NULL;
 	struct kexec_elf_info elf_info;
 	struct kexec_buf kbuf = { .image = image, .buf_min = 0,
 				  .buf_max = ppc64_rma_size };
@@ -47,7 +49,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (image->type == KEXEC_TYPE_CRASH) {
+	if (IS_ENABLED(CONFIG_CRASH_DUMP) && image->type == KEXEC_TYPE_CRASH) {
 		/* min & max buffer values for kdump case */
 		kbuf.buf_min = pbuf.buf_min = crashk_res.start;
 		kbuf.buf_max = pbuf.buf_max =
@@ -59,7 +61,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 	if (ret)
 		goto out;
 
-	pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr);
+	kexec_dprintk("Loaded the kernel at 0x%lx\n", kernel_load_addr);
 
 	ret = kexec_load_purgatory(image, &pbuf);
 	if (ret) {
@@ -67,10 +69,10 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 		goto out;
 	}
 
-	pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem);
+	kexec_dprintk("Loaded purgatory at 0x%lx\n", pbuf.mem);
 
 	/* Load additional segments needed for panic kernel */
-	if (image->type == KEXEC_TYPE_CRASH) {
+	if (IS_ENABLED(CONFIG_CRASH_DUMP) && image->type == KEXEC_TYPE_CRASH) {
 		ret = load_crashdump_segments_ppc64(image, &kbuf);
 		if (ret) {
 			pr_err("Failed to load kdump kernel segments\n");
@@ -99,24 +101,28 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 			goto out;
 		initrd_load_addr = kbuf.mem;
 
-		pr_debug("Loaded initrd at 0x%lx\n", initrd_load_addr);
+		kexec_dprintk("Loaded initrd at 0x%lx\n", initrd_load_addr);
 	}
 
+	ret = get_reserved_memory_ranges(&rmem);
+	if (ret)
+		goto out;
+
 	fdt = of_kexec_alloc_and_setup_fdt(image, initrd_load_addr,
 					   initrd_len, cmdline,
-					   kexec_extra_fdt_size_ppc64(image));
+					   kexec_extra_fdt_size_ppc64(image, rmem));
 	if (!fdt) {
 		pr_err("Error setting up the new device tree.\n");
 		ret = -EINVAL;
 		goto out;
 	}
 
-	ret = setup_new_fdt_ppc64(image, fdt, initrd_load_addr,
-				  initrd_len, cmdline);
+	ret = setup_new_fdt_ppc64(image, fdt, rmem);
 	if (ret)
 		goto out_free_fdt;
 
-	fdt_pack(fdt);
+	if (!IS_ENABLED(CONFIG_CRASH_HOTPLUG) || image->type != KEXEC_TYPE_CRASH)
+		fdt_pack(fdt);
 
 	kbuf.buffer = fdt;
 	kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt);
@@ -132,7 +138,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 
 	fdt_load_addr = kbuf.mem;
 
-	pr_debug("Loaded device tree at 0x%lx\n", fdt_load_addr);
+	kexec_dprintk("Loaded device tree at 0x%lx\n", fdt_load_addr);
 
 	slave_code = elf_info.buffer + elf_info.proghdrs[0].p_offset;
 	ret = setup_purgatory_ppc64(image, slave_code, fdt, kernel_load_addr,
@@ -145,6 +151,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 out_free_fdt:
 	kvfree(fdt);
 out:
+	kfree(rmem);
 	kfree(modified_cmdline);
 	kexec_free_elf_info(&elf_info);
 
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index 110d28bede2a..e7ef8b2a2554 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -17,7 +17,8 @@
 #include <linux/kexec.h>
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
@@ -27,11 +28,13 @@
 #include <asm/kexec_ranges.h>
 #include <asm/crashdump-ppc64.h>
 #include <asm/mmzone.h>
+#include <asm/iommu.h>
 #include <asm/prom.h>
 #include <asm/plpks.h>
+#include <asm/cputhreads.h>
 
 struct umem_info {
-	u64 *buf;		/* data buffer for usable-memory property */
+	__be64 *buf;		/* data buffer for usable-memory property */
 	u32 size;		/* size allocated for the data buffer */
 	u32 max_entries;	/* maximum no. of entries */
 	u32 idx;		/* index of current entry */
@@ -46,393 +49,21 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 	NULL
 };
 
-/**
- * get_exclude_memory_ranges - Get exclude memory ranges. This list includes
- *                             regions like opal/rtas, tce-table, initrd,
- *                             kernel, htab which should be avoided while
- *                             setting up kexec load segments.
- * @mem_ranges:                Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
-{
-	int ret;
-
-	ret = add_tce_mem_ranges(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_initrd_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_htab_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_kernel_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_opal_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_reserved_mem_ranges(mem_ranges);
-	if (ret)
-		goto out;
-
-	/* exclude memory ranges should be sorted for easy lookup */
-	sort_memory_ranges(*mem_ranges, true);
-out:
-	if (ret)
-		pr_err("Failed to setup exclude memory ranges\n");
-	return ret;
-}
-
-/**
- * get_usable_memory_ranges - Get usable memory ranges. This list includes
- *                            regions like crashkernel, opal/rtas & tce-table,
- *                            that kdump kernel could use.
- * @mem_ranges:               Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_usable_memory_ranges(struct crash_mem **mem_ranges)
-{
-	int ret;
-
-	/*
-	 * Early boot failure observed on guests when low memory (first memory
-	 * block?) is not added to usable memory. So, add [0, crashk_res.end]
-	 * instead of [crashk_res.start, crashk_res.end] to workaround it.
-	 * Also, crashed kernel's memory must be added to reserve map to
-	 * avoid kdump kernel from using it.
-	 */
-	ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1);
-	if (ret)
-		goto out;
-
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_opal_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_tce_mem_ranges(mem_ranges);
-out:
-	if (ret)
-		pr_err("Failed to setup usable memory ranges\n");
-	return ret;
-}
-
-/**
- * get_crash_memory_ranges - Get crash memory ranges. This list includes
- *                           first/crashing kernel's memory regions that
- *                           would be exported via an elfcore.
- * @mem_ranges:              Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_crash_memory_ranges(struct crash_mem **mem_ranges)
-{
-	phys_addr_t base, end;
-	struct crash_mem *tmem;
-	u64 i;
-	int ret;
-
-	for_each_mem_range(i, &base, &end) {
-		u64 size = end - base;
-
-		/* Skip backup memory region, which needs a separate entry */
-		if (base == BACKUP_SRC_START) {
-			if (size > BACKUP_SRC_SIZE) {
-				base = BACKUP_SRC_END + 1;
-				size -= BACKUP_SRC_SIZE;
-			} else
-				continue;
-		}
-
-		ret = add_mem_range(mem_ranges, base, size);
-		if (ret)
-			goto out;
-
-		/* Try merging adjacent ranges before reallocation attempt */
-		if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges)
-			sort_memory_ranges(*mem_ranges, true);
-	}
-
-	/* Reallocate memory ranges if there is no space to split ranges */
-	tmem = *mem_ranges;
-	if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
-		tmem = realloc_mem_ranges(mem_ranges);
-		if (!tmem)
-			goto out;
-	}
-
-	/* Exclude crashkernel region */
-	ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end);
-	if (ret)
-		goto out;
-
-	/*
-	 * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
-	 *        regions are exported to save their context at the time of
-	 *        crash, they should actually be backed up just like the
-	 *        first 64K bytes of memory.
-	 */
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_opal_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	/* create a separate program header for the backup region */
-	ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE);
-	if (ret)
-		goto out;
-
-	sort_memory_ranges(*mem_ranges, false);
-out:
-	if (ret)
-		pr_err("Failed to setup crash memory ranges\n");
-	return ret;
-}
-
-/**
- * get_reserved_memory_ranges - Get reserve memory ranges. This list includes
- *                              memory regions that should be added to the
- *                              memory reserve map to ensure the region is
- *                              protected from any mischief.
- * @mem_ranges:                 Range list to add the memory ranges to.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int get_reserved_memory_ranges(struct crash_mem **mem_ranges)
-{
-	int ret;
-
-	ret = add_rtas_mem_range(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_tce_mem_ranges(mem_ranges);
-	if (ret)
-		goto out;
-
-	ret = add_reserved_mem_ranges(mem_ranges);
-out:
-	if (ret)
-		pr_err("Failed to setup reserved memory ranges\n");
-	return ret;
-}
-
-/**
- * __locate_mem_hole_top_down - Looks top down for a large enough memory hole
- *                              in the memory regions between buf_min & buf_max
- *                              for the buffer. If found, sets kbuf->mem.
- * @kbuf:                       Buffer contents and memory parameters.
- * @buf_min:                    Minimum address for the buffer.
- * @buf_max:                    Maximum address for the buffer.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int __locate_mem_hole_top_down(struct kexec_buf *kbuf,
-				      u64 buf_min, u64 buf_max)
-{
-	int ret = -EADDRNOTAVAIL;
-	phys_addr_t start, end;
-	u64 i;
-
-	for_each_mem_range_rev(i, &start, &end) {
-		/*
-		 * memblock uses [start, end) convention while it is
-		 * [start, end] here. Fix the off-by-one to have the
-		 * same convention.
-		 */
-		end -= 1;
-
-		if (start > buf_max)
-			continue;
-
-		/* Memory hole not found */
-		if (end < buf_min)
-			break;
-
-		/* Adjust memory region based on the given range */
-		if (start < buf_min)
-			start = buf_min;
-		if (end > buf_max)
-			end = buf_max;
-
-		start = ALIGN(start, kbuf->buf_align);
-		if (start < end && (end - start + 1) >= kbuf->memsz) {
-			/* Suitable memory range found. Set kbuf->mem */
-			kbuf->mem = ALIGN_DOWN(end - kbuf->memsz + 1,
-					       kbuf->buf_align);
-			ret = 0;
-			break;
-		}
-	}
-
-	return ret;
-}
-
-/**
- * locate_mem_hole_top_down_ppc64 - Skip special memory regions to find a
- *                                  suitable buffer with top down approach.
- * @kbuf:                           Buffer contents and memory parameters.
- * @buf_min:                        Minimum address for the buffer.
- * @buf_max:                        Maximum address for the buffer.
- * @emem:                           Exclude memory ranges.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int locate_mem_hole_top_down_ppc64(struct kexec_buf *kbuf,
-					  u64 buf_min, u64 buf_max,
-					  const struct crash_mem *emem)
-{
-	int i, ret = 0, err = -EADDRNOTAVAIL;
-	u64 start, end, tmin, tmax;
-
-	tmax = buf_max;
-	for (i = (emem->nr_ranges - 1); i >= 0; i--) {
-		start = emem->ranges[i].start;
-		end = emem->ranges[i].end;
-
-		if (start > tmax)
-			continue;
-
-		if (end < tmax) {
-			tmin = (end < buf_min ? buf_min : end + 1);
-			ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
-			if (!ret)
-				return 0;
-		}
-
-		tmax = start - 1;
-
-		if (tmax < buf_min) {
-			ret = err;
-			break;
-		}
-		ret = 0;
-	}
-
-	if (!ret) {
-		tmin = buf_min;
-		ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
-	}
-	return ret;
-}
-
-/**
- * __locate_mem_hole_bottom_up - Looks bottom up for a large enough memory hole
- *                               in the memory regions between buf_min & buf_max
- *                               for the buffer. If found, sets kbuf->mem.
- * @kbuf:                        Buffer contents and memory parameters.
- * @buf_min:                     Minimum address for the buffer.
- * @buf_max:                     Maximum address for the buffer.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf,
-				       u64 buf_min, u64 buf_max)
+int arch_check_excluded_range(struct kimage *image, unsigned long start,
+			      unsigned long end)
 {
-	int ret = -EADDRNOTAVAIL;
-	phys_addr_t start, end;
-	u64 i;
-
-	for_each_mem_range(i, &start, &end) {
-		/*
-		 * memblock uses [start, end) convention while it is
-		 * [start, end] here. Fix the off-by-one to have the
-		 * same convention.
-		 */
-		end -= 1;
-
-		if (end < buf_min)
-			continue;
-
-		/* Memory hole not found */
-		if (start > buf_max)
-			break;
-
-		/* Adjust memory region based on the given range */
-		if (start < buf_min)
-			start = buf_min;
-		if (end > buf_max)
-			end = buf_max;
-
-		start = ALIGN(start, kbuf->buf_align);
-		if (start < end && (end - start + 1) >= kbuf->memsz) {
-			/* Suitable memory range found. Set kbuf->mem */
-			kbuf->mem = start;
-			ret = 0;
-			break;
-		}
-	}
-
-	return ret;
-}
-
-/**
- * locate_mem_hole_bottom_up_ppc64 - Skip special memory regions to find a
- *                                   suitable buffer with bottom up approach.
- * @kbuf:                            Buffer contents and memory parameters.
- * @buf_min:                         Minimum address for the buffer.
- * @buf_max:                         Maximum address for the buffer.
- * @emem:                            Exclude memory ranges.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
-					   u64 buf_min, u64 buf_max,
-					   const struct crash_mem *emem)
-{
-	int i, ret = 0, err = -EADDRNOTAVAIL;
-	u64 start, end, tmin, tmax;
-
-	tmin = buf_min;
-	for (i = 0; i < emem->nr_ranges; i++) {
-		start = emem->ranges[i].start;
-		end = emem->ranges[i].end;
-
-		if (end < tmin)
-			continue;
-
-		if (start > tmin) {
-			tmax = (start > buf_max ? buf_max : start - 1);
-			ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
-			if (!ret)
-				return 0;
-		}
+	struct crash_mem *emem;
+	int i;
 
-		tmin = end + 1;
+	emem = image->arch.exclude_ranges;
+	for (i = 0; i < emem->nr_ranges; i++)
+		if (start < emem->ranges[i].end && end > emem->ranges[i].start)
+			return 1;
 
-		if (tmin > buf_max) {
-			ret = err;
-			break;
-		}
-		ret = 0;
-	}
-
-	if (!ret) {
-		tmax = buf_max;
-		ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
-	}
-	return ret;
+	return 0;
 }
 
+#ifdef CONFIG_CRASH_DUMP
 /**
  * check_realloc_usable_mem - Reallocate buffer if it can't accommodate entries
  * @um_info:                  Usable memory buffer and ranges info.
@@ -442,10 +73,10 @@ static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
  *
  * Returns buffer on success, NULL on error.
  */
-static u64 *check_realloc_usable_mem(struct umem_info *um_info, int cnt)
+static __be64 *check_realloc_usable_mem(struct umem_info *um_info, int cnt)
 {
 	u32 new_size;
-	u64 *tbuf;
+	__be64 *tbuf;
 
 	if ((um_info->idx + cnt) <= um_info->max_entries)
 		return um_info->buf;
@@ -563,11 +194,10 @@ static int kdump_setup_usable_lmb(struct drmem_lmb *lmb, const __be32 **usm,
 static int add_usable_mem_property(void *fdt, struct device_node *dn,
 				   struct umem_info *um_info)
 {
-	int n_mem_addr_cells, n_mem_size_cells, node;
+	int node;
 	char path[NODE_PATH_LEN];
-	int i, len, ranges, ret;
-	const __be32 *prop;
-	u64 base, end;
+	int i, ret;
+	u64 base, size;
 
 	of_node_get(dn);
 
@@ -576,7 +206,7 @@ static int add_usable_mem_property(void *fdt, struct device_node *dn,
 		       NODE_PATH_LEN, dn);
 		return -EOVERFLOW;
 	}
-	pr_debug("Memory node path: %s\n", path);
+	kexec_dprintk("Memory node path: %s\n", path);
 
 	/* Now that we know the path, find its offset in kdump kernel's fdt */
 	node = fdt_path_offset(fdt, path);
@@ -586,41 +216,30 @@ static int add_usable_mem_property(void *fdt, struct device_node *dn,
 		goto out;
 	}
 
-	/* Get the address & size cells */
-	n_mem_addr_cells = of_n_addr_cells(dn);
-	n_mem_size_cells = of_n_size_cells(dn);
-	pr_debug("address cells: %d, size cells: %d\n", n_mem_addr_cells,
-		 n_mem_size_cells);
-
 	um_info->idx  = 0;
 	if (!check_realloc_usable_mem(um_info, 2)) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	prop = of_get_property(dn, "reg", &len);
-	if (!prop || len <= 0) {
-		ret = 0;
-		goto out;
-	}
-
 	/*
 	 * "reg" property represents sequence of (addr,size) tuples
 	 * each representing a memory range.
 	 */
-	ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells);
-
-	for (i = 0; i < ranges; i++) {
-		base = of_read_number(prop, n_mem_addr_cells);
-		prop += n_mem_addr_cells;
-		end = base + of_read_number(prop, n_mem_size_cells) - 1;
-		prop += n_mem_size_cells;
+	for (i = 0; ; i++) {
+		ret = of_property_read_reg(dn, i, &base, &size);
+		if (ret)
+			break;
 
-		ret = add_usable_mem(um_info, base, end);
+		ret = add_usable_mem(um_info, base, base + size - 1);
 		if (ret)
 			goto out;
 	}
 
+	// No reg or empty reg? Skip this node.
+	if (i == 0)
+		goto out;
+
 	/*
 	 * No kdump kernel usable memory found in this memory node.
 	 * Write (0,0) tuple in linux,usable-memory property for
@@ -663,7 +282,7 @@ static int update_usable_mem_fdt(void *fdt, struct crash_mem *usable_mem)
 
 	node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory");
 	if (node == -FDT_ERR_NOTFOUND)
-		pr_debug("No dynamic reconfiguration memory found\n");
+		kexec_dprintk("No dynamic reconfiguration memory found\n");
 	else if (node < 0) {
 		pr_err("Malformed device tree: error reading /ibm,dynamic-reconfiguration-memory.\n");
 		return -EINVAL;
@@ -775,13 +394,30 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr)
 	for (i = 0; i < ehdr->e_phnum; i++) {
 		if (phdr->p_paddr == BACKUP_SRC_START) {
 			phdr->p_offset = image->arch.backup_start;
-			pr_debug("Backup region offset updated to 0x%lx\n",
-				 image->arch.backup_start);
+			kexec_dprintk("Backup region offset updated to 0x%lx\n",
+				      image->arch.backup_start);
 			return;
 		}
 	}
 }
 
+static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem)
+{
+#if defined(CONFIG_CRASH_HOTPLUG) && defined(CONFIG_MEMORY_HOTPLUG)
+	unsigned int extra_sz = 0;
+
+	if (CONFIG_CRASH_MAX_MEMORY_RANGES > (unsigned int)PN_XNUM)
+		pr_warn("Number of Phdrs %u exceeds max\n", CONFIG_CRASH_MAX_MEMORY_RANGES);
+	else if (cmem->nr_ranges >= CONFIG_CRASH_MAX_MEMORY_RANGES)
+		pr_warn("Configured crash mem ranges may not be enough\n");
+	else
+		extra_sz = (CONFIG_CRASH_MAX_MEMORY_RANGES - cmem->nr_ranges) * sizeof(Elf64_Phdr);
+
+	return extra_sz;
+#endif
+	return 0;
+}
+
 /**
  * load_elfcorehdr_segment - Setup crash memory ranges and initialize elfcorehdr
  *                           segment needed to load kdump kernel.
@@ -813,7 +449,8 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
 
 	kbuf->buffer = headers;
 	kbuf->mem = KEXEC_BUF_MEM_UNKNOWN;
-	kbuf->bufsz = kbuf->memsz = headers_sz;
+	kbuf->bufsz = headers_sz;
+	kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem);
 	kbuf->top_down = false;
 
 	ret = kexec_add_buffer(kbuf);
@@ -849,7 +486,7 @@ int load_crashdump_segments_ppc64(struct kimage *image,
 		pr_err("Failed to load backup segment\n");
 		return ret;
 	}
-	pr_debug("Loaded the backup region at 0x%lx\n", kbuf->mem);
+	kexec_dprintk("Loaded the backup region at 0x%lx\n", kbuf->mem);
 
 	/* Load elfcorehdr segment - to export crashing kernel's vmcore */
 	ret = load_elfcorehdr_segment(image, kbuf);
@@ -857,11 +494,12 @@ int load_crashdump_segments_ppc64(struct kimage *image,
 		pr_err("Failed to load elfcorehdr segment\n");
 		return ret;
 	}
-	pr_debug("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n",
-		 image->elf_load_addr, kbuf->bufsz, kbuf->memsz);
+	kexec_dprintk("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n",
+		      image->elf_load_addr, kbuf->bufsz, kbuf->memsz);
 
 	return 0;
 }
+#endif
 
 /**
  * setup_purgatory_ppc64 - initialize PPC64 specific purgatory's global
@@ -915,13 +553,18 @@ int setup_purgatory_ppc64(struct kimage *image, const void *slave_code,
 	if (dn) {
 		u64 val;
 
-		of_property_read_u64(dn, "opal-base-address", &val);
+		ret = of_property_read_u64(dn, "opal-base-address", &val);
+		if (ret)
+			goto out;
+
 		ret = kexec_purgatory_get_set_symbol(image, "opal_base", &val,
 						     sizeof(val), false);
 		if (ret)
 			goto out;
 
-		of_property_read_u64(dn, "opal-entry-address", &val);
+		ret = of_property_read_u64(dn, "opal-entry-address", &val);
+		if (ret)
+			goto out;
 		ret = kexec_purgatory_get_set_symbol(image, "opal_entry", &val,
 						     sizeof(val), false);
 	}
@@ -933,9 +576,9 @@ out:
 }
 
 /**
- * get_cpu_node_size - Compute the size of a CPU node in the FDT.
- *                     This should be done only once and the value is stored in
- *                     a static variable.
+ * cpu_node_size - Compute the size of a CPU node in the FDT.
+ *                 This should be done only once and the value is stored in
+ *                 a static variable.
  * Returns the max size of a CPU node in the FDT.
  */
 static unsigned int cpu_node_size(void)
@@ -971,26 +614,16 @@ static unsigned int cpu_node_size(void)
 	return size;
 }
 
-/**
- * kexec_extra_fdt_size_ppc64 - Return the estimated additional size needed to
- *                              setup FDT for kexec/kdump kernel.
- * @image:                      kexec image being loaded.
- *
- * Returns the estimated extra size needed for kexec/kdump kernel FDT.
- */
-unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
+static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image, unsigned int cpu_nodes)
 {
-	unsigned int cpu_nodes, extra_size = 0;
-	struct device_node *dn;
+	unsigned int extra_size = 0;
 	u64 usm_entries;
+#ifdef CONFIG_CRASH_HOTPLUG
+	unsigned int possible_cpu_nodes;
+#endif
 
-	// Budget some space for the password blob. There's already extra space
-	// for the key name
-	if (plpks_is_available())
-		extra_size += (unsigned int)plpks_get_passwordlen();
-
-	if (image->type != KEXEC_TYPE_CRASH)
-		return extra_size;
+	if (!IS_ENABLED(CONFIG_CRASH_DUMP) || image->type != KEXEC_TYPE_CRASH)
+		return 0;
 
 	/*
 	 * For kdump kernel, account for linux,usable-memory and
@@ -1003,106 +636,53 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
 		extra_size += (unsigned int)(usm_entries * sizeof(u64));
 	}
 
+#ifdef CONFIG_CRASH_HOTPLUG
 	/*
-	 * Get the number of CPU nodes in the current DT. This allows to
-	 * reserve places for CPU nodes added since the boot time.
+	 * Make sure enough space is reserved to accommodate possible CPU nodes
+	 * in the crash FDT. This allows packing possible CPU nodes which are
+	 * not yet present in the system without regenerating the entire FDT.
 	 */
-	cpu_nodes = 0;
-	for_each_node_by_type(dn, "cpu") {
-		cpu_nodes++;
+	if (image->type == KEXEC_TYPE_CRASH) {
+		possible_cpu_nodes = num_possible_cpus() / threads_per_core;
+		if (possible_cpu_nodes > cpu_nodes)
+			extra_size += (possible_cpu_nodes - cpu_nodes) * cpu_node_size();
 	}
-
-	if (cpu_nodes > boot_cpu_node_count)
-		extra_size += (cpu_nodes - boot_cpu_node_count) * cpu_node_size();
+#endif
 
 	return extra_size;
 }
 
 /**
- * add_node_props - Reads node properties from device node structure and add
- *                  them to fdt.
- * @fdt:            Flattened device tree of the kernel
- * @node_offset:    offset of the node to add a property at
- * @dn:             device node pointer
+ * kexec_extra_fdt_size_ppc64 - Return the estimated additional size needed to
+ *                              setup FDT for kexec/kdump kernel.
+ * @image:                      kexec image being loaded.
  *
- * Returns 0 on success, negative errno on error.
+ * Returns the estimated extra size needed for kexec/kdump kernel FDT.
  */
-static int add_node_props(void *fdt, int node_offset, const struct device_node *dn)
+unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image, struct crash_mem *rmem)
 {
-	int ret = 0;
-	struct property *pp;
-
-	if (!dn)
-		return -EINVAL;
-
-	for_each_property_of_node(dn, pp) {
-		ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length);
-		if (ret < 0) {
-			pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret));
-			return ret;
-		}
-	}
-	return ret;
-}
+	struct device_node *dn;
+	unsigned int cpu_nodes = 0, extra_size = 0;
 
-/**
- * update_cpus_node - Update cpus node of flattened device tree using of_root
- *                    device node.
- * @fdt:              Flattened device tree of the kernel.
- *
- * Returns 0 on success, negative errno on error.
- */
-static int update_cpus_node(void *fdt)
-{
-	struct device_node *cpus_node, *dn;
-	int cpus_offset, cpus_subnode_offset, ret = 0;
-
-	cpus_offset = fdt_path_offset(fdt, "/cpus");
-	if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) {
-		pr_err("Malformed device tree: error reading /cpus node: %s\n",
-		       fdt_strerror(cpus_offset));
-		return cpus_offset;
-	}
+	// Budget some space for the password blob. There's already extra space
+	// for the key name
+	if (plpks_is_available())
+		extra_size += (unsigned int)plpks_get_passwordlen();
 
-	if (cpus_offset > 0) {
-		ret = fdt_del_node(fdt, cpus_offset);
-		if (ret < 0) {
-			pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret));
-			return -EINVAL;
-		}
+	/* Get the number of CPU nodes in the current device tree */
+	for_each_node_by_type(dn, "cpu") {
+		cpu_nodes++;
 	}
 
-	/* Add cpus node to fdt */
-	cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus");
-	if (cpus_offset < 0) {
-		pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset));
-		return -EINVAL;
-	}
+	/* Consider extra space for CPU nodes added since the boot time */
+	if (cpu_nodes > boot_cpu_node_count)
+		extra_size += (cpu_nodes - boot_cpu_node_count) * cpu_node_size();
 
-	/* Add cpus node properties */
-	cpus_node = of_find_node_by_path("/cpus");
-	ret = add_node_props(fdt, cpus_offset, cpus_node);
-	of_node_put(cpus_node);
-	if (ret < 0)
-		return ret;
+	/* Consider extra space for reserved memory ranges if any */
+	if (rmem->nr_ranges > 0)
+		extra_size += sizeof(struct fdt_reserve_entry) * rmem->nr_ranges;
 
-	/* Loop through all subnodes of cpus and add them to fdt */
-	for_each_node_by_type(dn, "cpu") {
-		cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
-		if (cpus_subnode_offset < 0) {
-			pr_err("Unable to add %s subnode: %s\n", dn->full_name,
-			       fdt_strerror(cpus_subnode_offset));
-			ret = cpus_subnode_offset;
-			goto out;
-		}
-
-		ret = add_node_props(fdt, cpus_subnode_offset, dn);
-		if (ret < 0)
-			goto out;
-	}
-out:
-	of_node_put(dn);
-	return ret;
+	return extra_size + kdump_extra_fdt_size_ppc64(image, cpu_nodes);
 }
 
 static int copy_property(void *fdt, int node_offset, const struct device_node *dn,
@@ -1137,11 +717,15 @@ static int update_pci_dma_nodes(void *fdt, const char *dmapropname)
 			continue;
 
 		ret = copy_property(fdt, pci_offset, dn, "ibm,dma-window");
-		if (ret < 0)
+		if (ret < 0) {
+			of_node_put(dn);
 			break;
+		}
 		ret = copy_property(fdt, pci_offset, dn, dmapropname);
-		if (ret < 0)
+		if (ret < 0) {
+			of_node_put(dn);
 			break;
+		}
 	}
 
 	return ret;
@@ -1152,20 +736,16 @@ static int update_pci_dma_nodes(void *fdt, const char *dmapropname)
  *                       being loaded.
  * @image:               kexec image being loaded.
  * @fdt:                 Flattened device tree for the next kernel.
- * @initrd_load_addr:    Address where the next initrd will be loaded.
- * @initrd_len:          Size of the next initrd, or 0 if there will be none.
- * @cmdline:             Command line for the next kernel, or NULL if there will
- *                       be none.
+ * @rmem:                Reserved memory ranges.
  *
  * Returns 0 on success, negative errno on error.
  */
-int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
-			unsigned long initrd_load_addr,
-			unsigned long initrd_len, const char *cmdline)
+int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem *rmem)
 {
-	struct crash_mem *umem = NULL, *rmem = NULL;
+	struct crash_mem *umem = NULL;
 	int i, nr_ranges, ret;
 
+#ifdef CONFIG_CRASH_DUMP
 	/*
 	 * Restrict memory usage for kdump kernel by setting up
 	 * usable memory ranges and memory reserve map.
@@ -1202,14 +782,13 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
 			goto out;
 		}
 	}
+#endif
 
 	/* Update cpus nodes information to account hotplug CPUs. */
 	ret =  update_cpus_node(fdt);
 	if (ret < 0)
 		goto out;
 
-#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info"
-#define DMA64_PROPNAME "linux,dma64-ddr-window-info"
 	ret = update_pci_dma_nodes(fdt, DIRECT64_PROPNAME);
 	if (ret < 0)
 		goto out;
@@ -1217,14 +796,8 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
 	ret = update_pci_dma_nodes(fdt, DMA64_PROPNAME);
 	if (ret < 0)
 		goto out;
-#undef DMA64_PROPNAME
-#undef DIRECT64_PROPNAME
 
 	/* Update memory reserve map */
-	ret = get_reserved_memory_ranges(&rmem);
-	if (ret)
-		goto out;
-
 	nr_ranges = rmem ? rmem->nr_ranges : 0;
 	for (i = 0; i < nr_ranges; i++) {
 		u64 base, size;
@@ -1244,70 +817,11 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
 		ret = plpks_populate_fdt(fdt);
 
 out:
-	kfree(rmem);
 	kfree(umem);
 	return ret;
 }
 
 /**
- * arch_kexec_locate_mem_hole - Skip special memory regions like rtas, opal,
- *                              tce-table, reserved-ranges & such (exclude
- *                              memory ranges) as they can't be used for kexec
- *                              segment buffer. Sets kbuf->mem when a suitable
- *                              memory hole is found.
- * @kbuf:                       Buffer contents and memory parameters.
- *
- * Assumes minimum of PAGE_SIZE alignment for kbuf->memsz & kbuf->buf_align.
- *
- * Returns 0 on success, negative errno on error.
- */
-int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
-{
-	struct crash_mem **emem;
-	u64 buf_min, buf_max;
-	int ret;
-
-	/* Look up the exclude ranges list while locating the memory hole */
-	emem = &(kbuf->image->arch.exclude_ranges);
-	if (!(*emem) || ((*emem)->nr_ranges == 0)) {
-		pr_warn("No exclude range list. Using the default locate mem hole method\n");
-		return kexec_locate_mem_hole(kbuf);
-	}
-
-	buf_min = kbuf->buf_min;
-	buf_max = kbuf->buf_max;
-	/* Segments for kdump kernel should be within crashkernel region */
-	if (kbuf->image->type == KEXEC_TYPE_CRASH) {
-		buf_min = (buf_min < crashk_res.start ?
-			   crashk_res.start : buf_min);
-		buf_max = (buf_max > crashk_res.end ?
-			   crashk_res.end : buf_max);
-	}
-
-	if (buf_min > buf_max) {
-		pr_err("Invalid buffer min and/or max values\n");
-		return -EINVAL;
-	}
-
-	if (kbuf->top_down)
-		ret = locate_mem_hole_top_down_ppc64(kbuf, buf_min, buf_max,
-						     *emem);
-	else
-		ret = locate_mem_hole_bottom_up_ppc64(kbuf, buf_min, buf_max,
-						      *emem);
-
-	/* Add the buffer allocated to the exclude list for the next lookup */
-	if (!ret) {
-		add_mem_range(emem, kbuf->mem, kbuf->memsz);
-		sort_memory_ranges(*emem, true);
-	} else {
-		pr_err("Failed to locate memory buffer of size %lu\n",
-		       kbuf->memsz);
-	}
-	return ret;
-}
-
-/**
  * arch_kexec_kernel_image_probe - Does additional handling needed to setup
  *                                 kexec segments.
  * @image:                         kexec image being loaded.
diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c
index 5fc53a5fcfdf..867135560e5c 100644
--- a/arch/powerpc/kexec/ranges.c
+++ b/arch/powerpc/kexec/ranges.c
@@ -18,11 +18,15 @@
 
 #include <linux/sort.h>
 #include <linux/kexec.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/slab.h>
+#include <linux/memblock.h>
+#include <linux/crash_core.h>
 #include <asm/sections.h>
 #include <asm/kexec_ranges.h>
+#include <asm/crashdump-ppc64.h>
 
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
 /**
  * get_max_nr_ranges - Get the max no. of ranges crash_mem structure
  *                     could hold, given the size allocated for it.
@@ -234,13 +238,16 @@ int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
 	return __add_mem_range(mem_ranges, base, size);
 }
 
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
+
+#ifdef CONFIG_KEXEC_FILE
 /**
  * add_tce_mem_ranges - Adds tce-table range to the given memory ranges list.
  * @mem_ranges:         Range list to add the memory range(s) to.
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_tce_mem_ranges(struct crash_mem **mem_ranges)
+static int add_tce_mem_ranges(struct crash_mem **mem_ranges)
 {
 	struct device_node *dn = NULL;
 	int ret = 0;
@@ -279,7 +286,7 @@ int add_tce_mem_ranges(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_initrd_mem_range(struct crash_mem **mem_ranges)
+static int add_initrd_mem_range(struct crash_mem **mem_ranges)
 {
 	u64 base, end;
 	int ret;
@@ -296,7 +303,6 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges)
 	return ret;
 }
 
-#ifdef CONFIG_PPC_64S_HASH_MMU
 /**
  * add_htab_mem_range - Adds htab range to the given memory ranges list,
  *                      if it exists
@@ -304,14 +310,18 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_htab_mem_range(struct crash_mem **mem_ranges)
+static int add_htab_mem_range(struct crash_mem **mem_ranges)
 {
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
 	if (!htab_address)
 		return 0;
 
 	return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes);
-}
+#else
+	return 0;
 #endif
+}
 
 /**
  * add_kernel_mem_range - Adds kernel text region to the given
@@ -320,18 +330,20 @@ int add_htab_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_kernel_mem_range(struct crash_mem **mem_ranges)
+static int add_kernel_mem_range(struct crash_mem **mem_ranges)
 {
 	return add_mem_range(mem_ranges, 0, __pa(_end));
 }
+#endif /* CONFIG_KEXEC_FILE */
 
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
 /**
  * add_rtas_mem_range - Adds RTAS region to the given memory ranges list.
  * @mem_ranges:         Range list to add the memory range to.
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_rtas_mem_range(struct crash_mem **mem_ranges)
+static int add_rtas_mem_range(struct crash_mem **mem_ranges)
 {
 	struct device_node *dn;
 	u32 base, size;
@@ -356,7 +368,7 @@ int add_rtas_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_opal_mem_range(struct crash_mem **mem_ranges)
+static int add_opal_mem_range(struct crash_mem **mem_ranges)
 {
 	struct device_node *dn;
 	u64 base, size;
@@ -374,7 +386,9 @@ int add_opal_mem_range(struct crash_mem **mem_ranges)
 	of_node_put(dn);
 	return ret;
 }
+#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */
 
+#ifdef CONFIG_KEXEC_FILE
 /**
  * add_reserved_mem_ranges - Adds "/reserved-ranges" regions exported by f/w
  *                           to the given memory ranges list.
@@ -382,17 +396,19 @@ int add_opal_mem_range(struct crash_mem **mem_ranges)
  *
  * Returns 0 on success, negative errno on error.
  */
-int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
+static int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
 {
 	int n_mem_addr_cells, n_mem_size_cells, i, len, cells, ret = 0;
+	struct device_node *root = of_find_node_by_path("/");
 	const __be32 *prop;
 
-	prop = of_get_property(of_root, "reserved-ranges", &len);
+	prop = of_get_property(root, "reserved-ranges", &len);
+	n_mem_addr_cells = of_n_addr_cells(root);
+	n_mem_size_cells = of_n_size_cells(root);
+	of_node_put(root);
 	if (!prop)
 		return 0;
 
-	n_mem_addr_cells = of_n_addr_cells(of_root);
-	n_mem_size_cells = of_n_size_cells(of_root);
 	cells = n_mem_addr_cells + n_mem_size_cells;
 
 	/* Each reserved range is an (address,size) pair */
@@ -410,3 +426,304 @@ int add_reserved_mem_ranges(struct crash_mem **mem_ranges)
 
 	return ret;
 }
+
+/**
+ * get_reserved_memory_ranges - Get reserve memory ranges. This list includes
+ *                              memory regions that should be added to the
+ *                              memory reserve map to ensure the region is
+ *                              protected from any mischief.
+ * @mem_ranges:                 Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_reserved_memory_ranges(struct crash_mem **mem_ranges)
+{
+	int ret;
+
+	ret = add_rtas_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_tce_mem_ranges(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_reserved_mem_ranges(mem_ranges);
+out:
+	if (ret)
+		pr_err("Failed to setup reserved memory ranges\n");
+	return ret;
+}
+
+/**
+ * get_exclude_memory_ranges - Get exclude memory ranges. This list includes
+ *                             regions like opal/rtas, tce-table, initrd,
+ *                             kernel, htab which should be avoided while
+ *                             setting up kexec load segments.
+ * @mem_ranges:                Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
+{
+	int ret;
+
+	ret = add_tce_mem_ranges(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_initrd_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_htab_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_kernel_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_rtas_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_opal_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_reserved_mem_ranges(mem_ranges);
+	if (ret)
+		goto out;
+
+	/* exclude memory ranges should be sorted for easy lookup */
+	sort_memory_ranges(*mem_ranges, true);
+out:
+	if (ret)
+		pr_err("Failed to setup exclude memory ranges\n");
+	return ret;
+}
+
+#ifdef CONFIG_CRASH_DUMP
+/**
+ * get_usable_memory_ranges - Get usable memory ranges. This list includes
+ *                            regions like crashkernel, opal/rtas & tce-table,
+ *                            that kdump kernel could use.
+ * @mem_ranges:               Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_usable_memory_ranges(struct crash_mem **mem_ranges)
+{
+	int ret, i;
+
+	/*
+	 * Early boot failure observed on guests when low memory (first memory
+	 * block?) is not added to usable memory. So, add [0, crashk_res.end]
+	 * instead of [crashk_res.start, crashk_res.end] to workaround it.
+	 * Also, crashed kernel's memory must be added to reserve map to
+	 * avoid kdump kernel from using it.
+	 */
+	ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1);
+	if (ret)
+		goto out;
+
+	for (i = 0; i < crashk_cma_cnt; i++) {
+		ret = add_mem_range(mem_ranges, crashk_cma_ranges[i].start,
+				    crashk_cma_ranges[i].end - crashk_cma_ranges[i].start + 1);
+		if (ret)
+			goto out;
+	}
+
+	ret = add_rtas_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_opal_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_tce_mem_ranges(mem_ranges);
+out:
+	if (ret)
+		pr_err("Failed to setup usable memory ranges\n");
+	return ret;
+}
+#endif /* CONFIG_CRASH_DUMP */
+#endif /* CONFIG_KEXEC_FILE */
+
+#ifdef CONFIG_CRASH_DUMP
+static int crash_exclude_mem_range_guarded(struct crash_mem **mem_ranges,
+					   unsigned long long mstart,
+					   unsigned long long mend)
+{
+	struct crash_mem *tmem = *mem_ranges;
+
+	/* Reallocate memory ranges if there is no space to split ranges */
+	if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
+		tmem = realloc_mem_ranges(mem_ranges);
+		if (!tmem)
+			return -ENOMEM;
+	}
+
+	return crash_exclude_mem_range(tmem, mstart, mend);
+}
+
+/**
+ * get_crash_memory_ranges - Get crash memory ranges. This list includes
+ *                           first/crashing kernel's memory regions that
+ *                           would be exported via an elfcore.
+ * @mem_ranges:              Range list to add the memory ranges to.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int get_crash_memory_ranges(struct crash_mem **mem_ranges)
+{
+	phys_addr_t base, end;
+	u64 i;
+	int ret;
+
+	for_each_mem_range(i, &base, &end) {
+		u64 size = end - base;
+
+		/* Skip backup memory region, which needs a separate entry */
+		if (base == BACKUP_SRC_START) {
+			if (size > BACKUP_SRC_SIZE) {
+				base = BACKUP_SRC_END + 1;
+				size -= BACKUP_SRC_SIZE;
+			} else
+				continue;
+		}
+
+		ret = add_mem_range(mem_ranges, base, size);
+		if (ret)
+			goto out;
+
+		/* Try merging adjacent ranges before reallocation attempt */
+		if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges)
+			sort_memory_ranges(*mem_ranges, true);
+	}
+
+	/* Exclude crashkernel region */
+	ret = crash_exclude_mem_range_guarded(mem_ranges, crashk_res.start, crashk_res.end);
+	if (ret)
+		goto out;
+
+	for (i = 0; i < crashk_cma_cnt; ++i) {
+		ret = crash_exclude_mem_range_guarded(mem_ranges, crashk_cma_ranges[i].start,
+					      crashk_cma_ranges[i].end);
+		if (ret)
+			goto out;
+	}
+
+	/*
+	 * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
+	 *        regions are exported to save their context at the time of
+	 *        crash, they should actually be backed up just like the
+	 *        first 64K bytes of memory.
+	 */
+	ret = add_rtas_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	ret = add_opal_mem_range(mem_ranges);
+	if (ret)
+		goto out;
+
+	/* create a separate program header for the backup region */
+	ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE);
+	if (ret)
+		goto out;
+
+	sort_memory_ranges(*mem_ranges, false);
+out:
+	if (ret)
+		pr_err("Failed to setup crash memory ranges\n");
+	return ret;
+}
+
+/**
+ * remove_mem_range - Removes the given memory range from the range list.
+ * @mem_ranges:    Range list to remove the memory range to.
+ * @base:          Base address of the range to remove.
+ * @size:          Size of the memory range to remove.
+ *
+ * (Re)allocates memory, if needed.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
+{
+	u64 end;
+	int ret = 0;
+	unsigned int i;
+	u64 mstart, mend;
+	struct crash_mem *mem_rngs = *mem_ranges;
+
+	if (!size)
+		return 0;
+
+	/*
+	 * Memory range are stored as start and end address, use
+	 * the same format to do remove operation.
+	 */
+	end = base + size - 1;
+
+	for (i = 0; i < mem_rngs->nr_ranges; i++) {
+		mstart = mem_rngs->ranges[i].start;
+		mend = mem_rngs->ranges[i].end;
+
+		/*
+		 * Memory range to remove is not part of this range entry
+		 * in the memory range list
+		 */
+		if (!(base >= mstart && end <= mend))
+			continue;
+
+		/*
+		 * Memory range to remove is equivalent to this entry in the
+		 * memory range list. Remove the range entry from the list.
+		 */
+		if (base == mstart && end == mend) {
+			for (; i < mem_rngs->nr_ranges - 1; i++) {
+				mem_rngs->ranges[i].start = mem_rngs->ranges[i+1].start;
+				mem_rngs->ranges[i].end = mem_rngs->ranges[i+1].end;
+			}
+			mem_rngs->nr_ranges--;
+			goto out;
+		}
+		/*
+		 * Start address of the memory range to remove and the
+		 * current memory range entry in the list is same. Just
+		 * move the start address of the current memory range
+		 * entry in the list to end + 1.
+		 */
+		else if (base == mstart) {
+			mem_rngs->ranges[i].start = end + 1;
+			goto out;
+		}
+		/*
+		 * End address of the memory range to remove and the
+		 * current memory range entry in the list is same.
+		 * Just move the end address of the current memory
+		 * range entry in the list to base - 1.
+		 */
+		else if (end == mend)  {
+			mem_rngs->ranges[i].end = base - 1;
+			goto out;
+		}
+		/*
+		 * Memory range to remove is not at the edge of current
+		 * memory range entry. Split the current memory entry into
+		 * two half.
+		 */
+		else {
+			size = mem_rngs->ranges[i].end - end + 1;
+			mem_rngs->ranges[i].end = base - 1;
+			ret = add_mem_range(mem_ranges, end + 1, size);
+		}
+	}
+out:
+	return ret;
+}
+#endif /* CONFIG_CRASH_DUMP */
diff --git a/arch/powerpc/kexec/relocate_32.S b/arch/powerpc/kexec/relocate_32.S
index d9f0dd9b34ff..dd86e338307d 100644
--- a/arch/powerpc/kexec/relocate_32.S
+++ b/arch/powerpc/kexec/relocate_32.S
@@ -8,6 +8,7 @@
  * 		Author: Suzuki Poulose <suzuki@in.ibm.com>
  */
 
+#include <linux/objtool.h>
 #include <asm/reg.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -347,15 +348,13 @@ write_utlb:
 	rlwinm	r10, r24, 0, 22, 27
 
 	cmpwi	r10, PPC47x_TLB0_4K
-	bne	0f
 	li	r10, 0x1000			/* r10 = 4k */
-	bl	1f
+	beq	0f
 
-0:
 	/* Defaults to 256M */
 	lis	r10, 0x1000
 
-	bcl	20,31,$+4
+0:	bcl	20,31,$+4
 1:	mflr	r4
 	addi	r4, r4, (2f-1b)			/* virtual address  of 2f */
 
diff --git a/arch/powerpc/kexec/vmcore_info.c b/arch/powerpc/kexec/vmcore_info.c
new file mode 100644
index 000000000000..2b65d2adca5e
--- /dev/null
+++ b/arch/powerpc/kexec/vmcore_info.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/vmcore_info.h>
+#include <asm/pgalloc.h>
+
+void arch_crash_save_vmcoreinfo(void)
+{
+
+#ifdef CONFIG_NUMA
+	VMCOREINFO_SYMBOL(node_data);
+	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
+#endif
+#ifndef CONFIG_NUMA
+	VMCOREINFO_SYMBOL(contig_page_data);
+#endif
+#if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP)
+	VMCOREINFO_SYMBOL(vmemmap_list);
+	VMCOREINFO_SYMBOL(mmu_vmemmap_psize);
+	VMCOREINFO_SYMBOL(mmu_psize_defs);
+	VMCOREINFO_STRUCT_SIZE(vmemmap_backing);
+	VMCOREINFO_OFFSET(vmemmap_backing, list);
+	VMCOREINFO_OFFSET(vmemmap_backing, phys);
+	VMCOREINFO_OFFSET(vmemmap_backing, virt_addr);
+	VMCOREINFO_STRUCT_SIZE(mmu_psize_def);
+	VMCOREINFO_OFFSET(mmu_psize_def, shift);
+#endif
+	VMCOREINFO_SYMBOL(cur_cpu_spec);
+	VMCOREINFO_OFFSET(cpu_spec, cpu_features);
+	VMCOREINFO_OFFSET(cpu_spec, mmu_features);
+	vmcoreinfo_append_str("NUMBER(RADIX_MMU)=%d\n", early_radix_enabled());
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+}
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 902611954200..c9a2d50ff1b0 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -19,13 +19,9 @@ if VIRTUALIZATION
 
 config KVM
 	bool
-	select PREEMPT_NOTIFIERS
-	select HAVE_KVM_EVENTFD
-	select HAVE_KVM_VCPU_ASYNC_IOCTL
+	select KVM_COMMON
 	select KVM_VFIO
-	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
-	select INTERVAL_TREE
 
 config KVM_BOOK3S_HANDLER
 	bool
@@ -42,7 +38,7 @@ config KVM_BOOK3S_64_HANDLER
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 
 config KVM_BOOK3S_HV_POSSIBLE
 	bool
@@ -85,7 +81,8 @@ config KVM_BOOK3S_64_HV
 	tristate "KVM for POWER7 and later using hypervisor mode in host"
 	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
+	select KVM_BOOK3S_HV_PMU
 	select CMA
 	help
 	  Support running unmodified book3s_64 guest kernels in
@@ -174,6 +171,18 @@ config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND
 	  those buggy L1s which saves the L2 state, at the cost of performance
 	  in all nested-capable guest entry/exit.
 
+config KVM_BOOK3S_HV_PMU
+	tristate "Hypervisor Perf events for KVM Book3s-HV"
+	depends on KVM_BOOK3S_64_HV
+	help
+	  Enable Book3s-HV Hypervisor Perf events PMU named 'kvm-hv'. These
+	  Perf events give an overview of hypervisor performance overall
+	  instead of a specific guests. Currently the PMU reports
+	  L0-Hypervisor stats on a kvm-hv enabled PSeries LPAR like:
+	  * Total/Used Guest-Heap
+	  * Total/Used Guest Page-table Memory
+	  * Total amount of Guest Page-table Memory reclaimed
+
 config KVM_BOOKE_HV
 	bool
 
@@ -194,7 +203,7 @@ config KVM_E500V2
 	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500v2 host processors.
@@ -211,7 +220,7 @@ config KVM_E500MC
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500MC/E5500/E6500 guest kernels in
 	  virtual machines on E500MC/E5500/E6500 host processors.
@@ -225,7 +234,6 @@ config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM && PPC_E500
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	help
@@ -238,7 +246,6 @@ config KVM_XICS
 	bool "KVM in-kernel XICS emulation"
 	depends on KVM_BOOK3S_64 && !KVM_MPIC
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	default y
 	help
 	  Include support for the XICS (eXternal Interrupt Controller
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 5319d889b184..4bd9d1230869 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -87,8 +87,12 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
 	book3s_hv_p9_perf.o \
+	book3s_hv_nestedv2.o \
+	guest-state-buffer.o \
 	$(kvm-book3s_64-builtin-tm-objs-y) \
 	$(kvm-book3s_64-builtin-xics-objs-y)
+
+obj-$(CONFIG_GUEST_STATE_BUFFER_TEST) += test-guest-state-buffer.o
 endif
 
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 686d8d9eda3e..d79c5d1098c0 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -302,11 +302,11 @@ static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
 
 	switch (priority) {
 	case BOOK3S_IRQPRIO_DECREMENTER:
-		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
+		deliver = !kvmhv_is_nestedv2() && (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
-		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
+		deliver = !kvmhv_is_nestedv2() && (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
 	case BOOK3S_IRQPRIO_SYSTEM_RESET:
@@ -360,10 +360,6 @@ static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-#if 0
-	printk(KERN_INFO "Deliver interrupt 0x%x? %x\n", vec, deliver);
-#endif
-
 	if (deliver)
 		kvmppc_inject_interrupt(vcpu, vec, 0);
 
@@ -426,7 +422,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter);
 
 kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing,
-			bool *writable)
+			    bool *writable, struct page **page)
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM;
 	gfn_t gfn = gpa >> PAGE_SHIFT;
@@ -441,13 +437,14 @@ kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing,
 		kvm_pfn_t pfn;
 
 		pfn = (kvm_pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT;
-		get_page(pfn_to_page(pfn));
+		*page = pfn_to_page(pfn);
+		get_page(*page);
 		if (writable)
 			*writable = true;
 		return pfn;
 	}
 
-	return gfn_to_pfn_prot(vcpu->kvm, gfn, writing, writable);
+	return kvm_faultin_pfn(vcpu, gfn, writing, writable, page);
 }
 EXPORT_SYMBOL_GPL(kvmppc_gpa_to_pfn);
 
@@ -565,7 +562,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->msr = kvmppc_get_msr(vcpu);
 	regs->srr0 = kvmppc_get_srr0(vcpu);
 	regs->srr1 = kvmppc_get_srr1(vcpu);
-	regs->pid = vcpu->arch.pid;
+	regs->pid = kvmppc_get_pid(vcpu);
 	regs->sprg0 = kvmppc_get_sprg0(vcpu);
 	regs->sprg1 = kvmppc_get_sprg1(vcpu);
 	regs->sprg2 = kvmppc_get_sprg2(vcpu);
@@ -636,17 +633,17 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 			i = id - KVM_REG_PPC_FPR0;
-			*val = get_reg_val(id, VCPU_FPR(vcpu, i));
+			*val = get_reg_val(id, kvmppc_get_fpr(vcpu, i));
 			break;
 		case KVM_REG_PPC_FPSCR:
-			*val = get_reg_val(id, vcpu->arch.fp.fpscr);
+			*val = get_reg_val(id, kvmppc_get_fpscr(vcpu));
 			break;
 #ifdef CONFIG_VSX
 		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
 			if (cpu_has_feature(CPU_FTR_VSX)) {
 				i = id - KVM_REG_PPC_VSR0;
-				val->vsxval[0] = vcpu->arch.fp.fpr[i][0];
-				val->vsxval[1] = vcpu->arch.fp.fpr[i][1];
+				val->vsxval[0] = kvmppc_get_vsx_fpr(vcpu, i, 0);
+				val->vsxval[1] = kvmppc_get_vsx_fpr(vcpu, i, 1);
 			} else {
 				r = -ENXIO;
 			}
@@ -683,19 +680,19 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
 			*val = get_reg_val(id, vcpu->arch.fscr);
 			break;
 		case KVM_REG_PPC_TAR:
-			*val = get_reg_val(id, vcpu->arch.tar);
+			*val = get_reg_val(id, kvmppc_get_tar(vcpu));
 			break;
 		case KVM_REG_PPC_EBBHR:
-			*val = get_reg_val(id, vcpu->arch.ebbhr);
+			*val = get_reg_val(id, kvmppc_get_ebbhr(vcpu));
 			break;
 		case KVM_REG_PPC_EBBRR:
-			*val = get_reg_val(id, vcpu->arch.ebbrr);
+			*val = get_reg_val(id, kvmppc_get_ebbrr(vcpu));
 			break;
 		case KVM_REG_PPC_BESCR:
-			*val = get_reg_val(id, vcpu->arch.bescr);
+			*val = get_reg_val(id, kvmppc_get_bescr(vcpu));
 			break;
 		case KVM_REG_PPC_IC:
-			*val = get_reg_val(id, vcpu->arch.ic);
+			*val = get_reg_val(id, kvmppc_get_ic(vcpu));
 			break;
 		default:
 			r = -EINVAL;
@@ -724,7 +721,7 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
 			i = id - KVM_REG_PPC_FPR0;
-			VCPU_FPR(vcpu, i) = set_reg_val(id, *val);
+			kvmppc_set_fpr(vcpu, i, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_FPSCR:
 			vcpu->arch.fp.fpscr = set_reg_val(id, *val);
@@ -733,8 +730,8 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
 			if (cpu_has_feature(CPU_FTR_VSX)) {
 				i = id - KVM_REG_PPC_VSR0;
-				vcpu->arch.fp.fpr[i][0] = val->vsxval[0];
-				vcpu->arch.fp.fpr[i][1] = val->vsxval[1];
+				kvmppc_set_vsx_fpr(vcpu, i, 0, val->vsxval[0]);
+				kvmppc_set_vsx_fpr(vcpu, i, 1, val->vsxval[1]);
 			} else {
 				r = -ENXIO;
 			}
@@ -765,22 +762,22 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 			break;
 #endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
-			vcpu->arch.fscr = set_reg_val(id, *val);
+			kvmppc_set_fpscr(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_TAR:
-			vcpu->arch.tar = set_reg_val(id, *val);
+			kvmppc_set_tar(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_EBBHR:
-			vcpu->arch.ebbhr = set_reg_val(id, *val);
+			kvmppc_set_ebbhr(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_EBBRR:
-			vcpu->arch.ebbrr = set_reg_val(id, *val);
+			kvmppc_set_ebbrr(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_BESCR:
-			vcpu->arch.bescr = set_reg_val(id, *val);
+			kvmppc_set_bescr(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_IC:
-			vcpu->arch.ic = set_reg_val(id, *val);
+			kvmppc_set_ic(vcpu, set_reg_val(id, *val));
 			break;
 		default:
 			r = -EINVAL;
@@ -899,11 +896,6 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	return kvm->arch.kvm_ops->test_age_gfn(kvm, range);
 }
 
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	return kvm->arch.kvm_ops->set_spte_gfn(kvm, range);
-}
-
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
 
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index 58391b4b32ed..4aa2ab89afbc 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -12,7 +12,6 @@ extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
 extern bool kvm_unmap_gfn_range_hv(struct kvm *kvm, struct kvm_gfn_range *range);
 extern bool kvm_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
 extern bool kvm_test_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
-extern bool kvm_set_spte_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range);
 
 extern int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu);
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 4b3a8d80cfa3..c7e4b62642ea 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -125,11 +125,10 @@ static u32 *kvmppc_mmu_get_pteg(struct kvm_vcpu *vcpu, u32 vsid, u32 eaddr,
 	return (u32*)pteg;
 }
 
-extern char etext[];
-
 int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 			bool iswrite)
 {
+	struct page *page;
 	kvm_pfn_t hpaddr;
 	u64 vpn;
 	u64 vsid;
@@ -145,7 +144,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	bool writable;
 
 	/* Get host physical address for gpa */
-	hpaddr = kvmppc_gpa_to_pfn(vcpu, orig_pte->raddr, iswrite, &writable);
+	hpaddr = kvmppc_gpa_to_pfn(vcpu, orig_pte->raddr, iswrite, &writable, &page);
 	if (is_error_noslot_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gpa %lx!\n",
 				 orig_pte->raddr);
@@ -232,7 +231,7 @@ next_pteg:
 
 	pte = kvmppc_mmu_hpte_cache_next(vcpu);
 	if (!pte) {
-		kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
+		kvm_release_page_unused(page);
 		r = -EAGAIN;
 		goto out;
 	}
@@ -250,7 +249,7 @@ next_pteg:
 
 	kvmppc_mmu_hpte_cache_map(vcpu, pte);
 
-	kvm_release_pfn_clean(hpaddr >> PAGE_SHIFT);
+	kvm_release_page_clean(page);
 out:
 	return r;
 }
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 6c2b1d17cb63..a9ab92abffe8 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -1,9 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
+#include <linux/export.h>
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
 #include <asm/code-patching-asm.h>
 #include <asm/exception-64s.h>
-#include <asm/export.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_book3s_asm.h>
 #include <asm/mmu.h>
@@ -19,7 +19,7 @@
 
 /*
  * This is a hcall, so register convention is as
- * Documentation/powerpc/papr_hcalls.rst.
+ * Documentation/arch/powerpc/papr_hcalls.rst.
  *
  * This may also be a syscall from PR-KVM userspace that is to be
  * reflected to the PR guest kernel, so registers may be set up for
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index bc6a381b5346..be20aee6fd7d 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -88,13 +88,14 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	struct hpte_cache *cpte;
 	unsigned long gfn = orig_pte->raddr >> PAGE_SHIFT;
 	unsigned long pfn;
+	struct page *page;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* Get host physical address for gpa */
-	pfn = kvmppc_gpa_to_pfn(vcpu, orig_pte->raddr, iswrite, &writable);
+	pfn = kvmppc_gpa_to_pfn(vcpu, orig_pte->raddr, iswrite, &writable, &page);
 	if (is_error_noslot_pfn(pfn)) {
 		printk(KERN_INFO "Couldn't get guest page for gpa %lx!\n",
 		       orig_pte->raddr);
@@ -121,13 +122,10 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 
 	vpn = hpt_vpn(orig_pte->eaddr, map->host_vsid, MMU_SEGSIZE_256M);
 
-	kvm_set_pfn_accessed(pfn);
 	if (!orig_pte->may_write || !writable)
 		rflags |= PP_RXRX;
-	else {
+	else
 		mark_page_dirty(vcpu->kvm, gfn);
-		kvm_set_pfn_dirty(pfn);
-	}
 
 	if (!orig_pte->may_execute)
 		rflags |= HPTE_R_N;
@@ -202,8 +200,10 @@ map_again:
 	}
 
 out_unlock:
+	/* FIXME: Don't unconditionally pass unused=false. */
+	kvm_release_faultin_page(kvm, page, false,
+				 orig_pte->may_write && writable);
 	spin_unlock(&kvm->mmu_lock);
-	kvm_release_pfn_clean(pfn);
 	if (cpte)
 		kvmppc_mmu_hpte_cache_free(cpte);
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 7f765d5ad436..f305395cf26e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -28,6 +28,7 @@
 #include <asm/pte-walk.h>
 
 #include "book3s.h"
+#include "book3s_hv.h"
 #include "trace_hv.h"
 
 //#define DEBUG_RESIZE_HPT	1
@@ -120,7 +121,7 @@ void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info)
 	kvm->arch.hpt = *info;
 	kvm->arch.sdr1 = __pa(info->virt) | (info->order - 18);
 
-	pr_debug("KVM guest htab at %lx (order %ld), LPID %x\n",
+	pr_debug("KVM guest htab at %lx (order %ld), LPID %llx\n",
 		 info->virt, (long)info->order, kvm->arch.lpid);
 }
 
@@ -182,7 +183,7 @@ void kvmppc_free_hpt(struct kvm_hpt_info *info)
 	vfree(info->rev);
 	info->rev = NULL;
 	if (info->cma)
-		kvm_free_hpt_cma(virt_to_page(info->virt),
+		kvm_free_hpt_cma(virt_to_page((void *)info->virt),
 				 1 << (info->order - PAGE_SHIFT));
 	else if (info->virt)
 		free_pages(info->virt, info->order - PAGE_SHIFT);
@@ -347,7 +348,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	unsigned long v, orig_v, gr;
 	__be64 *hptep;
 	long int index;
-	int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);
+	int virtmode = __kvmppc_get_msr_hv(vcpu) & (data ? MSR_DR : MSR_IR);
 
 	if (kvm_is_radix(vcpu->kvm))
 		return kvmppc_mmu_radix_xlate(vcpu, eaddr, gpte, data, iswrite);
@@ -385,7 +386,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 	/* Get PP bits and key for permission check */
 	pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
-	key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
+	key = (__kvmppc_get_msr_hv(vcpu) & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
 	key &= slb_v;
 
 	/* Calculate permissions */
@@ -602,27 +603,10 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
 	write_ok = writing;
 	hva = gfn_to_hva_memslot(memslot, gfn);
 
-	/*
-	 * Do a fast check first, since __gfn_to_pfn_memslot doesn't
-	 * do it with !atomic && !async, which is how we call it.
-	 * We always ask for write permission since the common case
-	 * is that the page is writable.
-	 */
-	if (get_user_page_fast_only(hva, FOLL_WRITE, &page)) {
-		write_ok = true;
-	} else {
-		/* Call KVM generic code to do the slow-path check */
-		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
-					   writing, &write_ok, NULL);
-		if (is_error_noslot_pfn(pfn))
-			return -EFAULT;
-		page = NULL;
-		if (pfn_valid(pfn)) {
-			page = pfn_to_page(pfn);
-			if (PageReserved(page))
-				page = NULL;
-		}
-	}
+	pfn = __kvm_faultin_pfn(memslot, gfn, writing ? FOLL_WRITE : 0,
+				&write_ok, &page);
+	if (is_error_noslot_pfn(pfn))
+		return -EFAULT;
 
 	/*
 	 * Read the PTE from the process' radix tree and use that
@@ -1009,18 +993,6 @@ bool kvm_test_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range)
 		return kvm_test_age_rmapp(kvm, range->slot, range->start);
 }
 
-bool kvm_set_spte_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	WARN_ON(range->start + 1 != range->end);
-
-	if (kvm_is_radix(kvm))
-		kvm_unmap_radix(kvm, range->slot, range->start);
-	else
-		kvm_unmap_rmapp(kvm, range->slot, range->start);
-
-	return false;
-}
-
 static int vcpus_running(struct kvm *kvm)
 {
 	return atomic_read(&kvm->arch.vcpus_running) != 0;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 461307b89c3a..b3e6e73d6a08 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -15,6 +15,7 @@
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
+#include "book3s_hv.h"
 #include <asm/page.h>
 #include <asm/mmu.h>
 #include <asm/pgalloc.h>
@@ -39,6 +40,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	unsigned long quadrant, ret = n;
 	bool is_load = !!to;
 
+	if (kvmhv_is_nestedv2())
+		return H_UNSUPPORTED;
+
 	/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
 	if (kvmhv_on_pseries())
 		return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
@@ -96,7 +100,7 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 					  void *to, void *from, unsigned long n)
 {
 	int lpid = vcpu->kvm->arch.lpid;
-	int pid = vcpu->arch.pid;
+	int pid;
 
 	/* This would cause a data segment intr so don't allow the access */
 	if (eaddr & (0x3FFUL << 52))
@@ -109,6 +113,8 @@ static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* If accessing quadrant 3 then pid is expected to be 0 */
 	if (((eaddr >> 62) & 0x3) == 0x3)
 		pid = 0;
+	else
+		pid = kvmppc_get_pid(vcpu);
 
 	eaddr &= ~(0xFFFUL << 52);
 
@@ -270,7 +276,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Work out effective PID */
 	switch (eaddr >> 62) {
 	case 0:
-		pid = vcpu->arch.pid;
+		pid = kvmppc_get_pid(vcpu);
 		break;
 	case 3:
 		pid = 0;
@@ -294,9 +300,9 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	} else {
 		if (!(pte & _PAGE_PRIVILEGED)) {
 			/* Check AMR/IAMR to see if strict mode is in force */
-			if (vcpu->arch.amr & (1ul << 62))
+			if (kvmppc_get_amr_hv(vcpu) & (1ul << 62))
 				gpte->may_read = 0;
-			if (vcpu->arch.amr & (1ul << 63))
+			if (kvmppc_get_amr_hv(vcpu) & (1ul << 63))
 				gpte->may_write = 0;
 			if (vcpu->arch.iamr & (1ul << 62))
 				gpte->may_execute = 0;
@@ -307,7 +313,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 }
 
 void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
-			     unsigned int pshift, unsigned int lpid)
+			     unsigned int pshift, u64 lpid)
 {
 	unsigned long psize = PAGE_SIZE;
 	int psi;
@@ -344,7 +350,7 @@ void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 		pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc);
 }
 
-static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
+static void kvmppc_radix_flush_pwc(struct kvm *kvm, u64 lpid)
 {
 	long rc;
 
@@ -417,7 +423,7 @@ static void kvmppc_pmd_free(pmd_t *pmdp)
 void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
 		      unsigned int shift,
 		      const struct kvm_memory_slot *memslot,
-		      unsigned int lpid)
+		      u64 lpid)
 
 {
 	unsigned long old;
@@ -468,7 +474,7 @@ void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
  * (or 4kB) mappings (of sub-pages of the same 2MB page).
  */
 static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
-				  unsigned int lpid)
+				  u64 lpid)
 {
 	if (full) {
 		memset(pte, 0, sizeof(long) << RADIX_PTE_INDEX_SIZE);
@@ -489,7 +495,7 @@ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
 }
 
 static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
-				  unsigned int lpid)
+				  u64 lpid)
 {
 	unsigned long im;
 	pmd_t *p = pmd;
@@ -497,7 +503,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
 	for (im = 0; im < PTRS_PER_PMD; ++im, ++p) {
 		if (!pmd_present(*p))
 			continue;
-		if (pmd_is_leaf(*p)) {
+		if (pmd_leaf(*p)) {
 			if (full) {
 				pmd_clear(p);
 			} else {
@@ -509,7 +515,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
 		} else {
 			pte_t *pte;
 
-			pte = pte_offset_map(p, 0);
+			pte = pte_offset_kernel(p, 0);
 			kvmppc_unmap_free_pte(kvm, pte, full, lpid);
 			pmd_clear(p);
 		}
@@ -518,7 +524,7 @@ static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
 }
 
 static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
-				  unsigned int lpid)
+				  u64 lpid)
 {
 	unsigned long iu;
 	pud_t *p = pud;
@@ -526,7 +532,7 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
 	for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++p) {
 		if (!pud_present(*p))
 			continue;
-		if (pud_is_leaf(*p)) {
+		if (pud_leaf(*p)) {
 			pud_clear(p);
 		} else {
 			pmd_t *pmd;
@@ -539,7 +545,7 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
 	pud_free(kvm->mm, pud);
 }
 
-void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, unsigned int lpid)
+void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, u64 lpid)
 {
 	unsigned long ig;
 
@@ -566,7 +572,7 @@ void kvmppc_free_radix(struct kvm *kvm)
 }
 
 static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
-					unsigned long gpa, unsigned int lpid)
+					unsigned long gpa, u64 lpid)
 {
 	pte_t *pte = pte_offset_kernel(pmd, 0);
 
@@ -582,7 +588,7 @@ static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
 }
 
 static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
-					unsigned long gpa, unsigned int lpid)
+					unsigned long gpa, u64 lpid)
 {
 	pmd_t *pmd = pmd_offset(pud, 0);
 
@@ -608,7 +614,7 @@ static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
 
 int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		      unsigned long gpa, unsigned int level,
-		      unsigned long mmu_seq, unsigned int lpid,
+		      unsigned long mmu_seq, u64 lpid,
 		      unsigned long *rmapp, struct rmap_nested **n_rmap)
 {
 	pgd_t *pgd;
@@ -629,12 +635,12 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		new_pud = pud_alloc_one(kvm->mm, gpa);
 
 	pmd = NULL;
-	if (pud && pud_present(*pud) && !pud_is_leaf(*pud))
+	if (pud && pud_present(*pud) && !pud_leaf(*pud))
 		pmd = pmd_offset(pud, gpa);
 	else if (level <= 1)
 		new_pmd = kvmppc_pmd_alloc();
 
-	if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd)))
+	if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_leaf(*pmd)))
 		new_ptep = kvmppc_pte_alloc();
 
 	/* Check if we might have been invalidated; let the guest retry if so */
@@ -652,7 +658,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		new_pud = NULL;
 	}
 	pud = pud_offset(p4d, gpa);
-	if (pud_is_leaf(*pud)) {
+	if (pud_leaf(*pud)) {
 		unsigned long hgpa = gpa & PUD_MASK;
 
 		/* Check if we raced and someone else has set the same thing */
@@ -703,7 +709,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		new_pmd = NULL;
 	}
 	pmd = pmd_offset(pud, gpa);
-	if (pmd_is_leaf(*pmd)) {
+	if (pmd_leaf(*pmd)) {
 		unsigned long lgpa = gpa & PMD_MASK;
 
 		/* Check if we raced and someone else has set the same thing */
@@ -785,7 +791,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 }
 
 bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing,
-			     unsigned long gpa, unsigned int lpid)
+			     unsigned long gpa, u64 lpid)
 {
 	unsigned long pgflags;
 	unsigned int shift;
@@ -815,7 +821,7 @@ bool kvmppc_hv_handle_set_rc(struct kvm *kvm, bool nested, bool writing,
 int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 				   unsigned long gpa,
 				   struct kvm_memory_slot *memslot,
-				   bool writing, bool kvm_ro,
+				   bool writing,
 				   pte_t *inserted_pte, unsigned int *levelp)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -823,40 +829,21 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 	unsigned long mmu_seq;
 	unsigned long hva, gfn = gpa >> PAGE_SHIFT;
 	bool upgrade_write = false;
-	bool *upgrade_p = &upgrade_write;
 	pte_t pte, *ptep;
 	unsigned int shift, level;
 	int ret;
 	bool large_enable;
+	kvm_pfn_t pfn;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
-	/*
-	 * Do a fast check first, since __gfn_to_pfn_memslot doesn't
-	 * do it with !atomic && !async, which is how we call it.
-	 * We always ask for write permission since the common case
-	 * is that the page is writable.
-	 */
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	if (!kvm_ro && get_user_page_fast_only(hva, FOLL_WRITE, &page)) {
-		upgrade_write = true;
-	} else {
-		unsigned long pfn;
-
-		/* Call KVM generic code to do the slow-path check */
-		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
-					   writing, upgrade_p, NULL);
-		if (is_error_noslot_pfn(pfn))
-			return -EFAULT;
-		page = NULL;
-		if (pfn_valid(pfn)) {
-			page = pfn_to_page(pfn);
-			if (PageReserved(page))
-				page = NULL;
-		}
-	}
+	pfn = __kvm_faultin_pfn(memslot, gfn, writing ? FOLL_WRITE : 0,
+				&upgrade_write, &page);
+	if (is_error_noslot_pfn(pfn))
+		return -EFAULT;
 
 	/*
 	 * Read the PTE from the process' radix tree and use that
@@ -944,7 +931,6 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
 	struct kvm_memory_slot *memslot;
 	long ret;
 	bool writing = !!(dsisr & DSISR_ISSTORE);
-	bool kvm_ro = false;
 
 	/* Check for unusual errors */
 	if (dsisr & DSISR_UNSUPP_MMU) {
@@ -997,7 +983,6 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
 					ea, DSISR_ISSTORE | DSISR_PROTFAULT);
 			return RESUME_GUEST;
 		}
-		kvm_ro = true;
 	}
 
 	/* Failed to set the reference/change bits */
@@ -1015,7 +1000,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
 
 	/* Try to insert a pte */
 	ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot, writing,
-					     kvm_ro, NULL, NULL);
+					     NULL, NULL);
 
 	if (ret == 0 || ret == -EAGAIN)
 		ret = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 93b695b289e9..742aa58a7c7e 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -20,6 +20,7 @@
 #include <linux/iommu.h>
 #include <linux/file.h>
 #include <linux/mm.h>
+#include <linux/rcupdate_wait.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -77,8 +78,8 @@ static void kvm_spapr_tce_liobn_put(struct kref *kref)
 	call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
 }
 
-extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
-		struct iommu_group *grp)
+void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+				       struct iommu_group *grp)
 {
 	int i;
 	struct kvmppc_spapr_tce_table *stt;
@@ -105,8 +106,8 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
 	rcu_read_unlock();
 }
 
-extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
-		struct iommu_group *grp)
+long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+				      struct iommu_group *grp)
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
 	bool found = false;
@@ -114,23 +115,20 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 	struct iommu_table_group *table_group;
 	long i;
 	struct kvmppc_spapr_tce_iommu_table *stit;
-	struct fd f;
+	CLASS(fd, f)(tablefd);
 
-	f = fdget(tablefd);
-	if (!f.file)
+	if (fd_empty(f))
 		return -EBADF;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt == f.file->private_data) {
+		if (stt == fd_file(f)->private_data) {
 			found = true;
 			break;
 		}
 	}
 	rcu_read_unlock();
 
-	fdput(f);
-
 	if (!found)
 		return -EINVAL;
 
@@ -786,12 +784,12 @@ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	idx = (ioba >> stt->page_shift) - stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
 	if (!page) {
-		vcpu->arch.regs.gpr[4] = 0;
+		kvmppc_set_gpr(vcpu, 4, 0);
 		return H_SUCCESS;
 	}
 	tbl = (u64 *)page_address(page);
 
-	vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];
+	kvmppc_set_gpr(vcpu, 4, tbl[idx % TCES_PER_PAGE]);
 
 	return H_SUCCESS;
 }
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 5bbfb2eed127..de126d153328 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -714,7 +714,7 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_HID1:
 		to_book3s(vcpu)->hid[1] = spr_val;
 		break;
-	case SPRN_HID2:
+	case SPRN_HID2_750FX:
 		to_book3s(vcpu)->hid[2] = spr_val;
 		break;
 	case SPRN_HID2_GEKKO:
@@ -900,7 +900,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val
 	case SPRN_HID1:
 		*spr_val = to_book3s(vcpu)->hid[1];
 		break;
-	case SPRN_HID2:
+	case SPRN_HID2_750FX:
 	case SPRN_HID2_GEKKO:
 		*spr_val = to_book3s(vcpu)->hid[2];
 		break;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 130bafdb1430..7667563fb9ff 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -391,13 +391,34 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 /* Dummy value used in computing PCR value below */
 #define PCR_ARCH_31    (PCR_ARCH_300 << 1)
 
+static inline unsigned long map_pcr_to_cap(unsigned long pcr)
+{
+	unsigned long cap = 0;
+
+	switch (pcr) {
+	case PCR_ARCH_300:
+		cap = H_GUEST_CAP_POWER9;
+		break;
+	case PCR_ARCH_31:
+		if (cpu_has_feature(CPU_FTR_P11_PVR))
+			cap = H_GUEST_CAP_POWER11;
+		else
+			cap = H_GUEST_CAP_POWER10;
+		break;
+	default:
+		break;
+	}
+
+	return cap;
+}
+
 static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 {
-	unsigned long host_pcr_bit = 0, guest_pcr_bit = 0;
+	unsigned long host_pcr_bit = 0, guest_pcr_bit = 0, cap = 0;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
 	/* We can (emulate) our own architecture version and anything older */
-	if (cpu_has_feature(CPU_FTR_ARCH_31))
+	if (cpu_has_feature(CPU_FTR_P11_PVR) || cpu_has_feature(CPU_FTR_ARCH_31))
 		host_pcr_bit = PCR_ARCH_31;
 	else if (cpu_has_feature(CPU_FTR_ARCH_300))
 		host_pcr_bit = PCR_ARCH_300;
@@ -426,6 +447,7 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 			guest_pcr_bit = PCR_ARCH_300;
 			break;
 		case PVR_ARCH_31:
+		case PVR_ARCH_31_P11:
 			guest_pcr_bit = PCR_ARCH_31;
 			break;
 		default:
@@ -437,8 +459,20 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 	if (guest_pcr_bit > host_pcr_bit)
 		return -EINVAL;
 
+	if (kvmhv_on_pseries() && kvmhv_is_nestedv2()) {
+		/*
+		 * 'arch_compat == 0' would mean the guest should default to
+		 * L1's compatibility. In this case, the guest would pick
+		 * host's PCR and evaluate the corresponding capabilities.
+		 */
+		cap = map_pcr_to_cap(guest_pcr_bit);
+		if (!(cap & nested_capabilities))
+			return -EINVAL;
+	}
+
 	spin_lock(&vc->lock);
 	vc->arch_compat = arch_compat;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LOGICAL_PVR);
 	/*
 	 * Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit
 	 * Also set all reserved PCR bits
@@ -642,7 +676,8 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 	return err;
 }
 
-static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
+static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap,
+			       struct kvmppc_vpa *old_vpap)
 {
 	struct kvm *kvm = vcpu->kvm;
 	void *va;
@@ -682,9 +717,8 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
 		kvmppc_unpin_guest_page(kvm, va, gpa, false);
 		va = NULL;
 	}
-	if (vpap->pinned_addr)
-		kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
-					vpap->dirty);
+	*old_vpap = *vpap;
+
 	vpap->gpa = gpa;
 	vpap->pinned_addr = va;
 	vpap->dirty = false;
@@ -694,6 +728,9 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
 
 static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
+	struct kvmppc_vpa old_vpa = { 0 };
+
 	if (!(vcpu->arch.vpa.update_pending ||
 	      vcpu->arch.slb_shadow.update_pending ||
 	      vcpu->arch.dtl.update_pending))
@@ -701,17 +738,34 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	if (vcpu->arch.vpa.update_pending) {
-		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
-		if (vcpu->arch.vpa.pinned_addr)
+		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa, &old_vpa);
+		if (old_vpa.pinned_addr) {
+			if (kvmhv_is_nestedv2())
+				kvmhv_nestedv2_set_vpa(vcpu, ~0ull);
+			kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+						old_vpa.dirty);
+		}
+		if (vcpu->arch.vpa.pinned_addr) {
 			init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
+			if (kvmhv_is_nestedv2())
+				kvmhv_nestedv2_set_vpa(vcpu, __pa(vcpu->arch.vpa.pinned_addr));
+		}
 	}
 	if (vcpu->arch.dtl.update_pending) {
-		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
+		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl, &old_vpa);
+		if (old_vpa.pinned_addr)
+			kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+						old_vpa.dirty);
 		vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
 		vcpu->arch.dtl_index = 0;
 	}
-	if (vcpu->arch.slb_shadow.update_pending)
-		kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
+	if (vcpu->arch.slb_shadow.update_pending) {
+		kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow, &old_vpa);
+		if (old_vpa.pinned_addr)
+			kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa,
+						old_vpa.dirty);
+	}
+
 	spin_unlock(&vcpu->arch.vpa_update_lock);
 }
 
@@ -794,7 +848,7 @@ static void kvmppc_update_vpa_dispatch(struct kvm_vcpu *vcpu,
 
 	vpa->enqueue_dispatch_tb = cpu_to_be64(be64_to_cpu(vpa->enqueue_dispatch_tb) + stolen);
 
-	__kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now + vc->tb_offset, stolen);
+	__kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now + kvmppc_get_tb_offset(vcpu), stolen);
 
 	vcpu->arch.vpa.dirty = true;
 }
@@ -845,9 +899,9 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu)
 
 static bool kvmppc_power8_compatible(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.vcore->arch_compat >= PVR_ARCH_207)
+	if (kvmppc_get_arch_compat(vcpu) >= PVR_ARCH_207)
 		return true;
-	if ((!vcpu->arch.vcore->arch_compat) &&
+	if ((!kvmppc_get_arch_compat(vcpu)) &&
 	    cpu_has_feature(CPU_FTR_ARCH_207S))
 		return true;
 	return false;
@@ -868,7 +922,7 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
 		/* Guests can't breakpoint the hypervisor */
 		if ((value1 & CIABR_PRIV) == CIABR_PRIV_HYPER)
 			return H_P3;
-		vcpu->arch.ciabr  = value1;
+		kvmppc_set_ciabr_hv(vcpu, value1);
 		return H_SUCCESS;
 	case H_SET_MODE_RESOURCE_SET_DAWR0:
 		if (!kvmppc_power8_compatible(vcpu))
@@ -879,8 +933,8 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
 			return H_UNSUPPORTED_FLAG_START;
 		if (value2 & DABRX_HYP)
 			return H_P4;
-		vcpu->arch.dawr0  = value1;
-		vcpu->arch.dawrx0 = value2;
+		kvmppc_set_dawr0_hv(vcpu, value1);
+		kvmppc_set_dawrx0_hv(vcpu, value2);
 		return H_SUCCESS;
 	case H_SET_MODE_RESOURCE_SET_DAWR1:
 		if (!kvmppc_power8_compatible(vcpu))
@@ -895,8 +949,8 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
 			return H_UNSUPPORTED_FLAG_START;
 		if (value2 & DABRX_HYP)
 			return H_P4;
-		vcpu->arch.dawr1  = value1;
-		vcpu->arch.dawrx1 = value2;
+		kvmppc_set_dawr1_hv(vcpu, value1);
+		kvmppc_set_dawrx1_hv(vcpu, value2);
 		return H_SUCCESS;
 	case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE:
 		/*
@@ -1267,10 +1321,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 			return RESUME_HOST;
 		break;
 #endif
-	case H_RANDOM:
-		if (!arch_get_random_seed_longs(&vcpu->arch.regs.gpr[4], 1))
+	case H_RANDOM: {
+		unsigned long rand;
+
+		if (!arch_get_random_seed_longs(&rand, 1))
 			ret = H_HARDWARE;
+		kvmppc_set_gpr(vcpu, 4, rand);
 		break;
+	}
 	case H_RPT_INVALIDATE:
 		ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4),
 					      kvmppc_get_gpr(vcpu, 5),
@@ -1370,7 +1428,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
  */
 static void kvmppc_cede(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.shregs.msr |= MSR_EE;
+	__kvmppc_set_msr_hv(vcpu, __kvmppc_get_msr_hv(vcpu) | MSR_EE);
 	vcpu->arch.ceded = 1;
 	smp_mb();
 	if (vcpu->arch.prodded) {
@@ -1544,7 +1602,7 @@ static int kvmppc_pmu_unavailable(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.hfscr_permitted & HFSCR_PM))
 		return EMULATE_FAIL;
 
-	vcpu->arch.hfscr |= HFSCR_PM;
+	kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_PM);
 
 	return RESUME_GUEST;
 }
@@ -1554,7 +1612,7 @@ static int kvmppc_ebb_unavailable(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.hfscr_permitted & HFSCR_EBB))
 		return EMULATE_FAIL;
 
-	vcpu->arch.hfscr |= HFSCR_EBB;
+	kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_EBB);
 
 	return RESUME_GUEST;
 }
@@ -1564,7 +1622,7 @@ static int kvmppc_tm_unavailable(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.hfscr_permitted & HFSCR_TM))
 		return EMULATE_FAIL;
 
-	vcpu->arch.hfscr |= HFSCR_TM;
+	kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_TM);
 
 	return RESUME_GUEST;
 }
@@ -1585,7 +1643,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 	 * That can happen due to a bug, or due to a machine check
 	 * occurring at just the wrong time.
 	 */
-	if (vcpu->arch.shregs.msr & MSR_HV) {
+	if (!kvmhv_is_nestedv2() && (__kvmppc_get_msr_hv(vcpu) & MSR_HV)) {
 		printk(KERN_EMERG "KVM trap in HV mode!\n");
 		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
 			vcpu->arch.trap, kvmppc_get_pc(vcpu),
@@ -1636,7 +1694,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 		 * so that it knows that the machine check occurred.
 		 */
 		if (!vcpu->kvm->arch.fwnmi_enabled) {
-			ulong flags = (vcpu->arch.shregs.msr & 0x083c0000) |
+			ulong flags = (__kvmppc_get_msr_hv(vcpu) & 0x083c0000) |
 					(kvmppc_get_msr(vcpu) & SRR1_PREFIXED);
 			kvmppc_core_queue_machine_check(vcpu, flags);
 			r = RESUME_GUEST;
@@ -1666,7 +1724,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 		 * as a result of a hypervisor emulation interrupt
 		 * (e40) getting turned into a 700 by BML RTAS.
 		 */
-		flags = (vcpu->arch.shregs.msr & 0x1f0000ull) |
+		flags = (__kvmppc_get_msr_hv(vcpu) & 0x1f0000ull) |
 			(kvmppc_get_msr(vcpu) & SRR1_PREFIXED);
 		kvmppc_core_queue_program(vcpu, flags);
 		r = RESUME_GUEST;
@@ -1676,7 +1734,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 	{
 		int i;
 
-		if (unlikely(vcpu->arch.shregs.msr & MSR_PR)) {
+		if (!kvmhv_is_nestedv2() && unlikely(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
 			/*
 			 * Guest userspace executed sc 1. This can only be
 			 * reached by the P9 path because the old path
@@ -1754,7 +1812,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 			break;
 		}
 
-		if (!(vcpu->arch.shregs.msr & MSR_DR))
+		if (!(__kvmppc_get_msr_hv(vcpu) & MSR_DR))
 			vsid = vcpu->kvm->arch.vrma_slb_v;
 		else
 			vsid = vcpu->arch.fault_gpa;
@@ -1778,7 +1836,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 		long err;
 
 		vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
-		vcpu->arch.fault_dsisr = vcpu->arch.shregs.msr &
+		vcpu->arch.fault_dsisr = __kvmppc_get_msr_hv(vcpu) &
 			DSISR_SRR1_MATCH_64S;
 		if (kvm_is_radix(vcpu->kvm) || !cpu_has_feature(CPU_FTR_ARCH_300)) {
 			/*
@@ -1787,7 +1845,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 			 * hash fault handling below is v3 only (it uses ASDR
 			 * via fault_gpa).
 			 */
-			if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE)
+			if (__kvmppc_get_msr_hv(vcpu) & HSRR1_HISI_WRITE)
 				vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
 			r = RESUME_PAGE_FAULT;
 			break;
@@ -1801,7 +1859,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 			break;
 		}
 
-		if (!(vcpu->arch.shregs.msr & MSR_IR))
+		if (!(__kvmppc_get_msr_hv(vcpu) & MSR_IR))
 			vsid = vcpu->kvm->arch.vrma_slb_v;
 		else
 			vsid = vcpu->arch.fault_gpa;
@@ -1863,18 +1921,26 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 	 * Otherwise, we just generate a program interrupt to the guest.
 	 */
 	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: {
-		u64 cause = vcpu->arch.hfscr >> 56;
+		u64 cause = kvmppc_get_hfscr_hv(vcpu) >> 56;
 
 		r = EMULATE_FAIL;
 		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
-			if (cause == FSCR_MSGP_LG)
+			switch (cause) {
+			case FSCR_MSGP_LG:
 				r = kvmppc_emulate_doorbell_instr(vcpu);
-			if (cause == FSCR_PM_LG)
+				break;
+			case FSCR_PM_LG:
 				r = kvmppc_pmu_unavailable(vcpu);
-			if (cause == FSCR_EBB_LG)
+				break;
+			case FSCR_EBB_LG:
 				r = kvmppc_ebb_unavailable(vcpu);
-			if (cause == FSCR_TM_LG)
+				break;
+			case FSCR_TM_LG:
 				r = kvmppc_tm_unavailable(vcpu);
+				break;
+			default:
+				break;
+			}
 		}
 		if (r == EMULATE_FAIL) {
 			kvmppc_core_queue_program(vcpu, SRR1_PROGILL |
@@ -1891,7 +1957,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
 		kvmppc_dump_regs(vcpu);
 		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
 			vcpu->arch.trap, kvmppc_get_pc(vcpu),
-			vcpu->arch.shregs.msr);
+			__kvmppc_get_msr_hv(vcpu));
 		run->hw.hardware_exit_reason = vcpu->arch.trap;
 		r = RESUME_HOST;
 		break;
@@ -1915,11 +1981,11 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 	 * That can happen due to a bug, or due to a machine check
 	 * occurring at just the wrong time.
 	 */
-	if (vcpu->arch.shregs.msr & MSR_HV) {
+	if (__kvmppc_get_msr_hv(vcpu) & MSR_HV) {
 		pr_emerg("KVM trap in HV mode while nested!\n");
 		pr_emerg("trap=0x%x | pc=0x%lx | msr=0x%llx\n",
 			 vcpu->arch.trap, kvmppc_get_pc(vcpu),
-			 vcpu->arch.shregs.msr);
+			 __kvmppc_get_msr_hv(vcpu));
 		kvmppc_dump_regs(vcpu);
 		return RESUME_HOST;
 	}
@@ -1976,7 +2042,7 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
 		vcpu->arch.fault_dsisr = kvmppc_get_msr(vcpu) &
 					 DSISR_SRR1_MATCH_64S;
-		if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE)
+		if (__kvmppc_get_msr_hv(vcpu) & HSRR1_HISI_WRITE)
 			vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
 		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvmhv_nested_page_fault(vcpu);
@@ -1997,36 +2063,9 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		fallthrough; /* go to facility unavailable handler */
 #endif
 
-	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: {
-		u64 cause = vcpu->arch.hfscr >> 56;
-
-		/*
-		 * Only pass HFU interrupts to the L1 if the facility is
-		 * permitted but disabled by the L1's HFSCR, otherwise
-		 * the interrupt does not make sense to the L1 so turn
-		 * it into a HEAI.
-		 */
-		if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) ||
-				(vcpu->arch.nested_hfscr & (1UL << cause))) {
-			ppc_inst_t pinst;
-			vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
-
-			/*
-			 * If the fetch failed, return to guest and
-			 * try executing it again.
-			 */
-			r = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst);
-			vcpu->arch.emul_inst = ppc_inst_val(pinst);
-			if (r != EMULATE_DONE)
-				r = RESUME_GUEST;
-			else
-				r = RESUME_HOST;
-		} else {
-			r = RESUME_HOST;
-		}
-
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+		r = RESUME_HOST;
 		break;
-	}
 
 	case BOOK3S_INTERRUPT_HV_RM_HARD:
 		vcpu->arch.trap = 0;
@@ -2183,6 +2222,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
 	}
 
 	vc->lpcr = new_lpcr;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LPCR);
 
 	spin_unlock(&vc->lock);
 }
@@ -2207,64 +2247,64 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		*val = get_reg_val(id, vcpu->arch.dabrx);
 		break;
 	case KVM_REG_PPC_DSCR:
-		*val = get_reg_val(id, vcpu->arch.dscr);
+		*val = get_reg_val(id, kvmppc_get_dscr_hv(vcpu));
 		break;
 	case KVM_REG_PPC_PURR:
-		*val = get_reg_val(id, vcpu->arch.purr);
+		*val = get_reg_val(id, kvmppc_get_purr_hv(vcpu));
 		break;
 	case KVM_REG_PPC_SPURR:
-		*val = get_reg_val(id, vcpu->arch.spurr);
+		*val = get_reg_val(id, kvmppc_get_spurr_hv(vcpu));
 		break;
 	case KVM_REG_PPC_AMR:
-		*val = get_reg_val(id, vcpu->arch.amr);
+		*val = get_reg_val(id, kvmppc_get_amr_hv(vcpu));
 		break;
 	case KVM_REG_PPC_UAMOR:
-		*val = get_reg_val(id, vcpu->arch.uamor);
+		*val = get_reg_val(id, kvmppc_get_uamor_hv(vcpu));
 		break;
 	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1:
 		i = id - KVM_REG_PPC_MMCR0;
-		*val = get_reg_val(id, vcpu->arch.mmcr[i]);
+		*val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, i));
 		break;
 	case KVM_REG_PPC_MMCR2:
-		*val = get_reg_val(id, vcpu->arch.mmcr[2]);
+		*val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, 2));
 		break;
 	case KVM_REG_PPC_MMCRA:
-		*val = get_reg_val(id, vcpu->arch.mmcra);
+		*val = get_reg_val(id, kvmppc_get_mmcra_hv(vcpu));
 		break;
 	case KVM_REG_PPC_MMCRS:
 		*val = get_reg_val(id, vcpu->arch.mmcrs);
 		break;
 	case KVM_REG_PPC_MMCR3:
-		*val = get_reg_val(id, vcpu->arch.mmcr[3]);
+		*val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, 3));
 		break;
 	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
 		i = id - KVM_REG_PPC_PMC1;
-		*val = get_reg_val(id, vcpu->arch.pmc[i]);
+		*val = get_reg_val(id, kvmppc_get_pmc_hv(vcpu, i));
 		break;
 	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
 		i = id - KVM_REG_PPC_SPMC1;
 		*val = get_reg_val(id, vcpu->arch.spmc[i]);
 		break;
 	case KVM_REG_PPC_SIAR:
-		*val = get_reg_val(id, vcpu->arch.siar);
+		*val = get_reg_val(id, kvmppc_get_siar_hv(vcpu));
 		break;
 	case KVM_REG_PPC_SDAR:
-		*val = get_reg_val(id, vcpu->arch.sdar);
+		*val = get_reg_val(id, kvmppc_get_sdar_hv(vcpu));
 		break;
 	case KVM_REG_PPC_SIER:
-		*val = get_reg_val(id, vcpu->arch.sier[0]);
+		*val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 0));
 		break;
 	case KVM_REG_PPC_SIER2:
-		*val = get_reg_val(id, vcpu->arch.sier[1]);
+		*val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 1));
 		break;
 	case KVM_REG_PPC_SIER3:
-		*val = get_reg_val(id, vcpu->arch.sier[2]);
+		*val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 2));
 		break;
 	case KVM_REG_PPC_IAMR:
-		*val = get_reg_val(id, vcpu->arch.iamr);
+		*val = get_reg_val(id, kvmppc_get_iamr_hv(vcpu));
 		break;
 	case KVM_REG_PPC_PSPB:
-		*val = get_reg_val(id, vcpu->arch.pspb);
+		*val = get_reg_val(id, kvmppc_get_pspb_hv(vcpu));
 		break;
 	case KVM_REG_PPC_DPDES:
 		/*
@@ -2279,22 +2319,31 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 			*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
 		break;
 	case KVM_REG_PPC_VTB:
-		*val = get_reg_val(id, vcpu->arch.vcore->vtb);
+		*val = get_reg_val(id, kvmppc_get_vtb(vcpu));
 		break;
 	case KVM_REG_PPC_DAWR:
-		*val = get_reg_val(id, vcpu->arch.dawr0);
+		*val = get_reg_val(id, kvmppc_get_dawr0_hv(vcpu));
 		break;
 	case KVM_REG_PPC_DAWRX:
-		*val = get_reg_val(id, vcpu->arch.dawrx0);
+		*val = get_reg_val(id, kvmppc_get_dawrx0_hv(vcpu));
 		break;
 	case KVM_REG_PPC_DAWR1:
-		*val = get_reg_val(id, vcpu->arch.dawr1);
+		*val = get_reg_val(id, kvmppc_get_dawr1_hv(vcpu));
 		break;
 	case KVM_REG_PPC_DAWRX1:
-		*val = get_reg_val(id, vcpu->arch.dawrx1);
+		*val = get_reg_val(id, kvmppc_get_dawrx1_hv(vcpu));
+		break;
+	case KVM_REG_PPC_DEXCR:
+		*val = get_reg_val(id, kvmppc_get_dexcr_hv(vcpu));
+		break;
+	case KVM_REG_PPC_HASHKEYR:
+		*val = get_reg_val(id, kvmppc_get_hashkeyr_hv(vcpu));
+		break;
+	case KVM_REG_PPC_HASHPKEYR:
+		*val = get_reg_val(id, kvmppc_get_hashpkeyr_hv(vcpu));
 		break;
 	case KVM_REG_PPC_CIABR:
-		*val = get_reg_val(id, vcpu->arch.ciabr);
+		*val = get_reg_val(id, kvmppc_get_ciabr_hv(vcpu));
 		break;
 	case KVM_REG_PPC_CSIGR:
 		*val = get_reg_val(id, vcpu->arch.csigr);
@@ -2306,13 +2355,13 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		*val = get_reg_val(id, vcpu->arch.tcscr);
 		break;
 	case KVM_REG_PPC_PID:
-		*val = get_reg_val(id, vcpu->arch.pid);
+		*val = get_reg_val(id, kvmppc_get_pid(vcpu));
 		break;
 	case KVM_REG_PPC_ACOP:
 		*val = get_reg_val(id, vcpu->arch.acop);
 		break;
 	case KVM_REG_PPC_WORT:
-		*val = get_reg_val(id, vcpu->arch.wort);
+		*val = get_reg_val(id, kvmppc_get_wort_hv(vcpu));
 		break;
 	case KVM_REG_PPC_TIDR:
 		*val = get_reg_val(id, vcpu->arch.tid);
@@ -2338,14 +2387,14 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		spin_unlock(&vcpu->arch.vpa_update_lock);
 		break;
 	case KVM_REG_PPC_TB_OFFSET:
-		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
+		*val = get_reg_val(id, kvmppc_get_tb_offset(vcpu));
 		break;
 	case KVM_REG_PPC_LPCR:
 	case KVM_REG_PPC_LPCR_64:
-		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
+		*val = get_reg_val(id, kvmppc_get_lpcr(vcpu));
 		break;
 	case KVM_REG_PPC_PPR:
-		*val = get_reg_val(id, vcpu->arch.ppr);
+		*val = get_reg_val(id, kvmppc_get_ppr_hv(vcpu));
 		break;
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	case KVM_REG_PPC_TFHAR:
@@ -2414,10 +2463,10 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		break;
 #endif
 	case KVM_REG_PPC_ARCH_COMPAT:
-		*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
+		*val = get_reg_val(id, kvmppc_get_arch_compat(vcpu));
 		break;
 	case KVM_REG_PPC_DEC_EXPIRY:
-		*val = get_reg_val(id, vcpu->arch.dec_expires);
+		*val = get_reg_val(id, kvmppc_get_dec_expires(vcpu));
 		break;
 	case KVM_REG_PPC_ONLINE:
 		*val = get_reg_val(id, vcpu->arch.online);
@@ -2425,6 +2474,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_PTCR:
 		*val = get_reg_val(id, vcpu->kvm->arch.l1_ptcr);
 		break;
+	case KVM_REG_PPC_FSCR:
+		*val = get_reg_val(id, kvmppc_get_fscr_hv(vcpu));
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -2453,64 +2505,64 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP;
 		break;
 	case KVM_REG_PPC_DSCR:
-		vcpu->arch.dscr = set_reg_val(id, *val);
+		kvmppc_set_dscr_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_PURR:
-		vcpu->arch.purr = set_reg_val(id, *val);
+		kvmppc_set_purr_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_SPURR:
-		vcpu->arch.spurr = set_reg_val(id, *val);
+		kvmppc_set_spurr_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_AMR:
-		vcpu->arch.amr = set_reg_val(id, *val);
+		kvmppc_set_amr_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_UAMOR:
-		vcpu->arch.uamor = set_reg_val(id, *val);
+		kvmppc_set_uamor_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1:
 		i = id - KVM_REG_PPC_MMCR0;
-		vcpu->arch.mmcr[i] = set_reg_val(id, *val);
+		kvmppc_set_mmcr_hv(vcpu, i, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_MMCR2:
-		vcpu->arch.mmcr[2] = set_reg_val(id, *val);
+		kvmppc_set_mmcr_hv(vcpu, 2, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_MMCRA:
-		vcpu->arch.mmcra = set_reg_val(id, *val);
+		kvmppc_set_mmcra_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_MMCRS:
 		vcpu->arch.mmcrs = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_MMCR3:
-		*val = get_reg_val(id, vcpu->arch.mmcr[3]);
+		kvmppc_set_mmcr_hv(vcpu, 3, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
 		i = id - KVM_REG_PPC_PMC1;
-		vcpu->arch.pmc[i] = set_reg_val(id, *val);
+		kvmppc_set_pmc_hv(vcpu, i, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
 		i = id - KVM_REG_PPC_SPMC1;
 		vcpu->arch.spmc[i] = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_SIAR:
-		vcpu->arch.siar = set_reg_val(id, *val);
+		kvmppc_set_siar_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_SDAR:
-		vcpu->arch.sdar = set_reg_val(id, *val);
+		kvmppc_set_sdar_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_SIER:
-		vcpu->arch.sier[0] = set_reg_val(id, *val);
+		kvmppc_set_sier_hv(vcpu, 0, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_SIER2:
-		vcpu->arch.sier[1] = set_reg_val(id, *val);
+		kvmppc_set_sier_hv(vcpu, 1, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_SIER3:
-		vcpu->arch.sier[2] = set_reg_val(id, *val);
+		kvmppc_set_sier_hv(vcpu, 2, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_IAMR:
-		vcpu->arch.iamr = set_reg_val(id, *val);
+		kvmppc_set_iamr_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_PSPB:
-		vcpu->arch.pspb = set_reg_val(id, *val);
+		kvmppc_set_pspb_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_DPDES:
 		if (cpu_has_feature(CPU_FTR_ARCH_300))
@@ -2519,25 +2571,34 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 			vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_VTB:
-		vcpu->arch.vcore->vtb = set_reg_val(id, *val);
+		kvmppc_set_vtb(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_DAWR:
-		vcpu->arch.dawr0 = set_reg_val(id, *val);
+		kvmppc_set_dawr0_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_DAWRX:
-		vcpu->arch.dawrx0 = set_reg_val(id, *val) & ~DAWRX_HYP;
+		kvmppc_set_dawrx0_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP);
 		break;
 	case KVM_REG_PPC_DAWR1:
-		vcpu->arch.dawr1 = set_reg_val(id, *val);
+		kvmppc_set_dawr1_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_DAWRX1:
-		vcpu->arch.dawrx1 = set_reg_val(id, *val) & ~DAWRX_HYP;
+		kvmppc_set_dawrx1_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP);
+		break;
+	case KVM_REG_PPC_DEXCR:
+		kvmppc_set_dexcr_hv(vcpu, set_reg_val(id, *val));
+		break;
+	case KVM_REG_PPC_HASHKEYR:
+		kvmppc_set_hashkeyr_hv(vcpu, set_reg_val(id, *val));
+		break;
+	case KVM_REG_PPC_HASHPKEYR:
+		kvmppc_set_hashpkeyr_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_CIABR:
-		vcpu->arch.ciabr = set_reg_val(id, *val);
+		kvmppc_set_ciabr_hv(vcpu, set_reg_val(id, *val));
 		/* Don't allow setting breakpoints in hypervisor code */
-		if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
-			vcpu->arch.ciabr &= ~CIABR_PRIV;	/* disable */
+		if ((kvmppc_get_ciabr_hv(vcpu) & CIABR_PRIV) == CIABR_PRIV_HYPER)
+			kvmppc_set_ciabr_hv(vcpu, kvmppc_get_ciabr_hv(vcpu) & ~CIABR_PRIV);
 		break;
 	case KVM_REG_PPC_CSIGR:
 		vcpu->arch.csigr = set_reg_val(id, *val);
@@ -2549,13 +2610,13 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		vcpu->arch.tcscr = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_PID:
-		vcpu->arch.pid = set_reg_val(id, *val);
+		kvmppc_set_pid(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_ACOP:
 		vcpu->arch.acop = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_WORT:
-		vcpu->arch.wort = set_reg_val(id, *val);
+		kvmppc_set_wort_hv(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_TIDR:
 		vcpu->arch.tid = set_reg_val(id, *val);
@@ -2602,10 +2663,11 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		 * decrementer, which is better than a large one that
 		 * causes a hang.
 		 */
-		if (!vcpu->arch.dec_expires && tb_offset)
-			vcpu->arch.dec_expires = get_tb() + tb_offset;
+		kvmppc_set_tb_offset(vcpu, tb_offset);
+		if (!kvmppc_get_dec_expires(vcpu) && tb_offset)
+			kvmppc_set_dec_expires(vcpu, get_tb() + tb_offset);
 
-		vcpu->arch.vcore->tb_offset = tb_offset;
+		kvmppc_set_tb_offset(vcpu, tb_offset);
 		break;
 	}
 	case KVM_REG_PPC_LPCR:
@@ -2615,7 +2677,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), false);
 		break;
 	case KVM_REG_PPC_PPR:
-		vcpu->arch.ppr = set_reg_val(id, *val);
+		kvmppc_set_ppr_hv(vcpu, set_reg_val(id, *val));
 		break;
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	case KVM_REG_PPC_TFHAR:
@@ -2686,7 +2748,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_DEC_EXPIRY:
-		vcpu->arch.dec_expires = set_reg_val(id, *val);
+		kvmppc_set_dec_expires(vcpu, set_reg_val(id, *val));
 		break;
 	case KVM_REG_PPC_ONLINE:
 		i = set_reg_val(id, *val);
@@ -2699,6 +2761,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	case KVM_REG_PPC_PTCR:
 		vcpu->kvm->arch.l1_ptcr = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_FSCR:
+		kvmppc_set_fscr_hv(vcpu, set_reg_val(id, *val));
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -2916,19 +2981,26 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	vcpu->arch.shared_big_endian = false;
 #endif
 #endif
-	vcpu->arch.mmcr[0] = MMCR0_FC;
+
+	if (kvmhv_is_nestedv2()) {
+		err = kvmhv_nestedv2_vcpu_create(vcpu, &vcpu->arch.nestedv2_io);
+		if (err < 0)
+			return err;
+	}
+
+	kvmppc_set_mmcr_hv(vcpu, 0, MMCR0_FC);
 	if (cpu_has_feature(CPU_FTR_ARCH_31)) {
-		vcpu->arch.mmcr[0] |= MMCR0_PMCCEXT;
-		vcpu->arch.mmcra = MMCRA_BHRB_DISABLE;
+		kvmppc_set_mmcr_hv(vcpu, 0, kvmppc_get_mmcr_hv(vcpu, 0) | MMCR0_PMCCEXT);
+		kvmppc_set_mmcra_hv(vcpu, MMCRA_BHRB_DISABLE);
 	}
 
-	vcpu->arch.ctrl = CTRL_RUNLATCH;
+	kvmppc_set_ctrl_hv(vcpu, CTRL_RUNLATCH);
 	/* default to host PVR, since we can't spoof it */
 	kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR));
 	spin_lock_init(&vcpu->arch.vpa_update_lock);
 	spin_lock_init(&vcpu->arch.tbacct_lock);
 	vcpu->arch.busy_preempt = TB_NIL;
-	vcpu->arch.shregs.msr = MSR_ME;
+	__kvmppc_set_msr_hv(vcpu, MSR_ME);
 	vcpu->arch.intr_msr = MSR_SF | MSR_ME;
 
 	/*
@@ -2938,29 +3010,30 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 	 * don't set the HFSCR_MSGP bit, and that causes those instructions
 	 * to trap and then we emulate them.
 	 */
-	vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB |
-		HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP;
+	kvmppc_set_hfscr_hv(vcpu, HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB |
+			    HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP);
 
 	/* On POWER10 and later, allow prefixed instructions */
 	if (cpu_has_feature(CPU_FTR_ARCH_31))
-		vcpu->arch.hfscr |= HFSCR_PREFIX;
+		kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_PREFIX);
 
 	if (cpu_has_feature(CPU_FTR_HVMODE)) {
-		vcpu->arch.hfscr &= mfspr(SPRN_HFSCR);
+		kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) & mfspr(SPRN_HFSCR));
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 		if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
-			vcpu->arch.hfscr |= HFSCR_TM;
+			kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_TM);
 #endif
 	}
 	if (cpu_has_feature(CPU_FTR_TM_COMP))
 		vcpu->arch.hfscr |= HFSCR_TM;
 
-	vcpu->arch.hfscr_permitted = vcpu->arch.hfscr;
+	vcpu->arch.hfscr_permitted = kvmppc_get_hfscr_hv(vcpu);
 
 	/*
 	 * PM, EBB, TM are demand-faulted so start with it clear.
 	 */
-	vcpu->arch.hfscr &= ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM);
+	kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) & ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM));
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
@@ -3071,6 +3144,8 @@ static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
 	unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
 	unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
 	spin_unlock(&vcpu->arch.vpa_update_lock);
+	if (kvmhv_is_nestedv2())
+		kvmhv_nestedv2_vcpu_free(vcpu, &vcpu->arch.nestedv2_io);
 }
 
 static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
@@ -3958,7 +4033,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	/* Return to whole-core mode if we split the core earlier */
 	if (cmd_bit) {
 		unsigned long hid0 = mfspr(SPRN_HID0);
-		unsigned long loops = 0;
 
 		hid0 &= ~HID0_POWER8_DYNLPARDIS;
 		stat_bit = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE;
@@ -3970,7 +4044,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 			if (!(hid0 & stat_bit))
 				break;
 			cpu_relax();
-			++loops;
 		}
 		split_info.do_nap = 0;
 	}
@@ -4035,10 +4108,207 @@ static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu)
 	}
 }
 
+/* Helper functions for reading L2's stats from L1's VPA */
+#ifdef CONFIG_PPC_PSERIES
+static DEFINE_PER_CPU(u64, l1_to_l2_cs);
+static DEFINE_PER_CPU(u64, l2_to_l1_cs);
+static DEFINE_PER_CPU(u64, l2_runtime_agg);
+
+int kvmhv_get_l2_counters_status(void)
+{
+	return firmware_has_feature(FW_FEATURE_LPAR) &&
+		get_lppaca()->l2_counters_enable;
+}
+
+void kvmhv_set_l2_counters_status(int cpu, bool status)
+{
+	if (!firmware_has_feature(FW_FEATURE_LPAR))
+		return;
+	if (status)
+		lppaca_of(cpu).l2_counters_enable = 1;
+	else
+		lppaca_of(cpu).l2_counters_enable = 0;
+}
+EXPORT_SYMBOL(kvmhv_set_l2_counters_status);
+
+int kvmhv_counters_tracepoint_regfunc(void)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		kvmhv_set_l2_counters_status(cpu, true);
+	}
+	return 0;
+}
+
+void kvmhv_counters_tracepoint_unregfunc(void)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		kvmhv_set_l2_counters_status(cpu, false);
+	}
+}
+
+static void do_trace_nested_cs_time(struct kvm_vcpu *vcpu)
+{
+	struct lppaca *lp = get_lppaca();
+	u64 l1_to_l2_ns, l2_to_l1_ns, l2_runtime_ns;
+	u64 *l1_to_l2_cs_ptr = this_cpu_ptr(&l1_to_l2_cs);
+	u64 *l2_to_l1_cs_ptr = this_cpu_ptr(&l2_to_l1_cs);
+	u64 *l2_runtime_agg_ptr = this_cpu_ptr(&l2_runtime_agg);
+
+	l1_to_l2_ns = tb_to_ns(be64_to_cpu(lp->l1_to_l2_cs_tb));
+	l2_to_l1_ns = tb_to_ns(be64_to_cpu(lp->l2_to_l1_cs_tb));
+	l2_runtime_ns = tb_to_ns(be64_to_cpu(lp->l2_runtime_tb));
+	trace_kvmppc_vcpu_stats(vcpu, l1_to_l2_ns - *l1_to_l2_cs_ptr,
+					l2_to_l1_ns - *l2_to_l1_cs_ptr,
+					l2_runtime_ns - *l2_runtime_agg_ptr);
+	*l1_to_l2_cs_ptr = l1_to_l2_ns;
+	*l2_to_l1_cs_ptr = l2_to_l1_ns;
+	*l2_runtime_agg_ptr = l2_runtime_ns;
+	vcpu->arch.l1_to_l2_cs = l1_to_l2_ns;
+	vcpu->arch.l2_to_l1_cs = l2_to_l1_ns;
+	vcpu->arch.l2_runtime_agg = l2_runtime_ns;
+}
+
+u64 kvmhv_get_l1_to_l2_cs_time(void)
+{
+	return tb_to_ns(be64_to_cpu(get_lppaca()->l1_to_l2_cs_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l1_to_l2_cs_time);
+
+u64 kvmhv_get_l2_to_l1_cs_time(void)
+{
+	return tb_to_ns(be64_to_cpu(get_lppaca()->l2_to_l1_cs_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l2_to_l1_cs_time);
+
+u64 kvmhv_get_l2_runtime_agg(void)
+{
+	return tb_to_ns(be64_to_cpu(get_lppaca()->l2_runtime_tb));
+}
+EXPORT_SYMBOL(kvmhv_get_l2_runtime_agg);
+
+u64 kvmhv_get_l1_to_l2_cs_time_vcpu(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_arch *arch;
+
+	vcpu = local_paca->kvm_hstate.kvm_vcpu;
+	if (vcpu) {
+		arch = &vcpu->arch;
+		return arch->l1_to_l2_cs;
+	} else {
+		return 0;
+	}
+}
+EXPORT_SYMBOL(kvmhv_get_l1_to_l2_cs_time_vcpu);
+
+u64 kvmhv_get_l2_to_l1_cs_time_vcpu(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_arch *arch;
+
+	vcpu = local_paca->kvm_hstate.kvm_vcpu;
+	if (vcpu) {
+		arch = &vcpu->arch;
+		return arch->l2_to_l1_cs;
+	} else {
+		return 0;
+	}
+}
+EXPORT_SYMBOL(kvmhv_get_l2_to_l1_cs_time_vcpu);
+
+u64 kvmhv_get_l2_runtime_agg_vcpu(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_arch *arch;
+
+	vcpu = local_paca->kvm_hstate.kvm_vcpu;
+	if (vcpu) {
+		arch = &vcpu->arch;
+		return arch->l2_runtime_agg;
+	} else {
+		return 0;
+	}
+}
+EXPORT_SYMBOL(kvmhv_get_l2_runtime_agg_vcpu);
+
+#else
+int kvmhv_get_l2_counters_status(void)
+{
+	return 0;
+}
+
+static void do_trace_nested_cs_time(struct kvm_vcpu *vcpu)
+{
+}
+#endif
+
+static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
+				     unsigned long lpcr, u64 *tb)
+{
+	struct kvmhv_nestedv2_io *io;
+	unsigned long msr, i;
+	int trap;
+	long rc;
+
+	if (vcpu->arch.doorbell_request) {
+		vcpu->arch.doorbell_request = 0;
+		kvmppc_set_dpdes(vcpu, 1);
+	}
+
+	io = &vcpu->arch.nestedv2_io;
+
+	msr = mfmsr();
+	kvmppc_msr_hard_disable_set_facilities(vcpu, msr);
+	if (lazy_irq_pending())
+		return 0;
+
+	rc = kvmhv_nestedv2_flush_vcpu(vcpu, time_limit);
+	if (rc < 0)
+		return -EINVAL;
+
+	kvmppc_gse_put_u64(io->vcpu_run_input, KVMPPC_GSID_LPCR, lpcr);
+
+	accumulate_time(vcpu, &vcpu->arch.in_guest);
+	rc = plpar_guest_run_vcpu(0, vcpu->kvm->arch.lpid, vcpu->vcpu_id,
+				  &trap, &i);
+
+	if (rc != H_SUCCESS) {
+		pr_err("KVM Guest Run VCPU hcall failed\n");
+		if (rc == H_INVALID_ELEMENT_ID)
+			pr_err("KVM: Guest Run VCPU invalid element id at %ld\n", i);
+		else if (rc == H_INVALID_ELEMENT_SIZE)
+			pr_err("KVM: Guest Run VCPU invalid element size at %ld\n", i);
+		else if (rc == H_INVALID_ELEMENT_VALUE)
+			pr_err("KVM: Guest Run VCPU invalid element value at %ld\n", i);
+		return -EINVAL;
+	}
+	accumulate_time(vcpu, &vcpu->arch.guest_exit);
+
+	*tb = mftb();
+	kvmppc_gsm_reset(io->vcpu_message);
+	kvmppc_gsm_reset(io->vcore_message);
+	kvmppc_gsbm_zero(&io->valids);
+
+	rc = kvmhv_nestedv2_parse_output(vcpu);
+	if (rc < 0)
+		return -EINVAL;
+
+	timer_rearm_host_dec(*tb);
+
+	/* Record context switch and guest_run_time data */
+	if (kvmhv_get_l2_counters_status())
+		do_trace_nested_cs_time(vcpu);
+
+	return trap;
+}
+
 /* call our hypervisor to load up HV regs and go */
 static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb)
 {
-	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	unsigned long host_psscr;
 	unsigned long msr;
 	struct hv_guest_state hvregs;
@@ -4083,6 +4353,15 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns
 	hvregs.hdec_expiry = time_limit;
 
 	/*
+	 * hvregs has the doorbell status, so zero it here which
+	 * enables us to receive doorbells when H_ENTER_NESTED is
+	 * in progress for this vCPU
+	 */
+
+	if (vcpu->arch.doorbell_request)
+		vcpu->arch.doorbell_request = 0;
+
+	/*
 	 * When setting DEC, we must always deal with irq_work_raise
 	 * via NMI vs setting DEC. The problem occurs right as we
 	 * switch into guest mode if a NMI hits and sets pending work
@@ -4118,7 +4397,7 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns
 	if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */
 		dec = (s32) dec;
 	*tb = mftb();
-	vcpu->arch.dec_expires = dec + (*tb + vc->tb_offset);
+	vcpu->arch.dec_expires = dec + (*tb + kvmppc_get_tb_offset(vcpu));
 
 	timer_rearm_host_dec(*tb);
 
@@ -4153,7 +4432,10 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	vcpu_vpa_increment_dispatch(vcpu);
 
 	if (kvmhv_on_pseries()) {
-		trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb);
+		if (kvmhv_is_nestedv1())
+			trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb);
+		else
+			trap = kvmhv_vcpu_entry_nestedv2(vcpu, time_limit, lpcr, tb);
 
 		/* H_CEDE has to be handled now, not later */
 		if (trap == BOOK3S_INTERRUPT_SYSCALL && !nested &&
@@ -4176,7 +4458,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 		__this_cpu_write(cpu_in_guest, NULL);
 
 		if (trap == BOOK3S_INTERRUPT_SYSCALL &&
-		    !(vcpu->arch.shregs.msr & MSR_PR)) {
+		    !(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
 			unsigned long req = kvmppc_get_gpr(vcpu, 3);
 
 			/*
@@ -4655,16 +4937,33 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	if (!nested) {
 		kvmppc_core_prepare_to_enter(vcpu);
-		if (vcpu->arch.shregs.msr & MSR_EE) {
-			if (xive_interrupt_pending(vcpu))
+		if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
+			     &vcpu->arch.pending_exceptions) ||
+		    xive_interrupt_pending(vcpu)) {
+			/*
+			 * For nested HV, don't synthesize but always pass MER,
+			 * the L0 will be able to optimise that more
+			 * effectively than manipulating registers directly.
+			 */
+			if (!kvmhv_on_pseries() && (__kvmppc_get_msr_hv(vcpu) & MSR_EE))
 				kvmppc_inject_interrupt_hv(vcpu,
-						BOOK3S_INTERRUPT_EXTERNAL, 0);
-		} else if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
-			     &vcpu->arch.pending_exceptions)) {
-			lpcr |= LPCR_MER;
+							   BOOK3S_INTERRUPT_EXTERNAL, 0);
+			else
+				lpcr |= LPCR_MER;
+		} else {
+			/*
+			 * L1's copy of L2's LPCR (vcpu->arch.vcore->lpcr) can get its MER bit
+			 * unexpectedly set - for e.g. during NMI handling when all register
+			 * states are synchronized from L0 to L1. L1 needs to inform L0 about
+			 * MER=1 only when there are pending external interrupts.
+			 * In the above if check, MER bit is set if there are pending
+			 * external interrupts. Hence, explicitly mask off MER bit
+			 * here as otherwise it may generate spurious interrupts in L2 KVM
+			 * causing an endless loop, which results in L2 guest getting hung.
+			 */
+			lpcr &= ~LPCR_MER;
 		}
 	} else if (vcpu->arch.pending_exceptions ||
-		   vcpu->arch.doorbell_request ||
 		   xive_interrupt_pending(vcpu)) {
 		vcpu->arch.ret = RESUME_HOST;
 		goto out;
@@ -4677,7 +4976,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	tb = mftb();
 
-	kvmppc_update_vpa_dispatch_p9(vcpu, vc, tb + vc->tb_offset);
+	kvmppc_update_vpa_dispatch_p9(vcpu, vc, tb + kvmppc_get_tb_offset(vcpu));
 
 	trace_kvm_guest_enter(vcpu);
 
@@ -4844,7 +5143,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 		msr |= MSR_VSX;
 	if ((cpu_has_feature(CPU_FTR_TM) ||
 	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) &&
-			(vcpu->arch.hfscr & HFSCR_TM))
+			(kvmppc_get_hfscr_hv(vcpu) & HFSCR_TM))
 		msr |= MSR_TM;
 	msr = msr_check_and_set(msr);
 
@@ -4868,7 +5167,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 		if (run->exit_reason == KVM_EXIT_PAPR_HCALL) {
 			accumulate_time(vcpu, &vcpu->arch.hcall);
 
-			if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_PR)) {
+			if (!kvmhv_is_nestedv2() && WARN_ON_ONCE(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) {
 				/*
 				 * These should have been caught reflected
 				 * into the guest by now. Final sanity check:
@@ -5133,6 +5432,14 @@ void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
 		if (++cores_done >= kvm->arch.online_vcores)
 			break;
 	}
+
+	if (kvmhv_is_nestedv2()) {
+		struct kvm_vcpu *vcpu;
+
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LPCR);
+		}
+	}
 }
 
 void kvmppc_setup_partition_table(struct kvm *kvm)
@@ -5399,15 +5706,43 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 
 	/* Allocate the guest's logical partition ID */
 
-	lpid = kvmppc_alloc_lpid();
-	if ((long)lpid < 0)
-		return -ENOMEM;
-	kvm->arch.lpid = lpid;
+	if (!kvmhv_is_nestedv2()) {
+		lpid = kvmppc_alloc_lpid();
+		if ((long)lpid < 0)
+			return -ENOMEM;
+		kvm->arch.lpid = lpid;
+	}
 
 	kvmppc_alloc_host_rm_ops();
 
 	kvmhv_vm_nested_init(kvm);
 
+	if (kvmhv_is_nestedv2()) {
+		long rc;
+		unsigned long guest_id;
+
+		rc = plpar_guest_create(0, &guest_id);
+
+		if (rc != H_SUCCESS)
+			pr_err("KVM: Create Guest hcall failed, rc=%ld\n", rc);
+
+		switch (rc) {
+		case H_PARAMETER:
+		case H_FUNCTION:
+		case H_STATE:
+			return -EINVAL;
+		case H_NOT_ENOUGH_RESOURCES:
+		case H_ABORTED:
+			return -ENOMEM;
+		case H_AUTHORITY:
+			return -EPERM;
+		case H_NOT_AVAILABLE:
+			return -EBUSY;
+		}
+		kvm->arch.lpid = guest_id;
+	}
+
+
 	/*
 	 * Since we don't flush the TLB when tearing down a VM,
 	 * and this lpid might have previously been used,
@@ -5477,7 +5812,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 			lpcr |= LPCR_HAIL;
 		ret = kvmppc_init_vm_radix(kvm);
 		if (ret) {
-			kvmppc_free_lpid(kvm->arch.lpid);
+			if (kvmhv_is_nestedv2())
+				plpar_guest_delete(0, kvm->arch.lpid);
+			else
+				kvmppc_free_lpid(kvm->arch.lpid);
 			return ret;
 		}
 		kvmppc_setup_partition_table(kvm);
@@ -5567,10 +5905,16 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 		kvm->arch.process_table = 0;
 		if (kvm->arch.secure_guest)
 			uv_svm_terminate(kvm->arch.lpid);
-		kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
+		if (!kvmhv_is_nestedv2())
+			kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
 	}
 
-	kvmppc_free_lpid(kvm->arch.lpid);
+	if (kvmhv_is_nestedv2()) {
+		kvmhv_flush_lpid(kvm->arch.lpid);
+		plpar_guest_delete(0, kvm->arch.lpid);
+	} else {
+		kvmppc_free_lpid(kvm->arch.lpid);
+	}
 
 	kvmppc_free_pimap(kvm);
 }
@@ -5697,7 +6041,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	 * the underlying calls, which will EOI the interrupt in real
 	 * mode, need an HW IRQ number mapped in the XICS IRQ domain.
 	 */
-	host_data = irq_domain_get_irq_data(irq_get_default_host(), host_irq);
+	host_data = irq_domain_get_irq_data(irq_get_default_domain(), host_irq);
 	irq_map->r_hwirq = (unsigned int)irqd_to_hwirq(host_data);
 
 	if (i == pimap->n_mapped)
@@ -5982,6 +6326,8 @@ static int kvmhv_enable_nested(struct kvm *kvm)
 		return -ENODEV;
 	if (!radix_enabled())
 		return -ENODEV;
+	if (kvmhv_is_nestedv2())
+		return -ENODEV;
 
 	/* kvm == NULL means the caller is testing if the capability exists */
 	if (kvm)
@@ -6084,7 +6430,7 @@ static int kvmhv_svm_off(struct kvm *kvm)
 	}
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct kvm_memory_slot *memslot;
 		struct kvm_memslots *slots = __kvm_memslots(kvm, i);
 		int bkt;
@@ -6185,7 +6531,6 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.unmap_gfn_range = kvm_unmap_gfn_range_hv,
 	.age_gfn = kvm_age_gfn_hv,
 	.test_age_gfn = kvm_test_age_gfn_hv,
-	.set_spte_gfn = kvm_set_spte_gfn_hv,
 	.free_memslot = kvmppc_core_free_memslot_hv,
 	.init_vm =  kvmppc_core_init_vm_hv,
 	.destroy_vm = kvmppc_core_destroy_vm_hv,
@@ -6196,10 +6541,6 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv,
 	.arch_vm_ioctl  = kvm_arch_vm_ioctl_hv,
 	.hcall_implemented = kvmppc_hcall_impl_hv,
-#ifdef CONFIG_KVM_XICS
-	.irq_bypass_add_producer = kvmppc_irq_bypass_add_producer_hv,
-	.irq_bypass_del_producer = kvmppc_irq_bypass_del_producer_hv,
-#endif
 	.configure_mmu = kvmhv_configure_mmu,
 	.get_rmmu_info = kvmhv_get_rmmu_info,
 	.set_smt_mode = kvmhv_set_smt_mode,
@@ -6317,6 +6658,22 @@ static int kvmppc_book3s_init_hv(void)
 		return r;
 	}
 
+#if defined(CONFIG_KVM_XICS)
+	/*
+	 * IRQ bypass is supported only for interrupts whose EOI operations are
+	 * handled via OPAL calls. Therefore, register IRQ bypass handlers
+	 * exclusively for PowerNV KVM when booted with 'xive=off', indicating
+	 * the use of the emulated XICS interrupt controller.
+	 */
+	if (!kvmhv_on_pseries()) {
+		pr_info("KVM-HV: Enabling IRQ bypass\n");
+		kvm_ops_hv.irq_bypass_add_producer =
+			kvmppc_irq_bypass_add_producer_hv;
+		kvm_ops_hv.irq_bypass_del_producer =
+			kvmppc_irq_bypass_del_producer_hv;
+	}
+#endif
+
 	kvm_ops_hv.owner = THIS_MODULE;
 	kvmppc_hv_ops = &kvm_ops_hv;
 
@@ -6341,6 +6698,7 @@ static void kvmppc_book3s_exit_hv(void)
 
 module_init(kvmppc_book3s_init_hv);
 module_exit(kvmppc_book3s_exit_hv);
+MODULE_DESCRIPTION("KVM on Book3S (POWER8 and later) in hypervisor mode");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_MISCDEV(KVM_MINOR);
 MODULE_ALIAS("devname:kvm");
diff --git a/arch/powerpc/kvm/book3s_hv.h b/arch/powerpc/kvm/book3s_hv.h
index 2f2e59d7d433..a404c9b221c1 100644
--- a/arch/powerpc/kvm/book3s_hv.h
+++ b/arch/powerpc/kvm/book3s_hv.h
@@ -3,6 +3,8 @@
 /*
  * Privileged (non-hypervisor) host registers to save.
  */
+#include "asm/guest-state-buffer.h"
+
 struct p9_host_os_sprs {
 	unsigned long iamr;
 	unsigned long amr;
@@ -50,3 +52,80 @@ void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next);
 #define start_timing(vcpu, next) do {} while (0)
 #define end_timing(vcpu) do {} while (0)
 #endif
+
+static inline void __kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 val)
+{
+	vcpu->arch.shregs.msr = val;
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_MSR);
+}
+
+static inline u64 __kvmppc_get_msr_hv(struct kvm_vcpu *vcpu)
+{
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, KVMPPC_GSID_MSR) < 0);
+	return vcpu->arch.shregs.msr;
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_SET(reg, size, iden)		\
+static inline void kvmppc_set_##reg ##_hv(struct kvm_vcpu *vcpu, u##size val)	\
+{									\
+	vcpu->arch.reg = val;						\
+	kvmhv_nestedv2_mark_dirty(vcpu, iden);				\
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_GET(reg, size, iden)		\
+static inline u##size kvmppc_get_##reg ##_hv(struct kvm_vcpu *vcpu)	\
+{									\
+	kvmhv_nestedv2_cached_reload(vcpu, iden);			\
+	return vcpu->arch.reg;						\
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(reg, size, iden)			\
+	KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_SET(reg, size, iden)		\
+	KVMPPC_BOOK3S_HV_VCPU_ACCESSOR_GET(reg, size, iden)		\
+
+#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_SET(reg, size, iden)	\
+static inline void kvmppc_set_##reg ##_hv(struct kvm_vcpu *vcpu, int i, u##size val)	\
+{									\
+	vcpu->arch.reg[i] = val;					\
+	kvmhv_nestedv2_mark_dirty(vcpu, iden(i));			\
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_GET(reg, size, iden)	\
+static inline u##size kvmppc_get_##reg ##_hv(struct kvm_vcpu *vcpu, int i)	\
+{									\
+	WARN_ON(kvmhv_nestedv2_cached_reload(vcpu, iden(i)) < 0);	\
+	return vcpu->arch.reg[i];					\
+}
+
+#define KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(reg, size, iden)		\
+	KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_SET(reg, size, iden)	\
+	KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR_GET(reg, size, iden)	\
+
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(mmcra, 64, KVMPPC_GSID_MMCRA)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(hfscr, 64, KVMPPC_GSID_HFSCR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(fscr, 64, KVMPPC_GSID_FSCR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dscr, 64, KVMPPC_GSID_DSCR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(purr, 64, KVMPPC_GSID_PURR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(spurr, 64, KVMPPC_GSID_SPURR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(amr, 64, KVMPPC_GSID_AMR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(uamor, 64, KVMPPC_GSID_UAMOR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(siar, 64, KVMPPC_GSID_SIAR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(sdar, 64, KVMPPC_GSID_SDAR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(iamr, 64, KVMPPC_GSID_IAMR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr0, 64, KVMPPC_GSID_DAWR0)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawr1, 64, KVMPPC_GSID_DAWR1)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx0, 64, KVMPPC_GSID_DAWRX0)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dawrx1, 64, KVMPPC_GSID_DAWRX1)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(dexcr, 64, KVMPPC_GSID_DEXCR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(hashkeyr, 64, KVMPPC_GSID_HASHKEYR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(hashpkeyr, 64, KVMPPC_GSID_HASHPKEYR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ciabr, 64, KVMPPC_GSID_CIABR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(wort, 64, KVMPPC_GSID_WORT)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ppr, 64, KVMPPC_GSID_PPR)
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(ctrl, 64, KVMPPC_GSID_CTRL);
+
+KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(mmcr, 64, KVMPPC_GSID_MMCR)
+KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(sier, 64, KVMPPC_GSID_SIER)
+KVMPPC_BOOK3S_HV_VCPU_ARRAY_ACCESSOR(pmc, 32, KVMPPC_GSID_PMC)
+
+KVMPPC_BOOK3S_HV_VCPU_ACCESSOR(pspb, 32, KVMPPC_GSID_PSPB)
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index da85f046377a..fa0e3a22cac0 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -32,6 +32,7 @@
 
 #include "book3s_xics.h"
 #include "book3s_xive.h"
+#include "book3s_hv.h"
 
 /*
  * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
@@ -182,9 +183,13 @@ EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
 
 long kvmppc_rm_h_random(struct kvm_vcpu *vcpu)
 {
+	unsigned long rand;
+
 	if (ppc_md.get_random_seed &&
-	    ppc_md.get_random_seed(&vcpu->arch.regs.gpr[4]))
+	    ppc_md.get_random_seed(&rand)) {
+		kvmppc_set_gpr(vcpu, 4, rand);
 		return H_SUCCESS;
+	}
 
 	return H_HARDWARE;
 }
@@ -406,7 +411,7 @@ static long kvmppc_read_one_intr(bool *again)
 		return 1;
 
 	/* see if a host IPI is pending */
-	host_ipi = local_paca->kvm_hstate.host_ipi;
+	host_ipi = READ_ONCE(local_paca->kvm_hstate.host_ipi);
 	if (host_ipi)
 		return 1;
 
@@ -466,7 +471,7 @@ static long kvmppc_read_one_intr(bool *again)
 		 * meantime. If it's clear, we bounce the interrupt to the
 		 * guest
 		 */
-		host_ipi = local_paca->kvm_hstate.host_ipi;
+		host_ipi = READ_ONCE(local_paca->kvm_hstate.host_ipi);
 		if (unlikely(host_ipi != 0)) {
 			/* We raced with the host,
 			 * we need to resend that IPI, bummer
@@ -510,7 +515,7 @@ void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 	 */
 	if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
 		msr &= ~MSR_TS_MASK;
-	vcpu->arch.shregs.msr = msr;
+	__kvmppc_set_msr_hv(vcpu, msr);
 	kvmppc_end_cede(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvmppc_set_msr_hv);
@@ -548,7 +553,7 @@ static void inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
 	kvmppc_set_srr0(vcpu, pc);
 	kvmppc_set_srr1(vcpu, (msr & SRR1_MSR_BITS) | srr1_flags);
 	kvmppc_set_pc(vcpu, new_pc);
-	vcpu->arch.shregs.msr = new_msr;
+	__kvmppc_set_msr_hv(vcpu, new_msr);
 }
 
 void kvmppc_inject_interrupt_hv(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags)
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 377d0b4a05ee..5f8c2321cfb5 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -32,7 +32,7 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
 	hr->pcr = vc->pcr | PCR_MASK;
-	hr->dpdes = vc->dpdes;
+	hr->dpdes = vcpu->arch.doorbell_request;
 	hr->hfscr = vcpu->arch.hfscr;
 	hr->tb_offset = vc->tb_offset;
 	hr->dawr0 = vcpu->arch.dawr0;
@@ -55,7 +55,7 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
 	hr->dawrx1 = vcpu->arch.dawrx1;
 }
 
-/* Use noinline_for_stack due to https://bugs.llvm.org/show_bug.cgi?id=49610 */
+/* Use noinline_for_stack due to https://llvm.org/pr49610 */
 static noinline_for_stack void byteswap_pt_regs(struct pt_regs *regs)
 {
 	unsigned long *addr = (unsigned long *) regs;
@@ -105,7 +105,7 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
-	hr->dpdes = vc->dpdes;
+	hr->dpdes = vcpu->arch.doorbell_request;
 	hr->purr = vcpu->arch.purr;
 	hr->spurr = vcpu->arch.spurr;
 	hr->ic = vcpu->arch.ic;
@@ -143,7 +143,7 @@ static void restore_hv_regs(struct kvm_vcpu *vcpu, const struct hv_guest_state *
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
 	vc->pcr = hr->pcr | PCR_MASK;
-	vc->dpdes = hr->dpdes;
+	vcpu->arch.doorbell_request = hr->dpdes;
 	vcpu->arch.hfscr = hr->hfscr;
 	vcpu->arch.dawr0 = hr->dawr0;
 	vcpu->arch.dawrx0 = hr->dawrx0;
@@ -170,7 +170,13 @@ void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
-	vc->dpdes = hr->dpdes;
+	/*
+	 * This L2 vCPU might have received a doorbell while H_ENTER_NESTED was being handled.
+	 * Make sure we preserve the doorbell if it was either:
+	 *   a) Sent after H_ENTER_NESTED was called on this vCPU (arch.doorbell_request would be 1)
+	 *   b) Doorbell was not handled and L2 exited for some other reason (hr->dpdes would be 1)
+	 */
+	vcpu->arch.doorbell_request = vcpu->arch.doorbell_request | hr->dpdes;
 	vcpu->arch.hfscr = hr->hfscr;
 	vcpu->arch.purr = hr->purr;
 	vcpu->arch.spurr = hr->spurr;
@@ -428,10 +434,12 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	return vcpu->arch.trap;
 }
 
+unsigned long nested_capabilities;
+
 long kvmhv_nested_init(void)
 {
 	long int ptb_order;
-	unsigned long ptcr;
+	unsigned long ptcr, host_capabilities;
 	long rc;
 
 	if (!kvmhv_on_pseries())
@@ -439,6 +447,31 @@ long kvmhv_nested_init(void)
 	if (!radix_enabled())
 		return -ENODEV;
 
+	rc = plpar_guest_get_capabilities(0, &host_capabilities);
+	if (rc == H_SUCCESS) {
+		unsigned long capabilities = 0;
+
+		if (cpu_has_feature(CPU_FTR_P11_PVR))
+			capabilities |= H_GUEST_CAP_POWER11;
+		if (cpu_has_feature(CPU_FTR_ARCH_31))
+			capabilities |= H_GUEST_CAP_POWER10;
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			capabilities |= H_GUEST_CAP_POWER9;
+
+		nested_capabilities = capabilities & host_capabilities;
+		rc = plpar_guest_set_capabilities(0, nested_capabilities);
+		if (rc != H_SUCCESS) {
+			pr_err("kvm-hv: Could not configure parent hypervisor capabilities (rc=%ld)",
+			       rc);
+			return -ENODEV;
+		}
+
+		static_branch_enable(&__kvmhv_is_nestedv2);
+		return 0;
+	}
+
+	pr_info("kvm-hv: nestedv2 get capabilities hcall failed, falling back to nestedv1 (rc=%ld)\n",
+		rc);
 	/* Partition table entry is 1<<4 bytes in size, hence the 4. */
 	ptb_order = KVM_MAX_NESTED_GUESTS_SHIFT + 4;
 	/* Minimum partition table size is 1<<12 bytes */
@@ -478,7 +511,7 @@ void kvmhv_nested_exit(void)
 	}
 }
 
-static void kvmhv_flush_lpid(unsigned int lpid)
+void kvmhv_flush_lpid(u64 lpid)
 {
 	long rc;
 
@@ -500,17 +533,22 @@ static void kvmhv_flush_lpid(unsigned int lpid)
 		pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc);
 }
 
-void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1)
+void kvmhv_set_ptbl_entry(u64 lpid, u64 dw0, u64 dw1)
 {
 	if (!kvmhv_on_pseries()) {
 		mmu_partition_table_set_entry(lpid, dw0, dw1, true);
 		return;
 	}
 
-	pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
-	pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
-	/* L0 will do the necessary barriers */
-	kvmhv_flush_lpid(lpid);
+	if (kvmhv_is_nestedv1()) {
+		pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
+		pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
+		/* L0 will do the necessary barriers */
+		kvmhv_flush_lpid(lpid);
+	}
+
+	if (kvmhv_is_nestedv2())
+		kvmhv_nestedv2_set_ptbl_entry(lpid, dw0, dw1);
 }
 
 static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp)
@@ -1497,7 +1535,6 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
 	unsigned long n_gpa, gpa, gfn, perm = 0UL;
 	unsigned int shift, l1_shift, level;
 	bool writing = !!(dsisr & DSISR_ISSTORE);
-	bool kvm_ro = false;
 	long int ret;
 
 	if (!gp->l1_gr_to_hr) {
@@ -1577,7 +1614,6 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
 					ea, DSISR_ISSTORE | DSISR_PROTFAULT);
 			return RESUME_GUEST;
 		}
-		kvm_ro = true;
 	}
 
 	/* 2. Find the host pte for this L1 guest real address */
@@ -1599,7 +1635,7 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
 	if (!pte_present(pte) || (writing && !(pte_val(pte) & _PAGE_WRITE))) {
 		/* No suitable pte found -> try to insert a mapping */
 		ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot,
-					writing, kvm_ro, &pte, &level);
+					writing, &pte, &level);
 		if (ret == -EAGAIN)
 			return RESUME_GUEST;
 		else if (ret)
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
new file mode 100644
index 000000000000..87691cf86cae
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -0,0 +1,1072 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2023 Jordan Niethe, IBM Corp. <jniethe5@gmail.com>
+ *
+ * Authors:
+ *    Jordan Niethe <jniethe5@gmail.com>
+ *
+ * Description: KVM functions specific to running on Book 3S
+ * processors as a NESTEDv2 guest.
+ *
+ */
+
+#include "linux/blk-mq.h"
+#include "linux/console.h"
+#include "linux/gfp_types.h"
+#include "linux/signal.h"
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/pgtable.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/hvcall.h>
+#include <asm/pgalloc.h>
+#include <asm/reg.h>
+#include <asm/plpar_wrappers.h>
+#include <asm/guest-state-buffer.h>
+#include "trace_hv.h"
+
+struct static_key_false __kvmhv_is_nestedv2 __read_mostly;
+EXPORT_SYMBOL_GPL(__kvmhv_is_nestedv2);
+
+
+static size_t
+gs_msg_ops_kvmhv_nestedv2_config_get_size(struct kvmppc_gs_msg *gsm)
+{
+	u16 ids[] = {
+		KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE,
+		KVMPPC_GSID_RUN_INPUT,
+		KVMPPC_GSID_RUN_OUTPUT,
+
+	};
+	size_t size = 0;
+
+	for (int i = 0; i < ARRAY_SIZE(ids); i++)
+		size += kvmppc_gse_total_size(kvmppc_gsid_size(ids[i]));
+	return size;
+}
+
+static int
+gs_msg_ops_kvmhv_nestedv2_config_fill_info(struct kvmppc_gs_buff *gsb,
+					   struct kvmppc_gs_msg *gsm)
+{
+	struct kvmhv_nestedv2_config *cfg;
+	int rc;
+
+	cfg = gsm->data;
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE)) {
+		rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE,
+					cfg->vcpu_run_output_size);
+		if (rc < 0)
+			return rc;
+	}
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_INPUT)) {
+		rc = kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_INPUT,
+					      cfg->vcpu_run_input_cfg);
+		if (rc < 0)
+			return rc;
+	}
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_OUTPUT)) {
+		rc = kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_OUTPUT,
+					      cfg->vcpu_run_output_cfg);
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int
+gs_msg_ops_kvmhv_nestedv2_config_refresh_info(struct kvmppc_gs_msg *gsm,
+					      struct kvmppc_gs_buff *gsb)
+{
+	struct kvmhv_nestedv2_config *cfg;
+	struct kvmppc_gs_parser gsp = { 0 };
+	struct kvmppc_gs_elem *gse;
+	int rc;
+
+	cfg = gsm->data;
+
+	rc = kvmppc_gse_parse(&gsp, gsb);
+	if (rc < 0)
+		return rc;
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE);
+	if (gse)
+		cfg->vcpu_run_output_size = kvmppc_gse_get_u64(gse);
+	return 0;
+}
+
+static struct kvmppc_gs_msg_ops config_msg_ops = {
+	.get_size = gs_msg_ops_kvmhv_nestedv2_config_get_size,
+	.fill_info = gs_msg_ops_kvmhv_nestedv2_config_fill_info,
+	.refresh_info = gs_msg_ops_kvmhv_nestedv2_config_refresh_info,
+};
+
+static size_t gs_msg_ops_vcpu_get_size(struct kvmppc_gs_msg *gsm)
+{
+	struct kvmppc_gs_bitmap gsbm = { 0 };
+	size_t size = 0;
+	u16 iden;
+
+	kvmppc_gsbm_fill(&gsbm);
+	kvmppc_gsbm_for_each(&gsbm, iden)
+	{
+		switch (iden) {
+		case KVMPPC_GSID_HOST_STATE_SIZE:
+		case KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE:
+		case KVMPPC_GSID_PARTITION_TABLE:
+		case KVMPPC_GSID_PROCESS_TABLE:
+		case KVMPPC_GSID_RUN_INPUT:
+		case KVMPPC_GSID_RUN_OUTPUT:
+		  /* Host wide counters */
+		case KVMPPC_GSID_L0_GUEST_HEAP:
+		case KVMPPC_GSID_L0_GUEST_HEAP_MAX:
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE:
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX:
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM:
+			break;
+		default:
+			size += kvmppc_gse_total_size(kvmppc_gsid_size(iden));
+		}
+	}
+	return size;
+}
+
+static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
+				     struct kvmppc_gs_msg *gsm)
+{
+	struct kvm_vcpu *vcpu;
+	vector128 v;
+	int rc, i;
+	u16 iden;
+	u32 arch_compat = 0;
+
+	vcpu = gsm->data;
+
+	kvmppc_gsm_for_each(gsm, iden)
+	{
+		rc = 0;
+
+		if ((gsm->flags & KVMPPC_GS_FLAGS_WIDE) !=
+		    (kvmppc_gsid_flags(iden) & KVMPPC_GS_FLAGS_WIDE))
+			continue;
+
+		switch (iden) {
+		case KVMPPC_GSID_DSCR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.dscr);
+			break;
+		case KVMPPC_GSID_MMCRA:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.mmcra);
+			break;
+		case KVMPPC_GSID_HFSCR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.hfscr);
+			break;
+		case KVMPPC_GSID_PURR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.purr);
+			break;
+		case KVMPPC_GSID_SPURR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.spurr);
+			break;
+		case KVMPPC_GSID_AMR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.amr);
+			break;
+		case KVMPPC_GSID_UAMOR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.uamor);
+			break;
+		case KVMPPC_GSID_SIAR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.siar);
+			break;
+		case KVMPPC_GSID_SDAR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.sdar);
+			break;
+		case KVMPPC_GSID_IAMR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.iamr);
+			break;
+		case KVMPPC_GSID_DAWR0:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.dawr0);
+			break;
+		case KVMPPC_GSID_DAWR1:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.dawr1);
+			break;
+		case KVMPPC_GSID_DAWRX0:
+			rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.dawrx0);
+			break;
+		case KVMPPC_GSID_DAWRX1:
+			rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.dawrx1);
+			break;
+		case KVMPPC_GSID_DEXCR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.dexcr);
+			break;
+		case KVMPPC_GSID_HASHKEYR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.hashkeyr);
+			break;
+		case KVMPPC_GSID_HASHPKEYR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.hashpkeyr);
+			break;
+		case KVMPPC_GSID_CIABR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ciabr);
+			break;
+		case KVMPPC_GSID_WORT:
+			rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.wort);
+			break;
+		case KVMPPC_GSID_PPR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ppr);
+			break;
+		case KVMPPC_GSID_PSPB:
+			rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.pspb);
+			break;
+		case KVMPPC_GSID_TAR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.tar);
+			break;
+		case KVMPPC_GSID_FSCR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.fscr);
+			break;
+		case KVMPPC_GSID_EBBHR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ebbhr);
+			break;
+		case KVMPPC_GSID_EBBRR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ebbrr);
+			break;
+		case KVMPPC_GSID_BESCR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.bescr);
+			break;
+		case KVMPPC_GSID_IC:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ic);
+			break;
+		case KVMPPC_GSID_CTRL:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.ctrl);
+			break;
+		case KVMPPC_GSID_PIDR:
+			rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.pid);
+			break;
+		case KVMPPC_GSID_AMOR: {
+			u64 amor = ~0;
+
+			rc = kvmppc_gse_put_u64(gsb, iden, amor);
+			break;
+		}
+		case KVMPPC_GSID_VRSAVE:
+			rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.vrsave);
+			break;
+		case KVMPPC_GSID_MMCR(0)... KVMPPC_GSID_MMCR(3):
+			i = iden - KVMPPC_GSID_MMCR(0);
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.mmcr[i]);
+			break;
+		case KVMPPC_GSID_SIER(0)... KVMPPC_GSID_SIER(2):
+			i = iden - KVMPPC_GSID_SIER(0);
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.sier[i]);
+			break;
+		case KVMPPC_GSID_PMC(0)... KVMPPC_GSID_PMC(5):
+			i = iden - KVMPPC_GSID_PMC(0);
+			rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.pmc[i]);
+			break;
+		case KVMPPC_GSID_GPR(0)... KVMPPC_GSID_GPR(31):
+			i = iden - KVMPPC_GSID_GPR(0);
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.regs.gpr[i]);
+			break;
+		case KVMPPC_GSID_CR:
+			rc = kvmppc_gse_put_u32(gsb, iden, vcpu->arch.regs.ccr);
+			break;
+		case KVMPPC_GSID_XER:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.regs.xer);
+			break;
+		case KVMPPC_GSID_CTR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.regs.ctr);
+			break;
+		case KVMPPC_GSID_LR:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.regs.link);
+			break;
+		case KVMPPC_GSID_NIA:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.regs.nip);
+			break;
+		case KVMPPC_GSID_SRR0:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.shregs.srr0);
+			break;
+		case KVMPPC_GSID_SRR1:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.shregs.srr1);
+			break;
+		case KVMPPC_GSID_SPRG0:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.shregs.sprg0);
+			break;
+		case KVMPPC_GSID_SPRG1:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.shregs.sprg1);
+			break;
+		case KVMPPC_GSID_SPRG2:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.shregs.sprg2);
+			break;
+		case KVMPPC_GSID_SPRG3:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.shregs.sprg3);
+			break;
+		case KVMPPC_GSID_DAR:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.shregs.dar);
+			break;
+		case KVMPPC_GSID_DSISR:
+			rc = kvmppc_gse_put_u32(gsb, iden,
+						vcpu->arch.shregs.dsisr);
+			break;
+		case KVMPPC_GSID_MSR:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.shregs.msr);
+			break;
+		case KVMPPC_GSID_VTB:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.vcore->vtb);
+			break;
+		case KVMPPC_GSID_DPDES:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.vcore->dpdes);
+			break;
+		case KVMPPC_GSID_LPCR:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.vcore->lpcr);
+			break;
+		case KVMPPC_GSID_TB_OFFSET:
+			rc = kvmppc_gse_put_u64(gsb, iden,
+						vcpu->arch.vcore->tb_offset);
+			break;
+		case KVMPPC_GSID_FPSCR:
+			rc = kvmppc_gse_put_u64(gsb, iden, vcpu->arch.fp.fpscr);
+			break;
+		case KVMPPC_GSID_VSRS(0)... KVMPPC_GSID_VSRS(31):
+			i = iden - KVMPPC_GSID_VSRS(0);
+			memcpy(&v, &vcpu->arch.fp.fpr[i],
+			       sizeof(vcpu->arch.fp.fpr[i]));
+			rc = kvmppc_gse_put_vector128(gsb, iden, &v);
+			break;
+#ifdef CONFIG_VSX
+		case KVMPPC_GSID_VSCR:
+			rc = kvmppc_gse_put_u32(gsb, iden,
+						vcpu->arch.vr.vscr.u[3]);
+			break;
+		case KVMPPC_GSID_VSRS(32)... KVMPPC_GSID_VSRS(63):
+			i = iden - KVMPPC_GSID_VSRS(32);
+			rc = kvmppc_gse_put_vector128(gsb, iden,
+						      &vcpu->arch.vr.vr[i]);
+			break;
+#endif
+		case KVMPPC_GSID_DEC_EXPIRY_TB: {
+			u64 dw;
+
+			dw = vcpu->arch.dec_expires -
+			     vcpu->arch.vcore->tb_offset;
+			rc = kvmppc_gse_put_u64(gsb, iden, dw);
+			break;
+		}
+		case KVMPPC_GSID_LOGICAL_PVR:
+			/*
+			 * Though 'arch_compat == 0' would mean the default
+			 * compatibility, arch_compat, being a Guest Wide
+			 * Element, cannot be filled with a value of 0 in GSB
+			 * as this would result into a kernel trap.
+			 * Hence, when `arch_compat == 0`, arch_compat should
+			 * default to L1's PVR.
+			 */
+			if (!vcpu->arch.vcore->arch_compat) {
+				if (cpu_has_feature(CPU_FTR_P11_PVR))
+					arch_compat = PVR_ARCH_31_P11;
+				else if (cpu_has_feature(CPU_FTR_ARCH_31))
+					arch_compat = PVR_ARCH_31;
+				else if (cpu_has_feature(CPU_FTR_ARCH_300))
+					arch_compat = PVR_ARCH_300;
+			} else {
+				arch_compat = vcpu->arch.vcore->arch_compat;
+			}
+			rc = kvmppc_gse_put_u32(gsb, iden, arch_compat);
+			break;
+		}
+
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int gs_msg_ops_vcpu_refresh_info(struct kvmppc_gs_msg *gsm,
+					struct kvmppc_gs_buff *gsb)
+{
+	struct kvmppc_gs_parser gsp = { 0 };
+	struct kvmhv_nestedv2_io *io;
+	struct kvmppc_gs_bitmap *valids;
+	struct kvm_vcpu *vcpu;
+	struct kvmppc_gs_elem *gse;
+	vector128 v;
+	int rc, i;
+	u16 iden;
+
+	vcpu = gsm->data;
+
+	rc = kvmppc_gse_parse(&gsp, gsb);
+	if (rc < 0)
+		return rc;
+
+	io = &vcpu->arch.nestedv2_io;
+	valids = &io->valids;
+
+	kvmppc_gsp_for_each(&gsp, iden, gse)
+	{
+		switch (iden) {
+		case KVMPPC_GSID_DSCR:
+			vcpu->arch.dscr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_MMCRA:
+			vcpu->arch.mmcra = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_HFSCR:
+			vcpu->arch.hfscr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_PURR:
+			vcpu->arch.purr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SPURR:
+			vcpu->arch.spurr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_AMR:
+			vcpu->arch.amr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_UAMOR:
+			vcpu->arch.uamor = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SIAR:
+			vcpu->arch.siar = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SDAR:
+			vcpu->arch.sdar = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_IAMR:
+			vcpu->arch.iamr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_DAWR0:
+			vcpu->arch.dawr0 = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_DAWR1:
+			vcpu->arch.dawr1 = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_DAWRX0:
+			vcpu->arch.dawrx0 = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_DAWRX1:
+			vcpu->arch.dawrx1 = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_DEXCR:
+			vcpu->arch.dexcr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_HASHKEYR:
+			vcpu->arch.hashkeyr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_HASHPKEYR:
+			vcpu->arch.hashpkeyr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_CIABR:
+			vcpu->arch.ciabr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_WORT:
+			vcpu->arch.wort = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_PPR:
+			vcpu->arch.ppr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_PSPB:
+			vcpu->arch.pspb = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_TAR:
+			vcpu->arch.tar = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_FSCR:
+			vcpu->arch.fscr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_EBBHR:
+			vcpu->arch.ebbhr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_EBBRR:
+			vcpu->arch.ebbrr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_BESCR:
+			vcpu->arch.bescr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_IC:
+			vcpu->arch.ic = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_CTRL:
+			vcpu->arch.ctrl = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_PIDR:
+			vcpu->arch.pid = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_AMOR:
+			break;
+		case KVMPPC_GSID_VRSAVE:
+			vcpu->arch.vrsave = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_MMCR(0)... KVMPPC_GSID_MMCR(3):
+			i = iden - KVMPPC_GSID_MMCR(0);
+			vcpu->arch.mmcr[i] = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SIER(0)... KVMPPC_GSID_SIER(2):
+			i = iden - KVMPPC_GSID_SIER(0);
+			vcpu->arch.sier[i] = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_PMC(0)... KVMPPC_GSID_PMC(5):
+			i = iden - KVMPPC_GSID_PMC(0);
+			vcpu->arch.pmc[i] = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_GPR(0)... KVMPPC_GSID_GPR(31):
+			i = iden - KVMPPC_GSID_GPR(0);
+			vcpu->arch.regs.gpr[i] = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_CR:
+			vcpu->arch.regs.ccr = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_XER:
+			vcpu->arch.regs.xer = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_CTR:
+			vcpu->arch.regs.ctr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_LR:
+			vcpu->arch.regs.link = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_NIA:
+			vcpu->arch.regs.nip = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SRR0:
+			vcpu->arch.shregs.srr0 = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SRR1:
+			vcpu->arch.shregs.srr1 = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SPRG0:
+			vcpu->arch.shregs.sprg0 = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SPRG1:
+			vcpu->arch.shregs.sprg1 = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SPRG2:
+			vcpu->arch.shregs.sprg2 = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_SPRG3:
+			vcpu->arch.shregs.sprg3 = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_DAR:
+			vcpu->arch.shregs.dar = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_DSISR:
+			vcpu->arch.shregs.dsisr = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_MSR:
+			vcpu->arch.shregs.msr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_VTB:
+			vcpu->arch.vcore->vtb = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_DPDES:
+			vcpu->arch.vcore->dpdes = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_LPCR:
+			vcpu->arch.vcore->lpcr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_TB_OFFSET:
+			vcpu->arch.vcore->tb_offset = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_FPSCR:
+			vcpu->arch.fp.fpscr = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_VSRS(0)... KVMPPC_GSID_VSRS(31):
+			kvmppc_gse_get_vector128(gse, &v);
+			i = iden - KVMPPC_GSID_VSRS(0);
+			memcpy(&vcpu->arch.fp.fpr[i], &v,
+			       sizeof(vcpu->arch.fp.fpr[i]));
+			break;
+#ifdef CONFIG_VSX
+		case KVMPPC_GSID_VSCR:
+			vcpu->arch.vr.vscr.u[3] = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_VSRS(32)... KVMPPC_GSID_VSRS(63):
+			i = iden - KVMPPC_GSID_VSRS(32);
+			kvmppc_gse_get_vector128(gse, &vcpu->arch.vr.vr[i]);
+			break;
+#endif
+		case KVMPPC_GSID_HDAR:
+			vcpu->arch.fault_dar = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_HDSISR:
+			vcpu->arch.fault_dsisr = kvmppc_gse_get_u32(gse);
+			break;
+		case KVMPPC_GSID_ASDR:
+			vcpu->arch.fault_gpa = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_HEIR:
+			vcpu->arch.emul_inst = kvmppc_gse_get_u64(gse);
+			break;
+		case KVMPPC_GSID_DEC_EXPIRY_TB: {
+			u64 dw;
+
+			dw = kvmppc_gse_get_u64(gse);
+			vcpu->arch.dec_expires =
+				dw + vcpu->arch.vcore->tb_offset;
+			break;
+		}
+		case KVMPPC_GSID_LOGICAL_PVR:
+			vcpu->arch.vcore->arch_compat = kvmppc_gse_get_u32(gse);
+			break;
+		default:
+			continue;
+		}
+		kvmppc_gsbm_set(valids, iden);
+	}
+
+	return 0;
+}
+
+static struct kvmppc_gs_msg_ops vcpu_message_ops = {
+	.get_size = gs_msg_ops_vcpu_get_size,
+	.fill_info = gs_msg_ops_vcpu_fill_info,
+	.refresh_info = gs_msg_ops_vcpu_refresh_info,
+};
+
+static int kvmhv_nestedv2_host_create(struct kvm_vcpu *vcpu,
+				      struct kvmhv_nestedv2_io *io)
+{
+	struct kvmhv_nestedv2_config *cfg;
+	struct kvmppc_gs_buff *gsb, *vcpu_run_output, *vcpu_run_input;
+	unsigned long guest_id, vcpu_id;
+	struct kvmppc_gs_msg *gsm, *vcpu_message, *vcore_message;
+	int rc;
+
+	cfg = &io->cfg;
+	guest_id = vcpu->kvm->arch.lpid;
+	vcpu_id = vcpu->vcpu_id;
+
+	gsm = kvmppc_gsm_new(&config_msg_ops, cfg, KVMPPC_GS_FLAGS_WIDE,
+			     GFP_KERNEL);
+	if (!gsm) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), guest_id, vcpu_id,
+			     GFP_KERNEL);
+	if (!gsb) {
+		rc = -ENOMEM;
+		goto free_gsm;
+	}
+
+	rc = kvmppc_gsb_receive_datum(gsb, gsm,
+				      KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE);
+	if (rc < 0) {
+		pr_err("KVM-NESTEDv2: couldn't get vcpu run output buffer minimum size\n");
+		goto free_gsb;
+	}
+
+	vcpu_run_output = kvmppc_gsb_new(cfg->vcpu_run_output_size, guest_id,
+					 vcpu_id, GFP_KERNEL);
+	if (!vcpu_run_output) {
+		rc = -ENOMEM;
+		goto free_gsb;
+	}
+
+	cfg->vcpu_run_output_cfg.address = kvmppc_gsb_paddress(vcpu_run_output);
+	cfg->vcpu_run_output_cfg.size = kvmppc_gsb_capacity(vcpu_run_output);
+	io->vcpu_run_output = vcpu_run_output;
+
+	gsm->flags = 0;
+	rc = kvmppc_gsb_send_datum(gsb, gsm, KVMPPC_GSID_RUN_OUTPUT);
+	if (rc < 0) {
+		pr_err("KVM-NESTEDv2: couldn't set vcpu run output buffer\n");
+		goto free_gs_out;
+	}
+
+	vcpu_message = kvmppc_gsm_new(&vcpu_message_ops, vcpu, 0, GFP_KERNEL);
+	if (!vcpu_message) {
+		rc = -ENOMEM;
+		goto free_gs_out;
+	}
+	kvmppc_gsm_include_all(vcpu_message);
+
+	io->vcpu_message = vcpu_message;
+
+	vcpu_run_input = kvmppc_gsb_new(kvmppc_gsm_size(vcpu_message), guest_id,
+					vcpu_id, GFP_KERNEL);
+	if (!vcpu_run_input) {
+		rc = -ENOMEM;
+		goto free_vcpu_message;
+	}
+
+	io->vcpu_run_input = vcpu_run_input;
+	cfg->vcpu_run_input_cfg.address = kvmppc_gsb_paddress(vcpu_run_input);
+	cfg->vcpu_run_input_cfg.size = kvmppc_gsb_capacity(vcpu_run_input);
+	rc = kvmppc_gsb_send_datum(gsb, gsm, KVMPPC_GSID_RUN_INPUT);
+	if (rc < 0) {
+		pr_err("KVM-NESTEDv2: couldn't set vcpu run input buffer\n");
+		goto free_vcpu_run_input;
+	}
+
+	vcore_message = kvmppc_gsm_new(&vcpu_message_ops, vcpu,
+				       KVMPPC_GS_FLAGS_WIDE, GFP_KERNEL);
+	if (!vcore_message) {
+		rc = -ENOMEM;
+		goto free_vcpu_run_input;
+	}
+
+	kvmppc_gsm_include_all(vcore_message);
+	kvmppc_gsbm_clear(&vcore_message->bitmap, KVMPPC_GSID_LOGICAL_PVR);
+	io->vcore_message = vcore_message;
+
+	kvmppc_gsbm_fill(&io->valids);
+	kvmppc_gsm_free(gsm);
+	kvmppc_gsb_free(gsb);
+	return 0;
+
+free_vcpu_run_input:
+	kvmppc_gsb_free(vcpu_run_input);
+free_vcpu_message:
+	kvmppc_gsm_free(vcpu_message);
+free_gs_out:
+	kvmppc_gsb_free(vcpu_run_output);
+free_gsb:
+	kvmppc_gsb_free(gsb);
+free_gsm:
+	kvmppc_gsm_free(gsm);
+err:
+	return rc;
+}
+
+/**
+ * __kvmhv_nestedv2_mark_dirty() - mark a Guest State ID to be sent to the host
+ * @vcpu: vcpu
+ * @iden: guest state ID
+ *
+ * Mark a guest state ID as having been changed by the L1 host and thus
+ * the new value must be sent to the L0 hypervisor. See kvmhv_nestedv2_flush_vcpu()
+ */
+int __kvmhv_nestedv2_mark_dirty(struct kvm_vcpu *vcpu, u16 iden)
+{
+	struct kvmhv_nestedv2_io *io;
+	struct kvmppc_gs_bitmap *valids;
+	struct kvmppc_gs_msg *gsm;
+
+	if (!iden)
+		return 0;
+
+	io = &vcpu->arch.nestedv2_io;
+	valids = &io->valids;
+	gsm = io->vcpu_message;
+	kvmppc_gsm_include(gsm, iden);
+	gsm = io->vcore_message;
+	kvmppc_gsm_include(gsm, iden);
+	kvmppc_gsbm_set(valids, iden);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__kvmhv_nestedv2_mark_dirty);
+
+/**
+ * __kvmhv_nestedv2_cached_reload() - reload a Guest State ID from the host
+ * @vcpu: vcpu
+ * @iden: guest state ID
+ *
+ * Reload the value for the guest state ID from the L0 host into the L1 host.
+ * This is cached so that going out to the L0 host only happens if necessary.
+ */
+int __kvmhv_nestedv2_cached_reload(struct kvm_vcpu *vcpu, u16 iden)
+{
+	struct kvmhv_nestedv2_io *io;
+	struct kvmppc_gs_bitmap *valids;
+	struct kvmppc_gs_buff *gsb;
+	struct kvmppc_gs_msg gsm;
+	int rc;
+
+	if (!iden)
+		return 0;
+
+	io = &vcpu->arch.nestedv2_io;
+	valids = &io->valids;
+	if (kvmppc_gsbm_test(valids, iden))
+		return 0;
+
+	gsb = io->vcpu_run_input;
+	kvmppc_gsm_init(&gsm, &vcpu_message_ops, vcpu, kvmppc_gsid_flags(iden));
+	rc = kvmppc_gsb_receive_datum(gsb, &gsm, iden);
+	if (rc < 0) {
+		pr_err("KVM-NESTEDv2: couldn't get GSID: 0x%x\n", iden);
+		return rc;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__kvmhv_nestedv2_cached_reload);
+
+/**
+ * kvmhv_nestedv2_flush_vcpu() - send modified Guest State IDs to the host
+ * @vcpu: vcpu
+ * @time_limit: hdec expiry tb
+ *
+ * Send the values marked by __kvmhv_nestedv2_mark_dirty() to the L0 host.
+ * Thread wide values are copied to the H_GUEST_RUN_VCPU input buffer. Guest
+ * wide values need to be sent with H_GUEST_SET first.
+ *
+ * The hdec tb offset is always sent to L0 host.
+ */
+int kvmhv_nestedv2_flush_vcpu(struct kvm_vcpu *vcpu, u64 time_limit)
+{
+	struct kvmhv_nestedv2_io *io;
+	struct kvmppc_gs_buff *gsb;
+	struct kvmppc_gs_msg *gsm;
+	int rc;
+
+	io = &vcpu->arch.nestedv2_io;
+	gsb = io->vcpu_run_input;
+	gsm = io->vcore_message;
+	rc = kvmppc_gsb_send_data(gsb, gsm);
+	if (rc < 0) {
+		pr_err("KVM-NESTEDv2: couldn't set guest wide elements\n");
+		return rc;
+	}
+
+	gsm = io->vcpu_message;
+	kvmppc_gsb_reset(gsb);
+	rc = kvmppc_gsm_fill_info(gsm, gsb);
+	if (rc < 0) {
+		pr_err("KVM-NESTEDv2: couldn't fill vcpu run input buffer\n");
+		return rc;
+	}
+
+	rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_HDEC_EXPIRY_TB, time_limit);
+	if (rc < 0)
+		return rc;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvmhv_nestedv2_flush_vcpu);
+
+/**
+ * kvmhv_nestedv2_set_ptbl_entry() - send partition and process table state to
+ * L0 host
+ * @lpid: guest id
+ * @dw0: partition table double word
+ * @dw1: process table double word
+ */
+int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1)
+{
+	struct kvmppc_gs_part_table patbl;
+	struct kvmppc_gs_proc_table prtbl;
+	struct kvmppc_gs_buff *gsb;
+	size_t size;
+	int rc;
+
+	size = kvmppc_gse_total_size(
+		       kvmppc_gsid_size(KVMPPC_GSID_PARTITION_TABLE)) +
+	       kvmppc_gse_total_size(
+		       kvmppc_gsid_size(KVMPPC_GSID_PROCESS_TABLE)) +
+	       sizeof(struct kvmppc_gs_header);
+	gsb = kvmppc_gsb_new(size, lpid, 0, GFP_KERNEL);
+	if (!gsb)
+		return -ENOMEM;
+
+	patbl.address = dw0 & RPDB_MASK;
+	patbl.ea_bits = ((((dw0 & RTS1_MASK) >> (RTS1_SHIFT - 3)) |
+			  ((dw0 & RTS2_MASK) >> RTS2_SHIFT)) +
+			 31);
+	patbl.gpd_size = 1ul << ((dw0 & RPDS_MASK) + 3);
+	rc = kvmppc_gse_put_part_table(gsb, KVMPPC_GSID_PARTITION_TABLE, patbl);
+	if (rc < 0)
+		goto free_gsb;
+
+	prtbl.address = dw1 & PRTB_MASK;
+	prtbl.gpd_size = 1ul << ((dw1 & PRTS_MASK) + 12);
+	rc = kvmppc_gse_put_proc_table(gsb, KVMPPC_GSID_PROCESS_TABLE, prtbl);
+	if (rc < 0)
+		goto free_gsb;
+
+	rc = kvmppc_gsb_send(gsb, KVMPPC_GS_FLAGS_WIDE);
+	if (rc < 0) {
+		pr_err("KVM-NESTEDv2: couldn't set the PATE\n");
+		goto free_gsb;
+	}
+
+	kvmppc_gsb_free(gsb);
+	return 0;
+
+free_gsb:
+	kvmppc_gsb_free(gsb);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(kvmhv_nestedv2_set_ptbl_entry);
+
+/**
+ * kvmhv_nestedv2_set_vpa() - register L2 VPA with L0
+ * @vcpu: vcpu
+ * @vpa: L1 logical real address
+ */
+int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa)
+{
+	struct kvmhv_nestedv2_io *io;
+	struct kvmppc_gs_buff *gsb;
+	int rc = 0;
+
+	io = &vcpu->arch.nestedv2_io;
+	gsb = io->vcpu_run_input;
+
+	kvmppc_gsb_reset(gsb);
+	rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_VPA, vpa);
+	if (rc < 0)
+		goto out;
+
+	rc = kvmppc_gsb_send(gsb, 0);
+	if (rc < 0)
+		pr_err("KVM-NESTEDv2: couldn't register the L2 VPA (rc=%d)\n", rc);
+
+out:
+	kvmppc_gsb_reset(gsb);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(kvmhv_nestedv2_set_vpa);
+
+/**
+ * kvmhv_nestedv2_parse_output() - receive values from H_GUEST_RUN_VCPU output
+ * @vcpu: vcpu
+ *
+ * Parse the output buffer from H_GUEST_RUN_VCPU to update vcpu.
+ */
+int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu)
+{
+	struct kvmhv_nestedv2_io *io;
+	struct kvmppc_gs_buff *gsb;
+	struct kvmppc_gs_msg gsm;
+
+	io = &vcpu->arch.nestedv2_io;
+	gsb = io->vcpu_run_output;
+
+	vcpu->arch.fault_dar = 0;
+	vcpu->arch.fault_dsisr = 0;
+	vcpu->arch.fault_gpa = 0;
+	vcpu->arch.emul_inst = KVM_INST_FETCH_FAILED;
+
+	kvmppc_gsm_init(&gsm, &vcpu_message_ops, vcpu, 0);
+	return kvmppc_gsm_refresh_info(&gsm, gsb);
+}
+EXPORT_SYMBOL_GPL(kvmhv_nestedv2_parse_output);
+
+static void kvmhv_nestedv2_host_free(struct kvm_vcpu *vcpu,
+				     struct kvmhv_nestedv2_io *io)
+{
+	kvmppc_gsm_free(io->vcpu_message);
+	kvmppc_gsm_free(io->vcore_message);
+	kvmppc_gsb_free(io->vcpu_run_input);
+	kvmppc_gsb_free(io->vcpu_run_output);
+}
+
+int __kvmhv_nestedv2_reload_ptregs(struct kvm_vcpu *vcpu, struct pt_regs *regs)
+{
+	struct kvmhv_nestedv2_io *io;
+	struct kvmppc_gs_bitmap *valids;
+	struct kvmppc_gs_buff *gsb;
+	struct kvmppc_gs_msg gsm;
+	int rc = 0;
+
+
+	io = &vcpu->arch.nestedv2_io;
+	valids = &io->valids;
+
+	gsb = io->vcpu_run_input;
+	kvmppc_gsm_init(&gsm, &vcpu_message_ops, vcpu, 0);
+
+	for (int i = 0; i < 32; i++) {
+		if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_GPR(i)))
+			kvmppc_gsm_include(&gsm, KVMPPC_GSID_GPR(i));
+	}
+
+	if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_CR))
+		kvmppc_gsm_include(&gsm, KVMPPC_GSID_CR);
+
+	if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_XER))
+		kvmppc_gsm_include(&gsm, KVMPPC_GSID_XER);
+
+	if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_CTR))
+		kvmppc_gsm_include(&gsm, KVMPPC_GSID_CTR);
+
+	if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_LR))
+		kvmppc_gsm_include(&gsm, KVMPPC_GSID_LR);
+
+	if (!kvmppc_gsbm_test(valids, KVMPPC_GSID_NIA))
+		kvmppc_gsm_include(&gsm, KVMPPC_GSID_NIA);
+
+	rc = kvmppc_gsb_receive_data(gsb, &gsm);
+	if (rc < 0)
+		pr_err("KVM-NESTEDv2: couldn't reload ptregs\n");
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(__kvmhv_nestedv2_reload_ptregs);
+
+int __kvmhv_nestedv2_mark_dirty_ptregs(struct kvm_vcpu *vcpu,
+				       struct pt_regs *regs)
+{
+	for (int i = 0; i < 32; i++)
+		kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_GPR(i));
+
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CR);
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_XER);
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_CTR);
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LR);
+	kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_NIA);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__kvmhv_nestedv2_mark_dirty_ptregs);
+
+/**
+ * kvmhv_nestedv2_vcpu_create() - create nested vcpu for the NESTEDv2 API
+ * @vcpu: vcpu
+ * @io: NESTEDv2 nested io state
+ *
+ * Parse the output buffer from H_GUEST_RUN_VCPU to update vcpu.
+ */
+int kvmhv_nestedv2_vcpu_create(struct kvm_vcpu *vcpu,
+			       struct kvmhv_nestedv2_io *io)
+{
+	long rc;
+
+	rc = plpar_guest_create_vcpu(0, vcpu->kvm->arch.lpid, vcpu->vcpu_id);
+
+	if (rc != H_SUCCESS) {
+		pr_err("KVM: Create Guest vcpu hcall failed, rc=%ld\n", rc);
+		switch (rc) {
+		case H_NOT_ENOUGH_RESOURCES:
+		case H_ABORTED:
+			return -ENOMEM;
+		case H_AUTHORITY:
+			return -EPERM;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	rc = kvmhv_nestedv2_host_create(vcpu, io);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(kvmhv_nestedv2_vcpu_create);
+
+/**
+ * kvmhv_nestedv2_vcpu_free() - free the NESTEDv2 state
+ * @vcpu: vcpu
+ * @io: NESTEDv2 nested io state
+ */
+void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu,
+			      struct kvmhv_nestedv2_io *io)
+{
+	kvmhv_nestedv2_host_free(vcpu, io);
+}
+EXPORT_SYMBOL_GPL(kvmhv_nestedv2_vcpu_free);
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index 34f1db212824..34bc0a8a1288 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -305,7 +305,7 @@ static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u6
 	u32 pid;
 
 	lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
-	pid = vcpu->arch.pid;
+	pid = kvmppc_get_pid(vcpu);
 
 	/*
 	 * Prior memory accesses to host PID Q3 must be completed before we
@@ -330,7 +330,7 @@ static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64
 	int i;
 
 	lpid = kvm->arch.lpid;
-	pid = vcpu->arch.pid;
+	pid = kvmppc_get_pid(vcpu);
 
 	/*
 	 * See switch_mmu_to_guest_radix. ptesync should not be required here
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index ccfd96965630..9012acadbca8 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -9,6 +9,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/kernel.h>
+#include <asm/lppaca.h>
 #include <asm/opal.h>
 #include <asm/mce.h>
 #include <asm/machdep.h>
@@ -173,14 +174,14 @@ long kvmppc_p9_realmode_hmi_handler(struct kvm_vcpu *vcpu)
 		ppc_md.hmi_exception_early(NULL);
 
 out:
-	if (vc->tb_offset) {
+	if (kvmppc_get_tb_offset(vcpu)) {
 		u64 new_tb = mftb() + vc->tb_offset;
 		mtspr(SPRN_TBU40, new_tb);
 		if ((mftb() & 0xffffff) < (new_tb & 0xffffff)) {
 			new_tb += 0x1000000;
 			mtspr(SPRN_TBU40, new_tb);
 		}
-		vc->tb_offset_applied = vc->tb_offset;
+		vc->tb_offset_applied = kvmppc_get_tb_offset(vcpu);
 	}
 
 	return ret;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 9182324dbef9..17cb75a127b0 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -776,8 +776,8 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 			r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
 			r &= ~HPTE_GR_RESERVED;
 		}
-		vcpu->arch.regs.gpr[4 + i * 2] = v;
-		vcpu->arch.regs.gpr[5 + i * 2] = r;
+		kvmppc_set_gpr(vcpu, 4 + i * 2, v);
+		kvmppc_set_gpr(vcpu, 5 + i * 2, r);
 	}
 	return H_SUCCESS;
 }
@@ -824,7 +824,7 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
 			}
 		}
 	}
-	vcpu->arch.regs.gpr[4] = gr;
+	kvmppc_set_gpr(vcpu, 4, gr);
 	ret = H_SUCCESS;
  out:
 	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
@@ -872,7 +872,7 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
 			kvmppc_set_dirty_from_hpte(kvm, v, gr);
 		}
 	}
-	vcpu->arch.regs.gpr[4] = gr;
+	kvmppc_set_gpr(vcpu, 4, gr);
 	ret = H_SUCCESS;
  out:
 	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index e165bfa842bf..f2636414d82a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -481,7 +481,7 @@ static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 
 unsigned long xics_rm_h_xirr_x(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.regs.gpr[5] = get_tb();
+	kvmppc_set_gpr(vcpu, 5, get_tb());
 	return xics_rm_h_xirr(vcpu);
 }
 
@@ -518,7 +518,7 @@ unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu)
 	} while (!icp_rm_try_update(icp, old_state, new_state));
 
 	/* Return the result in GPR4 */
-	vcpu->arch.regs.gpr[4] = xirr;
+	kvmppc_set_gpr(vcpu, 4, xirr);
 
 	return check_too_hard(xics, icp);
 }
@@ -837,7 +837,7 @@ static inline void this_cpu_inc_rm(unsigned int __percpu *addr)
  */
 static void kvmppc_rm_handle_irq_desc(struct irq_desc *desc)
 {
-	this_cpu_inc_rm(desc->kstat_irqs);
+	this_cpu_inc_rm(&desc->kstat_irqs->cnt);
 	__this_cpu_inc(kstat.irqs_sum);
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 870110e3d9b1..83f7504349d2 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -10,6 +10,7 @@
  * Authors: Alexander Graf <agraf@suse.de>
  */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <linux/objtool.h>
 #include <asm/ppc_asm.h>
@@ -24,7 +25,6 @@
 #include <asm/exception-64s.h>
 #include <asm/kvm_book3s_asm.h>
 #include <asm/book3s/64/mmu-hash.h>
-#include <asm/export.h>
 #include <asm/tm.h>
 #include <asm/opal.h>
 #include <asm/thread_info.h>
@@ -1524,14 +1524,12 @@ kvm_flush_link_stack:
 
 	/* Flush the link stack. On Power8 it's up to 32 entries in size. */
 	.rept 32
-	ANNOTATE_INTRA_FUNCTION_CALL
 	bl	.+4
 	.endr
 
 	/* And on Power9 it's up to 64. */
 BEGIN_FTR_SECTION
 	.rept 32
-	ANNOTATE_INTRA_FUNCTION_CALL
 	bl	.+4
 	.endr
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 709ebd578394..e5000bef90f2 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -393,7 +393,7 @@ static int kvmppc_memslot_page_merge(struct kvm *kvm,
 {
 	unsigned long gfn = memslot->base_gfn;
 	unsigned long end, start = gfn_to_hva(kvm, gfn);
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 	int ret = 0;
 	struct vm_area_struct *vma;
 	int merge_flag = (merge) ? MADV_MERGEABLE : MADV_UNMERGEABLE;
@@ -410,6 +410,7 @@ static int kvmppc_memslot_page_merge(struct kvm *kvm,
 			ret = H_STATE;
 			break;
 		}
+		vma_start_write(vma);
 		/* Copy vm_flags to avoid partial modifications in ksm_madvise */
 		vm_flags = vma->vm_flags;
 		ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
@@ -722,7 +723,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
 
 	dpage = pfn_to_page(uvmem_pfn);
 	dpage->zone_device_data = pvt;
-	zone_device_page_init(dpage);
+	zone_device_page_init(dpage, 0);
 	return dpage;
 out_clear:
 	spin_lock(&kvmppc_uvmem_bitmap_lock);
@@ -857,7 +858,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
 	}
 
 	kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
-	pr_info("LPID %d went secure\n", kvm->arch.lpid);
+	pr_info("LPID %lld went secure\n", kvm->arch.lpid);
 
 out:
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
@@ -878,9 +879,8 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
 {
 
 	int ret = H_PARAMETER;
-	struct page *uvmem_page;
+	struct page *page, *uvmem_page;
 	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn;
 	unsigned long gfn = gpa >> page_shift;
 	int srcu_idx;
 	unsigned long uvmem_pfn;
@@ -900,8 +900,8 @@ static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
 
 retry:
 	mutex_unlock(&kvm->arch.uvmem_lock);
-	pfn = gfn_to_pfn(kvm, gfn);
-	if (is_error_noslot_pfn(pfn))
+	page = gfn_to_page(kvm, gfn);
+	if (!page)
 		goto out;
 
 	mutex_lock(&kvm->arch.uvmem_lock);
@@ -910,16 +910,16 @@ retry:
 		pvt = uvmem_page->zone_device_data;
 		pvt->skip_page_out = true;
 		pvt->remove_gfn = false; /* it continues to be a valid GFN */
-		kvm_release_pfn_clean(pfn);
+		kvm_release_page_unused(page);
 		goto retry;
 	}
 
-	if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
+	if (!uv_page_in(kvm->arch.lpid, page_to_pfn(page) << page_shift, gpa, 0,
 				page_shift)) {
 		kvmppc_gfn_shared(gfn, kvm);
 		ret = H_SUCCESS;
 	}
-	kvm_release_pfn_clean(pfn);
+	kvm_release_page_clean(page);
 	mutex_unlock(&kvm->arch.uvmem_lock);
 out:
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
@@ -1014,8 +1014,9 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
  * to a normal PFN during H_SVM_PAGE_OUT.
  * Gets called with kvm->arch.uvmem_lock held.
  */
-static void kvmppc_uvmem_page_free(struct page *page)
+static void kvmppc_uvmem_folio_free(struct folio *folio)
 {
+	struct page *page = &folio->page;
 	unsigned long pfn = page_to_pfn(page) -
 			(kvmppc_uvmem_pgmap.range.start >> PAGE_SHIFT);
 	struct kvmppc_uvmem_page_pvt *pvt;
@@ -1034,7 +1035,7 @@ static void kvmppc_uvmem_page_free(struct page *page)
 }
 
 static const struct dev_pagemap_ops kvmppc_uvmem_ops = {
-	.page_free = kvmppc_uvmem_page_free,
+	.folio_free = kvmppc_uvmem_folio_free,
 	.migrate_to_ram	= kvmppc_uvmem_migrate_to_ram,
 };
 
@@ -1082,21 +1083,21 @@ out:
 
 int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
 {
-	unsigned long pfn;
+	struct page *page;
 	int ret = U_SUCCESS;
 
-	pfn = gfn_to_pfn(kvm, gfn);
-	if (is_error_noslot_pfn(pfn))
+	page = gfn_to_page(kvm, gfn);
+	if (!page)
 		return -EFAULT;
 
 	mutex_lock(&kvm->arch.uvmem_lock);
 	if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL))
 		goto out;
 
-	ret = uv_page_in(kvm->arch.lpid, pfn << PAGE_SHIFT, gfn << PAGE_SHIFT,
-			 0, PAGE_SHIFT);
+	ret = uv_page_in(kvm->arch.lpid, page_to_pfn(page) << PAGE_SHIFT,
+			 gfn << PAGE_SHIFT, 0, PAGE_SHIFT);
 out:
-	kvm_release_pfn_clean(pfn);
+	kvm_release_page_clean(page);
 	mutex_unlock(&kvm->arch.uvmem_lock);
 	return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT;
 }
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index ce79ac33e8d3..d904e13e069b 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -92,12 +92,6 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	spin_unlock(&vcpu3s->mmu_lock);
 }
 
-static void free_pte_rcu(struct rcu_head *head)
-{
-	struct hpte_cache *pte = container_of(head, struct hpte_cache, rcu_head);
-	kmem_cache_free(hpte_cache, pte);
-}
-
 static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
@@ -126,7 +120,7 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 
 	spin_unlock(&vcpu3s->mmu_lock);
 
-	call_rcu(&pte->rcu_head, free_pte_rcu);
+	kfree_rcu(pte, rcu_head);
 }
 
 static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 9118242063fb..83bcdc80ce51 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -461,12 +461,6 @@ static bool kvm_test_age_gfn_pr(struct kvm *kvm, struct kvm_gfn_range *range)
 	return false;
 }
 
-static bool kvm_set_spte_gfn_pr(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	/* The page will get remapped properly on its next fault */
-	return do_kvm_unmap_gfn(kvm, range);
-}
-
 /*****************************************/
 
 static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
@@ -604,6 +598,7 @@ static void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
 	case PVR_POWER8:
 	case PVR_POWER8E:
 	case PVR_POWER8NVL:
+	case PVR_HX_C2000:
 	case PVR_POWER9:
 		vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
 			BOOK3S_HFLAG_NEW_TLBIE;
@@ -644,29 +639,27 @@ static void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
  */
 static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
 {
-	struct page *hpage;
+	struct kvm_host_map map;
 	u64 hpage_offset;
 	u32 *page;
-	int i;
+	int i, r;
 
-	hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
-	if (is_error_page(hpage))
+	r = kvm_vcpu_map(vcpu, pte->raddr >> PAGE_SHIFT, &map);
+	if (r)
 		return;
 
 	hpage_offset = pte->raddr & ~PAGE_MASK;
 	hpage_offset &= ~0xFFFULL;
 	hpage_offset /= 4;
 
-	get_page(hpage);
-	page = kmap_atomic(hpage);
+	page = map.hva;
 
 	/* patch dcbz into reserved instruction, so we trap */
 	for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++)
 		if ((be32_to_cpu(page[i]) & 0xff0007ff) == INS_DCBZ)
 			page[i] &= cpu_to_be32(0xfffffff7);
 
-	kunmap_atomic(page);
-	put_page(hpage);
+	kvm_vcpu_unmap(vcpu, &map);
 }
 
 static bool kvmppc_visible_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
@@ -2070,7 +2063,6 @@ static struct kvmppc_ops kvm_ops_pr = {
 	.unmap_gfn_range = kvm_unmap_gfn_range_pr,
 	.age_gfn  = kvm_age_gfn_pr,
 	.test_age_gfn = kvm_test_age_gfn_pr,
-	.set_spte_gfn = kvm_set_spte_gfn_pr,
 	.free_memslot = kvmppc_core_free_memslot_pr,
 	.init_vm = kvmppc_core_init_vm_pr,
 	.destroy_vm = kvmppc_core_destroy_vm_pr,
@@ -2117,6 +2109,7 @@ void kvmppc_book3s_exit_pr(void)
 module_init(kvmppc_book3s_init_pr);
 module_exit(kvmppc_book3s_exit_pr);
 
+MODULE_DESCRIPTION("KVM on Book3S without using hypervisor mode");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_MISCDEV(KVM_MINOR);
 MODULE_ALIAS("devname:kvm");
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index f4115819e738..89a1b8c21ab4 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -328,7 +328,7 @@ static unsigned long xive_vm_h_xirr(struct kvm_vcpu *vcpu)
 	 */
 
 	/* Return interrupt and old CPPR in GPR4 */
-	vcpu->arch.regs.gpr[4] = hirq | (old_cppr << 24);
+	kvmppc_set_gpr(vcpu, 4, hirq | (old_cppr << 24));
 
 	return H_SUCCESS;
 }
@@ -364,7 +364,7 @@ static unsigned long xive_vm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server
 	hirq = xive_vm_scan_interrupts(xc, pending, scan_poll);
 
 	/* Return interrupt and old CPPR in GPR4 */
-	vcpu->arch.regs.gpr[4] = hirq | (xc->cppr << 24);
+	kvmppc_set_gpr(vcpu, 4, hirq | (xc->cppr << 24));
 
 	return H_SUCCESS;
 }
@@ -531,7 +531,7 @@ static int xive_vm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
 	xc->cppr = xive_prio_from_guest(new_cppr);
 
 	/*
-	 * IPIs are synthetized from MFRR and thus don't need
+	 * IPIs are synthesized from MFRR and thus don't need
 	 * any special EOI handling. The underlying interrupt
 	 * used to signal MFRR changes is EOId when fetched from
 	 * the queue.
@@ -884,10 +884,10 @@ int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
 	}
 
 	if (single_escalation)
-		name = kasprintf(GFP_KERNEL, "kvm-%d-%d",
+		name = kasprintf(GFP_KERNEL, "kvm-%lld-%d",
 				 vcpu->kvm->arch.lpid, xc->server_num);
 	else
-		name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d",
+		name = kasprintf(GFP_KERNEL, "kvm-%lld-%d-%d",
 				 vcpu->kvm->arch.lpid, xc->server_num, prio);
 	if (!name) {
 		pr_err("Failed to allocate escalation irq name for queue %d of VCPU %d\n",
@@ -916,8 +916,7 @@ int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
 	 * it fires once.
 	 */
 	if (single_escalation) {
-		struct irq_data *d = irq_get_irq_data(xc->esc_virq[prio]);
-		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+		struct xive_irq_data *xd = irq_get_chip_data(xc->esc_virq[prio]);
 
 		xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01);
 		vcpu->arch.xive_esc_raddr = xd->eoi_page;
@@ -1555,7 +1554,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	struct kvmppc_xive_src_block *sb;
 	struct kvmppc_xive_irq_state *state;
 	struct irq_data *host_data =
-		irq_domain_get_irq_data(irq_get_default_host(), host_irq);
+		irq_domain_get_irq_data(irq_get_default_domain(), host_irq);
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(host_data);
 	u16 idx;
 	u8 prio;
@@ -1612,7 +1611,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 
 	/* Grab info about irq */
 	state->pt_number = hw_irq;
-	state->pt_data = irq_data_get_irq_handler_data(host_data);
+	state->pt_data = irq_data_get_irq_chip_data(host_data);
 
 	/*
 	 * Configure the IRQ to match the existing configuration of
@@ -1787,8 +1786,7 @@ void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
  */
 void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu, int irq)
 {
-	struct irq_data *d = irq_get_irq_data(irq);
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_get_chip_data(irq);
 
 	/*
 	 * This slightly odd sequence gives the right result
@@ -2779,8 +2777,6 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 
 int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 {
-	struct kvmppc_vcore *vc = vcpu->arch.vcore;
-
 	/* The VM should have configured XICS mode before doing XICS hcalls. */
 	if (!kvmppc_xics_enabled(vcpu))
 		return H_TOO_HARD;
@@ -2799,7 +2795,7 @@ int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 		return xive_vm_h_ipoll(vcpu, kvmppc_get_gpr(vcpu, 4));
 	case H_XIRR_X:
 		xive_vm_h_xirr(vcpu);
-		kvmppc_set_gpr(vcpu, 5, get_tb() + vc->tb_offset);
+		kvmppc_set_gpr(vcpu, 5, get_tb() + kvmppc_get_tb_offset(vcpu));
 		return H_SUCCESS;
 	}
 
@@ -2829,9 +2825,7 @@ int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu)
 				   i0, i1);
 		}
 		if (xc->esc_virq[i]) {
-			struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]);
-			struct xive_irq_data *xd =
-				irq_data_get_irq_handler_data(d);
+			struct xive_irq_data *xd = irq_get_chip_data(xc->esc_virq[i]);
 			u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
 
 			seq_printf(m, "    ESC %d %c%c EOI @%llx",
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 712ab91ced39..d9bf1bc3ff61 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -567,7 +567,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	u8 priority;
 	struct kvm_ppc_xive_eq kvm_eq;
 	int rc;
-	__be32 *qaddr = 0;
+	__be32 *qaddr = NULL;
 	struct page *page;
 	struct xive_q *q;
 	gfn_t gfn;
@@ -654,7 +654,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	}
 
 	page = gfn_to_page(kvm, gfn);
-	if (is_error_page(page)) {
+	if (!page) {
 		srcu_read_unlock(&kvm->srcu, srcu_idx);
 		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
 		return -EINVAL;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 6a5be025a8af..3401b96be475 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -572,7 +572,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 
 /*
  * Return the number of jiffies until the next timeout.  If the timeout is
- * longer than the NEXT_TIMER_MAX_DELTA, then return NEXT_TIMER_MAX_DELTA
+ * longer than the TIMER_NEXT_MAX_DELTA, then return TIMER_NEXT_MAX_DELTA
  * because the larger value can break the timer APIs.
  */
 static unsigned long watchdog_next_timeout(struct kvm_vcpu *vcpu)
@@ -598,7 +598,7 @@ static unsigned long watchdog_next_timeout(struct kvm_vcpu *vcpu)
 	if (do_div(nr_jiffies, tb_ticks_per_jiffy))
 		nr_jiffies++;
 
-	return min_t(unsigned long long, nr_jiffies, NEXT_TIMER_MAX_DELTA);
+	return min_t(unsigned long long, nr_jiffies, TIMER_NEXT_MAX_DELTA);
 }
 
 static void arm_next_watchdog(struct kvm_vcpu *vcpu)
@@ -616,19 +616,19 @@ static void arm_next_watchdog(struct kvm_vcpu *vcpu)
 	spin_lock_irqsave(&vcpu->arch.wdt_lock, flags);
 	nr_jiffies = watchdog_next_timeout(vcpu);
 	/*
-	 * If the number of jiffies of watchdog timer >= NEXT_TIMER_MAX_DELTA
+	 * If the number of jiffies of watchdog timer >= TIMER_NEXT_MAX_DELTA
 	 * then do not run the watchdog timer as this can break timer APIs.
 	 */
-	if (nr_jiffies < NEXT_TIMER_MAX_DELTA)
+	if (nr_jiffies < TIMER_NEXT_MAX_DELTA)
 		mod_timer(&vcpu->arch.wdt_timer, jiffies + nr_jiffies);
 	else
-		del_timer(&vcpu->arch.wdt_timer);
+		timer_delete(&vcpu->arch.wdt_timer);
 	spin_unlock_irqrestore(&vcpu->arch.wdt_lock, flags);
 }
 
 static void kvmppc_watchdog_func(struct timer_list *t)
 {
-	struct kvm_vcpu *vcpu = from_timer(vcpu, t, arch.wdt_timer);
+	struct kvm_vcpu *vcpu = timer_container_of(vcpu, t, arch.wdt_timer);
 	u32 tsr, new_tsr;
 	int final;
 
@@ -1441,7 +1441,7 @@ int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
 
 void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
-	del_timer_sync(&vcpu->arch.wdt_timer);
+	timer_delete_sync(&vcpu->arch.wdt_timer);
 }
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index 6d0d329cbb35..f9acf866c709 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -34,6 +34,8 @@ enum vcpu_ftr {
 #define E500_TLB_BITMAP		(1 << 30)
 /* TLB1 entry is mapped by host TLB0 */
 #define E500_TLB_TLB0		(1 << 29)
+/* entry is writable on the host */
+#define E500_TLB_WRITABLE	(1 << 28)
 /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */
 #define E500_TLB_MAS2_ATTR	(0x7f)
 
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index ccb8f16ffe41..06caf8bbbe2b 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -45,11 +45,14 @@ static inline unsigned int tlb1_max_shadow_size(void)
 	return host_tlb_params[1].entries - tlbcam_index - 1;
 }
 
-static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
+static inline u32 e500_shadow_mas3_attrib(u32 mas3, bool writable, int usermode)
 {
 	/* Mask off reserved bits. */
 	mas3 &= MAS3_ATTRIB_MASK;
 
+	if (!writable)
+		mas3 &= ~(MAS3_UW|MAS3_SW);
+
 #ifndef CONFIG_KVM_BOOKE_HV
 	if (!usermode) {
 		/* Guest is in supervisor mode,
@@ -244,19 +247,16 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
 
 static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 					 struct kvm_book3e_206_tlb_entry *gtlbe,
-					 kvm_pfn_t pfn, unsigned int wimg)
+					 kvm_pfn_t pfn, unsigned int wimg,
+					 bool writable)
 {
 	ref->pfn = pfn;
 	ref->flags = E500_TLB_VALID;
+	if (writable)
+		ref->flags |= E500_TLB_WRITABLE;
 
 	/* Use guest supplied MAS2_G and MAS2_E */
 	ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg;
-
-	/* Mark the page accessed */
-	kvm_set_pfn_accessed(pfn);
-
-	if (tlbe_is_writable(gtlbe))
-		kvm_set_pfn_dirty(pfn);
 }
 
 static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
@@ -309,6 +309,7 @@ static void kvmppc_e500_setup_stlbe(
 {
 	kvm_pfn_t pfn = ref->pfn;
 	u32 pr = vcpu->arch.shared->msr & MSR_PR;
+	bool writable = !!(ref->flags & E500_TLB_WRITABLE);
 
 	BUG_ON(!(ref->flags & E500_TLB_VALID));
 
@@ -316,7 +317,7 @@ static void kvmppc_e500_setup_stlbe(
 	stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
 	stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR);
 	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
-			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
+			e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr);
 }
 
 static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -325,18 +326,19 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	struct tlbe_ref *ref)
 {
 	struct kvm_memory_slot *slot;
-	unsigned long pfn = 0; /* silence GCC warning */
+	unsigned int psize;
+	unsigned long pfn;
+	struct page *page = NULL;
 	unsigned long hva;
-	int pfnmap = 0;
 	int tsize = BOOK3E_PAGESZ_4K;
 	int ret = 0;
 	unsigned long mmu_seq;
 	struct kvm *kvm = vcpu_e500->vcpu.kvm;
-	unsigned long tsize_pages = 0;
 	pte_t *ptep;
 	unsigned int wimg = 0;
 	pgd_t *pgdir;
 	unsigned long flags;
+	bool writable = false;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_invalidate_seq;
@@ -353,110 +355,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn);
 	hva = gfn_to_hva_memslot(slot, gfn);
 
-	if (tlbsel == 1) {
-		struct vm_area_struct *vma;
-		mmap_read_lock(kvm->mm);
-
-		vma = find_vma(kvm->mm, hva);
-		if (vma && hva >= vma->vm_start &&
-		    (vma->vm_flags & VM_PFNMAP)) {
-			/*
-			 * This VMA is a physically contiguous region (e.g.
-			 * /dev/mem) that bypasses normal Linux page
-			 * management.  Find the overlap between the
-			 * vma and the memslot.
-			 */
-
-			unsigned long start, end;
-			unsigned long slot_start, slot_end;
-
-			pfnmap = 1;
-
-			start = vma->vm_pgoff;
-			end = start +
-			      vma_pages(vma);
-
-			pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT);
-
-			slot_start = pfn - (gfn - slot->base_gfn);
-			slot_end = slot_start + slot->npages;
-
-			if (start < slot_start)
-				start = slot_start;
-			if (end > slot_end)
-				end = slot_end;
-
-			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
-				MAS1_TSIZE_SHIFT;
-
-			/*
-			 * e500 doesn't implement the lowest tsize bit,
-			 * or 1K pages.
-			 */
-			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
-
-			/*
-			 * Now find the largest tsize (up to what the guest
-			 * requested) that will cover gfn, stay within the
-			 * range, and for which gfn and pfn are mutually
-			 * aligned.
-			 */
-
-			for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
-				unsigned long gfn_start, gfn_end;
-				tsize_pages = 1UL << (tsize - 2);
-
-				gfn_start = gfn & ~(tsize_pages - 1);
-				gfn_end = gfn_start + tsize_pages;
-
-				if (gfn_start + pfn - gfn < start)
-					continue;
-				if (gfn_end + pfn - gfn > end)
-					continue;
-				if ((gfn & (tsize_pages - 1)) !=
-				    (pfn & (tsize_pages - 1)))
-					continue;
-
-				gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
-				pfn &= ~(tsize_pages - 1);
-				break;
-			}
-		} else if (vma && hva >= vma->vm_start &&
-			   is_vm_hugetlb_page(vma)) {
-			unsigned long psize = vma_kernel_pagesize(vma);
-
-			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
-				MAS1_TSIZE_SHIFT;
-
-			/*
-			 * Take the largest page size that satisfies both host
-			 * and guest mapping
-			 */
-			tsize = min(__ilog2(psize) - 10, tsize);
-
-			/*
-			 * e500 doesn't implement the lowest tsize bit,
-			 * or 1K pages.
-			 */
-			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
-		}
-
-		mmap_read_unlock(kvm->mm);
-	}
-
-	if (likely(!pfnmap)) {
-		tsize_pages = 1UL << (tsize + 10 - PAGE_SHIFT);
-		pfn = gfn_to_pfn_memslot(slot, gfn);
-		if (is_error_noslot_pfn(pfn)) {
-			if (printk_ratelimit())
-				pr_err("%s: real page not found for gfn %lx\n",
-				       __func__, (long)gfn);
-			return -EINVAL;
-		}
-
-		/* Align guest and physical address to page map boundaries */
-		pfn &= ~(tsize_pages - 1);
-		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
+	pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &page);
+	if (is_error_noslot_pfn(pfn)) {
+		if (printk_ratelimit())
+			pr_err("%s: real page not found for gfn %lx\n",
+			       __func__, (long)gfn);
+		return -EINVAL;
 	}
 
 	spin_lock(&kvm->mmu_lock);
@@ -474,14 +378,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	 * can't run hence pfn won't change.
 	 */
 	local_irq_save(flags);
-	ptep = find_linux_pte(pgdir, hva, NULL, NULL);
+	ptep = find_linux_pte(pgdir, hva, NULL, &psize);
 	if (ptep) {
 		pte_t pte = READ_ONCE(*ptep);
 
 		if (pte_present(pte)) {
 			wimg = (pte_val(pte) >> PTE_WIMGE_SHIFT) &
 				MAS2_WIMGE_MASK;
-			local_irq_restore(flags);
 		} else {
 			local_irq_restore(flags);
 			pr_err_ratelimited("%s: pte not present: gfn %lx,pfn %lx\n",
@@ -490,20 +393,79 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 			goto out;
 		}
 	}
-	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg);
+	local_irq_restore(flags);
+
+	if (psize && tlbsel == 1) {
+		unsigned long psize_pages, tsize_pages;
+		unsigned long start, end;
+		unsigned long slot_start, slot_end;
+
+		psize_pages = 1UL << (psize - PAGE_SHIFT);
+		start = pfn & ~(psize_pages - 1);
+		end = start + psize_pages;
+
+		slot_start = pfn - (gfn - slot->base_gfn);
+		slot_end = slot_start + slot->npages;
+
+		if (start < slot_start)
+			start = slot_start;
+		if (end > slot_end)
+			end = slot_end;
+
+		tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
+			MAS1_TSIZE_SHIFT;
+
+		/*
+		 * Any page size that doesn't satisfy the host mapping
+		 * will fail the start and end tests.
+		 */
+		tsize = min(psize - PAGE_SHIFT + BOOK3E_PAGESZ_4K, tsize);
+
+		/*
+		 * e500 doesn't implement the lowest tsize bit,
+		 * or 1K pages.
+		 */
+		tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
+
+		/*
+		 * Now find the largest tsize (up to what the guest
+		 * requested) that will cover gfn, stay within the
+		 * range, and for which gfn and pfn are mutually
+		 * aligned.
+		 */
+
+		for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
+			unsigned long gfn_start, gfn_end;
+			tsize_pages = 1UL << (tsize - 2);
+
+			gfn_start = gfn & ~(tsize_pages - 1);
+			gfn_end = gfn_start + tsize_pages;
+
+			if (gfn_start + pfn - gfn < start)
+				continue;
+			if (gfn_end + pfn - gfn > end)
+				continue;
+			if ((gfn & (tsize_pages - 1)) !=
+			    (pfn & (tsize_pages - 1)))
+				continue;
+
+			gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
+			pfn &= ~(tsize_pages - 1);
+			break;
+		}
+	}
 
+	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable);
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
 				ref, gvaddr, stlbe);
+	writable = tlbe_is_writable(stlbe);
 
 	/* Clear i-cache for new pages */
 	kvmppc_mmu_flush_icache(pfn);
 
 out:
+	kvm_release_faultin_page(kvm, page, !!ret, writable);
 	spin_unlock(&kvm->mmu_lock);
-
-	/* Drop refcount on page, so that mmu notifiers can clear it */
-	kvm_release_pfn_clean(pfn);
-
 	return ret;
 }
 
@@ -747,12 +709,6 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	return false;
 }
 
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	/* The page will get remapped properly on its next fault */
-	return kvm_e500_mmu_unmap_gfn(kvm, range);
-}
-
 /*****************************************/
 
 int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500)
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index d58df71ace58..e476e107a932 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -20,6 +20,7 @@
 #include <asm/cputable.h>
 #include <asm/kvm_ppc.h>
 #include <asm/dbell.h>
+#include <asm/ppc-opcode.h>
 
 #include "booke.h"
 #include "e500.h"
@@ -92,7 +93,11 @@ void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 	local_irq_save(flags);
 	mtspr(SPRN_MAS5, MAS5_SGS | get_lpid(&vcpu_e500->vcpu));
-	asm volatile("tlbilxlpid");
+	/*
+	 * clang-17 and older could not assemble tlbilxlpid.
+	 * https://github.com/ClangBuiltLinux/linux/issues/1891
+	 */
+	asm volatile (PPC_TLBILX_LPID);
 	mtspr(SPRN_MAS5, 0);
 	local_irq_restore(flags);
 }
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 059c08ae0340..ec60c7979718 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -92,7 +92,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmio_host_swabbed = 0;
 
 	emulated = EMULATE_FAIL;
-	vcpu->arch.regs.msr = vcpu->arch.shared->msr;
+	vcpu->arch.regs.msr = kvmppc_get_msr(vcpu);
 	if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) {
 		int type = op.type & INSTR_TYPE_MASK;
 		int size = GETSIZE(op.type);
@@ -111,7 +111,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 						op.reg, size, !instr_byte_swap);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
 		}
@@ -131,7 +131,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 					     KVM_MMIO_REG_FPR|op.reg, size, 1);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
 #endif
@@ -223,16 +223,17 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 			break;
 		}
 #endif
-		case STORE:
-			/* if need byte reverse, op.val has been reversed by
-			 * analyse_instr().
-			 */
-			emulated = kvmppc_handle_store(vcpu, op.val, size, 1);
+		case STORE: {
+			int instr_byte_swap = op.type & BYTEREV;
+
+			emulated = kvmppc_handle_store(vcpu, kvmppc_get_gpr(vcpu, op.reg),
+						       size, !instr_byte_swap);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
+		}
 #ifdef CONFIG_PPC_FPU
 		case STORE_FP:
 			if (kvmppc_check_fp_disabled(vcpu))
@@ -250,10 +251,10 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 				vcpu->arch.mmio_sp64_extend = 1;
 
 			emulated = kvmppc_handle_store(vcpu,
-					VCPU_FPR(vcpu, op.reg), size, 1);
+					kvmppc_get_fpr(vcpu, op.reg), size, 1);
 
 			if ((op.type & UPDATE) && (emulated != EMULATE_FAIL))
-				kvmppc_set_gpr(vcpu, op.update_reg, op.ea);
+				kvmppc_set_gpr(vcpu, op.update_reg, vcpu->arch.vaddr_accessed);
 
 			break;
 #endif
diff --git a/arch/powerpc/kvm/guest-state-buffer.c b/arch/powerpc/kvm/guest-state-buffer.c
new file mode 100644
index 000000000000..871cf60ddeb6
--- /dev/null
+++ b/arch/powerpc/kvm/guest-state-buffer.c
@@ -0,0 +1,660 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "asm/hvcall.h"
+#include <linux/log2.h>
+#include <asm/pgalloc.h>
+#include <asm/guest-state-buffer.h>
+
+static const u16 kvmppc_gse_iden_len[__KVMPPC_GSE_TYPE_MAX] = {
+	[KVMPPC_GSE_BE32] = sizeof(__be32),
+	[KVMPPC_GSE_BE64] = sizeof(__be64),
+	[KVMPPC_GSE_VEC128] = sizeof(vector128),
+	[KVMPPC_GSE_PARTITION_TABLE] = sizeof(struct kvmppc_gs_part_table),
+	[KVMPPC_GSE_PROCESS_TABLE] = sizeof(struct kvmppc_gs_proc_table),
+	[KVMPPC_GSE_BUFFER] = sizeof(struct kvmppc_gs_buff_info),
+};
+
+/**
+ * kvmppc_gsb_new() - create a new guest state buffer
+ * @size: total size of the guest state buffer (includes header)
+ * @guest_id: guest_id
+ * @vcpu_id: vcpu_id
+ * @flags: GFP flags
+ *
+ * Returns a guest state buffer.
+ */
+struct kvmppc_gs_buff *kvmppc_gsb_new(size_t size, unsigned long guest_id,
+				      unsigned long vcpu_id, gfp_t flags)
+{
+	struct kvmppc_gs_buff *gsb;
+
+	gsb = kzalloc(sizeof(*gsb), flags);
+	if (!gsb)
+		return NULL;
+
+	size = roundup_pow_of_two(size);
+	gsb->hdr = kzalloc(size, GFP_KERNEL);
+	if (!gsb->hdr)
+		goto free;
+
+	gsb->capacity = size;
+	gsb->len = sizeof(struct kvmppc_gs_header);
+	gsb->vcpu_id = vcpu_id;
+	gsb->guest_id = guest_id;
+
+	gsb->hdr->nelems = cpu_to_be32(0);
+
+	return gsb;
+
+free:
+	kfree(gsb);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsb_new);
+
+/**
+ * kvmppc_gsb_free() - free a guest state buffer
+ * @gsb: guest state buffer
+ */
+void kvmppc_gsb_free(struct kvmppc_gs_buff *gsb)
+{
+	kfree(gsb->hdr);
+	kfree(gsb);
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsb_free);
+
+/**
+ * kvmppc_gsb_put() - allocate space in a guest state buffer
+ * @gsb: buffer to allocate in
+ * @size: amount of space to allocate
+ *
+ * Returns a pointer to the amount of space requested within the buffer and
+ * increments the count of elements in the buffer.
+ *
+ * Does not check if there is enough space in the buffer.
+ */
+void *kvmppc_gsb_put(struct kvmppc_gs_buff *gsb, size_t size)
+{
+	u32 nelems = kvmppc_gsb_nelems(gsb);
+	void *p;
+
+	p = (void *)kvmppc_gsb_header(gsb) + kvmppc_gsb_len(gsb);
+	gsb->len += size;
+
+	kvmppc_gsb_header(gsb)->nelems = cpu_to_be32(nelems + 1);
+	return p;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsb_put);
+
+static int kvmppc_gsid_class(u16 iden)
+{
+	if ((iden >= KVMPPC_GSE_GUESTWIDE_START) &&
+	    (iden <= KVMPPC_GSE_GUESTWIDE_END))
+		return KVMPPC_GS_CLASS_GUESTWIDE;
+
+	if ((iden >= KVMPPC_GSE_HOSTWIDE_START) &&
+	    (iden <= KVMPPC_GSE_HOSTWIDE_END))
+		return KVMPPC_GS_CLASS_HOSTWIDE;
+
+	if ((iden >= KVMPPC_GSE_META_START) && (iden <= KVMPPC_GSE_META_END))
+		return KVMPPC_GS_CLASS_META;
+
+	if ((iden >= KVMPPC_GSE_DW_REGS_START) &&
+	    (iden <= KVMPPC_GSE_DW_REGS_END))
+		return KVMPPC_GS_CLASS_DWORD_REG;
+
+	if ((iden >= KVMPPC_GSE_W_REGS_START) &&
+	    (iden <= KVMPPC_GSE_W_REGS_END))
+		return KVMPPC_GS_CLASS_WORD_REG;
+
+	if ((iden >= KVMPPC_GSE_VSRS_START) && (iden <= KVMPPC_GSE_VSRS_END))
+		return KVMPPC_GS_CLASS_VECTOR;
+
+	if ((iden >= KVMPPC_GSE_INTR_REGS_START) &&
+	    (iden <= KVMPPC_GSE_INTR_REGS_END))
+		return KVMPPC_GS_CLASS_INTR;
+
+	return -1;
+}
+
+static int kvmppc_gsid_type(u16 iden)
+{
+	int type = -1;
+
+	switch (kvmppc_gsid_class(iden)) {
+	case KVMPPC_GS_CLASS_HOSTWIDE:
+		switch (iden) {
+		case KVMPPC_GSID_L0_GUEST_HEAP:
+			fallthrough;
+		case KVMPPC_GSID_L0_GUEST_HEAP_MAX:
+			fallthrough;
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE:
+			fallthrough;
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX:
+			fallthrough;
+		case KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM:
+			type = KVMPPC_GSE_BE64;
+			break;
+		}
+		break;
+	case KVMPPC_GS_CLASS_GUESTWIDE:
+		switch (iden) {
+		case KVMPPC_GSID_HOST_STATE_SIZE:
+		case KVMPPC_GSID_RUN_OUTPUT_MIN_SIZE:
+		case KVMPPC_GSID_TB_OFFSET:
+			type = KVMPPC_GSE_BE64;
+			break;
+		case KVMPPC_GSID_PARTITION_TABLE:
+			type = KVMPPC_GSE_PARTITION_TABLE;
+			break;
+		case KVMPPC_GSID_PROCESS_TABLE:
+			type = KVMPPC_GSE_PROCESS_TABLE;
+			break;
+		case KVMPPC_GSID_LOGICAL_PVR:
+			type = KVMPPC_GSE_BE32;
+			break;
+		}
+		break;
+	case KVMPPC_GS_CLASS_META:
+		switch (iden) {
+		case KVMPPC_GSID_RUN_INPUT:
+		case KVMPPC_GSID_RUN_OUTPUT:
+			type = KVMPPC_GSE_BUFFER;
+			break;
+		case KVMPPC_GSID_VPA:
+			type = KVMPPC_GSE_BE64;
+			break;
+		}
+		break;
+	case KVMPPC_GS_CLASS_DWORD_REG:
+		type = KVMPPC_GSE_BE64;
+		break;
+	case KVMPPC_GS_CLASS_WORD_REG:
+		type = KVMPPC_GSE_BE32;
+		break;
+	case KVMPPC_GS_CLASS_VECTOR:
+		type = KVMPPC_GSE_VEC128;
+		break;
+	case KVMPPC_GS_CLASS_INTR:
+		switch (iden) {
+		case KVMPPC_GSID_HDAR:
+		case KVMPPC_GSID_ASDR:
+		case KVMPPC_GSID_HEIR:
+			type = KVMPPC_GSE_BE64;
+			break;
+		case KVMPPC_GSID_HDSISR:
+			type = KVMPPC_GSE_BE32;
+			break;
+		}
+		break;
+	}
+
+	return type;
+}
+
+/**
+ * kvmppc_gsid_flags() - the flags for a guest state ID
+ * @iden: guest state ID
+ *
+ * Returns any flags for the guest state ID.
+ */
+unsigned long kvmppc_gsid_flags(u16 iden)
+{
+	unsigned long flags = 0;
+
+	switch (kvmppc_gsid_class(iden)) {
+	case KVMPPC_GS_CLASS_GUESTWIDE:
+		flags = KVMPPC_GS_FLAGS_WIDE;
+		break;
+	case KVMPPC_GS_CLASS_HOSTWIDE:
+		flags = KVMPPC_GS_FLAGS_HOST_WIDE;
+		break;
+	case KVMPPC_GS_CLASS_META:
+	case KVMPPC_GS_CLASS_DWORD_REG:
+	case KVMPPC_GS_CLASS_WORD_REG:
+	case KVMPPC_GS_CLASS_VECTOR:
+	case KVMPPC_GS_CLASS_INTR:
+		break;
+	}
+
+	return flags;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsid_flags);
+
+/**
+ * kvmppc_gsid_size() - the size of a guest state ID
+ * @iden: guest state ID
+ *
+ * Returns the size of guest state ID.
+ */
+u16 kvmppc_gsid_size(u16 iden)
+{
+	int type;
+
+	type = kvmppc_gsid_type(iden);
+	if (type == -1)
+		return 0;
+
+	if (type >= __KVMPPC_GSE_TYPE_MAX)
+		return 0;
+
+	return kvmppc_gse_iden_len[type];
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsid_size);
+
+/**
+ * kvmppc_gsid_mask() - the settable bits of a guest state ID
+ * @iden: guest state ID
+ *
+ * Returns a mask of settable bits for a guest state ID.
+ */
+u64 kvmppc_gsid_mask(u16 iden)
+{
+	u64 mask = ~0ull;
+
+	switch (iden) {
+	case KVMPPC_GSID_LPCR:
+		mask = LPCR_DPFD | LPCR_ILE | LPCR_AIL | LPCR_LD | LPCR_MER |
+		       LPCR_GTSE;
+		break;
+	case KVMPPC_GSID_MSR:
+		mask = ~(MSR_HV | MSR_S | MSR_ME);
+		break;
+	}
+
+	return mask;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsid_mask);
+
+/**
+ * __kvmppc_gse_put() - add a guest state element to a buffer
+ * @gsb: buffer to the element to
+ * @iden: guest state ID
+ * @size: length of data
+ * @data: pointer to data
+ */
+int __kvmppc_gse_put(struct kvmppc_gs_buff *gsb, u16 iden, u16 size,
+		     const void *data)
+{
+	struct kvmppc_gs_elem *gse;
+	u16 total_size;
+
+	total_size = sizeof(*gse) + size;
+	if (total_size + kvmppc_gsb_len(gsb) > kvmppc_gsb_capacity(gsb))
+		return -ENOMEM;
+
+	if (kvmppc_gsid_size(iden) != size)
+		return -EINVAL;
+
+	gse = kvmppc_gsb_put(gsb, total_size);
+	gse->iden = cpu_to_be16(iden);
+	gse->len = cpu_to_be16(size);
+	memcpy(gse->data, data, size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__kvmppc_gse_put);
+
+/**
+ * kvmppc_gse_parse() - create a parse map from a guest state buffer
+ * @gsp: guest state parser
+ * @gsb: guest state buffer
+ */
+int kvmppc_gse_parse(struct kvmppc_gs_parser *gsp, struct kvmppc_gs_buff *gsb)
+{
+	struct kvmppc_gs_elem *curr;
+	int rem, i;
+
+	kvmppc_gsb_for_each_elem(i, curr, gsb, rem) {
+		if (kvmppc_gse_len(curr) !=
+		    kvmppc_gsid_size(kvmppc_gse_iden(curr)))
+			return -EINVAL;
+		kvmppc_gsp_insert(gsp, kvmppc_gse_iden(curr), curr);
+	}
+
+	if (kvmppc_gsb_nelems(gsb) != i)
+		return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gse_parse);
+
+static inline int kvmppc_gse_flatten_iden(u16 iden)
+{
+	int bit = 0;
+	int class;
+
+	class = kvmppc_gsid_class(iden);
+
+	if (class == KVMPPC_GS_CLASS_GUESTWIDE) {
+		bit += iden - KVMPPC_GSE_GUESTWIDE_START;
+		return bit;
+	}
+
+	bit += KVMPPC_GSE_GUESTWIDE_COUNT;
+
+	if (class == KVMPPC_GS_CLASS_HOSTWIDE) {
+		bit += iden - KVMPPC_GSE_HOSTWIDE_START;
+		return bit;
+	}
+
+	bit += KVMPPC_GSE_HOSTWIDE_COUNT;
+
+	if (class == KVMPPC_GS_CLASS_META) {
+		bit += iden - KVMPPC_GSE_META_START;
+		return bit;
+	}
+
+	bit += KVMPPC_GSE_META_COUNT;
+
+	if (class == KVMPPC_GS_CLASS_DWORD_REG) {
+		bit += iden - KVMPPC_GSE_DW_REGS_START;
+		return bit;
+	}
+
+	bit += KVMPPC_GSE_DW_REGS_COUNT;
+
+	if (class == KVMPPC_GS_CLASS_WORD_REG) {
+		bit += iden - KVMPPC_GSE_W_REGS_START;
+		return bit;
+	}
+
+	bit += KVMPPC_GSE_W_REGS_COUNT;
+
+	if (class == KVMPPC_GS_CLASS_VECTOR) {
+		bit += iden - KVMPPC_GSE_VSRS_START;
+		return bit;
+	}
+
+	bit += KVMPPC_GSE_VSRS_COUNT;
+
+	if (class == KVMPPC_GS_CLASS_INTR) {
+		bit += iden - KVMPPC_GSE_INTR_REGS_START;
+		return bit;
+	}
+
+	return 0;
+}
+
+static inline u16 kvmppc_gse_unflatten_iden(int bit)
+{
+	u16 iden;
+
+	if (bit < KVMPPC_GSE_GUESTWIDE_COUNT) {
+		iden = KVMPPC_GSE_GUESTWIDE_START + bit;
+		return iden;
+	}
+	bit -= KVMPPC_GSE_GUESTWIDE_COUNT;
+
+	if (bit < KVMPPC_GSE_HOSTWIDE_COUNT) {
+		iden = KVMPPC_GSE_HOSTWIDE_START + bit;
+		return iden;
+	}
+	bit -= KVMPPC_GSE_HOSTWIDE_COUNT;
+
+	if (bit < KVMPPC_GSE_META_COUNT) {
+		iden = KVMPPC_GSE_META_START + bit;
+		return iden;
+	}
+	bit -= KVMPPC_GSE_META_COUNT;
+
+	if (bit < KVMPPC_GSE_DW_REGS_COUNT) {
+		iden = KVMPPC_GSE_DW_REGS_START + bit;
+		return iden;
+	}
+	bit -= KVMPPC_GSE_DW_REGS_COUNT;
+
+	if (bit < KVMPPC_GSE_W_REGS_COUNT) {
+		iden = KVMPPC_GSE_W_REGS_START + bit;
+		return iden;
+	}
+	bit -= KVMPPC_GSE_W_REGS_COUNT;
+
+	if (bit < KVMPPC_GSE_VSRS_COUNT) {
+		iden = KVMPPC_GSE_VSRS_START + bit;
+		return iden;
+	}
+	bit -= KVMPPC_GSE_VSRS_COUNT;
+
+	if (bit < KVMPPC_GSE_IDEN_COUNT) {
+		iden = KVMPPC_GSE_INTR_REGS_START + bit;
+		return iden;
+	}
+
+	return 0;
+}
+
+/**
+ * kvmppc_gsp_insert() - add a mapping from an guest state ID to an element
+ * @gsp: guest state parser
+ * @iden: guest state id (key)
+ * @gse: guest state element (value)
+ */
+void kvmppc_gsp_insert(struct kvmppc_gs_parser *gsp, u16 iden,
+		       struct kvmppc_gs_elem *gse)
+{
+	int i;
+
+	i = kvmppc_gse_flatten_iden(iden);
+	kvmppc_gsbm_set(&gsp->iterator, iden);
+	gsp->gses[i] = gse;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsp_insert);
+
+/**
+ * kvmppc_gsp_lookup() - lookup an element from a guest state ID
+ * @gsp: guest state parser
+ * @iden: guest state ID (key)
+ *
+ * Returns the guest state element if present.
+ */
+struct kvmppc_gs_elem *kvmppc_gsp_lookup(struct kvmppc_gs_parser *gsp, u16 iden)
+{
+	int i;
+
+	i = kvmppc_gse_flatten_iden(iden);
+	return gsp->gses[i];
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsp_lookup);
+
+/**
+ * kvmppc_gsbm_set() - set the guest state ID
+ * @gsbm: guest state bitmap
+ * @iden: guest state ID
+ */
+void kvmppc_gsbm_set(struct kvmppc_gs_bitmap *gsbm, u16 iden)
+{
+	set_bit(kvmppc_gse_flatten_iden(iden), gsbm->bitmap);
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsbm_set);
+
+/**
+ * kvmppc_gsbm_clear() - clear the guest state ID
+ * @gsbm: guest state bitmap
+ * @iden: guest state ID
+ */
+void kvmppc_gsbm_clear(struct kvmppc_gs_bitmap *gsbm, u16 iden)
+{
+	clear_bit(kvmppc_gse_flatten_iden(iden), gsbm->bitmap);
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsbm_clear);
+
+/**
+ * kvmppc_gsbm_test() - test the guest state ID
+ * @gsbm: guest state bitmap
+ * @iden: guest state ID
+ */
+bool kvmppc_gsbm_test(struct kvmppc_gs_bitmap *gsbm, u16 iden)
+{
+	return test_bit(kvmppc_gse_flatten_iden(iden), gsbm->bitmap);
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsbm_test);
+
+/**
+ * kvmppc_gsbm_next() - return the next set guest state ID
+ * @gsbm: guest state bitmap
+ * @prev: last guest state ID
+ */
+u16 kvmppc_gsbm_next(struct kvmppc_gs_bitmap *gsbm, u16 prev)
+{
+	int bit, pbit;
+
+	pbit = prev ? kvmppc_gse_flatten_iden(prev) + 1 : 0;
+	bit = find_next_bit(gsbm->bitmap, KVMPPC_GSE_IDEN_COUNT, pbit);
+
+	if (bit < KVMPPC_GSE_IDEN_COUNT)
+		return kvmppc_gse_unflatten_iden(bit);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsbm_next);
+
+/**
+ * kvmppc_gsm_init() - initialize a guest state message
+ * @gsm: guest state message
+ * @ops: callbacks
+ * @data: private data
+ * @flags: guest wide or thread wide
+ */
+int kvmppc_gsm_init(struct kvmppc_gs_msg *gsm, struct kvmppc_gs_msg_ops *ops,
+		    void *data, unsigned long flags)
+{
+	memset(gsm, 0, sizeof(*gsm));
+	gsm->ops = ops;
+	gsm->data = data;
+	gsm->flags = flags;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsm_init);
+
+/**
+ * kvmppc_gsm_new() - creates a new guest state message
+ * @ops: callbacks
+ * @data: private data
+ * @flags: guest wide or thread wide
+ * @gfp_flags: GFP allocation flags
+ *
+ * Returns an initialized guest state message.
+ */
+struct kvmppc_gs_msg *kvmppc_gsm_new(struct kvmppc_gs_msg_ops *ops, void *data,
+				     unsigned long flags, gfp_t gfp_flags)
+{
+	struct kvmppc_gs_msg *gsm;
+
+	gsm = kzalloc(sizeof(*gsm), gfp_flags);
+	if (!gsm)
+		return NULL;
+
+	kvmppc_gsm_init(gsm, ops, data, flags);
+
+	return gsm;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsm_new);
+
+/**
+ * kvmppc_gsm_size() - creates a new guest state message
+ * @gsm: self
+ *
+ * Returns the size required for the message.
+ */
+size_t kvmppc_gsm_size(struct kvmppc_gs_msg *gsm)
+{
+	if (gsm->ops->get_size)
+		return gsm->ops->get_size(gsm);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsm_size);
+
+/**
+ * kvmppc_gsm_free() - free guest state message
+ * @gsm: guest state message
+ *
+ * Returns the size required for the message.
+ */
+void kvmppc_gsm_free(struct kvmppc_gs_msg *gsm)
+{
+	kfree(gsm);
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsm_free);
+
+/**
+ * kvmppc_gsm_fill_info() - serialises message to guest state buffer format
+ * @gsm: self
+ * @gsb: buffer to serialise into
+ */
+int kvmppc_gsm_fill_info(struct kvmppc_gs_msg *gsm, struct kvmppc_gs_buff *gsb)
+{
+	if (!gsm->ops->fill_info)
+		return -EINVAL;
+
+	return gsm->ops->fill_info(gsb, gsm);
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsm_fill_info);
+
+/**
+ * kvmppc_gsm_refresh_info() - deserialises from guest state buffer
+ * @gsm: self
+ * @gsb: buffer to serialise from
+ */
+int kvmppc_gsm_refresh_info(struct kvmppc_gs_msg *gsm,
+			    struct kvmppc_gs_buff *gsb)
+{
+	if (!gsm->ops->fill_info)
+		return -EINVAL;
+
+	return gsm->ops->refresh_info(gsm, gsb);
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsm_refresh_info);
+
+/**
+ * kvmppc_gsb_send - send all elements in the buffer to the hypervisor.
+ * @gsb: guest state buffer
+ * @flags: guest wide or thread wide
+ *
+ * Performs the H_GUEST_SET_STATE hcall for the guest state buffer.
+ */
+int kvmppc_gsb_send(struct kvmppc_gs_buff *gsb, unsigned long flags)
+{
+	unsigned long hflags = 0;
+	unsigned long i;
+	int rc;
+
+	if (kvmppc_gsb_nelems(gsb) == 0)
+		return 0;
+
+	if (flags & KVMPPC_GS_FLAGS_WIDE)
+		hflags |= H_GUEST_FLAGS_WIDE;
+	if (flags & KVMPPC_GS_FLAGS_HOST_WIDE)
+		hflags |= H_GUEST_FLAGS_HOST_WIDE;
+
+	rc = plpar_guest_set_state(hflags, gsb->guest_id, gsb->vcpu_id,
+				   __pa(gsb->hdr), gsb->capacity, &i);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsb_send);
+
+/**
+ * kvmppc_gsb_recv - request all elements in the buffer have their value
+ * updated.
+ * @gsb: guest state buffer
+ * @flags: guest wide or thread wide
+ *
+ * Performs the H_GUEST_GET_STATE hcall for the guest state buffer.
+ * After returning from the hcall the guest state elements that were
+ * present in the buffer will have updated values from the hypervisor.
+ */
+int kvmppc_gsb_recv(struct kvmppc_gs_buff *gsb, unsigned long flags)
+{
+	unsigned long hflags = 0;
+	unsigned long i;
+	int rc;
+
+	if (flags & KVMPPC_GS_FLAGS_WIDE)
+		hflags |= H_GUEST_FLAGS_WIDE;
+	if (flags & KVMPPC_GS_FLAGS_HOST_WIDE)
+		hflags |= H_GUEST_FLAGS_HOST_WIDE;
+
+	rc = plpar_guest_get_state(hflags, gsb->guest_id, gsb->vcpu_id,
+				   __pa(gsb->hdr), gsb->capacity, &i);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gsb_recv);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 7197c8256668..9a89a6d98f97 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -69,7 +69,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 
 /*
  * Common checks before entering the guest world.  Call with interrupts
- * disabled.
+ * enabled.
  *
  * returns:
  *
@@ -528,7 +528,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
@@ -551,12 +550,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
+		fallthrough;
 	case KVM_CAP_SPAPR_TCE_64:
-		r = 1;
-		break;
 	case KVM_CAP_SPAPR_TCE_VFIO:
-		r = !!cpu_has_feature(CPU_FTR_HVMODE);
-		break;
 	case KVM_CAP_PPC_RTAS:
 	case KVM_CAP_PPC_FIXUP_HCALL:
 	case KVM_CAP_PPC_ENABLE_HCALL:
@@ -578,7 +574,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQFD_RESAMPLE:
 		r = !xive_enabled();
 		break;
@@ -613,9 +609,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 				r = 8 | 4 | 2 | 1;
 		}
 		break;
-	case KVM_CAP_PPC_RMA:
-		r = 0;
-		break;
 	case KVM_CAP_PPC_HWRNG:
 		r = kvmppc_hwrng_present();
 		break;
@@ -632,13 +625,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-		r = hv_enabled;
-#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+		BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER));
 		r = 1;
-#else
-		r = 0;
-#endif
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD:
@@ -775,8 +763,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	int err;
 
-	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
+	hrtimer_setup(&vcpu->arch.dec_timer, kvmppc_decrementer_wakeup, CLOCK_REALTIME,
+		      HRTIMER_MODE_ABS);
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	mutex_init(&vcpu->arch.exit_timing_lock);
@@ -934,11 +922,11 @@ static inline void kvmppc_set_vsr_dword(struct kvm_vcpu *vcpu,
 		return;
 
 	if (index >= 32) {
-		val.vval = VCPU_VSX_VR(vcpu, index - 32);
+		kvmppc_get_vsx_vr(vcpu, index - 32, &val.vval);
 		val.vsxval[offset] = gpr;
-		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
+		kvmppc_set_vsx_vr(vcpu, index - 32, &val.vval);
 	} else {
-		VCPU_VSX_FPR(vcpu, index, offset) = gpr;
+		kvmppc_set_vsx_fpr(vcpu, index, offset, gpr);
 	}
 }
 
@@ -949,13 +937,13 @@ static inline void kvmppc_set_vsr_dword_dump(struct kvm_vcpu *vcpu,
 	int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
 
 	if (index >= 32) {
-		val.vval = VCPU_VSX_VR(vcpu, index - 32);
+		kvmppc_get_vsx_vr(vcpu, index - 32, &val.vval);
 		val.vsxval[0] = gpr;
 		val.vsxval[1] = gpr;
-		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
+		kvmppc_set_vsx_vr(vcpu, index - 32, &val.vval);
 	} else {
-		VCPU_VSX_FPR(vcpu, index, 0) = gpr;
-		VCPU_VSX_FPR(vcpu, index, 1) = gpr;
+		kvmppc_set_vsx_fpr(vcpu, index, 0, gpr);
+		kvmppc_set_vsx_fpr(vcpu, index, 1,  gpr);
 	}
 }
 
@@ -970,12 +958,12 @@ static inline void kvmppc_set_vsr_word_dump(struct kvm_vcpu *vcpu,
 		val.vsx32val[1] = gpr;
 		val.vsx32val[2] = gpr;
 		val.vsx32val[3] = gpr;
-		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
+		kvmppc_set_vsx_vr(vcpu, index - 32, &val.vval);
 	} else {
 		val.vsx32val[0] = gpr;
 		val.vsx32val[1] = gpr;
-		VCPU_VSX_FPR(vcpu, index, 0) = val.vsxval[0];
-		VCPU_VSX_FPR(vcpu, index, 1) = val.vsxval[0];
+		kvmppc_set_vsx_fpr(vcpu, index, 0, val.vsxval[0]);
+		kvmppc_set_vsx_fpr(vcpu, index, 1, val.vsxval[0]);
 	}
 }
 
@@ -991,15 +979,15 @@ static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu,
 		return;
 
 	if (index >= 32) {
-		val.vval = VCPU_VSX_VR(vcpu, index - 32);
+		kvmppc_get_vsx_vr(vcpu, index - 32, &val.vval);
 		val.vsx32val[offset] = gpr32;
-		VCPU_VSX_VR(vcpu, index - 32) = val.vval;
+		kvmppc_set_vsx_vr(vcpu, index - 32, &val.vval);
 	} else {
 		dword_offset = offset / 2;
 		word_offset = offset % 2;
-		val.vsxval[0] = VCPU_VSX_FPR(vcpu, index, dword_offset);
+		val.vsxval[0] = kvmppc_get_vsx_fpr(vcpu, index, dword_offset);
 		val.vsx32val[word_offset] = gpr32;
-		VCPU_VSX_FPR(vcpu, index, dword_offset) = val.vsxval[0];
+		kvmppc_set_vsx_fpr(vcpu, index, dword_offset, val.vsxval[0]);
 	}
 }
 #endif /* CONFIG_VSX */
@@ -1058,9 +1046,9 @@ static inline void kvmppc_set_vmx_dword(struct kvm_vcpu *vcpu,
 	if (offset == -1)
 		return;
 
-	val.vval = VCPU_VSX_VR(vcpu, index);
+	kvmppc_get_vsx_vr(vcpu, index, &val.vval);
 	val.vsxval[offset] = gpr;
-	VCPU_VSX_VR(vcpu, index) = val.vval;
+	kvmppc_set_vsx_vr(vcpu, index, &val.vval);
 }
 
 static inline void kvmppc_set_vmx_word(struct kvm_vcpu *vcpu,
@@ -1074,9 +1062,9 @@ static inline void kvmppc_set_vmx_word(struct kvm_vcpu *vcpu,
 	if (offset == -1)
 		return;
 
-	val.vval = VCPU_VSX_VR(vcpu, index);
+	kvmppc_get_vsx_vr(vcpu, index, &val.vval);
 	val.vsx32val[offset] = gpr32;
-	VCPU_VSX_VR(vcpu, index) = val.vval;
+	kvmppc_set_vsx_vr(vcpu, index, &val.vval);
 }
 
 static inline void kvmppc_set_vmx_hword(struct kvm_vcpu *vcpu,
@@ -1090,9 +1078,9 @@ static inline void kvmppc_set_vmx_hword(struct kvm_vcpu *vcpu,
 	if (offset == -1)
 		return;
 
-	val.vval = VCPU_VSX_VR(vcpu, index);
+	kvmppc_get_vsx_vr(vcpu, index, &val.vval);
 	val.vsx16val[offset] = gpr16;
-	VCPU_VSX_VR(vcpu, index) = val.vval;
+	kvmppc_set_vsx_vr(vcpu, index, &val.vval);
 }
 
 static inline void kvmppc_set_vmx_byte(struct kvm_vcpu *vcpu,
@@ -1106,9 +1094,9 @@ static inline void kvmppc_set_vmx_byte(struct kvm_vcpu *vcpu,
 	if (offset == -1)
 		return;
 
-	val.vval = VCPU_VSX_VR(vcpu, index);
+	kvmppc_get_vsx_vr(vcpu, index, &val.vval);
 	val.vsx8val[offset] = gpr8;
-	VCPU_VSX_VR(vcpu, index) = val.vval;
+	kvmppc_set_vsx_vr(vcpu, index, &val.vval);
 }
 #endif /* CONFIG_ALTIVEC */
 
@@ -1194,14 +1182,14 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu)
 		if (vcpu->kvm->arch.kvm_ops->giveup_ext)
 			vcpu->kvm->arch.kvm_ops->giveup_ext(vcpu, MSR_FP);
 
-		VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
+		kvmppc_set_fpr(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK, gpr);
 		break;
 #ifdef CONFIG_PPC_BOOK3S
 	case KVM_MMIO_REG_QPR:
 		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
 		break;
 	case KVM_MMIO_REG_FQPR:
-		VCPU_FPR(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK) = gpr;
+		kvmppc_set_fpr(vcpu, vcpu->arch.io_gpr & KVM_MMIO_REG_MASK, gpr);
 		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
 		break;
 #endif
@@ -1419,9 +1407,9 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
 		}
 
 		if (rs < 32) {
-			*val = VCPU_VSX_FPR(vcpu, rs, vsx_offset);
+			*val = kvmppc_get_vsx_fpr(vcpu, rs, vsx_offset);
 		} else {
-			reg.vval = VCPU_VSX_VR(vcpu, rs - 32);
+			kvmppc_get_vsx_vr(vcpu, rs - 32, &reg.vval);
 			*val = reg.vsxval[vsx_offset];
 		}
 		break;
@@ -1438,10 +1426,10 @@ static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
 		if (rs < 32) {
 			dword_offset = vsx_offset / 2;
 			word_offset = vsx_offset % 2;
-			reg.vsxval[0] = VCPU_VSX_FPR(vcpu, rs, dword_offset);
+			reg.vsxval[0] = kvmppc_get_vsx_fpr(vcpu, rs, dword_offset);
 			*val = reg.vsx32val[word_offset];
 		} else {
-			reg.vval = VCPU_VSX_VR(vcpu, rs - 32);
+			kvmppc_get_vsx_vr(vcpu, rs - 32, &reg.vval);
 			*val = reg.vsx32val[vsx_offset];
 		}
 		break;
@@ -1556,7 +1544,7 @@ static int kvmppc_get_vmx_dword(struct kvm_vcpu *vcpu, int index, u64 *val)
 	if (vmx_offset == -1)
 		return -1;
 
-	reg.vval = VCPU_VSX_VR(vcpu, index);
+	kvmppc_get_vsx_vr(vcpu, index, &reg.vval);
 	*val = reg.vsxval[vmx_offset];
 
 	return result;
@@ -1574,7 +1562,7 @@ static int kvmppc_get_vmx_word(struct kvm_vcpu *vcpu, int index, u64 *val)
 	if (vmx_offset == -1)
 		return -1;
 
-	reg.vval = VCPU_VSX_VR(vcpu, index);
+	kvmppc_get_vsx_vr(vcpu, index, &reg.vval);
 	*val = reg.vsx32val[vmx_offset];
 
 	return result;
@@ -1592,7 +1580,7 @@ static int kvmppc_get_vmx_hword(struct kvm_vcpu *vcpu, int index, u64 *val)
 	if (vmx_offset == -1)
 		return -1;
 
-	reg.vval = VCPU_VSX_VR(vcpu, index);
+	kvmppc_get_vsx_vr(vcpu, index, &reg.vval);
 	*val = reg.vsx16val[vmx_offset];
 
 	return result;
@@ -1610,7 +1598,7 @@ static int kvmppc_get_vmx_byte(struct kvm_vcpu *vcpu, int index, u64 *val)
 	if (vmx_offset == -1)
 		return -1;
 
-	reg.vval = VCPU_VSX_VR(vcpu, index);
+	kvmppc_get_vsx_vr(vcpu, index, &reg.vval);
 	*val = reg.vsx8val[vmx_offset];
 
 	return result;
@@ -1719,17 +1707,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
+			kvmppc_get_vsx_vr(vcpu, reg->id - KVM_REG_PPC_VR0, &val.vval);
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
+			val = get_reg_val(reg->id, kvmppc_get_vscr(vcpu));
 			break;
 		case KVM_REG_PPC_VRSAVE:
-			val = get_reg_val(reg->id, vcpu->arch.vrsave);
+			val = get_reg_val(reg->id, kvmppc_get_vrsave(vcpu));
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:
@@ -1770,21 +1758,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
+			kvmppc_set_vsx_vr(vcpu, reg->id - KVM_REG_PPC_VR0, &val.vval);
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
+			kvmppc_set_vscr(vcpu, set_reg_val(reg->id, val));
 			break;
 		case KVM_REG_PPC_VRSAVE:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vrsave = set_reg_val(reg->id, val);
+			kvmppc_set_vrsave(vcpu, set_reg_val(reg->id, val));
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:
@@ -1858,7 +1846,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	kvm_sigset_activate(vcpu);
 
-	if (run->immediate_exit)
+	if (!vcpu->wants_to_run)
 		r = -EINTR;
 	else
 		r = kvmppc_vcpu_run(vcpu);
@@ -1939,54 +1927,48 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 #endif
 #ifdef CONFIG_KVM_MPIC
 	case KVM_CAP_IRQ_MPIC: {
-		struct fd f;
+		CLASS(fd, f)(cap->args[0]);
 		struct kvm_device *dev;
 
 		r = -EBADF;
-		f = fdget(cap->args[0]);
-		if (!f.file)
+		if (fd_empty(f))
 			break;
 
 		r = -EPERM;
-		dev = kvm_device_from_filp(f.file);
+		dev = kvm_device_from_filp(fd_file(f));
 		if (dev)
 			r = kvmppc_mpic_connect_vcpu(dev, vcpu, cap->args[1]);
 
-		fdput(f);
 		break;
 	}
 #endif
 #ifdef CONFIG_KVM_XICS
 	case KVM_CAP_IRQ_XICS: {
-		struct fd f;
+		CLASS(fd, f)(cap->args[0]);
 		struct kvm_device *dev;
 
 		r = -EBADF;
-		f = fdget(cap->args[0]);
-		if (!f.file)
+		if (fd_empty(f))
 			break;
 
 		r = -EPERM;
-		dev = kvm_device_from_filp(f.file);
+		dev = kvm_device_from_filp(fd_file(f));
 		if (dev) {
 			if (xics_on_xive())
 				r = kvmppc_xive_connect_vcpu(dev, vcpu, cap->args[1]);
 			else
 				r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
 		}
-
-		fdput(f);
 		break;
 	}
 #endif /* CONFIG_KVM_XICS */
 #ifdef CONFIG_KVM_XIVE
 	case KVM_CAP_PPC_IRQ_XIVE: {
-		struct fd f;
+		CLASS(fd, f)(cap->args[0]);
 		struct kvm_device *dev;
 
 		r = -EBADF;
-		f = fdget(cap->args[0]);
-		if (!f.file)
+		if (fd_empty(f))
 			break;
 
 		r = -ENXIO;
@@ -1994,12 +1976,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 			break;
 
 		r = -EPERM;
-		dev = kvm_device_from_filp(f.file);
+		dev = kvm_device_from_filp(fd_file(f));
 		if (dev)
 			r = kvmppc_xive_native_connect_vcpu(dev, vcpu,
 							    cap->args[1]);
-
-		fdput(f);
 		break;
 	}
 #endif /* CONFIG_KVM_XIVE */
@@ -2048,8 +2028,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
-long kvm_arch_vcpu_async_ioctl(struct file *filp,
-			       unsigned int ioctl, unsigned long arg)
+long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl,
+				  unsigned long arg)
 {
 	struct kvm_vcpu *vcpu = filp->private_data;
 	void __user *argp = (void __user *)arg;
@@ -2544,9 +2524,8 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_
 		vcpu->kvm->arch.kvm_ops->create_vcpu_debugfs(vcpu, debugfs_dentry);
 }
 
-int kvm_arch_create_vm_debugfs(struct kvm *kvm)
+void kvm_arch_create_vm_debugfs(struct kvm *kvm)
 {
 	if (kvm->arch.kvm_ops->create_vm_debugfs)
 		kvm->arch.kvm_ops->create_vm_debugfs(kvm);
-	return 0;
 }
diff --git a/arch/powerpc/kvm/test-guest-state-buffer.c b/arch/powerpc/kvm/test-guest-state-buffer.c
new file mode 100644
index 000000000000..5ccca306997a
--- /dev/null
+++ b/arch/powerpc/kvm/test-guest-state-buffer.c
@@ -0,0 +1,543 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/init.h>
+#include <linux/log2.h>
+#include <kunit/test.h>
+
+#include <asm/guest-state-buffer.h>
+#include <asm/kvm_ppc.h>
+
+static void test_creating_buffer(struct kunit *test)
+{
+	struct kvmppc_gs_buff *gsb;
+	size_t size = 0x100;
+
+	gsb = kvmppc_gsb_new(size, 0, 0, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb->hdr);
+
+	KUNIT_EXPECT_EQ(test, gsb->capacity, roundup_pow_of_two(size));
+	KUNIT_EXPECT_EQ(test, gsb->len, sizeof(__be32));
+
+	kvmppc_gsb_free(gsb);
+}
+
+static void test_adding_element(struct kunit *test)
+{
+	const struct kvmppc_gs_elem *head, *curr;
+	union {
+		__vector128 v;
+		u64 dw[2];
+	} u;
+	int rem;
+	struct kvmppc_gs_buff *gsb;
+	size_t size = 0x1000;
+	int i, rc;
+	u64 data;
+
+	gsb = kvmppc_gsb_new(size, 0, 0, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb);
+
+	/* Single elements, direct use of __kvmppc_gse_put() */
+	data = 0xdeadbeef;
+	rc = __kvmppc_gse_put(gsb, KVMPPC_GSID_GPR(0), 8, &data);
+	KUNIT_EXPECT_GE(test, rc, 0);
+
+	head = kvmppc_gsb_data(gsb);
+	KUNIT_EXPECT_EQ(test, kvmppc_gse_iden(head), KVMPPC_GSID_GPR(0));
+	KUNIT_EXPECT_EQ(test, kvmppc_gse_len(head), 8);
+	data = 0;
+	memcpy(&data, kvmppc_gse_data(head), 8);
+	KUNIT_EXPECT_EQ(test, data, 0xdeadbeef);
+
+	/* Multiple elements, simple wrapper */
+	rc = kvmppc_gse_put_u64(gsb, KVMPPC_GSID_GPR(1), 0xcafef00d);
+	KUNIT_EXPECT_GE(test, rc, 0);
+
+	u.dw[0] = 0x1;
+	u.dw[1] = 0x2;
+	rc = kvmppc_gse_put_vector128(gsb, KVMPPC_GSID_VSRS(0), &u.v);
+	KUNIT_EXPECT_GE(test, rc, 0);
+	u.dw[0] = 0x0;
+	u.dw[1] = 0x0;
+
+	kvmppc_gsb_for_each_elem(i, curr, gsb, rem) {
+		switch (i) {
+		case 0:
+			KUNIT_EXPECT_EQ(test, kvmppc_gse_iden(curr),
+					KVMPPC_GSID_GPR(0));
+			KUNIT_EXPECT_EQ(test, kvmppc_gse_len(curr), 8);
+			KUNIT_EXPECT_EQ(test, kvmppc_gse_get_be64(curr),
+					0xdeadbeef);
+			break;
+		case 1:
+			KUNIT_EXPECT_EQ(test, kvmppc_gse_iden(curr),
+					KVMPPC_GSID_GPR(1));
+			KUNIT_EXPECT_EQ(test, kvmppc_gse_len(curr), 8);
+			KUNIT_EXPECT_EQ(test, kvmppc_gse_get_u64(curr),
+					0xcafef00d);
+			break;
+		case 2:
+			KUNIT_EXPECT_EQ(test, kvmppc_gse_iden(curr),
+					KVMPPC_GSID_VSRS(0));
+			KUNIT_EXPECT_EQ(test, kvmppc_gse_len(curr), 16);
+			kvmppc_gse_get_vector128(curr, &u.v);
+			KUNIT_EXPECT_EQ(test, u.dw[0], 0x1);
+			KUNIT_EXPECT_EQ(test, u.dw[1], 0x2);
+			break;
+		}
+	}
+	KUNIT_EXPECT_EQ(test, i, 3);
+
+	kvmppc_gsb_reset(gsb);
+	KUNIT_EXPECT_EQ(test, kvmppc_gsb_nelems(gsb), 0);
+	KUNIT_EXPECT_EQ(test, kvmppc_gsb_len(gsb),
+			sizeof(struct kvmppc_gs_header));
+
+	kvmppc_gsb_free(gsb);
+}
+
+static void test_gs_parsing(struct kunit *test)
+{
+	struct kvmppc_gs_elem *gse;
+	struct kvmppc_gs_parser gsp = { 0 };
+	struct kvmppc_gs_buff *gsb;
+	size_t size = 0x1000;
+	u64 tmp1, tmp2;
+
+	gsb = kvmppc_gsb_new(size, 0, 0, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb);
+
+	tmp1 = 0xdeadbeefull;
+	kvmppc_gse_put_u64(gsb, KVMPPC_GSID_GPR(0), tmp1);
+
+	KUNIT_EXPECT_GE(test, kvmppc_gse_parse(&gsp, gsb), 0);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_GPR(0));
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gse);
+
+	tmp2 = kvmppc_gse_get_u64(gse);
+	KUNIT_EXPECT_EQ(test, tmp2, 0xdeadbeefull);
+
+	kvmppc_gsb_free(gsb);
+}
+
+static void test_gs_bitmap(struct kunit *test)
+{
+	struct kvmppc_gs_bitmap gsbm = { 0 };
+	struct kvmppc_gs_bitmap gsbm1 = { 0 };
+	struct kvmppc_gs_bitmap gsbm2 = { 0 };
+	u16 iden;
+	int i, j;
+
+	i = 0;
+	for (u16 iden = KVMPPC_GSID_HOST_STATE_SIZE;
+	     iden <= KVMPPC_GSID_PROCESS_TABLE; iden++) {
+		kvmppc_gsbm_set(&gsbm, iden);
+		kvmppc_gsbm_set(&gsbm1, iden);
+		KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
+		kvmppc_gsbm_clear(&gsbm, iden);
+		KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden));
+		i++;
+	}
+
+	for (u16 iden = KVMPPC_GSID_L0_GUEST_HEAP;
+	     iden <= KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM; iden++) {
+		kvmppc_gsbm_set(&gsbm, iden);
+		kvmppc_gsbm_set(&gsbm1, iden);
+		KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
+		kvmppc_gsbm_clear(&gsbm, iden);
+		KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden));
+		i++;
+	}
+
+	for (u16 iden = KVMPPC_GSID_RUN_INPUT; iden <= KVMPPC_GSID_VPA;
+	     iden++) {
+		kvmppc_gsbm_set(&gsbm, iden);
+		kvmppc_gsbm_set(&gsbm1, iden);
+		KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
+		kvmppc_gsbm_clear(&gsbm, iden);
+		KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden));
+		i++;
+	}
+
+	for (u16 iden = KVMPPC_GSID_GPR(0); iden <= KVMPPC_GSE_DW_REGS_END; iden++) {
+		kvmppc_gsbm_set(&gsbm, iden);
+		kvmppc_gsbm_set(&gsbm1, iden);
+		KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
+		kvmppc_gsbm_clear(&gsbm, iden);
+		KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden));
+		i++;
+	}
+
+	for (u16 iden = KVMPPC_GSID_CR; iden <= KVMPPC_GSID_PSPB; iden++) {
+		kvmppc_gsbm_set(&gsbm, iden);
+		kvmppc_gsbm_set(&gsbm1, iden);
+		KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
+		kvmppc_gsbm_clear(&gsbm, iden);
+		KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden));
+		i++;
+	}
+
+	for (u16 iden = KVMPPC_GSID_VSRS(0); iden <= KVMPPC_GSID_VSRS(63);
+	     iden++) {
+		kvmppc_gsbm_set(&gsbm, iden);
+		kvmppc_gsbm_set(&gsbm1, iden);
+		KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
+		kvmppc_gsbm_clear(&gsbm, iden);
+		KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden));
+		i++;
+	}
+
+	for (u16 iden = KVMPPC_GSID_HDAR; iden <= KVMPPC_GSID_ASDR; iden++) {
+		kvmppc_gsbm_set(&gsbm, iden);
+		kvmppc_gsbm_set(&gsbm1, iden);
+		KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
+		kvmppc_gsbm_clear(&gsbm, iden);
+		KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden));
+		i++;
+	}
+
+	j = 0;
+	kvmppc_gsbm_for_each(&gsbm1, iden)
+	{
+		kvmppc_gsbm_set(&gsbm2, iden);
+		j++;
+	}
+	KUNIT_EXPECT_EQ(test, i, j);
+	KUNIT_EXPECT_MEMEQ(test, &gsbm1, &gsbm2, sizeof(gsbm1));
+}
+
+struct kvmppc_gs_msg_test1_data {
+	u64 a;
+	u32 b;
+	struct kvmppc_gs_part_table c;
+	struct kvmppc_gs_proc_table d;
+	struct kvmppc_gs_buff_info e;
+};
+
+static size_t test1_get_size(struct kvmppc_gs_msg *gsm)
+{
+	size_t size = 0;
+	u16 ids[] = {
+		KVMPPC_GSID_PARTITION_TABLE,
+		KVMPPC_GSID_PROCESS_TABLE,
+		KVMPPC_GSID_RUN_INPUT,
+		KVMPPC_GSID_GPR(0),
+		KVMPPC_GSID_CR,
+	};
+
+	for (int i = 0; i < ARRAY_SIZE(ids); i++)
+		size += kvmppc_gse_total_size(kvmppc_gsid_size(ids[i]));
+	return size;
+}
+
+static int test1_fill_info(struct kvmppc_gs_buff *gsb,
+			   struct kvmppc_gs_msg *gsm)
+{
+	struct kvmppc_gs_msg_test1_data *data = gsm->data;
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_GPR(0)))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_GPR(0), data->a);
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_CR))
+		kvmppc_gse_put_u32(gsb, KVMPPC_GSID_CR, data->b);
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_PARTITION_TABLE))
+		kvmppc_gse_put_part_table(gsb, KVMPPC_GSID_PARTITION_TABLE,
+					  data->c);
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_PROCESS_TABLE))
+		kvmppc_gse_put_proc_table(gsb, KVMPPC_GSID_PARTITION_TABLE,
+					  data->d);
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_INPUT))
+		kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_INPUT, data->e);
+
+	return 0;
+}
+
+static int test1_refresh_info(struct kvmppc_gs_msg *gsm,
+			      struct kvmppc_gs_buff *gsb)
+{
+	struct kvmppc_gs_parser gsp = { 0 };
+	struct kvmppc_gs_msg_test1_data *data = gsm->data;
+	struct kvmppc_gs_elem *gse;
+	int rc;
+
+	rc = kvmppc_gse_parse(&gsp, gsb);
+	if (rc < 0)
+		return rc;
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_GPR(0));
+	if (gse)
+		data->a = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_CR);
+	if (gse)
+		data->b = kvmppc_gse_get_u32(gse);
+
+	return 0;
+}
+
+static struct kvmppc_gs_msg_ops gs_msg_test1_ops = {
+	.get_size = test1_get_size,
+	.fill_info = test1_fill_info,
+	.refresh_info = test1_refresh_info,
+};
+
+static void test_gs_msg(struct kunit *test)
+{
+	struct kvmppc_gs_msg_test1_data test1_data = {
+		.a = 0xdeadbeef,
+		.b = 0x1,
+	};
+	struct kvmppc_gs_msg *gsm;
+	struct kvmppc_gs_buff *gsb;
+
+	gsm = kvmppc_gsm_new(&gs_msg_test1_ops, &test1_data, GSM_SEND,
+			     GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsm);
+
+	gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), 0, 0, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_PARTITION_TABLE);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_PROCESS_TABLE);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_RUN_INPUT);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_GPR(0));
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_CR);
+
+	kvmppc_gsm_fill_info(gsm, gsb);
+
+	memset(&test1_data, 0, sizeof(test1_data));
+
+	kvmppc_gsm_refresh_info(gsm, gsb);
+	KUNIT_EXPECT_EQ(test, test1_data.a, 0xdeadbeef);
+	KUNIT_EXPECT_EQ(test, test1_data.b, 0x1);
+
+	kvmppc_gsm_free(gsm);
+}
+
+/* Test data struct for hostwide/L0 counters */
+struct kvmppc_gs_msg_test_hostwide_data {
+	u64 guest_heap;
+	u64 guest_heap_max;
+	u64 guest_pgtable_size;
+	u64 guest_pgtable_size_max;
+	u64 guest_pgtable_reclaim;
+};
+
+static size_t test_hostwide_get_size(struct kvmppc_gs_msg *gsm)
+
+{
+	size_t size = 0;
+	u16 ids[] = {
+		KVMPPC_GSID_L0_GUEST_HEAP,
+		KVMPPC_GSID_L0_GUEST_HEAP_MAX,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM
+	};
+
+	for (int i = 0; i < ARRAY_SIZE(ids); i++)
+		size += kvmppc_gse_total_size(kvmppc_gsid_size(ids[i]));
+	return size;
+}
+
+static int test_hostwide_fill_info(struct kvmppc_gs_buff *gsb,
+				   struct kvmppc_gs_msg *gsm)
+{
+	struct kvmppc_gs_msg_test_hostwide_data *data = gsm->data;
+
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_HEAP,
+				   data->guest_heap);
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_HEAP_MAX,
+				   data->guest_heap_max);
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE,
+				   data->guest_pgtable_size);
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX,
+				   data->guest_pgtable_size_max);
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM))
+		kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM,
+				   data->guest_pgtable_reclaim);
+
+	return 0;
+}
+
+static int test_hostwide_refresh_info(struct kvmppc_gs_msg *gsm,
+				      struct kvmppc_gs_buff *gsb)
+{
+	struct kvmppc_gs_parser gsp = { 0 };
+	struct kvmppc_gs_msg_test_hostwide_data *data = gsm->data;
+	struct kvmppc_gs_elem *gse;
+	int rc;
+
+	rc = kvmppc_gse_parse(&gsp, gsb);
+	if (rc < 0)
+		return rc;
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP);
+	if (gse)
+		data->guest_heap = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	if (gse)
+		data->guest_heap_max = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	if (gse)
+		data->guest_pgtable_size = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	if (gse)
+		data->guest_pgtable_size_max = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+	if (gse)
+		data->guest_pgtable_reclaim = kvmppc_gse_get_u64(gse);
+
+	return 0;
+}
+
+static struct kvmppc_gs_msg_ops gs_msg_test_hostwide_ops = {
+	.get_size = test_hostwide_get_size,
+	.fill_info = test_hostwide_fill_info,
+	.refresh_info = test_hostwide_refresh_info,
+};
+
+static void test_gs_hostwide_msg(struct kunit *test)
+{
+	struct kvmppc_gs_msg_test_hostwide_data test_data = {
+		.guest_heap = 0xdeadbeef,
+		.guest_heap_max = ~0ULL,
+		.guest_pgtable_size = 0xff,
+		.guest_pgtable_size_max = 0xffffff,
+		.guest_pgtable_reclaim = 0xdeadbeef,
+	};
+	struct kvmppc_gs_msg *gsm;
+	struct kvmppc_gs_buff *gsb;
+
+	gsm = kvmppc_gsm_new(&gs_msg_test_hostwide_ops, &test_data, GSM_SEND,
+			     GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsm);
+
+	gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), 0, 0, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+
+	kvmppc_gsm_fill_info(gsm, gsb);
+
+	memset(&test_data, 0, sizeof(test_data));
+
+	kvmppc_gsm_refresh_info(gsm, gsb);
+	KUNIT_EXPECT_EQ(test, test_data.guest_heap, 0xdeadbeef);
+	KUNIT_EXPECT_EQ(test, test_data.guest_heap_max, ~0ULL);
+	KUNIT_EXPECT_EQ(test, test_data.guest_pgtable_size, 0xff);
+	KUNIT_EXPECT_EQ(test, test_data.guest_pgtable_size_max, 0xffffff);
+	KUNIT_EXPECT_EQ(test, test_data.guest_pgtable_reclaim, 0xdeadbeef);
+
+	kvmppc_gsm_free(gsm);
+}
+
+/* Test if the H_GUEST_GET_STATE for hostwide counters works */
+static void test_gs_hostwide_counters(struct kunit *test)
+{
+	struct kvmppc_gs_msg_test_hostwide_data test_data;
+	struct kvmppc_gs_parser gsp = { 0 };
+
+	struct kvmppc_gs_msg *gsm;
+	struct kvmppc_gs_buff *gsb;
+	struct kvmppc_gs_elem *gse;
+	int rc;
+
+	if (!kvmhv_on_pseries())
+		kunit_skip(test, "This test need a kmv-hv guest");
+
+	gsm = kvmppc_gsm_new(&gs_msg_test_hostwide_ops, &test_data, GSM_SEND,
+			     GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsm);
+
+	gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), 0, 0, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+
+	kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+
+	kvmppc_gsm_fill_info(gsm, gsb);
+
+	/* With HOST_WIDE flags guestid and vcpuid will be ignored */
+	rc = kvmppc_gsb_recv(gsb, KVMPPC_GS_FLAGS_HOST_WIDE);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	/* Parse the guest state buffer is successful */
+	rc = kvmppc_gse_parse(&gsp, gsb);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	/* Parse the GSB and get the counters */
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 Heap counter missing");
+	kunit_info(test, "Guest Heap Size=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 Heap counter max missing");
+	kunit_info(test, "Guest Heap Size Max=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 page-table size missing");
+	kunit_info(test, "Guest Page-table Size=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 page-table size-max missing");
+	kunit_info(test, "Guest Page-table Size Max=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+	KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 page-table reclaim size missing");
+	kunit_info(test, "Guest Page-table Reclaim Size=%llu bytes",
+		   kvmppc_gse_get_u64(gse));
+
+	kvmppc_gsm_free(gsm);
+	kvmppc_gsb_free(gsb);
+}
+
+static struct kunit_case guest_state_buffer_testcases[] = {
+	KUNIT_CASE(test_creating_buffer),
+	KUNIT_CASE(test_adding_element),
+	KUNIT_CASE(test_gs_bitmap),
+	KUNIT_CASE(test_gs_parsing),
+	KUNIT_CASE(test_gs_msg),
+	KUNIT_CASE(test_gs_hostwide_msg),
+	KUNIT_CASE(test_gs_hostwide_counters),
+	{}
+};
+
+static struct kunit_suite guest_state_buffer_test_suite = {
+	.name = "guest_state_buffer_test",
+	.test_cases = guest_state_buffer_testcases,
+};
+
+kunit_test_suites(&guest_state_buffer_test_suite);
+
+MODULE_DESCRIPTION("KUnit tests for Guest State Buffer APIs");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h
index 45817ab82bb4..14b0e23f601f 100644
--- a/arch/powerpc/kvm/timing.h
+++ b/arch/powerpc/kvm/timing.h
@@ -38,11 +38,7 @@ static inline void kvmppc_set_exit_type(struct kvm_vcpu *vcpu, int type) {}
 static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type)
 {
 	/* type has to be known at build time for optimization */
-
-	/* The BUILD_BUG_ON below breaks in funny ways, commented out
-	 * for now ... -BenH
 	BUILD_BUG_ON(!__builtin_constant_p(type));
-	*/
 	switch (type) {
 	case EXT_INTR_EXITS:
 		vcpu->stat.ext_intr_exits++;
diff --git a/arch/powerpc/kvm/tm.S b/arch/powerpc/kvm/tm.S
index 2158f61e317f..b506c4d9a8d9 100644
--- a/arch/powerpc/kvm/tm.S
+++ b/arch/powerpc/kvm/tm.S
@@ -6,10 +6,10 @@
  * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  */
 
+#include <linux/export.h>
 #include <asm/reg.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/tm.h>
 #include <asm/cputable.h>
 
diff --git a/arch/powerpc/kvm/trace_book3s.h b/arch/powerpc/kvm/trace_book3s.h
index 372a82fa2de3..9260ddbd557f 100644
--- a/arch/powerpc/kvm/trace_book3s.h
+++ b/arch/powerpc/kvm/trace_book3s.h
@@ -25,6 +25,7 @@
 	{0xe00, "H_DATA_STORAGE"}, \
 	{0xe20, "H_INST_STORAGE"}, \
 	{0xe40, "H_EMUL_ASSIST"}, \
+	{0xea0, "H_VIRT"}, \
 	{0xf00, "PERFMON"}, \
 	{0xf20, "ALTIVEC"}, \
 	{0xf40, "VSX"}
diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h
index 8d57c8428531..35fccaa575cc 100644
--- a/arch/powerpc/kvm/trace_hv.h
+++ b/arch/powerpc/kvm/trace_hv.h
@@ -512,6 +512,35 @@ TRACE_EVENT(kvmppc_run_vcpu_exit,
 			__entry->vcpu_id, __entry->exit, __entry->ret)
 );
 
+#ifdef CONFIG_PPC_PSERIES
+
+TRACE_EVENT_FN_COND(kvmppc_vcpu_stats,
+	TP_PROTO(struct kvm_vcpu *vcpu, u64 l1_to_l2_cs, u64 l2_to_l1_cs, u64 l2_runtime),
+
+	TP_ARGS(vcpu, l1_to_l2_cs, l2_to_l1_cs, l2_runtime),
+
+	TP_CONDITION(l1_to_l2_cs || l2_to_l1_cs || l2_runtime),
+
+	TP_STRUCT__entry(
+		__field(int,		vcpu_id)
+		__field(u64,		l1_to_l2_cs)
+		__field(u64,		l2_to_l1_cs)
+		__field(u64,		l2_runtime)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id  = vcpu->vcpu_id;
+		__entry->l1_to_l2_cs = l1_to_l2_cs;
+		__entry->l2_to_l1_cs = l2_to_l1_cs;
+		__entry->l2_runtime = l2_runtime;
+	),
+
+	TP_printk("VCPU %d: l1_to_l2_cs_time=%llu ns l2_to_l1_cs_time=%llu ns l2_runtime=%llu ns",
+		__entry->vcpu_id,  __entry->l1_to_l2_cs,
+		__entry->l2_to_l1_cs, __entry->l2_runtime),
+	kvmhv_counters_tracepoint_regfunc, kvmhv_counters_tracepoint_unregfunc
+);
+#endif
 #endif /* _TRACE_KVM_HV_H */
 
 /* This part must be outside protection */
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index c4db459d304a..f14ecab674a3 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -3,8 +3,6 @@
 # Makefile for ppc-specific library files..
 #
 
-ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
-
 CFLAGS_code-patching.o += -fno-stack-protector
 CFLAGS_feature-fixups.o += -fno-stack-protector
 
@@ -27,7 +25,7 @@ endif
 CFLAGS_code-patching.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_feature-fixups.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 
-obj-y += alloc.o code-patching.o feature-fixups.o pmem.o
+obj-y += code-patching.o feature-fixups.o pmem.o
 
 obj-$(CONFIG_CODE_PATCHING_SELFTEST) += test-code-patching.o
 
@@ -44,8 +42,8 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
 # 64-bit linker creates .sfpr on demand for final link (vmlinux),
 # so it is only needed for modules, and only for older linkers which
 # do not support --save-restore-funcs
-ifeq ($(call ld-ifversion, -lt, 22500, y),y)
-extra-$(CONFIG_PPC64)	+= crtsavres.o
+ifndef CONFIG_LD_IS_BFD
+always-$(CONFIG_PPC64)	+= crtsavres.o
 endif
 
 obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
@@ -76,7 +74,7 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
 obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o
 
 obj-$(CONFIG_ALTIVEC)	+= xor_vmx.o xor_vmx_glue.o
-CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec)
+CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec)
 # Enable <altivec.h>
 CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include)
 
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
deleted file mode 100644
index ce180870bd52..000000000000
--- a/arch/powerpc/lib/alloc.c
+++ /dev/null
@@ -1,23 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/memblock.h>
-#include <linux/string.h>
-#include <asm/setup.h>
-
-
-void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask)
-{
-	void *p;
-
-	if (slab_is_available())
-		p = kzalloc(size, mask);
-	else {
-		p = memblock_alloc(size, SMP_CACHE_BYTES);
-		if (!p)
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      size);
-	}
-	return p;
-}
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index 4541e8e29467..cd00b9bdd772 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -8,12 +8,12 @@
  * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au).
  */
 
+#include <linux/export.h>
 #include <linux/sys.h>
 #include <asm/processor.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 
 	.text
 
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 98ff51bd2f7d..d53d8f09a2c2 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -8,11 +8,11 @@
  * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au).
  */
 
+#include <linux/export.h>
 #include <linux/sys.h>
 #include <asm/processor.h>
 #include <asm/errno.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 
 /*
  * Computes the checksum of a memory block at buff, length len,
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index b00112d7ad46..f84e0337cc02 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -17,18 +17,17 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/page.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/inst.h>
 
-static int __patch_instruction(u32 *exec_addr, ppc_inst_t instr, u32 *patch_addr)
+static int __patch_mem(void *exec_addr, unsigned long val, void *patch_addr, bool is_dword)
 {
-	if (!ppc_inst_prefixed(instr)) {
-		u32 val = ppc_inst_val(instr);
+	if (!IS_ENABLED(CONFIG_PPC64) || likely(!is_dword)) {
+		/* For big endian correctness: plain address would use the wrong half */
+		u32 val32 = val;
 
-		__put_kernel_nofault(patch_addr, &val, u32, failed);
+		__put_kernel_nofault(patch_addr, &val32, u32, failed);
 	} else {
-		u64 val = ppc_inst_as_ulong(instr);
-
 		__put_kernel_nofault(patch_addr, &val, u64, failed);
 	}
 
@@ -38,12 +37,16 @@ static int __patch_instruction(u32 *exec_addr, ppc_inst_t instr, u32 *patch_addr
 	return 0;
 
 failed:
+	mb();  /* sync */
 	return -EPERM;
 }
 
 int raw_patch_instruction(u32 *addr, ppc_inst_t instr)
 {
-	return __patch_instruction(addr, instr, addr);
+	if (ppc_inst_prefixed(instr))
+		return __patch_mem(addr, ppc_inst_as_ulong(instr), addr, true);
+	else
+		return __patch_mem(addr, ppc_inst_val(instr), addr, false);
 }
 
 struct patch_context {
@@ -105,7 +108,7 @@ static int text_area_cpu_up(unsigned int cpu)
 	unsigned long addr;
 	int err;
 
-	area = get_vm_area(PAGE_SIZE, VM_ALLOC);
+	area = get_vm_area(PAGE_SIZE, 0);
 	if (!area) {
 		WARN_ONCE(1, "Failed to create text area for cpu %d\n",
 			cpu);
@@ -204,9 +207,6 @@ void __init poking_init(void)
 {
 	int ret;
 
-	if (!IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
-		return;
-
 	if (mm_patch_enabled())
 		ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 					"powerpc/text_poke_mm:online",
@@ -227,7 +227,7 @@ void __init poking_init(void)
 
 static unsigned long get_patch_pfn(void *addr)
 {
-	if (IS_ENABLED(CONFIG_MODULES) && is_vmalloc_or_module_addr(addr))
+	if (IS_ENABLED(CONFIG_EXECMEM) && is_vmalloc_or_module_addr(addr))
 		return vmalloc_to_pfn(addr);
 	else
 		return __pa_symbol(addr) >> PAGE_SHIFT;
@@ -278,7 +278,7 @@ static void unmap_patch_area(unsigned long addr)
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 }
 
-static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr)
+static int __do_patch_mem_mm(void *addr, unsigned long val, bool is_dword)
 {
 	int err;
 	u32 *patch_addr;
@@ -307,11 +307,7 @@ static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr)
 
 	orig_mm = start_using_temp_mm(patching_mm);
 
-	err = __patch_instruction(addr, instr, patch_addr);
-
-	/* hwsync performed by __patch_instruction (sync) if successful */
-	if (err)
-		mb();  /* sync */
+	err = __patch_mem(addr, val, patch_addr, is_dword);
 
 	/* context synchronisation performed by __patch_instruction (isync or exception) */
 	stop_using_temp_mm(patching_mm, orig_mm);
@@ -328,7 +324,7 @@ static int __do_patch_instruction_mm(u32 *addr, ppc_inst_t instr)
 	return err;
 }
 
-static int __do_patch_instruction(u32 *addr, ppc_inst_t instr)
+static int __do_patch_mem(void *addr, unsigned long val, bool is_dword)
 {
 	int err;
 	u32 *patch_addr;
@@ -345,7 +341,7 @@ static int __do_patch_instruction(u32 *addr, ppc_inst_t instr)
 	if (radix_enabled())
 		asm volatile("ptesync": : :"memory");
 
-	err = __patch_instruction(addr, instr, patch_addr);
+	err = __patch_mem(addr, val, patch_addr, is_dword);
 
 	pte_clear(&init_mm, text_poke_addr, pte);
 	flush_tlb_kernel_range(text_poke_addr, text_poke_addr + PAGE_SIZE);
@@ -353,7 +349,7 @@ static int __do_patch_instruction(u32 *addr, ppc_inst_t instr)
 	return err;
 }
 
-int patch_instruction(u32 *addr, ppc_inst_t instr)
+static int patch_mem(void *addr, unsigned long val, bool is_dword)
 {
 	int err;
 	unsigned long flags;
@@ -365,19 +361,220 @@ int patch_instruction(u32 *addr, ppc_inst_t instr)
 	 */
 	if (!IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) ||
 	    !static_branch_likely(&poking_init_done))
-		return raw_patch_instruction(addr, instr);
+		return __patch_mem(addr, val, addr, is_dword);
 
 	local_irq_save(flags);
 	if (mm_patch_enabled())
-		err = __do_patch_instruction_mm(addr, instr);
+		err = __do_patch_mem_mm(addr, val, is_dword);
 	else
-		err = __do_patch_instruction(addr, instr);
+		err = __do_patch_mem(addr, val, is_dword);
 	local_irq_restore(flags);
 
 	return err;
 }
+
+#ifdef CONFIG_PPC64
+
+int patch_instruction(u32 *addr, ppc_inst_t instr)
+{
+	if (ppc_inst_prefixed(instr))
+		return patch_mem(addr, ppc_inst_as_ulong(instr), true);
+	else
+		return patch_mem(addr, ppc_inst_val(instr), false);
+}
 NOKPROBE_SYMBOL(patch_instruction);
 
+int patch_uint(void *addr, unsigned int val)
+{
+	if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned int)))
+		return -EINVAL;
+
+	return patch_mem(addr, val, false);
+}
+NOKPROBE_SYMBOL(patch_uint);
+
+int patch_ulong(void *addr, unsigned long val)
+{
+	if (!IS_ALIGNED((unsigned long)addr, sizeof(unsigned long)))
+		return -EINVAL;
+
+	return patch_mem(addr, val, true);
+}
+NOKPROBE_SYMBOL(patch_ulong);
+
+#else
+
+int patch_instruction(u32 *addr, ppc_inst_t instr)
+{
+	return patch_mem(addr, ppc_inst_val(instr), false);
+}
+NOKPROBE_SYMBOL(patch_instruction)
+
+#endif
+
+static int patch_memset64(u64 *addr, u64 val, size_t count)
+{
+	for (u64 *end = addr + count; addr < end; addr++)
+		__put_kernel_nofault(addr, &val, u64, failed);
+
+	return 0;
+
+failed:
+	return -EPERM;
+}
+
+static int patch_memset32(u32 *addr, u32 val, size_t count)
+{
+	for (u32 *end = addr + count; addr < end; addr++)
+		__put_kernel_nofault(addr, &val, u32, failed);
+
+	return 0;
+
+failed:
+	return -EPERM;
+}
+
+static int __patch_instructions(u32 *patch_addr, u32 *code, size_t len, bool repeat_instr)
+{
+	unsigned long start = (unsigned long)patch_addr;
+	int err;
+
+	/* Repeat instruction */
+	if (repeat_instr) {
+		ppc_inst_t instr = ppc_inst_read(code);
+
+		if (ppc_inst_prefixed(instr)) {
+			u64 val = ppc_inst_as_ulong(instr);
+
+			err = patch_memset64((u64 *)patch_addr, val, len / 8);
+		} else {
+			u32 val = ppc_inst_val(instr);
+
+			err = patch_memset32(patch_addr, val, len / 4);
+		}
+	} else {
+		err = copy_to_kernel_nofault(patch_addr, code, len);
+	}
+
+	smp_wmb();	/* smp write barrier */
+	flush_icache_range(start, start + len);
+	return err;
+}
+
+/*
+ * A page is mapped and instructions that fit the page are patched.
+ * Assumes 'len' to be (PAGE_SIZE - offset_in_page(addr)) or below.
+ */
+static int __do_patch_instructions_mm(u32 *addr, u32 *code, size_t len, bool repeat_instr)
+{
+	struct mm_struct *patching_mm, *orig_mm;
+	unsigned long pfn = get_patch_pfn(addr);
+	unsigned long text_poke_addr;
+	spinlock_t *ptl;
+	u32 *patch_addr;
+	pte_t *pte;
+	int err;
+
+	patching_mm = __this_cpu_read(cpu_patching_context.mm);
+	text_poke_addr = __this_cpu_read(cpu_patching_context.addr);
+	patch_addr = (u32 *)(text_poke_addr + offset_in_page(addr));
+
+	pte = get_locked_pte(patching_mm, text_poke_addr, &ptl);
+	if (!pte)
+		return -ENOMEM;
+
+	__set_pte_at(patching_mm, text_poke_addr, pte, pfn_pte(pfn, PAGE_KERNEL), 0);
+
+	/* order PTE update before use, also serves as the hwsync */
+	asm volatile("ptesync" ::: "memory");
+
+	/* order context switch after arbitrary prior code */
+	isync();
+
+	orig_mm = start_using_temp_mm(patching_mm);
+
+	kasan_disable_current();
+	err = __patch_instructions(patch_addr, code, len, repeat_instr);
+	kasan_enable_current();
+
+	/* context synchronisation performed by __patch_instructions */
+	stop_using_temp_mm(patching_mm, orig_mm);
+
+	pte_clear(patching_mm, text_poke_addr, pte);
+	/*
+	 * ptesync to order PTE update before TLB invalidation done
+	 * by radix__local_flush_tlb_page_psize (in _tlbiel_va)
+	 */
+	local_flush_tlb_page_psize(patching_mm, text_poke_addr, mmu_virtual_psize);
+
+	pte_unmap_unlock(pte, ptl);
+
+	return err;
+}
+
+/*
+ * A page is mapped and instructions that fit the page are patched.
+ * Assumes 'len' to be (PAGE_SIZE - offset_in_page(addr)) or below.
+ */
+static int __do_patch_instructions(u32 *addr, u32 *code, size_t len, bool repeat_instr)
+{
+	unsigned long pfn = get_patch_pfn(addr);
+	unsigned long text_poke_addr;
+	u32 *patch_addr;
+	pte_t *pte;
+	int err;
+
+	text_poke_addr = (unsigned long)__this_cpu_read(cpu_patching_context.addr) & PAGE_MASK;
+	patch_addr = (u32 *)(text_poke_addr + offset_in_page(addr));
+
+	pte = __this_cpu_read(cpu_patching_context.pte);
+	__set_pte_at(&init_mm, text_poke_addr, pte, pfn_pte(pfn, PAGE_KERNEL), 0);
+	/* See ptesync comment in radix__set_pte_at() */
+	if (radix_enabled())
+		asm volatile("ptesync" ::: "memory");
+
+	err = __patch_instructions(patch_addr, code, len, repeat_instr);
+
+	pte_clear(&init_mm, text_poke_addr, pte);
+	flush_tlb_kernel_range(text_poke_addr, text_poke_addr + PAGE_SIZE);
+
+	return err;
+}
+
+/*
+ * Patch 'addr' with 'len' bytes of instructions from 'code'.
+ *
+ * If repeat_instr is true, the same instruction is filled for
+ * 'len' bytes.
+ */
+int patch_instructions(u32 *addr, u32 *code, size_t len, bool repeat_instr)
+{
+	while (len > 0) {
+		unsigned long flags;
+		size_t plen;
+		int err;
+
+		plen = min_t(size_t, PAGE_SIZE - offset_in_page(addr), len);
+
+		local_irq_save(flags);
+		if (mm_patch_enabled())
+			err = __do_patch_instructions_mm(addr, code, plen, repeat_instr);
+		else
+			err = __do_patch_instructions(addr, code, plen, repeat_instr);
+		local_irq_restore(flags);
+		if (err)
+			return err;
+
+		len -= plen;
+		addr = (u32 *)((unsigned long)addr + plen);
+		if (!repeat_instr)
+			code = (u32 *)((unsigned long)code + plen);
+	}
+
+	return 0;
+}
+NOKPROBE_SYMBOL(patch_instructions);
+
 int patch_branch(u32 *addr, unsigned long target, int flags)
 {
 	ppc_inst_t instr;
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 3e9c27c46331..933b685e7ab6 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -4,11 +4,11 @@
  *
  * Copyright (C) 1996-2005 Paul Mackerras.
  */
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 #include <asm/code-patching-asm.h>
 #include <asm/kasan.h>
 
diff --git a/arch/powerpc/lib/copy_mc_64.S b/arch/powerpc/lib/copy_mc_64.S
index 88d46c471493..bf1014b28fe8 100644
--- a/arch/powerpc/lib/copy_mc_64.S
+++ b/arch/powerpc/lib/copy_mc_64.S
@@ -4,9 +4,9 @@
  * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
  * Author - Balbir Singh <bsingharora@gmail.com>
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
 #include <asm/errno.h>
-#include <asm/export.h>
 
 	.macro err1
 100:
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
index 5d09a029b556..f33a2e6088e5 100644
--- a/arch/powerpc/lib/copypage_64.S
+++ b/arch/powerpc/lib/copypage_64.S
@@ -2,11 +2,11 @@
 /*
  * Copyright (C) 2008 Mark Nelson, IBM Corp.
  */
+#include <linux/export.h>
 #include <asm/page.h>
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 
 _GLOBAL_TOC(copy_page)
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
index a783973f1215..07e7cec4d135 100644
--- a/arch/powerpc/lib/copypage_power7.S
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -27,17 +27,7 @@ _GLOBAL(copypage_power7)
 #endif
 	ori	r10,r7,1	/* stream=1 */
 
-	lis	r8,0x8000	/* GO=1 */
-	clrldi	r8,r8,32
-
-	/* setup read stream 0  */
-	dcbt	0,r4,0b01000  	/* addr from */
-	dcbt	0,r7,0b01010   /* length and depth from */
-	/* setup write stream 1 */
-	dcbtst	0,r9,0b01000   /* addr to */
-	dcbtst	0,r10,0b01010  /* length and depth to */
-	eieio
-	dcbt	0,r8,0b01010	/* all streams GO */
+	DCBT_SETUP_STREAMS(r4, r7, r9, r10, r8)
 
 #ifdef CONFIG_ALTIVEC
 	mflr	r0
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index db8719a14846..9af969d2cc0c 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -2,9 +2,9 @@
 /*
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
  */
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index ac41053c3a5a..8474c682a178 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -298,17 +298,7 @@ err1;	stb	r0,0(r3)
 	or	r7,r7,r0
 	ori	r10,r7,1	/* stream=1 */
 
-	lis	r8,0x8000	/* GO=1 */
-	clrldi	r8,r8,32
-
-	/* setup read stream 0 */
-	dcbt	0,r6,0b01000   /* addr from */
-	dcbt	0,r7,0b01010   /* length and depth from */
-	/* setup write stream 1 */
-	dcbtst	0,r9,0b01000   /* addr to */
-	dcbtst	0,r10,0b01010  /* length and depth to */
-	eieio
-	dcbt	0,r8,0b01010	/* all streams GO */
+	DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8)
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy
 
diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S
index 7e5e1c28e56a..8967903c15e9 100644
--- a/arch/powerpc/lib/crtsavres.S
+++ b/arch/powerpc/lib/crtsavres.S
@@ -46,7 +46,7 @@
 
 	.section ".text"
 
-#ifndef CONFIG_PPC64
+#ifndef __powerpc64__
 
 /* Routines for saving integer registers, called by the compiler.  */
 /* Called with r11 pointing to the stack header word of the caller of the */
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 80def1c2afcb..587c8cf1230f 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -16,7 +16,7 @@
 #include <linux/sched/mm.h>
 #include <linux/stop_machine.h>
 #include <asm/cputable.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/interrupt.h>
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -25,6 +25,13 @@
 #include <asm/firmware.h>
 #include <asm/inst.h>
 
+/*
+ * Used to generate warnings if mmu or cpu feature check functions that
+ * use static keys before they are initialized.
+ */
+bool static_key_feature_checks_initialized __read_mostly;
+EXPORT_SYMBOL_GPL(static_key_feature_checks_initialized);
+
 struct fixup_entry {
 	unsigned long	mask;
 	unsigned long	value;
@@ -67,7 +74,8 @@ static int patch_alt_instruction(u32 *src, u32 *dest, u32 *alt_start, u32 *alt_e
 	return 0;
 }
 
-static int patch_feature_section(unsigned long value, struct fixup_entry *fcur)
+static int patch_feature_section_mask(unsigned long value, unsigned long mask,
+				      struct fixup_entry *fcur)
 {
 	u32 *start, *end, *alt_start, *alt_end, *src, *dest;
 
@@ -79,7 +87,7 @@ static int patch_feature_section(unsigned long value, struct fixup_entry *fcur)
 	if ((alt_end - alt_start) > (end - start))
 		return 1;
 
-	if ((value & fcur->mask) == fcur->value)
+	if ((value & fcur->mask & mask) == (fcur->value & mask))
 		return 0;
 
 	src = alt_start;
@@ -97,7 +105,8 @@ static int patch_feature_section(unsigned long value, struct fixup_entry *fcur)
 	return 0;
 }
 
-void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
+static void do_feature_fixups_mask(unsigned long value, unsigned long mask,
+				   void *fixup_start, void *fixup_end)
 {
 	struct fixup_entry *fcur, *fend;
 
@@ -105,7 +114,7 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 	fend = fixup_end;
 
 	for (; fcur < fend; fcur++) {
-		if (patch_feature_section(value, fcur)) {
+		if (patch_feature_section_mask(value, mask, fcur)) {
 			WARN_ON(1);
 			printk("Unable to patch feature section at %p - %p" \
 				" with %p - %p\n",
@@ -117,6 +126,11 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 	}
 }
 
+void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
+{
+	do_feature_fixups_mask(value, ~0, fixup_start, fixup_end);
+}
+
 #ifdef CONFIG_PPC_BARRIER_NOSPEC
 static bool is_fixup_addr_valid(void *dest, size_t size)
 {
@@ -651,6 +665,17 @@ void __init apply_feature_fixups(void)
 	do_final_fixups();
 }
 
+void __init update_mmu_feature_fixups(unsigned long mask)
+{
+	saved_mmu_features &= ~mask;
+	saved_mmu_features |= cur_cpu_spec->mmu_features & mask;
+
+	do_feature_fixups_mask(cur_cpu_spec->mmu_features, mask,
+			       PTRRELOC(&__start___mmu_ftr_fixup),
+			       PTRRELOC(&__stop___mmu_ftr_fixup));
+	mmu_feature_keys_init();
+}
+
 void __init setup_feature_keys(void)
 {
 	/*
@@ -661,6 +686,7 @@ void __init setup_feature_keys(void)
 	jump_label_init();
 	cpu_feature_keys_init();
 	mmu_feature_keys_init();
+	static_key_feature_checks_initialized = true;
 }
 
 static int __init check_features(void)
@@ -683,6 +709,11 @@ late_initcall(check_features);
 #define check(x)	\
 	if (!(x)) printk("feature-fixups: test failed at line %d\n", __LINE__);
 
+static int patch_feature_section(unsigned long value, struct fixup_entry *fcur)
+{
+	return patch_feature_section_mask(value, ~0, fcur);
+}
+
 /* This must be after the text it fixes up, vmlinux.lds.S enforces that atm */
 static struct fixup_entry fixup;
 
diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S
index 09af29561314..151875050da9 100644
--- a/arch/powerpc/lib/hweight_64.S
+++ b/arch/powerpc/lib/hweight_64.S
@@ -5,9 +5,9 @@
  *
  * Author: Anton Blanchard <anton@au.ibm.com>
  */
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 
 /* Note: This code relies on -mminimal-toc */
diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S
index 9351ffab409c..6fd06cd20faa 100644
--- a/arch/powerpc/lib/mem_64.S
+++ b/arch/powerpc/lib/mem_64.S
@@ -4,10 +4,10 @@
  *
  * Copyright (C) 1996 Paul Mackerras.
  */
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <asm/errno.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 #include <asm/kasan.h>
 
 #ifndef CONFIG_KASAN
diff --git a/arch/powerpc/lib/memcmp_32.S b/arch/powerpc/lib/memcmp_32.S
index 5010e376f7b8..f6fca5664e91 100644
--- a/arch/powerpc/lib/memcmp_32.S
+++ b/arch/powerpc/lib/memcmp_32.S
@@ -7,8 +7,8 @@
  *
  */
 
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 
 	.text
 
diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S
index 0b9b1685a33d..142c666d3897 100644
--- a/arch/powerpc/lib/memcmp_64.S
+++ b/arch/powerpc/lib/memcmp_64.S
@@ -3,8 +3,8 @@
  * Author: Anton Blanchard <anton@au.ibm.com>
  * Copyright 2015 IBM Corporation.
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 #include <asm/ppc-opcode.h>
 
 #define off8	r6
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 016c91e958d8..b5a67e20143f 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -2,9 +2,9 @@
 /*
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
  */
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 #include <asm/kasan.h>
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index 9398b2b746c4..b7c5e7fca8b9 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -244,15 +244,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	or	r7,r7,r0
 	ori	r10,r7,1	/* stream=1 */
 
-	lis	r8,0x8000	/* GO=1 */
-	clrldi	r8,r8,32
-
-	dcbt	0,r6,0b01000
-	dcbt	0,r7,0b01010
-	dcbtst	0,r9,0b01000
-	dcbtst	0,r10,0b01010
-	eieio
-	dcbt	0,r8,0b01010	/* GO */
+	DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8)
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy
 
diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
index e4bd145255d0..95ab4cdf582e 100644
--- a/arch/powerpc/lib/qspinlock.c
+++ b/arch/powerpc/lib/qspinlock.c
@@ -9,6 +9,7 @@
 #include <linux/sched/clock.h>
 #include <asm/qspinlock.h>
 #include <asm/paravirt.h>
+#include <trace/events/lock.h>
 
 #define MAX_NODES	4
 
@@ -16,7 +17,8 @@ struct qnode {
 	struct qnode	*next;
 	struct qspinlock *lock;
 	int		cpu;
-	int		yield_cpu;
+	u8		sleepy; /* 1 if the previous vCPU was preempted or
+				 * if the previous node was sleepy */
 	u8		locked; /* 1 if lock acquired */
 };
 
@@ -43,7 +45,7 @@ static bool pv_sleepy_lock_sticky __read_mostly = false;
 static u64 pv_sleepy_lock_interval_ns __read_mostly = 0;
 static int pv_sleepy_lock_factor __read_mostly = 256;
 static bool pv_yield_prev __read_mostly = true;
-static bool pv_yield_propagate_owner __read_mostly = true;
+static bool pv_yield_sleepy_owner __read_mostly = true;
 static bool pv_prod_head __read_mostly = false;
 
 static DEFINE_PER_CPU_ALIGNED(struct qnodes, qnodes);
@@ -161,6 +163,8 @@ static __always_inline u32 publish_tail_cpu(struct qspinlock *lock, u32 tail)
 {
 	u32 prev, tmp;
 
+	kcsan_release();
+
 	asm volatile(
 "\t"	PPC_RELEASE_BARRIER "						\n"
 "1:	lwarx	%0,0,%2		# publish_tail_cpu			\n"
@@ -245,22 +249,18 @@ static __always_inline void seen_sleepy_lock(void)
 		this_cpu_write(sleepy_lock_seen_clock, sched_clock());
 }
 
-static __always_inline void seen_sleepy_node(struct qspinlock *lock, u32 val)
+static __always_inline void seen_sleepy_node(void)
 {
 	if (pv_sleepy_lock) {
 		if (pv_sleepy_lock_interval_ns)
 			this_cpu_write(sleepy_lock_seen_clock, sched_clock());
-		if (val & _Q_LOCKED_VAL) {
-			if (!(val & _Q_SLEEPY_VAL))
-				try_set_sleepy(lock, val);
-		}
+		/* Don't set sleepy because we likely have a stale val */
 	}
 }
 
-static struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val)
+static struct qnode *get_tail_qnode(struct qspinlock *lock, int prev_cpu)
 {
-	int cpu = decode_tail_cpu(val);
-	struct qnodes *qnodesp = per_cpu_ptr(&qnodes, cpu);
+	struct qnodes *qnodesp = per_cpu_ptr(&qnodes, prev_cpu);
 	int idx;
 
 	/*
@@ -351,74 +351,66 @@ static __always_inline bool yield_head_to_locked_owner(struct qspinlock *lock, u
 	return __yield_to_locked_owner(lock, val, paravirt, mustq);
 }
 
-static __always_inline void propagate_yield_cpu(struct qnode *node, u32 val, int *set_yield_cpu, bool paravirt)
+static __always_inline void propagate_sleepy(struct qnode *node, u32 val, bool paravirt)
 {
 	struct qnode *next;
 	int owner;
 
 	if (!paravirt)
 		return;
-	if (!pv_yield_propagate_owner)
-		return;
-
-	owner = get_owner_cpu(val);
-	if (*set_yield_cpu == owner)
+	if (!pv_yield_sleepy_owner)
 		return;
 
 	next = READ_ONCE(node->next);
 	if (!next)
 		return;
 
-	if (vcpu_is_preempted(owner)) {
-		next->yield_cpu = owner;
-		*set_yield_cpu = owner;
-	} else if (*set_yield_cpu != -1) {
-		next->yield_cpu = owner;
-		*set_yield_cpu = owner;
-	}
+	if (next->sleepy)
+		return;
+
+	owner = get_owner_cpu(val);
+	if (vcpu_is_preempted(owner))
+		next->sleepy = 1;
 }
 
 /* Called inside spin_begin() */
-static __always_inline bool yield_to_prev(struct qspinlock *lock, struct qnode *node, u32 val, bool paravirt)
+static __always_inline bool yield_to_prev(struct qspinlock *lock, struct qnode *node, int prev_cpu, bool paravirt)
 {
-	int prev_cpu = decode_tail_cpu(val);
 	u32 yield_count;
-	int yield_cpu;
 	bool preempted = false;
 
 	if (!paravirt)
 		goto relax;
 
-	if (!pv_yield_propagate_owner)
+	if (!pv_yield_sleepy_owner)
 		goto yield_prev;
 
-	yield_cpu = READ_ONCE(node->yield_cpu);
-	if (yield_cpu == -1) {
-		/* Propagate back the -1 CPU */
-		if (node->next && node->next->yield_cpu != -1)
-			node->next->yield_cpu = yield_cpu;
-		goto yield_prev;
-	}
-
-	yield_count = yield_count_of(yield_cpu);
-	if ((yield_count & 1) == 0)
-		goto yield_prev; /* owner vcpu is running */
-
-	spin_end();
-
-	preempted = true;
-	seen_sleepy_node(lock, val);
+	/*
+	 * If the previous waiter was preempted it might not be able to
+	 * propagate sleepy to us, so check the lock in that case too.
+	 */
+	if (node->sleepy || vcpu_is_preempted(prev_cpu)) {
+		u32 val = READ_ONCE(lock->val);
 
-	smp_rmb();
+		if (val & _Q_LOCKED_VAL) {
+			if (node->next && !node->next->sleepy) {
+				/*
+				 * Propagate sleepy to next waiter. Only if
+				 * owner is preempted, which allows the queue
+				 * to become "non-sleepy" if vCPU preemption
+				 * ceases to occur, even if the lock remains
+				 * highly contended.
+				 */
+				if (vcpu_is_preempted(get_owner_cpu(val)))
+					node->next->sleepy = 1;
+			}
 
-	if (yield_cpu == node->yield_cpu) {
-		if (node->next && node->next->yield_cpu != yield_cpu)
-			node->next->yield_cpu = yield_cpu;
-		yield_to_preempted(yield_cpu, yield_count);
-		spin_begin();
-		return preempted;
+			preempted = yield_to_locked_owner(lock, val, paravirt);
+			if (preempted)
+				return preempted;
+		}
+		node->sleepy = false;
 	}
-	spin_begin();
 
 yield_prev:
 	if (!pv_yield_prev)
@@ -431,11 +423,11 @@ yield_prev:
 	spin_end();
 
 	preempted = true;
-	seen_sleepy_node(lock, val);
+	seen_sleepy_node();
 
 	smp_rmb(); /* See __yield_to_locked_owner comment */
 
-	if (!node->locked) {
+	if (!READ_ONCE(node->locked)) {
 		yield_to_preempted(prev_cpu, yield_count);
 		spin_begin();
 		return preempted;
@@ -541,7 +533,6 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 	bool sleepy = false;
 	bool mustq = false;
 	int idx;
-	int set_yield_cpu = -1;
 	int iters = 0;
 
 	BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
@@ -565,11 +556,16 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 	node->next = NULL;
 	node->lock = lock;
 	node->cpu = smp_processor_id();
-	node->yield_cpu = -1;
+	node->sleepy = 0;
 	node->locked = 0;
 
 	tail = encode_tail_cpu(node->cpu);
 
+	/*
+	 * Assign all attributes of a node before it can be published.
+	 * Issues an lwsync, serving as a release barrier, as well as a
+	 * compiler barrier.
+	 */
 	old = publish_tail_cpu(lock, tail);
 
 	/*
@@ -577,26 +573,23 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 	 * head of the waitqueue.
 	 */
 	if (old & _Q_TAIL_CPU_MASK) {
-		struct qnode *prev = get_tail_qnode(lock, old);
+		int prev_cpu = decode_tail_cpu(old);
+		struct qnode *prev = get_tail_qnode(lock, prev_cpu);
 
 		/* Link @node into the waitqueue. */
 		WRITE_ONCE(prev->next, node);
 
 		/* Wait for mcs node lock to be released */
 		spin_begin();
-		while (!node->locked) {
+		while (!READ_ONCE(node->locked)) {
 			spec_barrier();
 
-			if (yield_to_prev(lock, node, old, paravirt))
+			if (yield_to_prev(lock, node, prev_cpu, paravirt))
 				seen_preempted = true;
 		}
 		spec_barrier();
 		spin_end();
 
-		/* Clear out stale propagated yield_cpu */
-		if (paravirt && pv_yield_propagate_owner && node->yield_cpu != -1)
-			node->yield_cpu = -1;
-
 		smp_rmb(); /* acquire barrier for the mcs lock */
 
 		/*
@@ -638,7 +631,7 @@ again:
 			}
 		}
 
-		propagate_yield_cpu(node, val, &set_yield_cpu, paravirt);
+		propagate_sleepy(node, val, paravirt);
 		preempted = yield_head_to_locked_owner(lock, val, paravirt);
 		if (!maybe_stealers)
 			continue;
@@ -705,29 +698,37 @@ again:
 	}
 
 release:
-	qnodesp->count--; /* release the node */
+	/*
+	 * Clear the lock before releasing the node, as another CPU might see stale
+	 * values if an interrupt occurs after we increment qnodesp->count
+	 * but before node->lock is initialized. The barrier ensures that
+	 * there are no further stores to the node after it has been released.
+	 */
+	node->lock = NULL;
+	barrier();
+	qnodesp->count--;
 }
 
-void queued_spin_lock_slowpath(struct qspinlock *lock)
+void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock)
 {
+	trace_contention_begin(lock, LCB_F_SPIN);
 	/*
 	 * This looks funny, but it induces the compiler to inline both
 	 * sides of the branch rather than share code as when the condition
 	 * is passed as the paravirt argument to the functions.
 	 */
 	if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && is_shared_processor()) {
-		if (try_to_steal_lock(lock, true)) {
+		if (try_to_steal_lock(lock, true))
 			spec_barrier();
-			return;
-		}
-		queued_spin_lock_mcs_queue(lock, true);
+		else
+			queued_spin_lock_mcs_queue(lock, true);
 	} else {
-		if (try_to_steal_lock(lock, false)) {
+		if (try_to_steal_lock(lock, false))
 			spec_barrier();
-			return;
-		}
-		queued_spin_lock_mcs_queue(lock, false);
+		else
+			queued_spin_lock_mcs_queue(lock, false);
 	}
+	trace_contention_end(lock, 0);
 }
 EXPORT_SYMBOL(queued_spin_lock_slowpath);
 
@@ -942,21 +943,21 @@ static int pv_yield_prev_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_prev, pv_yield_prev_get, pv_yield_prev_set, "%llu\n");
 
-static int pv_yield_propagate_owner_set(void *data, u64 val)
+static int pv_yield_sleepy_owner_set(void *data, u64 val)
 {
-	pv_yield_propagate_owner = !!val;
+	pv_yield_sleepy_owner = !!val;
 
 	return 0;
 }
 
-static int pv_yield_propagate_owner_get(void *data, u64 *val)
+static int pv_yield_sleepy_owner_get(void *data, u64 *val)
 {
-	*val = pv_yield_propagate_owner;
+	*val = pv_yield_sleepy_owner;
 
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_propagate_owner, pv_yield_propagate_owner_get, pv_yield_propagate_owner_set, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_sleepy_owner, pv_yield_sleepy_owner_get, pv_yield_sleepy_owner_set, "%llu\n");
 
 static int pv_prod_head_set(void *data, u64 val)
 {
@@ -988,7 +989,7 @@ static __init int spinlock_debugfs_init(void)
 		debugfs_create_file("qspl_pv_sleepy_lock_interval_ns", 0600, arch_debugfs_dir, NULL, &fops_pv_sleepy_lock_interval_ns);
 		debugfs_create_file("qspl_pv_sleepy_lock_factor", 0600, arch_debugfs_dir, NULL, &fops_pv_sleepy_lock_factor);
 		debugfs_create_file("qspl_pv_yield_prev", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_prev);
-		debugfs_create_file("qspl_pv_yield_propagate_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_propagate_owner);
+		debugfs_create_file("qspl_pv_yield_sleepy_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_sleepy_owner);
 		debugfs_create_file("qspl_pv_prod_head", 0600, arch_debugfs_dir, NULL, &fops_pv_prod_head);
 	}
 
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 38158b77a801..ac3ee19531d8 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -485,7 +485,7 @@ write_mem_aligned(unsigned long val, unsigned long ea, int nb, struct pt_regs *r
  * Copy from a buffer to userspace, using the largest possible
  * aligned accesses, up to sizeof(long).
  */
-static nokprobe_inline int __copy_mem_out(u8 *dest, unsigned long ea, int nb, struct pt_regs *regs)
+static __always_inline int __copy_mem_out(u8 *dest, unsigned long ea, int nb, struct pt_regs *regs)
 {
 	int c;
 
@@ -586,6 +586,8 @@ static int do_fp_load(struct instruction_op *op, unsigned long ea,
 	} u;
 
 	nb = GETSIZE(op->type);
+	if (nb > sizeof(u))
+		return -EINVAL;
 	if (!address_ok(regs, ea, nb))
 		return -EFAULT;
 	rn = op->reg;
@@ -636,6 +638,8 @@ static int do_fp_store(struct instruction_op *op, unsigned long ea,
 	} u;
 
 	nb = GETSIZE(op->type);
+	if (nb > sizeof(u))
+		return -EINVAL;
 	if (!address_ok(regs, ea, nb))
 		return -EFAULT;
 	rn = op->reg;
@@ -680,6 +684,9 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea,
 		u8 b[sizeof(__vector128)];
 	} u = {};
 
+	if (size > sizeof(u))
+		return -EINVAL;
+
 	if (!address_ok(regs, ea & ~0xfUL, 16))
 		return -EFAULT;
 	/* align to multiple of size */
@@ -688,7 +695,7 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea,
 	if (err)
 		return err;
 	if (unlikely(cross_endian))
-		do_byte_reverse(&u.b[ea & 0xf], size);
+		do_byte_reverse(&u.b[ea & 0xf], min_t(size_t, size, sizeof(u)));
 	preempt_disable();
 	if (regs->msr & MSR_VEC)
 		put_vr(rn, &u.v);
@@ -707,6 +714,9 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea,
 		u8 b[sizeof(__vector128)];
 	} u;
 
+	if (size > sizeof(u))
+		return -EINVAL;
+
 	if (!address_ok(regs, ea & ~0xfUL, 16))
 		return -EFAULT;
 	/* align to multiple of size */
@@ -719,7 +729,7 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea,
 		u.v = current->thread.vr_state.vr[rn];
 	preempt_enable();
 	if (unlikely(cross_endian))
-		do_byte_reverse(&u.b[ea & 0xf], size);
+		do_byte_reverse(&u.b[ea & 0xf], min_t(size_t, size, sizeof(u)));
 	return copy_mem_out(&u.b[ea & 0xf], ea, size, regs);
 }
 #endif /* CONFIG_ALTIVEC */
@@ -770,8 +780,8 @@ static nokprobe_inline int emulate_stq(struct pt_regs *regs, unsigned long ea,
 #endif /* __powerpc64 */
 
 #ifdef CONFIG_VSX
-void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
-		      const void *mem, bool rev)
+static nokprobe_inline void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
+					     const void *mem, bool rev)
 {
 	int size, read_size;
 	int i, j;
@@ -853,11 +863,9 @@ void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
 		break;
 	}
 }
-EXPORT_SYMBOL_GPL(emulate_vsx_load);
-NOKPROBE_SYMBOL(emulate_vsx_load);
 
-void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
-		       void *mem, bool rev)
+static nokprobe_inline void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
+					      void *mem, bool rev)
 {
 	int size, write_size;
 	int i, j;
@@ -945,8 +953,6 @@ void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
 		break;
 	}
 }
-EXPORT_SYMBOL_GPL(emulate_vsx_store);
-NOKPROBE_SYMBOL(emulate_vsx_store);
 
 static nokprobe_inline int do_vsx_load(struct instruction_op *op,
 				       unsigned long ea, struct pt_regs *regs,
@@ -1043,7 +1049,7 @@ static nokprobe_inline int do_vsx_store(struct instruction_op *op,
 }
 #endif /* CONFIG_VSX */
 
-static int __emulate_dcbz(unsigned long ea)
+static __always_inline int __emulate_dcbz(unsigned long ea)
 {
 	unsigned long i;
 	unsigned long size = l1_dcache_bytes();
@@ -1419,7 +1425,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 			return 1;
 
 		case 18:	/* rfid, scary */
-			if (regs->msr & MSR_PR)
+			if (user_mode(regs))
 				goto priv;
 			op->type = RFI;
 			return 0;
@@ -1732,13 +1738,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 			return 1;
 #endif
 		case 83:	/* mfmsr */
-			if (regs->msr & MSR_PR)
+			if (user_mode(regs))
 				goto priv;
 			op->type = MFMSR;
 			op->reg = rd;
 			return 0;
 		case 146:	/* mtmsr */
-			if (regs->msr & MSR_PR)
+			if (user_mode(regs))
 				goto priv;
 			op->type = MTMSR;
 			op->reg = rd;
@@ -1746,7 +1752,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 			return 0;
 #ifdef CONFIG_PPC64
 		case 178:	/* mtmsrd */
-			if (regs->msr & MSR_PR)
+			if (user_mode(regs))
 				goto priv;
 			op->type = MTMSR;
 			op->reg = rd;
@@ -3427,14 +3433,14 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
 		 * stored in the thread_struct.  If the instruction is in
 		 * the kernel, we must not touch the state in the thread_struct.
 		 */
-		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP))
+		if (!user_mode(regs) && !(regs->msr & MSR_FP))
 			return 0;
 		err = do_fp_load(op, ea, regs, cross_endian);
 		break;
 #endif
 #ifdef CONFIG_ALTIVEC
 	case LOAD_VMX:
-		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC))
+		if (!user_mode(regs) && !(regs->msr & MSR_VEC))
 			return 0;
 		err = do_vec_load(op->reg, ea, size, regs, cross_endian);
 		break;
@@ -3449,7 +3455,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
 		 */
 		if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC))
 			msrbit = MSR_VEC;
-		if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit))
+		if (!user_mode(regs) && !(regs->msr & msrbit))
 			return 0;
 		err = do_vsx_load(op, ea, regs, cross_endian);
 		break;
@@ -3485,8 +3491,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
 		}
 #endif
 		if ((op->type & UPDATE) && size == sizeof(long) &&
-		    op->reg == 1 && op->update_reg == 1 &&
-		    !(regs->msr & MSR_PR) &&
+		    op->reg == 1 && op->update_reg == 1 && !user_mode(regs) &&
 		    ea >= regs->gpr[1] - STACK_INT_FRAME_SIZE) {
 			err = handle_stack_update(ea, regs);
 			break;
@@ -3498,14 +3503,14 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
 
 #ifdef CONFIG_PPC_FPU
 	case STORE_FP:
-		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP))
+		if (!user_mode(regs) && !(regs->msr & MSR_FP))
 			return 0;
 		err = do_fp_store(op, ea, regs, cross_endian);
 		break;
 #endif
 #ifdef CONFIG_ALTIVEC
 	case STORE_VMX:
-		if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC))
+		if (!user_mode(regs) && !(regs->msr & MSR_VEC))
 			return 0;
 		err = do_vec_store(op->reg, ea, size, regs, cross_endian);
 		break;
@@ -3520,7 +3525,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op)
 		 */
 		if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC))
 			msrbit = MSR_VEC;
-		if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit))
+		if (!user_mode(regs) && !(regs->msr & msrbit))
 			return 0;
 		err = do_vsx_store(op, ea, regs, cross_endian);
 		break;
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index 2752b1cc1d45..daa72061dc0c 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -4,8 +4,8 @@
  *
  * Copyright (C) 1996 Paul Mackerras.
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 #include <asm/cache.h>
 
 	.text
diff --git a/arch/powerpc/lib/string_32.S b/arch/powerpc/lib/string_32.S
index 1ddb26394e8a..3ee45619a3f8 100644
--- a/arch/powerpc/lib/string_32.S
+++ b/arch/powerpc/lib/string_32.S
@@ -7,8 +7,8 @@
  *
  */
 
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 #include <asm/cache.h>
 
 	.text
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
index df41ce06f86b..a25eb8588434 100644
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -6,10 +6,10 @@
  * Author: Anton Blanchard <anton@au.ibm.com>
  */
 
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
 #include <asm/linkage.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 
 /**
  * __arch_clear_user: - Zero a block of memory in user space, with less checking.
diff --git a/arch/powerpc/lib/strlen_32.S b/arch/powerpc/lib/strlen_32.S
index 0a8d3f64d493..bbd24feb233f 100644
--- a/arch/powerpc/lib/strlen_32.S
+++ b/arch/powerpc/lib/strlen_32.S
@@ -6,8 +6,8 @@
  *
  * Inspired from glibc implementation
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
-#include <asm/export.h>
 #include <asm/cache.h>
 
 	.text
diff --git a/arch/powerpc/lib/test-code-patching.c b/arch/powerpc/lib/test-code-patching.c
index c44823292f73..1440d99630b3 100644
--- a/arch/powerpc/lib/test-code-patching.c
+++ b/arch/powerpc/lib/test-code-patching.c
@@ -6,7 +6,7 @@
 #include <linux/vmalloc.h>
 #include <linux/init.h>
 
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 
 static int __init instr_is_branch_to_addr(const u32 *instr, unsigned long addr)
 {
@@ -347,6 +347,137 @@ static void __init test_prefixed_patching(void)
 	check(!memcmp(iptr, expected, sizeof(expected)));
 }
 
+static void __init test_multi_instruction_patching(void)
+{
+	u32 code[32];
+	void *buf;
+	u32 *addr32;
+	u64 *addr64;
+	ppc_inst_t inst64 = ppc_inst_prefix(OP_PREFIX << 26 | 3UL << 24, PPC_RAW_TRAP());
+	u32 inst32 = PPC_RAW_NOP();
+
+	buf = vzalloc(PAGE_SIZE * 8);
+	check(buf);
+	if (!buf)
+		return;
+
+	/* Test single page 32-bit repeated instruction */
+	addr32 = buf + PAGE_SIZE;
+	check(!patch_instructions(addr32 + 1, &inst32, 12, true));
+
+	check(addr32[0] == 0);
+	check(addr32[1] == inst32);
+	check(addr32[2] == inst32);
+	check(addr32[3] == inst32);
+	check(addr32[4] == 0);
+
+	/* Test single page 64-bit repeated instruction */
+	if (IS_ENABLED(CONFIG_PPC64)) {
+		check(ppc_inst_prefixed(inst64));
+
+		addr64 = buf + PAGE_SIZE * 2;
+		ppc_inst_write(code, inst64);
+		check(!patch_instructions((u32 *)(addr64 + 1), code, 24, true));
+
+		check(addr64[0] == 0);
+		check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[1]), inst64));
+		check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[2]), inst64));
+		check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[3]), inst64));
+		check(addr64[4] == 0);
+	}
+
+	/* Test single page memcpy */
+	addr32 = buf + PAGE_SIZE * 3;
+
+	for (int i = 0; i < ARRAY_SIZE(code); i++)
+		code[i] = i + 1;
+
+	check(!patch_instructions(addr32 + 1, code, sizeof(code), false));
+
+	check(addr32[0] == 0);
+	check(!memcmp(&addr32[1], code, sizeof(code)));
+	check(addr32[ARRAY_SIZE(code) + 1] == 0);
+
+	/* Test multipage 32-bit repeated instruction */
+	addr32 = buf + PAGE_SIZE * 4 - 8;
+	check(!patch_instructions(addr32 + 1, &inst32, 12, true));
+
+	check(addr32[0] == 0);
+	check(addr32[1] == inst32);
+	check(addr32[2] == inst32);
+	check(addr32[3] == inst32);
+	check(addr32[4] == 0);
+
+	/* Test multipage 64-bit repeated instruction */
+	if (IS_ENABLED(CONFIG_PPC64)) {
+		check(ppc_inst_prefixed(inst64));
+
+		addr64 = buf + PAGE_SIZE * 5 - 8;
+		ppc_inst_write(code, inst64);
+		check(!patch_instructions((u32 *)(addr64 + 1), code, 24, true));
+
+		check(addr64[0] == 0);
+		check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[1]), inst64));
+		check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[2]), inst64));
+		check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[3]), inst64));
+		check(addr64[4] == 0);
+	}
+
+	/* Test multipage memcpy */
+	addr32 = buf + PAGE_SIZE * 6 - 12;
+
+	for (int i = 0; i < ARRAY_SIZE(code); i++)
+		code[i] = i + 1;
+
+	check(!patch_instructions(addr32 + 1, code, sizeof(code), false));
+
+	check(addr32[0] == 0);
+	check(!memcmp(&addr32[1], code, sizeof(code)));
+	check(addr32[ARRAY_SIZE(code) + 1] == 0);
+
+	vfree(buf);
+}
+
+static void __init test_data_patching(void)
+{
+	void *buf;
+	u32 *addr32;
+
+	buf = vzalloc(PAGE_SIZE);
+	check(buf);
+	if (!buf)
+		return;
+
+	addr32 = buf + 128;
+
+	addr32[1] = 0xA0A1A2A3;
+	addr32[2] = 0xB0B1B2B3;
+
+	check(!patch_uint(&addr32[1], 0xC0C1C2C3));
+
+	check(addr32[0] == 0);
+	check(addr32[1] == 0xC0C1C2C3);
+	check(addr32[2] == 0xB0B1B2B3);
+	check(addr32[3] == 0);
+
+	/* Unaligned patch_ulong() should fail */
+	if (IS_ENABLED(CONFIG_PPC64))
+		check(patch_ulong(&addr32[1], 0xD0D1D2D3) == -EINVAL);
+
+	check(!patch_ulong(&addr32[2], 0xD0D1D2D3));
+
+	check(addr32[0] == 0);
+	check(addr32[1] == 0xC0C1C2C3);
+	check(*(unsigned long *)(&addr32[2]) == 0xD0D1D2D3);
+
+	if (!IS_ENABLED(CONFIG_PPC64))
+		check(addr32[3] == 0);
+
+	check(addr32[4] == 0);
+
+	vfree(buf);
+}
+
 static int __init test_code_patching(void)
 {
 	pr_info("Running code patching self-tests ...\n");
@@ -356,6 +487,8 @@ static int __init test_code_patching(void)
 	test_create_function_call();
 	test_translate_branch();
 	test_prefixed_patching();
+	test_multi_instruction_patching();
+	test_data_patching();
 
 	return 0;
 }
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 23c7805fb7b3..66b5b4fa1686 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -11,7 +11,7 @@
 #include <asm/cpu_has_feature.h>
 #include <asm/sstep.h>
 #include <asm/ppc-opcode.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/inst.h>
 
 #define MAX_SUBTESTS	16
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index d491da8d1838..54340912398f 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -45,7 +45,7 @@ int exit_vmx_usercopy(void)
 	 * set and we are preemptible. The hack here is to schedule a
 	 * decrementer to fire here and reschedule for us if necessary.
 	 */
-	if (IS_ENABLED(CONFIG_PREEMPT) && need_resched())
+	if (need_irq_preemption() && need_resched())
 		set_dec(1);
 	return 0;
 }
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 503a6e249940..8c1582b2987d 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -3,8 +3,6 @@
 # Makefile for the linux ppc-specific parts of the memory manager.
 #
 
-ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
-
 obj-y				:= fault.o mem.o pgtable.o maccess.o pageattr.o \
 				   init_$(BITS).o pgtable_$(BITS).o \
 				   pgtable-frag.o ioremap.o ioremap_$(BITS).o \
@@ -17,5 +15,5 @@ obj-$(CONFIG_NUMA) += numa.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
-obj-$(CONFIG_PTDUMP_CORE)	+= ptdump/
+obj-$(CONFIG_PTDUMP)		+= ptdump/
 obj-$(CONFIG_KASAN)		+= kasan/
diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S
index 6925ce998557..4ed0efd03db5 100644
--- a/arch/powerpc/mm/book3s32/hash_low.S
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -14,6 +14,7 @@
  *  hash table, so this file is not used on them.)
  */
 
+#include <linux/export.h>
 #include <linux/pgtable.h>
 #include <linux/init.h>
 #include <asm/reg.h>
@@ -22,7 +23,6 @@
 #include <asm/ppc_asm.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/feature-fixups.h>
 #include <asm/code-patching-asm.h>
 
@@ -36,8 +36,9 @@
 
 /*
  * Load a PTE into the hash table, if possible.
- * The address is in r4, and r3 contains an access flag:
- * _PAGE_RW (0x400) if a write.
+ * The address is in r4, and r3 contains required access flags:
+ *   - For ISI: _PAGE_PRESENT | _PAGE_EXEC
+ *   - For DSI: _PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE if a write.
  * r9 contains the SRR1 value, from which we use the MSR_PR bit.
  * SPRG_THREAD contains the physical address of the current task's thread.
  *
@@ -67,12 +68,16 @@ _GLOBAL(hash_page)
 	lis	r0, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r4,r0
 	mfspr	r8,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
-	ori	r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
 	lwz	r5,PGDIR(r8)		/* virt page-table root */
 	blt+	112f			/* assume user more likely */
 	lis	r5,swapper_pg_dir@ha	/* if kernel address, use */
+	andi.	r0,r9,MSR_PR		/* Check usermode */
 	addi	r5,r5,swapper_pg_dir@l	/* kernel page table */
-	rlwimi	r3,r9,32-12,29,29	/* MSR_PR -> _PAGE_USER */
+#ifdef CONFIG_SMP
+	bne-	.Lhash_page_out		/* return if usermode */
+#else
+	bnelr-
+#endif
 112:	tophys(r5, r5)
 #ifndef CONFIG_PTE_64BIT
 	rlwimi	r5,r4,12,20,29		/* insert top 10 bits of address */
@@ -113,15 +118,15 @@ _GLOBAL(hash_page)
 	lwarx	r6,0,r8			/* get linux-style pte, flag word */
 #ifdef CONFIG_PPC_KUAP
 	mfsrin	r5,r4
-	rlwinm	r0,r9,28,_PAGE_RW	/* MSR[PR] => _PAGE_RW */
-	rlwinm	r5,r5,12,_PAGE_RW	/* Ks => _PAGE_RW */
+	rlwinm	r0,r9,28,_PAGE_WRITE	/* MSR[PR] => _PAGE_WRITE */
+	rlwinm	r5,r5,12,_PAGE_WRITE	/* Ks => _PAGE_WRITE */
 	andc	r5,r5,r0		/* Ks & ~MSR[PR] */
-	andc	r5,r6,r5		/* Clear _PAGE_RW when Ks = 1 && MSR[PR] = 0 */
+	andc	r5,r6,r5		/* Clear _PAGE_WRITE when Ks = 1 && MSR[PR] = 0 */
 	andc.	r5,r3,r5		/* check access & ~permission */
 #else
 	andc.	r5,r3,r6		/* check access & ~permission */
 #endif
-	rlwinm	r0,r3,32-3,24,24	/* _PAGE_RW access -> _PAGE_DIRTY */
+	rlwinm	r0,r3,32-3,24,24	/* _PAGE_WRITE access -> _PAGE_DIRTY */
 	ori	r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE
 #ifdef CONFIG_SMP
 	bne-	.Lhash_page_out		/* return if access not permitted */
@@ -199,12 +204,12 @@ _GLOBAL(add_hash_page)
 	lis	r6, (mmu_hash_lock - PAGE_OFFSET)@ha
 	addi	r6, r6, (mmu_hash_lock - PAGE_OFFSET)@l
 10:	lwarx	r0,0,r6			/* take the mmu_hash_lock */
-	cmpi	0,r0,0
+	cmpwi	0,r0,0
 	bne-	11f
 	stwcx.	r8,0,r6
 	beq+	12f
 11:	lwz	r0,0(r6)
-	cmpi	0,r0,0
+	cmpwi	0,r0,0
 	beq	10b
 	b	11b
 12:	isync
@@ -307,12 +312,15 @@ Hash_msk = (((1 << Hash_bits) - 1) * 64)
 __REF
 _GLOBAL(create_hpte)
 	/* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */
-	rlwinm	r8,r5,32-9,30,30	/* _PAGE_RW -> PP msb */
+	lis	r0, TASK_SIZE@h
+	rlwinm	r5,r5,0,~3		/* Clear PP bits */
+	cmplw	r4,r0
+	rlwinm	r8,r5,32-9,30,30	/* _PAGE_WRITE -> PP msb */
 	rlwinm	r0,r5,32-6,30,30	/* _PAGE_DIRTY -> PP msb */
 	and	r8,r8,r0		/* writable if _RW & _DIRTY */
-	rlwimi	r5,r5,32-1,30,30	/* _PAGE_USER -> PP msb */
-	rlwimi	r5,r5,32-2,31,31	/* _PAGE_USER -> PP lsb */
-	ori	r8,r8,0xe04		/* clear out reserved bits */
+	bge-	1f			/* Kernelspace ? Skip */
+	ori	r5,r5,3			/* Userspace ? PP = 3 */
+1:	ori	r8,r8,0xe04		/* clear out reserved bits */
 	andc	r8,r5,r8		/* PP = user? (rw&dirty? 1: 3): 0 */
 BEGIN_FTR_SECTION
 	rlwinm	r8,r8,0,~_PAGE_COHERENT	/* clear M (coherence not required) */
@@ -512,12 +520,12 @@ _GLOBAL(flush_hash_pages)
 	lwz	r8, TASK_CPU(r8)
 	oris	r8,r8,9
 10:	lwarx	r0,0,r9
-	cmpi	0,r0,0
+	cmpwi	0,r0,0
 	bne-	11f
 	stwcx.	r8,0,r9
 	beq+	12f
 11:	lwz	r0,0(r9)
-	cmpi	0,r0,0
+	cmpwi	0,r0,0
 	beq	10b
 	b	11b
 12:	isync
diff --git a/arch/powerpc/mm/book3s32/kuap.c b/arch/powerpc/mm/book3s32/kuap.c
index 28676cabb005..3a8815555a48 100644
--- a/arch/powerpc/mm/book3s32/kuap.c
+++ b/arch/powerpc/mm/book3s32/kuap.c
@@ -3,25 +3,11 @@
 #include <asm/kup.h>
 #include <asm/smp.h>
 
-struct static_key_false disable_kuap_key;
-EXPORT_SYMBOL(disable_kuap_key);
-
-void kuap_lock_all_ool(void)
-{
-	kuap_lock_all();
-}
-EXPORT_SYMBOL(kuap_lock_all_ool);
-
-void kuap_unlock_all_ool(void)
-{
-	kuap_unlock_all();
-}
-EXPORT_SYMBOL(kuap_unlock_all_ool);
-
 void setup_kuap(bool disabled)
 {
 	if (!disabled) {
-		kuap_lock_all_ool();
+		update_user_segments(mfsr(0) | SR_KS);
+		isync();        /* Context sync required after mtsr() */
 		init_mm.context.sr0 |= SR_KS;
 		current->thread.sr0 |= SR_KS;
 	}
@@ -30,7 +16,7 @@ void setup_kuap(bool disabled)
 		return;
 
 	if (disabled)
-		static_branch_enable(&disable_kuap_key);
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_KUAP;
 	else
 		pr_info("Activating Kernel Userspace Access Protection\n");
 }
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 850783cfa9c7..c42ecdf94e48 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -25,7 +25,7 @@
 
 #include <asm/mmu.h>
 #include <asm/machdep.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/sections.h>
 
 #include <mm/mmu_decl.h>
@@ -127,7 +127,7 @@ static void setibat(int index, unsigned long virt, phys_addr_t phys,
 	wimgxpp = (flags & _PAGE_COHERENT) | (_PAGE_EXEC ? BPP_RX : BPP_XX);
 	bat[0].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */
 	bat[0].batl = BAT_PHYS_ADDR(phys) | wimgxpp;
-	if (flags & _PAGE_USER)
+	if (!is_kernel_addr(virt))
 		bat[0].batu |= 1;	/* Vp = 1 */
 }
 
@@ -184,7 +184,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 
 static bool is_module_segment(unsigned long addr)
 {
-	if (!IS_ENABLED(CONFIG_MODULES))
+	if (!IS_ENABLED(CONFIG_EXECMEM))
 		return false;
 	if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M))
 		return false;
@@ -193,7 +193,7 @@ static bool is_module_segment(unsigned long addr)
 	return true;
 }
 
-void mmu_mark_initmem_nx(void)
+int mmu_mark_initmem_nx(void)
 {
 	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
 	int i;
@@ -204,7 +204,7 @@ void mmu_mark_initmem_nx(void)
 
 	for (i = 0; i < nb - 1 && base < top;) {
 		size = bat_block_size(base, top);
-		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_X);
 		base += size;
 	}
 	if (base < top) {
@@ -215,7 +215,7 @@ void mmu_mark_initmem_nx(void)
 				pr_warn("Some RW data is getting mapped X. "
 					"Adjust CONFIG_DATA_SHIFT to avoid that.\n");
 		}
-		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_X);
 		base += size;
 	}
 	for (; i < nb; i++)
@@ -223,6 +223,8 @@ void mmu_mark_initmem_nx(void)
 
 	update_bats();
 
+	BUILD_BUG_ON(ALIGN_DOWN(MODULES_VADDR, SZ_256M) < TASK_SIZE);
+
 	for (i = TASK_SIZE >> 28; i < 16; i++) {
 		/* Do not set NX on VM space for modules */
 		if (is_module_segment(i << 28))
@@ -230,9 +232,10 @@ void mmu_mark_initmem_nx(void)
 
 		mtsr(mfsr(i << 28) | 0x10000000, i << 28);
 	}
+	return 0;
 }
 
-void mmu_mark_rodata_ro(void)
+int mmu_mark_rodata_ro(void)
 {
 	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
 	int i;
@@ -245,6 +248,8 @@ void mmu_mark_rodata_ro(void)
 	}
 
 	update_bats();
+
+	return 0;
 }
 
 /*
@@ -277,10 +282,10 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys,
 	/* Do DBAT first */
 	wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
 			   | _PAGE_COHERENT | _PAGE_GUARDED);
-	wimgxpp |= (flags & _PAGE_RW)? BPP_RW: BPP_RX;
+	wimgxpp |= (flags & _PAGE_WRITE) ? BPP_RW : BPP_RX;
 	bat[1].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */
 	bat[1].batl = BAT_PHYS_ADDR(phys) | wimgxpp;
-	if (flags & _PAGE_USER)
+	if (!is_kernel_addr(virt))
 		bat[1].batu |= 1; 	/* Vp = 1 */
 	if (flags & _PAGE_GUARDED) {
 		/* G bit must be zero in IBATs */
@@ -372,10 +377,7 @@ void __init MMU_init_hw(void)
 	 * Find some memory for the hash table.
 	 */
 	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
-	Hash = memblock_alloc(Hash_size, Hash_size);
-	if (!Hash)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, Hash_size, Hash_size);
+	Hash = memblock_alloc_or_panic(Hash_size, Hash_size);
 	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
 
 	pr_info("Total memory = %lldMB; using %ldkB for hash table\n",
diff --git a/arch/powerpc/mm/book3s32/mmu_context.c b/arch/powerpc/mm/book3s32/mmu_context.c
index 269a3eb25a73..1922f9a6b058 100644
--- a/arch/powerpc/mm/book3s32/mmu_context.c
+++ b/arch/powerpc/mm/book3s32/mmu_context.c
@@ -71,7 +71,7 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm)
 	mm->context.id = __init_new_context();
 	mm->context.sr0 = CTX_TO_VSID(mm->context.id, 0);
 
-	if (!kuep_is_disabled())
+	if (IS_ENABLED(CONFIG_PPC_KUEP))
 		mm->context.sr0 |= SR_NX;
 	if (!kuap_is_disabled())
 		mm->context.sr0 |= SR_KS;
diff --git a/arch/powerpc/mm/book3s32/tlb.c b/arch/powerpc/mm/book3s32/tlb.c
index 9ad6b56bfec9..e54a7b011232 100644
--- a/arch/powerpc/mm/book3s32/tlb.c
+++ b/arch/powerpc/mm/book3s32/tlb.c
@@ -105,3 +105,12 @@ void hash__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 		flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1);
 }
 EXPORT_SYMBOL(hash__flush_tlb_page);
+
+void hash__flush_gather(struct mmu_gather *tlb)
+{
+	if (tlb->fullmm || tlb->need_flush_all)
+		hash__flush_tlb_mm(tlb->mm);
+	else
+		hash__flush_range(tlb->mm, tlb->start, tlb->end);
+}
+EXPORT_SYMBOL(hash__flush_gather);
diff --git a/arch/powerpc/mm/book3s64/Makefile b/arch/powerpc/mm/book3s64/Makefile
index cad2abc1730f..33af5795856a 100644
--- a/arch/powerpc/mm/book3s64/Makefile
+++ b/arch/powerpc/mm/book3s64/Makefile
@@ -1,7 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
-ccflags-y	:= $(NO_MINIMAL_TOC)
-
 obj-y				+= mmu_context.o pgtable.o trace.o
 ifdef CONFIG_PPC_64S_HASH_MMU
 CFLAGS_REMOVE_slb.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/powerpc/mm/book3s64/hash_hugepage.c b/arch/powerpc/mm/book3s64/hash_hugepage.c
index c0fabe6c5a12..cdfd4fe75edb 100644
--- a/arch/powerpc/mm/book3s64/hash_hugepage.c
+++ b/arch/powerpc/mm/book3s64/hash_hugepage.c
@@ -54,21 +54,18 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	/*
 	 * Make sure this is thp or devmap entry
 	 */
-	if (!(old_pmd & (H_PAGE_THP_HUGE | _PAGE_DEVMAP)))
+	if (!(old_pmd & H_PAGE_THP_HUGE))
 		return 0;
 
 	rflags = htab_convert_pte_flags(new_pmd, flags);
 
-#if 0
-	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {
+	/*
+	 * THPs are only supported on platforms that can do mixed page size
+	 * segments (MPSS) and all such platforms have coherent icache. Hence we
+	 * don't need to do lazy icache flush (hash_page_do_lazy_icache()) on
+	 * noexecute fault.
+	 */
 
-		/*
-		 * No CPU has hugepages but lacks no execute, so we
-		 * don't need to worry about that case
-		 */
-		rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap);
-	}
-#endif
 	/*
 	 * Find the slot index details for this ea, using base page size.
 	 */
diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c
index 9342e79870df..e9e2dd70c060 100644
--- a/arch/powerpc/mm/book3s64/hash_native.c
+++ b/arch/powerpc/mm/book3s64/hash_native.c
@@ -27,8 +27,6 @@
 #include <asm/ppc-opcode.h>
 #include <asm/feature-fixups.h>
 
-#include <misc/cxl-base.h>
-
 #ifdef DEBUG_LOW
 #define DBG_LOW(fmt...) udbg_printf(fmt)
 #else
@@ -217,11 +215,9 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 static inline void tlbie(unsigned long vpn, int psize, int apsize,
 			 int ssize, int local)
 {
-	unsigned int use_local;
+	unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
-	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) && !cxl_ctx_in_use();
-
 	if (use_local)
 		use_local = mmu_psize_defs[psize].tlbiel;
 	if (lock_tlbie && !use_local)
@@ -328,10 +324,12 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 
 static long native_hpte_remove(unsigned long hpte_group)
 {
+	unsigned long hpte_v, flags;
 	struct hash_pte *hptep;
 	int i;
 	int slot_offset;
-	unsigned long hpte_v;
+
+	local_irq_save(flags);
 
 	DBG_LOW("    remove(group=%lx)\n", hpte_group);
 
@@ -356,13 +354,16 @@ static long native_hpte_remove(unsigned long hpte_group)
 		slot_offset &= 0x7;
 	}
 
-	if (i == HPTES_PER_GROUP)
-		return -1;
+	if (i == HPTES_PER_GROUP) {
+		i = -1;
+		goto out;
+	}
 
 	/* Invalidate the hpte. NOTE: this also unlocks it */
 	release_hpte_lock();
 	hptep->v = 0;
-
+out:
+	local_irq_restore(flags);
 	return i;
 }
 
@@ -784,10 +785,6 @@ static void native_flush_hash_range(unsigned long number, int local)
 	unsigned long psize = batch->psize;
 	int ssize = batch->ssize;
 	int i;
-	unsigned int use_local;
-
-	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
-		mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
 
 	local_irq_save(flags);
 
@@ -822,7 +819,8 @@ static void native_flush_hash_range(unsigned long number, int local)
 		} pte_iterate_hashed_end();
 	}
 
-	if (use_local) {
+	if (mmu_has_feature(MMU_FTR_TLBIEL) &&
+	    mmu_psize_defs[psize].tlbiel && local) {
 		asm volatile("ptesync":::"memory");
 		for (i = 0; i < number; i++) {
 			vpn = batch->vpn[i];
diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c
index 51f48984abca..82d31177630b 100644
--- a/arch/powerpc/mm/book3s64/hash_pgtable.c
+++ b/arch/powerpc/mm/book3s64/hash_pgtable.c
@@ -195,7 +195,7 @@ unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr
 	unsigned long old;
 
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(!hash__pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
+	WARN_ON(!hash__pmd_trans_huge(*pmdp));
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
 #endif
 
@@ -214,7 +214,7 @@ unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr
 
 	old = be64_to_cpu(old_be);
 
-	trace_hugepage_update(addr, old, clr, set);
+	trace_hugepage_update_pmd(addr, old, clr, set);
 	if (old & H_PAGE_HASHPTE)
 		hpte_do_hugepage_flush(mm, addr, pmdp, old);
 	return old;
@@ -227,7 +227,6 @@ pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addres
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(pmd_trans_huge(*pmdp));
-	VM_BUG_ON(pmd_devmap(*pmdp));
 
 	pmd = *pmdp;
 	pmd_clear(pmdp);
diff --git a/arch/powerpc/mm/book3s64/hash_tlb.c b/arch/powerpc/mm/book3s64/hash_tlb.c
index a64ea0a7ef96..21fcad97ae80 100644
--- a/arch/powerpc/mm/book3s64/hash_tlb.c
+++ b/arch/powerpc/mm/book3s64/hash_tlb.c
@@ -239,12 +239,16 @@ void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long
 	local_irq_save(flags);
 	arch_enter_lazy_mmu_mode();
 	start_pte = pte_offset_map(pmd, addr);
+	if (!start_pte)
+		goto out;
 	for (pte = start_pte; pte < start_pte + PTRS_PER_PTE; pte++) {
 		unsigned long pteval = pte_val(*pte);
 		if (pteval & H_PAGE_HASHPTE)
 			hpte_need_flush(mm, addr, pte, pteval, 0);
 		addr += PAGE_SIZE;
 	}
+	pte_unmap(start_pte);
+out:
 	arch_leave_lazy_mmu_mode();
 	local_irq_restore(flags);
 }
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index fedffe3ae136..9dc5889d6ecb 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -40,12 +40,14 @@
 #include <linux/random.h>
 #include <linux/elf-randomize.h>
 #include <linux/of_fdt.h>
+#include <linux/kfence.h>
 
 #include <asm/interrupt.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
+#include <asm/pgalloc.h>
 #include <asm/types.h>
 #include <linux/uaccess.h>
 #include <asm/machdep.h>
@@ -55,9 +57,9 @@
 #include <asm/cacheflush.h>
 #include <asm/cputable.h>
 #include <asm/sections.h>
-#include <asm/copro.h>
+#include <asm/spu.h>
 #include <asm/udbg.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/fadump.h>
 #include <asm/firmware.h>
 #include <asm/tm.h>
@@ -66,6 +68,7 @@
 #include <asm/pte-walk.h>
 #include <asm/asm-prototypes.h>
 #include <asm/ultravisor.h>
+#include <asm/kfence.h>
 
 #include <mm/mmu_decl.h>
 
@@ -123,9 +126,7 @@ EXPORT_SYMBOL_GPL(mmu_slb_size);
 #ifdef CONFIG_PPC_64K_PAGES
 int mmu_ci_restrictions;
 #endif
-static u8 *linear_map_hash_slots;
-static unsigned long linear_map_hash_count;
-struct mmu_hash_ops mmu_hash_ops;
+struct mmu_hash_ops mmu_hash_ops __ro_after_init;
 EXPORT_SYMBOL(mmu_hash_ops);
 
 /*
@@ -273,6 +274,272 @@ void hash__tlbiel_all(unsigned int action)
 		WARN(1, "%s called on pre-POWER7 CPU\n", __func__);
 }
 
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+static void kernel_map_linear_page(unsigned long vaddr, unsigned long idx,
+				   u8 *slots, raw_spinlock_t *lock)
+{
+	unsigned long hash;
+	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
+	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
+	unsigned long mode = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL), HPTE_USE_KERNEL_KEY);
+	long ret;
+
+	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
+
+	/* Don't create HPTE entries for bad address */
+	if (!vsid)
+		return;
+
+	if (slots[idx] & 0x80)
+		return;
+
+	ret = hpte_insert_repeating(hash, vpn, __pa(vaddr), mode,
+				    HPTE_V_BOLTED,
+				    mmu_linear_psize, mmu_kernel_ssize);
+
+	BUG_ON (ret < 0);
+	raw_spin_lock(lock);
+	BUG_ON(slots[idx] & 0x80);
+	slots[idx] = ret | 0x80;
+	raw_spin_unlock(lock);
+}
+
+static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long idx,
+				     u8 *slots, raw_spinlock_t *lock)
+{
+	unsigned long hash, hslot, slot;
+	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
+	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
+
+	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
+	raw_spin_lock(lock);
+	if (!(slots[idx] & 0x80)) {
+		raw_spin_unlock(lock);
+		return;
+	}
+	hslot = slots[idx] & 0x7f;
+	slots[idx] = 0;
+	raw_spin_unlock(lock);
+	if (hslot & _PTEIDX_SECONDARY)
+		hash = ~hash;
+	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+	slot += hslot & _PTEIDX_GROUP_IX;
+	mmu_hash_ops.hpte_invalidate(slot, vpn, mmu_linear_psize,
+				     mmu_linear_psize,
+				     mmu_kernel_ssize, 0);
+}
+#endif
+
+static inline bool hash_supports_debug_pagealloc(void)
+{
+	unsigned long max_hash_count = ppc64_rma_size / 4;
+	unsigned long linear_map_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
+
+	if (!debug_pagealloc_enabled() || linear_map_count > max_hash_count)
+		return false;
+	return true;
+}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+static u8 *linear_map_hash_slots;
+static unsigned long linear_map_hash_count;
+static DEFINE_RAW_SPINLOCK(linear_map_hash_lock);
+static __init void hash_debug_pagealloc_alloc_slots(void)
+{
+	if (!hash_supports_debug_pagealloc())
+		return;
+
+	linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
+	linear_map_hash_slots = memblock_alloc_try_nid(
+			linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT,
+			ppc64_rma_size,	NUMA_NO_NODE);
+	if (!linear_map_hash_slots)
+		panic("%s: Failed to allocate %lu bytes max_addr=%pa\n",
+		      __func__, linear_map_hash_count, &ppc64_rma_size);
+}
+
+static inline void hash_debug_pagealloc_add_slot(phys_addr_t paddr,
+							int slot)
+{
+	if (!debug_pagealloc_enabled() || !linear_map_hash_count)
+		return;
+	if ((paddr >> PAGE_SHIFT) < linear_map_hash_count)
+		linear_map_hash_slots[paddr >> PAGE_SHIFT] = slot | 0x80;
+}
+
+static int hash_debug_pagealloc_map_pages(struct page *page, int numpages,
+					  int enable)
+{
+	unsigned long flags, vaddr, lmi;
+	int i;
+
+	if (!debug_pagealloc_enabled() || !linear_map_hash_count)
+		return 0;
+
+	local_irq_save(flags);
+	for (i = 0; i < numpages; i++, page++) {
+		vaddr = (unsigned long)page_address(page);
+		lmi = __pa(vaddr) >> PAGE_SHIFT;
+		if (lmi >= linear_map_hash_count)
+			continue;
+		if (enable)
+			kernel_map_linear_page(vaddr, lmi,
+				linear_map_hash_slots, &linear_map_hash_lock);
+		else
+			kernel_unmap_linear_page(vaddr, lmi,
+				linear_map_hash_slots, &linear_map_hash_lock);
+	}
+	local_irq_restore(flags);
+	return 0;
+}
+
+#else /* CONFIG_DEBUG_PAGEALLOC */
+static inline void hash_debug_pagealloc_alloc_slots(void) {}
+static inline void hash_debug_pagealloc_add_slot(phys_addr_t paddr, int slot) {}
+static int __maybe_unused
+hash_debug_pagealloc_map_pages(struct page *page, int numpages, int enable)
+{
+	return 0;
+}
+#endif /* CONFIG_DEBUG_PAGEALLOC */
+
+#ifdef CONFIG_KFENCE
+static u8 *linear_map_kf_hash_slots;
+static unsigned long linear_map_kf_hash_count;
+static DEFINE_RAW_SPINLOCK(linear_map_kf_hash_lock);
+
+static phys_addr_t kfence_pool;
+
+static __init void hash_kfence_alloc_pool(void)
+{
+	if (!kfence_early_init_enabled())
+		goto err;
+
+	/* allocate linear map for kfence within RMA region */
+	linear_map_kf_hash_count = KFENCE_POOL_SIZE >> PAGE_SHIFT;
+	linear_map_kf_hash_slots = memblock_alloc_try_nid(
+					linear_map_kf_hash_count, 1,
+					MEMBLOCK_LOW_LIMIT, ppc64_rma_size,
+					NUMA_NO_NODE);
+	if (!linear_map_kf_hash_slots) {
+		pr_err("%s: memblock for linear map (%lu) failed\n", __func__,
+				linear_map_kf_hash_count);
+		goto err;
+	}
+
+	/* allocate kfence pool early */
+	kfence_pool = memblock_phys_alloc_range(KFENCE_POOL_SIZE, PAGE_SIZE,
+				MEMBLOCK_LOW_LIMIT, MEMBLOCK_ALLOC_ANYWHERE);
+	if (!kfence_pool) {
+		pr_err("%s: memblock for kfence pool (%lu) failed\n", __func__,
+				KFENCE_POOL_SIZE);
+		memblock_free(linear_map_kf_hash_slots,
+				linear_map_kf_hash_count);
+		linear_map_kf_hash_count = 0;
+		goto err;
+	}
+	memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE);
+
+	return;
+err:
+	pr_info("Disabling kfence\n");
+	disable_kfence();
+}
+
+static __init void hash_kfence_map_pool(void)
+{
+	unsigned long kfence_pool_start, kfence_pool_end;
+	unsigned long prot = pgprot_val(PAGE_KERNEL);
+	unsigned int pshift = mmu_psize_defs[mmu_linear_psize].shift;
+
+	if (!kfence_pool)
+		return;
+
+	kfence_pool_start = (unsigned long) __va(kfence_pool);
+	kfence_pool_end = kfence_pool_start + KFENCE_POOL_SIZE;
+	__kfence_pool = (char *) kfence_pool_start;
+	BUG_ON(htab_bolt_mapping(kfence_pool_start, kfence_pool_end,
+				    kfence_pool, prot, mmu_linear_psize,
+				    mmu_kernel_ssize));
+	update_page_count(mmu_linear_psize, KFENCE_POOL_SIZE >> pshift);
+	memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
+}
+
+static inline void hash_kfence_add_slot(phys_addr_t paddr, int slot)
+{
+	unsigned long vaddr = (unsigned long) __va(paddr);
+	unsigned long lmi = (vaddr - (unsigned long)__kfence_pool)
+					>> PAGE_SHIFT;
+
+	if (!kfence_pool)
+		return;
+	BUG_ON(!is_kfence_address((void *)vaddr));
+	BUG_ON(lmi >= linear_map_kf_hash_count);
+	linear_map_kf_hash_slots[lmi] = slot | 0x80;
+}
+
+static int hash_kfence_map_pages(struct page *page, int numpages, int enable)
+{
+	unsigned long flags, vaddr, lmi;
+	int i;
+
+	WARN_ON_ONCE(!linear_map_kf_hash_count);
+	local_irq_save(flags);
+	for (i = 0; i < numpages; i++, page++) {
+		vaddr = (unsigned long)page_address(page);
+		lmi = (vaddr - (unsigned long)__kfence_pool) >> PAGE_SHIFT;
+
+		/* Ideally this should never happen */
+		if (lmi >= linear_map_kf_hash_count) {
+			WARN_ON_ONCE(1);
+			continue;
+		}
+
+		if (enable)
+			kernel_map_linear_page(vaddr, lmi,
+					       linear_map_kf_hash_slots,
+					       &linear_map_kf_hash_lock);
+		else
+			kernel_unmap_linear_page(vaddr, lmi,
+						 linear_map_kf_hash_slots,
+						 &linear_map_kf_hash_lock);
+	}
+	local_irq_restore(flags);
+	return 0;
+}
+#else
+static inline void hash_kfence_alloc_pool(void) {}
+static inline void hash_kfence_map_pool(void) {}
+static inline void hash_kfence_add_slot(phys_addr_t paddr, int slot) {}
+static int __maybe_unused
+hash_kfence_map_pages(struct page *page, int numpages, int enable)
+{
+	return 0;
+}
+#endif
+
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+int hash__kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	void *vaddr = page_address(page);
+
+	if (is_kfence_address(vaddr))
+		return hash_kfence_map_pages(page, numpages, enable);
+	else
+		return hash_debug_pagealloc_map_pages(page, numpages, enable);
+}
+
+static void hash_linear_map_add_slot(phys_addr_t paddr, int slot)
+{
+	if (is_kfence_address(__va(paddr)))
+		hash_kfence_add_slot(paddr, slot);
+	else
+		hash_debug_pagealloc_add_slot(paddr, slot);
+}
+#else
+static void hash_linear_map_add_slot(phys_addr_t paddr, int slot) {}
+#endif
+
 /*
  * 'R' and 'C' update notes:
  *  - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
@@ -310,9 +577,16 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags
 			else
 				rflags |= 0x3;
 		}
+		VM_WARN_ONCE(!(pteflags & _PAGE_RWX), "no-access mapping request");
 	} else {
 		if (pteflags & _PAGE_RWX)
 			rflags |= 0x2;
+		/*
+		 * We should never hit this in normal fault handling because
+		 * a permission check (check_pte_access()) will bubble this
+		 * to higher level linux handler even for PAGE_NONE.
+		 */
+		VM_WARN_ONCE(!(pteflags & _PAGE_RWX), "no-access mapping request");
 		if (!((pteflags & _PAGE_WRITE) && (pteflags & _PAGE_DIRTY)))
 			rflags |= 0x1;
 	}
@@ -424,9 +698,8 @@ repeat:
 			break;
 
 		cond_resched();
-		if (debug_pagealloc_enabled_or_kfence() &&
-			(paddr >> PAGE_SHIFT) < linear_map_hash_count)
-			linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80;
+		/* add slot info in debug_pagealloc / kfence linear map */
+		hash_linear_map_add_slot(paddr, ret);
 	}
 	return ret < 0 ? ret : 0;
 }
@@ -682,7 +955,7 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
 	block_size = be64_to_cpu(addr_prop[1]);
 	if (block_size != (16 * GB))
 		return 0;
-	printk(KERN_INFO "Huge page(16GB) memory: "
+	pr_info("Huge page(16GB) memory: "
 			"addr = 0x%lX size = 0x%lX pages = %d\n",
 			phys_addr, block_size, expected_pages);
 	if (phys_addr + block_size * expected_pages <= memblock_end_of_DRAM()) {
@@ -807,7 +1080,7 @@ static void __init htab_init_page_sizes(void)
 	bool aligned = true;
 	init_hpte_page_sizes();
 
-	if (!debug_pagealloc_enabled_or_kfence()) {
+	if (!hash_supports_debug_pagealloc() && !kfence_early_init_enabled()) {
 		/*
 		 * Pick a size for the linear mapping. Currently, we only
 		 * support 16M, 1M and 4K which is the default
@@ -865,7 +1138,7 @@ static void __init htab_init_page_sizes(void)
 		mmu_vmemmap_psize = mmu_virtual_psize;
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
-	printk(KERN_DEBUG "Page orders: linear mapping = %d, "
+	pr_info("Page orders: linear mapping = %d, "
 	       "virtual = %d, io = %d"
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	       ", vmemmap = %d"
@@ -964,6 +1237,7 @@ int hash__create_section_mapping(unsigned long start, unsigned long end,
 				 int nid, pgprot_t prot)
 {
 	int rc;
+	unsigned int pshift = mmu_psize_defs[mmu_linear_psize].shift;
 
 	if (end >= H_VMALLOC_START) {
 		pr_warn("Outside the supported range\n");
@@ -981,17 +1255,22 @@ int hash__create_section_mapping(unsigned long start, unsigned long end,
 					      mmu_kernel_ssize);
 		BUG_ON(rc2 && (rc2 != -ENOENT));
 	}
+	update_page_count(mmu_linear_psize, (end - start) >> pshift);
 	return rc;
 }
 
 int hash__remove_section_mapping(unsigned long start, unsigned long end)
 {
+	unsigned int pshift = mmu_psize_defs[mmu_linear_psize].shift;
+
 	int rc = htab_remove_mapping(start, end, mmu_linear_psize,
 				     mmu_kernel_ssize);
 
 	if (resize_hpt_for_hotplug(memblock_phys_mem_size()) == -ENOSPC)
 		pr_warn("Hash collision while resizing HPT\n");
 
+	if (!rc)
+		update_page_count(mmu_linear_psize, -((end - start) >> pshift));
 	return rc;
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
@@ -1032,27 +1311,34 @@ static void __init htab_initialize(void)
 	unsigned long table;
 	unsigned long pteg_count;
 	unsigned long prot;
-	phys_addr_t base = 0, size = 0, end;
+	phys_addr_t base = 0, size = 0, end, limit = MEMBLOCK_ALLOC_ANYWHERE;
 	u64 i;
+	unsigned int pshift = mmu_psize_defs[mmu_linear_psize].shift;
 
 	DBG(" -> htab_initialize()\n");
 
+	if (firmware_has_feature(FW_FEATURE_LPAR))
+		limit = ppc64_rma_size;
+
 	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
 		mmu_kernel_ssize = MMU_SEGSIZE_1T;
 		mmu_highuser_ssize = MMU_SEGSIZE_1T;
-		printk(KERN_INFO "Using 1TB segments\n");
+		pr_info("Using 1TB segments\n");
 	}
 
 	if (stress_slb_enabled)
 		static_branch_enable(&stress_slb_key);
 
+	if (no_slb_preload)
+		static_branch_enable(&no_slb_preload_key);
+
 	if (stress_hpt_enabled) {
 		unsigned long tmp;
 		static_branch_enable(&stress_hpt_key);
 		// Too early to use nr_cpu_ids, so use NR_CPUS
 		tmp = memblock_phys_alloc_range(sizeof(struct stress_hpt_struct) * NR_CPUS,
 						__alignof__(struct stress_hpt_struct),
-						0, MEMBLOCK_ALLOC_ANYWHERE);
+						MEMBLOCK_LOW_LIMIT, limit);
 		memset((void *)tmp, 0xff, sizeof(struct stress_hpt_struct) * NR_CPUS);
 		stress_hpt_struct = __va(tmp);
 
@@ -1086,23 +1372,10 @@ static void __init htab_initialize(void)
 			mmu_hash_ops.hpte_clear_all();
 #endif
 	} else {
-		unsigned long limit = MEMBLOCK_ALLOC_ANYWHERE;
-
-#ifdef CONFIG_PPC_CELL
-		/*
-		 * Cell may require the hash table down low when using the
-		 * Axon IOMMU in order to fit the dynamic region over it, see
-		 * comments in cell/iommu.c
-		 */
-		if (fdt_subnode_offset(initial_boot_params, 0, "axon") > 0) {
-			limit = 0x80000000;
-			pr_info("Hash table forced below 2G for Axon IOMMU\n");
-		}
-#endif /* CONFIG_PPC_CELL */
 
 		table = memblock_phys_alloc_range(htab_size_bytes,
 						  htab_size_bytes,
-						  0, limit);
+						  MEMBLOCK_LOW_LIMIT, limit);
 		if (!table)
 			panic("ERROR: Failed to allocate %pa bytes below %pa\n",
 			      &htab_size_bytes, &limit);
@@ -1127,23 +1400,15 @@ static void __init htab_initialize(void)
 
 	prot = pgprot_val(PAGE_KERNEL);
 
-	if (debug_pagealloc_enabled_or_kfence()) {
-		linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
-		linear_map_hash_slots = memblock_alloc_try_nid(
-				linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT,
-				ppc64_rma_size,	NUMA_NO_NODE);
-		if (!linear_map_hash_slots)
-			panic("%s: Failed to allocate %lu bytes max_addr=%pa\n",
-			      __func__, linear_map_hash_count, &ppc64_rma_size);
-	}
-
+	hash_debug_pagealloc_alloc_slots();
+	hash_kfence_alloc_pool();
 	/* create bolted the linear mapping in the hash table */
 	for_each_mem_range(i, &base, &end) {
 		size = end - base;
 		base = (unsigned long)__va(base);
 
-		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
-		    base, size, prot);
+		pr_debug("creating mapping for region: 0x%pa..0x%pa (prot: %lx)\n",
+				&base, &size, prot);
 
 		if ((base + size) >= H_VMALLOC_START) {
 			pr_warn("Outside the supported range\n");
@@ -1152,7 +1417,10 @@ static void __init htab_initialize(void)
 
 		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
 				prot, mmu_linear_psize, mmu_kernel_ssize));
+
+		update_page_count(mmu_linear_psize, size >> pshift);
 	}
+	hash_kfence_map_pool();
 	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 
 	/*
@@ -1172,6 +1440,8 @@ static void __init htab_initialize(void)
 		BUG_ON(htab_bolt_mapping(tce_alloc_start, tce_alloc_end,
 					 __pa(tce_alloc_start), prot,
 					 mmu_linear_psize, mmu_kernel_ssize));
+		update_page_count(mmu_linear_psize,
+				  (tce_alloc_end - tce_alloc_start) >> pshift);
 	}
 
 
@@ -1226,10 +1496,6 @@ void __init hash__early_init_mmu(void)
 	__pmd_table_size = H_PMD_TABLE_SIZE;
 	__pud_table_size = H_PUD_TABLE_SIZE;
 	__pgd_table_size = H_PGD_TABLE_SIZE;
-	/*
-	 * 4k use hugepd format, so for hash set then to
-	 * zero
-	 */
 	__pmd_val_bits = HASH_PMD_VAL_BITS;
 	__pud_val_bits = HASH_PUD_VAL_BITS;
 	__pgd_val_bits = HASH_PGD_VAL_BITS;
@@ -1307,18 +1573,19 @@ void hash__early_init_mmu_secondary(void)
  */
 unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 {
-	struct page *page;
+	struct folio *folio;
 
 	if (!pfn_valid(pte_pfn(pte)))
 		return pp;
 
-	page = pte_page(pte);
+	folio = page_folio(pte_page(pte));
 
 	/* page is dirty */
-	if (!test_bit(PG_dcache_clean, &page->flags) && !PageReserved(page)) {
+	if (!test_bit(PG_dcache_clean, &folio->flags.f) &&
+	    !folio_test_reserved(folio)) {
 		if (trap == INTERRUPT_INST_STORAGE) {
-			flush_dcache_icache_page(page);
-			set_bit(PG_dcache_clean, &page->flags);
+			flush_dcache_icache_folio(folio);
+			set_bit(PG_dcache_clean, &folio->flags.f);
 		} else
 			pp |= HPTE_R_N;
 	}
@@ -1352,7 +1619,9 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
 	if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
 		return;
 	slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
-	copro_flush_all_slbs(mm);
+#ifdef CONFIG_SPU_BASE
+	spu_flush_all_slbs(mm);
+#endif
 	if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {
 
 		copy_mm_to_paca(mm);
@@ -1538,6 +1807,13 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		goto bail;
 	}
 
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled()) {
+		if (hugeshift == PMD_SHIFT && psize == MMU_PAGE_16M)
+			hugeshift = mmu_psize_defs[MMU_PAGE_16M].shift;
+		if (hugeshift == PUD_SHIFT && psize == MMU_PAGE_16G)
+			hugeshift = mmu_psize_defs[MMU_PAGE_16G].shift;
+	}
+
 	/*
 	 * Add _PAGE_PRESENT to the required access perm. If there are parallel
 	 * updates to the pte that can possibly clear _PAGE_PTE, catch that too.
@@ -1610,11 +1886,13 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 			 * in vmalloc space, so switch vmalloc
 			 * to 4k pages
 			 */
-			printk(KERN_ALERT "Reducing vmalloc segment "
+			pr_alert("Reducing vmalloc segment "
 			       "to 4kB pages because of "
 			       "non-cacheable mapping\n");
 			psize = mmu_vmalloc_psize = MMU_PAGE_4K;
-			copro_flush_all_slbs(mm);
+#ifdef CONFIG_SPU_BASE
+			spu_flush_all_slbs(mm);
+#endif
 		}
 	}
 
@@ -2109,81 +2387,6 @@ void hpt_do_stress(unsigned long ea, unsigned long hpte_group)
 	}
 }
 
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-static DEFINE_RAW_SPINLOCK(linear_map_hash_lock);
-
-static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
-{
-	unsigned long hash;
-	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
-	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
-	unsigned long mode = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL), HPTE_USE_KERNEL_KEY);
-	long ret;
-
-	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
-
-	/* Don't create HPTE entries for bad address */
-	if (!vsid)
-		return;
-
-	if (linear_map_hash_slots[lmi] & 0x80)
-		return;
-
-	ret = hpte_insert_repeating(hash, vpn, __pa(vaddr), mode,
-				    HPTE_V_BOLTED,
-				    mmu_linear_psize, mmu_kernel_ssize);
-
-	BUG_ON (ret < 0);
-	raw_spin_lock(&linear_map_hash_lock);
-	BUG_ON(linear_map_hash_slots[lmi] & 0x80);
-	linear_map_hash_slots[lmi] = ret | 0x80;
-	raw_spin_unlock(&linear_map_hash_lock);
-}
-
-static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
-{
-	unsigned long hash, hidx, slot;
-	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
-	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
-
-	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
-	raw_spin_lock(&linear_map_hash_lock);
-	if (!(linear_map_hash_slots[lmi] & 0x80)) {
-		raw_spin_unlock(&linear_map_hash_lock);
-		return;
-	}
-	hidx = linear_map_hash_slots[lmi] & 0x7f;
-	linear_map_hash_slots[lmi] = 0;
-	raw_spin_unlock(&linear_map_hash_lock);
-	if (hidx & _PTEIDX_SECONDARY)
-		hash = ~hash;
-	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-	slot += hidx & _PTEIDX_GROUP_IX;
-	mmu_hash_ops.hpte_invalidate(slot, vpn, mmu_linear_psize,
-				     mmu_linear_psize,
-				     mmu_kernel_ssize, 0);
-}
-
-void hash__kernel_map_pages(struct page *page, int numpages, int enable)
-{
-	unsigned long flags, vaddr, lmi;
-	int i;
-
-	local_irq_save(flags);
-	for (i = 0; i < numpages; i++, page++) {
-		vaddr = (unsigned long)page_address(page);
-		lmi = __pa(vaddr) >> PAGE_SHIFT;
-		if (lmi >= linear_map_hash_count)
-			continue;
-		if (enable)
-			kernel_map_linear_page(vaddr, lmi);
-		else
-			kernel_unmap_linear_page(vaddr, lmi);
-	}
-	local_irq_restore(flags);
-}
-#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_KFENCE */
-
 void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
 				phys_addr_t first_memblock_size)
 {
@@ -2248,6 +2451,8 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n")
 
 static int __init hash64_debugfs(void)
 {
+	if (radix_enabled())
+		return 0;
 	debugfs_create_file("hpt_order", 0600, arch_debugfs_dir, NULL,
 			    &fops_hpt_order);
 	return 0;
diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c
index 3bc0eb21b2a0..2bcbbf9d85ac 100644
--- a/arch/powerpc/mm/book3s64/hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/hugetlbpage.c
@@ -53,6 +53,16 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		/* If PTE permissions don't match, take page fault */
 		if (unlikely(!check_pte_access(access, old_pte)))
 			return 1;
+		/*
+		 * If hash-4k, hugepages use seeral contiguous PxD entries
+		 * so bail out and let mm make the page young or dirty
+		 */
+		if (IS_ENABLED(CONFIG_PPC_4K_PAGES)) {
+			if (!(old_pte & _PAGE_ACCESSED))
+				return 1;
+			if ((access & _PAGE_WRITE) && !(old_pte & _PAGE_DIRTY))
+				return 1;
+		}
 
 		/*
 		 * Try to lock the PTE, add ACCESSED and DIRTY if it was
@@ -64,7 +74,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	} while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
 	/* Make sure this is a hugetlb entry */
-	if (old_pte & (H_PAGE_THP_HUGE | _PAGE_DEVMAP))
+	if (old_pte & H_PAGE_THP_HUGE)
 		return 0;
 
 	rflags = htab_convert_pte_flags(new_pte, flags);
@@ -143,11 +153,14 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 				  pte_t *ptep, pte_t old_pte, pte_t pte)
 {
+	unsigned long psize;
 
 	if (radix_enabled())
 		return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
 							   old_pte, pte);
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+
+	psize = huge_page_size(hstate_vma(vma));
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }
 
 void __init hugetlbpage_init_defaultsize(void)
diff --git a/arch/powerpc/mm/book3s64/internal.h b/arch/powerpc/mm/book3s64/internal.h
index a57a25f06a21..cad08d83369c 100644
--- a/arch/powerpc/mm/book3s64/internal.h
+++ b/arch/powerpc/mm/book3s64/internal.h
@@ -22,9 +22,14 @@ static inline bool stress_hpt(void)
 	return static_branch_unlikely(&stress_hpt_key);
 }
 
-void hpt_do_stress(unsigned long ea, unsigned long hpte_group);
+extern bool no_slb_preload;
+DECLARE_STATIC_KEY_FALSE(no_slb_preload_key);
+static inline bool slb_preload_disabled(void)
+{
+	return static_branch_unlikely(&no_slb_preload_key);
+}
 
-void slb_setup_new_exec(void);
+void hpt_do_stress(unsigned long ea, unsigned long hpte_group);
 
 void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush);
 
diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
index 81d7185e2ae8..c0e8d597e4cb 100644
--- a/arch/powerpc/mm/book3s64/iommu_api.c
+++ b/arch/powerpc/mm/book3s64/iommu_api.c
@@ -97,7 +97,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 	mmap_read_lock(mm);
-	chunk = (1UL << (PAGE_SHIFT + MAX_ORDER)) /
+	chunk = (1UL << (PAGE_SHIFT + MAX_PAGE_ORDER)) /
 			sizeof(struct vm_area_struct *);
 	chunk = min(chunk, entries);
 	for (entry = 0; entry < entries; entry += chunk) {
@@ -105,7 +105,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 
 		ret = pin_user_pages(ua + (entry << PAGE_SHIFT), n,
 				FOLL_WRITE | FOLL_LONGTERM,
-				mem->hpages + entry, NULL);
+				mem->hpages + entry);
 		if (ret == n) {
 			pinned += n;
 			continue;
diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c
index c766e4c26e42..fb9dcf9ca599 100644
--- a/arch/powerpc/mm/book3s64/mmu_context.c
+++ b/arch/powerpc/mm/book3s64/mmu_context.c
@@ -150,8 +150,6 @@ static int hash__init_new_context(struct mm_struct *mm)
 void hash__setup_new_exec(void)
 {
 	slice_setup_new_exec();
-
-	slb_setup_new_exec();
 }
 #else
 static inline int hash__init_new_context(struct mm_struct *mm)
@@ -246,15 +244,15 @@ static void destroy_contexts(mm_context_t *ctx)
 static void pmd_frag_destroy(void *pmd_frag)
 {
 	int count;
-	struct page *page;
+	struct ptdesc *ptdesc;
 
-	page = virt_to_page(pmd_frag);
+	ptdesc = virt_to_ptdesc(pmd_frag);
 	/* drop all the pending references */
 	count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT;
 	/* We allow PTE_FRAG_NR fragments from a PTE page */
-	if (atomic_sub_and_test(PMD_FRAG_NR - count, &page->pt_frag_refcount)) {
-		pgtable_pmd_page_dtor(page);
-		__free_page(page);
+	if (atomic_sub_and_test(PMD_FRAG_NR - count, &ptdesc->pt_frag_refcount)) {
+		pagetable_dtor(ptdesc);
+		pagetable_free(ptdesc);
 	}
 }
 
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 85c84e89e3ea..e3485db7de02 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -9,7 +9,7 @@
 #include <linux/memremap.h>
 #include <linux/pkeys.h>
 #include <linux/debugfs.h>
-#include <misc/cxl-base.h>
+#include <linux/proc_fs.h>
 
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
@@ -36,6 +36,19 @@ EXPORT_SYMBOL(__pmd_frag_nr);
 unsigned long __pmd_frag_size_shift;
 EXPORT_SYMBOL(__pmd_frag_size_shift);
 
+#ifdef CONFIG_KFENCE
+extern bool kfence_early_init;
+static int __init parse_kfence_early_init(char *arg)
+{
+	int val;
+
+	if (get_option(&arg, &val))
+		kfence_early_init = !!val;
+	return 0;
+}
+early_param("kfence.sample_interval", parse_kfence_early_init);
+#endif
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * This is called when relaxing access to a hugepage. It's also called in the page
@@ -49,7 +62,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 {
 	int changed;
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
+	WARN_ON(!pmd_trans_huge(*pmdp));
 	assert_spin_locked(pmd_lockptr(vma->vm_mm, pmdp));
 #endif
 	changed = !pmd_same(*(pmdp), entry);
@@ -64,11 +77,38 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 	return changed;
 }
 
+int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+			  pud_t *pudp, pud_t entry, int dirty)
+{
+	int changed;
+#ifdef CONFIG_DEBUG_VM
+	assert_spin_locked(pud_lockptr(vma->vm_mm, pudp));
+#endif
+	changed = !pud_same(*(pudp), entry);
+	if (changed) {
+		/*
+		 * We can use MMU_PAGE_1G here, because only radix
+		 * path look at the psize.
+		 */
+		__ptep_set_access_flags(vma, pudp_ptep(pudp),
+					pud_pte(entry), address, MMU_PAGE_1G);
+	}
+	return changed;
+}
+
+
 int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 			      unsigned long address, pmd_t *pmdp)
 {
 	return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp);
 }
+
+int pudp_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long address, pud_t *pudp)
+{
+	return __pudp_test_and_clear_young(vma->vm_mm, address, pudp);
+}
+
 /*
  * set a new huge pmd. We should not be called for updating
  * an existing pmd entry. That should go via pmd_hugepage_update.
@@ -84,12 +124,29 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 
 	WARN_ON(pte_hw_valid(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
-	WARN_ON(!(pmd_large(pmd)));
+	WARN_ON(!(pmd_leaf(pmd)));
 #endif
 	trace_hugepage_set_pmd(addr, pmd_val(pmd));
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
 }
 
+void set_pud_at(struct mm_struct *mm, unsigned long addr,
+		pud_t *pudp, pud_t pud)
+{
+#ifdef CONFIG_DEBUG_VM
+	/*
+	 * Make sure hardware valid bit is not set. We don't do
+	 * tlb flush for this update.
+	 */
+
+	WARN_ON(pte_hw_valid(pud_pte(*pudp)));
+	assert_spin_locked(pud_lockptr(mm, pudp));
+	WARN_ON(!(pud_leaf(pud)));
+#endif
+	trace_hugepage_set_pud(addr, pud_val(pud));
+	return set_pte_at(mm, addr, pudp_ptep(pudp), pud_pte(pud));
+}
+
 static void do_serialize(void *arg)
 {
 	/* We've taken the IPI, so try to trim the mask while here */
@@ -124,18 +181,30 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 {
 	unsigned long old_pmd;
 
+	VM_WARN_ON_ONCE(!pmd_present(*pmdp));
 	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID);
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return __pmd(old_pmd);
 }
 
+pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		      pud_t *pudp)
+{
+	unsigned long old_pud;
+
+	VM_WARN_ON_ONCE(!pud_present(*pudp));
+	old_pud = pud_hugepage_update(vma->vm_mm, address, pudp, _PAGE_PRESENT, _PAGE_INVALID);
+	flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+	return __pud(old_pud);
+}
+
 pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma,
 				   unsigned long addr, pmd_t *pmdp, int full)
 {
 	pmd_t pmd;
 	VM_BUG_ON(addr & ~HPAGE_PMD_MASK);
-	VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
-		   !pmd_devmap(*pmdp)) || !pmd_present(*pmdp));
+	VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp)) ||
+		   !pmd_present(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
 	/*
 	 * if it not a fullmm flush, then we can possibly end up converting
@@ -147,11 +216,34 @@ pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma,
 	return pmd;
 }
 
+pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma,
+				   unsigned long addr, pud_t *pudp, int full)
+{
+	pud_t pud;
+
+	VM_BUG_ON(addr & ~HPAGE_PMD_MASK);
+	VM_BUG_ON(!pud_present(*pudp));
+	pud = pudp_huge_get_and_clear(vma->vm_mm, addr, pudp);
+	/*
+	 * if it not a fullmm flush, then we can possibly end up converting
+	 * this PMD pte entry to a regular level 0 PTE by a parallel page fault.
+	 * Make sure we flush the tlb in this case.
+	 */
+	if (!full)
+		flush_pud_tlb_range(vma, addr, addr + HPAGE_PUD_SIZE);
+	return pud;
+}
+
 static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
 {
 	return __pmd(pmd_val(pmd) | pgprot_val(pgprot));
 }
 
+static pud_t pud_set_protbits(pud_t pud, pgprot_t pgprot)
+{
+	return __pud(pud_val(pud) | pgprot_val(pgprot));
+}
+
 /*
  * At some point we should be able to get rid of
  * pmd_mkhuge() and mk_huge_pmd() when we update all the
@@ -166,9 +258,13 @@ pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
 	return __pmd_mkhuge(pmd_set_protbits(__pmd(pmdv), pgprot));
 }
 
-pmd_t mk_pmd(struct page *page, pgprot_t pgprot)
+pud_t pfn_pud(unsigned long pfn, pgprot_t pgprot)
 {
-	return pfn_pmd(page_to_pfn(page), pgprot);
+	unsigned long pudv;
+
+	pudv = (pfn << PAGE_SHIFT) & PTE_RPN_MASK;
+
+	return __pud_mkhuge(pud_set_protbits(__pud(pudv), pgprot));
 }
 
 pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
@@ -179,6 +275,15 @@ pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 	pmdv &= _HPAGE_CHG_MASK;
 	return pmd_set_protbits(__pmd(pmdv), newprot);
 }
+
+pud_t pud_modify(pud_t pud, pgprot_t newprot)
+{
+	unsigned long pudv;
+
+	pudv = pud_val(pud);
+	pudv &= _HPAGE_CHG_MASK;
+	return pud_set_protbits(__pud(pudv), newprot);
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /* For use by kexec, called with MMU off */
@@ -217,11 +322,7 @@ void __init mmu_partition_table_init(void)
 	unsigned long ptcr;
 
 	/* Initialize the Partition Table with no entries */
-	partition_tb = memblock_alloc(patb_size, patb_size);
-	if (!partition_tb)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, patb_size, patb_size);
-
+	partition_tb = memblock_alloc_or_panic(patb_size, patb_size);
 	ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12);
 	set_ptcr_when_no_uv(ptcr);
 	powernv_set_nmmu_ptcr(ptcr);
@@ -306,22 +407,22 @@ static pmd_t *get_pmd_from_cache(struct mm_struct *mm)
 static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm)
 {
 	void *ret = NULL;
-	struct page *page;
+	struct ptdesc *ptdesc;
 	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO;
 
 	if (mm == &init_mm)
 		gfp &= ~__GFP_ACCOUNT;
-	page = alloc_page(gfp);
-	if (!page)
+	ptdesc = pagetable_alloc(gfp, 0);
+	if (!ptdesc)
 		return NULL;
-	if (!pgtable_pmd_page_ctor(page)) {
-		__free_pages(page, 0);
+	if (!pagetable_pmd_ctor(mm, ptdesc)) {
+		pagetable_free(ptdesc);
 		return NULL;
 	}
 
-	atomic_set(&page->pt_frag_refcount, 1);
+	atomic_set(&ptdesc->pt_frag_refcount, 1);
 
-	ret = page_address(page);
+	ret = ptdesc_address(ptdesc);
 	/*
 	 * if we support only one fragment just return the
 	 * allocated page.
@@ -331,12 +432,12 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm)
 
 	spin_lock(&mm->page_table_lock);
 	/*
-	 * If we find pgtable_page set, we return
+	 * If we find ptdesc_page set, we return
 	 * the allocated page with single fragment
 	 * count.
 	 */
 	if (likely(!mm->context.pmd_frag)) {
-		atomic_set(&page->pt_frag_refcount, PMD_FRAG_NR);
+		atomic_set(&ptdesc->pt_frag_refcount, PMD_FRAG_NR);
 		mm->context.pmd_frag = ret + PMD_FRAG_SIZE;
 	}
 	spin_unlock(&mm->page_table_lock);
@@ -357,15 +458,15 @@ pmd_t *pmd_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr)
 
 void pmd_fragment_free(unsigned long *pmd)
 {
-	struct page *page = virt_to_page(pmd);
+	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
 
-	if (PageReserved(page))
-		return free_reserved_page(page);
+	if (pagetable_is_reserved(ptdesc))
+		return free_reserved_ptdesc(ptdesc);
 
-	BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0);
-	if (atomic_dec_and_test(&page->pt_frag_refcount)) {
-		pgtable_pmd_page_dtor(page);
-		__free_page(page);
+	BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0);
+	if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) {
+		pagetable_dtor(ptdesc);
+		pagetable_free(ptdesc);
 	}
 }
 
@@ -381,18 +482,6 @@ static inline void pgtable_free(void *table, int index)
 	case PUD_INDEX:
 		__pud_free(table);
 		break;
-#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
-		/* 16M hugepd directory at pud level */
-	case HTLB_16M_INDEX:
-		BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0);
-		kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table);
-		break;
-		/* 16G hugepd directory at the pgd level */
-	case HTLB_16G_INDEX:
-		BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0);
-		kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table);
-		break;
-#endif
 		/* We don't free pgd table via RCU callback */
 	default:
 		BUG();
@@ -421,20 +510,21 @@ atomic_long_t direct_pages_count[MMU_PAGE_COUNT];
 
 void arch_report_meminfo(struct seq_file *m)
 {
-	/*
-	 * Hash maps the memory with one size mmu_linear_psize.
-	 * So don't bother to print these on hash
-	 */
-	if (!radix_enabled())
-		return;
 	seq_printf(m, "DirectMap4k:    %8lu kB\n",
 		   atomic_long_read(&direct_pages_count[MMU_PAGE_4K]) << 2);
-	seq_printf(m, "DirectMap64k:    %8lu kB\n",
+	seq_printf(m, "DirectMap64k:   %8lu kB\n",
 		   atomic_long_read(&direct_pages_count[MMU_PAGE_64K]) << 6);
-	seq_printf(m, "DirectMap2M:    %8lu kB\n",
-		   atomic_long_read(&direct_pages_count[MMU_PAGE_2M]) << 11);
-	seq_printf(m, "DirectMap1G:    %8lu kB\n",
-		   atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20);
+	if (radix_enabled()) {
+		seq_printf(m, "DirectMap2M:    %8lu kB\n",
+			   atomic_long_read(&direct_pages_count[MMU_PAGE_2M]) << 11);
+		seq_printf(m, "DirectMap1G:    %8lu kB\n",
+			   atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20);
+	} else {
+		seq_printf(m, "DirectMap16M:   %8lu kB\n",
+			   atomic_long_read(&direct_pages_count[MMU_PAGE_16M]) << 14);
+		seq_printf(m, "DirectMap16G:   %8lu kB\n",
+			   atomic_long_read(&direct_pages_count[MMU_PAGE_16G]) << 24);
+	}
 }
 #endif /* CONFIG_PROC_FS */
 
@@ -463,6 +553,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 	set_pte_at(vma->vm_mm, addr, ptep, pte);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * For hash translation mode, we use the deposited table to store hash slot
  * information and they are stored at PTRS_PER_PMD offset from related pmd
@@ -484,11 +575,12 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
 
 	return true;
 }
+#endif
 
 /*
  * Does the CPU support tlbie?
  */
-bool tlbie_capable __read_mostly = true;
+bool tlbie_capable __read_mostly = IS_ENABLED(CONFIG_PPC_RADIX_BROADCAST_TLBIE);
 EXPORT_SYMBOL(tlbie_capable);
 
 /*
@@ -496,7 +588,7 @@ EXPORT_SYMBOL(tlbie_capable);
  * address spaces? tlbie may still be used for nMMU accelerators, and for KVM
  * guest address spaces.
  */
-bool tlbie_enabled __read_mostly = true;
+bool tlbie_enabled __read_mostly = IS_ENABLED(CONFIG_PPC_RADIX_BROADCAST_TLBIE);
 
 static int __init setup_disable_tlbie(char *str)
 {
@@ -551,17 +643,15 @@ unsigned long memremap_compat_align(void)
 EXPORT_SYMBOL_GPL(memremap_compat_align);
 #endif
 
-pgprot_t vm_get_page_prot(unsigned long vm_flags)
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 {
 	unsigned long prot;
 
 	/* Radix supports execute-only, but protection_map maps X -> RX */
-	if (radix_enabled() && ((vm_flags & VM_ACCESS_FLAGS) == VM_EXEC)) {
-		prot = pgprot_val(PAGE_EXECONLY);
-	} else {
-		prot = pgprot_val(protection_map[vm_flags &
-						 (VM_ACCESS_FLAGS | VM_SHARED)]);
-	}
+	if (!radix_enabled() && ((vm_flags & VM_ACCESS_FLAGS) == VM_EXEC))
+		vm_flags |= VM_READ;
+
+	prot = pgprot_val(protection_map[vm_flags & (VM_ACCESS_FLAGS | VM_SHARED)]);
 
 	if (vm_flags & VM_SAO)
 		prot |= _PAGE_SAO;
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index 1d2675ab6711..a974baf8f327 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -89,7 +89,8 @@ static int __init scan_pkey_feature(void)
 			unsigned long pvr = mfspr(SPRN_PVR);
 
 			if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E ||
-			    PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9)
+			    PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9 ||
+			    PVR_VER(pvr) == PVR_HX_C2000)
 				pkeys_total = 32;
 		}
 	}
@@ -291,7 +292,7 @@ void setup_kuap(bool disabled)
 
 	if (smp_processor_id() == boot_cpuid) {
 		pr_info("Activating Kernel Userspace Access Prevention\n");
-		cur_cpu_spec->mmu_features |= MMU_FTR_BOOK3S_KUAP;
+		cur_cpu_spec->mmu_features |= MMU_FTR_KUAP;
 	}
 
 	/*
diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
index 5e3195568525..35fd2a95be24 100644
--- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
@@ -39,6 +39,7 @@ void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long st
 		radix__flush_tlb_pwc_range_psize(vma->vm_mm, start, end, psize);
 	else
 		radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize);
+	mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end);
 }
 
 void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
@@ -46,6 +47,7 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 					 pte_t old_pte, pte_t pte)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	unsigned long psize = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * POWER9 NMMU must flush the TLB after clearing the PTE before
@@ -57,5 +59,5 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 	    atomic_read(&mm->context.copros) > 0)
 		radix__flush_hugetlb_page(vma, addr);
 
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 26245aaf12b8..73977dbabcf2 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -17,6 +17,7 @@
 #include <linux/hugetlb.h>
 #include <linux/string_helpers.h>
 #include <linux/memory.h>
+#include <linux/kfence.h>
 
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
@@ -31,13 +32,13 @@
 #include <asm/uaccess.h>
 #include <asm/ultravisor.h>
 #include <asm/set_memory.h>
+#include <asm/kfence.h>
 
 #include <trace/events/thp.h>
 
 #include <mm/mmu_decl.h>
 
 unsigned int mmu_base_pid;
-unsigned long radix_mem_block_size __ro_after_init;
 
 static __ref void *early_alloc_pgtable(unsigned long size, int nid,
 			unsigned long region_start, unsigned long region_end)
@@ -205,14 +206,14 @@ static void radix__change_memory_range(unsigned long start, unsigned long end,
 		pudp = pud_alloc(&init_mm, p4dp, idx);
 		if (!pudp)
 			continue;
-		if (pud_is_leaf(*pudp)) {
+		if (pud_leaf(*pudp)) {
 			ptep = (pte_t *)pudp;
 			goto update_the_pte;
 		}
 		pmdp = pmd_alloc(&init_mm, pudp, idx);
 		if (!pmdp)
 			continue;
-		if (pmd_is_leaf(*pmdp)) {
+		if (pmd_leaf(*pmdp)) {
 			ptep = pmdp_ptep(pmdp);
 			goto update_the_pte;
 		}
@@ -294,15 +295,19 @@ static unsigned long next_boundary(unsigned long addr, unsigned long end)
 
 static int __meminit create_physical_mapping(unsigned long start,
 					     unsigned long end,
-					     int nid, pgprot_t _prot)
+					     int nid, pgprot_t _prot,
+					     unsigned long mapping_sz_limit)
 {
 	unsigned long vaddr, addr, mapping_size = 0;
 	bool prev_exec, exec = false;
 	pgprot_t prot;
 	int psize;
-	unsigned long max_mapping_size = radix_mem_block_size;
+	unsigned long max_mapping_size = memory_block_size;
 
-	if (debug_pagealloc_enabled_or_kfence())
+	if (mapping_sz_limit < max_mapping_size)
+		max_mapping_size = mapping_sz_limit;
+
+	if (debug_pagealloc_enabled())
 		max_mapping_size = PAGE_SIZE;
 
 	start = ALIGN(start, PAGE_SIZE);
@@ -357,8 +362,62 @@ static int __meminit create_physical_mapping(unsigned long start,
 	return 0;
 }
 
+#ifdef CONFIG_KFENCE
+static __init phys_addr_t alloc_kfence_pool(void)
+{
+	phys_addr_t kfence_pool;
+
+	/*
+	 * TODO: Support to enable KFENCE after bootup depends on the ability to
+	 *       split page table mappings. As such support is not currently
+	 *       implemented for radix pagetables, support enabling KFENCE
+	 *       only at system startup for now.
+	 *
+	 *       After support for splitting mappings is available on radix,
+	 *       alloc_kfence_pool() & map_kfence_pool() can be dropped and
+	 *       mapping for __kfence_pool memory can be
+	 *       split during arch_kfence_init_pool().
+	 */
+	if (!kfence_early_init)
+		goto no_kfence;
+
+	kfence_pool = memblock_phys_alloc(KFENCE_POOL_SIZE, PAGE_SIZE);
+	if (!kfence_pool)
+		goto no_kfence;
+
+	memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE);
+	return kfence_pool;
+
+no_kfence:
+	disable_kfence();
+	return 0;
+}
+
+static __init void map_kfence_pool(phys_addr_t kfence_pool)
+{
+	if (!kfence_pool)
+		return;
+
+	if (create_physical_mapping(kfence_pool, kfence_pool + KFENCE_POOL_SIZE,
+				    -1, PAGE_KERNEL, PAGE_SIZE))
+		goto err;
+
+	memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
+	__kfence_pool = __va(kfence_pool);
+	return;
+
+err:
+	memblock_phys_free(kfence_pool, KFENCE_POOL_SIZE);
+	disable_kfence();
+}
+#else
+static inline phys_addr_t alloc_kfence_pool(void) { return 0; }
+static inline void map_kfence_pool(phys_addr_t kfence_pool) { }
+#endif
+
 static void __init radix_init_pgtable(void)
 {
+	phys_addr_t kfence_pool;
 	unsigned long rts_field;
 	phys_addr_t start, end;
 	u64 i;
@@ -366,6 +425,8 @@ static void __init radix_init_pgtable(void)
 	/* We don't support slb for radix */
 	slb_set_size(0);
 
+	kfence_pool = alloc_kfence_pool();
+
 	/*
 	 * Create the linear mapping
 	 */
@@ -382,9 +443,11 @@ static void __init radix_init_pgtable(void)
 		}
 
 		WARN_ON(create_physical_mapping(start, end,
-						-1, PAGE_KERNEL));
+						-1, PAGE_KERNEL, ~0UL));
 	}
 
+	map_kfence_pool(kfence_pool);
+
 	if (!cpu_has_feature(CPU_FTR_HVMODE) &&
 			cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
 		/*
@@ -502,58 +565,6 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
 	return 1;
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-static int __init probe_memory_block_size(unsigned long node, const char *uname, int
-					  depth, void *data)
-{
-	unsigned long *mem_block_size = (unsigned long *)data;
-	const __be32 *prop;
-	int len;
-
-	if (depth != 1)
-		return 0;
-
-	if (strcmp(uname, "ibm,dynamic-reconfiguration-memory"))
-		return 0;
-
-	prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len);
-
-	if (!prop || len < dt_root_size_cells * sizeof(__be32))
-		/*
-		 * Nothing in the device tree
-		 */
-		*mem_block_size = MIN_MEMORY_BLOCK_SIZE;
-	else
-		*mem_block_size = of_read_number(prop, dt_root_size_cells);
-	return 1;
-}
-
-static unsigned long __init radix_memory_block_size(void)
-{
-	unsigned long mem_block_size = MIN_MEMORY_BLOCK_SIZE;
-
-	/*
-	 * OPAL firmware feature is set by now. Hence we are ok
-	 * to test OPAL feature.
-	 */
-	if (firmware_has_feature(FW_FEATURE_OPAL))
-		mem_block_size = 1UL * 1024 * 1024 * 1024;
-	else
-		of_scan_flat_dt(probe_memory_block_size, &mem_block_size);
-
-	return mem_block_size;
-}
-
-#else   /* CONFIG_MEMORY_HOTPLUG */
-
-static unsigned long __init radix_memory_block_size(void)
-{
-	return 1UL * 1024 * 1024 * 1024;
-}
-
-#endif /* CONFIG_MEMORY_HOTPLUG */
-
-
 void __init radix__early_init_devtree(void)
 {
 	int rc;
@@ -577,16 +588,6 @@ void __init radix__early_init_devtree(void)
 		mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize =
 			psize_to_rpti_pgsize(MMU_PAGE_64K);
 	}
-
-	/*
-	 * Max mapping size used when mapping pages. We don't use
-	 * ppc_md.memory_block_size() here because this get called
-	 * early and we don't have machine probe called yet. Also
-	 * the pseries implementation only check for ibm,lmb-size.
-	 * All hypervisor supporting radix do expose that device
-	 * tree node.
-	 */
-	radix_mem_block_size = radix_memory_block_size();
 	return;
 }
 
@@ -601,17 +602,6 @@ void __init radix__early_init_mmu(void)
 #else
 	mmu_virtual_psize = MMU_PAGE_4K;
 #endif
-
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-	/* vmemmap mapping */
-	if (mmu_psize_defs[MMU_PAGE_2M].shift) {
-		/*
-		 * map vmemmap using 2M if available
-		 */
-		mmu_vmemmap_psize = MMU_PAGE_2M;
-	} else
-		mmu_vmemmap_psize = mmu_virtual_psize;
-#endif
 #endif
 	/*
 	 * initialize page table size
@@ -744,10 +734,60 @@ static void free_pud_table(pud_t *pud_start, p4d_t *p4d)
 	p4d_clear(p4d);
 }
 
-static void remove_pte_table(pte_t *pte_start, unsigned long addr,
-			     unsigned long end)
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end)
 {
-	unsigned long next;
+	unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);
+
+	return !vmemmap_populated(start, PMD_SIZE);
+}
+
+static bool __meminit vmemmap_page_is_unused(unsigned long addr, unsigned long end)
+{
+	unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
+
+	return !vmemmap_populated(start, PAGE_SIZE);
+
+}
+#endif
+
+static void __meminit free_vmemmap_pages(struct page *page,
+					 struct vmem_altmap *altmap,
+					 int order)
+{
+	unsigned int nr_pages = 1 << order;
+
+	if (altmap) {
+		unsigned long alt_start, alt_end;
+		unsigned long base_pfn = page_to_pfn(page);
+
+		/*
+		 * with 2M vmemmap mmaping we can have things setup
+		 * such that even though atlmap is specified we never
+		 * used altmap.
+		 */
+		alt_start = altmap->base_pfn;
+		alt_end = altmap->base_pfn + altmap->reserve + altmap->free;
+
+		if (base_pfn >= alt_start && base_pfn < alt_end) {
+			vmem_altmap_free(altmap, nr_pages);
+			return;
+		}
+	}
+
+	if (PageReserved(page)) {
+		/* allocated from memblock */
+		while (nr_pages--)
+			free_reserved_page(page++);
+	} else
+		__free_pages(page, order);
+}
+
+static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr,
+				       unsigned long end, bool direct,
+				       struct vmem_altmap *altmap)
+{
+	unsigned long next, pages = 0;
 	pte_t *pte;
 
 	pte = pte_start + pte_index(addr);
@@ -759,23 +799,28 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr,
 		if (!pte_present(*pte))
 			continue;
 
-		if (!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(next)) {
-			/*
-			 * The vmemmap_free() and remove_section_mapping()
-			 * codepaths call us with aligned addresses.
-			 */
-			WARN_ONCE(1, "%s: unaligned range\n", __func__);
-			continue;
+		if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) {
+			if (!direct)
+				free_vmemmap_pages(pte_page(*pte), altmap, 0);
+			pte_clear(&init_mm, addr, pte);
+			pages++;
 		}
-
-		pte_clear(&init_mm, addr, pte);
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+		else if (!direct && vmemmap_page_is_unused(addr, next)) {
+			free_vmemmap_pages(pte_page(*pte), altmap, 0);
+			pte_clear(&init_mm, addr, pte);
+		}
+#endif
 	}
+	if (direct)
+		update_page_count(mmu_virtual_psize, -pages);
 }
 
 static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
-			     unsigned long end)
+				       unsigned long end, bool direct,
+				       struct vmem_altmap *altmap)
 {
-	unsigned long next;
+	unsigned long next, pages = 0;
 	pte_t *pte_base;
 	pmd_t *pmd;
 
@@ -786,26 +831,36 @@ static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
 		if (!pmd_present(*pmd))
 			continue;
 
-		if (pmd_is_leaf(*pmd)) {
-			if (!IS_ALIGNED(addr, PMD_SIZE) ||
-			    !IS_ALIGNED(next, PMD_SIZE)) {
-				WARN_ONCE(1, "%s: unaligned range\n", __func__);
-				continue;
+		if (pmd_leaf(*pmd)) {
+			if (IS_ALIGNED(addr, PMD_SIZE) &&
+			    IS_ALIGNED(next, PMD_SIZE)) {
+				if (!direct)
+					free_vmemmap_pages(pmd_page(*pmd), altmap, get_order(PMD_SIZE));
+				pte_clear(&init_mm, addr, (pte_t *)pmd);
+				pages++;
+			}
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+			else if (!direct && vmemmap_pmd_is_unused(addr, next)) {
+				free_vmemmap_pages(pmd_page(*pmd), altmap, get_order(PMD_SIZE));
+				pte_clear(&init_mm, addr, (pte_t *)pmd);
 			}
-			pte_clear(&init_mm, addr, (pte_t *)pmd);
+#endif
 			continue;
 		}
 
 		pte_base = (pte_t *)pmd_page_vaddr(*pmd);
-		remove_pte_table(pte_base, addr, next);
+		remove_pte_table(pte_base, addr, next, direct, altmap);
 		free_pte_table(pte_base, pmd);
 	}
+	if (direct)
+		update_page_count(MMU_PAGE_2M, -pages);
 }
 
 static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr,
-			     unsigned long end)
+				       unsigned long end, bool direct,
+				       struct vmem_altmap *altmap)
 {
-	unsigned long next;
+	unsigned long next, pages = 0;
 	pmd_t *pmd_base;
 	pud_t *pud;
 
@@ -816,23 +871,28 @@ static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr,
 		if (!pud_present(*pud))
 			continue;
 
-		if (pud_is_leaf(*pud)) {
+		if (pud_leaf(*pud)) {
 			if (!IS_ALIGNED(addr, PUD_SIZE) ||
 			    !IS_ALIGNED(next, PUD_SIZE)) {
 				WARN_ONCE(1, "%s: unaligned range\n", __func__);
 				continue;
 			}
 			pte_clear(&init_mm, addr, (pte_t *)pud);
+			pages++;
 			continue;
 		}
 
 		pmd_base = pud_pgtable(*pud);
-		remove_pmd_table(pmd_base, addr, next);
+		remove_pmd_table(pmd_base, addr, next, direct, altmap);
 		free_pmd_table(pmd_base, pud);
 	}
+	if (direct)
+		update_page_count(MMU_PAGE_1G, -pages);
 }
 
-static void __meminit remove_pagetable(unsigned long start, unsigned long end)
+static void __meminit
+remove_pagetable(unsigned long start, unsigned long end, bool direct,
+		 struct vmem_altmap *altmap)
 {
 	unsigned long addr, next;
 	pud_t *pud_base;
@@ -849,7 +909,7 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end)
 		if (!p4d_present(*p4d))
 			continue;
 
-		if (p4d_is_leaf(*p4d)) {
+		if (p4d_leaf(*p4d)) {
 			if (!IS_ALIGNED(addr, P4D_SIZE) ||
 			    !IS_ALIGNED(next, P4D_SIZE)) {
 				WARN_ONCE(1, "%s: unaligned range\n", __func__);
@@ -861,7 +921,7 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end)
 		}
 
 		pud_base = p4d_pgtable(*p4d);
-		remove_pud_table(pud_base, addr, next);
+		remove_pud_table(pud_base, addr, next, direct, altmap);
 		free_pud_table(pud_base, p4d);
 	}
 
@@ -879,12 +939,12 @@ int __meminit radix__create_section_mapping(unsigned long start,
 	}
 
 	return create_physical_mapping(__pa(start), __pa(end),
-				       nid, prot);
+				       nid, prot, ~0UL);
 }
 
 int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
 {
-	remove_pagetable(start, end);
+	remove_pagetable(start, end, true, NULL);
 	return 0;
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
@@ -902,7 +962,6 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start,
 				      unsigned long phys)
 {
 	/* Create a PTE encoding */
-	unsigned long flags = _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_KERNEL_RW;
 	int nid = early_pfn_to_nid(phys >> PAGE_SHIFT);
 	int ret;
 
@@ -911,32 +970,458 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start,
 		return -1;
 	}
 
-	ret = __map_kernel_page_nid(start, phys, __pgprot(flags), page_size, nid);
+	ret = __map_kernel_page_nid(start, phys, PAGE_KERNEL, page_size, nid);
 	BUG_ON(ret);
 
 	return 0;
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size)
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
+bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
 {
-	remove_pagetable(start, start + page_size);
+	if (radix_enabled())
+		return __vmemmap_can_optimize(altmap, pgmap);
+
+	return false;
 }
 #endif
-#endif
 
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-void radix__kernel_map_pages(struct page *page, int numpages, int enable)
+int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
+				unsigned long addr, unsigned long next)
+{
+	int large = pmd_leaf(*pmdp);
+
+	if (large)
+		vmemmap_verify(pmdp_ptep(pmdp), node, addr, next);
+
+	return large;
+}
+
+void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node,
+			       unsigned long addr, unsigned long next)
+{
+	pte_t entry;
+	pte_t *ptep = pmdp_ptep(pmdp);
+
+	VM_BUG_ON(!IS_ALIGNED(addr, PMD_SIZE));
+	entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
+	set_pte_at(&init_mm, addr, ptep, entry);
+	asm volatile("ptesync": : :"memory");
+
+	vmemmap_verify(ptep, node, addr, next);
+}
+
+static pte_t * __meminit radix__vmemmap_pte_populate(pmd_t *pmdp, unsigned long addr,
+						     int node,
+						     struct vmem_altmap *altmap,
+						     struct page *reuse)
+{
+	pte_t *pte = pte_offset_kernel(pmdp, addr);
+
+	if (pte_none(*pte)) {
+		pte_t entry;
+		void *p;
+
+		if (!reuse) {
+			/*
+			 * make sure we don't create altmap mappings
+			 * covering things outside the device.
+			 */
+			if (altmap && altmap_cross_boundary(altmap, addr, PAGE_SIZE))
+				altmap = NULL;
+
+			p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
+			if (!p && altmap)
+				p = vmemmap_alloc_block_buf(PAGE_SIZE, node, NULL);
+			if (!p)
+				return NULL;
+			pr_debug("PAGE_SIZE vmemmap mapping\n");
+		} else {
+			/*
+			 * When a PTE/PMD entry is freed from the init_mm
+			 * there's a free_pages() call to this page allocated
+			 * above. Thus this get_page() is paired with the
+			 * put_page_testzero() on the freeing path.
+			 * This can only called by certain ZONE_DEVICE path,
+			 * and through vmemmap_populate_compound_pages() when
+			 * slab is available.
+			 */
+			get_page(reuse);
+			p = page_to_virt(reuse);
+			pr_debug("Tail page reuse vmemmap mapping\n");
+		}
+
+		VM_BUG_ON(!PAGE_ALIGNED(addr));
+		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
+		set_pte_at(&init_mm, addr, pte, entry);
+		asm volatile("ptesync": : :"memory");
+	}
+	return pte;
+}
+
+static inline pud_t *vmemmap_pud_alloc(p4d_t *p4dp, int node,
+				       unsigned long address)
+{
+	pud_t *pud;
+
+	/* All early vmemmap mapping to keep simple do it at PAGE_SIZE */
+	if (unlikely(p4d_none(*p4dp))) {
+		if (unlikely(!slab_is_available())) {
+			pud = early_alloc_pgtable(PAGE_SIZE, node, 0, 0);
+			p4d_populate(&init_mm, p4dp, pud);
+			/* go to the pud_offset */
+		} else
+			return pud_alloc(&init_mm, p4dp, address);
+	}
+	return pud_offset(p4dp, address);
+}
+
+static inline pmd_t *vmemmap_pmd_alloc(pud_t *pudp, int node,
+				       unsigned long address)
+{
+	pmd_t *pmd;
+
+	/* All early vmemmap mapping to keep simple do it at PAGE_SIZE */
+	if (unlikely(pud_none(*pudp))) {
+		if (unlikely(!slab_is_available())) {
+			pmd = early_alloc_pgtable(PAGE_SIZE, node, 0, 0);
+			pud_populate(&init_mm, pudp, pmd);
+		} else
+			return pmd_alloc(&init_mm, pudp, address);
+	}
+	return pmd_offset(pudp, address);
+}
+
+static inline pte_t *vmemmap_pte_alloc(pmd_t *pmdp, int node,
+				       unsigned long address)
+{
+	pte_t *pte;
+
+	/* All early vmemmap mapping to keep simple do it at PAGE_SIZE */
+	if (unlikely(pmd_none(*pmdp))) {
+		if (unlikely(!slab_is_available())) {
+			pte = early_alloc_pgtable(PAGE_SIZE, node, 0, 0);
+			pmd_populate(&init_mm, pmdp, pte);
+		} else
+			return pte_alloc_kernel(pmdp, address);
+	}
+	return pte_offset_kernel(pmdp, address);
+}
+
+
+
+int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end, int node,
+				      struct vmem_altmap *altmap)
 {
 	unsigned long addr;
+	unsigned long next;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
 
-	addr = (unsigned long)page_address(page);
+	/*
+	 * If altmap is present, Make sure we align the start vmemmap addr
+	 * to PAGE_SIZE so that we calculate the correct start_pfn in
+	 * altmap boundary check to decide whether we should use altmap or
+	 * RAM based backing memory allocation. Also the address need to be
+	 * aligned for set_pte operation. If the start addr is already
+	 * PMD_SIZE aligned and with in the altmap boundary then we will
+	 * try to use a pmd size altmap mapping else we go for page size
+	 * mapping.
+	 *
+	 * If altmap is not present, align the vmemmap addr to PMD_SIZE and
+	 * always allocate a PMD size page for vmemmap backing.
+	 *
+	 */
 
-	if (enable)
-		set_memory_p(addr, numpages);
+	if (altmap)
+		start = ALIGN_DOWN(start, PAGE_SIZE);
 	else
-		set_memory_np(addr, numpages);
+		start = ALIGN_DOWN(start, PMD_SIZE);
+
+	for (addr = start; addr < end; addr = next) {
+		next = pmd_addr_end(addr, end);
+
+		pgd = pgd_offset_k(addr);
+		p4d = p4d_offset(pgd, addr);
+		pud = vmemmap_pud_alloc(p4d, node, addr);
+		if (!pud)
+			return -ENOMEM;
+		pmd = vmemmap_pmd_alloc(pud, node, addr);
+		if (!pmd)
+			return -ENOMEM;
+
+		if (pmd_none(READ_ONCE(*pmd))) {
+			void *p;
+
+			/*
+			 * keep it simple by checking addr PMD_SIZE alignment
+			 * and verifying the device boundary condition.
+			 * For us to use a pmd mapping, both addr and pfn should
+			 * be aligned. We skip if addr is not aligned and for
+			 * pfn we hope we have extra area in the altmap that
+			 * can help to find an aligned block. This can result
+			 * in altmap block allocation failures, in which case
+			 * we fallback to RAM for vmemmap allocation.
+			 */
+			if (altmap && (!IS_ALIGNED(addr, PMD_SIZE) ||
+			    altmap_cross_boundary(altmap, addr, PMD_SIZE))) {
+				/*
+				 * make sure we don't create altmap mappings
+				 * covering things outside the device.
+				 */
+				goto base_mapping;
+			}
+
+			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
+			if (p) {
+				vmemmap_set_pmd(pmd, p, node, addr, next);
+				pr_debug("PMD_SIZE vmemmap mapping\n");
+				continue;
+			} else {
+				/*
+				 * A vmemmap block allocation can fail due to
+				 * alignment requirements and we trying to align
+				 * things aggressively there by running out of
+				 * space. Try base mapping on failure.
+				 */
+				goto base_mapping;
+			}
+		} else if (vmemmap_check_pmd(pmd, node, addr, next)) {
+			/*
+			 * If a huge mapping exist due to early call to
+			 * vmemmap_populate, let's try to use that.
+			 */
+			continue;
+		}
+base_mapping:
+		/*
+		 * Not able allocate higher order memory to back memmap
+		 * or we found a pointer to pte page. Allocate base page
+		 * size vmemmap
+		 */
+		pte = vmemmap_pte_alloc(pmd, node, addr);
+		if (!pte)
+			return -ENOMEM;
+
+		pte = radix__vmemmap_pte_populate(pmd, addr, node, altmap, NULL);
+		if (!pte)
+			return -ENOMEM;
+
+		vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+		next = addr + PAGE_SIZE;
+	}
+	return 0;
+}
+
+static pte_t * __meminit radix__vmemmap_populate_address(unsigned long addr, int node,
+							 struct vmem_altmap *altmap,
+							 struct page *reuse)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset_k(addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = vmemmap_pud_alloc(p4d, node, addr);
+	if (!pud)
+		return NULL;
+	pmd = vmemmap_pmd_alloc(pud, node, addr);
+	if (!pmd)
+		return NULL;
+	if (pmd_leaf(*pmd))
+		/*
+		 * The second page is mapped as a hugepage due to a nearby request.
+		 * Force our mapping to page size without deduplication
+		 */
+		return NULL;
+	pte = vmemmap_pte_alloc(pmd, node, addr);
+	if (!pte)
+		return NULL;
+	radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL);
+	vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+	return pte;
+}
+
+static pte_t * __meminit vmemmap_compound_tail_page(unsigned long addr,
+						    unsigned long pfn_offset, int node)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long map_addr;
+
+	/* the second vmemmap page which we use for duplication */
+	map_addr = addr - pfn_offset * sizeof(struct page) + PAGE_SIZE;
+	pgd = pgd_offset_k(map_addr);
+	p4d = p4d_offset(pgd, map_addr);
+	pud = vmemmap_pud_alloc(p4d, node, map_addr);
+	if (!pud)
+		return NULL;
+	pmd = vmemmap_pmd_alloc(pud, node, map_addr);
+	if (!pmd)
+		return NULL;
+	if (pmd_leaf(*pmd))
+		/*
+		 * The second page is mapped as a hugepage due to a nearby request.
+		 * Force our mapping to page size without deduplication
+		 */
+		return NULL;
+	pte = vmemmap_pte_alloc(pmd, node, map_addr);
+	if (!pte)
+		return NULL;
+	/*
+	 * Check if there exist a mapping to the left
+	 */
+	if (pte_none(*pte)) {
+		/*
+		 * Populate the head page vmemmap page.
+		 * It can fall in different pmd, hence
+		 * vmemmap_populate_address()
+		 */
+		pte = radix__vmemmap_populate_address(map_addr - PAGE_SIZE, node, NULL, NULL);
+		if (!pte)
+			return NULL;
+		/*
+		 * Populate the tail pages vmemmap page
+		 */
+		pte = radix__vmemmap_pte_populate(pmd, map_addr, node, NULL, NULL);
+		if (!pte)
+			return NULL;
+		vmemmap_verify(pte, node, map_addr, map_addr + PAGE_SIZE);
+		return pte;
+	}
+	return pte;
 }
+
+int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
+					      unsigned long start,
+					      unsigned long end, int node,
+					      struct dev_pagemap *pgmap)
+{
+	/*
+	 * we want to map things as base page size mapping so that
+	 * we can save space in vmemmap. We could have huge mapping
+	 * covering out both edges.
+	 */
+	unsigned long addr;
+	unsigned long addr_pfn = start_pfn;
+	unsigned long next;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	for (addr = start; addr < end; addr = next) {
+
+		pgd = pgd_offset_k(addr);
+		p4d = p4d_offset(pgd, addr);
+		pud = vmemmap_pud_alloc(p4d, node, addr);
+		if (!pud)
+			return -ENOMEM;
+		pmd = vmemmap_pmd_alloc(pud, node, addr);
+		if (!pmd)
+			return -ENOMEM;
+
+		if (pmd_leaf(READ_ONCE(*pmd))) {
+			/* existing huge mapping. Skip the range */
+			addr_pfn += (PMD_SIZE >> PAGE_SHIFT);
+			next = pmd_addr_end(addr, end);
+			continue;
+		}
+		pte = vmemmap_pte_alloc(pmd, node, addr);
+		if (!pte)
+			return -ENOMEM;
+		if (!pte_none(*pte)) {
+			/*
+			 * This could be because we already have a compound
+			 * page whose VMEMMAP_RESERVE_NR pages were mapped and
+			 * this request fall in those pages.
+			 */
+			addr_pfn += 1;
+			next = addr + PAGE_SIZE;
+			continue;
+		} else {
+			unsigned long nr_pages = pgmap_vmemmap_nr(pgmap);
+			unsigned long pfn_offset = addr_pfn - ALIGN_DOWN(addr_pfn, nr_pages);
+			pte_t *tail_page_pte;
+
+			/*
+			 * if the address is aligned to huge page size it is the
+			 * head mapping.
+			 */
+			if (pfn_offset == 0) {
+				/* Populate the head page vmemmap page */
+				pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL);
+				if (!pte)
+					return -ENOMEM;
+				vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+				/*
+				 * Populate the tail pages vmemmap page
+				 * It can fall in different pmd, hence
+				 * vmemmap_populate_address()
+				 */
+				pte = radix__vmemmap_populate_address(addr + PAGE_SIZE, node, NULL, NULL);
+				if (!pte)
+					return -ENOMEM;
+
+				addr_pfn += 2;
+				next = addr + 2 * PAGE_SIZE;
+				continue;
+			}
+			/*
+			 * get the 2nd mapping details
+			 * Also create it if that doesn't exist
+			 */
+			tail_page_pte = vmemmap_compound_tail_page(addr, pfn_offset, node);
+			if (!tail_page_pte) {
+
+				pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, NULL);
+				if (!pte)
+					return -ENOMEM;
+				vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+				addr_pfn += 1;
+				next = addr + PAGE_SIZE;
+				continue;
+			}
+
+			pte = radix__vmemmap_pte_populate(pmd, addr, node, NULL, pte_page(*tail_page_pte));
+			if (!pte)
+				return -ENOMEM;
+			vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+			addr_pfn += 1;
+			next = addr + PAGE_SIZE;
+			continue;
+		}
+	}
+	return 0;
+}
+
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size)
+{
+	remove_pagetable(start, start + page_size, true, NULL);
+}
+
+void __ref radix__vmemmap_free(unsigned long start, unsigned long end,
+			       struct vmem_altmap *altmap)
+{
+	remove_pagetable(start, end, false, altmap);
+}
+#endif
 #endif
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -948,12 +1433,29 @@ unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long add
 	unsigned long old;
 
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(!radix__pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
+	WARN_ON(!radix__pmd_trans_huge(*pmdp));
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
 #endif
 
-	old = radix__pte_update(mm, addr, (pte_t *)pmdp, clr, set, 1);
-	trace_hugepage_update(addr, old, clr, set);
+	old = radix__pte_update(mm, addr, pmdp_ptep(pmdp), clr, set, 1);
+	trace_hugepage_update_pmd(addr, old, clr, set);
+
+	return old;
+}
+
+unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr,
+					 pud_t *pudp, unsigned long clr,
+					 unsigned long set)
+{
+	unsigned long old;
+
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pud_trans_huge(*pudp));
+	assert_spin_locked(pud_lockptr(mm, pudp));
+#endif
+
+	old = radix__pte_update(mm, addr, pudp_ptep(pudp), clr, set, 1);
+	trace_hugepage_update_pud(addr, old, clr, set);
 
 	return old;
 }
@@ -966,7 +1468,6 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(radix__pmd_trans_huge(*pmdp));
-	VM_BUG_ON(pmd_devmap(*pmdp));
 	/*
 	 * khugepaged calls this for normal pmd
 	 */
@@ -1034,14 +1535,25 @@ pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
 	return old_pmd;
 }
 
+pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pud_t *pudp)
+{
+	pud_t old_pud;
+	unsigned long old;
+
+	old = radix__pud_hugepage_update(mm, addr, pudp, ~0UL, 0);
+	old_pud = __pud(old);
+	return old_pud;
+}
+
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
 				  pte_t entry, unsigned long address, int psize)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED |
-					      _PAGE_RW | _PAGE_EXEC);
+	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY |
+					      _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
 
 	unsigned long change = pte_val(entry) ^ pte_val(*ptep);
 	/*
@@ -1112,7 +1624,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 
 int pud_clear_huge(pud_t *pud)
 {
-	if (pud_is_leaf(*pud)) {
+	if (pud_leaf(*pud)) {
 		pud_clear(pud);
 		return 1;
 	}
@@ -1159,7 +1671,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 
 int pmd_clear_huge(pmd_t *pmd)
 {
-	if (pmd_is_leaf(*pmd)) {
+	if (pmd_leaf(*pmd)) {
 		pmd_clear(pmd);
 		return 1;
 	}
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index ce804b7bf84e..9e1f6558d026 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -127,21 +127,6 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
-static __always_inline void __tlbie_pid_lpid(unsigned long pid,
-					     unsigned long lpid,
-					     unsigned long ric)
-{
-	unsigned long rb, rs, prs, r;
-
-	rb = PPC_BIT(53); /* IS = 1 */
-	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
-	prs = 1; /* process scoped */
-	r = 1;   /* radix format */
-
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
-}
 static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
@@ -202,23 +187,6 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
-static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
-					    unsigned long lpid,
-					    unsigned long ap, unsigned long ric)
-{
-	unsigned long rb, rs, prs, r;
-
-	rb = va & ~(PPC_BITMASK(52, 63));
-	rb |= ap << PPC_BITLSHIFT(58);
-	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
-	prs = 1; /* process scoped */
-	r = 1;   /* radix format */
-
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(0, 0, rb, rs, ric, prs, r);
-}
-
 static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
 					    unsigned long ap, unsigned long ric)
 {
@@ -264,22 +232,6 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid,
 	}
 }
 
-static inline void fixup_tlbie_va_range_lpid(unsigned long va,
-					     unsigned long pid,
-					     unsigned long lpid,
-					     unsigned long ap)
-{
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
-		asm volatile("ptesync" : : : "memory");
-		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
-	}
-
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
-		asm volatile("ptesync" : : : "memory");
-		__tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
-	}
-}
-
 static inline void fixup_tlbie_pid(unsigned long pid)
 {
 	/*
@@ -299,26 +251,6 @@ static inline void fixup_tlbie_pid(unsigned long pid)
 	}
 }
 
-static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
-{
-	/*
-	 * We can use any address for the invalidation, pick one which is
-	 * probably unused as an optimisation.
-	 */
-	unsigned long va = ((1UL << 52) - 1);
-
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
-		asm volatile("ptesync" : : : "memory");
-		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
-	}
-
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
-		asm volatile("ptesync" : : : "memory");
-		__tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
-				RIC_FLUSH_TLB);
-	}
-}
-
 static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid,
 				       unsigned long ap)
 {
@@ -416,31 +348,6 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
-				   unsigned long ric)
-{
-	asm volatile("ptesync" : : : "memory");
-
-	/*
-	 * Workaround the fact that the "ric" argument to __tlbie_pid
-	 * must be a compile-time contraint to match the "i" constraint
-	 * in the asm statement.
-	 */
-	switch (ric) {
-	case RIC_FLUSH_TLB:
-		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
-		fixup_tlbie_pid_lpid(pid, lpid);
-		break;
-	case RIC_FLUSH_PWC:
-		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
-		break;
-	case RIC_FLUSH_ALL:
-	default:
-		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
-		fixup_tlbie_pid_lpid(pid, lpid);
-	}
-	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-}
 struct tlbiel_pid {
 	unsigned long pid;
 	unsigned long ric;
@@ -566,20 +473,6 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end,
 	fixup_tlbie_va_range(addr - page_size, pid, ap);
 }
 
-static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
-					 unsigned long pid, unsigned long lpid,
-					 unsigned long page_size,
-					 unsigned long psize)
-{
-	unsigned long addr;
-	unsigned long ap = mmu_get_ap(psize);
-
-	for (addr = start; addr < end; addr += page_size)
-		__tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
-
-	fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
-}
-
 static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
 				      unsigned long psize, unsigned long ric)
 {
@@ -660,18 +553,6 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
-					unsigned long pid, unsigned long lpid,
-					unsigned long page_size,
-					unsigned long psize, bool also_pwc)
-{
-	asm volatile("ptesync" : : : "memory");
-	if (also_pwc)
-		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
-	__tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
-	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-}
-
 static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
 				unsigned long start, unsigned long end,
 				unsigned long pid, unsigned long page_size,
@@ -795,12 +676,20 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush)
 		goto out;
 
 	if (current->active_mm == mm) {
+		unsigned long flags;
+
 		WARN_ON_ONCE(current->mm != NULL);
-		/* Is a kernel thread and is using mm as the lazy tlb */
+		/*
+		 * It is a kernel thread and is using mm as the lazy tlb, so
+		 * switch it to init_mm. This is not always called from IPI
+		 * (e.g., flush_type_needed), so must disable irqs.
+		 */
+		local_irq_save(flags);
 		mmgrab_lazy_tlb(&init_mm);
 		current->active_mm = &init_mm;
 		switch_mm_irqs_off(mm, &init_mm, current);
 		mmdrop_lazy_tlb(mm);
+		local_irq_restore(flags);
 	}
 
 	/*
@@ -812,7 +701,7 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush)
 	 * that's what the caller expects.
 	 */
 	if (cpumask_test_cpu(cpu, mm_cpumask(mm))) {
-		atomic_dec(&mm->context.active_cpus);
+		dec_mm_active_cpus(mm);
 		cpumask_clear_cpu(cpu, mm_cpumask(mm));
 		always_flush = true;
 	}
@@ -979,6 +868,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 		}
 	}
 	preempt_enable();
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 EXPORT_SYMBOL(radix__flush_tlb_mm);
 
@@ -1012,6 +902,7 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
 			_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL);
 	}
 	preempt_enable();
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
 void radix__flush_all_mm(struct mm_struct *mm)
@@ -1220,6 +1111,7 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 	}
 out:
 	preempt_enable();
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
 void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -1305,7 +1197,28 @@ void radix__tlb_flush(struct mmu_gather *tlb)
 	 * See the comment for radix in arch_exit_mmap().
 	 */
 	if (tlb->fullmm) {
-		__flush_all_mm(mm, true);
+		if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) {
+			/*
+			 * Shootdown based lazy tlb mm refcounting means we
+			 * have to IPI everyone in the mm_cpumask anyway soon
+			 * when the mm goes away, so might as well do it as
+			 * part of the final flush now.
+			 *
+			 * If lazy shootdown was improved to reduce IPIs (e.g.,
+			 * by batching), then it may end up being better to use
+			 * tlbies here instead.
+			 */
+			preempt_disable();
+
+			smp_mb(); /* see radix__flush_tlb_mm */
+			exit_flush_lazy_tlbs(mm);
+			__flush_all_mm(mm, true);
+
+			preempt_enable();
+		} else {
+			__flush_all_mm(mm, true);
+		}
+
 	} else if ( (psize = radix_get_mmu_psize(page_size)) == -1) {
 		if (!tlb->freed_tables)
 			radix__flush_tlb_mm(mm);
@@ -1384,6 +1297,7 @@ static void __radix__flush_tlb_range_psize(struct mm_struct *mm,
 	}
 out:
 	preempt_enable();
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
 void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
@@ -1453,6 +1367,13 @@ void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL(radix__flush_pmd_tlb_range);
 
+void radix__flush_pud_tlb_range(struct vm_area_struct *vma,
+				unsigned long start, unsigned long end)
+{
+	radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_1G);
+}
+EXPORT_SYMBOL(radix__flush_pud_tlb_range);
+
 void radix__flush_tlb_all(void)
 {
 	unsigned long rb,prs,r,rs;
@@ -1478,6 +1399,127 @@ void radix__flush_tlb_all(void)
 }
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static __always_inline void __tlbie_pid_lpid(unsigned long pid,
+					     unsigned long lpid,
+					     unsigned long ric)
+{
+	unsigned long rb, rs, prs, r;
+
+	rb = PPC_BIT(53); /* IS = 1 */
+	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
+	prs = 1; /* process scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
+static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
+					    unsigned long lpid,
+					    unsigned long ap, unsigned long ric)
+{
+	unsigned long rb, rs, prs, r;
+
+	rb = va & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
+	prs = 1; /* process scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
+static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
+{
+	/*
+	 * We can use any address for the invalidation, pick one which is
+	 * probably unused as an optimisation.
+	 */
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
+				RIC_FLUSH_TLB);
+	}
+}
+
+static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
+				   unsigned long ric)
+{
+	asm volatile("ptesync" : : : "memory");
+
+	/*
+	 * Workaround the fact that the "ric" argument to __tlbie_pid
+	 * must be a compile-time contraint to match the "i" constraint
+	 * in the asm statement.
+	 */
+	switch (ric) {
+	case RIC_FLUSH_TLB:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
+		fixup_tlbie_pid_lpid(pid, lpid);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
+		fixup_tlbie_pid_lpid(pid, lpid);
+	}
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
+
+static inline void fixup_tlbie_va_range_lpid(unsigned long va,
+					     unsigned long pid,
+					     unsigned long lpid,
+					     unsigned long ap)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
+	}
+}
+
+static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
+					 unsigned long pid, unsigned long lpid,
+					 unsigned long page_size,
+					 unsigned long psize)
+{
+	unsigned long addr;
+	unsigned long ap = mmu_get_ap(psize);
+
+	for (addr = start; addr < end; addr += page_size)
+		__tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
+
+	fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
+}
+
+static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
+					unsigned long pid, unsigned long lpid,
+					unsigned long page_size,
+					unsigned long psize, bool also_pwc)
+{
+	asm volatile("ptesync" : : : "memory");
+	if (also_pwc)
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+	__tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
+
 /*
  * Performs process-scoped invalidations for a given LPID
  * as part of H_RPT_INVALIDATE hcall.
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 6956f637a38c..15f73abd1506 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -13,6 +13,7 @@
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/paca.h>
+#include <asm/lppaca.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
@@ -23,7 +24,7 @@
 #include <linux/pgtable.h>
 
 #include <asm/udbg.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 
 #include "internal.h"
 
@@ -41,6 +42,15 @@ early_param("stress_slb", parse_stress_slb);
 
 __ro_after_init DEFINE_STATIC_KEY_FALSE(stress_slb_key);
 
+bool no_slb_preload __initdata;
+static int __init parse_no_slb_preload(char *p)
+{
+	no_slb_preload = true;
+	return 0;
+}
+early_param("no_slb_preload", parse_no_slb_preload);
+__ro_after_init DEFINE_STATIC_KEY_FALSE(no_slb_preload_key);
+
 static void assert_slb_presence(bool present, unsigned long ea)
 {
 #ifdef CONFIG_DEBUG_VM
@@ -293,11 +303,14 @@ static bool preload_hit(struct thread_info *ti, unsigned long esid)
 	return false;
 }
 
-static bool preload_add(struct thread_info *ti, unsigned long ea)
+static void preload_add(struct thread_info *ti, unsigned long ea)
 {
 	unsigned char idx;
 	unsigned long esid;
 
+	if (slb_preload_disabled())
+		return;
+
 	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
 		/* EAs are stored >> 28 so 256MB segments don't need clearing */
 		if (ea & ESID_MASK_1T)
@@ -307,7 +320,7 @@ static bool preload_add(struct thread_info *ti, unsigned long ea)
 	esid = ea >> SID_SHIFT;
 
 	if (preload_hit(ti, esid))
-		return false;
+		return;
 
 	idx = (ti->slb_preload_tail + ti->slb_preload_nr) % SLB_PRELOAD_NR;
 	ti->slb_preload_esid[idx] = esid;
@@ -315,8 +328,6 @@ static bool preload_add(struct thread_info *ti, unsigned long ea)
 		ti->slb_preload_tail = (ti->slb_preload_tail + 1) % SLB_PRELOAD_NR;
 	else
 		ti->slb_preload_nr++;
-
-	return true;
 }
 
 static void preload_age(struct thread_info *ti)
@@ -327,94 +338,6 @@ static void preload_age(struct thread_info *ti)
 	ti->slb_preload_tail = (ti->slb_preload_tail + 1) % SLB_PRELOAD_NR;
 }
 
-void slb_setup_new_exec(void)
-{
-	struct thread_info *ti = current_thread_info();
-	struct mm_struct *mm = current->mm;
-	unsigned long exec = 0x10000000;
-
-	WARN_ON(irqs_disabled());
-
-	/*
-	 * preload cache can only be used to determine whether a SLB
-	 * entry exists if it does not start to overflow.
-	 */
-	if (ti->slb_preload_nr + 2 > SLB_PRELOAD_NR)
-		return;
-
-	hard_irq_disable();
-
-	/*
-	 * We have no good place to clear the slb preload cache on exec,
-	 * flush_thread is about the earliest arch hook but that happens
-	 * after we switch to the mm and have already preloaded the SLBEs.
-	 *
-	 * For the most part that's probably okay to use entries from the
-	 * previous exec, they will age out if unused. It may turn out to
-	 * be an advantage to clear the cache before switching to it,
-	 * however.
-	 */
-
-	/*
-	 * preload some userspace segments into the SLB.
-	 * Almost all 32 and 64bit PowerPC executables are linked at
-	 * 0x10000000 so it makes sense to preload this segment.
-	 */
-	if (!is_kernel_addr(exec)) {
-		if (preload_add(ti, exec))
-			slb_allocate_user(mm, exec);
-	}
-
-	/* Libraries and mmaps. */
-	if (!is_kernel_addr(mm->mmap_base)) {
-		if (preload_add(ti, mm->mmap_base))
-			slb_allocate_user(mm, mm->mmap_base);
-	}
-
-	/* see switch_slb */
-	asm volatile("isync" : : : "memory");
-
-	local_irq_enable();
-}
-
-void preload_new_slb_context(unsigned long start, unsigned long sp)
-{
-	struct thread_info *ti = current_thread_info();
-	struct mm_struct *mm = current->mm;
-	unsigned long heap = mm->start_brk;
-
-	WARN_ON(irqs_disabled());
-
-	/* see above */
-	if (ti->slb_preload_nr + 3 > SLB_PRELOAD_NR)
-		return;
-
-	hard_irq_disable();
-
-	/* Userspace entry address. */
-	if (!is_kernel_addr(start)) {
-		if (preload_add(ti, start))
-			slb_allocate_user(mm, start);
-	}
-
-	/* Top of stack, grows down. */
-	if (!is_kernel_addr(sp)) {
-		if (preload_add(ti, sp))
-			slb_allocate_user(mm, sp);
-	}
-
-	/* Bottom of heap, grows up. */
-	if (heap && !is_kernel_addr(heap)) {
-		if (preload_add(ti, heap))
-			slb_allocate_user(mm, heap);
-	}
-
-	/* see switch_slb */
-	asm volatile("isync" : : : "memory");
-
-	local_irq_enable();
-}
-
 static void slb_cache_slbie_kernel(unsigned int index)
 {
 	unsigned long slbie_data = get_paca()->slb_cache[index];
@@ -501,6 +424,9 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 
 	copy_mm_to_paca(mm);
 
+	if (slb_preload_disabled())
+		return;
+
 	/*
 	 * We gradually age out SLBs after a number of context switches to
 	 * reduce reload overhead of unused entries (like we do with FP/VEC
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index c0b58afb9a47..28bec5bc7879 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -22,7 +22,7 @@
 #include <linux/security.h>
 #include <asm/mman.h>
 #include <asm/mmu.h>
-#include <asm/copro.h>
+#include <asm/spu.h>
 #include <asm/hugetlb.h>
 #include <asm/mmu_context.h>
 
@@ -248,7 +248,9 @@ static void slice_convert(struct mm_struct *mm,
 
 	spin_unlock_irqrestore(&slice_convert_lock, flags);
 
-	copro_flush_all_slbs(mm);
+#ifdef CONFIG_SPU_BASE
+	spu_flush_all_slbs(mm);
+#endif
 }
 
 /*
@@ -282,12 +284,10 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 	unsigned long found, next_end;
-	struct vm_unmapped_area_info info;
-
-	info.flags = 0;
-	info.length = len;
-	info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
-	info.align_offset = 0;
+	struct vm_unmapped_area_info info = {
+		.length = len,
+		.align_mask = PAGE_MASK & ((1ul << pshift) - 1),
+	};
 	/*
 	 * Check till the allow max value for this mmap request
 	 */
@@ -326,13 +326,13 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 	unsigned long found, prev;
-	struct vm_unmapped_area_info info;
+	struct vm_unmapped_area_info info = {
+		.flags = VM_UNMAPPED_AREA_TOPDOWN,
+		.length = len,
+		.align_mask = PAGE_MASK & ((1ul << pshift) - 1),
+	};
 	unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr);
 
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
-	info.align_offset = 0;
 	/*
 	 * If we are trying to allocate above DEFAULT_MAP_WINDOW
 	 * Add the different to the mmap_base.
@@ -635,30 +635,58 @@ return_addr:
 }
 EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
 
+#ifdef CONFIG_HUGETLB_PAGE
+static int file_to_psize(struct file *file)
+{
+	struct hstate *hstate = hstate_file(file);
+
+	return shift_to_mmu_psize(huge_page_shift(hstate));
+}
+#else
+static int file_to_psize(struct file *file)
+{
+	return 0;
+}
+#endif
+
 unsigned long arch_get_unmapped_area(struct file *filp,
 				     unsigned long addr,
 				     unsigned long len,
 				     unsigned long pgoff,
-				     unsigned long flags)
+				     unsigned long flags,
+				     vm_flags_t vm_flags)
 {
+	unsigned int psize;
+
 	if (radix_enabled())
-		return generic_get_unmapped_area(filp, addr, len, pgoff, flags);
+		return generic_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags);
 
-	return slice_get_unmapped_area(addr, len, flags,
-				       mm_ctx_user_psize(&current->mm->context), 0);
+	if (filp && is_file_hugepages(filp))
+		psize = file_to_psize(filp);
+	else
+		psize = mm_ctx_user_psize(&current->mm->context);
+
+	return slice_get_unmapped_area(addr, len, flags, psize, 0);
 }
 
 unsigned long arch_get_unmapped_area_topdown(struct file *filp,
 					     const unsigned long addr0,
 					     const unsigned long len,
 					     const unsigned long pgoff,
-					     const unsigned long flags)
+					     const unsigned long flags,
+					     vm_flags_t vm_flags)
 {
+	unsigned int psize;
+
 	if (radix_enabled())
-		return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags);
+		return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags, vm_flags);
+
+	if (filp && is_file_hugepages(filp))
+		psize = file_to_psize(filp);
+	else
+		psize = mm_ctx_user_psize(&current->mm->context);
 
-	return slice_get_unmapped_area(addr0, len, flags,
-				       mm_ctx_user_psize(&current->mm->context), 1);
+	return slice_get_unmapped_area(addr0, len, flags, psize, 1);
 }
 
 unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr)
@@ -788,20 +816,4 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 
 	return 1UL << mmu_psize_to_shift(get_slice_psize(vma->vm_mm, vma->vm_start));
 }
-
-static int file_to_psize(struct file *file)
-{
-	struct hstate *hstate = hstate_file(file);
-	return shift_to_mmu_psize(huge_page_shift(hstate));
-}
-
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-					unsigned long len, unsigned long pgoff,
-					unsigned long flags)
-{
-	if (radix_enabled())
-		return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
-
-	return slice_get_unmapped_area(addr, len, flags, file_to_psize(file), 1);
-}
 #endif
diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c
index b75a9fb99599..ec98e526167e 100644
--- a/arch/powerpc/mm/book3s64/subpage_prot.c
+++ b/arch/powerpc/mm/book3s64/subpage_prot.c
@@ -71,6 +71,8 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
 	if (pmd_none(*pmd))
 		return;
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	if (!pte)
+		return;
 	arch_enter_lazy_mmu_mode();
 	for (; npages > 0; --npages) {
 		pte_update(mm, addr, pte, 0, 0, 0);
@@ -143,6 +145,7 @@ static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
 
 static const struct mm_walk_ops subpage_walk_ops = {
 	.pmd_entry	= subpage_walk_pmd_entry,
+	.walk_lock	= PGWALK_WRLOCK_VERIFY,
 };
 
 static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/powerpc/mm/cacheflush.c b/arch/powerpc/mm/cacheflush.c
index 0e9b4879c0f9..7186516eca52 100644
--- a/arch/powerpc/mm/cacheflush.c
+++ b/arch/powerpc/mm/cacheflush.c
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(flush_icache_range);
 
 #ifdef CONFIG_HIGHMEM
 /**
- * flush_dcache_icache_phys() - Flush a page by it's physical address
+ * flush_dcache_icache_phys() - Flush a page by its physical address
  * @physaddr: the physical address of the page
  */
 static void flush_dcache_icache_phys(unsigned long physaddr)
@@ -148,44 +148,31 @@ static void __flush_dcache_icache(void *p)
 	invalidate_icache_range(addr, addr + PAGE_SIZE);
 }
 
-static void flush_dcache_icache_hugepage(struct page *page)
+void flush_dcache_icache_folio(struct folio *folio)
 {
-	int i;
-	int nr = compound_nr(page);
+	unsigned int i, nr = folio_nr_pages(folio);
 
-	if (!PageHighMem(page)) {
+	if (flush_coherent_icache())
+		return;
+
+	if (!folio_test_highmem(folio)) {
+		void *addr = folio_address(folio);
 		for (i = 0; i < nr; i++)
-			__flush_dcache_icache(lowmem_page_address(page + i));
-	} else {
+			__flush_dcache_icache(addr + i * PAGE_SIZE);
+	} else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
 		for (i = 0; i < nr; i++) {
-			void *start = kmap_local_page(page + i);
+			void *start = kmap_local_folio(folio, i * PAGE_SIZE);
 
 			__flush_dcache_icache(start);
 			kunmap_local(start);
 		}
-	}
-}
-
-void flush_dcache_icache_page(struct page *page)
-{
-	if (flush_coherent_icache())
-		return;
-
-	if (PageCompound(page))
-		return flush_dcache_icache_hugepage(page);
-
-	if (!PageHighMem(page)) {
-		__flush_dcache_icache(lowmem_page_address(page));
-	} else if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
-		void *start = kmap_local_page(page);
-
-		__flush_dcache_icache(start);
-		kunmap_local(start);
 	} else {
-		flush_dcache_icache_phys(page_to_phys(page));
+		unsigned long pfn = folio_pfn(folio);
+		for (i = 0; i < nr; i++)
+			flush_dcache_icache_phys((pfn + i) * PAGE_SIZE);
 	}
 }
-EXPORT_SYMBOL(flush_dcache_icache_page);
+EXPORT_SYMBOL(flush_dcache_icache_folio);
 
 void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
 {
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 7c507fb48182..f5f8692e2c69 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -12,8 +12,6 @@
 #include <linux/export.h>
 #include <asm/reg.h>
 #include <asm/copro.h>
-#include <asm/spu.h>
-#include <misc/cxl-base.h>
 
 /*
  * This ought to be kept in sync with the powerpc specific do_page_fault
@@ -33,19 +31,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 	if (mm->pgd == NULL)
 		return -EFAULT;
 
-	mmap_read_lock(mm);
-	ret = -EFAULT;
-	vma = find_vma(mm, ea);
+	vma = lock_mm_and_find_vma(mm, ea, NULL);
 	if (!vma)
-		goto out_unlock;
-
-	if (ea < vma->vm_start) {
-		if (!(vma->vm_flags & VM_GROWSDOWN))
-			goto out_unlock;
-		if (expand_stack(vma, ea))
-			goto out_unlock;
-	}
+		return -EFAULT;
 
+	ret = -EFAULT;
 	is_write = dsisr & DSISR_ISSTORE;
 	if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
@@ -143,13 +133,4 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(copro_calculate_slb);
-
-void copro_flush_all_slbs(struct mm_struct *mm)
-{
-#ifdef CONFIG_SPU_BASE
-	spu_flush_all_slbs(mm);
-#endif
-	cxl_slbia(mm);
-}
-EXPORT_SYMBOL_GPL(copro_flush_all_slbs);
 #endif
diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
index 2369d1bf2411..8dd7b340d51f 100644
--- a/arch/powerpc/mm/drmem.c
+++ b/arch/powerpc/mm/drmem.c
@@ -67,7 +67,7 @@ static int drmem_update_dt_v1(struct device_node *memory,
 	struct property *new_prop;
 	struct of_drconf_cell_v1 *dr_cell;
 	struct drmem_lmb *lmb;
-	u32 *p;
+	__be32 *p;
 
 	new_prop = clone_property(prop, prop->length);
 	if (!new_prop)
@@ -393,17 +393,17 @@ static const __be32 *of_get_usable_memory(struct device_node *dn)
 int walk_drmem_lmbs(struct device_node *dn, void *data,
 		    int (*func)(struct drmem_lmb *, const __be32 **, void *))
 {
+	struct device_node *root = of_find_node_by_path("/");
 	const __be32 *prop, *usm;
 	int ret = -ENODEV;
 
-	if (!of_root)
+	if (!root)
 		return ret;
 
 	/* Get the address & size cells */
-	of_node_get(of_root);
-	n_root_addr_cells = of_n_addr_cells(of_root);
-	n_root_size_cells = of_n_size_cells(of_root);
-	of_node_put(of_root);
+	n_root_addr_cells = of_n_addr_cells(root);
+	n_root_size_cells = of_n_size_cells(root);
+	of_node_put(root);
 
 	if (init_drmem_lmb_size(dn))
 		return ret;
@@ -491,10 +491,8 @@ static int __init drmem_init(void)
 	const __be32 *prop;
 
 	dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
-	if (!dn) {
-		pr_info("No dynamic reconfiguration memory found\n");
+	if (!dn)
 		return 0;
-	}
 
 	if (init_drmem_lmb_size(dn)) {
 		of_node_put(dn);
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 531177a4ee08..806c74e0d5ab 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/types.h>
 #include <linux/pagemap.h>
 #include <linux/ptrace.h>
@@ -71,28 +72,26 @@ static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long add
 	return __bad_area_nosemaphore(regs, address, SEGV_MAPERR);
 }
 
-static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code)
+static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code,
+		      struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	struct mm_struct *mm = current->mm;
 
 	/*
 	 * Something tried to access memory that isn't in our memory map..
 	 * Fix it, but check if it's kernel or user first..
 	 */
-	mmap_read_unlock(mm);
+	if (mm)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 
 	return __bad_area_nosemaphore(regs, address, si_code);
 }
 
-static noinline int bad_area(struct pt_regs *regs, unsigned long address)
-{
-	return __bad_area(regs, address, SEGV_MAPERR);
-}
-
 static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
+				    struct mm_struct *mm,
 				    struct vm_area_struct *vma)
 {
-	struct mm_struct *mm = current->mm;
 	int pkey;
 
 	/*
@@ -114,7 +113,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
 	 */
 	pkey = vma_pkey(vma);
 
-	mmap_read_unlock(mm);
+	if (mm)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 
 	/*
 	 * If we are in kernel mode, bail out with a SEGV, this will
@@ -129,9 +131,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address,
 	return 0;
 }
 
-static noinline int bad_access(struct pt_regs *regs, unsigned long address)
+static noinline int bad_access(struct pt_regs *regs, unsigned long address,
+			       struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	return __bad_area(regs, address, SEGV_ACCERR);
+	return __bad_area(regs, address, SEGV_ACCERR, mm, vma);
 }
 
 static int do_sigbus(struct pt_regs *regs, unsigned long address,
@@ -216,7 +219,7 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
 	// Read/write fault blocked by KUAP is bad, it can never succeed.
 	if (bad_kuap_fault(regs, address, is_write)) {
 		pr_crit_ratelimited("Kernel attempted to %s user page (%lx) - exploit attempt? (uid: %d)\n",
-				    is_write ? "write" : "read", address,
+				    str_write_read(is_write), address,
 				    from_kuid(&init_user_ns, current_uid()));
 
 		// Fault on user outside of certain regions (eg. copy_tofrom_user()) is bad
@@ -271,14 +274,15 @@ static bool access_error(bool is_write, bool is_exec, struct vm_area_struct *vma
 	}
 
 	/*
-	 * VM_READ, VM_WRITE and VM_EXEC all imply read permissions, as
-	 * defined in protection_map[].  Read faults can only be caused by
-	 * a PROT_NONE mapping, or with a PROT_EXEC-only mapping on Radix.
+	 * VM_READ, VM_WRITE and VM_EXEC may imply read permissions, as
+	 * defined in protection_map[].  In that case Read faults can only be
+	 * caused by a PROT_NONE mapping. However a non exec access on a
+	 * VM_EXEC only mapping is invalid anyway, so report it as such.
 	 */
 	if (unlikely(!vma_is_accessible(vma)))
 		return true;
 
-	if (unlikely(radix_enabled() && ((vma->vm_flags & VM_ACCESS_FLAGS) == VM_EXEC)))
+	if ((vma->vm_flags & VM_ACCESS_FLAGS) == VM_EXEC)
 		return true;
 
 	/*
@@ -365,13 +369,13 @@ static void sanity_check_fault(bool is_write, bool is_user,
  * Define the correct "is_write" bit in error_code based
  * on the processor family
  */
-#if (defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+#ifdef CONFIG_BOOKE
 #define page_fault_is_write(__err)	((__err) & ESR_DST)
 #else
 #define page_fault_is_write(__err)	((__err) & DSISR_ISSTORE)
 #endif
 
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+#ifdef CONFIG_BOOKE
 #define page_fault_is_bad(__err)	(0)
 #elif defined(CONFIG_PPC_8xx)
 #define page_fault_is_bad(__err)	((__err) & DSISR_NOEXEC_OR_G)
@@ -436,10 +440,16 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 	/*
 	 * The kernel should never take an execute fault nor should it
 	 * take a page fault to a kernel address or a page fault to a user
-	 * address outside of dedicated places
+	 * address outside of dedicated places.
+	 *
+	 * Rather than kfence directly reporting false negatives, search whether
+	 * the NIP belongs to the fixup table for cases where fault could come
+	 * from functions like copy_from_kernel_nofault().
 	 */
 	if (unlikely(!is_user && bad_kernel_fault(regs, error_code, address, is_write))) {
-		if (kfence_handle_page_fault(address, is_write, regs))
+		if (is_kfence_address((void *)address) &&
+		    !search_exception_tables(instruction_pointer(regs)) &&
+		    kfence_handle_page_fault(address, is_write, regs))
 			return 0;
 
 		return SIGSEGV;
@@ -474,7 +484,6 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (is_exec)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
-#ifdef CONFIG_PER_VMA_LOCK
 	if (!(flags & FAULT_FLAG_USER))
 		goto lock_mmap;
 
@@ -484,29 +493,31 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	if (unlikely(access_pkey_error(is_write, is_exec,
 				       (error_code & DSISR_KEYFAULT), vma))) {
-		vma_end_read(vma);
-		goto lock_mmap;
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		return bad_access_pkey(regs, address, NULL, vma);
 	}
 
 	if (unlikely(access_error(is_write, is_exec, vma))) {
-		vma_end_read(vma);
-		goto lock_mmap;
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		return bad_access(regs, address, NULL, vma);
 	}
 
 	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
-	vma_end_read(vma);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
 
 	if (!(fault & VM_FAULT_RETRY)) {
 		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	if (fault_signal_pending(fault, regs))
 		return user_mode(regs) ? 0 : SIGBUS;
 
 lock_mmap:
-#endif /* CONFIG_PER_VMA_LOCK */
 
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
@@ -515,47 +526,19 @@ lock_mmap:
 	 * we will deadlock attempting to validate the fault against the
 	 * address space.  Luckily the kernel only validly references user
 	 * space from well defined areas of code, which are listed in the
-	 * exceptions table.
-	 *
-	 * As the vast majority of faults will be valid we will only perform
-	 * the source reference check when there is a possibility of a deadlock.
-	 * Attempt to lock the address space, if we cannot we then validate the
-	 * source.  If this is invalid we can skip the address space check,
-	 * thus avoiding the deadlock.
+	 * exceptions table. lock_mm_and_find_vma() handles that logic.
 	 */
-	if (unlikely(!mmap_read_trylock(mm))) {
-		if (!is_user && !search_exception_tables(regs->nip))
-			return bad_area_nosemaphore(regs, address);
-
 retry:
-		mmap_read_lock(mm);
-	} else {
-		/*
-		 * The above down_read_trylock() might have succeeded in
-		 * which case we'll have missed the might_sleep() from
-		 * down_read():
-		 */
-		might_sleep();
-	}
-
-	vma = find_vma(mm, address);
+	vma = lock_mm_and_find_vma(mm, address, regs);
 	if (unlikely(!vma))
-		return bad_area(regs, address);
-
-	if (unlikely(vma->vm_start > address)) {
-		if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
-			return bad_area(regs, address);
-
-		if (unlikely(expand_stack(vma, address)))
-			return bad_area(regs, address);
-	}
+		return bad_area_nosemaphore(regs, address);
 
 	if (unlikely(access_pkey_error(is_write, is_exec,
 				       (error_code & DSISR_KEYFAULT), vma)))
-		return bad_access_pkey(regs, address, vma);
+		return bad_access_pkey(regs, address, mm, vma);
 
 	if (unlikely(access_error(is_write, is_exec, vma)))
-		return bad_access(regs, address);
+		return bad_access(regs, address, mm, vma);
 
 	/*
 	 * If for any reason at all we couldn't handle the fault,
@@ -584,9 +567,7 @@ retry:
 
 	mmap_read_unlock(current->mm);
 
-#ifdef CONFIG_PER_VMA_LOCK
 done:
-#endif
 	if (unlikely(fault & VM_FAULT_ERROR))
 		return mm_fault_error(regs, address, fault);
 
@@ -645,7 +626,7 @@ static void __bad_page_fault(struct pt_regs *regs, int sig)
 	case INTERRUPT_DATA_STORAGE:
 	case INTERRUPT_H_DATA_STORAGE:
 		pr_alert("BUG: %s on %s at 0x%08lx\n", msg,
-			 is_write ? "write" : "read", regs->dar);
+			 str_write_read(is_write), regs->dar);
 		break;
 	case INTERRUPT_DATA_SEGMENT:
 		pr_alert("BUG: %s at 0x%08lx\n", msg, regs->dar);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index b900933507da..d3c1b749dcfc 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -28,8 +28,6 @@
 
 bool hugetlb_disabled = false;
 
-#define hugepd_none(hpd)	(hpd_val(hpd) == 0)
-
 #define PTE_T_ORDER	(__builtin_ffs(sizeof(pte_basic_t)) - \
 			 __builtin_ffs(sizeof(void *)))
 
@@ -42,156 +40,43 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long s
 	return __find_linux_pte(mm->pgd, addr, NULL, NULL);
 }
 
-static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
-			   unsigned long address, unsigned int pdshift,
-			   unsigned int pshift, spinlock_t *ptl)
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, unsigned long sz)
 {
-	struct kmem_cache *cachep;
-	pte_t *new;
-	int i;
-	int num_hugepd;
-
-	if (pshift >= pdshift) {
-		cachep = PGT_CACHE(PTE_T_ORDER);
-		num_hugepd = 1 << (pshift - pdshift);
-	} else {
-		cachep = PGT_CACHE(pdshift - pshift);
-		num_hugepd = 1;
-	}
-
-	if (!cachep) {
-		WARN_ONCE(1, "No page table cache created for hugetlb tables");
-		return -ENOMEM;
-	}
-
-	new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
 
-	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
-	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
+	addr &= ~(sz - 1);
 
-	if (!new)
-		return -ENOMEM;
+	p4d = p4d_offset(pgd_offset(mm, addr), addr);
+	if (!mm_pud_folded(mm) && sz >= P4D_SIZE)
+		return (pte_t *)p4d;
 
-	/*
-	 * Make sure other cpus find the hugepd set only after a
-	 * properly initialized page table is visible to them.
-	 * For more details look for comment in __pte_alloc().
-	 */
-	smp_wmb();
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+	if (!mm_pmd_folded(mm) && sz >= PUD_SIZE)
+		return (pte_t *)pud;
 
-	spin_lock(ptl);
-	/*
-	 * We have multiple higher-level entries that point to the same
-	 * actual pte location.  Fill in each as we go and backtrack on error.
-	 * We need all of these so the DTLB pgtable walk code can find the
-	 * right higher-level entry without knowing if it's a hugepage or not.
-	 */
-	for (i = 0; i < num_hugepd; i++, hpdp++) {
-		if (unlikely(!hugepd_none(*hpdp)))
-			break;
-		hugepd_populate(hpdp, new, pshift);
-	}
-	/* If we bailed from the for loop early, an error occurred, clean up */
-	if (i < num_hugepd) {
-		for (i = i - 1 ; i >= 0; i--, hpdp--)
-			*hpdp = __hugepd(0);
-		kmem_cache_free(cachep, new);
-	} else {
-		kmemleak_ignore(new);
-	}
-	spin_unlock(ptl);
-	return 0;
-}
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return NULL;
 
-/*
- * At this point we do the placement change only for BOOK3S 64. This would
- * possibly work on other subarchs.
- */
-pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
-		      unsigned long addr, unsigned long sz)
-{
-	pgd_t *pg;
-	p4d_t *p4;
-	pud_t *pu;
-	pmd_t *pm;
-	hugepd_t *hpdp = NULL;
-	unsigned pshift = __ffs(sz);
-	unsigned pdshift = PGDIR_SHIFT;
-	spinlock_t *ptl;
-
-	addr &= ~(sz-1);
-	pg = pgd_offset(mm, addr);
-	p4 = p4d_offset(pg, addr);
+	if (sz >= PMD_SIZE) {
+		/* On 8xx, all hugepages are handled as contiguous PTEs */
+		if (IS_ENABLED(CONFIG_PPC_8xx)) {
+			int i;
 
-#ifdef CONFIG_PPC_BOOK3S_64
-	if (pshift == PGDIR_SHIFT)
-		/* 16GB huge page */
-		return (pte_t *) p4;
-	else if (pshift > PUD_SHIFT) {
-		/*
-		 * We need to use hugepd table
-		 */
-		ptl = &mm->page_table_lock;
-		hpdp = (hugepd_t *)p4;
-	} else {
-		pdshift = PUD_SHIFT;
-		pu = pud_alloc(mm, p4, addr);
-		if (!pu)
-			return NULL;
-		if (pshift == PUD_SHIFT)
-			return (pte_t *)pu;
-		else if (pshift > PMD_SHIFT) {
-			ptl = pud_lockptr(mm, pu);
-			hpdp = (hugepd_t *)pu;
-		} else {
-			pdshift = PMD_SHIFT;
-			pm = pmd_alloc(mm, pu, addr);
-			if (!pm)
-				return NULL;
-			if (pshift == PMD_SHIFT)
-				/* 16MB hugepage */
-				return (pte_t *)pm;
-			else {
-				ptl = pmd_lockptr(mm, pm);
-				hpdp = (hugepd_t *)pm;
+			for (i = 0; i < sz / PMD_SIZE; i++) {
+				if (!pte_alloc_huge(mm, pmd + i, addr))
+					return NULL;
 			}
 		}
+		return (pte_t *)pmd;
 	}
-#else
-	if (pshift >= PGDIR_SHIFT) {
-		ptl = &mm->page_table_lock;
-		hpdp = (hugepd_t *)p4;
-	} else {
-		pdshift = PUD_SHIFT;
-		pu = pud_alloc(mm, p4, addr);
-		if (!pu)
-			return NULL;
-		if (pshift >= PUD_SHIFT) {
-			ptl = pud_lockptr(mm, pu);
-			hpdp = (hugepd_t *)pu;
-		} else {
-			pdshift = PMD_SHIFT;
-			pm = pmd_alloc(mm, pu, addr);
-			if (!pm)
-				return NULL;
-			ptl = pmd_lockptr(mm, pm);
-			hpdp = (hugepd_t *)pm;
-		}
-	}
-#endif
-	if (!hpdp)
-		return NULL;
-
-	if (IS_ENABLED(CONFIG_PPC_8xx) && pshift < PMD_SHIFT)
-		return pte_alloc_map(mm, (pmd_t *)hpdp, addr);
-
-	BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
 
-	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr,
-						  pdshift, pshift, ptl))
-		return NULL;
-
-	return hugepte_offset(*hpdp, addr, pdshift);
+	return pte_alloc_huge(mm, pmd, addr);
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -226,8 +111,9 @@ static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate)
 		return 0;
 	m = phys_to_virt(gpage_freearray[--nr_gpages]);
 	gpage_freearray[nr_gpages] = 0;
-	list_add(&m->list, &huge_boot_pages);
+	list_add(&m->list, &huge_boot_pages[0]);
 	m->hstate = hstate;
+	m->flags = 0;
 	return 1;
 }
 
@@ -248,264 +134,6 @@ int __init alloc_bootmem_huge_page(struct hstate *h, int nid)
 	return __alloc_bootmem_huge_page(h, nid);
 }
 
-#ifndef CONFIG_PPC_BOOK3S_64
-#define HUGEPD_FREELIST_SIZE \
-	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
-
-struct hugepd_freelist {
-	struct rcu_head	rcu;
-	unsigned int index;
-	void *ptes[];
-};
-
-static DEFINE_PER_CPU(struct hugepd_freelist *, hugepd_freelist_cur);
-
-static void hugepd_free_rcu_callback(struct rcu_head *head)
-{
-	struct hugepd_freelist *batch =
-		container_of(head, struct hugepd_freelist, rcu);
-	unsigned int i;
-
-	for (i = 0; i < batch->index; i++)
-		kmem_cache_free(PGT_CACHE(PTE_T_ORDER), batch->ptes[i]);
-
-	free_page((unsigned long)batch);
-}
-
-static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
-{
-	struct hugepd_freelist **batchp;
-
-	batchp = &get_cpu_var(hugepd_freelist_cur);
-
-	if (atomic_read(&tlb->mm->mm_users) < 2 ||
-	    mm_is_thread_local(tlb->mm)) {
-		kmem_cache_free(PGT_CACHE(PTE_T_ORDER), hugepte);
-		put_cpu_var(hugepd_freelist_cur);
-		return;
-	}
-
-	if (*batchp == NULL) {
-		*batchp = (struct hugepd_freelist *)__get_free_page(GFP_ATOMIC);
-		(*batchp)->index = 0;
-	}
-
-	(*batchp)->ptes[(*batchp)->index++] = hugepte;
-	if ((*batchp)->index == HUGEPD_FREELIST_SIZE) {
-		call_rcu(&(*batchp)->rcu, hugepd_free_rcu_callback);
-		*batchp = NULL;
-	}
-	put_cpu_var(hugepd_freelist_cur);
-}
-#else
-static inline void hugepd_free(struct mmu_gather *tlb, void *hugepte) {}
-#endif
-
-/* Return true when the entry to be freed maps more than the area being freed */
-static bool range_is_outside_limits(unsigned long start, unsigned long end,
-				    unsigned long floor, unsigned long ceiling,
-				    unsigned long mask)
-{
-	if ((start & mask) < floor)
-		return true;
-	if (ceiling) {
-		ceiling &= mask;
-		if (!ceiling)
-			return true;
-	}
-	return end - 1 > ceiling - 1;
-}
-
-static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
-			      unsigned long start, unsigned long end,
-			      unsigned long floor, unsigned long ceiling)
-{
-	pte_t *hugepte = hugepd_page(*hpdp);
-	int i;
-
-	unsigned long pdmask = ~((1UL << pdshift) - 1);
-	unsigned int num_hugepd = 1;
-	unsigned int shift = hugepd_shift(*hpdp);
-
-	/* Note: On fsl the hpdp may be the first of several */
-	if (shift > pdshift)
-		num_hugepd = 1 << (shift - pdshift);
-
-	if (range_is_outside_limits(start, end, floor, ceiling, pdmask))
-		return;
-
-	for (i = 0; i < num_hugepd; i++, hpdp++)
-		*hpdp = __hugepd(0);
-
-	if (shift >= pdshift)
-		hugepd_free(tlb, hugepte);
-	else
-		pgtable_free_tlb(tlb, hugepte,
-				 get_hugepd_cache_index(pdshift - shift));
-}
-
-static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
-				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling)
-{
-	pgtable_t token = pmd_pgtable(*pmd);
-
-	if (range_is_outside_limits(addr, end, floor, ceiling, PMD_MASK))
-		return;
-
-	pmd_clear(pmd);
-	pte_free_tlb(tlb, token, addr);
-	mm_dec_nr_ptes(tlb->mm);
-}
-
-static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
-				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling)
-{
-	pmd_t *pmd;
-	unsigned long next;
-	unsigned long start;
-
-	start = addr;
-	do {
-		unsigned long more;
-
-		pmd = pmd_offset(pud, addr);
-		next = pmd_addr_end(addr, end);
-		if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
-			if (pmd_none_or_clear_bad(pmd))
-				continue;
-
-			/*
-			 * if it is not hugepd pointer, we should already find
-			 * it cleared.
-			 */
-			WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx));
-
-			hugetlb_free_pte_range(tlb, pmd, addr, end, floor, ceiling);
-
-			continue;
-		}
-		/*
-		 * Increment next by the size of the huge mapping since
-		 * there may be more than one entry at this level for a
-		 * single hugepage, but all of them point to
-		 * the same kmem cache that holds the hugepte.
-		 */
-		more = addr + (1UL << hugepd_shift(*(hugepd_t *)pmd));
-		if (more > next)
-			next = more;
-
-		free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT,
-				  addr, next, floor, ceiling);
-	} while (addr = next, addr != end);
-
-	if (range_is_outside_limits(start, end, floor, ceiling, PUD_MASK))
-		return;
-
-	pmd = pmd_offset(pud, start & PUD_MASK);
-	pud_clear(pud);
-	pmd_free_tlb(tlb, pmd, start & PUD_MASK);
-	mm_dec_nr_pmds(tlb->mm);
-}
-
-static void hugetlb_free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
-				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling)
-{
-	pud_t *pud;
-	unsigned long next;
-	unsigned long start;
-
-	start = addr;
-	do {
-		pud = pud_offset(p4d, addr);
-		next = pud_addr_end(addr, end);
-		if (!is_hugepd(__hugepd(pud_val(*pud)))) {
-			if (pud_none_or_clear_bad(pud))
-				continue;
-			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
-					       ceiling);
-		} else {
-			unsigned long more;
-			/*
-			 * Increment next by the size of the huge mapping since
-			 * there may be more than one entry at this level for a
-			 * single hugepage, but all of them point to
-			 * the same kmem cache that holds the hugepte.
-			 */
-			more = addr + (1UL << hugepd_shift(*(hugepd_t *)pud));
-			if (more > next)
-				next = more;
-
-			free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT,
-					  addr, next, floor, ceiling);
-		}
-	} while (addr = next, addr != end);
-
-	if (range_is_outside_limits(start, end, floor, ceiling, PGDIR_MASK))
-		return;
-
-	pud = pud_offset(p4d, start & PGDIR_MASK);
-	p4d_clear(p4d);
-	pud_free_tlb(tlb, pud, start & PGDIR_MASK);
-	mm_dec_nr_puds(tlb->mm);
-}
-
-/*
- * This function frees user-level page tables of a process.
- */
-void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-			    unsigned long addr, unsigned long end,
-			    unsigned long floor, unsigned long ceiling)
-{
-	pgd_t *pgd;
-	p4d_t *p4d;
-	unsigned long next;
-
-	/*
-	 * Because there are a number of different possible pagetable
-	 * layouts for hugepage ranges, we limit knowledge of how
-	 * things should be laid out to the allocation path
-	 * (huge_pte_alloc(), above).  Everything else works out the
-	 * structure as it goes from information in the hugepd
-	 * pointers.  That means that we can't here use the
-	 * optimization used in the normal page free_pgd_range(), of
-	 * checking whether we're actually covering a large enough
-	 * range to have to do anything at the top level of the walk
-	 * instead of at the bottom.
-	 *
-	 * To make sense of this, you should probably go read the big
-	 * block comment at the top of the normal free_pgd_range(),
-	 * too.
-	 */
-
-	do {
-		next = pgd_addr_end(addr, end);
-		pgd = pgd_offset(tlb->mm, addr);
-		p4d = p4d_offset(pgd, addr);
-		if (!is_hugepd(__hugepd(pgd_val(*pgd)))) {
-			if (p4d_none_or_clear_bad(p4d))
-				continue;
-			hugetlb_free_pud_range(tlb, p4d, addr, next, floor, ceiling);
-		} else {
-			unsigned long more;
-			/*
-			 * Increment next by the size of the huge mapping since
-			 * there may be more than one entry at the pgd level
-			 * for a single hugepage, but all of them point to the
-			 * same kmem cache that holds the hugepte.
-			 */
-			more = addr + (1UL << hugepd_shift(*(hugepd_t *)pgd));
-			if (more > next)
-				next = more;
-
-			free_hugepd_range(tlb, (hugepd_t *)p4d, PGDIR_SHIFT,
-					  addr, next, floor, ceiling);
-		}
-	} while (addr = next, addr != end);
-}
-
 bool __init arch_hugetlb_valid_size(unsigned long size)
 {
 	int shift = __ffs(size);
@@ -552,44 +180,14 @@ static int __init hugetlbpage_init(void)
 
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 		unsigned shift;
-		unsigned pdshift;
 
 		if (!mmu_psize_defs[psize].shift)
 			continue;
 
 		shift = mmu_psize_to_shift(psize);
 
-#ifdef CONFIG_PPC_BOOK3S_64
-		if (shift > PGDIR_SHIFT)
-			continue;
-		else if (shift > PUD_SHIFT)
-			pdshift = PGDIR_SHIFT;
-		else if (shift > PMD_SHIFT)
-			pdshift = PUD_SHIFT;
-		else
-			pdshift = PMD_SHIFT;
-#else
-		if (shift < PUD_SHIFT)
-			pdshift = PMD_SHIFT;
-		else if (shift < PGDIR_SHIFT)
-			pdshift = PUD_SHIFT;
-		else
-			pdshift = PGDIR_SHIFT;
-#endif
-
 		if (add_huge_page_size(1ULL << shift) < 0)
 			continue;
-		/*
-		 * if we have pdshift and shift value same, we don't
-		 * use pgt cache for hugepd.
-		 */
-		if (pdshift > shift) {
-			if (!IS_ENABLED(CONFIG_PPC_8xx))
-				pgtable_cache_add(pdshift - shift);
-		} else if (IS_ENABLED(CONFIG_PPC_E500) ||
-			   IS_ENABLED(CONFIG_PPC_8xx)) {
-			pgtable_cache_add(PTE_T_ORDER);
-		}
 
 		configured = true;
 	}
@@ -614,8 +212,6 @@ void __init gigantic_hugetlb_cma_reserve(void)
 		 */
 		order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT;
 
-	if (order) {
-		VM_WARN_ON(order <= MAX_ORDER);
+	if (order)
 		hugetlb_cma_reserve(order);
-	}
 }
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index 119ef491f797..745097554bea 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -31,6 +31,10 @@ EXPORT_SYMBOL_GPL(kernstart_virt_addr);
 
 bool disable_kuep = !IS_ENABLED(CONFIG_PPC_KUEP);
 bool disable_kuap = !IS_ENABLED(CONFIG_PPC_KUAP);
+#ifdef CONFIG_KFENCE
+bool __ro_after_init kfence_disabled;
+bool __ro_after_init kfence_early_init = !!CONFIG_KFENCE_SAMPLE_INTERVAL;
+#endif
 
 static int __init parse_nosmep(char *p)
 {
@@ -70,7 +74,7 @@ void setup_kup(void)
 
 #define CTOR(shift) static void ctor_##shift(void *addr) \
 {							\
-	memset(addr, 0, sizeof(void *) << (shift));	\
+	memset(addr, 0, sizeof(pgd_t) << (shift));	\
 }
 
 CTOR(0); CTOR(1); CTOR(2); CTOR(3); CTOR(4); CTOR(5); CTOR(6); CTOR(7);
@@ -114,19 +118,15 @@ EXPORT_SYMBOL_GPL(pgtable_cache);	/* used by kvm_hv module */
 void pgtable_cache_add(unsigned int shift)
 {
 	char *name;
-	unsigned long table_size = sizeof(void *) << shift;
+	unsigned long table_size = sizeof(pgd_t) << shift;
 	unsigned long align = table_size;
 
 	/* When batching pgtable pointers for RCU freeing, we store
 	 * the index size in the low bits.  Table alignment must be
 	 * big enough to fit it.
-	 *
-	 * Likewise, hugeapge pagetable pointers contain a (different)
-	 * shift value in the low bits.  All tables must be aligned so
-	 * as to leave enough 0 bits in the address to contain it. */
-	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
-				     HUGEPD_SHIFT_MASK + 1);
-	struct kmem_cache *new;
+	 */
+	unsigned long minalign = MAX_PGTABLE_INDEX_SIZE + 1;
+	struct kmem_cache *new = NULL;
 
 	/* It would be nice if this was a BUILD_BUG_ON(), but at the
 	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
@@ -139,7 +139,8 @@ void pgtable_cache_add(unsigned int shift)
 
 	align = max_t(unsigned long, align, minalign);
 	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
-	new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
+	if (name)
+		new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
 	if (!new)
 		panic("Could not allocate pgtable cache for order %d", shift);
 
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index d4cc3749e621..4e71dfe7d026 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -39,6 +39,7 @@
 #include <asm/hugetlb.h>
 #include <asm/kup.h>
 #include <asm/kasan.h>
+#include <asm/fixmap.h>
 
 #include <mm/mmu_decl.h>
 
@@ -126,6 +127,8 @@ void __init MMU_init(void)
 
 	setup_kup();
 
+	update_mmu_feature_fixups(MMU_FTR_KUAP);
+
 	/* Shortly after that, the entire linear mapping will be available */
 	memblock_set_current_limit(lowmem_end_addr);
 }
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 05b0d584e50b..b6f3ae03ca9e 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -40,6 +40,8 @@
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
 #include <linux/memremap.h>
+#include <linux/memory.h>
+#include <linux/bootmem_info.h>
 
 #include <asm/pgalloc.h>
 #include <asm/page.h>
@@ -92,7 +94,7 @@ static struct page * __meminit vmemmap_subsection_start(unsigned long vmemmap_ad
  * a page table lookup here because with the hash translation we don't keep
  * vmemmap details in linux page table.
  */
-static int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size)
+int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size)
 {
 	struct page *start;
 	unsigned long vmemmap_end = vmemmap_addr + vmemmap_map_size;
@@ -183,13 +185,13 @@ static __meminit int vmemmap_list_populate(unsigned long phys,
 	return 0;
 }
 
-static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start,
-				unsigned long page_size)
+bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start,
+			   unsigned long page_size)
 {
 	unsigned long nr_pfn = page_size / sizeof(struct page);
 	unsigned long start_pfn = page_to_pfn((struct page *)start);
 
-	if ((start_pfn + nr_pfn) > altmap->end_pfn)
+	if ((start_pfn + nr_pfn - 1) > altmap->end_pfn)
 		return true;
 
 	if (start_pfn < altmap->base_pfn)
@@ -198,8 +200,8 @@ static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long star
 	return false;
 }
 
-int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
-		struct vmem_altmap *altmap)
+static int __meminit __vmemmap_populate(unsigned long start, unsigned long end, int node,
+					struct vmem_altmap *altmap)
 {
 	bool altmap_alloc;
 	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
@@ -272,6 +274,18 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	return 0;
 }
 
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
+			       struct vmem_altmap *altmap)
+{
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (radix_enabled())
+		return radix__vmemmap_populate(start, end, node, altmap);
+#endif
+
+	return __vmemmap_populate(start, end, node, altmap);
+}
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 static unsigned long vmemmap_list_free(unsigned long start)
 {
@@ -303,8 +317,8 @@ static unsigned long vmemmap_list_free(unsigned long start)
 	return vmem_back->phys;
 }
 
-void __ref vmemmap_free(unsigned long start, unsigned long end,
-		struct vmem_altmap *altmap)
+static void __ref __vmemmap_free(unsigned long start, unsigned long end,
+				 struct vmem_altmap *altmap)
 {
 	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
 	unsigned long page_order = get_order(page_size);
@@ -314,8 +328,7 @@ void __ref vmemmap_free(unsigned long start, unsigned long end,
 	start = ALIGN_DOWN(start, page_size);
 	if (altmap) {
 		alt_start = altmap->base_pfn;
-		alt_end = altmap->base_pfn + altmap->reserve +
-			  altmap->free + altmap->alloc + altmap->align;
+		alt_end = altmap->base_pfn + altmap->reserve + altmap->free;
 	}
 
 	pr_debug("vmemmap_free %lx...%lx\n", start, end);
@@ -362,11 +375,25 @@ void __ref vmemmap_free(unsigned long start, unsigned long end,
 		vmemmap_remove_mapping(start, page_size);
 	}
 }
+
+void __ref vmemmap_free(unsigned long start, unsigned long end,
+			struct vmem_altmap *altmap)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (radix_enabled())
+		return radix__vmemmap_free(start, end, altmap);
 #endif
+	return __vmemmap_free(start, end, altmap);
+}
+
+#endif
+
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
 void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long size)
 {
 }
+#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
 
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
@@ -471,6 +498,130 @@ static int __init dt_scan_mmu_pid_width(unsigned long node,
 	return 1;
 }
 
+/*
+ * Outside hotplug the kernel uses this value to map the kernel direct map
+ * with radix. To be compatible with older kernels, let's keep this value
+ * as 16M which is also SECTION_SIZE with SPARSEMEM. We can ideally map
+ * things with 1GB size in the case where we don't support hotplug.
+ */
+#ifndef CONFIG_MEMORY_HOTPLUG
+#define DEFAULT_MEMORY_BLOCK_SIZE	SZ_16M
+#else
+#define DEFAULT_MEMORY_BLOCK_SIZE	MIN_MEMORY_BLOCK_SIZE
+#endif
+
+static void update_memory_block_size(unsigned long *block_size, unsigned long mem_size)
+{
+	unsigned long min_memory_block_size = DEFAULT_MEMORY_BLOCK_SIZE;
+
+	for (; *block_size > min_memory_block_size; *block_size >>= 2) {
+		if ((mem_size & *block_size) == 0)
+			break;
+	}
+}
+
+static int __init probe_memory_block_size(unsigned long node, const char *uname, int
+					  depth, void *data)
+{
+	const char *type;
+	unsigned long *block_size = (unsigned long *)data;
+	const __be32 *reg, *endp;
+	int l;
+
+	if (depth != 1)
+		return 0;
+	/*
+	 * If we have dynamic-reconfiguration-memory node, use the
+	 * lmb value.
+	 */
+	if (strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) {
+
+		const __be32 *prop;
+
+		prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &l);
+
+		if (!prop || l < dt_root_size_cells * sizeof(__be32))
+			/*
+			 * Nothing in the device tree
+			 */
+			*block_size = DEFAULT_MEMORY_BLOCK_SIZE;
+		else
+			*block_size = of_read_number(prop, dt_root_size_cells);
+		/*
+		 * We have found the final value. Don't probe further.
+		 */
+		return 1;
+	}
+	/*
+	 * Find all the device tree nodes of memory type and make sure
+	 * the area can be mapped using the memory block size value
+	 * we end up using. We start with 1G value and keep reducing
+	 * it such that we can map the entire area using memory_block_size.
+	 * This will be used on powernv and older pseries that don't
+	 * have ibm,lmb-size node.
+	 * For ex: with P5 we can end up with
+	 * memory@0 -> 128MB
+	 * memory@128M -> 64M
+	 * This will end up using 64MB  memory block size value.
+	 */
+	type = of_get_flat_dt_prop(node, "device_type", NULL);
+	if (type == NULL || strcmp(type, "memory") != 0)
+		return 0;
+
+	reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l);
+	if (!reg)
+		reg = of_get_flat_dt_prop(node, "reg", &l);
+	if (!reg)
+		return 0;
+
+	endp = reg + (l / sizeof(__be32));
+	while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
+		const char *compatible;
+		u64 size;
+
+		dt_mem_next_cell(dt_root_addr_cells, &reg);
+		size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+		if (size) {
+			update_memory_block_size(block_size, size);
+			continue;
+		}
+		/*
+		 * ibm,coherent-device-memory with linux,usable-memory = 0
+		 * Force 256MiB block size. Work around for GPUs on P9 PowerNV
+		 * linux,usable-memory == 0 implies driver managed memory and
+		 * we can't use large memory block size due to hotplug/unplug
+		 * limitations.
+		 */
+		compatible = of_get_flat_dt_prop(node, "compatible", NULL);
+		if (compatible && !strcmp(compatible, "ibm,coherent-device-memory")) {
+			if (*block_size > SZ_256M)
+				*block_size = SZ_256M;
+			/*
+			 * We keep 256M as the upper limit with GPU present.
+			 */
+			return 0;
+		}
+	}
+	/* continue looking for other memory device types */
+	return 0;
+}
+
+/*
+ * start with 1G memory block size. Early init will
+ * fix this with correct value.
+ */
+unsigned long memory_block_size __ro_after_init = 1UL << 30;
+static void __init early_init_memory_block_size(void)
+{
+	/*
+	 * We need to do memory_block_size probe early so that
+	 * radix__early_init_mmu() can use this as limit for
+	 * mapping page size.
+	 */
+	of_scan_flat_dt(probe_memory_block_size, &memory_block_size);
+}
+
 void __init mmu_early_init_devtree(void)
 {
 	bool hvmode = !!(mfmsr() & MSR_HV);
@@ -504,6 +655,8 @@ void __init mmu_early_init_devtree(void)
 	if (!hvmode)
 		early_check_vec5();
 
+	early_init_memory_block_size();
+
 	if (early_radix_enabled()) {
 		radix__early_init_devtree();
 
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
index 4f12504fb405..4b4feba9873b 100644
--- a/arch/powerpc/mm/ioremap.c
+++ b/arch/powerpc/mm/ioremap.c
@@ -4,7 +4,6 @@
 #include <linux/slab.h>
 #include <linux/mmzone.h>
 #include <linux/vmalloc.h>
-#include <asm/io-workarounds.h>
 
 unsigned long ioremap_bot;
 EXPORT_SYMBOL(ioremap_bot);
@@ -14,8 +13,6 @@ void __iomem *ioremap(phys_addr_t addr, unsigned long size)
 	pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
 	void *caller = __builtin_return_address(0);
 
-	if (iowa_is_active())
-		return iowa_ioremap(addr, size, prot, caller);
 	return __ioremap_caller(addr, size, prot, caller);
 }
 EXPORT_SYMBOL(ioremap);
@@ -25,8 +22,6 @@ void __iomem *ioremap_wc(phys_addr_t addr, unsigned long size)
 	pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
 	void *caller = __builtin_return_address(0);
 
-	if (iowa_is_active())
-		return iowa_ioremap(addr, size, prot, caller);
 	return __ioremap_caller(addr, size, prot, caller);
 }
 EXPORT_SYMBOL(ioremap_wc);
@@ -36,26 +31,18 @@ void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size)
 	pgprot_t prot = pgprot_cached(PAGE_KERNEL);
 	void *caller = __builtin_return_address(0);
 
-	if (iowa_is_active())
-		return iowa_ioremap(addr, size, prot, caller);
 	return __ioremap_caller(addr, size, prot, caller);
 }
 
-void __iomem *ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
+void __iomem *ioremap_prot(phys_addr_t addr, size_t size, pgprot_t prot)
 {
-	pte_t pte = __pte(flags);
+	pte_t pte = __pte(pgprot_val(prot));
 	void *caller = __builtin_return_address(0);
 
 	/* writeable implies dirty for kernel addresses */
 	if (pte_write(pte))
 		pte = pte_mkdirty(pte);
 
-	/* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
-	pte = pte_exprotect(pte);
-	pte = pte_mkprivileged(pte);
-
-	if (iowa_is_active())
-		return iowa_ioremap(addr, size, pte_pgprot(pte), caller);
 	return __ioremap_caller(addr, size, pte_pgprot(pte), caller);
 }
 EXPORT_SYMBOL(ioremap_prot);
@@ -66,7 +53,7 @@ int early_ioremap_range(unsigned long ea, phys_addr_t pa,
 	unsigned long i;
 
 	for (i = 0; i < size; i += PAGE_SIZE) {
-		int err = map_kernel_page(ea + i, pa + i, prot);
+		int err = map_kernel_page(ea + i, pa + i, pgprot_nx(prot));
 
 		if (WARN_ON_ONCE(err))  /* Should clean up */
 			return err;
@@ -74,27 +61,3 @@ int early_ioremap_range(unsigned long ea, phys_addr_t pa,
 
 	return 0;
 }
-
-void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
-			 pgprot_t prot, void *caller)
-{
-	struct vm_struct *area;
-	int ret;
-	unsigned long va;
-
-	area = __get_vm_area_caller(size, VM_IOREMAP, IOREMAP_START, IOREMAP_END, caller);
-	if (area == NULL)
-		return NULL;
-
-	area->phys_addr = pa;
-	va = (unsigned long)area->addr;
-
-	ret = ioremap_page_range(va, va + size, pa, prot);
-	if (!ret)
-		return (void __iomem *)area->addr + offset;
-
-	vunmap_range(va, va + size);
-	free_vm_area(area);
-
-	return NULL;
-}
diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c
index 9d13143b8be4..ca5bc6be3e6f 100644
--- a/arch/powerpc/mm/ioremap_32.c
+++ b/arch/powerpc/mm/ioremap_32.c
@@ -22,6 +22,13 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
 	int err;
 
 	/*
+	 * If the address lies within the first 16 MB, assume it's in ISA
+	 * memory space
+	 */
+	if (addr < SZ_16M)
+		addr += _ISA_MEM_BASE;
+
+	/*
 	 * Choose an address to map it to.
 	 * Once the vmalloc system is running, we use it.
 	 * Before then, we use space going down from IOREMAP_TOP
@@ -31,13 +38,6 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
 	offset = addr & ~PAGE_MASK;
 	size = PAGE_ALIGN(addr + size) - p;
 
-	/*
-	 * If the address lies within the first 16 MB, assume it's in ISA
-	 * memory space
-	 */
-	if (p < 16 * 1024 * 1024)
-		p += _ISA_MEM_BASE;
-
 #ifndef CONFIG_CRASH_DUMP
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using.
@@ -63,7 +63,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
 		return (void __iomem *)v + offset;
 
 	if (slab_is_available())
-		return do_ioremap(p, offset, size, prot, caller);
+		return generic_ioremap_prot(addr, size, prot);
 
 	/*
 	 * Should check if it is a candidate for a BAT mapping
@@ -87,7 +87,6 @@ void iounmap(volatile void __iomem *addr)
 	if (v_block_mapped((unsigned long)addr))
 		return;
 
-	if (addr > high_memory && (unsigned long)addr < ioremap_bot)
-		vunmap((void *)(PAGE_MASK & (unsigned long)addr));
+	generic_iounmap(addr);
 }
 EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c
index 3acece00b33e..fb8b55bd2cd5 100644
--- a/arch/powerpc/mm/ioremap_64.c
+++ b/arch/powerpc/mm/ioremap_64.c
@@ -29,7 +29,7 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
 		return NULL;
 
 	if (slab_is_available())
-		return do_ioremap(paligned, offset, size, prot, caller);
+		return generic_ioremap_prot(addr, size, prot);
 
 	pr_warn("ioremap() called early from %pS. Use early_ioremap() instead\n", caller);
 
@@ -49,17 +49,9 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
  */
 void iounmap(volatile void __iomem *token)
 {
-	void *addr;
-
 	if (!slab_is_available())
 		return;
 
-	addr = (void *)((unsigned long __force)PCI_FIX_ADDR(token) & PAGE_MASK);
-
-	if ((unsigned long)addr < ioremap_bot) {
-		pr_warn("Attempt to iounmap early bolted mapping at 0x%p\n", addr);
-		return;
-	}
-	vunmap(addr);
+	generic_iounmap(token);
 }
 EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/kasan/8xx.c b/arch/powerpc/mm/kasan/8xx.c
index 2784224054f8..989d6cdf4141 100644
--- a/arch/powerpc/mm/kasan/8xx.c
+++ b/arch/powerpc/mm/kasan/8xx.c
@@ -6,28 +6,33 @@
 #include <linux/memblock.h>
 #include <linux/hugetlb.h>
 
+#include <asm/pgalloc.h>
+
 static int __init
 kasan_init_shadow_8M(unsigned long k_start, unsigned long k_end, void *block)
 {
 	pmd_t *pmd = pmd_off_k(k_start);
 	unsigned long k_cur, k_next;
 
-	for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd += 2, block += SZ_8M) {
-		pte_basic_t *new;
+	for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd++, block += SZ_4M) {
+		pte_t *ptep;
+		int i;
 
 		k_next = pgd_addr_end(k_cur, k_end);
-		k_next = pgd_addr_end(k_next, k_end);
 		if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte)
 			continue;
 
-		new = memblock_alloc(sizeof(pte_basic_t), SZ_4K);
-		if (!new)
+		ptep = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE);
+		if (!ptep)
 			return -ENOMEM;
 
-		*new = pte_val(pte_mkhuge(pfn_pte(PHYS_PFN(__pa(block)), PAGE_KERNEL)));
+		for (i = 0; i < PTRS_PER_PTE; i++) {
+			pte_t pte = pte_mkhuge(pfn_pte(PHYS_PFN(__pa(block + i * PAGE_SIZE)), PAGE_KERNEL));
 
-		hugepd_populate_kernel((hugepd_t *)pmd, (pte_t *)new, PAGE_SHIFT_8M);
-		hugepd_populate_kernel((hugepd_t *)pmd + 1, (pte_t *)new, PAGE_SHIFT_8M);
+			__set_pte_at(&init_mm, k_cur, ptep + i, pte, 1);
+		}
+		pmd_populate_kernel(&init_mm, pmd, ptep);
+		*pmd = __pmd(pmd_val(*pmd) | _PMD_PAGE_8M);
 	}
 	return 0;
 }
diff --git a/arch/powerpc/mm/kasan/Makefile b/arch/powerpc/mm/kasan/Makefile
index 699eeffd9f55..f9522fd70b2f 100644
--- a/arch/powerpc/mm/kasan/Makefile
+++ b/arch/powerpc/mm/kasan/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 KASAN_SANITIZE := n
+KCOV_INSTRUMENT := n
 
 obj-$(CONFIG_PPC32)		+= init_32.o
 obj-$(CONFIG_PPC_8xx)		+= 8xx.o
diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c
index a70828a6d935..1d083597464f 100644
--- a/arch/powerpc/mm/kasan/init_32.c
+++ b/arch/powerpc/mm/kasan/init_32.c
@@ -7,7 +7,7 @@
 #include <linux/memblock.h>
 #include <linux/sched/task.h>
 #include <asm/pgalloc.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <mm/mmu_decl.h>
 
 static pgprot_t __init kasan_prot_ro(void)
@@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size)
 	if (ret)
 		return ret;
 
+	k_start = k_start & PAGE_MASK;
 	block = memblock_alloc(k_end - k_start, PAGE_SIZE);
 	if (!block)
 		return -ENOMEM;
@@ -164,7 +165,7 @@ void __init kasan_init(void)
 
 	/* At this point kasan is fully initialized. Enable error messages */
 	init_task.kasan_depth = 0;
-	pr_info("KASAN init done\n");
+	kasan_init_generic();
 }
 
 void __init kasan_late_init(void)
diff --git a/arch/powerpc/mm/kasan/init_book3e_64.c b/arch/powerpc/mm/kasan/init_book3e_64.c
index 11519e88dc6b..0d3a73d6d4b0 100644
--- a/arch/powerpc/mm/kasan/init_book3e_64.c
+++ b/arch/powerpc/mm/kasan/init_book3e_64.c
@@ -40,19 +40,19 @@ static int __init kasan_map_kernel_page(unsigned long ea, unsigned long pa, pgpr
 	pgdp = pgd_offset_k(ea);
 	p4dp = p4d_offset(pgdp, ea);
 	if (kasan_pud_table(*p4dp)) {
-		pudp = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
+		pudp = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
 		memcpy(pudp, kasan_early_shadow_pud, PUD_TABLE_SIZE);
 		p4d_populate(&init_mm, p4dp, pudp);
 	}
 	pudp = pud_offset(p4dp, ea);
 	if (kasan_pmd_table(*pudp)) {
-		pmdp = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
+		pmdp = memblock_alloc_or_panic(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
 		memcpy(pmdp, kasan_early_shadow_pmd, PMD_TABLE_SIZE);
 		pud_populate(&init_mm, pudp, pmdp);
 	}
 	pmdp = pmd_offset(pudp, ea);
 	if (kasan_pte_table(*pmdp)) {
-		ptep = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
+		ptep = memblock_alloc_or_panic(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
 		memcpy(ptep, kasan_early_shadow_pte, PTE_TABLE_SIZE);
 		pmd_populate_kernel(&init_mm, pmdp, ptep);
 	}
@@ -74,7 +74,7 @@ static void __init kasan_init_phys_region(void *start, void *end)
 	k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE);
 	k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE);
 
-	va = memblock_alloc(k_end - k_start, PAGE_SIZE);
+	va = memblock_alloc_or_panic(k_end - k_start, PAGE_SIZE);
 	for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE)
 		kasan_map_kernel_page(k_cur, __pa(va), PAGE_KERNEL);
 }
@@ -112,7 +112,7 @@ void __init kasan_init(void)
 	pte_t zero_pte = pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL_RO);
 
 	for_each_mem_range(i, &start, &end)
-		kasan_init_phys_region((void *)start, (void *)end);
+		kasan_init_phys_region(phys_to_virt(start), phys_to_virt(end));
 
 	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
 		kasan_remove_zero_shadow((void *)VMALLOC_START, VMALLOC_SIZE);
@@ -127,7 +127,7 @@ void __init kasan_init(void)
 
 	/* Enable error messages */
 	init_task.kasan_depth = 0;
-	pr_info("KASAN init done\n");
+	kasan_init_generic();
 }
 
 void __init kasan_late_init(void) { }
diff --git a/arch/powerpc/mm/kasan/init_book3s_64.c b/arch/powerpc/mm/kasan/init_book3s_64.c
index 9300d641cf9a..dcafa641804c 100644
--- a/arch/powerpc/mm/kasan/init_book3s_64.c
+++ b/arch/powerpc/mm/kasan/init_book3s_64.c
@@ -19,8 +19,6 @@
 #include <linux/memblock.h>
 #include <asm/pgalloc.h>
 
-DEFINE_STATIC_KEY_FALSE(powerpc_kasan_enabled_key);
-
 static void __init kasan_init_phys_region(void *start, void *end)
 {
 	unsigned long k_start, k_end, k_cur;
@@ -32,7 +30,7 @@ static void __init kasan_init_phys_region(void *start, void *end)
 	k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE);
 	k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE);
 
-	va = memblock_alloc(k_end - k_start, PAGE_SIZE);
+	va = memblock_alloc_or_panic(k_end - k_start, PAGE_SIZE);
 	for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE)
 		map_kernel_page(k_cur, __pa(va), PAGE_KERNEL);
 }
@@ -62,7 +60,7 @@ void __init kasan_init(void)
 	}
 
 	for_each_mem_range(i, &start, &end)
-		kasan_init_phys_region((void *)start, (void *)end);
+		kasan_init_phys_region(phys_to_virt(start), phys_to_virt(end));
 
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		__set_pte_at(&init_mm, (unsigned long)kasan_early_shadow_page,
@@ -92,11 +90,9 @@ void __init kasan_init(void)
 	 */
 	memset(kasan_early_shadow_page, 0, PAGE_SIZE);
 
-	static_branch_inc(&powerpc_kasan_enabled_key);
-
 	/* Enable error messages */
 	init_task.kasan_depth = 0;
-	pr_info("KASAN init done\n");
+	kasan_init_generic();
 }
 
 void __init kasan_early_init(void) { }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 8b121df7b08f..3ddbfdbfa941 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -16,6 +16,8 @@
 #include <linux/highmem.h>
 #include <linux/suspend.h>
 #include <linux/dma-direct.h>
+#include <linux/execmem.h>
+#include <linux/vmalloc.h>
 
 #include <asm/swiotlb.h>
 #include <asm/machdep.h>
@@ -24,28 +26,29 @@
 #include <asm/svm.h>
 #include <asm/mmzone.h>
 #include <asm/ftrace.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/setup.h>
+#include <asm/fixmap.h>
 
 #include <mm/mmu_decl.h>
 
-unsigned long long memory_limit;
+unsigned long long memory_limit __initdata;
 
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
 
-pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-			      unsigned long size, pgprot_t vma_prot)
+pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size,
+				pgprot_t vma_prot)
 {
 	if (ppc_md.phys_mem_access_prot)
-		return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot);
+		return ppc_md.phys_mem_access_prot(pfn, size, vma_prot);
 
 	if (!page_is_ram(pfn))
 		vma_prot = pgprot_noncached(vma_prot);
 
 	return vma_prot;
 }
-EXPORT_SYMBOL(phys_mem_access_prot);
+EXPORT_SYMBOL(__phys_mem_access_prot);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 static DEFINE_MUTEX(linear_mapping_mutex);
@@ -213,7 +216,7 @@ static int __init mark_nonram_nosave(void)
  * everything else. GFP_DMA32 page allocations automatically fall back to
  * ZONE_DMA.
  *
- * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the
+ * By using 31-bit unconditionally, we can exploit zone_dma_limit to inform the
  * generic DMA mapping code.  32-bit only devices (if not handled by an IOMMU
  * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by
  * ZONE_DMA.
@@ -227,6 +230,7 @@ void __init paging_init(void)
 {
 	unsigned long long total_ram = memblock_phys_mem_size();
 	phys_addr_t top_of_ram = memblock_end_of_DRAM();
+	int zone_dma_bits;
 
 #ifdef CONFIG_HIGHMEM
 	unsigned long v = __fix_to_virt(FIX_KMAP_END);
@@ -253,6 +257,8 @@ void __init paging_init(void)
 	else
 		zone_dma_bits = 31;
 
+	zone_dma_limit = DMA_BIT_MASK(zone_dma_bits);
+
 #ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA]	= min(max_low_pfn,
 				      1UL << (zone_dma_bits - PAGE_SHIFT));
@@ -267,7 +273,7 @@ void __init paging_init(void)
 	mark_nonram_nosave();
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	/*
 	 * book3s is limited to 16 page sizes due to encoding this in
@@ -287,27 +293,8 @@ void __init mem_init(void)
 	swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags);
 #endif
 
-	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
-	set_max_mapnr(max_pfn);
-
 	kasan_late_init();
 
-	memblock_free_all();
-
-#ifdef CONFIG_HIGHMEM
-	{
-		unsigned long pfn, highmem_mapnr;
-
-		highmem_mapnr = lowmem_end_addr >> PAGE_SHIFT;
-		for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) {
-			phys_addr_t paddr = (phys_addr_t)pfn << PAGE_SHIFT;
-			struct page *page = pfn_to_page(pfn);
-			if (memblock_is_memory(paddr) && !memblock_is_reserved(paddr))
-				free_highmem_page(page);
-		}
-	}
-#endif /* CONFIG_HIGHMEM */
-
 #if defined(CONFIG_PPC_E500) && !defined(CONFIG_SMP)
 	/*
 	 * If smp is enabled, next_tlbcam_idx is initialized in the cpu up
@@ -316,28 +303,6 @@ void __init mem_init(void)
 	per_cpu(next_tlbcam_idx, smp_processor_id()) =
 		(mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1;
 #endif
-
-#ifdef CONFIG_PPC32
-	pr_info("Kernel virtual memory layout:\n");
-#ifdef CONFIG_KASAN
-	pr_info("  * 0x%08lx..0x%08lx  : kasan shadow mem\n",
-		KASAN_SHADOW_START, KASAN_SHADOW_END);
-#endif
-	pr_info("  * 0x%08lx..0x%08lx  : fixmap\n", FIXADDR_START, FIXADDR_TOP);
-#ifdef CONFIG_HIGHMEM
-	pr_info("  * 0x%08lx..0x%08lx  : highmem PTEs\n",
-		PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP));
-#endif /* CONFIG_HIGHMEM */
-	if (ioremap_bot != IOREMAP_TOP)
-		pr_info("  * 0x%08lx..0x%08lx  : early ioremap\n",
-			ioremap_bot, IOREMAP_TOP);
-	pr_info("  * 0x%08lx..0x%08lx  : vmalloc & ioremap\n",
-		VMALLOC_START, VMALLOC_END);
-#ifdef MODULES_VADDR
-	pr_info("  * 0x%08lx..0x%08lx  : modules\n",
-		MODULES_VADDR, MODULES_END);
-#endif
-#endif /* CONFIG_PPC32 */
 }
 
 void free_initmem(void)
@@ -373,7 +338,7 @@ static int __init add_system_ram_resources(void)
 			 */
 			res->end = end - 1;
 			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
-			WARN_ON(request_resource(&iomem_resource, res) < 0);
+			WARN_ON(insert_resource(&iomem_resource, res) < 0);
 		}
 	}
 
@@ -406,3 +371,80 @@ int devmem_is_allowed(unsigned long pfn)
  * the EHEA driver. Drop this when drivers/net/ethernet/ibm/ehea is removed.
  */
 EXPORT_SYMBOL_GPL(walk_system_ram_range);
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+#if defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_BOOK3S_603)
+static void prealloc_execmem_pgtable(void)
+{
+	unsigned long va;
+
+	for (va = ALIGN_DOWN(MODULES_VADDR, PGDIR_SIZE); va < MODULES_END; va += PGDIR_SIZE)
+		pte_alloc_kernel(pmd_off_k(va), va);
+}
+#else
+static void prealloc_execmem_pgtable(void) { }
+#endif
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+	pgprot_t kprobes_prot = strict_module_rwx_enabled() ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+	pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
+	unsigned long fallback_start = 0, fallback_end = 0;
+	unsigned long start, end;
+
+	/*
+	 * BOOK3S_32 and 8xx define MODULES_VADDR for text allocations and
+	 * allow allocating data in the entire vmalloc space
+	 */
+#ifdef MODULES_VADDR
+	unsigned long limit = (unsigned long)_etext - SZ_32M;
+
+	BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
+
+	/* First try within 32M limit from _etext to avoid branch trampolines */
+	if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit) {
+		start = limit;
+		fallback_start = MODULES_VADDR;
+		fallback_end = MODULES_END;
+	} else {
+		start = MODULES_VADDR;
+	}
+
+	end = MODULES_END;
+#else
+	start = VMALLOC_START;
+	end = VMALLOC_END;
+#endif
+
+	prealloc_execmem_pgtable();
+
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.start	= start,
+				.end	= end,
+				.pgprot	= prot,
+				.alignment = 1,
+				.fallback_start	= fallback_start,
+				.fallback_end	= fallback_end,
+			},
+			[EXECMEM_KPROBES] = {
+				.start	= VMALLOC_START,
+				.end	= VMALLOC_END,
+				.pgprot	= kprobes_prot,
+				.alignment = 1,
+			},
+			[EXECMEM_MODULE_DATA] = {
+				.start	= VMALLOC_START,
+				.end	= VMALLOC_END,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = 1,
+			},
+		},
+	};
+
+	return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index 1fb9c99f8679..3e3af29b4523 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -21,7 +21,7 @@ static inline void switch_mm_pgdir(struct task_struct *tsk,
 #ifdef CONFIG_PPC_BOOK3S_32
 	tsk->thread.sr0 = mm->context.sr0;
 #endif
-#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP)
+#if defined(CONFIG_BOOKE) && defined(CONFIG_PPC_KUAP)
 	tsk->thread.pid = mm->context.id;
 #endif
 }
@@ -43,11 +43,13 @@ static inline void switch_mm_pgdir(struct task_struct *tsk,
 void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			struct task_struct *tsk)
 {
+	int cpu = smp_processor_id();
 	bool new_on_cpu = false;
 
 	/* Mark this context has been used on the new CPU */
-	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) {
-		cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
+	if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+		VM_WARN_ON_ONCE(next == &init_mm);
+		cpumask_set_cpu(cpu, mm_cpumask(next));
 		inc_mm_active_cpus(next);
 
 		/*
@@ -100,6 +102,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	 * sub architectures. Out of line for now
 	 */
 	switch_mmu_context(prev, next, tsk);
+
+	VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(prev)));
 }
 
 #ifndef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index c6dccb4f06dc..b2d1eea09761 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -20,9 +20,9 @@
 #include <asm/trace.h>
 
 /*
- * On 40x and 8xx, we directly inline tlbia and tlbivax
+ * On 8xx, we directly inline tlbia
  */
-#if defined(CONFIG_40x) || defined(CONFIG_PPC_8xx)
+#ifdef CONFIG_PPC_8xx
 static inline void _tlbil_all(void)
 {
 	asm volatile ("sync; tlbia; isync" : : : "memory");
@@ -35,7 +35,7 @@ static inline void _tlbil_pid(unsigned int pid)
 }
 #define _tlbil_pid_noind(pid)	_tlbil_pid(pid)
 
-#else /* CONFIG_40x || CONFIG_PPC_8xx */
+#else /* CONFIG_PPC_8xx */
 extern void _tlbil_all(void);
 extern void _tlbil_pid(unsigned int pid);
 #ifdef CONFIG_PPC_BOOK3E_64
@@ -43,7 +43,7 @@ extern void _tlbil_pid_noind(unsigned int pid);
 #else
 #define _tlbil_pid_noind(pid)	_tlbil_pid(pid)
 #endif
-#endif /* !(CONFIG_40x || CONFIG_PPC_8xx) */
+#endif /* !CONFIG_PPC_8xx */
 
 /*
  * On 8xx, we directly inline tlbie, on others, it's extern
@@ -110,6 +110,7 @@ extern void MMU_init_hw(void);
 void MMU_init_hw_patch(void);
 unsigned long mmu_mapin_ram(unsigned long base, unsigned long top);
 #endif
+void mmu_init_secondary(int cpu);
 
 #ifdef CONFIG_PPC_E500
 extern unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx,
@@ -159,24 +160,25 @@ static inline unsigned long p_block_mapped(phys_addr_t pa) { return 0; }
 #endif
 
 #if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC_E500)
-void mmu_mark_initmem_nx(void);
-void mmu_mark_rodata_ro(void);
+int mmu_mark_initmem_nx(void);
+int mmu_mark_rodata_ro(void);
 #else
-static inline void mmu_mark_initmem_nx(void) { }
-static inline void mmu_mark_rodata_ro(void) { }
+static inline int mmu_mark_initmem_nx(void) { return 0; }
+static inline int mmu_mark_rodata_ro(void) { return 0; }
 #endif
 
 #ifdef CONFIG_PPC_8xx
 void __init mmu_mapin_immr(void);
 #endif
 
-#ifdef CONFIG_DEBUG_WX
-void ptdump_check_wx(void);
-#else
-static inline void ptdump_check_wx(void) { }
-#endif
-
 static inline bool debug_pagealloc_enabled_or_kfence(void)
 {
 	return IS_ENABLED(CONFIG_KFENCE) || debug_pagealloc_enabled();
 }
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int create_section_mapping(unsigned long start, unsigned long end,
+			   int nid, pgprot_t prot);
+#endif
+
+int hash__kernel_map_pages(struct page *page, int numpages, int enable);
diff --git a/arch/powerpc/mm/nohash/40x.c b/arch/powerpc/mm/nohash/40x.c
deleted file mode 100644
index 3684d6e570fb..000000000000
--- a/arch/powerpc/mm/nohash/40x.c
+++ /dev/null
@@ -1,156 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * This file contains the routines for initializing the MMU
- * on the 4xx series of chips.
- *  -- paulus
- *
- *  Derived from arch/ppc/mm/init.c:
- *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
- *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
- *    Copyright (C) 1996 Paul Mackerras
- *
- *  Derived from "arch/i386/mm/init.c"
- *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- */
-
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/stddef.h>
-#include <linux/vmalloc.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/highmem.h>
-#include <linux/memblock.h>
-
-#include <asm/io.h>
-#include <asm/mmu_context.h>
-#include <asm/mmu.h>
-#include <linux/uaccess.h>
-#include <asm/smp.h>
-#include <asm/bootx.h>
-#include <asm/machdep.h>
-#include <asm/setup.h>
-
-#include <mm/mmu_decl.h>
-
-/*
- * MMU_init_hw does the chip-specific initialization of the MMU hardware.
- */
-void __init MMU_init_hw(void)
-{
-	/*
-	 * The Zone Protection Register (ZPR) defines how protection will
-	 * be applied to every page which is a member of a given zone. At
-	 * present, we utilize only two of the 4xx's zones.
-	 * The zone index bits (of ZSEL) in the PTE are used for software
-	 * indicators, except the LSB.  For user access, zone 1 is used,
-	 * for kernel access, zone 0 is used.  We set all but zone 1
-	 * to zero, allowing only kernel access as indicated in the PTE.
-	 * For zone 1, we set a 01 binary (a value of 10 will not work)
-	 * to allow user access as indicated in the PTE.  This also allows
-	 * kernel access as indicated in the PTE.
-	 */
-
-        mtspr(SPRN_ZPR, 0x10000000);
-
-	flush_instruction_cache();
-
-	/*
-	 * Set up the real-mode cache parameters for the exception vector
-	 * handlers (which are run in real-mode).
-	 */
-
-        mtspr(SPRN_DCWR, 0x00000000);	/* All caching is write-back */
-
-        /*
-	 * Cache instruction and data space where the exception
-	 * vectors and the kernel live in real-mode.
-	 */
-
-        mtspr(SPRN_DCCR, 0xFFFF0000);	/* 2GByte of data space at 0x0. */
-        mtspr(SPRN_ICCR, 0xFFFF0000);	/* 2GByte of instr. space at 0x0. */
-}
-
-#define LARGE_PAGE_SIZE_16M	(1<<24)
-#define LARGE_PAGE_SIZE_4M	(1<<22)
-
-unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
-{
-	unsigned long v, s, mapped;
-	phys_addr_t p;
-
-	v = KERNELBASE;
-	p = 0;
-	s = total_lowmem;
-
-	if (IS_ENABLED(CONFIG_KFENCE))
-		return 0;
-
-	if (debug_pagealloc_enabled())
-		return 0;
-
-	if (strict_kernel_rwx_enabled())
-		return 0;
-
-	while (s >= LARGE_PAGE_SIZE_16M) {
-		pmd_t *pmdp;
-		unsigned long val = p | _PMD_SIZE_16M | _PAGE_EXEC | _PAGE_RW;
-
-		pmdp = pmd_off_k(v);
-		*pmdp++ = __pmd(val);
-		*pmdp++ = __pmd(val);
-		*pmdp++ = __pmd(val);
-		*pmdp++ = __pmd(val);
-
-		v += LARGE_PAGE_SIZE_16M;
-		p += LARGE_PAGE_SIZE_16M;
-		s -= LARGE_PAGE_SIZE_16M;
-	}
-
-	while (s >= LARGE_PAGE_SIZE_4M) {
-		pmd_t *pmdp;
-		unsigned long val = p | _PMD_SIZE_4M | _PAGE_EXEC | _PAGE_RW;
-
-		pmdp = pmd_off_k(v);
-		*pmdp = __pmd(val);
-
-		v += LARGE_PAGE_SIZE_4M;
-		p += LARGE_PAGE_SIZE_4M;
-		s -= LARGE_PAGE_SIZE_4M;
-	}
-
-	mapped = total_lowmem - s;
-
-	/* If the size of RAM is not an exact power of two, we may not
-	 * have covered RAM in its entirety with 16 and 4 MiB
-	 * pages. Consequently, restrict the top end of RAM currently
-	 * allocable so that calls to the MEMBLOCK to allocate PTEs for "tail"
-	 * coverage with normal-sized pages (or other reasons) do not
-	 * attempt to allocate outside the allowed range.
-	 */
-	memblock_set_current_limit(mapped);
-
-	return mapped;
-}
-
-void setup_initial_memory_limit(phys_addr_t first_memblock_base,
-				phys_addr_t first_memblock_size)
-{
-	/* We don't currently support the first MEMBLOCK not mapping 0
-	 * physical on those processors
-	 */
-	BUG_ON(first_memblock_base != 0);
-
-	/* 40x can only access 16MB at the moment (see head_40x.S) */
-	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
-}
diff --git a/arch/powerpc/mm/nohash/44x.c b/arch/powerpc/mm/nohash/44x.c
index 1beae802bb1c..6d10c6d8be71 100644
--- a/arch/powerpc/mm/nohash/44x.c
+++ b/arch/powerpc/mm/nohash/44x.c
@@ -24,7 +24,7 @@
 #include <asm/mmu.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/smp.h>
 
 #include <mm/mmu_decl.h>
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index dbbfe897455d..ab1505cf42bf 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -10,6 +10,9 @@
 #include <linux/memblock.h>
 #include <linux/hugetlb.h>
 
+#include <asm/fixmap.h>
+#include <asm/pgalloc.h>
+
 #include <mm/mmu_decl.h>
 
 #define IMMR_SIZE (FIX_IMMR_SIZE << PAGE_SHIFT)
@@ -46,52 +49,47 @@ unsigned long p_block_mapped(phys_addr_t pa)
 	return 0;
 }
 
-static pte_t __init *early_hugepd_alloc_kernel(hugepd_t *pmdp, unsigned long va)
-{
-	if (hpd_val(*pmdp) == 0) {
-		pte_t *ptep = memblock_alloc(sizeof(pte_basic_t), SZ_4K);
-
-		if (!ptep)
-			return NULL;
-
-		hugepd_populate_kernel((hugepd_t *)pmdp, ptep, PAGE_SHIFT_8M);
-		hugepd_populate_kernel((hugepd_t *)pmdp + 1, ptep, PAGE_SHIFT_8M);
-	}
-	return hugepte_offset(*(hugepd_t *)pmdp, va, PGDIR_SHIFT);
-}
-
 static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
 					     pgprot_t prot, int psize, bool new)
 {
 	pmd_t *pmdp = pmd_off_k(va);
 	pte_t *ptep;
-
-	if (WARN_ON(psize != MMU_PAGE_512K && psize != MMU_PAGE_8M))
-		return -EINVAL;
+	unsigned int shift = mmu_psize_to_shift(psize);
 
 	if (new) {
 		if (WARN_ON(slab_is_available()))
 			return -EINVAL;
 
-		if (psize == MMU_PAGE_512K)
+		if (psize == MMU_PAGE_8M) {
+			if (WARN_ON(!pmd_none(*pmdp) || !pmd_none(*(pmdp + 1))))
+				return -EINVAL;
+
+			ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
+			pmd_populate_kernel(&init_mm, pmdp, ptep);
+
+			ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
+			pmd_populate_kernel(&init_mm, pmdp + 1, ptep);
+
+			ptep = (pte_t *)pmdp;
+		} else {
 			ptep = early_pte_alloc_kernel(pmdp, va);
-		else
-			ptep = early_hugepd_alloc_kernel((hugepd_t *)pmdp, va);
+			/* The PTE should never be already present */
+			if (WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
+				return -EINVAL;
+		}
 	} else {
-		if (psize == MMU_PAGE_512K)
-			ptep = pte_offset_kernel(pmdp, va);
+		if (psize == MMU_PAGE_8M)
+			ptep = (pte_t *)pmdp;
 		else
-			ptep = hugepte_offset(*(hugepd_t *)pmdp, va, PGDIR_SHIFT);
+			ptep = pte_offset_kernel(pmdp, va);
 	}
 
 	if (WARN_ON(!ptep))
 		return -ENOMEM;
 
-	/* The PTE should never be already present */
-	if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
-		return -EINVAL;
-
-	set_huge_pte_at(&init_mm, va, ptep, pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)));
+	set_huge_pte_at(&init_mm, va, ptep,
+			arch_make_huge_pte(pfn_pte(pa >> PAGE_SHIFT, prot), shift, 0),
+			1UL << shift);
 
 	return 0;
 }
@@ -116,23 +114,30 @@ void __init mmu_mapin_immr(void)
 				    PAGE_KERNEL_NCG, MMU_PAGE_512K, true);
 }
 
-static void mmu_mapin_ram_chunk(unsigned long offset, unsigned long top,
-				pgprot_t prot, bool new)
+static int mmu_mapin_ram_chunk(unsigned long offset, unsigned long top,
+			       pgprot_t prot, bool new)
 {
 	unsigned long v = PAGE_OFFSET + offset;
 	unsigned long p = offset;
+	int err = 0;
 
-	WARN_ON(!IS_ALIGNED(offset, SZ_512K) || !IS_ALIGNED(top, SZ_512K));
+	WARN_ON(!IS_ALIGNED(offset, SZ_16K) || !IS_ALIGNED(top, SZ_16K));
 
-	for (; p < ALIGN(p, SZ_8M) && p < top; p += SZ_512K, v += SZ_512K)
-		__early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
-	for (; p < ALIGN_DOWN(top, SZ_8M) && p < top; p += SZ_8M, v += SZ_8M)
-		__early_map_kernel_hugepage(v, p, prot, MMU_PAGE_8M, new);
-	for (; p < ALIGN_DOWN(top, SZ_512K) && p < top; p += SZ_512K, v += SZ_512K)
-		__early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
+	for (; p < ALIGN(p, SZ_512K) && p < top && !err; p += SZ_16K, v += SZ_16K)
+		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_16K, new);
+	for (; p < ALIGN(p, SZ_8M) && p < top && !err; p += SZ_512K, v += SZ_512K)
+		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
+	for (; p < ALIGN_DOWN(top, SZ_8M) && p < top && !err; p += SZ_8M, v += SZ_8M)
+		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_8M, new);
+	for (; p < ALIGN_DOWN(top, SZ_512K) && p < top && !err; p += SZ_512K, v += SZ_512K)
+		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_512K, new);
+	for (; p < ALIGN_DOWN(top, SZ_16K) && p < top && !err; p += SZ_16K, v += SZ_16K)
+		err = __early_map_kernel_hugepage(v, p, prot, MMU_PAGE_16K, new);
 
 	if (!new)
 		flush_tlb_kernel_range(PAGE_OFFSET + v, PAGE_OFFSET + top);
+
+	return err;
 }
 
 unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
@@ -147,11 +152,11 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 
 	mmu_mapin_immr();
 
-	mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_TEXT, true);
+	mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_X, true);
 	if (debug_pagealloc_enabled_or_kfence()) {
 		top = boundary;
 	} else {
-		mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_TEXT, true);
+		mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_X, true);
 		mmu_mapin_ram_chunk(einittext8, top, PAGE_KERNEL, true);
 	}
 
@@ -163,27 +168,34 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 	return top;
 }
 
-void mmu_mark_initmem_nx(void)
+int mmu_mark_initmem_nx(void)
 {
 	unsigned long etext8 = ALIGN(__pa(_etext), SZ_8M);
 	unsigned long sinittext = __pa(_sinittext);
 	unsigned long boundary = strict_kernel_rwx_enabled() ? sinittext : etext8;
 	unsigned long einittext8 = ALIGN(__pa(_einittext), SZ_8M);
+	int err = 0;
 
 	if (!debug_pagealloc_enabled_or_kfence())
-		mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL, false);
+		err = mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL, false);
+
+	if (IS_ENABLED(CONFIG_PIN_TLB_TEXT))
+		mmu_pin_tlb(block_mapped_ram, false);
 
-	mmu_pin_tlb(block_mapped_ram, false);
+	return err;
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
-void mmu_mark_rodata_ro(void)
+int mmu_mark_rodata_ro(void)
 {
 	unsigned long sinittext = __pa(_sinittext);
+	int err;
 
-	mmu_mapin_ram_chunk(0, sinittext, PAGE_KERNEL_ROX, false);
+	err = mmu_mapin_ram_chunk(0, sinittext, PAGE_KERNEL_ROX, false);
 	if (IS_ENABLED(CONFIG_PIN_TLB_DATA))
 		mmu_pin_tlb(block_mapped_ram, true);
+
+	return err;
 }
 #endif
 
@@ -197,6 +209,8 @@ void __init setup_initial_memory_limit(phys_addr_t first_memblock_base,
 
 	/* 8xx can only access 32MB at the moment */
 	memblock_set_current_limit(min_t(u64, first_memblock_size, SZ_32M));
+
+	BUILD_BUG_ON(ALIGN_DOWN(MODULES_VADDR, PGDIR_SIZE) < TASK_SIZE);
 }
 
 int pud_clear_huge(pud_t *pud)
diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile
index f3894e79d5f7..cf60c776c883 100644
--- a/arch/powerpc/mm/nohash/Makefile
+++ b/arch/powerpc/mm/nohash/Makefile
@@ -1,10 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
-ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
-
 obj-y				+= mmu_context.o tlb.o tlb_low.o kup.o
-obj-$(CONFIG_PPC_BOOK3E_64)  	+= tlb_low_64e.o book3e_pgtable.o
-obj-$(CONFIG_40x)		+= 40x.o
+obj-$(CONFIG_PPC_BOOK3E_64)  	+= tlb_64e.o tlb_low_64e.o book3e_pgtable.o
 obj-$(CONFIG_44x)		+= 44x.o
 obj-$(CONFIG_PPC_8xx)		+= 8xx.o
 obj-$(CONFIG_PPC_E500)		+= e500.o
diff --git a/arch/powerpc/mm/nohash/book3e_pgtable.c b/arch/powerpc/mm/nohash/book3e_pgtable.c
index b80fc4a91a53..062e8785c1bb 100644
--- a/arch/powerpc/mm/nohash/book3e_pgtable.c
+++ b/arch/powerpc/mm/nohash/book3e_pgtable.c
@@ -10,7 +10,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/dma.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 
 #include <mm/mmu_decl.h>
 
@@ -29,10 +29,10 @@ int __meminit vmemmap_create_mapping(unsigned long start,
 		_PAGE_KERNEL_RW;
 
 	/* PTEs only contain page size encodings up to 32M */
-	BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].enc > 0xf);
+	BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].shift - 10 > 0xf);
 
 	/* Encode the size in the PTE */
-	flags |= mmu_psize_defs[mmu_vmemmap_psize].enc << 8;
+	flags |= (mmu_psize_defs[mmu_vmemmap_psize].shift - 10) << 8;
 
 	/* For each PTE for that area, map things. Note that we don't
 	 * increment phys because all PTEs are of the large size and
@@ -71,7 +71,7 @@ static void __init *early_alloc_pgtable(unsigned long size)
  * map_kernel_page adds an entry to the ioremap page table
  * and adds an entry to the HPT, possibly bolting it
  */
-int __ref map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
+int __ref map_kernel_page(unsigned long ea, phys_addr_t pa, pgprot_t prot)
 {
 	pgd_t *pgdp;
 	p4d_t *p4dp;
diff --git a/arch/powerpc/mm/nohash/e500.c b/arch/powerpc/mm/nohash/e500.c
index 40a4e69ae1a9..266fb22131fc 100644
--- a/arch/powerpc/mm/nohash/e500.c
+++ b/arch/powerpc/mm/nohash/e500.c
@@ -117,15 +117,15 @@ static void settlbcam(int index, unsigned long virt, phys_addr_t phys,
 	TLBCAM[index].MAS2 |= (flags & _PAGE_ENDIAN) ? MAS2_E : 0;
 
 	TLBCAM[index].MAS3 = (phys & MAS3_RPN) | MAS3_SR;
-	TLBCAM[index].MAS3 |= (flags & _PAGE_RW) ? MAS3_SW : 0;
+	TLBCAM[index].MAS3 |= (flags & _PAGE_WRITE) ? MAS3_SW : 0;
 	if (mmu_has_feature(MMU_FTR_BIG_PHYS))
 		TLBCAM[index].MAS7 = (u64)phys >> 32;
 
 	/* Below is unlikely -- only for large user pages or similar */
-	if (pte_user(__pte(flags))) {
+	if (!is_kernel_addr(virt)) {
 		TLBCAM[index].MAS3 |= MAS3_UR;
 		TLBCAM[index].MAS3 |= (flags & _PAGE_EXEC) ? MAS3_UX : 0;
-		TLBCAM[index].MAS3 |= (flags & _PAGE_RW) ? MAS3_UW : 0;
+		TLBCAM[index].MAS3 |= (flags & _PAGE_WRITE) ? MAS3_UW : 0;
 	} else {
 		TLBCAM[index].MAS3 |= (flags & _PAGE_EXEC) ? MAS3_SX : 0;
 	}
@@ -285,19 +285,23 @@ void __init adjust_total_lowmem(void)
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
-void mmu_mark_rodata_ro(void)
+int mmu_mark_rodata_ro(void)
 {
 	unsigned long remapped;
 
 	remapped = map_mem_in_cams(__max_low_memory, CONFIG_LOWMEM_CAM_NUM, false, false);
 
-	WARN_ON(__max_low_memory != remapped);
+	if (WARN_ON(__max_low_memory != remapped))
+		return -EINVAL;
+
+	return 0;
 }
 #endif
 
-void mmu_mark_initmem_nx(void)
+int mmu_mark_initmem_nx(void)
 {
 	/* Everything is done in mmu_mark_rodata_ro() */
+	return 0;
 }
 
 void setup_initial_memory_limit(phys_addr_t first_memblock_base,
diff --git a/arch/powerpc/mm/nohash/e500_hugetlbpage.c b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
index 58c8d9849cb1..a134d28a0e4d 100644
--- a/arch/powerpc/mm/nohash/e500_hugetlbpage.c
+++ b/arch/powerpc/mm/nohash/e500_hugetlbpage.c
@@ -178,7 +178,7 @@ book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte)
  *
  * This must always be called with the pte lock held.
  */
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 {
 	if (is_vm_hugetlb_page(vma))
 		book3e_hugetlb_preload(vma, address, *ptep);
diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c
index 2fb3edafe9ab..5e4897daaaea 100644
--- a/arch/powerpc/mm/nohash/kaslr_booke.c
+++ b/arch/powerpc/mm/nohash/kaslr_booke.c
@@ -13,7 +13,7 @@
 #include <linux/delay.h>
 #include <linux/memblock.h>
 #include <linux/libfdt.h>
-#include <linux/crash_core.h>
+#include <linux/crash_reserve.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <asm/cacheflush.h>
@@ -173,12 +173,12 @@ static __init bool overlaps_region(const void *fdt, u32 start,
 
 static void __init get_crash_kernel(void *fdt, unsigned long size)
 {
-#ifdef CONFIG_CRASH_CORE
+#ifdef CONFIG_CRASH_RESERVE
 	unsigned long long crash_size, crash_base;
 	int ret;
 
 	ret = parse_crashkernel(boot_command_line, size, &crash_size,
-				&crash_base);
+				&crash_base, NULL, NULL, NULL);
 	if (ret != 0 || crash_size == 0)
 		return;
 	if (crash_base == 0)
@@ -376,7 +376,7 @@ notrace void __init kaslr_early_init(void *dt_ptr, phys_addr_t size)
 		create_kaslr_tlb_entry(1, tlb_virt, tlb_phys);
 	}
 
-	/* Copy the kernel to it's new location and run */
+	/* Copy the kernel to its new location and run */
 	memcpy((void *)kernstart_virt_addr, (void *)_stext, kernel_sz);
 	flush_icache_range(kernstart_virt_addr, kernstart_virt_addr + kernel_sz);
 
diff --git a/arch/powerpc/mm/nohash/kup.c b/arch/powerpc/mm/nohash/kup.c
index 552becf90e97..c20c4f357fbf 100644
--- a/arch/powerpc/mm/nohash/kup.c
+++ b/arch/powerpc/mm/nohash/kup.c
@@ -5,7 +5,6 @@
 
 #include <linux/export.h>
 #include <linux/init.h>
-#include <linux/jump_label.h>
 #include <linux/printk.h>
 #include <linux/smp.h>
 
@@ -13,21 +12,16 @@
 #include <asm/smp.h>
 
 #ifdef CONFIG_PPC_KUAP
-struct static_key_false disable_kuap_key;
-EXPORT_SYMBOL(disable_kuap_key);
-
 void setup_kuap(bool disabled)
 {
 	if (disabled) {
-		if (IS_ENABLED(CONFIG_40x))
-			disable_kuep = true;
 		if (smp_processor_id() == boot_cpuid)
-			static_branch_enable(&disable_kuap_key);
+			cur_cpu_spec->mmu_features &= ~MMU_FTR_KUAP;
 		return;
 	}
 
 	pr_info("Activating Kernel Userspace Access Protection\n");
 
-	__prevent_user_access(KUAP_READ_WRITE);
+	prevent_user_access(KUAP_READ_WRITE);
 }
 #endif
diff --git a/arch/powerpc/mm/nohash/mmu_context.c b/arch/powerpc/mm/nohash/mmu_context.c
index ccd5819b1bd9..28a96a10c907 100644
--- a/arch/powerpc/mm/nohash/mmu_context.c
+++ b/arch/powerpc/mm/nohash/mmu_context.c
@@ -203,15 +203,7 @@ static unsigned int steal_context_up(unsigned int id)
 static void set_context(unsigned long id, pgd_t *pgd)
 {
 	if (IS_ENABLED(CONFIG_PPC_8xx)) {
-		s16 offset = (s16)(__pa(swapper_pg_dir));
-
-		/*
-		 * Register M_TWB will contain base address of level 1 table minus the
-		 * lower part of the kernel PGDIR base address, so that all accesses to
-		 * level 1 table are done relative to lower part of kernel PGDIR base
-		 * address.
-		 */
-		mtspr(SPRN_M_TWB, __pa(pgd) - offset);
+		mtspr(SPRN_M_TWB, __pa(pgd));
 
 		/* Update context */
 		mtspr(SPRN_M_CASID, id - 1);
@@ -219,9 +211,6 @@ static void set_context(unsigned long id, pgd_t *pgd)
 		/* sync */
 		mb();
 	} else if (kuap_is_disabled()) {
-		if (IS_ENABLED(CONFIG_40x))
-			mb();	/* sync */
-
 		mtspr(SPRN_PID, id);
 		isync();
 	}
@@ -306,7 +295,7 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next,
 	if (IS_ENABLED(CONFIG_BDI_SWITCH))
 		abatron_pteptrs[1] = next->pgd;
 	set_context(id, next->pgd);
-#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP)
+#if defined(CONFIG_BOOKE) && defined(CONFIG_PPC_KUAP)
 	tsk->thread.pid = id;
 #endif
 	raw_spin_unlock(&context_lock);
@@ -388,21 +377,11 @@ void __init mmu_context_init(void)
 	/*
 	 * Allocate the maps used by context management
 	 */
-	context_map = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES);
-	if (!context_map)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      CTX_MAP_SIZE);
-	context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1),
+	context_map = memblock_alloc_or_panic(CTX_MAP_SIZE, SMP_CACHE_BYTES);
+	context_mm = memblock_alloc_or_panic(sizeof(void *) * (LAST_CONTEXT + 1),
 				    SMP_CACHE_BYTES);
-	if (!context_mm)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(void *) * (LAST_CONTEXT + 1));
 	if (IS_ENABLED(CONFIG_SMP)) {
-		stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES);
-		if (!stale_map[boot_cpuid])
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      CTX_MAP_SIZE);
-
+		stale_map[boot_cpuid] = memblock_alloc_or_panic(CTX_MAP_SIZE, SMP_CACHE_BYTES);
 		cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE,
 					  "powerpc/mmu/ctx:prepare",
 					  mmu_ctx_cpu_prepare, mmu_ctx_cpu_dead);
diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
index a903b308acc5..0a650742f3a0 100644
--- a/arch/powerpc/mm/nohash/tlb.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -37,7 +37,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/cputhreads.h>
 #include <asm/hugetlb.h>
 #include <asm/paca.h>
@@ -53,37 +53,30 @@
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 	[MMU_PAGE_4K] = {
 		.shift	= 12,
-		.enc	= BOOK3E_PAGESZ_4K,
 	},
 	[MMU_PAGE_2M] = {
 		.shift	= 21,
-		.enc	= BOOK3E_PAGESZ_2M,
 	},
 	[MMU_PAGE_4M] = {
 		.shift	= 22,
-		.enc	= BOOK3E_PAGESZ_4M,
 	},
 	[MMU_PAGE_16M] = {
 		.shift	= 24,
-		.enc	= BOOK3E_PAGESZ_16M,
 	},
 	[MMU_PAGE_64M] = {
 		.shift	= 26,
-		.enc	= BOOK3E_PAGESZ_64M,
 	},
 	[MMU_PAGE_256M] = {
 		.shift	= 28,
-		.enc	= BOOK3E_PAGESZ_256M,
 	},
 	[MMU_PAGE_1G] = {
 		.shift	= 30,
-		.enc	= BOOK3E_PAGESZ_1GB,
 	},
 };
 
 static inline int mmu_get_tsize(int psize)
 {
-	return mmu_psize_defs[psize].enc;
+	return mmu_psize_defs[psize].shift - 10;
 }
 #else
 static inline int mmu_get_tsize(int psize)
@@ -110,28 +103,6 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 };
 #endif
 
-/* The variables below are currently only used on 64-bit Book3E
- * though this will probably be made common with other nohash
- * implementations at some point
- */
-#ifdef CONFIG_PPC64
-
-int mmu_pte_psize;		/* Page size used for PTE pages */
-int mmu_vmemmap_psize;		/* Page size used for the virtual mem map */
-int book3e_htw_mode;		/* HW tablewalk?  Value is PPC_HTW_* */
-unsigned long linear_map_top;	/* Top of linear mapping */
-
-
-/*
- * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug
- * exceptions.  This is used for bolted and e6500 TLB miss handlers which
- * do not modify this SPRG in the TLB miss code; for other TLB miss handlers,
- * this is set to zero.
- */
-int extlb_level_exc;
-
-#endif /* CONFIG_PPC64 */
-
 #ifdef CONFIG_PPC_E500
 /* next_tlbcam_idx is used to round-robin tlbcam entry assignment */
 DEFINE_PER_CPU(int, next_tlbcam_idx);
@@ -318,17 +289,6 @@ EXPORT_SYMBOL(flush_tlb_page);
 
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_PPC_47x
-void __init early_init_mmu_47x(void)
-{
-#ifdef CONFIG_SMP
-	unsigned long root = of_get_flat_dt_root();
-	if (of_get_flat_dt_prop(root, "cooperative-partition", NULL))
-		mmu_clear_feature(MMU_FTR_USE_TLBIVAX_BCAST);
-#endif /* CONFIG_SMP */
-}
-#endif /* CONFIG_PPC_47x */
-
 /*
  * Flush kernel TLB entries in the given range
  */
@@ -369,385 +329,13 @@ void tlb_flush(struct mmu_gather *tlb)
 	flush_tlb_mm(tlb->mm);
 }
 
-/*
- * Below are functions specific to the 64-bit variant of Book3E though that
- * may change in the future
- */
-
-#ifdef CONFIG_PPC64
-
-/*
- * Handling of virtual linear page tables or indirect TLB entries
- * flushing when PTE pages are freed
- */
-void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
-{
-	int tsize = mmu_psize_defs[mmu_pte_psize].enc;
-
-	if (book3e_htw_mode != PPC_HTW_NONE) {
-		unsigned long start = address & PMD_MASK;
-		unsigned long end = address + PMD_SIZE;
-		unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
-
-		/* This isn't the most optimal, ideally we would factor out the
-		 * while preempt & CPU mask mucking around, or even the IPI but
-		 * it will do for now
-		 */
-		while (start < end) {
-			__flush_tlb_page(tlb->mm, start, tsize, 1);
-			start += size;
-		}
-	} else {
-		unsigned long rmask = 0xf000000000000000ul;
-		unsigned long rid = (address & rmask) | 0x1000000000000000ul;
-		unsigned long vpte = address & ~rmask;
-
-		vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
-		vpte |= rid;
-		__flush_tlb_page(tlb->mm, vpte, tsize, 0);
-	}
-}
-
-static void __init setup_page_sizes(void)
-{
-	unsigned int tlb0cfg;
-	unsigned int tlb0ps;
-	unsigned int eptcfg;
-	int i, psize;
-
-#ifdef CONFIG_PPC_E500
-	unsigned int mmucfg = mfspr(SPRN_MMUCFG);
-	int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E);
-
-	if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) {
-		unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
-		unsigned int min_pg, max_pg;
-
-		min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
-		max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
-
-		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-			struct mmu_psize_def *def;
-			unsigned int shift;
-
-			def = &mmu_psize_defs[psize];
-			shift = def->shift;
-
-			if (shift == 0 || shift & 1)
-				continue;
-
-			/* adjust to be in terms of 4^shift Kb */
-			shift = (shift - 10) >> 1;
-
-			if ((shift >= min_pg) && (shift <= max_pg))
-				def->flags |= MMU_PAGE_SIZE_DIRECT;
-		}
-
-		goto out;
-	}
-
-	if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) {
-		u32 tlb1cfg, tlb1ps;
-
-		tlb0cfg = mfspr(SPRN_TLB0CFG);
-		tlb1cfg = mfspr(SPRN_TLB1CFG);
-		tlb1ps = mfspr(SPRN_TLB1PS);
-		eptcfg = mfspr(SPRN_EPTCFG);
-
-		if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT))
-			book3e_htw_mode = PPC_HTW_E6500;
-
-		/*
-		 * We expect 4K subpage size and unrestricted indirect size.
-		 * The lack of a restriction on indirect size is a Freescale
-		 * extension, indicated by PSn = 0 but SPSn != 0.
-		 */
-		if (eptcfg != 2)
-			book3e_htw_mode = PPC_HTW_NONE;
-
-		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-			struct mmu_psize_def *def = &mmu_psize_defs[psize];
-
-			if (!def->shift)
-				continue;
-
-			if (tlb1ps & (1U << (def->shift - 10))) {
-				def->flags |= MMU_PAGE_SIZE_DIRECT;
-
-				if (book3e_htw_mode && psize == MMU_PAGE_2M)
-					def->flags |= MMU_PAGE_SIZE_INDIRECT;
-			}
-		}
-
-		goto out;
-	}
-#endif
-
-	tlb0cfg = mfspr(SPRN_TLB0CFG);
-	tlb0ps = mfspr(SPRN_TLB0PS);
-	eptcfg = mfspr(SPRN_EPTCFG);
-
-	/* Look for supported direct sizes */
-	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-		struct mmu_psize_def *def = &mmu_psize_defs[psize];
-
-		if (tlb0ps & (1U << (def->shift - 10)))
-			def->flags |= MMU_PAGE_SIZE_DIRECT;
-	}
-
-	/* Indirect page sizes supported ? */
-	if ((tlb0cfg & TLBnCFG_IND) == 0 ||
-	    (tlb0cfg & TLBnCFG_PT) == 0)
-		goto out;
-
-	book3e_htw_mode = PPC_HTW_IBM;
-
-	/* Now, we only deal with one IND page size for each
-	 * direct size. Hopefully all implementations today are
-	 * unambiguous, but we might want to be careful in the
-	 * future.
-	 */
-	for (i = 0; i < 3; i++) {
-		unsigned int ps, sps;
-
-		sps = eptcfg & 0x1f;
-		eptcfg >>= 5;
-		ps = eptcfg & 0x1f;
-		eptcfg >>= 5;
-		if (!ps || !sps)
-			continue;
-		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
-			struct mmu_psize_def *def = &mmu_psize_defs[psize];
-
-			if (ps == (def->shift - 10))
-				def->flags |= MMU_PAGE_SIZE_INDIRECT;
-			if (sps == (def->shift - 10))
-				def->ind = ps + 10;
-		}
-	}
-
-out:
-	/* Cleanup array and print summary */
-	pr_info("MMU: Supported page sizes\n");
-	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-		struct mmu_psize_def *def = &mmu_psize_defs[psize];
-		const char *__page_type_names[] = {
-			"unsupported",
-			"direct",
-			"indirect",
-			"direct & indirect"
-		};
-		if (def->flags == 0) {
-			def->shift = 0;	
-			continue;
-		}
-		pr_info("  %8ld KB as %s\n", 1ul << (def->shift - 10),
-			__page_type_names[def->flags & 0x3]);
-	}
-}
-
-static void __init setup_mmu_htw(void)
-{
-	/*
-	 * If we want to use HW tablewalk, enable it by patching the TLB miss
-	 * handlers to branch to the one dedicated to it.
-	 */
-
-	switch (book3e_htw_mode) {
-	case PPC_HTW_IBM:
-		patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e);
-		patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e);
-		break;
-#ifdef CONFIG_PPC_E500
-	case PPC_HTW_E6500:
-		extlb_level_exc = EX_TLB_SIZE;
-		patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
-		patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
-		break;
-#endif
-	}
-	pr_info("MMU: Book3E HW tablewalk %s\n",
-		book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported");
-}
-
-/*
- * Early initialization of the MMU TLB code
- */
-static void early_init_this_mmu(void)
-{
-	unsigned int mas4;
-
-	/* Set MAS4 based on page table setting */
-
-	mas4 = 0x4 << MAS4_WIMGED_SHIFT;
-	switch (book3e_htw_mode) {
-	case PPC_HTW_E6500:
-		mas4 |= MAS4_INDD;
-		mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT;
-		mas4 |= MAS4_TLBSELD(1);
-		mmu_pte_psize = MMU_PAGE_2M;
-		break;
-
-	case PPC_HTW_IBM:
-		mas4 |= MAS4_INDD;
-		mas4 |=	BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT;
-		mmu_pte_psize = MMU_PAGE_1M;
-		break;
-
-	case PPC_HTW_NONE:
-		mas4 |=	BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
-		mmu_pte_psize = mmu_virtual_psize;
-		break;
-	}
-	mtspr(SPRN_MAS4, mas4);
-
-#ifdef CONFIG_PPC_E500
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
-		unsigned int num_cams;
-		bool map = true;
-
-		/* use a quarter of the TLBCAM for bolted linear map */
-		num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
-
-		/*
-		 * Only do the mapping once per core, or else the
-		 * transient mapping would cause problems.
-		 */
-#ifdef CONFIG_SMP
-		if (hweight32(get_tensr()) > 1)
-			map = false;
-#endif
-
-		if (map)
-			linear_map_top = map_mem_in_cams(linear_map_top,
-							 num_cams, false, true);
-	}
-#endif
-
-	/* A sync won't hurt us after mucking around with
-	 * the MMU configuration
-	 */
-	mb();
-}
-
-static void __init early_init_mmu_global(void)
-{
-	/* XXX This should be decided at runtime based on supported
-	 * page sizes in the TLB, but for now let's assume 16M is
-	 * always there and a good fit (which it probably is)
-	 *
-	 * Freescale booke only supports 4K pages in TLB0, so use that.
-	 */
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
-		mmu_vmemmap_psize = MMU_PAGE_4K;
-	else
-		mmu_vmemmap_psize = MMU_PAGE_16M;
-
-	/* XXX This code only checks for TLB 0 capabilities and doesn't
-	 *     check what page size combos are supported by the HW. It
-	 *     also doesn't handle the case where a separate array holds
-	 *     the IND entries from the array loaded by the PT.
-	 */
-	/* Look for supported page sizes */
-	setup_page_sizes();
-
-	/* Look for HW tablewalk support */
-	setup_mmu_htw();
-
-#ifdef CONFIG_PPC_E500
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
-		if (book3e_htw_mode == PPC_HTW_NONE) {
-			extlb_level_exc = EX_TLB_SIZE;
-			patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
-			patch_exception(0x1e0,
-				exc_instruction_tlb_miss_bolted_book3e);
-		}
-	}
-#endif
-
-	/* Set the global containing the top of the linear mapping
-	 * for use by the TLB miss code
-	 */
-	linear_map_top = memblock_end_of_DRAM();
-
-	ioremap_bot = IOREMAP_BASE;
-}
-
-static void __init early_mmu_set_memory_limit(void)
-{
-#ifdef CONFIG_PPC_E500
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
-		/*
-		 * Limit memory so we dont have linear faults.
-		 * Unlike memblock_set_current_limit, which limits
-		 * memory available during early boot, this permanently
-		 * reduces the memory available to Linux.  We need to
-		 * do this because highmem is not supported on 64-bit.
-		 */
-		memblock_enforce_memory_limit(linear_map_top);
-	}
-#endif
-
-	memblock_set_current_limit(linear_map_top);
-}
-
-/* boot cpu only */
+#ifndef CONFIG_PPC64
 void __init early_init_mmu(void)
 {
-	early_init_mmu_global();
-	early_init_this_mmu();
-	early_mmu_set_memory_limit();
-}
-
-void early_init_mmu_secondary(void)
-{
-	early_init_this_mmu();
-}
-
-void setup_initial_memory_limit(phys_addr_t first_memblock_base,
-				phys_addr_t first_memblock_size)
-{
-	/* On non-FSL Embedded 64-bit, we adjust the RMA size to match
-	 * the bolted TLB entry. We know for now that only 1G
-	 * entries are supported though that may eventually
-	 * change.
-	 *
-	 * on FSL Embedded 64-bit, usually all RAM is bolted, but with
-	 * unusual memory sizes it's possible for some RAM to not be mapped
-	 * (such RAM is not used at all by Linux, since we don't support
-	 * highmem on 64-bit).  We limit ppc64_rma_size to what would be
-	 * mappable if this memblock is the only one.  Additional memblocks
-	 * can only increase, not decrease, the amount that ends up getting
-	 * mapped.  We still limit max to 1G even if we'll eventually map
-	 * more.  This is due to what the early init code is set up to do.
-	 *
-	 * We crop it to the size of the first MEMBLOCK to
-	 * avoid going over total available memory just in case...
-	 */
-#ifdef CONFIG_PPC_E500
-	if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
-		unsigned long linear_sz;
-		unsigned int num_cams;
-
-		/* use a quarter of the TLBCAM for bolted linear map */
-		num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
-
-		linear_sz = map_mem_in_cams(first_memblock_size, num_cams,
-					    true, true);
-
-		ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
-	} else
-#endif
-		ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+	unsigned long root = of_get_flat_dt_root();
 
-	/* Finally limit subsequent allocations */
-	memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
-}
-#else /* ! CONFIG_PPC64 */
-void __init early_init_mmu(void)
-{
-#ifdef CONFIG_PPC_47x
-	early_init_mmu_47x();
-#endif
+	if (IS_ENABLED(CONFIG_PPC_47x) && IS_ENABLED(CONFIG_SMP) &&
+	    of_get_flat_dt_prop(root, "cooperative-partition", NULL))
+		mmu_clear_feature(MMU_FTR_USE_TLBIVAX_BCAST);
 }
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/mm/nohash/tlb_64e.c b/arch/powerpc/mm/nohash/tlb_64e.c
new file mode 100644
index 000000000000..4f925adf2695
--- /dev/null
+++ b/arch/powerpc/mm/nohash/tlb_64e.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2008,2009 Ben Herrenschmidt <benh@kernel.crashing.org>
+ *                     IBM Corp.
+ *
+ *  Derived from arch/ppc/mm/init.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/memblock.h>
+
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+#include <asm/text-patching.h>
+#include <asm/cputhreads.h>
+
+#include <mm/mmu_decl.h>
+
+/* The variables below are currently only used on 64-bit Book3E
+ * though this will probably be made common with other nohash
+ * implementations at some point
+ */
+static int mmu_pte_psize;	/* Page size used for PTE pages */
+int mmu_vmemmap_psize;		/* Page size used for the virtual mem map */
+int book3e_htw_mode;		/* HW tablewalk?  Value is PPC_HTW_* */
+unsigned long linear_map_top;	/* Top of linear mapping */
+
+
+/*
+ * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug
+ * exceptions.  This is used for bolted and e6500 TLB miss handlers which
+ * do not modify this SPRG in the TLB miss code; for other TLB miss handlers,
+ * this is set to zero.
+ */
+int extlb_level_exc;
+
+/*
+ * Handling of virtual linear page tables or indirect TLB entries
+ * flushing when PTE pages are freed
+ */
+void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
+{
+	int tsize = mmu_psize_defs[mmu_pte_psize].shift - 10;
+
+	if (book3e_htw_mode != PPC_HTW_NONE) {
+		unsigned long start = address & PMD_MASK;
+		unsigned long end = address + PMD_SIZE;
+		unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
+
+		/* This isn't the most optimal, ideally we would factor out the
+		 * while preempt & CPU mask mucking around, or even the IPI but
+		 * it will do for now
+		 */
+		while (start < end) {
+			__flush_tlb_page(tlb->mm, start, tsize, 1);
+			start += size;
+		}
+	} else {
+		unsigned long rmask = 0xf000000000000000ul;
+		unsigned long rid = (address & rmask) | 0x1000000000000000ul;
+		unsigned long vpte = address & ~rmask;
+
+		vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
+		vpte |= rid;
+		__flush_tlb_page(tlb->mm, vpte, tsize, 0);
+	}
+}
+
+static void __init setup_page_sizes(void)
+{
+	unsigned int tlb0cfg;
+	unsigned int eptcfg;
+	int psize;
+
+	unsigned int mmucfg = mfspr(SPRN_MMUCFG);
+
+	if ((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) {
+		unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
+		unsigned int min_pg, max_pg;
+
+		min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
+		max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
+
+		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+			struct mmu_psize_def *def;
+			unsigned int shift;
+
+			def = &mmu_psize_defs[psize];
+			shift = def->shift;
+
+			if (shift == 0 || shift & 1)
+				continue;
+
+			/* adjust to be in terms of 4^shift Kb */
+			shift = (shift - 10) >> 1;
+
+			if ((shift >= min_pg) && (shift <= max_pg))
+				def->flags |= MMU_PAGE_SIZE_DIRECT;
+		}
+
+		goto out;
+	}
+
+	if ((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) {
+		u32 tlb1cfg, tlb1ps;
+
+		tlb0cfg = mfspr(SPRN_TLB0CFG);
+		tlb1cfg = mfspr(SPRN_TLB1CFG);
+		tlb1ps = mfspr(SPRN_TLB1PS);
+		eptcfg = mfspr(SPRN_EPTCFG);
+
+		if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT))
+			book3e_htw_mode = PPC_HTW_E6500;
+
+		/*
+		 * We expect 4K subpage size and unrestricted indirect size.
+		 * The lack of a restriction on indirect size is a Freescale
+		 * extension, indicated by PSn = 0 but SPSn != 0.
+		 */
+		if (eptcfg != 2)
+			book3e_htw_mode = PPC_HTW_NONE;
+
+		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+			struct mmu_psize_def *def = &mmu_psize_defs[psize];
+
+			if (!def->shift)
+				continue;
+
+			if (tlb1ps & (1U << (def->shift - 10))) {
+				def->flags |= MMU_PAGE_SIZE_DIRECT;
+
+				if (book3e_htw_mode && psize == MMU_PAGE_2M)
+					def->flags |= MMU_PAGE_SIZE_INDIRECT;
+			}
+		}
+
+		goto out;
+	}
+out:
+	/* Cleanup array and print summary */
+	pr_info("MMU: Supported page sizes\n");
+	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+		struct mmu_psize_def *def = &mmu_psize_defs[psize];
+		const char *__page_type_names[] = {
+			"unsupported",
+			"direct",
+			"indirect",
+			"direct & indirect"
+		};
+		if (def->flags == 0) {
+			def->shift = 0;
+			continue;
+		}
+		pr_info("  %8ld KB as %s\n", 1ul << (def->shift - 10),
+			__page_type_names[def->flags & 0x3]);
+	}
+}
+
+/*
+ * Early initialization of the MMU TLB code
+ */
+static void early_init_this_mmu(void)
+{
+	unsigned int mas4;
+
+	/* Set MAS4 based on page table setting */
+
+	mas4 = 0x4 << MAS4_WIMGED_SHIFT;
+	switch (book3e_htw_mode) {
+	case PPC_HTW_E6500:
+		mas4 |= MAS4_INDD;
+		mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT;
+		mas4 |= MAS4_TLBSELD(1);
+		mmu_pte_psize = MMU_PAGE_2M;
+		break;
+
+	case PPC_HTW_NONE:
+		mas4 |=	BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
+		mmu_pte_psize = mmu_virtual_psize;
+		break;
+	}
+	mtspr(SPRN_MAS4, mas4);
+
+	unsigned int num_cams;
+	bool map = true;
+
+	/* use a quarter of the TLBCAM for bolted linear map */
+	num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+
+	/*
+	 * Only do the mapping once per core, or else the
+	 * transient mapping would cause problems.
+	 */
+#ifdef CONFIG_SMP
+	if (hweight32(get_tensr()) > 1)
+		map = false;
+#endif
+
+	if (map)
+		linear_map_top = map_mem_in_cams(linear_map_top,
+						 num_cams, false, true);
+
+	/* A sync won't hurt us after mucking around with
+	 * the MMU configuration
+	 */
+	mb();
+}
+
+static void __init early_init_mmu_global(void)
+{
+	/*
+	 * Freescale booke only supports 4K pages in TLB0, so use that.
+	 */
+	mmu_vmemmap_psize = MMU_PAGE_4K;
+
+	/* XXX This code only checks for TLB 0 capabilities and doesn't
+	 *     check what page size combos are supported by the HW. It
+	 *     also doesn't handle the case where a separate array holds
+	 *     the IND entries from the array loaded by the PT.
+	 */
+	/* Look for supported page sizes */
+	setup_page_sizes();
+
+	/*
+	 * If we want to use HW tablewalk, enable it by patching the TLB miss
+	 * handlers to branch to the one dedicated to it.
+	 */
+	extlb_level_exc = EX_TLB_SIZE;
+	switch (book3e_htw_mode) {
+	case PPC_HTW_E6500:
+		patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
+		patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
+		break;
+	}
+
+	pr_info("MMU: Book3E HW tablewalk %s\n",
+		book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported");
+
+	/* Set the global containing the top of the linear mapping
+	 * for use by the TLB miss code
+	 */
+	linear_map_top = memblock_end_of_DRAM();
+
+	ioremap_bot = IOREMAP_BASE;
+}
+
+static void __init early_mmu_set_memory_limit(void)
+{
+	/*
+	 * Limit memory so we dont have linear faults.
+	 * Unlike memblock_set_current_limit, which limits
+	 * memory available during early boot, this permanently
+	 * reduces the memory available to Linux.  We need to
+	 * do this because highmem is not supported on 64-bit.
+	 */
+	memblock_enforce_memory_limit(linear_map_top);
+
+	memblock_set_current_limit(linear_map_top);
+}
+
+/* boot cpu only */
+void __init early_init_mmu(void)
+{
+	early_init_mmu_global();
+	early_init_this_mmu();
+	early_mmu_set_memory_limit();
+}
+
+void early_init_mmu_secondary(void)
+{
+	early_init_this_mmu();
+}
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/*
+	 * On FSL Embedded 64-bit, usually all RAM is bolted, but with
+	 * unusual memory sizes it's possible for some RAM to not be mapped
+	 * (such RAM is not used at all by Linux, since we don't support
+	 * highmem on 64-bit).  We limit ppc64_rma_size to what would be
+	 * mappable if this memblock is the only one.  Additional memblocks
+	 * can only increase, not decrease, the amount that ends up getting
+	 * mapped.  We still limit max to 1G even if we'll eventually map
+	 * more.  This is due to what the early init code is set up to do.
+	 *
+	 * We crop it to the size of the first MEMBLOCK to
+	 * avoid going over total available memory just in case...
+	 */
+	unsigned long linear_sz;
+	unsigned int num_cams;
+
+	/* use a quarter of the TLBCAM for bolted linear map */
+	num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+
+	linear_sz = map_mem_in_cams(first_memblock_size, num_cams, true, true);
+	ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
+
+	/* Finally limit subsequent allocations */
+	memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
+}
diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S
index e1199608ff4d..c4d296e73731 100644
--- a/arch/powerpc/mm/nohash/tlb_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -32,32 +32,7 @@
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
-#if defined(CONFIG_40x)
-
-/*
- * 40x implementation needs only tlbil_va
- */
-_GLOBAL(__tlbil_va)
-	/* We run the search with interrupts disabled because we have to change
-	 * the PID and I don't want to preempt when that happens.
-	 */
-	mfmsr	r5
-	mfspr	r6,SPRN_PID
-	wrteei	0
-	mtspr	SPRN_PID,r4
-	tlbsx.	r3, 0, r3
-	mtspr	SPRN_PID,r6
-	wrtee	r5
-	bne	1f
-	sync
-	/* There are only 64 TLB entries, so r3 < 64, which means bit 25 is
-	 * clear. Since 25 is the V bit in the TLB_TAG, loading this value
-	 * will invalidate the TLB entry. */
-	tlbwe	r3, r3, TLB_TAG
-	isync
-1:	blr
-
-#elif defined(CONFIG_PPC_8xx)
+#if defined(CONFIG_PPC_8xx)
 
 /*
  * Nothing to do for 8xx, everything is inline
diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S
index 7e0b8fe1c279..de568297d5c5 100644
--- a/arch/powerpc/mm/nohash/tlb_low_64e.S
+++ b/arch/powerpc/mm/nohash/tlb_low_64e.S
@@ -450,11 +450,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SMT)
 
 tlb_miss_huge_e6500:
 	beq	tlb_miss_fault_e6500
-	li	r10,1
-	andi.	r15,r14,HUGEPD_SHIFT_MASK@l /* r15 = psize */
-	rldimi	r14,r10,63,0		/* Set PD_HUGE */
-	xor	r14,r14,r15		/* Clear size bits */
-	ldx	r14,0,r14
+	rlwinm	r15,r14,32-_PAGE_PSIZE_SHIFT,0x1e
 
 	/*
 	 * Now we build the MAS for a huge page.
@@ -465,7 +461,6 @@ tlb_miss_huge_e6500:
 	 * MAS 2,3+7:	Needs to be redone similar to non-tablewalk handler
 	 */
 
-	subi	r15,r15,10		/* Convert psize to tsize */
 	mfspr	r10,SPRN_MAS1
 	rlwinm	r10,r10,0,~MAS1_IND
 	rlwimi	r10,r15,MAS1_TSIZE_SHIFT,MAS1_TSIZE_MASK
@@ -511,232 +506,6 @@ itlb_miss_fault_e6500:
 	tlb_epilog_bolted
 	b	exc_instruction_storage_book3e
 
-/**********************************************************************
- *                                                                    *
- * TLB miss handling for Book3E with TLB reservation and HES support  *
- *                                                                    *
- **********************************************************************/
-
-
-/* Data TLB miss */
-	START_EXCEPTION(data_tlb_miss)
-	TLB_MISS_PROLOG
-
-	/* Now we handle the fault proper. We only save DEAR in normal
-	 * fault case since that's the only interesting values here.
-	 * We could probably also optimize by not saving SRR0/1 in the
-	 * linear mapping case but I'll leave that for later
-	 */
-	mfspr	r14,SPRN_ESR
-	mfspr	r16,SPRN_DEAR		/* get faulting address */
-	srdi	r15,r16,44		/* get region */
-	xoris	r15,r15,0xc
-	cmpldi	cr0,r15,0		/* linear mapping ? */
-	beq	tlb_load_linear		/* yes -> go to linear map load */
-	cmpldi	cr1,r15,1		/* vmalloc mapping ? */
-
-	/* The page tables are mapped virtually linear. At this point, though,
-	 * we don't know whether we are trying to fault in a first level
-	 * virtual address or a virtual page table address. We can get that
-	 * from bit 0x1 of the region ID which we have set for a page table
-	 */
-	andis.	r10,r15,0x1
-	bne-	virt_page_table_tlb_miss
-
-	std	r14,EX_TLB_ESR(r12);	/* save ESR */
-	std	r16,EX_TLB_DEAR(r12);	/* save DEAR */
-
-	 /* We need _PAGE_PRESENT and  _PAGE_ACCESSED set */
-	li	r11,_PAGE_PRESENT
-	oris	r11,r11,_PAGE_ACCESSED@h
-
-	/* We do the user/kernel test for the PID here along with the RW test
-	 */
-	srdi.	r15,r16,60		/* Check for user region */
-
-	/* We pre-test some combination of permissions to avoid double
-	 * faults:
-	 *
-	 * We move the ESR:ST bit into the position of _PAGE_BAP_SW in the PTE
-	 * ESR_ST   is 0x00800000
-	 * _PAGE_BAP_SW is 0x00000010
-	 * So the shift is >> 19. This tests for supervisor writeability.
-	 * If the page happens to be supervisor writeable and not user
-	 * writeable, we will take a new fault later, but that should be
-	 * a rare enough case.
-	 *
-	 * We also move ESR_ST in _PAGE_DIRTY position
-	 * _PAGE_DIRTY is 0x00001000 so the shift is >> 11
-	 *
-	 * MAS1 is preset for all we need except for TID that needs to
-	 * be cleared for kernel translations
-	 */
-	rlwimi	r11,r14,32-19,27,27
-	rlwimi	r11,r14,32-16,19,19
-	beq	normal_tlb_miss_user
-	/* XXX replace the RMW cycles with immediate loads + writes */
-1:	mfspr	r10,SPRN_MAS1
-	rlwinm	r10,r10,0,16,1		/* Clear TID */
-	mtspr	SPRN_MAS1,r10
-	beq+	cr1,normal_tlb_miss
-
-	/* We got a crappy address, just fault with whatever DEAR and ESR
-	 * are here
-	 */
-	TLB_MISS_EPILOG_ERROR
-	b	exc_data_storage_book3e
-
-/* Instruction TLB miss */
-	START_EXCEPTION(instruction_tlb_miss)
-	TLB_MISS_PROLOG
-
-	/* If we take a recursive fault, the second level handler may need
-	 * to know whether we are handling a data or instruction fault in
-	 * order to get to the right store fault handler. We provide that
-	 * info by writing a crazy value in ESR in our exception frame
-	 */
-	li	r14,-1	/* store to exception frame is done later */
-
-	/* Now we handle the fault proper. We only save DEAR in the non
-	 * linear mapping case since we know the linear mapping case will
-	 * not re-enter. We could indeed optimize and also not save SRR0/1
-	 * in the linear mapping case but I'll leave that for later
-	 *
-	 * Faulting address is SRR0 which is already in r16
-	 */
-	srdi	r15,r16,44		/* get region */
-	xoris	r15,r15,0xc
-	cmpldi	cr0,r15,0		/* linear mapping ? */
-	beq	tlb_load_linear		/* yes -> go to linear map load */
-	cmpldi	cr1,r15,1		/* vmalloc mapping ? */
-
-	/* We do the user/kernel test for the PID here along with the RW test
-	 */
-	li	r11,_PAGE_PRESENT|_PAGE_BAP_UX	/* Base perm */
-	oris	r11,r11,_PAGE_ACCESSED@h
-
-	srdi.	r15,r16,60			/* Check for user region */
-	std	r14,EX_TLB_ESR(r12)		/* write crazy -1 to frame */
-	beq	normal_tlb_miss_user
-
-	li	r11,_PAGE_PRESENT|_PAGE_BAP_SX	/* Base perm */
-	oris	r11,r11,_PAGE_ACCESSED@h
-	/* XXX replace the RMW cycles with immediate loads + writes */
-	mfspr	r10,SPRN_MAS1
-	rlwinm	r10,r10,0,16,1			/* Clear TID */
-	mtspr	SPRN_MAS1,r10
-	beq+	cr1,normal_tlb_miss
-
-	/* We got a crappy address, just fault */
-	TLB_MISS_EPILOG_ERROR
-	b	exc_instruction_storage_book3e
-
-/*
- * This is the guts of the first-level TLB miss handler for direct
- * misses. We are entered with:
- *
- * r16 = faulting address
- * r15 = region ID
- * r14 = crap (free to use)
- * r13 = PACA
- * r12 = TLB exception frame in PACA
- * r11 = PTE permission mask
- * r10 = crap (free to use)
- */
-normal_tlb_miss_user:
-#ifdef CONFIG_PPC_KUAP
-	mfspr	r14,SPRN_MAS1
-	rlwinm.	r14,r14,0,0x3fff0000
-	beq-	normal_tlb_miss_access_fault /* KUAP fault */
-#endif
-normal_tlb_miss:
-	/* So we first construct the page table address. We do that by
-	 * shifting the bottom of the address (not the region ID) by
-	 * PAGE_SHIFT-3, clearing the bottom 3 bits (get a PTE ptr) and
-	 * or'ing the fourth high bit.
-	 *
-	 * NOTE: For 64K pages, we do things slightly differently in
-	 * order to handle the weird page table format used by linux
-	 */
-	srdi	r15,r16,44
-	oris	r10,r15,0x1
-	rldicl	r14,r16,64-(PAGE_SHIFT-3),PAGE_SHIFT-3+4
-	sldi	r15,r10,44
-	clrrdi	r14,r14,19
-	or	r10,r15,r14
-
-	ld	r14,0(r10)
-
-finish_normal_tlb_miss:
-	/* Check if required permissions are met */
-	andc.	r15,r11,r14
-	bne-	normal_tlb_miss_access_fault
-
-	/* Now we build the MAS:
-	 *
-	 * MAS 0   :	Fully setup with defaults in MAS4 and TLBnCFG
-	 * MAS 1   :	Almost fully setup
-	 *               - PID already updated by caller if necessary
-	 *               - TSIZE need change if !base page size, not
-	 *                 yet implemented for now
-	 * MAS 2   :	Defaults not useful, need to be redone
-	 * MAS 3+7 :	Needs to be done
-	 *
-	 * TODO: mix up code below for better scheduling
-	 */
-	clrrdi	r10,r16,12		/* Clear low crap in EA */
-	rlwimi	r10,r14,32-19,27,31	/* Insert WIMGE */
-	mtspr	SPRN_MAS2,r10
-
-	/* Check page size, if not standard, update MAS1 */
-	rldicl	r10,r14,64-8,64-8
-	cmpldi	cr0,r10,BOOK3E_PAGESZ_4K
-	beq-	1f
-	mfspr	r11,SPRN_MAS1
-	rlwimi	r11,r14,31,21,24
-	rlwinm	r11,r11,0,21,19
-	mtspr	SPRN_MAS1,r11
-1:
-	/* Move RPN in position */
-	rldicr	r11,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
-	clrldi	r15,r11,12		/* Clear crap at the top */
-	rlwimi	r15,r14,32-8,22,25	/* Move in U bits */
-	rlwimi	r15,r14,32-2,26,31	/* Move in BAP bits */
-
-	/* Mask out SW and UW if !DIRTY (XXX optimize this !) */
-	andi.	r11,r14,_PAGE_DIRTY
-	bne	1f
-	li	r11,MAS3_SW|MAS3_UW
-	andc	r15,r15,r11
-1:
-	srdi	r16,r15,32
-	mtspr	SPRN_MAS3,r15
-	mtspr	SPRN_MAS7,r16
-
-	tlbwe
-
-normal_tlb_miss_done:
-	/* We don't bother with restoring DEAR or ESR since we know we are
-	 * level 0 and just going back to userland. They are only needed
-	 * if you are going to take an access fault
-	 */
-	TLB_MISS_EPILOG_SUCCESS
-	rfi
-
-normal_tlb_miss_access_fault:
-	/* We need to check if it was an instruction miss */
-	andi.	r10,r11,_PAGE_BAP_UX
-	bne	1f
-	ld	r14,EX_TLB_DEAR(r12)
-	ld	r15,EX_TLB_ESR(r12)
-	mtspr	SPRN_DEAR,r14
-	mtspr	SPRN_ESR,r15
-	TLB_MISS_EPILOG_ERROR
-	b	exc_data_storage_book3e
-1:	TLB_MISS_EPILOG_ERROR
-	b	exc_instruction_storage_book3e
-
-
 /*
  * This is the guts of the second-level TLB miss handler for direct
  * misses. We are entered with:
@@ -893,201 +662,6 @@ virt_page_table_tlb_miss_whacko_fault:
 	TLB_MISS_EPILOG_ERROR
 	b	exc_data_storage_book3e
 
-
-/**************************************************************
- *                                                            *
- * TLB miss handling for Book3E with hw page table support    *
- *                                                            *
- **************************************************************/
-
-
-/* Data TLB miss */
-	START_EXCEPTION(data_tlb_miss_htw)
-	TLB_MISS_PROLOG
-
-	/* Now we handle the fault proper. We only save DEAR in normal
-	 * fault case since that's the only interesting values here.
-	 * We could probably also optimize by not saving SRR0/1 in the
-	 * linear mapping case but I'll leave that for later
-	 */
-	mfspr	r14,SPRN_ESR
-	mfspr	r16,SPRN_DEAR		/* get faulting address */
-	srdi	r11,r16,44		/* get region */
-	xoris	r11,r11,0xc
-	cmpldi	cr0,r11,0		/* linear mapping ? */
-	beq	tlb_load_linear		/* yes -> go to linear map load */
-	cmpldi	cr1,r11,1		/* vmalloc mapping ? */
-
-	/* We do the user/kernel test for the PID here along with the RW test
-	 */
-	srdi.	r11,r16,60		/* Check for user region */
-	ld	r15,PACAPGD(r13)	/* Load user pgdir */
-	beq	htw_tlb_miss
-
-	/* XXX replace the RMW cycles with immediate loads + writes */
-1:	mfspr	r10,SPRN_MAS1
-	rlwinm	r10,r10,0,16,1		/* Clear TID */
-	mtspr	SPRN_MAS1,r10
-	ld	r15,PACA_KERNELPGD(r13)	/* Load kernel pgdir */
-	beq+	cr1,htw_tlb_miss
-
-	/* We got a crappy address, just fault with whatever DEAR and ESR
-	 * are here
-	 */
-	TLB_MISS_EPILOG_ERROR
-	b	exc_data_storage_book3e
-
-/* Instruction TLB miss */
-	START_EXCEPTION(instruction_tlb_miss_htw)
-	TLB_MISS_PROLOG
-
-	/* If we take a recursive fault, the second level handler may need
-	 * to know whether we are handling a data or instruction fault in
-	 * order to get to the right store fault handler. We provide that
-	 * info by keeping a crazy value for ESR in r14
-	 */
-	li	r14,-1	/* store to exception frame is done later */
-
-	/* Now we handle the fault proper. We only save DEAR in the non
-	 * linear mapping case since we know the linear mapping case will
-	 * not re-enter. We could indeed optimize and also not save SRR0/1
-	 * in the linear mapping case but I'll leave that for later
-	 *
-	 * Faulting address is SRR0 which is already in r16
-	 */
-	srdi	r11,r16,44		/* get region */
-	xoris	r11,r11,0xc
-	cmpldi	cr0,r11,0		/* linear mapping ? */
-	beq	tlb_load_linear		/* yes -> go to linear map load */
-	cmpldi	cr1,r11,1		/* vmalloc mapping ? */
-
-	/* We do the user/kernel test for the PID here along with the RW test
-	 */
-	srdi.	r11,r16,60		/* Check for user region */
-	ld	r15,PACAPGD(r13)		/* Load user pgdir */
-	beq	htw_tlb_miss
-
-	/* XXX replace the RMW cycles with immediate loads + writes */
-1:	mfspr	r10,SPRN_MAS1
-	rlwinm	r10,r10,0,16,1			/* Clear TID */
-	mtspr	SPRN_MAS1,r10
-	ld	r15,PACA_KERNELPGD(r13)		/* Load kernel pgdir */
-	beq+	htw_tlb_miss
-
-	/* We got a crappy address, just fault */
-	TLB_MISS_EPILOG_ERROR
-	b	exc_instruction_storage_book3e
-
-
-/*
- * This is the guts of the second-level TLB miss handler for direct
- * misses. We are entered with:
- *
- * r16 = virtual page table faulting address
- * r15 = PGD pointer
- * r14 = ESR
- * r13 = PACA
- * r12 = TLB exception frame in PACA
- * r11 = crap (free to use)
- * r10 = crap (free to use)
- *
- * It can be re-entered by the linear mapping miss handler. However, to
- * avoid too much complication, it will save/restore things for us
- */
-htw_tlb_miss:
-#ifdef CONFIG_PPC_KUAP
-	mfspr	r10,SPRN_MAS1
-	rlwinm.	r10,r10,0,0x3fff0000
-	beq-	htw_tlb_miss_fault /* KUAP fault */
-#endif
-	/* Search if we already have a TLB entry for that virtual address, and
-	 * if we do, bail out.
-	 *
-	 * MAS1:IND should be already set based on MAS4
-	 */
-	PPC_TLBSRX_DOT(0,R16)
-	beq	htw_tlb_miss_done
-
-	/* Now, we need to walk the page tables. First check if we are in
-	 * range.
-	 */
-	rldicl.	r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
-	bne-	htw_tlb_miss_fault
-
-	/* Get the PGD pointer */
-	cmpldi	cr0,r15,0
-	beq-	htw_tlb_miss_fault
-
-	/* Get to PGD entry */
-	rldicl	r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3
-	clrrdi	r10,r11,3
-	ldx	r15,r10,r15
-	cmpdi	cr0,r15,0
-	bge	htw_tlb_miss_fault
-
-	/* Get to PUD entry */
-	rldicl	r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3
-	clrrdi	r10,r11,3
-	ldx	r15,r10,r15
-	cmpdi	cr0,r15,0
-	bge	htw_tlb_miss_fault
-
-	/* Get to PMD entry */
-	rldicl	r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3
-	clrrdi	r10,r11,3
-	ldx	r15,r10,r15
-	cmpdi	cr0,r15,0
-	bge	htw_tlb_miss_fault
-
-	/* Ok, we're all right, we can now create an indirect entry for
-	 * a 1M or 256M page.
-	 *
-	 * The last trick is now that because we use "half" pages for
-	 * the HTW (1M IND is 2K and 256M IND is 32K) we need to account
-	 * for an added LSB bit to the RPN. For 64K pages, there is no
-	 * problem as we already use 32K arrays (half PTE pages), but for
-	 * 4K page we need to extract a bit from the virtual address and
-	 * insert it into the "PA52" bit of the RPN.
-	 */
-	rlwimi	r15,r16,32-9,20,20
-	/* Now we build the MAS:
-	 *
-	 * MAS 0   :	Fully setup with defaults in MAS4 and TLBnCFG
-	 * MAS 1   :	Almost fully setup
-	 *               - PID already updated by caller if necessary
-	 *               - TSIZE for now is base ind page size always
-	 * MAS 2   :	Use defaults
-	 * MAS 3+7 :	Needs to be done
-	 */
-	ori	r10,r15,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT)
-
-	srdi	r16,r10,32
-	mtspr	SPRN_MAS3,r10
-	mtspr	SPRN_MAS7,r16
-
-	tlbwe
-
-htw_tlb_miss_done:
-	/* We don't bother with restoring DEAR or ESR since we know we are
-	 * level 0 and just going back to userland. They are only needed
-	 * if you are going to take an access fault
-	 */
-	TLB_MISS_EPILOG_SUCCESS
-	rfi
-
-htw_tlb_miss_fault:
-	/* We need to check if it was an instruction miss. We know this
-	 * though because r14 would contain -1
-	 */
-	cmpdi	cr0,r14,-1
-	beq	1f
-	mtspr	SPRN_DEAR,r16
-	mtspr	SPRN_ESR,r14
-	TLB_MISS_EPILOG_ERROR
-	b	exc_data_storage_book3e
-1:	TLB_MISS_EPILOG_ERROR
-	b	exc_instruction_storage_book3e
-
 /*
  * This is the guts of "any" level TLB miss handler for kernel linear
  * mapping misses. We are entered with:
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 9f73d089eac1..603a0f652ba6 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -34,6 +34,7 @@
 #include <asm/hvcall.h>
 #include <asm/setup.h>
 #include <asm/vdso.h>
+#include <asm/vphn.h>
 #include <asm/drmem.h>
 
 static int numa_enabled = 1;
@@ -42,11 +43,9 @@ static char *cmdline __initdata;
 
 int numa_cpu_lookup_table[NR_CPUS];
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
-struct pglist_data *node_data[MAX_NUMNODES];
 
 EXPORT_SYMBOL(numa_cpu_lookup_table);
 EXPORT_SYMBOL(node_to_cpumask_map);
-EXPORT_SYMBOL(node_data);
 
 static int primary_domain_index;
 static int n_mem_addr_cells, n_mem_size_cells;
@@ -895,7 +894,7 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
 
 static int __init parse_numa_properties(void)
 {
-	struct device_node *memory;
+	struct device_node *memory, *pci;
 	int default_nid = 0;
 	unsigned long i;
 	const __be32 *associativity;
@@ -1009,6 +1008,18 @@ new_range:
 			goto new_range;
 	}
 
+	for_each_node_by_name(pci, "pci") {
+		int nid = NUMA_NO_NODE;
+
+		associativity = of_get_associativity(pci);
+		if (associativity) {
+			nid = associativity_to_nid(associativity);
+			initialize_form1_numa_distance(associativity);
+		}
+		if (likely(nid >= 0) && !node_online(nid))
+			node_set_online(nid);
+	}
+
 	/*
 	 * Now do the same thing for each MEMBLOCK listed in the
 	 * ibm,dynamic-memory property in the
@@ -1082,27 +1093,9 @@ void __init dump_numa_cpu_topology(void)
 static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 {
 	u64 spanned_pages = end_pfn - start_pfn;
-	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
-	u64 nd_pa;
-	void *nd;
-	int tnid;
-
-	nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
-	if (!nd_pa)
-		panic("Cannot allocate %zu bytes for node %d data\n",
-		      nd_size, nid);
-
-	nd = __va(nd_pa);
-
-	/* report and initialize */
-	pr_info("  NODE_DATA [mem %#010Lx-%#010Lx]\n",
-		nd_pa, nd_pa + nd_size - 1);
-	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
-	if (tnid != nid)
-		pr_info("    NODE_DATA(%d) on node %d\n", nid, tnid);
-
-	node_data[nid] = nd;
-	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+
+	alloc_node_data(nid);
+
 	NODE_DATA(nid)->node_id = nid;
 	NODE_DATA(nid)->node_start_pfn = start_pfn;
 	NODE_DATA(nid)->node_spanned_pages = spanned_pages;
@@ -1110,7 +1103,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 
 static void __init find_possible_nodes(void)
 {
-	struct device_node *rtas;
+	struct device_node *rtas, *root;
 	const __be32 *domains = NULL;
 	int prop_length, max_nodes;
 	u32 i;
@@ -1131,10 +1124,12 @@ static void __init find_possible_nodes(void)
 	 * If the LPAR is migratable, new nodes might be activated after a LPM,
 	 * so we should consider the max number in that case.
 	 */
-	if (!of_get_property(of_root, "ibm,migratable-partition", NULL))
+	root = of_find_node_by_path("/");
+	if (!of_get_property(root, "ibm,migratable-partition", NULL))
 		domains = of_get_property(rtas,
 					  "ibm,current-associativity-domains",
 					  &prop_length);
+	of_node_put(root);
 	if (!domains) {
 		domains = of_get_property(rtas, "ibm,max-associativity-domains",
 					&prop_length);
@@ -1341,7 +1336,7 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 	return nid;
 }
 
-static u64 hot_add_drconf_memory_max(void)
+u64 hot_add_drconf_memory_max(void)
 {
 	struct device_node *memory = NULL;
 	struct device_node *dn = NULL;
diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
index 6163e484bc6d..ac22bf28086f 100644
--- a/arch/powerpc/mm/pageattr.c
+++ b/arch/powerpc/mm/pageattr.c
@@ -14,6 +14,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
+#include <mm/mmu_decl.h>
 
 static pte_basic_t pte_update_delta(pte_t *ptep, unsigned long addr,
 				    unsigned long old, unsigned long new)
@@ -38,6 +39,10 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
 		/* Don't clear DIRTY bit */
 		pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_RO);
 		break;
+	case SET_MEMORY_ROX:
+		/* Don't clear DIRTY bit */
+		pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_ROX);
+		break;
 	case SET_MEMORY_RW:
 		pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_RW);
 		break;
@@ -97,3 +102,26 @@ int change_memory_attr(unsigned long addr, int numpages, long action)
 	return apply_to_existing_page_range(&init_mm, start, size,
 					    change_page_attr, (void *)action);
 }
+
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
+#ifdef CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	int err;
+	unsigned long addr = (unsigned long)page_address(page);
+
+	if (PageHighMem(page))
+		return;
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled())
+		err = hash__kernel_map_pages(page, numpages, enable);
+	else if (enable)
+		err = set_memory_p(addr, numpages);
+	else
+		err = set_memory_np(addr, numpages);
+
+	if (err)
+		panic("%s: changing memory protections failed\n", __func__);
+}
+#endif
+#endif
diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c
index 20652daa1d7e..77e55eac16e4 100644
--- a/arch/powerpc/mm/pgtable-frag.c
+++ b/arch/powerpc/mm/pgtable-frag.c
@@ -18,15 +18,15 @@
 void pte_frag_destroy(void *pte_frag)
 {
 	int count;
-	struct page *page;
+	struct ptdesc *ptdesc;
 
-	page = virt_to_page(pte_frag);
+	ptdesc = virt_to_ptdesc(pte_frag);
 	/* drop all the pending references */
 	count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT;
 	/* We allow PTE_FRAG_NR fragments from a PTE page */
-	if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) {
-		pgtable_pte_page_dtor(page);
-		__free_page(page);
+	if (atomic_sub_and_test(PTE_FRAG_NR - count, &ptdesc->pt_frag_refcount)) {
+		pagetable_dtor(ptdesc);
+		pagetable_free(ptdesc);
 	}
 }
 
@@ -55,25 +55,23 @@ static pte_t *get_pte_from_cache(struct mm_struct *mm)
 static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel)
 {
 	void *ret = NULL;
-	struct page *page;
-
-	if (!kernel) {
-		page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT);
-		if (!page)
-			return NULL;
-		if (!pgtable_pte_page_ctor(page)) {
-			__free_page(page);
-			return NULL;
-		}
-	} else {
-		page = alloc_page(PGALLOC_GFP);
-		if (!page)
-			return NULL;
+	struct ptdesc *ptdesc;
+	gfp_t gfp = PGALLOC_GFP;
+
+	if (!kernel)
+		gfp |= __GFP_ACCOUNT;
+
+	ptdesc = pagetable_alloc(gfp, 0);
+	if (!ptdesc)
+		return NULL;
+	if (!pagetable_pte_ctor(mm, ptdesc)) {
+		pagetable_free(ptdesc);
+		return NULL;
 	}
 
-	atomic_set(&page->pt_frag_refcount, 1);
+	atomic_set(&ptdesc->pt_frag_refcount, 1);
 
-	ret = page_address(page);
+	ret = ptdesc_address(ptdesc);
 	/*
 	 * if we support only one fragment just return the
 	 * allocated page.
@@ -82,12 +80,12 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel)
 		return ret;
 	spin_lock(&mm->page_table_lock);
 	/*
-	 * If we find pgtable_page set, we return
+	 * If we find ptdesc_page set, we return
 	 * the allocated page with single fragment
 	 * count.
 	 */
 	if (likely(!pte_frag_get(&mm->context))) {
-		atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR);
+		atomic_set(&ptdesc->pt_frag_refcount, PTE_FRAG_NR);
 		pte_frag_set(&mm->context, ret + PTE_FRAG_SIZE);
 	}
 	spin_unlock(&mm->page_table_lock);
@@ -106,17 +104,38 @@ pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel)
 	return __alloc_for_ptecache(mm, kernel);
 }
 
+static void pte_free_now(struct rcu_head *head)
+{
+	struct ptdesc *ptdesc;
+
+	ptdesc = container_of(head, struct ptdesc, pt_rcu_head);
+	pagetable_dtor(ptdesc);
+	pagetable_free(ptdesc);
+}
+
 void pte_fragment_free(unsigned long *table, int kernel)
 {
-	struct page *page = virt_to_page(table);
+	struct ptdesc *ptdesc = virt_to_ptdesc(table);
 
-	if (PageReserved(page))
-		return free_reserved_page(page);
+	if (pagetable_is_reserved(ptdesc))
+		return free_reserved_ptdesc(ptdesc);
 
-	BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0);
-	if (atomic_dec_and_test(&page->pt_frag_refcount)) {
-		if (!kernel)
-			pgtable_pte_page_dtor(page);
-		__free_page(page);
+	BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0);
+	if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) {
+		if (kernel || !folio_test_clear_active(ptdesc_folio(ptdesc)))
+			pte_free_now(&ptdesc->pt_rcu_head);
+		else
+			call_rcu(&ptdesc->pt_rcu_head, pte_free_now);
 	}
 }
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
+{
+	struct folio *folio;
+
+	folio = virt_to_folio(pgtable);
+	folio_set_active(folio);
+	pte_fragment_free((unsigned long *)pgtable, 0);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index cb2dcdb18f8e..56d7e8960e77 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -46,19 +46,19 @@ static inline int is_exec_fault(void)
  * and we avoid _PAGE_SPECIAL and cache inhibited pte. We also only do that
  * on userspace PTEs
  */
-static inline int pte_looks_normal(pte_t pte)
+static inline int pte_looks_normal(pte_t pte, unsigned long addr)
 {
 
 	if (pte_present(pte) && !pte_special(pte)) {
 		if (pte_ci(pte))
 			return 0;
-		if (pte_user(pte))
+		if (!is_kernel_addr(addr))
 			return 1;
 	}
 	return 0;
 }
 
-static struct page *maybe_pte_to_page(pte_t pte)
+static struct folio *maybe_pte_to_folio(pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
 	struct page *page;
@@ -68,7 +68,7 @@ static struct page *maybe_pte_to_page(pte_t pte)
 	page = pfn_to_page(pfn);
 	if (PageReserved(page))
 		return NULL;
-	return page;
+	return page_folio(page);
 }
 
 #ifdef CONFIG_PPC_BOOK3S
@@ -79,17 +79,17 @@ static struct page *maybe_pte_to_page(pte_t pte)
  * support falls into the same category.
  */
 
-static pte_t set_pte_filter_hash(pte_t pte)
+static pte_t set_pte_filter_hash(pte_t pte, unsigned long addr)
 {
 	pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
-	if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
-				       cpu_has_feature(CPU_FTR_NOEXECUTE))) {
-		struct page *pg = maybe_pte_to_page(pte);
-		if (!pg)
+	if (pte_looks_normal(pte, addr) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
+					     cpu_has_feature(CPU_FTR_NOEXECUTE))) {
+		struct folio *folio = maybe_pte_to_folio(pte);
+		if (!folio)
 			return pte;
-		if (!test_bit(PG_dcache_clean, &pg->flags)) {
-			flush_dcache_icache_page(pg);
-			set_bit(PG_dcache_clean, &pg->flags);
+		if (!test_bit(PG_dcache_clean, &folio->flags.f)) {
+			flush_dcache_icache_folio(folio);
+			set_bit(PG_dcache_clean, &folio->flags.f);
 		}
 	}
 	return pte;
@@ -97,41 +97,43 @@ static pte_t set_pte_filter_hash(pte_t pte)
 
 #else /* CONFIG_PPC_BOOK3S */
 
-static pte_t set_pte_filter_hash(pte_t pte) { return pte; }
+static pte_t set_pte_filter_hash(pte_t pte, unsigned long addr) { return pte; }
 
 #endif /* CONFIG_PPC_BOOK3S */
 
 /* Embedded type MMU with HW exec support. This is a bit more complicated
  * as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so
  * instead we "filter out" the exec permission for non clean pages.
+ *
+ * This is also called once for the folio. So only work with folio->flags here.
  */
-static inline pte_t set_pte_filter(pte_t pte)
+static inline pte_t set_pte_filter(pte_t pte, unsigned long addr)
 {
-	struct page *pg;
+	struct folio *folio;
 
 	if (radix_enabled())
 		return pte;
 
 	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
-		return set_pte_filter_hash(pte);
+		return set_pte_filter_hash(pte, addr);
 
 	/* No exec permission in the first place, move on */
-	if (!pte_exec(pte) || !pte_looks_normal(pte))
+	if (!pte_exec(pte) || !pte_looks_normal(pte, addr))
 		return pte;
 
 	/* If you set _PAGE_EXEC on weird pages you're on your own */
-	pg = maybe_pte_to_page(pte);
-	if (unlikely(!pg))
+	folio = maybe_pte_to_folio(pte);
+	if (unlikely(!folio))
 		return pte;
 
 	/* If the page clean, we move on */
-	if (test_bit(PG_dcache_clean, &pg->flags))
+	if (test_bit(PG_dcache_clean, &folio->flags.f))
 		return pte;
 
 	/* If it's an exec fault, we flush the cache and make it clean */
 	if (is_exec_fault()) {
-		flush_dcache_icache_page(pg);
-		set_bit(PG_dcache_clean, &pg->flags);
+		flush_dcache_icache_folio(folio);
+		set_bit(PG_dcache_clean, &folio->flags.f);
 		return pte;
 	}
 
@@ -142,7 +144,7 @@ static inline pte_t set_pte_filter(pte_t pte)
 static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
 				     int dirty)
 {
-	struct page *pg;
+	struct folio *folio;
 
 	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
 		return pte;
@@ -168,17 +170,17 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
 #endif /* CONFIG_DEBUG_VM */
 
 	/* If you set _PAGE_EXEC on weird pages you're on your own */
-	pg = maybe_pte_to_page(pte);
-	if (unlikely(!pg))
+	folio = maybe_pte_to_folio(pte);
+	if (unlikely(!folio))
 		goto bail;
 
 	/* If the page is already clean, we move on */
-	if (test_bit(PG_dcache_clean, &pg->flags))
+	if (test_bit(PG_dcache_clean, &folio->flags.f))
 		goto bail;
 
 	/* Clean the page and set PG_dcache_clean */
-	flush_dcache_icache_page(pg);
-	set_bit(PG_dcache_clean, &pg->flags);
+	flush_dcache_icache_folio(folio);
+	set_bit(PG_dcache_clean, &folio->flags.f);
 
  bail:
 	return pte_mkexec(pte);
@@ -187,23 +189,39 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
 /*
  * set_pte stores a linux PTE into the linux page table.
  */
-void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
-		pte_t pte)
+void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		pte_t pte, unsigned int nr)
 {
-	/*
-	 * Make sure hardware valid bit is not set. We don't do
-	 * tlb flush for this update.
-	 */
-	VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
 
 	/* Note: mm->context.id might not yet have been assigned as
 	 * this context might not have been activated yet when this
-	 * is called.
+	 * is called. Filter the pte value and use the filtered value
+	 * to setup all the ptes in the range.
 	 */
-	pte = set_pte_filter(pte);
+	pte = set_pte_filter(pte, addr);
 
-	/* Perform the setting of the PTE */
-	__set_pte_at(mm, addr, ptep, pte, 0);
+	/*
+	 * We don't need to call arch_enter/leave_lazy_mmu_mode()
+	 * because we expect set_ptes to be only be used on not present
+	 * and not hw_valid ptes. Hence there is no translation cache flush
+	 * involved that need to be batched.
+	 */
+	for (;;) {
+
+		/*
+		 * Make sure hardware valid bit is not set. We don't do
+		 * tlb flush for this update.
+		 */
+		VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
+
+		/* Perform the setting of the PTE */
+		__set_pte_at(mm, addr, ptep, pte, 0);
+		if (--nr == 0)
+			break;
+		ptep++;
+		addr += PAGE_SIZE;
+		pte = pte_next_pfn(pte);
+	}
 }
 
 void unmap_kernel_page(unsigned long va)
@@ -279,10 +297,14 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 }
 
 #if defined(CONFIG_PPC_8xx)
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+
+#if defined(CONFIG_SPLIT_PTE_PTLOCKS) || defined(CONFIG_SPLIT_PMD_PTLOCKS)
+/* We need the same lock to protect the PMD table and the two PTE tables. */
+#error "8M hugetlb folios are incompatible with split page table locks"
+#endif
+
+static void __set_huge_pte_at(pmd_t *pmd, pte_t *ptep, pte_basic_t val)
 {
-	pmd_t *pmd = pmd_off(mm, addr);
-	pte_basic_t val;
 	pte_basic_t *entry = (pte_basic_t *)ptep;
 	int num, i;
 
@@ -292,15 +314,60 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_
 	 */
 	VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
 
-	pte = set_pte_filter(pte);
-
-	val = pte_val(pte);
-
 	num = number_of_cells_per_pte(pmd, val, 1);
 
 	for (i = 0; i < num; i++, entry++, val += SZ_4K)
 		*entry = val;
 }
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz)
+{
+	pmd_t *pmdp = pmd_off(mm, addr);
+
+	pte = set_pte_filter(pte, addr);
+
+	if (sz == SZ_8M) { /* Flag both PMD entries as 8M and fill both page tables */
+		*pmdp = __pmd(pmd_val(*pmdp) | _PMD_PAGE_8M);
+		*(pmdp + 1) = __pmd(pmd_val(*(pmdp + 1)) | _PMD_PAGE_8M);
+
+		__set_huge_pte_at(pmdp, pte_offset_kernel(pmdp, 0), pte_val(pte));
+		__set_huge_pte_at(pmdp, pte_offset_kernel(pmdp + 1, 0), pte_val(pte) + SZ_4M);
+	} else {
+		__set_huge_pte_at(pmdp, ptep, pte_val(pte));
+	}
+}
+#else
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz)
+{
+	unsigned long pdsize;
+	int i;
+
+	pte = set_pte_filter(pte, addr);
+
+	/*
+	 * Make sure hardware valid bit is not set. We don't do
+	 * tlb flush for this update.
+	 */
+	VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
+
+	if (sz < PMD_SIZE)
+		pdsize = PAGE_SIZE;
+	else if (sz < PUD_SIZE)
+		pdsize = PMD_SIZE;
+	else if (sz < P4D_SIZE)
+		pdsize = PUD_SIZE;
+	else if (sz < PGDIR_SIZE)
+		pdsize = P4D_SIZE;
+	else
+		pdsize = PGDIR_SIZE;
+
+	for (i = 0; i < sz / pdsize; i++, ptep++, addr += pdsize) {
+		__set_pte_at(mm, addr, ptep, pte, 0);
+		pte = __pte(pte_val(pte) + ((unsigned long long)pdsize / PAGE_SIZE << PFN_PTE_SHIFT));
+	}
+}
 #endif
 #endif /* CONFIG_HUGETLB_PAGE */
 
@@ -311,6 +378,8 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
+	pte_t *pte;
+	spinlock_t *ptl;
 
 	if (mm == &init_mm)
 		return;
@@ -329,8 +398,10 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 	 */
 	if (pmd_none(*pmd))
 		return;
-	BUG_ON(!pmd_present(*pmd));
-	assert_spin_locked(pte_lockptr(mm, pmd));
+	pte = pte_offset_map_ro_nolock(mm, pmd, addr, &ptl);
+	BUG_ON(!pte);
+	assert_spin_locked(ptl);
+	pte_unmap(pte);
 }
 #endif /* CONFIG_DEBUG_VM */
 
@@ -344,11 +415,10 @@ unsigned long vmalloc_to_phys(void *va)
 EXPORT_SYMBOL_GPL(vmalloc_to_phys);
 
 /*
- * We have 4 cases for pgds and pmds:
+ * We have 3 cases for pgds and pmds:
  * (1) invalid (all zeroes)
  * (2) pointer to next table, as normal; bottom 6 bits == 0
  * (3) leaf pte for huge page _PAGE_PTE set
- * (4) hugepd pointer, _PAGE_PTE = 0 and bits [2..6] indicate size of table
  *
  * So long as we atomically load page table pointers we are safe against teardown,
  * we can follow the address down to the page and take a ref on it.
@@ -359,11 +429,12 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 			bool *is_thp, unsigned *hpage_shift)
 {
 	pgd_t *pgdp;
+#ifdef CONFIG_PPC64
 	p4d_t p4d, *p4dp;
 	pud_t pud, *pudp;
+#endif
 	pmd_t pmd, *pmdp;
 	pte_t *ret_pte;
-	hugepd_t *hpdp = NULL;
 	unsigned pdshift;
 
 	if (hpage_shift)
@@ -378,8 +449,12 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 	 * page fault or a page unmap. The return pte_t * is still not
 	 * stable. So should be checked there for above conditions.
 	 * Top level is an exception because it is folded into p4d.
+	 *
+	 * On PPC32, P4D/PUD/PMD are folded into PGD so go straight to
+	 * PMD level.
 	 */
 	pgdp = pgdir + pgd_index(ea);
+#ifdef CONFIG_PPC64
 	p4dp = p4d_offset(pgdp, ea);
 	p4d  = READ_ONCE(*p4dp);
 	pdshift = P4D_SHIFT;
@@ -387,16 +462,11 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 	if (p4d_none(p4d))
 		return NULL;
 
-	if (p4d_is_leaf(p4d)) {
+	if (p4d_leaf(p4d)) {
 		ret_pte = (pte_t *)p4dp;
 		goto out;
 	}
 
-	if (is_hugepd(__hugepd(p4d_val(p4d)))) {
-		hpdp = (hugepd_t *)&p4d;
-		goto out_huge;
-	}
-
 	/*
 	 * Even if we end up with an unmap, the pgtable will not
 	 * be freed, because we do an rcu free and here we are
@@ -409,18 +479,16 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 	if (pud_none(pud))
 		return NULL;
 
-	if (pud_is_leaf(pud)) {
+	if (pud_leaf(pud)) {
 		ret_pte = (pte_t *)pudp;
 		goto out;
 	}
 
-	if (is_hugepd(__hugepd(pud_val(pud)))) {
-		hpdp = (hugepd_t *)&pud;
-		goto out_huge;
-	}
-
-	pdshift = PMD_SHIFT;
 	pmdp = pmd_offset(&pud, ea);
+#else
+	pmdp = pmd_offset(pud_offset(p4d_offset(pgdp, ea), ea), ea);
+#endif
+	pdshift = PMD_SHIFT;
 	pmd  = READ_ONCE(*pmdp);
 
 	/*
@@ -441,31 +509,20 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 		return NULL;
 #endif
 
-	if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
+	if (pmd_trans_huge(pmd)) {
 		if (is_thp)
 			*is_thp = true;
 		ret_pte = (pte_t *)pmdp;
 		goto out;
 	}
 
-	if (pmd_is_leaf(pmd)) {
+	if (pmd_leaf(pmd)) {
 		ret_pte = (pte_t *)pmdp;
 		goto out;
 	}
 
-	if (is_hugepd(__hugepd(pmd_val(pmd)))) {
-		hpdp = (hugepd_t *)&pmd;
-		goto out_huge;
-	}
-
 	return pte_offset_kernel(&pmd, ea);
 
-out_huge:
-	if (!hpdp)
-		return NULL;
-
-	ret_pte = hugepte_offset(*hpdp, ea, pdshift);
-	pdshift = hugepd_shift(*hpdp);
 out:
 	if (hpage_shift)
 		*hpage_shift = pdshift;
@@ -479,7 +536,7 @@ const pgprot_t protection_map[16] = {
 	[VM_READ]					= PAGE_READONLY,
 	[VM_WRITE]					= PAGE_COPY,
 	[VM_WRITE | VM_READ]				= PAGE_COPY,
-	[VM_EXEC]					= PAGE_READONLY_X,
+	[VM_EXEC]					= PAGE_EXECONLY_X,
 	[VM_EXEC | VM_READ]				= PAGE_READONLY_X,
 	[VM_EXEC | VM_WRITE]				= PAGE_COPY_X,
 	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY_X,
@@ -487,7 +544,7 @@ const pgprot_t protection_map[16] = {
 	[VM_SHARED | VM_READ]				= PAGE_READONLY,
 	[VM_SHARED | VM_WRITE]				= PAGE_SHARED,
 	[VM_SHARED | VM_WRITE | VM_READ]		= PAGE_SHARED,
-	[VM_SHARED | VM_EXEC]				= PAGE_READONLY_X,
+	[VM_SHARED | VM_EXEC]				= PAGE_EXECONLY_X,
 	[VM_SHARED | VM_EXEC | VM_READ]			= PAGE_READONLY_X,
 	[VM_SHARED | VM_EXEC | VM_WRITE]		= PAGE_SHARED_X,
 	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED_X
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 5c02fd08d61e..0c9ef705803e 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -48,15 +48,10 @@ notrace void __init early_ioremap_init(void)
 	early_ioremap_setup();
 }
 
-static void __init *early_alloc_pgtable(unsigned long size)
+void __init *early_alloc_pgtable(unsigned long size)
 {
-	void *ptr = memblock_alloc(size, size);
+	return memblock_alloc_or_panic(size, size);
 
-	if (!ptr)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, size, size);
-
-	return ptr;
 }
 
 pte_t __init *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va)
@@ -109,7 +104,7 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
 	p = memstart_addr + s;
 	for (; s < top; s += PAGE_SIZE) {
 		ktext = core_kernel_text(v);
-		map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL);
+		map_kernel_page(v, p, ktext ? PAGE_KERNEL_X : PAGE_KERNEL);
 		v += PAGE_SIZE;
 		p += PAGE_SIZE;
 	}
@@ -130,32 +125,41 @@ void __init mapin_ram(void)
 	}
 }
 
-void mark_initmem_nx(void)
+static int __mark_initmem_nx(void)
 {
 	unsigned long numpages = PFN_UP((unsigned long)_einittext) -
 				 PFN_DOWN((unsigned long)_sinittext);
+	int err;
 
-	mmu_mark_initmem_nx();
+	err = mmu_mark_initmem_nx();
 
 	if (!v_block_mapped((unsigned long)_sinittext)) {
-		set_memory_nx((unsigned long)_sinittext, numpages);
-		set_memory_rw((unsigned long)_sinittext, numpages);
+		err = set_memory_nx((unsigned long)_sinittext, numpages);
+		if (err)
+			return err;
+		err = set_memory_rw((unsigned long)_sinittext, numpages);
 	}
+	return err;
+}
+
+void mark_initmem_nx(void)
+{
+	int err = __mark_initmem_nx();
+
+	if (err)
+		panic("%s() failed, err = %d\n", __func__, err);
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
-void mark_rodata_ro(void)
+static int __mark_rodata_ro(void)
 {
 	unsigned long numpages;
 
 	if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX) && mmu_has_feature(MMU_FTR_HPTE_TABLE))
 		pr_warn("This platform has HASH MMU, STRICT_MODULE_RWX won't work\n");
 
-	if (v_block_mapped((unsigned long)_stext + 1)) {
-		mmu_mark_rodata_ro();
-		ptdump_check_wx();
-		return;
-	}
+	if (v_block_mapped((unsigned long)_stext + 1))
+		return mmu_mark_rodata_ro();
 
 	/*
 	 * mark text and rodata as read only. __end_rodata is set by
@@ -165,24 +169,14 @@ void mark_rodata_ro(void)
 	numpages = PFN_UP((unsigned long)__end_rodata) -
 		   PFN_DOWN((unsigned long)_stext);
 
-	set_memory_ro((unsigned long)_stext, numpages);
-
-	// mark_initmem_nx() should have already run by now
-	ptdump_check_wx();
+	return set_memory_ro((unsigned long)_stext, numpages);
 }
-#endif
 
-#if defined(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && defined(CONFIG_DEBUG_PAGEALLOC)
-void __kernel_map_pages(struct page *page, int numpages, int enable)
+void mark_rodata_ro(void)
 {
-	unsigned long addr = (unsigned long)page_address(page);
-
-	if (PageHighMem(page))
-		return;
+	int err = __mark_rodata_ro();
 
-	if (enable)
-		set_memory_p(addr, numpages);
-	else
-		set_memory_np(addr, numpages);
+	if (err)
+		panic("%s() failed, err = %d\n", __func__, err);
 }
-#endif /* CONFIG_DEBUG_PAGEALLOC */
+#endif
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 5ac1fd30341b..6621cfc3baf8 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -100,9 +100,9 @@ EXPORT_SYMBOL(__pte_frag_size_shift);
 /* 4 level page table */
 struct page *p4d_page(p4d_t p4d)
 {
-	if (p4d_is_leaf(p4d)) {
+	if (p4d_leaf(p4d)) {
 		if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
-			VM_WARN_ON(!p4d_huge(p4d));
+			VM_WARN_ON(!p4d_leaf(p4d));
 		return pte_page(p4d_pte(p4d));
 	}
 	return virt_to_page(p4d_pgtable(p4d));
@@ -111,9 +111,9 @@ struct page *p4d_page(p4d_t p4d)
 
 struct page *pud_page(pud_t pud)
 {
-	if (pud_is_leaf(pud)) {
+	if (pud_leaf(pud)) {
 		if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
-			VM_WARN_ON(!pud_huge(pud));
+			VM_WARN_ON(!pud_leaf(pud));
 		return pte_page(pud_pte(pud));
 	}
 	return virt_to_page(pud_pgtable(pud));
@@ -125,14 +125,14 @@ struct page *pud_page(pud_t pud)
  */
 struct page *pmd_page(pmd_t pmd)
 {
-	if (pmd_is_leaf(pmd)) {
+	if (pmd_leaf(pmd)) {
 		/*
 		 * vmalloc_to_page may be called on any vmap address (not only
 		 * vmalloc), and it uses pmd_page() etc., when huge vmap is
 		 * enabled so these checks can't be used.
 		 */
 		if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
-			VM_WARN_ON(!(pmd_large(pmd) || pmd_huge(pmd)));
+			VM_WARN_ON(!pmd_leaf(pmd));
 		return pte_page(pmd_pte(pmd));
 	}
 	return virt_to_page(pmd_page_vaddr(pmd));
@@ -150,9 +150,6 @@ void mark_rodata_ro(void)
 		radix__mark_rodata_ro();
 	else
 		hash__mark_rodata_ro();
-
-	// mark_initmem_nx() should have already run by now
-	ptdump_check_wx();
 }
 
 void mark_initmem_nx(void)
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c
index fac932eb8f9a..ff845f251724 100644
--- a/arch/powerpc/mm/ptdump/8xx.c
+++ b/arch/powerpc/mm/ptdump/8xx.c
@@ -21,11 +21,6 @@ static const struct flag_info flag_array[] = {
 		.set	= "huge",
 		.clear	= "    ",
 	}, {
-		.mask	= _PAGE_SH,
-		.val	= 0,
-		.set	= "user",
-		.clear	= "    ",
-	}, {
 		.mask	= _PAGE_RO | _PAGE_NA,
 		.val	= 0,
 		.set	= "rw",
@@ -74,20 +69,25 @@ static const struct flag_info flag_array[] = {
 	}
 };
 
-struct pgtable_level pg_level[5] = {
+struct ptdump_pg_level pg_level[5] = {
 	{ /* pgd */
+		.name	= "PGD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* p4d */
+		.name	= "P4D",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
+		.name	= "PUD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pmd */
+		.name	= "PMD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pte */
+		.name	= "PTE",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	},
diff --git a/arch/powerpc/mm/ptdump/Makefile b/arch/powerpc/mm/ptdump/Makefile
index dc896d2874f3..0f7a050f327e 100644
--- a/arch/powerpc/mm/ptdump/Makefile
+++ b/arch/powerpc/mm/ptdump/Makefile
@@ -2,7 +2,7 @@
 
 obj-y	+= ptdump.o
 
-obj-$(CONFIG_4xx)		+= shared.o
+obj-$(CONFIG_44x)		+= shared.o
 obj-$(CONFIG_PPC_8xx)		+= 8xx.o
 obj-$(CONFIG_PPC_E500)		+= shared.o
 obj-$(CONFIG_PPC_BOOK3S_32)	+= shared.o
diff --git a/arch/powerpc/mm/ptdump/book3s64.c b/arch/powerpc/mm/ptdump/book3s64.c
index 5ad92d9dc5d1..e8a21c6dc32e 100644
--- a/arch/powerpc/mm/ptdump/book3s64.c
+++ b/arch/powerpc/mm/ptdump/book3s64.c
@@ -102,20 +102,25 @@ static const struct flag_info flag_array[] = {
 	}
 };
 
-struct pgtable_level pg_level[5] = {
+struct ptdump_pg_level pg_level[5] = {
 	{ /* pgd */
+		.name	= "PGD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* p4d */
+		.name	= "P4D",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
+		.name	= "PUD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pmd */
+		.name	= "PMD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pte */
+		.name	= "PTE",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	},
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index 9a601587836b..671d0dc00c6d 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -216,6 +216,8 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64
 	vpn  = hpt_vpn(ea, vsid, ssize);
 	hash = hpt_hash(vpn, shift, ssize);
 	want_v = hpte_encode_avpn(vpn, psize, ssize);
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		want_v = hpte_old_to_new_v(want_v);
 
 	/* to check in the secondary hash table, we invert the hash */
 	if (!primary)
@@ -229,6 +231,10 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64
 			/* HPTE matches */
 			*v = be64_to_cpu(hptep->v);
 			*r = be64_to_cpu(hptep->r);
+			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+				*v = hpte_new_to_old_v(*v, *r);
+				*r = hpte_new_to_old_r(*r);
+			}
 			return 0;
 		}
 		++hpte_group;
@@ -491,7 +497,7 @@ static void walk_vmemmap(struct pg_state *st)
 	 * Traverse the vmemmaped memory and dump pages that are in the hash
 	 * pagetable.
 	 */
-	while (ptr->list) {
+	while (ptr) {
 		hpte_find(st, ptr->virt_addr, mmu_vmemmap_psize);
 		ptr = ptr->list;
 	}
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 2313053fe679..0d499aebee72 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -178,19 +178,21 @@ static void dump_addr(struct pg_state *st, unsigned long addr)
 	pt_dump_seq_printf(st->seq, REG "-" REG " ", st->start_address, addr - 1);
 	pt_dump_seq_printf(st->seq, " " REG " ", st->start_pa);
 	pt_dump_size(st->seq, addr - st->start_address);
+	pt_dump_seq_printf(st->seq, "%s ", pg_level[st->level].name);
 }
 
 static void note_prot_wx(struct pg_state *st, unsigned long addr)
 {
 	pte_t pte = __pte(st->current_flags);
 
-	if (!IS_ENABLED(CONFIG_DEBUG_WX) || !st->check_wx)
+	if (!st->check_wx)
 		return;
 
 	if (!pte_write(pte) || !pte_exec(pte))
 		return;
 
-	WARN_ONCE(1, "powerpc/mm: Found insecure W+X mapping at address %p/%pS\n",
+	WARN_ONCE(IS_ENABLED(CONFIG_DEBUG_WX),
+		  "powerpc/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;
@@ -297,6 +299,38 @@ static void populate_markers(void)
 #endif
 }
 
+static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte)
+{
+	note_page(pt_st, addr, 4, pte_val(pte));
+}
+
+static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd)
+{
+	note_page(pt_st, addr, 3, pmd_val(pmd));
+}
+
+static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud)
+{
+	note_page(pt_st, addr, 2, pud_val(pud));
+}
+
+static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d)
+{
+	note_page(pt_st, addr, 1, p4d_val(p4d));
+}
+
+static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd)
+{
+	note_page(pt_st, addr, 0, pgd_val(pgd));
+}
+
+static void note_page_flush(struct ptdump_state *pt_st)
+{
+	pte_t pte_zero = {0};
+
+	note_page(pt_st, 0, -1, pte_val(pte_zero));
+}
+
 static int ptdump_show(struct seq_file *m, void *v)
 {
 	struct pg_state st = {
@@ -304,7 +338,12 @@ static int ptdump_show(struct seq_file *m, void *v)
 		.marker = address_markers,
 		.level = -1,
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = ptdump_range,
 		}
 	};
@@ -326,8 +365,7 @@ static void __init build_pgtable_complete_mask(void)
 				pg_level[i].mask |= pg_level[i].flag[j].mask;
 }
 
-#ifdef CONFIG_DEBUG_WX
-void ptdump_check_wx(void)
+bool ptdump_check_wx(void)
 {
 	struct pg_state st = {
 		.seq = NULL,
@@ -338,20 +376,32 @@ void ptdump_check_wx(void)
 		.level = -1,
 		.check_wx = true,
 		.ptdump = {
-			.note_page = note_page,
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
 			.range = ptdump_range,
 		}
 	};
 
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !mmu_has_feature(MMU_FTR_KERNEL_RO))
+		return true;
+
 	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
 
-	if (st.wx_pages)
+	if (st.wx_pages) {
 		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n",
 			st.wx_pages);
-	else
+
+		return false;
+	} else {
 		pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+
+		return true;
+	}
 }
-#endif
 
 static int __init ptdump_init(void)
 {
diff --git a/arch/powerpc/mm/ptdump/ptdump.h b/arch/powerpc/mm/ptdump/ptdump.h
index 154efae96ae0..12aa9eca8b0c 100644
--- a/arch/powerpc/mm/ptdump/ptdump.h
+++ b/arch/powerpc/mm/ptdump/ptdump.h
@@ -11,12 +11,13 @@ struct flag_info {
 	int		shift;
 };
 
-struct pgtable_level {
+struct ptdump_pg_level {
 	const struct flag_info *flag;
+	char name[4];
 	size_t num;
 	u64 mask;
 };
 
-extern struct pgtable_level pg_level[5];
+extern struct ptdump_pg_level pg_level[5];
 
 void pt_dump_size(struct seq_file *m, unsigned long delta);
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index f884760ca5cf..edc69da19b85 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -11,15 +11,15 @@
 
 static const struct flag_info flag_array[] = {
 	{
-		.mask	= _PAGE_USER,
-		.val	= _PAGE_USER,
-		.set	= "user",
-		.clear	= "    ",
+		.mask	= _PAGE_READ,
+		.val	= 0,
+		.set	= " ",
+		.clear	= "r",
 	}, {
-		.mask	= _PAGE_RW,
+		.mask	= _PAGE_WRITE,
 		.val	= 0,
-		.set	= "r ",
-		.clear	= "rw",
+		.set	= " ",
+		.clear	= "w",
 	}, {
 		.mask	= _PAGE_EXEC,
 		.val	= _PAGE_EXEC,
@@ -67,20 +67,25 @@ static const struct flag_info flag_array[] = {
 	}
 };
 
-struct pgtable_level pg_level[5] = {
+struct ptdump_pg_level pg_level[5] = {
 	{ /* pgd */
+		.name	= "PGD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* p4d */
+		.name	= "P4D",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
+		.name	= "PUD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pmd */
+		.name	= "PMD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pte */
+		.name	= "PTE",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	},
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 72b7bb34fade..8334cd667bba 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -8,10 +8,11 @@
 #ifndef _BPF_JIT_H
 #define _BPF_JIT_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/types.h>
 #include <asm/ppc-opcode.h>
+#include <linux/build_bug.h>
 
 #ifdef CONFIG_PPC64_ELF_ABI_V1
 #define FUNCTION_DESCR_SIZE	24
@@ -21,6 +22,9 @@
 
 #define CTX_NIA(ctx) ((unsigned long)ctx->idx * 4)
 
+#define SZL			sizeof(unsigned long)
+#define BPF_INSN_SAFETY		64
+
 #define PLANT_INSTR(d, idx, instr)					      \
 	do { if (d) { (d)[idx] = instr; } idx++; } while (0)
 #define EMIT(instr)		PLANT_INSTR(image, ctx->idx, instr)
@@ -36,9 +40,6 @@
 		EMIT(PPC_RAW_BRANCH(offset));				      \
 	} while (0)
 
-/* bl (unconditional 'branch' with link) */
-#define PPC_BL(dest)	EMIT(PPC_RAW_BL((dest) - (unsigned long)(image + ctx->idx)))
-
 /* "cond" here covers BO:BI fields. */
 #define PPC_BCC_SHORT(cond, dest)					      \
 	do {								      \
@@ -50,8 +51,16 @@
 		EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc));					\
 	} while (0)
 
-/* Sign-extended 32-bit immediate load */
+/*
+ * Sign-extended 32-bit immediate load
+ *
+ * If this is a dummy pass (!image), account for
+ * maximum possible instructions.
+ */
 #define PPC_LI32(d, i)		do {					      \
+	if (!image)							      \
+		ctx->idx += 2;						      \
+	else {								      \
 		if ((int)(uintptr_t)(i) >= -32768 &&			      \
 				(int)(uintptr_t)(i) < 32768)		      \
 			EMIT(PPC_RAW_LI(d, i));				      \
@@ -59,10 +68,15 @@
 			EMIT(PPC_RAW_LIS(d, IMM_H(i)));			      \
 			if (IMM_L(i))					      \
 				EMIT(PPC_RAW_ORI(d, d, IMM_L(i)));	      \
-		} } while(0)
+		}							      \
+	} } while (0)
 
 #ifdef CONFIG_PPC64
+/* If dummy pass (!image), account for maximum possible instructions */
 #define PPC_LI64(d, i)		do {					      \
+	if (!image)							      \
+		ctx->idx += 5;						      \
+	else {								      \
 		if ((long)(i) >= -2147483648 &&				      \
 				(long)(i) < 2147483648)			      \
 			PPC_LI32(d, i);					      \
@@ -83,7 +97,20 @@
 			if ((uintptr_t)(i) & 0x000000000000ffffULL)	      \
 				EMIT(PPC_RAW_ORI(d, d, (uintptr_t)(i) &       \
 							0xffff));             \
-		} } while (0)
+		}							      \
+	} } while (0)
+#define PPC_LI_ADDR	PPC_LI64
+
+#ifndef CONFIG_PPC_KERNEL_PCREL
+#define PPC64_LOAD_PACA()						      \
+	EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc)))
+#else
+#define PPC64_LOAD_PACA()	do {} while (0)
+#endif
+#else
+#define PPC_LI64(d, i)	BUILD_BUG()
+#define PPC_LI_ADDR	PPC_LI32
+#define PPC64_LOAD_PACA() BUILD_BUG()
 #endif
 
 /*
@@ -134,9 +161,11 @@ struct codegen_context {
 	unsigned int seen;
 	unsigned int idx;
 	unsigned int stack_size;
-	int b2p[MAX_BPF_JIT_REG + 2];
+	int b2p[MAX_BPF_JIT_REG + 3];
 	unsigned int exentry_idx;
 	unsigned int alt_exit_addr;
+	u64 arena_vm_start;
+	u64 user_vm_start;
 };
 
 #define bpf_to_ppc(r)	(ctx->b2p[r])
@@ -147,12 +176,6 @@ struct codegen_context {
 #define BPF_FIXUP_LEN	2 /* Two instructions => 8 bytes */
 #endif
 
-static inline void bpf_flush_icache(void *start, void *end)
-{
-	smp_wmb();	/* smp write barrier */
-	flush_icache_range((unsigned long)start, (unsigned long)end);
-}
-
 static inline bool bpf_is_seen_register(struct codegen_context *ctx, int i)
 {
 	return ctx->seen & (1 << (31 - i));
@@ -169,16 +192,18 @@ static inline void bpf_clear_seen_register(struct codegen_context *ctx, int i)
 }
 
 void bpf_jit_init_reg_mapping(struct codegen_context *ctx);
-int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func);
-int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
+int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func);
+int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx,
 		       u32 *addrs, int pass, bool extra_pass);
 void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx);
 void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
+void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx);
 void bpf_jit_realloc_regs(struct codegen_context *ctx);
 int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr);
 
-int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct codegen_context *ctx,
-			  int insn_idx, int jmp_off, int dst_reg);
+int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass,
+			  struct codegen_context *ctx, int insn_idx,
+			  int jmp_off, int dst_reg, u32 code);
 
 #endif
 
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index e93aefcfb83f..5e976730b2f5 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -13,16 +13,90 @@
 #include <linux/netdevice.h>
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
-#include <asm/kprobes.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
 #include <linux/bpf.h>
 
+#include <asm/kprobes.h>
+#include <asm/text-patching.h>
+
 #include "bpf_jit.h"
 
+/* These offsets are from bpf prog end and stay the same across progs */
+static int bpf_jit_ool_stub, bpf_jit_long_branch_stub;
+
 static void bpf_jit_fill_ill_insns(void *area, unsigned int size)
 {
 	memset32(area, BREAKPOINT_INSTRUCTION, size / 4);
 }
 
+void dummy_tramp(void);
+
+asm (
+"	.pushsection .text, \"ax\", @progbits	;"
+"	.global dummy_tramp			;"
+"	.type dummy_tramp, @function		;"
+"dummy_tramp:					;"
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+"	blr					;"
+#else
+/* LR is always in r11, so we don't need a 'mflr r11' here */
+"	mtctr	11				;"
+"	mtlr	0				;"
+"	bctr					;"
+#endif
+"	.size dummy_tramp, .-dummy_tramp	;"
+"	.popsection				;"
+);
+
+void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx)
+{
+	int ool_stub_idx, long_branch_stub_idx;
+
+	/*
+	 * Out-of-line stub:
+	 *	mflr	r0
+	 *	[b|bl]	tramp
+	 *	mtlr	r0 // only with CONFIG_PPC_FTRACE_OUT_OF_LINE
+	 *	b	bpf_func + 4
+	 */
+	ool_stub_idx = ctx->idx;
+	EMIT(PPC_RAW_MFLR(_R0));
+	EMIT(PPC_RAW_NOP());
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+		EMIT(PPC_RAW_MTLR(_R0));
+	WARN_ON_ONCE(!is_offset_in_branch_range(4 - (long)ctx->idx * 4));
+	EMIT(PPC_RAW_BRANCH(4 - (long)ctx->idx * 4));
+
+	/*
+	 * Long branch stub:
+	 *	.long	<dummy_tramp_addr>
+	 *	mflr	r11
+	 *	bcl	20,31,$+4
+	 *	mflr	r12
+	 *	ld	r12, -8-SZL(r12)
+	 *	mtctr	r12
+	 *	mtlr	r11 // needed to retain ftrace ABI
+	 *	bctr
+	 */
+	if (image)
+		*((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp;
+	ctx->idx += SZL / 4;
+	long_branch_stub_idx = ctx->idx;
+	EMIT(PPC_RAW_MFLR(_R11));
+	EMIT(PPC_RAW_BCL4());
+	EMIT(PPC_RAW_MFLR(_R12));
+	EMIT(PPC_RAW_LL(_R12, _R12, -8-SZL));
+	EMIT(PPC_RAW_MTCTR(_R12));
+	EMIT(PPC_RAW_MTLR(_R11));
+	EMIT(PPC_RAW_BCTR());
+
+	if (!bpf_jit_ool_stub) {
+		bpf_jit_ool_stub = (ctx->idx - ool_stub_idx) * 4;
+		bpf_jit_long_branch_stub = (ctx->idx - long_branch_stub_idx) * 4;
+	}
+}
+
 int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr)
 {
 	if (!exit_addr || is_offset_in_branch_range(exit_addr - (ctx->idx * 4))) {
@@ -39,10 +113,13 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg,
 	return 0;
 }
 
-struct powerpc64_jit_data {
-	struct bpf_binary_header *header;
+struct powerpc_jit_data {
+	/* address of rw header */
+	struct bpf_binary_header *hdr;
+	/* address of ro final header */
+	struct bpf_binary_header *fhdr;
 	u32 *addrs;
-	u8 *image;
+	u8 *fimage;
 	u32 proglen;
 	struct codegen_context ctx;
 };
@@ -59,15 +136,18 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	u8 *image = NULL;
 	u32 *code_base;
 	u32 *addrs;
-	struct powerpc64_jit_data *jit_data;
+	struct powerpc_jit_data *jit_data;
 	struct codegen_context cgctx;
 	int pass;
 	int flen;
-	struct bpf_binary_header *bpf_hdr;
+	struct bpf_binary_header *fhdr = NULL;
+	struct bpf_binary_header *hdr = NULL;
 	struct bpf_prog *org_fp = fp;
 	struct bpf_prog *tmp_fp;
 	bool bpf_blinded = false;
 	bool extra_pass = false;
+	u8 *fimage = NULL;
+	u32 *fcode_base;
 	u32 extable_len;
 	u32 fixup_len;
 
@@ -97,10 +177,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	addrs = jit_data->addrs;
 	if (addrs) {
 		cgctx = jit_data->ctx;
-		image = jit_data->image;
-		bpf_hdr = jit_data->header;
+		/*
+		 * JIT compiled to a writable location (image/code_base) first.
+		 * It is then moved to the readonly final location (fimage/fcode_base)
+		 * using instruction patching.
+		 */
+		fimage = jit_data->fimage;
+		fhdr = jit_data->fhdr;
 		proglen = jit_data->proglen;
+		hdr = jit_data->hdr;
+		image = (void *)hdr + ((void *)fimage - (void *)fhdr);
 		extra_pass = true;
+		/* During extra pass, ensure index is reset before repopulating extable entries */
+		cgctx.exentry_idx = 0;
 		goto skip_init_ctx;
 	}
 
@@ -115,9 +204,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 
 	/* Make sure that the stack is quadword aligned. */
 	cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
+	cgctx.arena_vm_start = bpf_arena_get_kern_vm_start(fp->aux->arena);
+	cgctx.user_vm_start = bpf_arena_get_user_vm_start(fp->aux->arena);
 
 	/* Scouting faux-generate pass 0 */
-	if (bpf_jit_build_body(fp, 0, &cgctx, addrs, 0, false)) {
+	if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) {
 		/* We hit something illegal or unsupported. */
 		fp = org_fp;
 		goto out_addrs;
@@ -132,7 +223,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	 */
 	if (cgctx.seen & SEEN_TAILCALL || !is_offset_in_branch_range((long)cgctx.idx * 4)) {
 		cgctx.idx = 0;
-		if (bpf_jit_build_body(fp, 0, &cgctx, addrs, 0, false)) {
+		if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) {
 			fp = org_fp;
 			goto out_addrs;
 		}
@@ -144,9 +235,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	 * update ctgtx.idx as it pretends to output instructions, then we can
 	 * calculate total size from idx.
 	 */
-	bpf_jit_build_prologue(0, &cgctx);
+	bpf_jit_build_prologue(NULL, &cgctx);
 	addrs[fp->len] = cgctx.idx * 4;
-	bpf_jit_build_epilogue(0, &cgctx);
+	bpf_jit_build_epilogue(NULL, &cgctx);
 
 	fixup_len = fp->aux->num_exentries * BPF_FIXUP_LEN * 4;
 	extable_len = fp->aux->num_exentries * sizeof(struct exception_table_entry);
@@ -154,17 +245,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	proglen = cgctx.idx * 4;
 	alloclen = proglen + FUNCTION_DESCR_SIZE + fixup_len + extable_len;
 
-	bpf_hdr = bpf_jit_binary_alloc(alloclen, &image, 4, bpf_jit_fill_ill_insns);
-	if (!bpf_hdr) {
+	fhdr = bpf_jit_binary_pack_alloc(alloclen, &fimage, 4, &hdr, &image,
+					      bpf_jit_fill_ill_insns);
+	if (!fhdr) {
 		fp = org_fp;
 		goto out_addrs;
 	}
 
 	if (extable_len)
-		fp->aux->extable = (void *)image + FUNCTION_DESCR_SIZE + proglen + fixup_len;
+		fp->aux->extable = (void *)fimage + FUNCTION_DESCR_SIZE + proglen + fixup_len;
 
 skip_init_ctx:
 	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
+	fcode_base = (u32 *)(fimage + FUNCTION_DESCR_SIZE);
 
 	/* Code generation passes 1-2 */
 	for (pass = 1; pass < 3; pass++) {
@@ -172,8 +265,10 @@ skip_init_ctx:
 		cgctx.idx = 0;
 		cgctx.alt_exit_addr = 0;
 		bpf_jit_build_prologue(code_base, &cgctx);
-		if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, pass, extra_pass)) {
-			bpf_jit_binary_free(bpf_hdr);
+		if (bpf_jit_build_body(fp, code_base, fcode_base, &cgctx, addrs, pass,
+				       extra_pass)) {
+			bpf_arch_text_copy(&fhdr->size, &hdr->size, sizeof(hdr->size));
+			bpf_jit_binary_pack_free(fhdr, hdr);
 			fp = org_fp;
 			goto out_addrs;
 		}
@@ -193,17 +288,19 @@ skip_init_ctx:
 
 #ifdef CONFIG_PPC64_ELF_ABI_V1
 	/* Function descriptor nastiness: Address + TOC */
-	((u64 *)image)[0] = (u64)code_base;
+	((u64 *)image)[0] = (u64)fcode_base;
 	((u64 *)image)[1] = local_paca->kernel_toc;
 #endif
 
-	fp->bpf_func = (void *)image;
+	fp->bpf_func = (void *)fimage;
 	fp->jited = 1;
-	fp->jited_len = proglen + FUNCTION_DESCR_SIZE;
+	fp->jited_len = cgctx.idx * 4 + FUNCTION_DESCR_SIZE;
 
-	bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + bpf_hdr->size);
 	if (!fp->is_func || extra_pass) {
-		bpf_jit_binary_lock_ro(bpf_hdr);
+		if (bpf_jit_binary_pack_finalize(fhdr, hdr)) {
+			fp = org_fp;
+			goto out_addrs;
+		}
 		bpf_prog_fill_jited_linfo(fp, addrs);
 out_addrs:
 		kfree(addrs);
@@ -213,8 +310,9 @@ out_addrs:
 		jit_data->addrs = addrs;
 		jit_data->ctx = cgctx;
 		jit_data->proglen = proglen;
-		jit_data->image = image;
-		jit_data->header = bpf_hdr;
+		jit_data->fimage = fimage;
+		jit_data->fhdr = fhdr;
+		jit_data->hdr = hdr;
 	}
 
 out:
@@ -228,12 +326,13 @@ out:
  * The caller should check for (BPF_MODE(code) == BPF_PROBE_MEM) before calling
  * this function, as this only applies to BPF_PROBE_MEM, for now.
  */
-int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct codegen_context *ctx,
-			  int insn_idx, int jmp_off, int dst_reg)
+int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass,
+			  struct codegen_context *ctx, int insn_idx, int jmp_off,
+			  int dst_reg, u32 code)
 {
 	off_t offset;
 	unsigned long pc;
-	struct exception_table_entry *ex;
+	struct exception_table_entry *ex, *ex_entry;
 	u32 *fixup;
 
 	/* Populate extable entries only in the last pass */
@@ -244,31 +343,889 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct code
 	    WARN_ON_ONCE(ctx->exentry_idx >= fp->aux->num_exentries))
 		return -EINVAL;
 
+	/*
+	 * Program is first written to image before copying to the
+	 * final location (fimage). Accordingly, update in the image first.
+	 * As all offsets used are relative, copying as is to the
+	 * final location should be alright.
+	 */
 	pc = (unsigned long)&image[insn_idx];
+	ex = (void *)fp->aux->extable - (void *)fimage + (void *)image;
 
-	fixup = (void *)fp->aux->extable -
+	fixup = (void *)ex -
 		(fp->aux->num_exentries * BPF_FIXUP_LEN * 4) +
 		(ctx->exentry_idx * BPF_FIXUP_LEN * 4);
 
 	fixup[0] = PPC_RAW_LI(dst_reg, 0);
+	if (BPF_CLASS(code) == BPF_ST || BPF_CLASS(code) == BPF_STX)
+		fixup[0] = PPC_RAW_NOP();
+
 	if (IS_ENABLED(CONFIG_PPC32))
 		fixup[1] = PPC_RAW_LI(dst_reg - 1, 0); /* clear higher 32-bit register too */
 
 	fixup[BPF_FIXUP_LEN - 1] =
 		PPC_RAW_BRANCH((long)(pc + jmp_off) - (long)&fixup[BPF_FIXUP_LEN - 1]);
 
-	ex = &fp->aux->extable[ctx->exentry_idx];
+	ex_entry = &ex[ctx->exentry_idx];
 
-	offset = pc - (long)&ex->insn;
+	offset = pc - (long)&ex_entry->insn;
 	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
 		return -ERANGE;
-	ex->insn = offset;
+	ex_entry->insn = offset;
 
-	offset = (long)fixup - (long)&ex->fixup;
+	offset = (long)fixup - (long)&ex_entry->fixup;
 	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
 		return -ERANGE;
-	ex->fixup = offset;
+	ex_entry->fixup = offset;
 
 	ctx->exentry_idx++;
 	return 0;
 }
+
+void *bpf_arch_text_copy(void *dst, void *src, size_t len)
+{
+	int err;
+
+	if (WARN_ON_ONCE(core_kernel_text((unsigned long)dst)))
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&text_mutex);
+	err = patch_instructions(dst, src, len, false);
+	mutex_unlock(&text_mutex);
+
+	return err ? ERR_PTR(err) : dst;
+}
+
+int bpf_arch_text_invalidate(void *dst, size_t len)
+{
+	u32 insn = BREAKPOINT_INSTRUCTION;
+	int ret;
+
+	if (WARN_ON_ONCE(core_kernel_text((unsigned long)dst)))
+		return -EINVAL;
+
+	mutex_lock(&text_mutex);
+	ret = patch_instructions(dst, &insn, len, true);
+	mutex_unlock(&text_mutex);
+
+	return ret;
+}
+
+void bpf_jit_free(struct bpf_prog *fp)
+{
+	if (fp->jited) {
+		struct powerpc_jit_data *jit_data = fp->aux->jit_data;
+		struct bpf_binary_header *hdr;
+
+		/*
+		 * If we fail the final pass of JIT (from jit_subprogs),
+		 * the program may not be finalized yet. Call finalize here
+		 * before freeing it.
+		 */
+		if (jit_data) {
+			bpf_jit_binary_pack_finalize(jit_data->fhdr, jit_data->hdr);
+			kvfree(jit_data->addrs);
+			kfree(jit_data);
+		}
+		hdr = bpf_jit_binary_pack_hdr(fp);
+		bpf_jit_binary_pack_free(hdr, NULL);
+		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
+	}
+
+	bpf_prog_unlock_free(fp);
+}
+
+bool bpf_jit_supports_kfunc_call(void)
+{
+	return true;
+}
+
+bool bpf_jit_supports_arena(void)
+{
+	return IS_ENABLED(CONFIG_PPC64);
+}
+
+bool bpf_jit_supports_far_kfunc_call(void)
+{
+	return IS_ENABLED(CONFIG_PPC64);
+}
+
+bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
+{
+	if (!in_arena)
+		return true;
+	switch (insn->code) {
+	case BPF_STX | BPF_ATOMIC | BPF_H:
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		if (bpf_atomic_is_load_store(insn))
+			return false;
+		return IS_ENABLED(CONFIG_PPC64);
+	}
+	return true;
+}
+
+void *arch_alloc_bpf_trampoline(unsigned int size)
+{
+	return bpf_prog_pack_alloc(size, bpf_jit_fill_ill_insns);
+}
+
+void arch_free_bpf_trampoline(void *image, unsigned int size)
+{
+	bpf_prog_pack_free(image, size);
+}
+
+int arch_protect_bpf_trampoline(void *image, unsigned int size)
+{
+	return 0;
+}
+
+static int invoke_bpf_prog(u32 *image, u32 *ro_image, struct codegen_context *ctx,
+			   struct bpf_tramp_link *l, int regs_off, int retval_off,
+			   int run_ctx_off, bool save_ret)
+{
+	struct bpf_prog *p = l->link.prog;
+	ppc_inst_t branch_insn;
+	u32 jmp_idx;
+	int ret = 0;
+
+	/* Save cookie */
+	if (IS_ENABLED(CONFIG_PPC64)) {
+		PPC_LI64(_R3, l->cookie);
+		EMIT(PPC_RAW_STD(_R3, _R1, run_ctx_off + offsetof(struct bpf_tramp_run_ctx,
+				 bpf_cookie)));
+	} else {
+		PPC_LI32(_R3, l->cookie >> 32);
+		PPC_LI32(_R4, l->cookie);
+		EMIT(PPC_RAW_STW(_R3, _R1,
+				 run_ctx_off + offsetof(struct bpf_tramp_run_ctx, bpf_cookie)));
+		EMIT(PPC_RAW_STW(_R4, _R1,
+				 run_ctx_off + offsetof(struct bpf_tramp_run_ctx, bpf_cookie) + 4));
+	}
+
+	/* __bpf_prog_enter(p, &bpf_tramp_run_ctx) */
+	PPC_LI_ADDR(_R3, p);
+	EMIT(PPC_RAW_MR(_R25, _R3));
+	EMIT(PPC_RAW_ADDI(_R4, _R1, run_ctx_off));
+	ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
+					 (unsigned long)bpf_trampoline_enter(p));
+	if (ret)
+		return ret;
+
+	/* Remember prog start time returned by __bpf_prog_enter */
+	EMIT(PPC_RAW_MR(_R26, _R3));
+
+	/*
+	 * if (__bpf_prog_enter(p) == 0)
+	 *	goto skip_exec_of_prog;
+	 *
+	 * Emit a nop to be later patched with conditional branch, once offset is known
+	 */
+	EMIT(PPC_RAW_CMPLI(_R3, 0));
+	jmp_idx = ctx->idx;
+	EMIT(PPC_RAW_NOP());
+
+	/* p->bpf_func(ctx) */
+	EMIT(PPC_RAW_ADDI(_R3, _R1, regs_off));
+	if (!p->jited)
+		PPC_LI_ADDR(_R4, (unsigned long)p->insnsi);
+	/* Account for max possible instructions during dummy pass for size calculation */
+	if (image && !create_branch(&branch_insn, (u32 *)&ro_image[ctx->idx],
+				    (unsigned long)p->bpf_func,
+				    BRANCH_SET_LINK)) {
+		image[ctx->idx] = ppc_inst_val(branch_insn);
+		ctx->idx++;
+	} else {
+		EMIT(PPC_RAW_LL(_R12, _R25, offsetof(struct bpf_prog, bpf_func)));
+		EMIT(PPC_RAW_MTCTR(_R12));
+		EMIT(PPC_RAW_BCTRL());
+	}
+
+	if (save_ret)
+		EMIT(PPC_RAW_STL(_R3, _R1, retval_off));
+
+	/* Fix up branch */
+	if (image) {
+		if (create_cond_branch(&branch_insn, &image[jmp_idx],
+				       (unsigned long)&image[ctx->idx], COND_EQ << 16))
+			return -EINVAL;
+		image[jmp_idx] = ppc_inst_val(branch_insn);
+	}
+
+	/* __bpf_prog_exit(p, start_time, &bpf_tramp_run_ctx) */
+	EMIT(PPC_RAW_MR(_R3, _R25));
+	EMIT(PPC_RAW_MR(_R4, _R26));
+	EMIT(PPC_RAW_ADDI(_R5, _R1, run_ctx_off));
+	ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
+					 (unsigned long)bpf_trampoline_exit(p));
+
+	return ret;
+}
+
+static int invoke_bpf_mod_ret(u32 *image, u32 *ro_image, struct codegen_context *ctx,
+			      struct bpf_tramp_links *tl, int regs_off, int retval_off,
+			      int run_ctx_off, u32 *branches)
+{
+	int i;
+
+	/*
+	 * The first fmod_ret program will receive a garbage return value.
+	 * Set this to 0 to avoid confusing the program.
+	 */
+	EMIT(PPC_RAW_LI(_R3, 0));
+	EMIT(PPC_RAW_STL(_R3, _R1, retval_off));
+	for (i = 0; i < tl->nr_links; i++) {
+		if (invoke_bpf_prog(image, ro_image, ctx, tl->links[i], regs_off, retval_off,
+				    run_ctx_off, true))
+			return -EINVAL;
+
+		/*
+		 * mod_ret prog stored return value after prog ctx. Emit:
+		 * if (*(u64 *)(ret_val) !=  0)
+		 *	goto do_fexit;
+		 */
+		EMIT(PPC_RAW_LL(_R3, _R1, retval_off));
+		EMIT(PPC_RAW_CMPLI(_R3, 0));
+
+		/*
+		 * Save the location of the branch and generate a nop, which is
+		 * replaced with a conditional jump once do_fexit (i.e. the
+		 * start of the fexit invocation) is finalized.
+		 */
+		branches[i] = ctx->idx;
+		EMIT(PPC_RAW_NOP());
+	}
+
+	return 0;
+}
+
+static void bpf_trampoline_setup_tail_call_cnt(u32 *image, struct codegen_context *ctx,
+					       int func_frame_offset, int r4_off)
+{
+	if (IS_ENABLED(CONFIG_PPC64)) {
+		/* See bpf_jit_stack_tailcallcnt() */
+		int tailcallcnt_offset = 7 * 8;
+
+		EMIT(PPC_RAW_LL(_R3, _R1, func_frame_offset - tailcallcnt_offset));
+		EMIT(PPC_RAW_STL(_R3, _R1, -tailcallcnt_offset));
+	} else {
+		/* See bpf_jit_stack_offsetof() and BPF_PPC_TC */
+		EMIT(PPC_RAW_LL(_R4, _R1, r4_off));
+	}
+}
+
+static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_context *ctx,
+						 int func_frame_offset, int r4_off)
+{
+	if (IS_ENABLED(CONFIG_PPC64)) {
+		/* See bpf_jit_stack_tailcallcnt() */
+		int tailcallcnt_offset = 7 * 8;
+
+		EMIT(PPC_RAW_LL(_R3, _R1, -tailcallcnt_offset));
+		EMIT(PPC_RAW_STL(_R3, _R1, func_frame_offset - tailcallcnt_offset));
+	} else {
+		/* See bpf_jit_stack_offsetof() and BPF_PPC_TC */
+		EMIT(PPC_RAW_STL(_R4, _R1, r4_off));
+	}
+}
+
+static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx, int func_frame_offset,
+				     int nr_regs, int regs_off)
+{
+	int param_save_area_offset;
+
+	param_save_area_offset = func_frame_offset; /* the two frames we alloted */
+	param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */
+
+	for (int i = 0; i < nr_regs; i++) {
+		if (i < 8) {
+			EMIT(PPC_RAW_STL(_R3 + i, _R1, regs_off + i * SZL));
+		} else {
+			EMIT(PPC_RAW_LL(_R3, _R1, param_save_area_offset + i * SZL));
+			EMIT(PPC_RAW_STL(_R3, _R1, regs_off + i * SZL));
+		}
+	}
+}
+
+/* Used when restoring just the register parameters when returning back */
+static void bpf_trampoline_restore_args_regs(u32 *image, struct codegen_context *ctx,
+					     int nr_regs, int regs_off)
+{
+	for (int i = 0; i < nr_regs && i < 8; i++)
+		EMIT(PPC_RAW_LL(_R3 + i, _R1, regs_off + i * SZL));
+}
+
+/* Used when we call into the traced function. Replicate parameter save area */
+static void bpf_trampoline_restore_args_stack(u32 *image, struct codegen_context *ctx,
+					      int func_frame_offset, int nr_regs, int regs_off)
+{
+	int param_save_area_offset;
+
+	param_save_area_offset = func_frame_offset; /* the two frames we alloted */
+	param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */
+
+	for (int i = 8; i < nr_regs; i++) {
+		EMIT(PPC_RAW_LL(_R3, _R1, param_save_area_offset + i * SZL));
+		EMIT(PPC_RAW_STL(_R3, _R1, STACK_FRAME_MIN_SIZE + i * SZL));
+	}
+	bpf_trampoline_restore_args_regs(image, ctx, nr_regs, regs_off);
+}
+
+static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_image,
+					 void *rw_image_end, void *ro_image,
+					 const struct btf_func_model *m, u32 flags,
+					 struct bpf_tramp_links *tlinks,
+					 void *func_addr)
+{
+	int regs_off, nregs_off, ip_off, run_ctx_off, retval_off, nvr_off, alt_lr_off, r4_off = 0;
+	int i, ret, nr_regs, bpf_frame_size = 0, bpf_dummy_frame_size = 0, func_frame_offset;
+	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
+	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
+	struct codegen_context codegen_ctx, *ctx;
+	u32 *image = (u32 *)rw_image;
+	ppc_inst_t branch_insn;
+	u32 *branches = NULL;
+	bool save_ret;
+
+	if (IS_ENABLED(CONFIG_PPC32))
+		return -EOPNOTSUPP;
+
+	nr_regs = m->nr_args;
+	/* Extra registers for struct arguments */
+	for (i = 0; i < m->nr_args; i++)
+		if (m->arg_size[i] > SZL)
+			nr_regs += round_up(m->arg_size[i], SZL) / SZL - 1;
+
+	if (nr_regs > MAX_BPF_FUNC_ARGS)
+		return -EOPNOTSUPP;
+
+	ctx = &codegen_ctx;
+	memset(ctx, 0, sizeof(*ctx));
+
+	/*
+	 * Generated stack layout:
+	 *
+	 * func prev back chain         [ back chain        ]
+	 *                              [                   ]
+	 * bpf prog redzone/tailcallcnt [ ...               ] 64 bytes (64-bit powerpc)
+	 *                              [                   ] --
+	 * LR save area                 [ r0 save (64-bit)  ]   | header
+	 *                              [ r0 save (32-bit)  ]   |
+	 * dummy frame for unwind       [ back chain 1      ] --
+	 *                              [ padding           ] align stack frame
+	 *       r4_off                 [ r4 (tailcallcnt)  ] optional - 32-bit powerpc
+	 *       alt_lr_off             [ real lr (ool stub)] optional - actual lr
+	 *                              [ r26               ]
+	 *       nvr_off                [ r25               ] nvr save area
+	 *       retval_off             [ return value      ]
+	 *                              [ reg argN          ]
+	 *                              [ ...               ]
+	 *       regs_off               [ reg_arg1          ] prog ctx context
+	 *       nregs_off              [ args count        ]
+	 *       ip_off                 [ traced function   ]
+	 *                              [ ...               ]
+	 *       run_ctx_off            [ bpf_tramp_run_ctx ]
+	 *                              [ reg argN          ]
+	 *                              [ ...               ]
+	 *       param_save_area        [ reg_arg1          ] min 8 doublewords, per ABI
+	 *                              [ TOC save (64-bit) ] --
+	 *                              [ LR save (64-bit)  ]   | header
+	 *                              [ LR save (32-bit)  ]   |
+	 * bpf trampoline frame	        [ back chain 2      ] --
+	 *
+	 */
+
+	/* Minimum stack frame header */
+	bpf_frame_size = STACK_FRAME_MIN_SIZE;
+
+	/*
+	 * Room for parameter save area.
+	 *
+	 * As per the ABI, this is required if we call into the traced
+	 * function (BPF_TRAMP_F_CALL_ORIG):
+	 * - if the function takes more than 8 arguments for the rest to spill onto the stack
+	 * - or, if the function has variadic arguments
+	 * - or, if this functions's prototype was not available to the caller
+	 *
+	 * Reserve space for at least 8 registers for now. This can be optimized later.
+	 */
+	bpf_frame_size += (nr_regs > 8 ? nr_regs : 8) * SZL;
+
+	/* Room for struct bpf_tramp_run_ctx */
+	run_ctx_off = bpf_frame_size;
+	bpf_frame_size += round_up(sizeof(struct bpf_tramp_run_ctx), SZL);
+
+	/* Room for IP address argument */
+	ip_off = bpf_frame_size;
+	if (flags & BPF_TRAMP_F_IP_ARG)
+		bpf_frame_size += SZL;
+
+	/* Room for args count */
+	nregs_off = bpf_frame_size;
+	bpf_frame_size += SZL;
+
+	/* Room for args */
+	regs_off = bpf_frame_size;
+	bpf_frame_size += nr_regs * SZL;
+
+	/* Room for return value of func_addr or fentry prog */
+	retval_off = bpf_frame_size;
+	save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
+	if (save_ret)
+		bpf_frame_size += SZL;
+
+	/* Room for nvr save area */
+	nvr_off = bpf_frame_size;
+	bpf_frame_size += 2 * SZL;
+
+	/* Optional save area for actual LR in case of ool ftrace */
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
+		alt_lr_off = bpf_frame_size;
+		bpf_frame_size += SZL;
+	}
+
+	if (IS_ENABLED(CONFIG_PPC32)) {
+		if (nr_regs < 2) {
+			r4_off = bpf_frame_size;
+			bpf_frame_size += SZL;
+		} else {
+			r4_off = regs_off + SZL;
+		}
+	}
+
+	/* Padding to align stack frame, if any */
+	bpf_frame_size = round_up(bpf_frame_size, SZL * 2);
+
+	/* Dummy frame size for proper unwind - includes 64-bytes red zone for 64-bit powerpc */
+	bpf_dummy_frame_size = STACK_FRAME_MIN_SIZE + 64;
+
+	/* Offset to the traced function's stack frame */
+	func_frame_offset = bpf_dummy_frame_size + bpf_frame_size;
+
+	/* Create dummy frame for unwind, store original return value */
+	EMIT(PPC_RAW_STL(_R0, _R1, PPC_LR_STKOFF));
+	/* Protect red zone where tail call count goes */
+	EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_dummy_frame_size));
+
+	/* Create our stack frame */
+	EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_frame_size));
+
+	/* 64-bit: Save TOC and load kernel TOC */
+	if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
+		EMIT(PPC_RAW_STD(_R2, _R1, 24));
+		PPC64_LOAD_PACA();
+	}
+
+	/* 32-bit: save tail call count in r4 */
+	if (IS_ENABLED(CONFIG_PPC32) && nr_regs < 2)
+		EMIT(PPC_RAW_STL(_R4, _R1, r4_off));
+
+	bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off);
+
+	/* Save our return address */
+	EMIT(PPC_RAW_MFLR(_R3));
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+		EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off));
+	else
+		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+
+	/*
+	 * Save ip address of the traced function.
+	 * We could recover this from LR, but we will need to address for OOL trampoline,
+	 * and optional GEP area.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) || flags & BPF_TRAMP_F_IP_ARG) {
+		EMIT(PPC_RAW_LWZ(_R4, _R3, 4));
+		EMIT(PPC_RAW_SLWI(_R4, _R4, 6));
+		EMIT(PPC_RAW_SRAWI(_R4, _R4, 6));
+		EMIT(PPC_RAW_ADD(_R3, _R3, _R4));
+		EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
+	}
+
+	if (flags & BPF_TRAMP_F_IP_ARG)
+		EMIT(PPC_RAW_STL(_R3, _R1, ip_off));
+
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+		/* Fake our LR for unwind */
+		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+
+	/* Save function arg count -- see bpf_get_func_arg_cnt() */
+	EMIT(PPC_RAW_LI(_R3, nr_regs));
+	EMIT(PPC_RAW_STL(_R3, _R1, nregs_off));
+
+	/* Save nv regs */
+	EMIT(PPC_RAW_STL(_R25, _R1, nvr_off));
+	EMIT(PPC_RAW_STL(_R26, _R1, nvr_off + SZL));
+
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
+		PPC_LI_ADDR(_R3, (unsigned long)im);
+		ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
+						 (unsigned long)__bpf_tramp_enter);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < fentry->nr_links; i++)
+		if (invoke_bpf_prog(image, ro_image, ctx, fentry->links[i], regs_off, retval_off,
+				    run_ctx_off, flags & BPF_TRAMP_F_RET_FENTRY_RET))
+			return -EINVAL;
+
+	if (fmod_ret->nr_links) {
+		branches = kcalloc(fmod_ret->nr_links, sizeof(u32), GFP_KERNEL);
+		if (!branches)
+			return -ENOMEM;
+
+		if (invoke_bpf_mod_ret(image, ro_image, ctx, fmod_ret, regs_off, retval_off,
+				       run_ctx_off, branches)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
+	}
+
+	/* Call the traced function */
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
+		/*
+		 * The address in LR save area points to the correct point in the original function
+		 * with both PPC_FTRACE_OUT_OF_LINE as well as with traditional ftrace instruction
+		 * sequence
+		 */
+		EMIT(PPC_RAW_LL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+		EMIT(PPC_RAW_MTCTR(_R3));
+
+		/* Replicate tail_call_cnt before calling the original BPF prog */
+		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+			bpf_trampoline_setup_tail_call_cnt(image, ctx, func_frame_offset, r4_off);
+
+		/* Restore args */
+		bpf_trampoline_restore_args_stack(image, ctx, func_frame_offset, nr_regs, regs_off);
+
+		/* Restore TOC for 64-bit */
+		if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+			EMIT(PPC_RAW_LD(_R2, _R1, 24));
+		EMIT(PPC_RAW_BCTRL());
+		if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+			PPC64_LOAD_PACA();
+
+		/* Store return value for bpf prog to access */
+		EMIT(PPC_RAW_STL(_R3, _R1, retval_off));
+
+		/* Restore updated tail_call_cnt */
+		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+			bpf_trampoline_restore_tail_call_cnt(image, ctx, func_frame_offset, r4_off);
+
+		/* Reserve space to patch branch instruction to skip fexit progs */
+		if (ro_image) /* image is NULL for dummy pass */
+			im->ip_after_call = &((u32 *)ro_image)[ctx->idx];
+		EMIT(PPC_RAW_NOP());
+	}
+
+	/* Update branches saved in invoke_bpf_mod_ret with address of do_fexit */
+	for (i = 0; i < fmod_ret->nr_links && image; i++) {
+		if (create_cond_branch(&branch_insn, &image[branches[i]],
+				       (unsigned long)&image[ctx->idx], COND_NE << 16)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
+
+		image[branches[i]] = ppc_inst_val(branch_insn);
+	}
+
+	for (i = 0; i < fexit->nr_links; i++)
+		if (invoke_bpf_prog(image, ro_image, ctx, fexit->links[i], regs_off, retval_off,
+				    run_ctx_off, false)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
+
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
+		if (ro_image) /* image is NULL for dummy pass */
+			im->ip_epilogue = &((u32 *)ro_image)[ctx->idx];
+		PPC_LI_ADDR(_R3, im);
+		ret = bpf_jit_emit_func_call_rel(image, ro_image, ctx,
+						 (unsigned long)__bpf_tramp_exit);
+		if (ret)
+			goto cleanup;
+	}
+
+	if (flags & BPF_TRAMP_F_RESTORE_REGS)
+		bpf_trampoline_restore_args_regs(image, ctx, nr_regs, regs_off);
+
+	/* Restore return value of func_addr or fentry prog */
+	if (save_ret)
+		EMIT(PPC_RAW_LL(_R3, _R1, retval_off));
+
+	/* Restore nv regs */
+	EMIT(PPC_RAW_LL(_R26, _R1, nvr_off + SZL));
+	EMIT(PPC_RAW_LL(_R25, _R1, nvr_off));
+
+	/* Epilogue */
+	if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+		EMIT(PPC_RAW_LD(_R2, _R1, 24));
+	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
+		/* Skip the traced function and return to parent */
+		EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+		EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
+		EMIT(PPC_RAW_MTLR(_R0));
+		EMIT(PPC_RAW_BLR());
+	} else {
+		if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
+			EMIT(PPC_RAW_LL(_R0, _R1, alt_lr_off));
+			EMIT(PPC_RAW_MTLR(_R0));
+			EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+			EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
+			EMIT(PPC_RAW_BLR());
+		} else {
+			EMIT(PPC_RAW_LL(_R0, _R1, bpf_frame_size + PPC_LR_STKOFF));
+			EMIT(PPC_RAW_MTCTR(_R0));
+			EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+			EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
+			EMIT(PPC_RAW_MTLR(_R0));
+			EMIT(PPC_RAW_BCTR());
+		}
+	}
+
+	/* Make sure the trampoline generation logic doesn't overflow */
+	if (image && WARN_ON_ONCE(&image[ctx->idx] > (u32 *)rw_image_end - BPF_INSN_SAFETY)) {
+		ret = -EFAULT;
+		goto cleanup;
+	}
+	ret = ctx->idx * 4 + BPF_INSN_SAFETY * 4;
+
+cleanup:
+	kfree(branches);
+	return ret;
+}
+
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr)
+{
+	struct bpf_tramp_image im;
+	int ret;
+
+	ret = __arch_prepare_bpf_trampoline(&im, NULL, NULL, NULL, m, flags, tlinks, func_addr);
+	return ret;
+}
+
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
+				const struct btf_func_model *m, u32 flags,
+				struct bpf_tramp_links *tlinks,
+				void *func_addr)
+{
+	u32 size = image_end - image;
+	void *rw_image, *tmp;
+	int ret;
+
+	/*
+	 * rw_image doesn't need to be in module memory range, so we can
+	 * use kvmalloc.
+	 */
+	rw_image = kvmalloc(size, GFP_KERNEL);
+	if (!rw_image)
+		return -ENOMEM;
+
+	ret = __arch_prepare_bpf_trampoline(im, rw_image, rw_image + size, image, m,
+					    flags, tlinks, func_addr);
+	if (ret < 0)
+		goto out;
+
+	if (bpf_jit_enable > 1)
+		bpf_jit_dump(1, ret - BPF_INSN_SAFETY * 4, 1, rw_image);
+
+	tmp = bpf_arch_text_copy(image, rw_image, size);
+	if (IS_ERR(tmp))
+		ret = PTR_ERR(tmp);
+
+out:
+	kvfree(rw_image);
+	return ret;
+}
+
+static int bpf_modify_inst(void *ip, ppc_inst_t old_inst, ppc_inst_t new_inst)
+{
+	ppc_inst_t org_inst;
+
+	if (copy_inst_from_kernel_nofault(&org_inst, ip)) {
+		pr_err("0x%lx: fetching instruction failed\n", (unsigned long)ip);
+		return -EFAULT;
+	}
+
+	if (!ppc_inst_equal(org_inst, old_inst)) {
+		pr_err("0x%lx: expected (%08lx) != found (%08lx)\n",
+		       (unsigned long)ip, ppc_inst_as_ulong(old_inst), ppc_inst_as_ulong(org_inst));
+		return -EINVAL;
+	}
+
+	if (ppc_inst_equal(old_inst, new_inst))
+		return 0;
+
+	return patch_instruction(ip, new_inst);
+}
+
+static void do_isync(void *info __maybe_unused)
+{
+	isync();
+}
+
+/*
+ * A 3-step process for bpf prog entry:
+ * 1. At bpf prog entry, a single nop/b:
+ * bpf_func:
+ *	[nop|b]	ool_stub
+ * 2. Out-of-line stub:
+ * ool_stub:
+ *	mflr	r0
+ *	[b|bl]	<bpf_prog>/<long_branch_stub>
+ *	mtlr	r0 // CONFIG_PPC_FTRACE_OUT_OF_LINE only
+ *	b	bpf_func + 4
+ * 3. Long branch stub:
+ * long_branch_stub:
+ *	.long	<branch_addr>/<dummy_tramp>
+ *	mflr	r11
+ *	bcl	20,31,$+4
+ *	mflr	r12
+ *	ld	r12, -16(r12)
+ *	mtctr	r12
+ *	mtlr	r11 // needed to retain ftrace ABI
+ *	bctr
+ *
+ * dummy_tramp is used to reduce synchronization requirements.
+ *
+ * When attaching a bpf trampoline to a bpf prog, we do not need any
+ * synchronization here since we always have a valid branch target regardless
+ * of the order in which the above stores are seen. dummy_tramp ensures that
+ * the long_branch stub goes to a valid destination on other cpus, even when
+ * the branch to the long_branch stub is seen before the updated trampoline
+ * address.
+ *
+ * However, when detaching a bpf trampoline from a bpf prog, or if changing
+ * the bpf trampoline address, we need synchronization to ensure that other
+ * cpus can no longer branch into the older trampoline so that it can be
+ * safely freed. bpf_tramp_image_put() uses rcu_tasks to ensure all cpus
+ * make forward progress, but we still need to ensure that other cpus
+ * execute isync (or some CSI) so that they don't go back into the
+ * trampoline again.
+ */
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+		       enum bpf_text_poke_type new_t, void *old_addr,
+		       void *new_addr)
+{
+	unsigned long bpf_func, bpf_func_end, size, offset;
+	ppc_inst_t old_inst, new_inst;
+	int ret = 0, branch_flags;
+	char name[KSYM_NAME_LEN];
+
+	if (IS_ENABLED(CONFIG_PPC32))
+		return -EOPNOTSUPP;
+
+	bpf_func = (unsigned long)ip;
+
+	/* We currently only support poking bpf programs */
+	if (!__bpf_address_lookup(bpf_func, &size, &offset, name)) {
+		pr_err("%s (0x%lx): kernel/modules are not supported\n", __func__, bpf_func);
+		return -EOPNOTSUPP;
+	}
+
+	/*
+	 * If we are not poking at bpf prog entry, then we are simply patching in/out
+	 * an unconditional branch instruction at im->ip_after_call
+	 */
+	if (offset) {
+		if (old_t == BPF_MOD_CALL || new_t == BPF_MOD_CALL) {
+			pr_err("%s (0x%lx): calls are not supported in bpf prog body\n", __func__,
+			       bpf_func);
+			return -EOPNOTSUPP;
+		}
+		old_inst = ppc_inst(PPC_RAW_NOP());
+		if (old_addr)
+			if (create_branch(&old_inst, ip, (unsigned long)old_addr, 0))
+				return -ERANGE;
+		new_inst = ppc_inst(PPC_RAW_NOP());
+		if (new_addr)
+			if (create_branch(&new_inst, ip, (unsigned long)new_addr, 0))
+				return -ERANGE;
+		mutex_lock(&text_mutex);
+		ret = bpf_modify_inst(ip, old_inst, new_inst);
+		mutex_unlock(&text_mutex);
+
+		/* Make sure all cpus see the new instruction */
+		smp_call_function(do_isync, NULL, 1);
+		return ret;
+	}
+
+	bpf_func_end = bpf_func + size;
+
+	/* Address of the jmp/call instruction in the out-of-line stub */
+	ip = (void *)(bpf_func_end - bpf_jit_ool_stub + 4);
+
+	if (!is_offset_in_branch_range((long)ip - 4 - bpf_func)) {
+		pr_err("%s (0x%lx): bpf prog too large, ool stub out of branch range\n", __func__,
+		       bpf_func);
+		return -ERANGE;
+	}
+
+	old_inst = ppc_inst(PPC_RAW_NOP());
+	branch_flags = old_t == BPF_MOD_CALL ? BRANCH_SET_LINK : 0;
+	if (old_addr) {
+		if (is_offset_in_branch_range(ip - old_addr))
+			create_branch(&old_inst, ip, (unsigned long)old_addr, branch_flags);
+		else
+			create_branch(&old_inst, ip, bpf_func_end - bpf_jit_long_branch_stub,
+				      branch_flags);
+	}
+	new_inst = ppc_inst(PPC_RAW_NOP());
+	branch_flags = new_t == BPF_MOD_CALL ? BRANCH_SET_LINK : 0;
+	if (new_addr) {
+		if (is_offset_in_branch_range(ip - new_addr))
+			create_branch(&new_inst, ip, (unsigned long)new_addr, branch_flags);
+		else
+			create_branch(&new_inst, ip, bpf_func_end - bpf_jit_long_branch_stub,
+				      branch_flags);
+	}
+
+	mutex_lock(&text_mutex);
+
+	/*
+	 * 1. Update the address in the long branch stub:
+	 * If new_addr is out of range, we will have to use the long branch stub, so patch new_addr
+	 * here. Otherwise, revert to dummy_tramp, but only if we had patched old_addr here.
+	 */
+	if ((new_addr && !is_offset_in_branch_range(new_addr - ip)) ||
+	    (old_addr && !is_offset_in_branch_range(old_addr - ip)))
+		ret = patch_ulong((void *)(bpf_func_end - bpf_jit_long_branch_stub - SZL),
+				  (new_addr && !is_offset_in_branch_range(new_addr - ip)) ?
+				  (unsigned long)new_addr : (unsigned long)dummy_tramp);
+	if (ret)
+		goto out;
+
+	/* 2. Update the branch/call in the out-of-line stub */
+	ret = bpf_modify_inst(ip, old_inst, new_inst);
+	if (ret)
+		goto out;
+
+	/* 3. Update instruction at bpf prog entry */
+	ip = (void *)bpf_func;
+	if (!old_addr || !new_addr) {
+		if (!old_addr) {
+			old_inst = ppc_inst(PPC_RAW_NOP());
+			create_branch(&new_inst, ip, bpf_func_end - bpf_jit_ool_stub, 0);
+		} else {
+			new_inst = ppc_inst(PPC_RAW_NOP());
+			create_branch(&old_inst, ip, bpf_func_end - bpf_jit_ool_stub, 0);
+		}
+		ret = bpf_modify_inst(ip, old_inst, new_inst);
+	}
+
+out:
+	mutex_unlock(&text_mutex);
+
+	/*
+	 * Sync only if we are not attaching a trampoline to a bpf prog so the older
+	 * trampoline can be freed safely.
+	 */
+	if (old_addr)
+		smp_call_function(do_isync, NULL, 1);
+
+	return ret;
+}
diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index 7f91ea064c08..3087e744fb25 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -127,13 +127,16 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 {
 	int i;
 
+	/* Instruction for trampoline attach */
+	EMIT(PPC_RAW_NOP());
+
 	/* Initialize tail_call_cnt, to be skipped if we do tail calls. */
 	if (ctx->seen & SEEN_TAILCALL)
 		EMIT(PPC_RAW_LI(_R4, 0));
 	else
 		EMIT(PPC_RAW_NOP());
 
-#define BPF_TAILCALL_PROLOGUE_SIZE	4
+#define BPF_TAILCALL_PROLOGUE_SIZE	8
 
 	if (bpf_has_stack_frame(ctx))
 		EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
@@ -198,14 +201,17 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 	bpf_jit_emit_common_epilogue(image, ctx);
 
 	EMIT(PPC_RAW_BLR());
+
+	bpf_jit_build_fentry_stubs(image, ctx);
 }
 
-int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func)
+/* Relative offset needs to be calculated based on final image location */
+int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
 {
-	s32 rel = (s32)func - (s32)(image + ctx->idx);
+	s32 rel = (s32)func - (s32)(fimage + ctx->idx);
 
 	if (image && rel < 0x2000000 && rel >= -0x2000000) {
-		PPC_BL(func);
+		EMIT(PPC_RAW_BL(rel));
 	} else {
 		/* Load function address into r0 */
 		EMIT(PPC_RAW_LIS(_R0, IMM_H(func)));
@@ -278,7 +284,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 }
 
 /* Assemble the body code between the prologue & epilogue */
-int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
+int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx,
 		       u32 *addrs, int pass, bool extra_pass)
 {
 	const struct bpf_insn *insn = fp->insnsi;
@@ -307,7 +313,6 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		u64 func_addr;
 		u32 true_cond;
 		u32 tmp_idx;
-		int j;
 
 		if (i && (BPF_CLASS(code) == BPF_ALU64 || BPF_CLASS(code) == BPF_ALU) &&
 		    (BPF_CLASS(prevcode) == BPF_ALU64 || BPF_CLASS(prevcode) == BPF_ALU) &&
@@ -449,10 +454,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			}
 			break;
 		case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
-			EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, src_reg));
+			if (off)
+				EMIT(PPC_RAW_DIVW(dst_reg, src2_reg, src_reg));
+			else
+				EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, src_reg));
 			break;
 		case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
-			EMIT(PPC_RAW_DIVWU(_R0, src2_reg, src_reg));
+			if (off)
+				EMIT(PPC_RAW_DIVW(_R0, src2_reg, src_reg));
+			else
+				EMIT(PPC_RAW_DIVWU(_R0, src2_reg, src_reg));
 			EMIT(PPC_RAW_MULW(_R0, src_reg, _R0));
 			EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0));
 			break;
@@ -466,10 +477,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			if (imm == 1) {
 				EMIT(PPC_RAW_MR(dst_reg, src2_reg));
 			} else if (is_power_of_2((u32)imm)) {
-				EMIT(PPC_RAW_SRWI(dst_reg, src2_reg, ilog2(imm)));
+				if (off)
+					EMIT(PPC_RAW_SRAWI(dst_reg, src2_reg, ilog2(imm)));
+				else
+					EMIT(PPC_RAW_SRWI(dst_reg, src2_reg, ilog2(imm)));
 			} else {
 				PPC_LI32(_R0, imm);
-				EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, _R0));
+				if (off)
+					EMIT(PPC_RAW_DIVW(dst_reg, src2_reg, _R0));
+				else
+					EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, _R0));
 			}
 			break;
 		case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
@@ -479,11 +496,19 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			if (!is_power_of_2((u32)imm)) {
 				bpf_set_seen_register(ctx, tmp_reg);
 				PPC_LI32(tmp_reg, imm);
-				EMIT(PPC_RAW_DIVWU(_R0, src2_reg, tmp_reg));
+				if (off)
+					EMIT(PPC_RAW_DIVW(_R0, src2_reg, tmp_reg));
+				else
+					EMIT(PPC_RAW_DIVWU(_R0, src2_reg, tmp_reg));
 				EMIT(PPC_RAW_MULW(_R0, tmp_reg, _R0));
 				EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0));
 			} else if (imm == 1) {
 				EMIT(PPC_RAW_LI(dst_reg, 0));
+			} else if (off) {
+				EMIT(PPC_RAW_SRAWI(_R0, src2_reg, ilog2(imm)));
+				EMIT(PPC_RAW_ADDZE(_R0, _R0));
+				EMIT(PPC_RAW_SLWI(_R0, _R0, ilog2(imm)));
+				EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0));
 			} else {
 				imm = ilog2((u32)imm);
 				EMIT(PPC_RAW_RLWINM(dst_reg, src2_reg, 0, 32 - imm, 31));
@@ -496,11 +521,21 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				imm = -imm;
 			if (!is_power_of_2(imm))
 				return -EOPNOTSUPP;
-			if (imm == 1)
+			if (imm == 1) {
 				EMIT(PPC_RAW_LI(dst_reg, 0));
-			else
+				EMIT(PPC_RAW_LI(dst_reg_h, 0));
+			} else if (off) {
+				EMIT(PPC_RAW_SRAWI(dst_reg_h, src2_reg_h, 31));
+				EMIT(PPC_RAW_XOR(dst_reg, src2_reg, dst_reg_h));
+				EMIT(PPC_RAW_SUBFC(dst_reg, dst_reg_h, dst_reg));
+				EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 32 - ilog2(imm), 31));
+				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg_h));
+				EMIT(PPC_RAW_SUBFC(dst_reg, dst_reg_h, dst_reg));
+				EMIT(PPC_RAW_SUBFE(dst_reg_h, dst_reg_h, dst_reg_h));
+			} else {
 				EMIT(PPC_RAW_RLWINM(dst_reg, src2_reg, 0, 32 - ilog2(imm), 31));
-			EMIT(PPC_RAW_LI(dst_reg_h, 0));
+				EMIT(PPC_RAW_LI(dst_reg_h, 0));
+			}
 			break;
 		case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */
 			if (!imm)
@@ -726,15 +761,30 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		 * MOV
 		 */
 		case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
-			if (dst_reg == src_reg)
-				break;
-			EMIT(PPC_RAW_MR(dst_reg, src_reg));
-			EMIT(PPC_RAW_MR(dst_reg_h, src_reg_h));
+			if (off == 8) {
+				EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
+				EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31));
+			} else if (off == 16) {
+				EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
+				EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31));
+			} else if (off == 32 && dst_reg == src_reg) {
+				EMIT(PPC_RAW_SRAWI(dst_reg_h, src_reg, 31));
+			} else if (off == 32) {
+				EMIT(PPC_RAW_MR(dst_reg, src_reg));
+				EMIT(PPC_RAW_SRAWI(dst_reg_h, src_reg, 31));
+			} else if (dst_reg != src_reg) {
+				EMIT(PPC_RAW_MR(dst_reg, src_reg));
+				EMIT(PPC_RAW_MR(dst_reg_h, src_reg_h));
+			}
 			break;
 		case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
 			/* special mov32 for zext */
 			if (imm == 1)
 				EMIT(PPC_RAW_LI(dst_reg_h, 0));
+			else if (off == 8)
+				EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
+			else if (off == 16)
+				EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
 			else if (dst_reg != src_reg)
 				EMIT(PPC_RAW_MR(dst_reg, src_reg));
 			break;
@@ -750,6 +800,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		 * BPF_FROM_BE/LE
 		 */
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
+		case BPF_ALU64 | BPF_END | BPF_FROM_LE:
 			switch (imm) {
 			case 16:
 				/* Copy 16 bits to upper part */
@@ -784,6 +835,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				EMIT(PPC_RAW_MR(dst_reg_h, tmp_reg));
 				break;
 			}
+			if (BPF_CLASS(code) == BPF_ALU64 && imm != 64)
+				EMIT(PPC_RAW_LI(dst_reg_h, 0));
 			break;
 		case BPF_ALU | BPF_END | BPF_FROM_BE:
 			switch (imm) {
@@ -851,6 +904,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 
 			/* Get offset into TMP_REG */
 			EMIT(PPC_RAW_LI(tmp_reg, off));
+			/*
+			 * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync'
+			 * before and after the operation.
+			 *
+			 * This is a requirement in the Linux Kernel Memory Model.
+			 * See __cmpxchg_u32() in asm/cmpxchg.h as an example.
+			 */
+			if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP))
+				EMIT(PPC_RAW_SYNC());
 			tmp_idx = ctx->idx * 4;
 			/* load value from memory into r0 */
 			EMIT(PPC_RAW_LWARX(_R0, tmp_reg, dst_reg, 0));
@@ -904,6 +966,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 
 			/* For the BPF_FETCH variant, get old data into src_reg */
 			if (imm & BPF_FETCH) {
+				/* Emit 'sync' to enforce full ordering */
+				if (IS_ENABLED(CONFIG_SMP))
+					EMIT(PPC_RAW_SYNC());
 				EMIT(PPC_RAW_MR(ret_reg, ax_reg));
 				if (!fp->aux->verifier_zext)
 					EMIT(PPC_RAW_LI(ret_reg - 1, 0)); /* higher 32-bit */
@@ -917,11 +982,17 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		 * BPF_LDX
 		 */
 		case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src + off) */
+		case BPF_LDX | BPF_MEMSX | BPF_B:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+		case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
 		case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */
+		case BPF_LDX | BPF_MEMSX | BPF_H:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+		case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
 		case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */
+		case BPF_LDX | BPF_MEMSX | BPF_W:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+		case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
 		case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
 			/*
@@ -930,7 +1001,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			 * load only if addr is kernel address (see is_kernel_addr()), otherwise
 			 * set dst_reg=0 and move on.
 			 */
-			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+			if (BPF_MODE(code) == BPF_PROBE_MEM || BPF_MODE(code) == BPF_PROBE_MEMSX) {
 				PPC_LI32(_R0, TASK_SIZE - off);
 				EMIT(PPC_RAW_CMPLW(src_reg, _R0));
 				PPC_BCC_SHORT(COND_GT, (ctx->idx + 4) * 4);
@@ -940,7 +1011,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				 * !fp->aux->verifier_zext. Emit NOP otherwise.
 				 *
 				 * Note that "li reg_h,0" is emitted for BPF_B/H/W case,
-				 * if necessary. So, jump there insted of emitting an
+				 * if necessary. So, jump there instead of emitting an
 				 * additional "li reg_h,0" instruction.
 				 */
 				if (size == BPF_DW && !fp->aux->verifier_zext)
@@ -952,30 +1023,48 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				 * as there are two load instructions for dst_reg_h & dst_reg
 				 * respectively.
 				 */
-				if (size == BPF_DW)
+				if (size == BPF_DW ||
+				    (size == BPF_B && BPF_MODE(code) == BPF_PROBE_MEMSX))
 					PPC_JMP((ctx->idx + 3) * 4);
 				else
 					PPC_JMP((ctx->idx + 2) * 4);
 			}
 
-			switch (size) {
-			case BPF_B:
-				EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
-				break;
-			case BPF_H:
-				EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
-				break;
-			case BPF_W:
-				EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
-				break;
-			case BPF_DW:
-				EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
-				EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
-				break;
-			}
+			if (BPF_MODE(code) == BPF_MEMSX || BPF_MODE(code) == BPF_PROBE_MEMSX) {
+				switch (size) {
+				case BPF_B:
+					EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+					EMIT(PPC_RAW_EXTSB(dst_reg, dst_reg));
+					break;
+				case BPF_H:
+					EMIT(PPC_RAW_LHA(dst_reg, src_reg, off));
+					break;
+				case BPF_W:
+					EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+					break;
+				}
+				if (!fp->aux->verifier_zext)
+					EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31));
 
-			if (size != BPF_DW && !fp->aux->verifier_zext)
-				EMIT(PPC_RAW_LI(dst_reg_h, 0));
+			} else {
+				switch (size) {
+				case BPF_B:
+					EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+					break;
+				case BPF_H:
+					EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+					break;
+				case BPF_W:
+					EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+					break;
+				case BPF_DW:
+					EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off));
+					EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4));
+					break;
+				}
+				if (size != BPF_DW && !fp->aux->verifier_zext)
+					EMIT(PPC_RAW_LI(dst_reg_h, 0));
+			}
 
 			if (BPF_MODE(code) == BPF_PROBE_MEM) {
 				int insn_idx = ctx->idx - 1;
@@ -997,8 +1086,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 					jmp_off += 4;
 				}
 
-				ret = bpf_add_extable_entry(fp, image, pass, ctx, insn_idx,
-							    jmp_off, dst_reg);
+				ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, insn_idx,
+							    jmp_off, dst_reg, code);
 				if (ret)
 					return ret;
 			}
@@ -1009,13 +1098,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		 * 16 byte instruction that uses two 'struct bpf_insn'
 		 */
 		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
-			tmp_idx = ctx->idx;
 			PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm);
 			PPC_LI32(dst_reg, (u32)insn[i].imm);
-			/* padding to allow full 4 instructions for later patching */
-			if (!image)
-				for (j = ctx->idx - tmp_idx; j < 4; j++)
-					EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;
@@ -1053,7 +1137,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_5), _R1, 12));
 			}
 
-			ret = bpf_jit_emit_func_call_rel(image, ctx, func_addr);
+			ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
 			if (ret)
 				return ret;
 
@@ -1067,6 +1151,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		case BPF_JMP | BPF_JA:
 			PPC_JMP(addrs[i + 1 + off]);
 			break;
+		case BPF_JMP32 | BPF_JA:
+			PPC_JMP(addrs[i + 1 + imm]);
+			break;
 
 		case BPF_JMP | BPF_JGT | BPF_K:
 		case BPF_JMP | BPF_JGT | BPF_X:
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 0f8048f6dad6..1fe37128c876 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -25,18 +25,18 @@
  * with our redzone usage.
  *
  *		[	prev sp		] <-------------
- *		[   nv gpr save area	] 5*8		|
+ *		[   nv gpr save area	] 6*8		|
  *		[    tail_call_cnt	] 8		|
- *		[    local_tmp_var	] 16		|
+ *		[    local_tmp_var	] 24		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
  *		[     frame header	] 32/112	|
  * sp (r1) --->	[    stack pointer	] --------------
  */
 
 /* for gpr non volatile registers BPG_REG_6 to 10 */
-#define BPF_PPC_STACK_SAVE	(5*8)
+#define BPF_PPC_STACK_SAVE	(6*8)
 /* for bpf JIT code internal usage */
-#define BPF_PPC_STACK_LOCALS	24
+#define BPF_PPC_STACK_LOCALS	32
 /* stack frame excluding BPF stack, ensure this is quadword aligned */
 #define BPF_PPC_STACKFRAME	(STACK_FRAME_MIN_SIZE + \
 				 BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE)
@@ -44,6 +44,7 @@
 /* BPF register usage */
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
+#define ARENA_VM_START  (MAX_BPF_JIT_REG + 2)
 
 /* BPF to ppc register mappings */
 void bpf_jit_init_reg_mapping(struct codegen_context *ctx)
@@ -67,10 +68,12 @@ void bpf_jit_init_reg_mapping(struct codegen_context *ctx)
 	ctx->b2p[BPF_REG_AX] = _R12;
 	ctx->b2p[TMP_REG_1] = _R9;
 	ctx->b2p[TMP_REG_2] = _R10;
+	/* non volatile register for kern_vm_start address */
+	ctx->b2p[ARENA_VM_START] = _R26;
 }
 
-/* PPC NVR range -- update this if we ever use NVRs below r27 */
-#define BPF_PPC_NVR_MIN		_R27
+/* PPC NVR range -- update this if we ever use NVRs below r26 */
+#define BPF_PPC_NVR_MIN		_R26
 
 static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
 {
@@ -84,27 +87,27 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
 }
 
 /*
- * When not setting up our own stackframe, the redzone usage is:
+ * When not setting up our own stackframe, the redzone (288 bytes) usage is:
  *
  *		[	prev sp		] <-------------
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
- *		[   nv gpr save area	] 5*8
+ *		[   nv gpr save area	] 6*8
  *		[    tail_call_cnt	] 8
- *		[    local_tmp_var	] 16
- *		[   unused red zone	] 208 bytes protected
+ *		[    local_tmp_var	] 24
+ *		[   unused red zone	] 224
  */
 static int bpf_jit_stack_local(struct codegen_context *ctx)
 {
 	if (bpf_has_stack_frame(ctx))
 		return STACK_FRAME_MIN_SIZE + ctx->stack_size;
 	else
-		return -(BPF_PPC_STACK_SAVE + 24);
+		return -(BPF_PPC_STACK_SAVE + 32);
 }
 
 static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx)
 {
-	return bpf_jit_stack_local(ctx) + 16;
+	return bpf_jit_stack_local(ctx) + 24;
 }
 
 static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
@@ -126,6 +129,9 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 {
 	int i;
 
+	/* Instruction for trampoline attach */
+	EMIT(PPC_RAW_NOP());
+
 #ifndef CONFIG_PPC_KERNEL_PCREL
 	if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
 		EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc)));
@@ -167,10 +173,17 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 		if (bpf_is_seen_register(ctx, bpf_to_ppc(i)))
 			EMIT(PPC_RAW_STD(bpf_to_ppc(i), _R1, bpf_jit_stack_offsetof(ctx, bpf_to_ppc(i))));
 
+	if (ctx->arena_vm_start)
+		EMIT(PPC_RAW_STD(bpf_to_ppc(ARENA_VM_START), _R1,
+				 bpf_jit_stack_offsetof(ctx, bpf_to_ppc(ARENA_VM_START))));
+
 	/* Setup frame pointer to point to the bpf stack area */
 	if (bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_FP)))
 		EMIT(PPC_RAW_ADDI(bpf_to_ppc(BPF_REG_FP), _R1,
 				STACK_FRAME_MIN_SIZE + ctx->stack_size));
+
+	if (ctx->arena_vm_start)
+		PPC_LI64(bpf_to_ppc(ARENA_VM_START), ctx->arena_vm_start);
 }
 
 static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx)
@@ -182,6 +195,10 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 		if (bpf_is_seen_register(ctx, bpf_to_ppc(i)))
 			EMIT(PPC_RAW_LD(bpf_to_ppc(i), _R1, bpf_jit_stack_offsetof(ctx, bpf_to_ppc(i))));
 
+	if (ctx->arena_vm_start)
+		EMIT(PPC_RAW_LD(bpf_to_ppc(ARENA_VM_START), _R1,
+				bpf_jit_stack_offsetof(ctx, bpf_to_ppc(ARENA_VM_START))));
+
 	/* Tear down our stack frame */
 	if (bpf_has_stack_frame(ctx)) {
 		EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME + ctx->stack_size));
@@ -200,31 +217,66 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 	EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));
 
 	EMIT(PPC_RAW_BLR());
+
+	bpf_jit_build_fentry_stubs(image, ctx);
 }
 
-static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u64 func)
+int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
 {
 	unsigned long func_addr = func ? ppc_function_entry((void *)func) : 0;
 	long reladdr;
 
-	if (WARN_ON_ONCE(!core_kernel_text(func_addr)))
-		return -EINVAL;
-
-	if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
-		reladdr = func_addr - CTX_NIA(ctx);
-
-		if (reladdr >= (long)SZ_8G || reladdr < -(long)SZ_8G) {
-			pr_err("eBPF: address of %ps out of range of pcrel address.\n",
-				(void *)func);
-			return -ERANGE;
-		}
-		/* pla r12,addr */
-		EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(1) | IMM_H18(reladdr));
-		EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | IMM_L(reladdr));
+	/* bpf to bpf call, func is not known in the initial pass. Emit 5 nops as a placeholder */
+	if (!func) {
+		for (int i = 0; i < 5; i++)
+			EMIT(PPC_RAW_NOP());
+		/* elfv1 needs an additional instruction to load addr from descriptor */
+		if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1))
+			EMIT(PPC_RAW_NOP());
 		EMIT(PPC_RAW_MTCTR(_R12));
-		EMIT(PPC_RAW_BCTR());
+		EMIT(PPC_RAW_BCTRL());
+		return 0;
+	}
+
+#ifdef CONFIG_PPC_KERNEL_PCREL
+	reladdr = func_addr - local_paca->kernelbase;
 
+	/*
+	 * If fimage is NULL (the initial pass to find image size),
+	 * account for the maximum no. of instructions possible.
+	 */
+	if (!fimage) {
+		ctx->idx += 7;
+		return 0;
+	} else if (reladdr < (long)SZ_8G && reladdr >= -(long)SZ_8G) {
+		EMIT(PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernelbase)));
+		/* Align for subsequent prefix instruction */
+		if (!IS_ALIGNED((unsigned long)fimage + CTX_NIA(ctx), 8))
+			EMIT(PPC_RAW_NOP());
+		/* paddi r12,r12,addr */
+		EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(0) | IMM_H18(reladdr));
+		EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | ___PPC_RA(_R12) | IMM_L(reladdr));
 	} else {
+		unsigned long pc = (unsigned long)fimage + CTX_NIA(ctx);
+		bool alignment_needed = !IS_ALIGNED(pc, 8);
+
+		reladdr = func_addr - (alignment_needed ? pc + 4 :  pc);
+
+		if (reladdr < (long)SZ_8G && reladdr >= -(long)SZ_8G) {
+			if (alignment_needed)
+				EMIT(PPC_RAW_NOP());
+			/* pla r12,addr */
+			EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(1) | IMM_H18(reladdr));
+			EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | IMM_L(reladdr));
+		} else {
+			/* We can clobber r12 */
+			PPC_LI64(_R12, func);
+		}
+	}
+	EMIT(PPC_RAW_MTCTR(_R12));
+	EMIT(PPC_RAW_BCTRL());
+#else
+	if (core_kernel_text(func_addr)) {
 		reladdr = func_addr - kernel_toc_addr();
 		if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
 			pr_err("eBPF: address of %ps out of range of kernel_toc.\n", (void *)func);
@@ -235,40 +287,34 @@ static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u
 		EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr)));
 		EMIT(PPC_RAW_MTCTR(_R12));
 		EMIT(PPC_RAW_BCTRL());
+	} else {
+		if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1)) {
+			/* func points to the function descriptor */
+			PPC_LI64(bpf_to_ppc(TMP_REG_2), func);
+			/* Load actual entry point from function descriptor */
+			EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), 0));
+			/* ... and move it to CTR */
+			EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_1)));
+			/*
+			 * Load TOC from function descriptor at offset 8.
+			 * We can clobber r2 since we get called through a
+			 * function pointer (so caller will save/restore r2).
+			 */
+			if (is_module_text_address(func_addr))
+				EMIT(PPC_RAW_LD(_R2, bpf_to_ppc(TMP_REG_2), 8));
+		} else {
+			PPC_LI64(_R12, func);
+			EMIT(PPC_RAW_MTCTR(_R12));
+		}
+		EMIT(PPC_RAW_BCTRL());
+		/*
+		 * Load r2 with kernel TOC as kernel TOC is used if function address falls
+		 * within core kernel text.
+		 */
+		if (is_module_text_address(func_addr))
+			EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc)));
 	}
-
-	return 0;
-}
-
-int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func)
-{
-	unsigned int i, ctx_idx = ctx->idx;
-
-	if (WARN_ON_ONCE(func && is_module_text_address(func)))
-		return -EINVAL;
-
-	/* skip past descriptor if elf v1 */
-	func += FUNCTION_DESCR_SIZE;
-
-	/* Load function address into r12 */
-	PPC_LI64(_R12, func);
-
-	/* For bpf-to-bpf function calls, the callee's address is unknown
-	 * until the last extra pass. As seen above, we use PPC_LI64() to
-	 * load the callee's address, but this may optimize the number of
-	 * instructions required based on the nature of the address.
-	 *
-	 * Since we don't want the number of instructions emitted to increase,
-	 * we pad the optimized PPC_LI64() call with NOPs to guarantee that
-	 * we always have a five-instruction sequence, which is the maximum
-	 * that PPC_LI64() can emit.
-	 */
-	if (!image)
-		for (i = ctx->idx - ctx_idx; i < 5; i++)
-			EMIT(PPC_RAW_NOP());
-
-	EMIT(PPC_RAW_MTCTR(_R12));
-	EMIT(PPC_RAW_BCTRL());
+#endif
 
 	return 0;
 }
@@ -283,9 +329,9 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	 */
 	int b2p_bpf_array = bpf_to_ppc(BPF_REG_2);
 	int b2p_index = bpf_to_ppc(BPF_REG_3);
-	int bpf_tailcall_prologue_size = 8;
+	int bpf_tailcall_prologue_size = 12;
 
-	if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
+	if (!IS_ENABLED(CONFIG_PPC_KERNEL_PCREL) && IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
 		bpf_tailcall_prologue_size += 4; /* skip past the toc load */
 
 	/*
@@ -338,6 +384,23 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	return 0;
 }
 
+bool bpf_jit_bypass_spec_v1(void)
+{
+#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64)
+	return !(security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR));
+#else
+	return true;
+#endif
+}
+
+bool bpf_jit_bypass_spec_v4(void)
+{
+	return !(security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_STF_BARRIER) &&
+		 stf_barrier_type_get() != STF_BARRIER_NONE);
+}
+
 /*
  * We spill into the redzone always, even if the bpf program has its own stackframe.
  * Offsets hardcoded based on BPF_PPC_STACK_SAVE -- see bpf_jit_stack_local()
@@ -347,11 +410,11 @@ void bpf_stf_barrier(void);
 asm (
 "		.global bpf_stf_barrier		;"
 "	bpf_stf_barrier:			;"
-"		std	21,-64(1)		;"
-"		std	22,-56(1)		;"
+"		std	21,-80(1)		;"
+"		std	22,-72(1)		;"
 "		sync				;"
-"		ld	21,-64(1)		;"
-"		ld	22,-56(1)		;"
+"		ld	21,-80(1)		;"
+"		ld	22,-72(1)		;"
 "		ori	31,31,0			;"
 "		.rept 14			;"
 "		b	1f			;"
@@ -360,11 +423,212 @@ asm (
 "		blr				;"
 );
 
+static int bpf_jit_emit_atomic_ops(u32 *image, struct codegen_context *ctx,
+				   const struct bpf_insn *insn, u32 *jmp_off,
+				   u32 *tmp_idx, u32 *addrp)
+{
+	u32 tmp1_reg = bpf_to_ppc(TMP_REG_1);
+	u32 tmp2_reg = bpf_to_ppc(TMP_REG_2);
+	u32 size = BPF_SIZE(insn->code);
+	u32 src_reg = bpf_to_ppc(insn->src_reg);
+	u32 dst_reg = bpf_to_ppc(insn->dst_reg);
+	s32 imm = insn->imm;
+
+	u32 save_reg = tmp2_reg;
+	u32 ret_reg = src_reg;
+	u32 fixup_idx;
+
+	/* Get offset into TMP_REG_1 */
+	EMIT(PPC_RAW_LI(tmp1_reg, insn->off));
+       /*
+	* Enforce full ordering for operations with BPF_FETCH by emitting a 'sync'
+	* before and after the operation.
+	*
+	* This is a requirement in the Linux Kernel Memory Model.
+	* See __cmpxchg_u64() in asm/cmpxchg.h as an example.
+	*/
+	if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP))
+		EMIT(PPC_RAW_SYNC());
+
+	*tmp_idx = ctx->idx;
+
+	/* load value from memory into TMP_REG_2 */
+	if (size == BPF_DW)
+		EMIT(PPC_RAW_LDARX(tmp2_reg, tmp1_reg, dst_reg, 0));
+	else
+		EMIT(PPC_RAW_LWARX(tmp2_reg, tmp1_reg, dst_reg, 0));
+	/* Save old value in _R0 */
+	if (imm & BPF_FETCH)
+		EMIT(PPC_RAW_MR(_R0, tmp2_reg));
+
+	switch (imm) {
+	case BPF_ADD:
+	case BPF_ADD | BPF_FETCH:
+		EMIT(PPC_RAW_ADD(tmp2_reg, tmp2_reg, src_reg));
+		break;
+	case BPF_AND:
+	case BPF_AND | BPF_FETCH:
+		EMIT(PPC_RAW_AND(tmp2_reg, tmp2_reg, src_reg));
+		break;
+	case BPF_OR:
+	case BPF_OR | BPF_FETCH:
+		EMIT(PPC_RAW_OR(tmp2_reg, tmp2_reg, src_reg));
+		break;
+	case BPF_XOR:
+	case BPF_XOR | BPF_FETCH:
+		EMIT(PPC_RAW_XOR(tmp2_reg, tmp2_reg, src_reg));
+		break;
+	case BPF_CMPXCHG:
+	       /*
+		* Return old value in BPF_REG_0 for BPF_CMPXCHG &
+		* in src_reg for other cases.
+		*/
+		ret_reg = bpf_to_ppc(BPF_REG_0);
+
+		/* Compare with old value in BPF_R0 */
+		if (size == BPF_DW)
+			EMIT(PPC_RAW_CMPD(bpf_to_ppc(BPF_REG_0), tmp2_reg));
+		else
+			EMIT(PPC_RAW_CMPW(bpf_to_ppc(BPF_REG_0), tmp2_reg));
+		/* Don't set if different from old value */
+		PPC_BCC_SHORT(COND_NE, (ctx->idx + 3) * 4);
+		fallthrough;
+	case BPF_XCHG:
+		save_reg = src_reg;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* store new value */
+	if (size == BPF_DW)
+		EMIT(PPC_RAW_STDCX(save_reg, tmp1_reg, dst_reg));
+	else
+		EMIT(PPC_RAW_STWCX(save_reg, tmp1_reg, dst_reg));
+	/* we're done if this succeeded */
+	PPC_BCC_SHORT(COND_NE, *tmp_idx * 4);
+	fixup_idx = ctx->idx;
+
+	if (imm & BPF_FETCH) {
+		/* Emit 'sync' to enforce full ordering */
+		if (IS_ENABLED(CONFIG_SMP))
+			EMIT(PPC_RAW_SYNC());
+		EMIT(PPC_RAW_MR(ret_reg, _R0));
+		/*
+		 * Skip unnecessary zero-extension for 32-bit cmpxchg.
+		 * For context, see commit 39491867ace5.
+		 */
+		if (size != BPF_DW && imm == BPF_CMPXCHG &&
+		    insn_is_zext(insn + 1))
+			*addrp = ctx->idx * 4;
+	}
+
+	*jmp_off = (fixup_idx - *tmp_idx) * 4;
+
+	return 0;
+}
+
+static int bpf_jit_emit_probe_mem_store(struct codegen_context *ctx, u32 src_reg, s16 off,
+					u32 code, u32 *image)
+{
+	u32 tmp1_reg = bpf_to_ppc(TMP_REG_1);
+	u32 tmp2_reg = bpf_to_ppc(TMP_REG_2);
+
+	switch (BPF_SIZE(code)) {
+	case BPF_B:
+		EMIT(PPC_RAW_STB(src_reg, tmp1_reg, off));
+		break;
+	case BPF_H:
+		EMIT(PPC_RAW_STH(src_reg, tmp1_reg, off));
+		break;
+	case BPF_W:
+		EMIT(PPC_RAW_STW(src_reg, tmp1_reg, off));
+		break;
+	case BPF_DW:
+		if (off % 4) {
+			EMIT(PPC_RAW_LI(tmp2_reg, off));
+			EMIT(PPC_RAW_STDX(src_reg, tmp1_reg, tmp2_reg));
+		} else {
+			EMIT(PPC_RAW_STD(src_reg, tmp1_reg, off));
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int emit_atomic_ld_st(const struct bpf_insn insn, struct codegen_context *ctx, u32 *image)
+{
+	u32 code = insn.code;
+	u32 dst_reg = bpf_to_ppc(insn.dst_reg);
+	u32 src_reg = bpf_to_ppc(insn.src_reg);
+	u32 size = BPF_SIZE(code);
+	u32 tmp1_reg = bpf_to_ppc(TMP_REG_1);
+	u32 tmp2_reg = bpf_to_ppc(TMP_REG_2);
+	s16 off = insn.off;
+	s32 imm = insn.imm;
+
+	switch (imm) {
+	case BPF_LOAD_ACQ:
+		switch (size) {
+		case BPF_B:
+			EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+			break;
+		case BPF_H:
+			EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+			break;
+		case BPF_W:
+			EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+			break;
+		case BPF_DW:
+			if (off % 4) {
+				EMIT(PPC_RAW_LI(tmp1_reg, off));
+				EMIT(PPC_RAW_LDX(dst_reg, src_reg, tmp1_reg));
+			} else {
+				EMIT(PPC_RAW_LD(dst_reg, src_reg, off));
+			}
+			break;
+		}
+		EMIT(PPC_RAW_LWSYNC());
+		break;
+	case BPF_STORE_REL:
+		EMIT(PPC_RAW_LWSYNC());
+		switch (size) {
+		case BPF_B:
+			EMIT(PPC_RAW_STB(src_reg, dst_reg, off));
+			break;
+		case BPF_H:
+			EMIT(PPC_RAW_STH(src_reg, dst_reg, off));
+			break;
+		case BPF_W:
+			EMIT(PPC_RAW_STW(src_reg, dst_reg, off));
+			break;
+		case BPF_DW:
+			if (off % 4) {
+				EMIT(PPC_RAW_LI(tmp2_reg, off));
+				EMIT(PPC_RAW_STDX(src_reg, dst_reg, tmp2_reg));
+			} else {
+				EMIT(PPC_RAW_STD(src_reg, dst_reg, off));
+			}
+			break;
+		}
+		break;
+	default:
+		pr_err_ratelimited("unexpected atomic load/store op code %02x\n",
+				   imm);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* Assemble the body code between the prologue & epilogue */
-int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
+int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx,
 		       u32 *addrs, int pass, bool extra_pass)
 {
 	enum stf_barrier_type stf_barrier = stf_barrier_type_get();
+	bool sync_emitted, ori31_emitted;
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
 	int i, ret;
@@ -379,7 +643,6 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		u32 size = BPF_SIZE(code);
 		u32 tmp1_reg = bpf_to_ppc(TMP_REG_1);
 		u32 tmp2_reg = bpf_to_ppc(TMP_REG_2);
-		u32 save_reg, ret_reg;
 		s16 off = insn[i].off;
 		s32 imm = insn[i].imm;
 		bool func_addr_fixed;
@@ -387,7 +650,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		u64 imm64;
 		u32 true_cond;
 		u32 tmp_idx;
-		int j;
+		u32 jmp_off;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -467,20 +730,33 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
 		case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
 			if (BPF_OP(code) == BPF_MOD) {
-				EMIT(PPC_RAW_DIVWU(tmp1_reg, dst_reg, src_reg));
+				if (off)
+					EMIT(PPC_RAW_DIVW(tmp1_reg, dst_reg, src_reg));
+				else
+					EMIT(PPC_RAW_DIVWU(tmp1_reg, dst_reg, src_reg));
+
 				EMIT(PPC_RAW_MULW(tmp1_reg, src_reg, tmp1_reg));
 				EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg));
 			} else
-				EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, src_reg));
+				if (off)
+					EMIT(PPC_RAW_DIVW(dst_reg, dst_reg, src_reg));
+				else
+					EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, src_reg));
 			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
 		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
 			if (BPF_OP(code) == BPF_MOD) {
-				EMIT(PPC_RAW_DIVDU(tmp1_reg, dst_reg, src_reg));
+				if (off)
+					EMIT(PPC_RAW_DIVD(tmp1_reg, dst_reg, src_reg));
+				else
+					EMIT(PPC_RAW_DIVDU(tmp1_reg, dst_reg, src_reg));
 				EMIT(PPC_RAW_MULD(tmp1_reg, src_reg, tmp1_reg));
 				EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg));
 			} else
-				EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, src_reg));
+				if (off)
+					EMIT(PPC_RAW_DIVD(dst_reg, dst_reg, src_reg));
+				else
+					EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, src_reg));
 			break;
 		case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
 		case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */
@@ -501,19 +777,31 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			switch (BPF_CLASS(code)) {
 			case BPF_ALU:
 				if (BPF_OP(code) == BPF_MOD) {
-					EMIT(PPC_RAW_DIVWU(tmp2_reg, dst_reg, tmp1_reg));
+					if (off)
+						EMIT(PPC_RAW_DIVW(tmp2_reg, dst_reg, tmp1_reg));
+					else
+						EMIT(PPC_RAW_DIVWU(tmp2_reg, dst_reg, tmp1_reg));
 					EMIT(PPC_RAW_MULW(tmp1_reg, tmp1_reg, tmp2_reg));
 					EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg));
 				} else
-					EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, tmp1_reg));
+					if (off)
+						EMIT(PPC_RAW_DIVW(dst_reg, dst_reg, tmp1_reg));
+					else
+						EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, tmp1_reg));
 				break;
 			case BPF_ALU64:
 				if (BPF_OP(code) == BPF_MOD) {
-					EMIT(PPC_RAW_DIVDU(tmp2_reg, dst_reg, tmp1_reg));
+					if (off)
+						EMIT(PPC_RAW_DIVD(tmp2_reg, dst_reg, tmp1_reg));
+					else
+						EMIT(PPC_RAW_DIVDU(tmp2_reg, dst_reg, tmp1_reg));
 					EMIT(PPC_RAW_MULD(tmp1_reg, tmp1_reg, tmp2_reg));
 					EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg));
 				} else
-					EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, tmp1_reg));
+					if (off)
+						EMIT(PPC_RAW_DIVD(dst_reg, dst_reg, tmp1_reg));
+					else
+						EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, tmp1_reg));
 				break;
 			}
 			goto bpf_alu32_trunc;
@@ -629,12 +917,28 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		 */
 		case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
 		case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
+
+			if (insn_is_cast_user(&insn[i])) {
+				EMIT(PPC_RAW_RLDICL_DOT(tmp1_reg, src_reg, 0, 32));
+				PPC_LI64(dst_reg, (ctx->user_vm_start & 0xffffffff00000000UL));
+				PPC_BCC_SHORT(COND_EQ, (ctx->idx + 2) * 4);
+				EMIT(PPC_RAW_OR(tmp1_reg, dst_reg, tmp1_reg));
+				EMIT(PPC_RAW_MR(dst_reg, tmp1_reg));
+				break;
+			}
+
 			if (imm == 1) {
 				/* special mov32 for zext */
 				EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31));
 				break;
-			}
-			EMIT(PPC_RAW_MR(dst_reg, src_reg));
+			} else if (off == 8) {
+				EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
+			} else if (off == 16) {
+				EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
+			} else if (off == 32) {
+				EMIT(PPC_RAW_EXTSW(dst_reg, src_reg));
+			} else if (dst_reg != src_reg)
+				EMIT(PPC_RAW_MR(dst_reg, src_reg));
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
 		case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */
@@ -656,11 +960,12 @@ bpf_alu32_trunc:
 		 */
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
 		case BPF_ALU | BPF_END | BPF_FROM_BE:
+		case BPF_ALU64 | BPF_END | BPF_FROM_LE:
 #ifdef __BIG_ENDIAN__
 			if (BPF_SRC(code) == BPF_FROM_BE)
 				goto emit_clear;
 #else /* !__BIG_ENDIAN__ */
-			if (BPF_SRC(code) == BPF_FROM_LE)
+			if (BPF_CLASS(code) == BPF_ALU && BPF_SRC(code) == BPF_FROM_LE)
 				goto emit_clear;
 #endif
 			switch (imm) {
@@ -726,30 +1031,51 @@ emit_clear:
 
 		/*
 		 * BPF_ST NOSPEC (speculation barrier)
+		 *
+		 * The following must act as a barrier against both Spectre v1
+		 * and v4 if we requested both mitigations. Therefore, also emit
+		 * 'isync; sync' on E500 or 'ori31' on BOOK3S_64 in addition to
+		 * the insns needed for a Spectre v4 barrier.
+		 *
+		 * If we requested only !bypass_spec_v1 OR only !bypass_spec_v4,
+		 * we can skip the respective other barrier type as an
+		 * optimization.
 		 */
 		case BPF_ST | BPF_NOSPEC:
-			if (!security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) ||
-					!security_ftr_enabled(SEC_FTR_STF_BARRIER))
-				break;
-
-			switch (stf_barrier) {
-			case STF_BARRIER_EIEIO:
-				EMIT(PPC_RAW_EIEIO() | 0x02000000);
-				break;
-			case STF_BARRIER_SYNC_ORI:
+			sync_emitted = false;
+			ori31_emitted = false;
+			if (IS_ENABLED(CONFIG_PPC_E500) &&
+			    !bpf_jit_bypass_spec_v1()) {
+				EMIT(PPC_RAW_ISYNC());
 				EMIT(PPC_RAW_SYNC());
-				EMIT(PPC_RAW_LD(tmp1_reg, _R13, 0));
-				EMIT(PPC_RAW_ORI(_R31, _R31, 0));
-				break;
-			case STF_BARRIER_FALLBACK:
-				ctx->seen |= SEEN_FUNC;
-				PPC_LI64(_R12, dereference_kernel_function_descriptor(bpf_stf_barrier));
-				EMIT(PPC_RAW_MTCTR(_R12));
-				EMIT(PPC_RAW_BCTRL());
-				break;
-			case STF_BARRIER_NONE:
-				break;
+				sync_emitted = true;
+			}
+			if (!bpf_jit_bypass_spec_v4()) {
+				switch (stf_barrier) {
+				case STF_BARRIER_EIEIO:
+					EMIT(PPC_RAW_EIEIO() | 0x02000000);
+					break;
+				case STF_BARRIER_SYNC_ORI:
+					if (!sync_emitted)
+						EMIT(PPC_RAW_SYNC());
+					EMIT(PPC_RAW_LD(tmp1_reg, _R13, 0));
+					EMIT(PPC_RAW_ORI(_R31, _R31, 0));
+					ori31_emitted = true;
+					break;
+				case STF_BARRIER_FALLBACK:
+					ctx->seen |= SEEN_FUNC;
+					PPC_LI64(_R12, dereference_kernel_function_descriptor(bpf_stf_barrier));
+					EMIT(PPC_RAW_MTCTR(_R12));
+					EMIT(PPC_RAW_BCTRL());
+					break;
+				case STF_BARRIER_NONE:
+					break;
+				}
 			}
+			if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) &&
+			    !bpf_jit_bypass_spec_v1() &&
+			    !ori31_emitted)
+				EMIT(PPC_RAW_ORI(_R31, _R31, 0));
 			break;
 
 		/*
@@ -793,86 +1119,107 @@ emit_clear:
 			}
 			break;
 
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_B:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_H:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_W:
+		case BPF_STX | BPF_PROBE_MEM32 | BPF_DW:
+
+			EMIT(PPC_RAW_ADD(tmp1_reg, dst_reg, bpf_to_ppc(ARENA_VM_START)));
+
+			ret = bpf_jit_emit_probe_mem_store(ctx, src_reg, off, code, image);
+			if (ret)
+				return ret;
+
+			ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
+						    ctx->idx - 1, 4, -1, code);
+			if (ret)
+				return ret;
+
+			break;
+
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_B:
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_H:
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
+		case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
+
+			EMIT(PPC_RAW_ADD(tmp1_reg, dst_reg, bpf_to_ppc(ARENA_VM_START)));
+
+			if (BPF_SIZE(code) == BPF_W || BPF_SIZE(code) == BPF_DW) {
+				PPC_LI32(tmp2_reg, imm);
+				src_reg = tmp2_reg;
+			} else {
+				EMIT(PPC_RAW_LI(tmp2_reg, imm));
+				src_reg = tmp2_reg;
+			}
+
+			ret = bpf_jit_emit_probe_mem_store(ctx, src_reg, off, code, image);
+			if (ret)
+				return ret;
+
+			ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
+						    ctx->idx - 1, 4, -1, code);
+			if (ret)
+				return ret;
+
+			break;
+
+		/*
+		 * BPF_STX PROBE_ATOMIC (arena atomic ops)
+		 */
+		case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
+		case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
+			EMIT(PPC_RAW_ADD(dst_reg, dst_reg, bpf_to_ppc(ARENA_VM_START)));
+			ret = bpf_jit_emit_atomic_ops(image, ctx, &insn[i],
+						      &jmp_off, &tmp_idx, &addrs[i + 1]);
+			if (ret) {
+				if (ret == -EOPNOTSUPP) {
+					pr_err_ratelimited(
+						"eBPF filter atomic op code %02x (@%d) unsupported\n",
+						code, i);
+				}
+				return ret;
+			}
+			/* LDARX/LWARX should land here on exception. */
+			ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
+						    tmp_idx, jmp_off, dst_reg, code);
+			if (ret)
+				return ret;
+
+			/* Retrieve the dst_reg */
+			EMIT(PPC_RAW_SUB(dst_reg, dst_reg, bpf_to_ppc(ARENA_VM_START)));
+			break;
+
 		/*
 		 * BPF_STX ATOMIC (atomic ops)
 		 */
+		case BPF_STX | BPF_ATOMIC | BPF_B:
+		case BPF_STX | BPF_ATOMIC | BPF_H:
 		case BPF_STX | BPF_ATOMIC | BPF_W:
 		case BPF_STX | BPF_ATOMIC | BPF_DW:
-			save_reg = tmp2_reg;
-			ret_reg = src_reg;
-
-			/* Get offset into TMP_REG_1 */
-			EMIT(PPC_RAW_LI(tmp1_reg, off));
-			tmp_idx = ctx->idx * 4;
-			/* load value from memory into TMP_REG_2 */
-			if (size == BPF_DW)
-				EMIT(PPC_RAW_LDARX(tmp2_reg, tmp1_reg, dst_reg, 0));
-			else
-				EMIT(PPC_RAW_LWARX(tmp2_reg, tmp1_reg, dst_reg, 0));
-
-			/* Save old value in _R0 */
-			if (imm & BPF_FETCH)
-				EMIT(PPC_RAW_MR(_R0, tmp2_reg));
-
-			switch (imm) {
-			case BPF_ADD:
-			case BPF_ADD | BPF_FETCH:
-				EMIT(PPC_RAW_ADD(tmp2_reg, tmp2_reg, src_reg));
-				break;
-			case BPF_AND:
-			case BPF_AND | BPF_FETCH:
-				EMIT(PPC_RAW_AND(tmp2_reg, tmp2_reg, src_reg));
-				break;
-			case BPF_OR:
-			case BPF_OR | BPF_FETCH:
-				EMIT(PPC_RAW_OR(tmp2_reg, tmp2_reg, src_reg));
-				break;
-			case BPF_XOR:
-			case BPF_XOR | BPF_FETCH:
-				EMIT(PPC_RAW_XOR(tmp2_reg, tmp2_reg, src_reg));
-				break;
-			case BPF_CMPXCHG:
-				/*
-				 * Return old value in BPF_REG_0 for BPF_CMPXCHG &
-				 * in src_reg for other cases.
-				 */
-				ret_reg = bpf_to_ppc(BPF_REG_0);
+			if (bpf_atomic_is_load_store(&insn[i])) {
+				ret = emit_atomic_ld_st(insn[i], ctx, image);
+				if (ret)
+					return ret;
 
-				/* Compare with old value in BPF_R0 */
-				if (size == BPF_DW)
-					EMIT(PPC_RAW_CMPD(bpf_to_ppc(BPF_REG_0), tmp2_reg));
-				else
-					EMIT(PPC_RAW_CMPW(bpf_to_ppc(BPF_REG_0), tmp2_reg));
-				/* Don't set if different from old value */
-				PPC_BCC_SHORT(COND_NE, (ctx->idx + 3) * 4);
-				fallthrough;
-			case BPF_XCHG:
-				save_reg = src_reg;
+				if (size != BPF_DW && insn_is_zext(&insn[i + 1]))
+					addrs[++i] = ctx->idx * 4;
 				break;
-			default:
+			} else if (size == BPF_B || size == BPF_H) {
 				pr_err_ratelimited(
 					"eBPF filter atomic op code %02x (@%d) unsupported\n",
 					code, i);
 				return -EOPNOTSUPP;
 			}
 
-			/* store new value */
-			if (size == BPF_DW)
-				EMIT(PPC_RAW_STDCX(save_reg, tmp1_reg, dst_reg));
-			else
-				EMIT(PPC_RAW_STWCX(save_reg, tmp1_reg, dst_reg));
-			/* we're done if this succeeded */
-			PPC_BCC_SHORT(COND_NE, tmp_idx);
-
-			if (imm & BPF_FETCH) {
-				EMIT(PPC_RAW_MR(ret_reg, _R0));
-				/*
-				 * Skip unnecessary zero-extension for 32-bit cmpxchg.
-				 * For context, see commit 39491867ace5.
-				 */
-				if (size != BPF_DW && imm == BPF_CMPXCHG &&
-				    insn_is_zext(&insn[i + 1]))
-					addrs[++i] = ctx->idx * 4;
+			ret = bpf_jit_emit_atomic_ops(image, ctx, &insn[i],
+						      &jmp_off, &tmp_idx, &addrs[i + 1]);
+			if (ret) {
+				if (ret == -EOPNOTSUPP) {
+					pr_err_ratelimited(
+						"eBPF filter atomic op code %02x (@%d) unsupported\n",
+						code, i);
+				}
+				return ret;
 			}
 			break;
 
@@ -881,13 +1228,19 @@ emit_clear:
 		 */
 		/* dst = *(u8 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
+		case BPF_LDX | BPF_MEMSX | BPF_B:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+		case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
 		/* dst = *(u16 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_H:
+		case BPF_LDX | BPF_MEMSX | BPF_H:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+		case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
 		/* dst = *(u32 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_W:
+		case BPF_LDX | BPF_MEMSX | BPF_W:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+		case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
@@ -897,7 +1250,7 @@ emit_clear:
 			 * load only if addr is kernel address (see is_kernel_addr()), otherwise
 			 * set dst_reg=0 and move on.
 			 */
-			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+			if (BPF_MODE(code) == BPF_PROBE_MEM || BPF_MODE(code) == BPF_PROBE_MEMSX) {
 				EMIT(PPC_RAW_ADDI(tmp1_reg, src_reg, off));
 				if (IS_ENABLED(CONFIG_PPC_BOOK3E_64))
 					PPC_LI64(tmp2_reg, 0x8000000000000000ul);
@@ -910,28 +1263,85 @@ emit_clear:
 				 * Check if 'off' is word aligned for BPF_DW, because
 				 * we might generate two instructions.
 				 */
-				if (BPF_SIZE(code) == BPF_DW && (off & 3))
+				if ((BPF_SIZE(code) == BPF_DW && (off & 3)) ||
+				    (BPF_SIZE(code) == BPF_B &&
+				     BPF_MODE(code) == BPF_PROBE_MEMSX) ||
+				    (BPF_SIZE(code) == BPF_B && BPF_MODE(code) == BPF_MEMSX))
 					PPC_JMP((ctx->idx + 3) * 4);
 				else
 					PPC_JMP((ctx->idx + 2) * 4);
 			}
 
+			if (BPF_MODE(code) == BPF_MEMSX || BPF_MODE(code) == BPF_PROBE_MEMSX) {
+				switch (size) {
+				case BPF_B:
+					EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+					EMIT(PPC_RAW_EXTSB(dst_reg, dst_reg));
+					break;
+				case BPF_H:
+					EMIT(PPC_RAW_LHA(dst_reg, src_reg, off));
+					break;
+				case BPF_W:
+					EMIT(PPC_RAW_LWA(dst_reg, src_reg, off));
+					break;
+				}
+			} else {
+				switch (size) {
+				case BPF_B:
+					EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+					break;
+				case BPF_H:
+					EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+					break;
+				case BPF_W:
+					EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+					break;
+				case BPF_DW:
+					if (off % 4) {
+						EMIT(PPC_RAW_LI(tmp1_reg, off));
+						EMIT(PPC_RAW_LDX(dst_reg, src_reg, tmp1_reg));
+					} else {
+						EMIT(PPC_RAW_LD(dst_reg, src_reg, off));
+					}
+					break;
+				}
+			}
+
+			if (size != BPF_DW && insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
+
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
+							    ctx->idx - 1, 4, dst_reg, code);
+				if (ret)
+					return ret;
+			}
+			break;
+
+		/* dst = *(u64 *)(ul) (src + ARENA_VM_START + off) */
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_B:
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_H:
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_W:
+		case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW:
+
+			EMIT(PPC_RAW_ADD(tmp1_reg, src_reg, bpf_to_ppc(ARENA_VM_START)));
+
 			switch (size) {
 			case BPF_B:
-				EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+				EMIT(PPC_RAW_LBZ(dst_reg, tmp1_reg, off));
 				break;
 			case BPF_H:
-				EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+				EMIT(PPC_RAW_LHZ(dst_reg, tmp1_reg, off));
 				break;
 			case BPF_W:
-				EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+				EMIT(PPC_RAW_LWZ(dst_reg, tmp1_reg, off));
 				break;
 			case BPF_DW:
 				if (off % 4) {
-					EMIT(PPC_RAW_LI(tmp1_reg, off));
-					EMIT(PPC_RAW_LDX(dst_reg, src_reg, tmp1_reg));
+					EMIT(PPC_RAW_LI(tmp2_reg, off));
+					EMIT(PPC_RAW_LDX(dst_reg, tmp1_reg, tmp2_reg));
 				} else {
-					EMIT(PPC_RAW_LD(dst_reg, src_reg, off));
+					EMIT(PPC_RAW_LD(dst_reg, tmp1_reg, off));
 				}
 				break;
 			}
@@ -939,12 +1349,10 @@ emit_clear:
 			if (size != BPF_DW && insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
 
-			if (BPF_MODE(code) == BPF_PROBE_MEM) {
-				ret = bpf_add_extable_entry(fp, image, pass, ctx, ctx->idx - 1,
-							    4, dst_reg);
-				if (ret)
-					return ret;
-			}
+			ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
+						    ctx->idx - 1, 4, dst_reg, code);
+			if (ret)
+				return ret;
 			break;
 
 		/*
@@ -954,12 +1362,7 @@ emit_clear:
 		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
 			imm64 = ((u64)(u32) insn[i].imm) |
 				    (((u64)(u32) insn[i+1].imm) << 32);
-			tmp_idx = ctx->idx;
 			PPC_LI64(dst_reg, imm64);
-			/* padding to allow full 5 instructions for later patching */
-			if (!image)
-				for (j = ctx->idx - tmp_idx; j < 5; j++)
-					EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;
@@ -992,11 +1395,7 @@ emit_clear:
 			if (ret < 0)
 				return ret;
 
-			if (func_addr_fixed)
-				ret = bpf_jit_emit_func_call_hlp(image, ctx, func_addr);
-			else
-				ret = bpf_jit_emit_func_call_rel(image, ctx, func_addr);
-
+			ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
 			if (ret)
 				return ret;
 
@@ -1010,6 +1409,9 @@ emit_clear:
 		case BPF_JMP | BPF_JA:
 			PPC_JMP(addrs[i + 1 + off]);
 			break;
+		case BPF_JMP32 | BPF_JA:
+			PPC_JMP(addrs[i + 1 + imm]);
+			break;
 
 		case BPF_JMP | BPF_JGT | BPF_K:
 		case BPF_JMP | BPF_JGT | BPF_X:
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c
index 308a2e40d7be..1d2972229e3a 100644
--- a/arch/powerpc/perf/8xx-pmu.c
+++ b/arch/powerpc/perf/8xx-pmu.c
@@ -14,7 +14,7 @@
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/ptrace.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/inst.h>
 
 #define PERF_8xx_ID_CPU_CYCLES		1
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 4f53d0b97539..78dd7e25219e 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -14,7 +14,11 @@ obj-$(CONFIG_PPC_POWERNV)	+= imc-pmu.o
 obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
 obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o
 
-obj-$(CONFIG_HV_PERF_CTRS) += hv-24x7.o hv-gpci.o hv-common.o
+obj-$(CONFIG_HV_PERF_CTRS) += hv-24x7.o hv-gpci.o hv-common.o vpa-dtl.o
+
+obj-$(CONFIG_VPA_PMU) += vpa-pmu.o
+
+obj-$(CONFIG_KVM_BOOK3S_HV_PMU) += kvm-hv-pmu.o
 
 obj-$(CONFIG_PPC_8xx) += 8xx-pmu.o
 
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 6b4434dd0ff3..26aa26482c9a 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -51,7 +51,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, perf_instruction_pointer(regs));
+	perf_callchain_store(entry, perf_arch_instruction_pointer(regs));
 
 	if (!validate_sp(sp, current))
 		return;
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index ea8cfe3806dc..ddcc2d8aa64a 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -139,7 +139,7 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 	long level = 0;
 	unsigned int __user *fp, *uregs;
 
-	next_ip = perf_instruction_pointer(regs);
+	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 488e8a21a11e..115d1c105e8a 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -74,7 +74,7 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 	struct signal_frame_64 __user *sigframe;
 	unsigned long __user *fp, *uregs;
 
-	next_ip = perf_instruction_pointer(regs);
+	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 8c1f7def596e..8b0081441f85 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -16,7 +16,7 @@
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/ptrace.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/hw_irq.h>
 #include <asm/interrupt.h>
 
@@ -132,7 +132,10 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
 
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
-static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) {}
+static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
+				 struct task_struct *task, bool sched_in)
+{
+}
 static inline void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
@@ -256,7 +259,7 @@ static bool regs_sipr(struct pt_regs *regs)
 
 static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 {
-	if (regs->msr & MSR_PR)
+	if (user_mode(regs))
 		return PERF_RECORD_MISC_USER;
 	if ((regs->msr & MSR_HV) && freeze_events_kernel != MMCR0_FCHV)
 		return PERF_RECORD_MISC_HYPERVISOR;
@@ -266,51 +269,44 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
 	bool use_siar = regs_use_siar(regs);
-	unsigned long mmcra = regs->dsisr;
-	int marked = mmcra & MMCRA_SAMPLE_ENABLE;
+	unsigned long siar;
+	unsigned long addr;
 
 	if (!use_siar)
 		return perf_flags_from_msr(regs);
 
 	/*
-	 * Check the address in SIAR to identify the
-	 * privilege levels since the SIER[MSR_HV, MSR_PR]
-	 * bits are not set for marked events in power10
-	 * DD1.
-	 */
-	if (marked && (ppmu->flags & PPMU_P10_DD1)) {
-		unsigned long siar = mfspr(SPRN_SIAR);
-		if (siar) {
-			if (is_kernel_addr(siar))
-				return PERF_RECORD_MISC_KERNEL;
-			return PERF_RECORD_MISC_USER;
-		} else {
-			if (is_kernel_addr(regs->nip))
-				return PERF_RECORD_MISC_KERNEL;
-			return PERF_RECORD_MISC_USER;
-		}
-	}
-
-	/*
 	 * If we don't have flags in MMCRA, rather than using
 	 * the MSR, we intuit the flags from the address in
 	 * SIAR which should give slightly more reliable
 	 * results
 	 */
 	if (ppmu->flags & PPMU_NO_SIPR) {
-		unsigned long siar = mfspr(SPRN_SIAR);
+		siar = mfspr(SPRN_SIAR);
 		if (is_kernel_addr(siar))
 			return PERF_RECORD_MISC_KERNEL;
 		return PERF_RECORD_MISC_USER;
 	}
 
 	/* PR has priority over HV, so order below is important */
-	if (regs_sipr(regs))
-		return PERF_RECORD_MISC_USER;
-
-	if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV))
+	if (regs_sipr(regs)) {
+		if (!(ppmu->flags & PPMU_P10))
+			return PERF_RECORD_MISC_USER;
+	} else if (regs_sihv(regs) && (freeze_events_kernel != MMCR0_FCHV))
 		return PERF_RECORD_MISC_HYPERVISOR;
 
+	/*
+	 * Check the address in SIAR to identify the
+	 * privilege levels since the SIER[MSR_HV, MSR_PR]
+	 * bits are not set correctly in power10 sometimes
+	 */
+	if (ppmu->flags & PPMU_P10) {
+		siar = mfspr(SPRN_SIAR);
+		addr = siar ? siar : regs->nip;
+		if (!is_kernel_addr(addr))
+			return PERF_RECORD_MISC_USER;
+	}
+
 	return PERF_RECORD_MISC_KERNEL;
 }
 
@@ -451,7 +447,8 @@ static void power_pmu_bhrb_disable(struct perf_event *event)
 /* Called from ctxsw to prevent one process's branch entries to
  * mingle with the other process's entries during context switch.
  */
-static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
+				 struct task_struct *task, bool sched_in)
 {
 	if (!ppmu->bhrb_nr)
 		return;
@@ -1371,8 +1368,7 @@ static void power_pmu_disable(struct pmu *pmu)
 		/*
 		 * Disable instruction sampling if it was enabled
 		 */
-		if (cpuhw->mmcr.mmcra & MMCRA_SAMPLE_ENABLE)
-			val &= ~MMCRA_SAMPLE_ENABLE;
+		val &= ~MMCRA_SAMPLE_ENABLE;
 
 		/* Disable BHRB via mmcra (BHRBRD) for p10 */
 		if (ppmu->flags & PPMU_ARCH_31)
@@ -1383,7 +1379,7 @@ static void power_pmu_disable(struct pmu *pmu)
 		 * instruction sampling or BHRB.
 		 */
 		if (val != mmcra) {
-			mtspr(SPRN_MMCRA, mmcra);
+			mtspr(SPRN_MMCRA, val);
 			mb();
 			isync();
 		}
@@ -2230,6 +2226,10 @@ static struct pmu power_pmu = {
 #define PERF_SAMPLE_ADDR_TYPE  (PERF_SAMPLE_ADDR |		\
 				PERF_SAMPLE_PHYS_ADDR |		\
 				PERF_SAMPLE_DATA_PAGE_SIZE)
+
+#define SIER_TYPE_SHIFT	15
+#define SIER_TYPE_MASK	(0x7ull << SIER_TYPE_SHIFT)
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -2239,6 +2239,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			       struct pt_regs *regs)
 {
 	u64 period = event->hw.sample_period;
+	const u64 last_period = event->hw.last_period;
 	s64 prev, delta, left;
 	int record = 0;
 
@@ -2299,12 +2300,28 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		record = 0;
 
 	/*
+	 * SIER[46-48] presents instruction type of the sampled instruction.
+	 * In ISA v3.0 and before values "0" and "7" are considered reserved.
+	 * In ISA v3.1, value "7" has been used to indicate "larx/stcx".
+	 * Drop the sample if "type" has reserved values for this field with a
+	 * ISA version check.
+	 */
+	if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
+			ppmu->get_mem_data_src) {
+		val = (regs->dar & SIER_TYPE_MASK) >> SIER_TYPE_SHIFT;
+		if (val == 0 || (val == 7 && !cpu_has_feature(CPU_FTR_ARCH_31))) {
+			record = 0;
+			atomic64_inc(&event->lost_samples);
+		}
+	}
+
+	/*
 	 * Finally record data if requested.
 	 */
 	if (record) {
 		struct perf_sample_data data;
 
-		perf_sample_data_init(&data, ~0ULL, event->hw.last_period);
+		perf_sample_data_init(&data, ~0ULL, last_period);
 
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR_TYPE)
 			perf_get_data_addr(event, regs, &data.addr);
@@ -2313,7 +2330,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			struct cpu_hw_events *cpuhw;
 			cpuhw = this_cpu_ptr(&cpu_hw_events);
 			power_pmu_bhrb_read(event, cpuhw);
-			perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack);
+			perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack, NULL);
 		}
 
 		if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
@@ -2327,12 +2344,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			ppmu->get_mem_weight(&data.weight.full, event->attr.sample_type);
 			data.sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
 		}
-		if (perf_event_overflow(event, &data, regs))
-			power_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	} else if (period) {
 		/* Account for interrupt in case of invalid SIAR */
-		if (perf_event_account_interrupt(event))
-			power_pmu_stop(event, 0);
+		perf_event_account_interrupt(event);
 	}
 }
 
@@ -2340,7 +2355,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
  * Called from generic code to get the misc flags (i.e. processor mode)
  * for an event_id.
  */
-unsigned long perf_misc_flags(struct pt_regs *regs)
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
 {
 	u32 flags = perf_get_misc_flags(regs);
 
@@ -2354,7 +2369,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
  * Called from generic code to get the instruction pointer
  * for an event_id.
  */
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long siar = mfspr(SPRN_SIAR);
 
@@ -2594,6 +2609,8 @@ static int __init init_ppc64_pmu(void)
 		return 0;
 	else if (!init_power10_pmu())
 		return 0;
+	else if (!init_power11_pmu())
+		return 0;
 	else if (!init_ppc970_pmu())
 		return 0;
 	else
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index ee721f420a7b..7120ab20cbfe 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -590,6 +590,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			       struct pt_regs *regs)
 {
 	u64 period = event->hw.sample_period;
+	const u64 last_period = event->hw.last_period;
 	s64 prev, delta, left;
 	int record = 0;
 
@@ -632,10 +633,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	if (record) {
 		struct perf_sample_data data;
 
-		perf_sample_data_init(&data, 0, event->hw.last_period);
+		perf_sample_data_init(&data, 0, last_period);
 
-		if (perf_event_overflow(event, &data, regs))
-			fsl_emb_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 }
 
@@ -645,7 +645,6 @@ static void perf_event_interrupt(struct pt_regs *regs)
 	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	unsigned long val;
-	int found = 0;
 
 	for (i = 0; i < ppmu->n_counter; ++i) {
 		event = cpuhw->event[i];
@@ -654,7 +653,6 @@ static void perf_event_interrupt(struct pt_regs *regs)
 		if ((int)val < 0) {
 			if (event) {
 				/* event has overflowed */
-				found = 1;
 				record_and_restart(event, val, regs);
 			} else {
 				/*
@@ -672,11 +670,13 @@ static void perf_event_interrupt(struct pt_regs *regs)
 	isync();
 }
 
-void hw_perf_event_setup(int cpu)
+static int fsl_emb_pmu_prepare_cpu(unsigned int cpu)
 {
 	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
 
 	memset(cpuhw, 0, sizeof(*cpuhw));
+
+	return 0;
 }
 
 int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu)
@@ -689,6 +689,8 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu)
 		pmu->name);
 
 	perf_pmu_register(&fsl_emb_pmu, "cpu", PERF_TYPE_RAW);
+	cpuhp_setup_state(CPUHP_PERF_POWER, "perf/powerpc:prepare",
+			  fsl_emb_pmu_prepare_cpu, NULL);
 
 	return 0;
 }
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 317175791d23..e42677cc254a 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -425,16 +425,6 @@ static char *memdup_to_str(char *maybe_str, int max_len, gfp_t gfp)
 	return kasprintf(gfp, "%.*s", max_len, maybe_str);
 }
 
-static ssize_t device_show_string(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct dev_ext_attribute *d;
-
-	d = container_of(attr, struct dev_ext_attribute, attr);
-
-	return sprintf(buf, "%s\n", (char *)d->var);
-}
-
 static ssize_t cpumask_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
@@ -723,12 +713,12 @@ static ssize_t catalog_event_len_validate(struct hv_24x7_event_data *event,
 	ev_len = be16_to_cpu(event->length);
 
 	if (ev_len % 16)
-		pr_info("event %zu has length %zu not divisible by 16: event=%pK\n",
+		pr_info("event %zu has length %zu not divisible by 16: event=%p\n",
 				event_idx, ev_len, event);
 
 	ev_end = (__u8 *)event + ev_len;
 	if (ev_end > end) {
-		pr_warn("event %zu has .length=%zu, ends after buffer end: ev_end=%pK > end=%pK, offset=%zu\n",
+		pr_warn("event %zu has .length=%zu, ends after buffer end: ev_end=%p > end=%p, offset=%zu\n",
 				event_idx, ev_len, ev_end, end,
 				offset);
 		return -1;
@@ -736,14 +726,14 @@ static ssize_t catalog_event_len_validate(struct hv_24x7_event_data *event,
 
 	calc_ev_end = event_end(event, end);
 	if (!calc_ev_end) {
-		pr_warn("event %zu has a calculated length which exceeds buffer length %zu: event=%pK end=%pK, offset=%zu\n",
+		pr_warn("event %zu has a calculated length which exceeds buffer length %zu: event=%p end=%p, offset=%zu\n",
 			event_idx, event_data_bytes, event, end,
 			offset);
 		return -1;
 	}
 
 	if (calc_ev_end > ev_end) {
-		pr_warn("event %zu exceeds its own length: event=%pK, end=%pK, offset=%zu, calc_ev_end=%pK\n",
+		pr_warn("event %zu exceeds its own length: event=%p, end=%p, offset=%zu, calc_ev_end=%p\n",
 			event_idx, event, ev_end, offset, calc_ev_end);
 		return -1;
 	}
@@ -1008,7 +998,7 @@ e_out:
 }
 
 static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr, char *buf,
+			    const struct bin_attribute *bin_attr, char *buf,
 			    loff_t offset, size_t count)
 {
 	long hret;
@@ -1118,14 +1108,14 @@ PAGE_0_ATTR(catalog_version, "%lld\n",
 		(unsigned long long)be64_to_cpu(page_0->version));
 PAGE_0_ATTR(catalog_len, "%lld\n",
 		(unsigned long long)be32_to_cpu(page_0->length) * 4096);
-static BIN_ATTR_RO(catalog, 0/* real length varies */);
+static const BIN_ATTR_RO(catalog, 0/* real length varies */);
 static DEVICE_ATTR_RO(domains);
 static DEVICE_ATTR_RO(sockets);
 static DEVICE_ATTR_RO(chipspersocket);
 static DEVICE_ATTR_RO(coresperchip);
 static DEVICE_ATTR_RO(cpumask);
 
-static struct bin_attribute *if_bin_attrs[] = {
+static const struct bin_attribute *const if_bin_attrs[] = {
 	&bin_attr_catalog,
 	NULL,
 };
@@ -1338,7 +1328,7 @@ static int get_count_from_result(struct perf_event *event,
 	for (i = count = 0, element_data = res->elements + data_offset;
 	     i < num_elements;
 	     i++, element_data += data_size + data_offset)
-		count += be64_to_cpu(*((u64 *) element_data));
+		count += be64_to_cpu(*((__be64 *)element_data));
 
 	*countp = count;
 
@@ -1418,7 +1408,7 @@ static int h_24x7_event_init(struct perf_event *event)
 	}
 
 	domain = event_get_domain(event);
-	if (domain >= HV_PERF_DOMAIN_MAX) {
+	if (domain  == 0 || domain >= HV_PERF_DOMAIN_MAX) {
 		pr_devel("invalid domain %d\n", domain);
 		return -EINVAL;
 	}
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 7ff8ff3509f5..241551d1282f 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -102,6 +102,514 @@ static ssize_t cpumask_show(struct device *dev,
 	return cpumap_print_to_pagebuf(true, buf, &hv_gpci_cpumask);
 }
 
+/* Interface attribute array index to store system information */
+#define INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR	6
+#define INTERFACE_PROCESSOR_CONFIG_ATTR		7
+#define INTERFACE_AFFINITY_DOMAIN_VIA_VP_ATTR	8
+#define INTERFACE_AFFINITY_DOMAIN_VIA_DOM_ATTR	9
+#define INTERFACE_AFFINITY_DOMAIN_VIA_PAR_ATTR	10
+#define INTERFACE_NULL_ATTR			11
+
+/* Counter request value to retrieve system information */
+enum {
+	PROCESSOR_BUS_TOPOLOGY,
+	PROCESSOR_CONFIG,
+	AFFINITY_DOMAIN_VIA_VP, /* affinity domain via virtual processor */
+	AFFINITY_DOMAIN_VIA_DOM, /* affinity domain via domain */
+	AFFINITY_DOMAIN_VIA_PAR, /* affinity domain via partition */
+};
+
+static int sysinfo_counter_request[] = {
+	[PROCESSOR_BUS_TOPOLOGY] = 0xD0,
+	[PROCESSOR_CONFIG] = 0x90,
+	[AFFINITY_DOMAIN_VIA_VP] = 0xA0,
+	[AFFINITY_DOMAIN_VIA_DOM] = 0xB0,
+	[AFFINITY_DOMAIN_VIA_PAR] = 0xB1,
+};
+
+static DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t));
+
+static unsigned long systeminfo_gpci_request(u32 req, u32 starting_index,
+			u16 secondary_index, char *buf,
+			size_t *n, struct hv_gpci_request_buffer *arg)
+{
+	unsigned long ret;
+	size_t i, j;
+
+	arg->params.counter_request = cpu_to_be32(req);
+	arg->params.starting_index = cpu_to_be32(starting_index);
+	arg->params.secondary_index = cpu_to_be16(secondary_index);
+
+	ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
+			virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE);
+
+	/*
+	 * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL',
+	 * which means that the current buffer size cannot accommodate
+	 * all the information and a partial buffer returned.
+	 * hcall fails incase of ret value other than H_SUCCESS or H_PARAMETER.
+	 *
+	 * ret value as H_AUTHORITY implies that partition is not permitted to retrieve
+	 * performance information, and required to set
+	 * "Enable Performance Information Collection" option.
+	 */
+	if (ret == H_AUTHORITY)
+		return -EPERM;
+
+	/*
+	 * hcall can fail with other possible ret value like H_PRIVILEGE/H_HARDWARE
+	 * because of invalid buffer-length/address or due to some hardware
+	 * error.
+	 */
+	if (ret && (ret != H_PARAMETER))
+		return -EIO;
+
+	/*
+	 * hcall H_GET_PERF_COUNTER_INFO populates the 'returned_values'
+	 * to show the total number of counter_value array elements
+	 * returned via hcall.
+	 * hcall also populates 'cv_element_size' corresponds to individual
+	 * counter_value array element size. Below loop go through all
+	 * counter_value array elements as per their size and add it to
+	 * the output buffer.
+	 */
+	for (i = 0; i < be16_to_cpu(arg->params.returned_values); i++) {
+		j = i * be16_to_cpu(arg->params.cv_element_size);
+
+		for (; j < (i + 1) * be16_to_cpu(arg->params.cv_element_size); j++)
+			*n += sprintf(buf + *n,  "%02x", (u8)arg->bytes[j]);
+		*n += sprintf(buf + *n,  "\n");
+	}
+
+	if (*n >= PAGE_SIZE) {
+		pr_info("System information exceeds PAGE_SIZE\n");
+		return -EFBIG;
+	}
+
+	return ret;
+}
+
+static ssize_t processor_bus_topology_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct hv_gpci_request_buffer *arg;
+	unsigned long ret;
+	size_t n = 0;
+
+	arg = (void *)get_cpu_var(hv_gpci_reqb);
+	memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+	/*
+	 * Pass the counter request value 0xD0 corresponds to request
+	 * type 'Processor_bus_topology', to retrieve
+	 * the system topology information.
+	 * starting_index value implies the starting hardware
+	 * chip id.
+	 */
+	ret = systeminfo_gpci_request(sysinfo_counter_request[PROCESSOR_BUS_TOPOLOGY],
+			0, 0, buf, &n, arg);
+
+	if (!ret)
+		return n;
+
+	if (ret != H_PARAMETER)
+		goto out;
+
+	/*
+	 * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', which
+	 * implies that buffer can't accommodate all information, and a partial buffer
+	 * returned. To handle that, we need to make subsequent requests
+	 * with next starting index to retrieve additional (missing) data.
+	 * Below loop do subsequent hcalls with next starting index and add it
+	 * to buffer util we get all the information.
+	 */
+	while (ret == H_PARAMETER) {
+		int returned_values = be16_to_cpu(arg->params.returned_values);
+		int elementsize = be16_to_cpu(arg->params.cv_element_size);
+		int last_element = (returned_values - 1) * elementsize;
+
+		/*
+		 * Since the starting index value is part of counter_value
+		 * buffer elements, use the starting index value in the last
+		 * element and add 1 to make subsequent hcalls.
+		 */
+		u32 starting_index = arg->bytes[last_element + 3] +
+				(arg->bytes[last_element + 2] << 8) +
+				(arg->bytes[last_element + 1] << 16) +
+				(arg->bytes[last_element] << 24) + 1;
+
+		memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+		ret = systeminfo_gpci_request(sysinfo_counter_request[PROCESSOR_BUS_TOPOLOGY],
+				starting_index, 0, buf, &n, arg);
+
+		if (!ret)
+			return n;
+
+		if (ret != H_PARAMETER)
+			goto out;
+	}
+
+	return n;
+
+out:
+	put_cpu_var(hv_gpci_reqb);
+	return ret;
+}
+
+static ssize_t processor_config_show(struct device *dev, struct device_attribute *attr,
+					char *buf)
+{
+	struct hv_gpci_request_buffer *arg;
+	unsigned long ret;
+	size_t n = 0;
+
+	arg = (void *)get_cpu_var(hv_gpci_reqb);
+	memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+	/*
+	 * Pass the counter request value 0x90 corresponds to request
+	 * type 'Processor_config', to retrieve
+	 * the system processor information.
+	 * starting_index value implies the starting hardware
+	 * processor index.
+	 */
+	ret = systeminfo_gpci_request(sysinfo_counter_request[PROCESSOR_CONFIG],
+			0, 0, buf, &n, arg);
+
+	if (!ret)
+		return n;
+
+	if (ret != H_PARAMETER)
+		goto out;
+
+	/*
+	 * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', which
+	 * implies that buffer can't accommodate all information, and a partial buffer
+	 * returned. To handle that, we need to take subsequent requests
+	 * with next starting index to retrieve additional (missing) data.
+	 * Below loop do subsequent hcalls with next starting index and add it
+	 * to buffer util we get all the information.
+	 */
+	while (ret == H_PARAMETER) {
+		int returned_values = be16_to_cpu(arg->params.returned_values);
+		int elementsize = be16_to_cpu(arg->params.cv_element_size);
+		int last_element = (returned_values - 1) * elementsize;
+
+		/*
+		 * Since the starting index is part of counter_value
+		 * buffer elements, use the starting index value in the last
+		 * element and add 1 to subsequent hcalls.
+		 */
+		u32 starting_index = arg->bytes[last_element + 3] +
+				(arg->bytes[last_element + 2] << 8) +
+				(arg->bytes[last_element + 1] << 16) +
+				(arg->bytes[last_element] << 24) + 1;
+
+		memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+		ret = systeminfo_gpci_request(sysinfo_counter_request[PROCESSOR_CONFIG],
+				starting_index, 0, buf, &n, arg);
+
+		if (!ret)
+			return n;
+
+		if (ret != H_PARAMETER)
+			goto out;
+	}
+
+	return n;
+
+out:
+	put_cpu_var(hv_gpci_reqb);
+	return ret;
+}
+
+static ssize_t affinity_domain_via_virtual_processor_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct hv_gpci_request_buffer *arg;
+	unsigned long ret;
+	size_t n = 0;
+
+	arg = (void *)get_cpu_var(hv_gpci_reqb);
+	memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+	/*
+	 * Pass the counter request 0xA0 corresponds to request
+	 * type 'Affinity_domain_information_by_virutal_processor',
+	 * to retrieve the system affinity domain information.
+	 * starting_index value refers to the starting hardware
+	 * processor index.
+	 */
+	ret = systeminfo_gpci_request(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_VP],
+			0, 0, buf, &n, arg);
+
+	if (!ret)
+		return n;
+
+	if (ret != H_PARAMETER)
+		goto out;
+
+	/*
+	 * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', which
+	 * implies that buffer can't accommodate all information, and a partial buffer
+	 * returned. To handle that, we need to take subsequent requests
+	 * with next secondary index to retrieve additional (missing) data.
+	 * Below loop do subsequent hcalls with next secondary index and add it
+	 * to buffer util we get all the information.
+	 */
+	while (ret == H_PARAMETER) {
+		int returned_values = be16_to_cpu(arg->params.returned_values);
+		int elementsize = be16_to_cpu(arg->params.cv_element_size);
+		int last_element = (returned_values - 1) * elementsize;
+
+		/*
+		 * Since the starting index and secondary index type is part of the
+		 * counter_value buffer elements, use the starting index value in the
+		 * last array element as subsequent starting index, and use secondary index
+		 * value in the last array element plus 1 as subsequent secondary index.
+		 * For counter request '0xA0', starting index points to partition id
+		 * and secondary index points to corresponding virtual processor index.
+		 */
+		u32 starting_index = arg->bytes[last_element + 1] + (arg->bytes[last_element] << 8);
+		u16 secondary_index = arg->bytes[last_element + 3] +
+				(arg->bytes[last_element + 2] << 8) + 1;
+
+		memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+		ret = systeminfo_gpci_request(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_VP],
+				starting_index, secondary_index, buf, &n, arg);
+
+		if (!ret)
+			return n;
+
+		if (ret != H_PARAMETER)
+			goto out;
+	}
+
+	return n;
+
+out:
+	put_cpu_var(hv_gpci_reqb);
+	return ret;
+}
+
+static ssize_t affinity_domain_via_domain_show(struct device *dev, struct device_attribute *attr,
+						char *buf)
+{
+	struct hv_gpci_request_buffer *arg;
+	unsigned long ret;
+	size_t n = 0;
+
+	arg = (void *)get_cpu_var(hv_gpci_reqb);
+	memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+	/*
+	 * Pass the counter request 0xB0 corresponds to request
+	 * type 'Affinity_domain_information_by_domain',
+	 * to retrieve the system affinity domain information.
+	 * starting_index value refers to the starting hardware
+	 * processor index.
+	 */
+	ret = systeminfo_gpci_request(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_DOM],
+			0, 0, buf, &n, arg);
+
+	if (!ret)
+		return n;
+
+	if (ret != H_PARAMETER)
+		goto out;
+
+	/*
+	 * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL', which
+	 * implies that buffer can't accommodate all information, and a partial buffer
+	 * returned. To handle that, we need to take subsequent requests
+	 * with next starting index to retrieve additional (missing) data.
+	 * Below loop do subsequent hcalls with next starting index and add it
+	 * to buffer util we get all the information.
+	 */
+	while (ret == H_PARAMETER) {
+		int returned_values = be16_to_cpu(arg->params.returned_values);
+		int elementsize = be16_to_cpu(arg->params.cv_element_size);
+		int last_element = (returned_values - 1) * elementsize;
+
+		/*
+		 * Since the starting index value is part of counter_value
+		 * buffer elements, use the starting index value in the last
+		 * element and add 1 to make subsequent hcalls.
+		 */
+		u32 starting_index = arg->bytes[last_element + 1] +
+			(arg->bytes[last_element] << 8) + 1;
+
+		memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+		ret = systeminfo_gpci_request(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_DOM],
+					starting_index, 0, buf, &n, arg);
+
+		if (!ret)
+			return n;
+
+		if (ret != H_PARAMETER)
+			goto out;
+	}
+
+	return n;
+
+out:
+	put_cpu_var(hv_gpci_reqb);
+	return ret;
+}
+
+static void affinity_domain_via_partition_result_parse(int returned_values,
+			int element_size, char *buf, size_t *last_element,
+			size_t *n, struct hv_gpci_request_buffer *arg)
+{
+	size_t i = 0, j = 0;
+	size_t k, l, m;
+	uint16_t total_affinity_domain_ele, size_of_each_affinity_domain_ele;
+
+	/*
+	 * hcall H_GET_PERF_COUNTER_INFO populates the 'returned_values'
+	 * to show the total number of counter_value array elements
+	 * returned via hcall.
+	 * Unlike other request types, the data structure returned by this
+	 * request is variable-size. For this counter request type,
+	 * hcall populates 'cv_element_size' corresponds to minimum size of
+	 * the structure returned i.e; the size of the structure with no domain
+	 * information. Below loop go through all counter_value array
+	 * to determine the number and size of each domain array element and
+	 * add it to the output buffer.
+	 */
+	while (i < returned_values) {
+		k = j;
+		for (; k < j + element_size; k++)
+			*n += sprintf(buf + *n,  "%02x", (u8)arg->bytes[k]);
+		*n += sprintf(buf + *n,  "\n");
+
+		total_affinity_domain_ele = (u8)arg->bytes[k - 2] << 8 | (u8)arg->bytes[k - 3];
+		size_of_each_affinity_domain_ele = (u8)arg->bytes[k] << 8 | (u8)arg->bytes[k - 1];
+
+		for (l = 0; l < total_affinity_domain_ele; l++) {
+			for (m = 0; m < size_of_each_affinity_domain_ele; m++) {
+				*n += sprintf(buf + *n,  "%02x", (u8)arg->bytes[k]);
+				k++;
+			}
+			*n += sprintf(buf + *n,  "\n");
+		}
+
+		*n += sprintf(buf + *n,  "\n");
+		i++;
+		j = k;
+	}
+
+	*last_element = k;
+}
+
+static ssize_t affinity_domain_via_partition_show(struct device *dev, struct device_attribute *attr,
+							char *buf)
+{
+	struct hv_gpci_request_buffer *arg;
+	unsigned long ret;
+	size_t n = 0;
+	size_t last_element = 0;
+	u32 starting_index;
+
+	arg = (void *)get_cpu_var(hv_gpci_reqb);
+	memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+	/*
+	 * Pass the counter request value 0xB1 corresponds to counter request
+	 * type 'Affinity_domain_information_by_partition',
+	 * to retrieve the system affinity domain by partition information.
+	 * starting_index value refers to the starting hardware
+	 * processor index.
+	 */
+	arg->params.counter_request = cpu_to_be32(sysinfo_counter_request[AFFINITY_DOMAIN_VIA_PAR]);
+	arg->params.starting_index = cpu_to_be32(0);
+
+	ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
+			virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE);
+
+	if (!ret)
+		goto parse_result;
+
+	if (ret && (ret != H_PARAMETER))
+		goto out;
+
+	/*
+	 * ret value as 'H_PARAMETER' implies that the current buffer size
+	 * can't accommodate all the information, and a partial buffer
+	 * returned. To handle that, we need to make subsequent requests
+	 * with next starting index to retrieve additional (missing) data.
+	 * Below loop do subsequent hcalls with next starting index and add it
+	 * to buffer util we get all the information.
+	 */
+	while (ret == H_PARAMETER) {
+		affinity_domain_via_partition_result_parse(
+			be16_to_cpu(arg->params.returned_values) - 1,
+			be16_to_cpu(arg->params.cv_element_size), buf,
+			&last_element, &n, arg);
+
+		if (n >= PAGE_SIZE) {
+			put_cpu_var(hv_gpci_reqb);
+			pr_debug("System information exceeds PAGE_SIZE\n");
+			return -EFBIG;
+		}
+
+		/*
+		 * Since the starting index value is part of counter_value
+		 * buffer elements, use the starting_index value in the last
+		 * element and add 1 to make subsequent hcalls.
+		 */
+		starting_index = (u8)arg->bytes[last_element] << 8 |
+				(u8)arg->bytes[last_element + 1];
+
+		memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+		arg->params.counter_request = cpu_to_be32(
+				sysinfo_counter_request[AFFINITY_DOMAIN_VIA_PAR]);
+		arg->params.starting_index = cpu_to_be32(starting_index);
+
+		ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
+				virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE);
+
+		if (ret && (ret != H_PARAMETER))
+			goto out;
+	}
+
+parse_result:
+	affinity_domain_via_partition_result_parse(
+		be16_to_cpu(arg->params.returned_values),
+		be16_to_cpu(arg->params.cv_element_size),
+		buf, &last_element, &n, arg);
+
+	put_cpu_var(hv_gpci_reqb);
+	return n;
+
+out:
+	put_cpu_var(hv_gpci_reqb);
+
+	/*
+	 * ret value as 'H_PARAMETER' corresponds to 'GEN_BUF_TOO_SMALL',
+	 * which means that the current buffer size cannot accommodate
+	 * all the information and a partial buffer returned.
+	 * hcall fails incase of ret value other than H_SUCCESS or H_PARAMETER.
+	 *
+	 * ret value as H_AUTHORITY implies that partition is not permitted to retrieve
+	 * performance information, and required to set
+	 * "Enable Performance Information Collection" option.
+	 */
+	if (ret == H_AUTHORITY)
+		return -EPERM;
+
+	/*
+	 * hcall can fail with other possible ret value like H_PRIVILEGE/H_HARDWARE
+	 * because of invalid buffer-length/address or due to some hardware
+	 * error.
+	 */
+	return -EIO;
+}
+
 static DEVICE_ATTR_RO(kernel_version);
 static DEVICE_ATTR_RO(cpumask);
 
@@ -118,6 +626,31 @@ static struct attribute *interface_attrs[] = {
 	&hv_caps_attr_expanded.attr,
 	&hv_caps_attr_lab.attr,
 	&hv_caps_attr_collect_privileged.attr,
+	/*
+	 * This NULL is a placeholder for the processor_bus_topology
+	 * attribute, set in init function if applicable.
+	 */
+	NULL,
+	/*
+	 * This NULL is a placeholder for the processor_config
+	 * attribute, set in init function if applicable.
+	 */
+	NULL,
+	/*
+	 * This NULL is a placeholder for the affinity_domain_via_virtual_processor
+	 * attribute, set in init function if applicable.
+	 */
+	NULL,
+	/*
+	 * This NULL is a placeholder for the affinity_domain_via_domain
+	 * attribute, set in init function if applicable.
+	 */
+	NULL,
+	/*
+	 * This NULL is a placeholder for the affinity_domain_via_partition
+	 * attribute, set in init function if applicable.
+	 */
+	NULL,
 	NULL,
 };
 
@@ -143,8 +676,6 @@ static const struct attribute_group *attr_groups[] = {
 	NULL,
 };
 
-static DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t));
-
 static unsigned long single_gpci_request(u32 req, u32 starting_index,
 		u16 secondary_index, u8 version_in, u32 offset, u8 length,
 		u64 *value)
@@ -164,6 +695,20 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index,
 
 	ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
 			virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE);
+
+	/*
+	 * ret value as 'H_PARAMETER' with detail_rc as 'GEN_BUF_TOO_SMALL',
+	 * specifies that the current buffer size cannot accommodate
+	 * all the information and a partial buffer returned.
+	 * Since in this function we are only accessing data for a given starting index,
+	 * we don't need to accommodate whole data and can get required count by
+	 * accessing first entry data.
+	 * Hence hcall fails only incase the ret value is other than H_SUCCESS or
+	 * H_PARAMETER with detail_rc value as GEN_BUF_TOO_SMALL(0x1B).
+	 */
+	if (ret == H_PARAMETER && be32_to_cpu(arg->params.detail_rc) == 0x1B)
+		ret = 0;
+
 	if (ret) {
 		pr_devel("hcall failed: 0x%lx\n", ret);
 		goto out;
@@ -228,6 +773,7 @@ static int h_gpci_event_init(struct perf_event *event)
 {
 	u64 count;
 	u8 length;
+	unsigned long ret;
 
 	/* Not our event */
 	if (event->attr.type != event->pmu->type)
@@ -258,13 +804,23 @@ static int h_gpci_event_init(struct perf_event *event)
 	}
 
 	/* check if the request works... */
-	if (single_gpci_request(event_get_request(event),
+	ret = single_gpci_request(event_get_request(event),
 				event_get_starting_index(event),
 				event_get_secondary_index(event),
 				event_get_counter_info_version(event),
 				event_get_offset(event),
 				length,
-				&count)) {
+				&count);
+
+	/*
+	 * ret value as H_AUTHORITY implies that partition is not permitted to retrieve
+	 * performance information, and required to set
+	 * "Enable Performance Information Collection" option.
+	 */
+	if (ret == H_AUTHORITY)
+		return -EPERM;
+
+	if (ret) {
 		pr_devel("gpci hcall failed\n");
 		return -EINVAL;
 	}
@@ -325,6 +881,107 @@ static int hv_gpci_cpu_hotplug_init(void)
 			  ppc_hv_gpci_cpu_offline);
 }
 
+static struct device_attribute *sysinfo_device_attr_create(int
+		sysinfo_interface_group_index, u32 req)
+{
+	struct device_attribute *attr = NULL;
+	unsigned long ret;
+	struct hv_gpci_request_buffer *arg;
+
+	if (sysinfo_interface_group_index < INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR ||
+			sysinfo_interface_group_index >= INTERFACE_NULL_ATTR) {
+		pr_info("Wrong interface group index for system information\n");
+		return NULL;
+	}
+
+	/* Check for given counter request value support */
+	arg = (void *)get_cpu_var(hv_gpci_reqb);
+	memset(arg, 0, HGPCI_REQ_BUFFER_SIZE);
+
+	arg->params.counter_request = cpu_to_be32(req);
+
+	ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO,
+			virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE);
+
+	put_cpu_var(hv_gpci_reqb);
+
+	/*
+	 * Add given counter request value attribute in the interface_attrs
+	 * attribute array, only for valid return types.
+	 */
+	if (!ret || ret == H_AUTHORITY || ret == H_PARAMETER) {
+		attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+		if (!attr)
+			return NULL;
+
+		sysfs_attr_init(&attr->attr);
+		attr->attr.mode = 0444;
+
+		switch (sysinfo_interface_group_index) {
+		case INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR:
+			attr->attr.name = "processor_bus_topology";
+			attr->show = processor_bus_topology_show;
+		break;
+		case INTERFACE_PROCESSOR_CONFIG_ATTR:
+			attr->attr.name = "processor_config";
+			attr->show = processor_config_show;
+		break;
+		case INTERFACE_AFFINITY_DOMAIN_VIA_VP_ATTR:
+			attr->attr.name = "affinity_domain_via_virtual_processor";
+			attr->show = affinity_domain_via_virtual_processor_show;
+		break;
+		case INTERFACE_AFFINITY_DOMAIN_VIA_DOM_ATTR:
+			attr->attr.name = "affinity_domain_via_domain";
+			attr->show = affinity_domain_via_domain_show;
+		break;
+		case INTERFACE_AFFINITY_DOMAIN_VIA_PAR_ATTR:
+			attr->attr.name = "affinity_domain_via_partition";
+			attr->show = affinity_domain_via_partition_show;
+		break;
+		}
+	} else
+		pr_devel("hcall failed, with error: 0x%lx\n", ret);
+
+	return attr;
+}
+
+static void add_sysinfo_interface_files(void)
+{
+	int sysfs_count;
+	struct device_attribute *attr[INTERFACE_NULL_ATTR - INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR];
+	int i;
+
+	sysfs_count = INTERFACE_NULL_ATTR - INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR;
+
+	/* Get device attribute for a given counter request value */
+	for (i = 0; i < sysfs_count; i++) {
+		attr[i] = sysinfo_device_attr_create(i + INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR,
+				sysinfo_counter_request[i]);
+
+		if (!attr[i])
+			goto out;
+	}
+
+	/* Add sysinfo interface attributes in the interface_attrs attribute array */
+	for (i = 0; i < sysfs_count; i++)
+		interface_attrs[i + INTERFACE_PROCESSOR_BUS_TOPOLOGY_ATTR] = &attr[i]->attr;
+
+	return;
+
+out:
+	/*
+	 * The sysinfo interface attributes will be added, only if hcall passed for
+	 * all the counter request values. Free the device attribute array incase
+	 * of any hcall failure.
+	 */
+	if (i > 0) {
+		while (i >= 0) {
+			kfree(attr[i]);
+			i--;
+		}
+	}
+}
+
 static int hv_gpci_init(void)
 {
 	int r;
@@ -388,6 +1045,10 @@ static int hv_gpci_init(void)
 	if (r)
 		return r;
 
+	/* sysinfo interface files are only available for power10 and above platforms */
+	if (PVR_VER(mfspr(SPRN_PVR)) >= PVR_POWER10)
+		add_sysinfo_interface_files();
+
 	return 0;
 }
 
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 9d229ef7f86e..8664a7d297ad 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -51,7 +51,7 @@ static int trace_imc_mem_size;
  * core and trace-imc
  */
 static struct imc_pmu_ref imc_global_refc = {
-	.lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock),
+	.lock = __SPIN_LOCK_UNLOCKED(imc_global_refc.lock),
 	.id = 0,
 	.refc = 0,
 };
@@ -299,6 +299,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 	attr_group->attrs = attrs;
 	do {
 		ev_val_str = kasprintf(GFP_KERNEL, "event=0x%x", pmu->events[i].value);
+		if (!ev_val_str)
+			continue;
 		dev_str = device_str_attr_create(pmu->events[i].name, ev_val_str);
 		if (!dev_str)
 			continue;
@@ -306,6 +308,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 		attrs[j++] = dev_str;
 		if (pmu->events[i].scale) {
 			ev_scale_str = kasprintf(GFP_KERNEL, "%s.scale", pmu->events[i].name);
+			if (!ev_scale_str)
+				continue;
 			dev_str = device_str_attr_create(ev_scale_str, pmu->events[i].scale);
 			if (!dev_str)
 				continue;
@@ -315,6 +319,8 @@ static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu)
 
 		if (pmu->events[i].unit) {
 			ev_unit_str = kasprintf(GFP_KERNEL, "%s.unit", pmu->events[i].name);
+			if (!ev_unit_str)
+				continue;
 			dev_str = device_str_attr_create(ev_unit_str, pmu->events[i].unit);
 			if (!dev_str)
 				continue;
@@ -544,7 +550,7 @@ static int nest_imc_event_init(struct perf_event *event)
 			break;
 		}
 		pcni++;
-	} while (pcni->vbase != 0);
+	} while (pcni->vbase);
 
 	if (!flag)
 		return -ENODEV;
@@ -1025,16 +1031,16 @@ static bool is_thread_imc_pmu(struct perf_event *event)
 	return false;
 }
 
-static u64 * get_event_base_addr(struct perf_event *event)
+static __be64 *get_event_base_addr(struct perf_event *event)
 {
 	u64 addr;
 
 	if (is_thread_imc_pmu(event)) {
 		addr = (u64)per_cpu(thread_imc_mem, smp_processor_id());
-		return (u64 *)(addr + (event->attr.config & IMC_EVENT_OFFSET_MASK));
+		return (__be64 *)(addr + (event->attr.config & IMC_EVENT_OFFSET_MASK));
 	}
 
-	return (u64 *)event->hw.event_base;
+	return (__be64 *)event->hw.event_base;
 }
 
 static void thread_imc_pmu_start_txn(struct pmu *pmu,
@@ -1058,7 +1064,8 @@ static int thread_imc_pmu_commit_txn(struct pmu *pmu)
 
 static u64 imc_read_counter(struct perf_event *event)
 {
-	u64 *addr, data;
+	__be64 *addr;
+	u64 data;
 
 	/*
 	 * In-Memory Collection (IMC) counters are free flowing counters.
diff --git a/arch/powerpc/perf/internal.h b/arch/powerpc/perf/internal.h
index 4c18b5504326..a70ac471a5a5 100644
--- a/arch/powerpc/perf/internal.h
+++ b/arch/powerpc/perf/internal.h
@@ -10,4 +10,5 @@ int __init init_power7_pmu(void);
 int __init init_power8_pmu(void);
 int __init init_power9_pmu(void);
 int __init init_power10_pmu(void);
+int __init init_power11_pmu(void);
 int __init init_generic_compat_pmu(void);
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 56301b2bc8ae..2b3547fdba4a 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -319,10 +319,18 @@ void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
 		return;
 	}
 
-	sier = mfspr(SPRN_SIER);
+	/*
+	 * Use regs-dar for SPRN_SIER which is saved
+	 * during perf_read_regs at the beginning
+	 * of the PMU interrupt handler to avoid multiple
+	 * reads of SPRN_SIER
+	 */
+	sier = regs->dar;
 	val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT;
-	if (val != 1 && val != 2 && !(val == 7 && cpu_has_feature(CPU_FTR_ARCH_31)))
+	if (val != 1 && val != 2 && !(val == 7 && cpu_has_feature(CPU_FTR_ARCH_31))) {
+		dsrc->val = 0;
 		return;
+	}
 
 	idx = (sier & ISA207_SIER_LDST_MASK) >> ISA207_SIER_LDST_SHIFT;
 	sub_idx = (sier & ISA207_SIER_DATA_SRC_MASK) >> ISA207_SIER_DATA_SRC_SHIFT;
@@ -338,8 +346,12 @@ void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags,
 		 * to determine the exact instruction type. If the sampling
 		 * criteria is neither load or store, set the type as default
 		 * to NA.
+		 *
+		 * Use regs->dsisr for MMCRA which is saved during perf_read_regs
+		 * at the beginning of the PMU interrupt handler to avoid
+		 * multiple reads of SPRN_MMCRA
 		 */
-		mmcra = mfspr(SPRN_MMCRA);
+		mmcra = regs->dsisr;
 
 		op_type = (mmcra >> MMCRA_SAMP_ELIG_SHIFT) & MMCRA_SAMP_ELIG_MASK;
 		switch (op_type) {
diff --git a/arch/powerpc/perf/kvm-hv-pmu.c b/arch/powerpc/perf/kvm-hv-pmu.c
new file mode 100644
index 000000000000..ae264c9080ef
--- /dev/null
+++ b/arch/powerpc/perf/kvm-hv-pmu.c
@@ -0,0 +1,435 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Description: PMUs specific to running nested KVM-HV guests
+ * on Book3S processors (specifically POWER9 and later).
+ */
+
+#define pr_fmt(fmt)  "kvmppc-pmu: " fmt
+
+#include "asm-generic/local64.h"
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/ratelimit.h>
+#include <linux/kvm_host.h>
+#include <linux/gfp_types.h>
+#include <linux/pgtable.h>
+#include <linux/perf_event.h>
+#include <linux/spinlock_types.h>
+#include <linux/spinlock.h>
+
+#include <asm/types.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu.h>
+#include <asm/pgalloc.h>
+#include <asm/pte-walk.h>
+#include <asm/reg.h>
+#include <asm/plpar_wrappers.h>
+#include <asm/firmware.h>
+
+#include "asm/guest-state-buffer.h"
+
+enum kvmppc_pmu_eventid {
+	KVMPPC_EVENT_HOST_HEAP,
+	KVMPPC_EVENT_HOST_HEAP_MAX,
+	KVMPPC_EVENT_HOST_PGTABLE,
+	KVMPPC_EVENT_HOST_PGTABLE_MAX,
+	KVMPPC_EVENT_HOST_PGTABLE_RECLAIM,
+	KVMPPC_EVENT_MAX,
+};
+
+#define KVMPPC_PMU_EVENT_ATTR(_name, _id) \
+	PMU_EVENT_ATTR_ID(_name, kvmppc_events_sysfs_show, _id)
+
+static ssize_t kvmppc_events_sysfs_show(struct device *dev,
+					struct device_attribute *attr,
+					char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+/* Holds the hostwide stats */
+static struct kvmppc_hostwide_stats {
+	u64 guest_heap;
+	u64 guest_heap_max;
+	u64 guest_pgtable_size;
+	u64 guest_pgtable_size_max;
+	u64 guest_pgtable_reclaim;
+} l0_stats;
+
+/* Protect access to l0_stats */
+static DEFINE_SPINLOCK(lock_l0_stats);
+
+/* GSB related structs needed to talk to L0 */
+static struct kvmppc_gs_msg *gsm_l0_stats;
+static struct kvmppc_gs_buff *gsb_l0_stats;
+static struct kvmppc_gs_parser gsp_l0_stats;
+
+static struct attribute *kvmppc_pmu_events_attr[] = {
+	KVMPPC_PMU_EVENT_ATTR(host_heap, KVMPPC_EVENT_HOST_HEAP),
+	KVMPPC_PMU_EVENT_ATTR(host_heap_max, KVMPPC_EVENT_HOST_HEAP_MAX),
+	KVMPPC_PMU_EVENT_ATTR(host_pagetable, KVMPPC_EVENT_HOST_PGTABLE),
+	KVMPPC_PMU_EVENT_ATTR(host_pagetable_max, KVMPPC_EVENT_HOST_PGTABLE_MAX),
+	KVMPPC_PMU_EVENT_ATTR(host_pagetable_reclaim, KVMPPC_EVENT_HOST_PGTABLE_RECLAIM),
+	NULL,
+};
+
+static const struct attribute_group kvmppc_pmu_events_group = {
+	.name = "events",
+	.attrs = kvmppc_pmu_events_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-5");
+static struct attribute *kvmppc_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group kvmppc_pmu_format_group = {
+	.name = "format",
+	.attrs = kvmppc_pmu_format_attr,
+};
+
+static const struct attribute_group *kvmppc_pmu_attr_groups[] = {
+	&kvmppc_pmu_events_group,
+	&kvmppc_pmu_format_group,
+	NULL,
+};
+
+/*
+ * Issue the hcall to get the L0-host stats.
+ * Should be called with l0-stat lock held
+ */
+static int kvmppc_update_l0_stats(void)
+{
+	int rc;
+
+	/* With HOST_WIDE flags guestid and vcpuid will be ignored */
+	rc = kvmppc_gsb_recv(gsb_l0_stats, KVMPPC_GS_FLAGS_HOST_WIDE);
+	if (rc)
+		goto out;
+
+	/* Parse the guest state buffer is successful */
+	rc = kvmppc_gse_parse(&gsp_l0_stats, gsb_l0_stats);
+	if (rc)
+		goto out;
+
+	/* Update the l0 returned stats*/
+	memset(&l0_stats, 0, sizeof(l0_stats));
+	rc = kvmppc_gsm_refresh_info(gsm_l0_stats, gsb_l0_stats);
+
+out:
+	return rc;
+}
+
+/* Update the value of the given perf_event */
+static int kvmppc_pmu_event_update(struct perf_event *event)
+{
+	int rc;
+	u64 curr_val, prev_val;
+	unsigned long flags;
+	unsigned int config = event->attr.config;
+
+	/* Ensure no one else is modifying the l0_stats */
+	spin_lock_irqsave(&lock_l0_stats, flags);
+
+	rc = kvmppc_update_l0_stats();
+	if (!rc) {
+		switch (config) {
+		case KVMPPC_EVENT_HOST_HEAP:
+			curr_val = l0_stats.guest_heap;
+			break;
+		case KVMPPC_EVENT_HOST_HEAP_MAX:
+			curr_val = l0_stats.guest_heap_max;
+			break;
+		case KVMPPC_EVENT_HOST_PGTABLE:
+			curr_val = l0_stats.guest_pgtable_size;
+			break;
+		case KVMPPC_EVENT_HOST_PGTABLE_MAX:
+			curr_val = l0_stats.guest_pgtable_size_max;
+			break;
+		case KVMPPC_EVENT_HOST_PGTABLE_RECLAIM:
+			curr_val = l0_stats.guest_pgtable_reclaim;
+			break;
+		default:
+			rc = -ENOENT;
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&lock_l0_stats, flags);
+
+	/* If no error than update the perf event */
+	if (!rc) {
+		prev_val = local64_xchg(&event->hw.prev_count, curr_val);
+		if (curr_val > prev_val)
+			local64_add(curr_val - prev_val, &event->count);
+	}
+
+	return rc;
+}
+
+static int kvmppc_pmu_event_init(struct perf_event *event)
+{
+	unsigned int config = event->attr.config;
+
+	pr_debug("%s: Event(%p) id=%llu cpu=%x on_cpu=%x config=%u",
+		 __func__, event, event->id, event->cpu,
+		 event->oncpu, config);
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (config >= KVMPPC_EVENT_MAX)
+		return -EINVAL;
+
+	local64_set(&event->hw.prev_count, 0);
+	local64_set(&event->count, 0);
+
+	return 0;
+}
+
+static void kvmppc_pmu_del(struct perf_event *event, int flags)
+{
+	kvmppc_pmu_event_update(event);
+}
+
+static int kvmppc_pmu_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		return kvmppc_pmu_event_update(event);
+	return 0;
+}
+
+static void kvmppc_pmu_read(struct perf_event *event)
+{
+	kvmppc_pmu_event_update(event);
+}
+
+/* Return the size of the needed guest state buffer */
+static size_t hostwide_get_size(struct kvmppc_gs_msg *gsm)
+
+{
+	size_t size = 0;
+	const u16 ids[] = {
+		KVMPPC_GSID_L0_GUEST_HEAP,
+		KVMPPC_GSID_L0_GUEST_HEAP_MAX,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX,
+		KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM
+	};
+
+	for (int i = 0; i < ARRAY_SIZE(ids); i++)
+		size += kvmppc_gse_total_size(kvmppc_gsid_size(ids[i]));
+	return size;
+}
+
+/* Populate the request guest state buffer */
+static int hostwide_fill_info(struct kvmppc_gs_buff *gsb,
+			      struct kvmppc_gs_msg *gsm)
+{
+	int rc = 0;
+	struct kvmppc_hostwide_stats  *stats = gsm->data;
+
+	/*
+	 * It doesn't matter what values are put into request buffer as
+	 * they are going to be overwritten anyways. But for the sake of
+	 * testcode and symmetry contents of existing stats are put
+	 * populated into the request guest state buffer.
+	 */
+	if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_HEAP,
+					stats->guest_heap);
+
+	if (!rc && kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_HEAP_MAX,
+					stats->guest_heap_max);
+
+	if (!rc && kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE,
+					stats->guest_pgtable_size);
+	if (!rc &&
+	    kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX,
+					stats->guest_pgtable_size_max);
+	if (!rc &&
+	    kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM))
+		rc = kvmppc_gse_put_u64(gsb,
+					KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM,
+					stats->guest_pgtable_reclaim);
+
+	return rc;
+}
+
+/* Parse and update the host wide stats from returned gsb */
+static int hostwide_refresh_info(struct kvmppc_gs_msg *gsm,
+				 struct kvmppc_gs_buff *gsb)
+{
+	struct kvmppc_gs_parser gsp = { 0 };
+	struct kvmppc_hostwide_stats *stats = gsm->data;
+	struct kvmppc_gs_elem *gse;
+	int rc;
+
+	rc = kvmppc_gse_parse(&gsp, gsb);
+	if (rc < 0)
+		return rc;
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP);
+	if (gse)
+		stats->guest_heap = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	if (gse)
+		stats->guest_heap_max = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	if (gse)
+		stats->guest_pgtable_size = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	if (gse)
+		stats->guest_pgtable_size_max = kvmppc_gse_get_u64(gse);
+
+	gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+	if (gse)
+		stats->guest_pgtable_reclaim = kvmppc_gse_get_u64(gse);
+
+	return 0;
+}
+
+/* gsb-message ops for setting up/parsing */
+static struct kvmppc_gs_msg_ops gsb_ops_l0_stats = {
+	.get_size = hostwide_get_size,
+	.fill_info = hostwide_fill_info,
+	.refresh_info = hostwide_refresh_info,
+};
+
+static int kvmppc_init_hostwide(void)
+{
+	int rc = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&lock_l0_stats, flags);
+
+	/* already registered ? */
+	if (gsm_l0_stats) {
+		rc = 0;
+		goto out;
+	}
+
+	/* setup the Guest state message/buffer to talk to L0 */
+	gsm_l0_stats = kvmppc_gsm_new(&gsb_ops_l0_stats, &l0_stats,
+				      GSM_SEND, GFP_KERNEL);
+	if (!gsm_l0_stats) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* Populate the Idents */
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_HEAP);
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_HEAP_MAX);
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE);
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX);
+	kvmppc_gsm_include(gsm_l0_stats, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM);
+
+	/* allocate GSB. Guest/Vcpu Id is ignored */
+	gsb_l0_stats = kvmppc_gsb_new(kvmppc_gsm_size(gsm_l0_stats), 0, 0,
+				      GFP_KERNEL);
+	if (!gsb_l0_stats) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* ask the ops to fill in the info */
+	rc = kvmppc_gsm_fill_info(gsm_l0_stats, gsb_l0_stats);
+
+out:
+	if (rc) {
+		if (gsm_l0_stats)
+			kvmppc_gsm_free(gsm_l0_stats);
+		if (gsb_l0_stats)
+			kvmppc_gsb_free(gsb_l0_stats);
+		gsm_l0_stats = NULL;
+		gsb_l0_stats = NULL;
+	}
+	spin_unlock_irqrestore(&lock_l0_stats, flags);
+	return rc;
+}
+
+static void kvmppc_cleanup_hostwide(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&lock_l0_stats, flags);
+
+	if (gsm_l0_stats)
+		kvmppc_gsm_free(gsm_l0_stats);
+	if (gsb_l0_stats)
+		kvmppc_gsb_free(gsb_l0_stats);
+	gsm_l0_stats = NULL;
+	gsb_l0_stats = NULL;
+
+	spin_unlock_irqrestore(&lock_l0_stats, flags);
+}
+
+/* L1 wide counters PMU */
+static struct pmu kvmppc_pmu = {
+	.module = THIS_MODULE,
+	.task_ctx_nr = perf_sw_context,
+	.name = "kvm-hv",
+	.event_init = kvmppc_pmu_event_init,
+	.add = kvmppc_pmu_add,
+	.del = kvmppc_pmu_del,
+	.read = kvmppc_pmu_read,
+	.attr_groups = kvmppc_pmu_attr_groups,
+	.type = -1,
+	.scope = PERF_PMU_SCOPE_SYS_WIDE,
+	.capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+};
+
+static int __init kvmppc_register_pmu(void)
+{
+	int rc = -EOPNOTSUPP;
+
+	/* only support events for nestedv2 right now */
+	if (kvmhv_is_nestedv2()) {
+		rc = kvmppc_init_hostwide();
+		if (rc)
+			goto out;
+
+		/* Register the pmu */
+		rc = perf_pmu_register(&kvmppc_pmu, kvmppc_pmu.name, -1);
+		if (rc)
+			goto out;
+
+		pr_info("Registered kvm-hv pmu");
+	}
+
+out:
+	return rc;
+}
+
+static void __exit kvmppc_unregister_pmu(void)
+{
+	if (kvmhv_is_nestedv2()) {
+		kvmppc_cleanup_hostwide();
+
+		if (kvmppc_pmu.type != -1)
+			perf_pmu_unregister(&kvmppc_pmu);
+
+		pr_info("kvmhv_pmu unregistered.\n");
+	}
+}
+
+module_init(kvmppc_register_pmu);
+module_exit(kvmppc_unregister_pmu);
+MODULE_DESCRIPTION("KVM PPC Book3s-hv PMU");
+MODULE_AUTHOR("Vaibhav Jain <vaibhav@linux.ibm.com>");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index 9b5133e361a7..bb57b7cfe640 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -593,7 +593,8 @@ static struct power_pmu power10_pmu = {
 	.get_mem_weight		= isa207_get_mem_weight,
 	.disable_pmc		= isa207_disable_pmc,
 	.flags			= PPMU_HAS_SIER | PPMU_ARCH_207S |
-				  PPMU_ARCH_31 | PPMU_HAS_ATTR_CONFIG1,
+				  PPMU_ARCH_31 | PPMU_HAS_ATTR_CONFIG1 |
+				  PPMU_P10,
 	.n_generic		= ARRAY_SIZE(power10_generic_events),
 	.generic_events		= power10_generic_events,
 	.cache_events		= &power10_cache_events,
@@ -634,3 +635,30 @@ int __init init_power10_pmu(void)
 
 	return 0;
 }
+
+static struct power_pmu power11_pmu;
+
+int __init init_power11_pmu(void)
+{
+	unsigned int pvr;
+	int rc;
+
+	pvr = mfspr(SPRN_PVR);
+	if (PVR_VER(pvr) != PVR_POWER11)
+		return -ENODEV;
+
+	/* Set the PERF_REG_EXTENDED_MASK here */
+	PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31;
+
+	power11_pmu = power10_pmu;
+	power11_pmu.name = "Power11";
+
+	rc = register_power_pmu(&power11_pmu);
+	if (rc)
+		return rc;
+
+	/* Tell userspace that EBB is supported */
+	cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB;
+
+	return 0;
+}
diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c
index 5729b6e059de..9f720b522e17 100644
--- a/arch/powerpc/perf/power6-pmu.c
+++ b/arch/powerpc/perf/power6-pmu.c
@@ -335,26 +335,38 @@ static const unsigned int event_alternatives[][MAX_ALT] = {
 	{ 0x3000fe, 0x400056 },			/* PM_DATA_FROM_L3MISS */
 };
 
-/*
- * This could be made more efficient with a binary search on
- * a presorted list, if necessary
- */
 static int find_alternatives_list(u64 event)
 {
-	int i, j;
-	unsigned int alt;
-
-	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
-		if (event < event_alternatives[i][0])
-			return -1;
-		for (j = 0; j < MAX_ALT; ++j) {
-			alt = event_alternatives[i][j];
-			if (!alt || event < alt)
-				break;
-			if (event == alt)
-				return i;
-		}
+	const unsigned int presorted_event_table[] = {
+		0x0130e8, 0x080080, 0x080088, 0x10000a, 0x10000b, 0x10000d, 0x10000e,
+		0x100010, 0x10001a, 0x100026, 0x100054, 0x100056, 0x1000f0, 0x1000f8,
+		0x1000fc, 0x200008, 0x20000e, 0x200010, 0x200012, 0x200054, 0x2000f0,
+		0x2000f2, 0x2000f4, 0x2000f5, 0x2000f6, 0x2000f8, 0x2000fc, 0x2000fe,
+		0x2d0030, 0x30000a, 0x30000c, 0x300010, 0x300012, 0x30001a, 0x300056,
+		0x3000f0, 0x3000f2, 0x3000f6, 0x3000f8, 0x3000fc, 0x3000fe, 0x400006,
+		0x400007, 0x40000a, 0x40000e, 0x400010, 0x400018, 0x400056, 0x4000f0,
+		0x4000f8, 0x600005
+	};
+	const unsigned int event_index_table[] = {
+		0,  1,  2,  3,  4,  1, 5,  6,  7,  8,  9,  10, 11, 12, 13, 12, 14,
+		7,  15, 2,  9,  16, 3, 4,  0,  17, 10, 18, 19, 20, 1,  17, 15, 19,
+		18, 2,  16, 21, 8,  0, 22, 13, 14, 11, 21, 5,  20, 22, 1,  6,  3
+	};
+	int hi = ARRAY_SIZE(presorted_event_table) - 1;
+	int lo = 0;
+
+	while (lo <= hi) {
+		int mid = lo + (hi - lo) / 2;
+		unsigned int alt = presorted_event_table[mid];
+
+		if (alt < event)
+			lo = mid + 1;
+		else if (alt > event)
+			hi = mid - 1;
+		else
+			return event_index_table[mid];
 	}
+
 	return -1;
 }
 
diff --git a/arch/powerpc/perf/vpa-dtl.c b/arch/powerpc/perf/vpa-dtl.c
new file mode 100644
index 000000000000..3c1d1c28deb9
--- /dev/null
+++ b/arch/powerpc/perf/vpa-dtl.c
@@ -0,0 +1,596 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Perf interface to expose Dispatch Trace Log counters.
+ *
+ * Copyright (C) 2024 Kajol Jain, IBM Corporation
+ */
+
+#ifdef CONFIG_PPC_SPLPAR
+#define pr_fmt(fmt) "vpa_dtl: " fmt
+
+#include <asm/dtl.h>
+#include <linux/perf_event.h>
+#include <asm/plpar_wrappers.h>
+#include <linux/vmalloc.h>
+
+#define EVENT(_name, _code)     enum{_name = _code}
+
+/*
+ * Based on Power Architecture Platform Reference(PAPR) documentation,
+ * Table 14.14. Per Virtual Processor Area, below Dispatch Trace Log(DTL)
+ * Enable Mask used to get corresponding virtual processor dispatch
+ * to preempt traces:
+ *   DTL_CEDE(0x1): Trace voluntary (OS initiated) virtual
+ *   processor waits
+ *   DTL_PREEMPT(0x2): Trace time slice preempts
+ *   DTL_FAULT(0x4): Trace virtual partition memory page
+ faults.
+ *   DTL_ALL(0x7): Trace all (DTL_CEDE | DTL_PREEMPT | DTL_FAULT)
+ *
+ * Event codes based on Dispatch Trace Log Enable Mask.
+ */
+EVENT(DTL_CEDE,         0x1);
+EVENT(DTL_PREEMPT,      0x2);
+EVENT(DTL_FAULT,        0x4);
+EVENT(DTL_ALL,          0x7);
+
+GENERIC_EVENT_ATTR(dtl_cede, DTL_CEDE);
+GENERIC_EVENT_ATTR(dtl_preempt, DTL_PREEMPT);
+GENERIC_EVENT_ATTR(dtl_fault, DTL_FAULT);
+GENERIC_EVENT_ATTR(dtl_all, DTL_ALL);
+
+PMU_FORMAT_ATTR(event, "config:0-7");
+
+static struct attribute *events_attr[] = {
+	GENERIC_EVENT_PTR(DTL_CEDE),
+	GENERIC_EVENT_PTR(DTL_PREEMPT),
+	GENERIC_EVENT_PTR(DTL_FAULT),
+	GENERIC_EVENT_PTR(DTL_ALL),
+	NULL
+};
+
+static struct attribute_group event_group = {
+	.name = "events",
+	.attrs = events_attr,
+};
+
+static struct attribute *format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static const struct attribute_group format_group = {
+	.name = "format",
+	.attrs = format_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+	&format_group,
+	&event_group,
+	NULL,
+};
+
+struct vpa_dtl {
+	struct dtl_entry	*buf;
+	u64			last_idx;
+};
+
+struct vpa_pmu_ctx {
+	struct perf_output_handle handle;
+};
+
+struct vpa_pmu_buf {
+	int     nr_pages;
+	bool    snapshot;
+	u64     *base;
+	u64     size;
+	u64     head;
+	u64	head_size;
+	/* boot timebase and frequency needs to be saved only at once */
+	int	boottb_freq_saved;
+	u64	threshold;
+	bool	full;
+};
+
+/*
+ * To corelate each DTL entry with other events across CPU's,
+ * we need to map timebase from "struct dtl_entry" which phyp
+ * provides with boot timebase. This also needs timebase frequency.
+ * Formula is: ((timbase from DTL entry - boot time) / frequency)
+ *
+ * To match with size of "struct dtl_entry" to ease post processing,
+ * padded 24 bytes to the structure.
+ */
+struct boottb_freq {
+	u64	boot_tb;
+	u64	tb_freq;
+	u64	timebase;
+	u64	padded[3];
+};
+
+static DEFINE_PER_CPU(struct vpa_pmu_ctx, vpa_pmu_ctx);
+static DEFINE_PER_CPU(struct vpa_dtl, vpa_dtl_cpu);
+
+/* variable to capture reference count for the active dtl threads */
+static int dtl_global_refc;
+static spinlock_t dtl_global_lock = __SPIN_LOCK_UNLOCKED(dtl_global_lock);
+
+/*
+ * Capture DTL data in AUX buffer
+ */
+static void vpa_dtl_capture_aux(long *n_entries, struct vpa_pmu_buf *buf,
+		struct vpa_dtl *dtl, int index)
+{
+	struct dtl_entry *aux_copy_buf = (struct dtl_entry *)buf->base;
+
+	/*
+	 * check if there is enough space to contain the
+	 * DTL data. If not, save the data for available
+	 * memory and set full to true.
+	 */
+	if (buf->head + *n_entries >= buf->threshold) {
+		*n_entries = buf->threshold - buf->head;
+		buf->full = 1;
+	}
+
+	/*
+	 * Copy to AUX buffer from per-thread address
+	 */
+	memcpy(aux_copy_buf + buf->head, &dtl->buf[index], *n_entries * sizeof(struct dtl_entry));
+
+	if (buf->full) {
+		/*
+		 * Set head of private aux to zero when buffer is full
+		 * so that next data will be copied to beginning of the
+		 * buffer
+		 */
+		buf->head = 0;
+		return;
+	}
+
+	buf->head += *n_entries;
+
+	return;
+}
+
+/*
+ * Function to dump the dispatch trace log buffer data to the
+ * perf data.
+ *
+ * perf_aux_output_begin: This function is called before writing
+ * to AUX area. This returns the pointer to aux area private structure,
+ * ie "struct vpa_pmu_buf" here which is set in setup_aux() function.
+ * The function obtains the output handle (used in perf_aux_output_end).
+ * when capture completes in vpa_dtl_capture_aux(), call perf_aux_output_end()
+ * to commit the recorded data.
+ *
+ * perf_aux_output_end: This function commits data by adjusting the
+ * aux_head of "struct perf_buffer". aux_tail will be moved in perf tools
+ * side when writing the data from aux buffer to perf.data file in disk.
+ *
+ * Here in the private aux structure, we maintain head to know where
+ * to copy data next time in the PMU driver. vpa_pmu_buf->head is moved to
+ * maintain the aux head for PMU driver. It is responsiblity of PMU
+ * driver to make sure data is copied between perf_aux_output_begin and
+ * perf_aux_output_end.
+ *
+ * After data is copied in vpa_dtl_capture_aux() function, perf_aux_output_end()
+ * is called to move the aux->head of "struct perf_buffer" to indicate size of
+ * data in aux buffer. This will post a PERF_RECORD_AUX into the perf buffer.
+ * Data will be written to disk only when the allocated buffer is full.
+ *
+ * By this approach, all the DTL data will be present as-is in the
+ * perf.data. The data will be pre-processed in perf tools side when doing
+ * perf report/perf script and this will avoid time taken to create samples
+ * in the kernel space.
+ */
+static void vpa_dtl_dump_sample_data(struct perf_event *event)
+{
+	u64 cur_idx, last_idx, i;
+	u64 boot_tb;
+	struct boottb_freq boottb_freq;
+
+	/* actual number of entries read */
+	long n_read = 0, read_size = 0;
+
+	/* number of entries added to dtl buffer */
+	long n_req;
+
+	struct vpa_pmu_ctx *vpa_ctx = this_cpu_ptr(&vpa_pmu_ctx);
+
+	struct vpa_pmu_buf *aux_buf;
+
+	struct vpa_dtl *dtl = &per_cpu(vpa_dtl_cpu, event->cpu);
+	u64 size;
+
+	cur_idx = be64_to_cpu(lppaca_of(event->cpu).dtl_idx);
+	last_idx = dtl->last_idx;
+
+	if (last_idx + N_DISPATCH_LOG <= cur_idx)
+		last_idx = cur_idx - N_DISPATCH_LOG + 1;
+
+	n_req = cur_idx - last_idx;
+
+	/* no new entry added to the buffer, return */
+	if (n_req <= 0)
+		return;
+
+	dtl->last_idx = last_idx + n_req;
+	boot_tb = get_boot_tb();
+
+	i = last_idx % N_DISPATCH_LOG;
+
+	aux_buf = perf_aux_output_begin(&vpa_ctx->handle, event);
+	if (!aux_buf) {
+		pr_debug("returning. no aux\n");
+		return;
+	}
+
+	if (!aux_buf->boottb_freq_saved) {
+		pr_debug("Copying boot tb to aux buffer: %lld\n", boot_tb);
+		/* Save boot_tb to convert raw timebase to it's relative system boot time */
+		boottb_freq.boot_tb = boot_tb;
+		/* Save tb_ticks_per_sec to convert timebase to sec */
+		boottb_freq.tb_freq = tb_ticks_per_sec;
+		boottb_freq.timebase = 0;
+		memcpy(aux_buf->base, &boottb_freq, sizeof(boottb_freq));
+		aux_buf->head += 1;
+		aux_buf->boottb_freq_saved = 1;
+		n_read += 1;
+	}
+
+	/* read the tail of the buffer if we've wrapped */
+	if (i + n_req > N_DISPATCH_LOG) {
+		read_size = N_DISPATCH_LOG - i;
+		vpa_dtl_capture_aux(&read_size, aux_buf, dtl, i);
+		n_req -= read_size;
+		n_read += read_size;
+		i = 0;
+		if (aux_buf->full) {
+			size = (n_read * sizeof(struct dtl_entry));
+			if ((size +  aux_buf->head_size) > aux_buf->size) {
+				size = aux_buf->size - aux_buf->head_size;
+				perf_aux_output_end(&vpa_ctx->handle, size);
+				aux_buf->head = 0;
+				aux_buf->head_size = 0;
+			} else {
+				aux_buf->head_size += (n_read * sizeof(struct dtl_entry));
+				perf_aux_output_end(&vpa_ctx->handle, n_read * sizeof(struct dtl_entry));
+			}
+			goto out;
+		}
+	}
+
+	/* .. and now the head */
+	vpa_dtl_capture_aux(&n_req, aux_buf, dtl, i);
+
+	size = ((n_req + n_read) * sizeof(struct dtl_entry));
+	if ((size +  aux_buf->head_size) > aux_buf->size) {
+		size = aux_buf->size - aux_buf->head_size;
+		perf_aux_output_end(&vpa_ctx->handle, size);
+		aux_buf->head = 0;
+		aux_buf->head_size = 0;
+	} else {
+		aux_buf->head_size += ((n_req + n_read) * sizeof(struct dtl_entry));
+		/* Move the aux->head to indicate size of data in aux buffer */
+		perf_aux_output_end(&vpa_ctx->handle, (n_req + n_read) * sizeof(struct dtl_entry));
+	}
+out:
+	aux_buf->full = 0;
+}
+
+/*
+ * The VPA Dispatch Trace log counters do not interrupt on overflow.
+ * Therefore, the kernel needs to poll the counters to avoid missing
+ * an overflow using hrtimer. The timer interval is based on sample_period
+ * count provided by user, and minimum interval is 1 millisecond.
+ */
+static enum hrtimer_restart vpa_dtl_hrtimer_handle(struct hrtimer *hrtimer)
+{
+	struct perf_event *event;
+	u64 period;
+
+	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
+
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return HRTIMER_NORESTART;
+
+	vpa_dtl_dump_sample_data(event);
+	period = max_t(u64, NSEC_PER_MSEC, event->hw.sample_period);
+	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
+
+	return HRTIMER_RESTART;
+}
+
+static void vpa_dtl_start_hrtimer(struct perf_event *event)
+{
+	u64 period;
+	struct hw_perf_event *hwc = &event->hw;
+
+	period = max_t(u64, NSEC_PER_MSEC, hwc->sample_period);
+	hrtimer_start(&hwc->hrtimer, ns_to_ktime(period), HRTIMER_MODE_REL_PINNED);
+}
+
+static void vpa_dtl_stop_hrtimer(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	hrtimer_cancel(&hwc->hrtimer);
+}
+
+static void vpa_dtl_reset_global_refc(struct perf_event *event)
+{
+	spin_lock(&dtl_global_lock);
+	dtl_global_refc--;
+	if (dtl_global_refc <= 0) {
+		dtl_global_refc = 0;
+		up_write(&dtl_access_lock);
+	}
+	spin_unlock(&dtl_global_lock);
+}
+
+static int vpa_dtl_mem_alloc(int cpu)
+{
+	struct vpa_dtl *dtl = &per_cpu(vpa_dtl_cpu, cpu);
+	struct dtl_entry *buf = NULL;
+
+	/* Check for dispatch trace log buffer cache */
+	if (!dtl_cache)
+		return -ENOMEM;
+
+	buf = kmem_cache_alloc_node(dtl_cache, GFP_KERNEL | GFP_ATOMIC, cpu_to_node(cpu));
+	if (!buf) {
+		pr_warn("buffer allocation failed for cpu %d\n", cpu);
+		return -ENOMEM;
+	}
+	dtl->buf = buf;
+	return 0;
+}
+
+static int vpa_dtl_event_init(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/* test the event attr type for PMU enumeration */
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (!perfmon_capable())
+		return -EACCES;
+
+	/* Return if this is a counting event */
+	if (!is_sampling_event(event))
+		return -EOPNOTSUPP;
+
+	/* no branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	/* Invalid eventcode */
+	switch (event->attr.config) {
+	case DTL_LOG_CEDE:
+	case DTL_LOG_PREEMPT:
+	case DTL_LOG_FAULT:
+	case DTL_LOG_ALL:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	spin_lock(&dtl_global_lock);
+
+	/*
+	 * To ensure there are no other conflicting dtl users
+	 * (example: /proc/powerpc/vcpudispatch_stats or debugfs dtl),
+	 * below code try to take the dtl_access_lock.
+	 * The dtl_access_lock is a rwlock defined in dtl.h, which is used
+	 * to unsure there is no conflicting dtl users.
+	 * Based on below code, vpa_dtl pmu tries to take write access lock
+	 * and also checks for dtl_global_refc, to make sure that the
+	 * dtl_access_lock is taken by vpa_dtl pmu interface.
+	 */
+	if (dtl_global_refc == 0 && !down_write_trylock(&dtl_access_lock)) {
+		spin_unlock(&dtl_global_lock);
+		return -EBUSY;
+	}
+
+	/* Allocate dtl buffer memory */
+	if (vpa_dtl_mem_alloc(event->cpu)) {
+		spin_unlock(&dtl_global_lock);
+		return -ENOMEM;
+	}
+
+	/*
+	 * Increment the number of active vpa_dtl pmu threads. The
+	 * dtl_global_refc is used to keep count of cpu threads that
+	 * currently capturing dtl data using vpa_dtl pmu interface.
+	 */
+	dtl_global_refc++;
+
+	spin_unlock(&dtl_global_lock);
+
+	hrtimer_setup(&hwc->hrtimer, vpa_dtl_hrtimer_handle, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+
+	/*
+	 * Since hrtimers have a fixed rate, we can do a static freq->period
+	 * mapping and avoid the whole period adjust feedback stuff.
+	 */
+	if (event->attr.freq) {
+		long freq = event->attr.sample_freq;
+
+		event->attr.sample_period = NSEC_PER_SEC / freq;
+		hwc->sample_period = event->attr.sample_period;
+		local64_set(&hwc->period_left, hwc->sample_period);
+		hwc->last_period = hwc->sample_period;
+		event->attr.freq = 0;
+	}
+
+	event->destroy = vpa_dtl_reset_global_refc;
+	return 0;
+}
+
+static int vpa_dtl_event_add(struct perf_event *event, int flags)
+{
+	int ret, hwcpu;
+	unsigned long addr;
+	struct vpa_dtl *dtl = &per_cpu(vpa_dtl_cpu, event->cpu);
+
+	/*
+	 * Register our dtl buffer with the hypervisor. The
+	 * HV expects the buffer size to be passed in the second
+	 * word of the buffer. Refer section '14.11.3.2. H_REGISTER_VPA'
+	 * from PAPR for more information.
+	 */
+	((u32 *)dtl->buf)[1] = cpu_to_be32(DISPATCH_LOG_BYTES);
+	dtl->last_idx = 0;
+
+	hwcpu = get_hard_smp_processor_id(event->cpu);
+	addr = __pa(dtl->buf);
+
+	ret = register_dtl(hwcpu, addr);
+	if (ret) {
+		pr_warn("DTL registration for cpu %d (hw %d) failed with %d\n",
+			event->cpu, hwcpu, ret);
+		return ret;
+	}
+
+	/* set our initial buffer indices */
+	lppaca_of(event->cpu).dtl_idx = 0;
+
+	/*
+	 * Ensure that our updates to the lppaca fields have
+	 * occurred before we actually enable the logging
+	 */
+	smp_wmb();
+
+	/* enable event logging */
+	lppaca_of(event->cpu).dtl_enable_mask = event->attr.config;
+
+	vpa_dtl_start_hrtimer(event);
+
+	return 0;
+}
+
+static void vpa_dtl_event_del(struct perf_event *event, int flags)
+{
+	int hwcpu = get_hard_smp_processor_id(event->cpu);
+	struct vpa_dtl *dtl = &per_cpu(vpa_dtl_cpu, event->cpu);
+
+	vpa_dtl_stop_hrtimer(event);
+	unregister_dtl(hwcpu);
+	kmem_cache_free(dtl_cache, dtl->buf);
+	dtl->buf = NULL;
+	lppaca_of(event->cpu).dtl_enable_mask = 0x0;
+}
+
+/*
+ * This function definition is empty as vpa_dtl_dump_sample_data
+ * is used to parse and dump the dispatch trace log data,
+ * to perf data.
+ */
+static void vpa_dtl_event_read(struct perf_event *event)
+{
+}
+
+/*
+ * Set up pmu-private data structures for an AUX area
+ * **pages contains the aux buffer allocated for this event
+ * for the corresponding cpu. rb_alloc_aux uses "alloc_pages_node"
+ * and returns pointer to each page address. Map these pages to
+ * contiguous space using vmap and use that as base address.
+ *
+ * The aux private data structure ie, "struct vpa_pmu_buf" mainly
+ * saves
+ * - buf->base: aux buffer base address
+ * - buf->head: offset from base address where data will be written to.
+ * - buf->size: Size of allocated memory
+ */
+static void *vpa_dtl_setup_aux(struct perf_event *event, void **pages,
+		int nr_pages, bool snapshot)
+{
+	int i, cpu = event->cpu;
+	struct vpa_pmu_buf *buf __free(kfree) = NULL;
+	struct page **pglist __free(kfree) = NULL;
+
+	/* We need at least one page for this to work. */
+	if (!nr_pages)
+		return NULL;
+
+	if (cpu == -1)
+		cpu = raw_smp_processor_id();
+
+	buf = kzalloc_node(sizeof(*buf), GFP_KERNEL, cpu_to_node(cpu));
+	if (!buf)
+		return NULL;
+
+	pglist = kcalloc(nr_pages, sizeof(*pglist), GFP_KERNEL);
+	if (!pglist)
+		return NULL;
+
+	for (i = 0; i < nr_pages; ++i)
+		pglist[i] = virt_to_page(pages[i]);
+
+	buf->base = vmap(pglist, nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!buf->base)
+		return NULL;
+
+	buf->nr_pages = nr_pages;
+	buf->snapshot = false;
+
+	buf->size = nr_pages << PAGE_SHIFT;
+	buf->head = 0;
+	buf->head_size = 0;
+	buf->boottb_freq_saved = 0;
+	buf->threshold = ((buf->size - 32) / sizeof(struct dtl_entry));
+	return no_free_ptr(buf);
+}
+
+/*
+ * free pmu-private AUX data structures
+ */
+static void vpa_dtl_free_aux(void *aux)
+{
+	struct vpa_pmu_buf *buf = aux;
+
+	vunmap(buf->base);
+	kfree(buf);
+}
+
+static struct pmu vpa_dtl_pmu = {
+	.task_ctx_nr = perf_invalid_context,
+
+	.name = "vpa_dtl",
+	.attr_groups = attr_groups,
+	.event_init  = vpa_dtl_event_init,
+	.add         = vpa_dtl_event_add,
+	.del         = vpa_dtl_event_del,
+	.read        = vpa_dtl_event_read,
+	.setup_aux   = vpa_dtl_setup_aux,
+	.free_aux    = vpa_dtl_free_aux,
+	.capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_EXCLUSIVE,
+};
+
+static int vpa_dtl_init(void)
+{
+	int r;
+
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		pr_debug("not a shared virtualized system, not enabling\n");
+		return -ENODEV;
+	}
+
+	/* This driver is intended only for L1 host. */
+	if (is_kvm_guest()) {
+		pr_debug("Only supported for L1 host system\n");
+		return -ENODEV;
+	}
+
+	r = perf_pmu_register(&vpa_dtl_pmu, vpa_dtl_pmu.name, -1);
+	if (r)
+		return r;
+
+	return 0;
+}
+
+device_initcall(vpa_dtl_init);
+#endif //CONFIG_PPC_SPLPAR
diff --git a/arch/powerpc/perf/vpa-pmu.c b/arch/powerpc/perf/vpa-pmu.c
new file mode 100644
index 000000000000..840733468959
--- /dev/null
+++ b/arch/powerpc/perf/vpa-pmu.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Performance monitoring support for Virtual Processor Area(VPA) based counters
+ *
+ * Copyright (C) 2024 IBM Corporation
+ */
+#define pr_fmt(fmt) "vpa_pmu: " fmt
+
+#include <linux/module.h>
+#include <linux/perf_event.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s_64.h>
+
+#define MODULE_VERS "1.0"
+#define MODULE_NAME "pseries_vpa_pmu"
+
+#define EVENT(_name, _code)     enum{_name = _code}
+
+#define VPA_PMU_EVENT_VAR(_id)  event_attr_##_id
+#define VPA_PMU_EVENT_PTR(_id)  (&event_attr_##_id.attr.attr)
+
+static ssize_t vpa_pmu_events_sysfs_show(struct device *dev,
+					 struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+#define VPA_PMU_EVENT_ATTR(_name, _id)				\
+	PMU_EVENT_ATTR(_name, VPA_PMU_EVENT_VAR(_id), _id,	\
+			vpa_pmu_events_sysfs_show)
+
+EVENT(L1_TO_L2_CS_LAT,	0x1);
+EVENT(L2_TO_L1_CS_LAT,	0x2);
+EVENT(L2_RUNTIME_AGG,	0x3);
+
+VPA_PMU_EVENT_ATTR(l1_to_l2_lat,  L1_TO_L2_CS_LAT);
+VPA_PMU_EVENT_ATTR(l2_to_l1_lat,  L2_TO_L1_CS_LAT);
+VPA_PMU_EVENT_ATTR(l2_runtime_agg, L2_RUNTIME_AGG);
+
+static struct attribute *vpa_pmu_events_attr[] = {
+	VPA_PMU_EVENT_PTR(L1_TO_L2_CS_LAT),
+	VPA_PMU_EVENT_PTR(L2_TO_L1_CS_LAT),
+	VPA_PMU_EVENT_PTR(L2_RUNTIME_AGG),
+	NULL
+};
+
+static const struct attribute_group vpa_pmu_events_group = {
+	.name = "events",
+	.attrs = vpa_pmu_events_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-31");
+static struct attribute *vpa_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group vpa_pmu_format_group = {
+	.name = "format",
+	.attrs = vpa_pmu_format_attr,
+};
+
+static const struct attribute_group *vpa_pmu_attr_groups[] = {
+	&vpa_pmu_events_group,
+	&vpa_pmu_format_group,
+	NULL
+};
+
+static int vpa_pmu_event_init(struct perf_event *event)
+{
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	/* it does not support event sampling mode */
+	if (is_sampling_event(event))
+		return -EOPNOTSUPP;
+
+	/* no branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	/* Invalid event code */
+	if ((event->attr.config <= 0) || (event->attr.config > 3))
+		return -EINVAL;
+
+	return 0;
+}
+
+static unsigned long get_counter_data(struct perf_event *event)
+{
+	unsigned int config = event->attr.config;
+	u64 data;
+
+	switch (config) {
+	case L1_TO_L2_CS_LAT:
+		if (event->attach_state & PERF_ATTACH_TASK)
+			data = kvmhv_get_l1_to_l2_cs_time_vcpu();
+		else
+			data = kvmhv_get_l1_to_l2_cs_time();
+		break;
+	case L2_TO_L1_CS_LAT:
+		if (event->attach_state & PERF_ATTACH_TASK)
+			data = kvmhv_get_l2_to_l1_cs_time_vcpu();
+		else
+			data = kvmhv_get_l2_to_l1_cs_time();
+		break;
+	case L2_RUNTIME_AGG:
+		if (event->attach_state & PERF_ATTACH_TASK)
+			data = kvmhv_get_l2_runtime_agg_vcpu();
+		else
+			data = kvmhv_get_l2_runtime_agg();
+		break;
+	default:
+		data = 0;
+		break;
+	}
+
+	return data;
+}
+
+static int vpa_pmu_add(struct perf_event *event, int flags)
+{
+	u64 data;
+
+	kvmhv_set_l2_counters_status(smp_processor_id(), true);
+
+	data = get_counter_data(event);
+	local64_set(&event->hw.prev_count, data);
+
+	return 0;
+}
+
+static void vpa_pmu_read(struct perf_event *event)
+{
+	u64 prev_data, new_data, final_data;
+
+	prev_data = local64_read(&event->hw.prev_count);
+	new_data = get_counter_data(event);
+	final_data = new_data - prev_data;
+
+	local64_add(final_data, &event->count);
+}
+
+static void vpa_pmu_del(struct perf_event *event, int flags)
+{
+	vpa_pmu_read(event);
+
+	/*
+	 * Disable vpa counter accumulation
+	 */
+	kvmhv_set_l2_counters_status(smp_processor_id(), false);
+}
+
+static struct pmu vpa_pmu = {
+	.module		= THIS_MODULE,
+	.task_ctx_nr	= perf_sw_context,
+	.name		= "vpa_pmu",
+	.event_init	= vpa_pmu_event_init,
+	.add		= vpa_pmu_add,
+	.del		= vpa_pmu_del,
+	.read		= vpa_pmu_read,
+	.attr_groups	= vpa_pmu_attr_groups,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+};
+
+static int __init pseries_vpa_pmu_init(void)
+{
+	/*
+	 * List of current Linux on Power platforms and
+	 * this driver is supported only in PowerVM LPAR
+	 * (L1) platform.
+	 *
+	 *	Enabled    Linux on Power Platforms
+	 *      ----------------------------------------
+	 *        [X]      PowerVM LPAR (L1)
+	 *        [ ]      KVM Guest On PowerVM KoP(L2)
+	 *        [ ]      Baremetal(PowerNV)
+	 *        [ ]      KVM Guest On PowerNV
+	 */
+	if (!firmware_has_feature(FW_FEATURE_LPAR) || is_kvm_guest())
+		return -ENODEV;
+
+	perf_pmu_register(&vpa_pmu, vpa_pmu.name, -1);
+	pr_info("Virtual Processor Area PMU registered.\n");
+
+	return 0;
+}
+
+static void __exit pseries_vpa_pmu_cleanup(void)
+{
+	perf_pmu_unregister(&vpa_pmu);
+	pr_info("Virtual Processor Area PMU unregistered.\n");
+}
+
+module_init(pseries_vpa_pmu_init);
+module_exit(pseries_vpa_pmu_cleanup);
+MODULE_DESCRIPTION("Perf Driver for pSeries VPA pmu counter");
+MODULE_AUTHOR("Kajol Jain <kjain@linux.ibm.com>");
+MODULE_AUTHOR("Madhavan Srinivasan <maddy@linux.ibm.com>");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig
deleted file mode 100644
index b3c466c50535..000000000000
--- a/arch/powerpc/platforms/40x/Kconfig
+++ /dev/null
@@ -1,78 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-config ACADIA
-	bool "Acadia"
-	depends on 40x
-	select PPC40x_SIMPLE
-	select 405EZ
-	help
-	  This option enables support for the AMCC 405EZ Acadia evaluation board.
-
-config HOTFOOT
-	bool "Hotfoot"
-	depends on 40x
-	select PPC40x_SIMPLE
-	select FORCE_PCI
-	help
-	  This option enables support for the ESTEEM 195E Hotfoot board.
-
-config KILAUEA
-	bool "Kilauea"
-	depends on 40x
-	select 405EX
-	select PPC40x_SIMPLE
-	select PPC4xx_PCI_EXPRESS
-	select FORCE_PCI
-	select PCI_MSI
-	help
-	  This option enables support for the AMCC PPC405EX evaluation board.
-
-config MAKALU
-	bool "Makalu"
-	depends on 40x
-	select 405EX
-	select FORCE_PCI
-	select PPC4xx_PCI_EXPRESS
-	select PPC40x_SIMPLE
-	help
-	  This option enables support for the AMCC PPC405EX board.
-
-config OBS600
-	bool "OpenBlockS 600"
-	depends on 40x
-	select 405EX
-	select PPC40x_SIMPLE
-	help
-	  This option enables support for PlatHome OpenBlockS 600 server
-
-config PPC40x_SIMPLE
-	bool "Simple PowerPC 40x board support"
-	depends on 40x
-	help
-	  This option enables the simple PowerPC 40x platform support.
-
-config 405EX
-	bool
-	select IBM_EMAC_EMAC4 if IBM_EMAC
-	select IBM_EMAC_RGMII if IBM_EMAC
-
-config 405EZ
-	bool
-	select IBM_EMAC_NO_FLOW_CTRL if IBM_EMAC
-	select IBM_EMAC_MAL_CLR_ICINTSTAT if IBM_EMAC
-	select IBM_EMAC_MAL_COMMON_ERR if IBM_EMAC
-
-config PPC4xx_GPIO
-	bool "PPC4xx GPIO support"
-	depends on 40x
-	select GPIOLIB
-	select OF_GPIO_MM_GPIOCHIP
-	help
-	  Enable gpiolib support for ppc40x based boards
-
-config APM8018X
-	bool "APM8018X"
-	depends on 40x
-	select PPC40x_SIMPLE
-	help
-	  This option enables support for the AppliedMicro APM8018X evaluation
-	  board.
diff --git a/arch/powerpc/platforms/40x/Makefile b/arch/powerpc/platforms/40x/Makefile
deleted file mode 100644
index 122de98527c4..000000000000
--- a/arch/powerpc/platforms/40x/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_PPC40x_SIMPLE)		+= ppc40x_simple.o
diff --git a/arch/powerpc/platforms/40x/ppc40x_simple.c b/arch/powerpc/platforms/40x/ppc40x_simple.c
deleted file mode 100644
index e454e9d2eff1..000000000000
--- a/arch/powerpc/platforms/40x/ppc40x_simple.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Generic PowerPC 40x platform support
- *
- * Copyright 2008 IBM Corporation
- *
- * This implements simple platform support for PowerPC 44x chips.  This is
- * mostly used for eval boards or other simple and "generic" 44x boards.  If
- * your board has custom functions or hardware, then you will likely want to
- * implement your own board.c file to accommodate it.
- */
-
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/ppc4xx.h>
-#include <asm/time.h>
-#include <asm/udbg.h>
-#include <asm/uic.h>
-
-#include <linux/init.h>
-#include <linux/of_platform.h>
-
-static const struct of_device_id ppc40x_of_bus[] __initconst = {
-	{ .compatible = "ibm,plb3", },
-	{ .compatible = "ibm,plb4", },
-	{ .compatible = "ibm,opb", },
-	{ .compatible = "ibm,ebc", },
-	{ .compatible = "simple-bus", },
-	{},
-};
-
-static int __init ppc40x_device_probe(void)
-{
-	of_platform_bus_probe(NULL, ppc40x_of_bus, NULL);
-
-	return 0;
-}
-machine_device_initcall(ppc40x_simple, ppc40x_device_probe);
-
-/* This is the list of boards that can be supported by this simple
- * platform code.  This does _not_ mean the boards are compatible,
- * as they most certainly are not from a device tree perspective.
- * However, their differences are handled by the device tree and the
- * drivers and therefore they don't need custom board support files.
- *
- * Again, if your board needs to do things differently then create a
- * board.c file for it rather than adding it to this list.
- */
-static const char * const board[] __initconst = {
-	"amcc,acadia",
-	"amcc,haleakala",
-	"amcc,kilauea",
-	"amcc,makalu",
-	"apm,klondike",
-	"est,hotfoot",
-	"plathome,obs600",
-	NULL
-};
-
-static int __init ppc40x_probe(void)
-{
-	if (of_device_compatible_match(of_root, board)) {
-		pci_set_flags(PCI_REASSIGN_ALL_RSRC);
-		return 1;
-	}
-
-	return 0;
-}
-
-define_machine(ppc40x_simple) {
-	.name = "PowerPC 40x Platform",
-	.probe = ppc40x_probe,
-	.progress = udbg_progress,
-	.init_IRQ = uic_init_tree,
-	.get_irq = uic_get_irq,
-	.restart = ppc4xx_reset_system,
-};
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 1624ebf95497..fc79f8466933 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -173,6 +173,7 @@ config ISS4xx
 config CURRITUCK
 	bool "IBM Currituck (476fpe) Support"
 	depends on PPC_47x
+	select I2C
 	select SWIOTLB
 	select 476FPE
 	select FORCE_PCI
@@ -230,7 +231,6 @@ config PPC4xx_GPIO
 	bool "PPC4xx GPIO support"
 	depends on 44x
 	select GPIOLIB
-	select OF_GPIO_MM_GPIOCHIP
 	help
 	  Enable gpiolib support for ppc440 based boards
 
diff --git a/arch/powerpc/platforms/44x/Makefile b/arch/powerpc/platforms/44x/Makefile
index 5ba031f57652..ca7b1bb442d9 100644
--- a/arch/powerpc/platforms/44x/Makefile
+++ b/arch/powerpc/platforms/44x/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-y	+= misc_44x.o machine_check.o
+obj-y	+= misc_44x.o machine_check.o uic.o soc.o
 ifneq ($(CONFIG_PPC4xx_CPM),y)
 obj-y	+= idle.o
 endif
@@ -12,3 +12,7 @@ obj-$(CONFIG_CANYONLANDS)+= canyonlands.o
 obj-$(CONFIG_CURRITUCK)	+= ppc476.o
 obj-$(CONFIG_AKEBONO)	+= ppc476.o
 obj-$(CONFIG_FSP2)	+= fsp2.o
+obj-$(CONFIG_PCI)		+= pci.o
+obj-$(CONFIG_PPC4xx_HSTA_MSI)	+= hsta_msi.o
+obj-$(CONFIG_PPC4xx_CPM)	+= cpm.o
+obj-$(CONFIG_PPC4xx_GPIO)	+= gpio.o
diff --git a/arch/powerpc/platforms/4xx/cpm.c b/arch/powerpc/platforms/44x/cpm.c
index 182e12855c27..670f8ad4465b 100644
--- a/arch/powerpc/platforms/4xx/cpm.c
+++ b/arch/powerpc/platforms/44x/cpm.c
@@ -18,7 +18,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/sysfs.h>
 #include <linux/cpu.h>
 #include <linux/suspend.h>
diff --git a/arch/powerpc/platforms/4xx/gpio.c b/arch/powerpc/platforms/44x/gpio.c
index e5f2319e5cbe..aea0d913b59d 100644
--- a/arch/powerpc/platforms/4xx/gpio.c
+++ b/arch/powerpc/platforms/44x/gpio.c
@@ -14,10 +14,10 @@
 #include <linux/spinlock.h>
 #include <linux/io.h>
 #include <linux/of.h>
-#include <linux/gpio/legacy-of-mm-gpiochip.h>
 #include <linux/gpio/driver.h>
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/platform_device.h>
 
 #define GPIO_MASK(gpio)		(0x80000000 >> (gpio))
 #define GPIO_MASK2(gpio)	(0xc0000000 >> ((gpio) * 2))
@@ -45,7 +45,8 @@ struct ppc4xx_gpio {
 };
 
 struct ppc4xx_gpio_chip {
-	struct of_mm_gpio_chip mm_gc;
+	struct gpio_chip gc;
+	void __iomem *regs;
 	spinlock_t lock;
 };
 
@@ -57,8 +58,8 @@ struct ppc4xx_gpio_chip {
 
 static int ppc4xx_gpio_get(struct gpio_chip *gc, unsigned int gpio)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct ppc4xx_gpio __iomem *regs = mm_gc->regs;
+	struct ppc4xx_gpio_chip *chip = gpiochip_get_data(gc);
+	struct ppc4xx_gpio __iomem *regs = chip->regs;
 
 	return !!(in_be32(&regs->ir) & GPIO_MASK(gpio));
 }
@@ -66,8 +67,8 @@ static int ppc4xx_gpio_get(struct gpio_chip *gc, unsigned int gpio)
 static inline void
 __ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct ppc4xx_gpio __iomem *regs = mm_gc->regs;
+	struct ppc4xx_gpio_chip *chip = gpiochip_get_data(gc);
+	struct ppc4xx_gpio __iomem *regs = chip->regs;
 
 	if (val)
 		setbits32(&regs->or, GPIO_MASK(gpio));
@@ -75,8 +76,7 @@ __ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 		clrbits32(&regs->or, GPIO_MASK(gpio));
 }
 
-static void
-ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
+static int ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 {
 	struct ppc4xx_gpio_chip *chip = gpiochip_get_data(gc);
 	unsigned long flags;
@@ -88,13 +88,14 @@ ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 	spin_unlock_irqrestore(&chip->lock, flags);
 
 	pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val);
+
+	return 0;
 }
 
 static int ppc4xx_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
 	struct ppc4xx_gpio_chip *chip = gpiochip_get_data(gc);
-	struct ppc4xx_gpio __iomem *regs = mm_gc->regs;
+	struct ppc4xx_gpio __iomem *regs = chip->regs;
 	unsigned long flags;
 
 	spin_lock_irqsave(&chip->lock, flags);
@@ -122,9 +123,8 @@ static int ppc4xx_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 static int
 ppc4xx_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
 	struct ppc4xx_gpio_chip *chip = gpiochip_get_data(gc);
-	struct ppc4xx_gpio __iomem *regs = mm_gc->regs;
+	struct ppc4xx_gpio __iomem *regs = chip->regs;
 	unsigned long flags;
 
 	spin_lock_irqsave(&chip->lock, flags);
@@ -154,42 +154,57 @@ ppc4xx_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 	return 0;
 }
 
-static int __init ppc4xx_add_gpiochips(void)
+static int ppc4xx_gpio_probe(struct platform_device *ofdev)
 {
-	struct device_node *np;
-
-	for_each_compatible_node(np, NULL, "ibm,ppc4xx-gpio") {
-		int ret;
-		struct ppc4xx_gpio_chip *ppc4xx_gc;
-		struct of_mm_gpio_chip *mm_gc;
-		struct gpio_chip *gc;
-
-		ppc4xx_gc = kzalloc(sizeof(*ppc4xx_gc), GFP_KERNEL);
-		if (!ppc4xx_gc) {
-			ret = -ENOMEM;
-			goto err;
-		}
-
-		spin_lock_init(&ppc4xx_gc->lock);
-
-		mm_gc = &ppc4xx_gc->mm_gc;
-		gc = &mm_gc->gc;
-
-		gc->ngpio = 32;
-		gc->direction_input = ppc4xx_gpio_dir_in;
-		gc->direction_output = ppc4xx_gpio_dir_out;
-		gc->get = ppc4xx_gpio_get;
-		gc->set = ppc4xx_gpio_set;
-
-		ret = of_mm_gpiochip_add_data(np, mm_gc, ppc4xx_gc);
-		if (ret)
-			goto err;
-		continue;
-err:
-		pr_err("%pOF: registration failed with status %d\n", np, ret);
-		kfree(ppc4xx_gc);
-		/* try others anyway */
-	}
-	return 0;
+	struct device *dev = &ofdev->dev;
+	struct device_node *np = dev->of_node;
+	struct ppc4xx_gpio_chip *chip;
+	struct gpio_chip *gc;
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	spin_lock_init(&chip->lock);
+
+	gc = &chip->gc;
+
+	gc->base = -1;
+	gc->ngpio = 32;
+	gc->direction_input = ppc4xx_gpio_dir_in;
+	gc->direction_output = ppc4xx_gpio_dir_out;
+	gc->get = ppc4xx_gpio_get;
+	gc->set = ppc4xx_gpio_set;
+
+	gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np);
+	if (!gc->label)
+		return -ENOMEM;
+
+	chip->regs = devm_of_iomap(dev, np, 0, NULL);
+	if (IS_ERR(chip->regs))
+		return PTR_ERR(chip->regs);
+
+	return devm_gpiochip_add_data(dev, gc, chip);
+}
+
+static const struct of_device_id ppc4xx_gpio_match[] = {
+	{
+		.compatible = "ibm,ppc4xx-gpio",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, ppc4xx_gpio_match);
+
+static struct platform_driver ppc4xx_gpio_driver = {
+	.probe		= ppc4xx_gpio_probe,
+	.driver		= {
+		.name	= "ppc4xx-gpio",
+		.of_match_table	= ppc4xx_gpio_match,
+	},
+};
+
+static int __init ppc4xx_gpio_init(void)
+{
+	return platform_driver_register(&ppc4xx_gpio_driver);
 }
-arch_initcall(ppc4xx_add_gpiochips);
+arch_initcall(ppc4xx_gpio_init);
diff --git a/arch/powerpc/platforms/4xx/hsta_msi.c b/arch/powerpc/platforms/44x/hsta_msi.c
index e11b57a62b05..c6bd846b0d65 100644
--- a/arch/powerpc/platforms/4xx/hsta_msi.c
+++ b/arch/powerpc/platforms/44x/hsta_msi.c
@@ -11,7 +11,7 @@
 #include <linux/msi.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/pci.h>
 #include <linux/semaphore.h>
 #include <asm/msi_bitmap.h>
diff --git a/arch/powerpc/platforms/44x/idle.c b/arch/powerpc/platforms/44x/idle.c
index f533b495e7db..e2eeef8dff78 100644
--- a/arch/powerpc/platforms/44x/idle.c
+++ b/arch/powerpc/platforms/44x/idle.c
@@ -27,7 +27,7 @@ static void ppc44x_idle(void)
 	isync();
 }
 
-int __init ppc44x_idle_init(void)
+static int __init ppc44x_idle_init(void)
 {
 	if (!mode_spin) {
 		/* If we are not setting spin mode 
diff --git a/arch/powerpc/platforms/44x/machine_check.c b/arch/powerpc/platforms/44x/machine_check.c
index 5d19daacd78a..85ff33a8d9b6 100644
--- a/arch/powerpc/platforms/44x/machine_check.c
+++ b/arch/powerpc/platforms/44x/machine_check.c
@@ -9,6 +9,21 @@
 #include <asm/reg.h>
 #include <asm/cacheflush.h>
 
+int machine_check_4xx(struct pt_regs *regs)
+{
+	unsigned long reason = regs->esr;
+
+	if (reason & ESR_IMCP) {
+		printk("Instruction");
+		mtspr(SPRN_ESR, reason & ~ESR_IMCP);
+	} else
+		printk("Data");
+
+	printk(" machine check in kernel mode.\n");
+
+	return 0;
+}
+
 int machine_check_440A(struct pt_regs *regs)
 {
 	unsigned long reason = regs->esr;
diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/44x/pci.c
index 48626615b18b..364aeb86ab64 100644
--- a/arch/powerpc/platforms/4xx/pci.c
+++ b/arch/powerpc/platforms/44x/pci.c
@@ -94,10 +94,8 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose,
 					  struct resource *res)
 {
 	u64 size;
-	const u32 *ranges;
-	int rlen;
-	int pna = of_n_addr_cells(hose->dn);
-	int np = pna + 5;
+	struct of_range_parser parser;
+	struct of_range range;
 
 	/* Default */
 	res->start = 0;
@@ -105,18 +103,15 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose,
 	res->end = size - 1;
 	res->flags = IORESOURCE_MEM | IORESOURCE_PREFETCH;
 
-	/* Get dma-ranges property */
-	ranges = of_get_property(hose->dn, "dma-ranges", &rlen);
-	if (ranges == NULL)
+	if (of_pci_dma_range_parser_init(&parser, hose->dn))
 		goto out;
 
-	/* Walk it */
-	while ((rlen -= np * 4) >= 0) {
-		u32 pci_space = ranges[0];
-		u64 pci_addr = of_read_number(ranges + 1, 2);
-		u64 cpu_addr = of_translate_dma_address(hose->dn, ranges + 3);
-		size = of_read_number(ranges + pna + 3, 2);
-		ranges += np;
+	for_each_of_range(&parser, &range) {
+		u32 pci_space = range.flags;
+		u64 pci_addr = range.bus_addr;
+		u64 cpu_addr = range.cpu_addr;
+		size = range.size;
+
 		if (cpu_addr == OF_BAD_ADDR || size == 0)
 			continue;
 
@@ -1263,102 +1258,6 @@ static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = {
 
 #endif /* CONFIG_44x */
 
-#ifdef CONFIG_40x
-
-static int __init ppc405ex_pciex_core_init(struct device_node *np)
-{
-	/* Nothing to do, return 2 ports */
-	return 2;
-}
-
-static void __init ppc405ex_pcie_phy_reset(struct ppc4xx_pciex_port *port)
-{
-	/* Assert the PE0_PHY reset */
-	mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x01010000);
-	msleep(1);
-
-	/* deassert the PE0_hotreset */
-	if (port->endpoint)
-		mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x01111000);
-	else
-		mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x01101000);
-
-	/* poll for phy !reset */
-	/* XXX FIXME add timeout */
-	while (!(mfdcri(SDR0, port->sdr_base + PESDRn_405EX_PHYSTA) & 0x00001000))
-		;
-
-	/* deassert the PE0_gpl_utl_reset */
-	mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x00101000);
-}
-
-static int __init ppc405ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
-{
-	u32 val;
-
-	if (port->endpoint)
-		val = PTYPE_LEGACY_ENDPOINT;
-	else
-		val = PTYPE_ROOT_PORT;
-
-	mtdcri(SDR0, port->sdr_base + PESDRn_DLPSET,
-	       1 << 24 | val << 20 | LNKW_X1 << 12);
-
-	mtdcri(SDR0, port->sdr_base + PESDRn_UTLSET1, 0x00000000);
-	mtdcri(SDR0, port->sdr_base + PESDRn_UTLSET2, 0x01010000);
-	mtdcri(SDR0, port->sdr_base + PESDRn_405EX_PHYSET1, 0x720F0000);
-	mtdcri(SDR0, port->sdr_base + PESDRn_405EX_PHYSET2, 0x70600003);
-
-	/*
-	 * Only reset the PHY when no link is currently established.
-	 * This is for the Atheros PCIe board which has problems to establish
-	 * the link (again) after this PHY reset. All other currently tested
-	 * PCIe boards don't show this problem.
-	 * This has to be re-tested and fixed in a later release!
-	 */
-	val = mfdcri(SDR0, port->sdr_base + PESDRn_LOOP);
-	if (!(val & 0x00001000))
-		ppc405ex_pcie_phy_reset(port);
-
-	dcr_write(port->dcrs, DCRO_PEGPL_CFG, 0x10000000);  /* guarded on */
-
-	port->has_ibpre = 1;
-
-	return ppc4xx_pciex_port_reset_sdr(port);
-}
-
-static int ppc405ex_pciex_init_utl(struct ppc4xx_pciex_port *port)
-{
-	dcr_write(port->dcrs, DCRO_PEGPL_SPECIAL, 0x0);
-
-	/*
-	 * Set buffer allocations and then assert VRB and TXE.
-	 */
-	out_be32(port->utl_base + PEUTL_OUTTR,   0x02000000);
-	out_be32(port->utl_base + PEUTL_INTR,    0x02000000);
-	out_be32(port->utl_base + PEUTL_OPDBSZ,  0x04000000);
-	out_be32(port->utl_base + PEUTL_PBBSZ,   0x21000000);
-	out_be32(port->utl_base + PEUTL_IPHBSZ,  0x02000000);
-	out_be32(port->utl_base + PEUTL_IPDBSZ,  0x04000000);
-	out_be32(port->utl_base + PEUTL_RCIRQEN, 0x00f00000);
-	out_be32(port->utl_base + PEUTL_PCTL,    0x80800066);
-
-	out_be32(port->utl_base + PEUTL_PBCTL,   0x08000000);
-
-	return 0;
-}
-
-static struct ppc4xx_pciex_hwops ppc405ex_pcie_hwops __initdata =
-{
-	.want_sdr	= true,
-	.core_init	= ppc405ex_pciex_core_init,
-	.port_init_hw	= ppc405ex_pciex_init_port_hw,
-	.setup_utl	= ppc405ex_pciex_init_utl,
-	.check_link	= ppc4xx_pciex_check_link_sdr,
-};
-
-#endif /* CONFIG_40x */
-
 #ifdef CONFIG_476FPE
 static int __init ppc_476fpe_pciex_core_init(struct device_node *np)
 {
@@ -1427,10 +1326,6 @@ static int __init ppc4xx_pciex_check_core_init(struct device_node *np)
 	if (of_device_is_compatible(np, "ibm,plb-pciex-apm821xx"))
 		ppc4xx_pciex_hwops = &apm821xx_pcie_hwops;
 #endif /* CONFIG_44x    */
-#ifdef CONFIG_40x
-	if (of_device_is_compatible(np, "ibm,plb-pciex-405ex"))
-		ppc4xx_pciex_hwops = &ppc405ex_pcie_hwops;
-#endif
 #ifdef CONFIG_476FPE
 	if (of_device_is_compatible(np, "ibm,plb-pciex-476fpe")
 		|| of_device_is_compatible(np, "ibm,plb-pciex-476gtr"))
diff --git a/arch/powerpc/platforms/4xx/pci.h b/arch/powerpc/platforms/44x/pci.h
index bb4821938ab1..bb4821938ab1 100644
--- a/arch/powerpc/platforms/4xx/pci.h
+++ b/arch/powerpc/platforms/44x/pci.h
diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c
index fbc6edad481f..e7b7bdaad341 100644
--- a/arch/powerpc/platforms/44x/ppc476.c
+++ b/arch/powerpc/platforms/44x/ppc476.c
@@ -95,7 +95,7 @@ static int avr_probe(struct i2c_client *client)
 }
 
 static const struct i2c_device_id avr_id[] = {
-	{ "akebono-avr", 0 },
+	{ "akebono-avr" },
 	{ }
 };
 
@@ -103,7 +103,7 @@ static struct i2c_driver avr_driver = {
 	.driver = {
 		.name = "akebono-avr",
 	},
-	.probe_new = avr_probe,
+	.probe = avr_probe,
 	.id_table = avr_id,
 };
 
diff --git a/arch/powerpc/platforms/4xx/soc.c b/arch/powerpc/platforms/44x/soc.c
index ac1cd8b17879..5412e6b21e10 100644
--- a/arch/powerpc/platforms/4xx/soc.c
+++ b/arch/powerpc/platforms/44x/soc.c
@@ -15,12 +15,13 @@
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
 
 #include <asm/dcr.h>
 #include <asm/dcr-regs.h>
 #include <asm/reg.h>
+#include <asm/ppc4xx.h>
 
 static u32 dcrbase_l2c;
 
@@ -111,7 +112,7 @@ static int __init ppc4xx_l2c_probe(void)
 	}
 
 	/* Install error handler */
-	if (request_irq(irq, l2c_error_handler, 0, "L2C", 0) < 0) {
+	if (request_irq(irq, l2c_error_handler, 0, "L2C", NULL) < 0) {
 		printk(KERN_ERR "Cannot install L2C error handler"
 		       ", cache is not enabled\n");
 		of_node_put(np);
diff --git a/arch/powerpc/platforms/4xx/uic.c b/arch/powerpc/platforms/44x/uic.c
index d667ad039bd3..85daf841fd3f 100644
--- a/arch/powerpc/platforms/4xx/uic.c
+++ b/arch/powerpc/platforms/44x/uic.c
@@ -24,6 +24,7 @@
 #include <asm/irq.h>
 #include <asm/io.h>
 #include <asm/dcr.h>
+#include <asm/uic.h>
 
 #define NR_UIC_INTS	32
 
@@ -36,7 +37,7 @@
 #define UIC_VR		0x7
 #define UIC_VCR		0x8
 
-struct uic *primary_uic;
+static struct uic *primary_uic;
 
 struct uic {
 	int index;
@@ -253,8 +254,9 @@ static struct uic * __init uic_init_one(struct device_node *node)
 	}
 	uic->dcrbase = *dcrreg;
 
-	uic->irqhost = irq_domain_add_linear(node, NR_UIC_INTS, &uic_host_ops,
-					     uic);
+	uic->irqhost = irq_domain_create_linear(of_fwnode_handle(node),
+						NR_UIC_INTS, &uic_host_ops,
+						uic);
 	if (! uic->irqhost)
 		return NULL; /* FIXME: panic? */
 
@@ -290,7 +292,7 @@ void __init uic_init_tree(void)
 	if (!primary_uic)
 		panic("Unable to initialize primary UIC %pOF\n", np);
 
-	irq_set_default_host(primary_uic->irqhost);
+	irq_set_default_domain(primary_uic->irqhost);
 	of_node_put(np);
 
 	/* The scan again for cascaded UICs */
@@ -326,5 +328,5 @@ unsigned int uic_get_irq(void)
 	msr = mfdcr(primary_uic->dcrbase + UIC_MSR);
 	src = 32 - ffs(msr);
 
-	return irq_linear_revmap(primary_uic->irqhost, src);
+	return irq_find_mapping(primary_uic->irqhost, src);
 }
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index bfeb9bdc3258..a5001d32f978 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -8,6 +8,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/kthread.h>
 #include <linux/leds.h>
 #include <linux/i2c.h>
@@ -83,45 +84,8 @@ static int __init warp_post_info(void)
 
 #ifdef CONFIG_SENSORS_AD7414
 
-static LIST_HEAD(dtm_shutdown_list);
 static void __iomem *dtm_fpga;
 
-struct dtm_shutdown {
-	struct list_head list;
-	void (*func)(void *arg);
-	void *arg;
-};
-
-int pika_dtm_register_shutdown(void (*func)(void *arg), void *arg)
-{
-	struct dtm_shutdown *shutdown;
-
-	shutdown = kmalloc(sizeof(struct dtm_shutdown), GFP_KERNEL);
-	if (shutdown == NULL)
-		return -ENOMEM;
-
-	shutdown->func = func;
-	shutdown->arg = arg;
-
-	list_add(&shutdown->list, &dtm_shutdown_list);
-
-	return 0;
-}
-
-int pika_dtm_unregister_shutdown(void (*func)(void *arg), void *arg)
-{
-	struct dtm_shutdown *shutdown;
-
-	list_for_each_entry(shutdown, &dtm_shutdown_list, list)
-		if (shutdown->func == func && shutdown->arg == arg) {
-			list_del(&shutdown->list);
-			kfree(shutdown);
-			return 0;
-		}
-
-	return -EINVAL;
-}
-
 #define WARP_GREEN_LED	0
 #define WARP_RED_LED	1
 
@@ -153,17 +117,12 @@ static struct platform_device warp_gpio_leds = {
 
 static irqreturn_t temp_isr(int irq, void *context)
 {
-	struct dtm_shutdown *shutdown;
 	int value = 1;
 
 	local_irq_disable();
 
 	gpiod_set_value(warp_gpio_led_pins[WARP_GREEN_LED].gpiod, 0);
 
-	/* Run through the shutdown list. */
-	list_for_each_entry(shutdown, &dtm_shutdown_list, list)
-		shutdown->func(shutdown->arg);
-
 	printk(KERN_EMERG "\n\nCritical Temperature Shutdown\n\n");
 
 	while (1) {
@@ -366,19 +325,6 @@ machine_late_initcall(warp, pika_dtm_start);
 
 #else /* !CONFIG_SENSORS_AD7414 */
 
-int pika_dtm_register_shutdown(void (*func)(void *arg), void *arg)
-{
-	return 0;
-}
-
-int pika_dtm_unregister_shutdown(void (*func)(void *arg), void *arg)
-{
-	return 0;
-}
-
 machine_late_initcall(warp, warp_post_info);
 
 #endif
-
-EXPORT_SYMBOL(pika_dtm_register_shutdown);
-EXPORT_SYMBOL(pika_dtm_unregister_shutdown);
diff --git a/arch/powerpc/platforms/4xx/Makefile b/arch/powerpc/platforms/4xx/Makefile
deleted file mode 100644
index 2071a0abe09b..000000000000
--- a/arch/powerpc/platforms/4xx/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-y				+= uic.o machine_check.o
-obj-$(CONFIG_4xx_SOC)		+= soc.o
-obj-$(CONFIG_PCI)		+= pci.o
-obj-$(CONFIG_PPC4xx_HSTA_MSI)	+= hsta_msi.o
-obj-$(CONFIG_PPC4xx_CPM)	+= cpm.o
-obj-$(CONFIG_PPC4xx_GPIO)	+= gpio.o
diff --git a/arch/powerpc/platforms/4xx/machine_check.c b/arch/powerpc/platforms/4xx/machine_check.c
deleted file mode 100644
index a905da1d6f41..000000000000
--- a/arch/powerpc/platforms/4xx/machine_check.c
+++ /dev/null
@@ -1,23 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- */
-
-#include <linux/kernel.h>
-#include <linux/printk.h>
-#include <linux/ptrace.h>
-
-#include <asm/reg.h>
-
-int machine_check_4xx(struct pt_regs *regs)
-{
-	unsigned long reason = regs->esr;
-
-	if (reason & ESR_IMCP) {
-		printk("Instruction");
-		mtspr(SPRN_ESR, reason & ~ESR_IMCP);
-	} else
-		printk("Data");
-	printk(" machine check in kernel mode.\n");
-
-	return 0;
-}
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.c b/arch/powerpc/platforms/512x/mpc5121_ads.c
index 80b25ce076bc..a18f85b3ef36 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads.c
@@ -10,7 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/io.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 
 #include <asm/machdep.h>
 #include <asm/ipic.h>
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index 6f08d07aee3b..2cf3c6237337 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -17,6 +17,8 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 
+#include "mpc5121_ads.h"
+
 static struct device_node *cpld_pic_node;
 static struct irq_domain *cpld_pic_host;
 
@@ -186,7 +188,8 @@ mpc5121_ads_cpld_pic_init(void)
 
 	cpld_pic_node = of_node_get(np);
 
-	cpld_pic_host = irq_domain_add_linear(np, 16, &cpld_pic_host_ops, NULL);
+	cpld_pic_host = irq_domain_create_linear(of_fwnode_handle(np), 16,
+						 &cpld_pic_host_ops, NULL);
 	if (!cpld_pic_host) {
 		printk(KERN_ERR "CPLD PIC: failed to allocate irq host!\n");
 		goto end;
diff --git a/arch/powerpc/platforms/512x/mpc512x.h b/arch/powerpc/platforms/512x/mpc512x.h
index 2f3c60e373e1..d2cb06e3a436 100644
--- a/arch/powerpc/platforms/512x/mpc512x.h
+++ b/arch/powerpc/platforms/512x/mpc512x.h
@@ -13,7 +13,6 @@ extern void __init mpc512x_init(void);
 extern void __init mpc512x_setup_arch(void);
 extern int __init mpc5121_clk_init(void);
 const char *__init mpc512x_select_psc_compat(void);
-const char *__init mpc512x_select_reset_compat(void);
 extern void __noreturn mpc512x_restart(char *cmd);
 
 #endif				/* __MPC512X_H__ */
diff --git a/arch/powerpc/platforms/512x/mpc512x_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c
index 97dfaac8f7ff..d4fa6c302ccf 100644
--- a/arch/powerpc/platforms/512x/mpc512x_generic.c
+++ b/arch/powerpc/platforms/512x/mpc512x_generic.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 
 #include <asm/machdep.h>
 #include <asm/ipic.h>
@@ -32,9 +32,6 @@ static const char * const board[] __initconst = {
  */
 static int __init mpc512x_generic_probe(void)
 {
-	if (!of_device_compatible_match(of_root, board))
-		return 0;
-
 	mpc512x_init_early();
 
 	return 1;
@@ -42,6 +39,7 @@ static int __init mpc512x_generic_probe(void)
 
 define_machine(mpc512x_generic) {
 	.name			= "MPC512x generic",
+	.compatibles		= board,
 	.probe			= mpc512x_generic_probe,
 	.init			= mpc512x_init,
 	.setup_arch		= mpc512x_setup_arch,
diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
index 04bf6ecf7d55..f251e0f68262 100644
--- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
+++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
@@ -10,9 +10,9 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_platform.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/platform_device.h>
 #include <asm/mpc5121.h>
 #include <asm/io.h>
 #include <linux/spinlock.h>
@@ -240,10 +240,8 @@ static int mpc512x_lpbfifo_kick(void)
 	dma_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 
 	/* Make DMA channel work with LPB FIFO data register */
-	if (dma_dev->device_config(lpbfifo.chan, &dma_conf)) {
-		ret = -EINVAL;
-		goto err_dma_prep;
-	}
+	if (dma_dev->device_config(lpbfifo.chan, &dma_conf))
+		return -EINVAL;
 
 	sg_init_table(&sg, 1);
 
@@ -373,50 +371,32 @@ static int get_cs_ranges(struct device *dev)
 {
 	int ret = -ENODEV;
 	struct device_node *lb_node;
-	const u32 *addr_cells_p;
-	const u32 *size_cells_p;
-	int proplen;
-	size_t i;
+	size_t i = 0;
+	struct of_range_parser parser;
+	struct of_range range;
 
 	lb_node = of_find_compatible_node(NULL, NULL, "fsl,mpc5121-localbus");
 	if (!lb_node)
 		return ret;
 
-	/*
-	 * The node defined as compatible with 'fsl,mpc5121-localbus'
-	 * should have two address cells and one size cell.
-	 * Every item of its ranges property should consist of:
-	 * - the first address cell which is the chipselect number;
-	 * - the second address cell which is the offset in the chipselect,
-	 *    must be zero.
-	 * - CPU address of the beginning of an access window;
-	 * - the only size cell which is the size of an access window.
-	 */
-	addr_cells_p = of_get_property(lb_node, "#address-cells", NULL);
-	size_cells_p = of_get_property(lb_node, "#size-cells", NULL);
-	if (addr_cells_p == NULL || *addr_cells_p != 2 ||
-				size_cells_p == NULL ||	*size_cells_p != 1) {
-		goto end;
-	}
+	of_range_parser_init(&parser, lb_node);
+	lpbfifo.cs_n = of_range_count(&parser);
 
-	proplen = of_property_count_u32_elems(lb_node, "ranges");
-	if (proplen <= 0 || proplen % 4 != 0)
-		goto end;
-
-	lpbfifo.cs_n = proplen / 4;
 	lpbfifo.cs_ranges = devm_kcalloc(dev, lpbfifo.cs_n,
 					sizeof(struct cs_range), GFP_KERNEL);
 	if (!lpbfifo.cs_ranges)
 		goto end;
 
-	if (of_property_read_u32_array(lb_node, "ranges",
-				(u32 *)lpbfifo.cs_ranges, proplen) != 0) {
-		goto end;
-	}
-
-	for (i = 0; i < lpbfifo.cs_n; i++) {
-		if (lpbfifo.cs_ranges[i].base != 0)
+	for_each_of_range(&parser, &range) {
+		u32 base = lower_32_bits(range.bus_addr);
+		if (base)
 			goto end;
+
+		lpbfifo.cs_ranges[i].csnum = upper_32_bits(range.bus_addr);
+		lpbfifo.cs_ranges[i].base = base;
+		lpbfifo.cs_ranges[i].addr = range.cpu_addr;
+		lpbfifo.cs_ranges[i].size = range.size;
+		i++;
 	}
 
 	ret = 0;
@@ -495,7 +475,7 @@ static int mpc512x_lpbfifo_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int mpc512x_lpbfifo_remove(struct platform_device *pdev)
+static void mpc512x_lpbfifo_remove(struct platform_device *pdev)
 {
 	unsigned long flags;
 	struct dma_device *dma_dev = lpbfifo.chan->device;
@@ -512,8 +492,6 @@ static int mpc512x_lpbfifo_remove(struct platform_device *pdev)
 	free_irq(lpbfifo.irq, &pdev->dev);
 	irq_dispose_mapping(lpbfifo.irq);
 	dma_release_channel(lpbfifo.chan);
-
-	return 0;
 }
 
 static const struct of_device_id mpc512x_lpbfifo_match[] = {
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index 5ac0ead2540f..8c1f3b629fc7 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -29,20 +29,6 @@
 
 static struct mpc512x_reset_module __iomem *reset_module_base;
 
-static void __init mpc512x_restart_init(void)
-{
-	struct device_node *np;
-	const char *reset_compat;
-
-	reset_compat = mpc512x_select_reset_compat();
-	np = of_find_compatible_node(NULL, NULL, reset_compat);
-	if (!np)
-		return;
-
-	reset_module_base = of_iomap(np, 0);
-	of_node_put(np);
-}
-
 void __noreturn mpc512x_restart(char *cmd)
 {
 	if (reset_module_base) {
@@ -293,7 +279,7 @@ static void __init mpc512x_setup_diu(void)
 	 * and so negatively affect boot time. Instead we reserve the
 	 * already configured frame buffer area so that it won't be
 	 * destroyed. The starting address of the area to reserve and
-	 * also it's length is passed to memblock_reserve(). It will be
+	 * also its length is passed to memblock_reserve(). It will be
 	 * freed later on first open of fbdev, when splash image is not
 	 * needed any more.
 	 */
@@ -363,7 +349,7 @@ const char *__init mpc512x_select_psc_compat(void)
 	return NULL;
 }
 
-const char *__init mpc512x_select_reset_compat(void)
+static const char *__init mpc512x_select_reset_compat(void)
 {
 	if (of_machine_is_compatible("fsl,mpc5121"))
 		return "fsl,mpc5121-reset";
@@ -455,6 +441,20 @@ static void __init mpc512x_psc_fifo_init(void)
 	}
 }
 
+static void __init mpc512x_restart_init(void)
+{
+	struct device_node *np;
+	const char *reset_compat;
+
+	reset_compat = mpc512x_select_reset_compat();
+	np = of_find_compatible_node(NULL, NULL, reset_compat);
+	if (!np)
+		return;
+
+	reset_module_base = of_iomap(np, 0);
+	of_node_put(np);
+}
+
 void __init mpc512x_init_early(void)
 {
 	mpc512x_restart_init();
diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c
index 4bdec1c25de7..8bbbf78bb42b 100644
--- a/arch/powerpc/platforms/512x/pdm360ng.c
+++ b/arch/powerpc/platforms/512x/pdm360ng.c
@@ -7,11 +7,12 @@
  * PDM360NG board setup
  */
 
+#include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 
 #include <asm/machdep.h>
 #include <asm/ipic.h>
@@ -100,7 +101,7 @@ static inline void __init pdm360ng_touchscreen_init(void)
 }
 #endif /* CONFIG_TOUCHSCREEN_ADS7846 */
 
-void __init pdm360ng_init(void)
+static void __init pdm360ng_init(void)
 {
 	mpc512x_init();
 	pdm360ng_touchscreen_init();
diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig
index b72ed2950ca8..384e4bef2c28 100644
--- a/arch/powerpc/platforms/52xx/Kconfig
+++ b/arch/powerpc/platforms/52xx/Kconfig
@@ -54,8 +54,3 @@ config PPC_MPC5200_BUGFIX
 	  for MPC5200B based boards.
 
 	  It is safe to say 'Y' here
-
-config PPC_MPC5200_LPBFIFO
-	tristate "MPC5200 LocalPlus bus FIFO driver"
-	depends on PPC_MPC52xx && PPC_BESTCOMM
-	select PPC_BESTCOMM_GEN_BD
diff --git a/arch/powerpc/platforms/52xx/Makefile b/arch/powerpc/platforms/52xx/Makefile
index f40d48eab779..1b1f72d83342 100644
--- a/arch/powerpc/platforms/52xx/Makefile
+++ b/arch/powerpc/platforms/52xx/Makefile
@@ -14,5 +14,3 @@ obj-$(CONFIG_PM)		+= mpc52xx_sleep.o mpc52xx_pm.o
 ifdef CONFIG_PPC_LITE5200
 	obj-$(CONFIG_PM)	+= lite5200_sleep.o lite5200_pm.o
 endif
-
-obj-$(CONFIG_PPC_MPC5200_LPBFIFO)	+= mpc52xx_lpbfifo.o
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index aa82e6b437f3..a7172f9ebaad 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -13,6 +13,7 @@
 #include <generated/utsrelease.h>
 #include <linux/pci.h>
 #include <linux/of.h>
+#include <linux/seq_file.h>
 #include <asm/dma.h>
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -195,8 +196,10 @@ static void __init efika_setup_arch(void)
 
 static int __init efika_probe(void)
 {
-	const char *model = of_get_property(of_root, "model", NULL);
+	struct device_node *root = of_find_node_by_path("/");
+	const char *model = of_get_property(root, "model", NULL);
 
+	of_node_put(root);
 	if (model == NULL)
 		return 0;
 	if (strcmp(model, "EFIKA5K2"))
diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c
index 0fd67b3ffc3e..0a161d82a3a8 100644
--- a/arch/powerpc/platforms/52xx/lite5200.c
+++ b/arch/powerpc/platforms/52xx/lite5200.c
@@ -172,17 +172,9 @@ static const char * const board[] __initconst = {
 	NULL,
 };
 
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init lite5200_probe(void)
-{
-	return of_device_compatible_match(of_root, board);
-}
-
 define_machine(lite5200) {
 	.name 		= "lite5200",
-	.probe 		= lite5200_probe,
+	.compatibles	= board,
 	.setup_arch 	= lite5200_setup_arch,
 	.discover_phbs	= mpc52xx_setup_pci,
 	.init		= mpc52xx_declare_of_platform_devices,
diff --git a/arch/powerpc/platforms/52xx/lite5200_pm.c b/arch/powerpc/platforms/52xx/lite5200_pm.c
index ee29b63fca16..4900f5f48cce 100644
--- a/arch/powerpc/platforms/52xx/lite5200_pm.c
+++ b/arch/powerpc/platforms/52xx/lite5200_pm.c
@@ -47,7 +47,7 @@ static int lite5200_pm_begin(suspend_state_t state)
 static int lite5200_pm_prepare(void)
 {
 	struct device_node *np;
-	const struct of_device_id immr_ids[] = {
+	static const struct of_device_id immr_ids[] = {
 		{ .compatible = "fsl,mpc5200-immr", },
 		{ .compatible = "fsl,mpc5200b-immr", },
 		{ .type = "soc", .compatible = "mpc5200", }, /* lite5200 */
diff --git a/arch/powerpc/platforms/52xx/lite5200_sleep.S b/arch/powerpc/platforms/52xx/lite5200_sleep.S
index 0b12647e7b42..0ec2522ee4ad 100644
--- a/arch/powerpc/platforms/52xx/lite5200_sleep.S
+++ b/arch/powerpc/platforms/52xx/lite5200_sleep.S
@@ -203,7 +203,8 @@ lite5200_wakeup:
 
 	/* HIDs, MSR */
 	LOAD_SPRN(HID1, 0x19)
-	LOAD_SPRN(HID2, 0x1a)
+	/* FIXME: Should this use HID2_G2_LE? */
+	LOAD_SPRN(HID2_750FX, 0x1a)
 
 
 	/* address translation is tricky (see turn_on_mmu) */
@@ -283,7 +284,8 @@ SYM_FUNC_START_LOCAL(save_regs)
 
 	SAVE_SPRN(HID0, 0x18)
 	SAVE_SPRN(HID1, 0x19)
-	SAVE_SPRN(HID2, 0x1a)
+	/* FIXME: Should this use HID2_G2_LE? */
+	SAVE_SPRN(HID2_750FX, 0x1a)
 	mfmsr	r10
 	stw	r10, (4*0x1b)(r4)
 	/*SAVE_SPRN(LR, 0x1c) have to save it before the call */
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 19626cd42406..bc7f83cfec1d 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -168,7 +168,7 @@ static void __init media5200_init_irq(void)
 
 	spin_lock_init(&media5200_irq.lock);
 
-	media5200_irq.irqhost = irq_domain_add_linear(fpga_np,
+	media5200_irq.irqhost = irq_domain_create_linear(of_fwnode_handle(fpga_np),
 			MEDIA5200_NUM_IRQS, &media5200_irq_ops, &media5200_irq);
 	if (!media5200_irq.irqhost)
 		goto out;
diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
index f1e85e86f5e5..7e0e4c34a40b 100644
--- a/arch/powerpc/platforms/52xx/mpc5200_simple.c
+++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c
@@ -59,17 +59,9 @@ static const char *board[] __initdata = {
 	NULL
 };
 
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init mpc5200_simple_probe(void)
-{
-	return of_device_compatible_match(of_root, board);
-}
-
 define_machine(mpc5200_simple_platform) {
 	.name		= "mpc5200-simple-platform",
-	.probe		= mpc5200_simple_probe,
+	.compatibles	= board,
 	.setup_arch	= mpc5200_simple_setup_arch,
 	.discover_phbs	= mpc52xx_setup_pci,
 	.init		= mpc52xx_declare_of_platform_devices,
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
index b4938e344f71..253421ffb4e5 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_common.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -12,12 +12,10 @@
 
 #undef DEBUG
 
-#include <linux/gpio.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
-#include <linux/of_gpio.h>
 #include <linux/export.h>
 #include <asm/io.h>
 #include <asm/mpc52xx.h>
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 3fce4e1c3af6..7748b6641a3c 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -48,7 +48,7 @@
  * the output mode.  This driver does not change the output mode setting.
  */
 
-#include <linux/device.h>
+#include <linux/gpio/driver.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -57,8 +57,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
-#include <linux/of_gpio.h>
+#include <linux/platform_device.h>
 #include <linux/kernel.h>
 #include <linux/property.h>
 #include <linux/slab.h>
@@ -248,9 +247,9 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node)
 	if (!cascade_virq)
 		return;
 
-	gpt->irqhost = irq_domain_add_linear(node, 1, &mpc52xx_gpt_irq_ops, gpt);
+	gpt->irqhost = irq_domain_create_linear(of_fwnode_handle(node), 1, &mpc52xx_gpt_irq_ops, gpt);
 	if (!gpt->irqhost) {
-		dev_err(gpt->dev, "irq_domain_add_linear() failed\n");
+		dev_err(gpt->dev, "irq_domain_create_linear() failed\n");
 		return;
 	}
 
@@ -281,7 +280,7 @@ static int mpc52xx_gpt_gpio_get(struct gpio_chip *gc, unsigned int gpio)
 	return (in_be32(&gpt->regs->status) >> 8) & 1;
 }
 
-static void
+static int
 mpc52xx_gpt_gpio_set(struct gpio_chip *gc, unsigned int gpio, int v)
 {
 	struct mpc52xx_gpt_priv *gpt = gpiochip_get_data(gc);
@@ -294,6 +293,8 @@ mpc52xx_gpt_gpio_set(struct gpio_chip *gc, unsigned int gpio, int v)
 	raw_spin_lock_irqsave(&gpt->lock, flags);
 	clrsetbits_be32(&gpt->regs->mode, MPC52xx_GPT_MODE_GPIO_MASK, r);
 	raw_spin_unlock_irqrestore(&gpt->lock, flags);
+
+	return 0;
 }
 
 static int mpc52xx_gpt_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
@@ -370,7 +371,7 @@ struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq)
 	mutex_lock(&mpc52xx_gpt_list_mutex);
 	list_for_each(pos, &mpc52xx_gpt_list) {
 		gpt = container_of(pos, struct mpc52xx_gpt_priv, list);
-		if (gpt->irqhost && irq == irq_linear_revmap(gpt->irqhost, 0)) {
+		if (gpt->irqhost && irq == irq_find_mapping(gpt->irqhost, 0)) {
 			mutex_unlock(&mpc52xx_gpt_list_mutex);
 			return gpt;
 		}
@@ -645,7 +646,6 @@ static int mpc52xx_wdt_release(struct inode *inode, struct file *file)
 
 static const struct file_operations mpc52xx_wdt_fops = {
 	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
 	.write		= mpc52xx_wdt_write,
 	.unlocked_ioctl = mpc52xx_wdt_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
deleted file mode 100644
index 6d1dd6e87478..000000000000
--- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
+++ /dev/null
@@ -1,594 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * LocalPlus Bus FIFO driver for the Freescale MPC52xx.
- *
- * Copyright (C) 2009 Secret Lab Technologies Ltd.
- *
- * Todo:
- * - Add support for multiple requests to be queued.
- */
-
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/of_platform.h>
-#include <linux/spinlock.h>
-#include <linux/module.h>
-#include <asm/io.h>
-#include <asm/mpc52xx.h>
-#include <asm/time.h>
-
-#include <linux/fsl/bestcomm/bestcomm.h>
-#include <linux/fsl/bestcomm/bestcomm_priv.h>
-#include <linux/fsl/bestcomm/gen_bd.h>
-
-MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>");
-MODULE_DESCRIPTION("MPC5200 LocalPlus FIFO device driver");
-MODULE_LICENSE("GPL");
-
-#define LPBFIFO_REG_PACKET_SIZE		(0x00)
-#define LPBFIFO_REG_START_ADDRESS	(0x04)
-#define LPBFIFO_REG_CONTROL		(0x08)
-#define LPBFIFO_REG_ENABLE		(0x0C)
-#define LPBFIFO_REG_BYTES_DONE_STATUS	(0x14)
-#define LPBFIFO_REG_FIFO_DATA		(0x40)
-#define LPBFIFO_REG_FIFO_STATUS		(0x44)
-#define LPBFIFO_REG_FIFO_CONTROL	(0x48)
-#define LPBFIFO_REG_FIFO_ALARM		(0x4C)
-
-struct mpc52xx_lpbfifo {
-	struct device *dev;
-	phys_addr_t regs_phys;
-	void __iomem *regs;
-	int irq;
-	spinlock_t lock;
-
-	struct bcom_task *bcom_tx_task;
-	struct bcom_task *bcom_rx_task;
-	struct bcom_task *bcom_cur_task;
-
-	/* Current state data */
-	struct mpc52xx_lpbfifo_request *req;
-	int dma_irqs_enabled;
-};
-
-/* The MPC5200 has only one fifo, so only need one instance structure */
-static struct mpc52xx_lpbfifo lpbfifo;
-
-/**
- * mpc52xx_lpbfifo_kick - Trigger the next block of data to be transferred
- *
- * @req: Pointer to request structure
- */
-static void mpc52xx_lpbfifo_kick(struct mpc52xx_lpbfifo_request *req)
-{
-	size_t transfer_size = req->size - req->pos;
-	struct bcom_bd *bd;
-	void __iomem *reg;
-	u32 *data;
-	int i;
-	int bit_fields;
-	int dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA);
-	int write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE;
-	int poll_dma = req->flags & MPC52XX_LPBFIFO_FLAG_POLL_DMA;
-
-	/* Set and clear the reset bits; is good practice in User Manual */
-	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
-
-	/* set master enable bit */
-	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x00000001);
-	if (!dma) {
-		/* While the FIFO can be setup for transfer sizes as large as
-		 * 16M-1, the FIFO itself is only 512 bytes deep and it does
-		 * not generate interrupts for FIFO full events (only transfer
-		 * complete will raise an IRQ).  Therefore when not using
-		 * Bestcomm to drive the FIFO it needs to either be polled, or
-		 * transfers need to constrained to the size of the fifo.
-		 *
-		 * This driver restricts the size of the transfer
-		 */
-		if (transfer_size > 512)
-			transfer_size = 512;
-
-		/* Load the FIFO with data */
-		if (write) {
-			reg = lpbfifo.regs + LPBFIFO_REG_FIFO_DATA;
-			data = req->data + req->pos;
-			for (i = 0; i < transfer_size; i += 4)
-				out_be32(reg, *data++);
-		}
-
-		/* Unmask both error and completion irqs */
-		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x00000301);
-	} else {
-		/* Choose the correct direction
-		 *
-		 * Configure the watermarks so DMA will always complete correctly.
-		 * It may be worth experimenting with the ALARM value to see if
-		 * there is a performance impact.  However, if it is wrong there
-		 * is a risk of DMA not transferring the last chunk of data
-		 */
-		if (write) {
-			out_be32(lpbfifo.regs + LPBFIFO_REG_FIFO_ALARM, 0x1e4);
-			out_8(lpbfifo.regs + LPBFIFO_REG_FIFO_CONTROL, 7);
-			lpbfifo.bcom_cur_task = lpbfifo.bcom_tx_task;
-		} else {
-			out_be32(lpbfifo.regs + LPBFIFO_REG_FIFO_ALARM, 0x1ff);
-			out_8(lpbfifo.regs + LPBFIFO_REG_FIFO_CONTROL, 0);
-			lpbfifo.bcom_cur_task = lpbfifo.bcom_rx_task;
-
-			if (poll_dma) {
-				if (lpbfifo.dma_irqs_enabled) {
-					disable_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task));
-					lpbfifo.dma_irqs_enabled = 0;
-				}
-			} else {
-				if (!lpbfifo.dma_irqs_enabled) {
-					enable_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task));
-					lpbfifo.dma_irqs_enabled = 1;
-				}
-			}
-		}
-
-		bd = bcom_prepare_next_buffer(lpbfifo.bcom_cur_task);
-		bd->status = transfer_size;
-		if (!write) {
-			/*
-			 * In the DMA read case, the DMA doesn't complete,
-			 * possibly due to incorrect watermarks in the ALARM
-			 * and CONTROL regs. For now instead of trying to
-			 * determine the right watermarks that will make this
-			 * work, just increase the number of bytes the FIFO is
-			 * expecting.
-			 *
-			 * When submitting another operation, the FIFO will get
-			 * reset, so the condition of the FIFO waiting for a
-			 * non-existent 4 bytes will get cleared.
-			 */
-			transfer_size += 4; /* BLECH! */
-		}
-		bd->data[0] = req->data_phys + req->pos;
-		bcom_submit_next_buffer(lpbfifo.bcom_cur_task, NULL);
-
-		/* error irq & master enabled bit */
-		bit_fields = 0x00000201;
-
-		/* Unmask irqs */
-		if (write && (!poll_dma))
-			bit_fields |= 0x00000100; /* completion irq too */
-		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, bit_fields);
-	}
-
-	/* Set transfer size, width, chip select and READ mode */
-	out_be32(lpbfifo.regs + LPBFIFO_REG_START_ADDRESS,
-		 req->offset + req->pos);
-	out_be32(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, transfer_size);
-
-	bit_fields = req->cs << 24 | 0x000008;
-	if (!write)
-		bit_fields |= 0x010000; /* read mode */
-	out_be32(lpbfifo.regs + LPBFIFO_REG_CONTROL, bit_fields);
-
-	/* Kick it off */
-	if (!lpbfifo.req->defer_xfer_start)
-		out_8(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, 0x01);
-	if (dma)
-		bcom_enable(lpbfifo.bcom_cur_task);
-}
-
-/**
- * mpc52xx_lpbfifo_irq - IRQ handler for LPB FIFO
- * @irq: IRQ number to be handled
- * @dev_id: device ID cookie
- *
- * On transmit, the dma completion irq triggers before the fifo completion
- * triggers.  Handle the dma completion here instead of the LPB FIFO Bestcomm
- * task completion irq because everything is not really done until the LPB FIFO
- * completion irq triggers.
- *
- * In other words:
- * For DMA, on receive, the "Fat Lady" is the bestcom completion irq. on
- * transmit, the fifo completion irq is the "Fat Lady". The opera (or in this
- * case the DMA/FIFO operation) is not finished until the "Fat Lady" sings.
- *
- * Reasons for entering this routine:
- * 1) PIO mode rx and tx completion irq
- * 2) DMA interrupt mode tx completion irq
- * 3) DMA polled mode tx
- *
- * Exit conditions:
- * 1) Transfer aborted
- * 2) FIFO complete without DMA; more data to do
- * 3) FIFO complete without DMA; all data transferred
- * 4) FIFO complete using DMA
- *
- * Condition 1 can occur regardless of whether or not DMA is used.
- * It requires executing the callback to report the error and exiting
- * immediately.
- *
- * Condition 2 requires programming the FIFO with the next block of data
- *
- * Condition 3 requires executing the callback to report completion
- *
- * Condition 4 means the same as 3, except that we also retrieve the bcom
- * buffer so DMA doesn't get clogged up.
- *
- * To make things trickier, the spinlock must be dropped before
- * executing the callback, otherwise we could end up with a deadlock
- * or nested spinlock condition.  The out path is non-trivial, so
- * extra fiddling is done to make sure all paths lead to the same
- * outbound code.
- *
- * Return: irqreturn code (%IRQ_HANDLED)
- */
-static irqreturn_t mpc52xx_lpbfifo_irq(int irq, void *dev_id)
-{
-	struct mpc52xx_lpbfifo_request *req;
-	u32 status = in_8(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS);
-	void __iomem *reg;
-	u32 *data;
-	int count, i;
-	int do_callback = 0;
-	u32 ts;
-	unsigned long flags;
-	int dma, write, poll_dma;
-
-	spin_lock_irqsave(&lpbfifo.lock, flags);
-	ts = mftb();
-
-	req = lpbfifo.req;
-	if (!req) {
-		spin_unlock_irqrestore(&lpbfifo.lock, flags);
-		pr_err("bogus LPBFIFO IRQ\n");
-		return IRQ_HANDLED;
-	}
-
-	dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA);
-	write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE;
-	poll_dma = req->flags & MPC52XX_LPBFIFO_FLAG_POLL_DMA;
-
-	if (dma && !write) {
-		spin_unlock_irqrestore(&lpbfifo.lock, flags);
-		pr_err("bogus LPBFIFO IRQ (dma and not writing)\n");
-		return IRQ_HANDLED;
-	}
-
-	if ((status & 0x01) == 0) {
-		goto out;
-	}
-
-	/* check abort bit */
-	if (status & 0x10) {
-		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
-		do_callback = 1;
-		goto out;
-	}
-
-	/* Read result from hardware */
-	count = in_be32(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS);
-	count &= 0x00ffffff;
-
-	if (!dma && !write) {
-		/* copy the data out of the FIFO */
-		reg = lpbfifo.regs + LPBFIFO_REG_FIFO_DATA;
-		data = req->data + req->pos;
-		for (i = 0; i < count; i += 4)
-			*data++ = in_be32(reg);
-	}
-
-	/* Update transfer position and count */
-	req->pos += count;
-
-	/* Decide what to do next */
-	if (req->size - req->pos)
-		mpc52xx_lpbfifo_kick(req); /* more work to do */
-	else
-		do_callback = 1;
-
- out:
-	/* Clear the IRQ */
-	out_8(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS, 0x01);
-
-	if (dma && (status & 0x11)) {
-		/*
-		 * Count the DMA as complete only when the FIFO completion
-		 * status or abort bits are set.
-		 *
-		 * (status & 0x01) should always be the case except sometimes
-		 * when using polled DMA.
-		 *
-		 * (status & 0x10) {transfer aborted}: This case needs more
-		 * testing.
-		 */
-		bcom_retrieve_buffer(lpbfifo.bcom_cur_task, &status, NULL);
-	}
-	req->last_byte = ((u8 *)req->data)[req->size - 1];
-
-	/* When the do_callback flag is set; it means the transfer is finished
-	 * so set the FIFO as idle */
-	if (do_callback)
-		lpbfifo.req = NULL;
-
-	if (irq != 0) /* don't increment on polled case */
-		req->irq_count++;
-
-	req->irq_ticks += mftb() - ts;
-	spin_unlock_irqrestore(&lpbfifo.lock, flags);
-
-	/* Spinlock is released; it is now safe to call the callback */
-	if (do_callback && req->callback)
-		req->callback(req);
-
-	return IRQ_HANDLED;
-}
-
-/**
- * mpc52xx_lpbfifo_bcom_irq - IRQ handler for LPB FIFO Bestcomm task
- * @irq: IRQ number to be handled
- * @dev_id: device ID cookie
- *
- * Only used when receiving data.
- *
- * Return: irqreturn code (%IRQ_HANDLED)
- */
-static irqreturn_t mpc52xx_lpbfifo_bcom_irq(int irq, void *dev_id)
-{
-	struct mpc52xx_lpbfifo_request *req;
-	unsigned long flags;
-	u32 status;
-	u32 ts;
-
-	spin_lock_irqsave(&lpbfifo.lock, flags);
-	ts = mftb();
-
-	req = lpbfifo.req;
-	if (!req || (req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA)) {
-		spin_unlock_irqrestore(&lpbfifo.lock, flags);
-		return IRQ_HANDLED;
-	}
-
-	if (irq != 0) /* don't increment on polled case */
-		req->irq_count++;
-
-	if (!bcom_buffer_done(lpbfifo.bcom_cur_task)) {
-		spin_unlock_irqrestore(&lpbfifo.lock, flags);
-
-		req->buffer_not_done_cnt++;
-		if ((req->buffer_not_done_cnt % 1000) == 0)
-			pr_err("transfer stalled\n");
-
-		return IRQ_HANDLED;
-	}
-
-	bcom_retrieve_buffer(lpbfifo.bcom_cur_task, &status, NULL);
-
-	req->last_byte = ((u8 *)req->data)[req->size - 1];
-
-	req->pos = status & 0x00ffffff;
-
-	/* Mark the FIFO as idle */
-	lpbfifo.req = NULL;
-
-	/* Release the lock before calling out to the callback. */
-	req->irq_ticks += mftb() - ts;
-	spin_unlock_irqrestore(&lpbfifo.lock, flags);
-
-	if (req->callback)
-		req->callback(req);
-
-	return IRQ_HANDLED;
-}
-
-/**
- * mpc52xx_lpbfifo_poll - Poll for DMA completion
- */
-void mpc52xx_lpbfifo_poll(void)
-{
-	struct mpc52xx_lpbfifo_request *req = lpbfifo.req;
-	int dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA);
-	int write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE;
-
-	/*
-	 * For more information, see comments on the "Fat Lady" 
-	 */
-	if (dma && write)
-		mpc52xx_lpbfifo_irq(0, NULL);
-	else 
-		mpc52xx_lpbfifo_bcom_irq(0, NULL);
-}
-EXPORT_SYMBOL(mpc52xx_lpbfifo_poll);
-
-/**
- * mpc52xx_lpbfifo_submit - Submit an LPB FIFO transfer request.
- * @req: Pointer to request structure
- *
- * Return: %0 on success, -errno code on error
- */
-int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req)
-{
-	unsigned long flags;
-
-	if (!lpbfifo.regs)
-		return -ENODEV;
-
-	spin_lock_irqsave(&lpbfifo.lock, flags);
-
-	/* If the req pointer is already set, then a transfer is in progress */
-	if (lpbfifo.req) {
-		spin_unlock_irqrestore(&lpbfifo.lock, flags);
-		return -EBUSY;
-	}
-
-	/* Setup the transfer */
-	lpbfifo.req = req;
-	req->irq_count = 0;
-	req->irq_ticks = 0;
-	req->buffer_not_done_cnt = 0;
-	req->pos = 0;
-
-	mpc52xx_lpbfifo_kick(req);
-	spin_unlock_irqrestore(&lpbfifo.lock, flags);
-	return 0;
-}
-EXPORT_SYMBOL(mpc52xx_lpbfifo_submit);
-
-int mpc52xx_lpbfifo_start_xfer(struct mpc52xx_lpbfifo_request *req)
-{
-	unsigned long flags;
-
-	if (!lpbfifo.regs)
-		return -ENODEV;
-
-	spin_lock_irqsave(&lpbfifo.lock, flags);
-
-	/*
-	 * If the req pointer is already set and a transfer was
-	 * started on submit, then this transfer is in progress
-	 */
-	if (lpbfifo.req && !lpbfifo.req->defer_xfer_start) {
-		spin_unlock_irqrestore(&lpbfifo.lock, flags);
-		return -EBUSY;
-	}
-
-	/*
-	 * If the req was previously submitted but not
-	 * started, start it now
-	 */
-	if (lpbfifo.req && lpbfifo.req == req &&
-	    lpbfifo.req->defer_xfer_start) {
-		out_8(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, 0x01);
-	}
-
-	spin_unlock_irqrestore(&lpbfifo.lock, flags);
-	return 0;
-}
-EXPORT_SYMBOL(mpc52xx_lpbfifo_start_xfer);
-
-void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&lpbfifo.lock, flags);
-	if (lpbfifo.req == req) {
-		/* Put it into reset and clear the state */
-		bcom_gen_bd_rx_reset(lpbfifo.bcom_rx_task);
-		bcom_gen_bd_tx_reset(lpbfifo.bcom_tx_task);
-		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
-		lpbfifo.req = NULL;
-	}
-	spin_unlock_irqrestore(&lpbfifo.lock, flags);
-}
-EXPORT_SYMBOL(mpc52xx_lpbfifo_abort);
-
-static int mpc52xx_lpbfifo_probe(struct platform_device *op)
-{
-	struct resource res;
-	int rc = -ENOMEM;
-
-	if (lpbfifo.dev != NULL)
-		return -ENOSPC;
-
-	lpbfifo.irq = irq_of_parse_and_map(op->dev.of_node, 0);
-	if (!lpbfifo.irq)
-		return -ENODEV;
-
-	if (of_address_to_resource(op->dev.of_node, 0, &res))
-		return -ENODEV;
-	lpbfifo.regs_phys = res.start;
-	lpbfifo.regs = of_iomap(op->dev.of_node, 0);
-	if (!lpbfifo.regs)
-		return -ENOMEM;
-
-	spin_lock_init(&lpbfifo.lock);
-
-	/* Put FIFO into reset */
-	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
-
-	/* Register the interrupt handler */
-	rc = request_irq(lpbfifo.irq, mpc52xx_lpbfifo_irq, 0,
-			 "mpc52xx-lpbfifo", &lpbfifo);
-	if (rc)
-		goto err_irq;
-
-	/* Request the Bestcomm receive (fifo --> memory) task and IRQ */
-	lpbfifo.bcom_rx_task =
-		bcom_gen_bd_rx_init(2, res.start + LPBFIFO_REG_FIFO_DATA,
-				    BCOM_INITIATOR_SCLPC, BCOM_IPR_SCLPC,
-				    16*1024*1024);
-	if (!lpbfifo.bcom_rx_task)
-		goto err_bcom_rx;
-
-	rc = request_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task),
-			 mpc52xx_lpbfifo_bcom_irq, 0,
-			 "mpc52xx-lpbfifo-rx", &lpbfifo);
-	if (rc)
-		goto err_bcom_rx_irq;
-
-	lpbfifo.dma_irqs_enabled = 1;
-
-	/* Request the Bestcomm transmit (memory --> fifo) task and IRQ */
-	lpbfifo.bcom_tx_task =
-		bcom_gen_bd_tx_init(2, res.start + LPBFIFO_REG_FIFO_DATA,
-				    BCOM_INITIATOR_SCLPC, BCOM_IPR_SCLPC);
-	if (!lpbfifo.bcom_tx_task)
-		goto err_bcom_tx;
-
-	lpbfifo.dev = &op->dev;
-	return 0;
-
- err_bcom_tx:
-	free_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task), &lpbfifo);
- err_bcom_rx_irq:
-	bcom_gen_bd_rx_release(lpbfifo.bcom_rx_task);
- err_bcom_rx:
-	free_irq(lpbfifo.irq, &lpbfifo);
- err_irq:
-	iounmap(lpbfifo.regs);
-	lpbfifo.regs = NULL;
-
-	dev_err(&op->dev, "mpc52xx_lpbfifo_probe() failed\n");
-	return -ENODEV;
-}
-
-
-static int mpc52xx_lpbfifo_remove(struct platform_device *op)
-{
-	if (lpbfifo.dev != &op->dev)
-		return 0;
-
-	/* Put FIFO in reset */
-	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
-
-	/* Release the bestcomm transmit task */
-	free_irq(bcom_get_task_irq(lpbfifo.bcom_tx_task), &lpbfifo);
-	bcom_gen_bd_tx_release(lpbfifo.bcom_tx_task);
-	
-	/* Release the bestcomm receive task */
-	free_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task), &lpbfifo);
-	bcom_gen_bd_rx_release(lpbfifo.bcom_rx_task);
-
-	free_irq(lpbfifo.irq, &lpbfifo);
-	iounmap(lpbfifo.regs);
-	lpbfifo.regs = NULL;
-	lpbfifo.dev = NULL;
-
-	return 0;
-}
-
-static const struct of_device_id mpc52xx_lpbfifo_match[] = {
-	{ .compatible = "fsl,mpc5200-lpbfifo", },
-	{},
-};
-MODULE_DEVICE_TABLE(of, mpc52xx_lpbfifo_match);
-
-static struct platform_driver mpc52xx_lpbfifo_driver = {
-	.driver = {
-		.name = "mpc52xx-lpbfifo",
-		.of_match_table = mpc52xx_lpbfifo_match,
-	},
-	.probe = mpc52xx_lpbfifo_probe,
-	.remove = mpc52xx_lpbfifo_remove,
-};
-module_platform_driver(mpc52xx_lpbfifo_driver);
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index 1e0a5e9644dc..eb6a4e745c08 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -446,14 +446,14 @@ void __init mpc52xx_init_irq(void)
 	 * As last step, add an irq host to translate the real
 	 * hw irq information provided by the ofw to linux virq
 	 */
-	mpc52xx_irqhost = irq_domain_add_linear(picnode,
+	mpc52xx_irqhost = irq_domain_create_linear(of_fwnode_handle(picnode),
 	                                 MPC52xx_IRQ_HIGHTESTHWIRQ,
 	                                 &mpc52xx_irqhost_ops, NULL);
 
 	if (!mpc52xx_irqhost)
 		panic(__FILE__ ": Cannot allocate the IRQ host\n");
 
-	irq_set_default_host(mpc52xx_irqhost);
+	irq_set_default_domain(mpc52xx_irqhost);
 
 	pr_info("MPC52xx PIC is up and running!\n");
 }
@@ -515,5 +515,5 @@ unsigned int mpc52xx_get_irq(void)
 		return 0;
 	}
 
-	return irq_linear_revmap(mpc52xx_irqhost, irq);
+	return irq_find_mapping(mpc52xx_irqhost, irq);
 }
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pm.c b/arch/powerpc/platforms/52xx/mpc52xx_pm.c
index 549b3629e39a..f0c31ae15da5 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pm.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pm.c
@@ -60,7 +60,7 @@ int mpc52xx_set_wakeup_gpio(u8 pin, u8 level)
 int mpc52xx_pm_prepare(void)
 {
 	struct device_node *np;
-	const struct of_device_id immr_ids[] = {
+	static const struct of_device_id immr_ids[] = {
 		{ .compatible = "fsl,mpc5200-immr", },
 		{ .compatible = "fsl,mpc5200b-immr", },
 		{ .type = "soc", .compatible = "mpc5200", }, /* lite5200 */
diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig
index 4eb372bdab70..1824536cf6f2 100644
--- a/arch/powerpc/platforms/82xx/Kconfig
+++ b/arch/powerpc/platforms/82xx/Kconfig
@@ -2,14 +2,14 @@
 menuconfig PPC_82xx
 	bool "82xx-based boards (PQ II)"
 	depends on PPC_BOOK3S_32
+	select FSL_SOC
 
 if PPC_82xx
 
 config EP8248E
 	bool "Embedded Planet EP8248E (a.k.a. CWH-PPC-8248N-VE)"
-	select 8272
-	select 8260
-	select FSL_SOC
+	select CPM2
+	select PPC_INDIRECT_PCI if PCI
 	select PHYLIB if NETDEVICES
 	select MDIO_BITBANG if PHYLIB
 	help
@@ -20,26 +20,9 @@ config EP8248E
 
 config MGCOGE
 	bool "Keymile MGCOGE"
-	select 8272
-	select 8260
-	select FSL_SOC
+	select CPM2
+	select PPC_INDIRECT_PCI if PCI
 	help
 	  This enables support for the Keymile MGCOGE board.
 
 endif
-
-config 8260
-	bool
-	depends on PPC_BOOK3S_32
-	select CPM2
-	help
-	  The MPC8260 is a typical embedded CPU made by Freescale.  Selecting
-	  this option means that you wish to build a kernel for a machine with
-	  an 8260 class CPU.
-
-config 8272
-	bool
-	select 8260
-	help
-	  The MPC8272 CPM has a different internal dpram setup than other CPM2
-	  devices
diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c
index 8f1856ba692e..8f918916e631 100644
--- a/arch/powerpc/platforms/82xx/ep8248e.c
+++ b/arch/powerpc/platforms/82xx/ep8248e.c
@@ -13,13 +13,13 @@
 #include <linux/of_mdio.h>
 #include <linux/slab.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 #include <asm/io.h>
 #include <asm/cpm2.h>
 #include <asm/udbg.h>
 #include <asm/machdep.h>
 #include <asm/time.h>
-#include <asm/mpc8260.h>
 
 #include <sysdev/fsl_soc.h>
 #include <sysdev/cpm2_pic.h>
@@ -128,7 +128,7 @@ static int ep8248e_mdio_probe(struct platform_device *ofdev)
 
 	bus->name = "ep8248e-mdio-bitbang";
 	bus->parent = &ofdev->dev;
-	snprintf(bus->id, MII_BUS_ID_SIZE, "%x", res.start);
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%pa", &res.start);
 
 	ret = of_mdiobus_register(bus, ofdev->dev.of_node);
 	if (ret)
@@ -140,12 +140,6 @@ err_free_bus:
 	return ret;
 }
 
-static int ep8248e_mdio_remove(struct platform_device *ofdev)
-{
-	BUG();
-	return 0;
-}
-
 static const struct of_device_id ep8248e_mdio_match[] = {
 	{
 		.compatible = "fsl,ep8248e-mdio-bitbang",
@@ -157,9 +151,9 @@ static struct platform_driver ep8248e_mdio_driver = {
 	.driver = {
 		.name = "ep8248e-mdio-bitbang",
 		.of_match_table = ep8248e_mdio_match,
+		.suppress_bind_attrs = true,
 	},
 	.probe = ep8248e_mdio_probe,
-	.remove = ep8248e_mdio_remove,
 };
 
 struct cpm_pin {
diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c
index 51c9bfd97592..99f0f0f41876 100644
--- a/arch/powerpc/platforms/82xx/km82xx.c
+++ b/arch/powerpc/platforms/82xx/km82xx.c
@@ -19,7 +19,6 @@
 #include <asm/udbg.h>
 #include <asm/machdep.h>
 #include <linux/time.h>
-#include <asm/mpc8260.h>
 
 #include <sysdev/fsl_soc.h>
 #include <sysdev/cpm2_pic.h>
@@ -28,15 +27,15 @@
 
 static void __init km82xx_pic_init(void)
 {
-	struct device_node *np = of_find_compatible_node(NULL, NULL,
-							"fsl,pq2-pic");
+	struct device_node *np __free(device_node);
+	np = of_find_compatible_node(NULL, NULL, "fsl,pq2-pic");
+
 	if (!np) {
 		pr_err("PIC init: can not find cpm-pic node\n");
 		return;
 	}
 
 	cpm2_pic_init(np);
-	of_node_put(np);
 }
 
 struct cpm_pin {
diff --git a/arch/powerpc/platforms/82xx/m82xx_pci.h b/arch/powerpc/platforms/82xx/m82xx_pci.h
deleted file mode 100644
index d07c4d7606f6..000000000000
--- a/arch/powerpc/platforms/82xx/m82xx_pci.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _PPC_KERNEL_M82XX_PCI_H
-#define _PPC_KERNEL_M82XX_PCI_H
-
-/*
- */
-
-#define SIU_INT_IRQ1   ((uint)0x13 + CPM_IRQ_OFFSET)
-
-#ifndef _IO_BASE
-#define _IO_BASE isa_io_base
-#endif
-
-#endif				/* _PPC_KERNEL_M8260_PCI_H */
diff --git a/arch/powerpc/platforms/82xx/pq2.c b/arch/powerpc/platforms/82xx/pq2.c
index 3b5cb39a564c..391d72a2e09d 100644
--- a/arch/powerpc/platforms/82xx/pq2.c
+++ b/arch/powerpc/platforms/82xx/pq2.c
@@ -32,49 +32,3 @@ void __noreturn pq2_restart(char *cmd)
 	panic("Restart failed\n");
 }
 NOKPROBE_SYMBOL(pq2_restart)
-
-#ifdef CONFIG_PCI
-static int pq2_pci_exclude_device(struct pci_controller *hose,
-                                  u_char bus, u8 devfn)
-{
-	if (bus == 0 && PCI_SLOT(devfn) == 0)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	else
-		return PCIBIOS_SUCCESSFUL;
-}
-
-static void __init pq2_pci_add_bridge(struct device_node *np)
-{
-	struct pci_controller *hose;
-	struct resource r;
-
-	if (of_address_to_resource(np, 0, &r) || r.end - r.start < 0x10b)
-		goto err;
-
-	pci_add_flags(PCI_REASSIGN_ALL_BUS);
-
-	hose = pcibios_alloc_controller(np);
-	if (!hose)
-		return;
-
-	hose->dn = np;
-
-	setup_indirect_pci(hose, r.start + 0x100, r.start + 0x104, 0);
-	pci_process_bridge_OF_ranges(hose, np, 1);
-
-	return;
-
-err:
-	printk(KERN_ERR "No valid PCI reg property in device tree\n");
-}
-
-void __init pq2_init_pci(void)
-{
-	struct device_node *np;
-
-	ppc_md.pci_exclude_device = pq2_pci_exclude_device;
-
-	for_each_compatible_node(np, NULL, "fsl,pq2-pci")
-		pq2_pci_add_bridge(np);
-}
-#endif
diff --git a/arch/powerpc/platforms/83xx/Makefile b/arch/powerpc/platforms/83xx/Makefile
index 6b4013e01b3b..6fc3dba943da 100644
--- a/arch/powerpc/platforms/83xx/Makefile
+++ b/arch/powerpc/platforms/83xx/Makefile
@@ -2,7 +2,7 @@
 #
 # Makefile for the PowerPC 83xx linux kernel.
 #
-obj-y				:= misc.o usb.o
+obj-y				:= misc.o
 obj-$(CONFIG_SUSPEND)		+= suspend.o suspend-asm.o
 obj-$(CONFIG_MCU_MPC8349EMITX)	+= mcu_mpc8349emitx.o
 obj-$(CONFIG_MPC830x_RDB)	+= mpc830x_rdb.o
@@ -13,3 +13,6 @@ obj-$(CONFIG_MPC836x_RDK)	+= mpc836x_rdk.o
 obj-$(CONFIG_MPC837x_RDB)	+= mpc837x_rdb.o
 obj-$(CONFIG_ASP834x)		+= asp834x.o
 obj-$(CONFIG_KMETER1)		+= km83xx.o
+obj-$(CONFIG_PPC_MPC831x)	+= usb_831x.o
+obj-$(CONFIG_PPC_MPC834x)	+= usb_834x.o
+obj-$(CONFIG_PPC_MPC837x)	+= usb_837x.o
diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index 26ddc7136547..2b5d187d9b62 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -20,8 +20,8 @@
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
 #include <linux/initrd.h>
-#include <linux/of_platform.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 
 #include <linux/atomic.h>
 #include <linux/time.h>
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index 77ed61306a73..80d944f29288 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -92,10 +92,11 @@ static void mcu_power_off(void)
 	mutex_unlock(&mcu->lock);
 }
 
-static void mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
+static int mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 {
 	struct mcu *mcu = gpiochip_get_data(gc);
 	u8 bit = 1 << (4 + gpio);
+	int ret;
 
 	mutex_lock(&mcu->lock);
 	if (val)
@@ -103,14 +104,16 @@ static void mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 	else
 		mcu->reg_ctrl |= bit;
 
-	i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL, mcu->reg_ctrl);
+	ret = i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL,
+					mcu->reg_ctrl);
 	mutex_unlock(&mcu->lock);
+
+	return ret;
 }
 
 static int mcu_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 {
-	mcu_gpio_set(gc, gpio, val);
-	return 0;
+	return mcu_gpio_set(gc, gpio, val);
 }
 
 static int mcu_gpiochip_add(struct mcu *mcu)
@@ -120,6 +123,8 @@ static int mcu_gpiochip_add(struct mcu *mcu)
 
 	gc->owner = THIS_MODULE;
 	gc->label = kasprintf(GFP_KERNEL, "%pfw", dev_fwnode(dev));
+	if (!gc->label)
+		return -ENOMEM;
 	gc->can_sleep = 1;
 	gc->ngpio = MCU_NUM_GPIO;
 	gc->base = -1;
@@ -211,7 +216,7 @@ static struct i2c_driver mcu_driver = {
 		.name = "mcu-mpc8349emitx",
 		.of_match_table = mcu_of_match_table,
 	},
-	.probe_new = mcu_probe,
+	.probe = mcu_probe,
 	.remove	= mcu_remove,
 	.id_table = mcu_ids,
 };
diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c
index 2fb2a85d131f..1135c1ab923c 100644
--- a/arch/powerpc/platforms/83xx/misc.c
+++ b/arch/powerpc/platforms/83xx/misc.c
@@ -14,6 +14,8 @@
 #include <asm/io.h>
 #include <asm/hw_irq.h>
 #include <asm/ipic.h>
+#include <asm/fixmap.h>
+
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
 
diff --git a/arch/powerpc/platforms/83xx/mpc830x_rdb.c b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
index 534bb227480d..63b6d213726a 100644
--- a/arch/powerpc/platforms/83xx/mpc830x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
@@ -34,19 +34,11 @@ static const char *board[] __initdata = {
 	NULL
 };
 
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init mpc830x_rdb_probe(void)
-{
-	return of_device_compatible_match(of_root, board);
-}
-
 machine_device_initcall(mpc830x_rdb, mpc83xx_declare_of_platform_devices);
 
 define_machine(mpc830x_rdb) {
 	.name			= "MPC830x RDB",
-	.probe			= mpc830x_rdb_probe,
+	.compatibles		= board,
 	.setup_arch		= mpc830x_rdb_setup_arch,
 	.discover_phbs		= mpc83xx_setup_pci,
 	.init_IRQ		= mpc83xx_ipic_init_IRQ,
diff --git a/arch/powerpc/platforms/83xx/mpc831x_rdb.c b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
index 7b901ab3b864..5c39966762e4 100644
--- a/arch/powerpc/platforms/83xx/mpc831x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
@@ -34,19 +34,11 @@ static const char *board[] __initdata = {
 	NULL
 };
 
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init mpc831x_rdb_probe(void)
-{
-	return of_device_compatible_match(of_root, board);
-}
-
 machine_device_initcall(mpc831x_rdb, mpc83xx_declare_of_platform_devices);
 
 define_machine(mpc831x_rdb) {
 	.name			= "MPC831x RDB",
-	.probe			= mpc831x_rdb_probe,
+	.compatibles		= board,
 	.setup_arch		= mpc831x_rdb_setup_arch,
 	.discover_phbs		= mpc83xx_setup_pci,
 	.init_IRQ		= mpc83xx_ipic_init_IRQ,
diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
index 3b4e4173c59e..d523ce0f48db 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
@@ -15,8 +15,10 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/mmc_spi.h>
 #include <linux/mmc/host.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/fsl_devices.h>
 
 #include <asm/time.h>
diff --git a/arch/powerpc/platforms/83xx/mpc837x_rdb.c b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
index 39e78018dd0b..45823e147933 100644
--- a/arch/powerpc/platforms/83xx/mpc837x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
@@ -61,17 +61,9 @@ static const char * const board[] __initconst = {
 	NULL
 };
 
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init mpc837x_rdb_probe(void)
-{
-	return of_device_compatible_match(of_root, board);
-}
-
 define_machine(mpc837x_rdb) {
 	.name			= "MPC837x RDB/WLAN",
-	.probe			= mpc837x_rdb_probe,
+	.compatibles		= board,
 	.setup_arch		= mpc837x_rdb_setup_arch,
 	.discover_phbs  	= mpc83xx_setup_pci,
 	.init_IRQ		= mpc83xx_ipic_init_IRQ,
diff --git a/arch/powerpc/platforms/83xx/mpc83xx.h b/arch/powerpc/platforms/83xx/mpc83xx.h
index aea803ba3a15..0b8738a2b980 100644
--- a/arch/powerpc/platforms/83xx/mpc83xx.h
+++ b/arch/powerpc/platforms/83xx/mpc83xx.h
@@ -3,8 +3,6 @@
 #define __MPC83XX_H__
 
 #include <linux/init.h>
-#include <linux/device.h>
-#include <asm/pci-bridge.h>
 
 /* System Clock Control Register */
 #define MPC83XX_SCCR_OFFS          0xA08
diff --git a/arch/powerpc/platforms/83xx/suspend-asm.S b/arch/powerpc/platforms/83xx/suspend-asm.S
index bc6bd4d0ae96..6a62ed6082c9 100644
--- a/arch/powerpc/platforms/83xx/suspend-asm.S
+++ b/arch/powerpc/platforms/83xx/suspend-asm.S
@@ -68,7 +68,8 @@ _GLOBAL(mpc83xx_enter_deep_sleep)
 
 	mfspr	r5, SPRN_HID0
 	mfspr	r6, SPRN_HID1
-	mfspr	r7, SPRN_HID2
+	/* FIXME: Should this use SPRN_HID2_G2_LE? */
+	mfspr	r7, SPRN_HID2_750FX
 
 	stw	r5, SS_HID+0(r3)
 	stw	r6, SS_HID+4(r3)
@@ -396,7 +397,8 @@ mpc83xx_deep_resume:
 
 	mtspr	SPRN_HID0, r5
 	mtspr	SPRN_HID1, r6
-	mtspr	SPRN_HID2, r7
+	/* FIXME: Should this use SPRN_HID2_G2_LE? */
+	mtspr	SPRN_HID2_750FX, r7
 
 	lwz	r4, SS_IABR+0(r3)
 	lwz	r5, SS_IABR+4(r3)
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 3fa8979ac8a6..99bd4355f28e 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -19,7 +19,7 @@
 #include <linux/fsl_devices.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/export.h>
 
 #include <asm/reg.h>
@@ -206,7 +206,8 @@ static int mpc83xx_suspend_enter(suspend_state_t state)
 		out_be32(&pmc_regs->config1,
 		         in_be32(&pmc_regs->config1) | PMCCR1_POWER_OFF);
 
-		enable_kernel_fp();
+		if (IS_ENABLED(CONFIG_PPC_FPU))
+			enable_kernel_fp();
 
 		mpc83xx_enter_deep_sleep(immrbase);
 
@@ -261,9 +262,10 @@ static int mpc83xx_suspend_begin(suspend_state_t state)
 
 static int agent_thread_fn(void *data)
 {
+	set_freezable();
+
 	while (1) {
-		wait_event_interruptible(agent_wq, pci_pm_state >= 2);
-		try_to_freeze();
+		wait_event_freezable(agent_wq, pci_pm_state >= 2);
 
 		if (signal_pending(current) || pci_pm_state < 2)
 			continue;
diff --git a/arch/powerpc/platforms/83xx/usb.c b/arch/powerpc/platforms/83xx/usb.c
deleted file mode 100644
index e2a13a052f96..000000000000
--- a/arch/powerpc/platforms/83xx/usb.c
+++ /dev/null
@@ -1,251 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Freescale 83xx USB SOC setup code
- *
- * Copyright (C) 2007 Freescale Semiconductor, Inc.
- * Author: Li Yang
- */
-
-
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-
-#include <asm/io.h>
-#include <sysdev/fsl_soc.h>
-
-#include "mpc83xx.h"
-
-
-#ifdef CONFIG_PPC_MPC834x
-int __init mpc834x_usb_cfg(void)
-{
-	unsigned long sccr, sicrl, sicrh;
-	void __iomem *immap;
-	struct device_node *np = NULL;
-	int port0_is_dr = 0, port1_is_dr = 0;
-	const void *prop, *dr_mode;
-
-	immap = ioremap(get_immrbase(), 0x1000);
-	if (!immap)
-		return -ENOMEM;
-
-	/* Read registers */
-	/* Note: DR and MPH must use the same clock setting in SCCR */
-	sccr = in_be32(immap + MPC83XX_SCCR_OFFS) & ~MPC83XX_SCCR_USB_MASK;
-	sicrl = in_be32(immap + MPC83XX_SICRL_OFFS) & ~MPC834X_SICRL_USB_MASK;
-	sicrh = in_be32(immap + MPC83XX_SICRH_OFFS) & ~MPC834X_SICRH_USB_UTMI;
-
-	np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr");
-	if (np) {
-		sccr |= MPC83XX_SCCR_USB_DRCM_11;  /* 1:3 */
-
-		prop = of_get_property(np, "phy_type", NULL);
-		port1_is_dr = 1;
-		if (prop && (!strcmp(prop, "utmi") ||
-					!strcmp(prop, "utmi_wide"))) {
-			sicrl |= MPC834X_SICRL_USB0 | MPC834X_SICRL_USB1;
-			sicrh |= MPC834X_SICRH_USB_UTMI;
-			port0_is_dr = 1;
-		} else if (prop && !strcmp(prop, "serial")) {
-			dr_mode = of_get_property(np, "dr_mode", NULL);
-			if (dr_mode && !strcmp(dr_mode, "otg")) {
-				sicrl |= MPC834X_SICRL_USB0 | MPC834X_SICRL_USB1;
-				port0_is_dr = 1;
-			} else {
-				sicrl |= MPC834X_SICRL_USB1;
-			}
-		} else if (prop && !strcmp(prop, "ulpi")) {
-			sicrl |= MPC834X_SICRL_USB1;
-		} else {
-			printk(KERN_WARNING "834x USB PHY type not supported\n");
-		}
-		of_node_put(np);
-	}
-	np = of_find_compatible_node(NULL, NULL, "fsl-usb2-mph");
-	if (np) {
-		sccr |= MPC83XX_SCCR_USB_MPHCM_11; /* 1:3 */
-
-		prop = of_get_property(np, "port0", NULL);
-		if (prop) {
-			if (port0_is_dr)
-				printk(KERN_WARNING
-					"834x USB port0 can't be used by both DR and MPH!\n");
-			sicrl &= ~MPC834X_SICRL_USB0;
-		}
-		prop = of_get_property(np, "port1", NULL);
-		if (prop) {
-			if (port1_is_dr)
-				printk(KERN_WARNING
-					"834x USB port1 can't be used by both DR and MPH!\n");
-			sicrl &= ~MPC834X_SICRL_USB1;
-		}
-		of_node_put(np);
-	}
-
-	/* Write back */
-	out_be32(immap + MPC83XX_SCCR_OFFS, sccr);
-	out_be32(immap + MPC83XX_SICRL_OFFS, sicrl);
-	out_be32(immap + MPC83XX_SICRH_OFFS, sicrh);
-
-	iounmap(immap);
-	return 0;
-}
-#endif /* CONFIG_PPC_MPC834x */
-
-#ifdef CONFIG_PPC_MPC831x
-int __init mpc831x_usb_cfg(void)
-{
-	u32 temp;
-	void __iomem *immap, *usb_regs;
-	struct device_node *np = NULL;
-	struct device_node *immr_node = NULL;
-	const void *prop;
-	struct resource res;
-	int ret = 0;
-#ifdef CONFIG_USB_OTG
-	const void *dr_mode;
-#endif
-
-	np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr");
-	if (!np)
-		return -ENODEV;
-	prop = of_get_property(np, "phy_type", NULL);
-
-	/* Map IMMR space for pin and clock settings */
-	immap = ioremap(get_immrbase(), 0x1000);
-	if (!immap) {
-		of_node_put(np);
-		return -ENOMEM;
-	}
-
-	/* Configure clock */
-	immr_node = of_get_parent(np);
-	if (immr_node && (of_device_is_compatible(immr_node, "fsl,mpc8315-immr") ||
-			of_device_is_compatible(immr_node, "fsl,mpc8308-immr")))
-		clrsetbits_be32(immap + MPC83XX_SCCR_OFFS,
-		                MPC8315_SCCR_USB_MASK,
-		                MPC8315_SCCR_USB_DRCM_01);
-	else
-		clrsetbits_be32(immap + MPC83XX_SCCR_OFFS,
-		                MPC83XX_SCCR_USB_MASK,
-		                MPC83XX_SCCR_USB_DRCM_11);
-
-	/* Configure pin mux for ULPI.  There is no pin mux for UTMI */
-	if (prop && !strcmp(prop, "ulpi")) {
-		if (of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) {
-			clrsetbits_be32(immap + MPC83XX_SICRH_OFFS,
-					MPC8308_SICRH_USB_MASK,
-					MPC8308_SICRH_USB_ULPI);
-		} else if (of_device_is_compatible(immr_node, "fsl,mpc8315-immr")) {
-			clrsetbits_be32(immap + MPC83XX_SICRL_OFFS,
-					MPC8315_SICRL_USB_MASK,
-					MPC8315_SICRL_USB_ULPI);
-			clrsetbits_be32(immap + MPC83XX_SICRH_OFFS,
-					MPC8315_SICRH_USB_MASK,
-					MPC8315_SICRH_USB_ULPI);
-		} else {
-			clrsetbits_be32(immap + MPC83XX_SICRL_OFFS,
-					MPC831X_SICRL_USB_MASK,
-					MPC831X_SICRL_USB_ULPI);
-			clrsetbits_be32(immap + MPC83XX_SICRH_OFFS,
-					MPC831X_SICRH_USB_MASK,
-					MPC831X_SICRH_USB_ULPI);
-		}
-	}
-
-	iounmap(immap);
-
-	of_node_put(immr_node);
-
-	/* Map USB SOC space */
-	ret = of_address_to_resource(np, 0, &res);
-	if (ret) {
-		of_node_put(np);
-		return ret;
-	}
-	usb_regs = ioremap(res.start, resource_size(&res));
-
-	/* Using on-chip PHY */
-	if (prop && (!strcmp(prop, "utmi_wide") ||
-		     !strcmp(prop, "utmi"))) {
-		u32 refsel;
-
-		if (of_device_is_compatible(immr_node, "fsl,mpc8308-immr"))
-			goto out;
-
-		if (of_device_is_compatible(immr_node, "fsl,mpc8315-immr"))
-			refsel = CONTROL_REFSEL_24MHZ;
-		else
-			refsel = CONTROL_REFSEL_48MHZ;
-		/* Set UTMI_PHY_EN and REFSEL */
-		out_be32(usb_regs + FSL_USB2_CONTROL_OFFS,
-				CONTROL_UTMI_PHY_EN | refsel);
-	/* Using external UPLI PHY */
-	} else if (prop && !strcmp(prop, "ulpi")) {
-		/* Set PHY_CLK_SEL to ULPI */
-		temp = CONTROL_PHY_CLK_SEL_ULPI;
-#ifdef CONFIG_USB_OTG
-		/* Set OTG_PORT */
-		if (!of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) {
-			dr_mode = of_get_property(np, "dr_mode", NULL);
-			if (dr_mode && !strcmp(dr_mode, "otg"))
-				temp |= CONTROL_OTG_PORT;
-		}
-#endif /* CONFIG_USB_OTG */
-		out_be32(usb_regs + FSL_USB2_CONTROL_OFFS, temp);
-	} else {
-		printk(KERN_WARNING "831x USB PHY type not supported\n");
-		ret = -EINVAL;
-	}
-
-out:
-	iounmap(usb_regs);
-	of_node_put(np);
-	return ret;
-}
-#endif /* CONFIG_PPC_MPC831x */
-
-#ifdef CONFIG_PPC_MPC837x
-int __init mpc837x_usb_cfg(void)
-{
-	void __iomem *immap;
-	struct device_node *np = NULL;
-	const void *prop;
-	int ret = 0;
-
-	np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr");
-	if (!np || !of_device_is_available(np)) {
-		of_node_put(np);
-		return -ENODEV;
-	}
-	prop = of_get_property(np, "phy_type", NULL);
-
-	if (!prop || (strcmp(prop, "ulpi") && strcmp(prop, "serial"))) {
-		printk(KERN_WARNING "837x USB PHY type not supported\n");
-		of_node_put(np);
-		return -EINVAL;
-	}
-
-	/* Map IMMR space for pin and clock settings */
-	immap = ioremap(get_immrbase(), 0x1000);
-	if (!immap) {
-		of_node_put(np);
-		return -ENOMEM;
-	}
-
-	/* Configure clock */
-	clrsetbits_be32(immap + MPC83XX_SCCR_OFFS, MPC837X_SCCR_USB_DRCM_11,
-			MPC837X_SCCR_USB_DRCM_11);
-
-	/* Configure pin mux for ULPI/serial */
-	clrsetbits_be32(immap + MPC83XX_SICRL_OFFS, MPC837X_SICRL_USB_MASK,
-			MPC837X_SICRL_USB_ULPI);
-
-	iounmap(immap);
-	of_node_put(np);
-	return ret;
-}
-#endif /* CONFIG_PPC_MPC837x */
diff --git a/arch/powerpc/platforms/83xx/usb_831x.c b/arch/powerpc/platforms/83xx/usb_831x.c
new file mode 100644
index 000000000000..28c24e90f022
--- /dev/null
+++ b/arch/powerpc/platforms/83xx/usb_831x.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Freescale 83xx USB SOC setup code
+ *
+ * Copyright (C) 2007 Freescale Semiconductor, Inc.
+ * Author: Li Yang
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+
+#include <sysdev/fsl_soc.h>
+
+#include "mpc83xx.h"
+
+int __init mpc831x_usb_cfg(void)
+{
+	u32 temp;
+	void __iomem *immap, *usb_regs;
+	struct device_node *np = NULL;
+	struct device_node *immr_node = NULL;
+	const void *prop;
+	struct resource res;
+	int ret = 0;
+#ifdef CONFIG_USB_OTG
+	const void *dr_mode;
+#endif
+
+	np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr");
+	if (!np)
+		return -ENODEV;
+	prop = of_get_property(np, "phy_type", NULL);
+
+	/* Map IMMR space for pin and clock settings */
+	immap = ioremap(get_immrbase(), 0x1000);
+	if (!immap) {
+		of_node_put(np);
+		return -ENOMEM;
+	}
+
+	/* Configure clock */
+	immr_node = of_get_parent(np);
+	if (immr_node && (of_device_is_compatible(immr_node, "fsl,mpc8315-immr") ||
+			  of_device_is_compatible(immr_node, "fsl,mpc8308-immr")))
+		clrsetbits_be32(immap + MPC83XX_SCCR_OFFS,
+				MPC8315_SCCR_USB_MASK,
+				MPC8315_SCCR_USB_DRCM_01);
+	else
+		clrsetbits_be32(immap + MPC83XX_SCCR_OFFS,
+				MPC83XX_SCCR_USB_MASK,
+				MPC83XX_SCCR_USB_DRCM_11);
+
+	/* Configure pin mux for ULPI.  There is no pin mux for UTMI */
+	if (prop && !strcmp(prop, "ulpi")) {
+		if (of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) {
+			clrsetbits_be32(immap + MPC83XX_SICRH_OFFS,
+					MPC8308_SICRH_USB_MASK,
+					MPC8308_SICRH_USB_ULPI);
+		} else if (of_device_is_compatible(immr_node, "fsl,mpc8315-immr")) {
+			clrsetbits_be32(immap + MPC83XX_SICRL_OFFS,
+					MPC8315_SICRL_USB_MASK,
+					MPC8315_SICRL_USB_ULPI);
+			clrsetbits_be32(immap + MPC83XX_SICRH_OFFS,
+					MPC8315_SICRH_USB_MASK,
+					MPC8315_SICRH_USB_ULPI);
+		} else {
+			clrsetbits_be32(immap + MPC83XX_SICRL_OFFS,
+					MPC831X_SICRL_USB_MASK,
+					MPC831X_SICRL_USB_ULPI);
+			clrsetbits_be32(immap + MPC83XX_SICRH_OFFS,
+					MPC831X_SICRH_USB_MASK,
+					MPC831X_SICRH_USB_ULPI);
+		}
+	}
+
+	iounmap(immap);
+
+	of_node_put(immr_node);
+
+	/* Map USB SOC space */
+	ret = of_address_to_resource(np, 0, &res);
+	if (ret) {
+		of_node_put(np);
+		return ret;
+	}
+	usb_regs = ioremap(res.start, resource_size(&res));
+
+	/* Using on-chip PHY */
+	if (prop && (!strcmp(prop, "utmi_wide") || !strcmp(prop, "utmi"))) {
+		u32 refsel;
+
+		if (of_device_is_compatible(immr_node, "fsl,mpc8308-immr"))
+			goto out;
+
+		if (of_device_is_compatible(immr_node, "fsl,mpc8315-immr"))
+			refsel = CONTROL_REFSEL_24MHZ;
+		else
+			refsel = CONTROL_REFSEL_48MHZ;
+		/* Set UTMI_PHY_EN and REFSEL */
+		out_be32(usb_regs + FSL_USB2_CONTROL_OFFS,
+			 CONTROL_UTMI_PHY_EN | refsel);
+	/* Using external UPLI PHY */
+	} else if (prop && !strcmp(prop, "ulpi")) {
+		/* Set PHY_CLK_SEL to ULPI */
+		temp = CONTROL_PHY_CLK_SEL_ULPI;
+#ifdef CONFIG_USB_OTG
+		/* Set OTG_PORT */
+		if (!of_device_is_compatible(immr_node, "fsl,mpc8308-immr")) {
+			dr_mode = of_get_property(np, "dr_mode", NULL);
+			if (dr_mode && !strcmp(dr_mode, "otg"))
+				temp |= CONTROL_OTG_PORT;
+		}
+#endif /* CONFIG_USB_OTG */
+		out_be32(usb_regs + FSL_USB2_CONTROL_OFFS, temp);
+	} else {
+		pr_warn("831x USB PHY type not supported\n");
+		ret = -EINVAL;
+	}
+
+out:
+	iounmap(usb_regs);
+	of_node_put(np);
+	return ret;
+}
diff --git a/arch/powerpc/platforms/83xx/usb_834x.c b/arch/powerpc/platforms/83xx/usb_834x.c
new file mode 100644
index 000000000000..3a8d6c662d06
--- /dev/null
+++ b/arch/powerpc/platforms/83xx/usb_834x.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Freescale 83xx USB SOC setup code
+ *
+ * Copyright (C) 2007 Freescale Semiconductor, Inc.
+ * Author: Li Yang
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+
+#include <sysdev/fsl_soc.h>
+
+#include "mpc83xx.h"
+
+int __init mpc834x_usb_cfg(void)
+{
+	unsigned long sccr, sicrl, sicrh;
+	void __iomem *immap;
+	struct device_node *np = NULL;
+	int port0_is_dr = 0, port1_is_dr = 0;
+	const void *prop, *dr_mode;
+
+	immap = ioremap(get_immrbase(), 0x1000);
+	if (!immap)
+		return -ENOMEM;
+
+	/* Read registers */
+	/* Note: DR and MPH must use the same clock setting in SCCR */
+	sccr = in_be32(immap + MPC83XX_SCCR_OFFS) & ~MPC83XX_SCCR_USB_MASK;
+	sicrl = in_be32(immap + MPC83XX_SICRL_OFFS) & ~MPC834X_SICRL_USB_MASK;
+	sicrh = in_be32(immap + MPC83XX_SICRH_OFFS) & ~MPC834X_SICRH_USB_UTMI;
+
+	np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr");
+	if (np) {
+		sccr |= MPC83XX_SCCR_USB_DRCM_11;  /* 1:3 */
+
+		prop = of_get_property(np, "phy_type", NULL);
+		port1_is_dr = 1;
+		if (prop &&
+		    (!strcmp(prop, "utmi") || !strcmp(prop, "utmi_wide"))) {
+			sicrl |= MPC834X_SICRL_USB0 | MPC834X_SICRL_USB1;
+			sicrh |= MPC834X_SICRH_USB_UTMI;
+			port0_is_dr = 1;
+		} else if (prop && !strcmp(prop, "serial")) {
+			dr_mode = of_get_property(np, "dr_mode", NULL);
+			if (dr_mode && !strcmp(dr_mode, "otg")) {
+				sicrl |= MPC834X_SICRL_USB0 | MPC834X_SICRL_USB1;
+				port0_is_dr = 1;
+			} else {
+				sicrl |= MPC834X_SICRL_USB1;
+			}
+		} else if (prop && !strcmp(prop, "ulpi")) {
+			sicrl |= MPC834X_SICRL_USB1;
+		} else {
+			pr_warn("834x USB PHY type not supported\n");
+		}
+		of_node_put(np);
+	}
+	np = of_find_compatible_node(NULL, NULL, "fsl-usb2-mph");
+	if (np) {
+		sccr |= MPC83XX_SCCR_USB_MPHCM_11; /* 1:3 */
+
+		prop = of_get_property(np, "port0", NULL);
+		if (prop) {
+			if (port0_is_dr)
+				pr_warn("834x USB port0 can't be used by both DR and MPH!\n");
+			sicrl &= ~MPC834X_SICRL_USB0;
+		}
+		prop = of_get_property(np, "port1", NULL);
+		if (prop) {
+			if (port1_is_dr)
+				pr_warn("834x USB port1 can't be used by both DR and MPH!\n");
+			sicrl &= ~MPC834X_SICRL_USB1;
+		}
+		of_node_put(np);
+	}
+
+	/* Write back */
+	out_be32(immap + MPC83XX_SCCR_OFFS, sccr);
+	out_be32(immap + MPC83XX_SICRL_OFFS, sicrl);
+	out_be32(immap + MPC83XX_SICRH_OFFS, sicrh);
+
+	iounmap(immap);
+	return 0;
+}
diff --git a/arch/powerpc/platforms/83xx/usb_837x.c b/arch/powerpc/platforms/83xx/usb_837x.c
new file mode 100644
index 000000000000..726935bb6e2d
--- /dev/null
+++ b/arch/powerpc/platforms/83xx/usb_837x.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Freescale 83xx USB SOC setup code
+ *
+ * Copyright (C) 2007 Freescale Semiconductor, Inc.
+ * Author: Li Yang
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/io.h>
+
+#include <sysdev/fsl_soc.h>
+
+#include "mpc83xx.h"
+
+int __init mpc837x_usb_cfg(void)
+{
+	void __iomem *immap;
+	struct device_node *np = NULL;
+	const void *prop;
+	int ret = 0;
+
+	np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr");
+	if (!np || !of_device_is_available(np)) {
+		of_node_put(np);
+		return -ENODEV;
+	}
+	prop = of_get_property(np, "phy_type", NULL);
+
+	if (!prop || (strcmp(prop, "ulpi") && strcmp(prop, "serial"))) {
+		pr_warn("837x USB PHY type not supported\n");
+		of_node_put(np);
+		return -EINVAL;
+	}
+
+	/* Map IMMR space for pin and clock settings */
+	immap = ioremap(get_immrbase(), 0x1000);
+	if (!immap) {
+		of_node_put(np);
+		return -ENOMEM;
+	}
+
+	/* Configure clock */
+	clrsetbits_be32(immap + MPC83XX_SCCR_OFFS, MPC837X_SCCR_USB_DRCM_11,
+			MPC837X_SCCR_USB_DRCM_11);
+
+	/* Configure pin mux for ULPI/serial */
+	clrsetbits_be32(immap + MPC83XX_SICRL_OFFS, MPC837X_SICRL_USB_MASK,
+			MPC837X_SICRL_USB_ULPI);
+
+	iounmap(immap);
+	of_node_put(np);
+	return ret;
+}
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 9315a3b69d6d..604c1b4b6d45 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -40,27 +40,6 @@ config BSC9132_QDS
 	  and dual StarCore SC3850 DSP cores.
 	  Manufacturer : Freescale Semiconductor, Inc
 
-config MPC8540_ADS
-	bool "Freescale MPC8540 ADS"
-	select DEFAULT_UIMAGE
-	help
-	  This option enables support for the MPC 8540 ADS board
-
-config MPC8560_ADS
-	bool "Freescale MPC8560 ADS"
-	select DEFAULT_UIMAGE
-	select CPM2
-	help
-	  This option enables support for the MPC 8560 ADS board
-
-config MPC85xx_CDS
-	bool "Freescale MPC85xx CDS"
-	select DEFAULT_UIMAGE
-	select PPC_I8259
-	select HAVE_RAPIDIO
-	help
-	  This option enables support for the MPC85xx CDS board
-
 config MPC85xx_MDS
 	bool "Freescale MPC8568 MDS / MPC8569 MDS / P1021 MDS"
 	select DEFAULT_UIMAGE
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index e3d977624e33..43c34f26f108 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -12,9 +12,6 @@ obj-y += common.o
 obj-$(CONFIG_BSC9131_RDB) += bsc913x_rdb.o
 obj-$(CONFIG_BSC9132_QDS) += bsc913x_qds.o
 obj-$(CONFIG_C293_PCIE)   += c293pcie.o
-obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o
-obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o
-obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o
 obj-$(CONFIG_MPC8536_DS)  += mpc8536_ds.o
 obj8259-$(CONFIG_PPC_I8259)   += mpc85xx_8259.o
 obj-$(CONFIG_MPC85xx_DS)  += mpc85xx_ds.o $(obj8259-y)
diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c
index a029aa090538..3ad8096fcf16 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_qds.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c
@@ -9,7 +9,7 @@
  * Copyright 2014 Freescale Semiconductor Inc.
  */
 
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/pci.h>
 #include <asm/mpic.h>
 #include <sysdev/fsl_soc.h>
@@ -19,7 +19,7 @@
 #include "mpc85xx.h"
 #include "smp.h"
 
-void __init bsc913x_qds_pic_init(void)
+static void __init bsc913x_qds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 	  MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
index 361b4371d073..dcd358c28201 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_rdb.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
@@ -7,7 +7,7 @@
  * Copyright 2011-2012 Freescale Semiconductor Inc.
  */
 
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/pci.h>
 #include <asm/mpic.h>
 #include <sysdev/fsl_soc.h>
@@ -15,7 +15,7 @@
 
 #include "mpc85xx.h"
 
-void __init bsc913x_rdb_pic_init(void)
+static void __init bsc913x_rdb_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 	  MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c
index 34975708be79..7a63a3ad5e8a 100644
--- a/arch/powerpc/platforms/85xx/c293pcie.c
+++ b/arch/powerpc/platforms/85xx/c293pcie.c
@@ -7,8 +7,7 @@
 
 #include <linux/stddef.h>
 #include <linux/kernel.h>
-#include <linux/of_fdt.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 
 #include <asm/machdep.h>
 #include <asm/udbg.h>
diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c
index a554b6d87cf7..757811155587 100644
--- a/arch/powerpc/platforms/85xx/common.c
+++ b/arch/powerpc/platforms/85xx/common.c
@@ -3,6 +3,7 @@
  * Routines common to most mpc85xx-based boards.
  */
 
+#include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index bfde391c42f4..c44400e95f55 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -30,7 +30,7 @@
 #include "smp.h"
 #include "mpc85xx.h"
 
-void __init corenet_gen_pic_init(void)
+static void __init corenet_gen_pic_init(void)
 {
 	struct mpic *mpic;
 	unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU |
@@ -48,7 +48,7 @@ void __init corenet_gen_pic_init(void)
 /*
  * Setup the architecture
  */
-void __init corenet_gen_setup_arch(void)
+static void __init corenet_gen_setup_arch(void)
 {
 	mpc85xx_smp_init();
 
@@ -101,7 +101,7 @@ static const struct of_device_id of_device_ids[] = {
 	{}
 };
 
-int __init corenet_gen_publish_devices(void)
+static int __init corenet_gen_publish_devices(void)
 {
 	return of_platform_bus_probe(NULL, of_device_ids, NULL);
 }
@@ -149,7 +149,7 @@ static int __init corenet_generic_probe(void)
 	extern struct smp_ops_t smp_85xx_ops;
 #endif
 
-	if (of_device_compatible_match(of_root, boards))
+	if (of_machine_compatible_match(boards))
 		return 1;
 
 	/* Check if we're running under the Freescale hypervisor */
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
index 3678a1fbf5ad..477852f1a726 100644
--- a/arch/powerpc/platforms/85xx/ge_imp3a.c
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -17,8 +17,8 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -38,7 +38,7 @@
 
 void __iomem *imp3a_regs;
 
-void __init ge_imp3a_pic_init(void)
+static void __init ge_imp3a_pic_init(void)
 {
 	struct mpic *mpic;
 	struct device_node *np;
diff --git a/arch/powerpc/platforms/85xx/ksi8560.c b/arch/powerpc/platforms/85xx/ksi8560.c
index af38c3aec042..1b6326a4b0f2 100644
--- a/arch/powerpc/platforms/85xx/ksi8560.c
+++ b/arch/powerpc/platforms/85xx/ksi8560.c
@@ -18,7 +18,8 @@
 #include <linux/kdev_t.h>
 #include <linux/delay.h>
 #include <linux/seq_file.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index 58ab3831913f..b3327a358eb4 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -12,7 +12,7 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -27,7 +27,7 @@
 
 #include "mpc85xx.h"
 
-void __init mpc8536_ds_pic_init(void)
+static void __init mpc8536_ds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
 			0, 256, " OpenPIC  ");
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
deleted file mode 100644
index 7c67438e76f8..000000000000
--- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c
+++ /dev/null
@@ -1,162 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * MPC85xx setup and early boot code plus other random bits.
- *
- * Maintained by Kumar Gala (see MAINTAINERS for contact information)
- *
- * Copyright 2005 Freescale Semiconductor Inc.
- */
-
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/delay.h>
-#include <linux/seq_file.h>
-#include <linux/of_platform.h>
-
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/mpic.h>
-#include <mm/mmu_decl.h>
-#include <asm/udbg.h>
-
-#include <sysdev/fsl_soc.h>
-#include <sysdev/fsl_pci.h>
-
-#ifdef CONFIG_CPM2
-#include <asm/cpm2.h>
-#include <sysdev/cpm2_pic.h>
-#endif
-
-#include "mpc85xx.h"
-
-static void __init mpc85xx_ads_pic_init(void)
-{
-	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
-			0, 256, " OpenPIC  ");
-	BUG_ON(mpic == NULL);
-	mpic_init(mpic);
-
-	mpc85xx_cpm2_pic_init();
-}
-
-/*
- * Setup the architecture
- */
-#ifdef CONFIG_CPM2
-struct cpm_pin {
-	int port, pin, flags;
-};
-
-static const struct cpm_pin mpc8560_ads_pins[] = {
-	/* SCC1 */
-	{3, 29, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{3, 30, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY},
-	{3, 31, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-
-	/* SCC2 */
-	{2, 12, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{2, 13, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{3, 26, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{3, 27, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{3, 28, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-
-	/* FCC2 */
-	{1, 18, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 19, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 20, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 21, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 22, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 23, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 24, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 25, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 26, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 27, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 28, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 29, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY},
-	{1, 30, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 31, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{2, 18, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, /* CLK14 */
-	{2, 19, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, /* CLK13 */
-
-	/* FCC3 */
-	{1, 4, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 5, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 6, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 8, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 9, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 10, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 11, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 12, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 13, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 14, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 15, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 16, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 17, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{2, 16, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, /* CLK16 */
-	{2, 17, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, /* CLK15 */
-	{2, 27, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-};
-
-static void __init init_ioports(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mpc8560_ads_pins); i++) {
-		const struct cpm_pin *pin = &mpc8560_ads_pins[i];
-		cpm2_set_pin(pin->port, pin->pin, pin->flags);
-	}
-
-	cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_RX);
-	cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_TX);
-	cpm2_clk_setup(CPM_CLK_SCC2, CPM_BRG2, CPM_CLK_RX);
-	cpm2_clk_setup(CPM_CLK_SCC2, CPM_BRG2, CPM_CLK_TX);
-	cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK13, CPM_CLK_RX);
-	cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK14, CPM_CLK_TX);
-	cpm2_clk_setup(CPM_CLK_FCC3, CPM_CLK15, CPM_CLK_RX);
-	cpm2_clk_setup(CPM_CLK_FCC3, CPM_CLK16, CPM_CLK_TX);
-}
-#endif
-
-static void __init mpc85xx_ads_setup_arch(void)
-{
-	if (ppc_md.progress)
-		ppc_md.progress("mpc85xx_ads_setup_arch()", 0);
-
-#ifdef CONFIG_CPM2
-	cpm2_reset();
-	init_ioports();
-#endif
-
-	fsl_pci_assign_primary();
-}
-
-static void mpc85xx_ads_show_cpuinfo(struct seq_file *m)
-{
-	uint pvid, svid, phid1;
-
-	pvid = mfspr(SPRN_PVR);
-	svid = mfspr(SPRN_SVR);
-
-	seq_printf(m, "Vendor\t\t: Freescale Semiconductor\n");
-	seq_printf(m, "PVR\t\t: 0x%x\n", pvid);
-	seq_printf(m, "SVR\t\t: 0x%x\n", svid);
-
-	/* Display cpu Pll setting */
-	phid1 = mfspr(SPRN_HID1);
-	seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
-}
-
-machine_arch_initcall(mpc85xx_ads, mpc85xx_common_publish_devices);
-
-define_machine(mpc85xx_ads) {
-	.name			= "MPC85xx ADS",
-	.compatible		= "MPC85xxADS",
-	.setup_arch		= mpc85xx_ads_setup_arch,
-	.init_IRQ		= mpc85xx_ads_pic_init,
-	.show_cpuinfo		= mpc85xx_ads_show_cpuinfo,
-	.get_irq		= mpic_get_irq,
-	.progress		= udbg_progress,
-};
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
deleted file mode 100644
index 0e6964c7fdd6..000000000000
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ /dev/null
@@ -1,387 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * MPC85xx setup and early boot code plus other random bits.
- *
- * Maintained by Kumar Gala (see MAINTAINERS for contact information)
- *
- * Copyright 2005, 2011-2012 Freescale Semiconductor Inc.
- */
-
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/reboot.h>
-#include <linux/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/major.h>
-#include <linux/console.h>
-#include <linux/delay.h>
-#include <linux/seq_file.h>
-#include <linux/initrd.h>
-#include <linux/interrupt.h>
-#include <linux/fsl_devices.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/of_platform.h>
-#include <linux/pgtable.h>
-
-#include <asm/page.h>
-#include <linux/atomic.h>
-#include <asm/time.h>
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/ipic.h>
-#include <asm/pci-bridge.h>
-#include <asm/irq.h>
-#include <mm/mmu_decl.h>
-#include <asm/udbg.h>
-#include <asm/mpic.h>
-#include <asm/i8259.h>
-
-#include <sysdev/fsl_soc.h>
-#include <sysdev/fsl_pci.h>
-
-#include "mpc85xx.h"
-
-/*
- * The CDS board contains an FPGA/CPLD called "Cadmus", which collects
- * various logic and performs system control functions.
- * Here is the FPGA/CPLD register map.
- */
-struct cadmus_reg {
-	u8 cm_ver;		/* Board version */
-	u8 cm_csr;		/* General control/status */
-	u8 cm_rst;		/* Reset control */
-	u8 cm_hsclk;	/* High speed clock */
-	u8 cm_hsxclk;	/* High speed clock extended */
-	u8 cm_led;		/* LED data */
-	u8 cm_pci;		/* PCI control/status */
-	u8 cm_dma;		/* DMA control */
-	u8 res[248];	/* Total 256 bytes */
-};
-
-static struct cadmus_reg *cadmus;
-
-#ifdef CONFIG_PCI
-
-#define ARCADIA_HOST_BRIDGE_IDSEL	17
-#define ARCADIA_2ND_BRIDGE_IDSEL	3
-
-static int mpc85xx_exclude_device(struct pci_controller *hose,
-				  u_char bus, u_char devfn)
-{
-	/* We explicitly do not go past the Tundra 320 Bridge */
-	if ((bus == 1) && (PCI_SLOT(devfn) == ARCADIA_2ND_BRIDGE_IDSEL))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	if ((bus == 0) && (PCI_SLOT(devfn) == ARCADIA_2ND_BRIDGE_IDSEL))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	else
-		return PCIBIOS_SUCCESSFUL;
-}
-
-static int mpc85xx_cds_restart(struct notifier_block *this,
-			       unsigned long mode, void *cmd)
-{
-	struct pci_dev *dev;
-	u_char tmp;
-
-	if ((dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C686,
-					NULL))) {
-
-		/* Use the VIA Super Southbridge to force a PCI reset */
-		pci_read_config_byte(dev, 0x47, &tmp);
-		pci_write_config_byte(dev, 0x47, tmp | 1);
-
-		/* Flush the outbound PCI write queues */
-		pci_read_config_byte(dev, 0x47, &tmp);
-
-		/*
-		 *  At this point, the hardware reset should have triggered.
-		 *  However, if it doesn't work for some mysterious reason,
-		 *  just fall through to the default reset below.
-		 */
-
-		pci_dev_put(dev);
-	}
-
-	/*
-	 *  If we can't find the VIA chip (maybe the P2P bridge is
-	 *  disabled) or the VIA chip reset didn't work, just return
-	 *  and let default reset sequence happen.
-	 */
-	return NOTIFY_DONE;
-}
-
-static int mpc85xx_cds_restart_register(void)
-{
-	static struct notifier_block restart_handler;
-
-	restart_handler.notifier_call = mpc85xx_cds_restart;
-	restart_handler.priority = 192;
-
-	return register_restart_handler(&restart_handler);
-}
-machine_arch_initcall(mpc85xx_cds, mpc85xx_cds_restart_register);
-
-
-static void __init mpc85xx_cds_pci_irq_fixup(struct pci_dev *dev)
-{
-	u_char c;
-	if (dev->vendor == PCI_VENDOR_ID_VIA) {
-		switch (dev->device) {
-		case PCI_DEVICE_ID_VIA_82C586_1:
-			/*
-			 * U-Boot does not set the enable bits
-			 * for the IDE device. Force them on here.
-			 */
-			pci_read_config_byte(dev, 0x40, &c);
-			c |= 0x03; /* IDE: Chip Enable Bits */
-			pci_write_config_byte(dev, 0x40, c);
-
-			/*
-			 * Since only primary interface works, force the
-			 * IDE function to standard primary IDE interrupt
-			 * w/ 8259 offset
-			 */
-			dev->irq = 14;
-			pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
-			break;
-		/*
-		 * Force legacy USB interrupt routing
-		 */
-		case PCI_DEVICE_ID_VIA_82C586_2:
-		/* There are two USB controllers.
-		 * Identify them by function number
-		 */
-			if (PCI_FUNC(dev->devfn) == 3)
-				dev->irq = 11;
-			else
-				dev->irq = 10;
-			pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
-			break;
-		default:
-			break;
-		}
-	}
-}
-
-static void skip_fake_bridge(struct pci_dev *dev)
-{
-	/* Make it an error to skip the fake bridge
-	 * in pci_setup_device() in probe.c */
-	dev->hdr_type = 0x7f;
-}
-DECLARE_PCI_FIXUP_EARLY(0x1957, 0x3fff, skip_fake_bridge);
-DECLARE_PCI_FIXUP_EARLY(0x3fff, 0x1957, skip_fake_bridge);
-DECLARE_PCI_FIXUP_EARLY(0xff3f, 0x5719, skip_fake_bridge);
-
-#define PCI_DEVICE_ID_IDT_TSI310	0x01a7
-
-/*
- * Fix Tsi310 PCI-X bridge resource.
- * Force the bridge to open a window from 0x0000-0x1fff in PCI I/O space.
- * This allows legacy I/O(i8259, etc) on the VIA southbridge to be accessed.
- */
-void mpc85xx_cds_fixup_bus(struct pci_bus *bus)
-{
-	struct pci_dev *dev = bus->self;
-	struct resource *res = bus->resource[0];
-
-	if (dev != NULL &&
-	    dev->vendor == PCI_VENDOR_ID_IBM &&
-	    dev->device == PCI_DEVICE_ID_IDT_TSI310) {
-		if (res) {
-			res->start = 0;
-			res->end   = 0x1fff;
-			res->flags = IORESOURCE_IO;
-			pr_info("mpc85xx_cds: PCI bridge resource fixup applied\n");
-			pr_info("mpc85xx_cds: %pR\n", res);
-		}
-	}
-
-	fsl_pcibios_fixup_bus(bus);
-}
-
-#ifdef CONFIG_PPC_I8259
-static void mpc85xx_8259_cascade_handler(struct irq_desc *desc)
-{
-	unsigned int cascade_irq = i8259_irq();
-
-	if (cascade_irq)
-		/* handle an interrupt from the 8259 */
-		generic_handle_irq(cascade_irq);
-
-	/* check for any interrupts from the shared IRQ line */
-	handle_fasteoi_irq(desc);
-}
-
-static irqreturn_t mpc85xx_8259_cascade_action(int irq, void *dev_id)
-{
-	return IRQ_HANDLED;
-}
-#endif /* PPC_I8259 */
-#endif /* CONFIG_PCI */
-
-static void __init mpc85xx_cds_pic_init(void)
-{
-	struct mpic *mpic;
-	mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
-			0, 256, " OpenPIC  ");
-	BUG_ON(mpic == NULL);
-	mpic_init(mpic);
-}
-
-#if defined(CONFIG_PPC_I8259) && defined(CONFIG_PCI)
-static int mpc85xx_cds_8259_attach(void)
-{
-	int ret;
-	struct device_node *np = NULL;
-	struct device_node *cascade_node = NULL;
-	int cascade_irq;
-
-	/* Initialize the i8259 controller */
-	for_each_node_by_type(np, "interrupt-controller")
-		if (of_device_is_compatible(np, "chrp,iic")) {
-			cascade_node = np;
-			break;
-		}
-
-	if (cascade_node == NULL) {
-		printk(KERN_DEBUG "Could not find i8259 PIC\n");
-		return -ENODEV;
-	}
-
-	cascade_irq = irq_of_parse_and_map(cascade_node, 0);
-	if (!cascade_irq) {
-		printk(KERN_ERR "Failed to map cascade interrupt\n");
-		return -ENXIO;
-	}
-
-	i8259_init(cascade_node, 0);
-	of_node_put(cascade_node);
-
-	/*
-	 *  Hook the interrupt to make sure desc->action is never NULL.
-	 *  This is required to ensure that the interrupt does not get
-	 *  disabled when the last user of the shared IRQ line frees their
-	 *  interrupt.
-	 */
-	ret = request_irq(cascade_irq, mpc85xx_8259_cascade_action,
-			  IRQF_SHARED | IRQF_NO_THREAD, "8259 cascade",
-			  cascade_node);
-	if (ret) {
-		printk(KERN_ERR "Failed to setup cascade interrupt\n");
-		return ret;
-	}
-
-	/* Success. Connect our low-level cascade handler. */
-	irq_set_handler(cascade_irq, mpc85xx_8259_cascade_handler);
-
-	return 0;
-}
-machine_device_initcall(mpc85xx_cds, mpc85xx_cds_8259_attach);
-
-#endif /* CONFIG_PPC_I8259 */
-
-static void __init mpc85xx_cds_pci_assign_primary(void)
-{
-#ifdef CONFIG_PCI
-	struct device_node *np;
-
-	if (fsl_pci_primary)
-		return;
-
-	/*
-	 * MPC85xx_CDS has ISA bridge but unfortunately there is no
-	 * isa node in device tree. We now looking for i8259 node as
-	 * a workaround for such a broken device tree. This routine
-	 * is for complying to all device trees.
-	 */
-	np = of_find_node_by_name(NULL, "i8259");
-	while ((fsl_pci_primary = of_get_parent(np))) {
-		of_node_put(np);
-		np = fsl_pci_primary;
-
-		if ((of_device_is_compatible(np, "fsl,mpc8540-pci") ||
-		    of_device_is_compatible(np, "fsl,mpc8548-pcie")) &&
-		    of_device_is_available(np))
-			return;
-	}
-#endif
-}
-
-/*
- * Setup the architecture
- */
-static void __init mpc85xx_cds_setup_arch(void)
-{
-	struct device_node *np;
-	int cds_pci_slot;
-
-	if (ppc_md.progress)
-		ppc_md.progress("mpc85xx_cds_setup_arch()", 0);
-
-	np = of_find_compatible_node(NULL, NULL, "fsl,mpc8548cds-fpga");
-	if (!np) {
-		pr_err("Could not find FPGA node.\n");
-		return;
-	}
-
-	cadmus = of_iomap(np, 0);
-	of_node_put(np);
-	if (!cadmus) {
-		pr_err("Fail to map FPGA area.\n");
-		return;
-	}
-
-	if (ppc_md.progress) {
-		char buf[40];
-		cds_pci_slot = ((in_8(&cadmus->cm_csr) >> 6) & 0x3) + 1;
-		snprintf(buf, 40, "CDS Version = 0x%x in slot %d\n",
-				in_8(&cadmus->cm_ver), cds_pci_slot);
-		ppc_md.progress(buf, 0);
-	}
-
-#ifdef CONFIG_PCI
-	ppc_md.pci_irq_fixup = mpc85xx_cds_pci_irq_fixup;
-	ppc_md.pci_exclude_device = mpc85xx_exclude_device;
-#endif
-
-	mpc85xx_cds_pci_assign_primary();
-	fsl_pci_assign_primary();
-}
-
-static void mpc85xx_cds_show_cpuinfo(struct seq_file *m)
-{
-	uint pvid, svid, phid1;
-
-	pvid = mfspr(SPRN_PVR);
-	svid = mfspr(SPRN_SVR);
-
-	seq_printf(m, "Vendor\t\t: Freescale Semiconductor\n");
-	seq_printf(m, "Machine\t\t: MPC85xx CDS (0x%x)\n",
-			in_8(&cadmus->cm_ver));
-	seq_printf(m, "PVR\t\t: 0x%x\n", pvid);
-	seq_printf(m, "SVR\t\t: 0x%x\n", svid);
-
-	/* Display cpu Pll setting */
-	phid1 = mfspr(SPRN_HID1);
-	seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
-}
-
-machine_arch_initcall(mpc85xx_cds, mpc85xx_common_publish_devices);
-
-define_machine(mpc85xx_cds) {
-	.name		= "MPC85xx CDS",
-	.compatible	= "MPC85xxCDS",
-	.setup_arch	= mpc85xx_cds_setup_arch,
-	.init_IRQ	= mpc85xx_cds_pic_init,
-	.show_cpuinfo	= mpc85xx_cds_show_cpuinfo,
-	.get_irq	= mpic_get_irq,
-#ifdef CONFIG_PCI
-	.pcibios_fixup_bus	= mpc85xx_cds_fixup_bus,
-	.pcibios_fixup_phb      = fsl_pcibios_fixup_phb,
-#endif
-	.progress	= udbg_progress,
-};
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index 4347d629b567..2856148321b3 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -15,8 +15,8 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 0546f19416c2..c19490cf6376 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -26,8 +26,8 @@
 #include <linux/seq_file.h>
 #include <linux/initrd.h>
 #include <linux/fsl_devices.h>
-#include <linux/of_platform.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/phy.h>
 #include <linux/memblock.h>
 #include <linux/fsl/guts.h>
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index c42a68da6dfd..e0cec670d8db 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -12,7 +12,8 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/fsl/guts.h>
 
 #include <asm/time.h>
@@ -75,7 +76,7 @@ static void __init mpc85xx_rdb_setup_arch(void)
 			/* P1025 has pins muxed for QE and other functions. To
 			* enable QE UEC mode, we need to set bit QE0 for UCC1
 			* in Eth mode, QE0 and QE3 for UCC5 in Eth mode, QE9
-			* and QE12 for QE MII management singals in PMUXCR
+			* and QE12 for QE MII management signals in PMUXCR
 			* register.
 			*/
 				setbits32(&guts->pmuxcr, MPC85xx_PMUXCR_QE(0) |
diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c
index 1b59e45a0c64..19122daadb55 100644
--- a/arch/powerpc/platforms/85xx/mvme2500.c
+++ b/arch/powerpc/platforms/85xx/mvme2500.c
@@ -21,7 +21,7 @@
 
 #include "mpc85xx.h"
 
-void __init mvme2500_pic_init(void)
+static void __init mvme2500_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0,
 		  MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 14ec79a32746..491895ac8bcf 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -10,7 +10,7 @@
 #include <linux/pci.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -24,7 +24,7 @@
 
 #include "mpc85xx.h"
 
-void __init p1010_rdb_pic_init(void)
+static void __init p1010_rdb_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 	  MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 23d0926298b9..adc3a2ee1415 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -18,8 +18,8 @@
 
 #include <linux/fsl/guts.h>
 #include <linux/pci.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 #include <asm/div64.h>
 #include <asm/mpic.h>
 #include <asm/swiotlb.h>
@@ -370,7 +370,7 @@ exit:
  *
  * @pixclock: the wavelength, in picoseconds, of the clock
  */
-void p1022ds_set_pixel_clock(unsigned int pixclock)
+static void p1022ds_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
 	struct ccsr_guts __iomem *guts;
@@ -418,7 +418,7 @@ void p1022ds_set_pixel_clock(unsigned int pixclock)
 /**
  * p1022ds_valid_monitor_port: set the monitor port for sysfs
  */
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
 p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
 	switch (port) {
@@ -432,7 +432,7 @@ p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 #endif
 
-void __init p1022_ds_pic_init(void)
+static void __init p1022_ds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 		MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
index d1159150c3b5..6198299d95b1 100644
--- a/arch/powerpc/platforms/85xx/p1022_rdk.c
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -14,8 +14,8 @@
 
 #include <linux/fsl/guts.h>
 #include <linux/pci.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 #include <asm/div64.h>
 #include <asm/mpic.h>
 #include <asm/swiotlb.h>
@@ -40,7 +40,7 @@
  *
  * @pixclock: the wavelength, in picoseconds, of the clock
  */
-void p1022rdk_set_pixel_clock(unsigned int pixclock)
+static void p1022rdk_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
 	struct ccsr_guts __iomem *guts;
@@ -88,7 +88,7 @@ void p1022rdk_set_pixel_clock(unsigned int pixclock)
 /**
  * p1022rdk_valid_monitor_port: set the monitor port for sysfs
  */
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
 p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
 	return FSL_DIU_PORT_DVI;
@@ -96,7 +96,7 @@ p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 #endif
 
-void __init p1022_rdk_pic_init(void)
+static void __init p1022_rdk_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 		MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1023_rdb.c b/arch/powerpc/platforms/85xx/p1023_rdb.c
index 9df0439a9382..e4fa8731fd2d 100644
--- a/arch/powerpc/platforms/85xx/p1023_rdb.c
+++ b/arch/powerpc/platforms/85xx/p1023_rdb.c
@@ -15,9 +15,8 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/fsl_devices.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
-#include <linux/of_device.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c
index 6e4b1ddf292b..3cd2f3bd4223 100644
--- a/arch/powerpc/platforms/85xx/qemu_e500.c
+++ b/arch/powerpc/platforms/85xx/qemu_e500.c
@@ -25,7 +25,7 @@
 #include "smp.h"
 #include "mpc85xx.h"
 
-void __init qemu_e500_pic_init(void)
+static void __init qemu_e500_pic_init(void)
 {
 	struct mpic *mpic;
 	unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU |
diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c
index 751395cbf022..e635b27ee718 100644
--- a/arch/powerpc/platforms/85xx/sgy_cts1000.c
+++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c
@@ -114,7 +114,7 @@ static int gpio_halt_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int gpio_halt_remove(struct platform_device *pdev)
+static void gpio_halt_remove(struct platform_device *pdev)
 {
 	free_irq(halt_irq, pdev);
 	cancel_work_sync(&gpio_halt_wq);
@@ -124,8 +124,6 @@ static int gpio_halt_remove(struct platform_device *pdev)
 
 	gpiod_put(halt_gpio);
 	halt_gpio = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id gpio_halt_match[] = {
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 9c43cf32f4c9..32fa5fb557c0 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -23,7 +23,7 @@
 #include <asm/mpic.h>
 #include <asm/cacheflush.h>
 #include <asm/dbell.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/cputhreads.h>
 #include <asm/fsl_pm.h>
 
@@ -180,7 +180,7 @@ static void wake_hw_thread(void *info)
 	unsigned long inia;
 	int cpu = *(const int *)info;
 
-	inia = *(unsigned long *)fsl_secondary_thread_init;
+	inia = ppc_function_entry(fsl_secondary_thread_init);
 	book3e_start_thread(cpu_thread_in_core(cpu), inia);
 }
 #endif
@@ -398,6 +398,7 @@ static void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary)
 	hard_irq_disable();
 	mpic_teardown_this_cpu(secondary);
 
+#ifdef CONFIG_CRASH_DUMP
 	if (cpu == crashing_cpu && cpu_thread_in_core(cpu) != 0) {
 		/*
 		 * We enter the crash kernel on whatever cpu crashed,
@@ -406,9 +407,11 @@ static void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary)
 		 */
 		disable_threadbit = 1;
 		disable_cpu = cpu_first_thread_sibling(cpu);
-	} else if (sibling != crashing_cpu &&
-		   cpu_thread_in_core(cpu) == 0 &&
-		   cpu_thread_in_core(sibling) != 0) {
+	} else if (sibling == crashing_cpu) {
+		return;
+	}
+#endif
+	if (cpu_thread_in_core(cpu) == 0 && cpu_thread_in_core(sibling) != 0) {
 		disable_threadbit = 2;
 		disable_cpu = sibling;
 	}
diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c
index 9fa1338bc002..403367b318db 100644
--- a/arch/powerpc/platforms/85xx/socrates.c
+++ b/arch/powerpc/platforms/85xx/socrates.c
@@ -23,7 +23,7 @@
 #include <linux/kdev_t.h>
 #include <linux/delay.h>
 #include <linux/seq_file.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 3768c86b9629..4b69fb321a68 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -6,9 +6,10 @@
 #include <linux/irq.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
 #include <linux/io.h>
 
+#include "socrates_fpga_pic.h"
+
 /*
  * The FPGA supports 9 interrupt sources, which can be routed to 3
  * interrupt request lines of the MPIC. The line to be used can be
@@ -82,7 +83,7 @@ static inline unsigned int socrates_fpga_pic_get_irq(unsigned int irq)
 		if (cause >> (i + 16))
 			break;
 	}
-	return irq_linear_revmap(socrates_fpga_pic_irq_host,
+	return irq_find_mapping(socrates_fpga_pic_irq_host,
 			(irq_hw_number_t)i);
 }
 
@@ -277,7 +278,7 @@ void __init socrates_fpga_pic_init(struct device_node *pic)
 	int i;
 
 	/* Setup an irq_domain structure */
-	socrates_fpga_pic_irq_host = irq_domain_add_linear(pic,
+	socrates_fpga_pic_irq_host = irq_domain_create_linear(of_fwnode_handle(pic),
 		    SOCRATES_FPGA_NUM_IRQS, &socrates_fpga_pic_host_ops, NULL);
 	if (socrates_fpga_pic_irq_host == NULL) {
 		pr_err("FPGA PIC: Unable to allocate host\n");
diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c
index 5e2646b4c039..c10efc45894c 100644
--- a/arch/powerpc/platforms/85xx/stx_gp3.c
+++ b/arch/powerpc/platforms/85xx/stx_gp3.c
@@ -22,7 +22,7 @@
 #include <linux/kdev_t.h>
 #include <linux/delay.h>
 #include <linux/seq_file.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/85xx/t1042rdb_diu.c b/arch/powerpc/platforms/85xx/t1042rdb_diu.c
index 767eed98a0a8..d4fbb6eff38a 100644
--- a/arch/powerpc/platforms/85xx/t1042rdb_diu.c
+++ b/arch/powerpc/platforms/85xx/t1042rdb_diu.c
@@ -149,4 +149,5 @@ static int __init t1042rdb_diu_init(void)
 
 early_initcall(t1042rdb_diu_init);
 
+MODULE_DESCRIPTION("Freescale T1042 DIU driver");
 MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c
index 80effb028bf4..f74d446c53f0 100644
--- a/arch/powerpc/platforms/85xx/tqm85xx.c
+++ b/arch/powerpc/platforms/85xx/tqm85xx.c
@@ -20,7 +20,7 @@
 #include <linux/kdev_t.h>
 #include <linux/delay.h>
 #include <linux/seq_file.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -112,17 +112,9 @@ static const char * const board[] __initconst = {
 	NULL
 };
 
-/*
- * Called very early, device-tree isn't unflattened
- */
-static int __init tqm85xx_probe(void)
-{
-	return of_device_compatible_match(of_root, board);
-}
-
 define_machine(tqm85xx) {
 	.name			= "TQM85xx",
-	.probe			= tqm85xx_probe,
+	.compatibles		= board,
 	.setup_arch		= tqm85xx_setup_arch,
 	.init_IRQ		= tqm85xx_pic_init,
 	.show_cpuinfo		= tqm85xx_show_cpuinfo,
diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c
index b88e23a334a4..c0a0456f1674 100644
--- a/arch/powerpc/platforms/85xx/twr_p102x.c
+++ b/arch/powerpc/platforms/85xx/twr_p102x.c
@@ -13,7 +13,8 @@
 #include <linux/errno.h>
 #include <linux/fsl/guts.h>
 #include <linux/pci.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 
 #include <asm/pci-bridge.h>
 #include <asm/udbg.h>
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 184013e6601e..2582427d8d01 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -16,8 +16,8 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
@@ -37,7 +37,7 @@
 #define MPC85xx_L2CTL_L2I		0x40000000 /* L2 flash invalidate */
 #define MPC85xx_L2CTL_L2SIZ_MASK	0x30000000 /* L2 SRAM size (R/O) */
 
-void __init xes_mpc85xx_pic_init(void)
+static void __init xes_mpc85xx_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
 			0, 256, " OpenPIC  ");
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 8bfafc9d2bf7..06b1e5c49d6f 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-config PPC_86xx
 menuconfig PPC_86xx
 	bool "86xx-based boards"
 	depends on PPC_BOOK3S_32
@@ -53,10 +52,3 @@ config MPC8641
 	select MPIC
 	default y if GEF_SBC610 || GEF_SBC310 || GEF_PPC9A \
 			|| MVME7100
-
-config MPC8610
-	bool
-	select HAVE_PCI
-	select FSL_PCI if PCI
-	select PPC_UDBG_16550
-	select MPIC
diff --git a/arch/powerpc/platforms/86xx/common.c b/arch/powerpc/platforms/86xx/common.c
index 0069d38263e7..a4a550527609 100644
--- a/arch/powerpc/platforms/86xx/common.c
+++ b/arch/powerpc/platforms/86xx/common.c
@@ -3,7 +3,10 @@
  * Routines common to most mpc86xx-based boards.
  */
 
+#include <linux/init.h>
+#include <linux/mod_devicetable.h>
 #include <linux/of_platform.h>
+#include <asm/reg.h>
 #include <asm/synch.h>
 
 #include "mpc86xx.h"
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index f0512e51300c..f7f98cca7b91 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -18,8 +18,8 @@
 #include <linux/kdev_t.h>
 #include <linux/delay.h>
 #include <linux/seq_file.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 1430b524d982..689835f7f088 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -18,8 +18,8 @@
 #include <linux/kdev_t.h>
 #include <linux/delay.h>
 #include <linux/seq_file.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index c92af0d964e1..365f511186ca 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -18,8 +18,8 @@
 #include <linux/kdev_t.h>
 #include <linux/delay.h>
 #include <linux/seq_file.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
index 8a7e55acf090..9be33e41af6d 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_smp.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
@@ -12,7 +12,7 @@
 #include <linux/delay.h>
 #include <linux/pgtable.h>
 
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/page.h>
 #include <asm/pci-bridge.h>
 #include <asm/mpic.h>
diff --git a/arch/powerpc/platforms/86xx/mvme7100.c b/arch/powerpc/platforms/86xx/mvme7100.c
index c0ac40514361..cee49ecd32d2 100644
--- a/arch/powerpc/platforms/86xx/mvme7100.c
+++ b/arch/powerpc/platforms/86xx/mvme7100.c
@@ -20,7 +20,6 @@
 #include <linux/pci.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 #include <linux/of_address.h>
 #include <asm/udbg.h>
 #include <asm/mpic.h>
diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c
index 2c32c3488afb..9ca36de23532 100644
--- a/arch/powerpc/platforms/86xx/pic.c
+++ b/arch/powerpc/platforms/86xx/pic.c
@@ -6,12 +6,14 @@
 #include <linux/stddef.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
 
 #include <asm/mpic.h>
 #include <asm/i8259.h>
 
+#include "mpc86xx.h"
+
 #ifdef CONFIG_PPC_I8259
 static void mpc86xx_8259_cascade(struct irq_desc *desc)
 {
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index a14d9d8997a4..abb2b45b2789 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -101,7 +101,6 @@ comment "Generic MPC8xx Options"
 config 8xx_GPIO
 	bool "GPIO API Support"
 	select GPIOLIB
-	select OF_GPIO_MM_GPIOCHIP
 	help
 	  Saying Y here will cause the ports on an MPC8xx processor to be used
 	  with the GPIO API.  If you say N here, the kernel needs less memory.
@@ -195,6 +194,13 @@ config PIN_TLB_IMMR
 	  CONFIG_PIN_TLB_DATA is also selected, it will reduce
 	  CONFIG_PIN_TLB_DATA to 24 Mbytes.
 
+config PIN_TLB_TEXT
+	bool "Pinned TLB for TEXT"
+	depends on PIN_TLB
+	default y
+	help
+	  This pins kernel text with 8M pages.
+
 endmenu
 
 endmenu
diff --git a/arch/powerpc/platforms/8xx/adder875.c b/arch/powerpc/platforms/8xx/adder875.c
index 7e83eb6746f4..d02f8dd66427 100644
--- a/arch/powerpc/platforms/8xx/adder875.c
+++ b/arch/powerpc/platforms/8xx/adder875.c
@@ -7,13 +7,12 @@
  */
 
 #include <linux/init.h>
-#include <linux/fs_enet_pd.h>
 #include <linux/of_platform.h>
 
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/cpm1.h>
-#include <asm/fs_pd.h>
+#include <asm/8xx_immap.h>
 #include <asm/udbg.h>
 
 #include "mpc8xx.h"
diff --git a/arch/powerpc/platforms/8xx/cpm1-ic.c b/arch/powerpc/platforms/8xx/cpm1-ic.c
index a18fc7c99f83..3292071e4da3 100644
--- a/arch/powerpc/platforms/8xx/cpm1-ic.c
+++ b/arch/powerpc/platforms/8xx/cpm1-ic.c
@@ -59,7 +59,7 @@ static int cpm_get_irq(struct irq_desc *desc)
 	cpm_vec = in_be16(&data->reg->cpic_civr);
 	cpm_vec >>= 11;
 
-	return irq_linear_revmap(data->host, cpm_vec);
+	return irq_find_mapping(data->host, cpm_vec);
 }
 
 static void cpm_cascade(struct irq_desc *desc)
@@ -110,7 +110,7 @@ static int cpm_pic_probe(struct platform_device *pdev)
 
 	out_be32(&data->reg->cpic_cimr, 0);
 
-	data->host = irq_domain_add_linear(dev->of_node, 64, &cpm_pic_host_ops, data);
+	data->host = irq_domain_create_linear(dev_fwnode(dev), 64, &cpm_pic_host_ops, data);
 	if (!data->host)
 		return -ENODEV;
 
diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c
index 34ab29966c8b..7433be7d66ee 100644
--- a/arch/powerpc/platforms/8xx/cpm1.c
+++ b/arch/powerpc/platforms/8xx/cpm1.c
@@ -40,11 +40,12 @@
 #include <asm/io.h>
 #include <asm/rheap.h>
 #include <asm/cpm.h>
+#include <asm/fixmap.h>
 
-#include <asm/fs_pd.h>
+#include <sysdev/fsl_soc.h>
 
 #ifdef CONFIG_8xx_GPIO
-#include <linux/gpio/legacy-of-mm-gpiochip.h>
+#include <linux/gpio/driver.h>
 #endif
 
 #define CPM_MAP_SIZE    (0x4000)
@@ -54,8 +55,6 @@ immap_t __iomem *mpc8xx_immr = (void __iomem *)VIRT_IMMR_BASE;
 
 void __init cpm_reset(void)
 {
-	sysconf8xx_t __iomem *siu_conf;
-
 	cpmp = &mpc8xx_immr->im_cpm;
 
 #ifndef CONFIG_PPC_EARLY_DEBUG_CPM
@@ -77,12 +76,10 @@ void __init cpm_reset(void)
 	 * manual recommends it.
 	 * Bit 25, FAM can also be set to use FEC aggressive mode (860T).
 	 */
-	siu_conf = immr_map(im_siu_conf);
 	if ((mfspr(SPRN_IMMR) & 0xffff) == 0x0900) /* MPC885 */
-		out_be32(&siu_conf->sc_sdcr, 0x40);
+		out_be32(&mpc8xx_immr->im_siu_conf.sc_sdcr, 0x40);
 	else
-		out_be32(&siu_conf->sc_sdcr, 1);
-	immr_unmap(siu_conf);
+		out_be32(&mpc8xx_immr->im_siu_conf.sc_sdcr, 1);
 }
 
 static DEFINE_SPINLOCK(cmd_lock);
@@ -379,7 +376,8 @@ int __init cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode)
 #ifdef CONFIG_8xx_GPIO
 
 struct cpm1_gpio16_chip {
-	struct of_mm_gpio_chip mm_gc;
+	struct gpio_chip gc;
+	void __iomem *regs;
 	spinlock_t lock;
 
 	/* shadowed data register to clear/set bits safely */
@@ -389,19 +387,17 @@ struct cpm1_gpio16_chip {
 	int irq[16];
 };
 
-static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc)
+static void cpm1_gpio16_save_regs(struct cpm1_gpio16_chip *cpm1_gc)
 {
-	struct cpm1_gpio16_chip *cpm1_gc =
-		container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc);
-	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+	struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
 
 	cpm1_gc->cpdata = in_be16(&iop->dat);
 }
 
 static int cpm1_gpio16_get(struct gpio_chip *gc, unsigned int gpio)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
+	struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
 	u16 pin_mask;
 
 	pin_mask = 1 << (15 - gpio);
@@ -409,11 +405,9 @@ static int cpm1_gpio16_get(struct gpio_chip *gc, unsigned int gpio)
 	return !!(in_be16(&iop->dat) & pin_mask);
 }
 
-static void __cpm1_gpio16_set(struct of_mm_gpio_chip *mm_gc, u16 pin_mask,
-	int value)
+static void __cpm1_gpio16_set(struct cpm1_gpio16_chip *cpm1_gc, u16 pin_mask, int value)
 {
-	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
-	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+	struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
 
 	if (value)
 		cpm1_gc->cpdata |= pin_mask;
@@ -423,40 +417,39 @@ static void __cpm1_gpio16_set(struct of_mm_gpio_chip *mm_gc, u16 pin_mask,
 	out_be16(&iop->dat, cpm1_gc->cpdata);
 }
 
-static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
+static int cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
 	unsigned long flags;
 	u16 pin_mask = 1 << (15 - gpio);
 
 	spin_lock_irqsave(&cpm1_gc->lock, flags);
 
-	__cpm1_gpio16_set(mm_gc, pin_mask, value);
+	__cpm1_gpio16_set(cpm1_gc, pin_mask, value);
 
 	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
+
+	return 0;
 }
 
 static int cpm1_gpio16_to_irq(struct gpio_chip *gc, unsigned int gpio)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
 
 	return cpm1_gc->irq[gpio] ? : -ENXIO;
 }
 
 static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
-	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
+	struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
 	unsigned long flags;
 	u16 pin_mask = 1 << (15 - gpio);
 
 	spin_lock_irqsave(&cpm1_gc->lock, flags);
 
 	setbits16(&iop->dir, pin_mask);
-	__cpm1_gpio16_set(mm_gc, pin_mask, val);
+	__cpm1_gpio16_set(cpm1_gc, pin_mask, val);
 
 	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
 
@@ -465,9 +458,8 @@ static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 static int cpm1_gpio16_dir_in(struct gpio_chip *gc, unsigned int gpio)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
-	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
+	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
+	struct cpm_ioport16 __iomem *iop = cpm1_gc->regs;
 	unsigned long flags;
 	u16 pin_mask = 1 << (15 - gpio);
 
@@ -484,11 +476,10 @@ int cpm1_gpiochip_add16(struct device *dev)
 {
 	struct device_node *np = dev->of_node;
 	struct cpm1_gpio16_chip *cpm1_gc;
-	struct of_mm_gpio_chip *mm_gc;
 	struct gpio_chip *gc;
 	u16 mask;
 
-	cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL);
+	cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL);
 	if (!cpm1_gc)
 		return -ENOMEM;
 
@@ -502,10 +493,8 @@ int cpm1_gpiochip_add16(struct device *dev)
 				cpm1_gc->irq[i] = irq_of_parse_and_map(np, j++);
 	}
 
-	mm_gc = &cpm1_gc->mm_gc;
-	gc = &mm_gc->gc;
-
-	mm_gc->save_regs = cpm1_gpio16_save_regs;
+	gc = &cpm1_gc->gc;
+	gc->base = -1;
 	gc->ngpio = 16;
 	gc->direction_input = cpm1_gpio16_dir_in;
 	gc->direction_output = cpm1_gpio16_dir_out;
@@ -515,30 +504,39 @@ int cpm1_gpiochip_add16(struct device *dev)
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
 
-	return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc);
+	gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np);
+	if (!gc->label)
+		return -ENOMEM;
+
+	cpm1_gc->regs = devm_of_iomap(dev, np, 0, NULL);
+	if (IS_ERR(cpm1_gc->regs))
+		return PTR_ERR(cpm1_gc->regs);
+
+	cpm1_gpio16_save_regs(cpm1_gc);
+
+	return devm_gpiochip_add_data(dev, gc, cpm1_gc);
 }
 
 struct cpm1_gpio32_chip {
-	struct of_mm_gpio_chip mm_gc;
+	struct gpio_chip gc;
+	void __iomem *regs;
 	spinlock_t lock;
 
 	/* shadowed data register to clear/set bits safely */
 	u32 cpdata;
 };
 
-static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
+static void cpm1_gpio32_save_regs(struct cpm1_gpio32_chip *cpm1_gc)
 {
-	struct cpm1_gpio32_chip *cpm1_gc =
-		container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc);
-	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+	struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
 
 	cpm1_gc->cpdata = in_be32(&iop->dat);
 }
 
 static int cpm1_gpio32_get(struct gpio_chip *gc, unsigned int gpio)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
+	struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
 	u32 pin_mask;
 
 	pin_mask = 1 << (31 - gpio);
@@ -546,11 +544,9 @@ static int cpm1_gpio32_get(struct gpio_chip *gc, unsigned int gpio)
 	return !!(in_be32(&iop->dat) & pin_mask);
 }
 
-static void __cpm1_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask,
-	int value)
+static void __cpm1_gpio32_set(struct cpm1_gpio32_chip *cpm1_gc, u32 pin_mask, int value)
 {
-	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
-	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+	struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
 
 	if (value)
 		cpm1_gc->cpdata |= pin_mask;
@@ -560,32 +556,32 @@ static void __cpm1_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask,
 	out_be32(&iop->dat, cpm1_gc->cpdata);
 }
 
-static void cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
+static int cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
 	unsigned long flags;
 	u32 pin_mask = 1 << (31 - gpio);
 
 	spin_lock_irqsave(&cpm1_gc->lock, flags);
 
-	__cpm1_gpio32_set(mm_gc, pin_mask, value);
+	__cpm1_gpio32_set(cpm1_gc, pin_mask, value);
 
 	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
+
+	return 0;
 }
 
 static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
-	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
+	struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
 	unsigned long flags;
 	u32 pin_mask = 1 << (31 - gpio);
 
 	spin_lock_irqsave(&cpm1_gc->lock, flags);
 
 	setbits32(&iop->dir, pin_mask);
-	__cpm1_gpio32_set(mm_gc, pin_mask, val);
+	__cpm1_gpio32_set(cpm1_gc, pin_mask, val);
 
 	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
 
@@ -594,9 +590,8 @@ static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 static int cpm1_gpio32_dir_in(struct gpio_chip *gc, unsigned int gpio)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
-	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
+	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
+	struct cpm_ioport32b __iomem *iop = cpm1_gc->regs;
 	unsigned long flags;
 	u32 pin_mask = 1 << (31 - gpio);
 
@@ -613,19 +608,16 @@ int cpm1_gpiochip_add32(struct device *dev)
 {
 	struct device_node *np = dev->of_node;
 	struct cpm1_gpio32_chip *cpm1_gc;
-	struct of_mm_gpio_chip *mm_gc;
 	struct gpio_chip *gc;
 
-	cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL);
+	cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL);
 	if (!cpm1_gc)
 		return -ENOMEM;
 
 	spin_lock_init(&cpm1_gc->lock);
 
-	mm_gc = &cpm1_gc->mm_gc;
-	gc = &mm_gc->gc;
-
-	mm_gc->save_regs = cpm1_gpio32_save_regs;
+	gc = &cpm1_gc->gc;
+	gc->base = -1;
 	gc->ngpio = 32;
 	gc->direction_input = cpm1_gpio32_dir_in;
 	gc->direction_output = cpm1_gpio32_dir_out;
@@ -634,7 +626,17 @@ int cpm1_gpiochip_add32(struct device *dev)
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
 
-	return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc);
+	gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np);
+	if (!gc->label)
+		return -ENOMEM;
+
+	cpm1_gc->regs = devm_of_iomap(dev, np, 0, NULL);
+	if (IS_ERR(cpm1_gc->regs))
+		return PTR_ERR(cpm1_gc->regs);
+
+	cpm1_gpio32_save_regs(cpm1_gc);
+
+	return devm_gpiochip_add_data(dev, gc, cpm1_gc);
 }
 
 #endif /* CONFIG_8xx_GPIO */
diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c
index 24f358f86d16..2336b687bc96 100644
--- a/arch/powerpc/platforms/8xx/m8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/m8xx_setup.c
@@ -22,7 +22,6 @@
 
 #include <asm/io.h>
 #include <asm/8xx_immap.h>
-#include <asm/fs_pd.h>
 #include <mm/mmu_decl.h>
 
 #include "pic.h"
@@ -37,20 +36,6 @@ static irqreturn_t timebase_interrupt(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-/* per-board overridable init_internal_rtc() function. */
-void __init __attribute__ ((weak))
-init_internal_rtc(void)
-{
-	sit8xx_t __iomem *sys_tmr = immr_map(im_sit);
-
-	/* Disable the RTC one second and alarm interrupts. */
-	clrbits16(&sys_tmr->sit_rtcsc, (RTCSC_SIE | RTCSC_ALE));
-
-	/* Enable the RTC */
-	setbits16(&sys_tmr->sit_rtcsc, (RTCSC_RTF | RTCSC_RTE));
-	immr_unmap(sys_tmr);
-}
-
 static int __init get_freq(char *name, unsigned long *val)
 {
 	struct device_node *cpu;
@@ -80,23 +65,14 @@ static int __init get_freq(char *name, unsigned long *val)
 void __init mpc8xx_calibrate_decr(void)
 {
 	struct device_node *cpu;
-	cark8xx_t __iomem *clk_r1;
-	car8xx_t __iomem *clk_r2;
-	sitk8xx_t __iomem *sys_tmr1;
-	sit8xx_t __iomem *sys_tmr2;
 	int irq, virq;
 
-	clk_r1 = immr_map(im_clkrstk);
-
 	/* Unlock the SCCR. */
-	out_be32(&clk_r1->cark_sccrk, ~KAPWR_KEY);
-	out_be32(&clk_r1->cark_sccrk, KAPWR_KEY);
-	immr_unmap(clk_r1);
+	out_be32(&mpc8xx_immr->im_clkrstk.cark_sccrk, ~KAPWR_KEY);
+	out_be32(&mpc8xx_immr->im_clkrstk.cark_sccrk, KAPWR_KEY);
 
 	/* Force all 8xx processors to use divide by 16 processor clock. */
-	clk_r2 = immr_map(im_clkrst);
-	setbits32(&clk_r2->car_sccr, 0x02000000);
-	immr_unmap(clk_r2);
+	setbits32(&mpc8xx_immr->im_clkrst.car_sccr, 0x02000000);
 
 	/* Processor frequency is MHz.
 	 */
@@ -123,16 +99,18 @@ void __init mpc8xx_calibrate_decr(void)
 	 * we guarantee the registers are locked, then we unlock them
 	 * for our use.
 	 */
-	sys_tmr1 = immr_map(im_sitk);
-	out_be32(&sys_tmr1->sitk_tbscrk, ~KAPWR_KEY);
-	out_be32(&sys_tmr1->sitk_rtcsck, ~KAPWR_KEY);
-	out_be32(&sys_tmr1->sitk_tbk, ~KAPWR_KEY);
-	out_be32(&sys_tmr1->sitk_tbscrk, KAPWR_KEY);
-	out_be32(&sys_tmr1->sitk_rtcsck, KAPWR_KEY);
-	out_be32(&sys_tmr1->sitk_tbk, KAPWR_KEY);
-	immr_unmap(sys_tmr1);
+	out_be32(&mpc8xx_immr->im_sitk.sitk_tbscrk, ~KAPWR_KEY);
+	out_be32(&mpc8xx_immr->im_sitk.sitk_rtcsck, ~KAPWR_KEY);
+	out_be32(&mpc8xx_immr->im_sitk.sitk_tbk, ~KAPWR_KEY);
+	out_be32(&mpc8xx_immr->im_sitk.sitk_tbscrk, KAPWR_KEY);
+	out_be32(&mpc8xx_immr->im_sitk.sitk_rtcsck, KAPWR_KEY);
+	out_be32(&mpc8xx_immr->im_sitk.sitk_tbk, KAPWR_KEY);
+
+	/* Disable the RTC one second and alarm interrupts. */
+	clrbits16(&mpc8xx_immr->im_sit.sit_rtcsc, (RTCSC_SIE | RTCSC_ALE));
 
-	init_internal_rtc();
+	/* Enable the RTC */
+	setbits16(&mpc8xx_immr->im_sit.sit_rtcsc, (RTCSC_RTF | RTCSC_RTE));
 
 	/* Enabling the decrementer also enables the timebase interrupts
 	 * (or from the other point of view, to get decrementer interrupts
@@ -144,10 +122,8 @@ void __init mpc8xx_calibrate_decr(void)
 	of_node_put(cpu);
 	irq = virq_to_hw(virq);
 
-	sys_tmr2 = immr_map(im_sit);
-	out_be16(&sys_tmr2->sit_tbscr, ((1 << (7 - (irq/2))) << 8) |
-					(TBSCR_TBF | TBSCR_TBE));
-	immr_unmap(sys_tmr2);
+	out_be16(&mpc8xx_immr->im_sit.sit_tbscr,
+		 ((1 << (7 - (irq / 2))) << 8) | (TBSCR_TBF | TBSCR_TBE));
 
 	if (request_irq(virq, timebase_interrupt, IRQF_NO_THREAD, "tbint",
 			NULL))
@@ -161,47 +137,36 @@ void __init mpc8xx_calibrate_decr(void)
 
 int mpc8xx_set_rtc_time(struct rtc_time *tm)
 {
-	sitk8xx_t __iomem *sys_tmr1;
-	sit8xx_t __iomem *sys_tmr2;
 	time64_t time;
 
-	sys_tmr1 = immr_map(im_sitk);
-	sys_tmr2 = immr_map(im_sit);
 	time = rtc_tm_to_time64(tm);
 
-	out_be32(&sys_tmr1->sitk_rtck, KAPWR_KEY);
-	out_be32(&sys_tmr2->sit_rtc, (u32)time);
-	out_be32(&sys_tmr1->sitk_rtck, ~KAPWR_KEY);
+	out_be32(&mpc8xx_immr->im_sitk.sitk_rtck, KAPWR_KEY);
+	out_be32(&mpc8xx_immr->im_sit.sit_rtc, (u32)time);
+	out_be32(&mpc8xx_immr->im_sitk.sitk_rtck, ~KAPWR_KEY);
 
-	immr_unmap(sys_tmr2);
-	immr_unmap(sys_tmr1);
 	return 0;
 }
 
 void mpc8xx_get_rtc_time(struct rtc_time *tm)
 {
 	unsigned long data;
-	sit8xx_t __iomem *sys_tmr = immr_map(im_sit);
 
 	/* Get time from the RTC. */
-	data = in_be32(&sys_tmr->sit_rtc);
+	data = in_be32(&mpc8xx_immr->im_sit.sit_rtc);
 	rtc_time64_to_tm(data, tm);
-	immr_unmap(sys_tmr);
 	return;
 }
 
 void __noreturn mpc8xx_restart(char *cmd)
 {
-	car8xx_t __iomem *clk_r = immr_map(im_clkrst);
-
-
 	local_irq_disable();
 
-	setbits32(&clk_r->car_plprcr, 0x00000080);
+	setbits32(&mpc8xx_immr->im_clkrst.car_plprcr, 0x00000080);
 	/* Clear the ME bit in MSR to cause checkstop on machine check
 	*/
 	mtmsr(mfmsr() & ~0x1000);
 
-	in_8(&clk_r->res[0]);
+	in_8(&mpc8xx_immr->im_clkrst.res[0]);
 	panic("Restart failed\n");
 }
diff --git a/arch/powerpc/platforms/8xx/mpc86xads_setup.c b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
index 11b3d1116db1..e4192c0a3c0c 100644
--- a/arch/powerpc/platforms/8xx/mpc86xads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
@@ -24,7 +24,6 @@
 #include <asm/time.h>
 #include <asm/8xx_immap.h>
 #include <asm/cpm1.h>
-#include <asm/fs_pd.h>
 #include <asm/udbg.h>
 
 #include "mpc86xads.h"
diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
index 2fc7cacbcd96..2d899be746eb 100644
--- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
@@ -21,8 +21,6 @@
 #include <linux/device.h>
 #include <linux/delay.h>
 
-#include <linux/fs_enet_pd.h>
-#include <linux/fs_uart_pd.h>
 #include <linux/fsl_devices.h>
 #include <linux/mii.h>
 #include <linux/of_address.h>
@@ -37,7 +35,6 @@
 #include <asm/time.h>
 #include <asm/8xx_immap.h>
 #include <asm/cpm1.h>
-#include <asm/fs_pd.h>
 #include <asm/udbg.h>
 
 #include "mpc885ads.h"
diff --git a/arch/powerpc/platforms/8xx/pic.c b/arch/powerpc/platforms/8xx/pic.c
index ea6b0e523c60..933d6ab7f512 100644
--- a/arch/powerpc/platforms/8xx/pic.c
+++ b/arch/powerpc/platforms/8xx/pic.c
@@ -80,7 +80,7 @@ unsigned int mpc8xx_get_irq(void)
 	if (irq == PIC_VEC_SPURRIOUS)
 		return 0;
 
-        return irq_linear_revmap(mpc8xx_pic_host, irq);
+        return irq_find_mapping(mpc8xx_pic_host, irq);
 
 }
 
@@ -146,7 +146,8 @@ void __init mpc8xx_pic_init(void)
 	if (!siu_reg)
 		goto out;
 
-	mpc8xx_pic_host = irq_domain_add_linear(np, 64, &mpc8xx_pic_host_ops, NULL);
+	mpc8xx_pic_host = irq_domain_create_linear(of_fwnode_handle(np), 64,
+						   &mpc8xx_pic_host_ops, NULL);
 	if (!mpc8xx_pic_host)
 		printk(KERN_ERR "MPC8xx PIC: failed to allocate irq host!\n");
 
diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
index 7d8eb50bb9cd..d97a7910c594 100644
--- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
@@ -24,8 +24,6 @@
 #include <linux/device.h>
 #include <linux/delay.h>
 
-#include <linux/fs_enet_pd.h>
-#include <linux/fs_uart_pd.h>
 #include <linux/fsl_devices.h>
 #include <linux/mii.h>
 #include <linux/of_fdt.h>
@@ -39,7 +37,6 @@
 #include <asm/time.h>
 #include <asm/8xx_immap.h>
 #include <asm/cpm1.h>
-#include <asm/fs_pd.h>
 #include <asm/udbg.h>
 
 #include "mpc8xx.h"
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 0d9b7609c7d5..c4e61843d9d9 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -7,7 +7,6 @@ source "arch/powerpc/platforms/chrp/Kconfig"
 source "arch/powerpc/platforms/512x/Kconfig"
 source "arch/powerpc/platforms/52xx/Kconfig"
 source "arch/powerpc/platforms/powermac/Kconfig"
-source "arch/powerpc/platforms/maple/Kconfig"
 source "arch/powerpc/platforms/pasemi/Kconfig"
 source "arch/powerpc/platforms/ps3/Kconfig"
 source "arch/powerpc/platforms/cell/Kconfig"
@@ -18,7 +17,6 @@ source "arch/powerpc/platforms/85xx/Kconfig"
 source "arch/powerpc/platforms/86xx/Kconfig"
 source "arch/powerpc/platforms/embedded6xx/Kconfig"
 source "arch/powerpc/platforms/44x/Kconfig"
-source "arch/powerpc/platforms/40x/Kconfig"
 source "arch/powerpc/platforms/amigaone/Kconfig"
 source "arch/powerpc/platforms/book3s/Kconfig"
 source "arch/powerpc/platforms/microwatt/Kconfig"
@@ -72,10 +70,6 @@ config PPC_DT_CPU_FTRS
 	  firmware provides this binding.
 	  If you're not sure say Y.
 
-config UDBG_RTAS_CONSOLE
-	bool "RTAS based debug console"
-	depends on PPC_RTAS
-
 config PPC_SMP_MUXED_IPI
 	bool
 	help
@@ -188,12 +182,6 @@ config PPC_INDIRECT_PIO
 	bool
 	select GENERIC_IOMAP
 
-config PPC_INDIRECT_MMIO
-	bool
-
-config PPC_IO_WORKAROUNDS
-	bool
-
 source "drivers/cpufreq/Kconfig"
 
 menu "CPUIdle driver"
@@ -244,18 +232,16 @@ config QE_GPIO
 	bool "QE GPIO support"
 	depends on QUICC_ENGINE
 	select GPIOLIB
-	select OF_GPIO_MM_GPIOCHIP
 	help
 	  Say Y here if you're going to use hardware that connects to the
 	  QE GPIOs.
 
 config CPM2
 	bool "Enable support for the CPM2 (Communications Processor Module)"
-	depends on (FSL_SOC_BOOKE && PPC32) || 8260
+	depends on (FSL_SOC_BOOKE && PPC32) || PPC_82xx
 	select CPM
 	select HAVE_PCI
 	select GPIOLIB
-	select OF_GPIO_MM_GPIOCHIP
 	help
 	  The CPM2 (Communications Processor Module) is a coprocessor on
 	  embedded CPUs made by Freescale.  Selecting this option means that
@@ -265,6 +251,7 @@ config CPM2
 config FSL_ULI1575
 	bool "ULI1575 PCIe south bridge support"
 	depends on FSL_SOC_BOOKE || PPC_86xx
+	depends on PCI
 	select FSL_PCI
 	select GENERIC_ISA_DMA
 	help
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 45fd975ef521..4c321a8ea896 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -43,19 +43,10 @@ config PPC_8xx
 	select HAVE_ARCH_VMAP_STACK
 	select HUGETLBFS
 
-config 40x
-	bool "AMCC 40x"
-	select PPC_DCR_NATIVE
-	select PPC_UDBG_16550
-	select 4xx_SOC
-	select HAVE_PCI
-	select PPC_KUEP if PPC_KUAP
-
 config 44x
 	bool "AMCC 44x, 46x or 47x"
 	select PPC_DCR_NATIVE
 	select PPC_UDBG_16550
-	select 4xx_SOC
 	select HAVE_PCI
 	select PHYS_64BIT
 	select PPC_KUEP
@@ -93,10 +84,8 @@ config PPC_BOOK3S_64
 	bool "Server processors"
 	select PPC_FPU
 	select PPC_HAVE_PMU_SUPPORT
-	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK
-	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select HAVE_MOVE_PMD
@@ -116,6 +105,14 @@ config PPC_BOOK3E_64
 
 endchoice
 
+config PPC_THP
+       def_bool y
+       depends on PPC_BOOK3S_64
+       depends on PPC_RADIX_MMU || (PPC_64S_HASH_MMU && PAGE_SIZE_64KB)
+       select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+       select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+       select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
+
 choice
 	prompt "CPU selection"
 	help
@@ -125,16 +122,11 @@ choice
 	  If unsure, select Generic.
 
 config POWERPC64_CPU
-	bool "Generic (POWER5 and PowerPC 970 and above)"
-	depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN
-	select PPC_64S_HASH_MMU
-
-config POWERPC64_CPU
-	bool "Generic (POWER8 and above)"
-	depends on PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
-	select ARCH_HAS_FAST_MULTIPLIER
+	bool "Generic 64 bits powerpc"
+	depends on PPC_BOOK3S_64
+	select ARCH_HAS_FAST_MULTIPLIER if CPU_LITTLE_ENDIAN
 	select PPC_64S_HASH_MMU
-	select PPC_HAS_LBARX_LHARX
+	select PPC_HAS_LBARX_LHARX if CPU_LITTLE_ENDIAN
 
 config POWERPC_CPU
 	bool "Generic 32 bits powerpc"
@@ -193,11 +185,6 @@ config E6500_CPU
 	depends on !CC_IS_CLANG
 	select PPC_HAS_LBARX_LHARX
 
-config 405_CPU
-	bool "40x family"
-	depends on 40x
-	depends on !CC_IS_CLANG
-
 config 440_CPU
 	bool "440 (44x family)"
 	depends on 44x
@@ -263,7 +250,6 @@ config TARGET_CPU
 	default "e6500" if E6500_CPU
 	default "power4" if POWERPC64_CPU && !CPU_LITTLE_ENDIAN
 	default "power8" if POWERPC64_CPU && CPU_LITTLE_ENDIAN
-	default "405" if 405_CPU
 	default "440" if 440_CPU
 	default "464" if 464_CPU
 	default "476" if 476_CPU
@@ -275,6 +261,13 @@ config TARGET_CPU
 	default "e500mc" if E500MC_CPU
 	default "powerpc" if POWERPC_CPU
 
+config TUNE_CPU
+	string
+	depends on POWERPC64_CPU
+	default "-mtune=power10" if $(cc-option,-mtune=power10)
+	default "-mtune=power9"  if $(cc-option,-mtune=power9)
+	default "-mtune=power8"  if $(cc-option,-mtune=power8)
+
 config PPC_BOOK3S
 	def_bool y
 	depends on PPC_BOOK3S_32 || PPC_BOOK3S_64
@@ -332,7 +325,7 @@ config FSL_EMB_PERF_EVENT_E500
 
 config 4xx
 	bool
-	depends on 40x || 44x
+	depends on 44x
 	default y
 
 config BOOKE
@@ -340,11 +333,6 @@ config BOOKE
 	depends on PPC_E500 || 44x
 	default y
 
-config BOOKE_OR_40x
-	bool
-	depends on BOOKE || 40x
-	default y
-
 config PTE_64BIT
 	bool
 	depends on 44x || PPC_E500 || PPC_86xx
@@ -435,7 +423,6 @@ config PPC_64S_HASH_MMU
 config PPC_RADIX_MMU
 	bool "Radix MMU Support"
 	depends on PPC_BOOK3S_64
-	select ARCH_HAS_GIGANTIC_PAGE
 	default y
 	help
 	  Enable support for the Power ISA 3.0 Radix style MMU. Currently this
@@ -456,6 +443,19 @@ config PPC_RADIX_MMU_DEFAULT
 
 	  If you're unsure, say Y.
 
+config PPC_RADIX_BROADCAST_TLBIE
+	bool
+	depends on PPC_RADIX_MMU
+	help
+	  Power ISA v3.0 and later implementations in the Linux Compliancy Subset
+	  and lower are not required to implement broadcast TLBIE instructions.
+	  Platforms with CPUs that do implement TLBIE broadcast, that is, where
+	  a TLB invalidation instruction performed on one CPU operates on the
+	  TLBs of all CPUs in the system, should select this option.  If this
+	  option is selected, the disable_tlbie kernel command line option can
+	  be used to cause global TLB invalidations to be done via IPIs; without
+	  it, IPIs will be used unconditionally.
+
 config PPC_KERNEL_PREFIXED
 	depends on PPC_HAVE_PREFIXED_SUPPORT
 	depends on CC_HAS_PREFIXED
@@ -487,8 +487,8 @@ config PPC_KERNEL_PCREL
 	  This option builds the kernel with the pc relative ABI model.
 
 config PPC_KUEP
-	bool "Kernel Userspace Execution Prevention" if !40x
-	default y if !40x
+	bool "Kernel Userspace Execution Prevention"
+	default y
 	help
 	  Enable support for Kernel Userspace Execution Prevention (KUEP)
 
@@ -574,7 +574,7 @@ config NR_CPUS
 
 config NOT_COHERENT_CACHE
 	bool
-	depends on 4xx || PPC_8xx || PPC_MPC512x || \
+	depends on 44x || PPC_8xx || PPC_MPC512x || \
 		GAMECUBE_COMMON || AMIGAONE
 	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index 94470fb27c99..3cee4a842736 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -4,8 +4,6 @@ obj-$(CONFIG_FSL_ULI1575)	+= fsl_uli1575.o
 
 obj-$(CONFIG_PPC_PMAC)		+= powermac/
 obj-$(CONFIG_PPC_CHRP)		+= chrp/
-obj-$(CONFIG_4xx)		+= 4xx/
-obj-$(CONFIG_40x)		+= 40x/
 obj-$(CONFIG_44x)		+= 44x/
 obj-$(CONFIG_PPC_MPC512x)	+= 512x/
 obj-$(CONFIG_PPC_MPC52xx)	+= 52xx/
@@ -16,7 +14,6 @@ obj-$(CONFIG_FSL_SOC_BOOKE)	+= 85xx/
 obj-$(CONFIG_PPC_86xx)		+= 86xx/
 obj-$(CONFIG_PPC_POWERNV)	+= powernv/
 obj-$(CONFIG_PPC_PSERIES)	+= pseries/
-obj-$(CONFIG_PPC_MAPLE)		+= maple/
 obj-$(CONFIG_PPC_PASEMI)	+= pasemi/
 obj-$(CONFIG_PPC_CELL)		+= cell/
 obj-$(CONFIG_PPC_PS3)		+= ps3/
diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c
index 6c6e714a7521..33f852a7625f 100644
--- a/arch/powerpc/platforms/amigaone/setup.c
+++ b/arch/powerpc/platforms/amigaone/setup.c
@@ -25,7 +25,7 @@
 
 extern void __flush_disable_L1(void);
 
-void amigaone_show_cpuinfo(struct seq_file *m)
+static void amigaone_show_cpuinfo(struct seq_file *m)
 {
 	seq_printf(m, "vendor\t\t: Eyetech Ltd.\n");
 }
@@ -65,7 +65,7 @@ static int __init amigaone_add_bridge(struct device_node *dev)
 	return 0;
 }
 
-void __init amigaone_setup_arch(void)
+static void __init amigaone_setup_arch(void)
 {
 	if (ppc_md.progress)
 		ppc_md.progress("Linux/PPC "UTS_RELEASE"\n", 0);
@@ -83,7 +83,7 @@ static void __init amigaone_discover_phbs(void)
 	BUG_ON(phb != 0);
 }
 
-void __init amigaone_init_IRQ(void)
+static void __init amigaone_init_IRQ(void)
 {
 	struct device_node *pic, *np = NULL;
 	const unsigned long *prop = NULL;
@@ -109,7 +109,7 @@ void __init amigaone_init_IRQ(void)
 
 	i8259_init(pic, int_ack);
 	ppc_md.get_irq = i8259_irq;
-	irq_set_default_host(i8259_get_host());
+	irq_set_default_domain(i8259_get_host());
 }
 
 static int __init request_isa_regions(void)
@@ -123,7 +123,7 @@ static int __init request_isa_regions(void)
 }
 machine_device_initcall(amigaone, request_isa_regions);
 
-void __noreturn amigaone_restart(char *cmd)
+static void __noreturn amigaone_restart(char *cmd)
 {
 	local_irq_disable();
 
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index 77ea9335fd04..49b15e7a8265 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -4,6 +4,8 @@
  * Copyright (C) 2019 Haren Myneni, IBM Corp
  */
 
+#define pr_fmt(fmt)	"vas-api: " fmt
+
 #include <linux/kernel.h>
 #include <linux/device.h>
 #include <linux/cdev.h>
@@ -78,7 +80,7 @@ int get_vas_user_win_ref(struct vas_user_win_ref *task_ref)
 	task_ref->mm = get_task_mm(current);
 	if (!task_ref->mm) {
 		put_pid(task_ref->pid);
-		pr_err("VAS: pid(%d): mm_struct is not found\n",
+		pr_err("pid(%d): mm_struct is not found\n",
 				current->pid);
 		return -EPERM;
 	}
@@ -235,8 +237,7 @@ void vas_update_csb(struct coprocessor_request_block *crb,
 	rc = kill_pid_info(SIGSEGV, &info, pid);
 	rcu_read_unlock();
 
-	pr_devel("%s(): pid %d kill_proc_info() rc %d\n", __func__,
-			pid_vnr(pid), rc);
+	pr_devel("pid %d kill_proc_info() rc %d\n", pid_vnr(pid), rc);
 }
 
 void vas_dump_crb(struct coprocessor_request_block *crb)
@@ -294,7 +295,7 @@ static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg)
 
 	rc = copy_from_user(&uattr, uptr, sizeof(uattr));
 	if (rc) {
-		pr_err("%s(): copy_from_user() returns %d\n", __func__, rc);
+		pr_err("copy_from_user() returns %d\n", rc);
 		return -EFAULT;
 	}
 
@@ -311,7 +312,7 @@ static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg)
 	txwin = cp_inst->coproc->vops->open_win(uattr.vas_id, uattr.flags,
 						cp_inst->coproc->cop_type);
 	if (IS_ERR(txwin)) {
-		pr_err("%s() VAS window open failed, %ld\n", __func__,
+		pr_err_ratelimited("VAS window open failed rc=%ld\n",
 				PTR_ERR(txwin));
 		return PTR_ERR(txwin);
 	}
@@ -405,8 +406,7 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
 	 * window is not opened. Shouldn't expect this error.
 	 */
 	if (!cp_inst || !cp_inst->txwin) {
-		pr_err("%s(): Unexpected fault on paste address with TX window closed\n",
-				__func__);
+		pr_err("Unexpected fault on paste address with TX window closed\n");
 		return VM_FAULT_SIGBUS;
 	}
 
@@ -421,28 +421,26 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
 	 * issue NX request.
 	 */
 	if (txwin->task_ref.vma != vmf->vma) {
-		pr_err("%s(): No previous mapping with paste address\n",
-			__func__);
+		pr_err("No previous mapping with paste address\n");
 		return VM_FAULT_SIGBUS;
 	}
 
-	mutex_lock(&txwin->task_ref.mmap_mutex);
 	/*
 	 * The window may be inactive due to lost credit (Ex: core
 	 * removal with DLPAR). If the window is active again when
 	 * the credit is available, map the new paste address at the
 	 * window virtual address.
 	 */
-	if (txwin->status == VAS_WIN_ACTIVE) {
-		paste_addr = cp_inst->coproc->vops->paste_addr(txwin);
-		if (paste_addr) {
-			fault = vmf_insert_pfn(vma, vma->vm_start,
-					(paste_addr >> PAGE_SHIFT));
-			mutex_unlock(&txwin->task_ref.mmap_mutex);
-			return fault;
+	scoped_guard(mutex, &txwin->task_ref.mmap_mutex) {
+		if (txwin->status == VAS_WIN_ACTIVE) {
+			paste_addr = cp_inst->coproc->vops->paste_addr(txwin);
+			if (paste_addr) {
+				fault = vmf_insert_pfn(vma, vma->vm_start,
+						(paste_addr >> PAGE_SHIFT));
+				return fault;
+			}
 		}
 	}
-	mutex_unlock(&txwin->task_ref.mmap_mutex);
 
 	/*
 	 * Received this fault due to closing the actual window.
@@ -465,7 +463,42 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
+/*
+ * During mmap() paste address, mapping VMA is saved in VAS window
+ * struct which is used to unmap during migration if the window is
+ * still open. But the user space can remove this mapping with
+ * munmap() before closing the window and the VMA address will
+ * be invalid. Set VAS window VMA to NULL in this function which
+ * is called before VMA free.
+ */
+static void vas_mmap_close(struct vm_area_struct *vma)
+{
+	struct file *fp = vma->vm_file;
+	struct coproc_instance *cp_inst = fp->private_data;
+	struct vas_window *txwin;
+
+	/* Should not happen */
+	if (!cp_inst || !cp_inst->txwin) {
+		pr_err("No attached VAS window for the paste address mmap\n");
+		return;
+	}
+
+	txwin = cp_inst->txwin;
+	/*
+	 * task_ref.vma is set in coproc_mmap() during mmap paste
+	 * address. So it has to be the same VMA that is getting freed.
+	 */
+	if (WARN_ON(txwin->task_ref.vma != vma)) {
+		pr_err("Invalid paste address mmaping\n");
+		return;
+	}
+
+	scoped_guard(mutex, &txwin->task_ref.mmap_mutex)
+		txwin->task_ref.vma = NULL;
+}
+
 static const struct vm_operations_struct vas_vm_ops = {
+	.close = vas_mmap_close,
 	.fault = vas_mmap_fault,
 };
 
@@ -481,19 +514,28 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
 	txwin = cp_inst->txwin;
 
 	if ((vma->vm_end - vma->vm_start) > PAGE_SIZE) {
-		pr_debug("%s(): size 0x%zx, PAGE_SIZE 0x%zx\n", __func__,
+		pr_debug("size 0x%zx, PAGE_SIZE 0x%zx\n",
 				(vma->vm_end - vma->vm_start), PAGE_SIZE);
 		return -EINVAL;
 	}
 
+	/*
+	 * Map complete page to the paste address. So the user
+	 * space should pass 0ULL to the offset parameter.
+	 */
+	if (vma->vm_pgoff) {
+		pr_debug("Page offset unsupported to map paste address\n");
+		return -EINVAL;
+	}
+
 	/* Ensure instance has an open send window */
 	if (!txwin) {
-		pr_err("%s(): No send window open?\n", __func__);
+		pr_err("No send window open?\n");
 		return -EINVAL;
 	}
 
 	if (!cp_inst->coproc->vops || !cp_inst->coproc->vops->paste_addr) {
-		pr_err("%s(): VAS API is not registered\n", __func__);
+		pr_err("VAS API is not registered\n");
 		return -EACCES;
 	}
 
@@ -508,18 +550,16 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
 	 * close/open event and allows mmap() only when the window is
 	 * active.
 	 */
-	mutex_lock(&txwin->task_ref.mmap_mutex);
+	guard(mutex)(&txwin->task_ref.mmap_mutex);
 	if (txwin->status != VAS_WIN_ACTIVE) {
-		pr_err("%s(): Window is not active\n", __func__);
-		rc = -EACCES;
-		goto out;
+		pr_err("Window is not active\n");
+		return -EACCES;
 	}
 
 	paste_addr = cp_inst->coproc->vops->paste_addr(txwin);
 	if (!paste_addr) {
-		pr_err("%s(): Window paste address failed\n", __func__);
-		rc = -EINVAL;
-		goto out;
+		pr_err("Window paste address failed\n");
+		return -EINVAL;
 	}
 
 	pfn = paste_addr >> PAGE_SHIFT;
@@ -533,14 +573,12 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
 	rc = remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
 			vma->vm_end - vma->vm_start, prot);
 
-	pr_devel("%s(): paste addr %llx at %lx, rc %d\n", __func__,
-			paste_addr, vma->vm_start, rc);
+	pr_devel("paste addr %llx at %lx, rc %d\n", paste_addr,
+			vma->vm_start, rc);
 
 	txwin->task_ref.vma = vma;
 	vma->vm_ops = &vas_vm_ops;
 
-out:
-	mutex_unlock(&txwin->task_ref.mmap_mutex);
 	return rc;
 }
 
@@ -609,8 +647,7 @@ int vas_register_coproc_api(struct module *mod, enum vas_cop_type cop_type,
 		goto err;
 	}
 
-	pr_devel("%s: Added dev [%d,%d]\n", __func__, MAJOR(devno),
-			MINOR(devno));
+	pr_devel("Added dev [%d,%d]\n", MAJOR(devno), MINOR(devno));
 
 	return 0;
 
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 34669b060f36..db65bfcd1e74 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -3,42 +3,6 @@ config PPC_CELL
 	select PPC_64S_HASH_MMU if PPC64
 	bool
 
-config PPC_CELL_COMMON
-	bool
-	select PPC_CELL
-	select PPC_DCR_MMIO
-	select PPC_INDIRECT_PIO
-	select PPC_INDIRECT_MMIO
-	select PPC_HASH_MMU_NATIVE
-	select PPC_RTAS
-	select IRQ_EDGE_EOI_HANDLER
-
-config PPC_CELL_NATIVE
-	bool
-	select PPC_CELL_COMMON
-	select MPIC
-	select PPC_IO_WORKAROUNDS
-	select IBM_EMAC_EMAC4 if IBM_EMAC
-	select IBM_EMAC_RGMII if IBM_EMAC
-	select IBM_EMAC_ZMII if IBM_EMAC #test only
-	select IBM_EMAC_TAH if IBM_EMAC  #test only
-
-config PPC_IBM_CELL_BLADE
-	bool "IBM Cell Blade"
-	depends on PPC64 && PPC_BOOK3S && CPU_BIG_ENDIAN
-	select PPC_CELL_NATIVE
-	select PPC_OF_PLATFORM_PCI
-	select FORCE_PCI
-	select MMIO_NVRAM
-	select PPC_UDBG_16550
-	select UDBG_RTAS_CONSOLE
-
-config AXON_MSI
-	bool
-	depends on PPC_IBM_CELL_BLADE && PCI_MSI
-	select IRQ_DOMAIN_NOMAP
-	default y
-
 menu "Cell Broadband Engine options"
 	depends on PPC_CELL
 
@@ -57,48 +21,4 @@ config SPU_BASE
 	bool
 	select PPC_COPRO_BASE
 
-config CBE_RAS
-	bool "RAS features for bare metal Cell BE"
-	depends on PPC_CELL_NATIVE
-	default y
-
-config PPC_IBM_CELL_RESETBUTTON
-	bool "IBM Cell Blade Pinhole reset button"
-	depends on CBE_RAS && PPC_IBM_CELL_BLADE
-	default y
-	help
-	  Support Pinhole Resetbutton on IBM Cell blades.
-	  This adds a method to trigger system reset via front panel pinhole button.
-
-config PPC_IBM_CELL_POWERBUTTON
-	tristate "IBM Cell Blade power button"
-	depends on PPC_IBM_CELL_BLADE && INPUT_EVDEV
-	default y
-	help
-	  Support Powerbutton on IBM Cell blades.
-	  This will enable the powerbutton as an input device.
-
-config CBE_THERM
-	tristate "CBE thermal support"
-	default m
-	depends on CBE_RAS && SPU_BASE
-
-config PPC_PMI
-	tristate
-	default y
-	depends on CPU_FREQ_CBE_PMI || PPC_IBM_CELL_POWERBUTTON
-	help
-	  PMI (Platform Management Interrupt) is a way to
-	  communicate with the BMC (Baseboard Management Controller).
-	  It is used in some IBM Cell blades.
-
-config CBE_CPUFREQ_SPU_GOVERNOR
-	tristate "CBE frequency scaling based on SPU usage"
-	depends on SPU_FS && CPU_FREQ
-	default m
-	help
-	  This governor checks for spu usage to adjust the cpu frequency.
-	  If no spu is running on a given cpu, that cpu will be throttled to
-	  the minimal possible frequency.
-
 endmenu
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index 7ea6692f67e2..7e5ff239c376 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -1,27 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_PPC_CELL_COMMON)		+= cbe_regs.o interrupt.o pervasive.o
-
-obj-$(CONFIG_PPC_CELL_NATIVE)		+= iommu.o setup.o spider-pic.o \
-					   pmu.o spider-pci.o
-obj-$(CONFIG_CBE_RAS)			+= ras.o
-
-obj-$(CONFIG_CBE_THERM)			+= cbe_thermal.o
-obj-$(CONFIG_CBE_CPUFREQ_SPU_GOVERNOR)	+= cpufreq_spudemand.o
-
-obj-$(CONFIG_PPC_IBM_CELL_POWERBUTTON)	+= cbe_powerbutton.o
-
-ifdef CONFIG_SMP
-obj-$(CONFIG_PPC_CELL_NATIVE)		+= smp.o
-endif
-
-# needed only when building loadable spufs.ko
-spu-priv1-$(CONFIG_PPC_CELL_COMMON)	+= spu_priv1_mmio.o
-spu-manage-$(CONFIG_PPC_CELL_COMMON)	+= spu_manage.o
-
 obj-$(CONFIG_SPU_BASE)			+= spu_callbacks.o spu_base.o \
 					   spu_syscalls.o \
-					   $(spu-priv1-y) \
-					   $(spu-manage-y) \
 					   spufs/
-
-obj-$(CONFIG_AXON_MSI)			+= axon_msi.o
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
deleted file mode 100644
index 106000449d3b..000000000000
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ /dev/null
@@ -1,480 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright 2007, Michael Ellerman, IBM Corporation.
- */
-
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/msi.h>
-#include <linux/export.h>
-#include <linux/of_platform.h>
-#include <linux/slab.h>
-#include <linux/debugfs.h>
-#include <linux/of_irq.h>
-
-#include <asm/dcr.h>
-#include <asm/machdep.h>
-
-#include "cell.h"
-
-/*
- * MSIC registers, specified as offsets from dcr_base
- */
-#define MSIC_CTRL_REG	0x0
-
-/* Base Address registers specify FIFO location in BE memory */
-#define MSIC_BASE_ADDR_HI_REG	0x3
-#define MSIC_BASE_ADDR_LO_REG	0x4
-
-/* Hold the read/write offsets into the FIFO */
-#define MSIC_READ_OFFSET_REG	0x5
-#define MSIC_WRITE_OFFSET_REG	0x6
-
-
-/* MSIC control register flags */
-#define MSIC_CTRL_ENABLE		0x0001
-#define MSIC_CTRL_FIFO_FULL_ENABLE	0x0002
-#define MSIC_CTRL_IRQ_ENABLE		0x0008
-#define MSIC_CTRL_FULL_STOP_ENABLE	0x0010
-
-/*
- * The MSIC can be configured to use a FIFO of 32KB, 64KB, 128KB or 256KB.
- * Currently we're using a 64KB FIFO size.
- */
-#define MSIC_FIFO_SIZE_SHIFT	16
-#define MSIC_FIFO_SIZE_BYTES	(1 << MSIC_FIFO_SIZE_SHIFT)
-
-/*
- * To configure the FIFO size as (1 << n) bytes, we write (n - 15) into bits
- * 8-9 of the MSIC control reg.
- */
-#define MSIC_CTRL_FIFO_SIZE	(((MSIC_FIFO_SIZE_SHIFT - 15) << 8) & 0x300)
-
-/*
- * We need to mask the read/write offsets to make sure they stay within
- * the bounds of the FIFO. Also they should always be 16-byte aligned.
- */
-#define MSIC_FIFO_SIZE_MASK	((MSIC_FIFO_SIZE_BYTES - 1) & ~0xFu)
-
-/* Each entry in the FIFO is 16 bytes, the first 4 bytes hold the irq # */
-#define MSIC_FIFO_ENTRY_SIZE	0x10
-
-
-struct axon_msic {
-	struct irq_domain *irq_domain;
-	__le32 *fifo_virt;
-	dma_addr_t fifo_phys;
-	dcr_host_t dcr_host;
-	u32 read_offset;
-#ifdef DEBUG
-	u32 __iomem *trigger;
-#endif
-};
-
-#ifdef DEBUG
-void axon_msi_debug_setup(struct device_node *dn, struct axon_msic *msic);
-#else
-static inline void axon_msi_debug_setup(struct device_node *dn,
-					struct axon_msic *msic) { }
-#endif
-
-
-static void msic_dcr_write(struct axon_msic *msic, unsigned int dcr_n, u32 val)
-{
-	pr_devel("axon_msi: dcr_write(0x%x, 0x%x)\n", val, dcr_n);
-
-	dcr_write(msic->dcr_host, dcr_n, val);
-}
-
-static void axon_msi_cascade(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct axon_msic *msic = irq_desc_get_handler_data(desc);
-	u32 write_offset, msi;
-	int idx;
-	int retry = 0;
-
-	write_offset = dcr_read(msic->dcr_host, MSIC_WRITE_OFFSET_REG);
-	pr_devel("axon_msi: original write_offset 0x%x\n", write_offset);
-
-	/* write_offset doesn't wrap properly, so we have to mask it */
-	write_offset &= MSIC_FIFO_SIZE_MASK;
-
-	while (msic->read_offset != write_offset && retry < 100) {
-		idx  = msic->read_offset / sizeof(__le32);
-		msi  = le32_to_cpu(msic->fifo_virt[idx]);
-		msi &= 0xFFFF;
-
-		pr_devel("axon_msi: woff %x roff %x msi %x\n",
-			  write_offset, msic->read_offset, msi);
-
-		if (msi < nr_irqs && irq_get_chip_data(msi) == msic) {
-			generic_handle_irq(msi);
-			msic->fifo_virt[idx] = cpu_to_le32(0xffffffff);
-		} else {
-			/*
-			 * Reading the MSIC_WRITE_OFFSET_REG does not
-			 * reliably flush the outstanding DMA to the
-			 * FIFO buffer. Here we were reading stale
-			 * data, so we need to retry.
-			 */
-			udelay(1);
-			retry++;
-			pr_devel("axon_msi: invalid irq 0x%x!\n", msi);
-			continue;
-		}
-
-		if (retry) {
-			pr_devel("axon_msi: late irq 0x%x, retry %d\n",
-				 msi, retry);
-			retry = 0;
-		}
-
-		msic->read_offset += MSIC_FIFO_ENTRY_SIZE;
-		msic->read_offset &= MSIC_FIFO_SIZE_MASK;
-	}
-
-	if (retry) {
-		printk(KERN_WARNING "axon_msi: irq timed out\n");
-
-		msic->read_offset += MSIC_FIFO_ENTRY_SIZE;
-		msic->read_offset &= MSIC_FIFO_SIZE_MASK;
-	}
-
-	chip->irq_eoi(&desc->irq_data);
-}
-
-static struct axon_msic *find_msi_translator(struct pci_dev *dev)
-{
-	struct irq_domain *irq_domain;
-	struct device_node *dn, *tmp;
-	const phandle *ph;
-	struct axon_msic *msic = NULL;
-
-	dn = of_node_get(pci_device_to_OF_node(dev));
-	if (!dn) {
-		dev_dbg(&dev->dev, "axon_msi: no pci_dn found\n");
-		return NULL;
-	}
-
-	for (; dn; dn = of_get_next_parent(dn)) {
-		ph = of_get_property(dn, "msi-translator", NULL);
-		if (ph)
-			break;
-	}
-
-	if (!ph) {
-		dev_dbg(&dev->dev,
-			"axon_msi: no msi-translator property found\n");
-		goto out_error;
-	}
-
-	tmp = dn;
-	dn = of_find_node_by_phandle(*ph);
-	of_node_put(tmp);
-	if (!dn) {
-		dev_dbg(&dev->dev,
-			"axon_msi: msi-translator doesn't point to a node\n");
-		goto out_error;
-	}
-
-	irq_domain = irq_find_host(dn);
-	if (!irq_domain) {
-		dev_dbg(&dev->dev, "axon_msi: no irq_domain found for node %pOF\n",
-			dn);
-		goto out_error;
-	}
-
-	msic = irq_domain->host_data;
-
-out_error:
-	of_node_put(dn);
-
-	return msic;
-}
-
-static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg)
-{
-	struct device_node *dn;
-	int len;
-	const u32 *prop;
-
-	dn = of_node_get(pci_device_to_OF_node(dev));
-	if (!dn) {
-		dev_dbg(&dev->dev, "axon_msi: no pci_dn found\n");
-		return -ENODEV;
-	}
-
-	for (; dn; dn = of_get_next_parent(dn)) {
-		if (!dev->no_64bit_msi) {
-			prop = of_get_property(dn, "msi-address-64", &len);
-			if (prop)
-				break;
-		}
-
-		prop = of_get_property(dn, "msi-address-32", &len);
-		if (prop)
-			break;
-	}
-
-	if (!prop) {
-		dev_dbg(&dev->dev,
-			"axon_msi: no msi-address-(32|64) properties found\n");
-		of_node_put(dn);
-		return -ENOENT;
-	}
-
-	switch (len) {
-	case 8:
-		msg->address_hi = prop[0];
-		msg->address_lo = prop[1];
-		break;
-	case 4:
-		msg->address_hi = 0;
-		msg->address_lo = prop[0];
-		break;
-	default:
-		dev_dbg(&dev->dev,
-			"axon_msi: malformed msi-address-(32|64) property\n");
-		of_node_put(dn);
-		return -EINVAL;
-	}
-
-	of_node_put(dn);
-
-	return 0;
-}
-
-static int axon_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	unsigned int virq, rc;
-	struct msi_desc *entry;
-	struct msi_msg msg;
-	struct axon_msic *msic;
-
-	msic = find_msi_translator(dev);
-	if (!msic)
-		return -ENODEV;
-
-	rc = setup_msi_msg_address(dev, &msg);
-	if (rc)
-		return rc;
-
-	msi_for_each_desc(entry, &dev->dev, MSI_DESC_NOTASSOCIATED) {
-		virq = irq_create_direct_mapping(msic->irq_domain);
-		if (!virq) {
-			dev_warn(&dev->dev,
-				 "axon_msi: virq allocation failed!\n");
-			return -1;
-		}
-		dev_dbg(&dev->dev, "axon_msi: allocated virq 0x%x\n", virq);
-
-		irq_set_msi_desc(virq, entry);
-		msg.data = virq;
-		pci_write_msi_msg(virq, &msg);
-	}
-
-	return 0;
-}
-
-static void axon_msi_teardown_msi_irqs(struct pci_dev *dev)
-{
-	struct msi_desc *entry;
-
-	dev_dbg(&dev->dev, "axon_msi: tearing down msi irqs\n");
-
-	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ASSOCIATED) {
-		irq_set_msi_desc(entry->irq, NULL);
-		irq_dispose_mapping(entry->irq);
-		entry->irq = 0;
-	}
-}
-
-static struct irq_chip msic_irq_chip = {
-	.irq_mask	= pci_msi_mask_irq,
-	.irq_unmask	= pci_msi_unmask_irq,
-	.irq_shutdown	= pci_msi_mask_irq,
-	.name		= "AXON-MSI",
-};
-
-static int msic_host_map(struct irq_domain *h, unsigned int virq,
-			 irq_hw_number_t hw)
-{
-	irq_set_chip_data(virq, h->host_data);
-	irq_set_chip_and_handler(virq, &msic_irq_chip, handle_simple_irq);
-
-	return 0;
-}
-
-static const struct irq_domain_ops msic_host_ops = {
-	.map	= msic_host_map,
-};
-
-static void axon_msi_shutdown(struct platform_device *device)
-{
-	struct axon_msic *msic = dev_get_drvdata(&device->dev);
-	u32 tmp;
-
-	pr_devel("axon_msi: disabling %pOF\n",
-		 irq_domain_get_of_node(msic->irq_domain));
-	tmp  = dcr_read(msic->dcr_host, MSIC_CTRL_REG);
-	tmp &= ~MSIC_CTRL_ENABLE & ~MSIC_CTRL_IRQ_ENABLE;
-	msic_dcr_write(msic, MSIC_CTRL_REG, tmp);
-}
-
-static int axon_msi_probe(struct platform_device *device)
-{
-	struct device_node *dn = device->dev.of_node;
-	struct axon_msic *msic;
-	unsigned int virq;
-	int dcr_base, dcr_len;
-
-	pr_devel("axon_msi: setting up dn %pOF\n", dn);
-
-	msic = kzalloc(sizeof(*msic), GFP_KERNEL);
-	if (!msic) {
-		printk(KERN_ERR "axon_msi: couldn't allocate msic for %pOF\n",
-		       dn);
-		goto out;
-	}
-
-	dcr_base = dcr_resource_start(dn, 0);
-	dcr_len = dcr_resource_len(dn, 0);
-
-	if (dcr_base == 0 || dcr_len == 0) {
-		printk(KERN_ERR
-		       "axon_msi: couldn't parse dcr properties on %pOF\n",
-			dn);
-		goto out_free_msic;
-	}
-
-	msic->dcr_host = dcr_map(dn, dcr_base, dcr_len);
-	if (!DCR_MAP_OK(msic->dcr_host)) {
-		printk(KERN_ERR "axon_msi: dcr_map failed for %pOF\n",
-		       dn);
-		goto out_free_msic;
-	}
-
-	msic->fifo_virt = dma_alloc_coherent(&device->dev, MSIC_FIFO_SIZE_BYTES,
-					     &msic->fifo_phys, GFP_KERNEL);
-	if (!msic->fifo_virt) {
-		printk(KERN_ERR "axon_msi: couldn't allocate fifo for %pOF\n",
-		       dn);
-		goto out_free_msic;
-	}
-
-	virq = irq_of_parse_and_map(dn, 0);
-	if (!virq) {
-		printk(KERN_ERR "axon_msi: irq parse and map failed for %pOF\n",
-		       dn);
-		goto out_free_fifo;
-	}
-	memset(msic->fifo_virt, 0xff, MSIC_FIFO_SIZE_BYTES);
-
-	/* We rely on being able to stash a virq in a u16, so limit irqs to < 65536 */
-	msic->irq_domain = irq_domain_add_nomap(dn, 65536, &msic_host_ops, msic);
-	if (!msic->irq_domain) {
-		printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %pOF\n",
-		       dn);
-		goto out_free_fifo;
-	}
-
-	irq_set_handler_data(virq, msic);
-	irq_set_chained_handler(virq, axon_msi_cascade);
-	pr_devel("axon_msi: irq 0x%x setup for axon_msi\n", virq);
-
-	/* Enable the MSIC hardware */
-	msic_dcr_write(msic, MSIC_BASE_ADDR_HI_REG, msic->fifo_phys >> 32);
-	msic_dcr_write(msic, MSIC_BASE_ADDR_LO_REG,
-				  msic->fifo_phys & 0xFFFFFFFF);
-	msic_dcr_write(msic, MSIC_CTRL_REG,
-			MSIC_CTRL_IRQ_ENABLE | MSIC_CTRL_ENABLE |
-			MSIC_CTRL_FIFO_SIZE);
-
-	msic->read_offset = dcr_read(msic->dcr_host, MSIC_WRITE_OFFSET_REG)
-				& MSIC_FIFO_SIZE_MASK;
-
-	dev_set_drvdata(&device->dev, msic);
-
-	cell_pci_controller_ops.setup_msi_irqs = axon_msi_setup_msi_irqs;
-	cell_pci_controller_ops.teardown_msi_irqs = axon_msi_teardown_msi_irqs;
-
-	axon_msi_debug_setup(dn, msic);
-
-	printk(KERN_DEBUG "axon_msi: setup MSIC on %pOF\n", dn);
-
-	return 0;
-
-out_free_fifo:
-	dma_free_coherent(&device->dev, MSIC_FIFO_SIZE_BYTES, msic->fifo_virt,
-			  msic->fifo_phys);
-out_free_msic:
-	kfree(msic);
-out:
-
-	return -1;
-}
-
-static const struct of_device_id axon_msi_device_id[] = {
-	{
-		.compatible	= "ibm,axon-msic"
-	},
-	{}
-};
-
-static struct platform_driver axon_msi_driver = {
-	.probe		= axon_msi_probe,
-	.shutdown	= axon_msi_shutdown,
-	.driver = {
-		.name = "axon-msi",
-		.of_match_table = axon_msi_device_id,
-	},
-};
-
-static int __init axon_msi_init(void)
-{
-	return platform_driver_register(&axon_msi_driver);
-}
-subsys_initcall(axon_msi_init);
-
-
-#ifdef DEBUG
-static int msic_set(void *data, u64 val)
-{
-	struct axon_msic *msic = data;
-	out_le32(msic->trigger, val);
-	return 0;
-}
-
-static int msic_get(void *data, u64 *val)
-{
-	*val = 0;
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(fops_msic, msic_get, msic_set, "%llu\n");
-
-void axon_msi_debug_setup(struct device_node *dn, struct axon_msic *msic)
-{
-	char name[8];
-	struct resource res;
-
-	if (of_address_to_resource(dn, 0, &res)) {
-		pr_devel("axon_msi: couldn't get reg property\n");
-		return;
-	}
-
-	msic->trigger = ioremap(res.start, 0x4);
-	if (!msic->trigger) {
-		pr_devel("axon_msi: ioremap failed\n");
-		return;
-	}
-
-	snprintf(name, sizeof(name), "msic_%d", of_node_to_nid(dn));
-
-	debugfs_create_file(name, 0600, arch_debugfs_dir, msic, &fops_msic);
-}
-#endif /* DEBUG */
diff --git a/arch/powerpc/platforms/cell/cbe_powerbutton.c b/arch/powerpc/platforms/cell/cbe_powerbutton.c
deleted file mode 100644
index a3ee397486f6..000000000000
--- a/arch/powerpc/platforms/cell/cbe_powerbutton.c
+++ /dev/null
@@ -1,105 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * driver for powerbutton on IBM cell blades
- *
- * (C) Copyright IBM Corp. 2005-2008
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#include <linux/input.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <asm/pmi.h>
-
-static struct input_dev *button_dev;
-static struct platform_device *button_pdev;
-
-static void cbe_powerbutton_handle_pmi(pmi_message_t pmi_msg)
-{
-	BUG_ON(pmi_msg.type != PMI_TYPE_POWER_BUTTON);
-
-	input_report_key(button_dev, KEY_POWER, 1);
-	input_sync(button_dev);
-	input_report_key(button_dev, KEY_POWER, 0);
-	input_sync(button_dev);
-}
-
-static struct pmi_handler cbe_pmi_handler = {
-	.type			= PMI_TYPE_POWER_BUTTON,
-	.handle_pmi_message	= cbe_powerbutton_handle_pmi,
-};
-
-static int __init cbe_powerbutton_init(void)
-{
-	int ret = 0;
-	struct input_dev *dev;
-
-	if (!of_machine_is_compatible("IBM,CBPLUS-1.0")) {
-		printk(KERN_ERR "%s: Not a cell blade.\n", __func__);
-		ret = -ENODEV;
-		goto out;
-	}
-
-	dev = input_allocate_device();
-	if (!dev) {
-		ret = -ENOMEM;
-		printk(KERN_ERR "%s: Not enough memory.\n", __func__);
-		goto out;
-	}
-
-	set_bit(EV_KEY, dev->evbit);
-	set_bit(KEY_POWER, dev->keybit);
-
-	dev->name = "Power Button";
-	dev->id.bustype = BUS_HOST;
-
-	/* this makes the button look like an acpi power button
-	 * no clue whether anyone relies on that though */
-	dev->id.product = 0x02;
-	dev->phys = "LNXPWRBN/button/input0";
-
-	button_pdev = platform_device_register_simple("power_button", 0, NULL, 0);
-	if (IS_ERR(button_pdev)) {
-		ret = PTR_ERR(button_pdev);
-		goto out_free_input;
-	}
-
-	dev->dev.parent = &button_pdev->dev;
-	ret = input_register_device(dev);
-	if (ret) {
-		printk(KERN_ERR "%s: Failed to register device\n", __func__);
-		goto out_free_pdev;
-	}
-
-	button_dev = dev;
-
-	ret = pmi_register_handler(&cbe_pmi_handler);
-	if (ret) {
-		printk(KERN_ERR "%s: Failed to register with pmi.\n", __func__);
-		goto out_free_pdev;
-	}
-
-	goto out;
-
-out_free_pdev:
-	platform_device_unregister(button_pdev);
-out_free_input:
-	input_free_device(dev);
-out:
-	return ret;
-}
-
-static void __exit cbe_powerbutton_exit(void)
-{
-	pmi_unregister_handler(&cbe_pmi_handler);
-	platform_device_unregister(button_pdev);
-	input_free_device(button_dev);
-}
-
-module_init(cbe_powerbutton_init);
-module_exit(cbe_powerbutton_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c
deleted file mode 100644
index fb4023f9ea6b..000000000000
--- a/arch/powerpc/platforms/cell/cbe_regs.c
+++ /dev/null
@@ -1,299 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * cbe_regs.c
- *
- * Accessor routines for the various MMIO register blocks of the CBE
- *
- * (c) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>, IBM Corp.
- */
-
-#include <linux/percpu.h>
-#include <linux/types.h>
-#include <linux/export.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/of_platform.h>
-#include <linux/pgtable.h>
-
-#include <asm/io.h>
-#include <asm/ptrace.h>
-#include <asm/cell-regs.h>
-
-/*
- * Current implementation uses "cpu" nodes. We build our own mapping
- * array of cpu numbers to cpu nodes locally for now to allow interrupt
- * time code to have a fast path rather than call of_get_cpu_node(). If
- * we implement cpu hotplug, we'll have to install an appropriate notifier
- * in order to release references to the cpu going away
- */
-static struct cbe_regs_map
-{
-	struct device_node *cpu_node;
-	struct device_node *be_node;
-	struct cbe_pmd_regs __iomem *pmd_regs;
-	struct cbe_iic_regs __iomem *iic_regs;
-	struct cbe_mic_tm_regs __iomem *mic_tm_regs;
-	struct cbe_pmd_shadow_regs pmd_shadow_regs;
-} cbe_regs_maps[MAX_CBE];
-static int cbe_regs_map_count;
-
-static struct cbe_thread_map
-{
-	struct device_node *cpu_node;
-	struct device_node *be_node;
-	struct cbe_regs_map *regs;
-	unsigned int thread_id;
-	unsigned int cbe_id;
-} cbe_thread_map[NR_CPUS];
-
-static cpumask_t cbe_local_mask[MAX_CBE] = { [0 ... MAX_CBE-1] = {CPU_BITS_NONE} };
-static cpumask_t cbe_first_online_cpu = { CPU_BITS_NONE };
-
-static struct cbe_regs_map *cbe_find_map(struct device_node *np)
-{
-	int i;
-	struct device_node *tmp_np;
-
-	if (!of_node_is_type(np, "spe")) {
-		for (i = 0; i < cbe_regs_map_count; i++)
-			if (cbe_regs_maps[i].cpu_node == np ||
-			    cbe_regs_maps[i].be_node == np)
-				return &cbe_regs_maps[i];
-		return NULL;
-	}
-
-	if (np->data)
-		return np->data;
-
-	/* walk up path until cpu or be node was found */
-	tmp_np = np;
-	do {
-		tmp_np = tmp_np->parent;
-		/* on a correct devicetree we wont get up to root */
-		BUG_ON(!tmp_np);
-	} while (!of_node_is_type(tmp_np, "cpu") ||
-		 !of_node_is_type(tmp_np, "be"));
-
-	np->data = cbe_find_map(tmp_np);
-
-	return np->data;
-}
-
-struct cbe_pmd_regs __iomem *cbe_get_pmd_regs(struct device_node *np)
-{
-	struct cbe_regs_map *map = cbe_find_map(np);
-	if (map == NULL)
-		return NULL;
-	return map->pmd_regs;
-}
-EXPORT_SYMBOL_GPL(cbe_get_pmd_regs);
-
-struct cbe_pmd_regs __iomem *cbe_get_cpu_pmd_regs(int cpu)
-{
-	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
-	if (map == NULL)
-		return NULL;
-	return map->pmd_regs;
-}
-EXPORT_SYMBOL_GPL(cbe_get_cpu_pmd_regs);
-
-struct cbe_pmd_shadow_regs *cbe_get_pmd_shadow_regs(struct device_node *np)
-{
-	struct cbe_regs_map *map = cbe_find_map(np);
-	if (map == NULL)
-		return NULL;
-	return &map->pmd_shadow_regs;
-}
-
-struct cbe_pmd_shadow_regs *cbe_get_cpu_pmd_shadow_regs(int cpu)
-{
-	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
-	if (map == NULL)
-		return NULL;
-	return &map->pmd_shadow_regs;
-}
-
-struct cbe_iic_regs __iomem *cbe_get_iic_regs(struct device_node *np)
-{
-	struct cbe_regs_map *map = cbe_find_map(np);
-	if (map == NULL)
-		return NULL;
-	return map->iic_regs;
-}
-
-struct cbe_iic_regs __iomem *cbe_get_cpu_iic_regs(int cpu)
-{
-	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
-	if (map == NULL)
-		return NULL;
-	return map->iic_regs;
-}
-
-struct cbe_mic_tm_regs __iomem *cbe_get_mic_tm_regs(struct device_node *np)
-{
-	struct cbe_regs_map *map = cbe_find_map(np);
-	if (map == NULL)
-		return NULL;
-	return map->mic_tm_regs;
-}
-
-struct cbe_mic_tm_regs __iomem *cbe_get_cpu_mic_tm_regs(int cpu)
-{
-	struct cbe_regs_map *map = cbe_thread_map[cpu].regs;
-	if (map == NULL)
-		return NULL;
-	return map->mic_tm_regs;
-}
-EXPORT_SYMBOL_GPL(cbe_get_cpu_mic_tm_regs);
-
-u32 cbe_get_hw_thread_id(int cpu)
-{
-	return cbe_thread_map[cpu].thread_id;
-}
-EXPORT_SYMBOL_GPL(cbe_get_hw_thread_id);
-
-u32 cbe_cpu_to_node(int cpu)
-{
-	return cbe_thread_map[cpu].cbe_id;
-}
-EXPORT_SYMBOL_GPL(cbe_cpu_to_node);
-
-u32 cbe_node_to_cpu(int node)
-{
-	return cpumask_first(&cbe_local_mask[node]);
-
-}
-EXPORT_SYMBOL_GPL(cbe_node_to_cpu);
-
-static struct device_node *__init cbe_get_be_node(int cpu_id)
-{
-	struct device_node *np;
-
-	for_each_node_by_type (np, "be") {
-		int len,i;
-		const phandle *cpu_handle;
-
-		cpu_handle = of_get_property(np, "cpus", &len);
-
-		/*
-		 * the CAB SLOF tree is non compliant, so we just assume
-		 * there is only one node
-		 */
-		if (WARN_ON_ONCE(!cpu_handle))
-			return np;
-
-		for (i = 0; i < len; i++) {
-			struct device_node *ch_np = of_find_node_by_phandle(cpu_handle[i]);
-			struct device_node *ci_np = of_get_cpu_node(cpu_id, NULL);
-
-			of_node_put(ch_np);
-			of_node_put(ci_np);
-
-			if (ch_np == ci_np)
-				return np;
-		}
-	}
-
-	return NULL;
-}
-
-static void __init cbe_fill_regs_map(struct cbe_regs_map *map)
-{
-	if(map->be_node) {
-		struct device_node *be, *np, *parent_np;
-
-		be = map->be_node;
-
-		for_each_node_by_type(np, "pervasive") {
-			parent_np = of_get_parent(np);
-			if (parent_np == be)
-				map->pmd_regs = of_iomap(np, 0);
-			of_node_put(parent_np);
-		}
-
-		for_each_node_by_type(np, "CBEA-Internal-Interrupt-Controller") {
-			parent_np = of_get_parent(np);
-			if (parent_np == be)
-				map->iic_regs = of_iomap(np, 2);
-			of_node_put(parent_np);
-		}
-
-		for_each_node_by_type(np, "mic-tm") {
-			parent_np = of_get_parent(np);
-			if (parent_np == be)
-				map->mic_tm_regs = of_iomap(np, 0);
-			of_node_put(parent_np);
-		}
-	} else {
-		struct device_node *cpu;
-		/* That hack must die die die ! */
-		const struct address_prop {
-			unsigned long address;
-			unsigned int len;
-		} __attribute__((packed)) *prop;
-
-		cpu = map->cpu_node;
-
-		prop = of_get_property(cpu, "pervasive", NULL);
-		if (prop != NULL)
-			map->pmd_regs = ioremap(prop->address, prop->len);
-
-		prop = of_get_property(cpu, "iic", NULL);
-		if (prop != NULL)
-			map->iic_regs = ioremap(prop->address, prop->len);
-
-		prop = of_get_property(cpu, "mic-tm", NULL);
-		if (prop != NULL)
-			map->mic_tm_regs = ioremap(prop->address, prop->len);
-	}
-}
-
-
-void __init cbe_regs_init(void)
-{
-	int i;
-	unsigned int thread_id;
-	struct device_node *cpu;
-
-	/* Build local fast map of CPUs */
-	for_each_possible_cpu(i) {
-		cbe_thread_map[i].cpu_node = of_get_cpu_node(i, &thread_id);
-		cbe_thread_map[i].be_node = cbe_get_be_node(i);
-		cbe_thread_map[i].thread_id = thread_id;
-	}
-
-	/* Find maps for each device tree CPU */
-	for_each_node_by_type(cpu, "cpu") {
-		struct cbe_regs_map *map;
-		unsigned int cbe_id;
-
-		cbe_id = cbe_regs_map_count++;
-		map = &cbe_regs_maps[cbe_id];
-
-		if (cbe_regs_map_count > MAX_CBE) {
-			printk(KERN_ERR "cbe_regs: More BE chips than supported"
-			       "!\n");
-			cbe_regs_map_count--;
-			of_node_put(cpu);
-			return;
-		}
-		of_node_put(map->cpu_node);
-		map->cpu_node = of_node_get(cpu);
-
-		for_each_possible_cpu(i) {
-			struct cbe_thread_map *thread = &cbe_thread_map[i];
-
-			if (thread->cpu_node == cpu) {
-				thread->regs = map;
-				thread->cbe_id = cbe_id;
-				map->be_node = thread->be_node;
-				cpumask_set_cpu(i, &cbe_local_mask[cbe_id]);
-				if(thread->thread_id == 0)
-					cpumask_set_cpu(i, &cbe_first_online_cpu);
-			}
-		}
-
-		cbe_fill_regs_map(map);
-	}
-}
-
diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c
deleted file mode 100644
index 2f45428e32c8..000000000000
--- a/arch/powerpc/platforms/cell/cbe_thermal.c
+++ /dev/null
@@ -1,386 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * thermal support for the cell processor
- *
- * This module adds some sysfs attributes to cpu and spu nodes.
- * Base for measurements are the digital thermal sensors (DTS)
- * located on the chip.
- * The accuracy is 2 degrees, starting from 65 up to 125 degrees celsius
- * The attributes can be found under
- * /sys/devices/system/cpu/cpuX/thermal
- * /sys/devices/system/spu/spuX/thermal
- *
- * The following attributes are added for each node:
- * temperature:
- *	contains the current temperature measured by the DTS
- * throttle_begin:
- *	throttling begins when temperature is greater or equal to
- *	throttle_begin. Setting this value to 125 prevents throttling.
- * throttle_end:
- *	throttling is being ceased, if the temperature is lower than
- *	throttle_end. Due to a delay between applying throttling and
- *	a reduced temperature this value should be less than throttle_begin.
- *	A value equal to throttle_begin provides only a very little hysteresis.
- * throttle_full_stop:
- *	If the temperatrue is greater or equal to throttle_full_stop,
- *	full throttling is applied to the cpu or spu. This value should be
- *	greater than throttle_begin and throttle_end. Setting this value to
- *	65 prevents the unit from running code at all.
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/kernel.h>
-#include <linux/cpu.h>
-#include <linux/stringify.h>
-#include <asm/spu.h>
-#include <asm/io.h>
-#include <asm/cell-regs.h>
-
-#include "spu_priv1_mmio.h"
-
-#define TEMP_MIN 65
-#define TEMP_MAX 125
-
-#define DEVICE_PREFIX_ATTR(_prefix,_name,_mode)			\
-struct device_attribute attr_ ## _prefix ## _ ## _name = {	\
-	.attr = { .name = __stringify(_name), .mode = _mode },	\
-	.show	= _prefix ## _show_ ## _name,			\
-	.store	= _prefix ## _store_ ## _name,			\
-};
-
-static inline u8 reg_to_temp(u8 reg_value)
-{
-	return ((reg_value & 0x3f) << 1) + TEMP_MIN;
-}
-
-static inline u8 temp_to_reg(u8 temp)
-{
-	return ((temp - TEMP_MIN) >> 1) & 0x3f;
-}
-
-static struct cbe_pmd_regs __iomem *get_pmd_regs(struct device *dev)
-{
-	struct spu *spu;
-
-	spu = container_of(dev, struct spu, dev);
-
-	return cbe_get_pmd_regs(spu_devnode(spu));
-}
-
-/* returns the value for a given spu in a given register */
-static u8 spu_read_register_value(struct device *dev, union spe_reg __iomem *reg)
-{
-	union spe_reg value;
-	struct spu *spu;
-
-	spu = container_of(dev, struct spu, dev);
-	value.val = in_be64(&reg->val);
-
-	return value.spe[spu->spe_id];
-}
-
-static ssize_t spu_show_temp(struct device *dev, struct device_attribute *attr,
-			char *buf)
-{
-	u8 value;
-	struct cbe_pmd_regs __iomem *pmd_regs;
-
-	pmd_regs = get_pmd_regs(dev);
-
-	value = spu_read_register_value(dev, &pmd_regs->ts_ctsr1);
-
-	return sprintf(buf, "%d\n", reg_to_temp(value));
-}
-
-static ssize_t show_throttle(struct cbe_pmd_regs __iomem *pmd_regs, char *buf, int pos)
-{
-	u64 value;
-
-	value = in_be64(&pmd_regs->tm_tpr.val);
-	/* access the corresponding byte */
-	value >>= pos;
-	value &= 0x3F;
-
-	return sprintf(buf, "%d\n", reg_to_temp(value));
-}
-
-static ssize_t store_throttle(struct cbe_pmd_regs __iomem *pmd_regs, const char *buf, size_t size, int pos)
-{
-	u64 reg_value;
-	unsigned int temp;
-	u64 new_value;
-	int ret;
-
-	ret = sscanf(buf, "%u", &temp);
-
-	if (ret != 1 || temp < TEMP_MIN || temp > TEMP_MAX)
-		return -EINVAL;
-
-	new_value = temp_to_reg(temp);
-
-	reg_value = in_be64(&pmd_regs->tm_tpr.val);
-
-	/* zero out bits for new value */
-	reg_value &= ~(0xffull << pos);
-	/* set bits to new value */
-	reg_value |= new_value << pos;
-
-	out_be64(&pmd_regs->tm_tpr.val, reg_value);
-	return size;
-}
-
-static ssize_t spu_show_throttle_end(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(get_pmd_regs(dev), buf, 0);
-}
-
-static ssize_t spu_show_throttle_begin(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(get_pmd_regs(dev), buf, 8);
-}
-
-static ssize_t spu_show_throttle_full_stop(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(get_pmd_regs(dev), buf, 16);
-}
-
-static ssize_t spu_store_throttle_end(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(get_pmd_regs(dev), buf, size, 0);
-}
-
-static ssize_t spu_store_throttle_begin(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(get_pmd_regs(dev), buf, size, 8);
-}
-
-static ssize_t spu_store_throttle_full_stop(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(get_pmd_regs(dev), buf, size, 16);
-}
-
-static ssize_t ppe_show_temp(struct device *dev, char *buf, int pos)
-{
-	struct cbe_pmd_regs __iomem *pmd_regs;
-	u64 value;
-
-	pmd_regs = cbe_get_cpu_pmd_regs(dev->id);
-	value = in_be64(&pmd_regs->ts_ctsr2);
-
-	value = (value >> pos) & 0x3f;
-
-	return sprintf(buf, "%d\n", reg_to_temp(value));
-}
-
-
-/* shows the temperature of the DTS on the PPE,
- * located near the linear thermal sensor */
-static ssize_t ppe_show_temp0(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return ppe_show_temp(dev, buf, 32);
-}
-
-/* shows the temperature of the second DTS on the PPE */
-static ssize_t ppe_show_temp1(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return ppe_show_temp(dev, buf, 0);
-}
-
-static ssize_t ppe_show_throttle_end(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, 32);
-}
-
-static ssize_t ppe_show_throttle_begin(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, 40);
-}
-
-static ssize_t ppe_show_throttle_full_stop(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	return show_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, 48);
-}
-
-static ssize_t ppe_store_throttle_end(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, size, 32);
-}
-
-static ssize_t ppe_store_throttle_begin(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, size, 40);
-}
-
-static ssize_t ppe_store_throttle_full_stop(struct device *dev,
-			struct device_attribute *attr, const char *buf, size_t size)
-{
-	return store_throttle(cbe_get_cpu_pmd_regs(dev->id), buf, size, 48);
-}
-
-
-static struct device_attribute attr_spu_temperature = {
-	.attr = {.name = "temperature", .mode = 0400 },
-	.show = spu_show_temp,
-};
-
-static DEVICE_PREFIX_ATTR(spu, throttle_end, 0600);
-static DEVICE_PREFIX_ATTR(spu, throttle_begin, 0600);
-static DEVICE_PREFIX_ATTR(spu, throttle_full_stop, 0600);
-
-
-static struct attribute *spu_attributes[] = {
-	&attr_spu_temperature.attr,
-	&attr_spu_throttle_end.attr,
-	&attr_spu_throttle_begin.attr,
-	&attr_spu_throttle_full_stop.attr,
-	NULL,
-};
-
-static const struct attribute_group spu_attribute_group = {
-	.name	= "thermal",
-	.attrs	= spu_attributes,
-};
-
-static struct device_attribute attr_ppe_temperature0 = {
-	.attr = {.name = "temperature0", .mode = 0400 },
-	.show = ppe_show_temp0,
-};
-
-static struct device_attribute attr_ppe_temperature1 = {
-	.attr = {.name = "temperature1", .mode = 0400 },
-	.show = ppe_show_temp1,
-};
-
-static DEVICE_PREFIX_ATTR(ppe, throttle_end, 0600);
-static DEVICE_PREFIX_ATTR(ppe, throttle_begin, 0600);
-static DEVICE_PREFIX_ATTR(ppe, throttle_full_stop, 0600);
-
-static struct attribute *ppe_attributes[] = {
-	&attr_ppe_temperature0.attr,
-	&attr_ppe_temperature1.attr,
-	&attr_ppe_throttle_end.attr,
-	&attr_ppe_throttle_begin.attr,
-	&attr_ppe_throttle_full_stop.attr,
-	NULL,
-};
-
-static struct attribute_group ppe_attribute_group = {
-	.name	= "thermal",
-	.attrs	= ppe_attributes,
-};
-
-/*
- * initialize throttling with default values
- */
-static int __init init_default_values(void)
-{
-	int cpu;
-	struct cbe_pmd_regs __iomem *pmd_regs;
-	struct device *dev;
-	union ppe_spe_reg tpr;
-	union spe_reg str1;
-	u64 str2;
-	union spe_reg cr1;
-	u64 cr2;
-
-	/* TPR defaults */
-	/* ppe
-	 *	1F - no full stop
-	 *	08 - dynamic throttling starts if over 80 degrees
-	 *	03 - dynamic throttling ceases if below 70 degrees */
-	tpr.ppe = 0x1F0803;
-	/* spe
-	 *	10 - full stopped when over 96 degrees
-	 *	08 - dynamic throttling starts if over 80 degrees
-	 *	03 - dynamic throttling ceases if below 70 degrees
-	 */
-	tpr.spe = 0x100803;
-
-	/* STR defaults */
-	/* str1
-	 *	10 - stop 16 of 32 cycles
-	 */
-	str1.val = 0x1010101010101010ull;
-	/* str2
-	 *	10 - stop 16 of 32 cycles
-	 */
-	str2 = 0x10;
-
-	/* CR defaults */
-	/* cr1
-	 *	4 - normal operation
-	 */
-	cr1.val = 0x0404040404040404ull;
-	/* cr2
-	 *	4 - normal operation
-	 */
-	cr2 = 0x04;
-
-	for_each_possible_cpu (cpu) {
-		pr_debug("processing cpu %d\n", cpu);
-		dev = get_cpu_device(cpu);
-
-		if (!dev) {
-			pr_info("invalid dev pointer for cbe_thermal\n");
-			return -EINVAL;
-		}
-
-		pmd_regs = cbe_get_cpu_pmd_regs(dev->id);
-
-		if (!pmd_regs) {
-			pr_info("invalid CBE regs pointer for cbe_thermal\n");
-			return -EINVAL;
-		}
-
-		out_be64(&pmd_regs->tm_str2, str2);
-		out_be64(&pmd_regs->tm_str1.val, str1.val);
-		out_be64(&pmd_regs->tm_tpr.val, tpr.val);
-		out_be64(&pmd_regs->tm_cr1.val, cr1.val);
-		out_be64(&pmd_regs->tm_cr2, cr2);
-	}
-
-	return 0;
-}
-
-
-static int __init thermal_init(void)
-{
-	int rc = init_default_values();
-
-	if (rc == 0) {
-		spu_add_dev_attr_group(&spu_attribute_group);
-		cpu_add_dev_attr_group(&ppe_attribute_group);
-	}
-
-	return rc;
-}
-module_init(thermal_init);
-
-static void __exit thermal_exit(void)
-{
-	spu_remove_dev_attr_group(&spu_attribute_group);
-	cpu_remove_dev_attr_group(&ppe_attribute_group);
-}
-module_exit(thermal_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
-
diff --git a/arch/powerpc/platforms/cell/cell.h b/arch/powerpc/platforms/cell/cell.h
deleted file mode 100644
index d5142e905ab3..000000000000
--- a/arch/powerpc/platforms/cell/cell.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Cell Platform common data structures
- *
- * Copyright 2015, Daniel Axtens, IBM Corporation
- */
-
-#ifndef CELL_H
-#define CELL_H
-
-#include <asm/pci-bridge.h>
-
-extern struct pci_controller_ops cell_pci_controller_ops;
-
-#endif
diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
deleted file mode 100644
index ca7849e113d7..000000000000
--- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c
+++ /dev/null
@@ -1,133 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * spu aware cpufreq governor for the cell processor
- *
- * © Copyright IBM Corporation 2006-2008
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#include <linux/cpufreq.h>
-#include <linux/sched.h>
-#include <linux/sched/loadavg.h>
-#include <linux/module.h>
-#include <linux/timer.h>
-#include <linux/workqueue.h>
-#include <linux/atomic.h>
-#include <asm/machdep.h>
-#include <asm/spu.h>
-
-#define POLL_TIME	100000		/* in µs */
-#define EXP		753		/* exp(-1) in fixed-point */
-
-struct spu_gov_info_struct {
-	unsigned long busy_spus;	/* fixed-point */
-	struct cpufreq_policy *policy;
-	struct delayed_work work;
-	unsigned int poll_int;		/* µs */
-};
-static DEFINE_PER_CPU(struct spu_gov_info_struct, spu_gov_info);
-
-static int calc_freq(struct spu_gov_info_struct *info)
-{
-	int cpu;
-	int busy_spus;
-
-	cpu = info->policy->cpu;
-	busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus);
-
-	info->busy_spus = calc_load(info->busy_spus, EXP, busy_spus * FIXED_1);
-	pr_debug("cpu %d: busy_spus=%d, info->busy_spus=%ld\n",
-			cpu, busy_spus, info->busy_spus);
-
-	return info->policy->max * info->busy_spus / FIXED_1;
-}
-
-static void spu_gov_work(struct work_struct *work)
-{
-	struct spu_gov_info_struct *info;
-	int delay;
-	unsigned long target_freq;
-
-	info = container_of(work, struct spu_gov_info_struct, work.work);
-
-	/* after cancel_delayed_work_sync we unset info->policy */
-	BUG_ON(info->policy == NULL);
-
-	target_freq = calc_freq(info);
-	__cpufreq_driver_target(info->policy, target_freq, CPUFREQ_RELATION_H);
-
-	delay = usecs_to_jiffies(info->poll_int);
-	schedule_delayed_work_on(info->policy->cpu, &info->work, delay);
-}
-
-static void spu_gov_init_work(struct spu_gov_info_struct *info)
-{
-	int delay = usecs_to_jiffies(info->poll_int);
-	INIT_DEFERRABLE_WORK(&info->work, spu_gov_work);
-	schedule_delayed_work_on(info->policy->cpu, &info->work, delay);
-}
-
-static void spu_gov_cancel_work(struct spu_gov_info_struct *info)
-{
-	cancel_delayed_work_sync(&info->work);
-}
-
-static int spu_gov_start(struct cpufreq_policy *policy)
-{
-	unsigned int cpu = policy->cpu;
-	struct spu_gov_info_struct *info = &per_cpu(spu_gov_info, cpu);
-	struct spu_gov_info_struct *affected_info;
-	int i;
-
-	if (!cpu_online(cpu)) {
-		printk(KERN_ERR "cpu %d is not online\n", cpu);
-		return -EINVAL;
-	}
-
-	if (!policy->cur) {
-		printk(KERN_ERR "no cpu specified in policy\n");
-		return -EINVAL;
-	}
-
-	/* initialize spu_gov_info for all affected cpus */
-	for_each_cpu(i, policy->cpus) {
-		affected_info = &per_cpu(spu_gov_info, i);
-		affected_info->policy = policy;
-	}
-
-	info->poll_int = POLL_TIME;
-
-	/* setup timer */
-	spu_gov_init_work(info);
-
-	return 0;
-}
-
-static void spu_gov_stop(struct cpufreq_policy *policy)
-{
-	unsigned int cpu = policy->cpu;
-	struct spu_gov_info_struct *info = &per_cpu(spu_gov_info, cpu);
-	int i;
-
-	/* cancel timer */
-	spu_gov_cancel_work(info);
-
-	/* clean spu_gov_info for all affected cpus */
-	for_each_cpu (i, policy->cpus) {
-		info = &per_cpu(spu_gov_info, i);
-		info->policy = NULL;
-	}
-}
-
-static struct cpufreq_governor spu_governor = {
-	.name = "spudemand",
-	.start = spu_gov_start,
-	.stop = spu_gov_stop,
-	.owner = THIS_MODULE,
-};
-cpufreq_governor_init(spu_governor);
-cpufreq_governor_exit(spu_governor);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
deleted file mode 100644
index 03ee8152ee97..000000000000
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ /dev/null
@@ -1,390 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cell Internal Interrupt Controller
- *
- * Copyright (C) 2006 Benjamin Herrenschmidt (benh@kernel.crashing.org)
- *                    IBM, Corp.
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * TODO:
- * - Fix various assumptions related to HW CPU numbers vs. linux CPU numbers
- *   vs node numbers in the setup code
- * - Implement proper handling of maxcpus=1/2 (that is, routing of irqs from
- *   a non-active node to the active node)
- */
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/export.h>
-#include <linux/percpu.h>
-#include <linux/types.h>
-#include <linux/ioport.h>
-#include <linux/kernel_stat.h>
-#include <linux/pgtable.h>
-#include <linux/of_address.h>
-
-#include <asm/io.h>
-#include <asm/ptrace.h>
-#include <asm/machdep.h>
-#include <asm/cell-regs.h>
-
-#include "interrupt.h"
-
-struct iic {
-	struct cbe_iic_thread_regs __iomem *regs;
-	u8 target_id;
-	u8 eoi_stack[16];
-	int eoi_ptr;
-	struct device_node *node;
-};
-
-static DEFINE_PER_CPU(struct iic, cpu_iic);
-#define IIC_NODE_COUNT	2
-static struct irq_domain *iic_host;
-
-/* Convert between "pending" bits and hw irq number */
-static irq_hw_number_t iic_pending_to_hwnum(struct cbe_iic_pending_bits bits)
-{
-	unsigned char unit = bits.source & 0xf;
-	unsigned char node = bits.source >> 4;
-	unsigned char class = bits.class & 3;
-
-	/* Decode IPIs */
-	if (bits.flags & CBE_IIC_IRQ_IPI)
-		return IIC_IRQ_TYPE_IPI | (bits.prio >> 4);
-	else
-		return (node << IIC_IRQ_NODE_SHIFT) | (class << 4) | unit;
-}
-
-static void iic_mask(struct irq_data *d)
-{
-}
-
-static void iic_unmask(struct irq_data *d)
-{
-}
-
-static void iic_eoi(struct irq_data *d)
-{
-	struct iic *iic = this_cpu_ptr(&cpu_iic);
-	out_be64(&iic->regs->prio, iic->eoi_stack[--iic->eoi_ptr]);
-	BUG_ON(iic->eoi_ptr < 0);
-}
-
-static struct irq_chip iic_chip = {
-	.name = "CELL-IIC",
-	.irq_mask = iic_mask,
-	.irq_unmask = iic_unmask,
-	.irq_eoi = iic_eoi,
-};
-
-
-static void iic_ioexc_eoi(struct irq_data *d)
-{
-}
-
-static void iic_ioexc_cascade(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct cbe_iic_regs __iomem *node_iic =
-		(void __iomem *)irq_desc_get_handler_data(desc);
-	unsigned int irq = irq_desc_get_irq(desc);
-	unsigned int base = (irq & 0xffffff00) | IIC_IRQ_TYPE_IOEXC;
-	unsigned long bits, ack;
-	int cascade;
-
-	for (;;) {
-		bits = in_be64(&node_iic->iic_is);
-		if (bits == 0)
-			break;
-		/* pre-ack edge interrupts */
-		ack = bits & IIC_ISR_EDGE_MASK;
-		if (ack)
-			out_be64(&node_iic->iic_is, ack);
-		/* handle them */
-		for (cascade = 63; cascade >= 0; cascade--)
-			if (bits & (0x8000000000000000UL >> cascade))
-				generic_handle_domain_irq(iic_host,
-							  base | cascade);
-		/* post-ack level interrupts */
-		ack = bits & ~IIC_ISR_EDGE_MASK;
-		if (ack)
-			out_be64(&node_iic->iic_is, ack);
-	}
-	chip->irq_eoi(&desc->irq_data);
-}
-
-
-static struct irq_chip iic_ioexc_chip = {
-	.name = "CELL-IOEX",
-	.irq_mask = iic_mask,
-	.irq_unmask = iic_unmask,
-	.irq_eoi = iic_ioexc_eoi,
-};
-
-/* Get an IRQ number from the pending state register of the IIC */
-static unsigned int iic_get_irq(void)
-{
-	struct cbe_iic_pending_bits pending;
-	struct iic *iic;
-	unsigned int virq;
-
-	iic = this_cpu_ptr(&cpu_iic);
-	*(unsigned long *) &pending =
-		in_be64((u64 __iomem *) &iic->regs->pending_destr);
-	if (!(pending.flags & CBE_IIC_IRQ_VALID))
-		return 0;
-	virq = irq_linear_revmap(iic_host, iic_pending_to_hwnum(pending));
-	if (!virq)
-		return 0;
-	iic->eoi_stack[++iic->eoi_ptr] = pending.prio;
-	BUG_ON(iic->eoi_ptr > 15);
-	return virq;
-}
-
-void iic_setup_cpu(void)
-{
-	out_be64(&this_cpu_ptr(&cpu_iic)->regs->prio, 0xff);
-}
-
-u8 iic_get_target_id(int cpu)
-{
-	return per_cpu(cpu_iic, cpu).target_id;
-}
-
-EXPORT_SYMBOL_GPL(iic_get_target_id);
-
-#ifdef CONFIG_SMP
-
-/* Use the highest interrupt priorities for IPI */
-static inline int iic_msg_to_irq(int msg)
-{
-	return IIC_IRQ_TYPE_IPI + 0xf - msg;
-}
-
-void iic_message_pass(int cpu, int msg)
-{
-	out_be64(&per_cpu(cpu_iic, cpu).regs->generate, (0xf - msg) << 4);
-}
-
-static void iic_request_ipi(int msg)
-{
-	int virq;
-
-	virq = irq_create_mapping(iic_host, iic_msg_to_irq(msg));
-	if (!virq) {
-		printk(KERN_ERR
-		       "iic: failed to map IPI %s\n", smp_ipi_name[msg]);
-		return;
-	}
-
-	/*
-	 * If smp_request_message_ipi encounters an error it will notify
-	 * the error.  If a message is not needed it will return non-zero.
-	 */
-	if (smp_request_message_ipi(virq, msg))
-		irq_dispose_mapping(virq);
-}
-
-void iic_request_IPIs(void)
-{
-	iic_request_ipi(PPC_MSG_CALL_FUNCTION);
-	iic_request_ipi(PPC_MSG_RESCHEDULE);
-	iic_request_ipi(PPC_MSG_TICK_BROADCAST);
-	iic_request_ipi(PPC_MSG_NMI_IPI);
-}
-
-#endif /* CONFIG_SMP */
-
-
-static int iic_host_match(struct irq_domain *h, struct device_node *node,
-			  enum irq_domain_bus_token bus_token)
-{
-	return of_device_is_compatible(node,
-				    "IBM,CBEA-Internal-Interrupt-Controller");
-}
-
-static int iic_host_map(struct irq_domain *h, unsigned int virq,
-			irq_hw_number_t hw)
-{
-	switch (hw & IIC_IRQ_TYPE_MASK) {
-	case IIC_IRQ_TYPE_IPI:
-		irq_set_chip_and_handler(virq, &iic_chip, handle_percpu_irq);
-		break;
-	case IIC_IRQ_TYPE_IOEXC:
-		irq_set_chip_and_handler(virq, &iic_ioexc_chip,
-					 handle_edge_eoi_irq);
-		break;
-	default:
-		irq_set_chip_and_handler(virq, &iic_chip, handle_edge_eoi_irq);
-	}
-	return 0;
-}
-
-static int iic_host_xlate(struct irq_domain *h, struct device_node *ct,
-			   const u32 *intspec, unsigned int intsize,
-			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
-
-{
-	unsigned int node, ext, unit, class;
-	const u32 *val;
-
-	if (!of_device_is_compatible(ct,
-				     "IBM,CBEA-Internal-Interrupt-Controller"))
-		return -ENODEV;
-	if (intsize != 1)
-		return -ENODEV;
-	val = of_get_property(ct, "#interrupt-cells", NULL);
-	if (val == NULL || *val != 1)
-		return -ENODEV;
-
-	node = intspec[0] >> 24;
-	ext = (intspec[0] >> 16) & 0xff;
-	class = (intspec[0] >> 8) & 0xff;
-	unit = intspec[0] & 0xff;
-
-	/* Check if node is in supported range */
-	if (node > 1)
-		return -EINVAL;
-
-	/* Build up interrupt number, special case for IO exceptions */
-	*out_hwirq = (node << IIC_IRQ_NODE_SHIFT);
-	if (unit == IIC_UNIT_IIC && class == 1)
-		*out_hwirq |= IIC_IRQ_TYPE_IOEXC | ext;
-	else
-		*out_hwirq |= IIC_IRQ_TYPE_NORMAL |
-			(class << IIC_IRQ_CLASS_SHIFT) | unit;
-
-	/* Dummy flags, ignored by iic code */
-	*out_flags = IRQ_TYPE_EDGE_RISING;
-
-	return 0;
-}
-
-static const struct irq_domain_ops iic_host_ops = {
-	.match = iic_host_match,
-	.map = iic_host_map,
-	.xlate = iic_host_xlate,
-};
-
-static void __init init_one_iic(unsigned int hw_cpu, unsigned long addr,
-				struct device_node *node)
-{
-	/* XXX FIXME: should locate the linux CPU number from the HW cpu
-	 * number properly. We are lucky for now
-	 */
-	struct iic *iic = &per_cpu(cpu_iic, hw_cpu);
-
-	iic->regs = ioremap(addr, sizeof(struct cbe_iic_thread_regs));
-	BUG_ON(iic->regs == NULL);
-
-	iic->target_id = ((hw_cpu & 2) << 3) | ((hw_cpu & 1) ? 0xf : 0xe);
-	iic->eoi_stack[0] = 0xff;
-	iic->node = of_node_get(node);
-	out_be64(&iic->regs->prio, 0);
-
-	printk(KERN_INFO "IIC for CPU %d target id 0x%x : %pOF\n",
-	       hw_cpu, iic->target_id, node);
-}
-
-static int __init setup_iic(void)
-{
-	struct device_node *dn;
-	struct resource r0, r1;
-	unsigned int node, cascade, found = 0;
-	struct cbe_iic_regs __iomem *node_iic;
-	const u32 *np;
-
-	for_each_node_by_name(dn, "interrupt-controller") {
-		if (!of_device_is_compatible(dn,
-				     "IBM,CBEA-Internal-Interrupt-Controller"))
-			continue;
-		np = of_get_property(dn, "ibm,interrupt-server-ranges", NULL);
-		if (np == NULL) {
-			printk(KERN_WARNING "IIC: CPU association not found\n");
-			of_node_put(dn);
-			return -ENODEV;
-		}
-		if (of_address_to_resource(dn, 0, &r0) ||
-		    of_address_to_resource(dn, 1, &r1)) {
-			printk(KERN_WARNING "IIC: Can't resolve addresses\n");
-			of_node_put(dn);
-			return -ENODEV;
-		}
-		found++;
-		init_one_iic(np[0], r0.start, dn);
-		init_one_iic(np[1], r1.start, dn);
-
-		/* Setup cascade for IO exceptions. XXX cleanup tricks to get
-		 * node vs CPU etc...
-		 * Note that we configure the IIC_IRR here with a hard coded
-		 * priority of 1. We might want to improve that later.
-		 */
-		node = np[0] >> 1;
-		node_iic = cbe_get_cpu_iic_regs(np[0]);
-		cascade = node << IIC_IRQ_NODE_SHIFT;
-		cascade |= 1 << IIC_IRQ_CLASS_SHIFT;
-		cascade |= IIC_UNIT_IIC;
-		cascade = irq_create_mapping(iic_host, cascade);
-		if (!cascade)
-			continue;
-		/*
-		 * irq_data is a generic pointer that gets passed back
-		 * to us later, so the forced cast is fine.
-		 */
-		irq_set_handler_data(cascade, (void __force *)node_iic);
-		irq_set_chained_handler(cascade, iic_ioexc_cascade);
-		out_be64(&node_iic->iic_ir,
-			 (1 << 12)		/* priority */ |
-			 (node << 4)		/* dest node */ |
-			 IIC_UNIT_THREAD_0	/* route them to thread 0 */);
-		/* Flush pending (make sure it triggers if there is
-		 * anything pending
-		 */
-		out_be64(&node_iic->iic_is, 0xfffffffffffffffful);
-	}
-
-	if (found)
-		return 0;
-	else
-		return -ENODEV;
-}
-
-void __init iic_init_IRQ(void)
-{
-	/* Setup an irq host data structure */
-	iic_host = irq_domain_add_linear(NULL, IIC_SOURCE_COUNT, &iic_host_ops,
-					 NULL);
-	BUG_ON(iic_host == NULL);
-	irq_set_default_host(iic_host);
-
-	/* Discover and initialize iics */
-	if (setup_iic() < 0)
-		panic("IIC: Failed to initialize !\n");
-
-	/* Set master interrupt handling function */
-	ppc_md.get_irq = iic_get_irq;
-
-	/* Enable on current CPU */
-	iic_setup_cpu();
-}
-
-void iic_set_interrupt_routing(int cpu, int thread, int priority)
-{
-	struct cbe_iic_regs __iomem *iic_regs = cbe_get_cpu_iic_regs(cpu);
-	u64 iic_ir = 0;
-	int node = cpu >> 1;
-
-	/* Set which node and thread will handle the next interrupt */
-	iic_ir |= CBE_IIC_IR_PRIO(priority) |
-		  CBE_IIC_IR_DEST_NODE(node);
-	if (thread == 0)
-		iic_ir |= CBE_IIC_IR_DEST_UNIT(CBE_IIC_IR_PT_0);
-	else
-		iic_ir |= CBE_IIC_IR_DEST_UNIT(CBE_IIC_IR_PT_1);
-	out_be64(&iic_regs->iic_ir, iic_ir);
-}
diff --git a/arch/powerpc/platforms/cell/interrupt.h b/arch/powerpc/platforms/cell/interrupt.h
deleted file mode 100644
index a47902248541..000000000000
--- a/arch/powerpc/platforms/cell/interrupt.h
+++ /dev/null
@@ -1,90 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_CELL_PIC_H
-#define ASM_CELL_PIC_H
-#ifdef __KERNEL__
-/*
- * Mapping of IIC pending bits into per-node interrupt numbers.
- *
- * Interrupt numbers are in the range 0...0x1ff where the top bit
- * (0x100) represent the source node. Only 2 nodes are supported with
- * the current code though it's trivial to extend that if necessary using
- * higher level bits
- *
- * The bottom 8 bits are split into 2 type bits and 6 data bits that
- * depend on the type:
- *
- * 00 (0x00 | data) : normal interrupt. data is (class << 4) | source
- * 01 (0x40 | data) : IO exception. data is the exception number as
- *                    defined by bit numbers in IIC_SR
- * 10 (0x80 | data) : IPI. data is the IPI number (obtained from the priority)
- *                    and node is always 0 (IPIs are per-cpu, their source is
- *                    not relevant)
- * 11 (0xc0 | data) : reserved
- *
- * In addition, interrupt number 0x80000000 is defined as always invalid
- * (that is the node field is expected to never extend to move than 23 bits)
- *
- */
-
-enum {
-	IIC_IRQ_INVALID		= 0x80000000u,
-	IIC_IRQ_NODE_MASK	= 0x100,
-	IIC_IRQ_NODE_SHIFT	= 8,
-	IIC_IRQ_MAX		= 0x1ff,
-	IIC_IRQ_TYPE_MASK	= 0xc0,
-	IIC_IRQ_TYPE_NORMAL	= 0x00,
-	IIC_IRQ_TYPE_IOEXC	= 0x40,
-	IIC_IRQ_TYPE_IPI	= 0x80,
-	IIC_IRQ_CLASS_SHIFT	= 4,
-	IIC_IRQ_CLASS_0		= 0x00,
-	IIC_IRQ_CLASS_1		= 0x10,
-	IIC_IRQ_CLASS_2		= 0x20,
-	IIC_SOURCE_COUNT	= 0x200,
-
-	/* Here are defined the various source/dest units. Avoid using those
-	 * definitions if you can, they are mostly here for reference
-	 */
-	IIC_UNIT_SPU_0		= 0x4,
-	IIC_UNIT_SPU_1		= 0x7,
-	IIC_UNIT_SPU_2		= 0x3,
-	IIC_UNIT_SPU_3		= 0x8,
-	IIC_UNIT_SPU_4		= 0x2,
-	IIC_UNIT_SPU_5		= 0x9,
-	IIC_UNIT_SPU_6		= 0x1,
-	IIC_UNIT_SPU_7		= 0xa,
-	IIC_UNIT_IOC_0		= 0x0,
-	IIC_UNIT_IOC_1		= 0xb,
-	IIC_UNIT_THREAD_0	= 0xe, /* target only */
-	IIC_UNIT_THREAD_1	= 0xf, /* target only */
-	IIC_UNIT_IIC		= 0xe, /* source only (IO exceptions) */
-
-	/* Base numbers for the external interrupts */
-	IIC_IRQ_EXT_IOIF0	=
-		IIC_IRQ_TYPE_NORMAL | IIC_IRQ_CLASS_2 | IIC_UNIT_IOC_0,
-	IIC_IRQ_EXT_IOIF1	=
-		IIC_IRQ_TYPE_NORMAL | IIC_IRQ_CLASS_2 | IIC_UNIT_IOC_1,
-
-	/* Base numbers for the IIC_ISR interrupts */
-	IIC_IRQ_IOEX_TMI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 63,
-	IIC_IRQ_IOEX_PMI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 62,
-	IIC_IRQ_IOEX_ATI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 61,
-	IIC_IRQ_IOEX_MATBFI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 60,
-	IIC_IRQ_IOEX_ELDI	= IIC_IRQ_TYPE_IOEXC | IIC_IRQ_CLASS_1 | 59,
-
-	/* Which bits in IIC_ISR are edge sensitive */
-	IIC_ISR_EDGE_MASK	= 0x4ul,
-};
-
-extern void iic_init_IRQ(void);
-extern void iic_message_pass(int cpu, int msg);
-extern void iic_request_IPIs(void);
-extern void iic_setup_cpu(void);
-
-extern u8 iic_get_target_id(int cpu);
-
-extern void spider_init_IRQ(void);
-
-extern void iic_set_interrupt_routing(int cpu, int thread, int priority);
-
-#endif
-#endif /* ASM_CELL_PIC_H */
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
deleted file mode 100644
index 8c7133039566..000000000000
--- a/arch/powerpc/platforms/cell/iommu.c
+++ /dev/null
@@ -1,1094 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * IOMMU implementation for Cell Broadband Processor Architecture
- *
- * (C) Copyright IBM Corporation 2006-2008
- *
- * Author: Jeremy Kerr <jk@ozlabs.org>
- */
-
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irqdomain.h>
-#include <linux/notifier.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
-#include <linux/slab.h>
-#include <linux/memblock.h>
-
-#include <asm/prom.h>
-#include <asm/iommu.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/udbg.h>
-#include <asm/firmware.h>
-#include <asm/cell-regs.h>
-
-#include "cell.h"
-#include "interrupt.h"
-
-/* Define CELL_IOMMU_REAL_UNMAP to actually unmap non-used pages
- * instead of leaving them mapped to some dummy page. This can be
- * enabled once the appropriate workarounds for spider bugs have
- * been enabled
- */
-#define CELL_IOMMU_REAL_UNMAP
-
-/* Define CELL_IOMMU_STRICT_PROTECTION to enforce protection of
- * IO PTEs based on the transfer direction. That can be enabled
- * once spider-net has been fixed to pass the correct direction
- * to the DMA mapping functions
- */
-#define CELL_IOMMU_STRICT_PROTECTION
-
-
-#define NR_IOMMUS			2
-
-/* IOC mmap registers */
-#define IOC_Reg_Size			0x2000
-
-#define IOC_IOPT_CacheInvd		0x908
-#define IOC_IOPT_CacheInvd_NE_Mask	0xffe0000000000000ul
-#define IOC_IOPT_CacheInvd_IOPTE_Mask	0x000003fffffffff8ul
-#define IOC_IOPT_CacheInvd_Busy		0x0000000000000001ul
-
-#define IOC_IOST_Origin			0x918
-#define IOC_IOST_Origin_E		0x8000000000000000ul
-#define IOC_IOST_Origin_HW		0x0000000000000800ul
-#define IOC_IOST_Origin_HL		0x0000000000000400ul
-
-#define IOC_IO_ExcpStat			0x920
-#define IOC_IO_ExcpStat_V		0x8000000000000000ul
-#define IOC_IO_ExcpStat_SPF_Mask	0x6000000000000000ul
-#define IOC_IO_ExcpStat_SPF_S		0x6000000000000000ul
-#define IOC_IO_ExcpStat_SPF_P		0x2000000000000000ul
-#define IOC_IO_ExcpStat_ADDR_Mask	0x00000007fffff000ul
-#define IOC_IO_ExcpStat_RW_Mask		0x0000000000000800ul
-#define IOC_IO_ExcpStat_IOID_Mask	0x00000000000007fful
-
-#define IOC_IO_ExcpMask			0x928
-#define IOC_IO_ExcpMask_SFE		0x4000000000000000ul
-#define IOC_IO_ExcpMask_PFE		0x2000000000000000ul
-
-#define IOC_IOCmd_Offset		0x1000
-
-#define IOC_IOCmd_Cfg			0xc00
-#define IOC_IOCmd_Cfg_TE		0x0000800000000000ul
-
-
-/* Segment table entries */
-#define IOSTE_V			0x8000000000000000ul /* valid */
-#define IOSTE_H			0x4000000000000000ul /* cache hint */
-#define IOSTE_PT_Base_RPN_Mask  0x3ffffffffffff000ul /* base RPN of IOPT */
-#define IOSTE_NPPT_Mask		0x0000000000000fe0ul /* no. pages in IOPT */
-#define IOSTE_PS_Mask		0x0000000000000007ul /* page size */
-#define IOSTE_PS_4K		0x0000000000000001ul /*   - 4kB  */
-#define IOSTE_PS_64K		0x0000000000000003ul /*   - 64kB */
-#define IOSTE_PS_1M		0x0000000000000005ul /*   - 1MB  */
-#define IOSTE_PS_16M		0x0000000000000007ul /*   - 16MB */
-
-
-/* IOMMU sizing */
-#define IO_SEGMENT_SHIFT	28
-#define IO_PAGENO_BITS(shift)	(IO_SEGMENT_SHIFT - (shift))
-
-/* The high bit needs to be set on every DMA address */
-#define SPIDER_DMA_OFFSET	0x80000000ul
-
-struct iommu_window {
-	struct list_head list;
-	struct cbe_iommu *iommu;
-	unsigned long offset;
-	unsigned long size;
-	unsigned int ioid;
-	struct iommu_table table;
-};
-
-#define NAMESIZE 8
-struct cbe_iommu {
-	int nid;
-	char name[NAMESIZE];
-	void __iomem *xlate_regs;
-	void __iomem *cmd_regs;
-	unsigned long *stab;
-	unsigned long *ptab;
-	void *pad_page;
-	struct list_head windows;
-};
-
-/* Static array of iommus, one per node
- *   each contains a list of windows, keyed from dma_window property
- *   - on bus setup, look for a matching window, or create one
- *   - on dev setup, assign iommu_table ptr
- */
-static struct cbe_iommu iommus[NR_IOMMUS];
-static int cbe_nr_iommus;
-
-static void invalidate_tce_cache(struct cbe_iommu *iommu, unsigned long *pte,
-		long n_ptes)
-{
-	u64 __iomem *reg;
-	u64 val;
-	long n;
-
-	reg = iommu->xlate_regs + IOC_IOPT_CacheInvd;
-
-	while (n_ptes > 0) {
-		/* we can invalidate up to 1 << 11 PTEs at once */
-		n = min(n_ptes, 1l << 11);
-		val = (((n /*- 1*/) << 53) & IOC_IOPT_CacheInvd_NE_Mask)
-			| (__pa(pte) & IOC_IOPT_CacheInvd_IOPTE_Mask)
-		        | IOC_IOPT_CacheInvd_Busy;
-
-		out_be64(reg, val);
-		while (in_be64(reg) & IOC_IOPT_CacheInvd_Busy)
-			;
-
-		n_ptes -= n;
-		pte += n;
-	}
-}
-
-static int tce_build_cell(struct iommu_table *tbl, long index, long npages,
-		unsigned long uaddr, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int i;
-	unsigned long *io_pte, base_pte;
-	struct iommu_window *window =
-		container_of(tbl, struct iommu_window, table);
-
-	/* implementing proper protection causes problems with the spidernet
-	 * driver - check mapping directions later, but allow read & write by
-	 * default for now.*/
-#ifdef CELL_IOMMU_STRICT_PROTECTION
-	/* to avoid referencing a global, we use a trick here to setup the
-	 * protection bit. "prot" is setup to be 3 fields of 4 bits appended
-	 * together for each of the 3 supported direction values. It is then
-	 * shifted left so that the fields matching the desired direction
-	 * lands on the appropriate bits, and other bits are masked out.
-	 */
-	const unsigned long prot = 0xc48;
-	base_pte =
-		((prot << (52 + 4 * direction)) &
-		 (CBE_IOPTE_PP_W | CBE_IOPTE_PP_R)) |
-		CBE_IOPTE_M | CBE_IOPTE_SO_RW |
-		(window->ioid & CBE_IOPTE_IOID_Mask);
-#else
-	base_pte = CBE_IOPTE_PP_W | CBE_IOPTE_PP_R | CBE_IOPTE_M |
-		CBE_IOPTE_SO_RW | (window->ioid & CBE_IOPTE_IOID_Mask);
-#endif
-	if (unlikely(attrs & DMA_ATTR_WEAK_ORDERING))
-		base_pte &= ~CBE_IOPTE_SO_RW;
-
-	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
-
-	for (i = 0; i < npages; i++, uaddr += (1 << tbl->it_page_shift))
-		io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask);
-
-	mb();
-
-	invalidate_tce_cache(window->iommu, io_pte, npages);
-
-	pr_debug("tce_build_cell(index=%lx,n=%lx,dir=%d,base_pte=%lx)\n",
-		 index, npages, direction, base_pte);
-	return 0;
-}
-
-static void tce_free_cell(struct iommu_table *tbl, long index, long npages)
-{
-
-	int i;
-	unsigned long *io_pte, pte;
-	struct iommu_window *window =
-		container_of(tbl, struct iommu_window, table);
-
-	pr_debug("tce_free_cell(index=%lx,n=%lx)\n", index, npages);
-
-#ifdef CELL_IOMMU_REAL_UNMAP
-	pte = 0;
-#else
-	/* spider bridge does PCI reads after freeing - insert a mapping
-	 * to a scratch page instead of an invalid entry */
-	pte = CBE_IOPTE_PP_R | CBE_IOPTE_M | CBE_IOPTE_SO_RW |
-		__pa(window->iommu->pad_page) |
-		(window->ioid & CBE_IOPTE_IOID_Mask);
-#endif
-
-	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
-
-	for (i = 0; i < npages; i++)
-		io_pte[i] = pte;
-
-	mb();
-
-	invalidate_tce_cache(window->iommu, io_pte, npages);
-}
-
-static irqreturn_t ioc_interrupt(int irq, void *data)
-{
-	unsigned long stat, spf;
-	struct cbe_iommu *iommu = data;
-
-	stat = in_be64(iommu->xlate_regs + IOC_IO_ExcpStat);
-	spf = stat & IOC_IO_ExcpStat_SPF_Mask;
-
-	/* Might want to rate limit it */
-	printk(KERN_ERR "iommu: DMA exception 0x%016lx\n", stat);
-	printk(KERN_ERR "  V=%d, SPF=[%c%c], RW=%s, IOID=0x%04x\n",
-	       !!(stat & IOC_IO_ExcpStat_V),
-	       (spf == IOC_IO_ExcpStat_SPF_S) ? 'S' : ' ',
-	       (spf == IOC_IO_ExcpStat_SPF_P) ? 'P' : ' ',
-	       (stat & IOC_IO_ExcpStat_RW_Mask) ? "Read" : "Write",
-	       (unsigned int)(stat & IOC_IO_ExcpStat_IOID_Mask));
-	printk(KERN_ERR "  page=0x%016lx\n",
-	       stat & IOC_IO_ExcpStat_ADDR_Mask);
-
-	/* clear interrupt */
-	stat &= ~IOC_IO_ExcpStat_V;
-	out_be64(iommu->xlate_regs + IOC_IO_ExcpStat, stat);
-
-	return IRQ_HANDLED;
-}
-
-static int __init cell_iommu_find_ioc(int nid, unsigned long *base)
-{
-	struct device_node *np;
-	struct resource r;
-
-	*base = 0;
-
-	/* First look for new style /be nodes */
-	for_each_node_by_name(np, "ioc") {
-		if (of_node_to_nid(np) != nid)
-			continue;
-		if (of_address_to_resource(np, 0, &r)) {
-			printk(KERN_ERR "iommu: can't get address for %pOF\n",
-			       np);
-			continue;
-		}
-		*base = r.start;
-		of_node_put(np);
-		return 0;
-	}
-
-	/* Ok, let's try the old way */
-	for_each_node_by_type(np, "cpu") {
-		const unsigned int *nidp;
-		const unsigned long *tmp;
-
-		nidp = of_get_property(np, "node-id", NULL);
-		if (nidp && *nidp == nid) {
-			tmp = of_get_property(np, "ioc-translation", NULL);
-			if (tmp) {
-				*base = *tmp;
-				of_node_put(np);
-				return 0;
-			}
-		}
-	}
-
-	return -ENODEV;
-}
-
-static void __init cell_iommu_setup_stab(struct cbe_iommu *iommu,
-				unsigned long dbase, unsigned long dsize,
-				unsigned long fbase, unsigned long fsize)
-{
-	struct page *page;
-	unsigned long segments, stab_size;
-
-	segments = max(dbase + dsize, fbase + fsize) >> IO_SEGMENT_SHIFT;
-
-	pr_debug("%s: iommu[%d]: segments: %lu\n",
-			__func__, iommu->nid, segments);
-
-	/* set up the segment table */
-	stab_size = segments * sizeof(unsigned long);
-	page = alloc_pages_node(iommu->nid, GFP_KERNEL, get_order(stab_size));
-	BUG_ON(!page);
-	iommu->stab = page_address(page);
-	memset(iommu->stab, 0, stab_size);
-}
-
-static unsigned long *__init cell_iommu_alloc_ptab(struct cbe_iommu *iommu,
-		unsigned long base, unsigned long size, unsigned long gap_base,
-		unsigned long gap_size, unsigned long page_shift)
-{
-	struct page *page;
-	int i;
-	unsigned long reg, segments, pages_per_segment, ptab_size,
-		      n_pte_pages, start_seg, *ptab;
-
-	start_seg = base >> IO_SEGMENT_SHIFT;
-	segments  = size >> IO_SEGMENT_SHIFT;
-	pages_per_segment = 1ull << IO_PAGENO_BITS(page_shift);
-	/* PTEs for each segment must start on a 4K boundary */
-	pages_per_segment = max(pages_per_segment,
-				(1 << 12) / sizeof(unsigned long));
-
-	ptab_size = segments * pages_per_segment * sizeof(unsigned long);
-	pr_debug("%s: iommu[%d]: ptab_size: %lu, order: %d\n", __func__,
-			iommu->nid, ptab_size, get_order(ptab_size));
-	page = alloc_pages_node(iommu->nid, GFP_KERNEL, get_order(ptab_size));
-	BUG_ON(!page);
-
-	ptab = page_address(page);
-	memset(ptab, 0, ptab_size);
-
-	/* number of 4K pages needed for a page table */
-	n_pte_pages = (pages_per_segment * sizeof(unsigned long)) >> 12;
-
-	pr_debug("%s: iommu[%d]: stab at %p, ptab at %p, n_pte_pages: %lu\n",
-			__func__, iommu->nid, iommu->stab, ptab,
-			n_pte_pages);
-
-	/* initialise the STEs */
-	reg = IOSTE_V | ((n_pte_pages - 1) << 5);
-
-	switch (page_shift) {
-	case 12: reg |= IOSTE_PS_4K;  break;
-	case 16: reg |= IOSTE_PS_64K; break;
-	case 20: reg |= IOSTE_PS_1M;  break;
-	case 24: reg |= IOSTE_PS_16M; break;
-	default: BUG();
-	}
-
-	gap_base = gap_base >> IO_SEGMENT_SHIFT;
-	gap_size = gap_size >> IO_SEGMENT_SHIFT;
-
-	pr_debug("Setting up IOMMU stab:\n");
-	for (i = start_seg; i < (start_seg + segments); i++) {
-		if (i >= gap_base && i < (gap_base + gap_size)) {
-			pr_debug("\toverlap at %d, skipping\n", i);
-			continue;
-		}
-		iommu->stab[i] = reg | (__pa(ptab) + (n_pte_pages << 12) *
-					(i - start_seg));
-		pr_debug("\t[%d] 0x%016lx\n", i, iommu->stab[i]);
-	}
-
-	return ptab;
-}
-
-static void __init cell_iommu_enable_hardware(struct cbe_iommu *iommu)
-{
-	int ret;
-	unsigned long reg, xlate_base;
-	unsigned int virq;
-
-	if (cell_iommu_find_ioc(iommu->nid, &xlate_base))
-		panic("%s: missing IOC register mappings for node %d\n",
-		      __func__, iommu->nid);
-
-	iommu->xlate_regs = ioremap(xlate_base, IOC_Reg_Size);
-	iommu->cmd_regs = iommu->xlate_regs + IOC_IOCmd_Offset;
-
-	/* ensure that the STEs have updated */
-	mb();
-
-	/* setup interrupts for the iommu. */
-	reg = in_be64(iommu->xlate_regs + IOC_IO_ExcpStat);
-	out_be64(iommu->xlate_regs + IOC_IO_ExcpStat,
-			reg & ~IOC_IO_ExcpStat_V);
-	out_be64(iommu->xlate_regs + IOC_IO_ExcpMask,
-			IOC_IO_ExcpMask_PFE | IOC_IO_ExcpMask_SFE);
-
-	virq = irq_create_mapping(NULL,
-			IIC_IRQ_IOEX_ATI | (iommu->nid << IIC_IRQ_NODE_SHIFT));
-	BUG_ON(!virq);
-
-	ret = request_irq(virq, ioc_interrupt, 0, iommu->name, iommu);
-	BUG_ON(ret);
-
-	/* set the IOC segment table origin register (and turn on the iommu) */
-	reg = IOC_IOST_Origin_E | __pa(iommu->stab) | IOC_IOST_Origin_HW;
-	out_be64(iommu->xlate_regs + IOC_IOST_Origin, reg);
-	in_be64(iommu->xlate_regs + IOC_IOST_Origin);
-
-	/* turn on IO translation */
-	reg = in_be64(iommu->cmd_regs + IOC_IOCmd_Cfg) | IOC_IOCmd_Cfg_TE;
-	out_be64(iommu->cmd_regs + IOC_IOCmd_Cfg, reg);
-}
-
-static void __init cell_iommu_setup_hardware(struct cbe_iommu *iommu,
-	unsigned long base, unsigned long size)
-{
-	cell_iommu_setup_stab(iommu, base, size, 0, 0);
-	iommu->ptab = cell_iommu_alloc_ptab(iommu, base, size, 0, 0,
-					    IOMMU_PAGE_SHIFT_4K);
-	cell_iommu_enable_hardware(iommu);
-}
-
-#if 0/* Unused for now */
-static struct iommu_window *find_window(struct cbe_iommu *iommu,
-		unsigned long offset, unsigned long size)
-{
-	struct iommu_window *window;
-
-	/* todo: check for overlapping (but not equal) windows) */
-
-	list_for_each_entry(window, &(iommu->windows), list) {
-		if (window->offset == offset && window->size == size)
-			return window;
-	}
-
-	return NULL;
-}
-#endif
-
-static inline u32 cell_iommu_get_ioid(struct device_node *np)
-{
-	const u32 *ioid;
-
-	ioid = of_get_property(np, "ioid", NULL);
-	if (ioid == NULL) {
-		printk(KERN_WARNING "iommu: missing ioid for %pOF using 0\n",
-		       np);
-		return 0;
-	}
-
-	return *ioid;
-}
-
-static struct iommu_table_ops cell_iommu_ops = {
-	.set = tce_build_cell,
-	.clear = tce_free_cell
-};
-
-static struct iommu_window * __init
-cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
-			unsigned long offset, unsigned long size,
-			unsigned long pte_offset)
-{
-	struct iommu_window *window;
-	struct page *page;
-	u32 ioid;
-
-	ioid = cell_iommu_get_ioid(np);
-
-	window = kzalloc_node(sizeof(*window), GFP_KERNEL, iommu->nid);
-	BUG_ON(window == NULL);
-
-	window->offset = offset;
-	window->size = size;
-	window->ioid = ioid;
-	window->iommu = iommu;
-
-	window->table.it_blocksize = 16;
-	window->table.it_base = (unsigned long)iommu->ptab;
-	window->table.it_index = iommu->nid;
-	window->table.it_page_shift = IOMMU_PAGE_SHIFT_4K;
-	window->table.it_offset =
-		(offset >> window->table.it_page_shift) + pte_offset;
-	window->table.it_size = size >> window->table.it_page_shift;
-	window->table.it_ops = &cell_iommu_ops;
-
-	if (!iommu_init_table(&window->table, iommu->nid, 0, 0))
-		panic("Failed to initialize iommu table");
-
-	pr_debug("\tioid      %d\n", window->ioid);
-	pr_debug("\tblocksize %ld\n", window->table.it_blocksize);
-	pr_debug("\tbase      0x%016lx\n", window->table.it_base);
-	pr_debug("\toffset    0x%lx\n", window->table.it_offset);
-	pr_debug("\tsize      %ld\n", window->table.it_size);
-
-	list_add(&window->list, &iommu->windows);
-
-	if (offset != 0)
-		return window;
-
-	/* We need to map and reserve the first IOMMU page since it's used
-	 * by the spider workaround. In theory, we only need to do that when
-	 * running on spider but it doesn't really matter.
-	 *
-	 * This code also assumes that we have a window that starts at 0,
-	 * which is the case on all spider based blades.
-	 */
-	page = alloc_pages_node(iommu->nid, GFP_KERNEL, 0);
-	BUG_ON(!page);
-	iommu->pad_page = page_address(page);
-	clear_page(iommu->pad_page);
-
-	__set_bit(0, window->table.it_map);
-	tce_build_cell(&window->table, window->table.it_offset, 1,
-		       (unsigned long)iommu->pad_page, DMA_TO_DEVICE, 0);
-
-	return window;
-}
-
-static struct cbe_iommu *cell_iommu_for_node(int nid)
-{
-	int i;
-
-	for (i = 0; i < cbe_nr_iommus; i++)
-		if (iommus[i].nid == nid)
-			return &iommus[i];
-	return NULL;
-}
-
-static unsigned long cell_dma_nommu_offset;
-
-static unsigned long dma_iommu_fixed_base;
-static bool cell_iommu_enabled;
-
-/* iommu_fixed_is_weak is set if booted with iommu_fixed=weak */
-bool iommu_fixed_is_weak;
-
-static struct iommu_table *cell_get_iommu_table(struct device *dev)
-{
-	struct iommu_window *window;
-	struct cbe_iommu *iommu;
-
-	/* Current implementation uses the first window available in that
-	 * node's iommu. We -might- do something smarter later though it may
-	 * never be necessary
-	 */
-	iommu = cell_iommu_for_node(dev_to_node(dev));
-	if (iommu == NULL || list_empty(&iommu->windows)) {
-		dev_err(dev, "iommu: missing iommu for %pOF (node %d)\n",
-		       dev->of_node, dev_to_node(dev));
-		return NULL;
-	}
-	window = list_entry(iommu->windows.next, struct iommu_window, list);
-
-	return &window->table;
-}
-
-static u64 cell_iommu_get_fixed_address(struct device *dev);
-
-static void cell_dma_dev_setup(struct device *dev)
-{
-	if (cell_iommu_enabled) {
-		u64 addr = cell_iommu_get_fixed_address(dev);
-
-		if (addr != OF_BAD_ADDR)
-			dev->archdata.dma_offset = addr + dma_iommu_fixed_base;
-		set_iommu_table_base(dev, cell_get_iommu_table(dev));
-	} else {
-		dev->archdata.dma_offset = cell_dma_nommu_offset;
-	}
-}
-
-static void cell_pci_dma_dev_setup(struct pci_dev *dev)
-{
-	cell_dma_dev_setup(&dev->dev);
-}
-
-static int cell_of_bus_notify(struct notifier_block *nb, unsigned long action,
-			      void *data)
-{
-	struct device *dev = data;
-
-	/* We are only interested in device addition */
-	if (action != BUS_NOTIFY_ADD_DEVICE)
-		return 0;
-
-	if (cell_iommu_enabled)
-		dev->dma_ops = &dma_iommu_ops;
-	cell_dma_dev_setup(dev);
-	return 0;
-}
-
-static struct notifier_block cell_of_bus_notifier = {
-	.notifier_call = cell_of_bus_notify
-};
-
-static int __init cell_iommu_get_window(struct device_node *np,
-					 unsigned long *base,
-					 unsigned long *size)
-{
-	const __be32 *dma_window;
-	unsigned long index;
-
-	/* Use ibm,dma-window if available, else, hard code ! */
-	dma_window = of_get_property(np, "ibm,dma-window", NULL);
-	if (dma_window == NULL) {
-		*base = 0;
-		*size = 0x80000000u;
-		return -ENODEV;
-	}
-
-	of_parse_dma_window(np, dma_window, &index, base, size);
-	return 0;
-}
-
-static struct cbe_iommu * __init cell_iommu_alloc(struct device_node *np)
-{
-	struct cbe_iommu *iommu;
-	int nid, i;
-
-	/* Get node ID */
-	nid = of_node_to_nid(np);
-	if (nid < 0) {
-		printk(KERN_ERR "iommu: failed to get node for %pOF\n",
-		       np);
-		return NULL;
-	}
-	pr_debug("iommu: setting up iommu for node %d (%pOF)\n",
-		 nid, np);
-
-	/* XXX todo: If we can have multiple windows on the same IOMMU, which
-	 * isn't the case today, we probably want here to check whether the
-	 * iommu for that node is already setup.
-	 * However, there might be issue with getting the size right so let's
-	 * ignore that for now. We might want to completely get rid of the
-	 * multiple window support since the cell iommu supports per-page ioids
-	 */
-
-	if (cbe_nr_iommus >= NR_IOMMUS) {
-		printk(KERN_ERR "iommu: too many IOMMUs detected ! (%pOF)\n",
-		       np);
-		return NULL;
-	}
-
-	/* Init base fields */
-	i = cbe_nr_iommus++;
-	iommu = &iommus[i];
-	iommu->stab = NULL;
-	iommu->nid = nid;
-	snprintf(iommu->name, sizeof(iommu->name), "iommu%d", i);
-	INIT_LIST_HEAD(&iommu->windows);
-
-	return iommu;
-}
-
-static void __init cell_iommu_init_one(struct device_node *np,
-				       unsigned long offset)
-{
-	struct cbe_iommu *iommu;
-	unsigned long base, size;
-
-	iommu = cell_iommu_alloc(np);
-	if (!iommu)
-		return;
-
-	/* Obtain a window for it */
-	cell_iommu_get_window(np, &base, &size);
-
-	pr_debug("\ttranslating window 0x%lx...0x%lx\n",
-		 base, base + size - 1);
-
-	/* Initialize the hardware */
-	cell_iommu_setup_hardware(iommu, base, size);
-
-	/* Setup the iommu_table */
-	cell_iommu_setup_window(iommu, np, base, size,
-				offset >> IOMMU_PAGE_SHIFT_4K);
-}
-
-static void __init cell_disable_iommus(void)
-{
-	int node;
-	unsigned long base, val;
-	void __iomem *xregs, *cregs;
-
-	/* Make sure IOC translation is disabled on all nodes */
-	for_each_online_node(node) {
-		if (cell_iommu_find_ioc(node, &base))
-			continue;
-		xregs = ioremap(base, IOC_Reg_Size);
-		if (xregs == NULL)
-			continue;
-		cregs = xregs + IOC_IOCmd_Offset;
-
-		pr_debug("iommu: cleaning up iommu on node %d\n", node);
-
-		out_be64(xregs + IOC_IOST_Origin, 0);
-		(void)in_be64(xregs + IOC_IOST_Origin);
-		val = in_be64(cregs + IOC_IOCmd_Cfg);
-		val &= ~IOC_IOCmd_Cfg_TE;
-		out_be64(cregs + IOC_IOCmd_Cfg, val);
-		(void)in_be64(cregs + IOC_IOCmd_Cfg);
-
-		iounmap(xregs);
-	}
-}
-
-static int __init cell_iommu_init_disabled(void)
-{
-	struct device_node *np = NULL;
-	unsigned long base = 0, size;
-
-	/* When no iommu is present, we use direct DMA ops */
-
-	/* First make sure all IOC translation is turned off */
-	cell_disable_iommus();
-
-	/* If we have no Axon, we set up the spider DMA magic offset */
-	np = of_find_node_by_name(NULL, "axon");
-	if (!np)
-		cell_dma_nommu_offset = SPIDER_DMA_OFFSET;
-	of_node_put(np);
-
-	/* Now we need to check to see where the memory is mapped
-	 * in PCI space. We assume that all busses use the same dma
-	 * window which is always the case so far on Cell, thus we
-	 * pick up the first pci-internal node we can find and check
-	 * the DMA window from there.
-	 */
-	for_each_node_by_name(np, "axon") {
-		if (np->parent == NULL || np->parent->parent != NULL)
-			continue;
-		if (cell_iommu_get_window(np, &base, &size) == 0)
-			break;
-	}
-	if (np == NULL) {
-		for_each_node_by_name(np, "pci-internal") {
-			if (np->parent == NULL || np->parent->parent != NULL)
-				continue;
-			if (cell_iommu_get_window(np, &base, &size) == 0)
-				break;
-		}
-	}
-	of_node_put(np);
-
-	/* If we found a DMA window, we check if it's big enough to enclose
-	 * all of physical memory. If not, we force enable IOMMU
-	 */
-	if (np && size < memblock_end_of_DRAM()) {
-		printk(KERN_WARNING "iommu: force-enabled, dma window"
-		       " (%ldMB) smaller than total memory (%lldMB)\n",
-		       size >> 20, memblock_end_of_DRAM() >> 20);
-		return -ENODEV;
-	}
-
-	cell_dma_nommu_offset += base;
-
-	if (cell_dma_nommu_offset != 0)
-		cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
-
-	printk("iommu: disabled, direct DMA offset is 0x%lx\n",
-	       cell_dma_nommu_offset);
-
-	return 0;
-}
-
-/*
- *  Fixed IOMMU mapping support
- *
- *  This code adds support for setting up a fixed IOMMU mapping on certain
- *  cell machines. For 64-bit devices this avoids the performance overhead of
- *  mapping and unmapping pages at runtime. 32-bit devices are unable to use
- *  the fixed mapping.
- *
- *  The fixed mapping is established at boot, and maps all of physical memory
- *  1:1 into device space at some offset. On machines with < 30 GB of memory
- *  we setup the fixed mapping immediately above the normal IOMMU window.
- *
- *  For example a machine with 4GB of memory would end up with the normal
- *  IOMMU window from 0-2GB and the fixed mapping window from 2GB to 6GB. In
- *  this case a 64-bit device wishing to DMA to 1GB would be told to DMA to
- *  3GB, plus any offset required by firmware. The firmware offset is encoded
- *  in the "dma-ranges" property.
- *
- *  On machines with 30GB or more of memory, we are unable to place the fixed
- *  mapping above the normal IOMMU window as we would run out of address space.
- *  Instead we move the normal IOMMU window to coincide with the hash page
- *  table, this region does not need to be part of the fixed mapping as no
- *  device should ever be DMA'ing to it. We then setup the fixed mapping
- *  from 0 to 32GB.
- */
-
-static u64 cell_iommu_get_fixed_address(struct device *dev)
-{
-	u64 cpu_addr, size, best_size, dev_addr = OF_BAD_ADDR;
-	struct device_node *np;
-	const u32 *ranges = NULL;
-	int i, len, best, naddr, nsize, pna, range_size;
-
-	/* We can be called for platform devices that have no of_node */
-	np = of_node_get(dev->of_node);
-	if (!np)
-		goto out;
-
-	while (1) {
-		naddr = of_n_addr_cells(np);
-		nsize = of_n_size_cells(np);
-		np = of_get_next_parent(np);
-		if (!np)
-			break;
-
-		ranges = of_get_property(np, "dma-ranges", &len);
-
-		/* Ignore empty ranges, they imply no translation required */
-		if (ranges && len > 0)
-			break;
-	}
-
-	if (!ranges) {
-		dev_dbg(dev, "iommu: no dma-ranges found\n");
-		goto out;
-	}
-
-	len /= sizeof(u32);
-
-	pna = of_n_addr_cells(np);
-	range_size = naddr + nsize + pna;
-
-	/* dma-ranges format:
-	 * child addr	: naddr cells
-	 * parent addr	: pna cells
-	 * size		: nsize cells
-	 */
-	for (i = 0, best = -1, best_size = 0; i < len; i += range_size) {
-		cpu_addr = of_translate_dma_address(np, ranges + i + naddr);
-		size = of_read_number(ranges + i + naddr + pna, nsize);
-
-		if (cpu_addr == 0 && size > best_size) {
-			best = i;
-			best_size = size;
-		}
-	}
-
-	if (best >= 0) {
-		dev_addr = of_read_number(ranges + best, naddr);
-	} else
-		dev_dbg(dev, "iommu: no suitable range found!\n");
-
-out:
-	of_node_put(np);
-
-	return dev_addr;
-}
-
-static bool cell_pci_iommu_bypass_supported(struct pci_dev *pdev, u64 mask)
-{
-	return mask == DMA_BIT_MASK(64) &&
-		cell_iommu_get_fixed_address(&pdev->dev) != OF_BAD_ADDR;
-}
-
-static void __init insert_16M_pte(unsigned long addr, unsigned long *ptab,
-			   unsigned long base_pte)
-{
-	unsigned long segment, offset;
-
-	segment = addr >> IO_SEGMENT_SHIFT;
-	offset = (addr >> 24) - (segment << IO_PAGENO_BITS(24));
-	ptab = ptab + (segment * (1 << 12) / sizeof(unsigned long));
-
-	pr_debug("iommu: addr %lx ptab %p segment %lx offset %lx\n",
-		  addr, ptab, segment, offset);
-
-	ptab[offset] = base_pte | (__pa(addr) & CBE_IOPTE_RPN_Mask);
-}
-
-static void __init cell_iommu_setup_fixed_ptab(struct cbe_iommu *iommu,
-	struct device_node *np, unsigned long dbase, unsigned long dsize,
-	unsigned long fbase, unsigned long fsize)
-{
-	unsigned long base_pte, uaddr, ioaddr, *ptab;
-
-	ptab = cell_iommu_alloc_ptab(iommu, fbase, fsize, dbase, dsize, 24);
-
-	dma_iommu_fixed_base = fbase;
-
-	pr_debug("iommu: mapping 0x%lx pages from 0x%lx\n", fsize, fbase);
-
-	base_pte = CBE_IOPTE_PP_W | CBE_IOPTE_PP_R | CBE_IOPTE_M |
-		(cell_iommu_get_ioid(np) & CBE_IOPTE_IOID_Mask);
-
-	if (iommu_fixed_is_weak)
-		pr_info("IOMMU: Using weak ordering for fixed mapping\n");
-	else {
-		pr_info("IOMMU: Using strong ordering for fixed mapping\n");
-		base_pte |= CBE_IOPTE_SO_RW;
-	}
-
-	for (uaddr = 0; uaddr < fsize; uaddr += (1 << 24)) {
-		/* Don't touch the dynamic region */
-		ioaddr = uaddr + fbase;
-		if (ioaddr >= dbase && ioaddr < (dbase + dsize)) {
-			pr_debug("iommu: fixed/dynamic overlap, skipping\n");
-			continue;
-		}
-
-		insert_16M_pte(uaddr, ptab, base_pte);
-	}
-
-	mb();
-}
-
-static int __init cell_iommu_fixed_mapping_init(void)
-{
-	unsigned long dbase, dsize, fbase, fsize, hbase, hend;
-	struct cbe_iommu *iommu;
-	struct device_node *np;
-
-	/* The fixed mapping is only supported on axon machines */
-	np = of_find_node_by_name(NULL, "axon");
-	of_node_put(np);
-
-	if (!np) {
-		pr_debug("iommu: fixed mapping disabled, no axons found\n");
-		return -1;
-	}
-
-	/* We must have dma-ranges properties for fixed mapping to work */
-	np = of_find_node_with_property(NULL, "dma-ranges");
-	of_node_put(np);
-
-	if (!np) {
-		pr_debug("iommu: no dma-ranges found, no fixed mapping\n");
-		return -1;
-	}
-
-	/* The default setup is to have the fixed mapping sit after the
-	 * dynamic region, so find the top of the largest IOMMU window
-	 * on any axon, then add the size of RAM and that's our max value.
-	 * If that is > 32GB we have to do other shennanigans.
-	 */
-	fbase = 0;
-	for_each_node_by_name(np, "axon") {
-		cell_iommu_get_window(np, &dbase, &dsize);
-		fbase = max(fbase, dbase + dsize);
-	}
-
-	fbase = ALIGN(fbase, 1 << IO_SEGMENT_SHIFT);
-	fsize = memblock_phys_mem_size();
-
-	if ((fbase + fsize) <= 0x800000000ul)
-		hbase = 0; /* use the device tree window */
-	else {
-		/* If we're over 32 GB we need to cheat. We can't map all of
-		 * RAM with the fixed mapping, and also fit the dynamic
-		 * region. So try to place the dynamic region where the hash
-		 * table sits, drivers never need to DMA to it, we don't
-		 * need a fixed mapping for that area.
-		 */
-		if (!htab_address) {
-			pr_debug("iommu: htab is NULL, on LPAR? Huh?\n");
-			return -1;
-		}
-		hbase = __pa(htab_address);
-		hend  = hbase + htab_size_bytes;
-
-		/* The window must start and end on a segment boundary */
-		if ((hbase != ALIGN(hbase, 1 << IO_SEGMENT_SHIFT)) ||
-		    (hend != ALIGN(hend, 1 << IO_SEGMENT_SHIFT))) {
-			pr_debug("iommu: hash window not segment aligned\n");
-			return -1;
-		}
-
-		/* Check the hash window fits inside the real DMA window */
-		for_each_node_by_name(np, "axon") {
-			cell_iommu_get_window(np, &dbase, &dsize);
-
-			if (hbase < dbase || (hend > (dbase + dsize))) {
-				pr_debug("iommu: hash window doesn't fit in"
-					 "real DMA window\n");
-				of_node_put(np);
-				return -1;
-			}
-		}
-
-		fbase = 0;
-	}
-
-	/* Setup the dynamic regions */
-	for_each_node_by_name(np, "axon") {
-		iommu = cell_iommu_alloc(np);
-		BUG_ON(!iommu);
-
-		if (hbase == 0)
-			cell_iommu_get_window(np, &dbase, &dsize);
-		else {
-			dbase = hbase;
-			dsize = htab_size_bytes;
-		}
-
-		printk(KERN_DEBUG "iommu: node %d, dynamic window 0x%lx-0x%lx "
-			"fixed window 0x%lx-0x%lx\n", iommu->nid, dbase,
-			 dbase + dsize, fbase, fbase + fsize);
-
-		cell_iommu_setup_stab(iommu, dbase, dsize, fbase, fsize);
-		iommu->ptab = cell_iommu_alloc_ptab(iommu, dbase, dsize, 0, 0,
-						    IOMMU_PAGE_SHIFT_4K);
-		cell_iommu_setup_fixed_ptab(iommu, np, dbase, dsize,
-					     fbase, fsize);
-		cell_iommu_enable_hardware(iommu);
-		cell_iommu_setup_window(iommu, np, dbase, dsize, 0);
-	}
-
-	cell_pci_controller_ops.iommu_bypass_supported =
-		cell_pci_iommu_bypass_supported;
-	return 0;
-}
-
-static int iommu_fixed_disabled;
-
-static int __init setup_iommu_fixed(char *str)
-{
-	struct device_node *pciep;
-
-	if (strcmp(str, "off") == 0)
-		iommu_fixed_disabled = 1;
-
-	/* If we can find a pcie-endpoint in the device tree assume that
-	 * we're on a triblade or a CAB so by default the fixed mapping
-	 * should be set to be weakly ordered; but only if the boot
-	 * option WASN'T set for strong ordering
-	 */
-	pciep = of_find_node_by_type(NULL, "pcie-endpoint");
-
-	if (strcmp(str, "weak") == 0 || (pciep && strcmp(str, "strong") != 0))
-		iommu_fixed_is_weak = true;
-
-	of_node_put(pciep);
-
-	return 1;
-}
-__setup("iommu_fixed=", setup_iommu_fixed);
-
-static int __init cell_iommu_init(void)
-{
-	struct device_node *np;
-
-	/* If IOMMU is disabled or we have little enough RAM to not need
-	 * to enable it, we setup a direct mapping.
-	 *
-	 * Note: should we make sure we have the IOMMU actually disabled ?
-	 */
-	if (iommu_is_off ||
-	    (!iommu_force_on && memblock_end_of_DRAM() <= 0x80000000ull))
-		if (cell_iommu_init_disabled() == 0)
-			goto bail;
-
-	/* Setup various callbacks */
-	cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
-
-	if (!iommu_fixed_disabled && cell_iommu_fixed_mapping_init() == 0)
-		goto done;
-
-	/* Create an iommu for each /axon node.  */
-	for_each_node_by_name(np, "axon") {
-		if (np->parent == NULL || np->parent->parent != NULL)
-			continue;
-		cell_iommu_init_one(np, 0);
-	}
-
-	/* Create an iommu for each toplevel /pci-internal node for
-	 * old hardware/firmware
-	 */
-	for_each_node_by_name(np, "pci-internal") {
-		if (np->parent == NULL || np->parent->parent != NULL)
-			continue;
-		cell_iommu_init_one(np, SPIDER_DMA_OFFSET);
-	}
- done:
-	/* Setup default PCI iommu ops */
-	set_pci_dma_ops(&dma_iommu_ops);
-	cell_iommu_enabled = true;
- bail:
-	/* Register callbacks on OF platform device addition/removal
-	 * to handle linking them to the right DMA operations
-	 */
-	bus_register_notifier(&platform_bus_type, &cell_of_bus_notifier);
-
-	return 0;
-}
-machine_arch_initcall(cell, cell_iommu_init);
diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c
deleted file mode 100644
index 58d967ee38b3..000000000000
--- a/arch/powerpc/platforms/cell/pervasive.c
+++ /dev/null
@@ -1,125 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * CBE Pervasive Monitor and Debug
- *
- * (C) Copyright IBM Corporation 2005
- *
- * Authors: Maximino Aguilar (maguilar@us.ibm.com)
- *          Michael N. Day (mnday@us.ibm.com)
- */
-
-#undef DEBUG
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/percpu.h>
-#include <linux/types.h>
-#include <linux/kallsyms.h>
-#include <linux/pgtable.h>
-
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/reg.h>
-#include <asm/cell-regs.h>
-#include <asm/cpu_has_feature.h>
-
-#include "pervasive.h"
-#include "ras.h"
-
-static void cbe_power_save(void)
-{
-	unsigned long ctrl, thread_switch_control;
-
-	/* Ensure our interrupt state is properly tracked */
-	if (!prep_irq_for_idle())
-		return;
-
-	ctrl = mfspr(SPRN_CTRLF);
-
-	/* Enable DEC and EE interrupt request */
-	thread_switch_control  = mfspr(SPRN_TSC_CELL);
-	thread_switch_control |= TSC_CELL_EE_ENABLE | TSC_CELL_EE_BOOST;
-
-	switch (ctrl & CTRL_CT) {
-	case CTRL_CT0:
-		thread_switch_control |= TSC_CELL_DEC_ENABLE_0;
-		break;
-	case CTRL_CT1:
-		thread_switch_control |= TSC_CELL_DEC_ENABLE_1;
-		break;
-	default:
-		printk(KERN_WARNING "%s: unknown configuration\n",
-			__func__);
-		break;
-	}
-	mtspr(SPRN_TSC_CELL, thread_switch_control);
-
-	/*
-	 * go into low thread priority, medium priority will be
-	 * restored for us after wake-up.
-	 */
-	HMT_low();
-
-	/*
-	 * atomically disable thread execution and runlatch.
-	 * External and Decrementer exceptions are still handled when the
-	 * thread is disabled but now enter in cbe_system_reset_exception()
-	 */
-	ctrl &= ~(CTRL_RUNLATCH | CTRL_TE);
-	mtspr(SPRN_CTRLT, ctrl);
-
-	/* Re-enable interrupts in MSR */
-	__hard_irq_enable();
-}
-
-static int cbe_system_reset_exception(struct pt_regs *regs)
-{
-	switch (regs->msr & SRR1_WAKEMASK) {
-	case SRR1_WAKEDEC:
-		set_dec(1);
-		break;
-	case SRR1_WAKEEE:
-		/*
-		 * Handle these when interrupts get re-enabled and we take
-		 * them as regular exceptions. We are in an NMI context
-		 * and can't handle these here.
-		 */
-		break;
-	case SRR1_WAKEMT:
-		return cbe_sysreset_hack();
-#ifdef CONFIG_CBE_RAS
-	case SRR1_WAKESYSERR:
-		cbe_system_error_exception(regs);
-		break;
-	case SRR1_WAKETHERM:
-		cbe_thermal_exception(regs);
-		break;
-#endif /* CONFIG_CBE_RAS */
-	default:
-		/* do system reset */
-		return 0;
-	}
-	/* everything handled */
-	return 1;
-}
-
-void __init cbe_pervasive_init(void)
-{
-	int cpu;
-
-	if (!cpu_has_feature(CPU_FTR_PAUSE_ZERO))
-		return;
-
-	for_each_possible_cpu(cpu) {
-		struct cbe_pmd_regs __iomem *regs = cbe_get_cpu_pmd_regs(cpu);
-		if (!regs)
-			continue;
-
-		 /* Enable Pause(0) control bit */
-		out_be64(&regs->pmcr, in_be64(&regs->pmcr) |
-					    CBE_PMD_PAUSE_ZERO_CONTROL);
-	}
-
-	ppc_md.power_save = cbe_power_save;
-	ppc_md.system_reset_exception = cbe_system_reset_exception;
-}
diff --git a/arch/powerpc/platforms/cell/pervasive.h b/arch/powerpc/platforms/cell/pervasive.h
deleted file mode 100644
index 0da74ab10716..000000000000
--- a/arch/powerpc/platforms/cell/pervasive.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Cell Pervasive Monitor and Debug interface and HW structures
- *
- * (C) Copyright IBM Corporation 2005
- *
- * Authors: Maximino Aguilar (maguilar@us.ibm.com)
- *          David J. Erb (djerb@us.ibm.com)
- */
-
-
-#ifndef PERVASIVE_H
-#define PERVASIVE_H
-
-extern void cbe_pervasive_init(void);
-
-#ifdef CONFIG_PPC_IBM_CELL_RESETBUTTON
-extern int cbe_sysreset_hack(void);
-#else
-static inline int cbe_sysreset_hack(void)
-{
-	return 1;
-}
-#endif /* CONFIG_PPC_IBM_CELL_RESETBUTTON */
-
-#endif
diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c
deleted file mode 100644
index b207a7f99be5..000000000000
--- a/arch/powerpc/platforms/cell/pmu.c
+++ /dev/null
@@ -1,412 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cell Broadband Engine Performance Monitor
- *
- * (C) Copyright IBM Corporation 2001,2006
- *
- * Author:
- *    David Erb (djerb@us.ibm.com)
- *    Kevin Corry (kevcorry@us.ibm.com)
- */
-
-#include <linux/interrupt.h>
-#include <linux/irqdomain.h>
-#include <linux/types.h>
-#include <linux/export.h>
-#include <asm/io.h>
-#include <asm/irq_regs.h>
-#include <asm/machdep.h>
-#include <asm/pmc.h>
-#include <asm/reg.h>
-#include <asm/spu.h>
-#include <asm/cell-regs.h>
-
-#include "interrupt.h"
-
-/*
- * When writing to write-only mmio addresses, save a shadow copy. All of the
- * registers are 32-bit, but stored in the upper-half of a 64-bit field in
- * pmd_regs.
- */
-
-#define WRITE_WO_MMIO(reg, x)					\
-	do {							\
-		u32 _x = (x);					\
-		struct cbe_pmd_regs __iomem *pmd_regs;		\
-		struct cbe_pmd_shadow_regs *shadow_regs;	\
-		pmd_regs = cbe_get_cpu_pmd_regs(cpu);		\
-		shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);	\
-		out_be64(&(pmd_regs->reg), (((u64)_x) << 32));	\
-		shadow_regs->reg = _x;				\
-	} while (0)
-
-#define READ_SHADOW_REG(val, reg)				\
-	do {							\
-		struct cbe_pmd_shadow_regs *shadow_regs;	\
-		shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);	\
-		(val) = shadow_regs->reg;			\
-	} while (0)
-
-#define READ_MMIO_UPPER32(val, reg)				\
-	do {							\
-		struct cbe_pmd_regs __iomem *pmd_regs;		\
-		pmd_regs = cbe_get_cpu_pmd_regs(cpu);		\
-		(val) = (u32)(in_be64(&pmd_regs->reg) >> 32);	\
-	} while (0)
-
-/*
- * Physical counter registers.
- * Each physical counter can act as one 32-bit counter or two 16-bit counters.
- */
-
-u32 cbe_read_phys_ctr(u32 cpu, u32 phys_ctr)
-{
-	u32 val_in_latch, val = 0;
-
-	if (phys_ctr < NR_PHYS_CTRS) {
-		READ_SHADOW_REG(val_in_latch, counter_value_in_latch);
-
-		/* Read the latch or the actual counter, whichever is newer. */
-		if (val_in_latch & (1 << phys_ctr)) {
-			READ_SHADOW_REG(val, pm_ctr[phys_ctr]);
-		} else {
-			READ_MMIO_UPPER32(val, pm_ctr[phys_ctr]);
-		}
-	}
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(cbe_read_phys_ctr);
-
-void cbe_write_phys_ctr(u32 cpu, u32 phys_ctr, u32 val)
-{
-	struct cbe_pmd_shadow_regs *shadow_regs;
-	u32 pm_ctrl;
-
-	if (phys_ctr < NR_PHYS_CTRS) {
-		/* Writing to a counter only writes to a hardware latch.
-		 * The new value is not propagated to the actual counter
-		 * until the performance monitor is enabled.
-		 */
-		WRITE_WO_MMIO(pm_ctr[phys_ctr], val);
-
-		pm_ctrl = cbe_read_pm(cpu, pm_control);
-		if (pm_ctrl & CBE_PM_ENABLE_PERF_MON) {
-			/* The counters are already active, so we need to
-			 * rewrite the pm_control register to "re-enable"
-			 * the PMU.
-			 */
-			cbe_write_pm(cpu, pm_control, pm_ctrl);
-		} else {
-			shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);
-			shadow_regs->counter_value_in_latch |= (1 << phys_ctr);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(cbe_write_phys_ctr);
-
-/*
- * "Logical" counter registers.
- * These will read/write 16-bits or 32-bits depending on the
- * current size of the counter. Counters 4 - 7 are always 16-bit.
- */
-
-u32 cbe_read_ctr(u32 cpu, u32 ctr)
-{
-	u32 val;
-	u32 phys_ctr = ctr & (NR_PHYS_CTRS - 1);
-
-	val = cbe_read_phys_ctr(cpu, phys_ctr);
-
-	if (cbe_get_ctr_size(cpu, phys_ctr) == 16)
-		val = (ctr < NR_PHYS_CTRS) ? (val >> 16) : (val & 0xffff);
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(cbe_read_ctr);
-
-void cbe_write_ctr(u32 cpu, u32 ctr, u32 val)
-{
-	u32 phys_ctr;
-	u32 phys_val;
-
-	phys_ctr = ctr & (NR_PHYS_CTRS - 1);
-
-	if (cbe_get_ctr_size(cpu, phys_ctr) == 16) {
-		phys_val = cbe_read_phys_ctr(cpu, phys_ctr);
-
-		if (ctr < NR_PHYS_CTRS)
-			val = (val << 16) | (phys_val & 0xffff);
-		else
-			val = (val & 0xffff) | (phys_val & 0xffff0000);
-	}
-
-	cbe_write_phys_ctr(cpu, phys_ctr, val);
-}
-EXPORT_SYMBOL_GPL(cbe_write_ctr);
-
-/*
- * Counter-control registers.
- * Each "logical" counter has a corresponding control register.
- */
-
-u32 cbe_read_pm07_control(u32 cpu, u32 ctr)
-{
-	u32 pm07_control = 0;
-
-	if (ctr < NR_CTRS)
-		READ_SHADOW_REG(pm07_control, pm07_control[ctr]);
-
-	return pm07_control;
-}
-EXPORT_SYMBOL_GPL(cbe_read_pm07_control);
-
-void cbe_write_pm07_control(u32 cpu, u32 ctr, u32 val)
-{
-	if (ctr < NR_CTRS)
-		WRITE_WO_MMIO(pm07_control[ctr], val);
-}
-EXPORT_SYMBOL_GPL(cbe_write_pm07_control);
-
-/*
- * Other PMU control registers. Most of these are write-only.
- */
-
-u32 cbe_read_pm(u32 cpu, enum pm_reg_name reg)
-{
-	u32 val = 0;
-
-	switch (reg) {
-	case group_control:
-		READ_SHADOW_REG(val, group_control);
-		break;
-
-	case debug_bus_control:
-		READ_SHADOW_REG(val, debug_bus_control);
-		break;
-
-	case trace_address:
-		READ_MMIO_UPPER32(val, trace_address);
-		break;
-
-	case ext_tr_timer:
-		READ_SHADOW_REG(val, ext_tr_timer);
-		break;
-
-	case pm_status:
-		READ_MMIO_UPPER32(val, pm_status);
-		break;
-
-	case pm_control:
-		READ_SHADOW_REG(val, pm_control);
-		break;
-
-	case pm_interval:
-		READ_MMIO_UPPER32(val, pm_interval);
-		break;
-
-	case pm_start_stop:
-		READ_SHADOW_REG(val, pm_start_stop);
-		break;
-	}
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(cbe_read_pm);
-
-void cbe_write_pm(u32 cpu, enum pm_reg_name reg, u32 val)
-{
-	switch (reg) {
-	case group_control:
-		WRITE_WO_MMIO(group_control, val);
-		break;
-
-	case debug_bus_control:
-		WRITE_WO_MMIO(debug_bus_control, val);
-		break;
-
-	case trace_address:
-		WRITE_WO_MMIO(trace_address, val);
-		break;
-
-	case ext_tr_timer:
-		WRITE_WO_MMIO(ext_tr_timer, val);
-		break;
-
-	case pm_status:
-		WRITE_WO_MMIO(pm_status, val);
-		break;
-
-	case pm_control:
-		WRITE_WO_MMIO(pm_control, val);
-		break;
-
-	case pm_interval:
-		WRITE_WO_MMIO(pm_interval, val);
-		break;
-
-	case pm_start_stop:
-		WRITE_WO_MMIO(pm_start_stop, val);
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(cbe_write_pm);
-
-/*
- * Get/set the size of a physical counter to either 16 or 32 bits.
- */
-
-u32 cbe_get_ctr_size(u32 cpu, u32 phys_ctr)
-{
-	u32 pm_ctrl, size = 0;
-
-	if (phys_ctr < NR_PHYS_CTRS) {
-		pm_ctrl = cbe_read_pm(cpu, pm_control);
-		size = (pm_ctrl & CBE_PM_16BIT_CTR(phys_ctr)) ? 16 : 32;
-	}
-
-	return size;
-}
-EXPORT_SYMBOL_GPL(cbe_get_ctr_size);
-
-void cbe_set_ctr_size(u32 cpu, u32 phys_ctr, u32 ctr_size)
-{
-	u32 pm_ctrl;
-
-	if (phys_ctr < NR_PHYS_CTRS) {
-		pm_ctrl = cbe_read_pm(cpu, pm_control);
-		switch (ctr_size) {
-		case 16:
-			pm_ctrl |= CBE_PM_16BIT_CTR(phys_ctr);
-			break;
-
-		case 32:
-			pm_ctrl &= ~CBE_PM_16BIT_CTR(phys_ctr);
-			break;
-		}
-		cbe_write_pm(cpu, pm_control, pm_ctrl);
-	}
-}
-EXPORT_SYMBOL_GPL(cbe_set_ctr_size);
-
-/*
- * Enable/disable the entire performance monitoring unit.
- * When we enable the PMU, all pending writes to counters get committed.
- */
-
-void cbe_enable_pm(u32 cpu)
-{
-	struct cbe_pmd_shadow_regs *shadow_regs;
-	u32 pm_ctrl;
-
-	shadow_regs = cbe_get_cpu_pmd_shadow_regs(cpu);
-	shadow_regs->counter_value_in_latch = 0;
-
-	pm_ctrl = cbe_read_pm(cpu, pm_control) | CBE_PM_ENABLE_PERF_MON;
-	cbe_write_pm(cpu, pm_control, pm_ctrl);
-}
-EXPORT_SYMBOL_GPL(cbe_enable_pm);
-
-void cbe_disable_pm(u32 cpu)
-{
-	u32 pm_ctrl;
-	pm_ctrl = cbe_read_pm(cpu, pm_control) & ~CBE_PM_ENABLE_PERF_MON;
-	cbe_write_pm(cpu, pm_control, pm_ctrl);
-}
-EXPORT_SYMBOL_GPL(cbe_disable_pm);
-
-/*
- * Reading from the trace_buffer.
- * The trace buffer is two 64-bit registers. Reading from
- * the second half automatically increments the trace_address.
- */
-
-void cbe_read_trace_buffer(u32 cpu, u64 *buf)
-{
-	struct cbe_pmd_regs __iomem *pmd_regs = cbe_get_cpu_pmd_regs(cpu);
-
-	*buf++ = in_be64(&pmd_regs->trace_buffer_0_63);
-	*buf++ = in_be64(&pmd_regs->trace_buffer_64_127);
-}
-EXPORT_SYMBOL_GPL(cbe_read_trace_buffer);
-
-/*
- * Enabling/disabling interrupts for the entire performance monitoring unit.
- */
-
-u32 cbe_get_and_clear_pm_interrupts(u32 cpu)
-{
-	/* Reading pm_status clears the interrupt bits. */
-	return cbe_read_pm(cpu, pm_status);
-}
-EXPORT_SYMBOL_GPL(cbe_get_and_clear_pm_interrupts);
-
-void cbe_enable_pm_interrupts(u32 cpu, u32 thread, u32 mask)
-{
-	/* Set which node and thread will handle the next interrupt. */
-	iic_set_interrupt_routing(cpu, thread, 0);
-
-	/* Enable the interrupt bits in the pm_status register. */
-	if (mask)
-		cbe_write_pm(cpu, pm_status, mask);
-}
-EXPORT_SYMBOL_GPL(cbe_enable_pm_interrupts);
-
-void cbe_disable_pm_interrupts(u32 cpu)
-{
-	cbe_get_and_clear_pm_interrupts(cpu);
-	cbe_write_pm(cpu, pm_status, 0);
-}
-EXPORT_SYMBOL_GPL(cbe_disable_pm_interrupts);
-
-static irqreturn_t cbe_pm_irq(int irq, void *dev_id)
-{
-	perf_irq(get_irq_regs());
-	return IRQ_HANDLED;
-}
-
-static int __init cbe_init_pm_irq(void)
-{
-	unsigned int irq;
-	int rc, node;
-
-	for_each_online_node(node) {
-		irq = irq_create_mapping(NULL, IIC_IRQ_IOEX_PMI |
-					       (node << IIC_IRQ_NODE_SHIFT));
-		if (!irq) {
-			printk("ERROR: Unable to allocate irq for node %d\n",
-			       node);
-			return -EINVAL;
-		}
-
-		rc = request_irq(irq, cbe_pm_irq,
-				 0, "cbe-pmu-0", NULL);
-		if (rc) {
-			printk("ERROR: Request for irq on node %d failed\n",
-			       node);
-			return rc;
-		}
-	}
-
-	return 0;
-}
-machine_arch_initcall(cell, cbe_init_pm_irq);
-
-void cbe_sync_irq(int node)
-{
-	unsigned int irq;
-
-	irq = irq_find_mapping(NULL,
-			       IIC_IRQ_IOEX_PMI
-			       | (node << IIC_IRQ_NODE_SHIFT));
-
-	if (!irq) {
-		printk(KERN_WARNING "ERROR, unable to get existing irq %d " \
-		"for node %d\n", irq, node);
-		return;
-	}
-
-	synchronize_irq(irq);
-}
-EXPORT_SYMBOL_GPL(cbe_sync_irq);
-
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
deleted file mode 100644
index 98db63b72d56..000000000000
--- a/arch/powerpc/platforms/cell/ras.c
+++ /dev/null
@@ -1,352 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright 2006-2008, IBM Corporation.
- */
-
-#undef DEBUG
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-#include <linux/reboot.h>
-#include <linux/kexec.h>
-#include <linux/crash_dump.h>
-#include <linux/of.h>
-
-#include <asm/kexec.h>
-#include <asm/reg.h>
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/rtas.h>
-#include <asm/cell-regs.h>
-
-#include "ras.h"
-
-
-static void dump_fir(int cpu)
-{
-	struct cbe_pmd_regs __iomem *pregs = cbe_get_cpu_pmd_regs(cpu);
-	struct cbe_iic_regs __iomem *iregs = cbe_get_cpu_iic_regs(cpu);
-
-	if (pregs == NULL)
-		return;
-
-	/* Todo: do some nicer parsing of bits and based on them go down
-	 * to other sub-units FIRs and not only IIC
-	 */
-	printk(KERN_ERR "Global Checkstop FIR    : 0x%016llx\n",
-	       in_be64(&pregs->checkstop_fir));
-	printk(KERN_ERR "Global Recoverable FIR  : 0x%016llx\n",
-	       in_be64(&pregs->checkstop_fir));
-	printk(KERN_ERR "Global MachineCheck FIR : 0x%016llx\n",
-	       in_be64(&pregs->spec_att_mchk_fir));
-
-	if (iregs == NULL)
-		return;
-	printk(KERN_ERR "IOC FIR                 : 0x%016llx\n",
-	       in_be64(&iregs->ioc_fir));
-
-}
-
-DEFINE_INTERRUPT_HANDLER(cbe_system_error_exception)
-{
-	int cpu = smp_processor_id();
-
-	printk(KERN_ERR "System Error Interrupt on CPU %d !\n", cpu);
-	dump_fir(cpu);
-	dump_stack();
-}
-
-DEFINE_INTERRUPT_HANDLER(cbe_maintenance_exception)
-{
-	int cpu = smp_processor_id();
-
-	/*
-	 * Nothing implemented for the maintenance interrupt at this point
-	 */
-
-	printk(KERN_ERR "Unhandled Maintenance interrupt on CPU %d !\n", cpu);
-	dump_stack();
-}
-
-DEFINE_INTERRUPT_HANDLER(cbe_thermal_exception)
-{
-	int cpu = smp_processor_id();
-
-	/*
-	 * Nothing implemented for the thermal interrupt at this point
-	 */
-
-	printk(KERN_ERR "Unhandled Thermal interrupt on CPU %d !\n", cpu);
-	dump_stack();
-}
-
-static int cbe_machine_check_handler(struct pt_regs *regs)
-{
-	int cpu = smp_processor_id();
-
-	printk(KERN_ERR "Machine Check Interrupt on CPU %d !\n", cpu);
-	dump_fir(cpu);
-
-	/* No recovery from this code now, lets continue */
-	return 0;
-}
-
-struct ptcal_area {
-	struct list_head list;
-	int nid;
-	int order;
-	struct page *pages;
-};
-
-static LIST_HEAD(ptcal_list);
-
-static int ptcal_start_tok, ptcal_stop_tok;
-
-static int __init cbe_ptcal_enable_on_node(int nid, int order)
-{
-	struct ptcal_area *area;
-	int ret = -ENOMEM;
-	unsigned long addr;
-
-	if (is_kdump_kernel())
-		rtas_call(ptcal_stop_tok, 1, 1, NULL, nid);
-
-	area = kmalloc(sizeof(*area), GFP_KERNEL);
-	if (!area)
-		goto out_err;
-
-	area->nid = nid;
-	area->order = order;
-	area->pages = __alloc_pages_node(area->nid,
-						GFP_KERNEL|__GFP_THISNODE,
-						area->order);
-
-	if (!area->pages) {
-		printk(KERN_WARNING "%s: no page on node %d\n",
-			__func__, area->nid);
-		goto out_free_area;
-	}
-
-	/*
-	 * We move the ptcal area to the middle of the allocated
-	 * page, in order to avoid prefetches in memcpy and similar
-	 * functions stepping on it.
-	 */
-	addr = __pa(page_address(area->pages)) + (PAGE_SIZE >> 1);
-	printk(KERN_DEBUG "%s: enabling PTCAL on node %d address=0x%016lx\n",
-			__func__, area->nid, addr);
-
-	ret = -EIO;
-	if (rtas_call(ptcal_start_tok, 3, 1, NULL, area->nid,
-				(unsigned int)(addr >> 32),
-				(unsigned int)(addr & 0xffffffff))) {
-		printk(KERN_ERR "%s: error enabling PTCAL on node %d!\n",
-				__func__, nid);
-		goto out_free_pages;
-	}
-
-	list_add(&area->list, &ptcal_list);
-
-	return 0;
-
-out_free_pages:
-	__free_pages(area->pages, area->order);
-out_free_area:
-	kfree(area);
-out_err:
-	return ret;
-}
-
-static int __init cbe_ptcal_enable(void)
-{
-	const u32 *size;
-	struct device_node *np;
-	int order, found_mic = 0;
-
-	np = of_find_node_by_path("/rtas");
-	if (!np)
-		return -ENODEV;
-
-	size = of_get_property(np, "ibm,cbe-ptcal-size", NULL);
-	if (!size) {
-		of_node_put(np);
-		return -ENODEV;
-	}
-
-	pr_debug("%s: enabling PTCAL, size = 0x%x\n", __func__, *size);
-	order = get_order(*size);
-	of_node_put(np);
-
-	/* support for malta device trees, with be@/mic@ nodes */
-	for_each_node_by_type(np, "mic-tm") {
-		cbe_ptcal_enable_on_node(of_node_to_nid(np), order);
-		found_mic = 1;
-	}
-
-	if (found_mic)
-		return 0;
-
-	/* support for older device tree - use cpu nodes */
-	for_each_node_by_type(np, "cpu") {
-		const u32 *nid = of_get_property(np, "node-id", NULL);
-		if (!nid) {
-			printk(KERN_ERR "%s: node %pOF is missing node-id?\n",
-					__func__, np);
-			continue;
-		}
-		cbe_ptcal_enable_on_node(*nid, order);
-		found_mic = 1;
-	}
-
-	return found_mic ? 0 : -ENODEV;
-}
-
-static int cbe_ptcal_disable(void)
-{
-	struct ptcal_area *area, *tmp;
-	int ret = 0;
-
-	pr_debug("%s: disabling PTCAL\n", __func__);
-
-	list_for_each_entry_safe(area, tmp, &ptcal_list, list) {
-		/* disable ptcal on this node */
-		if (rtas_call(ptcal_stop_tok, 1, 1, NULL, area->nid)) {
-			printk(KERN_ERR "%s: error disabling PTCAL "
-					"on node %d!\n", __func__,
-					area->nid);
-			ret = -EIO;
-			continue;
-		}
-
-		/* ensure we can access the PTCAL area */
-		memset(page_address(area->pages), 0,
-				1 << (area->order + PAGE_SHIFT));
-
-		/* clean up */
-		list_del(&area->list);
-		__free_pages(area->pages, area->order);
-		kfree(area);
-	}
-
-	return ret;
-}
-
-static int cbe_ptcal_notify_reboot(struct notifier_block *nb,
-		unsigned long code, void *data)
-{
-	return cbe_ptcal_disable();
-}
-
-static void cbe_ptcal_crash_shutdown(void)
-{
-	cbe_ptcal_disable();
-}
-
-static struct notifier_block cbe_ptcal_reboot_notifier = {
-	.notifier_call = cbe_ptcal_notify_reboot
-};
-
-#ifdef CONFIG_PPC_IBM_CELL_RESETBUTTON
-static int sysreset_hack;
-
-static int __init cbe_sysreset_init(void)
-{
-	struct cbe_pmd_regs __iomem *regs;
-
-	sysreset_hack = of_machine_is_compatible("IBM,CBPLUS-1.0");
-	if (!sysreset_hack)
-		return 0;
-
-	regs = cbe_get_cpu_pmd_regs(0);
-	if (!regs)
-		return 0;
-
-	/* Enable JTAG system-reset hack */
-	out_be32(&regs->fir_mode_reg,
-		in_be32(&regs->fir_mode_reg) |
-		CBE_PMD_FIR_MODE_M8);
-
-	return 0;
-}
-device_initcall(cbe_sysreset_init);
-
-int cbe_sysreset_hack(void)
-{
-	struct cbe_pmd_regs __iomem *regs;
-
-	/*
-	 * The BMC can inject user triggered system reset exceptions,
-	 * but cannot set the system reset reason in srr1,
-	 * so check an extra register here.
-	 */
-	if (sysreset_hack && (smp_processor_id() == 0)) {
-		regs = cbe_get_cpu_pmd_regs(0);
-		if (!regs)
-			return 0;
-		if (in_be64(&regs->ras_esc_0) & 0x0000ffff) {
-			out_be64(&regs->ras_esc_0, 0);
-			return 0;
-		}
-	}
-	return 1;
-}
-#endif /* CONFIG_PPC_IBM_CELL_RESETBUTTON */
-
-static int __init cbe_ptcal_init(void)
-{
-	int ret;
-	ptcal_start_tok = rtas_function_token(RTAS_FN_IBM_CBE_START_PTCAL);
-	ptcal_stop_tok = rtas_function_token(RTAS_FN_IBM_CBE_STOP_PTCAL);
-
-	if (ptcal_start_tok == RTAS_UNKNOWN_SERVICE
-			|| ptcal_stop_tok == RTAS_UNKNOWN_SERVICE)
-		return -ENODEV;
-
-	ret = register_reboot_notifier(&cbe_ptcal_reboot_notifier);
-	if (ret)
-		goto out1;
-
-	ret = crash_shutdown_register(&cbe_ptcal_crash_shutdown);
-	if (ret)
-		goto out2;
-
-	return cbe_ptcal_enable();
-
-out2:
-	unregister_reboot_notifier(&cbe_ptcal_reboot_notifier);
-out1:
-	printk(KERN_ERR "Can't disable PTCAL, so not enabling\n");
-	return ret;
-}
-
-arch_initcall(cbe_ptcal_init);
-
-void __init cbe_ras_init(void)
-{
-	unsigned long hid0;
-
-	/*
-	 * Enable System Error & thermal interrupts and wakeup conditions
-	 */
-
-	hid0 = mfspr(SPRN_HID0);
-	hid0 |= HID0_CBE_THERM_INT_EN | HID0_CBE_THERM_WAKEUP |
-		HID0_CBE_SYSERR_INT_EN | HID0_CBE_SYSERR_WAKEUP;
-	mtspr(SPRN_HID0, hid0);
-	mb();
-
-	/*
-	 * Install machine check handler. Leave setting of precise mode to
-	 * what the firmware did for now
-	 */
-	ppc_md.machine_check_exception = cbe_machine_check_handler;
-	mb();
-
-	/*
-	 * For now, we assume that IOC_FIR is already set to forward some
-	 * error conditions to the System Error handler. If that is not true
-	 * then it will have to be fixed up here.
-	 */
-}
diff --git a/arch/powerpc/platforms/cell/ras.h b/arch/powerpc/platforms/cell/ras.h
deleted file mode 100644
index 226dbd48efad..000000000000
--- a/arch/powerpc/platforms/cell/ras.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef RAS_H
-#define RAS_H
-
-#include <asm/interrupt.h>
-
-DECLARE_INTERRUPT_HANDLER(cbe_system_error_exception);
-DECLARE_INTERRUPT_HANDLER(cbe_maintenance_exception);
-DECLARE_INTERRUPT_HANDLER(cbe_thermal_exception);
-
-extern void cbe_ras_init(void);
-
-#endif /* RAS_H */
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
deleted file mode 100644
index 9e07d101bcee..000000000000
--- a/arch/powerpc/platforms/cell/setup.c
+++ /dev/null
@@ -1,273 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  linux/arch/powerpc/platforms/cell/cell_setup.c
- *
- *  Copyright (C) 1995  Linus Torvalds
- *  Adapted from 'alpha' version by Gary Thomas
- *  Modified by Cort Dougan (cort@cs.nmt.edu)
- *  Modified by PPC64 Team, IBM Corp
- *  Modified by Cell Team, IBM Deutschland Entwicklung GmbH
- */
-#undef DEBUG
-
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/export.h>
-#include <linux/unistd.h>
-#include <linux/user.h>
-#include <linux/reboot.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/irq.h>
-#include <linux/seq_file.h>
-#include <linux/root_dev.h>
-#include <linux/console.h>
-#include <linux/mutex.h>
-#include <linux/memory_hotplug.h>
-#include <linux/of_platform.h>
-
-#include <asm/mmu.h>
-#include <asm/processor.h>
-#include <asm/io.h>
-#include <asm/rtas.h>
-#include <asm/pci-bridge.h>
-#include <asm/iommu.h>
-#include <asm/dma.h>
-#include <asm/machdep.h>
-#include <asm/time.h>
-#include <asm/nvram.h>
-#include <asm/cputable.h>
-#include <asm/ppc-pci.h>
-#include <asm/irq.h>
-#include <asm/spu.h>
-#include <asm/spu_priv1.h>
-#include <asm/udbg.h>
-#include <asm/mpic.h>
-#include <asm/cell-regs.h>
-#include <asm/io-workarounds.h>
-
-#include "cell.h"
-#include "interrupt.h"
-#include "pervasive.h"
-#include "ras.h"
-
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
-static void cell_show_cpuinfo(struct seq_file *m)
-{
-	struct device_node *root;
-	const char *model = "";
-
-	root = of_find_node_by_path("/");
-	if (root)
-		model = of_get_property(root, "model", NULL);
-	seq_printf(m, "machine\t\t: CHRP %s\n", model);
-	of_node_put(root);
-}
-
-static void cell_progress(char *s, unsigned short hex)
-{
-	printk("*** %04x : %s\n", hex, s ? s : "");
-}
-
-static void cell_fixup_pcie_rootcomplex(struct pci_dev *dev)
-{
-	struct pci_controller *hose;
-	const char *s;
-	int i;
-
-	if (!machine_is(cell))
-		return;
-
-	/* We're searching for a direct child of the PHB */
-	if (dev->bus->self != NULL || dev->devfn != 0)
-		return;
-
-	hose = pci_bus_to_host(dev->bus);
-	if (hose == NULL)
-		return;
-
-	/* Only on PCIE */
-	if (!of_device_is_compatible(hose->dn, "pciex"))
-		return;
-
-	/* And only on axon */
-	s = of_get_property(hose->dn, "model", NULL);
-	if (!s || strcmp(s, "Axon") != 0)
-		return;
-
-	for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) {
-		dev->resource[i].start = dev->resource[i].end = 0;
-		dev->resource[i].flags = 0;
-	}
-
-	printk(KERN_DEBUG "PCI: Hiding resources on Axon PCIE RC %s\n",
-	       pci_name(dev));
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, cell_fixup_pcie_rootcomplex);
-
-static int cell_setup_phb(struct pci_controller *phb)
-{
-	const char *model;
-	struct device_node *np;
-
-	int rc = rtas_setup_phb(phb);
-	if (rc)
-		return rc;
-
-	phb->controller_ops = cell_pci_controller_ops;
-
-	np = phb->dn;
-	model = of_get_property(np, "model", NULL);
-	if (model == NULL || !of_node_name_eq(np, "pci"))
-		return 0;
-
-	/* Setup workarounds for spider */
-	if (strcmp(model, "Spider"))
-		return 0;
-
-	iowa_register_bus(phb, &spiderpci_ops, &spiderpci_iowa_init,
-				  (void *)SPIDER_PCI_REG_BASE);
-	return 0;
-}
-
-static const struct of_device_id cell_bus_ids[] __initconst = {
-	{ .type = "soc", },
-	{ .compatible = "soc", },
-	{ .type = "spider", },
-	{ .type = "axon", },
-	{ .type = "plb5", },
-	{ .type = "plb4", },
-	{ .type = "opb", },
-	{ .type = "ebc", },
-	{},
-};
-
-static int __init cell_publish_devices(void)
-{
-	struct device_node *root = of_find_node_by_path("/");
-	struct device_node *np;
-	int node;
-
-	/* Publish OF platform devices for southbridge IOs */
-	of_platform_bus_probe(NULL, cell_bus_ids, NULL);
-
-	/* On spider based blades, we need to manually create the OF
-	 * platform devices for the PCI host bridges
-	 */
-	for_each_child_of_node(root, np) {
-		if (!of_node_is_type(np, "pci") && !of_node_is_type(np, "pciex"))
-			continue;
-		of_platform_device_create(np, NULL, NULL);
-	}
-
-	of_node_put(root);
-
-	/* There is no device for the MIC memory controller, thus we create
-	 * a platform device for it to attach the EDAC driver to.
-	 */
-	for_each_online_node(node) {
-		if (cbe_get_cpu_mic_tm_regs(cbe_node_to_cpu(node)) == NULL)
-			continue;
-		platform_device_register_simple("cbe-mic", node, NULL, 0);
-	}
-
-	return 0;
-}
-machine_subsys_initcall(cell, cell_publish_devices);
-
-static void __init mpic_init_IRQ(void)
-{
-	struct device_node *dn;
-	struct mpic *mpic;
-
-	for_each_node_by_name(dn, "interrupt-controller") {
-		if (!of_device_is_compatible(dn, "CBEA,platform-open-pic"))
-			continue;
-
-		/* The MPIC driver will get everything it needs from the
-		 * device-tree, just pass 0 to all arguments
-		 */
-		mpic = mpic_alloc(dn, 0, MPIC_SECONDARY | MPIC_NO_RESET,
-				0, 0, " MPIC     ");
-		if (mpic == NULL)
-			continue;
-		mpic_init(mpic);
-	}
-}
-
-
-static void __init cell_init_irq(void)
-{
-	iic_init_IRQ();
-	spider_init_IRQ();
-	mpic_init_IRQ();
-}
-
-static void __init cell_set_dabrx(void)
-{
-	mtspr(SPRN_DABRX, DABRX_KERNEL | DABRX_USER);
-}
-
-static void __init cell_setup_arch(void)
-{
-#ifdef CONFIG_SPU_BASE
-	spu_priv1_ops = &spu_priv1_mmio_ops;
-	spu_management_ops = &spu_management_of_ops;
-#endif
-
-	cbe_regs_init();
-
-	cell_set_dabrx();
-
-#ifdef CONFIG_CBE_RAS
-	cbe_ras_init();
-#endif
-
-#ifdef CONFIG_SMP
-	smp_init_cell();
-#endif
-	/* init to some ~sane value until calibrate_delay() runs */
-	loops_per_jiffy = 50000000;
-
-	/* Find and initialize PCI host bridges */
-	init_pci_config_tokens();
-
-	cbe_pervasive_init();
-
-	mmio_nvram_init();
-}
-
-static int __init cell_probe(void)
-{
-	if (!of_machine_is_compatible("IBM,CBEA") &&
-	    !of_machine_is_compatible("IBM,CPBW-1.0"))
-		return 0;
-
-	pm_power_off = rtas_power_off;
-
-	return 1;
-}
-
-define_machine(cell) {
-	.name			= "Cell",
-	.probe			= cell_probe,
-	.setup_arch		= cell_setup_arch,
-	.show_cpuinfo		= cell_show_cpuinfo,
-	.restart		= rtas_restart,
-	.halt			= rtas_halt,
-	.get_boot_time		= rtas_get_boot_time,
-	.get_rtc_time		= rtas_get_rtc_time,
-	.set_rtc_time		= rtas_set_rtc_time,
-	.progress		= cell_progress,
-	.init_IRQ       	= cell_init_irq,
-	.pci_setup_phb		= cell_setup_phb,
-};
-
-struct pci_controller_ops cell_pci_controller_ops;
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
deleted file mode 100644
index 30394c6f8894..000000000000
--- a/arch/powerpc/platforms/cell/smp.c
+++ /dev/null
@@ -1,161 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SMP support for BPA machines.
- *
- * Dave Engebretsen, Peter Bergner, and
- * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
- *
- * Plus various changes from other IBM teams...
- */
-
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/cache.h>
-#include <linux/err.h>
-#include <linux/device.h>
-#include <linux/cpu.h>
-#include <linux/pgtable.h>
-
-#include <asm/ptrace.h>
-#include <linux/atomic.h>
-#include <asm/irq.h>
-#include <asm/page.h>
-#include <asm/io.h>
-#include <asm/smp.h>
-#include <asm/paca.h>
-#include <asm/machdep.h>
-#include <asm/cputable.h>
-#include <asm/firmware.h>
-#include <asm/rtas.h>
-#include <asm/cputhreads.h>
-#include <asm/code-patching.h>
-
-#include "interrupt.h"
-#include <asm/udbg.h>
-
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
-/*
- * The Primary thread of each non-boot processor was started from the OF client
- * interface by prom_hold_cpus and is spinning on secondary_hold_spinloop.
- */
-static cpumask_t of_spin_map;
-
-/**
- * smp_startup_cpu() - start the given cpu
- *
- * At boot time, there is nothing to do for primary threads which were
- * started from Open Firmware.  For anything else, call RTAS with the
- * appropriate start location.
- *
- * Returns:
- *	0	- failure
- *	1	- success
- */
-static inline int smp_startup_cpu(unsigned int lcpu)
-{
-	int status;
-	unsigned long start_here =
-			__pa(ppc_function_entry(generic_secondary_smp_init));
-	unsigned int pcpu;
-	int start_cpu;
-
-	if (cpumask_test_cpu(lcpu, &of_spin_map))
-		/* Already started by OF and sitting in spin loop */
-		return 1;
-
-	pcpu = get_hard_smp_processor_id(lcpu);
-
-	/*
-	 * If the RTAS start-cpu token does not exist then presume the
-	 * cpu is already spinning.
-	 */
-	start_cpu = rtas_function_token(RTAS_FN_START_CPU);
-	if (start_cpu == RTAS_UNKNOWN_SERVICE)
-		return 1;
-
-	status = rtas_call(start_cpu, 3, 1, NULL, pcpu, start_here, lcpu);
-	if (status != 0) {
-		printk(KERN_ERR "start-cpu failed: %i\n", status);
-		return 0;
-	}
-
-	return 1;
-}
-
-static void smp_cell_setup_cpu(int cpu)
-{
-	if (cpu != boot_cpuid)
-		iic_setup_cpu();
-
-	/*
-	 * change default DABRX to allow user watchpoints
-	 */
-	mtspr(SPRN_DABRX, DABRX_KERNEL | DABRX_USER);
-}
-
-static int smp_cell_kick_cpu(int nr)
-{
-	if (nr < 0 || nr >= nr_cpu_ids)
-		return -EINVAL;
-
-	if (!smp_startup_cpu(nr))
-		return -ENOENT;
-
-	/*
-	 * The processor is currently spinning, waiting for the
-	 * cpu_start field to become non-zero After we set cpu_start,
-	 * the processor will continue on to secondary_start
-	 */
-	paca_ptrs[nr]->cpu_start = 1;
-
-	return 0;
-}
-
-static struct smp_ops_t bpa_iic_smp_ops = {
-	.message_pass	= iic_message_pass,
-	.probe		= iic_request_IPIs,
-	.kick_cpu	= smp_cell_kick_cpu,
-	.setup_cpu	= smp_cell_setup_cpu,
-	.cpu_bootable	= smp_generic_cpu_bootable,
-};
-
-/* This is called very early */
-void __init smp_init_cell(void)
-{
-	int i;
-
-	DBG(" -> smp_init_cell()\n");
-
-	smp_ops = &bpa_iic_smp_ops;
-
-	/* Mark threads which are still spinning in hold loops. */
-	if (cpu_has_feature(CPU_FTR_SMT)) {
-		for_each_present_cpu(i) {
-			if (cpu_thread_in_core(i) == 0)
-				cpumask_set_cpu(i, &of_spin_map);
-		}
-	} else
-		cpumask_copy(&of_spin_map, cpu_present_mask);
-
-	cpumask_clear_cpu(boot_cpuid, &of_spin_map);
-
-	/* Non-lpar has additional take/give timebase */
-	if (rtas_function_token(RTAS_FN_FREEZE_TIME_BASE) != RTAS_UNKNOWN_SERVICE) {
-		smp_ops->give_timebase = rtas_give_timebase;
-		smp_ops->take_timebase = rtas_take_timebase;
-	}
-
-	DBG(" <- smp_init_cell()\n");
-}
diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c
deleted file mode 100644
index e36ebd84f55b..000000000000
--- a/arch/powerpc/platforms/cell/spider-pci.c
+++ /dev/null
@@ -1,171 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * IO workarounds for PCI on Celleb/Cell platform
- *
- * (C) Copyright 2006-2007 TOSHIBA CORPORATION
- */
-
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-
-#include <asm/ppc-pci.h>
-#include <asm/pci-bridge.h>
-#include <asm/io-workarounds.h>
-
-#define SPIDER_PCI_DISABLE_PREFETCH
-
-struct spiderpci_iowa_private {
-	void __iomem *regs;
-};
-
-static void spiderpci_io_flush(struct iowa_bus *bus)
-{
-	struct spiderpci_iowa_private *priv;
-
-	priv = bus->private;
-	in_be32(priv->regs + SPIDER_PCI_DUMMY_READ);
-	iosync();
-}
-
-#define SPIDER_PCI_MMIO_READ(name, ret)					\
-static ret spiderpci_##name(const PCI_IO_ADDR addr)			\
-{									\
-	ret val = __do_##name(addr);					\
-	spiderpci_io_flush(iowa_mem_find_bus(addr));			\
-	return val;							\
-}
-
-#define SPIDER_PCI_MMIO_READ_STR(name)					\
-static void spiderpci_##name(const PCI_IO_ADDR addr, void *buf, 	\
-			     unsigned long count)			\
-{									\
-	__do_##name(addr, buf, count);					\
-	spiderpci_io_flush(iowa_mem_find_bus(addr));			\
-}
-
-SPIDER_PCI_MMIO_READ(readb, u8)
-SPIDER_PCI_MMIO_READ(readw, u16)
-SPIDER_PCI_MMIO_READ(readl, u32)
-SPIDER_PCI_MMIO_READ(readq, u64)
-SPIDER_PCI_MMIO_READ(readw_be, u16)
-SPIDER_PCI_MMIO_READ(readl_be, u32)
-SPIDER_PCI_MMIO_READ(readq_be, u64)
-SPIDER_PCI_MMIO_READ_STR(readsb)
-SPIDER_PCI_MMIO_READ_STR(readsw)
-SPIDER_PCI_MMIO_READ_STR(readsl)
-
-static void spiderpci_memcpy_fromio(void *dest, const PCI_IO_ADDR src,
-				    unsigned long n)
-{
-	__do_memcpy_fromio(dest, src, n);
-	spiderpci_io_flush(iowa_mem_find_bus(src));
-}
-
-static int __init spiderpci_pci_setup_chip(struct pci_controller *phb,
-					   void __iomem *regs)
-{
-	void *dummy_page_va;
-	dma_addr_t dummy_page_da;
-
-#ifdef SPIDER_PCI_DISABLE_PREFETCH
-	u32 val = in_be32(regs + SPIDER_PCI_VCI_CNTL_STAT);
-	pr_debug("SPIDER_IOWA:PVCI_Control_Status was 0x%08x\n", val);
-	out_be32(regs + SPIDER_PCI_VCI_CNTL_STAT, val | 0x8);
-#endif /* SPIDER_PCI_DISABLE_PREFETCH */
-
-	/* setup dummy read */
-	/*
-	 * On CellBlade, we can't know that which XDR memory is used by
-	 * kmalloc() to allocate dummy_page_va.
-	 * In order to improve the performance, the XDR which is used to
-	 * allocate dummy_page_va is the nearest the spider-pci.
-	 * We have to select the CBE which is the nearest the spider-pci
-	 * to allocate memory from the best XDR, but I don't know that
-	 * how to do.
-	 *
-	 * Celleb does not have this problem, because it has only one XDR.
-	 */
-	dummy_page_va = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!dummy_page_va) {
-		pr_err("SPIDERPCI-IOWA:Alloc dummy_page_va failed.\n");
-		return -1;
-	}
-
-	dummy_page_da = dma_map_single(phb->parent, dummy_page_va,
-				       PAGE_SIZE, DMA_FROM_DEVICE);
-	if (dma_mapping_error(phb->parent, dummy_page_da)) {
-		pr_err("SPIDER-IOWA:Map dummy page filed.\n");
-		kfree(dummy_page_va);
-		return -1;
-	}
-
-	out_be32(regs + SPIDER_PCI_DUMMY_READ_BASE, dummy_page_da);
-
-	return 0;
-}
-
-int __init spiderpci_iowa_init(struct iowa_bus *bus, void *data)
-{
-	void __iomem *regs = NULL;
-	struct spiderpci_iowa_private *priv;
-	struct device_node *np = bus->phb->dn;
-	struct resource r;
-	unsigned long offset = (unsigned long)data;
-
-	pr_debug("SPIDERPCI-IOWA:Bus initialize for spider(%pOF)\n",
-		 np);
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		pr_err("SPIDERPCI-IOWA:"
-		       "Can't allocate struct spiderpci_iowa_private");
-		return -1;
-	}
-
-	if (of_address_to_resource(np, 0, &r)) {
-		pr_err("SPIDERPCI-IOWA:Can't get resource.\n");
-		goto error;
-	}
-
-	regs = ioremap(r.start + offset, SPIDER_PCI_REG_SIZE);
-	if (!regs) {
-		pr_err("SPIDERPCI-IOWA:ioremap failed.\n");
-		goto error;
-	}
-	priv->regs = regs;
-	bus->private = priv;
-
-	if (spiderpci_pci_setup_chip(bus->phb, regs))
-		goto error;
-
-	return 0;
-
-error:
-	kfree(priv);
-	bus->private = NULL;
-
-	if (regs)
-		iounmap(regs);
-
-	return -1;
-}
-
-struct ppc_pci_io spiderpci_ops = {
-	.readb = spiderpci_readb,
-	.readw = spiderpci_readw,
-	.readl = spiderpci_readl,
-	.readq = spiderpci_readq,
-	.readw_be = spiderpci_readw_be,
-	.readl_be = spiderpci_readl_be,
-	.readq_be = spiderpci_readq_be,
-	.readsb = spiderpci_readsb,
-	.readsw = spiderpci_readsw,
-	.readsl = spiderpci_readsl,
-	.memcpy_fromio = spiderpci_memcpy_fromio,
-};
-
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
deleted file mode 100644
index 11df737c8c6a..000000000000
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ /dev/null
@@ -1,344 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * External Interrupt Controller on Spider South Bridge
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * Author: Arnd Bergmann <arndb@de.ibm.com>
- */
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/ioport.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/pgtable.h>
-
-#include <asm/io.h>
-
-#include "interrupt.h"
-
-/* register layout taken from Spider spec, table 7.4-4 */
-enum {
-	TIR_DEN		= 0x004, /* Detection Enable Register */
-	TIR_MSK		= 0x084, /* Mask Level Register */
-	TIR_EDC		= 0x0c0, /* Edge Detection Clear Register */
-	TIR_PNDA	= 0x100, /* Pending Register A */
-	TIR_PNDB	= 0x104, /* Pending Register B */
-	TIR_CS		= 0x144, /* Current Status Register */
-	TIR_LCSA	= 0x150, /* Level Current Status Register A */
-	TIR_LCSB	= 0x154, /* Level Current Status Register B */
-	TIR_LCSC	= 0x158, /* Level Current Status Register C */
-	TIR_LCSD	= 0x15c, /* Level Current Status Register D */
-	TIR_CFGA	= 0x200, /* Setting Register A0 */
-	TIR_CFGB	= 0x204, /* Setting Register B0 */
-			/* 0x208 ... 0x3ff Setting Register An/Bn */
-	TIR_PPNDA	= 0x400, /* Packet Pending Register A */
-	TIR_PPNDB	= 0x404, /* Packet Pending Register B */
-	TIR_PIERA	= 0x408, /* Packet Output Error Register A */
-	TIR_PIERB	= 0x40c, /* Packet Output Error Register B */
-	TIR_PIEN	= 0x444, /* Packet Output Enable Register */
-	TIR_PIPND	= 0x454, /* Packet Output Pending Register */
-	TIRDID		= 0x484, /* Spider Device ID Register */
-	REISTIM		= 0x500, /* Reissue Command Timeout Time Setting */
-	REISTIMEN	= 0x504, /* Reissue Command Timeout Setting */
-	REISWAITEN	= 0x508, /* Reissue Wait Control*/
-};
-
-#define SPIDER_CHIP_COUNT	4
-#define SPIDER_SRC_COUNT	64
-#define SPIDER_IRQ_INVALID	63
-
-struct spider_pic {
-	struct irq_domain		*host;
-	void __iomem		*regs;
-	unsigned int		node_id;
-};
-static struct spider_pic spider_pics[SPIDER_CHIP_COUNT];
-
-static struct spider_pic *spider_irq_data_to_pic(struct irq_data *d)
-{
-	return irq_data_get_irq_chip_data(d);
-}
-
-static void __iomem *spider_get_irq_config(struct spider_pic *pic,
-					   unsigned int src)
-{
-	return pic->regs + TIR_CFGA + 8 * src;
-}
-
-static void spider_unmask_irq(struct irq_data *d)
-{
-	struct spider_pic *pic = spider_irq_data_to_pic(d);
-	void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d));
-
-	out_be32(cfg, in_be32(cfg) | 0x30000000u);
-}
-
-static void spider_mask_irq(struct irq_data *d)
-{
-	struct spider_pic *pic = spider_irq_data_to_pic(d);
-	void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d));
-
-	out_be32(cfg, in_be32(cfg) & ~0x30000000u);
-}
-
-static void spider_ack_irq(struct irq_data *d)
-{
-	struct spider_pic *pic = spider_irq_data_to_pic(d);
-	unsigned int src = irqd_to_hwirq(d);
-
-	/* Reset edge detection logic if necessary
-	 */
-	if (irqd_is_level_type(d))
-		return;
-
-	/* Only interrupts 47 to 50 can be set to edge */
-	if (src < 47 || src > 50)
-		return;
-
-	/* Perform the clear of the edge logic */
-	out_be32(pic->regs + TIR_EDC, 0x100 | (src & 0xf));
-}
-
-static int spider_set_irq_type(struct irq_data *d, unsigned int type)
-{
-	unsigned int sense = type & IRQ_TYPE_SENSE_MASK;
-	struct spider_pic *pic = spider_irq_data_to_pic(d);
-	unsigned int hw = irqd_to_hwirq(d);
-	void __iomem *cfg = spider_get_irq_config(pic, hw);
-	u32 old_mask;
-	u32 ic;
-
-	/* Note that only level high is supported for most interrupts */
-	if (sense != IRQ_TYPE_NONE && sense != IRQ_TYPE_LEVEL_HIGH &&
-	    (hw < 47 || hw > 50))
-		return -EINVAL;
-
-	/* Decode sense type */
-	switch(sense) {
-	case IRQ_TYPE_EDGE_RISING:
-		ic = 0x3;
-		break;
-	case IRQ_TYPE_EDGE_FALLING:
-		ic = 0x2;
-		break;
-	case IRQ_TYPE_LEVEL_LOW:
-		ic = 0x0;
-		break;
-	case IRQ_TYPE_LEVEL_HIGH:
-	case IRQ_TYPE_NONE:
-		ic = 0x1;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* Configure the source. One gross hack that was there before and
-	 * that I've kept around is the priority to the BE which I set to
-	 * be the same as the interrupt source number. I don't know whether
-	 * that's supposed to make any kind of sense however, we'll have to
-	 * decide that, but for now, I'm not changing the behaviour.
-	 */
-	old_mask = in_be32(cfg) & 0x30000000u;
-	out_be32(cfg, old_mask | (ic << 24) | (0x7 << 16) |
-		 (pic->node_id << 4) | 0xe);
-	out_be32(cfg + 4, (0x2 << 16) | (hw & 0xff));
-
-	return 0;
-}
-
-static struct irq_chip spider_pic = {
-	.name = "SPIDER",
-	.irq_unmask = spider_unmask_irq,
-	.irq_mask = spider_mask_irq,
-	.irq_ack = spider_ack_irq,
-	.irq_set_type = spider_set_irq_type,
-};
-
-static int spider_host_map(struct irq_domain *h, unsigned int virq,
-			irq_hw_number_t hw)
-{
-	irq_set_chip_data(virq, h->host_data);
-	irq_set_chip_and_handler(virq, &spider_pic, handle_level_irq);
-
-	/* Set default irq type */
-	irq_set_irq_type(virq, IRQ_TYPE_NONE);
-
-	return 0;
-}
-
-static int spider_host_xlate(struct irq_domain *h, struct device_node *ct,
-			   const u32 *intspec, unsigned int intsize,
-			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
-
-{
-	/* Spider interrupts have 2 cells, first is the interrupt source,
-	 * second, well, I don't know for sure yet ... We mask the top bits
-	 * because old device-trees encode a node number in there
-	 */
-	*out_hwirq = intspec[0] & 0x3f;
-	*out_flags = IRQ_TYPE_LEVEL_HIGH;
-	return 0;
-}
-
-static const struct irq_domain_ops spider_host_ops = {
-	.map = spider_host_map,
-	.xlate = spider_host_xlate,
-};
-
-static void spider_irq_cascade(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct spider_pic *pic = irq_desc_get_handler_data(desc);
-	unsigned int cs;
-
-	cs = in_be32(pic->regs + TIR_CS) >> 24;
-	if (cs != SPIDER_IRQ_INVALID)
-		generic_handle_domain_irq(pic->host, cs);
-
-	chip->irq_eoi(&desc->irq_data);
-}
-
-/* For hooking up the cascade we have a problem. Our device-tree is
- * crap and we don't know on which BE iic interrupt we are hooked on at
- * least not the "standard" way. We can reconstitute it based on two
- * informations though: which BE node we are connected to and whether
- * we are connected to IOIF0 or IOIF1. Right now, we really only care
- * about the IBM cell blade and we know that its firmware gives us an
- * interrupt-map property which is pretty strange.
- */
-static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
-{
-	unsigned int virq;
-	const u32 *imap, *tmp;
-	int imaplen, intsize, unit;
-	struct device_node *iic;
-	struct device_node *of_node;
-
-	of_node = irq_domain_get_of_node(pic->host);
-
-	/* First, we check whether we have a real "interrupts" in the device
-	 * tree in case the device-tree is ever fixed
-	 */
-	virq = irq_of_parse_and_map(of_node, 0);
-	if (virq)
-		return virq;
-
-	/* Now do the horrible hacks */
-	tmp = of_get_property(of_node, "#interrupt-cells", NULL);
-	if (tmp == NULL)
-		return 0;
-	intsize = *tmp;
-	imap = of_get_property(of_node, "interrupt-map", &imaplen);
-	if (imap == NULL || imaplen < (intsize + 1))
-		return 0;
-	iic = of_find_node_by_phandle(imap[intsize]);
-	if (iic == NULL)
-		return 0;
-	imap += intsize + 1;
-	tmp = of_get_property(iic, "#interrupt-cells", NULL);
-	if (tmp == NULL) {
-		of_node_put(iic);
-		return 0;
-	}
-	intsize = *tmp;
-	/* Assume unit is last entry of interrupt specifier */
-	unit = imap[intsize - 1];
-	/* Ok, we have a unit, now let's try to get the node */
-	tmp = of_get_property(iic, "ibm,interrupt-server-ranges", NULL);
-	if (tmp == NULL) {
-		of_node_put(iic);
-		return 0;
-	}
-	/* ugly as hell but works for now */
-	pic->node_id = (*tmp) >> 1;
-	of_node_put(iic);
-
-	/* Ok, now let's get cracking. You may ask me why I just didn't match
-	 * the iic host from the iic OF node, but that way I'm still compatible
-	 * with really really old old firmwares for which we don't have a node
-	 */
-	/* Manufacture an IIC interrupt number of class 2 */
-	virq = irq_create_mapping(NULL,
-				  (pic->node_id << IIC_IRQ_NODE_SHIFT) |
-				  (2 << IIC_IRQ_CLASS_SHIFT) |
-				  unit);
-	if (!virq)
-		printk(KERN_ERR "spider_pic: failed to map cascade !");
-	return virq;
-}
-
-
-static void __init spider_init_one(struct device_node *of_node, int chip,
-				   unsigned long addr)
-{
-	struct spider_pic *pic = &spider_pics[chip];
-	int i, virq;
-
-	/* Map registers */
-	pic->regs = ioremap(addr, 0x1000);
-	if (pic->regs == NULL)
-		panic("spider_pic: can't map registers !");
-
-	/* Allocate a host */
-	pic->host = irq_domain_add_linear(of_node, SPIDER_SRC_COUNT,
-					  &spider_host_ops, pic);
-	if (pic->host == NULL)
-		panic("spider_pic: can't allocate irq host !");
-
-	/* Go through all sources and disable them */
-	for (i = 0; i < SPIDER_SRC_COUNT; i++) {
-		void __iomem *cfg = pic->regs + TIR_CFGA + 8 * i;
-		out_be32(cfg, in_be32(cfg) & ~0x30000000u);
-	}
-
-	/* do not mask any interrupts because of level */
-	out_be32(pic->regs + TIR_MSK, 0x0);
-
-	/* enable interrupt packets to be output */
-	out_be32(pic->regs + TIR_PIEN, in_be32(pic->regs + TIR_PIEN) | 0x1);
-
-	/* Hook up the cascade interrupt to the iic and nodeid */
-	virq = spider_find_cascade_and_node(pic);
-	if (!virq)
-		return;
-	irq_set_handler_data(virq, pic);
-	irq_set_chained_handler(virq, spider_irq_cascade);
-
-	printk(KERN_INFO "spider_pic: node %d, addr: 0x%lx %pOF\n",
-	       pic->node_id, addr, of_node);
-
-	/* Enable the interrupt detection enable bit. Do this last! */
-	out_be32(pic->regs + TIR_DEN, in_be32(pic->regs + TIR_DEN) | 0x1);
-}
-
-void __init spider_init_IRQ(void)
-{
-	struct resource r;
-	struct device_node *dn;
-	int chip = 0;
-
-	/* XXX node numbers are totally bogus. We _hope_ we get the device
-	 * nodes in the right order here but that's definitely not guaranteed,
-	 * we need to get the node from the device tree instead.
-	 * There is currently no proper property for it (but our whole
-	 * device-tree is bogus anyway) so all we can do is pray or maybe test
-	 * the address and deduce the node-id
-	 */
-	for_each_node_by_name(dn, "interrupt-controller") {
-		if (of_device_is_compatible(dn, "CBEA,platform-spider-pic")) {
-			if (of_address_to_resource(dn, 0, &r)) {
-				printk(KERN_WARNING "spider-pic: Failed\n");
-				continue;
-			}
-		} else if (of_device_is_compatible(dn, "sti,platform-spider-pic")
-			   && (chip < 2)) {
-			static long hard_coded_pics[] =
-				{ 0x24000008000ul, 0x34000008000ul};
-			r.start = hard_coded_pics[chip];
-		} else
-			continue;
-		spider_init_one(dn, chip++, r.start);
-	}
-}
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 7bd0b563e163..3c8624870967 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -23,7 +23,6 @@
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
 #include <asm/spu_csa.h>
-#include <asm/xmon.h>
 #include <asm/kexec.h>
 
 const struct spu_management_ops *spu_management_ops;
@@ -326,12 +325,6 @@ spu_irq_class_1(int irq, void *data)
 	if (stat & CLASS1_STORAGE_FAULT_INTR)
 		__spu_trap_data_map(spu, dar, dsisr);
 
-	if (stat & CLASS1_LS_COMPARE_SUSPEND_ON_GET_INTR)
-		;
-
-	if (stat & CLASS1_LS_COMPARE_SUSPEND_ON_PUT_INTR)
-		;
-
 	spu->class_1_dsisr = 0;
 	spu->class_1_dar = 0;
 
@@ -471,7 +464,7 @@ void spu_init_channels(struct spu *spu)
 }
 EXPORT_SYMBOL_GPL(spu_init_channels);
 
-static struct bus_type spu_subsys = {
+static const struct bus_type spu_subsys = {
 	.name = "spu",
 	.dev_name = "spu",
 };
@@ -733,7 +726,7 @@ static inline void crash_register_spus(struct list_head *list)
 }
 #endif
 
-static void spu_shutdown(void)
+static void spu_shutdown(void *data)
 {
 	struct spu *spu;
 
@@ -745,10 +738,14 @@ static void spu_shutdown(void)
 	mutex_unlock(&spu_full_list_mutex);
 }
 
-static struct syscore_ops spu_syscore_ops = {
+static const struct syscore_ops spu_syscore_ops = {
 	.shutdown = spu_shutdown,
 };
 
+static struct syscore spu_syscore = {
+	.ops = &spu_syscore_ops,
+};
+
 static int __init init_spu_base(void)
 {
 	int i, ret = 0;
@@ -778,11 +775,10 @@ static int __init init_spu_base(void)
 		fb_append_extra_logo(&logo_spe_clut224, ret);
 
 	mutex_lock(&spu_full_list_mutex);
-	xmon_register_spus(&spu_full_list);
 	crash_register_spus(&spu_full_list);
 	mutex_unlock(&spu_full_list_mutex);
 	spu_add_dev_attr(&dev_attr_stat);
-	register_syscore_ops(&spu_syscore_ops);
+	register_syscore(&spu_syscore);
 
 	spu_init_affinity();
 
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
deleted file mode 100644
index 74567b32c48c..000000000000
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ /dev/null
@@ -1,529 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * spu management operations for of based platforms
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- * Copyright 2006 Sony Corp.
- * (C) Copyright 2007 TOSHIBA CORPORATION
- */
-
-#include <linux/interrupt.h>
-#include <linux/list.h>
-#include <linux/export.h>
-#include <linux/ptrace.h>
-#include <linux/wait.h>
-#include <linux/mm.h>
-#include <linux/io.h>
-#include <linux/mutex.h>
-#include <linux/device.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-
-#include <asm/spu.h>
-#include <asm/spu_priv1.h>
-#include <asm/firmware.h>
-
-#include "spufs/spufs.h"
-#include "interrupt.h"
-
-struct device_node *spu_devnode(struct spu *spu)
-{
-	return spu->devnode;
-}
-
-EXPORT_SYMBOL_GPL(spu_devnode);
-
-static u64 __init find_spu_unit_number(struct device_node *spe)
-{
-	const unsigned int *prop;
-	int proplen;
-
-	/* new device trees should provide the physical-id attribute */
-	prop = of_get_property(spe, "physical-id", &proplen);
-	if (proplen == 4)
-		return (u64)*prop;
-
-	/* celleb device tree provides the unit-id */
-	prop = of_get_property(spe, "unit-id", &proplen);
-	if (proplen == 4)
-		return (u64)*prop;
-
-	/* legacy device trees provide the id in the reg attribute */
-	prop = of_get_property(spe, "reg", &proplen);
-	if (proplen == 4)
-		return (u64)*prop;
-
-	return 0;
-}
-
-static void spu_unmap(struct spu *spu)
-{
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
-		iounmap(spu->priv1);
-	iounmap(spu->priv2);
-	iounmap(spu->problem);
-	iounmap((__force u8 __iomem *)spu->local_store);
-}
-
-static int __init spu_map_interrupts_old(struct spu *spu,
-	struct device_node *np)
-{
-	unsigned int isrc;
-	const u32 *tmp;
-	int nid;
-
-	/* Get the interrupt source unit from the device-tree */
-	tmp = of_get_property(np, "isrc", NULL);
-	if (!tmp)
-		return -ENODEV;
-	isrc = tmp[0];
-
-	tmp = of_get_property(np->parent->parent, "node-id", NULL);
-	if (!tmp) {
-		printk(KERN_WARNING "%s: can't find node-id\n", __func__);
-		nid = spu->node;
-	} else
-		nid = tmp[0];
-
-	/* Add the node number */
-	isrc |= nid << IIC_IRQ_NODE_SHIFT;
-
-	/* Now map interrupts of all 3 classes */
-	spu->irqs[0] = irq_create_mapping(NULL, IIC_IRQ_CLASS_0 | isrc);
-	spu->irqs[1] = irq_create_mapping(NULL, IIC_IRQ_CLASS_1 | isrc);
-	spu->irqs[2] = irq_create_mapping(NULL, IIC_IRQ_CLASS_2 | isrc);
-
-	/* Right now, we only fail if class 2 failed */
-	if (!spu->irqs[2])
-		return -EINVAL;
-
-	return 0;
-}
-
-static void __iomem * __init spu_map_prop_old(struct spu *spu,
-					      struct device_node *n,
-					      const char *name)
-{
-	const struct address_prop {
-		unsigned long address;
-		unsigned int len;
-	} __attribute__((packed)) *prop;
-	int proplen;
-
-	prop = of_get_property(n, name, &proplen);
-	if (prop == NULL || proplen != sizeof (struct address_prop))
-		return NULL;
-
-	return ioremap(prop->address, prop->len);
-}
-
-static int __init spu_map_device_old(struct spu *spu)
-{
-	struct device_node *node = spu->devnode;
-	const char *prop;
-	int ret;
-
-	ret = -ENODEV;
-	spu->name = of_get_property(node, "name", NULL);
-	if (!spu->name)
-		goto out;
-
-	prop = of_get_property(node, "local-store", NULL);
-	if (!prop)
-		goto out;
-	spu->local_store_phys = *(unsigned long *)prop;
-
-	/* we use local store as ram, not io memory */
-	spu->local_store = (void __force *)
-		spu_map_prop_old(spu, node, "local-store");
-	if (!spu->local_store)
-		goto out;
-
-	prop = of_get_property(node, "problem", NULL);
-	if (!prop)
-		goto out_unmap;
-	spu->problem_phys = *(unsigned long *)prop;
-
-	spu->problem = spu_map_prop_old(spu, node, "problem");
-	if (!spu->problem)
-		goto out_unmap;
-
-	spu->priv2 = spu_map_prop_old(spu, node, "priv2");
-	if (!spu->priv2)
-		goto out_unmap;
-
-	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
-		spu->priv1 = spu_map_prop_old(spu, node, "priv1");
-		if (!spu->priv1)
-			goto out_unmap;
-	}
-
-	ret = 0;
-	goto out;
-
-out_unmap:
-	spu_unmap(spu);
-out:
-	return ret;
-}
-
-static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
-{
-	int i;
-
-	for (i=0; i < 3; i++) {
-		spu->irqs[i] = irq_of_parse_and_map(np, i);
-		if (!spu->irqs[i])
-			goto err;
-	}
-	return 0;
-
-err:
-	pr_debug("failed to map irq %x for spu %s\n", i, spu->name);
-	for (; i >= 0; i--) {
-		if (spu->irqs[i])
-			irq_dispose_mapping(spu->irqs[i]);
-	}
-	return -EINVAL;
-}
-
-static int __init spu_map_resource(struct spu *spu, int nr,
-			    void __iomem** virt, unsigned long *phys)
-{
-	struct device_node *np = spu->devnode;
-	struct resource resource = { };
-	unsigned long len;
-	int ret;
-
-	ret = of_address_to_resource(np, nr, &resource);
-	if (ret)
-		return ret;
-	if (phys)
-		*phys = resource.start;
-	len = resource_size(&resource);
-	*virt = ioremap(resource.start, len);
-	if (!*virt)
-		return -EINVAL;
-	return 0;
-}
-
-static int __init spu_map_device(struct spu *spu)
-{
-	struct device_node *np = spu->devnode;
-	int ret = -ENODEV;
-
-	spu->name = of_get_property(np, "name", NULL);
-	if (!spu->name)
-		goto out;
-
-	ret = spu_map_resource(spu, 0, (void __iomem**)&spu->local_store,
-			       &spu->local_store_phys);
-	if (ret) {
-		pr_debug("spu_new: failed to map %pOF resource 0\n",
-			 np);
-		goto out;
-	}
-	ret = spu_map_resource(spu, 1, (void __iomem**)&spu->problem,
-			       &spu->problem_phys);
-	if (ret) {
-		pr_debug("spu_new: failed to map %pOF resource 1\n",
-			 np);
-		goto out_unmap;
-	}
-	ret = spu_map_resource(spu, 2, (void __iomem**)&spu->priv2, NULL);
-	if (ret) {
-		pr_debug("spu_new: failed to map %pOF resource 2\n",
-			 np);
-		goto out_unmap;
-	}
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
-		ret = spu_map_resource(spu, 3,
-			       (void __iomem**)&spu->priv1, NULL);
-	if (ret) {
-		pr_debug("spu_new: failed to map %pOF resource 3\n",
-			 np);
-		goto out_unmap;
-	}
-	pr_debug("spu_new: %pOF maps:\n", np);
-	pr_debug("  local store   : 0x%016lx -> 0x%p\n",
-		 spu->local_store_phys, spu->local_store);
-	pr_debug("  problem state : 0x%016lx -> 0x%p\n",
-		 spu->problem_phys, spu->problem);
-	pr_debug("  priv2         :                       0x%p\n", spu->priv2);
-	pr_debug("  priv1         :                       0x%p\n", spu->priv1);
-
-	return 0;
-
-out_unmap:
-	spu_unmap(spu);
-out:
-	pr_debug("failed to map spe %s: %d\n", spu->name, ret);
-	return ret;
-}
-
-static int __init of_enumerate_spus(int (*fn)(void *data))
-{
-	int ret;
-	struct device_node *node;
-	unsigned int n = 0;
-
-	ret = -ENODEV;
-	for_each_node_by_type(node, "spe") {
-		ret = fn(node);
-		if (ret) {
-			printk(KERN_WARNING "%s: Error initializing %pOFn\n",
-				__func__, node);
-			of_node_put(node);
-			break;
-		}
-		n++;
-	}
-	return ret ? ret : n;
-}
-
-static int __init of_create_spu(struct spu *spu, void *data)
-{
-	int ret;
-	struct device_node *spe = (struct device_node *)data;
-	static int legacy_map = 0, legacy_irq = 0;
-
-	spu->devnode = of_node_get(spe);
-	spu->spe_id = find_spu_unit_number(spe);
-
-	spu->node = of_node_to_nid(spe);
-	if (spu->node >= MAX_NUMNODES) {
-		printk(KERN_WARNING "SPE %pOF on node %d ignored,"
-		       " node number too big\n", spe, spu->node);
-		printk(KERN_WARNING "Check if CONFIG_NUMA is enabled.\n");
-		ret = -ENODEV;
-		goto out;
-	}
-
-	ret = spu_map_device(spu);
-	if (ret) {
-		if (!legacy_map) {
-			legacy_map = 1;
-			printk(KERN_WARNING "%s: Legacy device tree found, "
-				"trying to map old style\n", __func__);
-		}
-		ret = spu_map_device_old(spu);
-		if (ret) {
-			printk(KERN_ERR "Unable to map %s\n",
-				spu->name);
-			goto out;
-		}
-	}
-
-	ret = spu_map_interrupts(spu, spe);
-	if (ret) {
-		if (!legacy_irq) {
-			legacy_irq = 1;
-			printk(KERN_WARNING "%s: Legacy device tree found, "
-				"trying old style irq\n", __func__);
-		}
-		ret = spu_map_interrupts_old(spu, spe);
-		if (ret) {
-			printk(KERN_ERR "%s: could not map interrupts\n",
-				spu->name);
-			goto out_unmap;
-		}
-	}
-
-	pr_debug("Using SPE %s %p %p %p %p %d\n", spu->name,
-		spu->local_store, spu->problem, spu->priv1,
-		spu->priv2, spu->number);
-	goto out;
-
-out_unmap:
-	spu_unmap(spu);
-out:
-	return ret;
-}
-
-static int of_destroy_spu(struct spu *spu)
-{
-	spu_unmap(spu);
-	of_node_put(spu->devnode);
-	return 0;
-}
-
-static void enable_spu_by_master_run(struct spu_context *ctx)
-{
-	ctx->ops->master_start(ctx);
-}
-
-static void disable_spu_by_master_run(struct spu_context *ctx)
-{
-	ctx->ops->master_stop(ctx);
-}
-
-/* Hardcoded affinity idxs for qs20 */
-#define QS20_SPES_PER_BE 8
-static int qs20_reg_idxs[QS20_SPES_PER_BE] =   { 0, 2, 4, 6, 7, 5, 3, 1 };
-static int qs20_reg_memory[QS20_SPES_PER_BE] = { 1, 1, 0, 0, 0, 0, 0, 0 };
-
-static struct spu *__init spu_lookup_reg(int node, u32 reg)
-{
-	struct spu *spu;
-	const u32 *spu_reg;
-
-	list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
-		spu_reg = of_get_property(spu_devnode(spu), "reg", NULL);
-		if (*spu_reg == reg)
-			return spu;
-	}
-	return NULL;
-}
-
-static void __init init_affinity_qs20_harcoded(void)
-{
-	int node, i;
-	struct spu *last_spu, *spu;
-	u32 reg;
-
-	for (node = 0; node < MAX_NUMNODES; node++) {
-		last_spu = NULL;
-		for (i = 0; i < QS20_SPES_PER_BE; i++) {
-			reg = qs20_reg_idxs[i];
-			spu = spu_lookup_reg(node, reg);
-			if (!spu)
-				continue;
-			spu->has_mem_affinity = qs20_reg_memory[reg];
-			if (last_spu)
-				list_add_tail(&spu->aff_list,
-						&last_spu->aff_list);
-			last_spu = spu;
-		}
-	}
-}
-
-static int __init of_has_vicinity(void)
-{
-	struct device_node *dn;
-
-	for_each_node_by_type(dn, "spe") {
-		if (of_property_present(dn, "vicinity"))  {
-			of_node_put(dn);
-			return 1;
-		}
-	}
-	return 0;
-}
-
-static struct spu *__init devnode_spu(int cbe, struct device_node *dn)
-{
-	struct spu *spu;
-
-	list_for_each_entry(spu, &cbe_spu_info[cbe].spus, cbe_list)
-		if (spu_devnode(spu) == dn)
-			return spu;
-	return NULL;
-}
-
-static struct spu * __init
-neighbour_spu(int cbe, struct device_node *target, struct device_node *avoid)
-{
-	struct spu *spu;
-	struct device_node *spu_dn;
-	const phandle *vic_handles;
-	int lenp, i;
-
-	list_for_each_entry(spu, &cbe_spu_info[cbe].spus, cbe_list) {
-		spu_dn = spu_devnode(spu);
-		if (spu_dn == avoid)
-			continue;
-		vic_handles = of_get_property(spu_dn, "vicinity", &lenp);
-		for (i=0; i < (lenp / sizeof(phandle)); i++) {
-			if (vic_handles[i] == target->phandle)
-				return spu;
-		}
-	}
-	return NULL;
-}
-
-static void __init init_affinity_node(int cbe)
-{
-	struct spu *spu, *last_spu;
-	struct device_node *vic_dn, *last_spu_dn;
-	phandle avoid_ph;
-	const phandle *vic_handles;
-	int lenp, i, added;
-
-	last_spu = list_first_entry(&cbe_spu_info[cbe].spus, struct spu,
-								cbe_list);
-	avoid_ph = 0;
-	for (added = 1; added < cbe_spu_info[cbe].n_spus; added++) {
-		last_spu_dn = spu_devnode(last_spu);
-		vic_handles = of_get_property(last_spu_dn, "vicinity", &lenp);
-
-		/*
-		 * Walk through each phandle in vicinity property of the spu
-		 * (typically two vicinity phandles per spe node)
-		 */
-		for (i = 0; i < (lenp / sizeof(phandle)); i++) {
-			if (vic_handles[i] == avoid_ph)
-				continue;
-
-			vic_dn = of_find_node_by_phandle(vic_handles[i]);
-			if (!vic_dn)
-				continue;
-
-			if (of_node_name_eq(vic_dn, "spe") ) {
-				spu = devnode_spu(cbe, vic_dn);
-				avoid_ph = last_spu_dn->phandle;
-			} else {
-				/*
-				 * "mic-tm" and "bif0" nodes do not have
-				 * vicinity property. So we need to find the
-				 * spe which has vic_dn as neighbour, but
-				 * skipping the one we came from (last_spu_dn)
-				 */
-				spu = neighbour_spu(cbe, vic_dn, last_spu_dn);
-				if (!spu)
-					continue;
-				if (of_node_name_eq(vic_dn, "mic-tm")) {
-					last_spu->has_mem_affinity = 1;
-					spu->has_mem_affinity = 1;
-				}
-				avoid_ph = vic_dn->phandle;
-			}
-
-			of_node_put(vic_dn);
-
-			list_add_tail(&spu->aff_list, &last_spu->aff_list);
-			last_spu = spu;
-			break;
-		}
-	}
-}
-
-static void __init init_affinity_fw(void)
-{
-	int cbe;
-
-	for (cbe = 0; cbe < MAX_NUMNODES; cbe++)
-		init_affinity_node(cbe);
-}
-
-static int __init init_affinity(void)
-{
-	if (of_has_vicinity()) {
-		init_affinity_fw();
-	} else {
-		if (of_machine_is_compatible("IBM,CPBW-1.0"))
-			init_affinity_qs20_harcoded();
-		else
-			printk("No affinity configuration found\n");
-	}
-
-	return 0;
-}
-
-const struct spu_management_ops spu_management_of_ops = {
-	.enumerate_spus = of_enumerate_spus,
-	.create_spu = of_create_spu,
-	.destroy_spu = of_destroy_spu,
-	.enable_spu = enable_spu_by_master_run,
-	.disable_spu = disable_spu_by_master_run,
-	.init_affinity = init_affinity,
-};
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.c b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
deleted file mode 100644
index d150e3987304..000000000000
--- a/arch/powerpc/platforms/cell/spu_priv1_mmio.c
+++ /dev/null
@@ -1,167 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * spu hypervisor abstraction for direct hardware access.
- *
- *  (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *  Copyright 2006 Sony Corp.
- */
-
-#include <linux/interrupt.h>
-#include <linux/list.h>
-#include <linux/ptrace.h>
-#include <linux/wait.h>
-#include <linux/mm.h>
-#include <linux/io.h>
-#include <linux/mutex.h>
-#include <linux/device.h>
-#include <linux/sched.h>
-
-#include <asm/spu.h>
-#include <asm/spu_priv1.h>
-#include <asm/firmware.h>
-
-#include "interrupt.h"
-#include "spu_priv1_mmio.h"
-
-static void int_mask_and(struct spu *spu, int class, u64 mask)
-{
-	u64 old_mask;
-
-	old_mask = in_be64(&spu->priv1->int_mask_RW[class]);
-	out_be64(&spu->priv1->int_mask_RW[class], old_mask & mask);
-}
-
-static void int_mask_or(struct spu *spu, int class, u64 mask)
-{
-	u64 old_mask;
-
-	old_mask = in_be64(&spu->priv1->int_mask_RW[class]);
-	out_be64(&spu->priv1->int_mask_RW[class], old_mask | mask);
-}
-
-static void int_mask_set(struct spu *spu, int class, u64 mask)
-{
-	out_be64(&spu->priv1->int_mask_RW[class], mask);
-}
-
-static u64 int_mask_get(struct spu *spu, int class)
-{
-	return in_be64(&spu->priv1->int_mask_RW[class]);
-}
-
-static void int_stat_clear(struct spu *spu, int class, u64 stat)
-{
-	out_be64(&spu->priv1->int_stat_RW[class], stat);
-}
-
-static u64 int_stat_get(struct spu *spu, int class)
-{
-	return in_be64(&spu->priv1->int_stat_RW[class]);
-}
-
-static void cpu_affinity_set(struct spu *spu, int cpu)
-{
-	u64 target;
-	u64 route;
-
-	if (nr_cpus_node(spu->node)) {
-		const struct cpumask *spumask = cpumask_of_node(spu->node),
-			*cpumask = cpumask_of_node(cpu_to_node(cpu));
-
-		if (!cpumask_intersects(spumask, cpumask))
-			return;
-	}
-
-	target = iic_get_target_id(cpu);
-	route = target << 48 | target << 32 | target << 16;
-	out_be64(&spu->priv1->int_route_RW, route);
-}
-
-static u64 mfc_dar_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->mfc_dar_RW);
-}
-
-static u64 mfc_dsisr_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->mfc_dsisr_RW);
-}
-
-static void mfc_dsisr_set(struct spu *spu, u64 dsisr)
-{
-	out_be64(&spu->priv1->mfc_dsisr_RW, dsisr);
-}
-
-static void mfc_sdr_setup(struct spu *spu)
-{
-	out_be64(&spu->priv1->mfc_sdr_RW, mfspr(SPRN_SDR1));
-}
-
-static void mfc_sr1_set(struct spu *spu, u64 sr1)
-{
-	out_be64(&spu->priv1->mfc_sr1_RW, sr1);
-}
-
-static u64 mfc_sr1_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->mfc_sr1_RW);
-}
-
-static void mfc_tclass_id_set(struct spu *spu, u64 tclass_id)
-{
-	out_be64(&spu->priv1->mfc_tclass_id_RW, tclass_id);
-}
-
-static u64 mfc_tclass_id_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->mfc_tclass_id_RW);
-}
-
-static void tlb_invalidate(struct spu *spu)
-{
-	out_be64(&spu->priv1->tlb_invalidate_entry_W, 0ul);
-}
-
-static void resource_allocation_groupID_set(struct spu *spu, u64 id)
-{
-	out_be64(&spu->priv1->resource_allocation_groupID_RW, id);
-}
-
-static u64 resource_allocation_groupID_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->resource_allocation_groupID_RW);
-}
-
-static void resource_allocation_enable_set(struct spu *spu, u64 enable)
-{
-	out_be64(&spu->priv1->resource_allocation_enable_RW, enable);
-}
-
-static u64 resource_allocation_enable_get(struct spu *spu)
-{
-	return in_be64(&spu->priv1->resource_allocation_enable_RW);
-}
-
-const struct spu_priv1_ops spu_priv1_mmio_ops =
-{
-	.int_mask_and = int_mask_and,
-	.int_mask_or = int_mask_or,
-	.int_mask_set = int_mask_set,
-	.int_mask_get = int_mask_get,
-	.int_stat_clear = int_stat_clear,
-	.int_stat_get = int_stat_get,
-	.cpu_affinity_set = cpu_affinity_set,
-	.mfc_dar_get = mfc_dar_get,
-	.mfc_dsisr_get = mfc_dsisr_get,
-	.mfc_dsisr_set = mfc_dsisr_set,
-	.mfc_sdr_setup = mfc_sdr_setup,
-	.mfc_sr1_set = mfc_sr1_set,
-	.mfc_sr1_get = mfc_sr1_get,
-	.mfc_tclass_id_set = mfc_tclass_id_set,
-	.mfc_tclass_id_get = mfc_tclass_id_get,
-	.tlb_invalidate = tlb_invalidate,
-	.resource_allocation_groupID_set = resource_allocation_groupID_set,
-	.resource_allocation_groupID_get = resource_allocation_groupID_get,
-	.resource_allocation_enable_set = resource_allocation_enable_set,
-	.resource_allocation_enable_get = resource_allocation_enable_get,
-};
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.h b/arch/powerpc/platforms/cell/spu_priv1_mmio.h
deleted file mode 100644
index 04f0db339dc1..000000000000
--- a/arch/powerpc/platforms/cell/spu_priv1_mmio.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * spu hypervisor abstraction for direct hardware access.
- *
- *  Copyright (C) 2006 Sony Computer Entertainment Inc.
- *  Copyright 2006 Sony Corp.
- */
-
-#ifndef SPU_PRIV1_MMIO_H
-#define SPU_PRIV1_MMIO_H
-
-struct device_node *spu_devnode(struct spu *spu);
-
-#endif /* SPU_PRIV1_MMIO_H */
diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c
index 87ad7d563cfa..000894e07b02 100644
--- a/arch/powerpc/platforms/cell/spu_syscalls.c
+++ b/arch/powerpc/platforms/cell/spu_syscalls.c
@@ -36,6 +36,9 @@ static inline struct spufs_calls *spufs_calls_get(void)
 
 static inline void spufs_calls_put(struct spufs_calls *calls)
 {
+	if (!calls)
+		return;
+
 	BUG_ON(calls != spufs_calls);
 
 	/* we don't need to rcu this, as we hold a reference to the module */
@@ -53,82 +56,55 @@ static inline void spufs_calls_put(struct spufs_calls *calls) { }
 
 #endif /* CONFIG_SPU_FS_MODULE */
 
+DEFINE_CLASS(spufs_calls, struct spufs_calls *, spufs_calls_put(_T), spufs_calls_get(), void)
+
 SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags,
 	umode_t, mode, int, neighbor_fd)
 {
-	long ret;
-	struct spufs_calls *calls;
-
-	calls = spufs_calls_get();
+	CLASS(spufs_calls, calls)();
 	if (!calls)
 		return -ENOSYS;
 
 	if (flags & SPU_CREATE_AFFINITY_SPU) {
-		struct fd neighbor = fdget(neighbor_fd);
-		ret = -EBADF;
-		if (neighbor.file) {
-			ret = calls->create_thread(name, flags, mode, neighbor.file);
-			fdput(neighbor);
-		}
-	} else
-		ret = calls->create_thread(name, flags, mode, NULL);
-
-	spufs_calls_put(calls);
-	return ret;
+		CLASS(fd, neighbor)(neighbor_fd);
+		if (fd_empty(neighbor))
+			return -EBADF;
+		return calls->create_thread(name, flags, mode, fd_file(neighbor));
+	} else {
+		return calls->create_thread(name, flags, mode, NULL);
+	}
 }
 
 SYSCALL_DEFINE3(spu_run,int, fd, __u32 __user *, unpc, __u32 __user *, ustatus)
 {
-	long ret;
-	struct fd arg;
-	struct spufs_calls *calls;
-
-	calls = spufs_calls_get();
+	CLASS(spufs_calls, calls)();
 	if (!calls)
 		return -ENOSYS;
 
-	ret = -EBADF;
-	arg = fdget(fd);
-	if (arg.file) {
-		ret = calls->spu_run(arg.file, unpc, ustatus);
-		fdput(arg);
-	}
+	CLASS(fd, arg)(fd);
+	if (fd_empty(arg))
+		return -EBADF;
 
-	spufs_calls_put(calls);
-	return ret;
+	return calls->spu_run(fd_file(arg), unpc, ustatus);
 }
 
 #ifdef CONFIG_COREDUMP
 int elf_coredump_extra_notes_size(void)
 {
-	struct spufs_calls *calls;
-	int ret;
-
-	calls = spufs_calls_get();
+	CLASS(spufs_calls, calls)();
 	if (!calls)
 		return 0;
 
-	ret = calls->coredump_extra_notes_size();
-
-	spufs_calls_put(calls);
-
-	return ret;
+	return calls->coredump_extra_notes_size();
 }
 
 int elf_coredump_extra_notes_write(struct coredump_params *cprm)
 {
-	struct spufs_calls *calls;
-	int ret;
-
-	calls = spufs_calls_get();
+	CLASS(spufs_calls, calls)();
 	if (!calls)
 		return 0;
 
-	ret = calls->coredump_extra_notes_write(cprm);
-
-	spufs_calls_put(calls);
-
-	return ret;
+	return calls->coredump_extra_notes_write(cprm);
 }
 #endif
 
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 1a587618015c..301ee7d8b7df 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -66,18 +66,19 @@ static int match_context(const void *v, struct file *file, unsigned fd)
  */
 static struct spu_context *coredump_next_context(int *fd)
 {
-	struct spu_context *ctx;
+	struct spu_context *ctx = NULL;
 	struct file *file;
 	int n = iterate_fd(current->files, *fd, match_context, NULL);
 	if (!n)
 		return NULL;
 	*fd = n - 1;
 
-	rcu_read_lock();
-	file = lookup_fd_rcu(*fd);
-	ctx = SPUFS_I(file_inode(file))->i_ctx;
-	get_spu_context(ctx);
-	rcu_read_unlock();
+	file = fget_raw(*fd);
+	if (file) {
+		ctx = SPUFS_I(file_inode(file))->i_ctx;
+		get_spu_context(ctx);
+		fput(file);
+	}
 
 	return ctx;
 }
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 02a8158c469d..ce839783c0df 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -453,7 +453,6 @@ static const struct file_operations spufs_cntl_fops = {
 	.release = spufs_cntl_release,
 	.read = simple_attr_read,
 	.write = simple_attr_write,
-	.llseek	= no_llseek,
 	.mmap = spufs_cntl_mmap,
 };
 
@@ -634,7 +633,6 @@ static ssize_t spufs_mbox_read(struct file *file, char __user *buf,
 static const struct file_operations spufs_mbox_fops = {
 	.open	= spufs_pipe_open,
 	.read	= spufs_mbox_read,
-	.llseek	= no_llseek,
 };
 
 static ssize_t spufs_mbox_stat_read(struct file *file, char __user *buf,
@@ -664,7 +662,6 @@ static ssize_t spufs_mbox_stat_read(struct file *file, char __user *buf,
 static const struct file_operations spufs_mbox_stat_fops = {
 	.open	= spufs_pipe_open,
 	.read	= spufs_mbox_stat_read,
-	.llseek = no_llseek,
 };
 
 /* low-level ibox access function */
@@ -769,7 +766,6 @@ static const struct file_operations spufs_ibox_fops = {
 	.open	= spufs_pipe_open,
 	.read	= spufs_ibox_read,
 	.poll	= spufs_ibox_poll,
-	.llseek = no_llseek,
 };
 
 static ssize_t spufs_ibox_stat_read(struct file *file, char __user *buf,
@@ -797,7 +793,6 @@ static ssize_t spufs_ibox_stat_read(struct file *file, char __user *buf,
 static const struct file_operations spufs_ibox_stat_fops = {
 	.open	= spufs_pipe_open,
 	.read	= spufs_ibox_stat_read,
-	.llseek = no_llseek,
 };
 
 /* low-level mailbox write */
@@ -901,7 +896,6 @@ static const struct file_operations spufs_wbox_fops = {
 	.open	= spufs_pipe_open,
 	.write	= spufs_wbox_write,
 	.poll	= spufs_wbox_poll,
-	.llseek = no_llseek,
 };
 
 static ssize_t spufs_wbox_stat_read(struct file *file, char __user *buf,
@@ -929,7 +923,6 @@ static ssize_t spufs_wbox_stat_read(struct file *file, char __user *buf,
 static const struct file_operations spufs_wbox_stat_fops = {
 	.open	= spufs_pipe_open,
 	.read	= spufs_wbox_stat_read,
-	.llseek = no_llseek,
 };
 
 static int spufs_signal1_open(struct inode *inode, struct file *file)
@@ -1056,7 +1049,6 @@ static const struct file_operations spufs_signal1_fops = {
 	.read = spufs_signal1_read,
 	.write = spufs_signal1_write,
 	.mmap = spufs_signal1_mmap,
-	.llseek = no_llseek,
 };
 
 static const struct file_operations spufs_signal1_nosched_fops = {
@@ -1064,7 +1056,6 @@ static const struct file_operations spufs_signal1_nosched_fops = {
 	.release = spufs_signal1_release,
 	.write = spufs_signal1_write,
 	.mmap = spufs_signal1_mmap,
-	.llseek = no_llseek,
 };
 
 static int spufs_signal2_open(struct inode *inode, struct file *file)
@@ -1195,7 +1186,6 @@ static const struct file_operations spufs_signal2_fops = {
 	.read = spufs_signal2_read,
 	.write = spufs_signal2_write,
 	.mmap = spufs_signal2_mmap,
-	.llseek = no_llseek,
 };
 
 static const struct file_operations spufs_signal2_nosched_fops = {
@@ -1203,7 +1193,6 @@ static const struct file_operations spufs_signal2_nosched_fops = {
 	.release = spufs_signal2_release,
 	.write = spufs_signal2_write,
 	.mmap = spufs_signal2_mmap,
-	.llseek = no_llseek,
 };
 
 /*
@@ -1343,7 +1332,6 @@ static const struct file_operations spufs_mss_fops = {
 	.open	 = spufs_mss_open,
 	.release = spufs_mss_release,
 	.mmap	 = spufs_mss_mmap,
-	.llseek  = no_llseek,
 };
 
 static vm_fault_t
@@ -1401,7 +1389,6 @@ static const struct file_operations spufs_psmap_fops = {
 	.open	 = spufs_psmap_open,
 	.release = spufs_psmap_release,
 	.mmap	 = spufs_psmap_mmap,
-	.llseek  = no_llseek,
 };
 
 
@@ -1443,7 +1430,7 @@ static int spufs_mfc_open(struct inode *inode, struct file *file)
 	if (ctx->owner != current->mm)
 		return -EINVAL;
 
-	if (atomic_read(&inode->i_count) != 1)
+	if (icount_read(inode) != 1)
 		return -EBUSY;
 
 	mutex_lock(&ctx->mapping_lock);
@@ -1704,23 +1691,11 @@ static int spufs_mfc_flush(struct file *file, fl_owner_t id)
 
 	ret = spu_acquire(ctx);
 	if (ret)
-		goto out;
-#if 0
-/* this currently hangs */
-	ret = spufs_wait(ctx->mfc_wq,
-			 ctx->ops->set_mfc_query(ctx, ctx->tagwait, 2));
-	if (ret)
-		goto out;
-	ret = spufs_wait(ctx->mfc_wq,
-			 ctx->ops->read_mfc_tagstatus(ctx) == ctx->tagwait);
-	if (ret)
-		goto out;
-#else
-	ret = 0;
-#endif
+		return ret;
+
 	spu_release(ctx);
-out:
-	return ret;
+
+	return 0;
 }
 
 static int spufs_mfc_fsync(struct file *file, loff_t start, loff_t end, int datasync)
@@ -1744,7 +1719,6 @@ static const struct file_operations spufs_mfc_fops = {
 	.flush	 = spufs_mfc_flush,
 	.fsync	 = spufs_mfc_fsync,
 	.mmap	 = spufs_mfc_mmap,
-	.llseek  = no_llseek,
 };
 
 static int spufs_npc_set(void *data, u64 val)
@@ -2114,7 +2088,6 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
 static const struct file_operations spufs_dma_info_fops = {
 	.open = spufs_info_open,
 	.read = spufs_dma_info_read,
-	.llseek = no_llseek,
 };
 
 static void spufs_get_proxydma_info(struct spu_context *ctx,
@@ -2171,7 +2144,6 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf,
 static const struct file_operations spufs_proxydma_info_fops = {
 	.open = spufs_info_open,
 	.read = spufs_proxydma_info_read,
-	.llseek = no_llseek,
 };
 
 static int spufs_show_tid(struct seq_file *s, void *private)
@@ -2454,7 +2426,6 @@ static const struct file_operations spufs_switch_log_fops = {
 	.read		= spufs_switch_log_read,
 	.poll		= spufs_switch_log_poll,
 	.release	= spufs_switch_log_release,
-	.llseek		= no_llseek,
 };
 
 /**
diff --git a/arch/powerpc/platforms/cell/spufs/gang.c b/arch/powerpc/platforms/cell/spufs/gang.c
index 827d338deaf4..2c2999de6bfa 100644
--- a/arch/powerpc/platforms/cell/spufs/gang.c
+++ b/arch/powerpc/platforms/cell/spufs/gang.c
@@ -25,6 +25,7 @@ struct spu_gang *alloc_spu_gang(void)
 	mutex_init(&gang->aff_mutex);
 	INIT_LIST_HEAD(&gang->list);
 	INIT_LIST_HEAD(&gang->aff_list_head);
+	gang->alive = 1;
 
 out:
 	return gang;
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index ea807aa0c31a..577a00c25217 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -86,7 +86,7 @@ spufs_new_inode(struct super_block *sb, umode_t mode)
 	inode->i_mode = mode;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();
-	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
+	simple_inode_init_ts(inode);
 out:
 	return inode;
 }
@@ -127,7 +127,7 @@ spufs_new_file(struct super_block *sb, struct dentry *dentry,
 	inode->i_fop = fops;
 	inode->i_size = size;
 	inode->i_private = SPUFS_I(inode)->i_ctx = get_spu_context(ctx);
-	d_add(dentry, inode);
+	d_make_persistent(dentry, inode);
 out:
 	return ret;
 }
@@ -143,41 +143,13 @@ spufs_evict_inode(struct inode *inode)
 		put_spu_gang(ei->i_gang);
 }
 
-static void spufs_prune_dir(struct dentry *dir)
-{
-	struct dentry *dentry, *tmp;
-
-	inode_lock(d_inode(dir));
-	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
-		spin_lock(&dentry->d_lock);
-		if (simple_positive(dentry)) {
-			dget_dlock(dentry);
-			__d_drop(dentry);
-			spin_unlock(&dentry->d_lock);
-			simple_unlink(d_inode(dir), dentry);
-			/* XXX: what was dcache_lock protecting here? Other
-			 * filesystems (IB, configfs) release dcache_lock
-			 * before unlink */
-			dput(dentry);
-		} else {
-			spin_unlock(&dentry->d_lock);
-		}
-	}
-	shrink_dcache_parent(dir);
-	inode_unlock(d_inode(dir));
-}
-
 /* Caller must hold parent->i_mutex */
-static int spufs_rmdir(struct inode *parent, struct dentry *dir)
+static void spufs_rmdir(struct inode *parent, struct dentry *dir)
 {
-	/* remove all entries */
-	int res;
-	spufs_prune_dir(dir);
-	d_drop(dir);
-	res = simple_rmdir(parent, dir);
-	/* We have to give up the mm_struct */
-	spu_forget(SPUFS_I(d_inode(dir))->i_ctx);
-	return res;
+	struct spu_context *ctx = SPUFS_I(d_inode(dir))->i_ctx;
+
+	locked_recursive_removal(dir, NULL);
+	spu_forget(ctx);
 }
 
 static int spufs_fill_dir(struct dentry *dir,
@@ -191,6 +163,7 @@ static int spufs_fill_dir(struct dentry *dir,
 			return -ENOMEM;
 		ret = spufs_new_file(dir->d_sb, dentry, files->ops,
 					files->mode & mode, files->size, ctx);
+		dput(dentry);
 		if (ret)
 			return ret;
 		files++;
@@ -198,20 +171,36 @@ static int spufs_fill_dir(struct dentry *dir,
 	return 0;
 }
 
+static void unuse_gang(struct dentry *dir)
+{
+	struct inode *inode = dir->d_inode;
+	struct spu_gang *gang = SPUFS_I(inode)->i_gang;
+
+	if (gang) {
+		bool dead;
+
+		inode_lock(inode); // exclusion with spufs_create_context()
+		dead = !--gang->alive;
+		inode_unlock(inode);
+
+		if (dead)
+			simple_recursive_removal(dir, NULL);
+	}
+}
+
 static int spufs_dir_close(struct inode *inode, struct file *file)
 {
 	struct inode *parent;
 	struct dentry *dir;
-	int ret;
 
 	dir = file->f_path.dentry;
 	parent = d_inode(dir->d_parent);
 
 	inode_lock_nested(parent, I_MUTEX_PARENT);
-	ret = spufs_rmdir(parent, dir);
+	spufs_rmdir(parent, dir);
 	inode_unlock(parent);
-	WARN_ON(ret);
 
+	unuse_gang(dir->d_parent);
 	return dcache_dir_close(inode, file);
 }
 
@@ -251,11 +240,10 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags,
 
 	inode_lock(inode);
 
-	dget(dentry);
 	inc_nlink(dir);
 	inc_nlink(inode);
 
-	d_instantiate(dentry, inode);
+	d_make_persistent(dentry, inode);
 
 	if (flags & SPU_CREATE_NOSCHED)
 		ret = spufs_fill_dir(dentry, spufs_dir_nosched_contents,
@@ -267,32 +255,21 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags,
 		ret = spufs_fill_dir(dentry, spufs_dir_debug_contents,
 				mode, ctx);
 
+	inode_unlock(inode);
+
 	if (ret)
 		spufs_rmdir(dir, dentry);
 
-	inode_unlock(inode);
-
 	return ret;
 }
 
 static int spufs_context_open(const struct path *path)
 {
-	int ret;
-	struct file *filp;
-
-	ret = get_unused_fd_flags(0);
-	if (ret < 0)
-		return ret;
-
-	filp = dentry_open(path, O_RDONLY, current_cred());
-	if (IS_ERR(filp)) {
-		put_unused_fd(ret);
-		return PTR_ERR(filp);
-	}
-
-	filp->f_op = &spufs_context_fops;
-	fd_install(ret, filp);
-	return ret;
+	FD_PREPARE(fdf, 0, dentry_open(path, O_RDONLY, current_cred()));
+	if (fdf.err)
+		return fdf.err;
+	fd_prepare_file(fdf)->f_op = &spufs_context_fops;
+	return fd_publish(fdf);
 }
 
 static struct spu_context *
@@ -404,7 +381,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 {
 	int ret;
 	int affinity;
-	struct spu_gang *gang;
+	struct spu_gang *gang = SPUFS_I(inode)->i_gang;
 	struct spu_context *neighbor;
 	struct path path = {.mnt = mnt, .dentry = dentry};
 
@@ -419,11 +396,15 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 	if ((flags & SPU_CREATE_ISOLATE) && !isolated_loader)
 		return -ENODEV;
 
-	gang = NULL;
+	if (gang) {
+		if (!gang->alive)
+			return -ENOENT;
+		gang->alive++;
+	}
+
 	neighbor = NULL;
 	affinity = flags & (SPU_CREATE_AFFINITY_MEM | SPU_CREATE_AFFINITY_SPU);
 	if (affinity) {
-		gang = SPUFS_I(inode)->i_gang;
 		if (!gang)
 			return -EINVAL;
 		mutex_lock(&gang->aff_mutex);
@@ -435,8 +416,11 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 	}
 
 	ret = spufs_mkdir(inode, dentry, flags, mode & 0777);
-	if (ret)
+	if (ret) {
+		if (neighbor)
+			put_spu_context(neighbor);
 		goto out_aff_unlock;
+	}
 
 	if (affinity) {
 		spufs_set_affinity(flags, SPUFS_I(d_inode(dentry))->i_ctx,
@@ -447,11 +431,13 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 
 	ret = spufs_context_open(&path);
 	if (ret < 0)
-		WARN_ON(spufs_rmdir(inode, dentry));
+		spufs_rmdir(inode, dentry);
 
 out_aff_unlock:
 	if (affinity)
 		mutex_unlock(&gang->aff_mutex);
+	if (ret && gang)
+		gang->alive--; // can't reach 0
 	return ret;
 }
 
@@ -480,9 +466,9 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_op = &simple_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 
-	d_instantiate(dentry, inode);
 	inc_nlink(dir);
-	inc_nlink(d_inode(dentry));
+	inc_nlink(inode);
+	d_make_persistent(dentry, inode);
 	return ret;
 
 out_iput:
@@ -491,28 +477,32 @@ out:
 	return ret;
 }
 
-static int spufs_gang_open(const struct path *path)
+static int spufs_gang_close(struct inode *inode, struct file *file)
 {
-	int ret;
-	struct file *filp;
+	unuse_gang(file->f_path.dentry);
+	return dcache_dir_close(inode, file);
+}
 
-	ret = get_unused_fd_flags(0);
-	if (ret < 0)
-		return ret;
+static const struct file_operations spufs_gang_fops = {
+	.open		= dcache_dir_open,
+	.release	= spufs_gang_close,
+	.llseek		= dcache_dir_lseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= dcache_readdir,
+	.fsync		= noop_fsync,
+};
 
+static int spufs_gang_open(const struct path *path)
+{
 	/*
 	 * get references for dget and mntget, will be released
 	 * in error path of *_open().
 	 */
-	filp = dentry_open(path, O_RDONLY, current_cred());
-	if (IS_ERR(filp)) {
-		put_unused_fd(ret);
-		return PTR_ERR(filp);
-	}
-
-	filp->f_op = &simple_dir_operations;
-	fd_install(ret, filp);
-	return ret;
+	FD_PREPARE(fdf, 0, dentry_open(path, O_RDONLY, current_cred()));
+	if (fdf.err)
+		return fdf.err;
+	fd_prepare_file(fdf)->f_op = &spufs_gang_fops;
+	return fd_publish(fdf);
 }
 
 static int spufs_create_gang(struct inode *inode,
@@ -525,10 +515,8 @@ static int spufs_create_gang(struct inode *inode,
 	ret = spufs_mkgang(inode, dentry, mode & 0777);
 	if (!ret) {
 		ret = spufs_gang_open(&path);
-		if (ret < 0) {
-			int err = simple_rmdir(inode, dentry);
-			WARN_ON(err);
-		}
+		if (ret < 0)
+			unuse_gang(dentry);
 	}
 	return ret;
 }
@@ -767,7 +755,7 @@ static struct file_system_type spufs_type = {
 	.name = "spufs",
 	.init_fs_context = spufs_init_fs_context,
 	.parameters	= spufs_fs_parameters,
-	.kill_sb = kill_litter_super,
+	.kill_sb = kill_anon_super,
 };
 MODULE_ALIAS_FS("spufs");
 
@@ -821,6 +809,7 @@ static void __exit spufs_exit(void)
 }
 module_exit(spufs_exit);
 
+MODULE_DESCRIPTION("SPU file system");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arnd Bergmann <arndb@de.ibm.com>");
 
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 99bd027a7f7c..8e7ed010bfde 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -508,7 +508,7 @@ static void __spu_del_from_rq(struct spu_context *ctx)
 
 	if (!list_empty(&ctx->rq)) {
 		if (!--spu_prio->nr_waiting)
-			del_timer(&spusched_timer);
+			timer_delete(&spusched_timer);
 		list_del_init(&ctx->rq);
 
 		if (list_empty(&spu_prio->runq[prio]))
@@ -868,7 +868,7 @@ static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio)
 }
 
 /**
- * spu_deactivate - unbind a context from it's physical spu
+ * spu_deactivate - unbind a context from its physical spu
  * @ctx:	spu context to unbind
  *
  * Unbind @ctx from the physical spu it is running on and schedule
@@ -1126,8 +1126,8 @@ void spu_sched_exit(void)
 
 	remove_proc_entry("spu_loadavg", NULL);
 
-	del_timer_sync(&spusched_timer);
-	del_timer_sync(&spuloadavg_timer);
+	timer_delete_sync(&spusched_timer);
+	timer_delete_sync(&spuloadavg_timer);
 	kthread_stop(spusched_task);
 
 	for (node = 0; node < MAX_NUMNODES; node++) {
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 84958487f696..d33787c57c39 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -151,6 +151,8 @@ struct spu_gang {
 	int aff_flags;
 	struct spu *aff_ref_spu;
 	atomic_t aff_sched_count;
+
+	int alive;
 };
 
 /* Flag bits for spu_gang aff_flags */
diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index 157e046e6e93..ea4ba1b6ce6a 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -67,11 +67,11 @@ static long do_spu_create(const char __user *pathname, unsigned int flags,
 	struct dentry *dentry;
 	int ret;
 
-	dentry = user_path_create(AT_FDCWD, pathname, &path, LOOKUP_DIRECTORY);
+	dentry = start_creating_user_path(AT_FDCWD, pathname, &path, LOOKUP_DIRECTORY);
 	ret = PTR_ERR(dentry);
 	if (!IS_ERR(dentry)) {
 		ret = spufs_create(&path, dentry, flags, mode, neighbor);
-		done_path_create(&path, dentry);
+		end_creating_path(&path, dentry);
 	}
 
 	return ret;
diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c
index 0eedae96498c..d3bf56a46656 100644
--- a/arch/powerpc/platforms/chrp/nvram.c
+++ b/arch/powerpc/platforms/chrp/nvram.c
@@ -92,4 +92,5 @@ void __init chrp_nvram_init(void)
 	return;
 }
 
+MODULE_DESCRIPTION("PPC NVRAM device driver");
 MODULE_LICENSE("GPL v2");
diff --git a/arch/powerpc/platforms/chrp/pegasos_eth.c b/arch/powerpc/platforms/chrp/pegasos_eth.c
index 5c4f1a9ca154..6f4a41a9352a 100644
--- a/arch/powerpc/platforms/chrp/pegasos_eth.c
+++ b/arch/powerpc/platforms/chrp/pegasos_eth.c
@@ -14,7 +14,7 @@
 #include <linux/ioport.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
-#include <linux/mv643xx.h>
+#include <linux/mv643xx_eth.h>
 #include <linux/pci.h>
 
 #define PEGASOS2_MARVELL_REGBASE 		(0xf1000000)
@@ -25,12 +25,15 @@
 #define PEGASOS2_SRAM_BASE_ETH_PORT0			(PEGASOS2_SRAM_BASE)
 #define PEGASOS2_SRAM_BASE_ETH_PORT1			(PEGASOS2_SRAM_BASE_ETH_PORT0 + (PEGASOS2_SRAM_SIZE / 2) )
 
-
 #define PEGASOS2_SRAM_RXRING_SIZE		(PEGASOS2_SRAM_SIZE/4)
 #define PEGASOS2_SRAM_TXRING_SIZE		(PEGASOS2_SRAM_SIZE/4)
 
 #undef BE_VERBOSE
 
+#define MV64340_BASE_ADDR_ENABLE                                    0x278
+#define MV64340_INTEGRATED_SRAM_BASE_ADDR                           0x268
+#define MV64340_SRAM_CONFIG                                         0x380
+
 static struct resource mv643xx_eth_shared_resources[] = {
 	[0] = {
 		.name	= "ethernet shared base",
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index 36ee3a5056a1..c1bfa4c3444c 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -486,7 +486,7 @@ static void __init chrp_find_8259(void)
 	i8259_init(pic, chrp_int_ack);
 	if (ppc_md.get_irq == NULL) {
 		ppc_md.get_irq = i8259_irq;
-		irq_set_default_host(i8259_get_host());
+		irq_set_default_domain(i8259_get_host());
 	}
 	if (chrp_mpic != NULL) {
 		cascade_irq = irq_of_parse_and_map(pic, 0);
diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig
index a57424d6ef20..c6adff216fe6 100644
--- a/arch/powerpc/platforms/embedded6xx/Kconfig
+++ b/arch/powerpc/platforms/embedded6xx/Kconfig
@@ -10,7 +10,7 @@ config LINKSTATION
 	select FSL_SOC
 	select PPC_UDBG_16550 if SERIAL_8250
 	select DEFAULT_UIMAGE
-	select MPC10X_BRIDGE
+	imply MPC10X_BRIDGE if PCI
 	help
 	  Select LINKSTATION if configuring for one of PPC- (MPC8241)
 	  based NAS systems from Buffalo Technology. So far only
@@ -24,7 +24,7 @@ config STORCENTER
 	select MPIC
 	select FSL_SOC
 	select PPC_UDBG_16550 if SERIAL_8250
-	select MPC10X_BRIDGE
+	imply MPC10X_BRIDGE if PCI
 	help
 	  Select STORCENTER if configuring for the iomega StorCenter
 	  with an 8241 CPU in it.
diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
index 4d9200bdba78..91a8f0a7086e 100644
--- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
@@ -149,8 +149,9 @@ static struct irq_domain * __init flipper_pic_init(struct device_node *np)
 
 	__flipper_quiesce(io_base);
 
-	irq_domain = irq_domain_add_linear(np, FLIPPER_NR_IRQS,
-				  &flipper_irq_domain_ops, io_base);
+	irq_domain = irq_domain_create_linear(of_fwnode_handle(np),
+					      FLIPPER_NR_IRQS,
+					      &flipper_irq_domain_ops, io_base);
 	if (!irq_domain) {
 		pr_err("failed to allocate irq_domain\n");
 		return NULL;
@@ -172,7 +173,7 @@ unsigned int flipper_pic_get_irq(void)
 		return 0;	/* no more IRQs pending */
 
 	irq = __ffs(irq_status);
-	return irq_linear_revmap(flipper_irq_host, irq);
+	return irq_find_mapping(flipper_irq_host, irq);
 }
 
 /*
@@ -190,7 +191,7 @@ void __init flipper_pic_probe(void)
 	flipper_irq_host = flipper_pic_init(np);
 	BUG_ON(!flipper_irq_host);
 
-	irq_set_default_host(flipper_irq_host);
+	irq_set_default_domain(flipper_irq_host);
 
 	of_node_put(np);
 }
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index 4d2d92de30af..b57e87b0b3ce 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -175,8 +175,9 @@ static struct irq_domain *__init hlwd_pic_init(struct device_node *np)
 
 	__hlwd_quiesce(io_base);
 
-	irq_domain = irq_domain_add_linear(np, HLWD_NR_IRQS,
-					   &hlwd_irq_domain_ops, io_base);
+	irq_domain = irq_domain_create_linear(of_fwnode_handle(np),
+					      HLWD_NR_IRQS,
+					      &hlwd_irq_domain_ops, io_base);
 	if (!irq_domain) {
 		pr_err("failed to allocate irq_domain\n");
 		iounmap(io_base);
@@ -189,7 +190,7 @@ static struct irq_domain *__init hlwd_pic_init(struct device_node *np)
 unsigned int hlwd_pic_get_irq(void)
 {
 	unsigned int hwirq = __hlwd_pic_get_irq(hlwd_irq_host);
-	return hwirq ? irq_linear_revmap(hlwd_irq_host, hwirq) : 0;
+	return hwirq ? irq_find_mapping(hlwd_irq_host, hwirq) : 0;
 }
 
 /*
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index 02ff260ae1ee..ce9e58ee9754 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -22,9 +22,9 @@
 #include <linux/serial.h>
 #include <linux/tty.h>
 #include <linux/serial_core.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
 #include <linux/extable.h>
 
 #include <asm/time.h>
diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c
index 9c10aac40c7b..4012f206ec63 100644
--- a/arch/powerpc/platforms/embedded6xx/linkstation.c
+++ b/arch/powerpc/platforms/embedded6xx/linkstation.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/initrd.h>
 #include <linux/of_platform.h>
+#include <linux/seq_file.h>
 
 #include <asm/time.h>
 #include <asm/mpic.h>
@@ -99,9 +100,6 @@ static void __init linkstation_init_IRQ(void)
 	mpic_init(mpic);
 }
 
-extern void avr_uart_configure(void);
-extern void avr_uart_send(const char);
-
 static void __noreturn linkstation_restart(char *cmd)
 {
 	local_irq_disable();
diff --git a/arch/powerpc/platforms/embedded6xx/mpc10x.h b/arch/powerpc/platforms/embedded6xx/mpc10x.h
index 5ad12023e562..ebc258fa4858 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc10x.h
+++ b/arch/powerpc/platforms/embedded6xx/mpc10x.h
@@ -156,4 +156,7 @@ int mpc10x_disable_store_gathering(struct pci_controller *hose);
 /* For MPC107 boards that use the built-in openpic */
 void mpc10x_set_openpic(void);
 
+void avr_uart_configure(void);
+void avr_uart_send(const char c);
+
 #endif	/* __PPC_KERNEL_MPC10X_H */
diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c
index 00bec0f051be..5ca41972ef22 100644
--- a/arch/powerpc/platforms/embedded6xx/mvme5100.c
+++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c
@@ -14,6 +14,7 @@
 
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
+#include <linux/seq_file.h>
 
 #include <asm/i8259.h>
 #include <asm/pci-bridge.h>
diff --git a/arch/powerpc/platforms/maple/Kconfig b/arch/powerpc/platforms/maple/Kconfig
deleted file mode 100644
index 4c058cc57c90..000000000000
--- a/arch/powerpc/platforms/maple/Kconfig
+++ /dev/null
@@ -1,19 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-config PPC_MAPLE
-	depends on PPC64 && PPC_BOOK3S && CPU_BIG_ENDIAN
-	bool "Maple 970FX Evaluation Board"
-	select FORCE_PCI
-	select MPIC
-	select U3_DART
-	select MPIC_U3_HT_IRQS
-	select GENERIC_TBSYNC
-	select PPC_UDBG_16550
-	select PPC_970_NAP
-	select PPC_64S_HASH_MMU
-	select PPC_HASH_MMU_NATIVE
-	select PPC_RTAS
-	select MMIO_NVRAM
-	select ATA_NONSTANDARD if ATA
-	help
-	  This option enables support for the Maple 970FX Evaluation Board.
-	  For more information, refer to <http://www.970eval.com>
diff --git a/arch/powerpc/platforms/maple/maple.h b/arch/powerpc/platforms/maple/maple.h
deleted file mode 100644
index 4f358b55c341..000000000000
--- a/arch/powerpc/platforms/maple/maple.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Declarations for maple-specific code.
- *
- * Maple is the name of a PPC970 evaluation board.
- */
-extern int maple_set_rtc_time(struct rtc_time *tm);
-extern void maple_get_rtc_time(struct rtc_time *tm);
-extern time64_t maple_get_boot_time(void);
-extern void maple_calibrate_decr(void);
-extern void maple_pci_init(void);
-extern void maple_pci_irq_fixup(struct pci_dev *dev);
-extern int maple_pci_get_legacy_ide_irq(struct pci_dev *dev, int channel);
-
-extern struct pci_controller_ops maple_pci_controller_ops;
diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c
deleted file mode 100644
index b911b31717cc..000000000000
--- a/arch/powerpc/platforms/maple/pci.c
+++ /dev/null
@@ -1,672 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org),
- *		      IBM Corp.
- */
-
-#undef DEBUG
-
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/string.h>
-#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/of_irq.h>
-
-#include <asm/sections.h>
-#include <asm/io.h>
-#include <asm/pci-bridge.h>
-#include <asm/machdep.h>
-#include <asm/iommu.h>
-#include <asm/ppc-pci.h>
-#include <asm/isa-bridge.h>
-
-#include "maple.h"
-
-#ifdef DEBUG
-#define DBG(x...) printk(x)
-#else
-#define DBG(x...)
-#endif
-
-static struct pci_controller *u3_agp, *u3_ht, *u4_pcie;
-
-static int __init fixup_one_level_bus_range(struct device_node *node, int higher)
-{
-	for (; node; node = node->sibling) {
-		const int *bus_range;
-		const unsigned int *class_code;
-		int len;
-
-		/* For PCI<->PCI bridges or CardBus bridges, we go down */
-		class_code = of_get_property(node, "class-code", NULL);
-		if (!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI &&
-			(*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS))
-			continue;
-		bus_range = of_get_property(node, "bus-range", &len);
-		if (bus_range != NULL && len > 2 * sizeof(int)) {
-			if (bus_range[1] > higher)
-				higher = bus_range[1];
-		}
-		higher = fixup_one_level_bus_range(node->child, higher);
-	}
-	return higher;
-}
-
-/* This routine fixes the "bus-range" property of all bridges in the
- * system since they tend to have their "last" member wrong on macs
- *
- * Note that the bus numbers manipulated here are OF bus numbers, they
- * are not Linux bus numbers.
- */
-static void __init fixup_bus_range(struct device_node *bridge)
-{
-	int *bus_range;
-	struct property *prop;
-	int len;
-
-	/* Lookup the "bus-range" property for the hose */
-	prop = of_find_property(bridge, "bus-range", &len);
-	if (prop == NULL  || prop->value == NULL || len < 2 * sizeof(int)) {
-		printk(KERN_WARNING "Can't get bus-range for %pOF\n",
-			       bridge);
-		return;
-	}
-	bus_range = prop->value;
-	bus_range[1] = fixup_one_level_bus_range(bridge->child, bus_range[1]);
-}
-
-
-static unsigned long u3_agp_cfa0(u8 devfn, u8 off)
-{
-	return (1 << (unsigned long)PCI_SLOT(devfn)) |
-		((unsigned long)PCI_FUNC(devfn) << 8) |
-		((unsigned long)off & 0xFCUL);
-}
-
-static unsigned long u3_agp_cfa1(u8 bus, u8 devfn, u8 off)
-{
-	return ((unsigned long)bus << 16) |
-		((unsigned long)devfn << 8) |
-		((unsigned long)off & 0xFCUL) |
-		1UL;
-}
-
-static volatile void __iomem *u3_agp_cfg_access(struct pci_controller* hose,
-				       u8 bus, u8 dev_fn, u8 offset)
-{
-	unsigned int caddr;
-
-	if (bus == hose->first_busno) {
-		if (dev_fn < (11 << 3))
-			return NULL;
-		caddr = u3_agp_cfa0(dev_fn, offset);
-	} else
-		caddr = u3_agp_cfa1(bus, dev_fn, offset);
-
-	/* Uninorth will return garbage if we don't read back the value ! */
-	do {
-		out_le32(hose->cfg_addr, caddr);
-	} while (in_le32(hose->cfg_addr) != caddr);
-
-	offset &= 0x07;
-	return hose->cfg_data + offset;
-}
-
-static int u3_agp_read_config(struct pci_bus *bus, unsigned int devfn,
-			      int offset, int len, u32 *val)
-{
-	struct pci_controller *hose;
-	volatile void __iomem *addr;
-
-	hose = pci_bus_to_host(bus);
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	addr = u3_agp_cfg_access(hose, bus->number, devfn, offset);
-	if (!addr)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	/*
-	 * Note: the caller has already checked that offset is
-	 * suitably aligned and that len is 1, 2 or 4.
-	 */
-	switch (len) {
-	case 1:
-		*val = in_8(addr);
-		break;
-	case 2:
-		*val = in_le16(addr);
-		break;
-	default:
-		*val = in_le32(addr);
-		break;
-	}
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static int u3_agp_write_config(struct pci_bus *bus, unsigned int devfn,
-			       int offset, int len, u32 val)
-{
-	struct pci_controller *hose;
-	volatile void __iomem *addr;
-
-	hose = pci_bus_to_host(bus);
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	addr = u3_agp_cfg_access(hose, bus->number, devfn, offset);
-	if (!addr)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	/*
-	 * Note: the caller has already checked that offset is
-	 * suitably aligned and that len is 1, 2 or 4.
-	 */
-	switch (len) {
-	case 1:
-		out_8(addr, val);
-		break;
-	case 2:
-		out_le16(addr, val);
-		break;
-	default:
-		out_le32(addr, val);
-		break;
-	}
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static struct pci_ops u3_agp_pci_ops =
-{
-	.read = u3_agp_read_config,
-	.write = u3_agp_write_config,
-};
-
-static unsigned long u3_ht_cfa0(u8 devfn, u8 off)
-{
-	return (devfn << 8) | off;
-}
-
-static unsigned long u3_ht_cfa1(u8 bus, u8 devfn, u8 off)
-{
-	return u3_ht_cfa0(devfn, off) + (bus << 16) + 0x01000000UL;
-}
-
-static volatile void __iomem *u3_ht_cfg_access(struct pci_controller* hose,
-				      u8 bus, u8 devfn, u8 offset)
-{
-	if (bus == hose->first_busno) {
-		if (PCI_SLOT(devfn) == 0)
-			return NULL;
-		return hose->cfg_data + u3_ht_cfa0(devfn, offset);
-	} else
-		return hose->cfg_data + u3_ht_cfa1(bus, devfn, offset);
-}
-
-static int u3_ht_root_read_config(struct pci_controller *hose, u8 offset,
-				  int len, u32 *val)
-{
-	volatile void __iomem *addr;
-
-	addr = hose->cfg_addr;
-	addr += ((offset & ~3) << 2) + (4 - len - (offset & 3));
-
-	switch (len) {
-	case 1:
-		*val = in_8(addr);
-		break;
-	case 2:
-		*val = in_be16(addr);
-		break;
-	default:
-		*val = in_be32(addr);
-		break;
-	}
-
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static int u3_ht_root_write_config(struct pci_controller *hose, u8 offset,
-				  int len, u32 val)
-{
-	volatile void __iomem *addr;
-
-	addr = hose->cfg_addr + ((offset & ~3) << 2) + (4 - len - (offset & 3));
-
-	if (offset >= PCI_BASE_ADDRESS_0 && offset < PCI_CAPABILITY_LIST)
-		return PCIBIOS_SUCCESSFUL;
-
-	switch (len) {
-	case 1:
-		out_8(addr, val);
-		break;
-	case 2:
-		out_be16(addr, val);
-		break;
-	default:
-		out_be32(addr, val);
-		break;
-	}
-
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static int u3_ht_read_config(struct pci_bus *bus, unsigned int devfn,
-			     int offset, int len, u32 *val)
-{
-	struct pci_controller *hose;
-	volatile void __iomem *addr;
-
-	hose = pci_bus_to_host(bus);
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	if (bus->number == hose->first_busno && devfn == PCI_DEVFN(0, 0))
-		return u3_ht_root_read_config(hose, offset, len, val);
-
-	if (offset > 0xff)
-		return PCIBIOS_BAD_REGISTER_NUMBER;
-
-	addr = u3_ht_cfg_access(hose, bus->number, devfn, offset);
-	if (!addr)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	/*
-	 * Note: the caller has already checked that offset is
-	 * suitably aligned and that len is 1, 2 or 4.
-	 */
-	switch (len) {
-	case 1:
-		*val = in_8(addr);
-		break;
-	case 2:
-		*val = in_le16(addr);
-		break;
-	default:
-		*val = in_le32(addr);
-		break;
-	}
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static int u3_ht_write_config(struct pci_bus *bus, unsigned int devfn,
-			      int offset, int len, u32 val)
-{
-	struct pci_controller *hose;
-	volatile void __iomem *addr;
-
-	hose = pci_bus_to_host(bus);
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	if (bus->number == hose->first_busno && devfn == PCI_DEVFN(0, 0))
-		return u3_ht_root_write_config(hose, offset, len, val);
-
-	if (offset > 0xff)
-		return PCIBIOS_BAD_REGISTER_NUMBER;
-
-	addr = u3_ht_cfg_access(hose, bus->number, devfn, offset);
-	if (!addr)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	/*
-	 * Note: the caller has already checked that offset is
-	 * suitably aligned and that len is 1, 2 or 4.
-	 */
-	switch (len) {
-	case 1:
-		out_8(addr, val);
-		break;
-	case 2:
-		out_le16(addr, val);
-		break;
-	default:
-		out_le32(addr, val);
-		break;
-	}
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static struct pci_ops u3_ht_pci_ops =
-{
-	.read = u3_ht_read_config,
-	.write = u3_ht_write_config,
-};
-
-static unsigned int u4_pcie_cfa0(unsigned int devfn, unsigned int off)
-{
-	return (1 << PCI_SLOT(devfn))	|
-	       (PCI_FUNC(devfn) << 8)	|
-	       ((off >> 8) << 28) 	|
-	       (off & 0xfcu);
-}
-
-static unsigned int u4_pcie_cfa1(unsigned int bus, unsigned int devfn,
-				 unsigned int off)
-{
-        return (bus << 16)		|
-	       (devfn << 8)		|
-	       ((off >> 8) << 28)	|
-	       (off & 0xfcu)		| 1u;
-}
-
-static volatile void __iomem *u4_pcie_cfg_access(struct pci_controller* hose,
-                                        u8 bus, u8 dev_fn, int offset)
-{
-        unsigned int caddr;
-
-        if (bus == hose->first_busno)
-                caddr = u4_pcie_cfa0(dev_fn, offset);
-        else
-                caddr = u4_pcie_cfa1(bus, dev_fn, offset);
-
-        /* Uninorth will return garbage if we don't read back the value ! */
-        do {
-                out_le32(hose->cfg_addr, caddr);
-        } while (in_le32(hose->cfg_addr) != caddr);
-
-        offset &= 0x03;
-        return hose->cfg_data + offset;
-}
-
-static int u4_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
-                               int offset, int len, u32 *val)
-{
-        struct pci_controller *hose;
-        volatile void __iomem *addr;
-
-        hose = pci_bus_to_host(bus);
-        if (hose == NULL)
-                return PCIBIOS_DEVICE_NOT_FOUND;
-        if (offset >= 0x1000)
-                return  PCIBIOS_BAD_REGISTER_NUMBER;
-        addr = u4_pcie_cfg_access(hose, bus->number, devfn, offset);
-        if (!addr)
-                return PCIBIOS_DEVICE_NOT_FOUND;
-        /*
-         * Note: the caller has already checked that offset is
-         * suitably aligned and that len is 1, 2 or 4.
-         */
-        switch (len) {
-        case 1:
-                *val = in_8(addr);
-                break;
-        case 2:
-                *val = in_le16(addr);
-                break;
-        default:
-                *val = in_le32(addr);
-                break;
-        }
-        return PCIBIOS_SUCCESSFUL;
-}
-static int u4_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
-                                int offset, int len, u32 val)
-{
-        struct pci_controller *hose;
-        volatile void __iomem *addr;
-
-        hose = pci_bus_to_host(bus);
-        if (hose == NULL)
-                return PCIBIOS_DEVICE_NOT_FOUND;
-        if (offset >= 0x1000)
-                return  PCIBIOS_BAD_REGISTER_NUMBER;
-        addr = u4_pcie_cfg_access(hose, bus->number, devfn, offset);
-        if (!addr)
-                return PCIBIOS_DEVICE_NOT_FOUND;
-        /*
-         * Note: the caller has already checked that offset is
-         * suitably aligned and that len is 1, 2 or 4.
-         */
-        switch (len) {
-        case 1:
-                out_8(addr, val);
-                break;
-        case 2:
-                out_le16(addr, val);
-                break;
-        default:
-                out_le32(addr, val);
-                break;
-        }
-        return PCIBIOS_SUCCESSFUL;
-}
-
-static struct pci_ops u4_pcie_pci_ops =
-{
-	.read = u4_pcie_read_config,
-	.write = u4_pcie_write_config,
-};
-
-static void __init setup_u3_agp(struct pci_controller* hose)
-{
-	/* On G5, we move AGP up to high bus number so we don't need
-	 * to reassign bus numbers for HT. If we ever have P2P bridges
-	 * on AGP, we'll have to move pci_assign_all_buses to the
-	 * pci_controller structure so we enable it for AGP and not for
-	 * HT childs.
-	 * We hard code the address because of the different size of
-	 * the reg address cell, we shall fix that by killing struct
-	 * reg_property and using some accessor functions instead
-	 */
-	hose->first_busno = 0xf0;
-	hose->last_busno = 0xff;
-	hose->ops = &u3_agp_pci_ops;
-	hose->cfg_addr = ioremap(0xf0000000 + 0x800000, 0x1000);
-	hose->cfg_data = ioremap(0xf0000000 + 0xc00000, 0x1000);
-
-	u3_agp = hose;
-}
-
-static void __init setup_u4_pcie(struct pci_controller* hose)
-{
-        /* We currently only implement the "non-atomic" config space, to
-         * be optimised later.
-         */
-        hose->ops = &u4_pcie_pci_ops;
-        hose->cfg_addr = ioremap(0xf0000000 + 0x800000, 0x1000);
-        hose->cfg_data = ioremap(0xf0000000 + 0xc00000, 0x1000);
-
-        u4_pcie = hose;
-}
-
-static void __init setup_u3_ht(struct pci_controller* hose)
-{
-	hose->ops = &u3_ht_pci_ops;
-
-	/* We hard code the address because of the different size of
-	 * the reg address cell, we shall fix that by killing struct
-	 * reg_property and using some accessor functions instead
-	 */
-	hose->cfg_data = ioremap(0xf2000000, 0x02000000);
-	hose->cfg_addr = ioremap(0xf8070000, 0x1000);
-
-	hose->first_busno = 0;
-	hose->last_busno = 0xef;
-
-	u3_ht = hose;
-}
-
-static int __init maple_add_bridge(struct device_node *dev)
-{
-	int len;
-	struct pci_controller *hose;
-	char* disp_name;
-	const int *bus_range;
-	int primary = 1;
-
-	DBG("Adding PCI host bridge %pOF\n", dev);
-
-	bus_range = of_get_property(dev, "bus-range", &len);
-	if (bus_range == NULL || len < 2 * sizeof(int)) {
-		printk(KERN_WARNING "Can't get bus-range for %pOF, assume bus 0\n",
-		dev);
-	}
-
-	hose = pcibios_alloc_controller(dev);
-	if (hose == NULL)
-		return -ENOMEM;
-	hose->first_busno = bus_range ? bus_range[0] : 0;
-	hose->last_busno = bus_range ? bus_range[1] : 0xff;
-	hose->controller_ops = maple_pci_controller_ops;
-
-	disp_name = NULL;
-	if (of_device_is_compatible(dev, "u3-agp")) {
-		setup_u3_agp(hose);
-		disp_name = "U3-AGP";
-		primary = 0;
-	} else if (of_device_is_compatible(dev, "u3-ht")) {
-		setup_u3_ht(hose);
-		disp_name = "U3-HT";
-		primary = 1;
-        } else if (of_device_is_compatible(dev, "u4-pcie")) {
-                setup_u4_pcie(hose);
-                disp_name = "U4-PCIE";
-                primary = 0;
-	}
-	printk(KERN_INFO "Found %s PCI host bridge. Firmware bus number: %d->%d\n",
-		disp_name, hose->first_busno, hose->last_busno);
-
-	/* Interpret the "ranges" property */
-	/* This also maps the I/O region and sets isa_io/mem_base */
-	pci_process_bridge_OF_ranges(hose, dev, primary);
-
-	/* Fixup "bus-range" OF property */
-	fixup_bus_range(dev);
-
-	/* Check for legacy IOs */
-	isa_bridge_find_early(hose);
-
-	/* create pci_dn's for DT nodes under this PHB */
-	pci_devs_phb_init_dynamic(hose);
-
-	return 0;
-}
-
-
-void maple_pci_irq_fixup(struct pci_dev *dev)
-{
-	DBG(" -> maple_pci_irq_fixup\n");
-
-	/* Fixup IRQ for PCIe host */
-	if (u4_pcie != NULL && dev->bus->number == 0 &&
-	    pci_bus_to_host(dev->bus) == u4_pcie) {
-		printk(KERN_DEBUG "Fixup U4 PCIe IRQ\n");
-		dev->irq = irq_create_mapping(NULL, 1);
-		if (dev->irq)
-			irq_set_irq_type(dev->irq, IRQ_TYPE_LEVEL_LOW);
-	}
-
-	/* Hide AMD8111 IDE interrupt when in legacy mode so
-	 * the driver calls pci_get_legacy_ide_irq()
-	 */
-	if (dev->vendor == PCI_VENDOR_ID_AMD &&
-	    dev->device == PCI_DEVICE_ID_AMD_8111_IDE &&
-	    (dev->class & 5) != 5) {
-		dev->irq = 0;
-	}
-
-	DBG(" <- maple_pci_irq_fixup\n");
-}
-
-static int maple_pci_root_bridge_prepare(struct pci_host_bridge *bridge)
-{
-	struct pci_controller *hose = pci_bus_to_host(bridge->bus);
-	struct device_node *np, *child;
-
-	if (hose != u3_agp)
-		return 0;
-
-	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
-	 * assume there is no P2P bridge on the AGP bus, which should be a
-	 * safe assumptions hopefully.
-	 */
-	np = hose->dn;
-	PCI_DN(np)->busno = 0xf0;
-	for_each_child_of_node(np, child)
-		PCI_DN(child)->busno = 0xf0;
-
-	return 0;
-}
-
-void __init maple_pci_init(void)
-{
-	struct device_node *np, *root;
-	struct device_node *ht = NULL;
-
-	/* Probe root PCI hosts, that is on U3 the AGP host and the
-	 * HyperTransport host. That one is actually "kept" around
-	 * and actually added last as it's resource management relies
-	 * on the AGP resources to have been setup first
-	 */
-	root = of_find_node_by_path("/");
-	if (root == NULL) {
-		printk(KERN_CRIT "maple_find_bridges: can't find root of device tree\n");
-		return;
-	}
-	for_each_child_of_node(root, np) {
-		if (!of_node_is_type(np, "pci") && !of_node_is_type(np, "ht"))
-			continue;
-		if ((of_device_is_compatible(np, "u4-pcie") ||
-		     of_device_is_compatible(np, "u3-agp")) &&
-		    maple_add_bridge(np) == 0)
-			of_node_get(np);
-
-		if (of_device_is_compatible(np, "u3-ht")) {
-			of_node_get(np);
-			ht = np;
-		}
-	}
-	of_node_put(root);
-
-	/* Now setup the HyperTransport host if we found any
-	 */
-	if (ht && maple_add_bridge(ht) != 0)
-		of_node_put(ht);
-
-	ppc_md.pcibios_root_bridge_prepare = maple_pci_root_bridge_prepare;
-
-	/* Tell pci.c to not change any resource allocations.  */
-	pci_add_flags(PCI_PROBE_ONLY);
-}
-
-int maple_pci_get_legacy_ide_irq(struct pci_dev *pdev, int channel)
-{
-	struct device_node *np;
-	unsigned int defirq = channel ? 15 : 14;
-	unsigned int irq;
-
-	if (pdev->vendor != PCI_VENDOR_ID_AMD ||
-	    pdev->device != PCI_DEVICE_ID_AMD_8111_IDE)
-		return defirq;
-
-	np = pci_device_to_OF_node(pdev);
-	if (np == NULL) {
-		printk("Failed to locate OF node for IDE %s\n",
-		       pci_name(pdev));
-		return defirq;
-	}
-	irq = irq_of_parse_and_map(np, channel & 0x1);
-	if (!irq) {
-		printk("Failed to map onboard IDE interrupt for channel %d\n",
-		       channel);
-		return defirq;
-	}
-	return irq;
-}
-
-static void quirk_ipr_msi(struct pci_dev *dev)
-{
-	/* Something prevents MSIs from the IPR from working on Bimini,
-	 * and the driver has no smarts to recover. So disable MSI
-	 * on it for now. */
-
-	if (machine_is(maple)) {
-		dev->no_msi = 1;
-		dev_info(&dev->dev, "Quirk disabled MSI\n");
-	}
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_OBSIDIAN,
-			quirk_ipr_msi);
-
-struct pci_controller_ops maple_pci_controller_ops = {
-};
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
deleted file mode 100644
index a4a79d77eca2..000000000000
--- a/arch/powerpc/platforms/maple/setup.c
+++ /dev/null
@@ -1,362 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  Maple (970 eval board) setup code
- *
- *  (c) Copyright 2004 Benjamin Herrenschmidt (benh@kernel.crashing.org),
- *                     IBM Corp. 
- */
-
-#undef DEBUG
-
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-#include <linux/tty.h>
-#include <linux/string.h>
-#include <linux/delay.h>
-#include <linux/ioport.h>
-#include <linux/major.h>
-#include <linux/initrd.h>
-#include <linux/vt_kern.h>
-#include <linux/console.h>
-#include <linux/pci.h>
-#include <linux/adb.h>
-#include <linux/cuda.h>
-#include <linux/pmu.h>
-#include <linux/irq.h>
-#include <linux/seq_file.h>
-#include <linux/root_dev.h>
-#include <linux/serial.h>
-#include <linux/smp.h>
-#include <linux/bitops.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/memblock.h>
-
-#include <asm/processor.h>
-#include <asm/sections.h>
-#include <asm/io.h>
-#include <asm/pci-bridge.h>
-#include <asm/iommu.h>
-#include <asm/machdep.h>
-#include <asm/dma.h>
-#include <asm/cputable.h>
-#include <asm/time.h>
-#include <asm/mpic.h>
-#include <asm/rtas.h>
-#include <asm/udbg.h>
-#include <asm/nvram.h>
-
-#include "maple.h"
-
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
-static unsigned long maple_find_nvram_base(void)
-{
-	struct device_node *rtcs;
-	unsigned long result = 0;
-
-	/* find NVRAM device */
-	rtcs = of_find_compatible_node(NULL, "nvram", "AMD8111");
-	if (rtcs) {
-		struct resource r;
-		if (of_address_to_resource(rtcs, 0, &r)) {
-			printk(KERN_EMERG "Maple: Unable to translate NVRAM"
-			       " address\n");
-			goto bail;
-		}
-		if (!(r.flags & IORESOURCE_IO)) {
-			printk(KERN_EMERG "Maple: NVRAM address isn't PIO!\n");
-			goto bail;
-		}
-		result = r.start;
-	} else
-		printk(KERN_EMERG "Maple: Unable to find NVRAM\n");
- bail:
-	of_node_put(rtcs);
-	return result;
-}
-
-static void __noreturn maple_restart(char *cmd)
-{
-	unsigned int maple_nvram_base;
-	const unsigned int *maple_nvram_offset, *maple_nvram_command;
-	struct device_node *sp;
-
-	maple_nvram_base = maple_find_nvram_base();
-	if (maple_nvram_base == 0)
-		goto fail;
-
-	/* find service processor device */
-	sp = of_find_node_by_name(NULL, "service-processor");
-	if (!sp) {
-		printk(KERN_EMERG "Maple: Unable to find Service Processor\n");
-		goto fail;
-	}
-	maple_nvram_offset = of_get_property(sp, "restart-addr", NULL);
-	maple_nvram_command = of_get_property(sp, "restart-value", NULL);
-	of_node_put(sp);
-
-	/* send command */
-	outb_p(*maple_nvram_command, maple_nvram_base + *maple_nvram_offset);
-	for (;;) ;
- fail:
-	printk(KERN_EMERG "Maple: Manual Restart Required\n");
-	for (;;) ;
-}
-
-static void __noreturn maple_power_off(void)
-{
-	unsigned int maple_nvram_base;
-	const unsigned int *maple_nvram_offset, *maple_nvram_command;
-	struct device_node *sp;
-
-	maple_nvram_base = maple_find_nvram_base();
-	if (maple_nvram_base == 0)
-		goto fail;
-
-	/* find service processor device */
-	sp = of_find_node_by_name(NULL, "service-processor");
-	if (!sp) {
-		printk(KERN_EMERG "Maple: Unable to find Service Processor\n");
-		goto fail;
-	}
-	maple_nvram_offset = of_get_property(sp, "power-off-addr", NULL);
-	maple_nvram_command = of_get_property(sp, "power-off-value", NULL);
-	of_node_put(sp);
-
-	/* send command */
-	outb_p(*maple_nvram_command, maple_nvram_base + *maple_nvram_offset);
-	for (;;) ;
- fail:
-	printk(KERN_EMERG "Maple: Manual Power-Down Required\n");
-	for (;;) ;
-}
-
-static void __noreturn maple_halt(void)
-{
-	maple_power_off();
-}
-
-#ifdef CONFIG_SMP
-static struct smp_ops_t maple_smp_ops = {
-	.probe		= smp_mpic_probe,
-	.message_pass	= smp_mpic_message_pass,
-	.kick_cpu	= smp_generic_kick_cpu,
-	.setup_cpu	= smp_mpic_setup_cpu,
-	.give_timebase	= smp_generic_give_timebase,
-	.take_timebase	= smp_generic_take_timebase,
-};
-#endif /* CONFIG_SMP */
-
-static void __init maple_use_rtas_reboot_and_halt_if_present(void)
-{
-	if (rtas_function_implemented(RTAS_FN_SYSTEM_REBOOT) &&
-	    rtas_function_implemented(RTAS_FN_POWER_OFF)) {
-		ppc_md.restart = rtas_restart;
-		pm_power_off = rtas_power_off;
-		ppc_md.halt = rtas_halt;
-	}
-}
-
-static void __init maple_setup_arch(void)
-{
-	/* init to some ~sane value until calibrate_delay() runs */
-	loops_per_jiffy = 50000000;
-
-	/* Setup SMP callback */
-#ifdef CONFIG_SMP
-	smp_ops = &maple_smp_ops;
-#endif
-	maple_use_rtas_reboot_and_halt_if_present();
-
-	printk(KERN_DEBUG "Using native/NAP idle loop\n");
-
-	mmio_nvram_init();
-}
-
-/*
- * This is almost identical to pSeries and CHRP. We need to make that
- * code generic at one point, with appropriate bits in the device-tree to
- * identify the presence of an HT APIC
- */
-static void __init maple_init_IRQ(void)
-{
-	struct device_node *root, *np, *mpic_node = NULL;
-	const unsigned int *opprop;
-	unsigned long openpic_addr = 0;
-	int naddr, n, i, opplen, has_isus = 0;
-	struct mpic *mpic;
-	unsigned int flags = 0;
-
-	/* Locate MPIC in the device-tree. Note that there is a bug
-	 * in Maple device-tree where the type of the controller is
-	 * open-pic and not interrupt-controller
-	 */
-
-	for_each_node_by_type(np, "interrupt-controller")
-		if (of_device_is_compatible(np, "open-pic")) {
-			mpic_node = np;
-			break;
-		}
-	if (mpic_node == NULL)
-		for_each_node_by_type(np, "open-pic") {
-			mpic_node = np;
-			break;
-		}
-	if (mpic_node == NULL) {
-		printk(KERN_ERR
-		       "Failed to locate the MPIC interrupt controller\n");
-		return;
-	}
-
-	/* Find address list in /platform-open-pic */
-	root = of_find_node_by_path("/");
-	naddr = of_n_addr_cells(root);
-	opprop = of_get_property(root, "platform-open-pic", &opplen);
-	if (opprop) {
-		openpic_addr = of_read_number(opprop, naddr);
-		has_isus = (opplen > naddr);
-		printk(KERN_DEBUG "OpenPIC addr: %lx, has ISUs: %d\n",
-		       openpic_addr, has_isus);
-	}
-
-	BUG_ON(openpic_addr == 0);
-
-	/* Check for a big endian MPIC */
-	if (of_property_read_bool(np, "big-endian"))
-		flags |= MPIC_BIG_ENDIAN;
-
-	/* XXX Maple specific bits */
-	flags |= MPIC_U3_HT_IRQS;
-	/* All U3/U4 are big-endian, older SLOF firmware doesn't encode this */
-	flags |= MPIC_BIG_ENDIAN;
-
-	/* Setup the openpic driver. More device-tree junks, we hard code no
-	 * ISUs for now. I'll have to revisit some stuffs with the folks doing
-	 * the firmware for those
-	 */
-	mpic = mpic_alloc(mpic_node, openpic_addr, flags,
-			  /*has_isus ? 16 :*/ 0, 0, " MPIC     ");
-	BUG_ON(mpic == NULL);
-
-	/* Add ISUs */
-	opplen /= sizeof(u32);
-	for (n = 0, i = naddr; i < opplen; i += naddr, n++) {
-		unsigned long isuaddr = of_read_number(opprop + i, naddr);
-		mpic_assign_isu(mpic, n, isuaddr);
-	}
-
-	/* All ISUs are setup, complete initialization */
-	mpic_init(mpic);
-	ppc_md.get_irq = mpic_get_irq;
-	of_node_put(mpic_node);
-	of_node_put(root);
-}
-
-static void __init maple_progress(char *s, unsigned short hex)
-{
-	printk("*** %04x : %s\n", hex, s ? s : "");
-}
-
-
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init maple_probe(void)
-{
-	if (!of_machine_is_compatible("Momentum,Maple") &&
-	    !of_machine_is_compatible("Momentum,Apache"))
-		return 0;
-
-	pm_power_off = maple_power_off;
-
-	iommu_init_early_dart(&maple_pci_controller_ops);
-
-	return 1;
-}
-
-#ifdef CONFIG_EDAC
-/*
- * Register a platform device for CPC925 memory controller on
- * all boards with U3H (CPC925) bridge.
- */
-static int __init maple_cpc925_edac_setup(void)
-{
-	struct platform_device *pdev;
-	struct device_node *np = NULL;
-	struct resource r;
-	int ret;
-	volatile void __iomem *mem;
-	u32 rev;
-
-	np = of_find_node_by_type(NULL, "memory-controller");
-	if (!np) {
-		printk(KERN_ERR "%s: Unable to find memory-controller node\n",
-			__func__);
-		return -ENODEV;
-	}
-
-	ret = of_address_to_resource(np, 0, &r);
-	of_node_put(np);
-
-	if (ret < 0) {
-		printk(KERN_ERR "%s: Unable to get memory-controller reg\n",
-			__func__);
-		return -ENODEV;
-	}
-
-	mem = ioremap(r.start, resource_size(&r));
-	if (!mem) {
-		printk(KERN_ERR "%s: Unable to map memory-controller memory\n",
-				__func__);
-		return -ENOMEM;
-	}
-
-	rev = __raw_readl(mem);
-	iounmap(mem);
-
-	if (rev < 0x34 || rev > 0x3f) { /* U3H */
-		printk(KERN_ERR "%s: Non-CPC925(U3H) bridge revision: %02x\n",
-			__func__, rev);
-		return 0;
-	}
-
-	pdev = platform_device_register_simple("cpc925_edac", 0, &r, 1);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
-
-	printk(KERN_INFO "%s: CPC925 platform device created\n", __func__);
-
-	return 0;
-}
-machine_device_initcall(maple, maple_cpc925_edac_setup);
-#endif
-
-define_machine(maple) {
-	.name			= "Maple",
-	.probe			= maple_probe,
-	.setup_arch		= maple_setup_arch,
-	.discover_phbs		= maple_pci_init,
-	.init_IRQ		= maple_init_IRQ,
-	.pci_irq_fixup		= maple_pci_irq_fixup,
-	.pci_get_legacy_ide_irq	= maple_pci_get_legacy_ide_irq,
-	.restart		= maple_restart,
-	.halt			= maple_halt,
-	.get_boot_time		= maple_get_boot_time,
-	.set_rtc_time		= maple_set_rtc_time,
-	.get_rtc_time		= maple_get_rtc_time,
-	.progress		= maple_progress,
-	.power_save		= power4_idle,
-};
diff --git a/arch/powerpc/platforms/maple/time.c b/arch/powerpc/platforms/maple/time.c
deleted file mode 100644
index 91606411d2e0..000000000000
--- a/arch/powerpc/platforms/maple/time.c
+++ /dev/null
@@ -1,170 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  (c) Copyright 2004 Benjamin Herrenschmidt (benh@kernel.crashing.org),
- *                     IBM Corp. 
- */
-
-#undef DEBUG
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/init.h>
-#include <linux/time.h>
-#include <linux/adb.h>
-#include <linux/pmu.h>
-#include <linux/interrupt.h>
-#include <linux/mc146818rtc.h>
-#include <linux/bcd.h>
-#include <linux/of_address.h>
-
-#include <asm/sections.h>
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/time.h>
-
-#include "maple.h"
-
-#ifdef DEBUG
-#define DBG(x...) printk(x)
-#else
-#define DBG(x...)
-#endif
-
-static int maple_rtc_addr;
-
-static int maple_clock_read(int addr)
-{
-	outb_p(addr, maple_rtc_addr);
-	return inb_p(maple_rtc_addr+1);
-}
-
-static void maple_clock_write(unsigned long val, int addr)
-{
-	outb_p(addr, maple_rtc_addr);
-	outb_p(val, maple_rtc_addr+1);
-}
-
-void maple_get_rtc_time(struct rtc_time *tm)
-{
-	do {
-		tm->tm_sec = maple_clock_read(RTC_SECONDS);
-		tm->tm_min = maple_clock_read(RTC_MINUTES);
-		tm->tm_hour = maple_clock_read(RTC_HOURS);
-		tm->tm_mday = maple_clock_read(RTC_DAY_OF_MONTH);
-		tm->tm_mon = maple_clock_read(RTC_MONTH);
-		tm->tm_year = maple_clock_read(RTC_YEAR);
-	} while (tm->tm_sec != maple_clock_read(RTC_SECONDS));
-
-	if (!(maple_clock_read(RTC_CONTROL) & RTC_DM_BINARY)
-	    || RTC_ALWAYS_BCD) {
-		tm->tm_sec = bcd2bin(tm->tm_sec);
-		tm->tm_min = bcd2bin(tm->tm_min);
-		tm->tm_hour = bcd2bin(tm->tm_hour);
-		tm->tm_mday = bcd2bin(tm->tm_mday);
-		tm->tm_mon = bcd2bin(tm->tm_mon);
-		tm->tm_year = bcd2bin(tm->tm_year);
-	  }
-	if ((tm->tm_year + 1900) < 1970)
-		tm->tm_year += 100;
-
-	tm->tm_wday = -1;
-}
-
-int maple_set_rtc_time(struct rtc_time *tm)
-{
-	unsigned char save_control, save_freq_select;
-	int sec, min, hour, mon, mday, year;
-
-	spin_lock(&rtc_lock);
-
-	save_control = maple_clock_read(RTC_CONTROL); /* tell the clock it's being set */
-
-	maple_clock_write((save_control|RTC_SET), RTC_CONTROL);
-
-	save_freq_select = maple_clock_read(RTC_FREQ_SELECT); /* stop and reset prescaler */
-
-	maple_clock_write((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT);
-
-	sec = tm->tm_sec;
-	min = tm->tm_min;
-	hour = tm->tm_hour;
-	mon = tm->tm_mon;
-	mday = tm->tm_mday;
-	year = tm->tm_year;
-
-	if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-		sec = bin2bcd(sec);
-		min = bin2bcd(min);
-		hour = bin2bcd(hour);
-		mon = bin2bcd(mon);
-		mday = bin2bcd(mday);
-		year = bin2bcd(year);
-	}
-	maple_clock_write(sec, RTC_SECONDS);
-	maple_clock_write(min, RTC_MINUTES);
-	maple_clock_write(hour, RTC_HOURS);
-	maple_clock_write(mon, RTC_MONTH);
-	maple_clock_write(mday, RTC_DAY_OF_MONTH);
-	maple_clock_write(year, RTC_YEAR);
-
-	/* The following flags have to be released exactly in this order,
-	 * otherwise the DS12887 (popular MC146818A clone with integrated
-	 * battery and quartz) will not reset the oscillator and will not
-	 * update precisely 500 ms later. You won't find this mentioned in
-	 * the Dallas Semiconductor data sheets, but who believes data
-	 * sheets anyway ...                           -- Markus Kuhn
-	 */
-	maple_clock_write(save_control, RTC_CONTROL);
-	maple_clock_write(save_freq_select, RTC_FREQ_SELECT);
-
-	spin_unlock(&rtc_lock);
-
-	return 0;
-}
-
-static struct resource rtc_iores = {
-	.name = "rtc",
-	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
-};
-
-time64_t __init maple_get_boot_time(void)
-{
-	struct rtc_time tm;
-	struct device_node *rtcs;
-
-	rtcs = of_find_compatible_node(NULL, "rtc", "pnpPNP,b00");
-	if (rtcs) {
-		struct resource r;
-		if (of_address_to_resource(rtcs, 0, &r)) {
-			printk(KERN_EMERG "Maple: Unable to translate RTC"
-			       " address\n");
-			goto bail;
-		}
-		if (!(r.flags & IORESOURCE_IO)) {
-			printk(KERN_EMERG "Maple: RTC address isn't PIO!\n");
-			goto bail;
-		}
-		maple_rtc_addr = r.start;
-		printk(KERN_INFO "Maple: Found RTC at IO 0x%x\n",
-		       maple_rtc_addr);
-	}
- bail:
-	of_node_put(rtcs);
-	if (maple_rtc_addr == 0) {
-		maple_rtc_addr = RTC_PORT(0); /* legacy address */
-		printk(KERN_INFO "Maple: No device node for RTC, assuming "
-		       "legacy address (0x%x)\n", maple_rtc_addr);
-	}
-
-	rtc_iores.start = maple_rtc_addr;
-	rtc_iores.end = maple_rtc_addr + 7;
-	request_resource(&ioport_resource, &rtc_iores);
-
-	maple_get_rtc_time(&tm);
-	return rtc_tm_to_time64(&tm);
-}
-
diff --git a/arch/powerpc/platforms/microwatt/Kconfig b/arch/powerpc/platforms/microwatt/Kconfig
index 6af443a1db99..cb2aff635bb0 100644
--- a/arch/powerpc/platforms/microwatt/Kconfig
+++ b/arch/powerpc/platforms/microwatt/Kconfig
@@ -1,11 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
 config PPC_MICROWATT
-	depends on PPC_BOOK3S_64 && !SMP
+	depends on PPC_BOOK3S_64
 	bool "Microwatt SoC platform"
 	select PPC_XICS
 	select PPC_ICS_NATIVE
 	select PPC_ICP_NATIVE
 	select PPC_UDBG_16550
+	select COMMON_CLK
 	help
           This option enables support for FPGA-based Microwatt implementations.
 
diff --git a/arch/powerpc/platforms/microwatt/Makefile b/arch/powerpc/platforms/microwatt/Makefile
index 116d6d3ad3f0..d973b2ab4042 100644
--- a/arch/powerpc/platforms/microwatt/Makefile
+++ b/arch/powerpc/platforms/microwatt/Makefile
@@ -1 +1,2 @@
 obj-y	+= setup.o rng.o
+obj-$(CONFIG_SMP) += smp.o
diff --git a/arch/powerpc/platforms/microwatt/microwatt.h b/arch/powerpc/platforms/microwatt/microwatt.h
index 335417e95e66..891aa2800768 100644
--- a/arch/powerpc/platforms/microwatt/microwatt.h
+++ b/arch/powerpc/platforms/microwatt/microwatt.h
@@ -3,5 +3,6 @@
 #define _MICROWATT_H
 
 void microwatt_rng_init(void);
+void microwatt_init_smp(void);
 
 #endif /* _MICROWATT_H */
diff --git a/arch/powerpc/platforms/microwatt/setup.c b/arch/powerpc/platforms/microwatt/setup.c
index 5e1c0997170d..6af2ccef736c 100644
--- a/arch/powerpc/platforms/microwatt/setup.c
+++ b/arch/powerpc/platforms/microwatt/setup.c
@@ -29,15 +29,33 @@ static int __init microwatt_populate(void)
 }
 machine_arch_initcall(microwatt, microwatt_populate);
 
+static int __init microwatt_probe(void)
+{
+	/* Main reason for having this is to start the other CPU(s) */
+	if (IS_ENABLED(CONFIG_SMP))
+		microwatt_init_smp();
+	return 1;
+}
+
 static void __init microwatt_setup_arch(void)
 {
 	microwatt_rng_init();
 }
 
+static void microwatt_idle(void)
+{
+	if (!prep_irq_for_idle_irqsoff())
+		return;
+
+	__asm__ __volatile__ ("wait");
+}
+
 define_machine(microwatt) {
 	.name			= "microwatt",
 	.compatible		= "microwatt-soc",
+	.probe			= microwatt_probe,
 	.init_IRQ		= microwatt_init_IRQ,
 	.setup_arch		= microwatt_setup_arch,
 	.progress		= udbg_progress,
+	.power_save		= microwatt_idle,
 };
diff --git a/arch/powerpc/platforms/microwatt/smp.c b/arch/powerpc/platforms/microwatt/smp.c
new file mode 100644
index 000000000000..7dbf2ca73d47
--- /dev/null
+++ b/arch/powerpc/platforms/microwatt/smp.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+/*
+ * SMP support functions for Microwatt
+ * Copyright 2025 Paul Mackerras <paulus@ozlabs.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/io.h>
+#include <asm/early_ioremap.h>
+#include <asm/ppc-opcode.h>
+#include <asm/reg.h>
+#include <asm/smp.h>
+#include <asm/xics.h>
+
+#include "microwatt.h"
+
+static void __init microwatt_smp_probe(void)
+{
+	xics_smp_probe();
+}
+
+static void microwatt_smp_setup_cpu(int cpu)
+{
+	if (cpu != 0)
+		xics_setup_cpu();
+}
+
+static struct smp_ops_t microwatt_smp_ops = {
+	.probe		= microwatt_smp_probe,
+	.message_pass	= NULL,		/* Use smp_muxed_ipi_message_pass */
+	.kick_cpu	= smp_generic_kick_cpu,
+	.setup_cpu	= microwatt_smp_setup_cpu,
+};
+
+/* XXX get from device tree */
+#define SYSCON_BASE	0xc0000000
+#define SYSCON_LENGTH	0x100
+
+#define SYSCON_CPU_CTRL	0x58
+
+void __init microwatt_init_smp(void)
+{
+	volatile unsigned char __iomem *syscon;
+	int ncpus;
+	int timeout;
+
+	syscon = early_ioremap(SYSCON_BASE, SYSCON_LENGTH);
+	if (syscon == NULL) {
+		pr_err("Failed to map SYSCON\n");
+		return;
+	}
+	ncpus = (readl(syscon + SYSCON_CPU_CTRL) >> 8) & 0xff;
+	if (ncpus < 2)
+		goto out;
+
+	smp_ops = &microwatt_smp_ops;
+
+	/*
+	 * Write two instructions at location 0:
+	 * mfspr r3, PIR
+	 * b __secondary_hold
+	 */
+	*(unsigned int *)KERNELBASE = PPC_RAW_MFSPR(3, SPRN_PIR);
+	*(unsigned int *)(KERNELBASE+4) = PPC_RAW_BRANCH(&__secondary_hold - (char *)(KERNELBASE+4));
+
+	/* enable the other CPUs, they start at location 0 */
+	writel((1ul << ncpus) - 1, syscon + SYSCON_CPU_CTRL);
+
+	timeout = 10000;
+	while (!__secondary_hold_acknowledge) {
+		if (--timeout == 0)
+			break;
+		barrier();
+	}
+
+ out:
+	early_iounmap((void *)syscon, SYSCON_LENGTH);
+}
diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c
index 913b77b92cea..e4538d471256 100644
--- a/arch/powerpc/platforms/pasemi/gpio_mdio.c
+++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c
@@ -20,7 +20,7 @@
 #include <linux/phy.h>
 #include <linux/of_address.h>
 #include <linux/of_mdio.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 #define DELAY 1
 
@@ -260,7 +260,7 @@ out:
 }
 
 
-static int gpio_mdio_remove(struct platform_device *dev)
+static void gpio_mdio_remove(struct platform_device *dev)
 {
 	struct mii_bus *bus = dev_get_drvdata(&dev->dev);
 
@@ -271,8 +271,6 @@ static int gpio_mdio_remove(struct platform_device *dev)
 	kfree(bus->priv);
 	bus->priv = NULL;
 	mdiobus_free(bus);
-
-	return 0;
 }
 
 static const struct of_device_id gpio_mdio_match[] =
diff --git a/arch/powerpc/platforms/pasemi/pasemi.h b/arch/powerpc/platforms/pasemi/pasemi.h
index 3f277a200fd8..6f6743b8e48d 100644
--- a/arch/powerpc/platforms/pasemi/pasemi.h
+++ b/arch/powerpc/platforms/pasemi/pasemi.h
@@ -4,7 +4,7 @@
 
 extern time64_t pas_get_boot_time(void);
 extern void pas_pci_init(void);
-extern void pas_pci_irq_fixup(struct pci_dev *dev);
+struct pci_dev;
 extern void pas_pci_dma_dev_setup(struct pci_dev *dev);
 
 void __iomem *__init pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset);
diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c
index f27d31414737..60f990a336c4 100644
--- a/arch/powerpc/platforms/pasemi/pci.c
+++ b/arch/powerpc/platforms/pasemi/pci.c
@@ -270,16 +270,18 @@ static int __init pas_add_bridge(struct device_node *dev)
 
 void __init pas_pci_init(void)
 {
+	struct device_node *root = of_find_node_by_path("/");
 	struct device_node *np;
 	int res;
 
 	pci_set_flags(PCI_SCAN_ALL_PCIE_DEVS);
 
-	np = of_find_compatible_node(of_root, NULL, "pasemi,rootbus");
+	np = of_find_compatible_node(root, NULL, "pasemi,rootbus");
 	if (np) {
 		res = pas_add_bridge(np);
 		of_node_put(np);
 	}
+	of_node_put(root);
 }
 
 void __iomem *__init pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset)
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 5c5b4a034f9e..d03b41336901 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -16,7 +16,9 @@
 #include <linux/console.h>
 #include <linux/export.h>
 #include <linux/pci.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/gfp.h>
 #include <linux/irqdomain.h>
 
@@ -62,7 +64,7 @@ static void __noreturn pas_restart(char *cmd)
 }
 
 #ifdef CONFIG_PPC_PASEMI_NEMO
-void pas_shutdown(void)
+static void pas_shutdown(void)
 {
 	/* Set the PLD bit that makes the SB600 think the power button is being pressed */
 	void __iomem *pld_map = ioremap(0xf5000000,4096);
@@ -226,7 +228,7 @@ static void __init nemo_init_IRQ(struct mpic *mpic)
 	irq_set_chained_handler(gpio_virq, sb600_8259_cascade);
 	mpic_unmask_irq(irq_get_irq_data(gpio_virq));
 
-	irq_set_default_host(mpic->irqhost);
+	irq_set_default_domain(mpic->irqhost);
 }
 
 #else
diff --git a/arch/powerpc/platforms/pasemi/time.c b/arch/powerpc/platforms/pasemi/time.c
index ad721882c8b6..70ac6db027d0 100644
--- a/arch/powerpc/platforms/pasemi/time.c
+++ b/arch/powerpc/platforms/pasemi/time.c
@@ -9,6 +9,8 @@
 
 #include <asm/time.h>
 
+#include "pasemi.h"
+
 time64_t __init pas_get_boot_time(void)
 {
 	/* Let's just return a fake date right now */
diff --git a/arch/powerpc/platforms/powermac/Kconfig b/arch/powerpc/platforms/powermac/Kconfig
index 130707ec9f99..84f101ec53a9 100644
--- a/arch/powerpc/platforms/powermac/Kconfig
+++ b/arch/powerpc/platforms/powermac/Kconfig
@@ -2,6 +2,7 @@
 config PPC_PMAC
 	bool "Apple PowerMac based machines"
 	depends on PPC_BOOK3S && CPU_BIG_ENDIAN
+	select ADB_CUDA if POWER_RESET && ADB
 	select MPIC
 	select FORCE_PCI
 	select PPC_INDIRECT_PCI if PPC32
diff --git a/arch/powerpc/platforms/powermac/backlight.c b/arch/powerpc/platforms/powermac/backlight.c
index aeb79a8b3e10..1796327955c6 100644
--- a/arch/powerpc/platforms/powermac/backlight.c
+++ b/arch/powerpc/platforms/powermac/backlight.c
@@ -9,9 +9,9 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/fb.h>
 #include <linux/backlight.h>
 #include <linux/adb.h>
+#include <linux/of.h>
 #include <linux/pmu.h>
 #include <linux/atomic.h>
 #include <linux/export.h>
@@ -58,43 +58,10 @@ struct backlight_device *pmac_backlight;
 int pmac_has_backlight_type(const char *type)
 {
 	struct device_node* bk_node = of_find_node_by_name(NULL, "backlight");
+	int i = of_property_match_string(bk_node, "backlight-control", type);
 
-	if (bk_node) {
-		const char *prop = of_get_property(bk_node,
-				"backlight-control", NULL);
-		if (prop && strncmp(prop, type, strlen(type)) == 0) {
-			of_node_put(bk_node);
-			return 1;
-		}
-		of_node_put(bk_node);
-	}
-
-	return 0;
-}
-
-int pmac_backlight_curve_lookup(struct fb_info *info, int value)
-{
-	int level = (FB_BACKLIGHT_LEVELS - 1);
-
-	if (info && info->bl_dev) {
-		int i, max = 0;
-
-		/* Look for biggest value */
-		for (i = 0; i < FB_BACKLIGHT_LEVELS; i++)
-			max = max((int)info->bl_curve[i], max);
-
-		/* Look for nearest value */
-		for (i = 0; i < FB_BACKLIGHT_LEVELS; i++) {
-			int diff = abs(info->bl_curve[i] - value);
-			if (diff < max) {
-				max = diff;
-				level = i;
-			}
-		}
-
-	}
-
-	return level;
+	of_node_put(bk_node);
+	return i >= 0;
 }
 
 static void pmac_backlight_key_worker(struct work_struct *work)
diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c
index a195d5faa4e5..2cc257f75c50 100644
--- a/arch/powerpc/platforms/powermac/feature.c
+++ b/arch/powerpc/platforms/powermac/feature.c
@@ -37,6 +37,8 @@
 #include <asm/pci-bridge.h>
 #include <asm/pmac_low_i2c.h>
 
+#include "pmac.h"
+
 #undef DEBUG_FEATURE
 
 #ifdef DEBUG_FEATURE
@@ -132,8 +134,10 @@ static struct pmac_mb_def pmac_mb;
  * Here are the chip specific feature functions
  */
 
-static inline int simple_feature_tweak(struct device_node *node, int type,
-				       int reg, u32 mask, int value)
+#ifndef CONFIG_PPC64
+
+static int simple_feature_tweak(struct device_node *node, int type, int reg,
+				u32 mask, int value)
 {
 	struct macio_chip*	macio;
 	unsigned long		flags;
@@ -152,8 +156,6 @@ static inline int simple_feature_tweak(struct device_node *node, int type,
 	return 0;
 }
 
-#ifndef CONFIG_PPC64
-
 static long ohare_htw_scc_enable(struct device_node *node, long param,
 				 long value)
 {
@@ -1053,11 +1055,11 @@ core99_reset_cpu(struct device_node *node, long param, long value)
 		return -ENODEV;
 
 	for_each_of_cpu_node(np) {
-		const u32 *num = of_get_property(np, "reg", NULL);
 		const u32 *rst = of_get_property(np, "soft-reset", NULL);
-		if (num == NULL || rst == NULL)
+		if (!rst)
 			continue;
-		if (param == *num) {
+		if (param == of_get_cpu_hwid(np, 0)) {
+			of_node_put(np);
 			reset_io = *rst;
 			break;
 		}
@@ -1499,11 +1501,11 @@ static long g5_reset_cpu(struct device_node *node, long param, long value)
 		return -ENODEV;
 
 	for_each_of_cpu_node(np) {
-		const u32 *num = of_get_property(np, "reg", NULL);
 		const u32 *rst = of_get_property(np, "soft-reset", NULL);
-		if (num == NULL || rst == NULL)
+		if (!rst)
 			continue;
-		if (param == *num) {
+		if (param == of_get_cpu_hwid(np, 0)) {
+			of_node_put(np);
 			reset_io = *rst;
 			break;
 		}
@@ -2331,7 +2333,6 @@ static struct pmac_mb_def pmac_mb_defs[] = {
 		PMAC_TYPE_POWERMAC_G5,		g5_features,
 		0,
 	},
-#ifdef CONFIG_PPC64
 	{	"PowerMac7,3",			"PowerMac G5",
 		PMAC_TYPE_POWERMAC_G5,		g5_features,
 		0,
@@ -2357,7 +2358,6 @@ static struct pmac_mb_def pmac_mb_defs[] = {
 		0,
 	},
 #endif /* CONFIG_PPC64 */
-#endif /* CONFIG_PPC64 */
 };
 
 /*
@@ -2612,7 +2612,8 @@ static void __init probe_one_macio(const char *name, const char *compat, int typ
 	struct device_node*	node;
 	int			i;
 	volatile u32 __iomem	*base;
-	const u32		*addrp, *revp;
+	const __be32		*addrp;
+	const u32		*revp;
 	phys_addr_t		addr;
 	u64			size;
 
diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c
index 40f3aa432fba..02474e27df9b 100644
--- a/arch/powerpc/platforms/powermac/low_i2c.c
+++ b/arch/powerpc/platforms/powermac/low_i2c.c
@@ -347,7 +347,7 @@ static irqreturn_t kw_i2c_irq(int irq, void *dev_id)
 	unsigned long flags;
 
 	spin_lock_irqsave(&host->lock, flags);
-	del_timer(&host->timeout_timer);
+	timer_delete(&host->timeout_timer);
 	kw_i2c_handle_interrupt(host, kw_read_reg(reg_isr));
 	if (host->state != state_idle) {
 		host->timeout_timer.expires = jiffies + KW_POLL_TIMEOUT;
@@ -359,7 +359,8 @@ static irqreturn_t kw_i2c_irq(int irq, void *dev_id)
 
 static void kw_i2c_timeout(struct timer_list *t)
 {
-	struct pmac_i2c_host_kw *host = from_timer(host, t, timeout_timer);
+	struct pmac_i2c_host_kw *host = timer_container_of(host, t,
+							   timeout_timer);
 	unsigned long flags;
 
 	spin_lock_irqsave(&host->lock, flags);
@@ -925,8 +926,10 @@ static void __init smu_i2c_probe(void)
 
 		sz = sizeof(struct pmac_i2c_bus) + sizeof(struct smu_i2c_cmd);
 		bus = kzalloc(sz, GFP_KERNEL);
-		if (bus == NULL)
+		if (bus == NULL) {
+			of_node_put(busnode);
 			return;
+		}
 
 		bus->controller = controller;
 		bus->busnode = of_node_get(busnode);
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index fe2e0249cbc2..a112d26185a0 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -514,10 +514,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr)
 		printk(KERN_ERR "nvram: no address\n");
 		return -EINVAL;
 	}
-	nvram_image = memblock_alloc(NVRAM_SIZE, SMP_CACHE_BYTES);
-	if (!nvram_image)
-		panic("%s: Failed to allocate %u bytes\n", __func__,
-		      NVRAM_SIZE);
+	nvram_image = memblock_alloc_or_panic(NVRAM_SIZE, SMP_CACHE_BYTES);
 	nvram_data = ioremap(addr, NVRAM_SIZE*2);
 	nvram_naddrs = 1; /* Make sure we get the correct case */
 
diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c
index 085e0ad20eba..8253de737373 100644
--- a/arch/powerpc/platforms/powermac/pfunc_base.c
+++ b/arch/powerpc/platforms/powermac/pfunc_base.c
@@ -313,7 +313,7 @@ static void __init uninorth_install_pfunc(void)
 	/*
 	 * Install handlers for the hwclock child if any
 	 */
-	for (np = NULL; (np = of_get_next_child(uninorth_node, np)) != NULL;)
+	for_each_child_of_node(uninorth_node, np)
 		if (of_node_name_eq(np, "hw-clock")) {
 			unin_hwclock = np;
 			break;
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 7135ea1d7db6..1959cc13438f 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -2,7 +2,7 @@
 /*
  *  Support for the interrupt controllers found on Power Macintosh,
  *  currently Apple's "Grand Central" interrupt controller in all
- *  it's incarnations. OpenPIC support used on newer machines is
+ *  its incarnations. OpenPIC support used on newer machines is
  *  in a separate file
  *
  *  Copyright (C) 1997 Paul Mackerras (paulus@samba.org)
@@ -250,7 +250,7 @@ static unsigned int pmac_pic_get_irq(void)
 	raw_spin_unlock_irqrestore(&pmac_pic_lock, flags);
 	if (unlikely(irq < 0))
 		return 0;
-	return irq_linear_revmap(pmac_pic_host, irq);
+	return irq_find_mapping(pmac_pic_host, irq);
 }
 
 static int pmac_pic_host_match(struct irq_domain *h, struct device_node *node,
@@ -327,10 +327,11 @@ static void __init pmac_pic_probe_oldstyle(void)
 	/*
 	 * Allocate an irq host
 	 */
-	pmac_pic_host = irq_domain_add_linear(master, max_irqs,
-					      &pmac_pic_host_ops, NULL);
+	pmac_pic_host = irq_domain_create_linear(of_fwnode_handle(master),
+						 max_irqs,
+						 &pmac_pic_host_ops, NULL);
 	BUG_ON(pmac_pic_host == NULL);
-	irq_set_default_host(pmac_pic_host);
+	irq_set_default_domain(pmac_pic_host);
 
 	/* Get addresses of first controller if we have a node for it */
 	BUG_ON(of_address_to_resource(master, 0, &r));
@@ -599,7 +600,7 @@ not_found:
 	return viaint;
 }
 
-static int pmacpic_suspend(void)
+static int pmacpic_suspend(void *data)
 {
 	int viaint = pmacpic_find_viaint();
 
@@ -620,7 +621,7 @@ static int pmacpic_suspend(void)
         return 0;
 }
 
-static void pmacpic_resume(void)
+static void pmacpic_resume(void *data)
 {
 	int i;
 
@@ -633,15 +634,19 @@ static void pmacpic_resume(void)
 			pmac_unmask_irq(irq_get_irq_data(i));
 }
 
-static struct syscore_ops pmacpic_syscore_ops = {
+static const struct syscore_ops pmacpic_syscore_ops = {
 	.suspend	= pmacpic_suspend,
 	.resume		= pmacpic_resume,
 };
 
+static struct syscore pmacpic_syscore = {
+	.ops = &pmacpic_syscore_ops,
+};
+
 static int __init init_pmacpic_syscore(void)
 {
 	if (pmac_irq_hw[0])
-		register_syscore_ops(&pmacpic_syscore_ops);
+		register_syscore(&pmacpic_syscore);
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 193cc9c39422..eb092f293113 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -28,13 +28,11 @@
 #include <linux/ptrace.h>
 #include <linux/export.h>
 #include <linux/user.h>
-#include <linux/tty.h>
 #include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/ioport.h>
 #include <linux/major.h>
 #include <linux/initrd.h>
-#include <linux/vt_kern.h>
 #include <linux/console.h>
 #include <linux/pci.h>
 #include <linux/adb.h>
@@ -45,7 +43,8 @@
 #include <linux/root_dev.h>
 #include <linux/bitops.h>
 #include <linux/suspend.h>
-#include <linux/of_device.h>
+#include <linux/string_choices.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
 
 #include <asm/reg.h>
@@ -76,7 +75,8 @@ int pmac_newworld;
 
 static int current_root_goodness = -1;
 
-#define DEFAULT_ROOT_DEVICE Root_SDA1	/* sda1 - slightly silly choice */
+/* sda1 - slightly silly choice */
+#define DEFAULT_ROOT_DEVICE	MKDEV(SCSI_DISK0_MAJOR, 1)
 
 sys_ctrler_t sys_ctrler = SYS_CTRLER_UNKNOWN;
 EXPORT_SYMBOL(sys_ctrler);
@@ -237,8 +237,7 @@ static void __init l2cr_init(void)
 				_set_L2CR(0);
 				_set_L2CR(*l2cr);
 				pr_info("L2CR overridden (0x%x), backside cache is %s\n",
-					*l2cr, ((*l2cr) & 0x80000000) ?
-					"enabled" : "disabled");
+					*l2cr, str_enabled_disabled((*l2cr) & 0x80000000));
 			}
 			of_node_put(np);
 			break;
diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S
index d497a60003d2..822ed70cdcbf 100644
--- a/arch/powerpc/platforms/powermac/sleep.S
+++ b/arch/powerpc/platforms/powermac/sleep.S
@@ -176,7 +176,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 	 *    memory location containing the PC to resume from
 	 *    at address 0.
 	 *  - On Core99, we must store the wakeup vector at
-	 *    address 0x80 and eventually it's parameters
+	 *    address 0x80 and eventually its parameters
 	 *    at address 0x84. I've have some trouble with those
 	 *    parameters however and I no longer use them.
 	 */
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 8be71920e63c..88e92af8acf9 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -35,7 +35,7 @@
 
 #include <asm/ptrace.h>
 #include <linux/atomic.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/irq.h>
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -190,7 +190,7 @@ static int __init psurge_secondary_ipi_init(void)
 {
 	int rc = -ENOMEM;
 
-	psurge_host = irq_domain_add_nomap(NULL, ~0, &psurge_host_ops, NULL);
+	psurge_host = irq_domain_create_nomap(NULL, ~0, &psurge_host_ops, NULL);
 
 	if (psurge_host)
 		psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
@@ -413,7 +413,7 @@ static void __init smp_psurge_setup_cpu(int cpu_nr)
 		printk(KERN_ERR "Couldn't get primary IPI interrupt");
 }
 
-void __init smp_psurge_take_timebase(void)
+static void __init smp_psurge_take_timebase(void)
 {
 	if (psurge_type != PSURGE_DUAL)
 		return;
@@ -429,7 +429,7 @@ void __init smp_psurge_take_timebase(void)
 	set_dec(tb_ticks_per_jiffy/2);
 }
 
-void __init smp_psurge_give_timebase(void)
+static void __init smp_psurge_give_timebase(void)
 {
 	/* Nothing to do here */
 }
@@ -598,8 +598,10 @@ static void __init smp_core99_setup_i2c_hwsync(int ncpus)
 			name = "Pulsar";
 			break;
 		}
-		if (pmac_tb_freeze != NULL)
+		if (pmac_tb_freeze != NULL) {
+			of_node_put(cc);
 			break;
+		}
 	}
 	if (pmac_tb_freeze != NULL) {
 		/* Open i2c bus for synchronous access */
@@ -825,7 +827,7 @@ static int smp_core99_kick_cpu(int nr)
 	mdelay(1);
 
 	/* Restore our exception vector */
-	patch_instruction(vector, ppc_inst(save_vector));
+	patch_uint(vector, save_vector);
 
 	local_irq_restore(flags);
 	if (ppc_md.progress) ppc_md.progress("smp_core99_kick_cpu done", 0x347);
diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c
index 4c5790aff1b5..b4426a35aca3 100644
--- a/arch/powerpc/platforms/powermac/time.c
+++ b/arch/powerpc/platforms/powermac/time.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/time.h>
@@ -26,8 +27,8 @@
 #include <linux/rtc.h>
 #include <linux/of_address.h>
 
+#include <asm/early_ioremap.h>
 #include <asm/sections.h>
-#include <asm/io.h>
 #include <asm/machdep.h>
 #include <asm/time.h>
 #include <asm/nvram.h>
@@ -77,7 +78,7 @@ long __init pmac_time_init(void)
 		delta |= 0xFF000000UL;
 	dst = ((pmac_xpram_read(PMAC_XPRAM_MACHINE_LOC + 0x8) & 0x80) != 0);
 	printk("GMT Delta read from XPRAM: %d minutes, DST: %s\n", delta/60,
-		dst ? "on" : "off");
+		str_on_off(dst));
 #endif
 	return delta;
 }
@@ -182,7 +183,7 @@ static int __init via_calibrate_decr(void)
 		return 0;
 	}
 	of_node_put(vias);
-	via = ioremap(rsrc.start, resource_size(&rsrc));
+	via = early_ioremap(rsrc.start, resource_size(&rsrc));
 	if (via == NULL) {
 		printk(KERN_ERR "Failed to map VIA for timer calibration !\n");
 		return 0;
@@ -207,7 +208,7 @@ static int __init via_calibrate_decr(void)
 
 	ppc_tb_freq = (dstart - dend) * 100 / 6;
 
-	iounmap(via);
+	early_iounmap((void *)via, resource_size(&rsrc));
 
 	return 1;
 }
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 70a46acc70d6..b5ad7c173ef0 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -9,6 +9,7 @@ config PPC_POWERNV
 	select PPC_P7_NAP
 	select FORCE_PCI
 	select PCI_MSI
+	select IRQ_MSI_LIB
 	select EPAPR_BOOT
 	select PPC_INDIRECT_PIO
 	select PPC_UDBG_16550
@@ -17,6 +18,7 @@ config PPC_POWERNV
 	select MMU_NOTIFIER
 	select FORCE_SMP
 	select ARCH_SUPPORTS_PER_VMA_LOCK
+	select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
 	default y
 
 config OPAL_PRD
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 19f0fc5c6f1b..9e5d0c847ee2 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -21,7 +21,6 @@ obj-$(CONFIG_PRESERVE_FA_DUMP)	+= opal-fadump.o
 obj-$(CONFIG_OPAL_CORE)	+= opal-core.o
 obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o pci-ioda-tce.o
 obj-$(CONFIG_PCI_IOV)   += pci-sriov.o
-obj-$(CONFIG_CXL_BASE)	+= pci-cxl.o
 obj-$(CONFIG_EEH)	+= eeh-powernv.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
 obj-$(CONFIG_OPAL_PRD)	+= opal-prd.o
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index a83cb679dd59..db3370d1673c 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -99,7 +99,6 @@ static ssize_t pnv_eeh_ei_write(struct file *filp,
 
 static const struct file_operations pnv_eeh_ei_fops = {
 	.open	= simple_open,
-	.llseek	= no_llseek,
 	.write	= pnv_eeh_ei_write,
 };
 
@@ -855,13 +854,12 @@ static int pnv_eeh_bridge_reset(struct pci_dev *pdev, int option)
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
 	struct device_node *dn = pci_device_to_OF_node(pdev);
-	uint64_t id = PCI_SLOT_ID(phb->opal_id,
-				  (pdev->bus->number << 8) | pdev->devfn);
+	uint64_t id = PCI_SLOT_ID(phb->opal_id, pci_dev_id(pdev));
 	uint8_t scope;
 	int64_t rc;
 
 	/* Hot reset to the bus if firmware cannot handle */
-	if (!dn || !of_get_property(dn, "ibm,reset-by-firmware", NULL))
+	if (!dn || !of_property_present(dn, "ibm,reset-by-firmware"))
 		return __pnv_eeh_bridge_reset(pdev, option);
 
 	pr_debug("%s: FW reset PCI bus %04x:%02x with option %d\n",
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 6dfe8d611164..d98b933e4984 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -18,7 +18,7 @@
 #include <asm/opal.h>
 #include <asm/cputhreads.h>
 #include <asm/cpuidle.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/smp.h>
 #include <asm/runlatch.h>
 #include <asm/dbell.h>
@@ -246,9 +246,9 @@ static inline void atomic_lock_thread_idle(void)
 {
 	int cpu = raw_smp_processor_id();
 	int first = cpu_first_thread_sibling(cpu);
-	unsigned long *state = &paca_ptrs[first]->idle_state;
+	unsigned long *lock = &paca_ptrs[first]->idle_lock;
 
-	while (unlikely(test_and_set_bit_lock(NR_PNV_CORE_IDLE_LOCK_BIT, state)))
+	while (unlikely(test_and_set_bit_lock(NR_PNV_CORE_IDLE_LOCK_BIT, lock)))
 		barrier();
 }
 
@@ -258,29 +258,31 @@ static inline void atomic_unlock_and_stop_thread_idle(void)
 	int first = cpu_first_thread_sibling(cpu);
 	unsigned long thread = 1UL << cpu_thread_in_core(cpu);
 	unsigned long *state = &paca_ptrs[first]->idle_state;
+	unsigned long *lock = &paca_ptrs[first]->idle_lock;
 	u64 s = READ_ONCE(*state);
 	u64 new, tmp;
 
-	BUG_ON(!(s & PNV_CORE_IDLE_LOCK_BIT));
+	BUG_ON(!(READ_ONCE(*lock) & PNV_CORE_IDLE_LOCK_BIT));
 	BUG_ON(s & thread);
 
 again:
-	new = (s | thread) & ~PNV_CORE_IDLE_LOCK_BIT;
+	new = s | thread;
 	tmp = cmpxchg(state, s, new);
 	if (unlikely(tmp != s)) {
 		s = tmp;
 		goto again;
 	}
+	clear_bit_unlock(NR_PNV_CORE_IDLE_LOCK_BIT, lock);
 }
 
 static inline void atomic_unlock_thread_idle(void)
 {
 	int cpu = raw_smp_processor_id();
 	int first = cpu_first_thread_sibling(cpu);
-	unsigned long *state = &paca_ptrs[first]->idle_state;
+	unsigned long *lock = &paca_ptrs[first]->idle_lock;
 
-	BUG_ON(!test_bit(NR_PNV_CORE_IDLE_LOCK_BIT, state));
-	clear_bit_unlock(NR_PNV_CORE_IDLE_LOCK_BIT, state);
+	BUG_ON(!test_bit(NR_PNV_CORE_IDLE_LOCK_BIT, lock));
+	clear_bit_unlock(NR_PNV_CORE_IDLE_LOCK_BIT, lock);
 }
 
 /* P7 and P8 */
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 877720c64515..2ea30b343354 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -48,11 +48,15 @@ static ssize_t memtrace_read(struct file *filp, char __user *ubuf,
 static int memtrace_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct memtrace_entry *ent = filp->private_data;
+	unsigned long ent_nrpages = ent->size >> PAGE_SHIFT;
+	unsigned long vma_nrpages = vma_pages(vma);
 
-	if (ent->size < vma->vm_end - vma->vm_start)
+	/* The requested page offset should be within object's page count */
+	if (vma->vm_pgoff >= ent_nrpages)
 		return -EINVAL;
 
-	if (vma->vm_pgoff << PAGE_SHIFT >= ent->size)
+	/* The requested mapping range should remain within the bounds */
+	if (vma_nrpages > ent_nrpages - vma->vm_pgoff)
 		return -EINVAL;
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
@@ -88,26 +92,6 @@ static void flush_dcache_range_chunked(unsigned long start, unsigned long stop,
 	}
 }
 
-static void memtrace_clear_range(unsigned long start_pfn,
-				 unsigned long nr_pages)
-{
-	unsigned long pfn;
-
-	/* As HIGHMEM does not apply, use clear_page() directly. */
-	for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
-		if (IS_ALIGNED(pfn, PAGES_PER_SECTION))
-			cond_resched();
-		clear_page(__va(PFN_PHYS(pfn)));
-	}
-	/*
-	 * Before we go ahead and use this range as cache inhibited range
-	 * flush the cache.
-	 */
-	flush_dcache_range_chunked((unsigned long)pfn_to_kaddr(start_pfn),
-				   (unsigned long)pfn_to_kaddr(start_pfn + nr_pages),
-				   FLUSH_CHUNK_SIZE);
-}
-
 static u64 memtrace_alloc_node(u32 nid, u64 size)
 {
 	const unsigned long nr_pages = PHYS_PFN(size);
@@ -119,17 +103,18 @@ static u64 memtrace_alloc_node(u32 nid, u64 size)
 	 * by alloc_contig_pages().
 	 */
 	page = alloc_contig_pages(nr_pages, GFP_KERNEL | __GFP_THISNODE |
-				  __GFP_NOWARN, nid, NULL);
+				  __GFP_NOWARN | __GFP_ZERO, nid, NULL);
 	if (!page)
 		return 0;
 	start_pfn = page_to_pfn(page);
 
 	/*
-	 * Clear the range while we still have a linear mapping.
-	 *
-	 * TODO: use __GFP_ZERO with alloc_contig_pages() once supported.
+	 * Before we go ahead and use this range as cache inhibited range
+	 * flush the cache.
 	 */
-	memtrace_clear_range(start_pfn, nr_pages);
+	flush_dcache_range_chunked((unsigned long)pfn_to_kaddr(start_pfn),
+				   (unsigned long)pfn_to_kaddr(start_pfn + nr_pages),
+				   FLUSH_CHUNK_SIZE);
 
 	/*
 	 * Set pages PageOffline(), to indicate that nobody (e.g., hibernation,
diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c
index 629067781cec..f8139948348e 100644
--- a/arch/powerpc/platforms/powernv/ocxl.c
+++ b/arch/powerpc/platforms/powernv/ocxl.c
@@ -172,12 +172,11 @@ static void pnv_ocxl_fixup_actag(struct pci_dev *dev)
 	if (phb->type != PNV_PHB_NPU_OCAPI)
 		return;
 
-	mutex_lock(&links_list_lock);
+	guard(mutex)(&links_list_lock);
 
 	link = find_link(dev);
 	if (!link) {
 		dev_warn(&dev->dev, "couldn't update actag information\n");
-		mutex_unlock(&links_list_lock);
 		return;
 	}
 
@@ -206,7 +205,6 @@ static void pnv_ocxl_fixup_actag(struct pci_dev *dev)
 	dev_dbg(&dev->dev, "total actags for function: %d\n",
 		link->fn_desired_actags[PCI_FUNC(dev->devfn)]);
 
-	mutex_unlock(&links_list_lock);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pnv_ocxl_fixup_actag);
 
@@ -253,12 +251,11 @@ int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled,
 {
 	struct npu_link *link;
 
-	mutex_lock(&links_list_lock);
+	guard(mutex)(&links_list_lock);
 
 	link = find_link(dev);
 	if (!link) {
 		dev_err(&dev->dev, "actag information not found\n");
-		mutex_unlock(&links_list_lock);
 		return -ENODEV;
 	}
 	/*
@@ -274,7 +271,6 @@ int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled,
 	*enabled   = link->fn_actags[PCI_FUNC(dev->devfn)].count;
 	*supported = link->fn_desired_actags[PCI_FUNC(dev->devfn)];
 
-	mutex_unlock(&links_list_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pnv_ocxl_get_actag);
@@ -293,12 +289,11 @@ int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count)
 	 *
 	 * We only support one AFU-carrying function for now.
 	 */
-	mutex_lock(&links_list_lock);
+	guard(mutex)(&links_list_lock);
 
 	link = find_link(dev);
 	if (!link) {
 		dev_err(&dev->dev, "actag information not found\n");
-		mutex_unlock(&links_list_lock);
 		return -ENODEV;
 	}
 
@@ -309,7 +304,6 @@ int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count)
 			break;
 		}
 
-	mutex_unlock(&links_list_lock);
 	dev_dbg(&dev->dev, "%d PASIDs available for function\n",
 		rc ? 0 : *count);
 	return rc;
@@ -449,7 +443,7 @@ int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask,
 	if (!data)
 		return -ENOMEM;
 
-	bdfn = (dev->bus->number << 8) | dev->devfn;
+	bdfn = pci_dev_id(dev);
 	rc = opal_npu_spa_setup(phb->opal_id, bdfn, virt_to_phys(spa_mem),
 				PE_mask);
 	if (rc) {
diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c
index f812c74c61e5..021b0ec29e24 100644
--- a/arch/powerpc/platforms/powernv/opal-call.c
+++ b/arch/powerpc/platforms/powernv/opal-call.c
@@ -167,8 +167,6 @@ OPAL_CALL(opal_pci_map_pe_mmio_window,		OPAL_PCI_MAP_PE_MMIO_WINDOW);
 OPAL_CALL(opal_pci_set_phb_table_memory,	OPAL_PCI_SET_PHB_TABLE_MEMORY);
 OPAL_CALL(opal_pci_set_pe,			OPAL_PCI_SET_PE);
 OPAL_CALL(opal_pci_set_peltv,			OPAL_PCI_SET_PELTV);
-OPAL_CALL(opal_pci_set_mve,			OPAL_PCI_SET_MVE);
-OPAL_CALL(opal_pci_set_mve_enable,		OPAL_PCI_SET_MVE_ENABLE);
 OPAL_CALL(opal_pci_get_xive_reissue,		OPAL_PCI_GET_XIVE_REISSUE);
 OPAL_CALL(opal_pci_set_xive_reissue,		OPAL_PCI_SET_XIVE_REISSUE);
 OPAL_CALL(opal_pci_set_xive_pe,			OPAL_PCI_SET_XIVE_PE);
diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c
index bb7657115f1d..784602a48afb 100644
--- a/arch/powerpc/platforms/powernv/opal-core.c
+++ b/arch/powerpc/platforms/powernv/opal-core.c
@@ -16,7 +16,7 @@
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
-#include <linux/crash_core.h>
+#include <linux/vmcore_info.h>
 #include <linux/of.h>
 
 #include <asm/page.h>
@@ -149,7 +149,7 @@ static Elf64_Word *__init auxv_to_elf64_notes(Elf64_Word *buf,
 	/* end of vector */
 	bufp[idx++] = cpu_to_be64(AT_NULL);
 
-	buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_AUXV,
+	buf = append_elf64_note(buf, NN_AUXV, NT_AUXV,
 				oc_conf->auxv_buf, AUXV_DESC_SZ);
 	return buf;
 }
@@ -159,7 +159,7 @@ static Elf64_Word *__init auxv_to_elf64_notes(Elf64_Word *buf,
  * Returns number of bytes read on success, -errno on failure.
  */
 static ssize_t read_opalcore(struct file *file, struct kobject *kobj,
-			     struct bin_attribute *bin_attr, char *to,
+			     const struct bin_attribute *bin_attr, char *to,
 			     loff_t pos, size_t count)
 {
 	struct opalcore *m;
@@ -206,7 +206,7 @@ static ssize_t read_opalcore(struct file *file, struct kobject *kobj,
 	return (tpos - pos);
 }
 
-static struct bin_attribute opal_core_attr = {
+static struct bin_attribute opal_core_attr __ro_after_init = {
 	.attr = {.name = "core", .mode = 0400},
 	.read = read_opalcore
 };
@@ -252,7 +252,7 @@ static Elf64_Word * __init opalcore_append_cpu_notes(Elf64_Word *buf)
 	 * crashing CPU's prstatus.
 	 */
 	first_cpu_note = buf;
-	buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+	buf = append_elf64_note(buf, NN_PRSTATUS, NT_PRSTATUS,
 				&prstatus, sizeof(prstatus));
 
 	for (i = 0; i < oc_conf->num_cpus; i++, bufp += size_per_thread) {
@@ -279,7 +279,7 @@ static Elf64_Word * __init opalcore_append_cpu_notes(Elf64_Word *buf)
 		fill_prstatus(&prstatus, thread_pir, &regs);
 
 		if (thread_pir != oc_conf->crashing_cpu) {
-			buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME,
+			buf = append_elf64_note(buf, NN_PRSTATUS,
 						NT_PRSTATUS, &prstatus,
 						sizeof(prstatus));
 		} else {
@@ -287,7 +287,7 @@ static Elf64_Word * __init opalcore_append_cpu_notes(Elf64_Word *buf)
 			 * Add crashing CPU as the first NT_PRSTATUS note for
 			 * GDB to process the core file appropriately.
 			 */
-			append_elf64_note(first_cpu_note, CRASH_CORE_NOTE_NAME,
+			append_elf64_note(first_cpu_note, NN_PRSTATUS,
 					  NT_PRSTATUS, &prstatus,
 					  sizeof(prstatus));
 		}
@@ -599,7 +599,7 @@ static struct attribute *mpipl_attr[] = {
 	NULL,
 };
 
-static struct bin_attribute *mpipl_bin_attr[] = {
+static const struct bin_attribute *const mpipl_bin_attr[] = {
 	&opal_core_attr,
 	NULL,
 
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 16c5860f1372..cc3cc9ddf9d1 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -210,7 +210,7 @@ static struct attribute *dump_default_attrs[] = {
 };
 ATTRIBUTE_GROUPS(dump_default);
 
-static struct kobj_type dump_ktype = {
+static const struct kobj_type dump_ktype = {
 	.sysfs_ops = &dump_sysfs_ops,
 	.release = &dump_release,
 	.default_groups = dump_default_groups,
@@ -286,7 +286,7 @@ out:
 }
 
 static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj,
-			      struct bin_attribute *bin_attr,
+			      const struct bin_attribute *bin_attr,
 			      char *buffer, loff_t pos, size_t count)
 {
 	ssize_t rc;
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 554fdd7f88b8..c3fc5d258146 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -146,7 +146,7 @@ static struct attribute *elog_default_attrs[] = {
 };
 ATTRIBUTE_GROUPS(elog_default);
 
-static struct kobj_type elog_ktype = {
+static const struct kobj_type elog_ktype = {
 	.sysfs_ops = &elog_sysfs_ops,
 	.release = &elog_release,
 	.default_groups = elog_default_groups,
@@ -156,7 +156,7 @@ static struct kobj_type elog_ktype = {
 #define OPAL_MAX_ERRLOG_SIZE	16384
 
 static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj,
-			     struct bin_attribute *bin_attr,
+			     const struct bin_attribute *bin_attr,
 			     char *buffer, loff_t pos, size_t count)
 {
 	int opal_rc;
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 964f464b1b0e..c9c1dfb35464 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -513,8 +513,8 @@ out:
 	final_note(note_buf);
 
 	pr_debug("Updating elfcore header (%llx) with cpu notes\n",
-		 fdh->elfcorehdr_addr);
-	fadump_update_elfcore_header(__va(fdh->elfcorehdr_addr));
+		 fadump_conf->elfcorehdr_addr);
+	fadump_update_elfcore_header((char *)fadump_conf->elfcorehdr_addr);
 	return 0;
 }
 
@@ -526,12 +526,7 @@ static int __init opal_fadump_process(struct fw_dump *fadump_conf)
 	if (!opal_fdm_active || !fadump_conf->fadumphdr_addr)
 		return rc;
 
-	/* Validate the fadump crash info header */
 	fdh = __va(fadump_conf->fadumphdr_addr);
-	if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
-		pr_err("Crash info header is not valid.\n");
-		return rc;
-	}
 
 #ifdef CONFIG_OPAL_CORE
 	/*
@@ -545,18 +540,7 @@ static int __init opal_fadump_process(struct fw_dump *fadump_conf)
 		kernel_initiated = true;
 #endif
 
-	rc = opal_fadump_build_cpu_notes(fadump_conf, fdh);
-	if (rc)
-		return rc;
-
-	/*
-	 * We are done validating dump info and elfcore header is now ready
-	 * to be exported. set elfcorehdr_addr so that vmcore module will
-	 * export the elfcore header through '/proc/vmcore'.
-	 */
-	elfcorehdr_addr = fdh->elfcorehdr_addr;
-
-	return rc;
+	return opal_fadump_build_cpu_notes(fadump_conf, fdh);
 }
 
 static void opal_fadump_region_show(struct fw_dump *fadump_conf,
@@ -615,6 +599,12 @@ static void opal_fadump_trigger(struct fadump_crash_info_header *fdh,
 		pr_emerg("No backend support for MPIPL!\n");
 }
 
+/* FADUMP_MAX_MEM_REGS or lower */
+static int opal_fadump_max_boot_mem_rgns(void)
+{
+	return FADUMP_MAX_MEM_REGS;
+}
+
 static struct fadump_ops opal_fadump_ops = {
 	.fadump_init_mem_struct		= opal_fadump_init_mem_struct,
 	.fadump_get_metadata_size	= opal_fadump_get_metadata_size,
@@ -627,6 +617,7 @@ static struct fadump_ops opal_fadump_ops = {
 	.fadump_process			= opal_fadump_process,
 	.fadump_region_show		= opal_fadump_region_show,
 	.fadump_trigger			= opal_fadump_trigger,
+	.fadump_max_boot_mem_rgns	= opal_fadump_max_boot_mem_rgns,
 };
 
 void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
@@ -674,8 +665,10 @@ void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
 		}
 	}
 
-	fadump_conf->ops		= &opal_fadump_ops;
-	fadump_conf->fadump_supported	= 1;
+	fadump_conf->ops			= &opal_fadump_ops;
+	fadump_conf->fadump_supported		= 1;
+	/* TODO: Add support to pass additional parameters */
+	fadump_conf->param_area_supported	= 0;
 
 	/*
 	 * Firmware supports 32-bit field for size. Align it to PAGE_SIZE
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h
index 3f715efb0aa6..5eeb794b5eb1 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.h
+++ b/arch/powerpc/platforms/powernv/opal-fadump.h
@@ -135,7 +135,7 @@ static inline void opal_fadump_read_regs(char *bufp, unsigned int regs_cnt,
 	for (i = 0; i < regs_cnt; i++, bufp += reg_entry_size) {
 		reg_entry = (struct hdat_fadump_reg_entry *)bufp;
 		val = (cpu_endian ? be64_to_cpu(reg_entry->reg_val) :
-		       (u64)(reg_entry->reg_val));
+		       (u64 __force)(reg_entry->reg_val));
 		opal_fadump_set_regval_regnum(regs,
 					      be32_to_cpu(reg_entry->reg_type),
 					      be32_to_cpu(reg_entry->reg_num),
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index d5ea04e8e4c5..a3f7a2928767 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -432,7 +432,7 @@ static int alloc_image_buf(char *buffer, size_t count)
  * and pre-allocate required memory.
  */
 static ssize_t image_data_write(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buffer, loff_t pos, size_t count)
 {
 	int rc;
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
index 348a8cdaecd6..828fc4d88471 100644
--- a/arch/powerpc/platforms/powernv/opal-imc.c
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -11,7 +11,6 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
 #include <linux/crash_dump.h>
 #include <linux/debugfs.h>
 #include <asm/opal.h>
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index d55652b5f6fa..e180bd8e1400 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -59,7 +59,7 @@ again:
 
 		cond_resched();
 	}
-	last_outstanding_events = 0;
+	WRITE_ONCE(last_outstanding_events, 0);
 	if (opal_poll_events(&events) != OPAL_SUCCESS)
 		return;
 	e = be64_to_cpu(events) & opal_event_irqchip.mask;
@@ -69,7 +69,7 @@ again:
 
 bool opal_have_pending_events(void)
 {
-	if (last_outstanding_events & opal_event_irqchip.mask)
+	if (READ_ONCE(last_outstanding_events) & opal_event_irqchip.mask)
 		return true;
 	return false;
 }
@@ -124,7 +124,7 @@ static irqreturn_t opal_interrupt(int irq, void *data)
 	__be64 events;
 
 	opal_handle_interrupt(virq_to_hw(irq), &events);
-	last_outstanding_events = be64_to_cpu(events);
+	WRITE_ONCE(last_outstanding_events, be64_to_cpu(events));
 	if (opal_have_pending_events())
 		opal_wake_poller();
 
@@ -191,7 +191,8 @@ int __init opal_event_init(void)
 	 * fall back to the legacy method (opal_event_request(...))
 	 * anyway. */
 	dn = of_find_compatible_node(NULL, NULL, "ibm,opal-event");
-	opal_event_irqchip.domain = irq_domain_add_linear(dn, MAX_NUM_EVENTS,
+	opal_event_irqchip.domain = irq_domain_create_linear(of_fwnode_handle(dn),
+				MAX_NUM_EVENTS,
 				&opal_event_domain_ops, &opal_event_irqchip);
 	of_node_put(dn);
 	if (!opal_event_irqchip.domain) {
@@ -275,11 +276,14 @@ int __init opal_event_init(void)
 		else
 			name = kasprintf(GFP_KERNEL, "opal");
 
+		if (!name)
+			continue;
 		/* Install interrupt handler */
 		rc = request_irq(r->start, opal_interrupt, r->flags & IRQD_TRIGGER_MASK,
 				 name, NULL);
 		if (rc) {
 			pr_warn("Error %d requesting OPAL irq %d\n", rc, (int)r->start);
+			kfree(name);
 			continue;
 		}
 	}
diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c
index 6c3bc4b4da98..bb4218fa796e 100644
--- a/arch/powerpc/platforms/powernv/opal-kmsg.c
+++ b/arch/powerpc/platforms/powernv/opal-kmsg.c
@@ -20,13 +20,13 @@
  * message, it just ensures that OPAL completely flushes the console buffer.
  */
 static void kmsg_dump_opal_console_flush(struct kmsg_dumper *dumper,
-				     enum kmsg_dump_reason reason)
+				     struct kmsg_dump_detail *detail)
 {
 	/*
 	 * Outside of a panic context the pollers will continue to run,
 	 * so we don't need to do any special flushing.
 	 */
-	if (reason != KMSG_DUMP_PANIC)
+	if (detail->reason != KMSG_DUMP_PANIC)
 		return;
 
 	opal_flush_console(0);
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index a16f07cdab26..8a7f39e106bd 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -393,7 +393,7 @@ void __init opal_lpc_init(void)
 	for_each_compatible_node(np, NULL, "ibm,power8-lpc") {
 		if (!of_device_is_available(np))
 			continue;
-		if (!of_get_property(np, "primary", NULL))
+		if (!of_property_present(np, "primary"))
 			continue;
 		opal_lpc_chip_id = of_get_ibm_chip_id(np);
 		of_node_put(np);
diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c
index 22d6efe17b0d..992a6b379a66 100644
--- a/arch/powerpc/platforms/powernv/opal-msglog.c
+++ b/arch/powerpc/platforms/powernv/opal-msglog.c
@@ -94,13 +94,13 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
 }
 
 static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj,
-				struct bin_attribute *bin_attr, char *to,
+				const struct bin_attribute *bin_attr, char *to,
 				loff_t pos, size_t count)
 {
 	return opal_msglog_copy(to, pos, count);
 }
 
-static struct bin_attribute opal_msglog_attr = {
+static struct bin_attribute opal_msglog_attr __ro_after_init = {
 	.attr = {.name = "msglog", .mode = 0400},
 	.read = opal_msglog_read
 };
diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c
index 7bfe4cbeb35a..ea917266aa17 100644
--- a/arch/powerpc/platforms/powernv/opal-powercap.c
+++ b/arch/powerpc/platforms/powernv/opal-powercap.c
@@ -196,6 +196,12 @@ void __init opal_powercap_init(void)
 
 		j = 0;
 		pcaps[i].pg.name = kasprintf(GFP_KERNEL, "%pOFn", node);
+		if (!pcaps[i].pg.name) {
+			kfree(pcaps[i].pattrs);
+			kfree(pcaps[i].pg.attrs);
+			goto out_pcaps_pattrs;
+		}
+
 		if (has_min) {
 			powercap_add_attr(min, "powercap-min",
 					  &pcaps[i].pattrs[j]);
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index 113bdb151f68..dc246ed4b7b4 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -24,13 +24,20 @@
 #include <linux/uaccess.h>
 
 
+struct opal_prd_msg {
+	union {
+		struct opal_prd_msg_header header;
+		DECLARE_FLEX_ARRAY(u8, data);
+	};
+};
+
 /*
  * The msg member must be at the end of the struct, as it's followed by the
  * message data.
  */
 struct opal_prd_msg_queue_item {
-	struct list_head		list;
-	struct opal_prd_msg_header	msg;
+	struct list_head	list;
+	struct opal_prd_msg	msg;
 };
 
 static struct device_node *prd_node;
@@ -59,6 +66,8 @@ static bool opal_prd_range_is_valid(uint64_t addr, uint64_t size)
 		const char *label;
 
 		addrp = of_get_address(node, 0, &range_size, NULL);
+		if (!addrp)
+			continue;
 
 		range_addr = of_read_number(addrp, 2);
 		range_end = range_addr + range_size;
@@ -156,7 +165,7 @@ static ssize_t opal_prd_read(struct file *file, char __user *buf,
 	int rc;
 
 	/* we need at least a header's worth of data */
-	if (count < sizeof(item->msg))
+	if (count < sizeof(item->msg.header))
 		return -EINVAL;
 
 	if (*ppos)
@@ -186,7 +195,7 @@ static ssize_t opal_prd_read(struct file *file, char __user *buf,
 			return -EINTR;
 	}
 
-	size = be16_to_cpu(item->msg.size);
+	size = be16_to_cpu(item->msg.header.size);
 	if (size > count) {
 		err = -EINVAL;
 		goto err_requeue;
@@ -214,8 +223,8 @@ static ssize_t opal_prd_write(struct file *file, const char __user *buf,
 		size_t count, loff_t *ppos)
 {
 	struct opal_prd_msg_header hdr;
+	struct opal_prd_msg *msg;
 	ssize_t size;
-	void *msg;
 	int rc;
 
 	size = sizeof(hdr);
@@ -247,12 +256,12 @@ static ssize_t opal_prd_write(struct file *file, const char __user *buf,
 
 static int opal_prd_release(struct inode *inode, struct file *file)
 {
-	struct opal_prd_msg_header msg;
+	struct opal_prd_msg msg;
 
-	msg.size = cpu_to_be16(sizeof(msg));
-	msg.type = OPAL_PRD_MSG_TYPE_FINI;
+	msg.header.size = cpu_to_be16(sizeof(msg));
+	msg.header.type = OPAL_PRD_MSG_TYPE_FINI;
 
-	opal_prd_msg((struct opal_prd_msg *)&msg);
+	opal_prd_msg(&msg);
 
 	atomic_xchg(&prd_usage, 0);
 
@@ -352,7 +361,7 @@ static int opal_prd_msg_notifier(struct notifier_block *nb,
 	if (!item)
 		return -ENOMEM;
 
-	memcpy(&item->msg, msg->params, msg_size);
+	memcpy(&item->msg.data, msg->params, msg_size);
 
 	spin_lock_irqsave(&opal_prd_msg_queue_lock, flags);
 	list_add_tail(&item->list, &opal_prd_msg_queue);
@@ -416,12 +425,11 @@ static int opal_prd_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int opal_prd_remove(struct platform_device *pdev)
+static void opal_prd_remove(struct platform_device *pdev)
 {
 	misc_deregister(&opal_prd_dev);
 	opal_message_notifier_unregister(OPAL_MSG_PRD, &opal_prd_event_nb);
 	opal_message_notifier_unregister(OPAL_MSG_PRD2, &opal_prd_event_nb2);
-	return 0;
 }
 
 static const struct of_device_id opal_prd_match[] = {
@@ -435,7 +443,7 @@ static struct platform_driver opal_prd_driver = {
 		.of_match_table	= opal_prd_match,
 	},
 	.probe	= opal_prd_probe,
-	.remove	= opal_prd_remove,
+	.remove = opal_prd_remove,
 };
 
 module_platform_driver(opal_prd_driver);
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index a9bcf9217e64..79011a263aa6 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -11,8 +11,9 @@
 #include <linux/bcd.h>
 #include <linux/rtc.h>
 #include <linux/delay.h>
-#include <linux/platform_device.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 #include <asm/opal.h>
 #include <asm/firmware.h>
diff --git a/arch/powerpc/platforms/powernv/opal-secvar.c b/arch/powerpc/platforms/powernv/opal-secvar.c
index a8436bf35e2f..6ac410f4d3c7 100644
--- a/arch/powerpc/platforms/powernv/opal-secvar.c
+++ b/arch/powerpc/platforms/powernv/opal-secvar.c
@@ -12,8 +12,8 @@
 #define pr_fmt(fmt) "secvar: "fmt
 
 #include <linux/types.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
-#include <linux/of_platform.h>
 #include <asm/opal.h>
 #include <asm/secvar.h>
 #include <asm/secure_boot.h>
diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
index 3192c614a1e1..8880a1c14573 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -6,7 +6,9 @@
  */
 
 #include <linux/delay.h>
+#include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <asm/opal.h>
 #include <asm/machdep.h>
 
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 6b4eed2ef4fa..748c2b97fa53 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -165,10 +165,15 @@ static int scom_debug_init_one(struct dentry *root, struct device_node *dn,
 	ent->chip = chip;
 	snprintf(ent->name, 16, "%08x", chip);
 	ent->path.data = (void *)kasprintf(GFP_KERNEL, "%pOF", dn);
+	if (!ent->path.data) {
+		kfree(ent);
+		return -ENOMEM;
+	}
+
 	ent->path.size = strlen((char *)ent->path.data);
 
 	dir = debugfs_create_dir(ent->name, root);
-	if (!dir) {
+	if (IS_ERR(dir)) {
 		kfree(ent->path.data);
 		kfree(ent);
 		return -1;
@@ -190,7 +195,7 @@ static int scom_debug_init(void)
 		return 0;
 
 	root = debugfs_create_dir("scom", arch_debugfs_dir);
-	if (!root)
+	if (IS_ERR(root))
 		return -1;
 
 	rc = 0;
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index cdf3838f08d3..09bd93464b4f 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -180,10 +180,7 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node,
 	/*
 	 * Allocate a buffer to hold the MC recoverable ranges.
 	 */
-	mc_recoverable_range = memblock_alloc(size, __alignof__(u64));
-	if (!mc_recoverable_range)
-		panic("%s: Failed to allocate %u bytes align=0x%lx\n",
-		      __func__, size, __alignof__(u64));
+	mc_recoverable_range = memblock_alloc_or_panic(size, __alignof__(u64));
 
 	for (i = 0; i < mc_recoverable_range_len; i++) {
 		mc_recoverable_range[i].start_addr =
@@ -424,7 +421,7 @@ static int __init opal_message_init(struct device_node *opal_node)
 	return 0;
 }
 
-int opal_get_chars(uint32_t vtermno, char *buf, int count)
+ssize_t opal_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	s64 rc;
 	__be64 evt, len;
@@ -441,10 +438,11 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count)
 	return 0;
 }
 
-static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, bool atomic)
+static ssize_t __opal_put_chars(uint32_t vtermno, const u8 *data,
+				size_t total_len, bool atomic)
 {
 	unsigned long flags = 0 /* shut up gcc */;
-	int written;
+	ssize_t written;
 	__be64 olen;
 	s64 rc;
 
@@ -484,7 +482,7 @@ static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, b
 		if (atomic) {
 			/* Should not happen */
 			pr_warn("atomic console write returned partial "
-				"len=%d written=%d\n", total_len, written);
+				"len=%zu written=%zd\n", total_len, written);
 		}
 		if (!written)
 			written = -EAGAIN;
@@ -497,7 +495,7 @@ out:
 	return written;
 }
 
-int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
+ssize_t opal_put_chars(uint32_t vtermno, const u8 *data, size_t total_len)
 {
 	return __opal_put_chars(vtermno, data, total_len, false);
 }
@@ -508,7 +506,8 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
  * true at the moment because console space can race with OPAL's console
  * writes.
  */
-int opal_put_chars_atomic(uint32_t vtermno, const char *data, int total_len)
+ssize_t opal_put_chars_atomic(uint32_t vtermno, const u8 *data,
+			      size_t total_len)
 {
 	return __opal_put_chars(vtermno, data, total_len, true);
 }
@@ -790,14 +789,6 @@ static int __init opal_sysfs_init(void)
 	return 0;
 }
 
-static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
-				struct bin_attribute *bin_attr, char *buf,
-				loff_t off, size_t count)
-{
-	return memory_read_from_buffer(buf, count, &off, bin_attr->private,
-				       bin_attr->size);
-}
-
 static int opal_add_one_export(struct kobject *parent, const char *export_name,
 			       struct device_node *np, const char *prop_name)
 {
@@ -824,7 +815,7 @@ static int opal_add_one_export(struct kobject *parent, const char *export_name,
 	sysfs_bin_attr_init(attr);
 	attr->attr.name = name;
 	attr->attr.mode = 0400;
-	attr->read = export_attr_read;
+	attr->read = sysfs_bin_attr_simple_read;
 	attr->private = __va(vals[0]);
 	attr->size = vals[1];
 
diff --git a/arch/powerpc/platforms/powernv/pci-cxl.c b/arch/powerpc/platforms/powernv/pci-cxl.c
deleted file mode 100644
index 7e419de71db8..000000000000
--- a/arch/powerpc/platforms/powernv/pci-cxl.c
+++ /dev/null
@@ -1,153 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright 2014-2016 IBM Corp.
- */
-
-#include <linux/module.h>
-#include <misc/cxl-base.h>
-#include <asm/pnv-pci.h>
-#include <asm/opal.h>
-
-#include "pci.h"
-
-int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pnv_ioda_pe *pe;
-	int rc;
-
-	pe = pnv_ioda_get_pe(dev);
-	if (!pe)
-		return -ENODEV;
-
-	pe_info(pe, "Switching PHB to CXL\n");
-
-	rc = opal_pci_set_phb_cxl_mode(phb->opal_id, mode, pe->pe_number);
-	if (rc == OPAL_UNSUPPORTED)
-		dev_err(&dev->dev, "Required cxl mode not supported by firmware - update skiboot\n");
-	else if (rc)
-		dev_err(&dev->dev, "opal_pci_set_phb_cxl_mode failed: %i\n", rc);
-
-	return rc;
-}
-EXPORT_SYMBOL(pnv_phb_to_cxl_mode);
-
-/* Find PHB for cxl dev and allocate MSI hwirqs?
- * Returns the absolute hardware IRQ number
- */
-int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	int hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, num);
-
-	if (hwirq < 0) {
-		dev_warn(&dev->dev, "Failed to find a free MSI\n");
-		return -ENOSPC;
-	}
-
-	return phb->msi_base + hwirq;
-}
-EXPORT_SYMBOL(pnv_cxl_alloc_hwirqs);
-
-void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-
-	msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, num);
-}
-EXPORT_SYMBOL(pnv_cxl_release_hwirqs);
-
-void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
-				  struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	int i, hwirq;
-
-	for (i = 1; i < CXL_IRQ_RANGES; i++) {
-		if (!irqs->range[i])
-			continue;
-		pr_devel("cxl release irq range 0x%x: offset: 0x%lx  limit: %ld\n",
-			 i, irqs->offset[i],
-			 irqs->range[i]);
-		hwirq = irqs->offset[i] - phb->msi_base;
-		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq,
-				       irqs->range[i]);
-	}
-}
-EXPORT_SYMBOL(pnv_cxl_release_hwirq_ranges);
-
-int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
-			       struct pci_dev *dev, int num)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	int i, hwirq, try;
-
-	memset(irqs, 0, sizeof(struct cxl_irq_ranges));
-
-	/* 0 is reserved for the multiplexed PSL DSI interrupt */
-	for (i = 1; i < CXL_IRQ_RANGES && num; i++) {
-		try = num;
-		while (try) {
-			hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, try);
-			if (hwirq >= 0)
-				break;
-			try /= 2;
-		}
-		if (!try)
-			goto fail;
-
-		irqs->offset[i] = phb->msi_base + hwirq;
-		irqs->range[i] = try;
-		pr_devel("cxl alloc irq range 0x%x: offset: 0x%lx  limit: %li\n",
-			 i, irqs->offset[i], irqs->range[i]);
-		num -= try;
-	}
-	if (num)
-		goto fail;
-
-	return 0;
-fail:
-	pnv_cxl_release_hwirq_ranges(irqs, dev);
-	return -ENOSPC;
-}
-EXPORT_SYMBOL(pnv_cxl_alloc_hwirq_ranges);
-
-int pnv_cxl_get_irq_count(struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-
-	return phb->msi_bmp.irq_count;
-}
-EXPORT_SYMBOL(pnv_cxl_get_irq_count);
-
-int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
-			   unsigned int virq)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	unsigned int xive_num = hwirq - phb->msi_base;
-	struct pnv_ioda_pe *pe;
-	int rc;
-
-	if (!(pe = pnv_ioda_get_pe(dev)))
-		return -ENODEV;
-
-	/* Assign XIVE to PE */
-	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
-	if (rc) {
-		pe_warn(pe, "%s: OPAL error %d setting msi_base 0x%x "
-			"hwirq 0x%x XIVE 0x%x PE\n",
-			pci_name(dev), rc, phb->msi_base, hwirq, xive_num);
-		return -EIO;
-	}
-	pnv_set_msi_irq_chip(phb, virq);
-
-	return 0;
-}
-EXPORT_SYMBOL(pnv_cxl_ioda_msi_setup);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index a02e9cdb5b5d..b0c1d9d16fb5 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/memblock.h>
 #include <linux/irq.h>
+#include <linux/irqchip/irq-msi-lib.h>
 #include <linux/io.h>
 #include <linux/msi.h>
 #include <linux/iommu.h>
@@ -37,19 +38,13 @@
 #include <asm/firmware.h>
 #include <asm/pnv-pci.h>
 #include <asm/mmzone.h>
-#include <asm/xive.h>
-
-#include <misc/cxl-base.h>
 
 #include "powernv.h"
 #include "pci.h"
 #include "../../../../drivers/pci/pci.h"
 
-#define PNV_IODA1_M64_NUM	16	/* Number of M64 BARs	*/
-#define PNV_IODA1_M64_SEGS	8	/* Segments per M64 BAR	*/
-#define PNV_IODA1_DMA32_SEGSIZE	0x10000000
-
-static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_OCAPI" };
+/* This array is indexed with enum pnv_phb_type */
+static const char * const pnv_phb_names[] = { "IODA2", "NPU_OCAPI" };
 
 static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
 static void pnv_pci_configure_bus(struct pci_bus *bus);
@@ -280,86 +275,6 @@ static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev,
 	}
 }
 
-static int pnv_ioda1_init_m64(struct pnv_phb *phb)
-{
-	struct resource *r;
-	int index;
-
-	/*
-	 * There are 16 M64 BARs, each of which has 8 segments. So
-	 * there are as many M64 segments as the maximum number of
-	 * PEs, which is 128.
-	 */
-	for (index = 0; index < PNV_IODA1_M64_NUM; index++) {
-		unsigned long base, segsz = phb->ioda.m64_segsize;
-		int64_t rc;
-
-		base = phb->ioda.m64_base +
-		       index * PNV_IODA1_M64_SEGS * segsz;
-		rc = opal_pci_set_phb_mem_window(phb->opal_id,
-				OPAL_M64_WINDOW_TYPE, index, base, 0,
-				PNV_IODA1_M64_SEGS * segsz);
-		if (rc != OPAL_SUCCESS) {
-			pr_warn("  Error %lld setting M64 PHB#%x-BAR#%d\n",
-				rc, phb->hose->global_number, index);
-			goto fail;
-		}
-
-		rc = opal_pci_phb_mmio_enable(phb->opal_id,
-				OPAL_M64_WINDOW_TYPE, index,
-				OPAL_ENABLE_M64_SPLIT);
-		if (rc != OPAL_SUCCESS) {
-			pr_warn("  Error %lld enabling M64 PHB#%x-BAR#%d\n",
-				rc, phb->hose->global_number, index);
-			goto fail;
-		}
-	}
-
-	for (index = 0; index < phb->ioda.total_pe_num; index++) {
-		int64_t rc;
-
-		/*
-		 * P7IOC supports M64DT, which helps mapping M64 segment
-		 * to one particular PE#. However, PHB3 has fixed mapping
-		 * between M64 segment and PE#. In order to have same logic
-		 * for P7IOC and PHB3, we enforce fixed mapping between M64
-		 * segment and PE# on P7IOC.
-		 */
-		rc = opal_pci_map_pe_mmio_window(phb->opal_id,
-				index, OPAL_M64_WINDOW_TYPE,
-				index / PNV_IODA1_M64_SEGS,
-				index % PNV_IODA1_M64_SEGS);
-		if (rc != OPAL_SUCCESS) {
-			pr_warn("%s: Error %lld mapping M64 for PHB#%x-PE#%x\n",
-				__func__, rc, phb->hose->global_number,
-				index);
-			goto fail;
-		}
-	}
-
-	/*
-	 * Exclude the segments for reserved and root bus PE, which
-	 * are first or last two PEs.
-	 */
-	r = &phb->hose->mem_resources[1];
-	if (phb->ioda.reserved_pe_idx == 0)
-		r->start += (2 * phb->ioda.m64_segsize);
-	else if (phb->ioda.reserved_pe_idx == (phb->ioda.total_pe_num - 1))
-		r->end -= (2 * phb->ioda.m64_segsize);
-	else
-		WARN(1, "Wrong reserved PE#%x on PHB#%x\n",
-		     phb->ioda.reserved_pe_idx, phb->hose->global_number);
-
-	return 0;
-
-fail:
-	for ( ; index >= 0; index--)
-		opal_pci_phb_mmio_enable(phb->opal_id,
-			OPAL_M64_WINDOW_TYPE, index, OPAL_DISABLE_M64);
-
-	return -EIO;
-}
-
 static void pnv_ioda_reserve_m64_pe(struct pci_bus *bus,
 				    unsigned long *pe_bitmap,
 				    bool all)
@@ -443,7 +358,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 	const __be32 *r;
 	u64 pci_addr;
 
-	if (phb->type != PNV_PHB_IODA1 && phb->type != PNV_PHB_IODA2) {
+	if (phb->type != PNV_PHB_IODA2) {
 		pr_info("  Not support M64 window\n");
 		return;
 	}
@@ -518,10 +433,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 	 * Setup init functions for M64 based on IODA version, IODA3 uses
 	 * the IODA2 code.
 	 */
-	if (phb->type == PNV_PHB_IODA1)
-		phb->init_m64 = pnv_ioda1_init_m64;
-	else
-		phb->init_m64 = pnv_ioda2_init_m64;
+	phb->init_m64 = pnv_ioda2_init_m64;
 }
 
 static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no)
@@ -952,29 +864,8 @@ int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	for (rid = pe->rid; rid < rid_end; rid++)
 		phb->ioda.pe_rmap[rid] = pe->pe_number;
 
-	/* Setup one MVTs on IODA1 */
-	if (phb->type != PNV_PHB_IODA1) {
-		pe->mve_number = 0;
-		goto out;
-	}
+	pe->mve_number = 0;
 
-	pe->mve_number = pe->pe_number;
-	rc = opal_pci_set_mve(phb->opal_id, pe->mve_number, pe->pe_number);
-	if (rc != OPAL_SUCCESS) {
-		pe_err(pe, "OPAL error %ld setting up MVE %x\n",
-		       rc, pe->mve_number);
-		pe->mve_number = -1;
-	} else {
-		rc = opal_pci_set_mve_enable(phb->opal_id,
-					     pe->mve_number, OPAL_ENABLE_MVE);
-		if (rc) {
-			pe_err(pe, "OPAL error %ld enabling MVE %x\n",
-			       rc, pe->mve_number);
-			pe->mve_number = -1;
-		}
-	}
-
-out:
 	return 0;
 }
 
@@ -1097,9 +988,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 	return pe;
 }
 
-static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
-				       struct pnv_ioda_pe *pe);
-
 static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev)
 {
 	struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus);
@@ -1107,14 +995,14 @@ static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev)
 	struct pnv_ioda_pe *pe;
 
 	/* Check if the BDFN for this device is associated with a PE yet */
-	pe = pnv_pci_bdfn_to_pe(phb, pdev->devfn | (pdev->bus->number << 8));
+	pe = pnv_pci_bdfn_to_pe(phb, pci_dev_id(pdev));
 	if (!pe) {
 		/* VF PEs should be pre-configured in pnv_pci_sriov_enable() */
 		if (WARN_ON(pdev->is_virtfn))
 			return;
 
 		pnv_pci_configure_bus(pdev->bus);
-		pe = pnv_pci_bdfn_to_pe(phb, pdev->devfn | (pdev->bus->number << 8));
+		pe = pnv_pci_bdfn_to_pe(phb, pci_dev_id(pdev));
 		pci_info(pdev, "Configured PE#%x\n", pe ? pe->pe_number : 0xfffff);
 
 
@@ -1134,9 +1022,6 @@ static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev)
 	 */
 	if (!pe->dma_setup_done && !pci_is_bridge(pdev)) {
 		switch (phb->type) {
-		case PNV_PHB_IODA1:
-			pnv_pci_ioda1_setup_dma_pe(phb, pe);
-			break;
 		case PNV_PHB_IODA2:
 			pnv_pci_ioda2_setup_dma_pe(phb, pe);
 			break;
@@ -1273,53 +1158,6 @@ static inline __be64 __iomem *pnv_ioda_get_inval_reg(struct pnv_phb *phb)
 	return phb->regs + 0x210;
 }
 
-static void pnv_pci_p7ioc_tce_invalidate(struct iommu_table *tbl,
-		unsigned long index, unsigned long npages)
-{
-	struct iommu_table_group_link *tgl = list_first_entry_or_null(
-			&tbl->it_group_list, struct iommu_table_group_link,
-			next);
-	struct pnv_ioda_pe *pe = container_of(tgl->table_group,
-			struct pnv_ioda_pe, table_group);
-	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb);
-	unsigned long start, end, inc;
-
-	start = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset);
-	end = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset +
-			npages - 1);
-
-	/* p7ioc-style invalidation, 2 TCEs per write */
-	start |= (1ull << 63);
-	end |= (1ull << 63);
-	inc = 16;
-        end |= inc - 1;	/* round up end to be different than start */
-
-        mb(); /* Ensure above stores are visible */
-        while (start <= end) {
-		__raw_writeq_be(start, invalidate);
-                start += inc;
-        }
-
-	/*
-	 * The iommu layer will do another mb() for us on build()
-	 * and we don't care on free()
-	 */
-}
-
-static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
-		long npages, unsigned long uaddr,
-		enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
-			attrs);
-
-	if (!ret)
-		pnv_pci_p7ioc_tce_invalidate(tbl, index, npages);
-
-	return ret;
-}
-
 #ifdef CONFIG_IOMMU_API
 /* Common for IODA1 and IODA2 */
 static int pnv_ioda_tce_xchg_no_kill(struct iommu_table *tbl, long index,
@@ -1329,25 +1167,6 @@ static int pnv_ioda_tce_xchg_no_kill(struct iommu_table *tbl, long index,
 }
 #endif
 
-static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
-		long npages)
-{
-	pnv_tce_free(tbl, index, npages);
-
-	pnv_pci_p7ioc_tce_invalidate(tbl, index, npages);
-}
-
-static struct iommu_table_ops pnv_ioda1_iommu_ops = {
-	.set = pnv_ioda1_tce_build,
-#ifdef CONFIG_IOMMU_API
-	.xchg_no_kill = pnv_ioda_tce_xchg_no_kill,
-	.tce_kill = pnv_pci_p7ioc_tce_invalidate,
-	.useraddrptr = pnv_tce_useraddrptr,
-#endif
-	.clear = pnv_ioda1_tce_free,
-	.get = pnv_tce_get,
-};
-
 #define PHB3_TCE_KILL_INVAL_ALL		PPC_BIT(0)
 #define PHB3_TCE_KILL_INVAL_PE		PPC_BIT(1)
 #define PHB3_TCE_KILL_INVAL_ONE		PPC_BIT(2)
@@ -1453,182 +1272,6 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = {
 	.free = pnv_pci_ioda2_table_free_pages,
 };
 
-static int pnv_pci_ioda_dev_dma_weight(struct pci_dev *dev, void *data)
-{
-	unsigned int *weight = (unsigned int *)data;
-
-	/* This is quite simplistic. The "base" weight of a device
-	 * is 10. 0 means no DMA is to be accounted for it.
-	 */
-	if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL)
-		return 0;
-
-	if (dev->class == PCI_CLASS_SERIAL_USB_UHCI ||
-	    dev->class == PCI_CLASS_SERIAL_USB_OHCI ||
-	    dev->class == PCI_CLASS_SERIAL_USB_EHCI)
-		*weight += 3;
-	else if ((dev->class >> 8) == PCI_CLASS_STORAGE_RAID)
-		*weight += 15;
-	else
-		*weight += 10;
-
-	return 0;
-}
-
-static unsigned int pnv_pci_ioda_pe_dma_weight(struct pnv_ioda_pe *pe)
-{
-	unsigned int weight = 0;
-
-	/* SRIOV VF has same DMA32 weight as its PF */
-#ifdef CONFIG_PCI_IOV
-	if ((pe->flags & PNV_IODA_PE_VF) && pe->parent_dev) {
-		pnv_pci_ioda_dev_dma_weight(pe->parent_dev, &weight);
-		return weight;
-	}
-#endif
-
-	if ((pe->flags & PNV_IODA_PE_DEV) && pe->pdev) {
-		pnv_pci_ioda_dev_dma_weight(pe->pdev, &weight);
-	} else if ((pe->flags & PNV_IODA_PE_BUS) && pe->pbus) {
-		struct pci_dev *pdev;
-
-		list_for_each_entry(pdev, &pe->pbus->devices, bus_list)
-			pnv_pci_ioda_dev_dma_weight(pdev, &weight);
-	} else if ((pe->flags & PNV_IODA_PE_BUS_ALL) && pe->pbus) {
-		pci_walk_bus(pe->pbus, pnv_pci_ioda_dev_dma_weight, &weight);
-	}
-
-	return weight;
-}
-
-static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
-				       struct pnv_ioda_pe *pe)
-{
-
-	struct page *tce_mem = NULL;
-	struct iommu_table *tbl;
-	unsigned int weight, total_weight = 0;
-	unsigned int tce32_segsz, base, segs, avail, i;
-	int64_t rc;
-	void *addr;
-
-	/* XXX FIXME: Handle 64-bit only DMA devices */
-	/* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */
-	/* XXX FIXME: Allocate multi-level tables on PHB3 */
-	weight = pnv_pci_ioda_pe_dma_weight(pe);
-	if (!weight)
-		return;
-
-	pci_walk_bus(phb->hose->bus, pnv_pci_ioda_dev_dma_weight,
-		     &total_weight);
-	segs = (weight * phb->ioda.dma32_count) / total_weight;
-	if (!segs)
-		segs = 1;
-
-	/*
-	 * Allocate contiguous DMA32 segments. We begin with the expected
-	 * number of segments. With one more attempt, the number of DMA32
-	 * segments to be allocated is decreased by one until one segment
-	 * is allocated successfully.
-	 */
-	do {
-		for (base = 0; base <= phb->ioda.dma32_count - segs; base++) {
-			for (avail = 0, i = base; i < base + segs; i++) {
-				if (phb->ioda.dma32_segmap[i] ==
-				    IODA_INVALID_PE)
-					avail++;
-			}
-
-			if (avail == segs)
-				goto found;
-		}
-	} while (--segs);
-
-	if (!segs) {
-		pe_warn(pe, "No available DMA32 segments\n");
-		return;
-	}
-
-found:
-	tbl = pnv_pci_table_alloc(phb->hose->node);
-	if (WARN_ON(!tbl))
-		return;
-
-#ifdef CONFIG_IOMMU_API
-	pe->table_group.ops = &spapr_tce_table_group_ops;
-	pe->table_group.pgsizes = SZ_4K;
-#endif
-	iommu_register_group(&pe->table_group, phb->hose->global_number,
-			pe->pe_number);
-	pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);
-
-	/* Grab a 32-bit TCE table */
-	pe_info(pe, "DMA weight %d (%d), assigned (%d) %d DMA32 segments\n",
-		weight, total_weight, base, segs);
-	pe_info(pe, " Setting up 32-bit TCE table at %08x..%08x\n",
-		base * PNV_IODA1_DMA32_SEGSIZE,
-		(base + segs) * PNV_IODA1_DMA32_SEGSIZE - 1);
-
-	/* XXX Currently, we allocate one big contiguous table for the
-	 * TCEs. We only really need one chunk per 256M of TCE space
-	 * (ie per segment) but that's an optimization for later, it
-	 * requires some added smarts with our get/put_tce implementation
-	 *
-	 * Each TCE page is 4KB in size and each TCE entry occupies 8
-	 * bytes
-	 */
-	tce32_segsz = PNV_IODA1_DMA32_SEGSIZE >> (IOMMU_PAGE_SHIFT_4K - 3);
-	tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL,
-				   get_order(tce32_segsz * segs));
-	if (!tce_mem) {
-		pe_err(pe, " Failed to allocate a 32-bit TCE memory\n");
-		goto fail;
-	}
-	addr = page_address(tce_mem);
-	memset(addr, 0, tce32_segsz * segs);
-
-	/* Configure HW */
-	for (i = 0; i < segs; i++) {
-		rc = opal_pci_map_pe_dma_window(phb->opal_id,
-					      pe->pe_number,
-					      base + i, 1,
-					      __pa(addr) + tce32_segsz * i,
-					      tce32_segsz, IOMMU_PAGE_SIZE_4K);
-		if (rc) {
-			pe_err(pe, " Failed to configure 32-bit TCE table, err %lld\n",
-			       rc);
-			goto fail;
-		}
-	}
-
-	/* Setup DMA32 segment mapping */
-	for (i = base; i < base + segs; i++)
-		phb->ioda.dma32_segmap[i] = pe->pe_number;
-
-	/* Setup linux iommu table */
-	pnv_pci_setup_iommu_table(tbl, addr, tce32_segsz * segs,
-				  base * PNV_IODA1_DMA32_SEGSIZE,
-				  IOMMU_PAGE_SHIFT_4K);
-
-	tbl->it_ops = &pnv_ioda1_iommu_ops;
-	pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift;
-	pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
-	tbl->it_index = (phb->hose->global_number << 16) | pe->pe_number;
-	if (!iommu_init_table(tbl, phb->hose->node, 0, 0))
-		panic("Failed to initialize iommu table");
-
-	pe->dma_setup_done = true;
-	return;
- fail:
-	/* XXX Failure: Try to fallback to 64-bit only ? */
-	if (tce_mem)
-		__free_pages(tce_mem, get_order(tce32_segsz * segs));
-	if (tbl) {
-		pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
-		iommu_tce_table_put(tbl);
-	}
-}
-
 static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
 		int num, struct iommu_table *tbl)
 {
@@ -1744,7 +1387,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	 * DMA window can be larger than available memory, which will
 	 * cause errors later.
 	 */
-	const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_ORDER);
+	const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_PAGE_ORDER);
 
 	/*
 	 * We create the default window as big as we can. The constraint is
@@ -1892,7 +1535,8 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 	}
 }
 
-static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
+static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group,
+				     struct device *dev __maybe_unused)
 {
 	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
 						table_group);
@@ -1917,7 +1561,8 @@ static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 	return 0;
 }
 
-static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
+static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group,
+					struct device *dev __maybe_unused)
 {
 	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
 						table_group);
@@ -1989,47 +1634,6 @@ int64_t pnv_opal_pci_msi_eoi(struct irq_data *d)
 	return opal_pci_msi_eoi(phb->opal_id, d->parent_data->hwirq);
 }
 
-/*
- * The IRQ data is mapped in the XICS domain, with OPAL HW IRQ numbers
- */
-static void pnv_ioda2_msi_eoi(struct irq_data *d)
-{
-	int64_t rc;
-	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
-	struct pci_controller *hose = irq_data_get_irq_chip_data(d);
-	struct pnv_phb *phb = hose->private_data;
-
-	rc = opal_pci_msi_eoi(phb->opal_id, hw_irq);
-	WARN_ON_ONCE(rc);
-
-	icp_native_eoi(d);
-}
-
-/* P8/CXL only */
-void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
-{
-	struct irq_data *idata;
-	struct irq_chip *ichip;
-
-	/* The MSI EOI OPAL call is only needed on PHB3 */
-	if (phb->model != PNV_PHB_MODEL_PHB3)
-		return;
-
-	if (!phb->ioda.irq_chip_init) {
-		/*
-		 * First time we setup an MSI IRQ, we need to setup the
-		 * corresponding IRQ chip to route correctly.
-		 */
-		idata = irq_get_irq_data(virq);
-		ichip = irq_data_get_irq_chip(idata);
-		phb->ioda.irq_chip_init = 1;
-		phb->ioda.irq_chip = *ichip;
-		phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
-	}
-	irq_set_chip(virq, &phb->ioda.irq_chip);
-	irq_set_chip_data(virq, phb->hose);
-}
-
 static struct irq_chip pnv_pci_msi_irq_chip;
 
 /*
@@ -2103,23 +1707,6 @@ static int __pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 	return 0;
 }
 
-/*
- * The msi_free() op is called before irq_domain_free_irqs_top() when
- * the handler data is still available. Use that to clear the XIVE
- * controller.
- */
-static void pnv_msi_ops_msi_free(struct irq_domain *domain,
-				 struct msi_domain_info *info,
-				 unsigned int irq)
-{
-	if (xive_enabled())
-		xive_irq_free_data(irq);
-}
-
-static struct msi_domain_ops pnv_pci_msi_domain_ops = {
-	.msi_free	= pnv_msi_ops_msi_free,
-};
-
 static void pnv_msi_shutdown(struct irq_data *d)
 {
 	d = d->parent_data;
@@ -2127,31 +1714,33 @@ static void pnv_msi_shutdown(struct irq_data *d)
 		d->chip->irq_shutdown(d);
 }
 
-static void pnv_msi_mask(struct irq_data *d)
+static bool pnv_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
+				  struct irq_domain *real_parent, struct msi_domain_info *info)
 {
-	pci_msi_mask_irq(d);
-	irq_chip_mask_parent(d);
-}
+	struct irq_chip *chip = info->chip;
 
-static void pnv_msi_unmask(struct irq_data *d)
-{
-	pci_msi_unmask_irq(d);
-	irq_chip_unmask_parent(d);
-}
+	if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info))
+		return false;
 
-static struct irq_chip pnv_pci_msi_irq_chip = {
-	.name		= "PNV-PCI-MSI",
-	.irq_shutdown	= pnv_msi_shutdown,
-	.irq_mask	= pnv_msi_mask,
-	.irq_unmask	= pnv_msi_unmask,
-	.irq_eoi	= irq_chip_eoi_parent,
-};
+	chip->irq_shutdown = pnv_msi_shutdown;
+	return true;
+}
 
-static struct msi_domain_info pnv_msi_domain_info = {
-	.flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		  MSI_FLAG_MULTI_PCI_MSI  | MSI_FLAG_PCI_MSIX),
-	.ops   = &pnv_pci_msi_domain_ops,
-	.chip  = &pnv_pci_msi_irq_chip,
+#define PNV_PCI_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS		| \
+				    MSI_FLAG_USE_DEF_CHIP_OPS		| \
+				    MSI_FLAG_PCI_MSI_MASK_PARENT)
+#define PNV_PCI_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK		| \
+				     MSI_FLAG_PCI_MSIX			| \
+				     MSI_FLAG_MULTI_PCI_MSI)
+
+static const struct msi_parent_ops pnv_msi_parent_ops = {
+	.required_flags		= PNV_PCI_MSI_FLAGS_REQUIRED,
+	.supported_flags	= PNV_PCI_MSI_FLAGS_SUPPORTED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI,
+	.bus_select_token	= DOMAIN_BUS_NEXUS,
+	.bus_select_mask	= MATCH_PCI_MSI,
+	.prefix			= "PNV-",
+	.init_dev_msi_info	= pnv_init_dev_msi_info,
 };
 
 static void pnv_msi_compose_msg(struct irq_data *d, struct msi_msg *msg)
@@ -2250,7 +1839,7 @@ static int pnv_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	return 0;
 
 out:
-	irq_domain_free_irqs_parent(domain, virq, i - 1);
+	irq_domain_free_irqs_parent(domain, virq, i);
 	msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq, nr_irqs);
 	return ret;
 }
@@ -2266,41 +1855,30 @@ static void pnv_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 		 virq, d->hwirq, nr_irqs);
 
 	msi_bitmap_free_hwirqs(&phb->msi_bmp, d->hwirq, nr_irqs);
-	/* XIVE domain is cleared through ->msi_free() */
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
 }
 
 static const struct irq_domain_ops pnv_irq_domain_ops = {
+	.select	= msi_lib_irq_domain_select,
 	.alloc  = pnv_irq_domain_alloc,
 	.free   = pnv_irq_domain_free,
 };
 
 static int __init pnv_msi_allocate_domains(struct pci_controller *hose, unsigned int count)
 {
-	struct pnv_phb *phb = hose->private_data;
-	struct irq_domain *parent = irq_get_default_host();
+	struct irq_domain *parent = irq_get_default_domain();
+	struct irq_domain_info info = {
+		.fwnode		= of_fwnode_handle(hose->dn),
+		.ops		= &pnv_irq_domain_ops,
+		.host_data	= hose,
+		.size		= count,
+		.parent		= parent,
+	};
 
-	hose->fwnode = irq_domain_alloc_named_id_fwnode("PNV-MSI", phb->opal_id);
-	if (!hose->fwnode)
-		return -ENOMEM;
-
-	hose->dev_domain = irq_domain_create_hierarchy(parent, 0, count,
-						       hose->fwnode,
-						       &pnv_irq_domain_ops, hose);
+	hose->dev_domain = msi_create_parent_irq_domain(&info, &pnv_msi_parent_ops);
 	if (!hose->dev_domain) {
-		pr_err("PCI: failed to create IRQ domain bridge %pOF (domain %d)\n",
-		       hose->dn, hose->global_number);
-		irq_domain_free_fwnode(hose->fwnode);
-		return -ENOMEM;
-	}
-
-	hose->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(hose->dn),
-						     &pnv_msi_domain_info,
-						     hose->dev_domain);
-	if (!hose->msi_domain) {
 		pr_err("PCI: failed to create MSI IRQ domain bridge %pOF (domain %d)\n",
 		       hose->dn, hose->global_number);
-		irq_domain_free_fwnode(hose->fwnode);
-		irq_domain_remove(hose->dev_domain);
 		return -ENOMEM;
 	}
 
@@ -2707,57 +2285,6 @@ static bool pnv_ocapi_enable_device_hook(struct pci_dev *dev)
 	return true;
 }
 
-static long pnv_pci_ioda1_unset_window(struct iommu_table_group *table_group,
-				       int num)
-{
-	struct pnv_ioda_pe *pe = container_of(table_group,
-					      struct pnv_ioda_pe, table_group);
-	struct pnv_phb *phb = pe->phb;
-	unsigned int idx;
-	long rc;
-
-	pe_info(pe, "Removing DMA window #%d\n", num);
-	for (idx = 0; idx < phb->ioda.dma32_count; idx++) {
-		if (phb->ioda.dma32_segmap[idx] != pe->pe_number)
-			continue;
-
-		rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
-						idx, 0, 0ul, 0ul, 0ul);
-		if (rc != OPAL_SUCCESS) {
-			pe_warn(pe, "Failure %ld unmapping DMA32 segment#%d\n",
-				rc, idx);
-			return rc;
-		}
-
-		phb->ioda.dma32_segmap[idx] = IODA_INVALID_PE;
-	}
-
-	pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
-	return OPAL_SUCCESS;
-}
-
-static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
-{
-	struct iommu_table *tbl = pe->table_group.tables[0];
-	int64_t rc;
-
-	if (!pe->dma_setup_done)
-		return;
-
-	rc = pnv_pci_ioda1_unset_window(&pe->table_group, 0);
-	if (rc != OPAL_SUCCESS)
-		return;
-
-	pnv_pci_p7ioc_tce_invalidate(tbl, tbl->it_offset, tbl->it_size);
-	if (pe->table_group.group) {
-		iommu_group_put(pe->table_group.group);
-		WARN_ON(pe->table_group.group);
-	}
-
-	free_pages(tbl->it_base, get_order(tbl->it_size << 3));
-	iommu_tce_table_put(tbl);
-}
-
 void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
 {
 	struct iommu_table *tbl = pe->table_group.tables[0];
@@ -2806,13 +2333,7 @@ static void pnv_ioda_release_pe_seg(struct pnv_ioda_pe *pe)
 {
 	struct pnv_phb *phb = pe->phb;
 
-	if (phb->type == PNV_PHB_IODA1) {
-		pnv_ioda_free_pe_seg(pe, OPAL_IO_WINDOW_TYPE,
-				     phb->ioda.io_segmap);
-		pnv_ioda_free_pe_seg(pe, OPAL_M32_WINDOW_TYPE,
-				     phb->ioda.m32_segmap);
-		/* M64 is pre-configured by pnv_ioda1_init_m64() */
-	} else if (phb->type == PNV_PHB_IODA2) {
+	if (phb->type == PNV_PHB_IODA2) {
 		pnv_ioda_free_pe_seg(pe, OPAL_M32_WINDOW_TYPE,
 				     phb->ioda.m32_segmap);
 	}
@@ -2830,9 +2351,6 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
 	mutex_unlock(&phb->ioda.pe_list_mutex);
 
 	switch (phb->type) {
-	case PNV_PHB_IODA1:
-		pnv_pci_ioda1_release_pe_dma(pe);
-		break;
 	case PNV_PHB_IODA2:
 		pnv_pci_ioda2_release_pe_dma(pe);
 		break;
@@ -2941,7 +2459,7 @@ static struct iommu_group *pnv_pci_device_group(struct pci_controller *hose,
 	if (WARN_ON(!phb))
 		return ERR_PTR(-ENODEV);
 
-	pe = pnv_pci_bdfn_to_pe(phb, pdev->devfn | (pdev->bus->number << 8));
+	pe = pnv_pci_bdfn_to_pe(phb, pci_dev_id(pdev));
 	if (!pe)
 		return ERR_PTR(-ENODEV);
 
@@ -2981,7 +2499,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
 	unsigned long size, m64map_off, m32map_off, pemap_off;
-	unsigned long iomap_off = 0, dma32map_off = 0;
 	struct pnv_ioda_pe *root_pe;
 	struct resource r;
 	const __be64 *prop64;
@@ -3092,10 +2609,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe_num;
 	phb->ioda.io_pci_base = 0; /* XXX calculate this ? */
 
-	/* Calculate how many 32-bit TCE segments we have */
-	phb->ioda.dma32_count = phb->ioda.m32_pci_base /
-				PNV_IODA1_DMA32_SEGSIZE;
-
 	/* Allocate aux data & arrays. We don't have IO ports on PHB3 */
 	size = ALIGN(max_t(unsigned, phb->ioda.total_pe_num, 8) / 8,
 			sizeof(unsigned long));
@@ -3103,13 +2616,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	size += phb->ioda.total_pe_num * sizeof(phb->ioda.m64_segmap[0]);
 	m32map_off = size;
 	size += phb->ioda.total_pe_num * sizeof(phb->ioda.m32_segmap[0]);
-	if (phb->type == PNV_PHB_IODA1) {
-		iomap_off = size;
-		size += phb->ioda.total_pe_num * sizeof(phb->ioda.io_segmap[0]);
-		dma32map_off = size;
-		size += phb->ioda.dma32_count *
-			sizeof(phb->ioda.dma32_segmap[0]);
-	}
 	pemap_off = size;
 	size += phb->ioda.total_pe_num * sizeof(struct pnv_ioda_pe);
 	aux = kzalloc(size, GFP_KERNEL);
@@ -3123,15 +2629,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		phb->ioda.m64_segmap[segno] = IODA_INVALID_PE;
 		phb->ioda.m32_segmap[segno] = IODA_INVALID_PE;
 	}
-	if (phb->type == PNV_PHB_IODA1) {
-		phb->ioda.io_segmap = aux + iomap_off;
-		for (segno = 0; segno < phb->ioda.total_pe_num; segno++)
-			phb->ioda.io_segmap[segno] = IODA_INVALID_PE;
-
-		phb->ioda.dma32_segmap = aux + dma32map_off;
-		for (segno = 0; segno < phb->ioda.dma32_count; segno++)
-			phb->ioda.dma32_segmap[segno] = IODA_INVALID_PE;
-	}
 	phb->ioda.pe_array = aux + pemap_off;
 
 	/*
@@ -3155,10 +2652,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	INIT_LIST_HEAD(&phb->ioda.pe_list);
 	mutex_init(&phb->ioda.pe_list_mutex);
 
-	/* Calculate how many 32-bit TCE segments we have */
-	phb->ioda.dma32_count = phb->ioda.m32_pci_base /
-				PNV_IODA1_DMA32_SEGSIZE;
-
 #if 0 /* We should really do that ... */
 	rc = opal_pci_set_phb_mem_window(opal->phb_id,
 					 window_type,
@@ -3265,27 +2758,3 @@ static void pnv_npu2_opencapi_cfg_size_fixup(struct pci_dev *dev)
 		dev->cfg_size = PCI_CFG_SPACE_EXP_SIZE;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pnv_npu2_opencapi_cfg_size_fixup);
-
-void __init pnv_pci_init_ioda_hub(struct device_node *np)
-{
-	struct device_node *phbn;
-	const __be64 *prop64;
-	u64 hub_id;
-
-	pr_info("Probing IODA IO-Hub %pOF\n", np);
-
-	prop64 = of_get_property(np, "ibm,opal-hubid", NULL);
-	if (!prop64) {
-		pr_err(" Missing \"ibm,opal-hubid\" property !\n");
-		return;
-	}
-	hub_id = be64_to_cpup(prop64);
-	pr_devel(" HUB-ID : 0x%016llx\n", hub_id);
-
-	/* Count child PHBs */
-	for_each_child_of_node(np, phbn) {
-		/* Look for IODA1 PHBs */
-		if (of_device_is_compatible(phbn, "ibm,ioda-phb"))
-			pnv_pci_init_ioda_phb(phbn, hub_id, PNV_PHB_IODA1);
-	}
-}
diff --git a/arch/powerpc/platforms/powernv/pci-sriov.c b/arch/powerpc/platforms/powernv/pci-sriov.c
index 7195133b26bb..cc7b1dd54ac6 100644
--- a/arch/powerpc/platforms/powernv/pci-sriov.c
+++ b/arch/powerpc/platforms/powernv/pci-sriov.c
@@ -238,7 +238,7 @@ void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev)
 	} else if (pdev->is_physfn) {
 		/*
 		 * For PFs adjust their allocated IOV resources to match what
-		 * the PHB can support using it's M64 BAR table.
+		 * the PHB can support using its M64 BAR table.
 		 */
 		pnv_pci_ioda_fixup_iov_resources(pdev);
 	}
@@ -594,12 +594,12 @@ static void pnv_pci_sriov_disable(struct pci_dev *pdev)
 	struct pnv_iov_data   *iov;
 
 	iov = pnv_iov_get(pdev);
-	num_vfs = iov->num_vfs;
-	base_pe = iov->vf_pe_arr[0].pe_number;
-
 	if (WARN_ON(!iov))
 		return;
 
+	num_vfs = iov->num_vfs;
+	base_pe = iov->vf_pe_arr[0].pe_number;
+
 	/* Release VF PEs */
 	pnv_ioda_release_vf_PE(pdev);
 
@@ -658,7 +658,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		list_add_tail(&pe->list, &phb->ioda.pe_list);
 		mutex_unlock(&phb->ioda.pe_list_mutex);
 
-		/* associate this pe to it's pdn */
+		/* associate this pe to its pdn */
 		list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) {
 			if (vf_pdn->busno == vf_bus &&
 			    vf_pdn->devfn == vf_devfn) {
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 233a50e65fce..b2c1da025410 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -14,7 +14,6 @@
 #include <linux/io.h>
 #include <linux/msi.h>
 #include <linux/iommu.h>
-#include <linux/sched/mm.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -33,8 +32,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-static DEFINE_MUTEX(tunnel_mutex);
-
 int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
 {
 	struct device_node *node = np;
@@ -744,64 +741,6 @@ struct iommu_table *pnv_pci_table_alloc(int nid)
 	return tbl;
 }
 
-struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
-{
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
-
-	return of_node_get(hose->dn);
-}
-EXPORT_SYMBOL(pnv_pci_get_phb_node);
-
-int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable)
-{
-	struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus);
-	u64 tunnel_bar;
-	__be64 val;
-	int rc;
-
-	if (!opal_check_token(OPAL_PCI_GET_PBCQ_TUNNEL_BAR))
-		return -ENXIO;
-	if (!opal_check_token(OPAL_PCI_SET_PBCQ_TUNNEL_BAR))
-		return -ENXIO;
-
-	mutex_lock(&tunnel_mutex);
-	rc = opal_pci_get_pbcq_tunnel_bar(phb->opal_id, &val);
-	if (rc != OPAL_SUCCESS) {
-		rc = -EIO;
-		goto out;
-	}
-	tunnel_bar = be64_to_cpu(val);
-	if (enable) {
-		/*
-		* Only one device per PHB can use atomics.
-		* Our policy is first-come, first-served.
-		*/
-		if (tunnel_bar) {
-			if (tunnel_bar != addr)
-				rc = -EBUSY;
-			else
-				rc = 0;	/* Setting same address twice is ok */
-			goto out;
-		}
-	} else {
-		/*
-		* The device that owns atomics and wants to release
-		* them must pass the same address with enable == 0.
-		*/
-		if (tunnel_bar != addr) {
-			rc = -EPERM;
-			goto out;
-		}
-		addr = 0x0ULL;
-	}
-	rc = opal_pci_set_pbcq_tunnel_bar(phb->opal_id, addr);
-	rc = opal_error_code(rc);
-out:
-	mutex_unlock(&tunnel_mutex);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(pnv_pci_set_tunnel_bar);
-
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
@@ -845,11 +784,6 @@ void __init pnv_pci_init(void)
 	pcie_ports_disabled = true;
 #endif
 
-	/* Look for IODA IO-Hubs. */
-	for_each_compatible_node(np, NULL, "ibm,ioda-hub") {
-		pnv_pci_init_ioda_hub(np);
-	}
-
 	/* Look for ioda2 built-in PHB3's */
 	for_each_compatible_node(np, NULL, "ibm,ioda2-phb")
 		pnv_pci_init_ioda2_phb(np);
@@ -865,28 +799,3 @@ void __init pnv_pci_init(void)
 	/* Configure IOMMU DMA hooks */
 	set_pci_dma_ops(&dma_iommu_ops);
 }
-
-static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb,
-		unsigned long action, void *data)
-{
-	struct device *dev = data;
-
-	switch (action) {
-	case BUS_NOTIFY_DEL_DEVICE:
-		iommu_del_device(dev);
-		return 0;
-	default:
-		return 0;
-	}
-}
-
-static struct notifier_block pnv_tce_iommu_bus_nb = {
-	.notifier_call = pnv_tce_iommu_bus_notifier,
-};
-
-static int __init pnv_tce_iommu_bus_notifier_init(void)
-{
-	bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb);
-	return 0;
-}
-machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index f12643958b8d..42075501663b 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -10,7 +10,6 @@
 struct pci_dn;
 
 enum pnv_phb_type {
-	PNV_PHB_IODA1,
 	PNV_PHB_IODA2,
 	PNV_PHB_NPU_OCAPI,
 };
@@ -163,12 +162,7 @@ struct pnv_phb {
 		unsigned int		*m32_segmap;
 		unsigned int		*io_segmap;
 
-		/* DMA32 segment maps - IODA1 only */
-		unsigned int		dma32_count;
-		unsigned int		*dma32_segmap;
-
 		/* IRQ chip */
-		int			irq_chip_init;
 		struct irq_chip		irq_chip;
 
 		/* Sorted list of used PE's based
@@ -279,7 +273,6 @@ int pnv_pci_cfg_write(struct pci_dn *pdn,
 		      int where, int size, u32 val);
 extern struct iommu_table *pnv_pci_table_alloc(int nid);
 
-extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
@@ -287,7 +280,6 @@ extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
 extern struct pnv_ioda_pe *pnv_pci_bdfn_to_pe(struct pnv_phb *phb, u16 bdfn);
 extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
-extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq);
 extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
 		__u64 window_size, __u32 levels);
 extern int pnv_eeh_post_init(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 5e9c6b55809f..4dbb47ddbdcc 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -482,15 +482,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 #ifdef CONFIG_MEMORY_HOTPLUG
 static unsigned long pnv_memory_block_size(void)
 {
-	/*
-	 * We map the kernel linear region with 1GB large pages on radix. For
-	 * memory hot unplug to work our memory block size must be at least
-	 * this size.
-	 */
-	if (radix_enabled())
-		return radix_mem_block_size;
-	else
-		return 256UL * 1024 * 1024;
+	return memory_block_size;
 }
 #endif
 
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 9e1a25398f98..8f41ef364fc6 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -28,7 +28,7 @@
 #include <asm/xive.h>
 #include <asm/opal.h>
 #include <asm/runlatch.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/dbell.h>
 #include <asm/kvm_ppc.h>
 #include <asm/ppc-opcode.h>
@@ -36,6 +36,7 @@
 #include <asm/kexec.h>
 #include <asm/reg.h>
 #include <asm/powernv.h>
+#include <asm/systemcfg.h>
 
 #include "powernv.h"
 
@@ -136,7 +137,9 @@ static int pnv_smp_cpu_disable(void)
 	 * the generic fixup_irqs. --BenH.
 	 */
 	set_cpu_online(cpu, false);
-	vdso_data->processorCount--;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->processorCount--;
+#endif
 	if (cpu == boot_cpuid)
 		boot_cpuid = cpumask_any(cpu_online_mask);
 	if (xive_enabled())
@@ -434,7 +437,7 @@ void __init pnv_smp_init(void)
 	smp_ops = &pnv_smp_ops;
 
 #ifdef CONFIG_HOTPLUG_CPU
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
 	crash_wake_offline = 1;
 #endif
 #endif
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 191424468f10..393e747541fb 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -425,7 +425,8 @@ static int subcore_init(void)
 
 	if (pvr_ver != PVR_POWER8 &&
 	    pvr_ver != PVR_POWER8E &&
-	    pvr_ver != PVR_POWER8NVL)
+	    pvr_ver != PVR_POWER8NVL &&
+	    pvr_ver != PVR_HX_C2000)
 		return 0;
 
 	/*
diff --git a/arch/powerpc/platforms/powernv/subcore.h b/arch/powerpc/platforms/powernv/subcore.h
index 77feee8436d4..413fd85d9bc2 100644
--- a/arch/powerpc/platforms/powernv/subcore.h
+++ b/arch/powerpc/platforms/powernv/subcore.h
@@ -9,7 +9,7 @@
 #define SYNC_STEP_REAL_MODE	2	/* Set by secondary when in real mode  */
 #define SYNC_STEP_FINISHED	3	/* Set by secondary when split/unsplit is done */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_SMP
 void split_core_secondary_loop(u8 *state);
@@ -18,4 +18,4 @@ extern void update_subcore_sibling_mask(void);
 static inline void update_subcore_sibling_mask(void) { }
 #endif /* CONFIG_SMP */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
diff --git a/arch/powerpc/platforms/powernv/ultravisor.c b/arch/powerpc/platforms/powernv/ultravisor.c
index 67c8c4b2d8b1..c526871a1229 100644
--- a/arch/powerpc/platforms/powernv/ultravisor.c
+++ b/arch/powerpc/platforms/powernv/ultravisor.c
@@ -32,13 +32,13 @@ int __init early_init_dt_scan_ultravisor(unsigned long node, const char *uname,
 static struct memcons *uv_memcons;
 
 static ssize_t uv_msglog_read(struct file *file, struct kobject *kobj,
-			      struct bin_attribute *bin_attr, char *to,
+			      const struct bin_attribute *bin_attr, char *to,
 			      loff_t pos, size_t count)
 {
 	return memcons_copy(uv_memcons, to, pos, count);
 }
 
-static struct bin_attribute uv_msglog_attr = {
+static struct bin_attribute uv_msglog_attr __ro_after_init = {
 	.attr = {.name = "msglog", .mode = 0400},
 	.read = uv_msglog_read
 };
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 0072682531d8..5147df3a18ac 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -1059,7 +1059,7 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
 		}
 	} else {
 		/*
-		 * Interrupt hanlder or fault window setup failed. Means
+		 * Interrupt handler or fault window setup failed. Means
 		 * NX can not generate fault for page fault. So not
 		 * opening for user space tx window.
 		 */
@@ -1310,8 +1310,8 @@ int vas_win_close(struct vas_window *vwin)
 	/* if send window, drop reference to matching receive window */
 	if (window->tx_win) {
 		if (window->user_win) {
-			put_vas_user_win_ref(&vwin->task_ref);
 			mm_context_remove_vas_window(vwin->task_ref.mm);
+			put_vas_user_win_ref(&vwin->task_ref);
 		}
 		put_rx_win(window->rxwin);
 	}
diff --git a/arch/powerpc/platforms/powernv/vas.c b/arch/powerpc/platforms/powernv/vas.c
index b65256a63e87..9c9650319f3b 100644
--- a/arch/powerpc/platforms/powernv/vas.c
+++ b/arch/powerpc/platforms/powernv/vas.c
@@ -121,7 +121,7 @@ static int init_vas_instance(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	xd = irq_get_handler_data(vinst->virq);
+	xd = irq_get_chip_data(vinst->virq);
 	if (!xd) {
 		pr_err("Inst%d: Invalid virq %d\n",
 				vinst->vas_id, vinst->virq);
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index a44869e5ea70..706194e5f0b4 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -67,6 +67,7 @@ config PS3_VUART
 config PS3_PS3AV
 	depends on PPC_PS3
 	tristate "PS3 AV settings driver" if PS3_ADVANCED
+	select VIDEO
 	select PS3_VUART
 	default y
 	help
@@ -167,16 +168,4 @@ config PS3_LPM
 	  profiling support of the Cell processor with programs like
 	  perfmon2, then say Y or M, otherwise say N.
 
-config PS3GELIC_UDBG
-	bool "PS3 udbg output via UDP broadcasts on Ethernet"
-	depends on PPC_PS3
-	help
-	  Enables udbg early debugging output by sending broadcast UDP
-	  via the Ethernet port (UDP port number 18194).
-
-	  This driver uses a trivial implementation and is independent
-	  from the main PS3 gelic network driver.
-
-	  If in doubt, say N here.
-
 endmenu
diff --git a/arch/powerpc/platforms/ps3/Makefile b/arch/powerpc/platforms/ps3/Makefile
index 86bf2967a8d4..bc79bb124d1e 100644
--- a/arch/powerpc/platforms/ps3/Makefile
+++ b/arch/powerpc/platforms/ps3/Makefile
@@ -3,7 +3,7 @@ obj-y += setup.o mm.o time.o hvcall.o htab.o repository.o
 obj-y += interrupt.o exports.o os-area.o
 obj-y += system-bus.o
 
-obj-$(CONFIG_PS3GELIC_UDBG) += gelic_udbg.o
+obj-$(CONFIG_PPC_EARLY_DEBUG_PS3GELIC) += gelic_udbg.o
 obj-$(CONFIG_SMP) += smp.o
 obj-$(CONFIG_SPU_BASE) += spu.o
 obj-y += device-init.o
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index e87360a0fb40..22d91ac424dd 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/reboot.h>
 #include <linux/rcuwait.h>
+#include <linux/string_choices.h>
 
 #include <asm/firmware.h>
 #include <asm/lv1call.h>
@@ -178,7 +179,7 @@ fail_malloc:
 	return result;
 }
 
-static int __ref ps3_setup_uhc_device(
+static int __init ps3_setup_uhc_device(
 	const struct ps3_repository_device *repo, enum ps3_match_id match_id,
 	enum ps3_interrupt_type interrupt_type, enum ps3_reg_type reg_type)
 {
@@ -724,7 +725,7 @@ static irqreturn_t ps3_notification_interrupt(int irq, void *data)
 static int ps3_notification_read_write(struct ps3_notification_device *dev,
 				       u64 lpar, int write)
 {
-	const char *op = write ? "write" : "read";
+	const char *op = str_write_read(write);
 	unsigned long flags;
 	int res;
 
@@ -770,49 +771,51 @@ static struct task_struct *probe_task;
 
 static int ps3_probe_thread(void *data)
 {
-	struct ps3_notification_device dev;
+	struct {
+		struct ps3_notification_device dev;
+		u8 buf[512];
+	} *local;
+	struct ps3_notify_cmd *notify_cmd;
+	struct ps3_notify_event *notify_event;
 	int res;
 	unsigned int irq;
 	u64 lpar;
-	void *buf;
-	struct ps3_notify_cmd *notify_cmd;
-	struct ps3_notify_event *notify_event;
 
 	pr_debug(" -> %s:%u: kthread started\n", __func__, __LINE__);
 
-	buf = kzalloc(512, GFP_KERNEL);
-	if (!buf)
+	local = kzalloc(sizeof(*local), GFP_KERNEL);
+	if (!local)
 		return -ENOMEM;
 
-	lpar = ps3_mm_phys_to_lpar(__pa(buf));
-	notify_cmd = buf;
-	notify_event = buf;
+	lpar = ps3_mm_phys_to_lpar(__pa(&local->buf));
+	notify_cmd = (struct ps3_notify_cmd *)&local->buf;
+	notify_event = (struct ps3_notify_event *)&local->buf;
 
 	/* dummy system bus device */
-	dev.sbd.bus_id = (u64)data;
-	dev.sbd.dev_id = PS3_NOTIFICATION_DEV_ID;
-	dev.sbd.interrupt_id = PS3_NOTIFICATION_INTERRUPT_ID;
+	local->dev.sbd.bus_id = (u64)data;
+	local->dev.sbd.dev_id = PS3_NOTIFICATION_DEV_ID;
+	local->dev.sbd.interrupt_id = PS3_NOTIFICATION_INTERRUPT_ID;
 
-	res = lv1_open_device(dev.sbd.bus_id, dev.sbd.dev_id, 0);
+	res = lv1_open_device(local->dev.sbd.bus_id, local->dev.sbd.dev_id, 0);
 	if (res) {
 		pr_err("%s:%u: lv1_open_device failed %s\n", __func__,
 		       __LINE__, ps3_result(res));
 		goto fail_free;
 	}
 
-	res = ps3_sb_event_receive_port_setup(&dev.sbd, PS3_BINDING_CPU_ANY,
-					      &irq);
+	res = ps3_sb_event_receive_port_setup(&local->dev.sbd,
+		PS3_BINDING_CPU_ANY, &irq);
 	if (res) {
 		pr_err("%s:%u: ps3_sb_event_receive_port_setup failed %d\n",
 		       __func__, __LINE__, res);
 	       goto fail_close_device;
 	}
 
-	spin_lock_init(&dev.lock);
-	rcuwait_init(&dev.wait);
+	spin_lock_init(&local->dev.lock);
+	rcuwait_init(&local->dev.wait);
 
 	res = request_irq(irq, ps3_notification_interrupt, 0,
-			  "ps3_notification", &dev);
+			  "ps3_notification", &local->dev);
 	if (res) {
 		pr_err("%s:%u: request_irq failed %d\n", __func__, __LINE__,
 		       res);
@@ -823,46 +826,48 @@ static int ps3_probe_thread(void *data)
 	notify_cmd->operation_code = 0; /* must be zero */
 	notify_cmd->event_mask = 1UL << notify_region_probe;
 
-	res = ps3_notification_read_write(&dev, lpar, 1);
+	res = ps3_notification_read_write(&local->dev, lpar, 1);
 	if (res)
 		goto fail_free_irq;
 
+	set_freezable();
 	/* Loop here processing the requested notification events. */
 	do {
 		try_to_freeze();
 
 		memset(notify_event, 0, sizeof(*notify_event));
 
-		res = ps3_notification_read_write(&dev, lpar, 0);
+		res = ps3_notification_read_write(&local->dev, lpar, 0);
 		if (res)
 			break;
 
 		pr_debug("%s:%u: notify event type 0x%llx bus id %llu dev id %llu"
 			 " type %llu port %llu\n", __func__, __LINE__,
-			 notify_event->event_type, notify_event->bus_id,
-			 notify_event->dev_id, notify_event->dev_type,
-			 notify_event->dev_port);
+			notify_event->event_type, notify_event->bus_id,
+			notify_event->dev_id, notify_event->dev_type,
+			notify_event->dev_port);
 
 		if (notify_event->event_type != notify_region_probe ||
-		    notify_event->bus_id != dev.sbd.bus_id) {
+			notify_event->bus_id != local->dev.sbd.bus_id) {
 			pr_warn("%s:%u: bad notify_event: event %llu, dev_id %llu, dev_type %llu\n",
 				__func__, __LINE__, notify_event->event_type,
 				notify_event->dev_id, notify_event->dev_type);
 			continue;
 		}
 
-		ps3_find_and_add_device(dev.sbd.bus_id, notify_event->dev_id);
+		ps3_find_and_add_device(local->dev.sbd.bus_id,
+			notify_event->dev_id);
 
 	} while (!kthread_should_stop());
 
 fail_free_irq:
-	free_irq(irq, &dev);
+	free_irq(irq, &local->dev);
 fail_sb_event_receive_port_destroy:
-	ps3_sb_event_receive_port_destroy(&dev.sbd, irq);
+	ps3_sb_event_receive_port_destroy(&local->dev.sbd, irq);
 fail_close_device:
-	lv1_close_device(dev.sbd.bus_id, dev.sbd.dev_id);
+	lv1_close_device(local->dev.sbd.bus_id, local->dev.sbd.dev_id);
 fail_free:
-	kfree(buf);
+	kfree(local);
 
 	probe_task = NULL;
 
diff --git a/arch/powerpc/platforms/ps3/gelic_udbg.c b/arch/powerpc/platforms/ps3/gelic_udbg.c
index 6b298010fd84..a5202c18c236 100644
--- a/arch/powerpc/platforms/ps3/gelic_udbg.c
+++ b/arch/powerpc/platforms/ps3/gelic_udbg.c
@@ -14,6 +14,7 @@
 #include <linux/ip.h>
 #include <linux/udp.h>
 
+#include <asm/ps3.h>
 #include <asm/io.h>
 #include <asm/udbg.h>
 #include <asm/lv1call.h>
diff --git a/arch/powerpc/platforms/ps3/hvcall.S b/arch/powerpc/platforms/ps3/hvcall.S
index 509e30ad01bb..e8ab3d6b03bd 100644
--- a/arch/powerpc/platforms/ps3/hvcall.S
+++ b/arch/powerpc/platforms/ps3/hvcall.S
@@ -9,6 +9,7 @@
 
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
+#include <asm/ptrace.h>
 
 #define lv1call .long 0x44000022; extsw r3, r3
 
@@ -16,12 +17,14 @@
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
+	stdu    r1, -STACK_FRAME_MIN_SIZE(r1);	\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE;	\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -38,18 +41,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
-	stdu    r3, -8(r1);			\
+	std	r3, -8(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-8(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 8;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+8;	\
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -57,21 +61,22 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r3, -8(r1);			\
-	stdu	r4, -16(r1);			\
+	std	r4, -16(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-16(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 16;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+16; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
 	std	r5, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -79,16 +84,17 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r3, -8(r1);			\
 	std	r4, -16(r1);			\
-	stdu	r5, -24(r1);			\
+	std	r5, -24(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-24(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 24;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+24; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -96,7 +102,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -24(r1);			\
 	std	r6, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -104,7 +110,7 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r3, -8(r1);			\
 	std	r4, -16(r1);			\
@@ -112,12 +118,13 @@ _GLOBAL(_##API_NAME)				\
 	std	r6, -32(r1);			\
 	std	r7, -40(r1);			\
 	std	r8, -48(r1);			\
-	stdu	r9, -56(r1);			\
+	std	r9, -56(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-56(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 56;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+56; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -133,7 +140,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -56(r1);			\
 	std	r10, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -141,18 +148,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
-	stdu    r4, -8(r1);			\
+	std	r4, -8(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-8(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 8;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+8;	\
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -160,21 +168,22 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r4, -8(r1);			\
-	stdu	r5, -16(r1);			\
+	std	r5, -16(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-16(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 16;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+16; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
 	std	r5, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -182,16 +191,17 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r4, -8(r1);			\
 	std	r5, -16(r1);			\
-	stdu	r6, -24(r1);			\
+	std	r6, -24(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-24(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 24;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+24; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -199,7 +209,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -24(r1);			\
 	std	r6, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -207,17 +217,18 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r4, -8(r1);			\
 	std	r5, -16(r1);			\
 	std	r6, -24(r1);			\
-	stdu	r7, -32(r1);			\
+	std	r7, -32(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-32(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 32;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+32; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -227,7 +238,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -32(r1);			\
 	std	r7, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -235,18 +246,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r4, -8(r1);			\
 	std	r5, -16(r1);			\
 	std	r6, -24(r1);			\
 	std	r7, -32(r1);			\
-	stdu	r8, -40(r1);			\
+	std	r8, -40(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-40(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 40;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+40; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -258,7 +270,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -40(r1);			\
 	std	r8, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -266,19 +278,20 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r4, -8(r1);			\
 	std	r5, -16(r1);			\
 	std	r6, -24(r1);			\
 	std	r7, -32(r1);			\
 	std	r8, -40(r1);			\
-	stdu	r9, -48(r1);			\
+	std	r9, -48(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-48(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 48;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+48; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -292,7 +305,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -48(r1);			\
 	std	r9, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -300,7 +313,7 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r4, -8(r1);			\
 	std	r5, -16(r1);			\
@@ -308,12 +321,13 @@ _GLOBAL(_##API_NAME)				\
 	std	r7, -32(r1);			\
 	std	r8, -40(r1);			\
 	std	r9, -48(r1);			\
-	stdu	r10, -56(r1);			\
+	std	r10, -56(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-56(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 56;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+56; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -329,7 +343,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -56(r1);			\
 	std	r10, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -337,18 +351,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
-	stdu	r5, -8(r1);			\
+	std	r5, -8(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-8(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 8;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+8;	\
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -356,21 +371,22 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r5, -8(r1);			\
-	stdu	r6, -16(r1);			\
+	std	r6, -16(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-16(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 16;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+16; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
 	std	r5, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -378,16 +394,17 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r5, -8(r1);			\
 	std	r6, -16(r1);			\
-	stdu	r7, -24(r1);			\
+	std	r7, -24(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-24(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 24;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+24; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -395,7 +412,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -24(r1);			\
 	std	r6, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -403,17 +420,18 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r5, -8(r1);			\
 	std	r6, -16(r1);			\
 	std	r7, -24(r1);			\
-	stdu	r8, -32(r1);			\
+	std	r8, -32(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-32(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 32;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+32;\
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -423,7 +441,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -32(r1);			\
 	std	r7, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -431,18 +449,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r5, -8(r1);			\
 	std	r6, -16(r1);			\
 	std	r7, -24(r1);			\
 	std	r8, -32(r1);			\
-	stdu	r9, -40(r1);			\
+	std	r9, -40(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-40(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 40;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+40; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -454,7 +473,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -40(r1);			\
 	std	r8, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -462,18 +481,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
-	stdu	r6, -8(r1);			\
+	std	r6, -8(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-8(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 8;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+8;	\
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -481,21 +501,22 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r6, -8(r1);			\
-	stdu	r7, -16(r1);			\
+	std	r7, -16(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-16(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 16;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+16; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
 	std	r5, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -503,16 +524,17 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r6, -8(r1);			\
 	std	r7, -16(r1);			\
-	stdu	r8, -24(r1);			\
+	std	r8, -24(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-24(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 24;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+24; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -520,7 +542,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -24(r1);			\
 	std	r6, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -528,18 +550,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
-	stdu    r7, -8(r1);			\
+	std	r7, -8(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-8(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 8;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+8;	\
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -547,21 +570,22 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r7, -8(r1);			\
-	stdu	r8, -16(r1);			\
+	std	r8, -16(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-16(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 16;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+16; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
 	std	r5, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -569,16 +593,17 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r7, -8(r1);			\
 	std	r8, -16(r1);			\
-	stdu	r9, -24(r1);			\
+	std	r9, -24(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-24(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 24;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+24; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -586,7 +611,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -24(r1);			\
 	std	r6, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -594,18 +619,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
-	stdu    r8, -8(r1);			\
+	std	r8, -8(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-8(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 8;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+8;	\
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -613,21 +639,22 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r8, -8(r1);			\
-	stdu	r9, -16(r1);			\
+	std	r9, -16(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-16(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 16;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+16; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
 	std	r5, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -635,16 +662,17 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r8, -8(r1);			\
 	std	r9, -16(r1);			\
-	stdu	r10, -24(r1);			\
+	std	r10, -24(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-24(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 24;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+24; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
@@ -652,7 +680,7 @@ _GLOBAL(_##API_NAME)				\
 	ld	r11, -24(r1);			\
 	std	r6, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -660,18 +688,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
-	stdu    r9, -8(r1);			\
+	std	r9, -8(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-8(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 8;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+8;	\
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -679,21 +708,22 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r9, -8(r1);			\
-	stdu    r10, -16(r1);			\
+	std	r10, -16(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-16(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 16;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+16; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
 	std	r5, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -701,23 +731,24 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
 	std     r9, -8(r1);			\
-	stdu    r10, -16(r1);			\
+	std	r10, -16(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-16(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 16;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+16; \
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 	ld	r11, -16(r1);			\
 	std	r5, 0(r11);			\
-	ld	r11, 48+8*8(r1);		\
+	ld	r11, STK_PARAM_AREA+8*8(r1);	\
 	std	r6, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -725,18 +756,19 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
-	stdu    r10, -8(r1);			\
+	std	r10, -8(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE-8(r1); \
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	addi	r1, r1, 8;			\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE+8;	\
 	ld	r11, -8(r1);			\
 	std	r4, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -744,27 +776,29 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
 						\
-	std	r10, 48+8*7(r1);		\
+	std	r10, STK_PARAM_AREA+8*7(r1);	\
+	stdu    r1, -STACK_FRAME_MIN_SIZE(r1);	\
 						\
 	li	r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	ld	r11, 48+8*7(r1);		\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE;	\
+	ld	r11, STK_PARAM_AREA+8*7(r1);	\
 	std	r4, 0(r11);			\
-	ld	r11, 48+8*8(r1);		\
+	ld	r11, STK_PARAM_AREA+8*8(r1);	\
 	std	r5, 0(r11);			\
-	ld	r11, 48+8*9(r1);		\
+	ld	r11, STK_PARAM_AREA+8*9(r1);	\
 	std	r6, 0(r11);			\
-	ld	r11, 48+8*10(r1);		\
+	ld	r11, STK_PARAM_AREA+8*10(r1);	\
 	std	r7, 0(r11);			\
-	ld	r11, 48+8*11(r1);		\
+	ld	r11, STK_PARAM_AREA+8*11(r1);	\
 	std	r8, 0(r11);			\
-	ld	r11, 48+8*12(r1);		\
+	ld	r11, STK_PARAM_AREA+8*12(r1);	\
 	std	r9, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
@@ -772,15 +806,17 @@ _GLOBAL(_##API_NAME)				\
 _GLOBAL(_##API_NAME)				\
 						\
 	mflr	r0;				\
-	std	r0, 16(r1);			\
+	std	r0, LRSAVE(r1);			\
+	stdu    r1, -STACK_FRAME_MIN_SIZE(r1);	\
 						\
 	li      r11, API_NUMBER;		\
 	lv1call;				\
 						\
-	ld	r11, 48+8*8(r1);		\
+	addi	r1, r1, STACK_FRAME_MIN_SIZE;	\
+	ld	r11, STK_PARAM_AREA+8*8(r1);	\
 	std	r4, 0(r11);			\
 						\
-	ld	r0, 16(r1);			\
+	ld	r0, LRSAVE(r1);			\
 	mtlr	r0;				\
 	blr
 
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 49871427f599..a4ad4b49eef7 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -378,9 +378,9 @@ int ps3_send_event_locally(unsigned int virq)
 
 /**
  * ps3_sb_event_receive_port_setup - Setup a system bus event receive port.
+ * @dev: The system bus device instance.
  * @cpu: enum ps3_cpu_binding indicating the cpu the interrupt should be
  * serviced on.
- * @dev: The system bus device instance.
  * @virq: The assigned Linux virq.
  *
  * An event irq represents a virtual device interrupt.  The interrupt_id
@@ -743,8 +743,8 @@ void __init ps3_init_IRQ(void)
 	unsigned cpu;
 	struct irq_domain *host;
 
-	host = irq_domain_add_nomap(NULL, PS3_PLUG_MAX + 1, &ps3_host_ops, NULL);
-	irq_set_default_host(host);
+	host = irq_domain_create_nomap(NULL, PS3_PLUG_MAX + 1, &ps3_host_ops, NULL);
+	irq_set_default_domain(host);
 
 	for_each_possible_cpu(cpu) {
 		struct ps3_private *pd = &per_cpu(ps3_private, cpu);
diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c
index 205763061a2d..b8c030eab138 100644
--- a/arch/powerpc/platforms/ps3/repository.c
+++ b/arch/powerpc/platforms/ps3/repository.c
@@ -73,9 +73,9 @@ static void _dump_node(unsigned int lpar_id, u64 n1, u64 n2, u64 n3, u64 n4,
 
 static u64 make_first_field(const char *text, u64 index)
 {
-	u64 n;
+	u64 n = 0;
 
-	strncpy((char *)&n, text, 8);
+	memcpy((char *)&n, text, strnlen(text, sizeof(n)));
 	return PS3_VENDOR_ID_NONE + (n >> 32) + index;
 }
 
@@ -940,7 +940,7 @@ int __init ps3_repository_read_vuart_sysmgr_port(unsigned int *port)
 
 /**
   * ps3_repository_read_boot_dat_info - Get address and size of cell_ext_os_area.
-  * address: lpar address of cell_ext_os_area
+  * @lpar_addr: lpar address of cell_ext_os_area
   * @size: size of cell_ext_os_area
   */
 
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 5144f11359f7..150c09b58ae8 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -115,10 +115,7 @@ static void __init prealloc(struct ps3_prealloc *p)
 	if (!p->size)
 		return;
 
-	p->address = memblock_alloc(p->size, p->align);
-	if (!p->address)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, p->size, p->align);
+	p->address = memblock_alloc_or_panic(p->size, p->align);
 
 	printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size,
 	       p->address);
diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c
index 4a2520ec6d7f..61b37c9400b2 100644
--- a/arch/powerpc/platforms/ps3/spu.c
+++ b/arch/powerpc/platforms/ps3/spu.c
@@ -190,10 +190,10 @@ static void spu_unmap(struct spu *spu)
 static int __init setup_areas(struct spu *spu)
 {
 	struct table {char* name; unsigned long addr; unsigned long size;};
-	unsigned long shadow_flags = pgprot_val(pgprot_noncached_wc(PAGE_KERNEL_RO));
 
 	spu_pdata(spu)->shadow = ioremap_prot(spu_pdata(spu)->shadow_addr,
-					      sizeof(struct spe_shadow), shadow_flags);
+					      sizeof(struct spe_shadow),
+					      pgprot_noncached_wc(PAGE_KERNEL_RO));
 	if (!spu_pdata(spu)->shadow) {
 		pr_debug("%s:%d: ioremap shadow failed\n", __func__, __LINE__);
 		goto fail_ioremap;
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index d6b5f5ecd515..0537a678a32f 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -333,10 +333,10 @@ int ps3_mmio_region_init(struct ps3_system_bus_device *dev,
 EXPORT_SYMBOL_GPL(ps3_mmio_region_init);
 
 static int ps3_system_bus_match(struct device *_dev,
-	struct device_driver *_drv)
+	const struct device_driver *_drv)
 {
 	int result;
-	struct ps3_system_bus_driver *drv = ps3_drv_to_system_bus_drv(_drv);
+	const struct ps3_system_bus_driver *drv = ps3_drv_to_system_bus_drv(_drv);
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 
 	if (!dev->match_sub_id)
@@ -453,10 +453,9 @@ static ssize_t modalias_show(struct device *_dev, struct device_attribute *a,
 	char *buf)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
-	int len = snprintf(buf, PAGE_SIZE, "ps3:%d:%d\n", dev->match_id,
-			   dev->match_sub_id);
 
-	return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len;
+	return sysfs_emit(buf, "ps3:%d:%d\n", dev->match_id,
+			  dev->match_sub_id);
 }
 static DEVICE_ATTR_RO(modalias);
 
@@ -466,7 +465,7 @@ static struct attribute *ps3_system_bus_dev_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ps3_system_bus_dev);
 
-static struct bus_type ps3_system_bus_type = {
+static const struct bus_type ps3_system_bus_type = {
 	.name = "ps3_system_bus",
 	.match = ps3_system_bus_match,
 	.uevent = ps3_system_bus_uevent,
@@ -552,18 +551,20 @@ static void ps3_free_coherent(struct device *_dev, size_t size, void *vaddr,
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
- * comprises a page address and offset into that page. The dma_addr_t
- * returned will point to the same byte within the page as was passed in.
+ * is physical address to that hat page. The dma_addr_t returned will point
+ * to the same byte within the page as was passed in.
  */
 
-static dma_addr_t ps3_sb_map_page(struct device *_dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction,
-	unsigned long attrs)
+static dma_addr_t ps3_sb_map_phys(struct device *_dev, phys_addr_t phys,
+	size_t size, enum dma_data_direction direction, unsigned long attrs)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
 	int result;
 	dma_addr_t bus_addr;
-	void *ptr = page_address(page) + offset;
+	void *ptr = phys_to_virt(phys);
+
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
 
 	result = ps3_dma_map(dev->d_region, (unsigned long)ptr, size,
 			     &bus_addr,
@@ -578,8 +579,8 @@ static dma_addr_t ps3_sb_map_page(struct device *_dev, struct page *page,
 	return bus_addr;
 }
 
-static dma_addr_t ps3_ioc0_map_page(struct device *_dev, struct page *page,
-				    unsigned long offset, size_t size,
+static dma_addr_t ps3_ioc0_map_phys(struct device *_dev, phys_addr_t phys,
+				    size_t size,
 				    enum dma_data_direction direction,
 				    unsigned long attrs)
 {
@@ -587,7 +588,10 @@ static dma_addr_t ps3_ioc0_map_page(struct device *_dev, struct page *page,
 	int result;
 	dma_addr_t bus_addr;
 	u64 iopte_flag;
-	void *ptr = page_address(page) + offset;
+	void *ptr = phys_to_virt(phys);
+
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
 
 	iopte_flag = CBE_IOPTE_M;
 	switch (direction) {
@@ -614,7 +618,7 @@ static dma_addr_t ps3_ioc0_map_page(struct device *_dev, struct page *page,
 	return bus_addr;
 }
 
-static void ps3_unmap_page(struct device *_dev, dma_addr_t dma_addr,
+static void ps3_unmap_phys(struct device *_dev, dma_addr_t dma_addr,
 	size_t size, enum dma_data_direction direction, unsigned long attrs)
 {
 	struct ps3_system_bus_device *dev = ps3_dev_to_system_bus_dev(_dev);
@@ -691,11 +695,11 @@ static const struct dma_map_ops ps3_sb_dma_ops = {
 	.map_sg = ps3_sb_map_sg,
 	.unmap_sg = ps3_sb_unmap_sg,
 	.dma_supported = ps3_dma_supported,
-	.map_page = ps3_sb_map_page,
-	.unmap_page = ps3_unmap_page,
+	.map_phys = ps3_sb_map_phys,
+	.unmap_phys = ps3_unmap_phys,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
-	.alloc_pages = dma_common_alloc_pages,
+	.alloc_pages_op = dma_common_alloc_pages,
 	.free_pages = dma_common_free_pages,
 };
 
@@ -705,11 +709,11 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = {
 	.map_sg = ps3_ioc0_map_sg,
 	.unmap_sg = ps3_ioc0_unmap_sg,
 	.dma_supported = ps3_dma_supported,
-	.map_page = ps3_ioc0_map_page,
-	.unmap_page = ps3_unmap_page,
+	.map_phys = ps3_ioc0_map_phys,
+	.unmap_phys = ps3_unmap_phys,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
-	.alloc_pages = dma_common_alloc_pages,
+	.alloc_pages_op = dma_common_alloc_pages,
 	.free_pages = dma_common_free_pages,
 };
 
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 4ebf2ef2845d..3e042218d6cd 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -7,6 +7,7 @@ config PPC_PSERIES
 	select OF_DYNAMIC
 	select FORCE_PCI
 	select PCI_MSI
+	select IRQ_MSI_LIB
 	select GENERIC_ALLOCATOR
 	select PPC_XICS
 	select PPC_XIVE_SPAPR
@@ -23,6 +24,7 @@ config PPC_PSERIES
 	select FORCE_SMP
 	select SWIOTLB
 	select ARCH_SUPPORTS_PER_VMA_LOCK
+	select PPC_RADIX_BROADCAST_TLBIE if PPC_RADIX_MMU
 	default y
 
 config PARAVIRT
@@ -128,6 +130,15 @@ config CMM
 	  will be reused for other LPARs. The interface allows firmware to
 	  balance memory across many LPARs.
 
+config HTMDUMP
+	tristate "PowerVM data dumper"
+	depends on PPC_PSERIES && DEBUG_FS
+	default m
+	help
+	  Select this option, if you want to enable the kernel debugfs
+	  interface to dump the Hardware Trace Macro (HTM) function data
+	  in the LPAR.
+
 config HV_PERF_CTRS
 	bool "Hypervisor supplied PMU events (24x7 & GPCI)"
 	default y
@@ -140,6 +151,20 @@ config HV_PERF_CTRS
 
 	  If unsure, select Y.
 
+config VPA_PMU
+	tristate "VPA PMU events"
+	depends on KVM_BOOK3S_64_HV && HV_PERF_CTRS
+	help
+	  Enable access to the VPA PMU counters via perf. This enables
+	  code that support measurement for KVM on PowerVM(KoP) feature.
+	  PAPR hypervisor has introduced three new counters in the VPA area
+	  of LPAR CPUs for KVM L2 guest observability. Two for context switches
+	  from host to guest and vice versa, and one counter for getting
+	  the total time spent inside the KVM guest. This config enables code
+	  that access these software counters via perf.
+
+	  If unsure, Select N.
+
 config IBMVIO
 	depends on PPC_PSERIES
 	bool
@@ -164,6 +189,12 @@ config PSERIES_PLPKS
 	# This option is selected by in-kernel consumers that require
 	# access to the PKS.
 
+config PSERIES_PLPKS_SED
+	depends on PPC_PSERIES
+	bool
+	# This option is selected by in-kernel consumers that require
+	# access to the SED PKS keystore.
+
 config PAPR_SCM
 	depends on PPC_PSERIES && MEMORY_HOTPLUG && LIBNVDIMM
 	tristate "Support for the PAPR Storage Class Memory interface"
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 53c3b91af2f7..931ebaa474c8 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -1,9 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
-ccflags-$(CONFIG_PPC64)			:= $(NO_MINIMAL_TOC)
 ccflags-$(CONFIG_PPC_PSERIES_DEBUG)	+= -DDEBUG
 
 obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   of_helpers.o rtas-work-area.o papr-sysparm.o \
+			   papr-rtas-common.o papr-vpd.o papr-indices.o \
+			   papr-platform-dump.o papr-phy-attest.o \
+			   papr-hvpipe.o \
 			   setup.o iommu.o event_sources.o ras.o \
 			   firmware.o power.o dlpar.o mobility.o rng.o \
 			   pci.o pci_dlpar.o eeh_pseries.o msi.o \
@@ -19,6 +21,7 @@ obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
 obj-$(CONFIG_HVCS)		+= hvcserver.o
 obj-$(CONFIG_HCALL_STATS)	+= hvCall_inst.o
 obj-$(CONFIG_CMM)		+= cmm.o
+obj-$(CONFIG_HTMDUMP)		+= htmdump.o
 obj-$(CONFIG_IO_EVENT_IRQ)	+= io_event_irq.o
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
@@ -29,6 +32,7 @@ obj-$(CONFIG_PPC_SVM)		+= svm.o
 obj-$(CONFIG_FA_DUMP)		+= rtas-fadump.o
 obj-$(CONFIG_PSERIES_PLPKS)	+= plpks.o
 obj-$(CONFIG_PPC_SECURE_BOOT)	+= plpks-secvar.o
+obj-$(CONFIG_PSERIES_PLPKS_SED)	+= plpks_sed_ops.o
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PPC_VAS)		+= vas.o vas-sysfs.o
 
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 5f4037c1d7fe..502133979e22 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -375,7 +375,7 @@ static struct device_attribute *cmm_attrs[] = {
 static DEVICE_ULONG_ATTR(simulate_loan_target_kb, 0644,
 			 simulate_loan_target_kb);
 
-static struct bus_type cmm_subsys = {
+static const struct bus_type cmm_subsys = {
 	.name = "cmm",
 	.dev_name = "cmm",
 };
@@ -532,7 +532,6 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info,
 
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 	balloon_page_insert(b_dev_info, newpage);
-	balloon_page_delete(page);
 	b_dev_info->isolated_pages--;
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 
@@ -542,10 +541,11 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info,
 	 */
 	plpar_page_set_active(page);
 
+	balloon_page_finalize(page);
 	/* balloon page list reference */
 	put_page(page);
 
-	return MIGRATEPAGE_SUCCESS;
+	return 0;
 }
 
 static void cmm_balloon_compaction_init(void)
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 719c97a155ed..979487da6522 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -23,6 +23,7 @@
 #include <linux/uaccess.h>
 #include <asm/rtas.h>
 #include <asm/rtas-work-area.h>
+#include <asm/prom.h>
 
 static struct workqueue_struct *pseries_hp_wq;
 
@@ -250,11 +251,8 @@ int dlpar_detach_node(struct device_node *dn)
 	struct device_node *child;
 	int rc;
 
-	child = of_get_next_child(dn, NULL);
-	while (child) {
+	for_each_child_of_node(dn, child)
 		dlpar_detach_node(child);
-		child = of_get_next_child(dn, child);
-	}
 
 	rc = of_detach_node(dn);
 	if (rc)
@@ -264,6 +262,20 @@ int dlpar_detach_node(struct device_node *dn)
 
 	return 0;
 }
+static int dlpar_changeset_attach_cc_nodes(struct of_changeset *ocs,
+					struct device_node *dn)
+{
+	int rc;
+
+	rc = of_changeset_attach_node(ocs, dn);
+
+	if (!rc && dn->child)
+		rc = dlpar_changeset_attach_cc_nodes(ocs, dn->child);
+	if (!rc && dn->sibling)
+		rc = dlpar_changeset_attach_cc_nodes(ocs, dn->sibling);
+
+	return rc;
+}
 
 #define DR_ENTITY_SENSE		9003
 #define DR_ENTITY_PRESENT	1
@@ -330,27 +342,254 @@ int dlpar_unisolate_drc(u32 drc_index)
 	return 0;
 }
 
-int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
+static struct device_node *
+get_device_node_with_drc_index(u32 index)
+{
+	struct device_node *np = NULL;
+	u32 node_index;
+	int rc;
+
+	for_each_node_with_property(np, "ibm,my-drc-index") {
+		rc = of_property_read_u32(np, "ibm,my-drc-index",
+					     &node_index);
+		if (rc) {
+			pr_err("%s: %pOF: of_property_read_u32 %s: %d\n",
+			       __func__, np, "ibm,my-drc-index", rc);
+			of_node_put(np);
+			return NULL;
+		}
+
+		if (index == node_index)
+			break;
+	}
+
+	return np;
+}
+
+static struct device_node *
+get_device_node_with_drc_info(u32 index)
+{
+	struct device_node *np = NULL;
+	struct of_drc_info drc;
+	struct property *info;
+	const __be32 *value;
+	u32 node_index;
+	int i, j, count;
+
+	for_each_node_with_property(np, "ibm,drc-info") {
+		info = of_find_property(np, "ibm,drc-info", NULL);
+		if (info == NULL) {
+			/* XXX can this happen? */
+			of_node_put(np);
+			return NULL;
+		}
+		value = of_prop_next_u32(info, NULL, &count);
+		if (value == NULL)
+			continue;
+		value++;
+		for (i = 0; i < count; i++) {
+			if (of_read_drc_info_cell(&info, &value, &drc))
+				break;
+			if (index > drc.last_drc_index)
+				continue;
+			node_index = drc.drc_index_start;
+			for (j = 0; j < drc.num_sequential_elems; j++) {
+				if (index == node_index)
+					return np;
+				node_index += drc.sequential_inc;
+			}
+		}
+	}
+
+	return NULL;
+}
+
+static struct device_node *
+get_device_node_with_drc_indexes(u32 drc_index)
+{
+	struct device_node *np = NULL;
+	u32 nr_indexes, index;
+	int i, rc;
+
+	for_each_node_with_property(np, "ibm,drc-indexes") {
+		/*
+		 * First element in the array is the total number of
+		 * DRC indexes returned.
+		 */
+		rc = of_property_read_u32_index(np, "ibm,drc-indexes",
+				0, &nr_indexes);
+		if (rc)
+			goto out_put_np;
+
+		/*
+		 * Retrieve DRC index from the list and return the
+		 * device node if matched with the specified index.
+		 */
+		for (i = 0; i < nr_indexes; i++) {
+			rc = of_property_read_u32_index(np, "ibm,drc-indexes",
+							i+1, &index);
+			if (rc)
+				goto out_put_np;
+
+			if (drc_index == index)
+				return np;
+		}
+	}
+
+	return NULL;
+
+out_put_np:
+	of_node_put(np);
+	return NULL;
+}
+
+static int dlpar_hp_dt_add(u32 index)
+{
+	struct device_node *np, *nodes;
+	struct of_changeset ocs;
+	int rc;
+
+	/*
+	 * Do not add device node(s) if already exists in the
+	 * device tree.
+	 */
+	np = get_device_node_with_drc_index(index);
+	if (np) {
+		pr_err("%s: Adding device node for index (%d), but "
+				"already exists in the device tree\n",
+				__func__, index);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Recent FW provides ibm,drc-info property. So search
+	 * for the user specified DRC index from ibm,drc-info
+	 * property. If this property is not available, search
+	 * in the indexes array from ibm,drc-indexes property.
+	 */
+	np = get_device_node_with_drc_info(index);
+
+	if (!np) {
+		np = get_device_node_with_drc_indexes(index);
+		if (!np)
+			return -EIO;
+	}
+
+	/* Next, configure the connector. */
+	nodes = dlpar_configure_connector(cpu_to_be32(index), np);
+	if (!nodes) {
+		rc = -EIO;
+		goto out;
+	}
+
+	/*
+	 * Add the new nodes from dlpar_configure_connector() onto
+	 * the device-tree.
+	 */
+	of_changeset_init(&ocs);
+	rc = dlpar_changeset_attach_cc_nodes(&ocs, nodes);
+
+	if (!rc)
+		rc = of_changeset_apply(&ocs);
+	else
+		dlpar_free_cc_nodes(nodes);
+
+	of_changeset_destroy(&ocs);
+
+out:
+	of_node_put(np);
+	return rc;
+}
+
+static int changeset_detach_node_recursive(struct of_changeset *ocs,
+					struct device_node *node)
+{
+	struct device_node *child;
+	int rc;
+
+	for_each_child_of_node(node, child) {
+		rc = changeset_detach_node_recursive(ocs, child);
+		if (rc) {
+			of_node_put(child);
+			return rc;
+		}
+	}
+
+	return of_changeset_detach_node(ocs, node);
+}
+
+static int dlpar_hp_dt_remove(u32 drc_index)
+{
+	struct device_node *np;
+	struct of_changeset ocs;
+	u32 index;
+	int rc = 0;
+
+	/*
+	 * Prune all nodes with a matching index.
+	 */
+	of_changeset_init(&ocs);
+
+	for_each_node_with_property(np, "ibm,my-drc-index") {
+		rc = of_property_read_u32(np, "ibm,my-drc-index", &index);
+		if (rc) {
+			pr_err("%s: %pOF: of_property_read_u32 %s: %d\n",
+				__func__, np, "ibm,my-drc-index", rc);
+			of_node_put(np);
+			goto out;
+		}
+
+		if (index == drc_index) {
+			rc = changeset_detach_node_recursive(&ocs, np);
+			if (rc) {
+				of_node_put(np);
+				goto out;
+			}
+		}
+	}
+
+	rc = of_changeset_apply(&ocs);
+
+out:
+	of_changeset_destroy(&ocs);
+	return rc;
+}
+
+static int dlpar_hp_dt(struct pseries_hp_errorlog *phpe)
 {
+	u32 drc_index;
 	int rc;
 
-	/* pseries error logs are in BE format, convert to cpu type */
-	switch (hp_elog->id_type) {
-	case PSERIES_HP_ELOG_ID_DRC_COUNT:
-		hp_elog->_drc_u.drc_count =
-				be32_to_cpu(hp_elog->_drc_u.drc_count);
+	if (phpe->id_type != PSERIES_HP_ELOG_ID_DRC_INDEX)
+		return -EINVAL;
+
+	drc_index = be32_to_cpu(phpe->_drc_u.drc_index);
+
+	lock_device_hotplug();
+
+	switch (phpe->action) {
+	case PSERIES_HP_ELOG_ACTION_ADD:
+		rc = dlpar_hp_dt_add(drc_index);
 		break;
-	case PSERIES_HP_ELOG_ID_DRC_INDEX:
-		hp_elog->_drc_u.drc_index =
-				be32_to_cpu(hp_elog->_drc_u.drc_index);
+	case PSERIES_HP_ELOG_ACTION_REMOVE:
+		rc = dlpar_hp_dt_remove(drc_index);
+		break;
+	default:
+		pr_err("Invalid action (%d) specified\n", phpe->action);
+		rc = -EINVAL;
 		break;
-	case PSERIES_HP_ELOG_ID_DRC_IC:
-		hp_elog->_drc_u.ic.count =
-				be32_to_cpu(hp_elog->_drc_u.ic.count);
-		hp_elog->_drc_u.ic.index =
-				be32_to_cpu(hp_elog->_drc_u.ic.index);
 	}
 
+	unlock_device_hotplug();
+
+	return rc;
+}
+
+int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
+{
+	int rc;
+
 	switch (hp_elog->resource) {
 	case PSERIES_HP_ELOG_RESOURCE_MEM:
 		rc = dlpar_memory(hp_elog);
@@ -361,6 +600,9 @@ int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
 	case PSERIES_HP_ELOG_RESOURCE_PMEM:
 		rc = dlpar_hp_pmem(hp_elog);
 		break;
+	case PSERIES_HP_ELOG_RESOURCE_DT:
+		rc = dlpar_hp_dt(hp_elog);
+		break;
 
 	default:
 		pr_warn_ratelimited("Invalid resource (%d) specified\n",
@@ -413,6 +655,8 @@ static int dlpar_parse_resource(char **cmd, struct pseries_hp_errorlog *hp_elog)
 		hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM;
 	} else if (sysfs_streq(arg, "cpu")) {
 		hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_CPU;
+	} else if (sysfs_streq(arg, "dt")) {
+		hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_DT;
 	} else {
 		pr_err("Invalid resource specified.\n");
 		return -EINVAL;
@@ -554,7 +798,7 @@ dlpar_store_out:
 static ssize_t dlpar_show(const struct class *class, const struct class_attribute *attr,
 			  char *buf)
 {
-	return sprintf(buf, "%s\n", "memory,cpu");
+	return sprintf(buf, "%s\n", "memory,cpu,dt");
 }
 
 static CLASS_ATTR_RW(dlpar);
@@ -564,8 +808,7 @@ int __init dlpar_workqueue_init(void)
 	if (pseries_hp_wq)
 		return 0;
 
-	pseries_hp_wq = alloc_workqueue("pseries hotplug workqueue",
-			WQ_UNBOUND, 1);
+	pseries_hp_wq = alloc_ordered_workqueue("pseries hotplug workqueue", 0);
 
 	return pseries_hp_wq ? 0 : -ENOMEM;
 }
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 3f1cdccebc9c..f293588b8c7b 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -191,7 +191,7 @@ static int dtl_enable(struct dtl *dtl)
 		return -EBUSY;
 
 	/* ensure there are no other conflicting dtl users */
-	if (!read_trylock(&dtl_access_lock))
+	if (!down_read_trylock(&dtl_access_lock))
 		return -EBUSY;
 
 	n_entries = dtl_buf_entries;
@@ -199,7 +199,7 @@ static int dtl_enable(struct dtl *dtl)
 	if (!buf) {
 		printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
 				__func__, dtl->cpu);
-		read_unlock(&dtl_access_lock);
+		up_read(&dtl_access_lock);
 		return -ENOMEM;
 	}
 
@@ -217,7 +217,7 @@ static int dtl_enable(struct dtl *dtl)
 	spin_unlock(&dtl->lock);
 
 	if (rc) {
-		read_unlock(&dtl_access_lock);
+		up_read(&dtl_access_lock);
 		kmem_cache_free(dtl_cache, buf);
 	}
 
@@ -232,7 +232,7 @@ static void dtl_disable(struct dtl *dtl)
 	dtl->buf = NULL;
 	dtl->buf_entries = 0;
 	spin_unlock(&dtl->lock);
-	read_unlock(&dtl_access_lock);
+	up_read(&dtl_access_lock);
 }
 
 /* file interface */
@@ -325,7 +325,6 @@ static const struct file_operations dtl_fops = {
 	.open		= dtl_file_open,
 	.release	= dtl_file_release,
 	.read		= dtl_file_read,
-	.llseek		= no_llseek,
 };
 
 static struct dentry *dtl_dir;
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index def184da51cf..b12ef382fec7 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -252,7 +252,7 @@ static int pseries_eeh_cap_start(struct pci_dn *pdn)
 	if (!pdn)
 		return 0;
 
-	rtas_read_config(pdn, PCI_STATUS, 2, &status);
+	rtas_pci_dn_read_config(pdn, PCI_STATUS, 2, &status);
 	if (!(status & PCI_STATUS_CAP_LIST))
 		return 0;
 
@@ -270,11 +270,11 @@ static int pseries_eeh_find_cap(struct pci_dn *pdn, int cap)
 		return 0;
 
         while (cnt--) {
-		rtas_read_config(pdn, pos, 1, &pos);
+		rtas_pci_dn_read_config(pdn, pos, 1, &pos);
 		if (pos < 0x40)
 			break;
 		pos &= ~3;
-		rtas_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
+		rtas_pci_dn_read_config(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
 		if (id == 0xff)
 			break;
 		if (id == cap)
@@ -294,7 +294,7 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
 
 	if (!edev || !edev->pcie_cap)
 		return 0;
-	if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+	if (rtas_pci_dn_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
 		return 0;
 	else if (!header)
 		return 0;
@@ -307,7 +307,7 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
 		if (pos < 256)
 			break;
 
-		if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+		if (rtas_pci_dn_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
 			break;
 	}
 
@@ -412,8 +412,8 @@ static void pseries_eeh_init_edev(struct pci_dn *pdn)
 	if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
 		if (edev->pcie_cap) {
-			rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
-					 2, &pcie_flags);
+			rtas_pci_dn_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
+						2, &pcie_flags);
 			pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4;
 			if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT)
 				edev->mode |= EEH_DEV_ROOT_PORT;
@@ -580,8 +580,10 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay)
 
 	switch(rets[0]) {
 	case 0:
-		result = EEH_STATE_MMIO_ACTIVE |
-			 EEH_STATE_DMA_ACTIVE;
+		result = EEH_STATE_MMIO_ACTIVE	|
+			 EEH_STATE_DMA_ACTIVE	|
+			 EEH_STATE_MMIO_ENABLED	|
+			 EEH_STATE_DMA_ENABLED;
 		break;
 	case 1:
 		result = EEH_STATE_RESET_ACTIVE |
@@ -676,7 +678,7 @@ static int pseries_eeh_read_config(struct eeh_dev *edev, int where, int size, u3
 {
 	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
-	return rtas_read_config(pdn, where, size, val);
+	return rtas_pci_dn_read_config(pdn, where, size, val);
 }
 
 /**
@@ -692,7 +694,7 @@ static int pseries_eeh_write_config(struct eeh_dev *edev, int where, int size, u
 {
 	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
-	return rtas_write_config(pdn, where, size, val);
+	return rtas_pci_dn_write_config(pdn, where, size, val);
 }
 
 #ifdef CONFIG_PCI_IOV
@@ -784,6 +786,43 @@ static int pseries_notify_resume(struct eeh_dev *edev)
 }
 #endif
 
+/**
+ * pseries_eeh_err_inject - Inject specified error to the indicated PE
+ * @pe: the indicated PE
+ * @type: error type
+ * @func: specific error type
+ * @addr: address
+ * @mask: address mask
+ * The routine is called to inject specified error, which is
+ * determined by @type and @func, to the indicated PE
+ */
+static int pseries_eeh_err_inject(struct eeh_pe *pe, int type, int func,
+				  unsigned long addr, unsigned long mask)
+{
+	struct	eeh_dev	*pdev;
+
+	/* Check on PCI error type */
+	if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
+		return -EINVAL;
+
+	switch (func) {
+	case EEH_ERR_FUNC_LD_MEM_ADDR:
+	case EEH_ERR_FUNC_LD_MEM_DATA:
+	case EEH_ERR_FUNC_ST_MEM_ADDR:
+	case EEH_ERR_FUNC_ST_MEM_DATA:
+		/* injects a MMIO error for all pdev's belonging to PE */
+		pci_lock_rescan_remove();
+		list_for_each_entry(pdev, &pe->edevs, entry)
+			eeh_pe_inject_mmio_error(pdev->pdev);
+		pci_unlock_rescan_remove();
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
 static struct eeh_ops pseries_eeh_ops = {
 	.name			= "pseries",
 	.probe			= pseries_eeh_probe,
@@ -792,7 +831,7 @@ static struct eeh_ops pseries_eeh_ops = {
 	.reset			= pseries_eeh_reset,
 	.get_log		= pseries_eeh_get_log,
 	.configure_bridge       = pseries_eeh_configure_bridge,
-	.err_inject		= NULL,
+	.err_inject		= pseries_eeh_err_inject,
 	.read_config		= pseries_eeh_read_config,
 	.write_config		= pseries_eeh_write_config,
 	.next_error		= NULL,
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 1a3cb313976a..bc6926dbf148 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -33,6 +33,7 @@
 #include <asm/xive.h>
 #include <asm/plpar_wrappers.h>
 #include <asm/topology.h>
+#include <asm/systemcfg.h>
 
 #include "pseries.h"
 
@@ -83,7 +84,9 @@ static int pseries_cpu_disable(void)
 	int cpu = smp_processor_id();
 
 	set_cpu_online(cpu, false);
-	vdso_data->processorCount--;
+#ifdef CONFIG_PPC64_PROC_SYSTEMCFG
+	systemcfg->processorCount--;
+#endif
 
 	/*fix boot_cpuid here*/
 	if (cpu == boot_cpuid)
@@ -398,6 +401,14 @@ static int dlpar_online_cpu(struct device_node *dn)
 		for_each_present_cpu(cpu) {
 			if (get_hard_smp_processor_id(cpu) != thread)
 				continue;
+
+			if (!topology_is_primary_thread(cpu)) {
+				if (cpu_smt_control != CPU_SMT_ENABLED)
+					break;
+				if (!topology_smt_thread_allowed(cpu))
+					break;
+			}
+
 			cpu_maps_update_done();
 			find_and_update_cpu_nid(cpu);
 			rc = device_online(get_cpu_device(cpu));
@@ -749,7 +760,7 @@ int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
 	u32 drc_index;
 	int rc;
 
-	drc_index = hp_elog->_drc_u.drc_index;
+	drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index);
 
 	lock_device_hotplug();
 
@@ -845,15 +856,9 @@ static struct notifier_block pseries_smp_nb = {
 	.notifier_call = pseries_smp_notifier,
 };
 
-static int __init pseries_cpu_hotplug_init(void)
+void __init pseries_cpu_hotplug_init(void)
 {
 	int qcss_tok;
-	unsigned int node;
-
-#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
-	ppc_md.cpu_probe = dlpar_cpu_probe;
-	ppc_md.cpu_release = dlpar_cpu_release;
-#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
 
 	rtas_stop_self_token = rtas_function_token(RTAS_FN_STOP_SELF);
 	qcss_tok = rtas_function_token(RTAS_FN_QUERY_CPU_STOPPED_STATE);
@@ -862,12 +867,22 @@ static int __init pseries_cpu_hotplug_init(void)
 			qcss_tok == RTAS_UNKNOWN_SERVICE) {
 		printk(KERN_INFO "CPU Hotplug not supported by firmware "
 				"- disabling.\n");
-		return 0;
+		return;
 	}
 
 	smp_ops->cpu_offline_self = pseries_cpu_offline_self;
 	smp_ops->cpu_disable = pseries_cpu_disable;
 	smp_ops->cpu_die = pseries_cpu_die;
+}
+
+static int __init pseries_dlpar_init(void)
+{
+	unsigned int node;
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+	ppc_md.cpu_probe = dlpar_cpu_probe;
+	ppc_md.cpu_release = dlpar_cpu_release;
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
 
 	/* Processors can be added/removed only on LPAR */
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
@@ -886,4 +901,4 @@ static int __init pseries_cpu_hotplug_init(void)
 
 	return 0;
 }
-machine_arch_initcall(pseries, pseries_cpu_hotplug_init);
+machine_arch_initcall(pseries, pseries_dlpar_init);
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 9c62c2c3b3d0..38dc4f7c9296 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -21,54 +21,6 @@
 #include <asm/drmem.h>
 #include "pseries.h"
 
-unsigned long pseries_memory_block_size(void)
-{
-	struct device_node *np;
-	u64 memblock_size = MIN_MEMORY_BLOCK_SIZE;
-	struct resource r;
-
-	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
-	if (np) {
-		int len;
-		int size_cells;
-		const __be32 *prop;
-
-		size_cells = of_n_size_cells(np);
-
-		prop = of_get_property(np, "ibm,lmb-size", &len);
-		if (prop && len >= size_cells * sizeof(__be32))
-			memblock_size = of_read_number(prop, size_cells);
-		of_node_put(np);
-
-	} else  if (machine_is(pseries)) {
-		/* This fallback really only applies to pseries */
-		unsigned int memzero_size = 0;
-
-		np = of_find_node_by_path("/memory@0");
-		if (np) {
-			if (!of_address_to_resource(np, 0, &r))
-				memzero_size = resource_size(&r);
-			of_node_put(np);
-		}
-
-		if (memzero_size) {
-			/* We now know the size of memory@0, use this to find
-			 * the first memoryblock and get its size.
-			 */
-			char buf[64];
-
-			sprintf(buf, "/memory@%x", memzero_size);
-			np = of_find_node_by_path(buf);
-			if (np) {
-				if (!of_address_to_resource(np, 0, &r))
-					memblock_size = resource_size(&r);
-				of_node_put(np);
-			}
-		}
-	}
-	return memblock_size;
-}
-
 static void dlpar_free_property(struct property *prop)
 {
 	kfree(prop->name);
@@ -103,7 +55,8 @@ static bool find_aa_index(struct device_node *dr_node,
 			 struct property *ala_prop,
 			 const u32 *lmb_assoc, u32 *aa_index)
 {
-	u32 *assoc_arrays, new_prop_size;
+	__be32 *assoc_arrays;
+	u32 new_prop_size;
 	struct property *new_prop;
 	int aa_arrays, aa_array_entries, aa_array_sz;
 	int i, index;
@@ -255,8 +208,10 @@ static int dlpar_change_lmb_state(struct drmem_lmb *lmb, bool online)
 	int rc;
 
 	mem_block = lmb_to_memblock(lmb);
-	if (!mem_block)
+	if (!mem_block) {
+		pr_err("Failed memory block lookup for LMB 0x%x\n", lmb->drc_index);
 		return -EINVAL;
+	}
 
 	if (online && mem_block->dev.offline)
 		rc = device_online(&mem_block->dev);
@@ -283,7 +238,7 @@ static int dlpar_offline_lmb(struct drmem_lmb *lmb)
 
 static int pseries_remove_memblock(unsigned long base, unsigned long memblock_size)
 {
-	unsigned long block_sz, start_pfn;
+	unsigned long start_pfn;
 	int sections_per_block;
 	int i;
 
@@ -294,8 +249,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si
 	if (!pfn_valid(start_pfn))
 		goto out;
 
-	block_sz = pseries_memory_block_size();
-	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+	sections_per_block = memory_block_size / MIN_MEMORY_BLOCK_SIZE;
 
 	for (i = 0; i < sections_per_block; i++) {
 		__remove_memory(base, MIN_MEMORY_BLOCK_SIZE);
@@ -354,7 +308,6 @@ static int dlpar_add_lmb(struct drmem_lmb *);
 static int dlpar_remove_lmb(struct drmem_lmb *lmb)
 {
 	struct memory_block *mem_block;
-	unsigned long block_sz;
 	int rc;
 
 	if (!lmb_is_removable(lmb))
@@ -370,13 +323,11 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb)
 		return rc;
 	}
 
-	block_sz = pseries_memory_block_size();
-
-	__remove_memory(lmb->base_addr, block_sz);
+	__remove_memory(lmb->base_addr, memory_block_size);
 	put_device(&mem_block->dev);
 
 	/* Update memory regions for memory remove */
-	memblock_remove(lmb->base_addr, block_sz);
+	memblock_remove(lmb->base_addr, memory_block_size);
 
 	invalidate_lmb_associativity_index(lmb);
 	lmb->flags &= ~DRCONF_MEM_ASSIGNED;
@@ -487,14 +438,15 @@ static int dlpar_memory_remove_by_index(u32 drc_index)
 		}
 	}
 
-	if (!lmb_found)
+	if (!lmb_found) {
+		pr_debug("Failed to look up LMB for drc index %x\n", drc_index);
 		rc = -EINVAL;
-
-	if (rc)
+	} else if (rc) {
 		pr_debug("Failed to hot-remove memory at %llx\n",
 			 lmb->base_addr);
-	else
+	} else {
 		pr_debug("Memory at %llx was hot-removed\n", lmb->base_addr);
+	}
 
 	return rc;
 }
@@ -626,6 +578,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 	rc = update_lmb_associativity_index(lmb);
 	if (rc) {
 		dlpar_release_drc(lmb->drc_index);
+		pr_err("Failed to configure LMB 0x%x\n", lmb->drc_index);
 		return rc;
 	}
 
@@ -637,14 +590,16 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 		nid = first_online_node;
 
 	/* Add the memory */
-	rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_NONE);
+	rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_MEMMAP_ON_MEMORY);
 	if (rc) {
+		pr_err("Failed to add LMB 0x%x to node %u", lmb->drc_index, nid);
 		invalidate_lmb_associativity_index(lmb);
 		return rc;
 	}
 
 	rc = dlpar_online_lmb(lmb);
 	if (rc) {
+		pr_err("Failed to online LMB 0x%x on node %u\n", lmb->drc_index, nid);
 		__remove_memory(lmb->base_addr, block_sz);
 		invalidate_lmb_associativity_index(lmb);
 	} else {
@@ -862,16 +817,16 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 	case PSERIES_HP_ELOG_ACTION_ADD:
 		switch (hp_elog->id_type) {
 		case PSERIES_HP_ELOG_ID_DRC_COUNT:
-			count = hp_elog->_drc_u.drc_count;
+			count = be32_to_cpu(hp_elog->_drc_u.drc_count);
 			rc = dlpar_memory_add_by_count(count);
 			break;
 		case PSERIES_HP_ELOG_ID_DRC_INDEX:
-			drc_index = hp_elog->_drc_u.drc_index;
+			drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index);
 			rc = dlpar_memory_add_by_index(drc_index);
 			break;
 		case PSERIES_HP_ELOG_ID_DRC_IC:
-			count = hp_elog->_drc_u.ic.count;
-			drc_index = hp_elog->_drc_u.ic.index;
+			count = be32_to_cpu(hp_elog->_drc_u.ic.count);
+			drc_index = be32_to_cpu(hp_elog->_drc_u.ic.index);
 			rc = dlpar_memory_add_by_ic(count, drc_index);
 			break;
 		default:
@@ -883,16 +838,16 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 	case PSERIES_HP_ELOG_ACTION_REMOVE:
 		switch (hp_elog->id_type) {
 		case PSERIES_HP_ELOG_ID_DRC_COUNT:
-			count = hp_elog->_drc_u.drc_count;
+			count = be32_to_cpu(hp_elog->_drc_u.drc_count);
 			rc = dlpar_memory_remove_by_count(count);
 			break;
 		case PSERIES_HP_ELOG_ID_DRC_INDEX:
-			drc_index = hp_elog->_drc_u.drc_index;
+			drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index);
 			rc = dlpar_memory_remove_by_index(drc_index);
 			break;
 		case PSERIES_HP_ELOG_ID_DRC_IC:
-			count = hp_elog->_drc_u.ic.count;
-			drc_index = hp_elog->_drc_u.ic.index;
+			count = be32_to_cpu(hp_elog->_drc_u.ic.count);
+			drc_index = be32_to_cpu(hp_elog->_drc_u.ic.index);
 			rc = dlpar_memory_remove_by_ic(count, drc_index);
 			break;
 		default:
diff --git a/arch/powerpc/platforms/pseries/htmdump.c b/arch/powerpc/platforms/pseries/htmdump.c
new file mode 100644
index 000000000000..742ec52c9d4d
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/htmdump.c
@@ -0,0 +1,490 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) IBM Corporation, 2024
+ */
+
+#define pr_fmt(fmt) "htmdump: " fmt
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/plpar_wrappers.h>
+#include <asm/kvm_guest.h>
+
+static void *htm_buf;
+static void *htm_status_buf;
+static void *htm_info_buf;
+static void *htm_caps_buf;
+static u32 nodeindex;
+static u32 nodalchipindex;
+static u32 coreindexonchip;
+static u32 htmtype;
+static u32 htmconfigure;
+static u32 htmstart;
+static u32 htmsetup;
+static u64 htmflags;
+
+static struct dentry *htmdump_debugfs_dir;
+#define	HTM_ENABLE	1
+#define	HTM_DISABLE	0
+#define	HTM_NOWRAP	1
+#define	HTM_WRAP	0
+
+/*
+ * Check the return code for H_HTM hcall.
+ * Return non-zero value (1) if either H_PARTIAL or H_SUCCESS
+ * is returned. For other return codes:
+ * Return zero if H_NOT_AVAILABLE.
+ * Return -EBUSY if hcall return busy.
+ * Return -EINVAL if any parameter or operation is not valid.
+ * Return -EPERM if HTM Virtualization Engine Technology code
+ * is not applied.
+ * Return -EIO if the HTM state is not valid.
+ */
+static ssize_t htm_return_check(long rc)
+{
+	switch (rc) {
+	case H_SUCCESS:
+	/* H_PARTIAL for the case where all available data can't be
+	 * returned due to buffer size constraint.
+	 */
+	case H_PARTIAL:
+		break;
+	/* H_NOT_AVAILABLE indicates reading from an offset outside the range,
+	 * i.e. past end of file.
+	 */
+	case H_NOT_AVAILABLE:
+		return 0;
+	case H_BUSY:
+	case H_LONG_BUSY_ORDER_1_MSEC:
+	case H_LONG_BUSY_ORDER_10_MSEC:
+	case H_LONG_BUSY_ORDER_100_MSEC:
+	case H_LONG_BUSY_ORDER_1_SEC:
+	case H_LONG_BUSY_ORDER_10_SEC:
+	case H_LONG_BUSY_ORDER_100_SEC:
+		return -EBUSY;
+	case H_PARAMETER:
+	case H_P2:
+	case H_P3:
+	case H_P4:
+	case H_P5:
+	case H_P6:
+		return -EINVAL;
+	case H_STATE:
+		return -EIO;
+	case H_AUTHORITY:
+		return -EPERM;
+	}
+
+	/*
+	 * Return 1 for H_SUCCESS/H_PARTIAL
+	 */
+	return 1;
+}
+
+static ssize_t htmdump_read(struct file *filp, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	void *htm_buf = filp->private_data;
+	unsigned long page, read_size, available;
+	loff_t offset;
+	long rc, ret;
+
+	page = ALIGN_DOWN(*ppos, PAGE_SIZE);
+	offset = (*ppos) % PAGE_SIZE;
+
+	/*
+	 * Invoke H_HTM call with:
+	 * - operation as htm dump (H_HTM_OP_DUMP_DATA)
+	 * - last three values are address, size and offset
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				   htmtype, H_HTM_OP_DUMP_DATA, virt_to_phys(htm_buf),
+				   PAGE_SIZE, page);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_DUMP_DATA, returning %ld\n", ret);
+		return ret;
+	}
+
+	available = PAGE_SIZE;
+	read_size = min(count, available);
+	*ppos += read_size;
+	return simple_read_from_buffer(ubuf, count, &offset, htm_buf, available);
+}
+
+static const struct file_operations htmdump_fops = {
+	.llseek = NULL,
+	.read	= htmdump_read,
+	.open	= simple_open,
+};
+
+static int  htmconfigure_set(void *data, u64 val)
+{
+	long rc, ret;
+	unsigned long param1 = -1, param2 = -1;
+
+	/*
+	 * value as 1 : configure HTM.
+	 * value as 0 : deconfigure HTM. Return -EINVAL for
+	 * other values.
+	 */
+	if (val == HTM_ENABLE) {
+		/*
+		 * Invoke H_HTM call with:
+		 * - operation as htm configure (H_HTM_OP_CONFIGURE)
+		 * - If htmflags is set, param1 and param2 will be -1
+		 *   which is an indicator to use default htm mode reg mask
+		 *   and htm mode reg value.
+		 * - last three values are unused, hence set to zero
+		 */
+		if (!htmflags) {
+			param1 = 0;
+			param2 = 0;
+		}
+
+		rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+			   htmtype, H_HTM_OP_CONFIGURE, param1, param2, 0);
+	} else if (val == HTM_DISABLE) {
+		/*
+		 * Invoke H_HTM call with:
+		 * - operation as htm deconfigure (H_HTM_OP_DECONFIGURE)
+		 * - last three values are unused, hence set to zero
+		 */
+		rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				htmtype, H_HTM_OP_DECONFIGURE, 0, 0, 0);
+	} else
+		return -EINVAL;
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed, returning %ld\n", ret);
+		return ret;
+	}
+
+	/* Set htmconfigure if operation succeeds */
+	htmconfigure = val;
+
+	return 0;
+}
+
+static int htmconfigure_get(void *data, u64 *val)
+{
+	*val = htmconfigure;
+	return 0;
+}
+
+static int  htmstart_set(void *data, u64 val)
+{
+	long rc, ret;
+
+	/*
+	 * value as 1: start HTM
+	 * value as 0: stop HTM
+	 * Return -EINVAL for other values.
+	 */
+	if (val == HTM_ENABLE) {
+		/*
+		 * Invoke H_HTM call with:
+		 * - operation as htm start (H_HTM_OP_START)
+		 * - last three values are unused, hence set to zero
+		 */
+		rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+			   htmtype, H_HTM_OP_START, 0, 0, 0);
+
+	} else if (val == HTM_DISABLE) {
+		/*
+		 * Invoke H_HTM call with:
+		 * - operation as htm stop (H_HTM_OP_STOP)
+		 * - last three values are unused, hence set to zero
+		 */
+		rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				htmtype, H_HTM_OP_STOP, 0, 0, 0);
+	} else
+		return -EINVAL;
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed, returning %ld\n", ret);
+		return ret;
+	}
+
+	/* Set htmstart if H_HTM_OP_START/H_HTM_OP_STOP operation succeeds */
+	htmstart = val;
+
+	return 0;
+}
+
+static int htmstart_get(void *data, u64 *val)
+{
+	*val = htmstart;
+	return 0;
+}
+
+static ssize_t htmstatus_read(struct file *filp, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	void *htm_status_buf = filp->private_data;
+	long rc, ret;
+	u64 *num_entries;
+	u64 to_copy;
+	int htmstatus_flag;
+
+	/*
+	 * Invoke H_HTM call with:
+	 * - operation as htm status (H_HTM_OP_STATUS)
+	 * - last three values as addr, size and offset
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				   htmtype, H_HTM_OP_STATUS, virt_to_phys(htm_status_buf),
+				   PAGE_SIZE, 0);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_STATUS, returning %ld\n", ret);
+		return ret;
+	}
+
+	/*
+	 * HTM status buffer, start of buffer + 0x10 gives the
+	 * number of HTM entries in the buffer. Each nest htm status
+	 * entry is 0x6 bytes where each core htm status entry is
+	 * 0x8 bytes.
+	 * So total count to copy is:
+	 * 32 bytes (for first 7 fields) + (number of HTM entries * entry size)
+	 */
+	num_entries = htm_status_buf + 0x10;
+	if (htmtype == 0x2)
+		htmstatus_flag = 0x8;
+	else
+		htmstatus_flag = 0x6;
+	to_copy = 32 + (be64_to_cpu(*num_entries) * htmstatus_flag);
+	return simple_read_from_buffer(ubuf, count, ppos, htm_status_buf, to_copy);
+}
+
+static const struct file_operations htmstatus_fops = {
+	.llseek = NULL,
+	.read	= htmstatus_read,
+	.open	= simple_open,
+};
+
+static ssize_t htminfo_read(struct file *filp, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	void *htm_info_buf = filp->private_data;
+	long rc, ret;
+	u64 *num_entries;
+	u64 to_copy;
+
+	/*
+	 * Invoke H_HTM call with:
+	 * - operation as htm status (H_HTM_OP_STATUS)
+	 * - last three values as addr, size and offset
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				   htmtype, H_HTM_OP_DUMP_SYSPROC_CONF, virt_to_phys(htm_info_buf),
+				   PAGE_SIZE, 0);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_DUMP_SYSPROC_CONF, returning %ld\n", ret);
+		return ret;
+	}
+
+	/*
+	 * HTM status buffer, start of buffer + 0x10 gives the
+	 * number of HTM entries in the buffer. Each entry of processor
+	 * is 16 bytes.
+	 *
+	 * So total count to copy is:
+	 * 32 bytes (for first 5 fields) + (number of HTM entries * entry size)
+	 */
+	num_entries = htm_info_buf + 0x10;
+	to_copy = 32 + (be64_to_cpu(*num_entries) * 16);
+	return simple_read_from_buffer(ubuf, count, ppos, htm_info_buf, to_copy);
+}
+
+static ssize_t htmcaps_read(struct file *filp, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	void *htm_caps_buf = filp->private_data;
+	long rc, ret;
+
+	/*
+	 * Invoke H_HTM call with:
+	 * - operation as htm capabilities (H_HTM_OP_CAPABILITIES)
+	 * - last three values as addr, size (0x80 for Capabilities Output Buffer
+	 *   and zero
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+				   htmtype, H_HTM_OP_CAPABILITIES, virt_to_phys(htm_caps_buf),
+				   0x80, 0);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_CAPABILITIES, returning %ld\n", ret);
+		return ret;
+	}
+
+	return simple_read_from_buffer(ubuf, count, ppos, htm_caps_buf, 0x80);
+}
+
+static const struct file_operations htminfo_fops = {
+	.llseek = NULL,
+	.read   = htminfo_read,
+	.open   = simple_open,
+};
+
+static const struct file_operations htmcaps_fops = {
+	.llseek = NULL,
+	.read   = htmcaps_read,
+	.open   = simple_open,
+};
+
+static int  htmsetup_set(void *data, u64 val)
+{
+	long rc, ret;
+
+	/*
+	 * Input value: HTM buffer size in the power of 2
+	 * example: hex value 0x21 ( decimal: 33 ) is for
+	 * 8GB
+	 * Invoke H_HTM call with:
+	 * - operation as htm start (H_HTM_OP_SETUP)
+	 * - parameter 1 set to input value.
+	 * - last two values are unused, hence set to zero
+	 */
+	rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip,
+			htmtype, H_HTM_OP_SETUP, val, 0, 0);
+
+	ret = htm_return_check(rc);
+	if (ret <= 0) {
+		pr_debug("H_HTM hcall failed for op: H_HTM_OP_SETUP, returning %ld\n", ret);
+		return ret;
+	}
+
+	/* Set htmsetup if H_HTM_OP_SETUP operation succeeds */
+	htmsetup = val;
+
+	return 0;
+}
+
+static int htmsetup_get(void *data, u64 *val)
+{
+	*val = htmsetup;
+	return 0;
+}
+
+static int  htmflags_set(void *data, u64 val)
+{
+	/*
+	 * Input value:
+	 * Currently supported flag value is to enable/disable
+	 * HTM buffer wrap. wrap is used along with "configure"
+	 * to prevent HTM buffer from wrapping.
+	 * Writing 1 will set noWrap while configuring HTM
+	 */
+	if (val == HTM_NOWRAP)
+		htmflags = H_HTM_FLAGS_NOWRAP;
+	else if (val == HTM_WRAP)
+		htmflags = 0;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int htmflags_get(void *data, u64 *val)
+{
+	*val = htmflags;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(htmconfigure_fops, htmconfigure_get, htmconfigure_set, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(htmstart_fops, htmstart_get, htmstart_set, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(htmsetup_fops, htmsetup_get, htmsetup_set, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(htmflags_fops, htmflags_get, htmflags_set, "%llu\n");
+
+static int htmdump_init_debugfs(void)
+{
+	htm_buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!htm_buf) {
+		pr_err("Failed to allocate htmdump buf\n");
+		return -ENOMEM;
+	}
+
+	htmdump_debugfs_dir = debugfs_create_dir("htmdump",
+						  arch_debugfs_dir);
+
+	debugfs_create_u32("nodeindex", 0600,
+			htmdump_debugfs_dir, &nodeindex);
+	debugfs_create_u32("nodalchipindex", 0600,
+			htmdump_debugfs_dir, &nodalchipindex);
+	debugfs_create_u32("coreindexonchip", 0600,
+			htmdump_debugfs_dir, &coreindexonchip);
+	debugfs_create_u32("htmtype", 0600,
+			htmdump_debugfs_dir, &htmtype);
+	debugfs_create_file("trace", 0400, htmdump_debugfs_dir, htm_buf, &htmdump_fops);
+
+	/*
+	 * Debugfs interface files to control HTM operations:
+	 */
+	debugfs_create_file("htmconfigure", 0600, htmdump_debugfs_dir, NULL, &htmconfigure_fops);
+	debugfs_create_file("htmstart", 0600, htmdump_debugfs_dir, NULL, &htmstart_fops);
+	debugfs_create_file("htmsetup", 0600, htmdump_debugfs_dir, NULL, &htmsetup_fops);
+	debugfs_create_file("htmflags", 0600, htmdump_debugfs_dir, NULL, &htmflags_fops);
+
+	/* Debugfs interface file to present status of HTM */
+	htm_status_buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!htm_status_buf) {
+		pr_err("Failed to allocate htmstatus buf\n");
+		return -ENOMEM;
+	}
+
+	/* Debugfs interface file to present System Processor Configuration */
+	htm_info_buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!htm_info_buf) {
+		pr_err("Failed to allocate htm info buf\n");
+		return -ENOMEM;
+	}
+
+	/* Debugfs interface file to present HTM capabilities */
+	htm_caps_buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!htm_caps_buf) {
+		pr_err("Failed to allocate htm caps buf\n");
+		return -ENOMEM;
+	}
+
+	debugfs_create_file("htmstatus", 0400, htmdump_debugfs_dir, htm_status_buf, &htmstatus_fops);
+	debugfs_create_file("htminfo", 0400, htmdump_debugfs_dir, htm_info_buf, &htminfo_fops);
+	debugfs_create_file("htmcaps", 0400, htmdump_debugfs_dir, htm_caps_buf, &htmcaps_fops);
+
+	return 0;
+}
+
+static int __init htmdump_init(void)
+{
+	/* Disable on kvm guest */
+	if (is_kvm_guest()) {
+		pr_info("htmdump not supported inside KVM guest\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (htmdump_init_debugfs())
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __exit htmdump_exit(void)
+{
+	debugfs_remove_recursive(htmdump_debugfs_dir);
+	kfree(htm_buf);
+}
+
+module_init(htmdump_init);
+module_exit(htmdump_exit);
+MODULE_DESCRIPTION("PHYP Hardware Trace Macro (HTM) data dumper");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index 35254ac7af5e..2b0cac6fb61f 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -91,7 +91,7 @@ BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
 	LOAD_REG_ADDR(r12, hcall_tracepoint_refcount) ;		\
-	std	r12,32(r1);					\
+	ld	r12,0(r12);					\
 	cmpdi	r12,0;						\
 	bne-	LABEL;						\
 1:
@@ -184,9 +184,6 @@ _GLOBAL_TOC(plpar_hcall)
 plpar_hcall_trace:
 	HCALL_INST_PRECALL(R5)
 
-	std	r4,STK_PARAM(R4)(r1)
-	mr	r0,r4
-
 	mr	r4,r5
 	mr	r5,r6
 	mr	r6,r7
@@ -196,7 +193,7 @@ plpar_hcall_trace:
 
 	HVSC
 
-	ld	r12,STK_PARAM(R4)(r1)
+	ld	r12,STACK_FRAME_MIN_SIZE+STK_PARAM(R4)(r1)
 	std	r4,0(r12)
 	std	r5,8(r12)
 	std	r6,16(r12)
@@ -296,9 +293,6 @@ _GLOBAL_TOC(plpar_hcall9)
 plpar_hcall9_trace:
 	HCALL_INST_PRECALL(R5)
 
-	std	r4,STK_PARAM(R4)(r1)
-	mr	r0,r4
-
 	mr	r4,r5
 	mr	r5,r6
 	mr	r6,r7
diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c
index 1ac52963e08b..8803c947998e 100644
--- a/arch/powerpc/platforms/pseries/hvconsole.c
+++ b/arch/powerpc/platforms/pseries/hvconsole.c
@@ -25,7 +25,7 @@
  *	firmware.
  * @count: not used?
  */
-int hvc_get_chars(uint32_t vtermno, char *buf, int count)
+ssize_t hvc_get_chars(uint32_t vtermno, u8 *buf, size_t count)
 {
 	long ret;
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(hvc_get_chars);
  *	firmware. Must be at least 16 bytes, even if count is less than 16.
  * @count: Send this number of characters.
  */
-int hvc_put_chars(uint32_t vtermno, const char *buf, int count)
+ssize_t hvc_put_chars(uint32_t vtermno, const u8 *buf, size_t count)
 {
 	unsigned long *lbuf = (unsigned long *) buf;
 	long ret;
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index 44703f13985b..cad2deb7e70d 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -47,6 +47,7 @@
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <asm/ibmebus.h>
 #include <asm/machdep.h>
 
@@ -54,7 +55,7 @@ static struct device ibmebus_bus_device = { /* fake "parent" device */
 	.init_name = "ibmebus",
 };
 
-struct bus_type ibmebus_bus_type;
+const struct bus_type ibmebus_bus_type;
 
 /* These devices will automatically be added to the bus during init */
 static const struct of_device_id ibmebus_matches[] __initconst = {
@@ -85,17 +86,18 @@ static void ibmebus_free_coherent(struct device *dev,
 	kfree(vaddr);
 }
 
-static dma_addr_t ibmebus_map_page(struct device *dev,
-				   struct page *page,
-				   unsigned long offset,
+static dma_addr_t ibmebus_map_phys(struct device *dev, phys_addr_t phys,
 				   size_t size,
 				   enum dma_data_direction direction,
 				   unsigned long attrs)
 {
-	return (dma_addr_t)(page_address(page) + offset);
+	if (attrs & DMA_ATTR_MMIO)
+		return DMA_MAPPING_ERROR;
+
+	return (dma_addr_t)(phys_to_virt(phys));
 }
 
-static void ibmebus_unmap_page(struct device *dev,
+static void ibmebus_unmap_phys(struct device *dev,
 			       dma_addr_t dma_addr,
 			       size_t size,
 			       enum dma_data_direction direction,
@@ -145,8 +147,8 @@ static const struct dma_map_ops ibmebus_dma_ops = {
 	.unmap_sg           = ibmebus_unmap_sg,
 	.dma_supported      = ibmebus_dma_supported,
 	.get_required_mask  = ibmebus_dma_get_required_mask,
-	.map_page           = ibmebus_map_page,
-	.unmap_page         = ibmebus_unmap_page,
+	.map_phys           = ibmebus_map_phys,
+	.unmap_phys         = ibmebus_unmap_phys,
 };
 
 static int ibmebus_match_path(struct device *dev, const void *data)
@@ -338,7 +340,7 @@ static struct attribute *ibmbus_bus_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ibmbus_bus);
 
-static int ibmebus_bus_bus_match(struct device *dev, struct device_driver *drv)
+static int ibmebus_bus_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	const struct of_device_id *matches = drv->of_match_table;
 
@@ -431,7 +433,7 @@ static int ibmebus_bus_modalias(const struct device *dev, struct kobj_uevent_env
 	return of_device_uevent_modalias(dev, env);
 }
 
-struct bus_type ibmebus_bus_type = {
+const struct bus_type ibmebus_bus_type = {
 	.name      = "ibmebus",
 	.uevent    = ibmebus_bus_modalias,
 	.bus_groups = ibmbus_bus_groups,
@@ -460,6 +462,7 @@ static int __init ibmebus_bus_init(void)
 	if (err) {
 		printk(KERN_WARNING "%s: device_register returned %i\n",
 		       __func__, err);
+		put_device(&ibmebus_bus_device);
 		bus_unregister(&ibmebus_bus_type);
 
 		return err;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 7464fa6e4145..eec333dd2e59 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -21,6 +21,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/crash_dump.h>
 #include <linux/memory.h>
+#include <linux/vmalloc.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/iommu.h>
@@ -51,7 +52,8 @@ enum {
 enum {
 	DDW_EXT_SIZE = 0,
 	DDW_EXT_RESET_DMA_WIN = 1,
-	DDW_EXT_QUERY_OUT_SIZE = 2
+	DDW_EXT_QUERY_OUT_SIZE = 2,
+	DDW_EXT_LIMITED_ADDR_MODE = 3
 };
 
 static struct iommu_table *iommu_pseries_alloc_table(int node)
@@ -67,6 +69,10 @@ static struct iommu_table *iommu_pseries_alloc_table(int node)
 	return tbl;
 }
 
+#ifdef CONFIG_IOMMU_API
+static struct iommu_table_group_ops spapr_tce_table_group_ops;
+#endif
+
 static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 {
 	struct iommu_table_group *table_group;
@@ -91,19 +97,24 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 		const char *node_name)
 {
-	struct iommu_table *tbl;
-
 	if (!table_group)
 		return;
 
-	tbl = table_group->tables[0];
 #ifdef CONFIG_IOMMU_API
 	if (table_group->group) {
 		iommu_group_put(table_group->group);
 		BUG_ON(table_group->group);
 	}
 #endif
-	iommu_tce_table_put(tbl);
+
+	/* Default DMA window table is at index 0, while DDW at 1. SR-IOV
+	 * adapters only have table on index 0(if not direct mapped).
+	 */
+	if (table_group->tables[0])
+		iommu_tce_table_put(table_group->tables[0]);
+
+	if (table_group->tables[1])
+		iommu_tce_table_put(table_group->tables[1]);
 
 	kfree(table_group);
 }
@@ -138,7 +149,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
 }
 
 
-static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
+static void tce_clear_pSeries(struct iommu_table *tbl, long index, long npages)
 {
 	__be64 *tcep;
 
@@ -157,6 +168,39 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
 	return be64_to_cpu(*tcep);
 }
 
+#ifdef CONFIG_IOMMU_API
+static long pseries_tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
+{
+	unsigned long cb = ALIGN(sizeof(tbl->it_userspace[0]) * tbl->it_size, PAGE_SIZE);
+	unsigned long *uas;
+
+	if (tbl->it_indirect_levels) /* Impossible */
+		return -EPERM;
+
+	WARN_ON(tbl->it_userspace);
+
+	uas = vzalloc(cb);
+	if (!uas)
+		return -ENOMEM;
+
+	tbl->it_userspace = (__be64 *) uas;
+
+	return 0;
+}
+#endif
+
+static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
+{
+	vfree(tbl->it_userspace);
+	tbl->it_userspace = NULL;
+}
+
+static void tce_free_pSeries(struct iommu_table *tbl)
+{
+	if (tbl->it_userspace)
+		tce_iommu_userspace_view_free(tbl);
+}
+
 static void tce_free_pSeriesLP(unsigned long liobn, long, long, long);
 static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
 
@@ -312,13 +356,22 @@ static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
 static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
 {
 	u64 rc;
+	long rpages = npages;
+	unsigned long limit;
 
 	if (!firmware_has_feature(FW_FEATURE_STUFF_TCE))
 		return tce_free_pSeriesLP(tbl->it_index, tcenum,
 					  tbl->it_page_shift, npages);
 
-	rc = plpar_tce_stuff((u64)tbl->it_index,
-			     (u64)tcenum << tbl->it_page_shift, 0, npages);
+	do {
+		limit = min_t(unsigned long, rpages, 512);
+
+		rc = plpar_tce_stuff((u64)tbl->it_index,
+				     (u64)tcenum << tbl->it_page_shift, 0, limit);
+
+		rpages -= limit;
+		tcenum += limit;
+	} while (rpages > 0 && !rc);
 
 	if (rc && printk_ratelimit()) {
 		printk("tce_freemulti_pSeriesLP: plpar_tce_stuff failed\n");
@@ -358,6 +411,7 @@ struct dynamic_dma_window_prop {
 struct dma_win {
 	struct device_node *device;
 	const struct dynamic_dma_window_prop *prop;
+	bool    direct;
 	struct list_head list;
 };
 
@@ -380,8 +434,6 @@ static LIST_HEAD(dma_win_list);
 static DEFINE_SPINLOCK(dma_win_list_lock);
 /* protects initializing window twice for same device */
 static DEFINE_MUTEX(dma_win_init_mutex);
-#define DIRECT64_PROPNAME "linux,direct64-ddr-window-info"
-#define DMA64_PROPNAME "linux,dma64-ddr-window-info"
 
 static int tce_clearrange_multi_pSeriesLP(unsigned long start_pfn,
 					unsigned long num_pfn, const void *arg)
@@ -561,32 +613,9 @@ static void iommu_table_setparms(struct pci_controller *phb,
 
 struct iommu_table_ops iommu_table_lpar_multi_ops;
 
-/*
- * iommu_table_setparms_lpar
- *
- * Function: On pSeries LPAR systems, return TCE table info, given a pci bus.
- */
-static void iommu_table_setparms_lpar(struct pci_controller *phb,
-				      struct device_node *dn,
-				      struct iommu_table *tbl,
-				      struct iommu_table_group *table_group,
-				      const __be32 *dma_window)
-{
-	unsigned long offset, size, liobn;
-
-	of_parse_dma_window(dn, dma_window, &liobn, &offset, &size);
-
-	iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL,
-				    &iommu_table_lpar_multi_ops);
-
-
-	table_group->tce32_start = offset;
-	table_group->tce32_size = size;
-}
-
 struct iommu_table_ops iommu_table_pseries_ops = {
 	.set = tce_build_pSeries,
-	.clear = tce_free_pSeries,
+	.clear = tce_clear_pSeries,
 	.get = tce_get_pseries
 };
 
@@ -695,42 +724,117 @@ static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
 
 	return rc;
 }
+
+static __be64 *tce_useraddr_pSeriesLP(struct iommu_table *tbl, long index,
+				      bool __always_unused alloc)
+{
+	return tbl->it_userspace ? &tbl->it_userspace[index - tbl->it_offset] : NULL;
+}
 #endif
 
 struct iommu_table_ops iommu_table_lpar_multi_ops = {
 	.set = tce_buildmulti_pSeriesLP,
 #ifdef CONFIG_IOMMU_API
 	.xchg_no_kill = tce_exchange_pseries,
+	.useraddrptr = tce_useraddr_pSeriesLP,
 #endif
 	.clear = tce_freemulti_pSeriesLP,
-	.get = tce_get_pSeriesLP
+	.get = tce_get_pSeriesLP,
+	.free = tce_free_pSeries
 };
 
+#ifdef CONFIG_IOMMU_API
+/*
+ * When the DMA window properties might have been removed,
+ * the parent node has the table_group setup on it.
+ */
+static struct device_node *pci_dma_find_parent_node(struct pci_dev *dev,
+					       struct iommu_table_group *table_group)
+{
+	struct device_node *dn = pci_device_to_OF_node(dev);
+	struct pci_dn *rpdn;
+
+	for (; dn && PCI_DN(dn); dn = dn->parent) {
+		rpdn = PCI_DN(dn);
+
+		if (table_group == rpdn->table_group)
+			return dn;
+	}
+
+	return NULL;
+}
+#endif
+
 /*
  * Find nearest ibm,dma-window (default DMA window) or direct DMA window or
  * dynamic 64bit DMA window, walking up the device tree.
  */
 static struct device_node *pci_dma_find(struct device_node *dn,
-					const __be32 **dma_window)
+					struct dynamic_dma_window_prop *prop)
 {
-	const __be32 *dw = NULL;
+	const __be32 *default_prop = NULL;
+	const __be32 *ddw_prop = NULL;
+	struct device_node *rdn = NULL;
+	bool default_win = false, ddw_win = false;
 
 	for ( ; dn && PCI_DN(dn); dn = dn->parent) {
-		dw = of_get_property(dn, "ibm,dma-window", NULL);
-		if (dw) {
-			if (dma_window)
-				*dma_window = dw;
-			return dn;
+		default_prop = of_get_property(dn, "ibm,dma-window", NULL);
+		if (default_prop) {
+			rdn = dn;
+			default_win = true;
 		}
-		dw = of_get_property(dn, DIRECT64_PROPNAME, NULL);
-		if (dw)
-			return dn;
-		dw = of_get_property(dn, DMA64_PROPNAME, NULL);
-		if (dw)
-			return dn;
+		ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL);
+		if (ddw_prop) {
+			rdn = dn;
+			ddw_win = true;
+			break;
+		}
+		ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL);
+		if (ddw_prop) {
+			rdn = dn;
+			ddw_win = true;
+			break;
+		}
+
+		/* At least found default window, which is the case for normal boot */
+		if (default_win)
+			break;
 	}
 
-	return NULL;
+	/* For PCI devices there will always be a DMA window, either on the device
+	 * or parent bus
+	 */
+	WARN_ON(!(default_win | ddw_win));
+
+	/* caller doesn't want to get DMA window property */
+	if (!prop)
+		return rdn;
+
+	/* parse DMA window property. During normal system boot, only default
+	 * DMA window is passed in OF. But, for kdump, a dedicated adapter might
+	 * have both default and DDW in FDT. In this scenario, DDW takes precedence
+	 * over default window.
+	 */
+	if (ddw_win) {
+		struct dynamic_dma_window_prop *p;
+
+		p = (struct dynamic_dma_window_prop *)ddw_prop;
+		prop->liobn = p->liobn;
+		prop->dma_base = p->dma_base;
+		prop->tce_shift = p->tce_shift;
+		prop->window_shift = p->window_shift;
+	} else if (default_win) {
+		unsigned long offset, size, liobn;
+
+		of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size);
+
+		prop->liobn = cpu_to_be32((u32)liobn);
+		prop->dma_base = cpu_to_be64(offset);
+		prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K);
+		prop->window_shift = cpu_to_be32(order_base_2(size));
+	}
+
+	return rdn;
 }
 
 static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
@@ -738,17 +842,28 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	struct iommu_table *tbl;
 	struct device_node *dn, *pdn;
 	struct pci_dn *ppci;
-	const __be32 *dma_window = NULL;
+	struct dynamic_dma_window_prop prop;
 
 	dn = pci_bus_to_OF_node(bus);
 
 	pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n",
 		 dn);
 
-	pdn = pci_dma_find(dn, &dma_window);
+	pdn = pci_dma_find(dn, &prop);
+
+	/* In PPC architecture, there will always be DMA window on bus or one of the
+	 * parent bus. During reboot, there will be ibm,dma-window property to
+	 * define DMA window. For kdump, there will at least be default window or DDW
+	 * or both.
+	 * There is an exception to the above. In case the PE goes into frozen
+	 * state, firmware may not provide ibm,dma-window property at the time
+	 * of LPAR boot up.
+	 */
 
-	if (dma_window == NULL)
+	if (!pdn) {
 		pr_debug("  no ibm,dma-window property !\n");
+		return;
+	}
 
 	ppci = PCI_DN(pdn);
 
@@ -758,13 +873,17 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	if (!ppci->table_group) {
 		ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
 		tbl = ppci->table_group->tables[0];
-		if (dma_window) {
-			iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
-						  ppci->table_group, dma_window);
 
-			if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
-				panic("Failed to initialize iommu table");
-		}
+		iommu_table_setparms_common(tbl, ppci->phb->bus->number,
+				be32_to_cpu(prop.liobn),
+				be64_to_cpu(prop.dma_base),
+				1ULL << be32_to_cpu(prop.window_shift),
+				be32_to_cpu(prop.tce_shift), NULL,
+				&iommu_table_lpar_multi_ops);
+
+		if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
+			panic("Failed to initialize iommu table");
+
 		iommu_register_group(ppci->table_group,
 				pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->table_group);
@@ -860,7 +979,7 @@ static void __remove_dma_window(struct device_node *np, u32 *ddw_avail, u64 liob
 }
 
 static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
-			      struct property *win)
+			      struct property *win, bool cleanup)
 {
 	struct dynamic_dma_window_prop *dwp;
 	u64 liobn;
@@ -868,11 +987,44 @@ static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
 	dwp = win->value;
 	liobn = (u64)be32_to_cpu(dwp->liobn);
 
-	clean_dma_window(np, dwp);
+	if (cleanup)
+		clean_dma_window(np, dwp);
 	__remove_dma_window(np, ddw_avail, liobn);
 }
 
-static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_name)
+static void copy_property(struct device_node *pdn, const char *from, const char *to)
+{
+	struct property *src, *dst;
+
+	src = of_find_property(pdn, from, NULL);
+	if (!src)
+		return;
+
+	dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+	if (!dst)
+		return;
+
+	dst->name = kstrdup(to, GFP_KERNEL);
+	dst->value = kmemdup(src->value, src->length, GFP_KERNEL);
+	dst->length = src->length;
+	if (!dst->name || !dst->value)
+		return;
+
+	if (of_add_property(pdn, dst)) {
+		pr_err("Unable to add DMA window property for %pOF", pdn);
+		goto free_prop;
+	}
+
+	return;
+
+free_prop:
+	kfree(dst->name);
+	kfree(dst->value);
+	kfree(dst);
+}
+
+static int remove_dma_window_named(struct device_node *np, bool remove_prop, const char *win_name,
+				   bool cleanup)
 {
 	struct property *win;
 	u32 ddw_avail[DDW_APPLICABLE_SIZE];
@@ -887,13 +1039,20 @@ static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_
 	if (ret)
 		return 0;
 
-
 	if (win->length >= sizeof(struct dynamic_dma_window_prop))
-		remove_dma_window(np, ddw_avail, win);
+		remove_dma_window(np, ddw_avail, win, cleanup);
 
 	if (!remove_prop)
 		return 0;
 
+	/* Default window property if removed is lost as reset-pe doesn't restore it.
+	 * Though FDT has a copy of it, the DLPAR hotplugged devices will not have a
+	 * node on FDT until next reboot. So, back it up.
+	 */
+	if ((strcmp(win_name, "ibm,dma-window") == 0) &&
+	    !of_find_property(np, "ibm,dma-window-saved", NULL))
+		copy_property(np, win_name, "ibm,dma-window-saved");
+
 	ret = of_remove_property(np, win);
 	if (ret)
 		pr_warn("%pOF: failed to remove DMA window property: %d\n",
@@ -901,7 +1060,8 @@ static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_
 	return 0;
 }
 
-static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift)
+static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift,
+			      bool *direct_mapping)
 {
 	struct dma_win *window;
 	const struct dynamic_dma_window_prop *dma64;
@@ -914,6 +1074,7 @@ static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *windo
 			dma64 = window->prop;
 			*dma_addr = be64_to_cpu(dma64->dma_base);
 			*window_shift = be32_to_cpu(dma64->window_shift);
+			*direct_mapping = window->direct;
 			found = true;
 			break;
 		}
@@ -934,6 +1095,7 @@ static struct dma_win *ddw_list_new_entry(struct device_node *pdn,
 
 	window->device = pdn;
 	window->prop = dma64;
+	window->direct = false;
 
 	return window;
 }
@@ -948,10 +1110,16 @@ static void find_existing_ddw_windows_named(const char *name)
 	for_each_node_with_property(pdn, name) {
 		dma64 = of_get_property(pdn, name, &len);
 		if (!dma64 || len < sizeof(*dma64)) {
-			remove_ddw(pdn, true, name);
+			remove_dma_window_named(pdn, true, name, true);
 			continue;
 		}
 
+		/* If at the time of system initialization, there are DDWs in OF,
+		 * it means this is during kexec. DDW could be direct or dynamic.
+		 * We will just mark DDWs as "dynamic" since this is kdump path,
+		 * no need to worry about perforance. ddw_list_new_entry() will
+		 * set window->direct = false.
+		 */
 		window = ddw_list_new_entry(pdn, dma64);
 		if (!window) {
 			of_node_put(pdn);
@@ -1117,17 +1285,13 @@ static LIST_HEAD(failed_ddw_pdn_list);
 
 static phys_addr_t ddw_memory_hotplug_max(void)
 {
-	resource_size_t max_addr = memory_hotplug_max();
-	struct device_node *memory;
-
-	for_each_node_by_type(memory, "memory") {
-		struct resource res;
-
-		if (of_address_to_resource(memory, 0, &res))
-			continue;
+	resource_size_t max_addr;
 
-		max_addr = max_t(resource_size_t, max_addr, res.end + 1);
-	}
+#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
+	max_addr = hot_add_drconf_memory_max();
+#else
+	max_addr = memblock_end_of_DRAM();
+#endif
 
 	return max_addr;
 }
@@ -1164,6 +1328,54 @@ static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
 			 ret);
 }
 
+/*
+ * Platforms support placing PHB in limited address mode starting with LoPAR
+ * level 2.13 implement. In this mode, the DMA address returned by DDW is over
+ * 4GB but, less than 64-bits. This benefits IO adapters that don't support
+ * 64-bits for DMA addresses.
+ */
+static int limited_dma_window(struct pci_dev *dev, struct device_node *par_dn)
+{
+	int ret;
+	u32 cfg_addr, reset_dma_win, las_supported;
+	u64 buid;
+	struct device_node *dn;
+	struct pci_dn *pdn;
+
+	ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win);
+	if (ret)
+		goto out;
+
+	ret = ddw_read_ext(par_dn, DDW_EXT_LIMITED_ADDR_MODE, &las_supported);
+
+	/* Limited Address Space extension available on the platform but DDW in
+	 * limited addressing mode not supported
+	 */
+	if (!ret && !las_supported)
+		ret = -EPROTO;
+
+	if (ret) {
+		dev_info(&dev->dev, "Limited Address Space for DDW not Supported, err: %d", ret);
+		goto out;
+	}
+
+	dn = pci_device_to_OF_node(dev);
+	pdn = PCI_DN(dn);
+	buid = pdn->phb->buid;
+	cfg_addr = (pdn->busno << 16) | (pdn->devfn << 8);
+
+	ret = rtas_call(reset_dma_win, 4, 1, NULL, cfg_addr, BUID_HI(buid),
+			BUID_LO(buid), 1);
+	if (ret)
+		dev_info(&dev->dev,
+			 "ibm,reset-pe-dma-windows(%x) for Limited Addr Support: %x %x %x returned %d ",
+			 reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid),
+			 ret);
+
+out:
+	return ret;
+}
+
 /* Return largest page shift based on "IO Page Sizes" output of ibm,query-pe-dma-window. */
 static int iommu_get_page_shift(u32 query_page_size)
 {
@@ -1231,14 +1443,14 @@ static struct property *ddw_property_create(const char *propname, u32 liobn, u64
  *
  * returns true if can map all pages (direct mapping), false otherwise..
  */
-static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
+static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn, u64 dma_mask)
 {
 	int len = 0, ret;
 	int max_ram_len = order_base_2(ddw_memory_hotplug_max());
 	struct ddw_query_response query;
 	struct ddw_create_response create;
 	int page_shift;
-	u64 win_addr;
+	u64 win_addr, dynamic_offset = 0;
 	const char *win_name;
 	struct device_node *dn;
 	u32 ddw_avail[DDW_APPLICABLE_SIZE];
@@ -1246,9 +1458,13 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	struct property *win64;
 	struct failed_ddw_pdn *fpdn;
 	bool default_win_removed = false, direct_mapping = false;
+	bool dynamic_mapping = false;
 	bool pmem_present;
 	struct pci_dn *pci = PCI_DN(pdn);
 	struct property *default_win = NULL;
+	bool limited_addr_req = false, limited_addr_enabled = false;
+	int dev_max_ddw;
+	int ddw_sz;
 
 	dn = of_find_node_by_type(NULL, "ibm,pmemory");
 	pmem_present = dn != NULL;
@@ -1256,10 +1472,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 
 	mutex_lock(&dma_win_init_mutex);
 
-	if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) {
-		direct_mapping = (len >= max_ram_len);
+	if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len, &direct_mapping))
 		goto out_unlock;
-	}
 
 	/*
 	 * If we already went through this for a previous function of
@@ -1277,7 +1491,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * the ibm,ddw-applicable property holds the tokens for:
 	 * ibm,query-pe-dma-window
 	 * ibm,create-pe-dma-window
-	 * ibm,remove-pe-dma-window
 	 * for the given node in that order.
 	 * the property is actually in the parent, not the PE
 	 */
@@ -1297,6 +1510,20 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	if (ret != 0)
 		goto out_failed;
 
+	/* DMA Limited Addressing required? This is when the driver has
+	 * requested to create DDW but supports mask which is less than 64-bits
+	 */
+	limited_addr_req = (dma_mask != DMA_BIT_MASK(64));
+
+	/* place the PHB in Limited Addressing mode */
+	if (limited_addr_req) {
+		if (limited_dma_window(dev, pdn))
+			goto out_failed;
+
+		/* PHB is in Limited address mode */
+		limited_addr_enabled = true;
+	}
+
 	/*
 	 * If there is no window available, remove the default DMA window,
 	 * if it's present. This will make all the resources available to the
@@ -1321,7 +1548,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		if (reset_win_ext)
 			goto out_failed;
 
-		remove_dma_window(pdn, ddw_avail, default_win);
+		remove_dma_window(pdn, ddw_avail, default_win, true);
 		default_win_removed = true;
 
 		/* Query again, to check if the window is available */
@@ -1343,6 +1570,14 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		goto out_failed;
 	}
 
+	/* Maximum DMA window size that the device can address (in log2) */
+	dev_max_ddw = fls64(dma_mask);
+
+	/* If the device DMA mask is less than 64-bits, make sure the DMA window
+	 * size is not bigger than what the device can access
+	 */
+	ddw_sz = min(order_base_2(query.largest_available_block << page_shift),
+			dev_max_ddw);
 
 	/*
 	 * The "ibm,pmemory" can appear anywhere in the address space.
@@ -1352,30 +1587,56 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 */
 	len = max_ram_len;
 	if (pmem_present) {
-		if (query.largest_available_block >=
-		    (1ULL << (MAX_PHYSMEM_BITS - page_shift)))
+		if (ddw_sz >= MAX_PHYSMEM_BITS)
 			len = MAX_PHYSMEM_BITS;
 		else
 			dev_info(&dev->dev, "Skipping ibm,pmemory");
 	}
 
 	/* check if the available block * number of ptes will map everything */
-	if (query.largest_available_block < (1ULL << (len - page_shift))) {
+	if (ddw_sz < len) {
 		dev_dbg(&dev->dev,
 			"can't map partition max 0x%llx with %llu %llu-sized pages\n",
 			1ULL << len,
 			query.largest_available_block,
 			1ULL << page_shift);
 
-		len = order_base_2(query.largest_available_block << page_shift);
-		win_name = DMA64_PROPNAME;
+		len = ddw_sz;
+		dynamic_mapping = true;
 	} else {
 		direct_mapping = !default_win_removed ||
 			(len == MAX_PHYSMEM_BITS) ||
 			(!pmem_present && (len == max_ram_len));
-		win_name = direct_mapping ? DIRECT64_PROPNAME : DMA64_PROPNAME;
+
+		/* DDW is big enough to direct map RAM. If there is vPMEM, check
+		 * if enough space is left in DDW where we can dynamically
+		 * allocate TCEs for vPMEM. For now, this Hybrid sharing of DDW
+		 * is only for SR-IOV devices.
+		 */
+		if (default_win_removed && pmem_present && !direct_mapping) {
+			/* DDW is big enough to be split */
+			if ((1ULL << ddw_sz) >=
+			    MIN_DDW_VPMEM_DMA_WINDOW + (1ULL << max_ram_len)) {
+
+				direct_mapping = true;
+
+				/* offset of the Dynamic part of DDW */
+				dynamic_offset = 1ULL << max_ram_len;
+			}
+
+			/* DDW will at least have dynamic allocation */
+			dynamic_mapping = true;
+
+			/* create max size DDW possible */
+			len = ddw_sz;
+		}
 	}
 
+	/* Even if the DDW is split into both direct mapped RAM and dynamically
+	 * mapped vPMEM, the DDW property in OF will be marked as Direct.
+	 */
+	win_name = direct_mapping ? DIRECT64_PROPNAME : DMA64_PROPNAME;
+
 	ret = create_ddw(dev, ddw_avail, &create, page_shift, len);
 	if (ret != 0)
 		goto out_failed;
@@ -1403,9 +1664,11 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	if (!window)
 		goto out_del_prop;
 
+	window->direct = direct_mapping;
+
 	if (direct_mapping) {
 		/* DDW maps the whole partition, so enable direct DMA mapping */
-		ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
+		ret = walk_system_ram_range(0, ddw_memory_hotplug_max() >> PAGE_SHIFT,
 					    win64->value, tce_setrange_multi_pSeriesLP_walk);
 		if (ret) {
 			dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n",
@@ -1415,10 +1678,18 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 			clean_dma_window(pdn, win64->value);
 			goto out_del_list;
 		}
-	} else {
+		if (default_win_removed) {
+			iommu_tce_table_put(pci->table_group->tables[0]);
+			pci->table_group->tables[0] = NULL;
+			set_iommu_table_base(&dev->dev, NULL);
+		}
+	}
+
+	if (dynamic_mapping) {
 		struct iommu_table *newtbl;
 		int i;
 		unsigned long start = 0, end = 0;
+		u64 dynamic_addr, dynamic_len;
 
 		for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
 			const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
@@ -1438,20 +1709,27 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 			goto out_del_list;
 		}
 
-		iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr,
-					    1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
-		iommu_init_table(newtbl, pci->phb->node, start, end);
+		/* If the DDW is split between directly mapped RAM and Dynamic
+		 * mapped for TCES, offset into the DDW where the dynamic part
+		 * begins.
+		 */
+		dynamic_addr = win_addr + dynamic_offset;
+		dynamic_len = (1UL << len) - dynamic_offset;
+		iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn,
+					    dynamic_addr, dynamic_len, page_shift, NULL,
+					    &iommu_table_lpar_multi_ops);
+		iommu_init_table(newtbl, pci->phb->node,
+				 start >> page_shift, end >> page_shift);
 
-		pci->table_group->tables[1] = newtbl;
+		pci->table_group->tables[default_win_removed ? 0 : 1] = newtbl;
 
 		set_iommu_table_base(&dev->dev, newtbl);
 	}
 
 	if (default_win_removed) {
-		iommu_tce_table_put(pci->table_group->tables[0]);
-		pci->table_group->tables[0] = NULL;
-
 		/* default_win is valid here because default_win_removed == true */
+		if (!of_find_property(pdn, "ibm,dma-window-saved", NULL))
+			copy_property(pdn, "ibm,dma-window", "ibm,dma-window-saved");
 		of_remove_property(pdn, default_win);
 		dev_info(&dev->dev, "Removed default DMA window for %pOF\n", pdn);
 	}
@@ -1479,7 +1757,7 @@ out_remove_win:
 	__remove_dma_window(pdn, ddw_avail, create.liobn);
 
 out_failed:
-	if (default_win_removed)
+	if (default_win_removed || limited_addr_enabled)
 		reset_dma_window(dev, pdn);
 
 	fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
@@ -1491,23 +1769,90 @@ out_failed:
 out_unlock:
 	mutex_unlock(&dma_win_init_mutex);
 
-	/*
-	 * If we have persistent memory and the window size is only as big
-	 * as RAM, then we failed to create a window to cover persistent
-	 * memory and need to set the DMA limit.
+	/* If we have persistent memory and the window size is not big enough
+	 * to directly map both RAM and vPMEM, then we need to set DMA limit.
 	 */
-	if (pmem_present && direct_mapping && len == max_ram_len)
-		dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len);
+	if (pmem_present && direct_mapping && len != MAX_PHYSMEM_BITS)
+		dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset +
+						(1ULL << max_ram_len);
+
+	dev_info(&dev->dev, "lsa_required: %x, lsa_enabled: %x, direct mapping: %x\n",
+			limited_addr_req, limited_addr_enabled, direct_mapping);
 
 	return direct_mapping;
 }
 
+static __u64 query_page_size_to_mask(u32 query_page_size)
+{
+	const long shift[] = {
+		(SZ_4K),   (SZ_64K), (SZ_16M),
+		(SZ_32M),  (SZ_64M), (SZ_128M),
+		(SZ_256M), (SZ_16G), (SZ_2M)
+	};
+	int i, ret = 0;
+
+	for (i = 0; i < ARRAY_SIZE(shift); i++) {
+		if (query_page_size & (1 << i))
+			ret |= shift[i];
+	}
+
+	return ret;
+}
+
+static void spapr_tce_init_table_group(struct pci_dev *pdev,
+				       struct device_node *pdn,
+				       struct dynamic_dma_window_prop prop)
+{
+	struct iommu_table_group  *table_group = PCI_DN(pdn)->table_group;
+	u32 ddw_avail[DDW_APPLICABLE_SIZE];
+
+	struct ddw_query_response query;
+	int ret;
+
+	/* Only for normal boot with default window. Doesn't matter during
+	 * kdump, since these will not be used during kdump.
+	 */
+	if (is_kdump_kernel())
+		return;
+
+	if (table_group->max_dynamic_windows_supported != 0)
+		return; /* already initialized */
+
+	table_group->tce32_start = be64_to_cpu(prop.dma_base);
+	table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
+
+	if (!of_find_property(pdn, "ibm,dma-window", NULL))
+		dev_err(&pdev->dev, "default dma window missing!\n");
+
+	ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
+			&ddw_avail[0], DDW_APPLICABLE_SIZE);
+	if (ret) {
+		table_group->max_dynamic_windows_supported = -1;
+		return;
+	}
+
+	ret = query_ddw(pdev, ddw_avail, &query, pdn);
+	if (ret) {
+		dev_err(&pdev->dev, "%s: query_ddw failed\n", __func__);
+		table_group->max_dynamic_windows_supported = -1;
+		return;
+	}
+
+	if (query.windows_available == 0)
+		table_group->max_dynamic_windows_supported = 1;
+	else
+		table_group->max_dynamic_windows_supported = IOMMU_TABLE_GROUP_MAX_TABLES;
+
+	table_group->max_levels = 1;
+	table_group->pgsizes |= query_page_size_to_mask(query.page_size);
+}
+
 static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 {
 	struct device_node *pdn, *dn;
 	struct iommu_table *tbl;
-	const __be32 *dma_window = NULL;
 	struct pci_dn *pci;
+	struct dynamic_dma_window_prop prop;
 
 	pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
 
@@ -1520,7 +1865,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	dn = pci_device_to_OF_node(dev);
 	pr_debug("  node is %pOF\n", dn);
 
-	pdn = pci_dma_find(dn, &dma_window);
+	pdn = pci_dma_find(dn, &prop);
 	if (!pdn || !PCI_DN(pdn)) {
 		printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: "
 		       "no DMA window found for pci dev=%s dn=%pOF\n",
@@ -1533,8 +1878,13 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	if (!pci->table_group) {
 		pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
 		tbl = pci->table_group->tables[0];
-		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
-				pci->table_group, dma_window);
+
+		iommu_table_setparms_common(tbl, pci->phb->bus->number,
+				be32_to_cpu(prop.liobn),
+				be64_to_cpu(prop.dma_base),
+				1ULL << be32_to_cpu(prop.window_shift),
+				be32_to_cpu(prop.tce_shift), NULL,
+				&iommu_table_lpar_multi_ops);
 
 		iommu_init_table(tbl, pci->phb->node, 0, 0);
 		iommu_register_group(pci->table_group,
@@ -1544,6 +1894,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 		pr_debug("  found DMA window, table: %p\n", pci->table_group);
 	}
 
+	spapr_tce_init_table_group(dev, pdn, prop);
+
 	set_iommu_table_base(&dev->dev, pci->table_group->tables[0]);
 	iommu_add_device(pci->table_group, &dev->dev);
 }
@@ -1552,8 +1904,11 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 {
 	struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
 
-	/* only attempt to use a new window if 64-bit DMA is requested */
-	if (dma_mask < DMA_BIT_MASK(64))
+	/* For DDW, DMA mask should be more than 32-bits. For mask more then
+	 * 32-bits but less then 64-bits, DMA addressing is supported in
+	 * Limited Addressing mode.
+	 */
+	if (dma_mask <= DMA_BIT_MASK(32))
 		return false;
 
 	dev_dbg(&pdev->dev, "node is %pOF\n", dn);
@@ -1566,11 +1921,501 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 	 */
 	pdn = pci_dma_find(dn, NULL);
 	if (pdn && PCI_DN(pdn))
-		return enable_ddw(pdev, pdn);
+		return enable_ddw(pdev, pdn, dma_mask);
+
+	return false;
+}
+
+#ifdef CONFIG_IOMMU_API
+/*
+ * A simple iommu_table_group_ops which only allows reusing the existing
+ * iommu_table. This handles VFIO for POWER7 or the nested KVM.
+ * The ops does not allow creating windows and only allows reusing the existing
+ * one if it matches table_group->tce32_start/tce32_size/page_shift.
+ */
+static unsigned long spapr_tce_get_table_size(__u32 page_shift,
+					      __u64 window_size, __u32 levels)
+{
+	unsigned long size;
+
+	if (levels > 1)
+		return ~0U;
+	size = window_size >> (page_shift - 3);
+	return size;
+}
+
+static struct pci_dev *iommu_group_get_first_pci_dev(struct iommu_group *group)
+{
+	struct pci_dev *pdev = NULL;
+	int ret;
+
+	/* No IOMMU group ? */
+	if (!group)
+		return NULL;
+
+	ret = iommu_group_for_each_dev(group, &pdev, dev_has_iommu_table);
+	if (!ret || !pdev)
+		return NULL;
+	return pdev;
+}
+
+static void restore_default_dma_window(struct pci_dev *pdev, struct device_node *pdn)
+{
+	reset_dma_window(pdev, pdn);
+	copy_property(pdn, "ibm,dma-window-saved", "ibm,dma-window");
+}
+
+static long remove_dynamic_dma_windows(struct pci_dev *pdev, struct device_node *pdn)
+{
+	struct pci_dn *pci = PCI_DN(pdn);
+	struct dma_win *window;
+	bool direct_mapping;
+	int len;
+
+	if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len, &direct_mapping)) {
+		remove_dma_window_named(pdn, true, direct_mapping ?
+						   DIRECT64_PROPNAME : DMA64_PROPNAME, true);
+		if (!direct_mapping) {
+			WARN_ON(!pci->table_group->tables[0] && !pci->table_group->tables[1]);
+
+			if (pci->table_group->tables[1]) {
+				iommu_tce_table_put(pci->table_group->tables[1]);
+				pci->table_group->tables[1] = NULL;
+			} else if (pci->table_group->tables[0]) {
+				/* Default window was removed and only the DDW exists */
+				iommu_tce_table_put(pci->table_group->tables[0]);
+				pci->table_group->tables[0] = NULL;
+			}
+		}
+		spin_lock(&dma_win_list_lock);
+		list_for_each_entry(window, &dma_win_list, list) {
+			if (window->device == pdn) {
+				list_del(&window->list);
+				kfree(window);
+				break;
+			}
+		}
+		spin_unlock(&dma_win_list_lock);
+	}
+
+	return 0;
+}
+
+static long pseries_setup_default_iommu_config(struct iommu_table_group *table_group,
+					       struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	const __be32 *default_prop;
+	long liobn, offset, size;
+	struct device_node *pdn;
+	struct iommu_table *tbl;
+	struct pci_dn *pci;
+
+	pdn = pci_dma_find_parent_node(pdev, table_group);
+	if (!pdn || !PCI_DN(pdn)) {
+		dev_warn(&pdev->dev, "No table_group configured for the node %pOF\n", pdn);
+		return -1;
+	}
+	pci = PCI_DN(pdn);
+
+	/* The default window is restored if not present already on removal of DDW.
+	 * However, if used by VFIO SPAPR sub driver, the user's order of removal of
+	 * windows might have been different to not leading to auto restoration,
+	 * suppose the DDW was removed first followed by the default one.
+	 * So, restore the default window with reset-pe-dma call explicitly.
+	 */
+	restore_default_dma_window(pdev, pdn);
+
+	default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
+	of_parse_dma_window(pdn, default_prop, &liobn, &offset, &size);
+	tbl = iommu_pseries_alloc_table(pci->phb->node);
+	if (!tbl) {
+		dev_err(&pdev->dev, "couldn't create new IOMMU table\n");
+		return -1;
+	}
+
+	iommu_table_setparms_common(tbl, pci->phb->bus->number, liobn, offset,
+				    size, IOMMU_PAGE_SHIFT_4K, NULL,
+				    &iommu_table_lpar_multi_ops);
+	iommu_init_table(tbl, pci->phb->node, 0, 0);
+
+	pci->table_group->tables[0] = tbl;
+	set_iommu_table_base(&pdev->dev, tbl);
+
+	return 0;
+}
+
+static bool is_default_window_request(struct iommu_table_group *table_group, __u32 page_shift,
+				      __u64 window_size)
+{
+	if ((window_size <= table_group->tce32_size) &&
+	    (page_shift == IOMMU_PAGE_SHIFT_4K))
+		return true;
 
 	return false;
 }
 
+static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
+				   __u32 page_shift, __u64 window_size, __u32 levels,
+				   struct iommu_table **ptbl)
+{
+	struct pci_dev *pdev = iommu_group_get_first_pci_dev(table_group->group);
+	u32 ddw_avail[DDW_APPLICABLE_SIZE];
+	struct ddw_create_response create;
+	unsigned long liobn, offset, size;
+	unsigned long start = 0, end = 0;
+	struct ddw_query_response query;
+	const __be32 *default_prop;
+	struct failed_ddw_pdn *fpdn;
+	unsigned int window_shift;
+	struct device_node *pdn;
+	struct iommu_table *tbl;
+	struct dma_win *window;
+	struct property *win64;
+	struct pci_dn *pci;
+	u64 win_addr;
+	int len, i;
+	long ret;
+
+	if (!is_power_of_2(window_size) || levels > 1)
+		return -EINVAL;
+
+	window_shift = order_base_2(window_size);
+
+	mutex_lock(&dma_win_init_mutex);
+
+	ret = -ENODEV;
+
+	pdn = pci_dma_find_parent_node(pdev, table_group);
+	if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
+		dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
+		goto out_failed;
+	}
+	pci = PCI_DN(pdn);
+
+	/* If the enable DDW failed for the pdn, dont retry! */
+	list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) {
+		if (fpdn->pdn == pdn) {
+			dev_info(&pdev->dev, "%pOF in failed DDW device list\n", pdn);
+			goto out_unlock;
+		}
+	}
+
+	tbl = iommu_pseries_alloc_table(pci->phb->node);
+	if (!tbl) {
+		dev_dbg(&pdev->dev, "couldn't create new IOMMU table\n");
+		goto out_unlock;
+	}
+
+	if (num == 0) {
+		bool direct_mapping;
+		/* The request is not for default window? Ensure there is no DDW window already */
+		if (!is_default_window_request(table_group, page_shift, window_size)) {
+			if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
+					      &direct_mapping)) {
+				dev_warn(&pdev->dev, "%pOF: 64-bit window already present.", pdn);
+				ret = -EPERM;
+				goto out_unlock;
+			}
+		} else {
+			/* Request is for Default window, ensure there is no DDW if there is a
+			 * need to reset. reset-pe otherwise removes the DDW also
+			 */
+			default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
+			if (!default_prop) {
+				if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
+						      &direct_mapping)) {
+					dev_warn(&pdev->dev, "%pOF: Attempt to create window#0 when 64-bit window is present. Preventing the attempt as that would destroy the 64-bit window",
+						 pdn);
+					ret = -EPERM;
+					goto out_unlock;
+				}
+
+				restore_default_dma_window(pdev, pdn);
+
+				default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
+				of_parse_dma_window(pdn, default_prop, &liobn, &offset, &size);
+				/* Limit the default window size to window_size */
+				iommu_table_setparms_common(tbl, pci->phb->bus->number, liobn,
+							    offset, 1UL << window_shift,
+							    IOMMU_PAGE_SHIFT_4K, NULL,
+							    &iommu_table_lpar_multi_ops);
+				iommu_init_table(tbl, pci->phb->node,
+						 start >> IOMMU_PAGE_SHIFT_4K,
+						 end >> IOMMU_PAGE_SHIFT_4K);
+
+				table_group->tables[0] = tbl;
+
+				mutex_unlock(&dma_win_init_mutex);
+
+				goto exit;
+			}
+		}
+	}
+
+	ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
+				&ddw_avail[0], DDW_APPLICABLE_SIZE);
+	if (ret) {
+		dev_info(&pdev->dev, "ibm,ddw-applicable not found\n");
+		goto out_failed;
+	}
+	ret = -ENODEV;
+
+	pr_err("%s: Calling query %pOF\n", __func__, pdn);
+	ret = query_ddw(pdev, ddw_avail, &query, pdn);
+	if (ret)
+		goto out_failed;
+	ret = -ENODEV;
+
+	len = window_shift;
+	if (query.largest_available_block < (1ULL << (len - page_shift))) {
+		dev_dbg(&pdev->dev, "can't map window 0x%llx with %llu %llu-sized pages\n",
+				1ULL << len, query.largest_available_block,
+				1ULL << page_shift);
+		ret = -EINVAL; /* Retry with smaller window size */
+		goto out_unlock;
+	}
+
+	if (create_ddw(pdev, ddw_avail, &create, page_shift, len)) {
+		pr_err("%s: Create ddw failed %pOF\n", __func__, pdn);
+		goto out_failed;
+	}
+
+	win_addr = ((u64)create.addr_hi << 32) | create.addr_lo;
+	win64 = ddw_property_create(DMA64_PROPNAME, create.liobn, win_addr, page_shift, len);
+	if (!win64)
+		goto remove_window;
+
+	ret = of_add_property(pdn, win64);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to add DMA window property for %pOF: %ld", pdn, ret);
+		goto free_property;
+	}
+	ret = -ENODEV;
+
+	window = ddw_list_new_entry(pdn, win64->value);
+	if (!window)
+		goto remove_property;
+
+	window->direct = false;
+
+	for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
+		const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
+
+		/* Look for MMIO32 */
+		if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
+			start = pci->phb->mem_resources[i].start;
+			end = pci->phb->mem_resources[i].end;
+				break;
+		}
+	}
+
+	/* New table for using DDW instead of the default DMA window */
+	iommu_table_setparms_common(tbl, pci->phb->bus->number, create.liobn, win_addr,
+				    1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
+	iommu_init_table(tbl, pci->phb->node, start >> page_shift, end >> page_shift);
+
+	pci->table_group->tables[num] = tbl;
+	set_iommu_table_base(&pdev->dev, tbl);
+	pdev->dev.archdata.dma_offset = win_addr;
+
+	spin_lock(&dma_win_list_lock);
+	list_add(&window->list, &dma_win_list);
+	spin_unlock(&dma_win_list_lock);
+
+	mutex_unlock(&dma_win_init_mutex);
+
+	goto exit;
+
+remove_property:
+	of_remove_property(pdn, win64);
+free_property:
+	kfree(win64->name);
+	kfree(win64->value);
+	kfree(win64);
+remove_window:
+	__remove_dma_window(pdn, ddw_avail, create.liobn);
+
+out_failed:
+	fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
+	if (!fpdn)
+		goto out_unlock;
+	fpdn->pdn = pdn;
+	list_add(&fpdn->list, &failed_ddw_pdn_list);
+
+out_unlock:
+	mutex_unlock(&dma_win_init_mutex);
+
+	return ret;
+exit:
+	/* Allocate the userspace view */
+	pseries_tce_iommu_userspace_view_alloc(tbl);
+	tbl->it_allocated_size = spapr_tce_get_table_size(page_shift, window_size, levels);
+
+	*ptbl = iommu_tce_table_get(tbl);
+
+	return 0;
+}
+
+static bool is_default_window_table(struct iommu_table_group *table_group, struct iommu_table *tbl)
+{
+	if (((tbl->it_size << tbl->it_page_shift)  <= table_group->tce32_size) &&
+	    (tbl->it_page_shift == IOMMU_PAGE_SHIFT_4K))
+		return true;
+
+	return false;
+}
+
+static long spapr_tce_set_window(struct iommu_table_group *table_group,
+				 int num, struct iommu_table *tbl)
+{
+	return tbl == table_group->tables[num] ? 0 : -EPERM;
+}
+
+static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
+{
+	struct pci_dev *pdev = iommu_group_get_first_pci_dev(table_group->group);
+	struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
+	struct iommu_table *tbl = table_group->tables[num];
+	struct failed_ddw_pdn *fpdn;
+	struct dma_win *window;
+	const char *win_name;
+	int ret = -ENODEV;
+
+	if (!tbl) /* The table was never created OR window was never opened */
+		return 0;
+
+	mutex_lock(&dma_win_init_mutex);
+
+	if ((num == 0) && is_default_window_table(table_group, tbl))
+		win_name = "ibm,dma-window";
+	else
+		win_name = DMA64_PROPNAME;
+
+	pdn = pci_dma_find(dn, NULL);
+	if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
+		dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
+		goto out_failed;
+	}
+
+	/* Dont clear the TCEs, User should have done it */
+	if (remove_dma_window_named(pdn, true, win_name, false)) {
+		pr_err("%s: The existing DDW removal failed for node %pOF\n", __func__, pdn);
+		goto out_failed; /* Could not remove it either! */
+	}
+
+	if (strcmp(win_name, DMA64_PROPNAME) == 0) {
+		spin_lock(&dma_win_list_lock);
+		list_for_each_entry(window, &dma_win_list, list) {
+			if (window->device == pdn) {
+				list_del(&window->list);
+				kfree(window);
+				break;
+			}
+		}
+		spin_unlock(&dma_win_list_lock);
+	}
+
+	iommu_tce_table_put(table_group->tables[num]);
+	table_group->tables[num] = NULL;
+
+	ret = 0;
+
+	goto out_unlock;
+
+out_failed:
+	fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
+	if (!fpdn)
+		goto out_unlock;
+	fpdn->pdn = pdn;
+	list_add(&fpdn->list, &failed_ddw_pdn_list);
+
+out_unlock:
+	mutex_unlock(&dma_win_init_mutex);
+
+	return ret;
+}
+
+static long spapr_tce_take_ownership(struct iommu_table_group *table_group, struct device *dev)
+{
+	struct iommu_table *tbl = table_group->tables[0];
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct device_node *dn = pci_device_to_OF_node(pdev);
+	struct device_node *pdn;
+
+	/* SRIOV VFs using direct map by the host driver OR multifunction devices
+	 * where the ownership was taken on the attempt by the first function
+	 */
+	if (!tbl && (table_group->max_dynamic_windows_supported != 1))
+		return 0;
+
+	mutex_lock(&dma_win_init_mutex);
+
+	pdn = pci_dma_find(dn, NULL);
+	if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
+		dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
+		mutex_unlock(&dma_win_init_mutex);
+		return -1;
+	}
+
+	/*
+	 * Though rtas call reset-pe removes the DDW, it doesn't clear the entries on the table
+	 * if there are any. In case of direct map, the entries will be left over, which
+	 * is fine for PEs with 2 DMA windows where the second window is created with create-pe
+	 * at which point the table is cleared. However, on VFs having only one DMA window, the
+	 * default window would end up seeing the entries left over from the direct map done
+	 * on the second window. So, remove the ddw explicitly so that clean_dma_window()
+	 * cleans up the entries if any.
+	 */
+	if (remove_dynamic_dma_windows(pdev, pdn)) {
+		dev_warn(&pdev->dev, "The existing DDW removal failed for node %pOF\n", pdn);
+		mutex_unlock(&dma_win_init_mutex);
+		return -1;
+	}
+
+	/* The table_group->tables[0] is not null now, it must be the default window
+	 * Remove it, let the userspace create it as it needs.
+	 */
+	if (table_group->tables[0]) {
+		remove_dma_window_named(pdn, true, "ibm,dma-window", true);
+		iommu_tce_table_put(tbl);
+		table_group->tables[0] = NULL;
+	}
+	set_iommu_table_base(dev, NULL);
+
+	mutex_unlock(&dma_win_init_mutex);
+
+	return 0;
+}
+
+static void spapr_tce_release_ownership(struct iommu_table_group *table_group, struct device *dev)
+{
+	struct iommu_table *tbl = table_group->tables[0];
+
+	if (tbl) { /* Default window already restored */
+		return;
+	}
+
+	mutex_lock(&dma_win_init_mutex);
+
+	/* Restore the default window */
+	pseries_setup_default_iommu_config(table_group, dev);
+
+	mutex_unlock(&dma_win_init_mutex);
+
+	return;
+}
+
+static struct iommu_table_group_ops spapr_tce_table_group_ops = {
+	.get_table_size = spapr_tce_get_table_size,
+	.create_table = spapr_tce_create_table,
+	.set_window = spapr_tce_set_window,
+	.unset_window = spapr_tce_unset_window,
+	.take_ownership = spapr_tce_take_ownership,
+	.release_ownership = spapr_tce_release_ownership,
+};
+#endif
+
 static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
 		void *data)
 {
@@ -1578,12 +2423,20 @@ static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
 	struct memory_notify *arg = data;
 	int ret = 0;
 
+	/* This notifier can get called when onlining persistent memory as well.
+	 * TCEs are not pre-mapped for persistent memory. Persistent memory will
+	 * always be above ddw_memory_hotplug_max()
+	 */
+
 	switch (action) {
 	case MEM_GOING_ONLINE:
 		spin_lock(&dma_win_list_lock);
 		list_for_each_entry(window, &dma_win_list, list) {
-			ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn,
-					arg->nr_pages, window->prop);
+			if (window->direct && (arg->start_pfn << PAGE_SHIFT) <
+				ddw_memory_hotplug_max()) {
+				ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn,
+						arg->nr_pages, window->prop);
+			}
 			/* XXX log error */
 		}
 		spin_unlock(&dma_win_list_lock);
@@ -1592,8 +2445,11 @@ static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
 	case MEM_OFFLINE:
 		spin_lock(&dma_win_list_lock);
 		list_for_each_entry(window, &dma_win_list, list) {
-			ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn,
-					arg->nr_pages, window->prop);
+			if (window->direct && (arg->start_pfn << PAGE_SHIFT) <
+				ddw_memory_hotplug_max()) {
+				ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn,
+						arg->nr_pages, window->prop);
+			}
 			/* XXX log error */
 		}
 		spin_unlock(&dma_win_list_lock);
@@ -1628,8 +2484,8 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
 		 * we have to remove the property when releasing
 		 * the device node.
 		 */
-		if (remove_ddw(np, false, DIRECT64_PROPNAME))
-			remove_ddw(np, false, DMA64_PROPNAME);
+		if (remove_dma_window_named(np, false, DIRECT64_PROPNAME, true))
+			remove_dma_window_named(np, false, DMA64_PROPNAME, true);
 
 		if (pci && pci->table_group)
 			iommu_pseries_free_group(pci->table_group,
@@ -1695,31 +2551,6 @@ static int __init disable_multitce(char *str)
 
 __setup("multitce=", disable_multitce);
 
-static int tce_iommu_bus_notifier(struct notifier_block *nb,
-		unsigned long action, void *data)
-{
-	struct device *dev = data;
-
-	switch (action) {
-	case BUS_NOTIFY_DEL_DEVICE:
-		iommu_del_device(dev);
-		return 0;
-	default:
-		return 0;
-	}
-}
-
-static struct notifier_block tce_iommu_bus_nb = {
-	.notifier_call = tce_iommu_bus_notifier,
-};
-
-static int __init tce_iommu_bus_notifier_init(void)
-{
-	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
-	return 0;
-}
-machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init);
-
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose,
 					     struct pci_dev *pdev)
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 096d09ed89f6..431be156ca9b 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -61,11 +61,3 @@ void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 	} else
 		xics_kexec_teardown_cpu(secondary);
 }
-
-void pseries_machine_kexec(struct kimage *image)
-{
-	if (firmware_has_feature(FW_FEATURE_SET_MODE))
-		pseries_disable_reloc_on_exc();
-
-	default_machine_kexec(image);
-}
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 2eab323f6970..6a415febc53b 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/delay.h>
+#include <linux/seq_file.h>
 #include <linux/stop_machine.h>
 #include <linux/spinlock.h>
 #include <linux/cpuhotplug.h>
@@ -41,6 +42,7 @@
 #include <asm/kexec.h>
 #include <asm/fadump.h>
 #include <asm/dtl.h>
+#include <asm/vphn.h>
 
 #include "pseries.h"
 
@@ -168,7 +170,7 @@ struct vcpu_dispatch_data {
  */
 #define NR_CPUS_H	NR_CPUS
 
-DEFINE_RWLOCK(dtl_access_lock);
+DECLARE_RWSEM(dtl_access_lock);
 static DEFINE_PER_CPU(struct vcpu_dispatch_data, vcpu_disp_data);
 static DEFINE_PER_CPU(u64, dtl_entry_ridx);
 static DEFINE_PER_CPU(struct dtl_worker, dtl_workers);
@@ -191,9 +193,9 @@ static void free_dtl_buffers(unsigned long *time_limit)
 			continue;
 		kmem_cache_free(dtl_cache, pp->dispatch_log);
 		pp->dtl_ridx = 0;
-		pp->dispatch_log = 0;
-		pp->dispatch_log_end = 0;
-		pp->dtl_curr = 0;
+		pp->dispatch_log = NULL;
+		pp->dispatch_log_end = NULL;
+		pp->dtl_curr = NULL;
 
 		if (time_limit && time_after(jiffies, *time_limit)) {
 			cond_resched();
@@ -222,7 +224,7 @@ static void destroy_cpu_associativity(void)
 {
 	kfree(vcpu_associativity);
 	kfree(pcpu_associativity);
-	vcpu_associativity = pcpu_associativity = 0;
+	vcpu_associativity = pcpu_associativity = NULL;
 }
 
 static __be32 *__get_cpu_associativity(int cpu, __be32 *cpu_assoc, int flag)
@@ -462,7 +464,7 @@ static int dtl_worker_enable(unsigned long *time_limit)
 {
 	int rc = 0, state;
 
-	if (!write_trylock(&dtl_access_lock)) {
+	if (!down_write_trylock(&dtl_access_lock)) {
 		rc = -EBUSY;
 		goto out;
 	}
@@ -478,7 +480,7 @@ static int dtl_worker_enable(unsigned long *time_limit)
 		pr_err("vcpudispatch_stats: unable to setup workqueue for DTL processing\n");
 		free_dtl_buffers(time_limit);
 		reset_global_dtl_mask();
-		write_unlock(&dtl_access_lock);
+		up_write(&dtl_access_lock);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -493,7 +495,7 @@ static void dtl_worker_disable(unsigned long *time_limit)
 	cpuhp_remove_state(dtl_worker_state);
 	free_dtl_buffers(time_limit);
 	reset_global_dtl_mask();
-	write_unlock(&dtl_access_lock);
+	up_write(&dtl_access_lock);
 }
 
 static ssize_t vcpudispatch_stats_write(struct file *file, const char __user *p,
@@ -525,8 +527,10 @@ static ssize_t vcpudispatch_stats_write(struct file *file, const char __user *p,
 
 	if (cmd) {
 		rc = init_cpu_associativity();
-		if (rc)
+		if (rc) {
+			destroy_cpu_associativity();
 			goto out;
+		}
 
 		for_each_possible_cpu(cpu) {
 			disp = per_cpu_ptr(&vcpu_disp_data, cpu);
@@ -639,16 +643,8 @@ static const struct proc_ops vcpudispatch_stats_freq_proc_ops = {
 
 static int __init vcpudispatch_stats_procfs_init(void)
 {
-	/*
-	 * Avoid smp_processor_id while preemptible. All CPUs should have
-	 * the same value for lppaca_shared_proc.
-	 */
-	preempt_disable();
-	if (!lppaca_shared_proc(get_lppaca())) {
-		preempt_enable();
+	if (!lppaca_shared_proc())
 		return 0;
-	}
-	preempt_enable();
 
 	if (!proc_create("powerpc/vcpudispatch_stats", 0600, NULL,
 					&vcpudispatch_stats_proc_ops))
@@ -667,8 +663,12 @@ u64 pseries_paravirt_steal_clock(int cpu)
 {
 	struct lppaca *lppaca = &lppaca_of(cpu);
 
-	return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
-		be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb));
+	/*
+	 * VPA steal time counters are reported at TB frequency. Hence do a
+	 * conversion to ns before returning
+	 */
+	return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
+			be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)));
 }
 #endif
 
@@ -1887,10 +1887,10 @@ out:
  * h_get_mpp
  * H_GET_MPP hcall returns info in 7 parms
  */
-int h_get_mpp(struct hvcall_mpp_data *mpp_data)
+long h_get_mpp(struct hvcall_mpp_data *mpp_data)
 {
-	int rc;
-	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+	long rc;
 
 	rc = plpar_hcall9(H_GET_MPP, retbuf);
 
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 8acc70509520..6554537984fb 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -29,7 +29,6 @@
 #include <asm/firmware.h>
 #include <asm/rtas.h>
 #include <asm/time.h>
-#include <asm/vdso_datapage.h>
 #include <asm/vio.h>
 #include <asm/mmu.h>
 #include <asm/machdep.h>
@@ -79,6 +78,8 @@ struct hvcall_ppp_data {
 	u8	capped;
 	u8	weight;
 	u8	unallocated_weight;
+	u8      resource_group_index;
+	u16     active_procs_in_resource_group;
 	u16	active_procs_in_pool;
 	u16	active_system_procs;
 	u16	phys_platform_procs;
@@ -87,7 +88,7 @@ struct hvcall_ppp_data {
 };
 
 /*
- * H_GET_PPP hcall returns info in 4 parms.
+ * H_GET_PPP hcall returns info in 5 parms.
  *  entitled_capacity,unallocated_capacity,
  *  aggregation, resource_capability).
  *
@@ -95,11 +96,11 @@ struct hvcall_ppp_data {
  *  R5 = Unallocated Processor Capacity Percentage.
  *  R6 (AABBCCDDEEFFGGHH).
  *      XXXX - reserved (0)
- *          XXXX - reserved (0)
+ *          XXXX - Active Cores in Resource Group
  *              XXXX - Group Number
  *                  XXXX - Pool Number.
  *  R7 (IIJJKKLLMMNNOOPP).
- *      XX - reserved. (0)
+ *      XX - Resource group Number
  *        XX - bit 0-6 reserved (0).   bit 7 is Capped indicator.
  *          XX - variable processor Capacity Weight
  *            XX - Unallocated Variable Processor Capacity Weight.
@@ -113,17 +114,19 @@ struct hvcall_ppp_data {
  */
 static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
 {
-	unsigned long rc;
-	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+	long rc;
 
 	rc = plpar_hcall9(H_GET_PPP, retbuf);
 
 	ppp_data->entitlement = retbuf[0];
 	ppp_data->unallocated_entitlement = retbuf[1];
 
+	ppp_data->active_procs_in_resource_group = (retbuf[2] >> 4 * 8) & 0xffff;
 	ppp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
 	ppp_data->pool_num = retbuf[2] & 0xffff;
 
+	ppp_data->resource_group_index = (retbuf[3] >> 7 *  8) & 0xff;
 	ppp_data->capped = (retbuf[3] >> 6 * 8) & 0x01;
 	ppp_data->weight = (retbuf[3] >> 5 * 8) & 0xff;
 	ppp_data->unallocated_weight = (retbuf[3] >> 4 * 8) & 0xff;
@@ -170,20 +173,24 @@ out:
 	kfree(buf);
 }
 
-static unsigned h_pic(unsigned long *pool_idle_time,
-		      unsigned long *num_procs)
+static long h_pic(unsigned long *pool_idle_time,
+		  unsigned long *num_procs)
 {
-	unsigned long rc;
-	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = {0};
 
 	rc = plpar_hcall(H_PIC, retbuf);
 
-	*pool_idle_time = retbuf[0];
-	*num_procs = retbuf[1];
+	if (pool_idle_time)
+		*pool_idle_time = retbuf[0];
+	if (num_procs)
+		*num_procs = retbuf[1];
 
 	return rc;
 }
 
+unsigned long boot_pool_idle_time;
+
 /*
  * parse_ppp_data
  * Parse out the data returned from h_get_ppp and h_pic
@@ -193,7 +200,7 @@ static void parse_ppp_data(struct seq_file *m)
 	struct hvcall_ppp_data ppp_data;
 	struct device_node *root;
 	const __be32 *perf_level;
-	int rc;
+	long rc;
 
 	rc = h_get_ppp(&ppp_data);
 	if (rc)
@@ -206,7 +213,7 @@ static void parse_ppp_data(struct seq_file *m)
 	           ppp_data.active_system_procs);
 
 	/* pool related entries are appropriate for shared configs */
-	if (lppaca_shared_proc(get_lppaca())) {
+	if (lppaca_shared_proc()) {
 		unsigned long pool_idle_time, pool_procs;
 
 		seq_printf(m, "pool=%d\n", ppp_data.pool_num);
@@ -215,9 +222,15 @@ static void parse_ppp_data(struct seq_file *m)
 		seq_printf(m, "pool_capacity=%d\n",
 			   ppp_data.active_procs_in_pool * 100);
 
-		h_pic(&pool_idle_time, &pool_procs);
-		seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
-		seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
+		/* In case h_pic call is not successful, this would result in
+		 * APP values being wrong in tools like lparstat.
+		 */
+
+		if (h_pic(&pool_idle_time, &pool_procs) == H_SUCCESS) {
+			seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
+			seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
+			seq_printf(m, "boot_pool_idle_time=%ld\n", boot_pool_idle_time);
+		}
 	}
 
 	seq_printf(m, "unallocated_capacity_weight=%d\n",
@@ -227,6 +240,13 @@ static void parse_ppp_data(struct seq_file *m)
 	seq_printf(m, "unallocated_capacity=%lld\n",
 		   ppp_data.unallocated_entitlement);
 
+	if (ppp_data.active_procs_in_resource_group)  {
+		seq_printf(m, "resource_group_number=%d\n",
+				ppp_data.resource_group_index);
+		seq_printf(m, "resource_group_active_processors=%d\n",
+				ppp_data.active_procs_in_resource_group);
+	}
+
 	/* The last bits of information returned from h_get_ppp are only
 	 * valid if the ibm,partition-performance-parameters-level
 	 * property is >= 1.
@@ -346,9 +366,13 @@ static int read_rtas_lpar_name(struct seq_file *m)
  */
 static int read_dt_lpar_name(struct seq_file *m)
 {
+	struct device_node *root = of_find_node_by_path("/");
 	const char *name;
+	int ret;
 
-	if (of_property_read_string(of_root, "ibm,partition-name", &name))
+	ret = of_property_read_string(root, "ibm,partition-name", &name);
+	of_node_put(root);
+	if (ret)
 		return -ENOENT;
 
 	seq_printf(m, "partition_name=%s\n", name);
@@ -357,8 +381,8 @@ static int read_dt_lpar_name(struct seq_file *m)
 
 static void read_lpar_name(struct seq_file *m)
 {
-	if (read_rtas_lpar_name(m) && read_dt_lpar_name(m))
-		pr_err_once("Error can't get the LPAR name");
+	if (read_rtas_lpar_name(m))
+		read_dt_lpar_name(m);
 }
 
 #define SPLPAR_MAXLENGTH 1026*(sizeof(char))
@@ -516,7 +540,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 		lrdrp = of_get_property(rtas_node, "ibm,lrdr-capacity", NULL);
 
 	if (lrdrp == NULL) {
-		partition_potential_processors = vdso_data->processorCount;
+		partition_potential_processors = num_possible_cpus();
 	} else {
 		partition_potential_processors = be32_to_cpup(lrdrp + 4);
 	}
@@ -539,7 +563,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 	} else {		/* non SPLPAR case */
 
 		seq_printf(m, "system_active_processors=%d\n",
-			   partition_potential_processors);
+			   partition_active_processors);
 
 		seq_printf(m, "system_potential_processors=%d\n",
 			   partition_potential_processors);
@@ -560,7 +584,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 		   partition_potential_processors);
 
 	seq_printf(m, "shared_processor_mode=%d\n",
-		   lppaca_shared_proc(get_lppaca()));
+		   lppaca_shared_proc());
 
 #ifdef CONFIG_PPC_64S_HASH_MMU
 	if (!radix_enabled())
@@ -788,6 +812,7 @@ static const struct proc_ops lparcfg_proc_ops = {
 static int __init lparcfg_init(void)
 {
 	umode_t mode = 0444;
+	long retval;
 
 	/* Allow writing if we have FW_FEATURE_SPLPAR */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR))
@@ -797,6 +822,16 @@ static int __init lparcfg_init(void)
 		printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
 		return -EIO;
 	}
+
+	/* If this call fails, it would result in APP values
+	 * being wrong for since boot reports of lparstat
+	 */
+	retval = h_pic(&boot_pool_idle_time, NULL);
+
+	if (retval != H_SUCCESS)
+		pr_debug("H_PIC failed during lparcfg init retval: %ld\n",
+			 retval);
+
 	return 0;
 }
 machine_device_initcall(pseries, lparcfg_init);
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 6f30113b5468..95fe802ccdfd 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -24,9 +24,11 @@
 #include <linux/stringify.h>
 
 #include <asm/machdep.h>
+#include <asm/nmi.h>
 #include <asm/rtas.h>
 #include "pseries.h"
 #include "vas.h"	/* vas_migration_handler() */
+#include "papr-hvpipe.h"	/* hvpipe_migration_handler() */
 #include "../../kernel/cacheinfo.h"
 
 static struct kobject *mobility_kobj;
@@ -52,7 +54,7 @@ struct update_props_workarea {
 static unsigned int nmi_wd_lpm_factor = 200;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
+static const struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
 	{
 		.procname	= "nmi_wd_lpm_factor",
 		.data		= &nmi_wd_lpm_factor,
@@ -60,7 +62,6 @@ static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_douintvec_minmax,
 	},
-	{}
 };
 
 static int __init register_nmi_wd_lpm_factor_sysctl(void)
@@ -744,13 +745,14 @@ static int pseries_migrate_partition(u64 handle)
 	 * by closing VAS windows at the beginning of this function.
 	 */
 	vas_migration_handler(VAS_SUSPEND);
+	hvpipe_migration_handler(HVPIPE_SUSPEND);
 
 	ret = wait_for_vasi_session_suspending(handle);
 	if (ret)
 		goto out;
 
 	if (factor)
-		watchdog_nmi_set_timeout_pct(factor);
+		watchdog_hardlockup_set_timeout_pct(factor);
 
 	ret = pseries_suspend(handle);
 	if (ret == 0) {
@@ -766,10 +768,11 @@ static int pseries_migrate_partition(u64 handle)
 		pseries_cancel_migration(handle, ret);
 
 	if (factor)
-		watchdog_nmi_set_timeout_pct(0);
+		watchdog_hardlockup_set_timeout_pct(0);
 
 out:
 	vas_migration_handler(VAS_RESUME);
+	hvpipe_migration_handler(HVPIPE_RESUME);
 
 	return ret;
 }
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 423ee1d5bd94..a82aaa786e9e 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -7,14 +7,15 @@
 #include <linux/crash_dump.h>
 #include <linux/device.h>
 #include <linux/irq.h>
+#include <linux/irqchip/irq-msi-lib.h>
 #include <linux/irqdomain.h>
 #include <linux/msi.h>
+#include <linux/seq_file.h>
 
 #include <asm/rtas.h>
 #include <asm/hw_irq.h>
 #include <asm/ppc-pci.h>
 #include <asm/machdep.h>
-#include <asm/xive.h>
 
 #include "pseries.h"
 
@@ -26,6 +27,7 @@ static int query_token, change_token;
 #define RTAS_CHANGE_MSI_FN	3
 #define RTAS_CHANGE_MSIX_FN	4
 #define RTAS_CHANGE_32MSI_FN	5
+#define RTAS_CHANGE_32MSIX_FN	6
 
 /* RTAS Helpers */
 
@@ -41,7 +43,7 @@ static int rtas_change_msi(struct pci_dn *pdn, u32 func, u32 num_irqs)
 	seq_num = 1;
 	do {
 		if (func == RTAS_CHANGE_MSI_FN || func == RTAS_CHANGE_MSIX_FN ||
-		    func == RTAS_CHANGE_32MSI_FN)
+		    func == RTAS_CHANGE_32MSI_FN || func == RTAS_CHANGE_32MSIX_FN)
 			rc = rtas_call(change_token, 6, 4, rtas_ret, addr,
 					BUID_HI(buid), BUID_LO(buid),
 					func, num_irqs, seq_num);
@@ -406,8 +408,12 @@ again:
 
 		if (use_32bit_msi_hack && rc > 0)
 			rtas_hack_32bit_msi_gen2(pdev);
-	} else
-		rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec);
+	} else {
+		if (pdev->no_64bit_msi)
+			rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSIX_FN, nvec);
+		else
+			rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec);
+	}
 
 	if (rc != nvec) {
 		if (nvec != nvec_in) {
@@ -424,43 +430,24 @@ again:
 static int pseries_msi_ops_prepare(struct irq_domain *domain, struct device *dev,
 				   int nvec, msi_alloc_info_t *arg)
 {
+	struct msi_domain_info *info = domain->host_data;
 	struct pci_dev *pdev = to_pci_dev(dev);
-	int type = pdev->msix_enabled ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI;
+	int type = (info->flags & MSI_FLAG_PCI_MSIX) ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI;
 
 	return rtas_prepare_msi_irqs(pdev, nvec, type, arg);
 }
 
 /*
- * ->msi_free() is called before irq_domain_free_irqs_top() when the
- * handler data is still available. Use that to clear the XIVE
- * controller data.
- */
-static void pseries_msi_ops_msi_free(struct irq_domain *domain,
-				     struct msi_domain_info *info,
-				     unsigned int irq)
-{
-	if (xive_enabled())
-		xive_irq_free_data(irq);
-}
-
-/*
  * RTAS can not disable one MSI at a time. It's all or nothing. Do it
  * at the end after all IRQs have been freed.
  */
-static void pseries_msi_post_free(struct irq_domain *domain, struct device *dev)
+static void pseries_msi_ops_teardown(struct irq_domain *domain, msi_alloc_info_t *arg)
 {
-	if (WARN_ON_ONCE(!dev_is_pci(dev)))
-		return;
+	struct pci_dev *pdev = to_pci_dev(domain->dev);
 
-	rtas_disable_msi(to_pci_dev(dev));
+	rtas_disable_msi(pdev);
 }
 
-static struct msi_domain_ops pseries_pci_msi_domain_ops = {
-	.msi_prepare	= pseries_msi_ops_prepare,
-	.msi_free	= pseries_msi_ops_msi_free,
-	.msi_post_free	= pseries_msi_post_free,
-};
-
 static void pseries_msi_shutdown(struct irq_data *d)
 {
 	d = d->parent_data;
@@ -468,18 +455,6 @@ static void pseries_msi_shutdown(struct irq_data *d)
 		d->chip->irq_shutdown(d);
 }
 
-static void pseries_msi_mask(struct irq_data *d)
-{
-	pci_msi_mask_irq(d);
-	irq_chip_mask_parent(d);
-}
-
-static void pseries_msi_unmask(struct irq_data *d)
-{
-	pci_msi_unmask_irq(d);
-	irq_chip_unmask_parent(d);
-}
-
 static void pseries_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 {
 	struct msi_desc *entry = irq_data_get_msi_desc(data);
@@ -494,32 +469,49 @@ static void pseries_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 	entry->msg = *msg;
 }
 
-static struct irq_chip pseries_pci_msi_irq_chip = {
-	.name		= "pSeries-PCI-MSI",
-	.irq_shutdown	= pseries_msi_shutdown,
-	.irq_mask	= pseries_msi_mask,
-	.irq_unmask	= pseries_msi_unmask,
-	.irq_eoi	= irq_chip_eoi_parent,
-	.irq_write_msi_msg	= pseries_msi_write_msg,
-};
+static bool pseries_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
+				      struct irq_domain *real_parent, struct msi_domain_info *info)
+{
+	struct irq_chip *chip = info->chip;
 
+	if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info))
+		return false;
 
-/*
- * Set MSI_FLAG_MSIX_CONTIGUOUS as there is no way to express to
- * firmware to request a discontiguous or non-zero based range of
- * MSI-X entries. Core code will reject such setup attempts.
- */
-static struct msi_domain_info pseries_msi_domain_info = {
-	.flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		  MSI_FLAG_MULTI_PCI_MSI  | MSI_FLAG_PCI_MSIX |
-		  MSI_FLAG_MSIX_CONTIGUOUS),
-	.ops   = &pseries_pci_msi_domain_ops,
-	.chip  = &pseries_pci_msi_irq_chip,
+	chip->irq_shutdown = pseries_msi_shutdown;
+	chip->irq_write_msi_msg	= pseries_msi_write_msg;
+
+	info->ops->msi_prepare = pseries_msi_ops_prepare;
+	info->ops->msi_teardown = pseries_msi_ops_teardown;
+
+	return true;
+}
+
+#define PSERIES_PCI_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS	| \
+					MSI_FLAG_USE_DEF_CHIP_OPS	| \
+					MSI_FLAG_PCI_MSI_MASK_PARENT)
+#define PSERIES_PCI_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK		| \
+					 MSI_FLAG_PCI_MSIX		| \
+					 MSI_FLAG_MSIX_CONTIGUOUS	| \
+					 MSI_FLAG_MULTI_PCI_MSI)
+
+static const struct msi_parent_ops pseries_msi_parent_ops = {
+	.required_flags		= PSERIES_PCI_MSI_FLAGS_REQUIRED,
+	.supported_flags	= PSERIES_PCI_MSI_FLAGS_SUPPORTED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI,
+	.bus_select_token	= DOMAIN_BUS_NEXUS,
+	.bus_select_mask	= MATCH_PCI_MSI,
+	.prefix			= "pSeries-",
+	.init_dev_msi_info	= pseries_init_dev_msi_info,
 };
 
 static void pseries_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	__pci_read_msi_msg(irq_data_get_msi_desc(data), msg);
+	struct pci_dev *dev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
+
+	if (dev->current_state == PCI_D0)
+		__pci_read_msi_msg(irq_data_get_msi_desc(data), msg);
+	else
+		get_cached_msi_msg(data->irq, msg);
 }
 
 static struct irq_chip pseries_msi_irq_chip = {
@@ -582,7 +574,7 @@ static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 
 out:
 	/* TODO: handle RTAS cleanup in ->msi_finish() ? */
-	irq_domain_free_irqs_parent(domain, virq, i - 1);
+	irq_domain_free_irqs_parent(domain, virq, i);
 	return ret;
 }
 
@@ -593,11 +585,11 @@ static void pseries_irq_domain_free(struct irq_domain *domain, unsigned int virq
 	struct pci_controller *phb = irq_data_get_irq_chip_data(d);
 
 	pr_debug("%s bridge %pOF %d #%d\n", __func__, phb->dn, virq, nr_irqs);
-
-	/* XIVE domain data is cleared through ->msi_free() */
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
 }
 
 static const struct irq_domain_ops pseries_irq_domain_ops = {
+	.select	= msi_lib_irq_domain_select,
 	.alloc  = pseries_irq_domain_alloc,
 	.free   = pseries_irq_domain_free,
 };
@@ -605,31 +597,19 @@ static const struct irq_domain_ops pseries_irq_domain_ops = {
 static int __pseries_msi_allocate_domains(struct pci_controller *phb,
 					  unsigned int count)
 {
-	struct irq_domain *parent = irq_get_default_host();
-
-	phb->fwnode = irq_domain_alloc_named_id_fwnode("pSeries-MSI",
-						       phb->global_number);
-	if (!phb->fwnode)
-		return -ENOMEM;
-
-	phb->dev_domain = irq_domain_create_hierarchy(parent, 0, count,
-						      phb->fwnode,
-						      &pseries_irq_domain_ops, phb);
+	struct irq_domain *parent = irq_get_default_domain();
+	struct irq_domain_info info = {
+		.fwnode		= of_fwnode_handle(phb->dn),
+		.ops		= &pseries_irq_domain_ops,
+		.host_data	= phb,
+		.size		= count,
+		.parent		= parent,
+	};
+
+	phb->dev_domain = msi_create_parent_irq_domain(&info, &pseries_msi_parent_ops);
 	if (!phb->dev_domain) {
-		pr_err("PCI: failed to create IRQ domain bridge %pOF (domain %d)\n",
-		       phb->dn, phb->global_number);
-		irq_domain_free_fwnode(phb->fwnode);
-		return -ENOMEM;
-	}
-
-	phb->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(phb->dn),
-						    &pseries_msi_domain_info,
-						    phb->dev_domain);
-	if (!phb->msi_domain) {
 		pr_err("PCI: failed to create MSI IRQ domain bridge %pOF (domain %d)\n",
 		       phb->dn, phb->global_number);
-		irq_domain_free_fwnode(phb->fwnode);
-		irq_domain_remove(phb->dev_domain);
 		return -ENOMEM;
 	}
 
@@ -651,12 +631,8 @@ int pseries_msi_allocate_domains(struct pci_controller *phb)
 
 void pseries_msi_free_domains(struct pci_controller *phb)
 {
-	if (phb->msi_domain)
-		irq_domain_remove(phb->msi_domain);
 	if (phb->dev_domain)
 		irq_domain_remove(phb->dev_domain);
-	if (phb->fwnode)
-		irq_domain_free_fwnode(phb->fwnode);
 }
 
 static void rtas_msi_pci_irq_fixup(struct pci_dev *pdev)
diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.c b/arch/powerpc/platforms/pseries/papr-hvpipe.c
new file mode 100644
index 000000000000..dd7b668799d9
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-hvpipe.c
@@ -0,0 +1,797 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-hvpipe: " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/delay.h>
+#include <linux/anon_inodes.h>
+#include <linux/miscdevice.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/of.h>
+#include <asm/machdep.h>
+#include <asm/rtas.h>
+#include <asm/rtas-work-area.h>
+#include <asm/papr-sysparm.h>
+#include <uapi/asm/papr-hvpipe.h>
+#include "pseries.h"
+#include "papr-hvpipe.h"
+
+static DEFINE_SPINLOCK(hvpipe_src_list_lock);
+static LIST_HEAD(hvpipe_src_list);
+
+static unsigned char hvpipe_ras_buf[RTAS_ERROR_LOG_MAX];
+static struct workqueue_struct *papr_hvpipe_wq;
+static struct work_struct *papr_hvpipe_work;
+static int hvpipe_check_exception_token;
+static bool hvpipe_feature;
+
+/*
+ * New PowerPC FW provides support for partitions and various
+ * sources (Ex: remote hardware management console (HMC)) to
+ * exchange information through an inband hypervisor channel
+ * called HVPIPE. Only HMCs are supported right now and
+ * partitions can communicate with multiple HMCs and each
+ * source represented by source ID.
+ *
+ * FW introduces send HVPIPE and recv HVPIPE RTAS calls for
+ * partitions to send and receive payloads respectively.
+ *
+ * These RTAS functions have the following certain requirements
+ * / limitations:
+ * - One hvpipe per partition for all sources.
+ * - Assume the return status of send HVPIPE as delivered to source
+ * - Assume the return status of recv HVPIPE as ACK to source
+ * - Generates HVPIPE event message when the payload is ready
+ *   for the partition. The hypervisor will not deliver another
+ *   event until the partition read the previous payload which
+ *   means the pipe is blocked for any sources.
+ *
+ * Linux implementation:
+ * Follow the similar interfaces that the OS has for other RTAS calls.
+ * ex: /dev/papr-indices, /dev/papr-vpd, etc.
+ * - /dev/papr-hvpipe is available for the user space.
+ * - devfd = open("/dev/papr-hvpipe", ..)
+ * - fd = ioctl(fd,HVPIPE_IOC_CREATE_HANDLE,&srcID)-for each source
+ * - write(fd, buf, size) --> Issue send HVPIPE RTAS call and
+ *   returns size for success or the corresponding error for RTAS
+ *   return code for failure.
+ * - poll(fd,..) -> wakeup FD if the payload is available to read.
+ *   HVPIPE event message handler wakeup FD based on source ID in
+ *   the event message
+ * - read(fd, buf, size) --> Issue recv HVPIPE RTAS call and
+ *   returns size for success or the corresponding error for RTAS
+ *   return code for failure.
+ */
+
+/*
+ * ibm,receive-hvpipe-msg RTAS call.
+ * @area: Caller-provided work area buffer for results.
+ * @srcID: Source ID returned by the RTAS call.
+ * @bytesw: Bytes written by RTAS call to @area.
+ */
+static int rtas_ibm_receive_hvpipe_msg(struct rtas_work_area *area,
+					u32 *srcID, u32 *bytesw)
+{
+	const s32 token = rtas_function_token(RTAS_FN_IBM_RECEIVE_HVPIPE_MSG);
+	u32 rets[2];
+	s32 fwrc;
+	int ret;
+
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	do {
+		fwrc = rtas_call(token, 2, 3, rets,
+				rtas_work_area_phys(area),
+				rtas_work_area_size(area));
+
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_SUCCESS:
+		*srcID = rets[0];
+		*bytesw = rets[1];
+		ret = 0;
+		break;
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER:
+		ret = -EINVAL;
+		break;
+	case RTAS_FUNC_NOT_SUPPORTED:
+		ret = -EOPNOTSUPP;
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,receive-hvpipe-msg status %d\n", fwrc);
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * ibm,send-hvpipe-msg RTAS call
+ * @area: Caller-provided work area buffer to send.
+ * @srcID: Target source for the send pipe message.
+ */
+static int rtas_ibm_send_hvpipe_msg(struct rtas_work_area *area, u32 srcID)
+{
+	const s32 token = rtas_function_token(RTAS_FN_IBM_SEND_HVPIPE_MSG);
+	s32 fwrc;
+	int ret;
+
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	do {
+		fwrc = rtas_call(token, 2, 1, NULL, srcID,
+				rtas_work_area_phys(area));
+
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_SUCCESS:
+		ret = 0;
+		break;
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER:
+		ret = -EINVAL;
+		break;
+	case RTAS_HVPIPE_CLOSED:
+		ret = -EPIPE;
+		break;
+	case RTAS_FUNC_NOT_SUPPORTED:
+		ret = -EOPNOTSUPP;
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,receive-hvpipe-msg status %d\n", fwrc);
+		break;
+	}
+
+	return ret;
+}
+
+static struct hvpipe_source_info *hvpipe_find_source(u32 srcID)
+{
+	struct hvpipe_source_info *src_info;
+
+	list_for_each_entry(src_info, &hvpipe_src_list, list)
+		if (src_info->srcID == srcID)
+			return src_info;
+
+	return NULL;
+}
+
+/*
+ * This work function collects receive buffer with recv HVPIPE
+ * RTAS call. Called from read()
+ * @buf: User specified buffer to copy the payload that returned
+ *       from recv HVPIPE RTAS.
+ * @size: Size of buffer user passed.
+ */
+static int hvpipe_rtas_recv_msg(char __user *buf, int size)
+{
+	struct rtas_work_area *work_area;
+	u32 srcID, bytes_written;
+	int ret;
+
+	work_area = rtas_work_area_alloc(SZ_4K);
+	if (!work_area) {
+		pr_err("Could not allocate RTAS buffer for recv pipe\n");
+		return -ENOMEM;
+	}
+
+	ret = rtas_ibm_receive_hvpipe_msg(work_area, &srcID,
+					&bytes_written);
+	if (!ret) {
+		/*
+		 * Recv HVPIPE RTAS is successful.
+		 * When releasing FD or no one is waiting on the
+		 * specific source, issue recv HVPIPE RTAS call
+		 * so that pipe is not blocked - this func is called
+		 * with NULL buf.
+		 */
+		if (buf) {
+			if (size < bytes_written) {
+				pr_err("Received the payload size = %d, but the buffer size = %d\n",
+					bytes_written, size);
+				bytes_written = size;
+			}
+			ret = copy_to_user(buf,
+					rtas_work_area_raw_buf(work_area),
+					bytes_written);
+			if (!ret)
+				ret = bytes_written;
+		}
+	} else {
+		pr_err("ibm,receive-hvpipe-msg failed with %d\n",
+				ret);
+	}
+
+	rtas_work_area_free(work_area);
+	return ret;
+}
+
+/*
+ * papr_hvpipe_handle_write -  Issue send HVPIPE RTAS and return
+ * the size (payload + HVPIPE_HDR_LEN) for RTAS success.
+ * Otherwise returns the status of RTAS to the user space
+ */
+static ssize_t papr_hvpipe_handle_write(struct file *file,
+	const char __user *buf, size_t size, loff_t *off)
+{
+	struct hvpipe_source_info *src_info = file->private_data;
+	struct rtas_work_area *work_area, *work_buf;
+	unsigned long ret, len;
+	__be64 *area_be;
+
+	/*
+	 * Return -ENXIO during migration
+	 */
+	if (!hvpipe_feature)
+		return -ENXIO;
+
+	if (!src_info)
+		return -EIO;
+
+	/*
+	 * Send HVPIPE RTAS is used to send payload to the specific
+	 * source with the input parameters source ID and the payload
+	 * as buffer list. Each entry in the buffer list contains
+	 * address/length pair of the buffer.
+	 *
+	 * The buffer list format is as follows:
+	 *
+	 * Header (length of address/length pairs and the header length)
+	 * Address of 4K buffer 1
+	 * Length of 4K buffer 1 used
+	 * ...
+	 * Address of 4K buffer n
+	 * Length of 4K buffer n used
+	 *
+	 * See PAPR 7.3.32.2 ibm,send-hvpipe-msg
+	 *
+	 * Even though can support max 1MB payload, the hypervisor
+	 * supports only 4048 bytes payload at present and also
+	 * just one address/length entry.
+	 *
+	 * writev() interface can be added in future when the
+	 * hypervisor supports multiple buffer list entries.
+	 */
+	/* HVPIPE_MAX_WRITE_BUFFER_SIZE = 4048 bytes */
+	if ((size > (HVPIPE_HDR_LEN + HVPIPE_MAX_WRITE_BUFFER_SIZE)) ||
+		(size <= HVPIPE_HDR_LEN))
+		return -EINVAL;
+
+	/*
+	 * The length of (address + length) pair + the length of header
+	 */
+	len = (2 * sizeof(u64)) + sizeof(u64);
+	size -= HVPIPE_HDR_LEN;
+	buf += HVPIPE_HDR_LEN;
+	mutex_lock(&rtas_ibm_send_hvpipe_msg_lock);
+	work_area = rtas_work_area_alloc(SZ_4K);
+	if (!work_area) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	area_be = (__be64 *)rtas_work_area_raw_buf(work_area);
+	/* header */
+	area_be[0] = cpu_to_be64(len);
+
+	work_buf = rtas_work_area_alloc(SZ_4K);
+	if (!work_buf) {
+		ret = -ENOMEM;
+		goto out_work;
+	}
+	/* First buffer address */
+	area_be[1] = cpu_to_be64(rtas_work_area_phys(work_buf));
+	/* First buffer address length */
+	area_be[2] = cpu_to_be64(size);
+
+	if (!copy_from_user(rtas_work_area_raw_buf(work_buf), buf, size)) {
+		ret = rtas_ibm_send_hvpipe_msg(work_area, src_info->srcID);
+		if (!ret)
+			ret = size + HVPIPE_HDR_LEN;
+	} else
+		ret = -EPERM;
+
+	rtas_work_area_free(work_buf);
+out_work:
+	rtas_work_area_free(work_area);
+out:
+	mutex_unlock(&rtas_ibm_send_hvpipe_msg_lock);
+	return ret;
+}
+
+/*
+ * papr_hvpipe_handle_read - If the payload for the specific
+ * source is pending in the hypervisor, issue recv HVPIPE RTAS
+ * and return the payload to the user space.
+ *
+ * When the payload is available for the partition, the
+ * hypervisor notifies HVPIPE event with the source ID
+ * and the event handler wakeup FD(s) that are waiting.
+ */
+static ssize_t papr_hvpipe_handle_read(struct file *file,
+		char __user *buf, size_t size, loff_t *off)
+{
+
+	struct hvpipe_source_info *src_info = file->private_data;
+	struct papr_hvpipe_hdr hdr;
+	long ret;
+
+	/*
+	 * Return -ENXIO during migration
+	 */
+	if (!hvpipe_feature)
+		return -ENXIO;
+
+	if (!src_info)
+		return -EIO;
+
+	/*
+	 * Max payload is 4048 (HVPIPE_MAX_WRITE_BUFFER_SIZE)
+	 */
+	if ((size > (HVPIPE_HDR_LEN + HVPIPE_MAX_WRITE_BUFFER_SIZE)) ||
+		(size < HVPIPE_HDR_LEN))
+		return -EINVAL;
+
+	/*
+	 * Payload is not available to receive or source pipe
+	 * is not closed.
+	 */
+	if (!src_info->hvpipe_status)
+		return 0;
+
+	hdr.version = 0;
+	hdr.flags = 0;
+
+	/*
+	 * In case if the hvpipe has payload and also the
+	 * hypervisor closed the pipe to the source, retrieve
+	 * the payload and return to the user space first and
+	 * then notify the userspace about the hvpipe close in
+	 * next read().
+	 */
+	if (src_info->hvpipe_status & HVPIPE_MSG_AVAILABLE)
+		hdr.flags = HVPIPE_MSG_AVAILABLE;
+	else if (src_info->hvpipe_status & HVPIPE_LOST_CONNECTION)
+		hdr.flags = HVPIPE_LOST_CONNECTION;
+	else
+		/*
+		 * Should not be here without one of the above
+		 * flags set
+		 */
+		return -EIO;
+
+	ret = copy_to_user(buf, &hdr, HVPIPE_HDR_LEN);
+	if (ret)
+		return ret;
+
+	/*
+	 * Message event has payload, so get the payload with
+	 * recv HVPIPE RTAS.
+	 */
+	if (hdr.flags & HVPIPE_MSG_AVAILABLE) {
+		ret = hvpipe_rtas_recv_msg(buf + HVPIPE_HDR_LEN,
+				size - HVPIPE_HDR_LEN);
+		if (ret > 0) {
+			src_info->hvpipe_status &= ~HVPIPE_MSG_AVAILABLE;
+			ret += HVPIPE_HDR_LEN;
+		}
+	} else if (hdr.flags & HVPIPE_LOST_CONNECTION) {
+		/*
+		 * Hypervisor is closing the pipe for the specific
+		 * source. So notify user space.
+		 */
+		src_info->hvpipe_status &= ~HVPIPE_LOST_CONNECTION;
+		ret = HVPIPE_HDR_LEN;
+	}
+
+	return ret;
+}
+
+/*
+ * The user space waits for the payload to receive.
+ * The hypervisor sends HVPIPE event message to the partition
+ * when the payload is available. The event handler wakeup FD
+ * depends on the source ID in the message event.
+ */
+static __poll_t papr_hvpipe_handle_poll(struct file *filp,
+		struct poll_table_struct *wait)
+{
+	struct hvpipe_source_info *src_info = filp->private_data;
+
+	/*
+	 * HVPIPE is disabled during SUSPEND and enabled after migration.
+	 * So return POLLRDHUP during migration
+	 */
+	if (!hvpipe_feature)
+		return POLLRDHUP;
+
+	if (!src_info)
+		return POLLNVAL;
+
+	/*
+	 * If hvpipe already has pending payload, return so that
+	 * the user space can issue read().
+	 */
+	if (src_info->hvpipe_status)
+		return POLLIN | POLLRDNORM;
+
+	/*
+	 * Wait for the message event
+	 * hvpipe_event_interrupt() wakes up this wait_queue
+	 */
+	poll_wait(filp, &src_info->recv_wqh, wait);
+	if (src_info->hvpipe_status)
+		return POLLIN | POLLRDNORM;
+
+	return 0;
+}
+
+static int papr_hvpipe_handle_release(struct inode *inode,
+				struct file *file)
+{
+	struct hvpipe_source_info *src_info;
+
+	/*
+	 * Hold the lock, remove source from src_list, reset the
+	 * hvpipe status and release the lock to prevent any race
+	 * with message event IRQ.
+	 */
+	spin_lock(&hvpipe_src_list_lock);
+	src_info = file->private_data;
+	list_del(&src_info->list);
+	file->private_data = NULL;
+	/*
+	 * If the pipe for this specific source has any pending
+	 * payload, issue recv HVPIPE RTAS so that pipe will not
+	 * be blocked.
+	 */
+	if (src_info->hvpipe_status & HVPIPE_MSG_AVAILABLE) {
+		src_info->hvpipe_status = 0;
+		spin_unlock(&hvpipe_src_list_lock);
+		hvpipe_rtas_recv_msg(NULL, 0);
+	} else
+		spin_unlock(&hvpipe_src_list_lock);
+
+	kfree(src_info);
+	return 0;
+}
+
+static const struct file_operations papr_hvpipe_handle_ops = {
+	.read		=	papr_hvpipe_handle_read,
+	.write		=	papr_hvpipe_handle_write,
+	.release	=	papr_hvpipe_handle_release,
+	.poll		=	papr_hvpipe_handle_poll,
+};
+
+static int papr_hvpipe_dev_create_handle(u32 srcID)
+{
+	struct hvpipe_source_info *src_info __free(kfree) = NULL;
+
+	spin_lock(&hvpipe_src_list_lock);
+	/*
+	 * Do not allow more than one process communicates with
+	 * each source.
+	 */
+	src_info = hvpipe_find_source(srcID);
+	if (src_info) {
+		spin_unlock(&hvpipe_src_list_lock);
+		pr_err("pid(%d) is already using the source(%d)\n",
+				src_info->tsk->pid, srcID);
+		return -EALREADY;
+	}
+	spin_unlock(&hvpipe_src_list_lock);
+
+	src_info = kzalloc(sizeof(*src_info), GFP_KERNEL_ACCOUNT);
+	if (!src_info)
+		return -ENOMEM;
+
+	src_info->srcID = srcID;
+	src_info->tsk = current;
+	init_waitqueue_head(&src_info->recv_wqh);
+
+	FD_PREPARE(fdf, O_RDONLY | O_CLOEXEC,
+		   anon_inode_getfile("[papr-hvpipe]", &papr_hvpipe_handle_ops,
+				      (void *)src_info, O_RDWR));
+	if (fdf.err)
+		return fdf.err;
+
+	retain_and_null_ptr(src_info);
+	spin_lock(&hvpipe_src_list_lock);
+	/*
+	 * If two processes are executing ioctl() for the same
+	 * source ID concurrently, prevent the second process to
+	 * acquire FD.
+	 */
+	if (hvpipe_find_source(srcID)) {
+		spin_unlock(&hvpipe_src_list_lock);
+		return -EALREADY;
+	}
+	list_add(&src_info->list, &hvpipe_src_list);
+	spin_unlock(&hvpipe_src_list_lock);
+	return fd_publish(fdf);
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr_hvpipe
+ *
+ * Use separate FD for each source (exa :HMC). So ioctl is called
+ * with source ID which returns FD.
+ */
+static long papr_hvpipe_dev_ioctl(struct file *filp, unsigned int ioctl,
+		unsigned long arg)
+{
+	u32 __user *argp = (void __user *)arg;
+	u32 srcID;
+	long ret;
+
+	/*
+	 * Return -ENXIO during migration
+	 */
+	if (!hvpipe_feature)
+		return -ENXIO;
+
+	if (get_user(srcID, argp))
+		return -EFAULT;
+
+	/*
+	 * Support only HMC source right now
+	 */
+	if (!(srcID & HVPIPE_HMC_ID_MASK))
+		return -EINVAL;
+
+	switch (ioctl) {
+	case PAPR_HVPIPE_IOC_CREATE_HANDLE:
+		ret = papr_hvpipe_dev_create_handle(srcID);
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * papr_hvpipe_work_fn - called to issue recv HVPIPE RTAS for
+ * sources that are not monitored by user space so that pipe
+ * will not be blocked.
+ */
+static void papr_hvpipe_work_fn(struct work_struct *work)
+{
+	hvpipe_rtas_recv_msg(NULL, 0);
+}
+
+/*
+ * HVPIPE event message IRQ handler.
+ * The hypervisor sends event IRQ if the partition has payload
+ * and generates another event only after payload is read with
+ * recv HVPIPE RTAS.
+ */
+static irqreturn_t hvpipe_event_interrupt(int irq, void *dev_id)
+{
+	struct hvpipe_event_buf *hvpipe_event;
+	struct pseries_errorlog *pseries_log;
+	struct hvpipe_source_info *src_info;
+	struct rtas_error_log *elog;
+	int rc;
+
+	rc = rtas_call(hvpipe_check_exception_token, 6, 1, NULL,
+		RTAS_VECTOR_EXTERNAL_INTERRUPT, virq_to_hw(irq),
+		RTAS_HVPIPE_MSG_EVENTS, 1, __pa(&hvpipe_ras_buf),
+		rtas_get_error_log_max());
+
+	if (rc != 0) {
+		pr_err_ratelimited("unexpected hvpipe-event-notification failed %d\n", rc);
+		return IRQ_HANDLED;
+	}
+
+	elog = (struct rtas_error_log *)hvpipe_ras_buf;
+	if (unlikely(rtas_error_type(elog) != RTAS_TYPE_HVPIPE)) {
+		pr_warn_ratelimited("Unexpected event type %d\n",
+				rtas_error_type(elog));
+		return IRQ_HANDLED;
+	}
+
+	pseries_log = get_pseries_errorlog(elog,
+				PSERIES_ELOG_SECT_ID_HVPIPE_EVENT);
+	hvpipe_event = (struct hvpipe_event_buf *)pseries_log->data;
+
+	/*
+	 * The hypervisor notifies partition when the payload is
+	 * available to read with recv HVPIPE RTAS and it will not
+	 * notify another event for any source until the previous
+	 * payload is read. Means the pipe is blocked in the
+	 * hypervisor until the payload is read.
+	 *
+	 * If the source is ready to accept payload and wakeup the
+	 * corresponding FD. Hold lock and update hvpipe_status
+	 * and this lock is needed in case the user space process
+	 * is in release FD instead of poll() so that release()
+	 * reads the payload to unblock pipe before closing FD.
+	 *
+	 * otherwise (means no other user process waiting for the
+	 * payload, issue recv HVPIPE RTAS (papr_hvpipe_work_fn())
+	 * to unblock pipe.
+	 */
+	spin_lock(&hvpipe_src_list_lock);
+	src_info = hvpipe_find_source(be32_to_cpu(hvpipe_event->srcID));
+	if (src_info) {
+		u32 flags = 0;
+
+		if (hvpipe_event->event_type & HVPIPE_LOST_CONNECTION)
+			flags = HVPIPE_LOST_CONNECTION;
+		else if (hvpipe_event->event_type & HVPIPE_MSG_AVAILABLE)
+			flags = HVPIPE_MSG_AVAILABLE;
+
+		src_info->hvpipe_status |= flags;
+		wake_up(&src_info->recv_wqh);
+		spin_unlock(&hvpipe_src_list_lock);
+	} else {
+		spin_unlock(&hvpipe_src_list_lock);
+		/*
+		 * user space is not waiting on this source. So
+		 * execute receive pipe RTAS so that pipe will not
+		 * be blocked.
+		 */
+		if (hvpipe_event->event_type & HVPIPE_MSG_AVAILABLE)
+			queue_work(papr_hvpipe_wq, papr_hvpipe_work);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * Enable hvpipe by system parameter set with parameter
+ * token = 64 and with 1 byte buffer data:
+ * 0 = hvpipe not in use/disable
+ * 1 = hvpipe in use/enable
+ */
+static int set_hvpipe_sys_param(u8 val)
+{
+	struct papr_sysparm_buf *buf;
+	int ret;
+
+	buf = papr_sysparm_buf_alloc();
+	if (!buf)
+		return -ENOMEM;
+
+	buf->len = cpu_to_be16(1);
+	buf->val[0] = val;
+	ret = papr_sysparm_set(PAPR_SYSPARM_HVPIPE_ENABLE, buf);
+	if (ret)
+		pr_err("Can not enable hvpipe %d\n", ret);
+
+	papr_sysparm_buf_free(buf);
+
+	return ret;
+}
+
+static int __init enable_hvpipe_IRQ(void)
+{
+	struct device_node *np;
+
+	hvpipe_check_exception_token = rtas_function_token(RTAS_FN_CHECK_EXCEPTION);
+	if (hvpipe_check_exception_token  == RTAS_UNKNOWN_SERVICE)
+		return -ENODEV;
+
+	/* hvpipe events */
+	np = of_find_node_by_path("/event-sources/ibm,hvpipe-msg-events");
+	if (np != NULL) {
+		request_event_sources_irqs(np, hvpipe_event_interrupt,
+					"HPIPE_EVENT");
+		of_node_put(np);
+	} else {
+		pr_err("Can not enable hvpipe event IRQ\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+void hvpipe_migration_handler(int action)
+{
+	pr_info("hvpipe migration event %d\n", action);
+
+	/*
+	 * HVPIPE is not used (Failed to create /dev/papr-hvpipe).
+	 * So nothing to do for migration.
+	 */
+	if (!papr_hvpipe_work)
+		return;
+
+	switch (action) {
+	case HVPIPE_SUSPEND:
+		if (hvpipe_feature) {
+			/*
+			 * Disable hvpipe_feature to the user space.
+			 * It will be enabled with RESUME event.
+			 */
+			hvpipe_feature = false;
+			/*
+			 * set system parameter hvpipe 'disable'
+			 */
+			set_hvpipe_sys_param(0);
+		}
+		break;
+	case HVPIPE_RESUME:
+		/*
+		 * set system parameter hvpipe 'enable'
+		 */
+		if (!set_hvpipe_sys_param(1))
+			hvpipe_feature = true;
+		else
+			pr_err("hvpipe is not enabled after migration\n");
+
+		break;
+	}
+}
+
+static const struct file_operations papr_hvpipe_ops = {
+	.unlocked_ioctl	=	papr_hvpipe_dev_ioctl,
+};
+
+static struct miscdevice papr_hvpipe_dev = {
+	.minor	=	MISC_DYNAMIC_MINOR,
+	.name	=	"papr-hvpipe",
+	.fops	=	&papr_hvpipe_ops,
+};
+
+static int __init papr_hvpipe_init(void)
+{
+	int ret;
+
+	if (!of_find_property(rtas.dev, "ibm,hypervisor-pipe-capable",
+		NULL))
+		return -ENODEV;
+
+	if (!rtas_function_implemented(RTAS_FN_IBM_SEND_HVPIPE_MSG) ||
+		!rtas_function_implemented(RTAS_FN_IBM_RECEIVE_HVPIPE_MSG))
+		return -ENODEV;
+
+	papr_hvpipe_work = kzalloc(sizeof(struct work_struct), GFP_ATOMIC);
+	if (!papr_hvpipe_work)
+		return -ENOMEM;
+
+	INIT_WORK(papr_hvpipe_work, papr_hvpipe_work_fn);
+
+	papr_hvpipe_wq = alloc_ordered_workqueue("papr hvpipe workqueue", 0);
+	if (!papr_hvpipe_wq) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = enable_hvpipe_IRQ();
+	if (!ret) {
+		ret = set_hvpipe_sys_param(1);
+		if (!ret)
+			ret = misc_register(&papr_hvpipe_dev);
+	}
+
+	if (!ret) {
+		pr_info("hvpipe feature is enabled\n");
+		hvpipe_feature = true;
+		return 0;
+	}
+
+	pr_err("hvpipe feature is not enabled %d\n", ret);
+	destroy_workqueue(papr_hvpipe_wq);
+out:
+	kfree(papr_hvpipe_work);
+	papr_hvpipe_work = NULL;
+	return ret;
+}
+machine_device_initcall(pseries, papr_hvpipe_init);
diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.h b/arch/powerpc/platforms/pseries/papr-hvpipe.h
new file mode 100644
index 000000000000..c343f4230865
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-hvpipe.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _PAPR_HVPIPE_H
+#define _PAPR_HVPIPE_H
+
+#define	HVPIPE_HMC_ID_MASK	0x02000000 /*02-HMC,00-reserved and HMC ID */
+#define	HVPIPE_MAX_WRITE_BUFFER_SIZE	4048
+/*
+ * hvpipe specific RTAS return values
+ */
+#define	RTAS_HVPIPE_CLOSED		-4
+
+#define	HVPIPE_HDR_LEN	sizeof(struct papr_hvpipe_hdr)
+
+enum hvpipe_migrate_action {
+	HVPIPE_SUSPEND,
+	HVPIPE_RESUME,
+};
+
+struct hvpipe_source_info {
+	struct list_head list;	/* list of sources */
+	u32 srcID;
+	u32 hvpipe_status;
+	wait_queue_head_t recv_wqh;	 /* wake up poll() waitq */
+	struct task_struct *tsk;
+};
+
+/*
+ * Source ID Format 0xCCRRQQQQ
+ * CC = indicating value is source type (ex: 0x02 for HMC)
+ * RR = 0x00 (reserved)
+ * QQQQ = 0x0000 – 0xFFFF indicating the source index indetifier
+ */
+struct hvpipe_event_buf {
+	__be32	srcID;		/* Source ID */
+	u8	event_type;	/* 0x01 for hvpipe message available */
+				/* from specified src ID */
+				/* 0x02 for loss of pipe connection */
+				/* with specified src ID */
+};
+
+void hvpipe_migration_handler(int action);
+#endif /* _PAPR_HVPIPE_H */
diff --git a/arch/powerpc/platforms/pseries/papr-indices.c b/arch/powerpc/platforms/pseries/papr-indices.c
new file mode 100644
index 000000000000..3c7545591c45
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-indices.c
@@ -0,0 +1,488 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-indices: " fmt
+
+#include <linux/build_bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/lockdep.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/string_helpers.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-indices.h>
+#include "papr-rtas-common.h"
+
+/*
+ * Function-specific return values for ibm,set-dynamic-indicator and
+ * ibm,get-dynamic-sensor-state RTAS calls.
+ * PAPR+ v2.13 7.3.18 and 7.3.19.
+ */
+#define RTAS_IBM_DYNAMIC_INDICE_NO_INDICATOR	-3
+
+/**
+ * struct rtas_get_indices_params - Parameters (in and out) for
+ *                                      ibm,get-indices.
+ * @is_sensor:	In: Caller-provided whether sensor or indicator.
+ * @indice_type:In: Caller-provided indice (sensor or indicator) token
+ * @work_area:	In: Caller-provided work area buffer for results.
+ * @next:	In: Sequence number. Out: Next sequence number.
+ * @status:	Out: RTAS call status.
+ */
+struct rtas_get_indices_params {
+	u8 is_sensor;
+	u32 indice_type;
+	struct rtas_work_area *work_area;
+	u32 next;
+	s32 status;
+};
+
+/*
+ * rtas_ibm_get_indices() - Call ibm,get-indices to fill a work area buffer.
+ * @params: See &struct rtas_ibm_get_indices_params.
+ *
+ * Calls ibm,get-indices until it errors or successfully deposits data
+ * into the supplied work area. Handles RTAS retry statuses. Maps RTAS
+ * error statuses to reasonable errno values.
+ *
+ * The caller is expected to invoke rtas_ibm_get_indices() multiple times
+ * to retrieve all indices data for the provided indice type. Only one
+ * sequence should be in progress at any time; starting a new sequence
+ * will disrupt any sequence already in progress. Serialization of
+ * indices retrieval sequences is the responsibility of the caller.
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 otherwise.
+ */
+static int rtas_ibm_get_indices(struct rtas_get_indices_params *params)
+{
+	struct rtas_work_area *work_area = params->work_area;
+	const s32 token = rtas_function_token(RTAS_FN_IBM_GET_INDICES);
+	u32 rets;
+	s32 fwrc;
+	int ret;
+
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	lockdep_assert_held(&rtas_ibm_get_indices_lock);
+
+	do {
+		fwrc = rtas_call(token, 5, 2, &rets, params->is_sensor,
+				params->indice_type,
+				rtas_work_area_phys(work_area),
+				rtas_work_area_size(work_area),
+				params->next);
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER: /* Indicator type is not supported */
+		ret = -EINVAL;
+		break;
+	case RTAS_SEQ_START_OVER:
+		ret = -EAGAIN;
+		pr_info_ratelimited("Indices changed during retrieval, retrying\n");
+		params->next = 1;
+		break;
+	case RTAS_SEQ_MORE_DATA:
+		params->next = rets;
+		ret = 0;
+		break;
+	case RTAS_SEQ_COMPLETE:
+		params->next = 0;
+		ret = 0;
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,get-indices status %d\n", fwrc);
+		break;
+	}
+
+	params->status = fwrc;
+	return ret;
+}
+
+/*
+ * Internal indices sequence APIs. A sequence is a series of calls to
+ * ibm,get-indices for a given location code. The sequence ends when
+ * an error is encountered or all indices for the input has been
+ * returned.
+ */
+
+/*
+ * indices_sequence_begin() - Begin a indices retrieval sequence.
+ *
+ * Context: May sleep.
+ */
+static void indices_sequence_begin(struct papr_rtas_sequence *seq)
+{
+	struct rtas_get_indices_params  *param;
+
+	param = (struct rtas_get_indices_params *)seq->params;
+	/*
+	 * We could allocate the work area before acquiring the
+	 * function lock, but that would allow concurrent requests to
+	 * exhaust the limited work area pool for no benefit. So
+	 * allocate the work area under the lock.
+	 */
+	mutex_lock(&rtas_ibm_get_indices_lock);
+	param->work_area = rtas_work_area_alloc(RTAS_GET_INDICES_BUF_SIZE);
+	param->next = 1;
+	param->status = 0;
+}
+
+/*
+ * indices_sequence_end() - Finalize a indices retrieval sequence.
+ *
+ * Releases resources obtained by indices_sequence_begin().
+ */
+static void indices_sequence_end(struct papr_rtas_sequence *seq)
+{
+	struct rtas_get_indices_params *param;
+
+	param =  (struct rtas_get_indices_params *)seq->params;
+	rtas_work_area_free(param->work_area);
+	mutex_unlock(&rtas_ibm_get_indices_lock);
+}
+
+/*
+ * Work function to be passed to papr_rtas_blob_generate().
+ *
+ * ibm,get-indices RTAS call fills the work area with the certain
+ * format but does not return the bytes written in the buffer. So
+ * instead of kernel parsing this work area to determine the buffer
+ * length, copy the complete work area (RTAS_GET_INDICES_BUF_SIZE)
+ * to the blob and let the user space to obtain the data.
+ * Means RTAS_GET_INDICES_BUF_SIZE data will be returned for each
+ * read().
+ */
+
+static const char *indices_sequence_fill_work_area(struct papr_rtas_sequence *seq,
+						size_t *len)
+{
+	struct rtas_get_indices_params *p;
+	bool init_state;
+
+	p = (struct rtas_get_indices_params *)seq->params;
+	init_state = (p->next == 1) ? true : false;
+
+	if (papr_rtas_sequence_should_stop(seq, p->status, init_state))
+		return NULL;
+	if (papr_rtas_sequence_set_err(seq, rtas_ibm_get_indices(p)))
+		return NULL;
+
+	*len = RTAS_GET_INDICES_BUF_SIZE;
+	return rtas_work_area_raw_buf(p->work_area);
+}
+
+/*
+ * papr_indices_handle_read - returns indices blob data to the user space
+ *
+ * ibm,get-indices RTAS call fills the work area with the certian
+ * format but does not return the bytes written in the buffer and
+ * copied RTAS_GET_INDICES_BUF_SIZE data to the blob for each RTAS
+ * call. So send RTAS_GET_INDICES_BUF_SIZE buffer to the user space
+ * for each read().
+ */
+static ssize_t papr_indices_handle_read(struct file *file,
+		char __user *buf, size_t size, loff_t *off)
+{
+	const struct papr_rtas_blob *blob = file->private_data;
+
+	/* we should not instantiate a handle without any data attached. */
+	if (!papr_rtas_blob_has_data(blob)) {
+		pr_err_once("handle without data\n");
+		return -EIO;
+	}
+
+	if (size < RTAS_GET_INDICES_BUF_SIZE) {
+		pr_err_once("Invalid buffer length %ld, expect %d\n",
+				size, RTAS_GET_INDICES_BUF_SIZE);
+		return -EINVAL;
+	} else if (size > RTAS_GET_INDICES_BUF_SIZE)
+		size = RTAS_GET_INDICES_BUF_SIZE;
+
+	return simple_read_from_buffer(buf, size, off, blob->data, blob->len);
+}
+
+static const struct file_operations papr_indices_handle_ops = {
+	.read = papr_indices_handle_read,
+	.llseek = papr_rtas_common_handle_seek,
+	.release = papr_rtas_common_handle_release,
+};
+
+/*
+ * papr_indices_create_handle() - Create a fd-based handle for reading
+ *                                indices data
+ * @ubuf: Input parameters to RTAS call such as whether sensor or indicator
+ *        and indice type in user memory
+ *
+ * Handler for PAPR_INDICES_IOC_GET ioctl command. Validates @ubuf
+ * and instantiates an immutable indices "blob" for it. The blob is
+ * attached to a file descriptor for reading by user space. The memory
+ * backing the blob is freed when the file is released.
+ *
+ * The entire requested indices is retrieved by this call and all
+ * necessary RTAS interactions are performed before returning the fd
+ * to user space. This keeps the read handler simple and ensures that
+ * the kernel can prevent interleaving of ibm,get-indices call sequences.
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_indices_create_handle(struct papr_indices_io_block __user *ubuf)
+{
+	struct papr_rtas_sequence seq = {};
+	struct rtas_get_indices_params params = {};
+	int fd;
+
+	if (get_user(params.is_sensor, &ubuf->indices.is_sensor))
+		return -EFAULT;
+
+	if (get_user(params.indice_type, &ubuf->indices.indice_type))
+		return -EFAULT;
+
+	seq = (struct papr_rtas_sequence) {
+		.begin = indices_sequence_begin,
+		.end = indices_sequence_end,
+		.work = indices_sequence_fill_work_area,
+	};
+
+	seq.params = &params;
+	fd = papr_rtas_setup_file_interface(&seq,
+			&papr_indices_handle_ops, "[papr-indices]");
+
+	return fd;
+}
+
+/*
+ * Create work area with the input parameters. This function is used
+ * for both ibm,set-dynamic-indicator and ibm,get-dynamic-sensor-state
+ * RTAS Calls.
+ */
+static struct rtas_work_area *
+papr_dynamic_indice_buf_from_user(struct papr_indices_io_block __user *ubuf,
+				struct papr_indices_io_block *kbuf)
+{
+	struct rtas_work_area *work_area;
+	u32 length;
+	__be32 len_be;
+
+	if (copy_from_user(kbuf, ubuf, sizeof(*kbuf)))
+		return ERR_PTR(-EFAULT);
+
+
+	if (!string_is_terminated(kbuf->dynamic_param.location_code_str,
+			ARRAY_SIZE(kbuf->dynamic_param.location_code_str)))
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * The input data in the work area should be as follows:
+	 * - 32-bit integer length of the location code string,
+	 *   including NULL.
+	 * - Location code string, NULL terminated, identifying the
+	 *   token (sensor or indicator).
+	 * PAPR 2.13 - R1–7.3.18–5 ibm,set-dynamic-indicator
+	 *           - R1–7.3.19–5 ibm,get-dynamic-sensor-state
+	 */
+	/*
+	 * Length that user space passed should also include NULL
+	 * terminator.
+	 */
+	length = strlen(kbuf->dynamic_param.location_code_str) + 1;
+	if (length > LOC_CODE_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	len_be = cpu_to_be32(length);
+
+	work_area = rtas_work_area_alloc(LOC_CODE_SIZE + sizeof(u32));
+	memcpy(rtas_work_area_raw_buf(work_area), &len_be, sizeof(u32));
+	memcpy((rtas_work_area_raw_buf(work_area) + sizeof(u32)),
+			&kbuf->dynamic_param.location_code_str, length);
+
+	return work_area;
+}
+
+/**
+ * papr_dynamic_indicator_ioc_set - ibm,set-dynamic-indicator RTAS Call
+ * PAPR 2.13 7.3.18
+ *
+ * @ubuf: Input parameters to RTAS call such as indicator token and
+ *        new state.
+ *
+ * Returns success or -errno.
+ */
+static long papr_dynamic_indicator_ioc_set(struct papr_indices_io_block __user *ubuf)
+{
+	struct papr_indices_io_block kbuf;
+	struct rtas_work_area *work_area;
+	s32 fwrc, token, ret;
+
+	token = rtas_function_token(RTAS_FN_IBM_SET_DYNAMIC_INDICATOR);
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	mutex_lock(&rtas_ibm_set_dynamic_indicator_lock);
+	work_area = papr_dynamic_indice_buf_from_user(ubuf, &kbuf);
+	if (IS_ERR(work_area)) {
+		ret = PTR_ERR(work_area);
+		goto out;
+	}
+
+	do {
+		fwrc = rtas_call(token, 3, 1, NULL,
+				kbuf.dynamic_param.token,
+				kbuf.dynamic_param.state,
+				rtas_work_area_phys(work_area));
+	} while (rtas_busy_delay(fwrc));
+
+	rtas_work_area_free(work_area);
+
+	switch (fwrc) {
+	case RTAS_SUCCESS:
+		ret = 0;
+		break;
+	case RTAS_IBM_DYNAMIC_INDICE_NO_INDICATOR:	/* No such indicator */
+		ret = -EOPNOTSUPP;
+		break;
+	default:
+		pr_err("unexpected ibm,set-dynamic-indicator result %d\n",
+			fwrc);
+		fallthrough;
+	case RTAS_HARDWARE_ERROR:	/* Hardware/platform error */
+		ret = -EIO;
+		break;
+	}
+
+out:
+	mutex_unlock(&rtas_ibm_set_dynamic_indicator_lock);
+	return ret;
+}
+
+/**
+ * papr_dynamic_sensor_ioc_get - ibm,get-dynamic-sensor-state RTAS Call
+ * PAPR 2.13 7.3.19
+ *
+ * @ubuf: Input parameters to RTAS call such as sensor token
+ *        Copies the state in user space buffer.
+ *
+ *
+ * Returns success or -errno.
+ */
+
+static long papr_dynamic_sensor_ioc_get(struct papr_indices_io_block __user *ubuf)
+{
+	struct papr_indices_io_block kbuf;
+	struct rtas_work_area *work_area;
+	s32 fwrc, token, ret;
+	u32 rets;
+
+	token = rtas_function_token(RTAS_FN_IBM_GET_DYNAMIC_SENSOR_STATE);
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	mutex_lock(&rtas_ibm_get_dynamic_sensor_state_lock);
+	work_area = papr_dynamic_indice_buf_from_user(ubuf, &kbuf);
+	if (IS_ERR(work_area)) {
+		ret = PTR_ERR(work_area);
+		goto out;
+	}
+
+	do {
+		fwrc = rtas_call(token, 2, 2, &rets,
+				kbuf.dynamic_param.token,
+				rtas_work_area_phys(work_area));
+	} while (rtas_busy_delay(fwrc));
+
+	rtas_work_area_free(work_area);
+
+	switch (fwrc) {
+	case RTAS_SUCCESS:
+		if (put_user(rets, &ubuf->dynamic_param.state))
+			ret = -EFAULT;
+		else
+			ret = 0;
+		break;
+	case RTAS_IBM_DYNAMIC_INDICE_NO_INDICATOR:	/* No such indicator */
+		ret = -EOPNOTSUPP;
+		break;
+	default:
+		pr_err("unexpected ibm,get-dynamic-sensor result %d\n",
+				fwrc);
+		fallthrough;
+	case RTAS_HARDWARE_ERROR:	/* Hardware/platform error */
+		ret = -EIO;
+		break;
+	}
+
+out:
+	mutex_unlock(&rtas_ibm_get_dynamic_sensor_state_lock);
+	return ret;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-indices.
+ */
+static long papr_indices_dev_ioctl(struct file *filp, unsigned int ioctl,
+				unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_INDICES_IOC_GET:
+		ret = papr_indices_create_handle(argp);
+		break;
+	case PAPR_DYNAMIC_SENSOR_IOC_GET:
+		ret = papr_dynamic_sensor_ioc_get(argp);
+		break;
+	case PAPR_DYNAMIC_INDICATOR_IOC_SET:
+		if (filp->f_mode & FMODE_WRITE)
+			ret = papr_dynamic_indicator_ioc_set(argp);
+		else
+			ret = -EBADF;
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+
+	return ret;
+}
+
+static const struct file_operations papr_indices_ops = {
+	.unlocked_ioctl = papr_indices_dev_ioctl,
+};
+
+static struct miscdevice papr_indices_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-indices",
+	.fops = &papr_indices_ops,
+};
+
+static __init int papr_indices_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_INDICES))
+		return -ENODEV;
+
+	if (!rtas_function_implemented(RTAS_FN_IBM_SET_DYNAMIC_INDICATOR))
+		return -ENODEV;
+
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_DYNAMIC_SENSOR_STATE))
+		return -ENODEV;
+
+	return misc_register(&papr_indices_dev);
+}
+machine_device_initcall(pseries, papr_indices_init);
diff --git a/arch/powerpc/platforms/pseries/papr-phy-attest.c b/arch/powerpc/platforms/pseries/papr-phy-attest.c
new file mode 100644
index 000000000000..1907f2411567
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-phy-attest.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-phy-attest: " fmt
+
+#include <linux/build_bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/lockdep.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/string_helpers.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-physical-attestation.h>
+#include "papr-rtas-common.h"
+
+/**
+ * struct rtas_phy_attest_params - Parameters (in and out) for
+ * ibm,physical-attestation.
+ *
+ * @cmd:  In: Caller-provided attestation command buffer. Must be
+ *        RTAS-addressable.
+ * @work_area: In: Caller-provided work area buffer for attestation
+ *             command structure
+ *             Out: Caller-provided work area buffer for the response
+ * @cmd_len:   In: Caller-provided attestation command structure
+ *             length
+ * @sequence:  In: Sequence number. Out: Next sequence number.
+ * @written:   Out: Bytes written by ibm,physical-attestation to
+ *             @work_area.
+ * @status:    Out: RTAS call status.
+ */
+struct rtas_phy_attest_params {
+	struct papr_phy_attest_io_block cmd;
+	struct rtas_work_area *work_area;
+	u32 cmd_len;
+	u32 sequence;
+	u32 written;
+	s32 status;
+};
+
+/**
+ * rtas_physical_attestation() - Call ibm,physical-attestation to
+ * fill a work area buffer.
+ * @params: See &struct rtas_phy_attest_params.
+ *
+ * Calls ibm,physical-attestation until it errors or successfully
+ * deposits data into the supplied work area. Handles RTAS retry
+ * statuses. Maps RTAS error statuses to reasonable errno values.
+ *
+ * The caller is expected to invoke rtas_physical_attestation()
+ * multiple times to retrieve all the data for the provided
+ * attestation command. Only one sequence should be in progress at
+ * any time; starting a new sequence will disrupt any sequence
+ * already in progress. Serialization of attestation retrieval
+ * sequences is the responsibility of the caller.
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 otherwise.
+ */
+static int rtas_physical_attestation(struct rtas_phy_attest_params *params)
+{
+	struct rtas_work_area *work_area;
+	s32 fwrc, token;
+	u32 rets[2];
+	int ret;
+
+	work_area = params->work_area;
+	token = rtas_function_token(RTAS_FN_IBM_PHYSICAL_ATTESTATION);
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return -ENOENT;
+
+	lockdep_assert_held(&rtas_ibm_physical_attestation_lock);
+
+	do {
+		fwrc = rtas_call(token, 3, 3, rets,
+				 rtas_work_area_phys(work_area),
+				 params->cmd_len,
+				 params->sequence);
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER:
+		ret = -EINVAL;
+		break;
+	case RTAS_SEQ_MORE_DATA:
+		params->sequence = rets[0];
+		fallthrough;
+	case RTAS_SEQ_COMPLETE:
+		params->written = rets[1];
+		/*
+		 * Kernel or firmware bug, do not continue.
+		 */
+		if (WARN(params->written > rtas_work_area_size(work_area),
+			 "possible write beyond end of work area"))
+			ret = -EFAULT;
+		else
+			ret = 0;
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,get-phy_attest status %d\n", fwrc);
+		break;
+	}
+
+	params->status = fwrc;
+	return ret;
+}
+
+/*
+ * Internal physical-attestation sequence APIs. A physical-attestation
+ * sequence is a series of calls to get ibm,physical-attestation
+ * for a given attestation command. The sequence ends when an error
+ * is encountered or all data for the attestation command has been
+ * returned.
+ */
+
+/**
+ * phy_attest_sequence_begin() - Begin a response data for attestation
+ * command retrieval sequence.
+ * @seq: user specified parameters for RTAS call from seq struct.
+ *
+ * Context: May sleep.
+ */
+static void phy_attest_sequence_begin(struct papr_rtas_sequence *seq)
+{
+	struct rtas_phy_attest_params *param;
+
+	/*
+	 * We could allocate the work area before acquiring the
+	 * function lock, but that would allow concurrent requests to
+	 * exhaust the limited work area pool for no benefit. So
+	 * allocate the work area under the lock.
+	 */
+	mutex_lock(&rtas_ibm_physical_attestation_lock);
+	param =  (struct rtas_phy_attest_params *)seq->params;
+	param->work_area = rtas_work_area_alloc(SZ_4K);
+	memcpy(rtas_work_area_raw_buf(param->work_area), &param->cmd,
+			param->cmd_len);
+	param->sequence = 1;
+	param->status = 0;
+}
+
+/**
+ * phy_attest_sequence_end() - Finalize a attestation command
+ * response retrieval sequence.
+ * @seq: Sequence state.
+ *
+ * Releases resources obtained by phy_attest_sequence_begin().
+ */
+static void phy_attest_sequence_end(struct papr_rtas_sequence *seq)
+{
+	struct rtas_phy_attest_params *param;
+
+	param =  (struct rtas_phy_attest_params *)seq->params;
+	rtas_work_area_free(param->work_area);
+	mutex_unlock(&rtas_ibm_physical_attestation_lock);
+	kfree(param);
+}
+
+/*
+ * Generator function to be passed to papr_rtas_blob_generate().
+ */
+static const char *phy_attest_sequence_fill_work_area(struct papr_rtas_sequence *seq,
+						size_t *len)
+{
+	struct rtas_phy_attest_params *p;
+	bool init_state;
+
+	p = (struct rtas_phy_attest_params *)seq->params;
+	init_state = (p->written == 0) ? true : false;
+
+	if (papr_rtas_sequence_should_stop(seq, p->status, init_state))
+		return NULL;
+	if (papr_rtas_sequence_set_err(seq, rtas_physical_attestation(p)))
+		return NULL;
+	*len = p->written;
+	return rtas_work_area_raw_buf(p->work_area);
+}
+
+static const struct file_operations papr_phy_attest_handle_ops = {
+	.read = papr_rtas_common_handle_read,
+	.llseek = papr_rtas_common_handle_seek,
+	.release = papr_rtas_common_handle_release,
+};
+
+/**
+ * papr_phy_attest_create_handle() - Create a fd-based handle for
+ * reading the response for the given attestation command.
+ * @ulc: Attestation command in user memory; defines the scope of
+ *       data for the attestation command to retrieve.
+ *
+ * Handler for PAPR_PHYSICAL_ATTESTATION_IOC_CREATE_HANDLE ioctl
+ * command. Validates @ulc and instantiates an immutable response
+ * "blob" for attestation command. The blob is attached to a file
+ * descriptor for reading by user space. The memory backing the blob
+ * is freed when the file is released.
+ *
+ * The entire requested response buffer for the attestation command
+ * retrieved by this call and all necessary RTAS interactions are
+ * performed before returning the fd to user space. This keeps the
+ * read handler simple and ensures that kernel can prevent
+ * interleaving ibm,physical-attestation call sequences.
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_phy_attest_create_handle(struct papr_phy_attest_io_block __user *ulc)
+{
+	struct rtas_phy_attest_params *params;
+	struct papr_rtas_sequence seq = {};
+	int fd;
+
+	/*
+	 * Freed in phy_attest_sequence_end().
+	 */
+	params =  kzalloc(sizeof(*params), GFP_KERNEL_ACCOUNT);
+	if (!params)
+		return -ENOMEM;
+
+	if (copy_from_user(&params->cmd, ulc,
+			sizeof(struct papr_phy_attest_io_block)))
+		return -EFAULT;
+
+	params->cmd_len = be32_to_cpu(params->cmd.length);
+	seq = (struct papr_rtas_sequence) {
+		.begin = phy_attest_sequence_begin,
+		.end = phy_attest_sequence_end,
+		.work = phy_attest_sequence_fill_work_area,
+	};
+
+	seq.params = (void *)params;
+
+	fd = papr_rtas_setup_file_interface(&seq,
+			&papr_phy_attest_handle_ops,
+			"[papr-physical-attestation]");
+
+	return fd;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-physical-attestation.
+ */
+static long papr_phy_attest_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_PHY_ATTEST_IOC_HANDLE:
+		ret = papr_phy_attest_create_handle(argp);
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_phy_attest_ops = {
+	.unlocked_ioctl = papr_phy_attest_dev_ioctl,
+};
+
+static struct miscdevice papr_phy_attest_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-physical-attestation",
+	.fops = &papr_phy_attest_ops,
+};
+
+static __init int papr_phy_attest_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_PHYSICAL_ATTESTATION))
+		return -ENODEV;
+
+	return misc_register(&papr_phy_attest_dev);
+}
+machine_device_initcall(pseries, papr_phy_attest_init);
diff --git a/arch/powerpc/platforms/pseries/papr-platform-dump.c b/arch/powerpc/platforms/pseries/papr-platform-dump.c
new file mode 100644
index 000000000000..be633c9a0e75
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-platform-dump.c
@@ -0,0 +1,397 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-platform-dump: " fmt
+
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <asm/machdep.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-platform-dump.h>
+
+/*
+ * Function-specific return values for ibm,platform-dump, derived from
+ * PAPR+ v2.13 7.3.3.4.1 "ibm,platform-dump RTAS Call".
+ */
+#define	RTAS_IBM_PLATFORM_DUMP_COMPLETE	0	/* Complete dump retrieved. */
+#define	RTAS_IBM_PLATFORM_DUMP_CONTINUE	1	/* Continue dump */
+#define	RTAS_NOT_AUTHORIZED		-9002	/* Not Authorized */
+
+#define	RTAS_IBM_PLATFORM_DUMP_START	2 /* Linux status to start dump */
+
+/**
+ * struct ibm_platform_dump_params - Parameters (in and out) for
+ *                                              ibm,platform-dump
+ * @work_area:		In: work area buffer for results.
+ * @buf_length:		In: work area buffer length in bytes
+ * @dump_tag_hi:	In: Most-significant 32 bits of a Dump_Tag representing
+ *                      an id of the dump being processed.
+ * @dump_tag_lo:	In: Least-significant 32 bits of a Dump_Tag representing
+ *                      an id of the dump being processed.
+ * @sequence_hi:	In: Sequence number in most-significant 32 bits.
+ *                      Out: Next sequence number in most-significant 32 bits.
+ * @sequence_lo:	In: Sequence number in Least-significant 32 bits
+ *                      Out: Next sequence number in Least-significant 32 bits.
+ * @bytes_ret_hi:	Out: Bytes written in most-significant 32 bits.
+ * @bytes_ret_lo:	Out: Bytes written in Least-significant 32 bits.
+ * @status:		Out: RTAS call status.
+ * @list:		Maintain the list of dumps are in progress. Can
+ *                      retrieve multiple dumps with different dump IDs at
+ *                      the same time but not with the same dump ID. This list
+ *                      is used to determine whether the dump for the same ID
+ *                      is in progress.
+ */
+struct ibm_platform_dump_params {
+	struct rtas_work_area	*work_area;
+	u32			buf_length;
+	u32			dump_tag_hi;
+	u32			dump_tag_lo;
+	u32			sequence_hi;
+	u32			sequence_lo;
+	u32			bytes_ret_hi;
+	u32			bytes_ret_lo;
+	s32			status;
+	struct list_head	list;
+};
+
+/*
+ * Multiple dumps with different dump IDs can be retrieved at the same
+ * time, but not with dame dump ID. platform_dump_list_mutex and
+ * platform_dump_list are used to prevent this behavior.
+ */
+static DEFINE_MUTEX(platform_dump_list_mutex);
+static LIST_HEAD(platform_dump_list);
+
+/**
+ * rtas_ibm_platform_dump() - Call ibm,platform-dump to fill a work area
+ * buffer.
+ * @params: See &struct ibm_platform_dump_params.
+ * @buf_addr: Address of dump buffer (work_area)
+ * @buf_length: Length of the buffer in bytes (min. 1024)
+ *
+ * Calls ibm,platform-dump until it errors or successfully deposits data
+ * into the supplied work area. Handles RTAS retry statuses. Maps RTAS
+ * error statuses to reasonable errno values.
+ *
+ * Can request multiple dumps with different dump IDs at the same time,
+ * but not with the same dump ID which is prevented with the check in
+ * the ioctl code (papr_platform_dump_create_handle()).
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 for dump complete and 1 for continue dump
+ */
+static int rtas_ibm_platform_dump(struct ibm_platform_dump_params *params,
+				phys_addr_t buf_addr, u32 buf_length)
+{
+	u32 rets[4];
+	s32 fwrc;
+	int ret = 0;
+
+	do {
+		fwrc = rtas_call(rtas_function_token(RTAS_FN_IBM_PLATFORM_DUMP),
+				6, 5,
+				rets,
+				params->dump_tag_hi,
+				params->dump_tag_lo,
+				params->sequence_hi,
+				params->sequence_lo,
+				buf_addr,
+				buf_length);
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_NOT_AUTHORIZED:
+		ret = -EPERM;
+		break;
+	case RTAS_IBM_PLATFORM_DUMP_CONTINUE:
+	case RTAS_IBM_PLATFORM_DUMP_COMPLETE:
+		params->sequence_hi = rets[0];
+		params->sequence_lo = rets[1];
+		params->bytes_ret_hi = rets[2];
+		params->bytes_ret_lo = rets[3];
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,platform-dump status %d\n",
+				fwrc);
+		break;
+	}
+
+	params->status = fwrc;
+	return ret;
+}
+
+/*
+ * Platform dump is used with multiple RTAS calls to retrieve the
+ * complete dump for the provided dump ID. Once the complete dump is
+ * retrieved, the hypervisor returns dump complete status (0) for the
+ * last RTAS call and expects the caller issues one more call with
+ * NULL buffer to invalidate the dump so that the hypervisor can remove
+ * the dump.
+ *
+ * After the specific dump is invalidated in the hypervisor, expect the
+ * dump complete status for the new sequence - the user space initiates
+ * new request for the same dump ID.
+ */
+static ssize_t papr_platform_dump_handle_read(struct file *file,
+		char __user *buf, size_t size, loff_t *off)
+{
+	struct ibm_platform_dump_params *params = file->private_data;
+	u64 total_bytes;
+	s32 fwrc;
+
+	/*
+	 * Dump already completed with the previous read calls.
+	 * In case if the user space issues further reads, returns
+	 * -EINVAL.
+	 */
+	if (!params->buf_length) {
+		pr_warn_once("Platform dump completed for dump ID %llu\n",
+			(u64) (((u64)params->dump_tag_hi << 32) |
+				params->dump_tag_lo));
+		return -EINVAL;
+	}
+
+	/*
+	 * The hypervisor returns status 0 if no more data available to
+	 * download. The dump will be invalidated with ioctl (see below).
+	 */
+	if (params->status == RTAS_IBM_PLATFORM_DUMP_COMPLETE) {
+		params->buf_length = 0;
+		/*
+		 * Returns 0 to the user space so that user
+		 * space read stops.
+		 */
+		return 0;
+	}
+
+	if (size < SZ_1K) {
+		pr_err_once("Buffer length should be minimum 1024 bytes\n");
+		return -EINVAL;
+	} else if (size > params->buf_length) {
+		/*
+		 * Allocate 4K work area. So if the user requests > 4K,
+		 * resize the buffer length.
+		 */
+		size = params->buf_length;
+	}
+
+	fwrc = rtas_ibm_platform_dump(params,
+			rtas_work_area_phys(params->work_area),
+			size);
+	if (fwrc < 0)
+		return fwrc;
+
+	total_bytes = (u64) (((u64)params->bytes_ret_hi << 32) |
+			params->bytes_ret_lo);
+
+	/*
+	 * Kernel or firmware bug, do not continue.
+	 */
+	if (WARN(total_bytes > size, "possible write beyond end of work area"))
+		return -EFAULT;
+
+	if (copy_to_user(buf, rtas_work_area_raw_buf(params->work_area),
+			total_bytes))
+		return -EFAULT;
+
+	return total_bytes;
+}
+
+static int papr_platform_dump_handle_release(struct inode *inode,
+					struct file *file)
+{
+	struct ibm_platform_dump_params *params = file->private_data;
+
+	if (params->work_area)
+		rtas_work_area_free(params->work_area);
+
+	mutex_lock(&platform_dump_list_mutex);
+	list_del(&params->list);
+	mutex_unlock(&platform_dump_list_mutex);
+
+	kfree(params);
+	file->private_data = NULL;
+	return 0;
+}
+
+/*
+ * This ioctl is used to invalidate the dump assuming the user space
+ * issue this ioctl after obtain the complete dump.
+ * Issue the last RTAS call with NULL buffer to invalidate the dump
+ * which means dump will be freed in the hypervisor.
+ */
+static long papr_platform_dump_invalidate_ioctl(struct file *file,
+				unsigned int ioctl, unsigned long arg)
+{
+	struct ibm_platform_dump_params *params;
+	u64 __user *argp = (void __user *)arg;
+	u64 param_dump_tag, dump_tag;
+
+	if (ioctl != PAPR_PLATFORM_DUMP_IOC_INVALIDATE)
+		return -ENOIOCTLCMD;
+
+	if (get_user(dump_tag, argp))
+		return -EFAULT;
+
+	/*
+	 * private_data is freeded during release(), so should not
+	 * happen.
+	 */
+	if (!file->private_data) {
+		pr_err("No valid FD to invalidate dump for the ID(%llu)\n",
+				dump_tag);
+		return -EINVAL;
+	}
+
+	params = file->private_data;
+	param_dump_tag = (u64) (((u64)params->dump_tag_hi << 32) |
+				params->dump_tag_lo);
+	if (dump_tag != param_dump_tag) {
+		pr_err("Invalid dump ID(%llu) to invalidate dump\n",
+				dump_tag);
+		return -EINVAL;
+	}
+
+	if (params->status != RTAS_IBM_PLATFORM_DUMP_COMPLETE) {
+		pr_err("Platform dump is not complete, but requested "
+			"to invalidate dump for ID(%llu)\n",
+			dump_tag);
+		return -EINPROGRESS;
+	}
+
+	return rtas_ibm_platform_dump(params, 0, 0);
+}
+
+static const struct file_operations papr_platform_dump_handle_ops = {
+	.read = papr_platform_dump_handle_read,
+	.release = papr_platform_dump_handle_release,
+	.unlocked_ioctl	= papr_platform_dump_invalidate_ioctl,
+};
+
+/**
+ * papr_platform_dump_create_handle() - Create a fd-based handle for
+ * reading platform dump
+ *
+ * Handler for PAPR_PLATFORM_DUMP_IOC_CREATE_HANDLE ioctl command
+ * Allocates RTAS parameter struct and work area and attached to the
+ * file descriptor for reading by user space with the multiple RTAS
+ * calls until the dump is completed. This memory allocation is freed
+ * when the file is released.
+ *
+ * Multiple dump requests with different IDs are allowed at the same
+ * time, but not with the same dump ID. So if the user space is
+ * already opened file descriptor for the specific dump ID, return
+ * -EALREADY for the next request.
+ *
+ * @dump_tag: Dump ID for the dump requested to retrieve from the
+ *		hypervisor
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_platform_dump_create_handle(u64 dump_tag)
+{
+	struct ibm_platform_dump_params *params;
+	u64 param_dump_tag;
+	int fd;
+
+	/*
+	 * Return failure if the user space is already opened FD for
+	 * the specific dump ID. This check will prevent multiple dump
+	 * requests for the same dump ID at the same time. Generally
+	 * should not expect this, but in case.
+	 */
+	list_for_each_entry(params, &platform_dump_list, list) {
+		param_dump_tag = (u64) (((u64)params->dump_tag_hi << 32) |
+					params->dump_tag_lo);
+		if (dump_tag == param_dump_tag) {
+			pr_err("Platform dump for ID(%llu) is already in progress\n",
+					dump_tag);
+			return -EALREADY;
+		}
+	}
+
+	params =  kzalloc(sizeof(struct ibm_platform_dump_params),
+			GFP_KERNEL_ACCOUNT);
+	if (!params)
+		return -ENOMEM;
+
+	params->work_area = rtas_work_area_alloc(SZ_4K);
+	params->buf_length = SZ_4K;
+	params->dump_tag_hi = (u32)(dump_tag >> 32);
+	params->dump_tag_lo = (u32)(dump_tag & 0x00000000ffffffffULL);
+	params->status = RTAS_IBM_PLATFORM_DUMP_START;
+
+	fd = FD_ADD(O_RDONLY | O_CLOEXEC,
+		    anon_inode_getfile_fmode("[papr-platform-dump]",
+					     &papr_platform_dump_handle_ops,
+					     (void *)params, O_RDONLY,
+					     FMODE_LSEEK | FMODE_PREAD));
+	if (fd < 0) {
+		rtas_work_area_free(params->work_area);
+		kfree(params);
+		return fd;
+	}
+
+	list_add(&params->list, &platform_dump_list);
+
+	pr_info("%s (%d) initiated platform dump for dump tag %llu\n",
+		current->comm, current->pid, dump_tag);
+	return fd;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-platform-dump.
+ */
+static long papr_platform_dump_dev_ioctl(struct file *filp,
+					unsigned int ioctl,
+					unsigned long arg)
+{
+	u64 __user *argp = (void __user *)arg;
+	u64 dump_tag;
+	long ret;
+
+	if (get_user(dump_tag, argp))
+		return -EFAULT;
+
+	switch (ioctl) {
+	case PAPR_PLATFORM_DUMP_IOC_CREATE_HANDLE:
+		mutex_lock(&platform_dump_list_mutex);
+		ret = papr_platform_dump_create_handle(dump_tag);
+		mutex_unlock(&platform_dump_list_mutex);
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_platform_dump_ops = {
+	.unlocked_ioctl = papr_platform_dump_dev_ioctl,
+};
+
+static struct miscdevice papr_platform_dump_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-platform-dump",
+	.fops = &papr_platform_dump_ops,
+};
+
+static __init int papr_platform_dump_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_PLATFORM_DUMP))
+		return -ENODEV;
+
+	return misc_register(&papr_platform_dump_dev);
+}
+machine_device_initcall(pseries, papr_platform_dump_init);
diff --git a/arch/powerpc/platforms/pseries/papr-rtas-common.c b/arch/powerpc/platforms/pseries/papr-rtas-common.c
new file mode 100644
index 000000000000..1630e0cd210c
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-rtas-common.c
@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-common: " fmt
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/sched/signal.h>
+#include "papr-rtas-common.h"
+
+/*
+ * Sequence based RTAS HCALL has to issue multiple times to retrieve
+ * complete data from the hypervisor. For some of these RTAS calls,
+ * the OS should not interleave calls with different input until the
+ * sequence is completed. So data is collected for these calls during
+ * ioctl handle and export to user space with read() handle.
+ * This file provides common functions needed for such sequence based
+ * RTAS calls Ex: ibm,get-vpd and ibm,get-indices.
+ */
+
+bool papr_rtas_blob_has_data(const struct papr_rtas_blob *blob)
+{
+	return blob->data && blob->len;
+}
+
+void papr_rtas_blob_free(const struct papr_rtas_blob *blob)
+{
+	if (blob) {
+		kvfree(blob->data);
+		kfree(blob);
+	}
+}
+
+/**
+ * papr_rtas_blob_extend() - Append data to a &struct papr_rtas_blob.
+ * @blob: The blob to extend.
+ * @data: The new data to append to @blob.
+ * @len:  The length of @data.
+ *
+ * Context: May sleep.
+ * Return: -ENOMEM on allocation failure, 0 otherwise.
+ */
+static int papr_rtas_blob_extend(struct papr_rtas_blob *blob,
+				const char *data, size_t len)
+{
+	const size_t new_len = blob->len + len;
+	const size_t old_len = blob->len;
+	const char *old_ptr = blob->data;
+	char *new_ptr;
+
+	new_ptr = kvrealloc(old_ptr, new_len, GFP_KERNEL_ACCOUNT);
+	if (!new_ptr)
+		return -ENOMEM;
+
+	memcpy(&new_ptr[old_len], data, len);
+	blob->data = new_ptr;
+	blob->len = new_len;
+	return 0;
+}
+
+/**
+ * papr_rtas_blob_generate() - Construct a new &struct papr_rtas_blob.
+ * @seq: work function of the caller that is called to obtain
+ *       data with the caller RTAS call.
+ *
+ * The @work callback is invoked until it returns NULL. @seq is
+ * passed to @work in its first argument on each call. When
+ * @work returns data, it should store the data length in its
+ * second argument.
+ *
+ * Context: May sleep.
+ * Return: A completely populated &struct papr_rtas_blob, or NULL on error.
+ */
+static const struct papr_rtas_blob *
+papr_rtas_blob_generate(struct papr_rtas_sequence *seq)
+{
+	struct papr_rtas_blob *blob;
+	const char *buf;
+	size_t len;
+	int err = 0;
+
+	blob  = kzalloc(sizeof(*blob), GFP_KERNEL_ACCOUNT);
+	if (!blob)
+		return NULL;
+
+	if (!seq->work)
+		return ERR_PTR(-EINVAL);
+
+
+	while (err == 0 && (buf = seq->work(seq, &len)))
+		err = papr_rtas_blob_extend(blob, buf, len);
+
+	if (err != 0 || !papr_rtas_blob_has_data(blob))
+		goto free_blob;
+
+	return blob;
+free_blob:
+	papr_rtas_blob_free(blob);
+	return NULL;
+}
+
+int papr_rtas_sequence_set_err(struct papr_rtas_sequence *seq, int err)
+{
+	/* Preserve the first error recorded. */
+	if (seq->error == 0)
+		seq->error = err;
+
+	return seq->error;
+}
+
+/*
+ * Higher-level retrieval code below. These functions use the
+ * papr_rtas_blob_* and sequence_* APIs defined above to create fd-based
+ * handles for consumption by user space.
+ */
+
+/**
+ * papr_rtas_run_sequence() - Run a single retrieval sequence.
+ * @seq:	Functions of the caller to complete the sequence
+ *
+ * Context: May sleep. Holds a mutex and an RTAS work area for its
+ *          duration. Typically performs multiple sleepable slab
+ *          allocations.
+ *
+ * Return: A populated &struct papr_rtas_blob on success. Encoded error
+ * pointer otherwise.
+ */
+static const struct papr_rtas_blob *papr_rtas_run_sequence(struct papr_rtas_sequence *seq)
+{
+	const struct papr_rtas_blob *blob;
+
+	if (seq->begin)
+		seq->begin(seq);
+
+	blob = papr_rtas_blob_generate(seq);
+	if (!blob)
+		papr_rtas_sequence_set_err(seq, -ENOMEM);
+
+	if (seq->end)
+		seq->end(seq);
+
+
+	if (seq->error) {
+		papr_rtas_blob_free(blob);
+		return ERR_PTR(seq->error);
+	}
+
+	return blob;
+}
+
+/**
+ * papr_rtas_retrieve() - Return the data blob that is exposed to
+ * user space.
+ * @seq: RTAS call specific functions to be invoked until the
+ *       sequence is completed.
+ *
+ * Run sequences against @param until a blob is successfully
+ * instantiated, or a hard error is encountered, or a fatal signal is
+ * pending.
+ *
+ * Context: May sleep.
+ * Return: A fully populated data blob when successful. Encoded error
+ * pointer otherwise.
+ */
+const struct papr_rtas_blob *papr_rtas_retrieve(struct papr_rtas_sequence *seq)
+{
+	const struct papr_rtas_blob *blob;
+
+	/*
+	 * EAGAIN means the sequence returns error with a -4 (data
+	 * changed and need to start the sequence) status from RTAS calls
+	 * and we should attempt a new sequence. PAPR+ (v2.13 R1–7.3.20–5
+	 * - ibm,get-vpd, R1–7.3.17–6 - ibm,get-indices) indicates that
+	 * this should be a transient condition, not something that
+	 * happens continuously. But we'll stop trying on a fatal signal.
+	 */
+	do {
+		blob = papr_rtas_run_sequence(seq);
+		if (!IS_ERR(blob)) /* Success. */
+			break;
+		if (PTR_ERR(blob) != -EAGAIN) /* Hard error. */
+			break;
+		cond_resched();
+	} while (!fatal_signal_pending(current));
+
+	return blob;
+}
+
+/**
+ * papr_rtas_setup_file_interface - Complete the sequence and obtain
+ * the data and export to user space with fd-based handles. Then the
+ * user spave gets the data with read() handle.
+ * @seq: RTAS call specific functions to get the data.
+ * @fops: RTAS call specific file operations such as read().
+ * @name: RTAS call specific char device node.
+ *
+ * Return: FD handle for consumption by user space
+ */
+long papr_rtas_setup_file_interface(struct papr_rtas_sequence *seq,
+				const struct file_operations *fops,
+				char *name)
+{
+	const struct papr_rtas_blob *blob;
+	int fd;
+
+	blob = papr_rtas_retrieve(seq);
+	if (IS_ERR(blob))
+		return PTR_ERR(blob);
+
+	fd = FD_ADD(O_RDONLY | O_CLOEXEC,
+		   anon_inode_getfile_fmode(name, fops, (void *)blob, O_RDONLY,
+					    FMODE_LSEEK | FMODE_PREAD));
+	if (fd < 0)
+		papr_rtas_blob_free(blob);
+	return fd;
+}
+
+/*
+ * papr_rtas_sequence_should_stop() - Determine whether RTAS retrieval
+ *                                    sequence should continue.
+ *
+ * Examines the sequence error state and outputs of the last call to
+ * the specific RTAS to determine whether the sequence in progress
+ * should continue or stop.
+ *
+ * Return: True if the sequence has encountered an error or if all data
+ *         for this sequence has been retrieved. False otherwise.
+ */
+bool papr_rtas_sequence_should_stop(const struct papr_rtas_sequence *seq,
+				s32 status, bool init_state)
+{
+	bool done;
+
+	if (seq->error)
+		return true;
+
+	switch (status) {
+	case RTAS_SEQ_COMPLETE:
+		if (init_state)
+			done = false; /* Initial state. */
+		else
+			done = true; /* All data consumed. */
+		break;
+	case RTAS_SEQ_MORE_DATA:
+		done = false; /* More data available. */
+		break;
+	default:
+		done = true; /* Error encountered. */
+		break;
+	}
+
+	return done;
+}
+
+/*
+ * User space read to retrieve data for the corresponding RTAS call.
+ * papr_rtas_blob is filled with the data using the corresponding RTAS
+ * call sequence API.
+ */
+ssize_t papr_rtas_common_handle_read(struct file *file,
+	       char __user *buf, size_t size, loff_t *off)
+{
+	const struct papr_rtas_blob *blob = file->private_data;
+
+	/* We should not instantiate a handle without any data attached. */
+	if (!papr_rtas_blob_has_data(blob)) {
+		pr_err_once("handle without data\n");
+		return -EIO;
+	}
+
+	return simple_read_from_buffer(buf, size, off, blob->data, blob->len);
+}
+
+int papr_rtas_common_handle_release(struct inode *inode,
+		struct file *file)
+{
+	const struct papr_rtas_blob *blob = file->private_data;
+
+	papr_rtas_blob_free(blob);
+
+	return 0;
+}
+
+loff_t papr_rtas_common_handle_seek(struct file *file, loff_t off,
+					int whence)
+{
+	const struct papr_rtas_blob *blob = file->private_data;
+
+	return fixed_size_llseek(file, off, whence, blob->len);
+}
diff --git a/arch/powerpc/platforms/pseries/papr-rtas-common.h b/arch/powerpc/platforms/pseries/papr-rtas-common.h
new file mode 100644
index 000000000000..4ceabcaf4905
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-rtas-common.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_POWERPC_PAPR_RTAS_COMMON_H
+#define _ASM_POWERPC_PAPR_RTAS_COMMON_H
+
+#include <linux/types.h>
+
+/*
+ * Return codes for sequence based RTAS calls.
+ * Not listed under PAPR+ v2.13 7.2.8: "Return Codes".
+ * But defined in the specific section of each RTAS call.
+ */
+#define RTAS_SEQ_COMPLETE	0 /* All data has been retrieved. */
+#define RTAS_SEQ_MORE_DATA	1 /* More data is available */
+#define RTAS_SEQ_START_OVER	-4 /* Data changed, restart call sequence. */
+
+/*
+ * Internal "blob" APIs for accumulating RTAS call results into
+ * an immutable buffer to be attached to a file descriptor.
+ */
+struct papr_rtas_blob {
+	const char *data;
+	size_t len;
+};
+
+/**
+ * struct papr_sequence - State for managing a sequence of RTAS calls.
+ * @error:  Shall be zero as long as the sequence has not encountered an error,
+ *          -ve errno otherwise. Use papr_rtas_sequence_set_err() to update.
+ * @params: Parameter block to pass to rtas_*() calls.
+ * @begin: Work area allocation and initialize the needed parameter
+ *         values passed to RTAS call
+ * @end: Free the allocated work area
+ * @work: Obtain data with RTAS call and invoke it until the sequence is
+ *        completed.
+ *
+ */
+struct papr_rtas_sequence {
+	int error;
+	void *params;
+	void (*begin)(struct papr_rtas_sequence *seq);
+	void (*end)(struct papr_rtas_sequence *seq);
+	const char *(*work)(struct papr_rtas_sequence *seq, size_t *len);
+};
+
+extern bool papr_rtas_blob_has_data(const struct papr_rtas_blob *blob);
+extern void papr_rtas_blob_free(const struct papr_rtas_blob *blob);
+extern int papr_rtas_sequence_set_err(struct papr_rtas_sequence *seq,
+		int err);
+extern const struct papr_rtas_blob *papr_rtas_retrieve(struct papr_rtas_sequence *seq);
+extern long papr_rtas_setup_file_interface(struct papr_rtas_sequence *seq,
+			const struct file_operations *fops, char *name);
+extern bool papr_rtas_sequence_should_stop(const struct papr_rtas_sequence *seq,
+				s32 status, bool init_state);
+extern ssize_t papr_rtas_common_handle_read(struct file *file,
+			char __user *buf, size_t size, loff_t *off);
+extern int papr_rtas_common_handle_release(struct inode *inode,
+					struct file *file);
+extern loff_t papr_rtas_common_handle_seek(struct file *file, loff_t off,
+					int whence);
+#endif /* _ASM_POWERPC_PAPR_RTAS_COMMON_H */
+
diff --git a/arch/powerpc/platforms/pseries/papr-sysparm.c b/arch/powerpc/platforms/pseries/papr-sysparm.c
index fedc61599e6c..7063ce8884e4 100644
--- a/arch/powerpc/platforms/pseries/papr-sysparm.c
+++ b/arch/powerpc/platforms/pseries/papr-sysparm.c
@@ -2,14 +2,20 @@
 
 #define pr_fmt(fmt)	"papr-sysparm: " fmt
 
+#include <linux/anon_inodes.h>
 #include <linux/bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/miscdevice.h>
 #include <linux/printk.h>
 #include <linux/slab.h>
-#include <asm/rtas.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
 #include <asm/papr-sysparm.h>
 #include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
 
 struct papr_sysparm_buf *papr_sysparm_buf_alloc(void)
 {
@@ -23,6 +29,46 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf)
 	kfree(buf);
 }
 
+static size_t papr_sysparm_buf_get_length(const struct papr_sysparm_buf *buf)
+{
+	return be16_to_cpu(buf->len);
+}
+
+static void papr_sysparm_buf_set_length(struct papr_sysparm_buf *buf, size_t length)
+{
+	WARN_ONCE(length > sizeof(buf->val),
+		  "bogus length %zu, clamping to safe value", length);
+	length = min(sizeof(buf->val), length);
+	buf->len = cpu_to_be16(length);
+}
+
+/*
+ * For use on buffers returned from ibm,get-system-parameter before
+ * returning them to callers. Ensures the encoded length of valid data
+ * cannot overrun buf->val[].
+ */
+static void papr_sysparm_buf_clamp_length(struct papr_sysparm_buf *buf)
+{
+	papr_sysparm_buf_set_length(buf, papr_sysparm_buf_get_length(buf));
+}
+
+/*
+ * Perform some basic diligence on the system parameter buffer before
+ * submitting it to RTAS.
+ */
+static bool papr_sysparm_buf_can_submit(const struct papr_sysparm_buf *buf)
+{
+	/*
+	 * Firmware ought to reject buffer lengths that exceed the
+	 * maximum specified in PAPR, but there's no reason for the
+	 * kernel to allow them either.
+	 */
+	if (papr_sysparm_buf_get_length(buf) > sizeof(buf->val))
+		return false;
+
+	return true;
+}
+
 /**
  * papr_sysparm_get() - Retrieve the value of a PAPR system parameter.
  * @param: PAPR system parameter token as described in
@@ -47,7 +93,6 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf)
  *
  * Return: 0 on success, -errno otherwise. @buf is unmodified on error.
  */
-
 int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
 {
 	const s32 token = rtas_function_token(RTAS_FN_IBM_GET_SYSTEM_PARAMETER);
@@ -63,6 +108,9 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
 	if (token == RTAS_UNKNOWN_SERVICE)
 		return -ENOENT;
 
+	if (!papr_sysparm_buf_can_submit(buf))
+		return -EINVAL;
+
 	work_area = rtas_work_area_alloc(sizeof(*buf));
 
 	memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf));
@@ -77,6 +125,7 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf)
 	case 0:
 		ret = 0;
 		memcpy(buf, rtas_work_area_raw_buf(work_area), sizeof(*buf));
+		papr_sysparm_buf_clamp_length(buf);
 		break;
 	case -3: /* parameter not implemented */
 		ret = -EOPNOTSUPP;
@@ -115,6 +164,9 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf)
 	if (token == RTAS_UNKNOWN_SERVICE)
 		return -ENOENT;
 
+	if (!papr_sysparm_buf_can_submit(buf))
+		return -EINVAL;
+
 	work_area = rtas_work_area_alloc(sizeof(*buf));
 
 	memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf));
@@ -149,3 +201,152 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf)
 
 	return ret;
 }
+
+static struct papr_sysparm_buf *
+papr_sysparm_buf_from_user(const struct papr_sysparm_io_block __user *user_iob)
+{
+	struct papr_sysparm_buf *kern_spbuf;
+	long err;
+	u16 len;
+
+	/*
+	 * The length of valid data that userspace claims to be in
+	 * user_iob->data[].
+	 */
+	if (get_user(len, &user_iob->length))
+		return ERR_PTR(-EFAULT);
+
+	static_assert(sizeof(user_iob->data) >= PAPR_SYSPARM_MAX_INPUT);
+	static_assert(sizeof(kern_spbuf->val) >= PAPR_SYSPARM_MAX_INPUT);
+
+	if (len > PAPR_SYSPARM_MAX_INPUT)
+		return ERR_PTR(-EINVAL);
+
+	kern_spbuf = papr_sysparm_buf_alloc();
+	if (!kern_spbuf)
+		return ERR_PTR(-ENOMEM);
+
+	papr_sysparm_buf_set_length(kern_spbuf, len);
+
+	if (len > 0 && copy_from_user(kern_spbuf->val, user_iob->data, len)) {
+		err = -EFAULT;
+		goto free_sysparm_buf;
+	}
+
+	return kern_spbuf;
+
+free_sysparm_buf:
+	papr_sysparm_buf_free(kern_spbuf);
+	return ERR_PTR(err);
+}
+
+static int papr_sysparm_buf_to_user(const struct papr_sysparm_buf *kern_spbuf,
+				    struct papr_sysparm_io_block __user *user_iob)
+{
+	u16 len_out = papr_sysparm_buf_get_length(kern_spbuf);
+
+	if (put_user(len_out, &user_iob->length))
+		return -EFAULT;
+
+	static_assert(sizeof(user_iob->data) >= PAPR_SYSPARM_MAX_OUTPUT);
+	static_assert(sizeof(kern_spbuf->val) >= PAPR_SYSPARM_MAX_OUTPUT);
+
+	if (copy_to_user(user_iob->data, kern_spbuf->val, PAPR_SYSPARM_MAX_OUTPUT))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long papr_sysparm_ioctl_get(struct papr_sysparm_io_block __user *user_iob)
+{
+	struct papr_sysparm_buf *kern_spbuf;
+	papr_sysparm_t param;
+	long ret;
+
+	if (get_user(param.token, &user_iob->parameter))
+		return -EFAULT;
+
+	kern_spbuf = papr_sysparm_buf_from_user(user_iob);
+	if (IS_ERR(kern_spbuf))
+		return PTR_ERR(kern_spbuf);
+
+	ret = papr_sysparm_get(param, kern_spbuf);
+	if (ret)
+		goto free_sysparm_buf;
+
+	ret = papr_sysparm_buf_to_user(kern_spbuf, user_iob);
+	if (ret)
+		goto free_sysparm_buf;
+
+	ret = 0;
+
+free_sysparm_buf:
+	papr_sysparm_buf_free(kern_spbuf);
+	return ret;
+}
+
+
+static long papr_sysparm_ioctl_set(struct papr_sysparm_io_block __user *user_iob)
+{
+	struct papr_sysparm_buf *kern_spbuf;
+	papr_sysparm_t param;
+	long ret;
+
+	if (get_user(param.token, &user_iob->parameter))
+		return -EFAULT;
+
+	kern_spbuf = papr_sysparm_buf_from_user(user_iob);
+	if (IS_ERR(kern_spbuf))
+		return PTR_ERR(kern_spbuf);
+
+	ret = papr_sysparm_set(param, kern_spbuf);
+	if (ret)
+		goto free_sysparm_buf;
+
+	ret = 0;
+
+free_sysparm_buf:
+	papr_sysparm_buf_free(kern_spbuf);
+	return ret;
+}
+
+static long papr_sysparm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_SYSPARM_IOC_GET:
+		ret = papr_sysparm_ioctl_get(argp);
+		break;
+	case PAPR_SYSPARM_IOC_SET:
+		if (filp->f_mode & FMODE_WRITE)
+			ret = papr_sysparm_ioctl_set(argp);
+		else
+			ret = -EBADF;
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_sysparm_ops = {
+	.unlocked_ioctl = papr_sysparm_ioctl,
+};
+
+static struct miscdevice papr_sysparm_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-sysparm",
+	.fops = &papr_sysparm_ops,
+};
+
+static __init int papr_sysparm_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_SYSTEM_PARAMETER))
+		return -ENODEV;
+
+	return misc_register(&papr_sysparm_dev);
+}
+machine_device_initcall(pseries, papr_sysparm_init);
diff --git a/arch/powerpc/platforms/pseries/papr-vpd.c b/arch/powerpc/platforms/pseries/papr-vpd.c
new file mode 100644
index 000000000000..f38c188fc4a1
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr-vpd.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "papr-vpd: " fmt
+
+#include <linux/build_bug.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/lockdep.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/string_helpers.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
+#include <asm/papr-vpd.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <uapi/asm/papr-vpd.h>
+#include "papr-rtas-common.h"
+
+/**
+ * struct rtas_ibm_get_vpd_params - Parameters (in and out) for ibm,get-vpd.
+ * @loc_code:  In: Caller-provided location code buffer. Must be RTAS-addressable.
+ * @work_area: In: Caller-provided work area buffer for results.
+ * @sequence:  In: Sequence number. Out: Next sequence number.
+ * @written:   Out: Bytes written by ibm,get-vpd to @work_area.
+ * @status:    Out: RTAS call status.
+ */
+struct rtas_ibm_get_vpd_params {
+	const struct papr_location_code *loc_code;
+	struct rtas_work_area *work_area;
+	u32 sequence;
+	u32 written;
+	s32 status;
+};
+
+/**
+ * rtas_ibm_get_vpd() - Call ibm,get-vpd to fill a work area buffer.
+ * @params: See &struct rtas_ibm_get_vpd_params.
+ *
+ * Calls ibm,get-vpd until it errors or successfully deposits data
+ * into the supplied work area. Handles RTAS retry statuses. Maps RTAS
+ * error statuses to reasonable errno values.
+ *
+ * The caller is expected to invoke rtas_ibm_get_vpd() multiple times
+ * to retrieve all the VPD for the provided location code. Only one
+ * sequence should be in progress at any time; starting a new sequence
+ * will disrupt any sequence already in progress. Serialization of VPD
+ * retrieval sequences is the responsibility of the caller.
+ *
+ * The caller should inspect @params.status to determine whether more
+ * calls are needed to complete the sequence.
+ *
+ * Context: May sleep.
+ * Return: -ve on error, 0 otherwise.
+ */
+static int rtas_ibm_get_vpd(struct rtas_ibm_get_vpd_params *params)
+{
+	const struct papr_location_code *loc_code = params->loc_code;
+	struct rtas_work_area *work_area = params->work_area;
+	u32 rets[2];
+	s32 fwrc;
+	int ret;
+
+	lockdep_assert_held(&rtas_ibm_get_vpd_lock);
+
+	do {
+		fwrc = rtas_call(rtas_function_token(RTAS_FN_IBM_GET_VPD), 4, 3,
+				 rets,
+				 __pa(loc_code),
+				 rtas_work_area_phys(work_area),
+				 rtas_work_area_size(work_area),
+				 params->sequence);
+	} while (rtas_busy_delay(fwrc));
+
+	switch (fwrc) {
+	case RTAS_HARDWARE_ERROR:
+		ret = -EIO;
+		break;
+	case RTAS_INVALID_PARAMETER:
+		ret = -EINVAL;
+		break;
+	case RTAS_SEQ_START_OVER:
+		ret = -EAGAIN;
+		pr_info_ratelimited("VPD changed during retrieval, retrying\n");
+		break;
+	case RTAS_SEQ_MORE_DATA:
+		params->sequence = rets[0];
+		fallthrough;
+	case RTAS_SEQ_COMPLETE:
+		params->written = rets[1];
+		/*
+		 * Kernel or firmware bug, do not continue.
+		 */
+		if (WARN(params->written > rtas_work_area_size(work_area),
+			 "possible write beyond end of work area"))
+			ret = -EFAULT;
+		else
+			ret = 0;
+		break;
+	default:
+		ret = -EIO;
+		pr_err_ratelimited("unexpected ibm,get-vpd status %d\n", fwrc);
+		break;
+	}
+
+	params->status = fwrc;
+	return ret;
+}
+
+/*
+ * Internal VPD sequence APIs. A VPD sequence is a series of calls to
+ * ibm,get-vpd for a given location code. The sequence ends when an
+ * error is encountered or all VPD for the location code has been
+ * returned.
+ */
+
+/**
+ * vpd_sequence_begin() - Begin a VPD retrieval sequence.
+ * @seq: vpd call parameters from sequence struct
+ *
+ * Context: May sleep.
+ */
+static void vpd_sequence_begin(struct papr_rtas_sequence *seq)
+{
+	struct rtas_ibm_get_vpd_params *vpd_params;
+	/*
+	 * Use a static data structure for the location code passed to
+	 * RTAS to ensure it's in the RMA and avoid a separate work
+	 * area allocation. Guarded by the function lock.
+	 */
+	static struct papr_location_code static_loc_code;
+
+	vpd_params =  (struct rtas_ibm_get_vpd_params *)seq->params;
+	/*
+	 * We could allocate the work area before acquiring the
+	 * function lock, but that would allow concurrent requests to
+	 * exhaust the limited work area pool for no benefit. So
+	 * allocate the work area under the lock.
+	 */
+	mutex_lock(&rtas_ibm_get_vpd_lock);
+	static_loc_code = *(struct papr_location_code *)vpd_params->loc_code;
+	vpd_params =  (struct rtas_ibm_get_vpd_params *)seq->params;
+	vpd_params->work_area = rtas_work_area_alloc(SZ_4K);
+	vpd_params->loc_code = &static_loc_code;
+	vpd_params->sequence = 1;
+	vpd_params->status = 0;
+}
+
+/**
+ * vpd_sequence_end() - Finalize a VPD retrieval sequence.
+ * @seq: Sequence state.
+ *
+ * Releases resources obtained by vpd_sequence_begin().
+ */
+static void vpd_sequence_end(struct papr_rtas_sequence *seq)
+{
+	struct rtas_ibm_get_vpd_params *vpd_params;
+
+	vpd_params =  (struct rtas_ibm_get_vpd_params *)seq->params;
+	rtas_work_area_free(vpd_params->work_area);
+	mutex_unlock(&rtas_ibm_get_vpd_lock);
+}
+
+/*
+ * Generator function to be passed to papr_rtas_blob_generate().
+ */
+static const char *vpd_sequence_fill_work_area(struct papr_rtas_sequence *seq,
+						size_t *len)
+{
+	struct rtas_ibm_get_vpd_params *p;
+	bool init_state;
+
+	p = (struct rtas_ibm_get_vpd_params *)seq->params;
+	init_state = (p->written == 0) ? true : false;
+
+	if (papr_rtas_sequence_should_stop(seq, p->status, init_state))
+		return NULL;
+	if (papr_rtas_sequence_set_err(seq, rtas_ibm_get_vpd(p)))
+		return NULL;
+	*len = p->written;
+	return rtas_work_area_raw_buf(p->work_area);
+}
+
+static const struct file_operations papr_vpd_handle_ops = {
+	.read = papr_rtas_common_handle_read,
+	.llseek = papr_rtas_common_handle_seek,
+	.release = papr_rtas_common_handle_release,
+};
+
+/**
+ * papr_vpd_create_handle() - Create a fd-based handle for reading VPD.
+ * @ulc: Location code in user memory; defines the scope of the VPD to
+ *       retrieve.
+ *
+ * Handler for PAPR_VPD_IOC_CREATE_HANDLE ioctl command. Validates
+ * @ulc and instantiates an immutable VPD "blob" for it. The blob is
+ * attached to a file descriptor for reading by user space. The memory
+ * backing the blob is freed when the file is released.
+ *
+ * The entire requested VPD is retrieved by this call and all
+ * necessary RTAS interactions are performed before returning the fd
+ * to user space. This keeps the read handler simple and ensures that
+ * the kernel can prevent interleaving of ibm,get-vpd call sequences.
+ *
+ * Return: The installed fd number if successful, -ve errno otherwise.
+ */
+static long papr_vpd_create_handle(struct papr_location_code __user *ulc)
+{
+	struct rtas_ibm_get_vpd_params vpd_params = {};
+	struct papr_rtas_sequence seq = {};
+	struct papr_location_code klc;
+	int fd;
+
+	if (copy_from_user(&klc, ulc, sizeof(klc)))
+		return -EFAULT;
+
+	if (!string_is_terminated(klc.str, ARRAY_SIZE(klc.str)))
+		return -EINVAL;
+
+	seq = (struct papr_rtas_sequence) {
+		.begin = vpd_sequence_begin,
+		.end = vpd_sequence_end,
+		.work = vpd_sequence_fill_work_area,
+	};
+
+	vpd_params.loc_code = &klc;
+	seq.params = (void *)&vpd_params;
+
+	fd = papr_rtas_setup_file_interface(&seq, &papr_vpd_handle_ops,
+			"[papr-vpd]");
+
+	return fd;
+}
+
+/*
+ * Top-level ioctl handler for /dev/papr-vpd.
+ */
+static long papr_vpd_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (__force void __user *)arg;
+	long ret;
+
+	switch (ioctl) {
+	case PAPR_VPD_IOC_CREATE_HANDLE:
+		ret = papr_vpd_create_handle(argp);
+		break;
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+	return ret;
+}
+
+static const struct file_operations papr_vpd_ops = {
+	.unlocked_ioctl = papr_vpd_dev_ioctl,
+};
+
+static struct miscdevice papr_vpd_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "papr-vpd",
+	.fops = &papr_vpd_ops,
+};
+
+static __init int papr_vpd_init(void)
+{
+	if (!rtas_function_implemented(RTAS_FN_IBM_GET_VPD))
+		return -ENODEV;
+
+	return misc_register(&papr_vpd_dev);
+}
+machine_device_initcall(pseries, papr_vpd_init);
diff --git a/arch/powerpc/platforms/pseries/papr_platform_attributes.c b/arch/powerpc/platforms/pseries/papr_platform_attributes.c
index 526c621b098b..eea2041b270b 100644
--- a/arch/powerpc/platforms/pseries/papr_platform_attributes.c
+++ b/arch/powerpc/platforms/pseries/papr_platform_attributes.c
@@ -101,10 +101,12 @@ retry:
 		esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * max_esi_attrs);
 
 		temp_buf = krealloc(buf, esi_buf_size, GFP_KERNEL);
-		if (temp_buf)
+		if (temp_buf) {
 			buf = temp_buf;
-		else
-			return -ENOMEM;
+		} else {
+			ret = -ENOMEM;
+			goto out_buf;
+		}
 
 		goto retry;
 	}
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 1a53e048ceb7..f7c9271bda58 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/ioport.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/ndctl.h>
 #include <linux/sched.h>
@@ -16,9 +17,10 @@
 #include <linux/nd.h>
 
 #include <asm/plpar_wrappers.h>
-#include <asm/papr_pdsm.h>
+#include <uapi/linux/papr_pdsm.h>
+#include <linux/papr_scm.h>
 #include <asm/mce.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <linux/perf_event.h>
 
 #define BIND_ANY_ADDR (~0ul)
@@ -29,46 +31,6 @@
 	 (1ul << ND_CMD_SET_CONFIG_DATA) | \
 	 (1ul << ND_CMD_CALL))
 
-/* DIMM health bitmap indicators */
-/* SCM device is unable to persist memory contents */
-#define PAPR_PMEM_UNARMED                   (1ULL << (63 - 0))
-/* SCM device failed to persist memory contents */
-#define PAPR_PMEM_SHUTDOWN_DIRTY            (1ULL << (63 - 1))
-/* SCM device contents are persisted from previous IPL */
-#define PAPR_PMEM_SHUTDOWN_CLEAN            (1ULL << (63 - 2))
-/* SCM device contents are not persisted from previous IPL */
-#define PAPR_PMEM_EMPTY                     (1ULL << (63 - 3))
-/* SCM device memory life remaining is critically low */
-#define PAPR_PMEM_HEALTH_CRITICAL           (1ULL << (63 - 4))
-/* SCM device will be garded off next IPL due to failure */
-#define PAPR_PMEM_HEALTH_FATAL              (1ULL << (63 - 5))
-/* SCM contents cannot persist due to current platform health status */
-#define PAPR_PMEM_HEALTH_UNHEALTHY          (1ULL << (63 - 6))
-/* SCM device is unable to persist memory contents in certain conditions */
-#define PAPR_PMEM_HEALTH_NON_CRITICAL       (1ULL << (63 - 7))
-/* SCM device is encrypted */
-#define PAPR_PMEM_ENCRYPTED                 (1ULL << (63 - 8))
-/* SCM device has been scrubbed and locked */
-#define PAPR_PMEM_SCRUBBED_AND_LOCKED       (1ULL << (63 - 9))
-
-/* Bits status indicators for health bitmap indicating unarmed dimm */
-#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED |		\
-				PAPR_PMEM_HEALTH_UNHEALTHY)
-
-/* Bits status indicators for health bitmap indicating unflushed dimm */
-#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY)
-
-/* Bits status indicators for health bitmap indicating unrestored dimm */
-#define PAPR_PMEM_BAD_RESTORE_MASK  (PAPR_PMEM_EMPTY)
-
-/* Bit status indicators for smart event notification */
-#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \
-				    PAPR_PMEM_HEALTH_FATAL |	\
-				    PAPR_PMEM_HEALTH_UNHEALTHY)
-
-#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS)
-#define PAPR_SCM_PERF_STATS_VERSION 0x1
-
 /* Struct holding a single performance metric */
 struct papr_scm_perf_stat {
 	u8 stat_id[8];
@@ -582,7 +544,7 @@ static int drc_pmem_query_health(struct papr_scm_priv *p)
 
 	/* Jiffies offset for which the health data is assumed to be same */
 	cache_timeout = p->lasthealth_jiffies +
-		msecs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL * 1000);
+		secs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL);
 
 	/* Fetch new health info is its older than MIN_HEALTH_QUERY_INTERVAL */
 	if (time_after(jiffies, cache_timeout))
@@ -1521,7 +1483,7 @@ err:	kfree(p);
 	return rc;
 }
 
-static int papr_scm_remove(struct platform_device *pdev)
+static void papr_scm_remove(struct platform_device *pdev)
 {
 	struct papr_scm_priv *p = platform_get_drvdata(pdev);
 
@@ -1538,8 +1500,6 @@ static int papr_scm_remove(struct platform_device *pdev)
 	pdev->archdata.priv = NULL;
 	kfree(p->bus_desc.provider_name);
 	kfree(p);
-
-	return 0;
 }
 
 static const struct of_device_id papr_scm_match[] = {
@@ -1577,5 +1537,6 @@ static void __exit papr_scm_exit(void)
 module_exit(papr_scm_exit);
 
 MODULE_DEVICE_TABLE(of, papr_scm_match);
+MODULE_DESCRIPTION("PAPR Storage Class Memory interface driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("IBM Corporation");
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 1772ae3d193d..6dbc73eb2ca2 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -18,33 +18,6 @@
 #include <asm/pci.h>
 #include "pseries.h"
 
-#if 0
-void pcibios_name_device(struct pci_dev *dev)
-{
-	struct device_node *dn;
-
-	/*
-	 * Add IBM loc code (slot) as a prefix to the device names for service
-	 */
-	dn = pci_device_to_OF_node(dev);
-	if (dn) {
-		const char *loc_code = of_get_property(dn, "ibm,loc-code",
-				NULL);
-		if (loc_code) {
-			int loc_len = strlen(loc_code);
-			if (loc_len < sizeof(dev->dev.name)) {
-				memmove(dev->dev.name+loc_len+1, dev->dev.name,
-					sizeof(dev->dev.name)-loc_len-1);
-				memcpy(dev->dev.name, loc_code, loc_len);
-				dev->dev.name[loc_len] = ' ';
-				dev->dev.name[sizeof(dev->dev.name)-1] = '\0';
-			}
-		}
-	}
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_name_device);
-#endif
-
 #ifdef CONFIG_PCI_IOV
 #define MAX_VFS_FOR_MAP_PE 256
 struct pe_map_bar_entry {
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 4ba824568119..8c77ec7980de 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -11,6 +11,7 @@
 
 #include <linux/pci.h>
 #include <linux/export.h>
+#include <linux/node.h>
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
@@ -21,9 +22,22 @@
 struct pci_controller *init_phb_dynamic(struct device_node *dn)
 {
 	struct pci_controller *phb;
+	int nid;
 
 	pr_debug("PCI: Initializing new hotplug PHB %pOF\n", dn);
 
+	nid = of_node_to_nid(dn);
+	if (likely((nid) >= 0)) {
+		if (!node_online(nid)) {
+			if (register_node(nid)) {
+				pr_err("PCI: Failed to register node %d\n", nid);
+			} else {
+				update_numa_distance(dn);
+				node_set_online(nid);
+			}
+		}
+	}
+
 	phb = pcibios_alloc_controller(dn);
 	if (!phb)
 		return NULL;
@@ -35,6 +49,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
 
 	pseries_msi_allocate_domains(phb);
 
+	ppc_iommu_register_device(phb);
+
 	/* Create EEH devices for the PHB */
 	eeh_phb_pe_create(phb);
 
@@ -76,6 +92,8 @@ int remove_phb_dynamic(struct pci_controller *phb)
 		}
 	}
 
+	ppc_iommu_unregister_device(phb);
+
 	pseries_msi_free_domains(phb);
 
 	/* Keep a reference so phb isn't freed yet */
diff --git a/arch/powerpc/platforms/pseries/plpks-secvar.c b/arch/powerpc/platforms/pseries/plpks-secvar.c
index 257fd1f8bc19..f9e9cc40c9d0 100644
--- a/arch/powerpc/platforms/pseries/plpks-secvar.c
+++ b/arch/powerpc/platforms/pseries/plpks-secvar.c
@@ -59,7 +59,14 @@ static u32 get_policy(const char *name)
 		return PLPKS_SIGNEDUPDATE;
 }
 
-static const char * const plpks_var_names[] = {
+static const char * const plpks_var_names_static[] = {
+	"PK",
+	"moduledb",
+	"trustedcadb",
+	NULL,
+};
+
+static const char * const plpks_var_names_dynamic[] = {
 	"PK",
 	"KEK",
 	"db",
@@ -152,39 +159,55 @@ err:
 	return rc;
 }
 
-// PLPKS dynamic secure boot doesn't give us a format string in the same way OPAL does.
-// Instead, report the format using the SB_VERSION variable in the keystore.
-// The string is made up by us, and takes the form "ibm,plpks-sb-v<n>" (or "ibm,plpks-sb-unknown"
-// if the SB_VERSION variable doesn't exist). Hypervisor defines the SB_VERSION variable as a
-// "1 byte unsigned integer value".
-static ssize_t plpks_secvar_format(char *buf, size_t bufsize)
+/*
+ * Return the key management mode.
+ *
+ * SB_VERSION is defined as a "1 byte unsigned integer value", taking values
+ * starting from 1. It is owned by the Partition Firmware and its presence
+ * indicates that the key management mode is dynamic. Any failure in
+ * reading SB_VERSION defaults the key management mode to static. The error
+ * codes -ENOENT or -EPERM are expected in static key management mode. An
+ * unexpected error code will have to be investigated. Only signed variables
+ * have null bytes in their names, SB_VERSION does not.
+ *
+ * Return 0 to indicate that the key management mode is static. Otherwise
+ * return the SB_VERSION value to indicate that the key management mode is
+ * dynamic.
+ */
+static u8 plpks_get_sb_keymgmt_mode(void)
 {
-	struct plpks_var var = {0};
-	ssize_t ret;
-	u8 version;
-
-	var.component = NULL;
-	// Only the signed variables have null bytes in their names, this one doesn't
-	var.name = "SB_VERSION";
-	var.namelen = strlen(var.name);
-	var.datalen = 1;
-	var.data = &version;
-
-	// Unlike the other vars, SB_VERSION is owned by firmware instead of the OS
-	ret = plpks_read_fw_var(&var);
-	if (ret) {
-		if (ret == -ENOENT) {
-			ret = snprintf(buf, bufsize, "ibm,plpks-sb-unknown");
-		} else {
-			pr_err("Error %ld reading SB_VERSION from firmware\n", ret);
-			ret = -EIO;
-		}
-		goto err;
+	u8 mode;
+	ssize_t rc;
+	struct plpks_var var = {
+		.component = NULL,
+		.name = "SB_VERSION",
+		.namelen = 10,
+		.datalen = 1,
+		.data = &mode,
+	};
+
+	rc = plpks_read_fw_var(&var);
+	if (rc) {
+		if (rc != -ENOENT && rc != -EPERM)
+			pr_info("Error %ld reading SB_VERSION from firmware\n", rc);
+		mode = 0;
 	}
+	return mode;
+}
 
-	ret = snprintf(buf, bufsize, "ibm,plpks-sb-v%hhu", version);
-err:
-	return ret;
+/*
+ * PLPKS dynamic secure boot doesn't give us a format string in the same way
+ * OPAL does. Instead, report the format using the SB_VERSION variable in the
+ * keystore. The string, made up by us, takes the form of either
+ * "ibm,plpks-sb-v<n>" or "ibm,plpks-sb-v0", based on the key management mode,
+ * and return the length of the secvar format property.
+ */
+static ssize_t plpks_secvar_format(char *buf, size_t bufsize)
+{
+	u8 mode;
+
+	mode = plpks_get_sb_keymgmt_mode();
+	return snprintf(buf, bufsize, "ibm,plpks-sb-v%hhu", mode);
 }
 
 static int plpks_max_size(u64 *max_size)
@@ -197,21 +220,34 @@ static int plpks_max_size(u64 *max_size)
 	return 0;
 }
 
+static const struct secvar_operations plpks_secvar_ops_static = {
+	.get = plpks_get_variable,
+	.set = plpks_set_variable,
+	.format = plpks_secvar_format,
+	.max_size = plpks_max_size,
+	.config_attrs = config_attrs,
+	.var_names = plpks_var_names_static,
+};
 
-static const struct secvar_operations plpks_secvar_ops = {
+static const struct secvar_operations plpks_secvar_ops_dynamic = {
 	.get = plpks_get_variable,
 	.set = plpks_set_variable,
 	.format = plpks_secvar_format,
 	.max_size = plpks_max_size,
 	.config_attrs = config_attrs,
-	.var_names = plpks_var_names,
+	.var_names = plpks_var_names_dynamic,
 };
 
 static int plpks_secvar_init(void)
 {
+	u8 mode;
+
 	if (!plpks_is_available())
 		return -ENODEV;
 
-	return set_secvar_ops(&plpks_secvar_ops);
+	mode = plpks_get_sb_keymgmt_mode();
+	if (mode)
+		return set_secvar_ops(&plpks_secvar_ops_dynamic);
+	return set_secvar_ops(&plpks_secvar_ops_static);
 }
 machine_device_initcall(pseries, plpks_secvar_init);
diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c
index b0658ea3eccb..b1667ed05f98 100644
--- a/arch/powerpc/platforms/pseries/plpks.c
+++ b/arch/powerpc/platforms/pseries/plpks.c
@@ -150,7 +150,7 @@ static int plpks_gen_password(void)
 		ospasswordlength = maxpwsize;
 		ospassword = kzalloc(maxpwsize, GFP_KERNEL);
 		if (!ospassword) {
-			kfree(password);
+			kfree_sensitive(password);
 			return -ENOMEM;
 		}
 		memcpy(ospassword, password, ospasswordlength);
@@ -163,7 +163,7 @@ static int plpks_gen_password(void)
 		}
 	}
 out:
-	kfree(password);
+	kfree_sensitive(password);
 
 	return pseries_status_to_err(rc);
 }
@@ -194,7 +194,7 @@ static struct plpks_auth *construct_auth(u8 consumer)
 	return auth;
 }
 
-/**
+/*
  * Label is combination of label attributes + name.
  * Label attributes are used internally by kernel and not exposed to the user.
  */
@@ -415,8 +415,7 @@ static int plpks_confirm_object_flushed(struct label *label,
 			break;
 		}
 
-		usleep_range(PLPKS_FLUSH_SLEEP,
-			     PLPKS_FLUSH_SLEEP + PLPKS_FLUSH_SLEEP_RANGE);
+		fsleep(PLPKS_FLUSH_SLEEP);
 		timeout = timeout + PLPKS_FLUSH_SLEEP;
 	} while (timeout < PLPKS_MAX_TIMEOUT);
 
@@ -464,9 +463,10 @@ int plpks_signed_update_var(struct plpks_var *var, u64 flags)
 
 		continuetoken = retbuf[0];
 		if (pseries_status_to_err(rc) == -EBUSY) {
-			int delay_ms = get_longbusy_msecs(rc);
-			mdelay(delay_ms);
-			timeout += delay_ms;
+			int delay_us = get_longbusy_msecs(rc) * 1000;
+
+			fsleep(delay_us);
+			timeout += delay_us;
 		}
 		rc = pseries_status_to_err(rc);
 	} while (rc == -EBUSY && timeout < PLPKS_MAX_TIMEOUT);
@@ -683,7 +683,7 @@ void __init plpks_early_init_devtree(void)
 out:
 	fdt_nop_property(fdt, chosen_node, "ibm,plpks-pw");
 	// Since we've cleared the password, we must update the FDT checksum
-	early_init_dt_verify(fdt);
+	early_init_dt_verify(fdt, __pa(fdt));
 }
 
 static __init int pseries_plpks_init(void)
diff --git a/arch/powerpc/platforms/pseries/plpks_sed_ops.c b/arch/powerpc/platforms/pseries/plpks_sed_ops.c
new file mode 100644
index 000000000000..7c873c9589ef
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/plpks_sed_ops.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * POWER Platform specific code for non-volatile SED key access
+ * Copyright (C) 2022 IBM Corporation
+ *
+ * Define operations for SED Opal to read/write keys
+ * from POWER LPAR Platform KeyStore(PLPKS).
+ *
+ * Self Encrypting Drives(SED) key storage using PLPKS
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/ioctl.h>
+#include <linux/sed-opal-key.h>
+#include <asm/plpks.h>
+
+static bool plpks_sed_initialized = false;
+static bool plpks_sed_available = false;
+
+/*
+ * structure that contains all SED data
+ */
+struct plpks_sed_object_data {
+	u_char version;
+	u_char pad1[7];
+	u_long authority;
+	u_long range;
+	u_int  key_len;
+	u_char key[32];
+};
+
+#define PLPKS_SED_OBJECT_DATA_V0        0
+#define PLPKS_SED_MANGLED_LABEL         "/default/pri"
+#define PLPKS_SED_COMPONENT             "sed-opal"
+#define PLPKS_SED_KEY                   "opal-boot-pin"
+
+/*
+ * authority is admin1 and range is global
+ */
+#define PLPKS_SED_AUTHORITY  0x0000000900010001
+#define PLPKS_SED_RANGE      0x0000080200000001
+
+static void plpks_init_var(struct plpks_var *var, char *keyname)
+{
+	if (!plpks_sed_initialized) {
+		plpks_sed_initialized = true;
+		plpks_sed_available = plpks_is_available();
+		if (!plpks_sed_available)
+			pr_err("SED: plpks not available\n");
+	}
+
+	var->name = keyname;
+	var->namelen = strlen(keyname);
+	if (strcmp(PLPKS_SED_KEY, keyname) == 0) {
+		var->name = PLPKS_SED_MANGLED_LABEL;
+		var->namelen = strlen(keyname);
+	}
+	var->policy = PLPKS_WORLDREADABLE;
+	var->os = PLPKS_VAR_COMMON;
+	var->data = NULL;
+	var->datalen = 0;
+	var->component = PLPKS_SED_COMPONENT;
+}
+
+/*
+ * Read the SED Opal key from PLPKS given the label
+ */
+int sed_read_key(char *keyname, char *key, u_int *keylen)
+{
+	struct plpks_var var;
+	struct plpks_sed_object_data data;
+	int ret;
+	u_int len;
+
+	plpks_init_var(&var, keyname);
+
+	if (!plpks_sed_available)
+		return -EOPNOTSUPP;
+
+	var.data = (u8 *)&data;
+	var.datalen = sizeof(data);
+
+	ret = plpks_read_os_var(&var);
+	if (ret != 0)
+		return ret;
+
+	len = min_t(u16, be32_to_cpu(data.key_len), var.datalen);
+	memcpy(key, data.key, len);
+	key[len] = '\0';
+	*keylen = len;
+
+	return 0;
+}
+
+/*
+ * Write the SED Opal key to PLPKS given the label
+ */
+int sed_write_key(char *keyname, char *key, u_int keylen)
+{
+	struct plpks_var var;
+	struct plpks_sed_object_data data;
+	struct plpks_var_name vname;
+
+	plpks_init_var(&var, keyname);
+
+	if (!plpks_sed_available)
+		return -EOPNOTSUPP;
+
+	var.datalen = sizeof(struct plpks_sed_object_data);
+	var.data = (u8 *)&data;
+
+	/* initialize SED object */
+	data.version = PLPKS_SED_OBJECT_DATA_V0;
+	data.authority = cpu_to_be64(PLPKS_SED_AUTHORITY);
+	data.range = cpu_to_be64(PLPKS_SED_RANGE);
+	memset(&data.pad1, '\0', sizeof(data.pad1));
+	data.key_len = cpu_to_be32(keylen);
+	memcpy(data.key, (char *)key, keylen);
+
+	/*
+	 * Key update requires remove first. The return value
+	 * is ignored since it's okay if the key doesn't exist.
+	 */
+	vname.namelen = var.namelen;
+	vname.name = var.name;
+	plpks_remove_var(var.component, var.os, vname);
+
+	return plpks_write_var(var);
+}
diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c
index 3c290b9ed01b..0f1d45f32e4a 100644
--- a/arch/powerpc/platforms/pseries/pmem.c
+++ b/arch/powerpc/platforms/pseries/pmem.c
@@ -121,7 +121,7 @@ int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog)
 		return -EINVAL;
 	}
 
-	drc_index = hp_elog->_drc_u.drc_index;
+	drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index);
 
 	lock_device_hotplug();
 
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index f8bce40ebd0c..3968a6970fa8 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -38,7 +38,6 @@ static inline void smp_init_pseries(void) { }
 #endif
 
 extern void pseries_kexec_cpu_down(int crash_shutdown, int secondary);
-void pseries_machine_kexec(struct kimage *image);
 
 extern void pSeries_final_fixup(void);
 
@@ -55,6 +54,7 @@ extern int dlpar_detach_node(struct device_node *);
 extern int dlpar_acquire_drc(u32 drc_index);
 extern int dlpar_release_drc(u32 drc_index);
 extern int dlpar_unisolate_drc(u32 drc_index);
+extern void post_mobility_fixup(void);
 
 void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog);
 int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_errlog);
@@ -75,11 +75,13 @@ static inline int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog)
 
 #ifdef CONFIG_HOTPLUG_CPU
 int dlpar_cpu(struct pseries_hp_errorlog *hp_elog);
+void pseries_cpu_hotplug_init(void);
 #else
 static inline int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
 {
 	return -EOPNOTSUPP;
 }
+static inline void pseries_cpu_hotplug_init(void) { }
 #endif
 
 /* PCI root bridge prepare function override for pseries */
@@ -90,8 +92,6 @@ extern struct pci_controller_ops pseries_pci_controller_ops;
 int pseries_msi_allocate_domains(struct pci_controller *phb);
 void pseries_msi_free_domains(struct pci_controller *phb);
 
-unsigned long pseries_memory_block_size(void);
-
 extern int CMO_PrPSP;
 extern int CMO_SecPSP;
 extern unsigned long CMO_PageSize;
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c
index b5853e9fcc3c..eceb3289383e 100644
--- a/arch/powerpc/platforms/pseries/rtas-fadump.c
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.c
@@ -18,6 +18,7 @@
 
 #include <asm/page.h>
 #include <asm/rtas.h>
+#include <asm/setup.h>
 #include <asm/fadump.h>
 #include <asm/fadump-internal.h>
 
@@ -29,9 +30,6 @@ static const struct rtas_fadump_mem_struct *fdm_active;
 static void rtas_fadump_update_config(struct fw_dump *fadump_conf,
 				      const struct rtas_fadump_mem_struct *fdm)
 {
-	fadump_conf->boot_mem_dest_addr =
-		be64_to_cpu(fdm->rmr_region.destination_address);
-
 	fadump_conf->fadumphdr_addr = (fadump_conf->boot_mem_dest_addr +
 				       fadump_conf->boot_memory_size);
 }
@@ -43,20 +41,56 @@ static void rtas_fadump_update_config(struct fw_dump *fadump_conf,
 static void __init rtas_fadump_get_config(struct fw_dump *fadump_conf,
 				   const struct rtas_fadump_mem_struct *fdm)
 {
-	fadump_conf->boot_mem_addr[0] =
-		be64_to_cpu(fdm->rmr_region.source_address);
-	fadump_conf->boot_mem_sz[0] = be64_to_cpu(fdm->rmr_region.source_len);
-	fadump_conf->boot_memory_size = fadump_conf->boot_mem_sz[0];
+	unsigned long base, size, last_end, hole_size;
 
-	fadump_conf->boot_mem_top = fadump_conf->boot_memory_size;
-	fadump_conf->boot_mem_regs_cnt = 1;
+	last_end = 0;
+	hole_size = 0;
+	fadump_conf->boot_memory_size = 0;
+	fadump_conf->boot_mem_regs_cnt = 0;
+	pr_debug("Boot memory regions:\n");
+	for (int i = 0; i < be16_to_cpu(fdm->header.dump_num_sections); i++) {
+		int type = be16_to_cpu(fdm->rgn[i].source_data_type);
+		u64 addr;
 
-	/*
-	 * Start address of reserve dump area (permanent reservation) for
-	 * re-registering FADump after dump capture.
-	 */
-	fadump_conf->reserve_dump_area_start =
-		be64_to_cpu(fdm->cpu_state_data.destination_address);
+		switch (type) {
+		case RTAS_FADUMP_CPU_STATE_DATA:
+			addr = be64_to_cpu(fdm->rgn[i].destination_address);
+
+			fadump_conf->cpu_state_dest_vaddr = (u64)__va(addr);
+			/*
+			 * Start address of reserve dump area (permanent reservation) for
+			 * re-registering FADump after dump capture.
+			 */
+			fadump_conf->reserve_dump_area_start = addr;
+			break;
+		case RTAS_FADUMP_HPTE_REGION:
+			/* Not processed currently. */
+			break;
+		case RTAS_FADUMP_REAL_MODE_REGION:
+			base = be64_to_cpu(fdm->rgn[i].source_address);
+			size = be64_to_cpu(fdm->rgn[i].source_len);
+			pr_debug("\t[%03d] base: 0x%lx, size: 0x%lx\n", i, base, size);
+			if (!base) {
+				fadump_conf->boot_mem_dest_addr =
+					be64_to_cpu(fdm->rgn[i].destination_address);
+			}
+
+			fadump_conf->boot_mem_addr[fadump_conf->boot_mem_regs_cnt] = base;
+			fadump_conf->boot_mem_sz[fadump_conf->boot_mem_regs_cnt] = size;
+			fadump_conf->boot_memory_size += size;
+			hole_size += (base - last_end);
+			last_end = base + size;
+			fadump_conf->boot_mem_regs_cnt++;
+			break;
+		case RTAS_FADUMP_PARAM_AREA:
+			fadump_conf->param_area = be64_to_cpu(fdm->rgn[i].destination_address);
+			break;
+		default:
+			pr_warn("Section type %d unsupported on this kernel. Ignoring!\n", type);
+			break;
+		}
+	}
+	fadump_conf->boot_mem_top = fadump_conf->boot_memory_size + hole_size;
 
 	rtas_fadump_update_config(fadump_conf, fdm);
 }
@@ -64,16 +98,15 @@ static void __init rtas_fadump_get_config(struct fw_dump *fadump_conf,
 static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
 {
 	u64 addr = fadump_conf->reserve_dump_area_start;
+	u16 sec_cnt = 0;
 
 	memset(&fdm, 0, sizeof(struct rtas_fadump_mem_struct));
 	addr = addr & PAGE_MASK;
 
 	fdm.header.dump_format_version = cpu_to_be32(0x00000001);
-	fdm.header.dump_num_sections = cpu_to_be16(3);
 	fdm.header.dump_status_flag = 0;
 	fdm.header.offset_first_dump_section =
-		cpu_to_be32((u32)offsetof(struct rtas_fadump_mem_struct,
-					  cpu_state_data));
+		cpu_to_be32((u32)offsetof(struct rtas_fadump_mem_struct, rgn));
 
 	/*
 	 * Fields for disk dump option.
@@ -89,25 +122,22 @@ static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
 
 	/* Kernel dump sections */
 	/* cpu state data section. */
-	fdm.cpu_state_data.request_flag =
-		cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
-	fdm.cpu_state_data.source_data_type =
-		cpu_to_be16(RTAS_FADUMP_CPU_STATE_DATA);
-	fdm.cpu_state_data.source_address = 0;
-	fdm.cpu_state_data.source_len =
-		cpu_to_be64(fadump_conf->cpu_state_data_size);
-	fdm.cpu_state_data.destination_address = cpu_to_be64(addr);
+	fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+	fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_CPU_STATE_DATA);
+	fdm.rgn[sec_cnt].source_address = 0;
+	fdm.rgn[sec_cnt].source_len = cpu_to_be64(fadump_conf->cpu_state_data_size);
+	fdm.rgn[sec_cnt].destination_address = cpu_to_be64(addr);
 	addr += fadump_conf->cpu_state_data_size;
+	sec_cnt++;
 
 	/* hpte region section */
-	fdm.hpte_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
-	fdm.hpte_region.source_data_type =
-		cpu_to_be16(RTAS_FADUMP_HPTE_REGION);
-	fdm.hpte_region.source_address = 0;
-	fdm.hpte_region.source_len =
-		cpu_to_be64(fadump_conf->hpte_region_size);
-	fdm.hpte_region.destination_address = cpu_to_be64(addr);
+	fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+	fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_HPTE_REGION);
+	fdm.rgn[sec_cnt].source_address = 0;
+	fdm.rgn[sec_cnt].source_len = cpu_to_be64(fadump_conf->hpte_region_size);
+	fdm.rgn[sec_cnt].destination_address = cpu_to_be64(addr);
 	addr += fadump_conf->hpte_region_size;
+	sec_cnt++;
 
 	/*
 	 * Align boot memory area destination address to page boundary to
@@ -115,14 +145,29 @@ static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
 	 */
 	addr = PAGE_ALIGN(addr);
 
-	/* RMA region section */
-	fdm.rmr_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
-	fdm.rmr_region.source_data_type =
-		cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION);
-	fdm.rmr_region.source_address = cpu_to_be64(0);
-	fdm.rmr_region.source_len = cpu_to_be64(fadump_conf->boot_memory_size);
-	fdm.rmr_region.destination_address = cpu_to_be64(addr);
-	addr += fadump_conf->boot_memory_size;
+	/* First boot memory region destination address */
+	fadump_conf->boot_mem_dest_addr = addr;
+	for (int i = 0; i < fadump_conf->boot_mem_regs_cnt; i++) {
+		/* Boot memory regions */
+		fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+		fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION);
+		fdm.rgn[sec_cnt].source_address = cpu_to_be64(fadump_conf->boot_mem_addr[i]);
+		fdm.rgn[sec_cnt].source_len = cpu_to_be64(fadump_conf->boot_mem_sz[i]);
+		fdm.rgn[sec_cnt].destination_address = cpu_to_be64(addr);
+		addr += fadump_conf->boot_mem_sz[i];
+		sec_cnt++;
+	}
+
+	/* Parameters area */
+	if (fadump_conf->param_area) {
+		fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+		fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_PARAM_AREA);
+		fdm.rgn[sec_cnt].source_address = cpu_to_be64(fadump_conf->param_area);
+		fdm.rgn[sec_cnt].source_len = cpu_to_be64(COMMAND_LINE_SIZE);
+		fdm.rgn[sec_cnt].destination_address = cpu_to_be64(fadump_conf->param_area);
+		sec_cnt++;
+	}
+	fdm.header.dump_num_sections = cpu_to_be16(sec_cnt);
 
 	rtas_fadump_update_config(fadump_conf, &fdm);
 
@@ -136,14 +181,21 @@ static u64 rtas_fadump_get_bootmem_min(void)
 
 static int rtas_fadump_register(struct fw_dump *fadump_conf)
 {
-	unsigned int wait_time;
+	unsigned int wait_time, fdm_size;
 	int rc, err = -EIO;
 
+	/*
+	 * Platform requires the exact size of the Dump Memory Structure.
+	 * Avoid including any unused rgns in the calculation, as this
+	 * could result in a parameter error (-3) from the platform.
+	 */
+	fdm_size = sizeof(struct rtas_fadump_section_header);
+	fdm_size += be16_to_cpu(fdm.header.dump_num_sections) * sizeof(struct rtas_fadump_section);
+
 	/* TODO: Add upper time limit for the delay */
 	do {
 		rc =  rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1,
-				NULL, FADUMP_REGISTER, &fdm,
-				sizeof(struct rtas_fadump_mem_struct));
+				NULL, FADUMP_REGISTER, &fdm, fdm_size);
 
 		wait_time = rtas_busy_delay_time(rc);
 		if (wait_time)
@@ -161,9 +213,7 @@ static int rtas_fadump_register(struct fw_dump *fadump_conf)
 		pr_err("Failed to register. Hardware Error(%d).\n", rc);
 		break;
 	case -3:
-		if (!is_fadump_boot_mem_contiguous())
-			pr_err("Can't have holes in boot memory area.\n");
-		else if (!is_fadump_reserved_mem_contiguous())
+		if (!is_fadump_reserved_mem_contiguous())
 			pr_err("Can't have holes in reserved memory area.\n");
 
 		pr_err("Failed to register. Parameter Error(%d).\n", rc);
@@ -316,11 +366,9 @@ static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf)
 	u32 num_cpus, *note_buf;
 	int i, rc = 0, cpu = 0;
 	struct pt_regs regs;
-	unsigned long addr;
 	void *vaddr;
 
-	addr = be64_to_cpu(fdm_active->cpu_state_data.destination_address);
-	vaddr = __va(addr);
+	vaddr = (void *)fadump_conf->cpu_state_dest_vaddr;
 
 	reg_header = vaddr;
 	if (be64_to_cpu(reg_header->magic_number) !=
@@ -375,11 +423,8 @@ static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf)
 	}
 	final_note(note_buf);
 
-	if (fdh) {
-		pr_debug("Updating elfcore header (%llx) with cpu notes\n",
-			 fdh->elfcorehdr_addr);
-		fadump_update_elfcore_header(__va(fdh->elfcorehdr_addr));
-	}
+	pr_debug("Updating elfcore header (%llx) with cpu notes\n", fadump_conf->elfcorehdr_addr);
+	fadump_update_elfcore_header((char *)fadump_conf->elfcorehdr_addr);
 	return 0;
 
 error_out:
@@ -389,57 +434,66 @@ error_out:
 }
 
 /*
- * Validate and process the dump data stored by firmware before exporting
- * it through '/proc/vmcore'.
+ * Validate and process the dump data stored by the firmware, and update
+ * the CPU notes of elfcorehdr.
  */
 static int __init rtas_fadump_process(struct fw_dump *fadump_conf)
 {
-	struct fadump_crash_info_header *fdh;
-	int rc = 0;
-
 	if (!fdm_active || !fadump_conf->fadumphdr_addr)
 		return -EINVAL;
 
 	/* Check if the dump data is valid. */
-	if ((be16_to_cpu(fdm_active->header.dump_status_flag) ==
-			RTAS_FADUMP_ERROR_FLAG) ||
-			(fdm_active->cpu_state_data.error_flags != 0) ||
-			(fdm_active->rmr_region.error_flags != 0)) {
-		pr_err("Dump taken by platform is not valid\n");
-		return -EINVAL;
-	}
-	if ((fdm_active->rmr_region.bytes_dumped !=
-			fdm_active->rmr_region.source_len) ||
-			!fdm_active->cpu_state_data.bytes_dumped) {
-		pr_err("Dump taken by platform is incomplete\n");
-		return -EINVAL;
-	}
+	for (int i = 0; i < be16_to_cpu(fdm_active->header.dump_num_sections); i++) {
+		int type = be16_to_cpu(fdm_active->rgn[i].source_data_type);
+		int rc = 0;
 
-	/* Validate the fadump crash info header */
-	fdh = __va(fadump_conf->fadumphdr_addr);
-	if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
-		pr_err("Crash info header is not valid.\n");
-		return -EINVAL;
+		switch (type) {
+		case RTAS_FADUMP_CPU_STATE_DATA:
+		case RTAS_FADUMP_HPTE_REGION:
+		case RTAS_FADUMP_REAL_MODE_REGION:
+			if (fdm_active->rgn[i].error_flags != 0) {
+				pr_err("Dump taken by platform is not valid (%d)\n", i);
+				rc = -EINVAL;
+			}
+			if (fdm_active->rgn[i].bytes_dumped != fdm_active->rgn[i].source_len) {
+				pr_err("Dump taken by platform is incomplete (%d)\n", i);
+				rc = -EINVAL;
+			}
+			if (rc) {
+				pr_warn("Region type: %u src addr: 0x%llx dest addr: 0x%llx\n",
+					be16_to_cpu(fdm_active->rgn[i].source_data_type),
+					be64_to_cpu(fdm_active->rgn[i].source_address),
+					be64_to_cpu(fdm_active->rgn[i].destination_address));
+				return rc;
+			}
+			break;
+		case RTAS_FADUMP_PARAM_AREA:
+			if (fdm_active->rgn[i].bytes_dumped != fdm_active->rgn[i].source_len ||
+			    fdm_active->rgn[i].error_flags != 0) {
+				pr_warn("Failed to process additional parameters! Proceeding anyway..\n");
+				fadump_conf->param_area = 0;
+			}
+			break;
+		default:
+			/*
+			 * If the first/crashed kernel added a new region type that the
+			 * second/fadump kernel doesn't recognize, skip it and process
+			 * assuming backward compatibility.
+			 */
+			pr_warn("Unknown region found: type: %u src addr: 0x%llx dest addr: 0x%llx\n",
+				be16_to_cpu(fdm_active->rgn[i].source_data_type),
+				be64_to_cpu(fdm_active->rgn[i].source_address),
+				be64_to_cpu(fdm_active->rgn[i].destination_address));
+			break;
+		}
 	}
 
-	rc = rtas_fadump_build_cpu_notes(fadump_conf);
-	if (rc)
-		return rc;
-
-	/*
-	 * We are done validating dump info and elfcore header is now ready
-	 * to be exported. set elfcorehdr_addr so that vmcore module will
-	 * export the elfcore header through '/proc/vmcore'.
-	 */
-	elfcorehdr_addr = fdh->elfcorehdr_addr;
-
-	return 0;
+	return rtas_fadump_build_cpu_notes(fadump_conf);
 }
 
 static void rtas_fadump_region_show(struct fw_dump *fadump_conf,
 				    struct seq_file *m)
 {
-	const struct rtas_fadump_section *cpu_data_section;
 	const struct rtas_fadump_mem_struct *fdm_ptr;
 
 	if (fdm_active)
@@ -447,27 +501,49 @@ static void rtas_fadump_region_show(struct fw_dump *fadump_conf,
 	else
 		fdm_ptr = &fdm;
 
-	cpu_data_section = &(fdm_ptr->cpu_state_data);
-	seq_printf(m, "CPU :[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
-		   be64_to_cpu(cpu_data_section->destination_address),
-		   be64_to_cpu(cpu_data_section->destination_address) +
-		   be64_to_cpu(cpu_data_section->source_len) - 1,
-		   be64_to_cpu(cpu_data_section->source_len),
-		   be64_to_cpu(cpu_data_section->bytes_dumped));
-
-	seq_printf(m, "HPTE:[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
-		   be64_to_cpu(fdm_ptr->hpte_region.destination_address),
-		   be64_to_cpu(fdm_ptr->hpte_region.destination_address) +
-		   be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1,
-		   be64_to_cpu(fdm_ptr->hpte_region.source_len),
-		   be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped));
-
-	seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ",
-		   be64_to_cpu(fdm_ptr->rmr_region.source_address),
-		   be64_to_cpu(fdm_ptr->rmr_region.destination_address));
-	seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n",
-		   be64_to_cpu(fdm_ptr->rmr_region.source_len),
-		   be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped));
+
+	for (int i = 0; i < be16_to_cpu(fdm_ptr->header.dump_num_sections); i++) {
+		int type = be16_to_cpu(fdm_ptr->rgn[i].source_data_type);
+
+		switch (type) {
+		case RTAS_FADUMP_CPU_STATE_DATA:
+			seq_printf(m, "CPU :[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
+				   be64_to_cpu(fdm_ptr->rgn[i].destination_address),
+				   be64_to_cpu(fdm_ptr->rgn[i].destination_address) +
+				   be64_to_cpu(fdm_ptr->rgn[i].source_len) - 1,
+				   be64_to_cpu(fdm_ptr->rgn[i].source_len),
+				   be64_to_cpu(fdm_ptr->rgn[i].bytes_dumped));
+			break;
+		case RTAS_FADUMP_HPTE_REGION:
+			seq_printf(m, "HPTE:[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n",
+				   be64_to_cpu(fdm_ptr->rgn[i].destination_address),
+				   be64_to_cpu(fdm_ptr->rgn[i].destination_address) +
+				   be64_to_cpu(fdm_ptr->rgn[i].source_len) - 1,
+				   be64_to_cpu(fdm_ptr->rgn[i].source_len),
+				   be64_to_cpu(fdm_ptr->rgn[i].bytes_dumped));
+			break;
+		case RTAS_FADUMP_REAL_MODE_REGION:
+			seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ",
+				   be64_to_cpu(fdm_ptr->rgn[i].source_address),
+				   be64_to_cpu(fdm_ptr->rgn[i].destination_address));
+			seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n",
+				   be64_to_cpu(fdm_ptr->rgn[i].source_len),
+				   be64_to_cpu(fdm_ptr->rgn[i].bytes_dumped));
+			break;
+		case RTAS_FADUMP_PARAM_AREA:
+			seq_printf(m, "\n[%#016llx-%#016llx]: cmdline append: '%s'\n",
+				   be64_to_cpu(fdm_ptr->rgn[i].destination_address),
+				   be64_to_cpu(fdm_ptr->rgn[i].destination_address) +
+				   be64_to_cpu(fdm_ptr->rgn[i].source_len) - 1,
+				   (char *)__va(be64_to_cpu(fdm_ptr->rgn[i].destination_address)));
+			break;
+		default:
+			seq_printf(m, "Unknown region type %d : Src: %#016llx, Dest: %#016llx, ",
+				   type, be64_to_cpu(fdm_ptr->rgn[i].source_address),
+				   be64_to_cpu(fdm_ptr->rgn[i].destination_address));
+			break;
+		}
+	}
 
 	/* Dump is active. Show preserved area start address. */
 	if (fdm_active) {
@@ -483,6 +559,20 @@ static void rtas_fadump_trigger(struct fadump_crash_info_header *fdh,
 	rtas_os_term((char *)msg);
 }
 
+/* FADUMP_MAX_MEM_REGS or lower */
+static int rtas_fadump_max_boot_mem_rgns(void)
+{
+	/*
+	 * Version 1 of Kernel Assisted Dump Memory Structure (PAPR) supports 10 sections.
+	 * With one each section taken for CPU state data & HPTE respectively, 8 sections
+	 * can be used for boot memory regions.
+	 *
+	 * If new region(s) is(are) defined, maximum boot memory regions will decrease
+	 * proportionally.
+	 */
+	return RTAS_FADUMP_MAX_BOOT_MEM_REGS;
+}
+
 static struct fadump_ops rtas_fadump_ops = {
 	.fadump_init_mem_struct		= rtas_fadump_init_mem_struct,
 	.fadump_get_bootmem_min		= rtas_fadump_get_bootmem_min,
@@ -492,6 +582,7 @@ static struct fadump_ops rtas_fadump_ops = {
 	.fadump_process			= rtas_fadump_process,
 	.fadump_region_show		= rtas_fadump_region_show,
 	.fadump_trigger			= rtas_fadump_trigger,
+	.fadump_max_boot_mem_rgns	= rtas_fadump_max_boot_mem_rgns,
 };
 
 void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
@@ -508,9 +599,10 @@ void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
 	if (!token)
 		return;
 
-	fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token);
-	fadump_conf->ops		= &rtas_fadump_ops;
-	fadump_conf->fadump_supported	= 1;
+	fadump_conf->ibm_configure_kernel_dump	= be32_to_cpu(*token);
+	fadump_conf->ops			= &rtas_fadump_ops;
+	fadump_conf->fadump_supported		= 1;
+	fadump_conf->param_area_supported	= 1;
 
 	/* Firmware supports 64-bit value for size, align it to pagesize. */
 	fadump_conf->max_copy_size = ALIGN_DOWN(U64_MAX, PAGE_SIZE);
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.h b/arch/powerpc/platforms/pseries/rtas-fadump.h
index fd59bd7ca9c3..c109abf6befd 100644
--- a/arch/powerpc/platforms/pseries/rtas-fadump.h
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.h
@@ -23,12 +23,24 @@
 #define RTAS_FADUMP_HPTE_REGION		0x0002
 #define RTAS_FADUMP_REAL_MODE_REGION	0x0011
 
+/* OS defined sections */
+#define RTAS_FADUMP_PARAM_AREA		0x0100
+
 /* Dump request flag */
 #define RTAS_FADUMP_REQUEST_FLAG	0x00000001
 
 /* Dump status flag */
 #define RTAS_FADUMP_ERROR_FLAG		0x2000
 
+/*
+ * The Firmware Assisted Dump Memory structure supports a maximum of 10 sections
+ * in the dump memory structure. Presently, three sections are used for
+ * CPU state data, HPTE & Parameters area, while the remaining seven sections
+ * can be used for boot memory regions.
+ */
+#define MAX_SECTIONS				10
+#define RTAS_FADUMP_MAX_BOOT_MEM_REGS		7
+
 /* Kernel Dump section info */
 struct rtas_fadump_section {
 	__be32	request_flag;
@@ -61,20 +73,15 @@ struct rtas_fadump_section_header {
  * Firmware Assisted dump memory structure. This structure is required for
  * registering future kernel dump with power firmware through rtas call.
  *
- * No disk dump option. Hence disk dump path string section is not included.
+ * In version 1, the platform permits one section header, dump-disk path
+ * and ten sections.
+ *
+ * Note: No disk dump option. Hence disk dump path string section is not
+ * included.
  */
 struct rtas_fadump_mem_struct {
 	struct rtas_fadump_section_header	header;
-
-	/* Kernel dump sections */
-	struct rtas_fadump_section		cpu_state_data;
-	struct rtas_fadump_section		hpte_region;
-
-	/*
-	 * TODO: Extend multiple boot memory regions support in the kernel
-	 *       for this platform.
-	 */
-	struct rtas_fadump_section		rmr_region;
+	struct rtas_fadump_section		rgn[MAX_SECTIONS];
 };
 
 /*
diff --git a/arch/powerpc/platforms/pseries/rtas-work-area.c b/arch/powerpc/platforms/pseries/rtas-work-area.c
index b37d52f40360..7fe34bee84d8 100644
--- a/arch/powerpc/platforms/pseries/rtas-work-area.c
+++ b/arch/powerpc/platforms/pseries/rtas-work-area.c
@@ -184,6 +184,7 @@ machine_arch_initcall(pseries, rtas_work_area_allocator_init);
 
 /**
  * rtas_work_area_reserve_arena() - Reserve memory suitable for RTAS work areas.
+ * @limit: Upper limit for memblock allocation.
  */
 void __init rtas_work_area_reserve_arena(const phys_addr_t limit)
 {
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index e2a57cfa6c83..b10a25325238 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -343,8 +343,8 @@ static int alloc_dispatch_log_kmem_cache(void)
 {
 	void (*ctor)(void *) = get_dtl_cache_ctor();
 
-	dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES,
-						DISPATCH_LOG_BYTES, 0, ctor);
+	dtl_cache = kmem_cache_create_usercopy("dtl", DISPATCH_LOG_BYTES,
+						DISPATCH_LOG_BYTES, 0, 0, DISPATCH_LOG_BYTES, ctor);
 	if (!dtl_cache) {
 		pr_warn("Failed to create dispatch trace log buffer cache\n");
 		pr_warn("Stolen time statistics will be unreliable\n");
@@ -816,6 +816,8 @@ static void __init pSeries_setup_arch(void)
 	/* Discover PIC type and setup ppc_md accordingly */
 	smp_init_pseries();
 
+	// Setup CPU hotplug callbacks
+	pseries_cpu_hotplug_init();
 
 	if (radix_enabled() && !mmu_has_feature(MMU_FTR_GTSE))
 		if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE))
@@ -847,7 +849,7 @@ static void __init pSeries_setup_arch(void)
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		vpa_init(boot_cpuid);
 
-		if (lppaca_shared_proc(get_lppaca())) {
+		if (lppaca_shared_proc()) {
 			static_branch_enable(&shared_processor);
 			pv_spinlocks_init();
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
@@ -1027,9 +1029,11 @@ static void __init pseries_add_hw_description(void)
 		return;
 	}
 
-	if (of_property_read_bool(of_root, "ibm,powervm-partition") ||
-	    of_property_read_bool(of_root, "ibm,fw-net-version"))
+	dn = of_find_node_by_path("/");
+	if (of_property_read_bool(dn, "ibm,powervm-partition") ||
+	    of_property_read_bool(dn, "ibm,fw-net-version"))
 		seq_buf_printf(&ppc_hw_desc, "hv:phyp ");
+	of_node_put(dn);
 }
 
 /*
@@ -1089,7 +1093,11 @@ static void pseries_power_off(void)
 
 static int __init pSeries_probe(void)
 {
-	if (!of_node_is_type(of_root, "chrp"))
+	struct device_node *root = of_find_node_by_path("/");
+	bool ret = of_node_is_type(root, "chrp");
+
+	of_node_put(root);
+	if (!ret)
 		return 0;
 
 	/* Cell blades firmware claims to be chrp while it's not. Until this
@@ -1116,6 +1124,13 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus)
 	return PCI_PROBE_NORMAL;
 }
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+static unsigned long pseries_memory_block_size(void)
+{
+	return memory_block_size;
+}
+#endif
+
 struct pci_controller_ops pseries_pci_controller_ops = {
 	.probe_mode		= pSeries_pci_probe_mode,
 #ifdef CONFIG_SPAPR_TCE_IOMMU
@@ -1144,7 +1159,6 @@ define_machine(pseries) {
 	.machine_check_exception = pSeries_machine_check_exception,
 	.machine_check_log_err	= pSeries_machine_check_log_err,
 #ifdef CONFIG_KEXEC_CORE
-	.machine_kexec          = pseries_machine_kexec,
 	.kexec_cpu_down         = pseries_kexec_cpu_down,
 #endif
 #ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index c597711ef20a..db99725e752b 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -39,7 +39,7 @@
 #include <asm/xive.h>
 #include <asm/dbell.h>
 #include <asm/plpar_wrappers.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/svm.h>
 #include <asm/kvm_guest.h>
 
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 5c43435472cc..c51db63d3e88 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -13,6 +13,7 @@
 #include <asm/mmu.h>
 #include <asm/rtas.h>
 #include <asm/topology.h>
+#include "pseries.h"
 
 static struct device suspend_dev;
 
@@ -125,7 +126,7 @@ static ssize_t show_hibernate(struct device *dev,
 
 static DEVICE_ATTR(hibernate, 0644, show_hibernate, store_hibernate);
 
-static struct bus_type suspend_subsys = {
+static const struct bus_type suspend_subsys = {
 	.name = "power",
 	.dev_name = "power",
 };
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
index 3b4045d508ec..384c9dc1899a 100644
--- a/arch/powerpc/platforms/pseries/svm.c
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -8,6 +8,7 @@
 
 #include <linux/mm.h>
 #include <linux/memblock.h>
+#include <linux/mem_encrypt.h>
 #include <linux/cc_platform.h>
 #include <asm/machdep.h>
 #include <asm/svm.h>
diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c
index f9f682724e77..9e05a0e99cad 100644
--- a/arch/powerpc/platforms/pseries/vas-sysfs.c
+++ b/arch/powerpc/platforms/pseries/vas-sysfs.c
@@ -162,13 +162,13 @@ static const struct sysfs_ops vas_sysfs_ops = {
 	.store	=	vas_type_store,
 };
 
-static struct kobj_type vas_def_attr_type = {
+static const struct kobj_type vas_def_attr_type = {
 		.release	=	vas_type_release,
 		.sysfs_ops      =       &vas_sysfs_ops,
 		.default_groups	=	vas_def_capab_groups,
 };
 
-static struct kobj_type vas_qos_attr_type = {
+static const struct kobj_type vas_qos_attr_type = {
 		.release	=	vas_type_release,
 		.sysfs_ops	=	&vas_sysfs_ops,
 		.default_groups	=	vas_qos_capab_groups,
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index 513180467562..c25eb1a38185 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -17,6 +17,7 @@
 #include <asm/hvcall.h>
 #include <asm/plpar_wrappers.h>
 #include <asm/firmware.h>
+#include <asm/vphn.h>
 #include <asm/vas.h>
 #include "vas.h"
 
@@ -37,7 +38,27 @@ static long hcall_return_busy_check(long rc)
 {
 	/* Check if we are stalled for some time */
 	if (H_IS_LONG_BUSY(rc)) {
-		msleep(get_longbusy_msecs(rc));
+		unsigned int ms;
+		/*
+		 * Allocate, Modify and Deallocate HCALLs returns
+		 * H_LONG_BUSY_ORDER_1_MSEC or H_LONG_BUSY_ORDER_10_MSEC
+		 * for the long delay. So the sleep time should always
+		 * be either 1 or 10msecs, but in case if the HCALL
+		 * returns the long delay > 10 msecs, clamp the sleep
+		 * time to 10msecs.
+		 */
+		ms = clamp(get_longbusy_msecs(rc), 1, 10);
+
+		/*
+		 * msleep() will often sleep at least 20 msecs even
+		 * though the hypervisor suggests that the OS reissue
+		 * HCALLs after 1 or 10msecs. Also the delay hint from
+		 * the HCALL is just a suggestion. So OK to pause for
+		 * less time than the hinted delay. Use usleep_range()
+		 * to ensure we don't sleep much longer than actually
+		 * needed.
+		 */
+		usleep_range(ms * (USEC_PER_MSEC / 10), ms * USEC_PER_MSEC);
 		rc = H_BUSY;
 	} else if (rc == H_BUSY) {
 		cond_resched();
@@ -227,7 +248,7 @@ static irqreturn_t pseries_vas_irq_handler(int irq, void *data)
 	struct pseries_vas_window *txwin = data;
 
 	/*
-	 * The thread hanlder will process this interrupt if it is
+	 * The thread handler will process this interrupt if it is
 	 * already running.
 	 */
 	atomic_inc(&txwin->pending_faults);
@@ -340,7 +361,7 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 
 	if (atomic_inc_return(&cop_feat_caps->nr_used_credits) >
 			atomic_read(&cop_feat_caps->nr_total_credits)) {
-		pr_err("Credits are not available to allocate window\n");
+		pr_err_ratelimited("Credits are not available to allocate window\n");
 		rc = -EINVAL;
 		goto out;
 	}
@@ -384,11 +405,15 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 	 * same fault IRQ is not freed by the OS before.
 	 */
 	mutex_lock(&vas_pseries_mutex);
-	if (migration_in_progress)
+	if (migration_in_progress) {
 		rc = -EBUSY;
-	else
+	} else {
 		rc = allocate_setup_window(txwin, (u64 *)&domain[0],
 				   cop_feat_caps->win_type);
+		if (!rc)
+			caps->nr_open_wins_progress++;
+	}
+
 	mutex_unlock(&vas_pseries_mutex);
 	if (rc)
 		goto out;
@@ -403,8 +428,17 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 		goto out_free;
 
 	txwin->win_type = cop_feat_caps->win_type;
-	mutex_lock(&vas_pseries_mutex);
+
 	/*
+	 * The migration SUSPEND thread sets migration_in_progress and
+	 * closes all open windows from the list. But the window is
+	 * added to the list after open and modify HCALLs. So possible
+	 * that migration_in_progress is set before modify HCALL which
+	 * may cause some windows are still open when the hypervisor
+	 * initiates the migration.
+	 * So checks the migration_in_progress flag again and close all
+	 * open windows.
+	 *
 	 * Possible to lose the acquired credit with DLPAR core
 	 * removal after the window is opened. So if there are any
 	 * closed windows (means with lost credits), do not give new
@@ -412,9 +446,11 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 	 * after the existing windows are reopened when credits are
 	 * available.
 	 */
-	if (!caps->nr_close_wins) {
+	mutex_lock(&vas_pseries_mutex);
+	if (!caps->nr_close_wins && !migration_in_progress) {
 		list_add(&txwin->win_list, &caps->list);
 		caps->nr_open_windows++;
+		caps->nr_open_wins_progress--;
 		mutex_unlock(&vas_pseries_mutex);
 		vas_user_win_add_mm_context(&txwin->vas_win.task_ref);
 		return &txwin->vas_win;
@@ -423,7 +459,7 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 
 	put_vas_user_win_ref(&txwin->vas_win.task_ref);
 	rc = -EBUSY;
-	pr_err("No credit is available to allocate window\n");
+	pr_err_ratelimited("No credit is available to allocate window\n");
 
 out_free:
 	/*
@@ -432,6 +468,12 @@ out_free:
 	 */
 	free_irq_setup(txwin);
 	h_deallocate_vas_window(txwin->vas_win.winid);
+	/*
+	 * Hold mutex and reduce nr_open_wins_progress counter.
+	 */
+	mutex_lock(&vas_pseries_mutex);
+	caps->nr_open_wins_progress--;
+	mutex_unlock(&vas_pseries_mutex);
 out:
 	atomic_dec(&cop_feat_caps->nr_used_credits);
 	kfree(txwin);
@@ -507,8 +549,8 @@ static int vas_deallocate_window(struct vas_window *vwin)
 	vascaps[win->win_type].nr_open_windows--;
 	mutex_unlock(&vas_pseries_mutex);
 
-	put_vas_user_win_ref(&vwin->task_ref);
 	mm_context_remove_vas_window(vwin->task_ref.mm);
+	put_vas_user_win_ref(&vwin->task_ref);
 
 	kfree(win);
 	return 0;
@@ -744,6 +786,12 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds,
 		}
 
 		task_ref = &win->vas_win.task_ref;
+		/*
+		 * VAS mmap (coproc_mmap()) and its fault handler
+		 * (vas_mmap_fault()) are called after holding mmap lock.
+		 * So hold mmap mutex after mmap_lock to avoid deadlock.
+		 */
+		mmap_write_lock(task_ref->mm);
 		mutex_lock(&task_ref->mmap_mutex);
 		vma = task_ref->vma;
 		/*
@@ -752,7 +800,6 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds,
 		 */
 		win->vas_win.status |= flag;
 
-		mmap_write_lock(task_ref->mm);
 		/*
 		 * vma is set in the original mapping. But this mapping
 		 * is done with mmap() after the window is opened with ioctl.
@@ -762,8 +809,8 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds,
 		if (vma)
 			zap_vma_pages(vma);
 
-		mmap_write_unlock(task_ref->mm);
 		mutex_unlock(&task_ref->mmap_mutex);
+		mmap_write_unlock(task_ref->mm);
 		/*
 		 * Close VAS window in the hypervisor, but do not
 		 * free vas_window struct since it may be reused
@@ -931,14 +978,14 @@ int vas_migration_handler(int action)
 	struct vas_caps *vcaps;
 	int i, rc = 0;
 
+	pr_info("VAS migration event %d\n", action);
+
 	/*
 	 * NX-GZIP is not enabled. Nothing to do for migration.
 	 */
 	if (!copypaste_feat)
 		return rc;
 
-	mutex_lock(&vas_pseries_mutex);
-
 	if (action == VAS_SUSPEND)
 		migration_in_progress = true;
 	else
@@ -984,12 +1031,27 @@ int vas_migration_handler(int action)
 
 		switch (action) {
 		case VAS_SUSPEND:
+			mutex_lock(&vas_pseries_mutex);
 			rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows,
 							true);
+			/*
+			 * Windows are included in the list after successful
+			 * open. So wait for closing these in-progress open
+			 * windows in vas_allocate_window() which will be
+			 * done if the migration_in_progress is set.
+			 */
+			while (vcaps->nr_open_wins_progress) {
+				mutex_unlock(&vas_pseries_mutex);
+				msleep(10);
+				mutex_lock(&vas_pseries_mutex);
+			}
+			mutex_unlock(&vas_pseries_mutex);
 			break;
 		case VAS_RESUME:
+			mutex_lock(&vas_pseries_mutex);
 			atomic_set(&caps->nr_total_credits, new_nr_creds);
 			rc = reconfig_open_windows(vcaps, new_nr_creds, true);
+			mutex_unlock(&vas_pseries_mutex);
 			break;
 		default:
 			/* should not happen */
@@ -1005,8 +1067,9 @@ int vas_migration_handler(int action)
 			goto out;
 	}
 
+	pr_info("VAS migration event (%d) successful\n", action);
+
 out:
-	mutex_unlock(&vas_pseries_mutex);
 	return rc;
 }
 
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index 7115043ec488..45567cd13178 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -91,6 +91,8 @@ struct vas_cop_feat_caps {
 struct vas_caps {
 	struct vas_cop_feat_caps caps;
 	struct list_head list;	/* List of open windows */
+	int nr_open_wins_progress;	/* Number of open windows in */
+					/* progress. Used in migration */
 	int nr_close_wins;	/* closed windows in the hypervisor for DLPAR */
 	int nr_open_windows;	/* Number of successful open windows */
 	u8 feat;		/* Feature type */
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 2dc9cbc4bcd8..18cffac5468f 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -512,18 +512,21 @@ static void vio_dma_iommu_free_coherent(struct device *dev, size_t size,
 	vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 }
 
-static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
-                                         unsigned long offset, size_t size,
-                                         enum dma_data_direction direction,
-                                         unsigned long attrs)
+static dma_addr_t vio_dma_iommu_map_phys(struct device *dev, phys_addr_t phys,
+					 size_t size,
+					 enum dma_data_direction direction,
+					 unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 	dma_addr_t ret = DMA_MAPPING_ERROR;
 
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return ret;
+
 	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))))
 		goto out_fail;
-	ret = iommu_map_page(dev, tbl, page, offset, size, dma_get_mask(dev),
+	ret = iommu_map_phys(dev, tbl, phys, size, dma_get_mask(dev),
 			direction, attrs);
 	if (unlikely(ret == DMA_MAPPING_ERROR))
 		goto out_deallocate;
@@ -536,7 +539,7 @@ out_fail:
 	return DMA_MAPPING_ERROR;
 }
 
-static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
+static void vio_dma_iommu_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 				     size_t size,
 				     enum dma_data_direction direction,
 				     unsigned long attrs)
@@ -544,7 +547,7 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
-	iommu_unmap_page(tbl, dma_handle, size, direction, attrs);
+	iommu_unmap_phys(tbl, dma_handle, size, direction, attrs);
 	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
 }
 
@@ -605,13 +608,13 @@ static const struct dma_map_ops vio_dma_mapping_ops = {
 	.free              = vio_dma_iommu_free_coherent,
 	.map_sg            = vio_dma_iommu_map_sg,
 	.unmap_sg          = vio_dma_iommu_unmap_sg,
-	.map_page          = vio_dma_iommu_map_page,
-	.unmap_page        = vio_dma_iommu_unmap_page,
+	.map_phys          = vio_dma_iommu_map_phys,
+	.unmap_phys        = vio_dma_iommu_unmap_phys,
 	.dma_supported     = dma_iommu_dma_supported,
 	.get_required_mask = dma_iommu_get_required_mask,
 	.mmap		   = dma_common_mmap,
 	.get_sgtable	   = dma_common_get_sgtable,
-	.alloc_pages	   = dma_common_alloc_pages,
+	.alloc_pages_op	   = dma_common_alloc_pages,
 	.free_pages	   = dma_common_free_pages,
 };
 
@@ -991,18 +994,6 @@ static DEVICE_ATTR_RO(cmo_allocated);
 static DEVICE_ATTR_RW(cmo_desired);
 static DEVICE_ATTR_RW(cmo_allocs_failed);
 
-static struct attribute *vio_cmo_dev_attrs[] = {
-	&dev_attr_name.attr,
-	&dev_attr_devspec.attr,
-	&dev_attr_modalias.attr,
-	&dev_attr_cmo_entitled.attr,
-	&dev_attr_cmo_allocated.attr,
-	&dev_attr_cmo_desired.attr,
-	&dev_attr_cmo_allocs_failed.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(vio_cmo_dev);
-
 /* sysfs bus functions and data structures for CMO */
 
 #define viobus_cmo_rd_attr(name)                                        \
@@ -1062,11 +1053,7 @@ static struct attribute *vio_bus_attrs[] = {
 };
 ATTRIBUTE_GROUPS(vio_bus);
 
-static void __init vio_cmo_sysfs_init(void)
-{
-	vio_bus_type.dev_groups = vio_cmo_dev_groups;
-	vio_bus_type.bus_groups = vio_bus_groups;
-}
+static void __init vio_cmo_sysfs_init(void) { }
 #else /* CONFIG_PPC_SMLPAR */
 int vio_cmo_entitlement_update(size_t new_entitlement) { return 0; }
 void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired) {}
@@ -1584,14 +1571,6 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(modalias);
 
-static struct attribute *vio_dev_attrs[] = {
-	&dev_attr_name.attr,
-	&dev_attr_devspec.attr,
-	&dev_attr_modalias.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(vio_dev);
-
 void vio_unregister_device(struct vio_dev *viodev)
 {
 	device_unregister(&viodev->dev);
@@ -1600,10 +1579,10 @@ void vio_unregister_device(struct vio_dev *viodev)
 }
 EXPORT_SYMBOL(vio_unregister_device);
 
-static int vio_bus_match(struct device *dev, struct device_driver *drv)
+static int vio_bus_match(struct device *dev, const struct device_driver *drv)
 {
 	const struct vio_dev *vio_dev = to_vio_dev(dev);
-	struct vio_driver *vio_drv = to_vio_driver(drv);
+	const struct vio_driver *vio_drv = to_vio_driver(drv);
 	const struct vio_device_id *ids = vio_drv->id_table;
 
 	return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL);
@@ -1616,17 +1595,45 @@ static int vio_hotplug(const struct device *dev, struct kobj_uevent_env *env)
 	const char *cp;
 
 	dn = dev->of_node;
-	if (!dn)
-		return -ENODEV;
-	cp = of_get_property(dn, "compatible", NULL);
-	if (!cp)
-		return -ENODEV;
+	if (dn && (cp = of_get_property(dn, "compatible", NULL)))
+		add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp);
 
-	add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp);
 	return 0;
 }
 
-struct bus_type vio_bus_type = {
+#ifdef CONFIG_PPC_SMLPAR
+static struct attribute *vio_cmo_dev_attrs[] = {
+	&dev_attr_name.attr,
+	&dev_attr_devspec.attr,
+	&dev_attr_modalias.attr,
+	&dev_attr_cmo_entitled.attr,
+	&dev_attr_cmo_allocated.attr,
+	&dev_attr_cmo_desired.attr,
+	&dev_attr_cmo_allocs_failed.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(vio_cmo_dev);
+
+const struct bus_type vio_bus_type = {
+	.name = "vio",
+	.dev_groups = vio_cmo_dev_groups,
+	.bus_groups = vio_bus_groups,
+	.uevent = vio_hotplug,
+	.match = vio_bus_match,
+	.probe = vio_bus_probe,
+	.remove = vio_bus_remove,
+	.shutdown = vio_bus_shutdown,
+};
+#else /* CONFIG_PPC_SMLPAR */
+static struct attribute *vio_dev_attrs[] = {
+	&dev_attr_name.attr,
+	&dev_attr_devspec.attr,
+	&dev_attr_modalias.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(vio_dev);
+
+const struct bus_type vio_bus_type = {
 	.name = "vio",
 	.dev_groups = vio_dev_groups,
 	.uevent = vio_hotplug,
@@ -1635,6 +1642,7 @@ struct bus_type vio_bus_type = {
 	.remove = vio_bus_remove,
 	.shutdown = vio_bus_shutdown,
 };
+#endif /* CONFIG_PPC_SMLPAR */
 
 /**
  * vio_get_attribute: - get attribute for virtual device
@@ -1684,7 +1692,7 @@ struct vio_dev *vio_find_node(struct device_node *vnode)
 	/* construct the kobject name from the device node */
 	if (of_node_is_type(vnode_parent, "vdevice")) {
 		const __be32 *prop;
-		
+
 		prop = of_get_property(vnode, "reg", NULL);
 		if (!prop)
 			goto out;
diff --git a/arch/powerpc/platforms/pseries/vphn.c b/arch/powerpc/platforms/pseries/vphn.c
index cca474a2c396..3f85ece3c872 100644
--- a/arch/powerpc/platforms/pseries/vphn.c
+++ b/arch/powerpc/platforms/pseries/vphn.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <asm/byteorder.h>
-#include <asm/lppaca.h>
+#include <asm/vphn.h>
 
 /*
  * The associativity domain numbers are returned from the hypervisor as a
diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile
index 6f5e2727963c..e9890085953e 100644
--- a/arch/powerpc/purgatory/Makefile
+++ b/arch/powerpc/purgatory/Makefile
@@ -1,10 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
 
-KASAN_SANITIZE := n
-KCSAN_SANITIZE := n
-
 targets += trampoline_$(BITS).o purgatory.ro
 
+# 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))
+
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined
 
 $(obj)/purgatory.ro: $(obj)/trampoline_$(BITS).o FORCE
diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig
index 5aa92ff3622d..18ff2c4a814a 100644
--- a/arch/powerpc/sysdev/Kconfig
+++ b/arch/powerpc/sysdev/Kconfig
@@ -5,12 +5,12 @@
 
 config PPC4xx_PCI_EXPRESS
 	bool
-	depends on PCI && 4xx
+	depends on PCI && 44x
 
 config PPC4xx_HSTA_MSI
 	bool
 	depends on PCI_MSI
-	depends on PCI && 4xx
+	depends on PCI && 44x
 
 config PPC_MSI_BITMAP
 	bool
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 9cb1d029511a..0834a9a12600 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -1,7 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
-ccflags-$(CONFIG_PPC64)		:= $(NO_MINIMAL_TOC)
-
 mpic-msi-obj-$(CONFIG_PCI_MSI)	+= mpic_msi.o mpic_u3msi.o
 obj-$(CONFIG_MPIC)		+= mpic.o $(mpic-msi-obj-y)
 obj-$(CONFIG_MPIC_TIMER)        += mpic_timer.o
@@ -14,7 +12,6 @@ obj-$(CONFIG_PPC_MSI_BITMAP)	+= msi_bitmap.o
 
 obj-$(CONFIG_PPC_MPC106)	+= grackle.o
 obj-$(CONFIG_PPC_DCR_NATIVE)	+= dcr-low.o
-obj-$(CONFIG_PPC_PMI)		+= pmi.o
 obj-$(CONFIG_U3_DART)		+= dart_iommu.o
 obj-$(CONFIG_MMIO_NVRAM)	+= mmio_nvram.o
 obj-$(CONFIG_FSL_SOC)		+= fsl_soc.o fsl_mpic_err.o
diff --git a/arch/powerpc/sysdev/cpm2.c b/arch/powerpc/sysdev/cpm2.c
index 915f4d3991c3..14cc5ea936c0 100644
--- a/arch/powerpc/sysdev/cpm2.c
+++ b/arch/powerpc/sysdev/cpm2.c
@@ -37,11 +37,9 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/mpc8260.h>
 #include <asm/page.h>
 #include <asm/cpm2.h>
 #include <asm/rheap.h>
-#include <asm/fs_pd.h>
 
 #include <sysdev/fsl_soc.h>
 
@@ -119,9 +117,9 @@ void __cpm2_setbrg(uint brg, uint rate, uint clk, int div16, int src)
 	/* This is good enough to get SMCs running.....
 	*/
 	if (brg < 4) {
-		bp = cpm2_map_size(im_brgc1, 16);
+		bp = &cpm2_immr->im_brgc1;
 	} else {
-		bp = cpm2_map_size(im_brgc5, 16);
+		bp = &cpm2_immr->im_brgc5;
 		brg -= 4;
 	}
 	bp += brg;
@@ -131,7 +129,6 @@ void __cpm2_setbrg(uint brg, uint rate, uint clk, int div16, int src)
 		val |= CPM_BRG_DIV16;
 
 	out_be32(bp, val);
-	cpm2_unmap(bp);
 }
 EXPORT_SYMBOL(__cpm2_setbrg);
 
@@ -140,7 +137,6 @@ int __init cpm2_clk_setup(enum cpm_clk_target target, int clock, int mode)
 	int ret = 0;
 	int shift;
 	int i, bits = 0;
-	cpmux_t __iomem *im_cpmux;
 	u32 __iomem *reg;
 	u32 mask = 7;
 
@@ -203,35 +199,33 @@ int __init cpm2_clk_setup(enum cpm_clk_target target, int clock, int mode)
 		{CPM_CLK_SCC4, CPM_CLK8, 7},
 	};
 
-	im_cpmux = cpm2_map(im_cpmux);
-
 	switch (target) {
 	case CPM_CLK_SCC1:
-		reg = &im_cpmux->cmx_scr;
+		reg = &cpm2_immr->im_cpmux.cmx_scr;
 		shift = 24;
 		break;
 	case CPM_CLK_SCC2:
-		reg = &im_cpmux->cmx_scr;
+		reg = &cpm2_immr->im_cpmux.cmx_scr;
 		shift = 16;
 		break;
 	case CPM_CLK_SCC3:
-		reg = &im_cpmux->cmx_scr;
+		reg = &cpm2_immr->im_cpmux.cmx_scr;
 		shift = 8;
 		break;
 	case CPM_CLK_SCC4:
-		reg = &im_cpmux->cmx_scr;
+		reg = &cpm2_immr->im_cpmux.cmx_scr;
 		shift = 0;
 		break;
 	case CPM_CLK_FCC1:
-		reg = &im_cpmux->cmx_fcr;
+		reg = &cpm2_immr->im_cpmux.cmx_fcr;
 		shift = 24;
 		break;
 	case CPM_CLK_FCC2:
-		reg = &im_cpmux->cmx_fcr;
+		reg = &cpm2_immr->im_cpmux.cmx_fcr;
 		shift = 16;
 		break;
 	case CPM_CLK_FCC3:
-		reg = &im_cpmux->cmx_fcr;
+		reg = &cpm2_immr->im_cpmux.cmx_fcr;
 		shift = 8;
 		break;
 	default:
@@ -261,7 +255,6 @@ int __init cpm2_clk_setup(enum cpm_clk_target target, int clock, int mode)
 
 	out_be32(reg, (in_be32(reg) & ~mask) | bits);
 
-	cpm2_unmap(im_cpmux);
 	return ret;
 }
 
@@ -270,7 +263,6 @@ int __init cpm2_smc_clk_setup(enum cpm_clk_target target, int clock)
 	int ret = 0;
 	int shift;
 	int i, bits = 0;
-	cpmux_t __iomem *im_cpmux;
 	u8 __iomem *reg;
 	u8 mask = 3;
 
@@ -285,16 +277,14 @@ int __init cpm2_smc_clk_setup(enum cpm_clk_target target, int clock)
 		{CPM_CLK_SMC2, CPM_CLK15, 3},
 	};
 
-	im_cpmux = cpm2_map(im_cpmux);
-
 	switch (target) {
 	case CPM_CLK_SMC1:
-		reg = &im_cpmux->cmx_smr;
+		reg = &cpm2_immr->im_cpmux.cmx_smr;
 		mask = 3;
 		shift = 4;
 		break;
 	case CPM_CLK_SMC2:
-		reg = &im_cpmux->cmx_smr;
+		reg = &cpm2_immr->im_cpmux.cmx_smr;
 		mask = 3;
 		shift = 0;
 		break;
@@ -317,7 +307,6 @@ int __init cpm2_smc_clk_setup(enum cpm_clk_target target, int clock)
 
 	out_8(reg, (in_8(reg) & ~mask) | bits);
 
-	cpm2_unmap(im_cpmux);
 	return ret;
 }
 
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index cb9ba4ef557a..4a59ed1d62ce 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -33,9 +33,7 @@
 #include <linux/irqdomain.h>
 
 #include <asm/immap_cpm2.h>
-#include <asm/mpc8260.h>
 #include <asm/io.h>
-#include <asm/fs_pd.h>
 
 #include "cpm2_pic.h"
 
@@ -209,7 +207,7 @@ unsigned int cpm2_get_irq(void)
 
 	if (irq == 0)
 		return(-1);
-	return irq_linear_revmap(cpm2_pic_host, irq);
+	return irq_find_mapping(cpm2_pic_host, irq);
 }
 
 static int cpm2_pic_host_map(struct irq_domain *h, unsigned int virq,
@@ -231,7 +229,7 @@ void cpm2_pic_init(struct device_node *node)
 {
 	int i;
 
-	cpm2_intctl = cpm2_map(im_intctl);
+	cpm2_intctl = &cpm2_immr->im_intctl;
 
 	/* Clear the CPM IRQ controller, in case it has any bits set
 	 * from the bootloader
@@ -261,7 +259,8 @@ void cpm2_pic_init(struct device_node *node)
 	out_be32(&cpm2_intctl->ic_scprrl, 0x05309770);
 
 	/* create a legacy host */
-	cpm2_pic_host = irq_domain_add_linear(node, 64, &cpm2_pic_host_ops, NULL);
+	cpm2_pic_host = irq_domain_create_linear(of_fwnode_handle(node), 64,
+						 &cpm2_pic_host_ops, NULL);
 	if (cpm2_pic_host == NULL) {
 		printk(KERN_ERR "CPM2 PIC: failed to allocate irq host!\n");
 		return;
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 8234013a8772..07ea605ab0e6 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -15,11 +15,9 @@
  */
 
 #include <linux/init.h>
-#include <linux/of_device.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
 #include <linux/slab.h>
 
 #include <asm/udbg.h>
@@ -30,10 +28,6 @@
 
 #include <mm/mmu_decl.h>
 
-#if defined(CONFIG_CPM2) || defined(CONFIG_8xx_GPIO)
-#include <linux/gpio/legacy-of-mm-gpiochip.h>
-#endif
-
 static int __init cpm_init(void)
 {
 	struct device_node *np;
@@ -93,32 +87,33 @@ void __init udbg_init_cpm(void)
 
 #if defined(CONFIG_CPM2) || defined(CONFIG_8xx_GPIO)
 
+#include <linux/gpio/driver.h>
+
 struct cpm2_ioports {
 	u32 dir, par, sor, odr, dat;
 	u32 res[3];
 };
 
 struct cpm2_gpio32_chip {
-	struct of_mm_gpio_chip mm_gc;
+	struct gpio_chip gc;
+	void __iomem *regs;
 	spinlock_t lock;
 
 	/* shadowed data register to clear/set bits safely */
 	u32 cpdata;
 };
 
-static void cpm2_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
+static void cpm2_gpio32_save_regs(struct cpm2_gpio32_chip *cpm2_gc)
 {
-	struct cpm2_gpio32_chip *cpm2_gc =
-		container_of(mm_gc, struct cpm2_gpio32_chip, mm_gc);
-	struct cpm2_ioports __iomem *iop = mm_gc->regs;
+	struct cpm2_ioports __iomem *iop = cpm2_gc->regs;
 
 	cpm2_gc->cpdata = in_be32(&iop->dat);
 }
 
 static int cpm2_gpio32_get(struct gpio_chip *gc, unsigned int gpio)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
-	struct cpm2_ioports __iomem *iop = mm_gc->regs;
+	struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(gc);
+	struct cpm2_ioports __iomem *iop = cpm2_gc->regs;
 	u32 pin_mask;
 
 	pin_mask = 1 << (31 - gpio);
@@ -126,11 +121,9 @@ static int cpm2_gpio32_get(struct gpio_chip *gc, unsigned int gpio)
 	return !!(in_be32(&iop->dat) & pin_mask);
 }
 
-static void __cpm2_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask,
-	int value)
+static void __cpm2_gpio32_set(struct cpm2_gpio32_chip *cpm2_gc, u32 pin_mask, int value)
 {
-	struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(&mm_gc->gc);
-	struct cpm2_ioports __iomem *iop = mm_gc->regs;
+	struct cpm2_ioports __iomem *iop = cpm2_gc->regs;
 
 	if (value)
 		cpm2_gc->cpdata |= pin_mask;
@@ -140,32 +133,32 @@ static void __cpm2_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask,
 	out_be32(&iop->dat, cpm2_gc->cpdata);
 }
 
-static void cpm2_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
+static int cpm2_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
 	struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(gc);
 	unsigned long flags;
 	u32 pin_mask = 1 << (31 - gpio);
 
 	spin_lock_irqsave(&cpm2_gc->lock, flags);
 
-	__cpm2_gpio32_set(mm_gc, pin_mask, value);
+	__cpm2_gpio32_set(cpm2_gc, pin_mask, value);
 
 	spin_unlock_irqrestore(&cpm2_gc->lock, flags);
+
+	return 0;
 }
 
 static int cpm2_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
 	struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(gc);
-	struct cpm2_ioports __iomem *iop = mm_gc->regs;
+	struct cpm2_ioports __iomem *iop = cpm2_gc->regs;
 	unsigned long flags;
 	u32 pin_mask = 1 << (31 - gpio);
 
 	spin_lock_irqsave(&cpm2_gc->lock, flags);
 
 	setbits32(&iop->dir, pin_mask);
-	__cpm2_gpio32_set(mm_gc, pin_mask, val);
+	__cpm2_gpio32_set(cpm2_gc, pin_mask, val);
 
 	spin_unlock_irqrestore(&cpm2_gc->lock, flags);
 
@@ -174,9 +167,8 @@ static int cpm2_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 static int cpm2_gpio32_dir_in(struct gpio_chip *gc, unsigned int gpio)
 {
-	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
 	struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(gc);
-	struct cpm2_ioports __iomem *iop = mm_gc->regs;
+	struct cpm2_ioports __iomem *iop = cpm2_gc->regs;
 	unsigned long flags;
 	u32 pin_mask = 1 << (31 - gpio);
 
@@ -193,19 +185,17 @@ int cpm2_gpiochip_add32(struct device *dev)
 {
 	struct device_node *np = dev->of_node;
 	struct cpm2_gpio32_chip *cpm2_gc;
-	struct of_mm_gpio_chip *mm_gc;
 	struct gpio_chip *gc;
 
-	cpm2_gc = kzalloc(sizeof(*cpm2_gc), GFP_KERNEL);
+	cpm2_gc = devm_kzalloc(dev, sizeof(*cpm2_gc), GFP_KERNEL);
 	if (!cpm2_gc)
 		return -ENOMEM;
 
 	spin_lock_init(&cpm2_gc->lock);
 
-	mm_gc = &cpm2_gc->mm_gc;
-	gc = &mm_gc->gc;
+	gc = &cpm2_gc->gc;
 
-	mm_gc->save_regs = cpm2_gpio32_save_regs;
+	gc->base = -1;
 	gc->ngpio = 32;
 	gc->direction_input = cpm2_gpio32_dir_in;
 	gc->direction_output = cpm2_gpio32_dir_out;
@@ -214,6 +204,16 @@ int cpm2_gpiochip_add32(struct device *dev)
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
 
-	return of_mm_gpiochip_add_data(np, mm_gc, cpm2_gc);
+	gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np);
+	if (!gc->label)
+		return -ENOMEM;
+
+	cpm2_gc->regs = devm_of_iomap(dev, np, 0, NULL);
+	if (IS_ERR(cpm2_gc->regs))
+		return PTR_ERR(cpm2_gc->regs);
+
+	cpm2_gpio32_save_regs(cpm2_gc);
+
+	return devm_gpiochip_add_data(dev, gc, cpm2_gc);
 }
 #endif /* CONFIG_CPM2 || CONFIG_8xx_GPIO */
diff --git a/arch/powerpc/sysdev/cpm_gpio.c b/arch/powerpc/sysdev/cpm_gpio.c
index 0695d26bd301..40f57111e93e 100644
--- a/arch/powerpc/sysdev/cpm_gpio.c
+++ b/arch/powerpc/sysdev/cpm_gpio.c
@@ -9,7 +9,8 @@
  */
 
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 
 #include <asm/cpm.h>
 #ifdef CONFIG_8xx_GPIO
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 98096bbfd62e..c0d10c149661 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -24,7 +24,6 @@
 #include <linux/suspend.h>
 #include <linux/memblock.h>
 #include <linux/gfp.h>
-#include <linux/kmemleak.h>
 #include <linux/of_address.h>
 #include <asm/io.h>
 #include <asm/iommu.h>
@@ -243,9 +242,6 @@ static void __init allocate_dart(void)
 	if (!dart_tablebase)
 		panic("Failed to allocate 16MB below 2GB for DART table\n");
 
-	/* There is no point scanning the DART space for leaks*/
-	kmemleak_no_scan((void *)dart_tablebase);
-
 	/* Allocate a spare page to map all invalid DART pages. We need to do
 	 * that to work around what looks like a problem with the HT bridge
 	 * prefetching into invalid pages and corrupting data
diff --git a/arch/powerpc/sysdev/dcr-low.S b/arch/powerpc/sysdev/dcr-low.S
index 329b9c4ae542..e8401b205d38 100644
--- a/arch/powerpc/sysdev/dcr-low.S
+++ b/arch/powerpc/sysdev/dcr-low.S
@@ -5,10 +5,10 @@
  * Copyright (c) 2004 Eugene Surovegin <ebs@ebshome.net>
  */
 
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
 #include <asm/processor.h>
 #include <asm/bug.h>
-#include <asm/export.h>
 
 #define DCR_ACCESS_PROLOG(table) \
 	cmplwi	cr0,r3,1024;	 \
diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c
index 70ce66eadff1..cb44a69958e7 100644
--- a/arch/powerpc/sysdev/dcr.c
+++ b/arch/powerpc/sysdev/dcr.c
@@ -11,107 +11,6 @@
 #include <linux/of_address.h>
 #include <asm/dcr.h>
 
-#ifdef CONFIG_PPC_DCR_MMIO
-static struct device_node *find_dcr_parent(struct device_node *node)
-{
-	struct device_node *par, *tmp;
-	const u32 *p;
-
-	for (par = of_node_get(node); par;) {
-		if (of_property_read_bool(par, "dcr-controller"))
-			break;
-		p = of_get_property(par, "dcr-parent", NULL);
-		tmp = par;
-		if (p == NULL)
-			par = of_get_parent(par);
-		else
-			par = of_find_node_by_phandle(*p);
-		of_node_put(tmp);
-	}
-	return par;
-}
-#endif
-
-#if defined(CONFIG_PPC_DCR_NATIVE) && defined(CONFIG_PPC_DCR_MMIO)
-
-bool dcr_map_ok_generic(dcr_host_t host)
-{
-	if (host.type == DCR_HOST_NATIVE)
-		return dcr_map_ok_native(host.host.native);
-	else if (host.type == DCR_HOST_MMIO)
-		return dcr_map_ok_mmio(host.host.mmio);
-	else
-		return false;
-}
-EXPORT_SYMBOL_GPL(dcr_map_ok_generic);
-
-dcr_host_t dcr_map_generic(struct device_node *dev,
-			   unsigned int dcr_n,
-			   unsigned int dcr_c)
-{
-	dcr_host_t host;
-	struct device_node *dp;
-	const char *prop;
-
-	host.type = DCR_HOST_INVALID;
-
-	dp = find_dcr_parent(dev);
-	if (dp == NULL)
-		return host;
-
-	prop = of_get_property(dp, "dcr-access-method", NULL);
-
-	pr_debug("dcr_map_generic(dcr-access-method = %s)\n", prop);
-
-	if (!strcmp(prop, "native")) {
-		host.type = DCR_HOST_NATIVE;
-		host.host.native = dcr_map_native(dev, dcr_n, dcr_c);
-	} else if (!strcmp(prop, "mmio")) {
-		host.type = DCR_HOST_MMIO;
-		host.host.mmio = dcr_map_mmio(dev, dcr_n, dcr_c);
-	}
-
-	of_node_put(dp);
-	return host;
-}
-EXPORT_SYMBOL_GPL(dcr_map_generic);
-
-void dcr_unmap_generic(dcr_host_t host, unsigned int dcr_c)
-{
-	if (host.type == DCR_HOST_NATIVE)
-		dcr_unmap_native(host.host.native, dcr_c);
-	else if (host.type == DCR_HOST_MMIO)
-		dcr_unmap_mmio(host.host.mmio, dcr_c);
-	else /* host.type == DCR_HOST_INVALID */
-		WARN_ON(true);
-}
-EXPORT_SYMBOL_GPL(dcr_unmap_generic);
-
-u32 dcr_read_generic(dcr_host_t host, unsigned int dcr_n)
-{
-	if (host.type == DCR_HOST_NATIVE)
-		return dcr_read_native(host.host.native, dcr_n);
-	else if (host.type == DCR_HOST_MMIO)
-		return dcr_read_mmio(host.host.mmio, dcr_n);
-	else /* host.type == DCR_HOST_INVALID */
-		WARN_ON(true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(dcr_read_generic);
-
-void dcr_write_generic(dcr_host_t host, unsigned int dcr_n, u32 value)
-{
-	if (host.type == DCR_HOST_NATIVE)
-		dcr_write_native(host.host.native, dcr_n, value);
-	else if (host.type == DCR_HOST_MMIO)
-		dcr_write_mmio(host.host.mmio, dcr_n, value);
-	else /* host.type == DCR_HOST_INVALID */
-		WARN_ON(true);
-}
-EXPORT_SYMBOL_GPL(dcr_write_generic);
-
-#endif /* defined(CONFIG_PPC_DCR_NATIVE) && defined(CONFIG_PPC_DCR_MMIO) */
-
 unsigned int dcr_resource_start(const struct device_node *np,
 				unsigned int index)
 {
@@ -137,86 +36,5 @@ unsigned int dcr_resource_len(const struct device_node *np, unsigned int index)
 }
 EXPORT_SYMBOL_GPL(dcr_resource_len);
 
-#ifdef CONFIG_PPC_DCR_MMIO
-
-static u64 of_translate_dcr_address(struct device_node *dev,
-				    unsigned int dcr_n,
-				    unsigned int *out_stride)
-{
-	struct device_node *dp;
-	const u32 *p;
-	unsigned int stride;
-	u64 ret = OF_BAD_ADDR;
-
-	dp = find_dcr_parent(dev);
-	if (dp == NULL)
-		return OF_BAD_ADDR;
-
-	/* Stride is not properly defined yet, default to 0x10 for Axon */
-	p = of_get_property(dp, "dcr-mmio-stride", NULL);
-	stride = (p == NULL) ? 0x10 : *p;
-
-	/* XXX FIXME: Which property name is to use of the 2 following ? */
-	p = of_get_property(dp, "dcr-mmio-range", NULL);
-	if (p == NULL)
-		p = of_get_property(dp, "dcr-mmio-space", NULL);
-	if (p == NULL)
-		goto done;
-
-	/* Maybe could do some better range checking here */
-	ret = of_translate_address(dp, p);
-	if (ret != OF_BAD_ADDR)
-		ret += (u64)(stride) * (u64)dcr_n;
-	if (out_stride)
-		*out_stride = stride;
-
- done:
-	of_node_put(dp);
-	return ret;
-}
-
-dcr_host_mmio_t dcr_map_mmio(struct device_node *dev,
-			     unsigned int dcr_n,
-			     unsigned int dcr_c)
-{
-	dcr_host_mmio_t ret = { .token = NULL, .stride = 0, .base = dcr_n };
-	u64 addr;
-
-	pr_debug("dcr_map(%pOF, 0x%x, 0x%x)\n",
-		 dev, dcr_n, dcr_c);
-
-	addr = of_translate_dcr_address(dev, dcr_n, &ret.stride);
-	pr_debug("translates to addr: 0x%llx, stride: 0x%x\n",
-		 (unsigned long long) addr, ret.stride);
-	if (addr == OF_BAD_ADDR)
-		return ret;
-	pr_debug("mapping 0x%x bytes\n", dcr_c * ret.stride);
-	ret.token = ioremap(addr, dcr_c * ret.stride);
-	if (ret.token == NULL)
-		return ret;
-	pr_debug("mapped at 0x%p -> base is 0x%p\n",
-		 ret.token, ret.token - dcr_n * ret.stride);
-	ret.token -= dcr_n * ret.stride;
-	return ret;
-}
-EXPORT_SYMBOL_GPL(dcr_map_mmio);
-
-void dcr_unmap_mmio(dcr_host_mmio_t host, unsigned int dcr_c)
-{
-	dcr_host_mmio_t h = host;
-
-	if (h.token == NULL)
-		return;
-	h.token += host.base * h.stride;
-	iounmap(h.token);
-	h.token = NULL;
-}
-EXPORT_SYMBOL_GPL(dcr_unmap_mmio);
-
-#endif /* defined(CONFIG_PPC_DCR_MMIO) */
-
-#ifdef CONFIG_PPC_DCR_NATIVE
 DEFINE_SPINLOCK(dcr_ind_lock);
 EXPORT_SYMBOL_GPL(dcr_ind_lock);
-#endif	/* defined(CONFIG_PPC_DCR_NATIVE) */
-
diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c
index c7327b836d2b..b6f9774038e1 100644
--- a/arch/powerpc/sysdev/ehv_pic.c
+++ b/arch/powerpc/sysdev/ehv_pic.c
@@ -42,33 +42,33 @@ static u32 __iomem *mpic_percpu_base_vaddr;
  * Linux descriptor level callbacks
  */
 
-void ehv_pic_unmask_irq(struct irq_data *d)
+static void ehv_pic_unmask_irq(struct irq_data *d)
 {
 	unsigned int src = virq_to_hw(d->irq);
 
 	ev_int_set_mask(src, 0);
 }
 
-void ehv_pic_mask_irq(struct irq_data *d)
+static void ehv_pic_mask_irq(struct irq_data *d)
 {
 	unsigned int src = virq_to_hw(d->irq);
 
 	ev_int_set_mask(src, 1);
 }
 
-void ehv_pic_end_irq(struct irq_data *d)
+static void ehv_pic_end_irq(struct irq_data *d)
 {
 	unsigned int src = virq_to_hw(d->irq);
 
 	ev_int_eoi(src);
 }
 
-void ehv_pic_direct_end_irq(struct irq_data *d)
+static void ehv_pic_direct_end_irq(struct irq_data *d)
 {
 	out_be32(mpic_percpu_base_vaddr + MPIC_EOI / 4, 0);
 }
 
-int ehv_pic_set_affinity(struct irq_data *d, const struct cpumask *dest,
+static int ehv_pic_set_affinity(struct irq_data *d, const struct cpumask *dest,
 			 bool force)
 {
 	unsigned int src = virq_to_hw(d->irq);
@@ -109,7 +109,7 @@ static unsigned int ehv_pic_type_to_vecpri(unsigned int type)
 	}
 }
 
-int ehv_pic_set_irq_type(struct irq_data *d, unsigned int flow_type)
+static int ehv_pic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 {
 	unsigned int src = virq_to_hw(d->irq);
 	unsigned int vecpri, vold, vnew, prio, cpu_dest;
@@ -175,7 +175,7 @@ unsigned int ehv_pic_get_irq(void)
 	 * this will also setup revmap[] in the slow path for the first
 	 * time, next calls will always use fast path by indexing revmap
 	 */
-	return irq_linear_revmap(global_ehv_pic->irqhost, irq);
+	return irq_find_mapping(global_ehv_pic->irqhost, irq);
 }
 
 static int ehv_pic_host_match(struct irq_domain *h, struct device_node *node,
@@ -269,8 +269,9 @@ void __init ehv_pic_init(void)
 		return;
 	}
 
-	ehv_pic->irqhost = irq_domain_add_linear(np, NR_EHV_PIC_INTS,
-						 &ehv_pic_host_ops, ehv_pic);
+	ehv_pic->irqhost = irq_domain_create_linear(of_fwnode_handle(np),
+						    NR_EHV_PIC_INTS,
+						    &ehv_pic_host_ops, ehv_pic);
 	if (!ehv_pic->irqhost) {
 		of_node_put(np);
 		kfree(ehv_pic);
@@ -291,5 +292,5 @@ void __init ehv_pic_init(void)
 	ehv_pic->coreint_flag = of_property_read_bool(np, "has-external-proxy");
 
 	global_ehv_pic = ehv_pic;
-	irq_set_default_host(global_ehv_pic->irqhost);
+	irq_set_default_domain(global_ehv_pic->irqhost);
 }
diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c
index 39186ad6b3c3..3dabc9621810 100644
--- a/arch/powerpc/sysdev/fsl_gtm.c
+++ b/arch/powerpc/sysdev/fsl_gtm.c
@@ -77,7 +77,7 @@ struct gtm {
 static LIST_HEAD(gtms);
 
 /**
- * gtm_get_timer - request GTM timer to use it with the rest of GTM API
+ * gtm_get_timer16 - request GTM timer to use it with the rest of GTM API
  * Context:	non-IRQ
  *
  * This function reserves GTM timer for later use. It returns gtm_timer
@@ -110,7 +110,7 @@ struct gtm_timer *gtm_get_timer16(void)
 EXPORT_SYMBOL(gtm_get_timer16);
 
 /**
- * gtm_get_specific_timer - request specific GTM timer
+ * gtm_get_specific_timer16 - request specific GTM timer
  * @gtm:	specific GTM, pass here GTM's device_node->data
  * @timer:	specific timer number, Timer1 is 0.
  * Context:	non-IRQ
@@ -260,7 +260,7 @@ int gtm_set_timer16(struct gtm_timer *tmr, unsigned long usec, bool reload)
 EXPORT_SYMBOL(gtm_set_timer16);
 
 /**
- * gtm_set_exact_utimer16 - (re)set 16 bits timer
+ * gtm_set_exact_timer16 - (re)set 16 bits timer
  * @tmr:	pointer to the gtm_timer structure obtained from gtm_get_timer
  * @usec:	timer interval in microseconds
  * @reload:	if set, the timer will reset upon expiry rather than
diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c
index 217cea150987..7ed07232a69a 100644
--- a/arch/powerpc/sysdev/fsl_lbc.c
+++ b/arch/powerpc/sysdev/fsl_lbc.c
@@ -350,7 +350,7 @@ err:
 #ifdef CONFIG_SUSPEND
 
 /* save lbc registers */
-static int fsl_lbc_syscore_suspend(void)
+static int fsl_lbc_syscore_suspend(void *data)
 {
 	struct fsl_lbc_ctrl *ctrl;
 	struct fsl_lbc_regs __iomem *lbc;
@@ -374,7 +374,7 @@ out:
 }
 
 /* restore lbc registers */
-static void fsl_lbc_syscore_resume(void)
+static void fsl_lbc_syscore_resume(void *data)
 {
 	struct fsl_lbc_ctrl *ctrl;
 	struct fsl_lbc_regs __iomem *lbc;
@@ -408,10 +408,14 @@ static const struct of_device_id fsl_lbc_match[] = {
 };
 
 #ifdef CONFIG_SUSPEND
-static struct syscore_ops lbc_syscore_pm_ops = {
+static const struct syscore_ops lbc_syscore_pm_ops = {
 	.suspend = fsl_lbc_syscore_suspend,
 	.resume = fsl_lbc_syscore_resume,
 };
+
+static struct syscore lbc_syscore_pm = {
+	.ops = &lbc_syscore_pm_ops,
+};
 #endif
 
 static struct platform_driver fsl_lbc_ctrl_driver = {
@@ -425,7 +429,7 @@ static struct platform_driver fsl_lbc_ctrl_driver = {
 static int __init fsl_lbc_init(void)
 {
 #ifdef CONFIG_SUSPEND
-	register_syscore_ops(&lbc_syscore_pm_ops);
+	register_syscore(&lbc_syscore_pm);
 #endif
 	return platform_driver_register(&fsl_lbc_ctrl_driver);
 }
diff --git a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
index ce6c739c51e5..06d9101a5d49 100644
--- a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
+++ b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
@@ -75,7 +75,7 @@ static ssize_t fsl_timer_wakeup_store(struct device *dev,
 	if (kstrtoll(buf, 0, &interval))
 		return -EINVAL;
 
-	mutex_lock(&sysfs_lock);
+	guard(mutex)(&sysfs_lock);
 
 	if (fsl_wakeup->timer) {
 		disable_irq_wake(fsl_wakeup->timer->irq);
@@ -83,31 +83,23 @@ static ssize_t fsl_timer_wakeup_store(struct device *dev,
 		fsl_wakeup->timer = NULL;
 	}
 
-	if (!interval) {
-		mutex_unlock(&sysfs_lock);
+	if (!interval)
 		return count;
-	}
 
 	fsl_wakeup->timer = mpic_request_timer(fsl_mpic_timer_irq,
 						fsl_wakeup, interval);
-	if (!fsl_wakeup->timer) {
-		mutex_unlock(&sysfs_lock);
+	if (!fsl_wakeup->timer)
 		return -EINVAL;
-	}
 
 	ret = enable_irq_wake(fsl_wakeup->timer->irq);
 	if (ret) {
 		mpic_free_timer(fsl_wakeup->timer);
 		fsl_wakeup->timer = NULL;
-		mutex_unlock(&sysfs_lock);
-
 		return ret;
 	}
 
 	mpic_start_timer(fsl_wakeup->timer);
 
-	mutex_unlock(&sysfs_lock);
-
 	return count;
 }
 
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 57978a44d55b..2a007bfb038d 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -11,9 +11,11 @@
 #include <linux/msi.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/seq_file.h>
@@ -73,7 +75,7 @@ static void fsl_msi_print_chip(struct irq_data *irqd, struct seq_file *p)
 	srs = (hwirq >> msi_data->srs_shift) & MSI_SRS_MASK;
 	cascade_virq = msi_data->cascade_array[srs]->virq;
 
-	seq_printf(p, " fsl-msi-%d", cascade_virq);
+	seq_printf(p, "fsl-msi-%d", cascade_virq);
 }
 
 
@@ -318,7 +320,7 @@ static irqreturn_t fsl_msi_cascade(int irq, void *data)
 	return ret;
 }
 
-static int fsl_of_msi_remove(struct platform_device *ofdev)
+static void fsl_of_msi_remove(struct platform_device *ofdev)
 {
 	struct fsl_msi *msi = platform_get_drvdata(ofdev);
 	int virq, i;
@@ -341,8 +343,6 @@ static int fsl_of_msi_remove(struct platform_device *ofdev)
 	if ((msi->feature & FSL_PIC_IP_MASK) != FSL_PIC_IP_VMPIC)
 		iounmap(msi->msi_regs);
 	kfree(msi);
-
-	return 0;
 }
 
 static struct lock_class_key fsl_msi_irq_class;
@@ -392,7 +392,6 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 static const struct of_device_id fsl_of_msi_ids[];
 static int fsl_of_msi_probe(struct platform_device *dev)
 {
-	const struct of_device_id *match;
 	struct fsl_msi *msi;
 	struct resource res, msiir;
 	int err, i, j, irq_index, count;
@@ -402,10 +401,7 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 	u32 offset;
 	struct pci_controller *phb;
 
-	match = of_match_device(fsl_of_msi_ids, &dev->dev);
-	if (!match)
-		return -EINVAL;
-	features = match->data;
+	features = device_get_match_data(&dev->dev);
 
 	printk(KERN_DEBUG "Setting up Freescale MSI support\n");
 
@@ -416,9 +412,8 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 	}
 	platform_set_drvdata(dev, msi);
 
-	msi->irqhost = irq_domain_add_linear(dev->dev.of_node,
-				      NR_MSI_IRQS_MAX, &fsl_msi_host_ops, msi);
-
+	msi->irqhost = irq_domain_create_linear(dev_fwnode(&dev->dev), NR_MSI_IRQS_MAX,
+						&fsl_msi_host_ops, msi);
 	if (msi->irqhost == NULL) {
 		dev_err(&dev->dev, "No memory for MSI irqhost\n");
 		err = -ENOMEM;
@@ -568,10 +563,12 @@ static const struct fsl_msi_feature ipic_msi_feature = {
 	.msiir_offset = 0x38,
 };
 
+#ifdef CONFIG_EPAPR_PARAVIRT
 static const struct fsl_msi_feature vmpic_msi_feature = {
 	.fsl_pic_ip = FSL_PIC_IP_VMPIC,
 	.msiir_offset = 0,
 };
+#endif
 
 static const struct of_device_id fsl_of_msi_ids[] = {
 	{
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index b7232c46b244..4e501654cb41 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -54,7 +54,7 @@ static void quirk_fsl_pcie_early(struct pci_dev *dev)
 
 	/* if we aren't in host mode don't bother */
 	pci_read_config_byte(dev, PCI_HEADER_TYPE, &hdr_type);
-	if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE)
+	if ((hdr_type & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_BRIDGE)
 		return;
 
 	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
@@ -519,7 +519,7 @@ void fsl_pcibios_fixup_bus(struct pci_bus *bus)
 	}
 }
 
-int fsl_add_bridge(struct platform_device *pdev, int is_primary)
+static int fsl_add_bridge(struct platform_device *pdev, int is_primary)
 {
 	int len;
 	struct pci_controller *hose;
@@ -581,7 +581,7 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary)
 		hose->ops = &fsl_indirect_pcie_ops;
 		/* For PCIE read HEADER_TYPE to identify controller mode */
 		early_read_config_byte(hose, 0, 0, PCI_HEADER_TYPE, &hdr_type);
-		if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE)
+		if ((hdr_type & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_BRIDGE)
 			goto no_bridge;
 
 	} else {
@@ -767,7 +767,7 @@ static int __init mpc83xx_pcie_setup(struct pci_controller *hose,
 	u32 cfg_bar;
 	int ret = -ENOMEM;
 
-	pcie = zalloc_maybe_bootmem(sizeof(*pcie), GFP_KERNEL);
+	pcie = kzalloc(sizeof(*pcie), GFP_KERNEL);
 	if (!pcie)
 		return ret;
 
@@ -1258,7 +1258,7 @@ static void fsl_pci_syscore_do_suspend(struct pci_controller *hose)
 	send_pme_turnoff_message(hose);
 }
 
-static int fsl_pci_syscore_suspend(void)
+static int fsl_pci_syscore_suspend(void *data)
 {
 	struct pci_controller *hose, *tmp;
 
@@ -1291,7 +1291,7 @@ static void fsl_pci_syscore_do_resume(struct pci_controller *hose)
 	setup_pci_atmu(hose);
 }
 
-static void fsl_pci_syscore_resume(void)
+static void fsl_pci_syscore_resume(void *data)
 {
 	struct pci_controller *hose, *tmp;
 
@@ -1299,10 +1299,14 @@ static void fsl_pci_syscore_resume(void)
 		fsl_pci_syscore_do_resume(hose);
 }
 
-static struct syscore_ops pci_syscore_pm_ops = {
+static const struct syscore_ops pci_syscore_pm_ops = {
 	.suspend = fsl_pci_syscore_suspend,
 	.resume = fsl_pci_syscore_resume,
 };
+
+static struct syscore pci_syscore_pm = {
+	.ops = &pci_syscore_pm_ops,
+};
 #endif
 
 void fsl_pcibios_fixup_phb(struct pci_controller *phb)
@@ -1353,12 +1357,13 @@ static struct platform_driver fsl_pci_driver = {
 		.of_match_table = pci_ids,
 	},
 	.probe = fsl_pci_probe,
+	.driver_managed_dma = true,
 };
 
 static int __init fsl_pci_init(void)
 {
 #ifdef CONFIG_PM_SLEEP
-	register_syscore_ops(&pci_syscore_pm_ops);
+	register_syscore(&pci_syscore_pm);
 #endif
 	return platform_driver_register(&fsl_pci_driver);
 }
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index 093a875d7d1e..3bc4ab9d8341 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -112,7 +112,6 @@ struct ccsr_pci {
 
 };
 
-extern int fsl_add_bridge(struct platform_device *pdev, int is_primary);
 extern void fsl_pcibios_fixup_bus(struct pci_bus *bus);
 extern void fsl_pcibios_fixup_phb(struct pci_controller *phb);
 extern int mpc83xx_add_bridge(struct device_node *dev);
diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c
index 76896de970ca..9f6dd11c1344 100644
--- a/arch/powerpc/sysdev/fsl_pmc.c
+++ b/arch/powerpc/sysdev/fsl_pmc.c
@@ -13,9 +13,9 @@
 #include <linux/export.h>
 #include <linux/suspend.h>
 #include <linux/delay.h>
-#include <linux/device.h>
+#include <linux/mod_devicetable.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 struct pmc_regs {
 	__be32 devdisr;
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index f8e492ee54cc..f9b214b299e7 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -23,16 +23,17 @@
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
-#include <linux/device.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 
 #include <linux/io.h>
 #include <linux/uaccess.h>
 #include <asm/machdep.h>
+#include <asm/rio.h>
 
 #include "fsl_rio.h"
 
@@ -303,8 +304,8 @@ static void fsl_rio_inbound_mem_init(struct rio_priv *priv)
 		out_be32(&priv->inb_atmu_regs[i].riwar, 0);
 }
 
-int fsl_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
-	u64 rstart, u64 size, u32 flags)
+static int fsl_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
+			   u64 rstart, u64 size, u32 flags)
 {
 	struct rio_priv *priv = mport->priv;
 	u32 base_size;
@@ -354,7 +355,7 @@ int fsl_map_inb_mem(struct rio_mport *mport, dma_addr_t lstart,
 	return 0;
 }
 
-void fsl_unmap_inb_mem(struct rio_mport *mport, dma_addr_t lstart)
+static void fsl_unmap_inb_mem(struct rio_mport *mport, dma_addr_t lstart)
 {
 	u32 win_start_shift, base_start_shift;
 	struct rio_priv *priv = mport->priv;
@@ -442,19 +443,17 @@ static inline void fsl_rio_info(struct device *dev, u32 ccsr)
  * master port with system-specific info, and registers the
  * master port with the RapidIO subsystem.
  */
-int fsl_rio_setup(struct platform_device *dev)
+static int fsl_rio_setup(struct platform_device *dev)
 {
 	struct rio_ops *ops;
 	struct rio_mport *port;
 	struct rio_priv *priv;
 	int rc = 0;
-	const u32 *dt_range, *cell, *port_index;
+	const u32 *port_index;
 	u32 active_ports = 0;
 	struct device_node *np, *rmu_node;
-	int rlen;
 	u32 ccsr;
-	u64 range_start, range_size;
-	int paw, aw, sw;
+	u64 range_start;
 	u32 i;
 	static int tmp;
 	struct device_node *rmu_np[MAX_MSG_UNIT_NUM] = {NULL};
@@ -528,15 +527,12 @@ int fsl_rio_setup(struct platform_device *dev)
 	dbell->bellirq = irq_of_parse_and_map(np, 1);
 	dev_info(&dev->dev, "bellirq: %d\n", dbell->bellirq);
 
-	aw = of_n_addr_cells(np);
-	dt_range = of_get_property(np, "reg", &rlen);
-	if (!dt_range) {
+	if (of_property_read_reg(np, 0, &range_start, NULL)) {
 		pr_err("%pOF: unable to find 'reg' property\n",
 			np);
 		rc = -ENOMEM;
 		goto err_pw;
 	}
-	range_start = of_read_number(dt_range, aw);
 	dbell->dbell_regs = (struct rio_dbell_regs *)(rmu_regs_win +
 				(u32)range_start);
 
@@ -556,19 +552,18 @@ int fsl_rio_setup(struct platform_device *dev)
 	pw->dev = &dev->dev;
 	pw->pwirq = irq_of_parse_and_map(np, 0);
 	dev_info(&dev->dev, "pwirq: %d\n", pw->pwirq);
-	aw = of_n_addr_cells(np);
-	dt_range = of_get_property(np, "reg", &rlen);
-	if (!dt_range) {
+	if (of_property_read_reg(np, 0, &range_start, NULL)) {
 		pr_err("%pOF: unable to find 'reg' property\n",
 			np);
 		rc = -ENOMEM;
 		goto err;
 	}
-	range_start = of_read_number(dt_range, aw);
 	pw->pw_regs = (struct rio_pw_regs *)(rmu_regs_win + (u32)range_start);
 
 	/*set up ports node*/
 	for_each_child_of_node(dev->dev.of_node, np) {
+		struct resource res;
+
 		port_index = of_get_property(np, "cell-index", NULL);
 		if (!port_index) {
 			dev_err(&dev->dev, "Can't get %pOF property 'cell-index'\n",
@@ -576,32 +571,14 @@ int fsl_rio_setup(struct platform_device *dev)
 			continue;
 		}
 
-		dt_range = of_get_property(np, "ranges", &rlen);
-		if (!dt_range) {
+		if (of_range_to_resource(np, 0, &res)) {
 			dev_err(&dev->dev, "Can't get %pOF property 'ranges'\n",
 					np);
 			continue;
 		}
 
-		/* Get node address wide */
-		cell = of_get_property(np, "#address-cells", NULL);
-		if (cell)
-			aw = *cell;
-		else
-			aw = of_n_addr_cells(np);
-		/* Get node size wide */
-		cell = of_get_property(np, "#size-cells", NULL);
-		if (cell)
-			sw = *cell;
-		else
-			sw = of_n_size_cells(np);
-		/* Get parent address wide wide */
-		paw = of_n_addr_cells(np);
-		range_start = of_read_number(dt_range + aw, paw);
-		range_size = of_read_number(dt_range + aw + paw, sw);
-
-		dev_info(&dev->dev, "%pOF: LAW start 0x%016llx, size 0x%016llx.\n",
-				np, range_start, range_size);
+		dev_info(&dev->dev, "%pOF: LAW %pR\n",
+				np, &res);
 
 		port = kzalloc(sizeof(struct rio_mport), GFP_KERNEL);
 		if (!port)
@@ -624,9 +601,7 @@ int fsl_rio_setup(struct platform_device *dev)
 		}
 
 		INIT_LIST_HEAD(&port->dbells);
-		port->iores.start = range_start;
-		port->iores.end = port->iores.start + range_size - 1;
-		port->iores.flags = IORESOURCE_MEM;
+		port->iores = res;	/* struct copy */
 		port->iores.name = "rio_io_win";
 
 		if (request_resource(&iomem_resource, &port->iores) < 0) {
diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c
index 7a5e2e2b9d06..f956591cb64e 100644
--- a/arch/powerpc/sysdev/fsl_rmu.c
+++ b/arch/powerpc/sysdev/fsl_rmu.c
@@ -23,8 +23,8 @@
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
+#include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
 #include <linux/slab.h>
 
 #include "fsl_rio.h"
@@ -359,7 +359,7 @@ out:
 	return IRQ_HANDLED;
 }
 
-void msg_unit_error_handler(void)
+static void msg_unit_error_handler(void)
 {
 
 	/*XXX: Error recovery is not implemented, we just clear errors */
@@ -1067,9 +1067,6 @@ int fsl_rio_setup_rmu(struct rio_mport *mport, struct device_node *node)
 	struct rio_priv *priv;
 	struct fsl_rmu *rmu;
 	u64 msg_start;
-	const u32 *msg_addr;
-	int mlen;
-	int aw;
 
 	if (!mport || !mport->priv)
 		return -EINVAL;
@@ -1086,16 +1083,12 @@ int fsl_rio_setup_rmu(struct rio_mport *mport, struct device_node *node)
 	if (!rmu)
 		return -ENOMEM;
 
-	aw = of_n_addr_cells(node);
-	msg_addr = of_get_property(node, "reg", &mlen);
-	if (!msg_addr) {
+	if (of_property_read_reg(node, 0, &msg_start, NULL)) {
 		pr_err("%pOF: unable to find 'reg' property of message-unit\n",
 			node);
 		kfree(rmu);
 		return -ENOMEM;
 	}
-	msg_start = of_read_number(msg_addr, aw);
-
 	rmu->msg_regs = (struct rio_msg_regs *)
 			(rmu_regs_win + (u32)msg_start);
 
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index 6ebbbca41065..3949ceb79e64 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -19,12 +19,9 @@
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
-#include <linux/of_platform.h>
 #include <linux/phy.h>
 #include <linux/spi/spi.h>
 #include <linux/fsl_devices.h>
-#include <linux/fs_enet_pd.h>
-#include <linux/fs_uart_pd.h>
 #include <linux/reboot.h>
 
 #include <linux/atomic.h>
@@ -37,9 +34,6 @@
 #include <asm/cpm2.h>
 #include <asm/fsl_hcalls.h>	/* For the Freescale hypervisor */
 
-extern void init_fcc_ioports(struct fs_platform_info*);
-extern void init_fec_ioports(struct fs_platform_info*);
-extern void init_smc_ioports(struct fs_uart_platform_info*);
 static phys_addr_t immrbase = -1;
 
 phys_addr_t get_immrbase(void)
@@ -51,18 +45,10 @@ phys_addr_t get_immrbase(void)
 
 	soc = of_find_node_by_type(NULL, "soc");
 	if (soc) {
-		int size;
-		u32 naddr;
-		const __be32 *prop = of_get_property(soc, "#address-cells", &size);
-
-		if (prop && size == 4)
-			naddr = be32_to_cpup(prop);
-		else
-			naddr = 2;
-
-		prop = of_get_property(soc, "ranges", &size);
-		if (prop)
-			immrbase = of_translate_address(soc, prop + naddr);
+		struct resource res;
+
+		if (!of_range_to_resource(soc, 0, &res))
+			immrbase = res.start;
 
 		of_node_put(soc);
 	}
diff --git a/arch/powerpc/sysdev/ge/ge_pic.c b/arch/powerpc/sysdev/ge/ge_pic.c
index a6c424680c37..0bc3f0b36528 100644
--- a/arch/powerpc/sysdev/ge/ge_pic.c
+++ b/arch/powerpc/sysdev/ge/ge_pic.c
@@ -214,8 +214,9 @@ void __init gef_pic_init(struct device_node *np)
 	}
 
 	/* Setup an irq_domain structure */
-	gef_pic_irq_host = irq_domain_add_linear(np, GEF_PIC_NUM_IRQS,
-					  &gef_pic_host_ops, NULL);
+	gef_pic_irq_host = irq_domain_create_linear(of_fwnode_handle(np),
+						    GEF_PIC_NUM_IRQS,
+						    &gef_pic_host_ops, NULL);
 	if (gef_pic_irq_host == NULL)
 		return;
 
@@ -244,7 +245,7 @@ unsigned int gef_pic_get_irq(void)
 			if (active & (0x1 << hwirq))
 				break;
 		}
-		virq = irq_linear_revmap(gef_pic_irq_host,
+		virq = irq_find_mapping(gef_pic_irq_host,
 			(irq_hw_number_t)hwirq);
 	}
 
diff --git a/arch/powerpc/sysdev/grackle.c b/arch/powerpc/sysdev/grackle.c
index fd2f94a884f0..7dce8278b71e 100644
--- a/arch/powerpc/sysdev/grackle.c
+++ b/arch/powerpc/sysdev/grackle.c
@@ -18,24 +18,8 @@
 #define GRACKLE_CFA(b, d, o)	(0x80 | ((b) << 8) | ((d) << 16) \
 				 | (((o) & ~3) << 24))
 
-#define GRACKLE_PICR1_STG		0x00000040
 #define GRACKLE_PICR1_LOOPSNOOP		0x00000010
 
-/* N.B. this is called before bridges is initialized, so we can't
-   use grackle_pcibios_{read,write}_config_dword. */
-static inline void grackle_set_stg(struct pci_controller* bp, int enable)
-{
-	unsigned int val;
-
-	out_be32(bp->cfg_addr, GRACKLE_CFA(0, 0, 0xa8));
-	val = in_le32(bp->cfg_data);
-	val = enable? (val | GRACKLE_PICR1_STG) :
-		(val & ~GRACKLE_PICR1_STG);
-	out_be32(bp->cfg_addr, GRACKLE_CFA(0, 0, 0xa8));
-	out_le32(bp->cfg_data, val);
-	(void)in_le32(bp->cfg_data);
-}
-
 static inline void grackle_set_loop_snoop(struct pci_controller *bp, int enable)
 {
 	unsigned int val;
@@ -56,7 +40,4 @@ void __init setup_grackle(struct pci_controller *hose)
 		pci_add_flags(PCI_REASSIGN_ALL_BUS);
 	if (of_machine_is_compatible("AAPL,PowerBook1998"))
 		grackle_set_loop_snoop(hose, 1);
-#if 0	/* Disabled for now, HW problems ??? */
-	grackle_set_stg(hose, 1);
-#endif
 }
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index 06e391485da7..99bb2b916949 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -260,8 +260,8 @@ void i8259_init(struct device_node *node, unsigned long intack_addr)
 	raw_spin_unlock_irqrestore(&i8259_lock, flags);
 
 	/* create a legacy host */
-	i8259_host = irq_domain_add_legacy(node, NR_IRQS_LEGACY, 0, 0,
-					   &i8259_host_ops, NULL);
+	i8259_host = irq_domain_create_legacy(of_fwnode_handle(node), NR_IRQS_LEGACY, 0, 0,
+					      &i8259_host_ops, NULL);
 	if (i8259_host == NULL) {
 		printk(KERN_ERR "i8259: failed to allocate irq host !\n");
 		return;
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index 5f69e2d50f26..290ba8427239 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -711,8 +711,9 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags)
 	if (ipic == NULL)
 		return NULL;
 
-	ipic->irqhost = irq_domain_add_linear(node, NR_IPIC_INTS,
-					      &ipic_host_ops, ipic);
+	ipic->irqhost = irq_domain_create_linear(of_fwnode_handle(node),
+						 NR_IPIC_INTS,
+						 &ipic_host_ops, ipic);
 	if (ipic->irqhost == NULL) {
 		kfree(ipic);
 		return NULL;
@@ -757,13 +758,12 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags)
 	ipic_write(ipic->regs, IPIC_SEMSR, temp);
 
 	primary_ipic = ipic;
-	irq_set_default_host(primary_ipic->irqhost);
+	irq_set_default_domain(primary_ipic->irqhost);
 
 	ipic_write(ipic->regs, IPIC_SIMSR_H, 0);
 	ipic_write(ipic->regs, IPIC_SIMSR_L, 0);
 
-	printk ("IPIC (%d IRQ sources) at %p\n", NR_IPIC_INTS,
-			primary_ipic->regs);
+	pr_info("IPIC (%d IRQ sources) at MMIO %pa\n", NR_IPIC_INTS, &res.start);
 
 	return ipic;
 }
@@ -801,7 +801,7 @@ unsigned int ipic_get_irq(void)
 	if (irq == 0)    /* 0 --> no irq is pending */
 		return 0;
 
-	return irq_linear_revmap(primary_ipic->irqhost, irq);
+	return irq_find_mapping(primary_ipic->irqhost, irq);
 }
 
 #ifdef CONFIG_SUSPEND
@@ -817,7 +817,7 @@ static struct {
 	u32 sercr;
 } ipic_saved_state;
 
-static int ipic_suspend(void)
+static int ipic_suspend(void *data)
 {
 	struct ipic *ipic = primary_ipic;
 
@@ -848,7 +848,7 @@ static int ipic_suspend(void)
 	return 0;
 }
 
-static void ipic_resume(void)
+static void ipic_resume(void *data)
 {
 	struct ipic *ipic = primary_ipic;
 
@@ -870,18 +870,22 @@ static void ipic_resume(void)
 #define ipic_resume NULL
 #endif
 
-static struct syscore_ops ipic_syscore_ops = {
+static const struct syscore_ops ipic_syscore_ops = {
 	.suspend = ipic_suspend,
 	.resume = ipic_resume,
 };
 
+static struct syscore ipic_syscore = {
+	.ops = &ipic_syscore_ops,
+};
+
 static int __init init_ipic_syscore(void)
 {
 	if (!primary_ipic || !primary_ipic->regs)
 		return -ENODEV;
 
 	printk(KERN_DEBUG "Registering ipic system core operations\n");
-	register_syscore_ops(&ipic_syscore_ops);
+	register_syscore(&ipic_syscore);
 
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/mpc5xxx_clocks.c b/arch/powerpc/sysdev/mpc5xxx_clocks.c
index c5bf7e1b3780..58cee28e2399 100644
--- a/arch/powerpc/sysdev/mpc5xxx_clocks.c
+++ b/arch/powerpc/sysdev/mpc5xxx_clocks.c
@@ -25,8 +25,10 @@ unsigned long mpc5xxx_fwnode_get_bus_frequency(struct fwnode_handle *fwnode)
 
 	fwnode_for_each_parent_node(fwnode, parent) {
 		ret = fwnode_property_read_u32(parent, "bus-frequency", &bus_freq);
-		if (!ret)
+		if (!ret) {
+			fwnode_handle_put(parent);
 			return bus_freq;
+		}
 	}
 
 	return 0;
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index ba287abcb008..67e51998d1ae 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -27,6 +27,7 @@
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/syscore_ops.h>
 #include <linux/ratelimit.h>
 #include <linux/pgtable.h>
@@ -49,7 +50,7 @@
 #define DBG(fmt...)
 #endif
 
-struct bus_type mpic_subsys = {
+const struct bus_type mpic_subsys = {
 	.name = "mpic",
 	.dev_name = "mpic",
 };
@@ -355,7 +356,7 @@ static void __init mpic_test_broken_ipi(struct mpic *mpic)
 	mpic_write(mpic->gregs, MPIC_INFO(GREG_IPI_VECTOR_PRI_0), MPIC_VECPRI_MASK);
 	r = mpic_read(mpic->gregs, MPIC_INFO(GREG_IPI_VECTOR_PRI_0));
 
-	if (r == le32_to_cpu(MPIC_VECPRI_MASK)) {
+	if (r == swab32(MPIC_VECPRI_MASK)) {
 		printk(KERN_INFO "mpic: Detected reversed IPI registers\n");
 		mpic->flags |= MPIC_BROKEN_IPI;
 	}
@@ -474,9 +475,9 @@ static void __init mpic_scan_ht_msi(struct mpic *mpic, u8 __iomem *devbase,
 		addr = addr | ((u64)readl(base + HT_MSI_ADDR_HI) << 32);
 	}
 
-	printk(KERN_DEBUG "mpic:   - HT:%02x.%x %s MSI mapping found @ 0x%llx\n",
-		PCI_SLOT(devfn), PCI_FUNC(devfn),
-		flags & HT_MSI_FLAGS_ENABLE ? "enabled" : "disabled", addr);
+	pr_debug("mpic:   - HT:%02x.%x %s MSI mapping found @ 0x%llx\n",
+		 PCI_SLOT(devfn), PCI_FUNC(devfn),
+		 str_enabled_disabled(flags & HT_MSI_FLAGS_ENABLE), addr);
 
 	if (!(flags & HT_MSI_FLAGS_ENABLE))
 		writeb(flags | HT_MSI_FLAGS_ENABLE, base + HT_MSI_FLAGS);
@@ -1483,9 +1484,9 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	mpic->isu_shift = 1 + __ilog2(mpic->isu_size - 1);
 	mpic->isu_mask = (1 << mpic->isu_shift) - 1;
 
-	mpic->irqhost = irq_domain_add_linear(mpic->node,
-				       intvec_top,
-				       &mpic_host_ops, mpic);
+	mpic->irqhost = irq_domain_create_linear(of_fwnode_handle(mpic->node),
+						 intvec_top,
+						 &mpic_host_ops, mpic);
 
 	/*
 	 * FIXME: The code leaks the MPIC object and mappings here; this
@@ -1520,7 +1521,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 
 	if (!(mpic->flags & MPIC_SECONDARY)) {
 		mpic_primary = mpic;
-		irq_set_default_host(mpic->irqhost);
+		irq_set_default_domain(mpic->irqhost);
 	}
 
 	return mpic;
@@ -1785,7 +1786,7 @@ static unsigned int _mpic_get_one_irq(struct mpic *mpic, int reg)
 		return 0;
 	}
 
-	return irq_linear_revmap(mpic->irqhost, src);
+	return irq_find_mapping(mpic->irqhost, src);
 }
 
 unsigned int mpic_get_one_irq(struct mpic *mpic)
@@ -1823,7 +1824,7 @@ unsigned int mpic_get_coreint_irq(void)
 		return 0;
 	}
 
-	return irq_linear_revmap(mpic->irqhost, src);
+	return irq_find_mapping(mpic->irqhost, src);
 #else
 	return 0;
 #endif
@@ -1943,7 +1944,7 @@ static void mpic_suspend_one(struct mpic *mpic)
 	}
 }
 
-static int mpic_suspend(void)
+static int mpic_suspend(void *data)
 {
 	struct mpic *mpic = mpics;
 
@@ -1985,7 +1986,7 @@ static void mpic_resume_one(struct mpic *mpic)
 	} /* end for loop */
 }
 
-static void mpic_resume(void)
+static void mpic_resume(void *data)
 {
 	struct mpic *mpic = mpics;
 
@@ -1995,19 +1996,23 @@ static void mpic_resume(void)
 	}
 }
 
-static struct syscore_ops mpic_syscore_ops = {
+static const struct syscore_ops mpic_syscore_ops = {
 	.resume = mpic_resume,
 	.suspend = mpic_suspend,
 };
 
+static struct syscore mpic_syscore = {
+	.ops = &mpic_syscore_ops,
+};
+
 static int mpic_init_sys(void)
 {
 	int rc;
 
-	register_syscore_ops(&mpic_syscore_ops);
+	register_syscore(&mpic_syscore);
 	rc = subsys_system_register(&mpic_subsys, NULL);
 	if (rc) {
-		unregister_syscore_ops(&mpic_syscore_ops);
+		unregister_syscore(&mpic_syscore);
 		pr_err("mpic: Failed to register subsystem!\n");
 		return rc;
 	}
diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c
index 1a3ac0b5dd89..7b449cc51aef 100644
--- a/arch/powerpc/sysdev/mpic_msgr.c
+++ b/arch/powerpc/sysdev/mpic_msgr.c
@@ -7,9 +7,10 @@
  */
 
 #include <linux/list.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/export.h>
diff --git a/arch/powerpc/sysdev/mpic_timer.c b/arch/powerpc/sysdev/mpic_timer.c
index b2f0a73e8f93..60f5b3934b51 100644
--- a/arch/powerpc/sysdev/mpic_timer.c
+++ b/arch/powerpc/sysdev/mpic_timer.c
@@ -16,7 +16,6 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/syscore_ops.h>
 #include <sysdev/fsl_soc.h>
@@ -520,7 +519,7 @@ out:
 	kfree(priv);
 }
 
-static void mpic_timer_resume(void)
+static void mpic_timer_resume(void *data)
 {
 	struct timer_group_priv *priv;
 
@@ -536,10 +535,14 @@ static const struct of_device_id mpic_timer_ids[] = {
 	{},
 };
 
-static struct syscore_ops mpic_timer_syscore_ops = {
+static const struct syscore_ops mpic_timer_syscore_ops = {
 	.resume = mpic_timer_resume,
 };
 
+static struct syscore mpic_timer_syscore = {
+	.ops = &mpic_timer_syscore_ops,
+};
+
 static int __init mpic_timer_init(void)
 {
 	struct device_node *np = NULL;
@@ -547,7 +550,7 @@ static int __init mpic_timer_init(void)
 	for_each_matching_node(np, mpic_timer_ids)
 		timer_group_init(np);
 
-	register_syscore_ops(&mpic_timer_syscore_ops);
+	register_syscore(&mpic_timer_syscore);
 
 	if (list_empty(&timer_group_list))
 		return -ENODEV;
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index 0b6e37f3ffb8..456a4f64ae0a 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -124,10 +124,7 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count,
 	if (bmp->bitmap_from_slab)
 		bmp->bitmap = kzalloc(size, GFP_KERNEL);
 	else {
-		bmp->bitmap = memblock_alloc(size, SMP_CACHE_BYTES);
-		if (!bmp->bitmap)
-			panic("%s: Failed to allocate %u bytes\n", __func__,
-			      size);
+		bmp->bitmap = memblock_alloc_or_panic(size, SMP_CACHE_BYTES);
 		/* the bitmap won't be freed from memblock allocator */
 		kmemleak_not_leak(bmp->bitmap);
 	}
diff --git a/arch/powerpc/sysdev/of_rtc.c b/arch/powerpc/sysdev/of_rtc.c
index 420f949b7485..2211937d3788 100644
--- a/arch/powerpc/sysdev/of_rtc.c
+++ b/arch/powerpc/sysdev/of_rtc.c
@@ -5,10 +5,10 @@
  * Copyright 2007 David Gibson <dwg@au1.ibm.com>, IBM Corporation.
  */
 #include <linux/kernel.h>
-#include <linux/of.h>
 #include <linux/init.h>
+#include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 
 #include <asm/prom.h>
diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c
deleted file mode 100644
index 9dabb50c36eb..000000000000
--- a/arch/powerpc/sysdev/pmi.c
+++ /dev/null
@@ -1,269 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * pmi driver
- *
- * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
- *
- * PMI (Platform Management Interrupt) is a way to communicate
- * with the BMC (Baseboard Management Controller) via interrupts.
- * Unlike IPMI it is bidirectional and has a low latency.
- *
- * Author: Christian Krafft <krafft@de.ibm.com>
- */
-
-#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/completion.h>
-#include <linux/spinlock.h>
-#include <linux/module.h>
-#include <linux/workqueue.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
-#include <linux/of_platform.h>
-
-#include <asm/io.h>
-#include <asm/pmi.h>
-
-struct pmi_data {
-	struct list_head	handler;
-	spinlock_t		handler_spinlock;
-	spinlock_t		pmi_spinlock;
-	struct mutex		msg_mutex;
-	pmi_message_t		msg;
-	struct completion	*completion;
-	struct platform_device	*dev;
-	int			irq;
-	u8 __iomem		*pmi_reg;
-	struct work_struct	work;
-};
-
-static struct pmi_data *data;
-
-static irqreturn_t pmi_irq_handler(int irq, void *dev_id)
-{
-	u8 type;
-	int rc;
-
-	spin_lock(&data->pmi_spinlock);
-
-	type = ioread8(data->pmi_reg + PMI_READ_TYPE);
-	pr_debug("pmi: got message of type %d\n", type);
-
-	if (type & PMI_ACK && !data->completion) {
-		printk(KERN_WARNING "pmi: got unexpected ACK message.\n");
-		rc = -EIO;
-		goto unlock;
-	}
-
-	if (data->completion && !(type & PMI_ACK)) {
-		printk(KERN_WARNING "pmi: expected ACK, but got %d\n", type);
-		rc = -EIO;
-		goto unlock;
-	}
-
-	data->msg.type = type;
-	data->msg.data0 = ioread8(data->pmi_reg + PMI_READ_DATA0);
-	data->msg.data1 = ioread8(data->pmi_reg + PMI_READ_DATA1);
-	data->msg.data2 = ioread8(data->pmi_reg + PMI_READ_DATA2);
-	rc = 0;
-unlock:
-	spin_unlock(&data->pmi_spinlock);
-
-	if (rc == -EIO) {
-		rc = IRQ_HANDLED;
-		goto out;
-	}
-
-	if (data->msg.type & PMI_ACK) {
-		complete(data->completion);
-		rc = IRQ_HANDLED;
-		goto out;
-	}
-
-	schedule_work(&data->work);
-
-	rc = IRQ_HANDLED;
-out:
-	return rc;
-}
-
-
-static const struct of_device_id pmi_match[] = {
-	{ .type = "ibm,pmi", .name = "ibm,pmi" },
-	{ .type = "ibm,pmi" },
-	{},
-};
-
-MODULE_DEVICE_TABLE(of, pmi_match);
-
-static void pmi_notify_handlers(struct work_struct *work)
-{
-	struct pmi_handler *handler;
-
-	spin_lock(&data->handler_spinlock);
-	list_for_each_entry(handler, &data->handler, node) {
-		pr_debug("pmi: notifying handler %p\n", handler);
-		if (handler->type == data->msg.type)
-			handler->handle_pmi_message(data->msg);
-	}
-	spin_unlock(&data->handler_spinlock);
-}
-
-static int pmi_of_probe(struct platform_device *dev)
-{
-	struct device_node *np = dev->dev.of_node;
-	int rc;
-
-	if (data) {
-		printk(KERN_ERR "pmi: driver has already been initialized.\n");
-		rc = -EBUSY;
-		goto out;
-	}
-
-	data = kzalloc(sizeof(struct pmi_data), GFP_KERNEL);
-	if (!data) {
-		printk(KERN_ERR "pmi: could not allocate memory.\n");
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	data->pmi_reg = of_iomap(np, 0);
-	if (!data->pmi_reg) {
-		printk(KERN_ERR "pmi: invalid register address.\n");
-		rc = -EFAULT;
-		goto error_cleanup_data;
-	}
-
-	INIT_LIST_HEAD(&data->handler);
-
-	mutex_init(&data->msg_mutex);
-	spin_lock_init(&data->pmi_spinlock);
-	spin_lock_init(&data->handler_spinlock);
-
-	INIT_WORK(&data->work, pmi_notify_handlers);
-
-	data->dev = dev;
-
-	data->irq = irq_of_parse_and_map(np, 0);
-	if (!data->irq) {
-		printk(KERN_ERR "pmi: invalid interrupt.\n");
-		rc = -EFAULT;
-		goto error_cleanup_iomap;
-	}
-
-	rc = request_irq(data->irq, pmi_irq_handler, 0, "pmi", NULL);
-	if (rc) {
-		printk(KERN_ERR "pmi: can't request IRQ %d: returned %d\n",
-				data->irq, rc);
-		goto error_cleanup_iomap;
-	}
-
-	printk(KERN_INFO "pmi: found pmi device at addr %p.\n", data->pmi_reg);
-
-	goto out;
-
-error_cleanup_iomap:
-	iounmap(data->pmi_reg);
-
-error_cleanup_data:
-	kfree(data);
-
-out:
-	return rc;
-}
-
-static int pmi_of_remove(struct platform_device *dev)
-{
-	struct pmi_handler *handler, *tmp;
-
-	free_irq(data->irq, NULL);
-	iounmap(data->pmi_reg);
-
-	spin_lock(&data->handler_spinlock);
-
-	list_for_each_entry_safe(handler, tmp, &data->handler, node)
-		list_del(&handler->node);
-
-	spin_unlock(&data->handler_spinlock);
-
-	kfree(data);
-	data = NULL;
-
-	return 0;
-}
-
-static struct platform_driver pmi_of_platform_driver = {
-	.probe		= pmi_of_probe,
-	.remove		= pmi_of_remove,
-	.driver = {
-		.name = "pmi",
-		.of_match_table = pmi_match,
-	},
-};
-module_platform_driver(pmi_of_platform_driver);
-
-int pmi_send_message(pmi_message_t msg)
-{
-	unsigned long flags;
-	DECLARE_COMPLETION_ONSTACK(completion);
-
-	if (!data)
-		return -ENODEV;
-
-	mutex_lock(&data->msg_mutex);
-
-	data->msg = msg;
-	pr_debug("pmi_send_message: msg is %08x\n", *(u32*)&msg);
-
-	data->completion = &completion;
-
-	spin_lock_irqsave(&data->pmi_spinlock, flags);
-	iowrite8(msg.data0, data->pmi_reg + PMI_WRITE_DATA0);
-	iowrite8(msg.data1, data->pmi_reg + PMI_WRITE_DATA1);
-	iowrite8(msg.data2, data->pmi_reg + PMI_WRITE_DATA2);
-	iowrite8(msg.type, data->pmi_reg + PMI_WRITE_TYPE);
-	spin_unlock_irqrestore(&data->pmi_spinlock, flags);
-
-	pr_debug("pmi_send_message: wait for completion\n");
-
-	wait_for_completion_interruptible_timeout(data->completion,
-						  PMI_TIMEOUT);
-
-	data->completion = NULL;
-
-	mutex_unlock(&data->msg_mutex);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pmi_send_message);
-
-int pmi_register_handler(struct pmi_handler *handler)
-{
-	if (!data)
-		return -ENODEV;
-
-	spin_lock(&data->handler_spinlock);
-	list_add_tail(&handler->node, &data->handler);
-	spin_unlock(&data->handler_spinlock);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pmi_register_handler);
-
-void pmi_unregister_handler(struct pmi_handler *handler)
-{
-	if (!data)
-		return;
-
-	pr_debug("pmi: unregistering handler %p\n", handler);
-
-	spin_lock(&data->handler_spinlock);
-	list_del(&handler->node);
-	spin_unlock(&data->handler_spinlock);
-}
-EXPORT_SYMBOL_GPL(pmi_unregister_handler);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
-MODULE_DESCRIPTION("IBM Platform Management Interrupt driver");
diff --git a/arch/powerpc/sysdev/rtc_cmos_setup.c b/arch/powerpc/sysdev/rtc_cmos_setup.c
index 47cc87bd6a33..9a232ae5e360 100644
--- a/arch/powerpc/sysdev/rtc_cmos_setup.c
+++ b/arch/powerpc/sysdev/rtc_cmos_setup.c
@@ -66,4 +66,5 @@ static int  __init add_rtc(void)
 }
 fs_initcall(add_rtc);
 
+MODULE_DESCRIPTION("PPC RTC CMOS driver");
 MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 0e42f7bad7db..07d0f6a83879 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -404,8 +404,8 @@ void __init tsi108_pci_int_init(struct device_node *node)
 {
 	DBG("Tsi108_pci_int_init: initializing PCI interrupts\n");
 
-	pci_irq_host = irq_domain_add_legacy(node, NR_IRQS_LEGACY, 0, 0,
-					     &pci_irq_domain_ops, NULL);
+	pci_irq_host = irq_domain_create_legacy(of_fwnode_handle(node), NR_IRQS_LEGACY, 0, 0,
+						&pci_irq_domain_ops, NULL);
 	if (pci_irq_host == NULL) {
 		printk(KERN_ERR "pci_irq_host: failed to allocate irq domain!\n");
 		return;
diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c
index 5020044400dc..4de57ba52236 100644
--- a/arch/powerpc/sysdev/udbg_memcons.c
+++ b/arch/powerpc/sysdev/udbg_memcons.c
@@ -41,7 +41,7 @@ struct memcons memcons = {
 	.input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE],
 };
 
-void memcons_putc(char c)
+static void memcons_putc(char c)
 {
 	char *new_output_pos;
 
@@ -54,7 +54,7 @@ void memcons_putc(char c)
 	memcons.output_pos = new_output_pos;
 }
 
-int memcons_getc_poll(void)
+static int memcons_getc_poll(void)
 {
 	char c;
 	char *new_input_pos;
@@ -77,7 +77,7 @@ int memcons_getc_poll(void)
 	return -1;
 }
 
-int memcons_getc(void)
+static int memcons_getc(void)
 {
 	int c;
 
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index f6ec6dba92dc..4e89158a577c 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -145,27 +145,6 @@ static void icp_native_cause_ipi(int cpu)
 	icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-void icp_native_cause_ipi_rm(int cpu)
-{
-	/*
-	 * Currently not used to send IPIs to another CPU
-	 * on the same core. Only caller is KVM real mode.
-	 * Need the physical address of the XICS to be
-	 * previously saved in kvm_hstate in the paca.
-	 */
-	void __iomem *xics_phys;
-
-	/*
-	 * Just like the cause_ipi functions, it is required to
-	 * include a full barrier before causing the IPI.
-	 */
-	xics_phys = paca_ptrs[cpu]->kvm_hstate.xics_phys;
-	mb();
-	__raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
-}
-#endif
-
 /*
  * Called when an interrupt is received on an off-line CPU to
  * clear the interrupt, so that the CPU can go back to nap mode.
@@ -236,6 +215,8 @@ static int __init icp_native_map_one_cpu(int hw_id, unsigned long addr,
 	rname = kasprintf(GFP_KERNEL, "CPU %d [0x%x] Interrupt Presentation",
 			  cpu, hw_id);
 
+	if (!rname)
+		return -ENOMEM;
 	if (!request_mem_region(addr, size, rname)) {
 		pr_warn("icp_native: Could not reserve ICP MMIO for CPU %d, interrupt server #0x%x\n",
 			cpu, hw_id);
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
index 6cfbb4fac7fb..5fe73dabab79 100644
--- a/arch/powerpc/sysdev/xics/ics-opal.c
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -111,7 +111,6 @@ static int ics_opal_set_affinity(struct irq_data *d,
 		       __func__, d->irq, hw_irq, rc);
 		return -1;
 	}
-	server = be16_to_cpu(oserver);
 
 	wanted_server = xics_get_irq_server(d->irq, cpumask, 1);
 	if (wanted_server < 0) {
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index d3a4156e8788..c3fa539a9898 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -472,7 +472,7 @@ static int __init xics_allocate_domain(void)
 		return -ENOMEM;
 	}
 
-	irq_set_default_host(xics_host);
+	irq_set_default_domain(xics_host);
 	return 0;
 }
 
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index a289cb97c1d7..8d0123b0ae84 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -317,7 +317,7 @@ int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d)
 	if (d) {
 		char buffer[128];
 
-		xive_irq_data_dump(irq_data_get_irq_handler_data(d),
+		xive_irq_data_dump(irq_data_get_irq_chip_data(d),
 				   buffer, sizeof(buffer));
 		xmon_printf("%s", buffer);
 	}
@@ -383,7 +383,7 @@ static unsigned int xive_get_irq(void)
  * CPU.
  *
  * If we find that there is indeed more in there, we call
- * force_external_irq_replay() to make Linux synthetize an
+ * force_external_irq_replay() to make Linux synthesize an
  * external interrupt on the next call to local_irq_restore().
  */
 static void xive_do_queue_eoi(struct xive_cpu *xc)
@@ -437,7 +437,7 @@ static void xive_do_source_eoi(struct xive_irq_data *xd)
 /* irq_chip eoi callback, called with irq descriptor lock held */
 static void xive_irq_eoi(struct irq_data *d)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 	struct xive_cpu *xc = __this_cpu_read(xive_cpu);
 
 	DBG_VERBOSE("eoi_irq: irq=%d [0x%lx] pending=%02x\n",
@@ -595,7 +595,7 @@ static int xive_pick_irq_target(struct irq_data *d,
 				const struct cpumask *affinity)
 {
 	static unsigned int fuzz;
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 	cpumask_var_t mask;
 	int cpu = -1;
 
@@ -628,7 +628,7 @@ static int xive_pick_irq_target(struct irq_data *d,
 
 static unsigned int xive_irq_startup(struct irq_data *d)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 	int target, rc;
 
@@ -673,7 +673,7 @@ static unsigned int xive_irq_startup(struct irq_data *d)
 /* called with irq descriptor lock held */
 static void xive_irq_shutdown(struct irq_data *d)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 
 	pr_debug("%s: irq %d [0x%x] data @%p\n", __func__, d->irq, hw_irq, d);
@@ -698,7 +698,7 @@ static void xive_irq_shutdown(struct irq_data *d)
 
 static void xive_irq_unmask(struct irq_data *d)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 
 	pr_debug("%s: irq %d data @%p\n", __func__, d->irq, xd);
 
@@ -707,7 +707,7 @@ static void xive_irq_unmask(struct irq_data *d)
 
 static void xive_irq_mask(struct irq_data *d)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 
 	pr_debug("%s: irq %d data @%p\n", __func__, d->irq, xd);
 
@@ -718,7 +718,7 @@ static int xive_irq_set_affinity(struct irq_data *d,
 				 const struct cpumask *cpumask,
 				 bool force)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 	u32 target, old_target;
 	int rc = 0;
@@ -726,7 +726,7 @@ static int xive_irq_set_affinity(struct irq_data *d,
 	pr_debug("%s: irq %d/0x%x\n", __func__, d->irq, hw_irq);
 
 	/* Is this valid ? */
-	if (cpumask_any_and(cpumask, cpu_online_mask) >= nr_cpu_ids)
+	if (!cpumask_intersects(cpumask, cpu_online_mask))
 		return -EINVAL;
 
 	/*
@@ -776,7 +776,7 @@ static int xive_irq_set_affinity(struct irq_data *d,
 
 static int xive_irq_set_type(struct irq_data *d, unsigned int flow_type)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 
 	/*
 	 * We only support these. This has really no effect other than setting
@@ -815,7 +815,7 @@ static int xive_irq_set_type(struct irq_data *d, unsigned int flow_type)
 
 static int xive_irq_retrigger(struct irq_data *d)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 
 	/* This should be only for MSIs */
 	if (WARN_ON(xd->flags & XIVE_IRQ_FLAG_LSI))
@@ -837,7 +837,7 @@ static int xive_irq_retrigger(struct irq_data *d)
  */
 static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(d);
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 	int rc;
 	u8 pq;
@@ -874,7 +874,7 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state)
 		 *
 		 * This also tells us that it's in flight to a host queue
 		 * or has already been fetched but hasn't been EOIed yet
-		 * by the host. This it's potentially using up a host
+		 * by the host. Thus it's potentially using up a host
 		 * queue slot. This is important to know because as long
 		 * as this is the case, we must not hard-unmask it when
 		 * "returning" that interrupt to the host.
@@ -951,7 +951,7 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state)
 static int xive_get_irqchip_state(struct irq_data *data,
 				  enum irqchip_irq_state which, bool *state)
 {
-	struct xive_irq_data *xd = irq_data_get_irq_handler_data(data);
+	struct xive_irq_data *xd = irq_data_get_irq_chip_data(data);
 	u8 pq;
 
 	switch (which) {
@@ -1011,21 +1011,20 @@ void xive_cleanup_irq_data(struct xive_irq_data *xd)
 }
 EXPORT_SYMBOL_GPL(xive_cleanup_irq_data);
 
-static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw)
+static struct xive_irq_data *xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw)
 {
 	struct xive_irq_data *xd;
 	int rc;
 
 	xd = kzalloc(sizeof(struct xive_irq_data), GFP_KERNEL);
 	if (!xd)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 	rc = xive_ops->populate_irq_data(hw, xd);
 	if (rc) {
 		kfree(xd);
-		return rc;
+		return ERR_PTR(rc);
 	}
 	xd->target = XIVE_INVALID_TARGET;
-	irq_set_handler_data(virq, xd);
 
 	/*
 	 * Turn OFF by default the interrupt being mapped. A side
@@ -1036,20 +1035,19 @@ static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw)
 	 */
 	xive_esb_read(xd, XIVE_ESB_SET_PQ_01);
 
-	return 0;
+	return xd;
 }
 
-void xive_irq_free_data(unsigned int virq)
+static void xive_irq_free_data(unsigned int virq)
 {
-	struct xive_irq_data *xd = irq_get_handler_data(virq);
+	struct xive_irq_data *xd = irq_get_chip_data(virq);
 
 	if (!xd)
 		return;
-	irq_set_handler_data(virq, NULL);
+	irq_set_chip_data(virq, NULL);
 	xive_cleanup_irq_data(xd);
 	kfree(xd);
 }
-EXPORT_SYMBOL_GPL(xive_irq_free_data);
 
 #ifdef CONFIG_SMP
 
@@ -1286,7 +1284,7 @@ void __init xive_smp_probe(void)
 static int xive_irq_domain_map(struct irq_domain *h, unsigned int virq,
 			       irq_hw_number_t hw)
 {
-	int rc;
+	struct xive_irq_data *xd;
 
 	/*
 	 * Mark interrupts as edge sensitive by default so that resend
@@ -1294,11 +1292,12 @@ static int xive_irq_domain_map(struct irq_domain *h, unsigned int virq,
 	 */
 	irq_clear_status_flags(virq, IRQ_LEVEL);
 
-	rc = xive_irq_alloc_data(virq, hw);
-	if (rc)
-		return rc;
+	xd = xive_irq_alloc_data(virq, hw);
+	if (IS_ERR(xd))
+		return PTR_ERR(xd);
 
 	irq_set_chip_and_handler(virq, &xive_irq_chip, handle_fasteoi_irq);
+	irq_set_chip_data(virq, xd);
 
 	return 0;
 }
@@ -1366,7 +1365,7 @@ static void xive_irq_domain_debug_show(struct seq_file *m, struct irq_domain *d,
 	seq_printf(m, "%*sXIVE:\n", ind, "");
 	ind++;
 
-	xd = irq_data_get_irq_handler_data(irqd);
+	xd = irq_data_get_irq_chip_data(irqd);
 	if (!xd) {
 		seq_printf(m, "%*snot assigned\n", ind, "");
 		return;
@@ -1403,6 +1402,7 @@ static int xive_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 				 unsigned int nr_irqs, void *arg)
 {
 	struct irq_fwspec *fwspec = arg;
+	struct xive_irq_data *xd;
 	irq_hw_number_t hwirq;
 	unsigned int type = IRQ_TYPE_NONE;
 	int i, rc;
@@ -1423,12 +1423,11 @@ static int xive_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 		irq_clear_status_flags(virq, IRQ_LEVEL);
 
 		/* allocates and sets handler data */
-		rc = xive_irq_alloc_data(virq + i, hwirq + i);
-		if (rc)
-			return rc;
+		xd = xive_irq_alloc_data(virq + i, hwirq + i);
+		if (IS_ERR(xd))
+			return PTR_ERR(xd);
 
-		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
-					      &xive_irq_chip, domain->host_data);
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i, &xive_irq_chip, xd);
 		irq_set_handler(virq + i, handle_fasteoi_irq);
 	}
 
@@ -1464,10 +1463,10 @@ static const struct irq_domain_ops xive_irq_domain_ops = {
 
 static void __init xive_init_host(struct device_node *np)
 {
-	xive_irq_domain = irq_domain_add_tree(np, &xive_irq_domain_ops, NULL);
+	xive_irq_domain = irq_domain_create_tree(of_fwnode_handle(np), &xive_irq_domain_ops, NULL);
 	if (WARN_ON(xive_irq_domain == NULL))
 		return;
-	irq_set_default_host(xive_irq_domain);
+	irq_set_default_domain(xive_irq_domain);
 }
 
 static void xive_cleanup_cpu_queues(unsigned int cpu, struct xive_cpu *xc)
@@ -1581,7 +1580,7 @@ static void xive_flush_cpu_queue(unsigned int cpu, struct xive_cpu *xc)
 			cpu, irq);
 #endif
 		raw_spin_lock(&desc->lock);
-		xd = irq_desc_get_handler_data(desc);
+		xd = irq_desc_get_chip_data(desc);
 
 		/*
 		 * Clear saved_p to indicate that it's no longer pending
@@ -1764,7 +1763,7 @@ static void xive_debug_show_irq(struct seq_file *m, struct irq_data *d)
 	seq_printf(m, "IRQ 0x%08x : target=0x%x prio=%02x lirq=0x%x ",
 		   hw_irq, target, prio, lirq);
 
-	xive_irq_data_dump(irq_data_get_irq_handler_data(d), buffer, sizeof(buffer));
+	xive_irq_data_dump(irq_data_get_irq_chip_data(d), buffer, sizeof(buffer));
 	seq_puts(m, buffer);
 	seq_puts(m, "\n");
 }
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 9f0af4d795d8..a0934b516933 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -415,7 +415,7 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
 		return;
 	}
 
-	/* Grab it's CAM value */
+	/* Grab its CAM value */
 	rc = opal_xive_get_vp_info(vp, NULL, &vp_cam_be, NULL, NULL);
 	if (rc) {
 		pr_err("Failed to get pool VP info CPU %d\n", cpu);
@@ -559,9 +559,7 @@ bool __init xive_native_init(void)
 	struct device_node *np;
 	struct resource r;
 	void __iomem *tima;
-	struct property *prop;
 	u8 max_prio = 7;
-	const __be32 *p;
 	u32 val, cpu;
 	s64 rc;
 
@@ -592,7 +590,7 @@ bool __init xive_native_init(void)
 		max_prio = val - 1;
 
 	/* Iterate the EQ sizes and pick one */
-	of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, p, val) {
+	of_property_for_each_u32(np, "ibm,xive-eq-sizes", val) {
 		xive_queue_shift = val;
 		if (val == PAGE_SHIFT)
 			break;
@@ -802,7 +800,7 @@ int xive_native_get_queue_info(u32 vp_id, u32 prio,
 	if (out_qpage)
 		*out_qpage = be64_to_cpu(qpage);
 	if (out_qsize)
-		*out_qsize = be32_to_cpu(qsize);
+		*out_qsize = be64_to_cpu(qsize);
 	if (out_qeoi_page)
 		*out_qeoi_page = be64_to_cpu(qeoi_page);
 	if (out_escalate_irq)
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index e45419264391..5aedbe3e8e6a 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -7,6 +7,7 @@
 
 #include <linux/types.h>
 #include <linux/irq.h>
+#include <linux/seq_file.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
@@ -814,7 +815,6 @@ bool __init xive_spapr_init(void)
 	struct device_node *np;
 	struct resource r;
 	void __iomem *tima;
-	struct property *prop;
 	u8 max_prio;
 	u32 val;
 	u32 len;
@@ -866,7 +866,7 @@ bool __init xive_spapr_init(void)
 	}
 
 	/* Iterate the EQ sizes and pick one */
-	of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, reg, val) {
+	of_property_for_each_u32(np, "ibm,xive-eq-sizes", val) {
 		xive_queue_shift = val;
 		if (val == PAGE_SHIFT)
 			break;
diff --git a/arch/powerpc/platforms/maple/Makefile b/arch/powerpc/tools/.gitignore
index 19f35ab828a7..ec380a14a09a 100644
--- a/arch/powerpc/platforms/maple/Makefile
+++ b/arch/powerpc/tools/.gitignore
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y	+= setup.o pci.o time.o
+/vmlinux.arch.S
diff --git a/arch/powerpc/tools/Makefile b/arch/powerpc/tools/Makefile
new file mode 100644
index 000000000000..e1f7afcd9fdf
--- /dev/null
+++ b/arch/powerpc/tools/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+quiet_cmd_gen_ftrace_ool_stubs = GEN     $@
+	cmd_gen_ftrace_ool_stubs = $< "$(CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE)" "$(CONFIG_64BIT)" \
+				   "$(OBJDUMP)" vmlinux.o $@
+
+$(obj)/vmlinux.arch.S: $(src)/ftrace-gen-ool-stubs.sh vmlinux.o FORCE
+	$(call if_changed,gen_ftrace_ool_stubs)
+
+targets += vmlinux.arch.S
diff --git a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
new file mode 100755
index 000000000000..bac186bdf64a
--- /dev/null
+++ b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
@@ -0,0 +1,52 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+# Error out on error
+set -e
+
+num_ool_stubs_text_builtin="$1"
+is_64bit="$2"
+objdump="$3"
+vmlinux_o="$4"
+arch_vmlinux_S="$5"
+
+RELOCATION=R_PPC64_ADDR64
+if [ -z "$is_64bit" ]; then
+	RELOCATION=R_PPC_ADDR32
+fi
+
+num_ool_stubs_total=$($objdump -r -j __patchable_function_entries "$vmlinux_o" |
+		      grep -c "$RELOCATION")
+num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries "$vmlinux_o" |
+			 grep -e ".init.text" -e ".text.startup" | grep -c "$RELOCATION")
+num_ool_stubs_text=$((num_ool_stubs_total - num_ool_stubs_inittext))
+
+if [ "$num_ool_stubs_text" -gt "$num_ool_stubs_text_builtin" ]; then
+	num_ool_stubs_text_end=$((num_ool_stubs_text - num_ool_stubs_text_builtin))
+else
+	num_ool_stubs_text_end=0
+fi
+
+cat > "$arch_vmlinux_S" <<EOF
+#include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
+#include <linux/linkage.h>
+
+.pushsection .tramp.ftrace.text,"aw"
+SYM_DATA(ftrace_ool_stub_text_end_count, .long $num_ool_stubs_text_end)
+
+SYM_START(ftrace_ool_stub_text_end, SYM_L_GLOBAL, .balign SZL)
+#if $num_ool_stubs_text_end
+	.space $num_ool_stubs_text_end * FTRACE_OOL_STUB_SIZE
+#endif
+SYM_CODE_END(ftrace_ool_stub_text_end)
+.popsection
+
+.pushsection .tramp.ftrace.init,"aw"
+SYM_DATA(ftrace_ool_stub_inittext_count, .long $num_ool_stubs_inittext)
+
+SYM_START(ftrace_ool_stub_inittext, SYM_L_GLOBAL, .balign SZL)
+	.space $num_ool_stubs_inittext * FTRACE_OOL_STUB_SIZE
+SYM_CODE_END(ftrace_ool_stub_inittext)
+.popsection
+EOF
diff --git a/arch/powerpc/tools/ftrace_check.sh b/arch/powerpc/tools/ftrace_check.sh
new file mode 100755
index 000000000000..405e7e306617
--- /dev/null
+++ b/arch/powerpc/tools/ftrace_check.sh
@@ -0,0 +1,50 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# This script checks vmlinux to ensure that all functions can call ftrace_caller() either directly,
+# or through the stub, ftrace_tramp_text, at the end of kernel text.
+
+# Error out if any command fails
+set -e
+
+# Allow for verbose output
+if [ "$V" = "1" ]; then
+	set -x
+fi
+
+if [ $# -lt 2 ]; then
+	echo "$0 [path to nm] [path to vmlinux]" 1>&2
+	exit 1
+fi
+
+# Have Kbuild supply the path to nm so we handle cross compilation.
+nm="$1"
+vmlinux="$2"
+
+stext_addr=$($nm "$vmlinux" | grep -e " [TA] _stext$" | \
+	cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+ftrace_caller_addr=$($nm "$vmlinux" | grep -e " T ftrace_caller$" | \
+	cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+ftrace_tramp_addr=$($nm "$vmlinux" | grep -e " T ftrace_tramp_text$" | \
+	cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+
+ftrace_caller_offset=$(echo "ibase=16;$ftrace_caller_addr - $stext_addr" | bc)
+ftrace_tramp_offset=$(echo "ibase=16;$ftrace_tramp_addr - $ftrace_caller_addr" | bc)
+sz_32m=$(printf "%d" 0x2000000)
+sz_64m=$(printf "%d" 0x4000000)
+
+# ftrace_caller - _stext < 32M
+if [ "$ftrace_caller_offset" -ge "$sz_32m" ]; then
+	echo "ERROR: ftrace_caller (0x$ftrace_caller_addr) is beyond 32MiB of _stext" 1>&2
+	echo "ERROR: consider disabling CONFIG_FUNCTION_TRACER, or reducing the size \
+		of kernel text" 1>&2
+	exit 1
+fi
+
+# ftrace_tramp_text - ftrace_caller < 64M
+if [ "$ftrace_tramp_offset" -ge "$sz_64m" ]; then
+	echo "ERROR: kernel text extends beyond 64MiB from ftrace_caller" 1>&2
+	echo "ERROR: consider disabling CONFIG_FUNCTION_TRACER, or reducing the size \
+		of kernel text" 1>&2
+	exit 1
+fi
diff --git a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh b/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh
new file mode 100755
index 000000000000..06706903503b
--- /dev/null
+++ b/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+set -o pipefail
+
+# To debug, uncomment the following line
+# set -x
+
+# Output from -fpatchable-function-entry can only vary on ppc64 elfv2, so this
+# should not be invoked for other targets. Therefore we can pass in -m64 and
+# -mabi explicitly, to take care of toolchains defaulting to other targets.
+
+# Test whether the compile option -fpatchable-function-entry exists and
+# generates appropriate code
+echo "int func() { return 0; }" | \
+    $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \
+    grep -q "__patchable_function_entries"
+
+# Test whether nops are generated after the local entry point
+echo "int x; int func() { return x; }" | \
+    $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \
+    awk 'BEGIN { RS = ";" } /\.localentry.*nop.*\n[[:space:]]*nop/ { print $0 }' | \
+    grep -q "func:"
+
+exit 0
diff --git a/arch/powerpc/tools/gcc-check-mprofile-kernel.sh b/arch/powerpc/tools/gcc-check-mprofile-kernel.sh
index 137f3376ac2b..73e331e7660e 100755
--- a/arch/powerpc/tools/gcc-check-mprofile-kernel.sh
+++ b/arch/powerpc/tools/gcc-check-mprofile-kernel.sh
@@ -7,20 +7,20 @@ set -o pipefail
 # To debug, uncomment the following line
 # set -x
 
-# -mprofile-kernel is only supported on 64le, so this should not be invoked
-# for other targets. Therefore we can pass in -m64 and -mlittle-endian
+# -mprofile-kernel is only supported on 64-bit with ELFv2, so this should not
+# be invoked for other targets. Therefore we can pass in -m64 and -mabi
 # explicitly, to take care of toolchains defaulting to other targets.
 
 # Test whether the compile option -mprofile-kernel exists and generates
 # profiling code (ie. a call to _mcount()).
 echo "int func() { return 0; }" | \
-    $* -m64 -mlittle-endian -S -x c -O2 -p -mprofile-kernel - -o - \
+    $* -m64 -mabi=elfv2 -S -x c -O2 -p -mprofile-kernel - -o - \
     2> /dev/null | grep -q "_mcount"
 
 # Test whether the notrace attribute correctly suppresses calls to _mcount().
 
 echo -e "#include <linux/compiler.h>\nnotrace int func() { return 0; }" | \
-    $* -m64 -mlittle-endian -S -x c -O2 -p -mprofile-kernel - -o - \
+    $* -m64 -mabi=elfv2 -S -x c -O2 -p -mprofile-kernel - -o - \
     2> /dev/null | grep -q "_mcount" && \
     exit 1
 
diff --git a/arch/powerpc/tools/head_check.sh b/arch/powerpc/tools/head_check.sh
index 689907cda996..a9cd06958921 100644
--- a/arch/powerpc/tools/head_check.sh
+++ b/arch/powerpc/tools/head_check.sh
@@ -1,3 +1,4 @@
+#!/bin/sh
 # Copyright © 2016 IBM Corporation
 
 # This program is free software; you can redistribute it and/or
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index d334de392e6c..d74b147126b7 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -10,17 +10,10 @@ KCSAN_SANITIZE := n
 # Disable ftrace for the entire directory
 ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
 
-ifdef CONFIG_CC_IS_CLANG
-# clang stores addresses on the stack causing the frame size to blow
+# Clang stores addresses on the stack causing the frame size to blow
 # out. See https://github.com/ClangBuiltLinux/linux/issues/252
-KBUILD_CFLAGS += -Wframe-larger-than=4096
-endif
-
-ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
+ccflags-$(CONFIG_CC_IS_CLANG) += -Wframe-larger-than=4096
 
 obj-y			+= xmon.o nonstdio.o spr_access.o xmon_bpts.o
 
-ifdef CONFIG_XMON_DISASSEMBLY
-obj-y			+= ppc-dis.o ppc-opc.o
-obj-$(CONFIG_SPU_BASE)	+= spu-dis.o spu-opc.o
-endif
+obj-$(CONFIG_XMON_DISASSEMBLY) += ppc-dis.o ppc-opc.o
diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c
index 75fa98221d48..af105e1bc3fc 100644
--- a/arch/powerpc/xmon/ppc-dis.c
+++ b/arch/powerpc/xmon/ppc-dis.c
@@ -122,32 +122,21 @@ int print_insn_powerpc (unsigned long insn, unsigned long memaddr)
   bool insn_is_short;
   ppc_cpu_t dialect;
 
-  dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON
-            | PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_ALTIVEC;
+  dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON;
 
-  if (cpu_has_feature(CPU_FTRS_POWER5))
-    dialect |= PPC_OPCODE_POWER5;
+  if (IS_ENABLED(CONFIG_PPC64))
+    dialect |= PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_CELL |
+	PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 | PPC_OPCODE_POWER8 |
+	PPC_OPCODE_POWER9;
 
-  if (cpu_has_feature(CPU_FTRS_CELL))
-    dialect |= (PPC_OPCODE_CELL | PPC_OPCODE_ALTIVEC);
+  if (cpu_has_feature(CPU_FTR_TM))
+    dialect |= PPC_OPCODE_HTM;
 
-  if (cpu_has_feature(CPU_FTRS_POWER6))
-    dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_ALTIVEC);
+  if (cpu_has_feature(CPU_FTR_ALTIVEC))
+    dialect |= PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2;
 
-  if (cpu_has_feature(CPU_FTRS_POWER7))
-    dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7
-                | PPC_OPCODE_ALTIVEC | PPC_OPCODE_VSX);
-
-  if (cpu_has_feature(CPU_FTRS_POWER8))
-    dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7
-		| PPC_OPCODE_POWER8 | PPC_OPCODE_HTM
-		| PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 | PPC_OPCODE_VSX);
-
-  if (cpu_has_feature(CPU_FTRS_POWER9))
-    dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7
-		| PPC_OPCODE_POWER8 | PPC_OPCODE_POWER9 | PPC_OPCODE_HTM
-		| PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2
-		| PPC_OPCODE_VSX | PPC_OPCODE_VSX3);
+  if (cpu_has_feature(CPU_FTR_VSX))
+    dialect |= PPC_OPCODE_VSX | PPC_OPCODE_VSX3;
 
   /* Get the major opcode of the insn.  */
   opcode = NULL;
diff --git a/arch/powerpc/xmon/ppc-opc.c b/arch/powerpc/xmon/ppc-opc.c
index 0774d711453e..de9b4236728c 100644
--- a/arch/powerpc/xmon/ppc-opc.c
+++ b/arch/powerpc/xmon/ppc-opc.c
@@ -954,8 +954,7 @@ const struct powerpc_operand powerpc_operands[] =
   { 0xff, 11, NULL, NULL, PPC_OPERAND_SIGNOPT },
 };
 
-const unsigned int num_powerpc_operands = (sizeof (powerpc_operands)
-					   / sizeof (powerpc_operands[0]));
+const unsigned int num_powerpc_operands = ARRAY_SIZE(powerpc_operands);
 
 /* The functions used to insert and extract complicated operands.  */
 
@@ -6968,9 +6967,8 @@ const struct powerpc_opcode powerpc_opcodes[] = {
 {"fcfidu.",	XRC(63,974,1),	XRA_MASK, POWER7|PPCA2,	PPCVLE,		{FRT, FRB}},
 };
 
-const int powerpc_num_opcodes =
-  sizeof (powerpc_opcodes) / sizeof (powerpc_opcodes[0]);
-
+const int powerpc_num_opcodes = ARRAY_SIZE(powerpc_opcodes);
+
 /* The VLE opcode table.
 
    The format of this opcode table is the same as the main opcode table.  */
@@ -7207,9 +7205,8 @@ const struct powerpc_opcode vle_opcodes[] = {
 {"se_bl",	BD8(58,0,1),	BD8_MASK,	PPCVLE,	0,		{B8}},
 };
 
-const int vle_num_opcodes =
-  sizeof (vle_opcodes) / sizeof (vle_opcodes[0]);
-
+const int vle_num_opcodes = ARRAY_SIZE(vle_opcodes);
+
 /* The macro table.  This is only used by the assembler.  */
 
 /* The expressions of the form (-x ! 31) & (x | 31) have the value 0
@@ -7276,5 +7273,4 @@ const struct powerpc_macro powerpc_macros[] = {
 {"e_clrlslwi",4, PPCVLE, "e_rlwinm %0,%1,%3,(%2)-(%3),31-(%3)"},
 };
 
-const int powerpc_num_macros =
-  sizeof (powerpc_macros) / sizeof (powerpc_macros[0]);
+const int powerpc_num_macros = ARRAY_SIZE(powerpc_macros);
diff --git a/arch/powerpc/xmon/spu-dis.c b/arch/powerpc/xmon/spu-dis.c
deleted file mode 100644
index 4b0a4e640f08..000000000000
--- a/arch/powerpc/xmon/spu-dis.c
+++ /dev/null
@@ -1,237 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* Disassemble SPU instructions
-
-   Copyright 2006 Free Software Foundation, Inc.
-
-   This file is part of GDB, GAS, and the GNU binutils.
-
- */
-
-#include <linux/string.h>
-#include "nonstdio.h"
-#include "ansidecl.h"
-#include "spu.h"
-#include "dis-asm.h"
-
-/* This file provides a disassembler function which uses
-   the disassembler interface defined in dis-asm.h.   */
-
-extern const struct spu_opcode spu_opcodes[];
-extern const int spu_num_opcodes;
-
-#define SPU_DISASM_TBL_SIZE (1 << 11)
-static const struct spu_opcode *spu_disassemble_table[SPU_DISASM_TBL_SIZE];
-
-static void
-init_spu_disassemble (void)
-{
-  int i;
-
-  /* If two instructions have the same opcode then we prefer the first
-   * one.  In most cases it is just an alternate mnemonic. */
-  for (i = 0; i < spu_num_opcodes; i++)
-    {
-      int o = spu_opcodes[i].opcode;
-      if (o >= SPU_DISASM_TBL_SIZE)
-	continue; /* abort (); */
-      if (spu_disassemble_table[o] == 0)
-	spu_disassemble_table[o] = &spu_opcodes[i];
-    }
-}
-
-/* Determine the instruction from the 10 least significant bits. */
-static const struct spu_opcode *
-get_index_for_opcode (unsigned int insn)
-{
-  const struct spu_opcode *index;
-  unsigned int opcode = insn >> (32-11);
-
-  /* Init the table.  This assumes that element 0/opcode 0 (currently
-   * NOP) is always used */
-  if (spu_disassemble_table[0] == 0)
-    init_spu_disassemble ();
-
-  if ((index = spu_disassemble_table[opcode & 0x780]) != 0
-      && index->insn_type == RRR)
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7f0]) != 0
-      && (index->insn_type == RI18 || index->insn_type == LBT))
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7f8]) != 0
-      && index->insn_type == RI10)
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7fc]) != 0
-      && (index->insn_type == RI16))
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7fe]) != 0
-      && (index->insn_type == RI8))
-    return index;
-
-  if ((index = spu_disassemble_table[opcode & 0x7ff]) != 0)
-    return index;
-
-  return NULL;
-}
-
-/* Print a Spu instruction.  */
-
-int
-print_insn_spu (unsigned long insn, unsigned long memaddr)
-{
-  int value;
-  int hex_value;
-  const struct spu_opcode *index;
-  enum spu_insns tag;
-
-  index = get_index_for_opcode (insn);
-
-  if (index == 0)
-    {
-      printf(".long 0x%lx", insn);
-    }
-  else
-    {
-      int i;
-      int paren = 0;
-      tag = (enum spu_insns)(index - spu_opcodes);
-      printf("%s", index->mnemonic);
-      if (tag == M_BI || tag == M_BISL || tag == M_IRET || tag == M_BISLED
-	  || tag == M_BIHNZ || tag == M_BIHZ || tag == M_BINZ || tag == M_BIZ
-          || tag == M_SYNC || tag == M_HBR)
-	{
-	  int fb = (insn >> (32-18)) & 0x7f;
-	  if (fb & 0x40)
-	    printf(tag == M_SYNC ? "c" : "p");
-	  if (fb & 0x20)
-	    printf("d");
-	  if (fb & 0x10)
-	    printf("e");
-	}
-      if (index->arg[0] != 0)
-	printf("\t");
-      hex_value = 0;
-      for (i = 1;  i <= index->arg[0]; i++)
-	{
-	  int arg = index->arg[i];
-	  if (arg != A_P && !paren && i > 1)
-	    printf(",");
-
-	  switch (arg)
-	    {
-	    case A_T:
-	      printf("$%lu",
-				     DECODE_INSN_RT (insn));
-	      break;
-	    case A_A:
-	      printf("$%lu",
-				     DECODE_INSN_RA (insn));
-	      break;
-	    case A_B:
-	      printf("$%lu",
-				     DECODE_INSN_RB (insn));
-	      break;
-	    case A_C:
-	      printf("$%lu",
-				     DECODE_INSN_RC (insn));
-	      break;
-	    case A_S:
-	      printf("$sp%lu",
-				     DECODE_INSN_RA (insn));
-	      break;
-	    case A_H:
-	      printf("$ch%lu",
-				     DECODE_INSN_RA (insn));
-	      break;
-	    case A_P:
-	      paren++;
-	      printf("(");
-	      break;
-	    case A_U7A:
-	      printf("%lu",
-				     173 - DECODE_INSN_U8 (insn));
-	      break;
-	    case A_U7B:
-	      printf("%lu",
-				     155 - DECODE_INSN_U8 (insn));
-	      break;
-	    case A_S3:
-	    case A_S6:
-	    case A_S7:
-	    case A_S7N:
-	    case A_U3:
-	    case A_U5:
-	    case A_U6:
-	    case A_U7:
-	      hex_value = DECODE_INSN_I7 (insn);
-	      printf("%d", hex_value);
-	      break;
-	    case A_S11:
-	      print_address(memaddr + DECODE_INSN_I9a (insn) * 4);
-	      break;
-	    case A_S11I:
-	      print_address(memaddr + DECODE_INSN_I9b (insn) * 4);
-	      break;
-	    case A_S10:
-	    case A_S10B:
-	      hex_value = DECODE_INSN_I10 (insn);
-	      printf("%d", hex_value);
-	      break;
-	    case A_S14:
-	      hex_value = DECODE_INSN_I10 (insn) * 16;
-	      printf("%d", hex_value);
-	      break;
-	    case A_S16:
-	      hex_value = DECODE_INSN_I16 (insn);
-	      printf("%d", hex_value);
-	      break;
-	    case A_X16:
-	      hex_value = DECODE_INSN_U16 (insn);
-	      printf("%u", hex_value);
-	      break;
-	    case A_R18:
-	      value = DECODE_INSN_I16 (insn) * 4;
-	      if (value == 0)
-		printf("%d", value);
-	      else
-		{
-		  hex_value = memaddr + value;
-		  print_address(hex_value & 0x3ffff);
-		}
-	      break;
-	    case A_S18:
-	      value = DECODE_INSN_U16 (insn) * 4;
-	      if (value == 0)
-		printf("%d", value);
-	      else
-		print_address(value);
-	      break;
-	    case A_U18:
-	      value = DECODE_INSN_U18 (insn);
-	      if (value == 0 || 1)
-		{
-		  hex_value = value;
-		  printf("%u", value);
-		}
-	      else
-		print_address(value);
-	      break;
-	    case A_U14:
-	      hex_value = DECODE_INSN_U14 (insn);
-	      printf("%u", hex_value);
-	      break;
-	    }
-	  if (arg != A_P && paren)
-	    {
-	      printf(")");
-	      paren--;
-	    }
-	}
-      if (hex_value > 16)
-	printf("\t# %x", hex_value);
-    }
-  return 4;
-}
diff --git a/arch/powerpc/xmon/spu-insns.h b/arch/powerpc/xmon/spu-insns.h
deleted file mode 100644
index 7e1126a19909..000000000000
--- a/arch/powerpc/xmon/spu-insns.h
+++ /dev/null
@@ -1,399 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* SPU ELF support for BFD.
-
-   Copyright 2006 Free Software Foundation, Inc.
-
-   This file is part of BFD, the Binary File Descriptor library.
-
- */
-
-/* SPU Opcode Table
-
--=-=-= FORMAT =-=-=-
-                                             		                                             
-       +----+-------+-------+-------+-------+  		       +------------+-------+-------+-------+
-RRR    | op |  RC   |  RB   |  RA   |  RT   |		RI7    | op         |  I7   |  RA   |  RT   |
-       +----+-------+-------+-------+-------+		       +------------+-------+-------+-------+
-        0  3       1       1       2       3		        0          1       1       2       3 
-                   0       7       4       1		                   0       7       4       1 
-
-       +-----------+--------+-------+-------+		       +---------+----------+-------+-------+
-RI8    | op        |   I8   |  RA   |  RT   |		RI10   | op      |   I10    |  RA   |  RT   |
-       +-----------+--------+-------+-------+		       +---------+----------+-------+-------+
-        0         9        1       2       3		        0       7          1       2       3 
-                           7       4       1		                           7       4       1 
-
-       +----------+-----------------+-------+		       +--------+-------------------+-------+
-RI16   | op       |       I16       |  RT   |		RI18   | op     |       I18         |  RT   |
-       +----------+-----------------+-------+		       +--------+-------------------+-------+
-        0        8                 2       3		        0      6                   2       3 
-                                   4       1		                                   4       1 
-
-       +------------+-------+-------+-------+		       +-------+--+-----------------+-------+
-RR     | op         |  RB   |  RA   |  RT   |		LBT    | op    |RO|       I16       |  RO   |
-       +------------+-------+-------+-------+		       +-------+--+-----------------+-------+
-        0          1       1       2       3		        0     6  8                 2       3 
-                   0       7       4       1		                                   4       1 
-
-							       +------------+----+--+-------+-------+
-							LBTI   | op         | // |RO|  RA   |  RO   |
-							       +------------+----+--+-------+-------+
-							        0          1    1  1       2       3
-							                   0    5  7       4       1
-
--=-=-= OPCODE =-=-=-
-
-OPCODE field specifies the most significant 11bit of the instruction. Some formats don't have 11bits for opcode field, and in this
-case, bit field other than op are defined as 0s. For example, opcode of fma instruction which is RRR format is defined as 0x700,
-since 0x700 -> 11'b11100000000, this means opcode is 4'b1110, and other 7bits are defined as 7'b0000000.
-
--=-=-= ASM_FORMAT =-=-=-
-
-RRR category						RI7 category                               
-	ASM_RRR		mnemonic RC, RA, RB, RT		        ASM_RI4         mnemonic RT, RA, I4
-							        ASM_RI7         mnemonic RT, RA, I7
-
-RI8 category						RI10 category                               
-	ASM_RUI8	mnemonic RT, RA, UI8		        ASM_AI10        mnemonic RA, I10    
-							        ASM_RI10        mnemonic RT, RA, R10
-							        ASM_RI10IDX     mnemonic RT, I10(RA)
-
-RI16 category						RI18 category                           
-	ASM_I16W	mnemonic I16W			        ASM_RI18        mnemonic RT, I18
-	ASM_RI16	mnemonic RT, I16
-	ASM_RI16W	mnemonic RT, I16W
-
-RR category						LBT category                                    
-	ASM_MFSPR	mnemonic RT, SA			        ASM_LBT         mnemonic brinst, brtarg 
-	ASM_MTSPR	mnemonic SA, RT			                                                
-	ASM_NOOP	mnemonic			LBTI category                                   
-	ASM_RA		mnemonic RA			        ASM_LBTI        mnemonic brinst, RA     
-	ASM_RAB		mnemonic RA, RB
-	ASM_RDCH	mnemonic RT, CA
-	ASM_RR		mnemonic RT, RA, RB
-	ASM_RT		mnemonic RT
-	ASM_RTA		mnemonic RT, RA
-	ASM_WRCH	mnemonic CA, RT
-
-Note that RRR instructions have the names for RC and RT reversed from
-what's in the ISA, in order to put RT in the same position it appears
-for other formats.
-
--=-=-= DEPENDENCY =-=-=-
-
-DEPENDENCY filed consists of 5 digits. This represents which register is used as source and which register is used as target.
-The first(most significant) digit is always 0. Then it is followd by RC, RB, RA and RT digits.
-If the digit is 0, this means the corresponding register is not used in the instruction.
-If the digit is 1, this means the corresponding register is used as a source in the instruction.
-If the digit is 2, this means the corresponding register is used as a target in the instruction.
-If the digit is 3, this means the corresponding register is used as both source and target in the instruction.
-For example, fms instruction has 00113 as the DEPENDENCY field. This means RC is not used in this operation, RB and RA are
-used as sources and RT is the target.
-
--=-=-= PIPE =-=-=-
-
-This field shows which execution pipe is used for the instruction
-
-pipe0 execution pipelines:
-	FP6	SP floating pipeline
-	FP7	integer operations executed in SP floating pipeline
-	FPD	DP floating pipeline
-	FX2	FXU pipeline
-	FX3	Rotate/Shift pipeline
-	FXB	Byte pipeline
-	NOP	No pipeline
-
-pipe1 execution pipelines:
-	BR	Branch pipeline
-	LNOP	No pipeline
-	LS	Load/Store pipeline
-	SHUF	Shuffle pipeline
-	SPR	SPR/CH pipeline
-
-*/
-
-#define _A0() {0}
-#define _A1(a) {1,a}
-#define _A2(a,b) {2,a,b}
-#define _A3(a,b,c) {3,a,b,c}
-#define _A4(a,b,c,d) {4,a,b,c,d}
-
-/*    TAG		FORMAT	OPCODE	MNEMONIC	ASM_FORMAT	DEPENDENCY	PIPE	COMMENT				*/
-/*									0[RC][RB][RA][RT]					*/
-/*									1:src, 2:target						*/
-
-APUOP(M_BR,		RI16,	0x190,	"br",		_A1(A_R18),	00000,	BR)	/* BRel          IP<-IP+I16 */
-APUOP(M_BRSL,		RI16,	0x198,	"brsl",		_A2(A_T,A_R18),	00002,	BR)	/* BRelSetLink   RT,IP<-IP,IP+I16 */
-APUOP(M_BRA,		RI16,	0x180,	"bra",		_A1(A_S18),	00000,	BR)	/* BRAbs         IP<-I16 */
-APUOP(M_BRASL,		RI16,	0x188,	"brasl",	_A2(A_T,A_S18),	00002,	BR)	/* BRAbsSetLink  RT,IP<-IP,I16 */
-APUOP(M_FSMBI,		RI16,	0x194,	"fsmbi",	_A2(A_T,A_X16),	00002,	SHUF)	/* FormSelMask%I RT<-fsm(I16) */
-APUOP(M_LQA,		RI16,	0x184,	"lqa",		_A2(A_T,A_S18),	00002,	LS)	/* LoadQAbs      RT<-M[I16] */
-APUOP(M_LQR,		RI16,	0x19C,	"lqr",		_A2(A_T,A_R18),	00002,	LS)	/* LoadQRel      RT<-M[IP+I16] */
-APUOP(M_STOP,		RR,	0x000,	"stop",		_A0(),		00000,	BR)	/* STOP          stop */
-APUOP(M_STOP2,		RR,	0x000,	"stop",		_A1(A_U14),	00000,	BR)	/* STOP          stop */
-APUOP(M_STOPD,		RR,	0x140,	"stopd",	_A3(A_T,A_A,A_B),         00111,	BR)	/* STOPD         stop (with register dependencies) */
-APUOP(M_LNOP,		RR,	0x001,	"lnop",		_A0(),		00000,	LNOP)	/* LNOP          no_operation */
-APUOP(M_SYNC,		RR,	0x002,	"sync",		_A0(),		00000,	BR)	/* SYNC          flush_pipe */
-APUOP(M_DSYNC,		RR,	0x003,	"dsync",	_A0(),		00000,	BR)	/* DSYNC         flush_store_queue */
-APUOP(M_MFSPR,		RR,	0x00c,	"mfspr",	_A2(A_T,A_S),	00002,	SPR)	/* MFSPR         RT<-SA */
-APUOP(M_RDCH,		RR,	0x00d,	"rdch",		_A2(A_T,A_H),	00002,	SPR)	/* ReaDCHannel   RT<-CA:data */
-APUOP(M_RCHCNT,		RR,	0x00f,	"rchcnt",	_A2(A_T,A_H),	00002,	SPR)	/* ReaDCHanCouNT RT<-CA:count */
-APUOP(M_HBRA,		LBT,	0x080,	"hbra",		_A2(A_S11,A_S18),	00000,	LS)	/* HBRA          BTB[B9]<-M[I16] */
-APUOP(M_HBRR,		LBT,	0x090,	"hbrr",		_A2(A_S11,A_R18),	00000,	LS)	/* HBRR          BTB[B9]<-M[IP+I16] */
-APUOP(M_BRZ,		RI16,	0x100,	"brz",		_A2(A_T,A_R18),	00001,	BR)	/* BRZ           IP<-IP+I16_if(RT) */
-APUOP(M_BRNZ,		RI16,	0x108,	"brnz",		_A2(A_T,A_R18),	00001,	BR)	/* BRNZ          IP<-IP+I16_if(RT) */
-APUOP(M_BRHZ,		RI16,	0x110,	"brhz",		_A2(A_T,A_R18),	00001,	BR)	/* BRHZ          IP<-IP+I16_if(RT) */
-APUOP(M_BRHNZ,		RI16,	0x118,	"brhnz",	_A2(A_T,A_R18),	00001,	BR)	/* BRHNZ         IP<-IP+I16_if(RT) */
-APUOP(M_STQA,		RI16,	0x104,	"stqa",		_A2(A_T,A_S18),	00001,	LS)	/* SToreQAbs     M[I16]<-RT */
-APUOP(M_STQR,		RI16,	0x11C,	"stqr",		_A2(A_T,A_R18),	00001,	LS)	/* SToreQRel     M[IP+I16]<-RT */
-APUOP(M_MTSPR,		RR,	0x10c,	"mtspr",	_A2(A_S,A_T),	00001,	SPR)	/* MTSPR         SA<-RT */
-APUOP(M_WRCH,		RR,	0x10d,	"wrch",		_A2(A_H,A_T),	00001,	SPR)	/* ChanWRite     CA<-RT */
-APUOP(M_LQD,		RI10,	0x1a0,	"lqd",		_A4(A_T,A_S14,A_P,A_A),	00012,	LS)	/* LoadQDisp     RT<-M[Ra+I10] */
-APUOP(M_BI,		RR,	0x1a8,	"bi",		_A1(A_A),		00010,	BR)	/* BI            IP<-RA */
-APUOP(M_BISL,		RR,	0x1a9,	"bisl",		_A2(A_T,A_A),	00012,	BR)	/* BISL          RT,IP<-IP,RA */
-APUOP(M_IRET,  		RR,	0x1aa,	"iret",	        _A1(A_A), 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOP(M_IRET2, 		RR,	0x1aa,	"iret",	        _A0(),	 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOP(M_BISLED,		RR,	0x1ab,	"bisled",	_A2(A_T,A_A),	00012,	BR)	/* BISLED        RT,IP<-IP,RA_if(ext) */
-APUOP(M_HBR,		LBTI,	0x1ac,	"hbr",		_A2(A_S11I,A_A),	00010,	LS)	/* HBR           BTB[B9]<-M[Ra] */
-APUOP(M_FREST,		RR,	0x1b8,	"frest",	_A2(A_T,A_A),	00012,	SHUF)	/* FREST         RT<-recip(RA) */
-APUOP(M_FRSQEST,	RR,	0x1b9,	"frsqest",	_A2(A_T,A_A),	00012,	SHUF)	/* FRSQEST       RT<-rsqrt(RA) */
-APUOP(M_FSM,		RR,	0x1b4,	"fsm",		_A2(A_T,A_A),	00012,	SHUF)	/* FormSelMask%  RT<-expand(Ra) */
-APUOP(M_FSMH,		RR,	0x1b5,	"fsmh",		_A2(A_T,A_A),	00012,	SHUF)	/* FormSelMask%  RT<-expand(Ra) */
-APUOP(M_FSMB,		RR,	0x1b6,	"fsmb",		_A2(A_T,A_A),	00012,	SHUF)	/* FormSelMask%  RT<-expand(Ra) */
-APUOP(M_GB,		RR,	0x1b0,	"gb",		_A2(A_T,A_A),	00012,	SHUF)	/* GatherBits%   RT<-gather(RA) */
-APUOP(M_GBH,		RR,	0x1b1,	"gbh",		_A2(A_T,A_A),	00012,	SHUF)	/* GatherBits%   RT<-gather(RA) */
-APUOP(M_GBB,		RR,	0x1b2,	"gbb",		_A2(A_T,A_A),	00012,	SHUF)	/* GatherBits%   RT<-gather(RA) */
-APUOP(M_CBD,		RI7,	0x1f4,	"cbd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
-APUOP(M_CHD,		RI7,	0x1f5,	"chd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
-APUOP(M_CWD,		RI7,	0x1f6,	"cwd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
-APUOP(M_CDD,		RI7,	0x1f7,	"cdd",		_A4(A_T,A_U7,A_P,A_A),	00012,	SHUF)	/* genCtl%%insD  RT<-sta(Ra+I4,siz) */
-APUOP(M_ROTQBII,	RI7,	0x1f8,	"rotqbii",	_A3(A_T,A_A,A_U3),	00012,	SHUF)	/* ROTQBII       RT<-RA<<<I7 */
-APUOP(M_ROTQBYI,	RI7,	0x1fc,	"rotqbyi",	_A3(A_T,A_A,A_S7N),	00012,	SHUF)	/* ROTQBYI       RT<-RA<<<(I7*8) */
-APUOP(M_ROTQMBII,	RI7,	0x1f9,	"rotqmbii",	_A3(A_T,A_A,A_S3),	00012,	SHUF)	/* ROTQMBII      RT<-RA<<I7 */
-APUOP(M_ROTQMBYI,	RI7,	0x1fd,	"rotqmbyi",	_A3(A_T,A_A,A_S6),	00012,	SHUF)	/* ROTQMBYI      RT<-RA<<I7 */
-APUOP(M_SHLQBII,	RI7,	0x1fb,	"shlqbii",	_A3(A_T,A_A,A_U3),	00012,	SHUF)	/* SHLQBII       RT<-RA<<I7 */
-APUOP(M_SHLQBYI,	RI7,	0x1ff,	"shlqbyi",	_A3(A_T,A_A,A_U5),	00012,	SHUF)	/* SHLQBYI       RT<-RA<<I7 */
-APUOP(M_STQD,		RI10,	0x120,	"stqd",		_A4(A_T,A_S14,A_P,A_A),	00011,	LS)	/* SToreQDisp    M[Ra+I10]<-RT */
-APUOP(M_BIHNZ,		RR,	0x12b,	"bihnz",	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
-APUOP(M_BIHZ,		RR,	0x12a,	"bihz",		_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOP(M_BINZ,		RR,	0x129,	"binz",		_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
-APUOP(M_BIZ,		RR,	0x128,	"biz",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOP(M_CBX,		RR,	0x1d4,	"cbx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
-APUOP(M_CHX,		RR,	0x1d5,	"chx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
-APUOP(M_CWX,		RR,	0x1d6,	"cwx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
-APUOP(M_CDX,		RR,	0x1d7,	"cdx",		_A3(A_T,A_A,A_B),		00112,	SHUF)	/* genCtl%%insX  RT<-sta(Ra+Rb,siz) */
-APUOP(M_LQX,		RR,	0x1c4,	"lqx",		_A3(A_T,A_A,A_B),		00112,	LS)	/* LoadQindeX    RT<-M[Ra+Rb] */
-APUOP(M_ROTQBI,		RR,	0x1d8,	"rotqbi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* ROTQBI        RT<-RA<<<Rb */
-APUOP(M_ROTQMBI,	RR,	0x1d9,	"rotqmbi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* ROTQMBI       RT<-RA<<Rb */
-APUOP(M_SHLQBI,		RR,	0x1db,	"shlqbi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* SHLQBI        RT<-RA<<Rb */
-APUOP(M_ROTQBY,		RR,	0x1dc,	"rotqby",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQBY        RT<-RA<<<(Rb*8) */
-APUOP(M_ROTQMBY,	RR,	0x1dd,	"rotqmby",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQMBY       RT<-RA<<Rb */
-APUOP(M_SHLQBY,		RR,	0x1df,	"shlqby",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* SHLQBY        RT<-RA<<Rb */
-APUOP(M_ROTQBYBI,	RR,	0x1cc,	"rotqbybi",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQBYBI      RT<-RA<<Rb */
-APUOP(M_ROTQMBYBI,	RR,	0x1cd,	"rotqmbybi",	_A3(A_T,A_A,A_B),		00112,		SHUF)	/* ROTQMBYBI     RT<-RA<<Rb */
-APUOP(M_SHLQBYBI,	RR,	0x1cf,	"shlqbybi",	_A3(A_T,A_A,A_B),		00112,	SHUF)	/* SHLQBYBI      RT<-RA<<Rb */
-APUOP(M_STQX,		RR,	0x144,	"stqx",		_A3(A_T,A_A,A_B),		00111,	LS)	/* SToreQindeX   M[Ra+Rb]<-RT */
-APUOP(M_SHUFB,		RRR,	0x580,	"shufb",	_A4(A_C,A_A,A_B,A_T),	02111,	SHUF)	/* SHUFfleBytes  RC<-f(RA,RB,RT) */
-APUOP(M_IL,		RI16,	0x204,	"il",		_A2(A_T,A_S16),	00002,	FX2)	/* ImmLoad       RT<-sxt(I16) */
-APUOP(M_ILH,		RI16,	0x20c,	"ilh",		_A2(A_T,A_X16),	00002,	FX2)	/* ImmLoadH      RT<-I16 */
-APUOP(M_ILHU,		RI16,	0x208,	"ilhu",		_A2(A_T,A_X16),	00002,	FX2)	/* ImmLoadHUpper RT<-I16<<16 */
-APUOP(M_ILA,		RI18,	0x210,	"ila",		_A2(A_T,A_U18),	00002,	FX2)	/* ImmLoadAddr   RT<-zxt(I18) */
-APUOP(M_NOP,		RR,	0x201,	"nop",		_A1(A_T),		00000,	NOP)	/* XNOP          no_operation */
-APUOP(M_NOP2,		RR,	0x201,	"nop",		_A0(),		00000,	NOP)	/* XNOP          no_operation */
-APUOP(M_IOHL,		RI16,	0x304,	"iohl",		_A2(A_T,A_X16),	00003,	FX2)	/* AddImmeXt     RT<-RT+sxt(I16) */
-APUOP(M_ANDBI,		RI10,	0x0b0,	"andbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* AND%I         RT<-RA&I10 */
-APUOP(M_ANDHI,		RI10,	0x0a8,	"andhi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* AND%I         RT<-RA&I10 */
-APUOP(M_ANDI,		RI10,	0x0a0,	"andi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* AND%I         RT<-RA&I10 */
-APUOP(M_ORBI,		RI10,	0x030,	"orbi",		_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
-APUOP(M_ORHI,		RI10,	0x028,	"orhi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
-APUOP(M_ORI,		RI10,	0x020,	"ori",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
-APUOP(M_ORX,		RR,	0x1f0,	"orx",		_A2(A_T,A_A),		00012,	BR)	/* ORX           RT<-RA.w0|RA.w1|RA.w2|RA.w3 */
-APUOP(M_XORBI,		RI10,	0x230,	"xorbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* XOR%I         RT<-RA^I10 */
-APUOP(M_XORHI,		RI10,	0x228,	"xorhi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* XOR%I         RT<-RA^I10 */
-APUOP(M_XORI,		RI10,	0x220,	"xori",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* XOR%I         RT<-RA^I10 */
-APUOP(M_AHI,		RI10,	0x0e8,	"ahi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* Add%Immed     RT<-RA+I10 */
-APUOP(M_AI,		RI10,	0x0e0,	"ai",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* Add%Immed     RT<-RA+I10 */
-APUOP(M_SFHI,		RI10,	0x068,	"sfhi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* SubFrom%Imm   RT<-I10-RA */
-APUOP(M_SFI,		RI10,	0x060,	"sfi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* SubFrom%Imm   RT<-I10-RA */
-APUOP(M_CGTBI,		RI10,	0x270,	"cgtbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* CGT%I         RT<-(RA>I10) */
-APUOP(M_CGTHI,		RI10,	0x268,	"cgthi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CGT%I         RT<-(RA>I10) */
-APUOP(M_CGTI,		RI10,	0x260,	"cgti",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CGT%I         RT<-(RA>I10) */
-APUOP(M_CLGTBI,		RI10,	0x2f0,	"clgtbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* CLGT%I        RT<-(RA>I10) */
-APUOP(M_CLGTHI,		RI10,	0x2e8,	"clgthi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CLGT%I        RT<-(RA>I10) */
-APUOP(M_CLGTI,		RI10,	0x2e0,	"clgti",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CLGT%I        RT<-(RA>I10) */
-APUOP(M_CEQBI,		RI10,	0x3f0,	"ceqbi",	_A3(A_T,A_A,A_S10B),	00012,	FX2)	/* CEQ%I         RT<-(RA=I10) */
-APUOP(M_CEQHI,		RI10,	0x3e8,	"ceqhi",	_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CEQ%I         RT<-(RA=I10) */
-APUOP(M_CEQI,		RI10,	0x3e0,	"ceqi",		_A3(A_T,A_A,A_S10),	00012,	FX2)	/* CEQ%I         RT<-(RA=I10) */
-APUOP(M_HGTI,		RI10,	0x278,	"hgti",		_A3(A_T,A_A,A_S10),	00010,	FX2)	/* HaltGTI       halt_if(RA>I10) */
-APUOP(M_HGTI2,		RI10,	0x278,	"hgti",		_A2(A_A,A_S10),	00010,	FX2)	/* HaltGTI       halt_if(RA>I10) */
-APUOP(M_HLGTI,		RI10,	0x2f8,	"hlgti",	_A3(A_T,A_A,A_S10),	00010,	FX2)	/* HaltLGTI      halt_if(RA>I10) */
-APUOP(M_HLGTI2,		RI10,	0x2f8,	"hlgti",	_A2(A_A,A_S10),	00010,	FX2)	/* HaltLGTI      halt_if(RA>I10) */
-APUOP(M_HEQI,		RI10,	0x3f8,	"heqi",		_A3(A_T,A_A,A_S10),	00010,	FX2)	/* HaltEQImm     halt_if(RA=I10) */
-APUOP(M_HEQI2,		RI10,	0x3f8,	"heqi",		_A2(A_A,A_S10),	00010,	FX2)	/* HaltEQImm     halt_if(RA=I10) */
-APUOP(M_MPYI,		RI10,	0x3a0,	"mpyi",		_A3(A_T,A_A,A_S10),	00012,	FP7)	/* MPYI          RT<-RA*I10 */
-APUOP(M_MPYUI,		RI10,	0x3a8,	"mpyui",	_A3(A_T,A_A,A_S10),	00012,	FP7)	/* MPYUI         RT<-RA*I10 */
-APUOP(M_CFLTS,		RI8,	0x3b0,	"cflts",	_A3(A_T,A_A,A_U7A),	00012,	FP7)	/* CFLTS         RT<-int(RA,I8) */
-APUOP(M_CFLTU,		RI8,	0x3b2,	"cfltu",	_A3(A_T,A_A,A_U7A),	00012,	FP7)	/* CFLTU         RT<-int(RA,I8) */
-APUOP(M_CSFLT,		RI8,	0x3b4,	"csflt",	_A3(A_T,A_A,A_U7B),	00012,	FP7)	/* CSFLT         RT<-flt(RA,I8) */
-APUOP(M_CUFLT,		RI8,	0x3b6,	"cuflt",	_A3(A_T,A_A,A_U7B),	00012,	FP7)	/* CUFLT         RT<-flt(RA,I8) */
-APUOP(M_FESD,		RR,	0x3b8,	"fesd",		_A2(A_T,A_A),	00012,	FPD)	/* FESD          RT<-double(RA) */
-APUOP(M_FRDS,		RR,	0x3b9,	"frds",		_A2(A_T,A_A),	00012,	FPD)	/* FRDS          RT<-single(RA) */
-APUOP(M_FSCRRD,		RR,	0x398,	"fscrrd",	_A1(A_T),		00002,	FPD)	/* FSCRRD        RT<-FP_status */
-APUOP(M_FSCRWR,		RR,	0x3ba,	"fscrwr",	_A2(A_T,A_A),	00010,	FP7)	/* FSCRWR        FP_status<-RA */
-APUOP(M_FSCRWR2,	RR,	0x3ba,	"fscrwr",	_A1(A_A),		00010,	FP7)	/* FSCRWR        FP_status<-RA */
-APUOP(M_CLZ,		RR,	0x2a5,	"clz",		_A2(A_T,A_A),	00012,	FX2)	/* CLZ           RT<-clz(RA) */
-APUOP(M_CNTB,		RR,	0x2b4,	"cntb",		_A2(A_T,A_A),	00012,	FXB)	/* CNT           RT<-pop(RA) */
-APUOP(M_XSBH,		RR,	0x2b6,	"xsbh",		_A2(A_T,A_A),	00012,	FX2)	/* eXtSignBtoH   RT<-sign_ext(RA) */
-APUOP(M_XSHW,		RR,	0x2ae,	"xshw",		_A2(A_T,A_A),	00012,	FX2)	/* eXtSignHtoW   RT<-sign_ext(RA) */
-APUOP(M_XSWD,		RR,	0x2a6,	"xswd",		_A2(A_T,A_A),	00012,	FX2)	/* eXtSignWtoD   RT<-sign_ext(RA) */
-APUOP(M_ROTI,		RI7,	0x078,	"roti",		_A3(A_T,A_A,A_S7N),	00012,	FX3)	/* ROT%I         RT<-RA<<<I7 */
-APUOP(M_ROTMI,		RI7,	0x079,	"rotmi",	_A3(A_T,A_A,A_S7),	00012,	FX3)	/* ROT%MI        RT<-RA<<I7 */
-APUOP(M_ROTMAI,		RI7,	0x07a,	"rotmai",	_A3(A_T,A_A,A_S7),	00012,	FX3)	/* ROTMA%I       RT<-RA<<I7 */
-APUOP(M_SHLI,		RI7,	0x07b,	"shli",		_A3(A_T,A_A,A_U6),	00012,	FX3)	/* SHL%I         RT<-RA<<I7 */
-APUOP(M_ROTHI,		RI7,	0x07c,	"rothi",	_A3(A_T,A_A,A_S7N),	00012,	FX3)	/* ROT%I         RT<-RA<<<I7 */
-APUOP(M_ROTHMI,		RI7,	0x07d,	"rothmi",	_A3(A_T,A_A,A_S6),	00012,	FX3)	/* ROT%MI        RT<-RA<<I7 */
-APUOP(M_ROTMAHI,	RI7,	0x07e,	"rotmahi",	_A3(A_T,A_A,A_S6),	00012,	FX3)	/* ROTMA%I       RT<-RA<<I7 */
-APUOP(M_SHLHI,		RI7,	0x07f,	"shlhi",	_A3(A_T,A_A,A_U5),	00012,	FX3)	/* SHL%I         RT<-RA<<I7 */
-APUOP(M_A,		RR,	0x0c0,	"a",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* Add%          RT<-RA+RB */
-APUOP(M_AH,		RR,	0x0c8,	"ah",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* Add%          RT<-RA+RB */
-APUOP(M_SF,		RR,	0x040,	"sf",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* SubFrom%      RT<-RB-RA */
-APUOP(M_SFH,		RR,	0x048,	"sfh",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* SubFrom%      RT<-RB-RA */
-APUOP(M_CGT,		RR,	0x240,	"cgt",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CGT%          RT<-(RA>RB) */
-APUOP(M_CGTB,		RR,	0x250,	"cgtb",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CGT%          RT<-(RA>RB) */
-APUOP(M_CGTH,		RR,	0x248,	"cgth",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CGT%          RT<-(RA>RB) */
-APUOP(M_CLGT,		RR,	0x2c0,	"clgt",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CLGT%         RT<-(RA>RB) */
-APUOP(M_CLGTB,		RR,	0x2d0,	"clgtb",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* CLGT%         RT<-(RA>RB) */
-APUOP(M_CLGTH,		RR,	0x2c8,	"clgth",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* CLGT%         RT<-(RA>RB) */
-APUOP(M_CEQ,		RR,	0x3c0,	"ceq",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CEQ%          RT<-(RA=RB) */
-APUOP(M_CEQB,		RR,	0x3d0,	"ceqb",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CEQ%          RT<-(RA=RB) */
-APUOP(M_CEQH,		RR,	0x3c8,	"ceqh",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* CEQ%          RT<-(RA=RB) */
-APUOP(M_HGT,		RR,	0x258,	"hgt",		_A3(A_T,A_A,A_B),		00110,	FX2)	/* HaltGT        halt_if(RA>RB) */
-APUOP(M_HGT2,		RR,	0x258,	"hgt",		_A2(A_A,A_B),	00110,	FX2)	/* HaltGT        halt_if(RA>RB) */
-APUOP(M_HLGT,		RR,	0x2d8,	"hlgt",		_A3(A_T,A_A,A_B),		00110,	FX2)	/* HaltLGT       halt_if(RA>RB) */
-APUOP(M_HLGT2,		RR,	0x2d8,	"hlgt",		_A2(A_A,A_B),	00110,	FX2)	/* HaltLGT       halt_if(RA>RB) */
-APUOP(M_HEQ,		RR,	0x3d8,	"heq",		_A3(A_T,A_A,A_B),		00110,	FX2)	/* HaltEQ        halt_if(RA=RB) */
-APUOP(M_HEQ2,		RR,	0x3d8,	"heq",		_A2(A_A,A_B),	00110,	FX2)	/* HaltEQ        halt_if(RA=RB) */
-APUOP(M_FCEQ,		RR,	0x3c2,	"fceq",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCEQ          RT<-(RA=RB) */
-APUOP(M_FCMEQ,		RR,	0x3ca,	"fcmeq",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCMEQ         RT<-(|RA|=|RB|) */
-APUOP(M_FCGT,		RR,	0x2c2,	"fcgt",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCGT          RT<-(RA<RB) */
-APUOP(M_FCMGT,		RR,	0x2ca,	"fcmgt",	_A3(A_T,A_A,A_B),		00112,	FX2)	/* FCMGT         RT<-(|RA|<|RB|) */
-APUOP(M_AND,		RR,	0x0c1,	"and",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* AND           RT<-RA&RB */
-APUOP(M_NAND,		RR,	0x0c9,	"nand",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* NAND          RT<-!(RA&RB) */
-APUOP(M_OR,		RR,	0x041,	"or",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* OR            RT<-RA|RB */
-APUOP(M_NOR,		RR,	0x049,	"nor",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* NOR           RT<-!(RA&RB) */
-APUOP(M_XOR,		RR,	0x241,	"xor",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* XOR           RT<-RA^RB */
-APUOP(M_EQV,		RR,	0x249,	"eqv",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* EQuiValent    RT<-!(RA^RB) */
-APUOP(M_ANDC,		RR,	0x2c1,	"andc",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* ANDComplement RT<-RA&!RB */
-APUOP(M_ORC,		RR,	0x2c9,	"orc",		_A3(A_T,A_A,A_B),		00112,	FX2)	/* ORComplement  RT<-RA|!RB */
-APUOP(M_ABSDB,		RR,	0x053,	"absdb",	_A3(A_T,A_A,A_B),		00112,	FXB)	/* ABSoluteDiff  RT<-|RA-RB| */
-APUOP(M_AVGB,		RR,	0x0d3,	"avgb",		_A3(A_T,A_A,A_B),		00112,	FXB)	/* AVG%          RT<-(RA+RB+1)/2 */
-APUOP(M_SUMB,		RR,	0x253,	"sumb",		_A3(A_T,A_A,A_B),		00112,	FXB)	/* SUM%          RT<-f(RA,RB) */
-APUOP(M_DFA,		RR,	0x2cc,	"dfa",		_A3(A_T,A_A,A_B),		00112,	FPD)	/* DFAdd         RT<-RA+RB */
-APUOP(M_DFM,		RR,	0x2ce,	"dfm",		_A3(A_T,A_A,A_B),		00112,	FPD)	/* DFMul         RT<-RA*RB */
-APUOP(M_DFS,		RR,	0x2cd,	"dfs",		_A3(A_T,A_A,A_B),		00112,	FPD)	/* DFSub         RT<-RA-RB */
-APUOP(M_FA,		RR,	0x2c4,	"fa",		_A3(A_T,A_A,A_B),		00112,	FP6)	/* FAdd          RT<-RA+RB */
-APUOP(M_FM,		RR,	0x2c6,	"fm",		_A3(A_T,A_A,A_B),		00112,	FP6)	/* FMul          RT<-RA*RB */
-APUOP(M_FS,		RR,	0x2c5,	"fs",		_A3(A_T,A_A,A_B),		00112,	FP6)	/* FSub          RT<-RA-RB */
-APUOP(M_MPY,		RR,	0x3c4,	"mpy",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPY           RT<-RA*RB */
-APUOP(M_MPYH,		RR,	0x3c5,	"mpyh",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYH          RT<-(RAh*RB)<<16 */
-APUOP(M_MPYHH,		RR,	0x3c6,	"mpyhh",	_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYHH         RT<-RAh*RBh */
-APUOP(M_MPYHHU,		RR,	0x3ce,	"mpyhhu",	_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYHHU        RT<-RAh*RBh */
-APUOP(M_MPYS,		RR,	0x3c7,	"mpys",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYS          RT<-(RA*RB)>>16 */
-APUOP(M_MPYU,		RR,	0x3cc,	"mpyu",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* MPYU          RT<-RA*RB */
-APUOP(M_FI,		RR,	0x3d4,	"fi",		_A3(A_T,A_A,A_B),		00112,	FP7)	/* FInterpolate  RT<-f(RA,RB) */
-APUOP(M_ROT,		RR,	0x058,	"rot",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%          RT<-RA<<<RB */
-APUOP(M_ROTM,		RR,	0x059,	"rotm",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%M         RT<-RA<<Rb */
-APUOP(M_ROTMA,		RR,	0x05a,	"rotma",	_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROTMA%        RT<-RA<<Rb */
-APUOP(M_SHL,		RR,	0x05b,	"shl",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* SHL%          RT<-RA<<Rb */
-APUOP(M_ROTH,		RR,	0x05c,	"roth",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%          RT<-RA<<<RB */
-APUOP(M_ROTHM,		RR,	0x05d,	"rothm",	_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROT%M         RT<-RA<<Rb */
-APUOP(M_ROTMAH,		RR,	0x05e,	"rotmah",	_A3(A_T,A_A,A_B),		00112,	FX3)	/* ROTMA%        RT<-RA<<Rb */
-APUOP(M_SHLH,		RR,	0x05f,	"shlh",		_A3(A_T,A_A,A_B),		00112,	FX3)	/* SHL%          RT<-RA<<Rb */
-APUOP(M_MPYHHA,		RR,	0x346,	"mpyhha",	_A3(A_T,A_A,A_B),		00113,	FP7)	/* MPYHHA        RT<-RAh*RBh+RT */
-APUOP(M_MPYHHAU,	RR,	0x34e,	"mpyhhau",	_A3(A_T,A_A,A_B),		00113,	FP7)	/* MPYHHAU       RT<-RAh*RBh+RT */
-APUOP(M_DFMA,		RR,	0x35c,	"dfma",		_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFMAdd        RT<-RT+RA*RB */
-APUOP(M_DFMS,		RR,	0x35d,	"dfms",		_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFMSub        RT<-RA*RB-RT */
-APUOP(M_DFNMS,		RR,	0x35e,	"dfnms",	_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFNMSub       RT<-RT-RA*RB */
-APUOP(M_DFNMA,		RR,	0x35f,	"dfnma",	_A3(A_T,A_A,A_B),		00113,	FPD)	/* DFNMAdd       RT<-(-RT)-RA*RB */
-APUOP(M_FMA,		RRR,	0x700,	"fma",		_A4(A_C,A_A,A_B,A_T),	02111,	FP6)	/* FMAdd         RC<-RT+RA*RB */
-APUOP(M_FMS,		RRR,	0x780,	"fms",		_A4(A_C,A_A,A_B,A_T),	02111,	FP6)	/* FMSub         RC<-RA*RB-RT */
-APUOP(M_FNMS,		RRR,	0x680,	"fnms",		_A4(A_C,A_A,A_B,A_T),	02111,	FP6)	/* FNMSub        RC<-RT-RA*RB */
-APUOP(M_MPYA,		RRR,	0x600,	"mpya",		_A4(A_C,A_A,A_B,A_T),	02111,	FP7)	/* MPYA          RC<-RA*RB+RT */
-APUOP(M_SELB,		RRR,	0x400,	"selb",		_A4(A_C,A_A,A_B,A_T),	02111,	FX2)	/* SELectBits    RC<-RA&RT|RB&!RT */
-/* for system function call, this uses op-code of mtspr */
-APUOP(M_SYSCALL,	RI7,    0x10c,	"syscall",      _A3(A_T,A_A,A_S7N),	00002,	SPR)        /* System Call */
-/*
-pseudo instruction:
-system call
-value of I9	operation
-0	halt
-1		rt[0] = open(MEM[ra[0]],	ra[1])
-2		rt[0] = close(ra[0])
-3		rt[0] = read(ra[0],	MEM[ra[1]],	ra[2])
-4		rt[0] = write(ra[0],	MEM[ra[1]],	ra[2])
-5		printf(MEM[ra[0]],	ra[1],	ra[2],	ra[3])
-42		rt[0] = clock()
-52		rt[0] = lseek(ra0,	ra1,	ra2)
-
-*/
-
-
-/* new multiprecision add/sub */
-APUOP(M_ADDX,		RR,	0x340,	"addx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* Add_eXtended  RT<-RA+RB+RT */
-APUOP(M_CG,		RR,	0x0c2,	"cg",		_A3(A_T,A_A,A_B),		00112,		FX2)	/* CarryGenerate RT<-cout(RA+RB) */
-APUOP(M_CGX,		RR,	0x342,	"cgx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* CarryGen_eXtd RT<-cout(RA+RB+RT) */
-APUOP(M_SFX,		RR,	0x341,	"sfx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* Add_eXtended  RT<-RA+RB+RT */
-APUOP(M_BG,		RR,	0x042,	"bg",		_A3(A_T,A_A,A_B),		00112,		FX2)	/* CarryGenerate RT<-cout(RA+RB) */
-APUOP(M_BGX,		RR,	0x343,	"bgx",		_A3(A_T,A_A,A_B),		00113,		FX2)	/* CarryGen_eXtd RT<-cout(RA+RB+RT) */
-
-/*
-
-The following ops are a subset of above except with feature bits set.
-Feature bits are bits 11-17 of the instruction:
-
-  11 - C & P feature bit
-  12 - disable interrupts
-  13 - enable interrupts
-
-*/
-APUOPFB(M_BID,		RR,	0x1a8,	0x20,	"bid",		_A1(A_A),		00010,	BR)	/* BI            IP<-RA */
-APUOPFB(M_BIE,		RR,	0x1a8,	0x10,	"bie",		_A1(A_A),		00010,	BR)	/* BI            IP<-RA */
-APUOPFB(M_BISLD,	RR,	0x1a9,	0x20,	"bisld",	_A2(A_T,A_A),	00012,	BR)	/* BISL          RT,IP<-IP,RA */
-APUOPFB(M_BISLE,	RR,	0x1a9,	0x10,	"bisle",	_A2(A_T,A_A),	00012,	BR)	/* BISL          RT,IP<-IP,RA */
-APUOPFB(M_IRETD,  	RR,	0x1aa,	0x20,	"iretd",	_A1(A_A), 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOPFB(M_IRETD2,  	RR,	0x1aa,	0x20,	"iretd",	_A0(),	 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOPFB(M_IRETE,  	RR,	0x1aa,	0x10,	"irete",	_A1(A_A), 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOPFB(M_IRETE2,  	RR,	0x1aa,	0x10,	"irete",	_A0(),	 	00010,	BR)	/* IRET          IP<-SRR0 */
-APUOPFB(M_BISLEDD,	RR,	0x1ab,	0x20,	"bisledd",	_A2(A_T,A_A),	00012,	BR)	/* BISLED        RT,IP<-IP,RA_if(ext) */
-APUOPFB(M_BISLEDE,	RR,	0x1ab,	0x10,	"bislede",	_A2(A_T,A_A),	00012,	BR)	/* BISLED        RT,IP<-IP,RA_if(ext) */
-APUOPFB(M_BIHNZD,	RR,	0x12b,	0x20,	"bihnzd",	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
-APUOPFB(M_BIHNZE,	RR,	0x12b,	0x10,	"bihnze",	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
-APUOPFB(M_BIHZD,	RR,	0x12a,	0x20,	"bihzd",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOPFB(M_BIHZE,	RR,	0x12a,	0x10,	"bihze",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOPFB(M_BINZD,	RR,	0x129,	0x20,	"binzd",	_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
-APUOPFB(M_BINZE,	RR,	0x129,	0x10,	"binze",	_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
-APUOPFB(M_BIZD,		RR,	0x128,	0x20,	"bizd",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOPFB(M_BIZE,		RR,	0x128,	0x10,	"bize",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOPFB(M_SYNCC,	RR,	0x002,	0x40,	"syncc",	_A0(),		00000,	BR)	/* SYNCC          flush_pipe */
-APUOPFB(M_HBRP,		LBTI,	0x1ac,	0x40,	"hbrp",		_A0(),	        00010,	LS)	/* HBR           BTB[B9]<-M[Ra] */
-
-/* Synonyms required by the AS manual. */
-APUOP(M_LR,		RI10,	0x020,	"lr",		_A2(A_T,A_A),	00012,	FX2)	/* OR%I          RT<-RA|I10 */
-APUOP(M_BIHT,		RR,	0x12b,	"biht", 	_A2(A_T,A_A),	00011,	BR)	/* BIHNZ         IP<-RA_if(RT) */
-APUOP(M_BIHF,		RR,	0x12a,	"bihf",		_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOP(M_BIT,		RR,	0x129,	"bit",		_A2(A_T,A_A),	00011,	BR)	/* BINZ          IP<-RA_if(RT) */
-APUOP(M_BIF,		RR,	0x128,	"bif",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOPFB(M_BIHTD,	RR,	0x12b,	0x20,	"bihtd",	_A2(A_T,A_A),	00011,	BR)	/* BIHNF         IP<-RA_if(RT) */
-APUOPFB(M_BIHTE,	RR,	0x12b,	0x10,	"bihte",	_A2(A_T,A_A),	00011,	BR)	/* BIHNF         IP<-RA_if(RT) */
-APUOPFB(M_BIHFD,	RR,	0x12a,	0x20,	"bihfd",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOPFB(M_BIHFE,	RR,	0x12a,	0x10,	"bihfe",	_A2(A_T,A_A),	00011,	BR)	/* BIHZ          IP<-RA_if(RT) */
-APUOPFB(M_BITD, 	RR,	0x129,	0x20,	"bitd", 	_A2(A_T,A_A),	00011,	BR)	/* BINF          IP<-RA_if(RT) */
-APUOPFB(M_BITE, 	RR,	0x129,	0x10,	"bite", 	_A2(A_T,A_A),	00011,	BR)	/* BINF          IP<-RA_if(RT) */
-APUOPFB(M_BIFD,		RR,	0x128,	0x20,	"bifd",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-APUOPFB(M_BIFE,		RR,	0x128,	0x10,	"bife",		_A2(A_T,A_A),	00011,	BR)	/* BIZ           IP<-RA_if(RT) */
-
-#undef _A0
-#undef _A1
-#undef _A2
-#undef _A3
-#undef _A4
diff --git a/arch/powerpc/xmon/spu-opc.c b/arch/powerpc/xmon/spu-opc.c
deleted file mode 100644
index 6d8197cc540b..000000000000
--- a/arch/powerpc/xmon/spu-opc.c
+++ /dev/null
@@ -1,34 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* SPU opcode list
-
-   Copyright 2006 Free Software Foundation, Inc.
-
-   This file is part of GDB, GAS, and the GNU binutils.
-
- */
-
-#include <linux/kernel.h>
-#include <linux/bug.h>
-#include "spu.h"
-
-/* This file holds the Spu opcode table */
-
-
-/*
-   Example contents of spu-insn.h
-      id_tag	mode	mode	type	opcode	mnemonic	asmtype	    dependency		FPU	L/S?	branch?	instruction   
-                QUAD	WORD                                               (0,RC,RB,RA,RT)    latency  			              		
-   APUOP(M_LQD,	1,	0,	RI9,	0x1f8,	"lqd",		ASM_RI9IDX,	00012,		FXU,	1,	0)	Load Quadword d-form 
- */
-
-const struct spu_opcode spu_opcodes[] = {
-#define APUOP(TAG,MACFORMAT,OPCODE,MNEMONIC,ASMFORMAT,DEP,PIPE) \
-	{ MACFORMAT, OPCODE, MNEMONIC, ASMFORMAT },
-#define APUOPFB(TAG,MACFORMAT,OPCODE,FB,MNEMONIC,ASMFORMAT,DEP,PIPE) \
-	{ MACFORMAT, OPCODE, MNEMONIC, ASMFORMAT },
-#include "spu-insns.h"
-#undef APUOP
-#undef APUOPFB
-};
-
-const int spu_num_opcodes = ARRAY_SIZE(spu_opcodes);
diff --git a/arch/powerpc/xmon/spu.h b/arch/powerpc/xmon/spu.h
deleted file mode 100644
index 2d13b1a5fa87..000000000000
--- a/arch/powerpc/xmon/spu.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* SPU ELF support for BFD.
-
-   Copyright 2006 Free Software Foundation, Inc.
-
-   This file is part of GDB, GAS, and the GNU binutils.
-
- */
-
-
-/* These two enums are from rel_apu/common/spu_asm_format.h */
-/* definition of instruction format */
-typedef enum {
-  RRR,
-  RI18,
-  RI16,
-  RI10,
-  RI8,
-  RI7,
-  RR,
-  LBT,
-  LBTI,
-  IDATA,
-  UNKNOWN_IFORMAT
-} spu_iformat;
-
-/* These values describe assembly instruction arguments.  They indicate
- * how to encode, range checking and which relocation to use. */
-typedef enum {
-  A_T,  /* register at pos 0 */
-  A_A,  /* register at pos 7 */
-  A_B,  /* register at pos 14 */
-  A_C,  /* register at pos 21 */
-  A_S,  /* special purpose register at pos 7 */
-  A_H,  /* channel register at pos 7 */
-  A_P,  /* parenthesis, this has to separate regs from immediates */
-  A_S3,
-  A_S6,
-  A_S7N,
-  A_S7,
-  A_U7A,
-  A_U7B,
-  A_S10B,
-  A_S10,
-  A_S11,
-  A_S11I,
-  A_S14,
-  A_S16,
-  A_S18,
-  A_R18,
-  A_U3,
-  A_U5,
-  A_U6,
-  A_U7,
-  A_U14,
-  A_X16,
-  A_U18,
-  A_MAX
-} spu_aformat;
-
-enum spu_insns {
-#define APUOP(TAG,MACFORMAT,OPCODE,MNEMONIC,ASMFORMAT,DEP,PIPE) \
-	TAG,
-#define APUOPFB(TAG,MACFORMAT,OPCODE,FB,MNEMONIC,ASMFORMAT,DEP,PIPE) \
-	TAG,
-#include "spu-insns.h"
-#undef APUOP
-#undef APUOPFB
-        M_SPU_MAX
-};
-
-struct spu_opcode
-{
-   spu_iformat insn_type;
-   unsigned int opcode;
-   char *mnemonic;
-   int arg[5];
-};
-
-#define SIGNED_EXTRACT(insn,size,pos) (((int)((insn) << (32-size-pos))) >> (32-size))
-#define UNSIGNED_EXTRACT(insn,size,pos) (((insn) >> pos) & ((1 << size)-1))
-
-#define DECODE_INSN_RT(insn) (insn & 0x7f)
-#define DECODE_INSN_RA(insn) ((insn >> 7) & 0x7f)
-#define DECODE_INSN_RB(insn) ((insn >> 14) & 0x7f)
-#define DECODE_INSN_RC(insn) ((insn >> 21) & 0x7f)
-
-#define DECODE_INSN_I10(insn) SIGNED_EXTRACT(insn,10,14)
-#define DECODE_INSN_U10(insn) UNSIGNED_EXTRACT(insn,10,14)
-
-/* For branching, immediate loads, hbr and  lqa/stqa. */
-#define DECODE_INSN_I16(insn) SIGNED_EXTRACT(insn,16,7)
-#define DECODE_INSN_U16(insn) UNSIGNED_EXTRACT(insn,16,7)
-
-/* for stop */
-#define DECODE_INSN_U14(insn) UNSIGNED_EXTRACT(insn,14,0)
-
-/* For ila */
-#define DECODE_INSN_I18(insn) SIGNED_EXTRACT(insn,18,7)
-#define DECODE_INSN_U18(insn) UNSIGNED_EXTRACT(insn,18,7)
-
-/* For rotate and shift and generate control mask */
-#define DECODE_INSN_I7(insn) SIGNED_EXTRACT(insn,7,14)
-#define DECODE_INSN_U7(insn) UNSIGNED_EXTRACT(insn,7,14)
-
-/* For float <-> int conversion */
-#define DECODE_INSN_I8(insn)  SIGNED_EXTRACT(insn,8,14)
-#define DECODE_INSN_U8(insn) UNSIGNED_EXTRACT(insn,8,14)
-
-/* For hbr  */
-#define DECODE_INSN_I9a(insn) ((SIGNED_EXTRACT(insn,2,23) << 7) | UNSIGNED_EXTRACT(insn,7,0))
-#define DECODE_INSN_I9b(insn) ((SIGNED_EXTRACT(insn,2,14) << 7) | UNSIGNED_EXTRACT(insn,7,0))
-#define DECODE_INSN_U9a(insn) ((UNSIGNED_EXTRACT(insn,2,23) << 7) | UNSIGNED_EXTRACT(insn,7,0))
-#define DECODE_INSN_U9b(insn) ((UNSIGNED_EXTRACT(insn,2,14) << 7) | UNSIGNED_EXTRACT(insn,7,0))
-
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 728d3c257e4a..cb3a3244ae6f 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -41,8 +41,6 @@
 #include <asm/rtas.h>
 #include <asm/sstep.h>
 #include <asm/irq_regs.h>
-#include <asm/spu.h>
-#include <asm/spu_priv1.h>
 #include <asm/setjmp.h>
 #include <asm/reg.h>
 #include <asm/debug.h>
@@ -50,7 +48,7 @@
 #include <asm/xive.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
-#include <asm/code-patching.h>
+#include <asm/text-patching.h>
 #include <asm/sections.h>
 #include <asm/inst.h>
 #include <asm/interrupt.h>
@@ -58,6 +56,7 @@
 #ifdef CONFIG_PPC64
 #include <asm/hvcall.h>
 #include <asm/paca.h>
+#include <asm/lppaca.h>
 #endif
 
 #include "nonstdio.h"
@@ -88,7 +87,7 @@ static unsigned long ndump = 64;
 static unsigned long nidump = 16;
 static unsigned long ncsum = 4096;
 static int termch;
-static char tmpstr[128];
+static char tmpstr[KSYM_NAME_LEN];
 static int tracing_enabled;
 
 static long bus_error_jmp[JMP_BUF_LEN];
@@ -187,8 +186,6 @@ static void xmon_print_symbol(unsigned long address, const char *mid,
 			      const char *after);
 static const char *getvecname(unsigned long vec);
 
-static int do_spu_cmd(void);
-
 #ifdef CONFIG_44x
 static void dump_tlb_44x(void);
 #endif
@@ -271,13 +268,6 @@ Commands:\n\
   P 	list processes/tasks\n\
   r	print registers\n\
   s	single step\n"
-#ifdef CONFIG_SPU_BASE
-"  ss	stop execution on all spus\n\
-  sr	restore execution on stopped spus\n\
-  sf  #	dump spu fields for spu # (in hex)\n\
-  sd  #	dump spu local store for spu # (in hex)\n\
-  sdi #	disassemble spu local store for spu # (in hex)\n"
-#endif
 "  S	print special registers\n\
   Sa    print all SPRs\n\
   Sr #	read SPR #\n\
@@ -642,10 +632,8 @@ static int xmon_core(struct pt_regs *regs, volatile int fromipi)
 			touch_nmi_watchdog();
 		} else {
 			cmd = 1;
-#ifdef CONFIG_SMP
 			if (xmon_batch)
 				cmd = batch_cmds(regs);
-#endif
 			if (!locked_down && cmd)
 				cmd = cmds(regs);
 			if (locked_down || cmd != 0) {
@@ -1084,7 +1072,7 @@ cmds(struct pt_regs *excp)
 				memzcan();
 				break;
 			case 'i':
-				show_mem(0, NULL);
+				show_mem();
 				break;
 			default:
 				termch = cmd;
@@ -1113,8 +1101,6 @@ cmds(struct pt_regs *excp)
 			cacheflush();
 			break;
 		case 's':
-			if (do_spu_cmd() == 0)
-				break;
 			if (do_step(excp))
 				return cmd;
 			break;
@@ -1272,11 +1258,7 @@ static int xmon_batch_next_cpu(void)
 {
 	unsigned long cpu;
 
-	while (!cpumask_empty(&xmon_batch_cpus)) {
-		cpu = cpumask_next_wrap(smp_processor_id(), &xmon_batch_cpus,
-					xmon_batch_start_cpu, true);
-		if (cpu >= nr_cpu_ids)
-			break;
+	for_each_cpu_wrap(cpu, &xmon_batch_cpus, xmon_batch_start_cpu) {
 		if (xmon_batch_start_cpu == -1)
 			xmon_batch_start_cpu = cpu;
 		if (xmon_switch_cpu(cpu))
@@ -1351,7 +1333,7 @@ static int cpu_cmd(void)
 	}
 	termch = cpu;
 
-	if (!scanhex(&cpu)) {
+	if (!scanhex(&cpu) || cpu >= num_possible_cpus()) {
 		/* print cpus waiting or in xmon */
 		printf("cpus stopped:");
 		last_cpu = first_cpu = NR_CPUS;
@@ -1788,7 +1770,7 @@ static void xmon_show_stack(unsigned long sp, unsigned long lr,
 				       sp + STACK_INT_FRAME_REGS);
 				break;
 			}
-			printf("--- Exception: %lx %s at ", regs.trap,
+			printf("---- Exception: %lx %s at ", regs.trap,
 			       getvecname(TRAP(&regs)));
 			pc = regs.nip;
 			lr = regs.link;
@@ -1819,8 +1801,8 @@ static void print_bug_trap(struct pt_regs *regs)
 	const struct bug_entry *bug;
 	unsigned long addr;
 
-	if (regs->msr & MSR_PR)
-		return;		/* not in kernel */
+	if (user_mode(regs))
+		return;
 	addr = regs->nip;	/* address of trap instruction */
 	if (!is_kernel_addr(addr))
 		return;
@@ -2624,9 +2606,9 @@ static void dump_one_paca(int cpu)
 
 	printf("paca for cpu 0x%x @ %px:\n", cpu, p);
 
-	printf(" %-*s = %s\n", 25, "possible", cpu_possible(cpu) ? "yes" : "no");
-	printf(" %-*s = %s\n", 25, "present", cpu_present(cpu) ? "yes" : "no");
-	printf(" %-*s = %s\n", 25, "online", cpu_online(cpu) ? "yes" : "no");
+	printf(" %-*s = %s\n", 25, "possible", str_yes_no(cpu_possible(cpu)));
+	printf(" %-*s = %s\n", 25, "present", str_yes_no(cpu_present(cpu)));
+	printf(" %-*s = %s\n", 25, "online", str_yes_no(cpu_online(cpu)));
 
 #define DUMP(paca, name, format)				\
 	printf(" %-*s = "format"\t(0x%lx)\n", 25, #name, 18, paca->name, \
@@ -2773,7 +2755,7 @@ static void dump_pacas(void)
 
 	termch = c;	/* Put c back, it wasn't 'a' */
 
-	if (scanhex(&num))
+	if (scanhex(&num) && num < num_possible_cpus())
 		dump_one_paca(num);
 	else
 		dump_one_paca(xmon_owner);
@@ -2846,7 +2828,7 @@ static void dump_xives(void)
 
 	termch = c;	/* Put c back, it wasn't 'a' */
 
-	if (scanhex(&num))
+	if (scanhex(&num) && num < num_possible_cpus())
 		dump_one_xive(num);
 	else
 		dump_one_xive(xmon_owner);
@@ -3303,7 +3285,7 @@ static void show_pte(unsigned long addr)
 {
 	unsigned long tskv = 0;
 	struct task_struct *volatile tsk = NULL;
-	struct mm_struct *mm;
+	struct mm_struct *volatile mm;
 	pgd_t *pgdp;
 	p4d_t *p4dp;
 	pud_t *pudp;
@@ -3341,7 +3323,7 @@ static void show_pte(unsigned long addr)
 		return;
 	}
 
-	if (p4d_is_leaf(*p4dp)) {
+	if (p4d_leaf(*p4dp)) {
 		format_pte(p4dp, p4d_val(*p4dp));
 		return;
 	}
@@ -3355,7 +3337,7 @@ static void show_pte(unsigned long addr)
 		return;
 	}
 
-	if (pud_is_leaf(*pudp)) {
+	if (pud_leaf(*pudp)) {
 		format_pte(pudp, pud_val(*pudp));
 		return;
 	}
@@ -3369,19 +3351,22 @@ static void show_pte(unsigned long addr)
 		return;
 	}
 
-	if (pmd_is_leaf(*pmdp)) {
+	if (pmd_leaf(*pmdp)) {
 		format_pte(pmdp, pmd_val(*pmdp));
 		return;
 	}
 	printf("pmdp @ 0x%px = 0x%016lx\n", pmdp, pmd_val(*pmdp));
 
 	ptep = pte_offset_map(pmdp, addr);
-	if (pte_none(*ptep)) {
+	if (!ptep || pte_none(*ptep)) {
+		if (ptep)
+			pte_unmap(ptep);
 		printf("no valid PTE\n");
 		return;
 	}
 
 	format_pte(ptep, pte_val(*ptep));
+	pte_unmap(ptep);
 
 	sync();
 	__delay(200);
@@ -3541,7 +3526,7 @@ scanhex(unsigned long *vp)
 		}
 	} else if (c == '$') {
 		int i;
-		for (i=0; i<63; i++) {
+		for (i = 0; i < (KSYM_NAME_LEN - 1); i++) {
 			c = inchar();
 			if (isspace(c) || c == '\0') {
 				termch = c;
@@ -3660,7 +3645,7 @@ symbol_lookup(void)
 	int type = inchar();
 	unsigned long addr, cpu;
 	void __percpu *ptr = NULL;
-	static char tmp[64];
+	static char tmp[KSYM_NAME_LEN];
 
 	switch (type) {
 	case 'a':
@@ -3669,7 +3654,7 @@ symbol_lookup(void)
 		termch = 0;
 		break;
 	case 's':
-		getstring(tmp, 64);
+		getstring(tmp, KSYM_NAME_LEN);
 		if (setjmp(bus_error_jmp) == 0) {
 			catch_memory_errors = 1;
 			sync();
@@ -3684,7 +3669,7 @@ symbol_lookup(void)
 		termch = 0;
 		break;
 	case 'p':
-		getstring(tmp, 64);
+		getstring(tmp, KSYM_NAME_LEN);
 		if (setjmp(bus_error_jmp) == 0) {
 			catch_memory_errors = 1;
 			sync();
@@ -3825,9 +3810,9 @@ static void dump_tlb_44x(void)
 #ifdef CONFIG_PPC_BOOK3E_64
 static void dump_tlb_book3e(void)
 {
-	u32 mmucfg, pidmask, lpidmask;
+	u32 mmucfg;
 	u64 ramask;
-	int i, tlb, ntlbs, pidsz, lpidsz, rasz, lrat = 0;
+	int i, tlb, ntlbs, pidsz, lpidsz, rasz;
 	int mmu_version;
 	static const char *pgsz_names[] = {
 		"  1K",
@@ -3871,12 +3856,8 @@ static void dump_tlb_book3e(void)
 	pidsz = ((mmucfg >> 6) & 0x1f) + 1;
 	lpidsz = (mmucfg >> 24) & 0xf;
 	rasz = (mmucfg >> 16) & 0x7f;
-	if ((mmu_version > 1) && (mmucfg & 0x10000))
-		lrat = 1;
 	printf("Book3E MMU MAV=%d.0,%d TLBs,%d-bit PID,%d-bit LPID,%d-bit RA\n",
 	       mmu_version, ntlbs, pidsz, lpidsz, rasz);
-	pidmask = (1ul << pidsz) - 1;
-	lpidmask = (1ul << lpidsz) - 1;
 	ramask = (1ull << rasz) - 1;
 
 	for (tlb = 0; tlb < ntlbs; tlb++) {
@@ -3988,7 +3969,7 @@ static void xmon_init(int enable)
 }
 
 #ifdef CONFIG_MAGIC_SYSRQ
-static void sysrq_handle_xmon(int key)
+static void sysrq_handle_xmon(u8 key)
 {
 	if (xmon_is_locked_down()) {
 		clear_all_bpt();
@@ -4109,263 +4090,3 @@ void __init xmon_setup(void)
 	if (xmon_early)
 		debugger(NULL);
 }
-
-#ifdef CONFIG_SPU_BASE
-
-struct spu_info {
-	struct spu *spu;
-	u64 saved_mfc_sr1_RW;
-	u32 saved_spu_runcntl_RW;
-	unsigned long dump_addr;
-	u8 stopped_ok;
-};
-
-#define XMON_NUM_SPUS	16	/* Enough for current hardware */
-
-static struct spu_info spu_info[XMON_NUM_SPUS];
-
-void __init xmon_register_spus(struct list_head *list)
-{
-	struct spu *spu;
-
-	list_for_each_entry(spu, list, full_list) {
-		if (spu->number >= XMON_NUM_SPUS) {
-			WARN_ON(1);
-			continue;
-		}
-
-		spu_info[spu->number].spu = spu;
-		spu_info[spu->number].stopped_ok = 0;
-		spu_info[spu->number].dump_addr = (unsigned long)
-				spu_info[spu->number].spu->local_store;
-	}
-}
-
-static void stop_spus(void)
-{
-	struct spu *spu;
-	volatile int i;
-	u64 tmp;
-
-	for (i = 0; i < XMON_NUM_SPUS; i++) {
-		if (!spu_info[i].spu)
-			continue;
-
-		if (setjmp(bus_error_jmp) == 0) {
-			catch_memory_errors = 1;
-			sync();
-
-			spu = spu_info[i].spu;
-
-			spu_info[i].saved_spu_runcntl_RW =
-				in_be32(&spu->problem->spu_runcntl_RW);
-
-			tmp = spu_mfc_sr1_get(spu);
-			spu_info[i].saved_mfc_sr1_RW = tmp;
-
-			tmp &= ~MFC_STATE1_MASTER_RUN_CONTROL_MASK;
-			spu_mfc_sr1_set(spu, tmp);
-
-			sync();
-			__delay(200);
-
-			spu_info[i].stopped_ok = 1;
-
-			printf("Stopped spu %.2d (was %s)\n", i,
-					spu_info[i].saved_spu_runcntl_RW ?
-					"running" : "stopped");
-		} else {
-			catch_memory_errors = 0;
-			printf("*** Error stopping spu %.2d\n", i);
-		}
-		catch_memory_errors = 0;
-	}
-}
-
-static void restart_spus(void)
-{
-	struct spu *spu;
-	volatile int i;
-
-	for (i = 0; i < XMON_NUM_SPUS; i++) {
-		if (!spu_info[i].spu)
-			continue;
-
-		if (!spu_info[i].stopped_ok) {
-			printf("*** Error, spu %d was not successfully stopped"
-					", not restarting\n", i);
-			continue;
-		}
-
-		if (setjmp(bus_error_jmp) == 0) {
-			catch_memory_errors = 1;
-			sync();
-
-			spu = spu_info[i].spu;
-			spu_mfc_sr1_set(spu, spu_info[i].saved_mfc_sr1_RW);
-			out_be32(&spu->problem->spu_runcntl_RW,
-					spu_info[i].saved_spu_runcntl_RW);
-
-			sync();
-			__delay(200);
-
-			printf("Restarted spu %.2d\n", i);
-		} else {
-			catch_memory_errors = 0;
-			printf("*** Error restarting spu %.2d\n", i);
-		}
-		catch_memory_errors = 0;
-	}
-}
-
-#define DUMP_WIDTH	23
-#define DUMP_VALUE(format, field, value)				\
-do {									\
-	if (setjmp(bus_error_jmp) == 0) {				\
-		catch_memory_errors = 1;				\
-		sync();							\
-		printf("  %-*s = "format"\n", DUMP_WIDTH,		\
-				#field, value);				\
-		sync();							\
-		__delay(200);						\
-	} else {							\
-		catch_memory_errors = 0;				\
-		printf("  %-*s = *** Error reading field.\n",		\
-					DUMP_WIDTH, #field);		\
-	}								\
-	catch_memory_errors = 0;					\
-} while (0)
-
-#define DUMP_FIELD(obj, format, field)	\
-	DUMP_VALUE(format, field, obj->field)
-
-static void dump_spu_fields(struct spu *spu)
-{
-	printf("Dumping spu fields at address %p:\n", spu);
-
-	DUMP_FIELD(spu, "0x%x", number);
-	DUMP_FIELD(spu, "%s", name);
-	DUMP_FIELD(spu, "0x%lx", local_store_phys);
-	DUMP_FIELD(spu, "0x%p", local_store);
-	DUMP_FIELD(spu, "0x%lx", ls_size);
-	DUMP_FIELD(spu, "0x%x", node);
-	DUMP_FIELD(spu, "0x%lx", flags);
-	DUMP_FIELD(spu, "%llu", class_0_pending);
-	DUMP_FIELD(spu, "0x%llx", class_0_dar);
-	DUMP_FIELD(spu, "0x%llx", class_1_dar);
-	DUMP_FIELD(spu, "0x%llx", class_1_dsisr);
-	DUMP_FIELD(spu, "0x%x", irqs[0]);
-	DUMP_FIELD(spu, "0x%x", irqs[1]);
-	DUMP_FIELD(spu, "0x%x", irqs[2]);
-	DUMP_FIELD(spu, "0x%x", slb_replace);
-	DUMP_FIELD(spu, "%d", pid);
-	DUMP_FIELD(spu, "0x%p", mm);
-	DUMP_FIELD(spu, "0x%p", ctx);
-	DUMP_FIELD(spu, "0x%p", rq);
-	DUMP_FIELD(spu, "0x%llx", timestamp);
-	DUMP_FIELD(spu, "0x%lx", problem_phys);
-	DUMP_FIELD(spu, "0x%p", problem);
-	DUMP_VALUE("0x%x", problem->spu_runcntl_RW,
-			in_be32(&spu->problem->spu_runcntl_RW));
-	DUMP_VALUE("0x%x", problem->spu_status_R,
-			in_be32(&spu->problem->spu_status_R));
-	DUMP_VALUE("0x%x", problem->spu_npc_RW,
-			in_be32(&spu->problem->spu_npc_RW));
-	DUMP_FIELD(spu, "0x%p", priv2);
-	DUMP_FIELD(spu, "0x%p", pdata);
-}
-
-static int spu_inst_dump(unsigned long adr, long count, int praddr)
-{
-	return generic_inst_dump(adr, count, praddr, print_insn_spu);
-}
-
-static void dump_spu_ls(unsigned long num, int subcmd)
-{
-	unsigned long offset, addr, ls_addr;
-
-	if (setjmp(bus_error_jmp) == 0) {
-		catch_memory_errors = 1;
-		sync();
-		ls_addr = (unsigned long)spu_info[num].spu->local_store;
-		sync();
-		__delay(200);
-	} else {
-		catch_memory_errors = 0;
-		printf("*** Error: accessing spu info for spu %ld\n", num);
-		return;
-	}
-	catch_memory_errors = 0;
-
-	if (scanhex(&offset))
-		addr = ls_addr + offset;
-	else
-		addr = spu_info[num].dump_addr;
-
-	if (addr >= ls_addr + LS_SIZE) {
-		printf("*** Error: address outside of local store\n");
-		return;
-	}
-
-	switch (subcmd) {
-	case 'i':
-		addr += spu_inst_dump(addr, 16, 1);
-		last_cmd = "sdi\n";
-		break;
-	default:
-		prdump(addr, 64);
-		addr += 64;
-		last_cmd = "sd\n";
-		break;
-	}
-
-	spu_info[num].dump_addr = addr;
-}
-
-static int do_spu_cmd(void)
-{
-	static unsigned long num = 0;
-	int cmd, subcmd = 0;
-
-	cmd = inchar();
-	switch (cmd) {
-	case 's':
-		stop_spus();
-		break;
-	case 'r':
-		restart_spus();
-		break;
-	case 'd':
-		subcmd = inchar();
-		if (isxdigit(subcmd) || subcmd == '\n')
-			termch = subcmd;
-		fallthrough;
-	case 'f':
-		scanhex(&num);
-		if (num >= XMON_NUM_SPUS || !spu_info[num].spu) {
-			printf("*** Error: invalid spu number\n");
-			return 0;
-		}
-
-		switch (cmd) {
-		case 'f':
-			dump_spu_fields(spu_info[num].spu);
-			break;
-		default:
-			dump_spu_ls(num, subcmd);
-			break;
-		}
-
-		break;
-	default:
-		return -1;
-	}
-
-	return 0;
-}
-#else /* ! CONFIG_SPU_BASE */
-static int do_spu_cmd(void)
-{
-	return -1;
-}
-#endif
diff --git a/arch/powerpc/xmon/xmon_bpts.h b/arch/powerpc/xmon/xmon_bpts.h
index 377068f52edb..e14e4fb862e0 100644
--- a/arch/powerpc/xmon/xmon_bpts.h
+++ b/arch/powerpc/xmon/xmon_bpts.h
@@ -3,12 +3,12 @@
 #define XMON_BPTS_H
 
 #define NBPTS	256
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/inst.h>
 #define BPT_SIZE	(sizeof(ppc_inst_t) * 2)
 #define BPT_WORDS	(BPT_SIZE / sizeof(ppc_inst_t))
 
 extern unsigned int bpt_table[NBPTS * BPT_WORDS];
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* XMON_BPTS_H */