diff --git a/arch/powerpc/Kbuild b/arch/powerpc/Kbuild
new file mode 100644
index 0000000..51e6908
--- /dev/null
+++ b/arch/powerpc/Kbuild
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+
+obj-y += kernel/
+obj-y += mm/
+obj-y += lib/
+obj-y += sysdev/
+obj-y += platforms/
+obj-y += math-emu/
+obj-y += crypto/
+obj-y += net/
+
+obj-$(CONFIG_XMON) += xmon/
+obj-$(CONFIG_KVM)  += kvm/
+
+obj-$(CONFIG_PERF_EVENTS) += perf/
+obj-$(CONFIG_KEXEC_FILE)  += purgatory/
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a806692..3e56c9c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -48,7 +48,7 @@
 	# Allow randomisation to consume up to 512MB of address space (2^29).
 	default 11 if PPC_256K_PAGES	# 11 = 29 (512MB) - 18 (256K)
 	default 13 if PPC_64K_PAGES	# 13 = 29 (512MB) - 16 (64K)
-	default 15 if PPC_16K_PAGES 	# 15 = 29 (512MB) - 14 (16K)
+	default 15 if PPC_16K_PAGES	# 15 = 29 (512MB) - 14 (16K)
 	default 17			# 17 = 29 (512MB) - 12 (4K)
 
 config ARCH_MMAP_RND_COMPAT_BITS_MIN
@@ -103,13 +103,6 @@
 	bool
 	default y
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
 config GENERIC_LOCKBREAK
 	bool
 	default y
@@ -119,32 +112,34 @@
 	bool
 	default y
 
-config ARCH_HAS_DMA_SET_COHERENT_MASK
-        bool
-
 config PPC
 	bool
 	default y
 	#
 	# Please keep this list sorted alphabetically.
 	#
+	select ARCH_32BIT_OFF_T if PPC32
+	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select ARCH_HAS_DMA_SET_COHERENT_MASK
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_KCOV
+	select ARCH_HAS_HUGEPD			if HUGETLB_PAGE
+	select ARCH_HAS_MMIOWB			if PPC64
 	select ARCH_HAS_PHYS_TO_DMA
-	select ARCH_HAS_PMEM_API                if PPC64
+	select ARCH_HAS_PMEM_API
+	select ARCH_HAS_PTE_DEVMAP		if PPC_BOOK3S_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
-	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
-	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
 	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
-	select ARCH_HAS_UACCESS_FLUSHCACHE	if PPC64
+	select ARCH_HAS_UACCESS_FLUSHCACHE
+	select ARCH_HAS_UACCESS_MCSAFE		if PPC64
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_HAS_ZONE_DEVICE		if PPC_BOOK3S_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_KEEP_MEMBLOCK
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
@@ -168,42 +163,53 @@
 	select GENERIC_CPU_VULNERABILITIES	if PPC_BARRIER_NOSPEC
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
+	select GENERIC_PCI_IOMAP		if PCI
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HUGE_VMAP		if PPC_BOOK3S_64 && PPC_RADIX_MMU
 	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KASAN			if PPC32
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if COMPAT
+	select HAVE_ARCH_NVRAM_OPS
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ASM_MODVERSIONS
+	select HAVE_C_RECORDMCOUNT
 	select HAVE_CBPF_JIT			if !PPC64
+	select HAVE_STACKPROTECTOR		if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
+	select HAVE_STACKPROTECTOR		if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
 	select HAVE_CONTEXT_TRACKING		if PPC64
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS	if MPROFILE_KERNEL
 	select HAVE_EBPF_JIT			if PPC64
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS	if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_ERROR_INJECTION
 	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_GENERIC_GUP
 	select HAVE_HW_BREAKPOINT		if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
 	select HAVE_IDE
 	select HAVE_IOREMAP_PROT
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK
 	select HAVE_KERNEL_GZIP
-	select HAVE_KERNEL_XZ			if PPC_BOOK3S
+	select HAVE_KERNEL_LZMA			if DEFAULT_UIMAGE
+	select HAVE_KERNEL_LZO			if DEFAULT_UIMAGE
+	select HAVE_KERNEL_XZ			if PPC_BOOK3S || 44x
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
 	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION
 	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI				if PERF_EVENTS || (PPC64 && PPC_BOOK3S)
@@ -216,8 +222,10 @@
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if SMP
+	select HAVE_RCU_TABLE_NO_INVALIDATE	if HAVE_RCU_TABLE_FREE
+	select HAVE_MMU_GATHER_PAGE_SIZE
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_RELIABLE_STACKTRACE		if PPC64 && CPU_LITTLE_ENDIAN
+	select HAVE_RELIABLE_STACKTRACE		if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select HAVE_IRQ_TIME_ACCOUNTING
@@ -228,27 +236,26 @@
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE		if PPC64 || NOT_COHERENT_CACHE
 	select NEED_SG_DMA_LENGTH
-	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
-	select OF_RESERVED_MEM
 	select OLD_SIGACTION			if PPC32
 	select OLD_SIGSUSPEND
+	select PCI_DOMAINS			if PCI
+	select PCI_SYSCALL			if PCI
+	select PPC_DAWR				if PPC64
 	select RTC_LIB
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
+	select THREAD_INFO_IN_TASK
 	select VIRT_TO_BUS			if !PPC64
 	#
 	# Please keep this list sorted alphabetically.
 	#
 
 config PPC_BARRIER_NOSPEC
-    bool
-    default y
-    depends on PPC_BOOK3S_64 || PPC_FSL_BOOK3E
-
-config GENERIC_CSUM
-	def_bool n
+	bool
+	default y
+	depends on PPC_BOOK3S_64 || PPC_FSL_BOOK3E
 
 config EARLY_PRINTK
 	bool
@@ -270,11 +277,6 @@
 	depends on COMPAT && SYSVIPC
 	default y
 
-# All PPC32s use generic nvram driver through ppc_md
-config GENERIC_NVRAM
-	bool
-	default y if PPC32
-
 config SCHED_OMIT_FRAME_POINTER
 	bool
 	default y
@@ -285,12 +287,10 @@
 
 config PPC_UDBG_16550
 	bool
-	default n
 
 config GENERIC_TBSYNC
 	bool
 	default y if PPC32 && SMP
-	default n
 
 config AUDIT_ARCH
 	bool
@@ -309,13 +309,11 @@
 	bool
 	help
 	  Used to allow a board to specify it wants an ePAPR compliant wrapper.
-	default n
 
 config DEFAULT_UIMAGE
 	bool
 	help
 	  Used to allow a board to specify it wants a uImage built by default
-	default n
 
 config ARCH_HIBERNATION_POSSIBLE
 	bool
@@ -327,13 +325,15 @@
 		   (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \
 		   || 44x || 40x
 
+config ARCH_SUSPEND_NONZERO_CPU
+	def_bool y
+	depends on PPC_POWERNV || PPC_PSERIES
+
 config PPC_DCR_NATIVE
 	bool
-	default n
 
 config PPC_DCR_MMIO
 	bool
-	default n
 
 config PPC_DCR
 	bool
@@ -344,7 +344,6 @@
 	bool
 	depends on PCI
 	depends on PPC64 # not supported on 32 bits yet
-	default n
 
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	depends on PPC32 || PPC_BOOK3S_64
@@ -380,14 +379,16 @@
 	depends on PPC_ADV_DEBUG_REGS && 44x
 	default y
 
-config ZONE_DMA32
+config PPC_DAWR
 	bool
-	default y if PPC64
+
+config ZONE_DMA
+	bool
+	default y if PPC_BOOK3E_64
 
 config PGTABLE_LEVELS
 	int
 	default 2 if !PPC64
-	default 3 if PPC_64K_PAGES && !PPC_BOOK3S_64
 	default 4
 
 source "arch/powerpc/sysdev/Kconfig"
@@ -399,17 +400,17 @@
 	bool "High memory support"
 	depends on PPC32
 
-source kernel/Kconfig.hz
+source "kernel/Kconfig.hz"
 
 config HUGETLB_PAGE_SIZE_VARIABLE
 	bool
-	depends on HUGETLB_PAGE
+	depends on HUGETLB_PAGE && PPC_BOOK3S_64
 	default y
 
 config MATH_EMULATION
 	bool "Math emulation"
 	depends on 4xx || PPC_8xx || PPC_MPC832x || BOOKE
-	---help---
+	help
 	  Some PowerPC chips designed for embedded applications do not have
 	  a floating-point unit and therefore do not implement the
 	  floating-point instructions in the PowerPC instruction set.  If you
@@ -428,33 +429,31 @@
 
 config	MATH_EMULATION_FULL
 	bool "Emulate all the floating point instructions"
-	---help---
+	help
 	  Select this option will enable the kernel to support to emulate
 	  all the floating point instructions. If your SoC doesn't have
 	  a FPU, you should select this.
 
 config MATH_EMULATION_HW_UNIMPLEMENTED
 	bool "Just emulate the FPU unimplemented instructions"
-	---help---
+	help
 	  Select this if you know there does have a hardware FPU on your
 	  SoC, but some floating point instructions are not implemented by that.
 
 endchoice
 
 config PPC_TRANSACTIONAL_MEM
-       bool "Transactional Memory support for POWERPC"
-       depends on PPC_BOOK3S_64
-       depends on SMP
-       select ALTIVEC
-       select VSX
-       default n
-       ---help---
-         Support user-mode Transactional Memory on POWERPC.
+	bool "Transactional Memory support for POWERPC"
+	depends on PPC_BOOK3S_64
+	depends on SMP
+	select ALTIVEC
+	select VSX
+	help
+	  Support user-mode Transactional Memory on POWERPC.
 
 config LD_HEAD_STUB_CATCH
 	bool "Reserve 256 bytes to cope with linker stubs in HEAD text" if EXPERT
 	depends on PPC64
-	default n
 	help
 	  Very large kernels can cause linker branch stubs to be generated by
 	  code in head_64.S, which moves the head text sections out of their
@@ -470,7 +469,7 @@
 	bool "Support for enabling/disabling CPUs"
 	depends on SMP && (PPC_PSERIES || \
 	PPC_PMAC || PPC_POWERNV || FSL_SOC_BOOKE)
-	---help---
+	help
 	  Say Y here to be able to disable and re-enable individual
 	  CPUs at runtime on SMP machines.
 
@@ -483,9 +482,6 @@
 config ARCH_ENABLE_MEMORY_HOTPLUG
 	def_bool y
 
-config ARCH_HAS_WALK_MEMORY
-	def_bool y
-
 config ARCH_ENABLE_MEMORY_HOTREMOVE
 	def_bool y
 
@@ -518,6 +514,7 @@
 	select KEXEC_CORE
 	select HAVE_IMA_KEXEC
 	select BUILD_BIN2C
+	select KEXEC_ELF
 	depends on PPC64
 	depends on CRYPTO=y
 	depends on CRYPTO_SHA256=y
@@ -557,7 +554,6 @@
 config RELOCATABLE_TEST
 	bool "Test relocatable kernel"
 	depends on (PPC64 && RELOCATABLE)
-	default n
 	help
 	  This runs the relocatable kernel at the address it was initially
 	  loaded at, which tends to be non-zero and therefore test the
@@ -565,7 +561,7 @@
 
 config CRASH_DUMP
 	bool "Build a dump capture kernel"
-	depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP)
+	depends on PPC64 || PPC_BOOK3S_32 || FSL_BOOKE || (44x && !SMP)
 	select RELOCATABLE if PPC64 || 44x || FSL_BOOKE
 	help
 	  Build a kernel suitable for use as a dump capture kernel.
@@ -574,7 +570,7 @@
 
 config FA_DUMP
 	bool "Firmware-assisted dump"
-	depends on PPC64 && PPC_RTAS
+	depends on PPC64 && (PPC_RTAS || PPC_POWERNV)
 	select CRASH_CORE
 	select CRASH_DUMP
 	help
@@ -585,7 +581,26 @@
 	  is meant to be a kdump replacement offering robustness and
 	  speed not possible without system firmware assistance.
 
-	  If unsure, say "N"
+	  If unsure, say "y". Only special kernels like petitboot may
+	  need to say "N" here.
+
+config PRESERVE_FA_DUMP
+	bool "Preserve Firmware-assisted dump"
+	depends on PPC64 && PPC_POWERNV && !FA_DUMP
+	help
+	  On a kernel with FA_DUMP disabled, this option helps to preserve
+	  crash data from a previously crash'ed kernel. Useful when the next
+	  memory preserving kernel boot would process this crash data.
+	  Petitboot kernel is the typical usecase for this option.
+
+config OPAL_CORE
+	bool "Export OPAL memory as /sys/firmware/opal/core"
+	depends on PPC64 && PPC_POWERNV
+	help
+	  This option uses the MPIPL support in firmware to provide an
+	  ELF core of OPAL memory after a crash. The ELF core is exported
+	  as /sys/firmware/opal/core file which is helpful in debugging
+	  OPAL crashes using GDB.
 
 config IRQ_ALL_CPUS
 	bool "Distribute interrupts on all CPUs by default"
@@ -702,7 +717,7 @@
 
 config PPC_64K_PAGES
 	bool "64k page size"
-	depends on !PPC_FSL_BOOK3E && (44x || PPC_BOOK3S_64 || PPC_BOOK3E_64)
+	depends on 44x || PPC_BOOK3S_64
 	select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
 
 config PPC_256K_PAGES
@@ -720,6 +735,13 @@
 
 endchoice
 
+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
@@ -730,6 +752,59 @@
 	  Used to define the stack size. The default is almost always what you
 	  want. Only change this if you know what you are doing.
 
+config ETEXT_SHIFT_BOOL
+	bool "Set custom etext alignment" if STRICT_KERNEL_RWX && \
+					     (PPC_BOOK3S_32 || PPC_8xx)
+	depends on ADVANCED_OPTIONS
+	help
+	  This option allows you to set the kernel end of text alignment. When
+	  RAM is mapped by blocks, the alignment needs to fit the size and
+	  number of possible blocks. The default should be OK for most configs.
+
+	  Say N here unless you know what you are doing.
+
+config ETEXT_SHIFT
+	int "_etext shift" if ETEXT_SHIFT_BOOL
+	range 17 28 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+	range 19 23 if STRICT_KERNEL_RWX && PPC_8xx
+	default 17 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+	default 19 if STRICT_KERNEL_RWX && PPC_8xx
+	default PPC_PAGE_SHIFT
+	help
+	  On Book3S 32 (603+), IBATs are used to map kernel text.
+	  Smaller is the alignment, greater is the number of necessary IBATs.
+
+	  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.
+
+config DATA_SHIFT_BOOL
+	bool "Set custom data alignment" if STRICT_KERNEL_RWX && \
+					    (PPC_BOOK3S_32 || PPC_8xx)
+	depends on ADVANCED_OPTIONS
+	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
+	  number of possible blocks. The default should be OK for most configs.
+
+	  Say N here unless you know what you are doing.
+
+config DATA_SHIFT
+	int "Data shift" if DATA_SHIFT_BOOL
+	default 24 if STRICT_KERNEL_RWX && PPC64
+	range 17 28 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+	range 19 23 if STRICT_KERNEL_RWX && PPC_8xx
+	default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+	default 23 if STRICT_KERNEL_RWX && PPC_8xx
+	default PPC_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.
+
 config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
 	range 8 9 if PPC64 && PPC_64K_PAGES
@@ -769,7 +844,6 @@
 
 config PPC_COPRO_BASE
 	bool
-	default n
 
 config SCHED_SMT
 	bool "SMT (Hyperthreading) scheduler support"
@@ -783,7 +857,7 @@
 	bool "PowerPC denormalisation exception handling"
 	depends on PPC_BOOK3S_64
 	default "y" if PPC_POWERNV
-	---help---
+	help
 	  Add support for handling denormalisation of single precision
 	  values.  Useful for bare metal only.  If unsure say Y here.
 
@@ -791,9 +865,9 @@
 	bool "Default bootloader kernel arguments"
 
 config CMDLINE
-	string "Initial kernel command string"
-	depends on CMDLINE_BOOL
-	default "console=ttyS0,9600 console=tty0 root=/dev/sda2"
+	string "Initial kernel command string" if CMDLINE_BOOL
+	default "console=ttyS0,9600 console=tty0 root=/dev/sda2" if CMDLINE_BOOL
+	default ""
 	help
 	  On some platforms, there is currently no way for the boot loader to
 	  pass arguments to the kernel. For these platforms, you can supply
@@ -826,7 +900,7 @@
 	def_bool y
 	depends on ADB_PMU
 
-source kernel/power/Kconfig
+source "kernel/power/Kconfig"
 
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
@@ -856,7 +930,7 @@
 	  page-based protections, but without requiring modification of the
 	  page tables when an application changes protection domains.
 
-	  For details, see Documentation/vm/protection-keys.rst
+	  For details, see Documentation/core-api/protection-keys.rst
 
 	  If unsure, say y.
 
@@ -879,10 +953,6 @@
 	  have an IBM RS/6000 or pSeries machine, say Y.  If you have an
 	  embedded board, consult your board documentation.
 
-config ZONE_DMA
-	bool
-	default y
-
 config GENERIC_ISA_DMA
 	bool
 	depends on ISA_DMA_API
@@ -892,10 +962,6 @@
 	bool
 	depends on PCI
 	default y if 40x || 44x
-	default n
-
-config EISA
-	bool
 
 config SBUS
 	bool
@@ -904,7 +970,8 @@
 	bool
 
 config FSL_PCI
- 	bool
+	bool
+	select ARCH_HAS_DMA_SET_MASK
 	select PPC_INDIRECT_PCI
 	select PCI_QUIRKS
 
@@ -941,78 +1008,24 @@
 	help
 	  Freescale General-purpose Timers support
 
-# Yes MCA RS/6000s exist but Linux-PPC does not currently support any
-config MCA
-	bool
-
-# Platforms that what PCI turned unconditionally just do select PCI
-# in their config node.  Platforms that want to choose at config
-# time should select PPC_PCI_CHOICE
-config PPC_PCI_CHOICE
-	bool
-
-config PCI
-	bool "PCI support" if PPC_PCI_CHOICE
-	default y if !40x && !CPM2 && !PPC_8xx && !PPC_83xx \
-		&& !PPC_85xx && !PPC_86xx && !GAMECUBE_COMMON
-	default PCI_QSPAN if PPC_8xx
-	select GENERIC_PCI_IOMAP
-	help
-	  Find out whether your system includes a PCI bus. PCI is the name of
-	  a bus system, i.e. the way the CPU talks to the other stuff inside
-	  your box.  If you say Y here, the kernel will include drivers and
-	  infrastructure code to support PCI bus devices.
-
-config PCI_DOMAINS
-	def_bool PCI
-
-config PCI_SYSCALL
-	def_bool PCI
-
-config PCI_QSPAN
-	bool "QSpan PCI"
-	depends on PPC_8xx
-	select PPC_I8259
-	help
-	  Say Y here if you have a system based on a Motorola 8xx-series
-	  embedded processor with a QSPAN PCI interface, otherwise say N.
-
 config PCI_8260
 	bool
 	depends on PCI && 8260
 	select PPC_INDIRECT_PCI
 	default y
 
-source "drivers/pci/Kconfig"
-
-source "drivers/pcmcia/Kconfig"
-
-config HAS_RAPIDIO
-	bool
-	default n
-
-config RAPIDIO
-	tristate "RapidIO support"
-	depends on HAS_RAPIDIO || PCI
-	help
-	  If you say Y here, the kernel will include drivers and
-	  infrastructure code to support RapidIO interconnect devices.
-
 config FSL_RIO
 	bool "Freescale Embedded SRIO Controller support"
-	depends on RAPIDIO = y && HAS_RAPIDIO
+	depends on RAPIDIO = y && HAVE_RAPIDIO
 	default "n"
-	---help---
+	help
 	  Include support for RapidIO controller on Freescale embedded
 	  processors (MPC8548, MPC8641, etc).
 
-source "drivers/rapidio/Kconfig"
-
 endmenu
 
 config NONSTATIC_KERNEL
 	bool
-	default n
 
 menu "Advanced setup"
 	depends on PPC32
@@ -1069,14 +1082,14 @@
 	select NONSTATIC_KERNEL
 	help
 	  This option enables the kernel to be loaded at any page aligned
-	  physical address. The kernel creates a mapping from KERNELBASE to 
+	  physical address. The kernel creates a mapping from KERNELBASE to
 	  the address where the kernel is loaded. The page size here implies
 	  the TLB page size of the mapping for kernel on the particular platform.
 	  Please refer to the init code for finding the TLB page size.
 
 	  DYNAMIC_MEMSTART is an easy way of implementing pseudo-RELOCATABLE
 	  kernel image, where the only restriction is the page aligned kernel
-	  load address. When this option is enabled, the compile time physical 
+	  load address. When this option is enabled, the compile time physical
 	  address CONFIG_PHYSICAL_START is ignored.
 
 	  This option is overridden by CONFIG_RELOCATABLE
@@ -1122,7 +1135,7 @@
 
 config PHYSICAL_START
 	hex "Physical address where the kernel is loaded" if PHYSICAL_START_BOOL
-	default "0x02000000" if PPC_STD_MMU && CRASH_DUMP && !NONSTATIC_KERNEL
+	default "0x02000000" if PPC_BOOK3S && CRASH_DUMP && !NONSTATIC_KERNEL
 	default "0x00000000"
 
 config PHYSICAL_ALIGN
@@ -1148,18 +1161,6 @@
 	default "0x80000000" if PPC_8xx
 	default "0xc0000000"
 
-config CONSISTENT_SIZE_BOOL
-	bool "Set custom consistent memory pool size"
-	depends on ADVANCED_OPTIONS && NOT_COHERENT_CACHE
-	help
-	  This option allows you to set the size of the
-	  consistent memory pool.  This pool of virtual memory
-	  is used to make consistent memory allocations.
-
-config CONSISTENT_SIZE
-	hex "Size of consistent memory pool" if CONSISTENT_SIZE_BOOL
-	default "0x00200000" if NOT_COHERENT_CACHE
-
 config PIN_TLB
 	bool "Pinned Kernel TLBs (860 ONLY)"
 	depends on ADVANCED_OPTIONS && PPC_8xx && \
@@ -1172,7 +1173,7 @@
 
 config PIN_TLB_IMMR
 	bool "Pinned TLB for IMMR"
-	depends on PIN_TLB
+	depends on PIN_TLB || PPC_EARLY_DEBUG_CPM
 	default y
 
 config PIN_TLB_TEXT
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index fd63cd9..c599209 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -2,7 +2,6 @@
 
 config PPC_DISABLE_WERROR
 	bool "Don't build arch/powerpc code with -Werror"
-	default n
 	help
 	  This option tells the compiler NOT to build the code under
 	  arch/powerpc with the -Werror flag (which means warnings
@@ -56,7 +55,6 @@
 config CODE_PATCHING_SELFTEST
 	bool "Run self-tests of the code-patching code"
 	depends on DEBUG_KERNEL
-	default n
 
 config JUMP_LABEL_FEATURE_CHECKS
 	bool "Enable use of jump label for cpu/mmu_has_feature()"
@@ -70,7 +68,6 @@
 config JUMP_LABEL_FEATURE_CHECK_DEBUG
 	bool "Do extra check on feature fixup calls"
 	depends on DEBUG_KERNEL && JUMP_LABEL_FEATURE_CHECKS
-	default n
 	help
 	  This tries to catch incorrect usage of cpu_has_feature() and
 	  mmu_has_feature() in the code.
@@ -80,16 +77,13 @@
 config FTR_FIXUP_SELFTEST
 	bool "Run self-tests of the feature-fixup code"
 	depends on DEBUG_KERNEL
-	default n
 
 config MSI_BITMAP_SELFTEST
 	bool "Run self-tests of the MSI bitmap code"
 	depends on DEBUG_KERNEL
-	default n
 
 config PPC_IRQ_SOFT_MASK_DEBUG
 	bool "Include extra checks for powerpc irq soft masking"
-	default n
 
 config XMON
 	bool "Include xmon kernel debugger"
@@ -123,6 +117,14 @@
 	  to say Y here, unless you're building for a memory-constrained
 	  system.
 
+config XMON_DEFAULT_RO_MODE
+	bool "Restrict xmon to read-only operations by default"
+	depends on XMON
+	default y
+	help
+          Operate xmon in read-only mode. The cmdline options 'xmon=rw' and
+          'xmon=ro' override this default.
+
 config DEBUGGER
 	bool
 	depends on KGDB || XMON
@@ -367,12 +369,32 @@
 
 	  If you are unsure, say N.
 
-config PPC_HTDUMP
-	def_bool y
-	depends on PPC_PTDUMP && PPC_BOOK3S_64
+config PPC_DEBUG_WX
+	bool "Warn on W+X mappings at boot"
+	depends on PPC_PTDUMP
+	help
+	  Generate a warning if any W+X mappings are found at boot.
+
+	  This is useful for discovering cases where the kernel is leaving
+	  W+X mappings after applying NX, as such mappings are a security risk.
+
+	  Note that even if the check fails, your kernel is possibly
+	  still fine, as W+X mappings are not a security hole in
+	  themselves, what they do is that they make the exploitation
+	  of other unfixed kernel bugs easier.
+
+	  There is no runtime or memory usage effect of this option
+	  once the kernel has booted up - it's a one time check.
+
+	  If in doubt, say "Y".
 
 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
+	default 0xe0000000
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index d2824b0..83522c9 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -30,19 +30,20 @@
 endif
 endif
 
-ifeq ($(CROSS_COMPILE),)
-KBUILD_DEFCONFIG := $(shell uname -m)_defconfig
-else
-KBUILD_DEFCONFIG := ppc64_defconfig
+ifdef CONFIG_PPC_BOOK3S_32
+KBUILD_CFLAGS		+= -mcpu=powerpc
 endif
 
-ifdef CONFIG_PPC64
+# 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.
+uname := $(shell uname -m)
+KBUILD_DEFCONFIG := $(if $(filter ppc%,$(uname)),$(uname),ppc64)_defconfig
+
 new_nm := $(shell if $(NM) --help 2>&1 | grep -- '--synthetic' > /dev/null; then echo y; else echo n; fi)
 
 ifeq ($(new_nm),y)
 NM		:= $(NM) --synthetic
 endif
-endif
 
 # BITS is used as extension for files which are available in a 32 bit
 # and a 64 bit version to simplify shared Makefiles.
@@ -64,7 +65,7 @@
 ifdef CONFIG_PPC32
 KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
 else
-KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/powerpc/kernel/module.lds
+KBUILD_LDS_MODULE += $(srctree)/arch/powerpc/kernel/module.lds
 ifeq ($(call ld-ifversion, -ge, 225000000, y),y)
 # Have the linker provide sfpr if possible.
 # There is a corresponding test in arch/powerpc/lib/Makefile
@@ -96,7 +97,7 @@
 aflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mabi=elfv2
 endif
 
-ifneq ($(cc-name),clang)
+ifndef CONFIG_CC_IS_CLANG
   cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mno-strict-align
 endif
 
@@ -109,7 +110,13 @@
 KBUILD_CFLAGS	+= -m$(BITS)
 KBUILD_AFLAGS	+= -m$(BITS) -Wl,-a$(BITS)
 KBUILD_LDFLAGS	+= -m elf$(BITS)$(LDEMULATION)
-KBUILD_ARFLAGS	+= --target=elf$(BITS)-$(GNUTARGET)
+endif
+
+cflags-$(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
@@ -145,7 +152,14 @@
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
 
-CFLAGS-$(CONFIG_PPC32)	:= -ffixed-r2 $(MULTIPLEWORD)
+# Clang unconditionally reserves r2 on ppc32 and does not support the flag
+# https://bugs.llvm.org/show_bug.cgi?id=39555
+CFLAGS-$(CONFIG_PPC32)	:= $(call cc-option, -ffixed-r2)
+
+# Clang doesn't support -mmultiple / -mno-multiple
+# https://bugs.llvm.org/show_bug.cgi?id=39556
+CFLAGS-$(CONFIG_PPC32)	+= $(call cc-option, $(MULTIPLEWORD))
+
 CFLAGS-$(CONFIG_PPC32)	+= $(call cc-option,-mno-readonly-in-sdata)
 
 ifdef CONFIG_PPC_BOOK3S_64
@@ -160,8 +174,17 @@
 CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64
 endif
 
+ifdef CONFIG_FUNCTION_TRACER
+CC_FLAGS_FTRACE := -pg
 ifdef CONFIG_MPROFILE_KERNEL
-	CC_FLAGS_FTRACE := -pg -mprofile-kernel
+CC_FLAGS_FTRACE += -mprofile-kernel
+endif
+# Work around gcc code-gen bugs with -pg / -fno-omit-frame-pointer in gcc <= 4.8
+# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=44199
+# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=52828
+ifndef CONFIG_CC_IS_CLANG
+CC_FLAGS_FTRACE	+= $(call cc-ifversion, -lt, 0409, -mno-sched-epilog)
+endif
 endif
 
 CFLAGS-$(CONFIG_TARGET_CPU_BOOL) += $(call cc-option,-mcpu=$(CONFIG_TARGET_CPU))
@@ -185,10 +208,10 @@
 
 asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
 
-KBUILD_CPPFLAGS	+= -Iarch/$(ARCH) $(asinstr)
-KBUILD_AFLAGS	+= -Iarch/$(ARCH) $(AFLAGS-y)
+KBUILD_CPPFLAGS	+= -I $(srctree)/arch/$(ARCH) $(asinstr)
+KBUILD_AFLAGS	+= $(AFLAGS-y)
 KBUILD_CFLAGS	+= $(call cc-option,-msoft-float)
-KBUILD_CFLAGS	+= -pipe -Iarch/$(ARCH) $(CFLAGS-y)
+KBUILD_CFLAGS	+= -pipe $(CFLAGS-y)
 CPP		= $(CC) -E $(KBUILD_CFLAGS)
 
 CHECKFLAGS	+= -m$(BITS) -D__powerpc__ -D__powerpc$(BITS)__
@@ -212,10 +235,6 @@
 KBUILD_CFLAGS += $(call cc-option,-mno-spe)
 KBUILD_CFLAGS += $(call cc-option,-mspe=no)
 
-# Enable unit-at-a-time mode when possible. It shrinks the
-# kernel considerably.
-KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
-
 # FIXME: the module load should be taught about the additional relocs
 # generated by this.
 # revert to pre-gcc-4.4 behaviour of .eh_frame
@@ -225,15 +244,6 @@
 # often slow when they are implemented at all
 KBUILD_CFLAGS		+= $(call cc-option,-mno-string)
 
-ifdef CONFIG_6xx
-KBUILD_CFLAGS		+= -mcpu=powerpc
-endif
-
-# Work around a gcc code-gen bug with -fno-omit-frame-pointer.
-ifdef CONFIG_FUNCTION_TRACER
-KBUILD_CFLAGS		+= -mno-sched-epilog
-endif
-
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
@@ -262,18 +272,8 @@
 head-$(CONFIG_ALTIVEC)		+= arch/powerpc/kernel/vector.o
 head-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE)  += arch/powerpc/kernel/prom_init.o
 
-core-y				+= arch/powerpc/kernel/ \
-				   arch/powerpc/mm/ \
-				   arch/powerpc/lib/ \
-				   arch/powerpc/sysdev/ \
-				   arch/powerpc/platforms/ \
-				   arch/powerpc/math-emu/ \
-				   arch/powerpc/crypto/ \
-				   arch/powerpc/net/
-core-$(CONFIG_XMON)		+= arch/powerpc/xmon/
-core-$(CONFIG_KVM) 		+= arch/powerpc/kvm/
-core-$(CONFIG_PERF_EVENTS)	+= arch/powerpc/perf/
-core-$(CONFIG_KEXEC_FILE)	+= arch/powerpc/purgatory/
+# See arch/powerpc/Kbuild for content of core part of the kernel
+core-y += arch/powerpc/
 
 drivers-$(CONFIG_OPROFILE)	+= arch/powerpc/oprofile/
 
@@ -297,9 +297,6 @@
 bootwrapper_install:
 	$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
 
-%.dtb: scripts
-	$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
-
 # Used to create 'merged defconfigs'
 # To use it $(call) it with the first argument as the base defconfig
 # and the second argument as a space separated list of .config files to merge,
@@ -319,6 +316,14 @@
 ppc64le_defconfig:
 	$(call merge_into_defconfig,ppc64_defconfig,le)
 
+PHONY += ppc64le_guest_defconfig
+ppc64le_guest_defconfig:
+	$(call merge_into_defconfig,ppc64_defconfig,le guest)
+
+PHONY += ppc64_guest_defconfig
+ppc64_guest_defconfig:
+	$(call merge_into_defconfig,ppc64_defconfig,be guest)
+
 PHONY += powernv_be_defconfig
 powernv_be_defconfig:
 	$(call merge_into_defconfig,powernv_defconfig,be)
@@ -358,6 +363,10 @@
 	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/book3s_32.config \
 		-f $(srctree)/Makefile allmodconfig
 
+PHONY += ppc_defconfig
+ppc_defconfig:
+	$(call merge_into_defconfig,book3s_32.config,)
+
 PHONY += ppc64le_allmodconfig
 ppc64le_allmodconfig:
 	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/le.config \
@@ -397,47 +406,39 @@
 ifdef CONFIG_PPC64
 	$(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso64 $@
 endif
+ifdef CONFIG_VDSO32
 	$(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso32 $@
+endif
 
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 
 archprepare: checkbin
 
-# Use the file '.tmp_gas_check' for binutils tests, as gas won't output
-# to stdout and these checks are run even on install targets.
-TOUT	:= .tmp_gas_check
+archheaders:
+	$(Q)$(MAKE) $(build)=arch/powerpc/kernel/syscalls all
 
-# Check gcc and binutils versions:
-# - gcc-3.4 and binutils-2.14 are a fatal combination
-# - Require gcc 4.0 or above on 64-bit
-# - gcc-4.2.0 has issues compiling modules on 64-bit
+ifdef CONFIG_STACKPROTECTOR
+prepare: 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))
+else
+	$(eval KBUILD_CFLAGS += -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "TASK_CANARY") print $$3;}' include/generated/asm-offsets.h))
+endif
+endif
+
+ifdef CONFIG_SMP
+prepare: task_cpu_prepare
+
+task_cpu_prepare: prepare0
+	$(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TASK_CPU") print $$3;}' include/generated/asm-offsets.h))
+endif
+
+# Check toolchain versions:
+# - gcc-4.6 is the minimum kernel-wide version so nothing required.
 checkbin:
-	@if test "$(cc-name)" != "clang" \
-	    && test "$(cc-version)" = "0304" ; then \
-		if ! /bin/echo mftb 5 | $(AS) -v -mppc -many -o $(TOUT) >/dev/null 2>&1 ; then \
-			echo -n '*** ${VERSION}.${PATCHLEVEL} kernels no longer build '; \
-			echo 'correctly with gcc-3.4 and your version of binutils.'; \
-			echo '*** Please upgrade your binutils or downgrade your gcc'; \
-			false; \
-		fi ; \
-	fi
-	@if test "$(cc-name)" != "clang" \
-	    && test "$(cc-version)" -lt "0400" \
-	    && test "x${CONFIG_PPC64}" = "xy" ; then \
-                echo -n "Sorry, GCC v4.0 or above is required to build " ; \
-                echo "the 64-bit powerpc kernel." ; \
-                false ; \
-        fi
-	@if test "$(cc-name)" != "clang" \
-	    && test "$(cc-fullversion)" = "040200" \
-	    && test "x${CONFIG_MODULES}${CONFIG_PPC64}" = "xyy" ; then \
-		echo -n '*** GCC-4.2.0 cannot compile the 64-bit powerpc ' ; \
-		echo 'kernel with modules enabled.' ; \
-		echo -n '*** Please use a different GCC version or ' ; \
-		echo 'disable kernel modules' ; \
-		false ; \
-	fi
 	@if test "x${CONFIG_CPU_LITTLE_ENDIAN}" = "xy" \
 	    && $(LD) --version | head -1 | grep ' 2\.24$$' >/dev/null ; then \
 		echo -n '*** binutils 2.24 miscompiles weak symbols ' ; \
@@ -445,7 +446,3 @@
 		echo -n '*** Please use a different binutils version.' ; \
 		false ; \
 	fi
-
-
-CLEAN_FILES += $(TOUT)
-
diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink
index 83f8e5b..134f12f 100644
--- a/arch/powerpc/Makefile.postlink
+++ b/arch/powerpc/Makefile.postlink
@@ -18,7 +18,7 @@
 ifdef CONFIG_PPC_BOOK3S_64
       cmd_relocs_check =						\
 	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" ; \
-	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@"
+	$(BASH) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@"
 else
       cmd_relocs_check =						\
 	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@"
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index f92d053..6610665 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -44,4 +44,3 @@
 fdt_wip.c
 libfdt.h
 libfdt_internal.h
-
diff --git a/arch/powerpc/boot/4xx.c b/arch/powerpc/boot/4xx.c
index f7da651..1699e95 100644
--- a/arch/powerpc/boot/4xx.c
+++ b/arch/powerpc/boot/4xx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2007 David Gibson, IBM Corporation.
  *
@@ -11,11 +12,6 @@
  * Copyright (C) 2009 Wind River Systems, Inc.
  *   Updated for supporting PPC405EX on Kilauea.
  *   Tiejun Chen <tiejun.chen@windriver.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stddef.h>
 #include "types.h"
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 0fb96c2..dfbd7f2 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -20,9 +20,6 @@
 
 all: $(obj)/zImage
 
-compress-$(CONFIG_KERNEL_GZIP) := CONFIG_KERNEL_GZIP
-compress-$(CONFIG_KERNEL_XZ)   := CONFIG_KERNEL_XZ
-
 ifdef CROSS32_COMPILE
     BOOTCC := $(CROSS32_COMPILE)gcc
     BOOTAR := $(CROSS32_COMPILE)ar
@@ -32,9 +29,9 @@
 endif
 
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
-		 -fno-strict-aliasing -Os -msoft-float -pipe \
-		 -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
-		 -D$(compress-y)
+		 -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \
+		 -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
+		 $(LINUXINCLUDE)
 
 ifdef CONFIG_PPC64_BOOT_WRAPPER
 BOOTCFLAGS	+= -m64
@@ -51,9 +48,14 @@
 BOOTCFLAGS	+= $(call cc-option,-mabi=elfv2)
 endif
 
-BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc
+BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc
 
-BOOTARFLAGS	:= -cr$(KBUILD_ARFLAGS)
+BOOTARFLAGS	:= -crD
+
+ifdef CONFIG_CC_IS_CLANG
+BOOTCFLAGS += $(CLANG_FLAGS)
+BOOTAFLAGS += $(CLANG_FLAGS)
+endif
 
 ifdef CONFIG_DEBUG_INFO
 BOOTCFLAGS	+= -g
@@ -208,7 +210,7 @@
       cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $<
 
 quiet_cmd_bootar = BOOTAR  $@
-      cmd_bootar = $(BOOTAR) $(BOOTARFLAGS) $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@
+      cmd_bootar = $(BOOTAR) $(BOOTARFLAGS) $@.$$$$ $(real-prereqs); mv $@.$$$$ $@
 
 $(obj-libfdt): $(obj)/%.o: $(srctree)/scripts/dtc/libfdt/%.c FORCE
 	$(call if_changed_dep,bootcc)
@@ -247,6 +249,8 @@
 
 compressor-$(CONFIG_KERNEL_GZIP) := gz
 compressor-$(CONFIG_KERNEL_XZ)   := xz
+compressor-$(CONFIG_KERNEL_LZMA)   := lzma
+compressor-$(CONFIG_KERNEL_LZO) := lzo
 
 # args (to if_changed): 1 = (this rule), 2 = platform, 3 = dts 4=dtb 5=initrd
 quiet_cmd_wrap	= WRAP    $@
@@ -304,9 +308,9 @@
 					   dtbImage.adder875-redboot
 
 # Board ports in arch/powerpc/platform/52xx/Kconfig
-image-$(CONFIG_PPC_LITE5200)		+= cuImage.lite5200 lite5200.dtb
-image-$(CONFIG_PPC_LITE5200)		+= cuImage.lite5200b lite5200b.dtb
-image-$(CONFIG_PPC_MEDIA5200)		+= cuImage.media5200 media5200.dtb
+image-$(CONFIG_PPC_LITE5200)		+= cuImage.lite5200
+image-$(CONFIG_PPC_LITE5200)		+= cuImage.lite5200b
+image-$(CONFIG_PPC_MEDIA5200)		+= cuImage.media5200
 
 # Board ports in arch/powerpc/platform/82xx/Kconfig
 image-$(CONFIG_MPC8272_ADS)		+= cuImage.mpc8272ads
@@ -381,11 +385,11 @@
 	$(call if_changed,wrap,$(subst $(obj)/zImage.,,$@))
 
 # dtbImage% - a dtbImage is a zImage with an embedded device tree blob
-$(obj)/dtbImage.initrd.%: vmlinux $(wrapperbits) $(obj)/%.dtb FORCE
-	$(call if_changed,wrap,$*,,$(obj)/$*.dtb,$(obj)/ramdisk.image.gz)
+$(obj)/dtbImage.initrd.%: vmlinux $(wrapperbits) $(obj)/dts/%.dtb FORCE
+	$(call if_changed,wrap,$*,,$(obj)/dts/$*.dtb,$(obj)/ramdisk.image.gz)
 
-$(obj)/dtbImage.%: vmlinux $(wrapperbits) $(obj)/%.dtb FORCE
-	$(call if_changed,wrap,$*,,$(obj)/$*.dtb)
+$(obj)/dtbImage.%: vmlinux $(wrapperbits) $(obj)/dts/%.dtb FORCE
+	$(call if_changed,wrap,$*,,$(obj)/dts/$*.dtb)
 
 # This cannot be in the root of $(src) as the zImage rule always adds a $(obj)
 # prefix
@@ -395,36 +399,33 @@
 $(obj)/uImage: vmlinux $(wrapperbits) FORCE
 	$(call if_changed,wrap,uboot)
 
-$(obj)/uImage.initrd.%: vmlinux $(obj)/%.dtb $(wrapperbits) FORCE
-	$(call if_changed,wrap,uboot-$*,,$(obj)/$*.dtb,$(obj)/ramdisk.image.gz)
+$(obj)/uImage.initrd.%: vmlinux $(obj)/dts/%.dtb $(wrapperbits) FORCE
+	$(call if_changed,wrap,uboot-$*,,$(obj)/dts/$*.dtb,$(obj)/ramdisk.image.gz)
 
-$(obj)/uImage.%: vmlinux $(obj)/%.dtb $(wrapperbits) FORCE
-	$(call if_changed,wrap,uboot-$*,,$(obj)/$*.dtb)
+$(obj)/uImage.%: vmlinux $(obj)/dts/%.dtb $(wrapperbits) FORCE
+	$(call if_changed,wrap,uboot-$*,,$(obj)/dts/$*.dtb)
 
-$(obj)/cuImage.initrd.%: vmlinux $(obj)/%.dtb $(wrapperbits) FORCE
-	$(call if_changed,wrap,cuboot-$*,,$(obj)/$*.dtb,$(obj)/ramdisk.image.gz)
+$(obj)/cuImage.initrd.%: vmlinux $(obj)/dts/%.dtb $(wrapperbits) FORCE
+	$(call if_changed,wrap,cuboot-$*,,$(obj)/dts/$*.dtb,$(obj)/ramdisk.image.gz)
 
-$(obj)/cuImage.%: vmlinux $(obj)/%.dtb $(wrapperbits) FORCE
-	$(call if_changed,wrap,cuboot-$*,,$(obj)/$*.dtb)
+$(obj)/cuImage.%: vmlinux $(obj)/dts/%.dtb $(wrapperbits) FORCE
+	$(call if_changed,wrap,cuboot-$*,,$(obj)/dts/$*.dtb)
 
-$(obj)/simpleImage.initrd.%: vmlinux $(obj)/%.dtb $(wrapperbits) FORCE
-	$(call if_changed,wrap,simpleboot-$*,,$(obj)/$*.dtb,$(obj)/ramdisk.image.gz)
+$(obj)/simpleImage.initrd.%: vmlinux $(obj)/dts/%.dtb $(wrapperbits) FORCE
+	$(call if_changed,wrap,simpleboot-$*,,$(obj)/dts/$*.dtb,$(obj)/ramdisk.image.gz)
 
-$(obj)/simpleImage.%: vmlinux $(obj)/%.dtb $(wrapperbits) FORCE
-	$(call if_changed,wrap,simpleboot-$*,,$(obj)/$*.dtb)
+$(obj)/simpleImage.%: vmlinux $(obj)/dts/%.dtb $(wrapperbits) FORCE
+	$(call if_changed,wrap,simpleboot-$*,,$(obj)/dts/$*.dtb)
 
-$(obj)/treeImage.initrd.%: vmlinux $(obj)/%.dtb $(wrapperbits) FORCE
-	$(call if_changed,wrap,treeboot-$*,,$(obj)/$*.dtb,$(obj)/ramdisk.image.gz)
+$(obj)/treeImage.initrd.%: vmlinux $(obj)/dts/%.dtb $(wrapperbits) FORCE
+	$(call if_changed,wrap,treeboot-$*,,$(obj)/dts/$*.dtb,$(obj)/ramdisk.image.gz)
 
-$(obj)/treeImage.%: vmlinux $(obj)/%.dtb $(wrapperbits) FORCE
-	$(call if_changed,wrap,treeboot-$*,,$(obj)/$*.dtb)
+$(obj)/treeImage.%: vmlinux $(obj)/dts/%.dtb $(wrapperbits) FORCE
+	$(call if_changed,wrap,treeboot-$*,,$(obj)/dts/$*.dtb)
 
-# Rule to build device tree blobs
-$(obj)/%.dtb: $(src)/dts/%.dts FORCE
-	$(call if_changed_dep,dtc)
-
-$(obj)/%.dtb: $(src)/dts/fsl/%.dts FORCE
-	$(call if_changed_dep,dtc)
+# Needed for the above targets to work with dts/fsl/ files
+$(obj)/dts/%.dtb: $(obj)/dts/fsl/%.dtb
+	@cp $< $@
 
 # If there isn't a platform selected then just strip the vmlinux.
 ifeq (,$(image-y))
diff --git a/arch/powerpc/boot/addnote.c b/arch/powerpc/boot/addnote.c
index 9d9f6f3..53b3b26 100644
--- a/arch/powerpc/boot/addnote.c
+++ b/arch/powerpc/boot/addnote.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Program to hack in a PT_NOTE program header entry in an ELF file.
  * This is needed for OF on RS/6000s to load an image correctly.
@@ -8,11 +9,6 @@
  *
  * Adapted for 64 bit little endian images by Andrew Tauferner.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * Usage: addnote zImage
  */
 #include <stdio.h>
@@ -223,7 +219,11 @@
 	PUT_16(E_PHNUM, np + 2);
 
 	/* write back */
-	lseek(fd, (long) 0, SEEK_SET);
+	i = lseek(fd, (long) 0, SEEK_SET);
+	if (i < 0) {
+		perror("lseek");
+		exit(1);
+	}
 	i = write(fd, buf, n);
 	if (i < 0) {
 		perror("write");
diff --git a/arch/powerpc/boot/bamboo.c b/arch/powerpc/boot/bamboo.c
index b82cacb..dcdfa58 100644
--- a/arch/powerpc/boot/bamboo.c
+++ b/arch/powerpc/boot/bamboo.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright IBM Corporation, 2007
  * Josh Boyer <jwboyer@linux.vnet.ibm.com>
@@ -7,10 +8,6 @@
  *
  * Clocking code based on code by:
  * Stefan Roese <sr@denx.de>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2 of the License
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S
index 32dfe6d..92608f3 100644
--- a/arch/powerpc/boot/crt0.S
+++ b/arch/powerpc/boot/crt0.S
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) Paul Mackerras 1997.
  *
  * Adapted for 64 bit LE PowerPC by Andrew Tauferner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include "ppc_asm.h"
@@ -15,7 +10,7 @@
 RELA = 7
 RELACOUNT = 0x6ffffff9
 
-	.text
+	.data
 	/* A procedure descriptor used when booting this as a COFF file.
 	 * When making COFF, this comes first in the link and we're
 	 * linked at 0x500000.
@@ -23,6 +18,8 @@
 	.globl	_zimage_start_opd
 _zimage_start_opd:
 	.long	0x500000, 0, 0, 0
+	.text
+	b	_zimage_start
 
 #ifdef __powerpc64__
 .balign 8
diff --git a/arch/powerpc/boot/cuboot-52xx.c b/arch/powerpc/boot/cuboot-52xx.c
index 4c42ec8..b332056 100644
--- a/arch/powerpc/boot/cuboot-52xx.c
+++ b/arch/powerpc/boot/cuboot-52xx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for MPC5200
  *
@@ -5,10 +6,6 @@
  *
  * Copyright (c) 2007 Secret Lab Technologies Ltd.
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-824x.c b/arch/powerpc/boot/cuboot-824x.c
index ced90c5..15818cb 100644
--- a/arch/powerpc/boot/cuboot-824x.c
+++ b/arch/powerpc/boot/cuboot-824x.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for 824x
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-83xx.c b/arch/powerpc/boot/cuboot-83xx.c
index 61af1c1..4063c62 100644
--- a/arch/powerpc/boot/cuboot-83xx.c
+++ b/arch/powerpc/boot/cuboot-83xx.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for 83xx
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-85xx-cpm2.c b/arch/powerpc/boot/cuboot-85xx-cpm2.c
index 723872d..ac5115b 100644
--- a/arch/powerpc/boot/cuboot-85xx-cpm2.c
+++ b/arch/powerpc/boot/cuboot-85xx-cpm2.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for 85xx
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-85xx.c b/arch/powerpc/boot/cuboot-85xx.c
index 277ba4a..1466cc6 100644
--- a/arch/powerpc/boot/cuboot-85xx.c
+++ b/arch/powerpc/boot/cuboot-85xx.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for 85xx
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-8xx.c b/arch/powerpc/boot/cuboot-8xx.c
index c202c88..e4499fb 100644
--- a/arch/powerpc/boot/cuboot-8xx.c
+++ b/arch/powerpc/boot/cuboot-8xx.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for 8xx
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-acadia.c b/arch/powerpc/boot/cuboot-acadia.c
index 0634aba..46e9675 100644
--- a/arch/powerpc/boot/cuboot-acadia.c
+++ b/arch/powerpc/boot/cuboot-acadia.c
@@ -1,13 +1,10 @@
+// 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
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-amigaone.c b/arch/powerpc/boot/cuboot-amigaone.c
index d502967..f3b6d62 100644
--- a/arch/powerpc/boot/cuboot-amigaone.c
+++ b/arch/powerpc/boot/cuboot-amigaone.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for AmigaOne
  *
@@ -5,10 +6,6 @@
  *
  *   Based on cuboot-83xx.c
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-bamboo.c b/arch/powerpc/boot/cuboot-bamboo.c
index b5c30f7..a5dcf30 100644
--- a/arch/powerpc/boot/cuboot-bamboo.c
+++ b/arch/powerpc/boot/cuboot-bamboo.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Bamboo
  *
@@ -6,10 +7,6 @@
  * Copyright 2007 IBM Corporation
  *
  * Based on cuboot-ebony.c
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-ebony.c b/arch/powerpc/boot/cuboot-ebony.c
index 56564ba..3e602ee 100644
--- a/arch/powerpc/boot/cuboot-ebony.c
+++ b/arch/powerpc/boot/cuboot-ebony.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Ebony
  *
@@ -6,10 +7,6 @@
  * Copyright 2007 David Gibson, IBM Corporatio.
  *   Based on cuboot-83xx.c, which is:
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-hotfoot.c b/arch/powerpc/boot/cuboot-hotfoot.c
index 8f697b9..888a6b9 100644
--- a/arch/powerpc/boot/cuboot-hotfoot.c
+++ b/arch/powerpc/boot/cuboot-hotfoot.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Esteem 195E Hotfoot CPU Board
  *
  * Author: Solomon Peachy <solomon@linux-wlan.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-katmai.c b/arch/powerpc/boot/cuboot-katmai.c
index 5434d70..034a748 100644
--- a/arch/powerpc/boot/cuboot-katmai.c
+++ b/arch/powerpc/boot/cuboot-katmai.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Katmai
  *
@@ -8,10 +9,6 @@
  * Copyright 2007 David Gibson, IBM Corporation.
  *   Based on cuboot-83xx.c, which is:
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-kilauea.c b/arch/powerpc/boot/cuboot-kilauea.c
index 80cdad6..fda182f 100644
--- a/arch/powerpc/boot/cuboot-kilauea.c
+++ b/arch/powerpc/boot/cuboot-kilauea.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for PPC405EX. This image is already included
  * a dtb.
@@ -5,10 +6,6 @@
  * Author: Tiejun Chen <tiejun.chen@windriver.com>
  *
  * Copyright (C) 2009 Wind River Systems, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-mpc7448hpc2.c b/arch/powerpc/boot/cuboot-mpc7448hpc2.c
index 1b89532..335fb65 100644
--- a/arch/powerpc/boot/cuboot-mpc7448hpc2.c
+++ b/arch/powerpc/boot/cuboot-mpc7448hpc2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -7,12 +8,6 @@
  * Old U-boot compatibility for mpc7448hpc2 board
  * Based on the code of Scott Wood <scottwood@freescale.com>
  * for 83xx and 85xx.
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of  the GNU General  Public License as published by
- * the Free Software Foundation;  either version 2 of the  License, or
- * (at your option) any later version.
- *
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-pq2.c b/arch/powerpc/boot/cuboot-pq2.c
index 9c7d134..d32765c 100644
--- a/arch/powerpc/boot/cuboot-pq2.c
+++ b/arch/powerpc/boot/cuboot-pq2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for PowerQUICC II
  * (a.k.a. 82xx with CPM, not the 8240 family of chips)
@@ -5,10 +6,6 @@
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-rainier.c b/arch/powerpc/boot/cuboot-rainier.c
index 0a3fdde..0464785 100644
--- a/arch/powerpc/boot/cuboot-rainier.c
+++ b/arch/powerpc/boot/cuboot-rainier.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Rainier
  *
@@ -9,10 +10,6 @@
  *
  * Based on Bamboo code by Josh Boyer <jwboyer@linux.vnet.ibm.com>
  * Copyright IBM Corporation, 2007
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2 of the License
  */
 
 #include <stdarg.h>
diff --git a/arch/powerpc/boot/cuboot-sam440ep.c b/arch/powerpc/boot/cuboot-sam440ep.c
index ec10a47..d875119 100644
--- a/arch/powerpc/boot/cuboot-sam440ep.c
+++ b/arch/powerpc/boot/cuboot-sam440ep.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Sam440ep based off bamboo.c code
  * original copyrights below
@@ -10,10 +11,6 @@
  *
  * Modified from cuboot-bamboo.c for sam440ep:
  * Copyright 2008 Giuseppe Coviello <gicoviello@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-sequoia.c b/arch/powerpc/boot/cuboot-sequoia.c
index caf8f2e..e0285c2 100644
--- a/arch/powerpc/boot/cuboot-sequoia.c
+++ b/arch/powerpc/boot/cuboot-sequoia.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Sequoia
  *
@@ -9,10 +10,6 @@
  *
  * Based on Bamboo code by Josh Boyer <jwboyer@linux.vnet.ibm.com>
  * Copyright IBM Corporation, 2007
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2 of the License
  */
 
 #include <stdarg.h>
diff --git a/arch/powerpc/boot/cuboot-taishan.c b/arch/powerpc/boot/cuboot-taishan.c
index 9bc906a..3d40670 100644
--- a/arch/powerpc/boot/cuboot-taishan.c
+++ b/arch/powerpc/boot/cuboot-taishan.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Taishan
  *
@@ -8,10 +9,6 @@
  * Copyright 2007 David Gibson, IBM Corporation.
  *   Based on cuboot-83xx.c, which is:
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-warp.c b/arch/powerpc/boot/cuboot-warp.c
index 806df69..1ec0fa2 100644
--- a/arch/powerpc/boot/cuboot-warp.c
+++ b/arch/powerpc/boot/cuboot-warp.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2008 PIKA Technologies
  *   Sean MacLennan <smaclennan@pikatech.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot-yosemite.c b/arch/powerpc/boot/cuboot-yosemite.c
index cc6e338..ce3fdb7 100644
--- a/arch/powerpc/boot/cuboot-yosemite.c
+++ b/arch/powerpc/boot/cuboot-yosemite.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Yosemite
  *
  * Author: Josh Boyer <jwboyer@linux.vnet.ibm.com>
  *
  * Copyright 2008 IBM Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/cuboot.c b/arch/powerpc/boot/cuboot.c
index 7768b23..7f18665 100644
--- a/arch/powerpc/boot/cuboot.c
+++ b/arch/powerpc/boot/cuboot.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Compatibility for old (not device tree aware) U-Boot versions
  *
@@ -6,10 +7,6 @@
  *
  * Copyright 2007 David Gibson, IBM Corporation.
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/decompress.c b/arch/powerpc/boot/decompress.c
index 3aff442..8bf39ef 100644
--- a/arch/powerpc/boot/decompress.c
+++ b/arch/powerpc/boot/decompress.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Wrapper around the kernel's pre-boot decompression library.
  *
  * Copyright (C) IBM Corporation 2016.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include "elf.h"
diff --git a/arch/powerpc/boot/devtree.c b/arch/powerpc/boot/devtree.c
index a7e21a3..5d91036 100644
--- a/arch/powerpc/boot/devtree.c
+++ b/arch/powerpc/boot/devtree.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * devtree.c - convenience functions for device tree manipulation
  * Copyright 2007 David Gibson, IBM Corporation.
@@ -5,11 +6,6 @@
  *
  * Authors: David Gibson <david@gibson.dropbear.id.au>
  *	    Scott Wood <scottwood@freescale.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/div64.S b/arch/powerpc/boot/div64.S
index bbcb8a4..4354928 100644
--- a/arch/powerpc/boot/div64.S
+++ b/arch/powerpc/boot/div64.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Divide a 64-bit unsigned number by a 32-bit unsigned number.
  * This routine assumes that the top 32 bits of the dividend are
@@ -7,11 +8,6 @@
  * On exit, r3 contains the remainder.
  *
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include "ppc_asm.h"
 
diff --git a/arch/powerpc/boot/dts/Makefile b/arch/powerpc/boot/dts/Makefile
new file mode 100644
index 0000000..1cbc0e4
--- /dev/null
+++ b/arch/powerpc/boot/dts/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+
+subdir-y += fsl
+
+dtstree		:= $(srctree)/$(src)
+dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
+dtb-$(CONFIG_XILINX_VIRTEX440_GENERIC_BOARD) += virtex440-ml507.dtb virtex440-ml510.dtb
diff --git a/arch/powerpc/boot/dts/a3m071.dts b/arch/powerpc/boot/dts/a3m071.dts
index 187ce45..034cfd8 100644
--- a/arch/powerpc/boot/dts/a3m071.dts
+++ b/arch/powerpc/boot/dts/a3m071.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * a3m071 board Device Tree Source
  *
@@ -8,11 +9,6 @@
  *
  * Copyright (C) 2007 Semihalf
  * Marian Balakowicz <m8@semihalf.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/a4m072.dts b/arch/powerpc/boot/dts/a4m072.dts
index 1f02034..a9cef57 100644
--- a/arch/powerpc/boot/dts/a4m072.dts
+++ b/arch/powerpc/boot/dts/a4m072.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * a4m072 board Device Tree Source
  *
@@ -6,11 +7,6 @@
  *
  * Copyright (C) 2007 Semihalf
  * Marian Balakowicz <m8@semihalf.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/ac14xx.dts b/arch/powerpc/boot/dts/ac14xx.dts
index 0be5c4f..5d8877e 100644
--- a/arch/powerpc/boot/dts/ac14xx.dts
+++ b/arch/powerpc/boot/dts/ac14xx.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree Source for the MPC5121e based ac14xx board
  *
  * Copyright 2012 Anatolij Gustschin <agust@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 
diff --git a/arch/powerpc/boot/dts/adder875-redboot.dts b/arch/powerpc/boot/dts/adder875-redboot.dts
index 7f5ff41..b51c97a 100644
--- a/arch/powerpc/boot/dts/adder875-redboot.dts
+++ b/arch/powerpc/boot/dts/adder875-redboot.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree Source for MPC885 ADS running RedBoot
  *
  * Copyright 2006 MontaVista Software, Inc.
  * Copyright 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/adder875-uboot.dts b/arch/powerpc/boot/dts/adder875-uboot.dts
index bd9f33c..ec77610 100644
--- a/arch/powerpc/boot/dts/adder875-uboot.dts
+++ b/arch/powerpc/boot/dts/adder875-uboot.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree Source for MPC885 ADS running U-Boot
  *
  * Copyright 2006 MontaVista Software, Inc.
  * Copyright 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/akebono.dts b/arch/powerpc/boot/dts/akebono.dts
index 8a7a101..cd9d660 100644
--- a/arch/powerpc/boot/dts/akebono.dts
+++ b/arch/powerpc/boot/dts/akebono.dts
@@ -40,7 +40,7 @@
 			d-cache-size = <32768>;
 			dcr-controller;
 			dcr-access-method = "native";
-			status = "ok";
+			status = "okay";
 		};
 		cpu@1 {
 			device_type = "cpu";
diff --git a/arch/powerpc/boot/dts/amigaone.dts b/arch/powerpc/boot/dts/amigaone.dts
index 7124301..5c68db3 100644
--- a/arch/powerpc/boot/dts/amigaone.dts
+++ b/arch/powerpc/boot/dts/amigaone.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * AmigaOne Device Tree Source
  *
  * Copyright 2008 Gerhard Pircher (gerhard_pircher@gmx.net)
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/arches.dts b/arch/powerpc/boot/dts/arches.dts
index 30f4120..75a376a 100644
--- a/arch/powerpc/boot/dts/arches.dts
+++ b/arch/powerpc/boot/dts/arches.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree Source for AMCC Arches (dual 460GT board)
  *
@@ -11,21 +12,6 @@
  *
  * See file CREDITS for list of people who contributed to this
  * project.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/asp834x-redboot.dts b/arch/powerpc/boot/dts/asp834x-redboot.dts
index e987b5a..52a8456 100644
--- a/arch/powerpc/boot/dts/asp834x-redboot.dts
+++ b/arch/powerpc/boot/dts/asp834x-redboot.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Analogue & Micro ASP8347 Device Tree Source
  *
  * Copyright 2008 Codehermit
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/bamboo.dts b/arch/powerpc/boot/dts/bamboo.dts
index 538e42b..b5861fa 100644
--- a/arch/powerpc/boot/dts/bamboo.dts
+++ b/arch/powerpc/boot/dts/bamboo.dts
@@ -268,8 +268,10 @@
 			/* 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
+			 * The chip also supports a larger memory range but
+			 * it's not naturally aligned, so our code will break
 			 */
-			ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x40000000
+			ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x20000000
 				  0x02000000 0x00000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00100000
 				  0x01000000 0x00000000 0x00000000 0x00000000 0xe8000000 0x00000000 0x00010000>;
 
diff --git a/arch/powerpc/boot/dts/bluestone.dts b/arch/powerpc/boot/dts/bluestone.dts
index b0b26d8..cc965a1 100644
--- a/arch/powerpc/boot/dts/bluestone.dts
+++ b/arch/powerpc/boot/dts/bluestone.dts
@@ -1,24 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree for Bluestone (APM821xx) board.
  *
  * Copyright (c) 2010, Applied Micro Circuits Corporation
  * Author: Tirumala R Marri <tmarri@apm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- *
  */
 
 /dts-v1/;
@@ -109,7 +94,7 @@
 
 	OCM: ocm@400040000 {
 		compatible = "ibm,ocm";
-		status = "ok";
+		status = "okay";
 		cell-index = <1>;
 		/* configured in U-Boot */
 		reg = <4 0x00040000 0x8000>; /* 32K */
diff --git a/arch/powerpc/boot/dts/charon.dts b/arch/powerpc/boot/dts/charon.dts
index 0e00e50..408b486 100644
--- a/arch/powerpc/boot/dts/charon.dts
+++ b/arch/powerpc/boot/dts/charon.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * charon board Device Tree Source
  *
@@ -6,11 +7,6 @@
  *
  * Copyright (C) 2010 DENX Software Engineering GmbH
  * Heiko Schocher <hs@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/cm5200.dts b/arch/powerpc/boot/dts/cm5200.dts
index fb580dd..66cae7b 100644
--- a/arch/powerpc/boot/dts/cm5200.dts
+++ b/arch/powerpc/boot/dts/cm5200.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * CM5200 board Device Tree Source
  *
  * Copyright (C) 2007 Semihalf
  * Marian Balakowicz <m8@semihalf.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/currituck.dts b/arch/powerpc/boot/dts/currituck.dts
index a04a4fc..b6d87b9 100644
--- a/arch/powerpc/boot/dts/currituck.dts
+++ b/arch/powerpc/boot/dts/currituck.dts
@@ -39,7 +39,7 @@
 			d-cache-size = <32768>;
 			dcr-controller;
 			dcr-access-method = "native";
-			status = "ok";
+			status = "okay";
 		};
 		cpu@1 {
 			device_type = "cpu";
diff --git a/arch/powerpc/boot/dts/digsy_mtc.dts b/arch/powerpc/boot/dts/digsy_mtc.dts
index c3922fc..0e5e9d3 100644
--- a/arch/powerpc/boot/dts/digsy_mtc.dts
+++ b/arch/powerpc/boot/dts/digsy_mtc.dts
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Digsy MTC board Device Tree Source
  *
  * Copyright (C) 2009 Semihalf
  *
  * Based on the CM5200 by M. Balakowicz
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/ep8248e.dts b/arch/powerpc/boot/dts/ep8248e.dts
index 8b3a49f..9ae2d92 100644
--- a/arch/powerpc/boot/dts/ep8248e.dts
+++ b/arch/powerpc/boot/dts/ep8248e.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree for the Embedded Planet EP8248E board running PlanetCore.
  *
  * Copyright 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/ep88xc.dts b/arch/powerpc/boot/dts/ep88xc.dts
index 2aa5bf5..b6b7e97 100644
--- a/arch/powerpc/boot/dts/ep88xc.dts
+++ b/arch/powerpc/boot/dts/ep88xc.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * EP88xC Device Tree Source
  *
  * Copyright 2006 MontaVista Software, Inc.
  * Copyright 2007,2008 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/fsl/Makefile b/arch/powerpc/boot/dts/fsl/Makefile
new file mode 100644
index 0000000..3bae982
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+
+dtstree		:= $(srctree)/$(src)
+dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
diff --git a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
index 88d8423..bb7b9b9 100644
--- a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
@@ -70,14 +70,14 @@
 		cpu0: PowerPC,e6500@0 {
 			device_type = "cpu";
 			reg = <0 1>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu1: PowerPC,e6500@2 {
 			device_type = "cpu";
 			reg = <2 3>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
diff --git a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
index f3f968c..388ba1b 100644
--- a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
@@ -75,28 +75,28 @@
 		cpu0: PowerPC,e6500@0 {
 			device_type = "cpu";
 			reg = <0 1>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu1: PowerPC,e6500@2 {
 			device_type = "cpu";
 			reg = <2 3>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu2: PowerPC,e6500@4 {
 			device_type = "cpu";
 			reg = <4 5>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu3: PowerPC,e6500@6 {
 			device_type = "cpu";
 			reg = <6 7>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
diff --git a/arch/powerpc/boot/dts/fsl/b4qds.dtsi b/arch/powerpc/boot/dts/fsl/b4qds.dtsi
index 999efd3..05be919 100644
--- a/arch/powerpc/boot/dts/fsl/b4qds.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4qds.dtsi
@@ -40,6 +40,7 @@
 	interrupt-parent = <&mpic>;
 
 	aliases {
+		crypto = &crypto;
 		phy_sgmii_10 = &phy_sgmii_10;
 		phy_sgmii_11 = &phy_sgmii_11;
 		phy_sgmii_1c = &phy_sgmii_1c;
diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
index 1b33f51..4f044b4 100644
--- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
@@ -398,21 +398,6 @@
 	};
 
 /include/ "qoriq-clockgen2.dtsi"
-	clockgen: global-utilities@e1000 {
-		compatible = "fsl,b4-clockgen", "fsl,qoriq-clockgen-2.0";
-		reg = <0xe1000 0x1000>;
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 0x4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				<&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll0-div4",
-				"pll1", "pll1-div2", "pll1-div4";
-			clock-output-names = "cmux0";
-		};
-	};
 
 	rcpm: global-utilities@e2000 {
 		compatible = "fsl,b4-rcpm", "fsl,qoriq-rcpm-2.0";
diff --git a/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts b/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts
index 26366e6..8da9842 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * BSC9131 RDB Device Tree Source
  *
  * Copyright 2011-2012 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "bsc9131si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts
index 56e6f13..7cb2158 100644
--- a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts
+++ b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * BSC9132 QDS Device Tree Source
  *
  * Copyright 2014 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "bsc9132si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/cyrus_p5020.dts b/arch/powerpc/boot/dts/fsl/cyrus_p5020.dts
index c603390..40ba060 100644
--- a/arch/powerpc/boot/dts/fsl/cyrus_p5020.dts
+++ b/arch/powerpc/boot/dts/fsl/cyrus_p5020.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Cyrus 5020 Device Tree Source, based on p5020ds.dts
  *
@@ -5,11 +6,6 @@
  *
  * p5020ds.dts copyright:
  * Copyright 2010 - 2014 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p5020si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/ge_imp3a.dts b/arch/powerpc/boot/dts/fsl/ge_imp3a.dts
index a2bb47f..da3de8e 100644
--- a/arch/powerpc/boot/dts/fsl/ge_imp3a.dts
+++ b/arch/powerpc/boot/dts/fsl/ge_imp3a.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * GE IMP3A Device Tree Source
  *
  * Copyright 2010-2011 GE Intelligent Platforms Embedded Systems, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Based on: P2020 DS Device Tree Source
  * Copyright 2009 Freescale Semiconductor Inc.
  */
diff --git a/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts b/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts
index c88d4ef..fc92bb0 100644
--- a/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts
+++ b/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * GE PPC9A Device Tree Source
  *
  * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Based on: SBS CM6 Device Tree Source
  * Copyright 2007 SBS Technologies GmbH & Co. KG
  * And: mpc8641_hpcn.dts (MPC8641 HPCN Device Tree Source)
diff --git a/arch/powerpc/boot/dts/fsl/gef_sbc310.dts b/arch/powerpc/boot/dts/fsl/gef_sbc310.dts
index 8385157..47ae85c 100644
--- a/arch/powerpc/boot/dts/fsl/gef_sbc310.dts
+++ b/arch/powerpc/boot/dts/fsl/gef_sbc310.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * GE SBC310 Device Tree Source
  *
  * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Based on: SBS CM6 Device Tree Source
  * Copyright 2007 SBS Technologies GmbH & Co. KG
  * And: mpc8641_hpcn.dts (MPC8641 HPCN Device Tree Source)
diff --git a/arch/powerpc/boot/dts/fsl/gef_sbc610.dts b/arch/powerpc/boot/dts/fsl/gef_sbc610.dts
index ff423ab..5322be4 100644
--- a/arch/powerpc/boot/dts/fsl/gef_sbc610.dts
+++ b/arch/powerpc/boot/dts/fsl/gef_sbc610.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * GE SBC610 Device Tree Source
  *
  * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Based on: SBS CM6 Device Tree Source
  * Copyright 2007 SBS Technologies GmbH & Co. KG
  * And: mpc8641_hpcn.dts (MPC8641 HPCN Device Tree Source)
diff --git a/arch/powerpc/boot/dts/fsl/kmcent2.dts b/arch/powerpc/boot/dts/fsl/kmcent2.dts
index 3094df0..48b7f97 100644
--- a/arch/powerpc/boot/dts/fsl/kmcent2.dts
+++ b/arch/powerpc/boot/dts/fsl/kmcent2.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Keymile kmcent2 Device Tree Source, based on T1040RDB DTS
  *
@@ -5,11 +6,6 @@
  * Valentin Longchamp, Keymile AG, valentin.longchamp@keymile.com
  *
  * Copyright 2014 - 2015 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "t104xsi-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/kmcoge4.dts b/arch/powerpc/boot/dts/fsl/kmcoge4.dts
index e103c0f..1c5f942 100644
--- a/arch/powerpc/boot/dts/fsl/kmcoge4.dts
+++ b/arch/powerpc/boot/dts/fsl/kmcoge4.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Keymile kmcoge4 Device Tree Source, based on the P2041RDB DTS
  *
@@ -5,11 +6,6 @@
  * Valentin Longchamp, Keymile AG, valentin.longchamp@keymile.com
  *
  * Copyright 2011 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p2041si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8536ds.dts b/arch/powerpc/boot/dts/fsl/mpc8536ds.dts
index 96cdce8..ab6997a 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8536ds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8536ds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8536 DS Device Tree Source
  *
  * Copyright 2008, 2011 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8536si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8536ds_36b.dts b/arch/powerpc/boot/dts/fsl/mpc8536ds_36b.dts
index 38d326c..1b79974 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8536ds_36b.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8536ds_36b.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8536DS Device Tree Source (36-bit address map)
  *
  * Copyright 2008-2009, 2011 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8536si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8540ads.dts b/arch/powerpc/boot/dts/fsl/mpc8540ads.dts
index e6d0b16..18a8851 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8540ads.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8540ads.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8540 ADS Device Tree Source
  *
  * Copyright 2006, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/fsl/mpc8541cds.dts b/arch/powerpc/boot/dts/fsl/mpc8541cds.dts
index 9fa2c73..ac381e7 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8541cds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8541cds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8541 CDS Device Tree Source
  *
  * Copyright 2006, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/fsl/mpc8544ds.dts b/arch/powerpc/boot/dts/fsl/mpc8544ds.dts
index 5a6e468..f4a8b71 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8544ds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8544ds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8544 DS Device Tree Source
  *
  * Copyright 2007, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8544si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8548cds_32b.dts b/arch/powerpc/boot/dts/fsl/mpc8548cds_32b.dts
index e4620bb..f6ba4a9 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8548cds_32b.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8548cds_32b.dts
@@ -1,12 +1,8 @@
+// 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.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8548si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8548cds_36b.dts b/arch/powerpc/boot/dts/fsl/mpc8548cds_36b.dts
index bca7c09..32e9076 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8548cds_36b.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8548cds_36b.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8548 CDS Device Tree Source (36-bit address map)
  *
  * Copyright 2012 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8548si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8555cds.dts b/arch/powerpc/boot/dts/fsl/mpc8555cds.dts
index 272f08c..9f58db2 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8555cds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8555cds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8555 CDS Device Tree Source
  *
  * Copyright 2006, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/fsl/mpc8560ads.dts b/arch/powerpc/boot/dts/fsl/mpc8560ads.dts
index 7a822b0..a24722c 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8560ads.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8560ads.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8560 ADS Device Tree Source
  *
  * Copyright 2006, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/fsl/mpc8568mds.dts b/arch/powerpc/boot/dts/fsl/mpc8568mds.dts
index bc3e803..3603b5a 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8568mds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8568mds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8568E MDS Device Tree Source
  *
  * Copyright 2007, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8568si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8569mds.dts b/arch/powerpc/boot/dts/fsl/mpc8569mds.dts
index d8367ce..206614e 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8569mds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8569mds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8569E MDS Device Tree Source
  *
  * Copyright (C) 2009 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8569si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8572ds.dts b/arch/powerpc/boot/dts/fsl/mpc8572ds.dts
index 8ee5b24..679d53c 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8572ds.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8572ds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8572 DS Device Tree Source
  *
  * Copyright 2007-2009 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8572si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8572ds_36b.dts b/arch/powerpc/boot/dts/fsl/mpc8572ds_36b.dts
index 5c48b46..f2abce2 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8572ds_36b.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8572ds_36b.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8572DS Device Tree Source (36-bit address map)
  *
  * Copyright 2007-2009 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8572si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8572ds_camp_core0.dts b/arch/powerpc/boot/dts/fsl/mpc8572ds_camp_core0.dts
index ef9ef56..d1a4993 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8572ds_camp_core0.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8572ds_camp_core0.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8572 DS Core0 Device Tree Source in CAMP mode.
  *
@@ -7,11 +8,6 @@
  * eth1, crypto, pci0, pci1.
  *
  * Copyright 2007-2009 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8572ds.dts"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8572ds_camp_core1.dts b/arch/powerpc/boot/dts/fsl/mpc8572ds_camp_core1.dts
index 24564ee..63e8243 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8572ds_camp_core1.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8572ds_camp_core1.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8572 DS Core1 Device Tree Source in CAMP mode.
  *
@@ -8,11 +9,6 @@
  * Please note to add "-b 1" for core1's dts compiling.
  *
  * Copyright 2007-2009 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8572ds.dts"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts b/arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts
index 11bea3e..f7a2430 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8641 HPCN Device Tree Source
  *
  * Copyright 2006 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8641si-pre.dtsi"
@@ -169,100 +165,100 @@
 		interrupt-map-mask = <0xff00 0 0 7>;
 		interrupt-map = <
 			/* IDSEL 0x11 func 0 - PCI slot 1 */
-			0x8800 0 0 1 &mpic 2 1
-			0x8800 0 0 2 &mpic 3 1
-			0x8800 0 0 3 &mpic 4 1
-			0x8800 0 0 4 &mpic 1 1
+			0x8800 0 0 1 &mpic 2 1 0 0
+			0x8800 0 0 2 &mpic 3 1 0 0
+			0x8800 0 0 3 &mpic 4 1 0 0
+			0x8800 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 1 - PCI slot 1 */
-			0x8900 0 0 1 &mpic 2 1
-			0x8900 0 0 2 &mpic 3 1
-			0x8900 0 0 3 &mpic 4 1
-			0x8900 0 0 4 &mpic 1 1
+			0x8900 0 0 1 &mpic 2 1 0 0
+			0x8900 0 0 2 &mpic 3 1 0 0
+			0x8900 0 0 3 &mpic 4 1 0 0
+			0x8900 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 2 - PCI slot 1 */
-			0x8a00 0 0 1 &mpic 2 1
-			0x8a00 0 0 2 &mpic 3 1
-			0x8a00 0 0 3 &mpic 4 1
-			0x8a00 0 0 4 &mpic 1 1
+			0x8a00 0 0 1 &mpic 2 1 0 0
+			0x8a00 0 0 2 &mpic 3 1 0 0
+			0x8a00 0 0 3 &mpic 4 1 0 0
+			0x8a00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 3 - PCI slot 1 */
-			0x8b00 0 0 1 &mpic 2 1
-			0x8b00 0 0 2 &mpic 3 1
-			0x8b00 0 0 3 &mpic 4 1
-			0x8b00 0 0 4 &mpic 1 1
+			0x8b00 0 0 1 &mpic 2 1 0 0
+			0x8b00 0 0 2 &mpic 3 1 0 0
+			0x8b00 0 0 3 &mpic 4 1 0 0
+			0x8b00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 4 - PCI slot 1 */
-			0x8c00 0 0 1 &mpic 2 1
-			0x8c00 0 0 2 &mpic 3 1
-			0x8c00 0 0 3 &mpic 4 1
-			0x8c00 0 0 4 &mpic 1 1
+			0x8c00 0 0 1 &mpic 2 1 0 0
+			0x8c00 0 0 2 &mpic 3 1 0 0
+			0x8c00 0 0 3 &mpic 4 1 0 0
+			0x8c00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 5 - PCI slot 1 */
-			0x8d00 0 0 1 &mpic 2 1
-			0x8d00 0 0 2 &mpic 3 1
-			0x8d00 0 0 3 &mpic 4 1
-			0x8d00 0 0 4 &mpic 1 1
+			0x8d00 0 0 1 &mpic 2 1 0 0
+			0x8d00 0 0 2 &mpic 3 1 0 0
+			0x8d00 0 0 3 &mpic 4 1 0 0
+			0x8d00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 6 - PCI slot 1 */
-			0x8e00 0 0 1 &mpic 2 1
-			0x8e00 0 0 2 &mpic 3 1
-			0x8e00 0 0 3 &mpic 4 1
-			0x8e00 0 0 4 &mpic 1 1
+			0x8e00 0 0 1 &mpic 2 1 0 0
+			0x8e00 0 0 2 &mpic 3 1 0 0
+			0x8e00 0 0 3 &mpic 4 1 0 0
+			0x8e00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 7 - PCI slot 1 */
-			0x8f00 0 0 1 &mpic 2 1
-			0x8f00 0 0 2 &mpic 3 1
-			0x8f00 0 0 3 &mpic 4 1
-			0x8f00 0 0 4 &mpic 1 1
+			0x8f00 0 0 1 &mpic 2 1 0 0
+			0x8f00 0 0 2 &mpic 3 1 0 0
+			0x8f00 0 0 3 &mpic 4 1 0 0
+			0x8f00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x12 func 0 - PCI slot 2 */
-			0x9000 0 0 1 &mpic 3 1
-			0x9000 0 0 2 &mpic 4 1
-			0x9000 0 0 3 &mpic 1 1
-			0x9000 0 0 4 &mpic 2 1
+			0x9000 0 0 1 &mpic 3 1 0 0
+			0x9000 0 0 2 &mpic 4 1 0 0
+			0x9000 0 0 3 &mpic 1 1 0 0
+			0x9000 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 1 - PCI slot 2 */
-			0x9100 0 0 1 &mpic 3 1
-			0x9100 0 0 2 &mpic 4 1
-			0x9100 0 0 3 &mpic 1 1
-			0x9100 0 0 4 &mpic 2 1
+			0x9100 0 0 1 &mpic 3 1 0 0
+			0x9100 0 0 2 &mpic 4 1 0 0
+			0x9100 0 0 3 &mpic 1 1 0 0
+			0x9100 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 2 - PCI slot 2 */
-			0x9200 0 0 1 &mpic 3 1
-			0x9200 0 0 2 &mpic 4 1
-			0x9200 0 0 3 &mpic 1 1
-			0x9200 0 0 4 &mpic 2 1
+			0x9200 0 0 1 &mpic 3 1 0 0
+			0x9200 0 0 2 &mpic 4 1 0 0
+			0x9200 0 0 3 &mpic 1 1 0 0
+			0x9200 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 3 - PCI slot 2 */
-			0x9300 0 0 1 &mpic 3 1
-			0x9300 0 0 2 &mpic 4 1
-			0x9300 0 0 3 &mpic 1 1
-			0x9300 0 0 4 &mpic 2 1
+			0x9300 0 0 1 &mpic 3 1 0 0
+			0x9300 0 0 2 &mpic 4 1 0 0
+			0x9300 0 0 3 &mpic 1 1 0 0
+			0x9300 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 4 - PCI slot 2 */
-			0x9400 0 0 1 &mpic 3 1
-			0x9400 0 0 2 &mpic 4 1
-			0x9400 0 0 3 &mpic 1 1
-			0x9400 0 0 4 &mpic 2 1
+			0x9400 0 0 1 &mpic 3 1 0 0
+			0x9400 0 0 2 &mpic 4 1 0 0
+			0x9400 0 0 3 &mpic 1 1 0 0
+			0x9400 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 5 - PCI slot 2 */
-			0x9500 0 0 1 &mpic 3 1
-			0x9500 0 0 2 &mpic 4 1
-			0x9500 0 0 3 &mpic 1 1
-			0x9500 0 0 4 &mpic 2 1
+			0x9500 0 0 1 &mpic 3 1 0 0
+			0x9500 0 0 2 &mpic 4 1 0 0
+			0x9500 0 0 3 &mpic 1 1 0 0
+			0x9500 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 6 - PCI slot 2 */
-			0x9600 0 0 1 &mpic 3 1
-			0x9600 0 0 2 &mpic 4 1
-			0x9600 0 0 3 &mpic 1 1
-			0x9600 0 0 4 &mpic 2 1
+			0x9600 0 0 1 &mpic 3 1 0 0
+			0x9600 0 0 2 &mpic 4 1 0 0
+			0x9600 0 0 3 &mpic 1 1 0 0
+			0x9600 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 7 - PCI slot 2 */
-			0x9700 0 0 1 &mpic 3 1
-			0x9700 0 0 2 &mpic 4 1
-			0x9700 0 0 3 &mpic 1 1
-			0x9700 0 0 4 &mpic 2 1
+			0x9700 0 0 1 &mpic 3 1 0 0
+			0x9700 0 0 2 &mpic 4 1 0 0
+			0x9700 0 0 3 &mpic 1 1 0 0
+			0x9700 0 0 4 &mpic 2 1 0 0
 
 			// IDSEL 0x1c  USB
 			0xe000 0 0 1 &i8259 12 2
diff --git a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts b/arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts
index 7ff6204..3f5f7a9 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts
+++ b/arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8641 HPCN Device Tree Source
  *
  * Copyright 2008-2009 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8641si-pre.dtsi"
@@ -136,100 +132,100 @@
 		interrupt-map-mask = <0xff00 0 0 7>;
 		interrupt-map = <
 			/* IDSEL 0x11 func 0 - PCI slot 1 */
-			0x8800 0 0 1 &mpic 2 1
-			0x8800 0 0 2 &mpic 3 1
-			0x8800 0 0 3 &mpic 4 1
-			0x8800 0 0 4 &mpic 1 1
+			0x8800 0 0 1 &mpic 2 1 0 0
+			0x8800 0 0 2 &mpic 3 1 0 0
+			0x8800 0 0 3 &mpic 4 1 0 0
+			0x8800 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 1 - PCI slot 1 */
-			0x8900 0 0 1 &mpic 2 1
-			0x8900 0 0 2 &mpic 3 1
-			0x8900 0 0 3 &mpic 4 1
-			0x8900 0 0 4 &mpic 1 1
+			0x8900 0 0 1 &mpic 2 1 0 0
+			0x8900 0 0 2 &mpic 3 1 0 0
+			0x8900 0 0 3 &mpic 4 1 0 0
+			0x8900 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 2 - PCI slot 1 */
-			0x8a00 0 0 1 &mpic 2 1
-			0x8a00 0 0 2 &mpic 3 1
-			0x8a00 0 0 3 &mpic 4 1
-			0x8a00 0 0 4 &mpic 1 1
+			0x8a00 0 0 1 &mpic 2 1 0 0
+			0x8a00 0 0 2 &mpic 3 1 0 0
+			0x8a00 0 0 3 &mpic 4 1 0 0
+			0x8a00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 3 - PCI slot 1 */
-			0x8b00 0 0 1 &mpic 2 1
-			0x8b00 0 0 2 &mpic 3 1
-			0x8b00 0 0 3 &mpic 4 1
-			0x8b00 0 0 4 &mpic 1 1
+			0x8b00 0 0 1 &mpic 2 1 0 0
+			0x8b00 0 0 2 &mpic 3 1 0 0
+			0x8b00 0 0 3 &mpic 4 1 0 0
+			0x8b00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 4 - PCI slot 1 */
-			0x8c00 0 0 1 &mpic 2 1
-			0x8c00 0 0 2 &mpic 3 1
-			0x8c00 0 0 3 &mpic 4 1
-			0x8c00 0 0 4 &mpic 1 1
+			0x8c00 0 0 1 &mpic 2 1 0 0
+			0x8c00 0 0 2 &mpic 3 1 0 0
+			0x8c00 0 0 3 &mpic 4 1 0 0
+			0x8c00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 5 - PCI slot 1 */
-			0x8d00 0 0 1 &mpic 2 1
-			0x8d00 0 0 2 &mpic 3 1
-			0x8d00 0 0 3 &mpic 4 1
-			0x8d00 0 0 4 &mpic 1 1
+			0x8d00 0 0 1 &mpic 2 1 0 0
+			0x8d00 0 0 2 &mpic 3 1 0 0
+			0x8d00 0 0 3 &mpic 4 1 0 0
+			0x8d00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 6 - PCI slot 1 */
-			0x8e00 0 0 1 &mpic 2 1
-			0x8e00 0 0 2 &mpic 3 1
-			0x8e00 0 0 3 &mpic 4 1
-			0x8e00 0 0 4 &mpic 1 1
+			0x8e00 0 0 1 &mpic 2 1 0 0
+			0x8e00 0 0 2 &mpic 3 1 0 0
+			0x8e00 0 0 3 &mpic 4 1 0 0
+			0x8e00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x11 func 7 - PCI slot 1 */
-			0x8f00 0 0 1 &mpic 2 1
-			0x8f00 0 0 2 &mpic 3 1
-			0x8f00 0 0 3 &mpic 4 1
-			0x8f00 0 0 4 &mpic 1 1
+			0x8f00 0 0 1 &mpic 2 1 0 0
+			0x8f00 0 0 2 &mpic 3 1 0 0
+			0x8f00 0 0 3 &mpic 4 1 0 0
+			0x8f00 0 0 4 &mpic 1 1 0 0
 
 			/* IDSEL 0x12 func 0 - PCI slot 2 */
-			0x9000 0 0 1 &mpic 3 1
-			0x9000 0 0 2 &mpic 4 1
-			0x9000 0 0 3 &mpic 1 1
-			0x9000 0 0 4 &mpic 2 1
+			0x9000 0 0 1 &mpic 3 1 0 0
+			0x9000 0 0 2 &mpic 4 1 0 0
+			0x9000 0 0 3 &mpic 1 1 0 0
+			0x9000 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 1 - PCI slot 2 */
-			0x9100 0 0 1 &mpic 3 1
-			0x9100 0 0 2 &mpic 4 1
-			0x9100 0 0 3 &mpic 1 1
-			0x9100 0 0 4 &mpic 2 1
+			0x9100 0 0 1 &mpic 3 1 0 0
+			0x9100 0 0 2 &mpic 4 1 0 0
+			0x9100 0 0 3 &mpic 1 1 0 0
+			0x9100 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 2 - PCI slot 2 */
-			0x9200 0 0 1 &mpic 3 1
-			0x9200 0 0 2 &mpic 4 1
-			0x9200 0 0 3 &mpic 1 1
-			0x9200 0 0 4 &mpic 2 1
+			0x9200 0 0 1 &mpic 3 1 0 0
+			0x9200 0 0 2 &mpic 4 1 0 0
+			0x9200 0 0 3 &mpic 1 1 0 0
+			0x9200 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 3 - PCI slot 2 */
-			0x9300 0 0 1 &mpic 3 1
-			0x9300 0 0 2 &mpic 4 1
-			0x9300 0 0 3 &mpic 1 1
-			0x9300 0 0 4 &mpic 2 1
+			0x9300 0 0 1 &mpic 3 1 0 0
+			0x9300 0 0 2 &mpic 4 1 0 0
+			0x9300 0 0 3 &mpic 1 1 0 0
+			0x9300 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 4 - PCI slot 2 */
-			0x9400 0 0 1 &mpic 3 1
-			0x9400 0 0 2 &mpic 4 1
-			0x9400 0 0 3 &mpic 1 1
-			0x9400 0 0 4 &mpic 2 1
+			0x9400 0 0 1 &mpic 3 1 0 0
+			0x9400 0 0 2 &mpic 4 1 0 0
+			0x9400 0 0 3 &mpic 1 1 0 0
+			0x9400 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 5 - PCI slot 2 */
-			0x9500 0 0 1 &mpic 3 1
-			0x9500 0 0 2 &mpic 4 1
-			0x9500 0 0 3 &mpic 1 1
-			0x9500 0 0 4 &mpic 2 1
+			0x9500 0 0 1 &mpic 3 1 0 0
+			0x9500 0 0 2 &mpic 4 1 0 0
+			0x9500 0 0 3 &mpic 1 1 0 0
+			0x9500 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 6 - PCI slot 2 */
-			0x9600 0 0 1 &mpic 3 1
-			0x9600 0 0 2 &mpic 4 1
-			0x9600 0 0 3 &mpic 1 1
-			0x9600 0 0 4 &mpic 2 1
+			0x9600 0 0 1 &mpic 3 1 0 0
+			0x9600 0 0 2 &mpic 4 1 0 0
+			0x9600 0 0 3 &mpic 1 1 0 0
+			0x9600 0 0 4 &mpic 2 1 0 0
 
 			/* IDSEL 0x12 func 7 - PCI slot 2 */
-			0x9700 0 0 1 &mpic 3 1
-			0x9700 0 0 2 &mpic 4 1
-			0x9700 0 0 3 &mpic 1 1
-			0x9700 0 0 4 &mpic 2 1
+			0x9700 0 0 1 &mpic 3 1 0 0
+			0x9700 0 0 2 &mpic 4 1 0 0
+			0x9700 0 0 3 &mpic 1 1 0 0
+			0x9700 0 0 4 &mpic 2 1 0 0
 
 			// IDSEL 0x1c  USB
 			0xe000 0 0 1 &i8259 12 2
diff --git a/arch/powerpc/boot/dts/fsl/mpc8641si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8641si-post.dtsi
index eeb7c65..77900b9 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8641si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8641si-post.dtsi
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8641 Silicon/SoC Device Tree Source (post include)
  *
  * Copyright 2016 Elettra-Sincrotrone Trieste S.C.p.A.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 &lbc {
@@ -97,6 +92,7 @@
 &pci0 {
 	compatible = "fsl,mpc8641-pcie";
 	device_type = "pci";
+	#interrupt-cells = <1>;
 	#size-cells = <2>;
 	#address-cells = <3>;
 	bus-range = <0x0 0xff>;
@@ -123,6 +119,7 @@
 &pci1 {
 	compatible = "fsl,mpc8641-pcie";
 	device_type = "pci";
+	#interrupt-cells = <1>;
 	#size-cells = <2>;
 	#address-cells = <3>;
 	bus-range = <0x0 0xff>;
diff --git a/arch/powerpc/boot/dts/fsl/mpc8641si-pre.dtsi b/arch/powerpc/boot/dts/fsl/mpc8641si-pre.dtsi
index 7c6db6f..a9f7e79 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8641si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8641si-pre.dtsi
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8641 Silicon/SoC Device Tree Source (pre include)
  *
  * Copyright 2016 Elettra-Sincrotrone Trieste S.C.p.A.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/fsl/mvme2500.dts b/arch/powerpc/boot/dts/fsl/mvme2500.dts
index 69559e9..e0f048a 100644
--- a/arch/powerpc/boot/dts/fsl/mvme2500.dts
+++ b/arch/powerpc/boot/dts/fsl/mvme2500.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device tree source for the Emerson/Artesyn MVME2500
  *
  * Copyright 2014 Elettra-Sincrotrone Trieste S.C.p.A.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Based on: P2020 DS Device Tree Source
  * Copyright 2009 Freescale Semiconductor Inc.
  */
diff --git a/arch/powerpc/boot/dts/fsl/mvme7100.dts b/arch/powerpc/boot/dts/fsl/mvme7100.dts
index 721cb53..bcc9ded 100644
--- a/arch/powerpc/boot/dts/fsl/mvme7100.dts
+++ b/arch/powerpc/boot/dts/fsl/mvme7100.dts
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device tree source for the Emerson/Artesyn MVME7100
  *
  * Copyright 2016 Elettra-Sincrotrone Trieste S.C.p.A.
  *
  * Author: Alessio Igor Bogani <alessio.bogani@elettra.eu>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 /include/ "mpc8641si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb-pa.dts b/arch/powerpc/boot/dts/fsl/p1010rdb-pa.dts
index e4ab53c..1e33d78 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb-pa.dts
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb-pa.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P1010 RDB Device Tree Source
  *
  * Copyright 2011 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p1010si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts b/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts
index 37681fd..3a94acb 100644
--- a/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts
+++ b/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P1010 RDB Device Tree Source
  *
  * Copyright 2011 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p1010si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1020rdb-pc.dtsi b/arch/powerpc/boot/dts/fsl/p1020rdb-pc.dtsi
index 25f81ee..a13876c 100644
--- a/arch/powerpc/boot/dts/fsl/p1020rdb-pc.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1020rdb-pc.dtsi
@@ -205,13 +205,13 @@
 	mdio@24000 {
 		phy0: ethernet-phy@0 {
 			interrupt-parent = <&mpic>;
-			interrupts = <3 1>;
+			interrupts = <3 1 0 0>;
 			reg = <0x0>;
 		};
 
 		phy1: ethernet-phy@1 {
 			interrupt-parent = <&mpic>;
-			interrupts = <2 1>;
+			interrupts = <2 1 0 0>;
 			reg = <0x1>;
 		};
 
diff --git a/arch/powerpc/boot/dts/fsl/p1020rdb-pc_camp_core0.dts b/arch/powerpc/boot/dts/fsl/p1020rdb-pc_camp_core0.dts
index f411515..42e1e2f 100644
--- a/arch/powerpc/boot/dts/fsl/p1020rdb-pc_camp_core0.dts
+++ b/arch/powerpc/boot/dts/fsl/p1020rdb-pc_camp_core0.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P1020 RDB-PC  Core0 Device Tree Source in CAMP mode.
  *
@@ -9,11 +10,6 @@
  * Please note to add "-b 0" for core0's dts compiling.
  *
  * Copyright 2012 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p1020rdb-pc_32b.dts"
diff --git a/arch/powerpc/boot/dts/fsl/p1020rdb-pc_camp_core1.dts b/arch/powerpc/boot/dts/fsl/p1020rdb-pc_camp_core1.dts
index a91335a..da9a8e7 100644
--- a/arch/powerpc/boot/dts/fsl/p1020rdb-pc_camp_core1.dts
+++ b/arch/powerpc/boot/dts/fsl/p1020rdb-pc_camp_core1.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P1020 RDB-PC Core1 Device Tree Source in CAMP mode.
  *
@@ -8,11 +9,6 @@
  * Please note to add "-b 1" for core1's dts compiling.
  *
  * Copyright 2012 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p1020rdb-pc_32b.dts"
diff --git a/arch/powerpc/boot/dts/fsl/p1020rdb.dts b/arch/powerpc/boot/dts/fsl/p1020rdb.dts
index 8136225..1a8d81e 100644
--- a/arch/powerpc/boot/dts/fsl/p1020rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/p1020rdb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P1020 RDB Device Tree Source
  *
  * Copyright 2009-2011 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p1020si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1020rdb_36b.dts b/arch/powerpc/boot/dts/fsl/p1020rdb_36b.dts
index 74471e3..fd09a19 100644
--- a/arch/powerpc/boot/dts/fsl/p1020rdb_36b.dts
+++ b/arch/powerpc/boot/dts/fsl/p1020rdb_36b.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P1020 RDB Device Tree Source (36-bit address map)
  *
  * Copyright 2009-2011 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p1020si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1021mds.dts b/arch/powerpc/boot/dts/fsl/p1021mds.dts
index 1047802..54af8de 100644
--- a/arch/powerpc/boot/dts/fsl/p1021mds.dts
+++ b/arch/powerpc/boot/dts/fsl/p1021mds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P1021 MDS Device Tree Source
  *
  * Copyright 2010,2012 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 /include/ "p1021si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p2020ds.dts b/arch/powerpc/boot/dts/fsl/p2020ds.dts
index 5ba06f7..ae380eb 100644
--- a/arch/powerpc/boot/dts/fsl/p2020ds.dts
+++ b/arch/powerpc/boot/dts/fsl/p2020ds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P2020 DS Device Tree Source
  *
  * Copyright 2009-2011 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p2020si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p2020rdb.dts b/arch/powerpc/boot/dts/fsl/p2020rdb.dts
index 435a319..3acd389 100644
--- a/arch/powerpc/boot/dts/fsl/p2020rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/p2020rdb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P2020 RDB Device Tree Source
  *
  * Copyright 2009-2012 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "p2020si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
index 51e975d..872e448 100644
--- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
@@ -327,24 +327,6 @@
 /include/ "qoriq-clockgen1.dtsi"
 	global-utilities@e1000 {
 		compatible = "fsl,p2041-clockgen", "fsl,qoriq-clockgen-1.0";
-
-		mux2: mux2@40 {
-			#clock-cells = <0>;
-			reg = <0x40 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux2";
-		};
-
-		mux3: mux3@60 {
-			#clock-cells = <0>;
-			reg = <0x60 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux3";
-		};
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi
index 941274c..6318962 100644
--- a/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi
@@ -89,7 +89,7 @@
 		cpu0: PowerPC,e500mc@0 {
 			device_type = "cpu";
 			reg = <0>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_0>;
 			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
@@ -99,7 +99,7 @@
 		cpu1: PowerPC,e500mc@1 {
 			device_type = "cpu";
 			reg = <1>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
@@ -109,7 +109,7 @@
 		cpu2: PowerPC,e500mc@2 {
 			device_type = "cpu";
 			reg = <2>;
-			clocks = <&mux2>;
+			clocks = <&clockgen 1 2>;
 			next-level-cache = <&L2_2>;
 			fsl,portid-mapping = <0x20000000>;
 			L2_2: l2-cache {
@@ -119,7 +119,7 @@
 		cpu3: PowerPC,e500mc@3 {
 			device_type = "cpu";
 			reg = <3>;
-			clocks = <&mux3>;
+			clocks = <&clockgen 1 3>;
 			next-level-cache = <&L2_3>;
 			fsl,portid-mapping = <0x10000000>;
 			L2_3: l2-cache {
diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
index 187676f..81bc75a 100644
--- a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
@@ -354,24 +354,6 @@
 /include/ "qoriq-clockgen1.dtsi"
 	global-utilities@e1000 {
 		compatible = "fsl,p3041-clockgen", "fsl,qoriq-clockgen-1.0";
-
-		mux2: mux2@40 {
-			#clock-cells = <0>;
-			reg = <0x40 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux2";
-		};
-
-		mux3: mux3@60 {
-			#clock-cells = <0>;
-			reg = <0x60 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux3";
-		};
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi
index 50b73e8..db92f11 100644
--- a/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi
@@ -90,7 +90,7 @@
 		cpu0: PowerPC,e500mc@0 {
 			device_type = "cpu";
 			reg = <0>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_0>;
 			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
@@ -100,7 +100,7 @@
 		cpu1: PowerPC,e500mc@1 {
 			device_type = "cpu";
 			reg = <1>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
@@ -110,7 +110,7 @@
 		cpu2: PowerPC,e500mc@2 {
 			device_type = "cpu";
 			reg = <2>;
-			clocks = <&mux2>;
+			clocks = <&clockgen 1 2>;
 			next-level-cache = <&L2_2>;
 			fsl,portid-mapping = <0x20000000>;
 			L2_2: l2-cache {
@@ -120,7 +120,7 @@
 		cpu3: PowerPC,e500mc@3 {
 			device_type = "cpu";
 			reg = <3>;
-			clocks = <&mux3>;
+			clocks = <&clockgen 1 3>;
 			next-level-cache = <&L2_3>;
 			fsl,portid-mapping = <0x10000000>;
 			L2_3: l2-cache {
diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
index a025208..4da49b6 100644
--- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
@@ -374,76 +374,6 @@
 /include/ "qoriq-clockgen1.dtsi"
 	global-utilities@e1000 {
 		compatible = "fsl,p4080-clockgen", "fsl,qoriq-clockgen-1.0";
-
-		pll2: pll2@840 {
-			#clock-cells = <1>;
-			reg = <0x840 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll2", "pll2-div2";
-		};
-
-		pll3: pll3@860 {
-			#clock-cells = <1>;
-			reg = <0x860 0x4>;
-			compatible = "fsl,qoriq-core-pll-1.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll3", "pll3-div2";
-		};
-
-		mux2: mux2@40 {
-			#clock-cells = <0>;
-			reg = <0x40 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux2";
-		};
-
-		mux3: mux3@60 {
-			#clock-cells = <0>;
-			reg = <0x60 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux3";
-		};
-
-		mux4: mux4@80 {
-			#clock-cells = <0>;
-			reg = <0x80 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll2 0>, <&pll2 1>, <&pll3 0>, <&pll3 1>;
-			clock-names = "pll2", "pll2-div2", "pll3", "pll3-div2";
-			clock-output-names = "cmux4";
-		};
-
-		mux5: mux5@a0 {
-			#clock-cells = <0>;
-			reg = <0xa0 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll2 0>, <&pll2 1>, <&pll3 0>, <&pll3 1>;
-			clock-names = "pll2", "pll2-div2", "pll3", "pll3-div2";
-			clock-output-names = "cmux5";
-		};
-
-		mux6: mux6@c0 {
-			#clock-cells = <0>;
-			reg = <0xc0 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll2 0>, <&pll2 1>, <&pll3 0>, <&pll3 1>;
-			clock-names = "pll2", "pll2-div2", "pll3", "pll3-div2";
-			clock-output-names = "cmux6";
-		};
-
-		mux7: mux7@e0 {
-			#clock-cells = <0>;
-			reg = <0xe0 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll2 0>, <&pll2 1>, <&pll3 0>, <&pll3 1>;
-			clock-names = "pll2", "pll2-div2", "pll3", "pll3-div2";
-			clock-output-names = "cmux7";
-		};
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi
index d56a546..0a7c65a 100644
--- a/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi
@@ -94,7 +94,7 @@
 		cpu0: PowerPC,e500mc@0 {
 			device_type = "cpu";
 			reg = <0>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_0>;
 			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
@@ -104,7 +104,7 @@
 		cpu1: PowerPC,e500mc@1 {
 			device_type = "cpu";
 			reg = <1>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
@@ -114,7 +114,7 @@
 		cpu2: PowerPC,e500mc@2 {
 			device_type = "cpu";
 			reg = <2>;
-			clocks = <&mux2>;
+			clocks = <&clockgen 1 2>;
 			next-level-cache = <&L2_2>;
 			fsl,portid-mapping = <0x20000000>;
 			L2_2: l2-cache {
@@ -124,7 +124,7 @@
 		cpu3: PowerPC,e500mc@3 {
 			device_type = "cpu";
 			reg = <3>;
-			clocks = <&mux3>;
+			clocks = <&clockgen 1 3>;
 			next-level-cache = <&L2_3>;
 			fsl,portid-mapping = <0x10000000>;
 			L2_3: l2-cache {
@@ -134,7 +134,7 @@
 		cpu4: PowerPC,e500mc@4 {
 			device_type = "cpu";
 			reg = <4>;
-			clocks = <&mux4>;
+			clocks = <&clockgen 1 4>;
 			next-level-cache = <&L2_4>;
 			fsl,portid-mapping = <0x08000000>;
 			L2_4: l2-cache {
@@ -144,7 +144,7 @@
 		cpu5: PowerPC,e500mc@5 {
 			device_type = "cpu";
 			reg = <5>;
-			clocks = <&mux5>;
+			clocks = <&clockgen 1 5>;
 			next-level-cache = <&L2_5>;
 			fsl,portid-mapping = <0x04000000>;
 			L2_5: l2-cache {
@@ -154,7 +154,7 @@
 		cpu6: PowerPC,e500mc@6 {
 			device_type = "cpu";
 			reg = <6>;
-			clocks = <&mux6>;
+			clocks = <&clockgen 1 6>;
 			next-level-cache = <&L2_6>;
 			fsl,portid-mapping = <0x02000000>;
 			L2_6: l2-cache {
@@ -164,7 +164,7 @@
 		cpu7: PowerPC,e500mc@7 {
 			device_type = "cpu";
 			reg = <7>;
-			clocks = <&mux7>;
+			clocks = <&clockgen 1 7>;
 			next-level-cache = <&L2_7>;
 			fsl,portid-mapping = <0x01000000>;
 			L2_7: l2-cache {
diff --git a/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi
index bfba0b4..2d74ea8 100644
--- a/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi
@@ -96,7 +96,7 @@
 		cpu0: PowerPC,e5500@0 {
 			device_type = "cpu";
 			reg = <0>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_0>;
 			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
@@ -106,7 +106,7 @@
 		cpu1: PowerPC,e5500@1 {
 			device_type = "cpu";
 			reg = <1>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
diff --git a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
index e2bd931..16b454b 100644
--- a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
@@ -319,24 +319,6 @@
 /include/ "qoriq-clockgen1.dtsi"
 	global-utilities@e1000 {
 		compatible = "fsl,p5040-clockgen", "fsl,qoriq-clockgen-1.0";
-
-		mux2: mux2@40 {
-			#clock-cells = <0>;
-			reg = <0x40 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux2";
-		};
-
-		mux3: mux3@60 {
-			#clock-cells = <0>;
-			reg = <0x60 0x4>;
-			compatible = "fsl,qoriq-core-mux-1.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-			clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-			clock-output-names = "cmux3";
-		};
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi
index dbd5775..ed89dbb 100644
--- a/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi
@@ -102,7 +102,7 @@
 		cpu0: PowerPC,e5500@0 {
 			device_type = "cpu";
 			reg = <0>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_0>;
 			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
@@ -112,7 +112,7 @@
 		cpu1: PowerPC,e5500@1 {
 			device_type = "cpu";
 			reg = <1>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
@@ -122,7 +122,7 @@
 		cpu2: PowerPC,e5500@2 {
 			device_type = "cpu";
 			reg = <2>;
-			clocks = <&mux2>;
+			clocks = <&clockgen 1 2>;
 			next-level-cache = <&L2_2>;
 			fsl,portid-mapping = <0x20000000>;
 			L2_2: l2-cache {
@@ -132,7 +132,7 @@
 		cpu3: PowerPC,e5500@3 {
 			device_type = "cpu";
 			reg = <3>;
-			clocks = <&mux3>;
+			clocks = <&clockgen 1 3>;
 			next-level-cache = <&L2_3>;
 			fsl,portid-mapping = <0x10000000>;
 			L2_3: l2-cache {
diff --git a/arch/powerpc/boot/dts/fsl/ppa8548.dts b/arch/powerpc/boot/dts/fsl/ppa8548.dts
index 8f9ffbe..f39838d 100644
--- a/arch/powerpc/boot/dts/fsl/ppa8548.dts
+++ b/arch/powerpc/boot/dts/fsl/ppa8548.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PPA8548 Device Tree Source (36-bit address map)
  * Copyright 2013 Prodrive B.V.
@@ -5,11 +6,6 @@
  * Based on:
  * MPC8548 CDS Device Tree Source (36-bit address map)
  * Copyright 2012 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8548si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-clockgen1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-clockgen1.dtsi
index 88cd70d..463c1ed 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-clockgen1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-clockgen1.dtsi
@@ -34,53 +34,6 @@
 
 clockgen: global-utilities@e1000 {
 	compatible = "fsl,qoriq-clockgen-1.0";
-	ranges = <0x0 0xe1000 0x1000>;
 	reg = <0xe1000 0x1000>;
-	clock-frequency = <0>;
-	#address-cells = <1>;
-	#size-cells = <1>;
 	#clock-cells = <2>;
-
-	sysclk: sysclk {
-		#clock-cells = <0>;
-		compatible = "fsl,qoriq-sysclk-1.0", "fixed-clock";
-		clock-output-names = "sysclk";
-	};
-	pll0: pll0@800 {
-		#clock-cells = <1>;
-		reg = <0x800 0x4>;
-		compatible = "fsl,qoriq-core-pll-1.0";
-		clocks = <&sysclk>;
-		clock-output-names = "pll0", "pll0-div2";
-	};
-	pll1: pll1@820 {
-		#clock-cells = <1>;
-		reg = <0x820 0x4>;
-		compatible = "fsl,qoriq-core-pll-1.0";
-		clocks = <&sysclk>;
-		clock-output-names = "pll1", "pll1-div2";
-	};
-	mux0: mux0@0 {
-		#clock-cells = <0>;
-		reg = <0x0 0x4>;
-		compatible = "fsl,qoriq-core-mux-1.0";
-		clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-		clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-		clock-output-names = "cmux0";
-	};
-	mux1: mux1@20 {
-		#clock-cells = <0>;
-		reg = <0x20 0x4>;
-		compatible = "fsl,qoriq-core-mux-1.0";
-		clocks = <&pll0 0>, <&pll0 1>, <&pll1 0>, <&pll1 1>;
-		clock-names = "pll0", "pll0-div2", "pll1", "pll1-div2";
-		clock-output-names = "cmux1";
-	};
-	platform_pll: platform-pll@c00 {
-		#clock-cells = <1>;
-		reg = <0xc00 0x4>;
-		compatible = "fsl,qoriq-platform-pll-1.0";
-		clocks = <&sysclk>;
-		clock-output-names = "platform-pll", "platform-pll-div2";
-	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-clockgen2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-clockgen2.dtsi
index 6dfd7c5..0361050 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-clockgen2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-clockgen2.dtsi
@@ -34,36 +34,6 @@
 
 clockgen: global-utilities@e1000 {
 	compatible = "fsl,qoriq-clockgen-2.0";
-	ranges = <0x0 0xe1000 0x1000>;
 	reg = <0xe1000 0x1000>;
-	#address-cells = <1>;
-	#size-cells = <1>;
 	#clock-cells = <2>;
-
-	sysclk: sysclk {
-		#clock-cells = <0>;
-		compatible = "fsl,qoriq-sysclk-2.0", "fixed-clock";
-		clock-output-names = "sysclk";
-	};
-	pll0: pll0@800 {
-		#clock-cells = <1>;
-		reg = <0x800 0x4>;
-		compatible = "fsl,qoriq-core-pll-2.0";
-		clocks = <&sysclk>;
-		clock-output-names = "pll0", "pll0-div2", "pll0-div4";
-	};
-	pll1: pll1@820 {
-		#clock-cells = <1>;
-		reg = <0x820 0x4>;
-		compatible = "fsl,qoriq-core-pll-2.0";
-		clocks = <&sysclk>;
-		clock-output-names = "pll1", "pll1-div2", "pll1-div4";
-	};
-	platform_pll: platform-pll@c00 {
-		#clock-cells = <1>;
-		reg = <0xc00 0x4>;
-		compatible = "fsl,qoriq-platform-pll-2.0";
-		clocks = <&sysclk>;
-		clock-output-names = "platform-pll", "platform-pll-div2";
-	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/sbc8641d.dts b/arch/powerpc/boot/dts/fsl/sbc8641d.dts
index 75870a1..3dca10a 100644
--- a/arch/powerpc/boot/dts/fsl/sbc8641d.dts
+++ b/arch/powerpc/boot/dts/fsl/sbc8641d.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SBC8641D Device Tree Source
  *
@@ -6,11 +7,6 @@
  * Paul Gortmaker (see MAINTAINERS for contact information)
  *
  * Based largely on the mpc8641_hpcn.dts by Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc8641si-pre.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
index 4908af5..d552044 100644
--- a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
@@ -345,22 +345,6 @@
 /include/ "qoriq-clockgen2.dtsi"
 	global-utilities@e1000 {
 		compatible = "fsl,t1023-clockgen", "fsl,qoriq-clockgen-2.0";
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 4>;
-			compatible = "fsl,core-mux-clock";
-			clocks = <&pll0 0>, <&pll0 1>;
-			clock-names = "pll0_0", "pll0_1";
-			clock-output-names = "cmux0";
-		};
-		mux1: mux1@20 {
-			#clock-cells = <0>;
-			reg = <0x20 4>;
-			compatible = "fsl,core-mux-clock";
-			clocks = <&pll0 0>, <&pll0 1>;
-			clock-names = "pll0_0", "pll0_1";
-			clock-output-names = "cmux1";
-		};
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi
index 9d08a36..d87ea13 100644
--- a/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi
@@ -74,7 +74,7 @@
 		cpu0: PowerPC,e5500@0 {
 			device_type = "cpu";
 			reg = <0>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			#cooling-cells = <2>;
 			L2_1: l2-cache {
@@ -84,7 +84,7 @@
 		cpu1: PowerPC,e5500@1 {
 			device_type = "cpu";
 			reg = <1>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_2>;
 			#cooling-cells = <2>;
 			L2_2: l2-cache {
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index 145c7f4..315d055 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -425,50 +425,6 @@
 /include/ "qoriq-clockgen2.dtsi"
 	global-utilities@e1000 {
 		compatible = "fsl,t1040-clockgen", "fsl,qoriq-clockgen-2.0";
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll1-div4",
-				"pll1", "pll1-div2", "pll1-div4";
-			clock-output-names = "cmux0";
-		};
-
-		mux1: mux1@20 {
-			#clock-cells = <0>;
-			reg = <0x20 4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll1-div4",
-				"pll1", "pll1-div2", "pll1-div4";
-			clock-output-names = "cmux1";
-		};
-
-		mux2: mux2@40 {
-			#clock-cells = <0>;
-			reg = <0x40 4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll1-div4",
-				"pll1", "pll1-div2", "pll1-div4";
-			clock-output-names = "cmux2";
-		};
-
-		mux3: mux3@60 {
-			#clock-cells = <0>;
-			reg = <0x60 4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0_0", "pll0_1", "pll0_2",
-				"pll1_0", "pll1_1", "pll1_2";
-			clock-output-names = "cmux3";
-		};
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi
index 6db0ee8..dd59e4b 100644
--- a/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi
@@ -74,7 +74,7 @@
 		cpu0: PowerPC,e5500@0 {
 			device_type = "cpu";
 			reg = <0>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			#cooling-cells = <2>;
 			L2_1: l2-cache {
@@ -84,7 +84,7 @@
 		cpu1: PowerPC,e5500@1 {
 			device_type = "cpu";
 			reg = <1>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_2>;
 			#cooling-cells = <2>;
 			L2_2: l2-cache {
@@ -94,7 +94,7 @@
 		cpu2: PowerPC,e5500@2 {
 			device_type = "cpu";
 			reg = <2>;
-			clocks = <&mux2>;
+			clocks = <&clockgen 1 2>;
 			next-level-cache = <&L2_3>;
 			#cooling-cells = <2>;
 			L2_3: l2-cache {
@@ -104,7 +104,7 @@
 		cpu3: PowerPC,e5500@3 {
 			device_type = "cpu";
 			reg = <3>;
-			clocks = <&mux3>;
+			clocks = <&clockgen 1 3>;
 			next-level-cache = <&L2_4>;
 			#cooling-cells = <2>;
 			L2_4: l2-cache {
diff --git a/arch/powerpc/boot/dts/fsl/t2080rdb.dts b/arch/powerpc/boot/dts/fsl/t2080rdb.dts
index 55c0210..092a400 100644
--- a/arch/powerpc/boot/dts/fsl/t2080rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t2080rdb.dts
@@ -77,12 +77,12 @@
 		};
 
 		ethernet@f0000 {
-			phy-handle = <&xg_cs4315_phy1>;
+			phy-handle = <&xg_cs4315_phy2>;
 			phy-connection-type = "xgmii";
 		};
 
 		ethernet@f2000 {
-			phy-handle = <&xg_cs4315_phy2>;
+			phy-handle = <&xg_cs4315_phy1>;
 			phy-connection-type = "xgmii";
 		};
 
diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
index a97296c..ecbb447 100644
--- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
@@ -535,28 +535,6 @@
 /include/ "qoriq-clockgen2.dtsi"
 	global-utilities@e1000 {
 		compatible = "fsl,t2080-clockgen", "fsl,qoriq-clockgen-2.0";
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll0-div4",
-				"pll1", "pll1-div2", "pll1-div4";
-			clock-output-names = "cmux0";
-		};
-
-		mux1: mux1@20 {
-			#clock-cells = <0>;
-			reg = <0x20 4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll0-div4",
-				"pll1", "pll1-div2", "pll1-div4";
-			clock-output-names = "cmux1";
-		};
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/t208xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t208xsi-pre.dtsi
index c2e5720..3f745de 100644
--- a/arch/powerpc/boot/dts/fsl/t208xsi-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t208xsi-pre.dtsi
@@ -81,28 +81,28 @@
 		cpu0: PowerPC,e6500@0 {
 			device_type = "cpu";
 			reg = <0 1>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu1: PowerPC,e6500@2 {
 			device_type = "cpu";
 			reg = <2 3>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu2: PowerPC,e6500@4 {
 			device_type = "cpu";
 			reg = <4 5>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu3: PowerPC,e6500@6 {
 			device_type = "cpu";
 			reg = <6 7>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
index 68c4ead..fcac734 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
@@ -950,67 +950,6 @@
 /include/ "qoriq-clockgen2.dtsi"
 	global-utilities@e1000 {
 		compatible = "fsl,t4240-clockgen", "fsl,qoriq-clockgen-2.0";
-
-		pll2: pll2@840 {
-			#clock-cells = <1>;
-			reg = <0x840 0x4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll2", "pll2-div2", "pll2-div4";
-		};
-
-		pll3: pll3@860 {
-			#clock-cells = <1>;
-			reg = <0x860 0x4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll3", "pll3-div2", "pll3-div4";
-		};
-
-		pll4: pll4@880 {
-			#clock-cells = <1>;
-			reg = <0x880 0x4>;
-			compatible = "fsl,qoriq-core-pll-2.0";
-			clocks = <&sysclk>;
-			clock-output-names = "pll4", "pll4-div2", "pll4-div4";
-		};
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 0x4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				<&pll1 0>, <&pll1 1>, <&pll1 2>,
-				<&pll2 0>, <&pll2 1>, <&pll2 2>;
-			clock-names = "pll0", "pll0-div2", "pll0-div4",
-				"pll1", "pll1-div2", "pll1-div4",
-				"pll2", "pll2-div2", "pll2-div4";
-			clock-output-names = "cmux0";
-		};
-
-		mux1: mux1@20 {
-			#clock-cells = <0>;
-			reg = <0x20 0x4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				<&pll1 0>, <&pll1 1>, <&pll1 2>,
-				<&pll2 0>, <&pll2 1>, <&pll2 2>;
-			clock-names = "pll0", "pll0-div2", "pll0-div4",
-				"pll1", "pll1-div2", "pll1-div4",
-				"pll2", "pll2-div2", "pll2-div4";
-			clock-output-names = "cmux1";
-		};
-
-		mux2: mux2@40 {
-			#clock-cells = <0>;
-			reg = <0x40 0x4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll3 0>, <&pll3 1>, <&pll3 2>,
-				<&pll4 0>, <&pll4 1>, <&pll4 2>;
-			clock-names = "pll3", "pll3-div2", "pll3-div4",
-				"pll4", "pll4-div2", "pll4-div4";
-			clock-output-names = "cmux2";
-		};
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
index 038cf8f..632314c 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
@@ -90,84 +90,84 @@
 		cpu0: PowerPC,e6500@0 {
 			device_type = "cpu";
 			reg = <0 1>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu1: PowerPC,e6500@2 {
 			device_type = "cpu";
 			reg = <2 3>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu2: PowerPC,e6500@4 {
 			device_type = "cpu";
 			reg = <4 5>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu3: PowerPC,e6500@6 {
 			device_type = "cpu";
 			reg = <6 7>;
-			clocks = <&mux0>;
+			clocks = <&clockgen 1 0>;
 			next-level-cache = <&L2_1>;
 			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu4: PowerPC,e6500@8 {
 			device_type = "cpu";
 			reg = <8 9>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_2>;
 			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu5: PowerPC,e6500@10 {
 			device_type = "cpu";
 			reg = <10 11>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_2>;
 			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu6: PowerPC,e6500@12 {
 			device_type = "cpu";
 			reg = <12 13>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_2>;
 			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu7: PowerPC,e6500@14 {
 			device_type = "cpu";
 			reg = <14 15>;
-			clocks = <&mux1>;
+			clocks = <&clockgen 1 1>;
 			next-level-cache = <&L2_2>;
 			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu8: PowerPC,e6500@16 {
 			device_type = "cpu";
 			reg = <16 17>;
-			clocks = <&mux2>;
+			clocks = <&clockgen 1 2>;
 			next-level-cache = <&L2_3>;
 			fsl,portid-mapping = <0x20000000>;
 		};
 		cpu9: PowerPC,e6500@18 {
 			device_type = "cpu";
 			reg = <18 19>;
-			clocks = <&mux2>;
+			clocks = <&clockgen 1 2>;
 			next-level-cache = <&L2_3>;
 			fsl,portid-mapping = <0x20000000>;
 		};
 		cpu10: PowerPC,e6500@20 {
 			device_type = "cpu";
 			reg = <20 21>;
-			clocks = <&mux2>;
+			clocks = <&clockgen 1 2>;
 			next-level-cache = <&L2_3>;
 			fsl,portid-mapping = <0x20000000>;
 		};
 		cpu11: PowerPC,e6500@22 {
 			device_type = "cpu";
 			reg = <22 23>;
-			clocks = <&mux2>;
+			clocks = <&clockgen 1 2>;
 			next-level-cache = <&L2_3>;
 			fsl,portid-mapping = <0x20000000>;
 		};
diff --git a/arch/powerpc/boot/dts/gamecube.dts b/arch/powerpc/boot/dts/gamecube.dts
index 58d06c9..a564cb7 100644
--- a/arch/powerpc/boot/dts/gamecube.dts
+++ b/arch/powerpc/boot/dts/gamecube.dts
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/boot/dts/gamecube.dts
  *
  * Nintendo GameCube platform device tree source
  * Copyright (C) 2007-2009 The GameCube Linux Team
  * Copyright (C) 2007,2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/iss4xx-mpic.dts b/arch/powerpc/boot/dts/iss4xx-mpic.dts
index f706319..c9f90f1 100644
--- a/arch/powerpc/boot/dts/iss4xx-mpic.dts
+++ b/arch/powerpc/boot/dts/iss4xx-mpic.dts
@@ -43,7 +43,7 @@
 			d-cache-size = <32768>;
 			dcr-controller;
 			dcr-access-method = "native";
-			status = "ok";
+			status = "okay";
 		};
 		cpu@1 {
 			device_type = "cpu";
diff --git a/arch/powerpc/boot/dts/klondike.dts b/arch/powerpc/boot/dts/klondike.dts
index d9613b7..9743217 100644
--- a/arch/powerpc/boot/dts/klondike.dts
+++ b/arch/powerpc/boot/dts/klondike.dts
@@ -1,24 +1,9 @@
+// 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>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- *
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/kmeter1.dts b/arch/powerpc/boot/dts/kmeter1.dts
index 9fa33d9..154f5d2 100644
--- a/arch/powerpc/boot/dts/kmeter1.dts
+++ b/arch/powerpc/boot/dts/kmeter1.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Keymile KMETER1 Device Tree Source
  *
  * 2008-2011 DENX Software Engineering GmbH
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/lite5200.dts b/arch/powerpc/boot/dts/lite5200.dts
index 179a178..cb2782d 100644
--- a/arch/powerpc/boot/dts/lite5200.dts
+++ b/arch/powerpc/boot/dts/lite5200.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Lite5200 board Device Tree Source
  *
  * Copyright 2006-2007 Secret Lab Technologies Ltd.
  * Grant Likely <grant.likely@secretlab.ca>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/lite5200b.dts b/arch/powerpc/boot/dts/lite5200b.dts
index 5abb46c..2b86c81 100644
--- a/arch/powerpc/boot/dts/lite5200b.dts
+++ b/arch/powerpc/boot/dts/lite5200b.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Lite5200B board Device Tree Source
  *
  * Copyright 2006-2007 Secret Lab Technologies Ltd.
  * Grant Likely <grant.likely@secretlab.ca>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/media5200.dts b/arch/powerpc/boot/dts/media5200.dts
index 843f156..61cae9d 100644
--- a/arch/powerpc/boot/dts/media5200.dts
+++ b/arch/powerpc/boot/dts/media5200.dts
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Freescale Media5200 board Device Tree Source
  *
  * Copyright 2009 Secret Lab Technologies Ltd.
  * Grant Likely <grant.likely@secretlab.ca>
  * Steven Cavanagh <scavanagh@secretlab.ca>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/mgcoge.dts b/arch/powerpc/boot/dts/mgcoge.dts
index d72fb5e..a2dd5f1 100644
--- a/arch/powerpc/boot/dts/mgcoge.dts
+++ b/arch/powerpc/boot/dts/mgcoge.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree for the MGCOGE plattform from keymile
  *
  * Copyright 2008 DENX Software Engineering GmbH
  * Heiko Schocher <hs@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/motionpro.dts b/arch/powerpc/boot/dts/motionpro.dts
index bbabd97..c236760 100644
--- a/arch/powerpc/boot/dts/motionpro.dts
+++ b/arch/powerpc/boot/dts/motionpro.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Motion-PRO board Device Tree Source
  *
  * Copyright (C) 2007 Semihalf
  * Marian Balakowicz <m8@semihalf.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/mpc5121.dtsi b/arch/powerpc/boot/dts/mpc5121.dtsi
index a015e45..3f66b91 100644
--- a/arch/powerpc/boot/dts/mpc5121.dtsi
+++ b/arch/powerpc/boot/dts/mpc5121.dtsi
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * base MPC5121 Device Tree Source
  *
  * Copyright 2007-2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <dt-bindings/clock/mpc512x-clock.h>
diff --git a/arch/powerpc/boot/dts/mpc5121ads.dts b/arch/powerpc/boot/dts/mpc5121ads.dts
index 1e81a7e..b407a50 100644
--- a/arch/powerpc/boot/dts/mpc5121ads.dts
+++ b/arch/powerpc/boot/dts/mpc5121ads.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC5121E ADS Device Tree Source
  *
  * Copyright 2007-2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include "mpc5121.dtsi"
diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts
index 898eb58..0bd2acc 100644
--- a/arch/powerpc/boot/dts/mpc5125twr.dts
+++ b/arch/powerpc/boot/dts/mpc5125twr.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * STx/Freescale ADS5125 MPC5125 silicon
  *
@@ -5,11 +6,6 @@
  *
  * Reworked by Matteo Facchinetti (engineering@sirius-es.it)
  * Copyright (C) 2013 Sirius Electronic Systems
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <dt-bindings/clock/mpc512x-clock.h>
diff --git a/arch/powerpc/boot/dts/mpc5200b.dtsi b/arch/powerpc/boot/dts/mpc5200b.dtsi
index 969b220..648fe31 100644
--- a/arch/powerpc/boot/dts/mpc5200b.dtsi
+++ b/arch/powerpc/boot/dts/mpc5200b.dtsi
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * base MPC5200b Device Tree Source
  *
  * Copyright (C) 2010 SecretLab
  * Grant Likely <grant@secretlab.ca>
  * John Bonesio <bones@secretlab.ca>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc7448hpc2.dts b/arch/powerpc/boot/dts/mpc7448hpc2.dts
index 20a0d22..9494af1 100644
--- a/arch/powerpc/boot/dts/mpc7448hpc2.dts
+++ b/arch/powerpc/boot/dts/mpc7448hpc2.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC7448HPC2 (Taiga) board Device Tree Source
  *
  * Copyright 2006, 2008 Freescale Semiconductor Inc.
  * 2006 Roy Zang <Roy Zang at freescale.com>.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8272ads.dts b/arch/powerpc/boot/dts/mpc8272ads.dts
index 98282c1..13ec786 100644
--- a/arch/powerpc/boot/dts/mpc8272ads.dts
+++ b/arch/powerpc/boot/dts/mpc8272ads.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8272 ADS Device Tree Source
  *
  * Copyright 2005,2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8308_p1m.dts b/arch/powerpc/boot/dts/mpc8308_p1m.dts
index cab933b..2638555 100644
--- a/arch/powerpc/boot/dts/mpc8308_p1m.dts
+++ b/arch/powerpc/boot/dts/mpc8308_p1m.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * mpc8308_p1m Device Tree Source
  *
  * Copyright 2010 Ilya Yanok, Emcraft Systems, yanok@emcraft.com
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8308rdb.dts b/arch/powerpc/boot/dts/mpc8308rdb.dts
index d0211f0..af2ed83 100644
--- a/arch/powerpc/boot/dts/mpc8308rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8308rdb.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8308RDB Device Tree Source
  *
  * Copyright 2009 Freescale Semiconductor Inc.
  * Copyright 2010 Ilya Yanok, Emcraft Systems, yanok@emcraft.com
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts
index 4b635dc..a831579 100644
--- a/arch/powerpc/boot/dts/mpc8313erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8313erdb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8313E RDB Device Tree Source
  *
  * Copyright 2005, 2006, 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index ca5139e..e09b37d 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8315E RDB Device Tree Source
  *
  * Copyright 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc832x_mds.dts b/arch/powerpc/boot/dts/mpc832x_mds.dts
index 49c7d65..3af073f 100644
--- a/arch/powerpc/boot/dts/mpc832x_mds.dts
+++ b/arch/powerpc/boot/dts/mpc832x_mds.dts
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8323E EMDS Device Tree Source
  *
  * Copyright 2006 Freescale Semiconductor Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
 
  * To enable external serial I/O on a Freescale MPC 8323 SYS/MDS board, do
  * this:
diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts
index 647cae1..b625718 100644
--- a/arch/powerpc/boot/dts/mpc832x_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC832x RDB Device Tree Source
  *
  * Copyright 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
@@ -311,13 +307,9 @@
 			compatible = "fsl,ucc-mdio";
 
 			phy00:ethernet-phy@0 {
-				interrupt-parent = <&ipic>;
-				interrupts = <0>;
 				reg = <0x0>;
 			};
 			phy04:ethernet-phy@4 {
-				interrupt-parent = <&ipic>;
-				interrupts = <0>;
 				reg = <0x4>;
 			};
 		};
diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts
index 648a858..d4ebbb9 100644
--- a/arch/powerpc/boot/dts/mpc8349emitx.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitx.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8349E-mITX Device Tree Source
  *
  * Copyright 2006 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
index f00066d..bcf68a0 100644
--- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8349E-mITX-GP Device Tree Source
  *
  * Copyright 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc834x_mds.dts b/arch/powerpc/boot/dts/mpc834x_mds.dts
index 4843c3f..6c8cb85 100644
--- a/arch/powerpc/boot/dts/mpc834x_mds.dts
+++ b/arch/powerpc/boot/dts/mpc834x_mds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8349E MDS Device Tree Source
  *
  * Copyright 2005, 2006 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc836x_mds.dts b/arch/powerpc/boot/dts/mpc836x_mds.dts
index 539fd9f..f4ca12e 100644
--- a/arch/powerpc/boot/dts/mpc836x_mds.dts
+++ b/arch/powerpc/boot/dts/mpc836x_mds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8360E EMDS Device Tree Source
  *
  * Copyright 2006 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 
diff --git a/arch/powerpc/boot/dts/mpc836x_rdk.dts b/arch/powerpc/boot/dts/mpc836x_rdk.dts
index 47c5fc6..a0cc195 100644
--- a/arch/powerpc/boot/dts/mpc836x_rdk.dts
+++ b/arch/powerpc/boot/dts/mpc836x_rdk.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8360E RDK Device Tree Source
  *
@@ -5,11 +6,6 @@
  * Copyright 2007-2008 MontaVista Software, Inc.
  *
  * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8377_mds.dts b/arch/powerpc/boot/dts/mpc8377_mds.dts
index c2c062e..9227bce 100644
--- a/arch/powerpc/boot/dts/mpc8377_mds.dts
+++ b/arch/powerpc/boot/dts/mpc8377_mds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8377E MDS Device Tree Source
  *
  * Copyright 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts
index 5e85d8c..7df452e 100644
--- a/arch/powerpc/boot/dts/mpc8377_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8377E RDB Device Tree Source
  *
  * Copyright 2007, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8377_wlan.dts b/arch/powerpc/boot/dts/mpc8377_wlan.dts
index fee15fc..d8e7d40 100644
--- a/arch/powerpc/boot/dts/mpc8377_wlan.dts
+++ b/arch/powerpc/boot/dts/mpc8377_wlan.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8377E WLAN Device Tree Source
  *
  * Copyright 2007-2009 Freescale Semiconductor Inc.
  * Copyright 2009 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8378_mds.dts b/arch/powerpc/boot/dts/mpc8378_mds.dts
index 1b82b77..e45b255 100644
--- a/arch/powerpc/boot/dts/mpc8378_mds.dts
+++ b/arch/powerpc/boot/dts/mpc8378_mds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8378E MDS Device Tree Source
  *
  * Copyright 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts
index e973d61..bdcfe83 100644
--- a/arch/powerpc/boot/dts/mpc8378_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8378E RDB Device Tree Source
  *
  * Copyright 2007, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8379_mds.dts b/arch/powerpc/boot/dts/mpc8379_mds.dts
index 38e5048..f7379a1 100644
--- a/arch/powerpc/boot/dts/mpc8379_mds.dts
+++ b/arch/powerpc/boot/dts/mpc8379_mds.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8379E MDS Device Tree Source
  *
  * Copyright 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts
index ed5d12f..a5f7023 100644
--- a/arch/powerpc/boot/dts/mpc8379_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8379E RDB Device Tree Source
  *
  * Copyright 2007, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc8610_hpcd.dts b/arch/powerpc/boot/dts/mpc8610_hpcd.dts
index 6a109a0..1a8321a 100644
--- a/arch/powerpc/boot/dts/mpc8610_hpcd.dts
+++ b/arch/powerpc/boot/dts/mpc8610_hpcd.dts
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * MPC8610 HPCD Device Tree Source
  *
  * Copyright 2007-2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under the terms of the GNU General Public License Version 2 as published
- * by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc866ads.dts b/arch/powerpc/boot/dts/mpc866ads.dts
index 4443fac..ff60d67 100644
--- a/arch/powerpc/boot/dts/mpc866ads.dts
+++ b/arch/powerpc/boot/dts/mpc866ads.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC866 ADS Device Tree Source
  *
  * Copyright 2006 MontaVista Software, Inc.
  * Copyright 2008 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/mpc885ads.dts b/arch/powerpc/boot/dts/mpc885ads.dts
index 5b037f5..be58e7f 100644
--- a/arch/powerpc/boot/dts/mpc885ads.dts
+++ b/arch/powerpc/boot/dts/mpc885ads.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC885 ADS Device Tree Source
  *
  * Copyright 2006 MontaVista Software, Inc.
  * Copyright 2007,2008 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
@@ -72,7 +68,7 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 		device_type = "soc";
-		ranges = <0x0 0xff000000 0x4000>;
+		ranges = <0x0 0xff000000 0x28000>;
 		bus-frequency = <0>;
 
 		// Temporary -- will go away once kernel uses ranges for get_immrbase().
@@ -224,6 +220,17 @@
 				#size-cells = <0>;
 			};
 		};
+
+		crypto@20000 {
+			compatible = "fsl,sec1.2", "fsl,sec1.0";
+			reg = <0x20000 0x8000>;
+			interrupts = <1 1>;
+			interrupt-parent = <&PIC>;
+			fsl,num-channels = <1>;
+			fsl,channel-fifo-len = <24>;
+			fsl,exec-units-mask = <0x4c>;
+			fsl,descriptor-types-mask = <0x05000154>;
+		};
 	};
 
 	chosen {
diff --git a/arch/powerpc/boot/dts/mucmc52.dts b/arch/powerpc/boot/dts/mucmc52.dts
index d3a792b..c6c6630 100644
--- a/arch/powerpc/boot/dts/mucmc52.dts
+++ b/arch/powerpc/boot/dts/mucmc52.dts
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Manroland mucmc52 board Device Tree Source
  *
  * Copyright (C) 2009 DENX Software Engineering GmbH
  * Heiko Schocher <hs@denx.de>
  * Copyright 2006-2007 Secret Lab Technologies Ltd.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/o2d.dts b/arch/powerpc/boot/dts/o2d.dts
index 9f6dd4d..24a46f6 100644
--- a/arch/powerpc/boot/dts/o2d.dts
+++ b/arch/powerpc/boot/dts/o2d.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * O2D Device Tree Source
  *
  * Copyright (C) 2012 DENX Software Engineering
  * Anatolij Gustschin <agust@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "o2d.dtsi"
diff --git a/arch/powerpc/boot/dts/o2d.dtsi b/arch/powerpc/boot/dts/o2d.dtsi
index cf073e6..6661955 100644
--- a/arch/powerpc/boot/dts/o2d.dtsi
+++ b/arch/powerpc/boot/dts/o2d.dtsi
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * O2D base Device Tree Source
  *
  * Copyright (C) 2012 DENX Software Engineering
  * Anatolij Gustschin <agust@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/o2d300.dts b/arch/powerpc/boot/dts/o2d300.dts
index 29affe0..55a25b7 100644
--- a/arch/powerpc/boot/dts/o2d300.dts
+++ b/arch/powerpc/boot/dts/o2d300.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * O2D300 Device Tree Source
  *
  * Copyright (C) 2012 DENX Software Engineering
  * Anatolij Gustschin <agust@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "o2d.dtsi"
diff --git a/arch/powerpc/boot/dts/o2dnt2.dts b/arch/powerpc/boot/dts/o2dnt2.dts
index a0f5b97..eeba7f5 100644
--- a/arch/powerpc/boot/dts/o2dnt2.dts
+++ b/arch/powerpc/boot/dts/o2dnt2.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * O2DNT2 Device Tree Source
  *
  * Copyright (C) 2012 DENX Software Engineering
  * Anatolij Gustschin <agust@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "o2d.dtsi"
diff --git a/arch/powerpc/boot/dts/o2i.dts b/arch/powerpc/boot/dts/o2i.dts
index e3cc99d..3fb2e0a 100644
--- a/arch/powerpc/boot/dts/o2i.dts
+++ b/arch/powerpc/boot/dts/o2i.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * O2I Device Tree Source
  *
  * Copyright (C) 2012 DENX Software Engineering
  * Anatolij Gustschin <agust@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "o2d.dtsi"
diff --git a/arch/powerpc/boot/dts/o2mnt.dts b/arch/powerpc/boot/dts/o2mnt.dts
index d91859a..c5e0ba6 100644
--- a/arch/powerpc/boot/dts/o2mnt.dts
+++ b/arch/powerpc/boot/dts/o2mnt.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * O2MNT Device Tree Source
  *
  * Copyright (C) 2012 DENX Software Engineering
  * Anatolij Gustschin <agust@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "o2d.dtsi"
diff --git a/arch/powerpc/boot/dts/o3dnt.dts b/arch/powerpc/boot/dts/o3dnt.dts
index acce493..fd00396 100644
--- a/arch/powerpc/boot/dts/o3dnt.dts
+++ b/arch/powerpc/boot/dts/o3dnt.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * O3DNT Device Tree Source
  *
  * Copyright (C) 2012 DENX Software Engineering
  * Anatolij Gustschin <agust@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "o2d.dtsi"
diff --git a/arch/powerpc/boot/dts/pcm030.dts b/arch/powerpc/boot/dts/pcm030.dts
index 836e47c..b1bc731 100644
--- a/arch/powerpc/boot/dts/pcm030.dts
+++ b/arch/powerpc/boot/dts/pcm030.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * phyCORE-MPC5200B-tiny (pcm030) board Device Tree Source
  *
@@ -5,11 +6,6 @@
  * Sascha Hauer <s.hauer@pengutronix.de>
  * Copyright 2007 Pengutronix
  * Juergen Beisert <j.beisert@pengutronix.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/pcm032.dts b/arch/powerpc/boot/dts/pcm032.dts
index 576249b..c259c6b 100644
--- a/arch/powerpc/boot/dts/pcm032.dts
+++ b/arch/powerpc/boot/dts/pcm032.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * phyCORE-MPC5200B-IO (pcm032) board Device Tree Source
  *
@@ -5,11 +6,6 @@
  * Sascha Hauer <s.hauer@pengutronix.de>
  * Juergen Beisert <j.beisert@pengutronix.de>
  * Wolfram Sang <w.sang@pengutronix.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/pdm360ng.dts b/arch/powerpc/boot/dts/pdm360ng.dts
index df1283b..67c3b9d 100644
--- a/arch/powerpc/boot/dts/pdm360ng.dts
+++ b/arch/powerpc/boot/dts/pdm360ng.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree Source for IFM PDM360NG.
  *
@@ -6,11 +7,6 @@
  *
  * Based on MPC5121E ADS dts.
  * Copyright 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 #include "mpc5121.dtsi"
diff --git a/arch/powerpc/boot/dts/pq2fads.dts b/arch/powerpc/boot/dts/pq2fads.dts
index a477615..b666621 100644
--- a/arch/powerpc/boot/dts/pq2fads.dts
+++ b/arch/powerpc/boot/dts/pq2fads.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree for the PQ2FADS-ZU board with an MPC8280 chip.
  *
  * Copyright 2007,2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/ps3.dts b/arch/powerpc/boot/dts/ps3.dts
index 96ba5b5..6bdfba6 100644
--- a/arch/powerpc/boot/dts/ps3.dts
+++ b/arch/powerpc/boot/dts/ps3.dts
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 Game Console device tree.
  *
  *  Copyright (C) 2007 Sony Computer Entertainment Inc.
  *  Copyright 2007 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/sbc8548-altflash.dts b/arch/powerpc/boot/dts/sbc8548-altflash.dts
index 8967a56..bb7a1e7 100644
--- a/arch/powerpc/boot/dts/sbc8548-altflash.dts
+++ b/arch/powerpc/boot/dts/sbc8548-altflash.dts
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SBC8548 Device Tree Source
  *
@@ -7,11 +8,6 @@
  * Copyright 2013 Wind River Systems Inc.
  *
  * Paul Gortmaker (see MAINTAINERS for contact information)
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 
diff --git a/arch/powerpc/boot/dts/sbc8548-post.dtsi b/arch/powerpc/boot/dts/sbc8548-post.dtsi
index 9b505c8..9d848d4 100644
--- a/arch/powerpc/boot/dts/sbc8548-post.dtsi
+++ b/arch/powerpc/boot/dts/sbc8548-post.dtsi
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SBC8548 Device Tree Source
  *
  * Copyright 2007 Wind River Systems Inc.
  *
  * Paul Gortmaker (see MAINTAINERS for contact information)
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /{
diff --git a/arch/powerpc/boot/dts/sbc8548-pre.dtsi b/arch/powerpc/boot/dts/sbc8548-pre.dtsi
index d8c6629..0e3665f 100644
--- a/arch/powerpc/boot/dts/sbc8548-pre.dtsi
+++ b/arch/powerpc/boot/dts/sbc8548-pre.dtsi
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SBC8548 Device Tree Source
  *
  * Copyright 2007 Wind River Systems Inc.
  *
  * Paul Gortmaker (see MAINTAINERS for contact information)
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /{
diff --git a/arch/powerpc/boot/dts/sbc8548.dts b/arch/powerpc/boot/dts/sbc8548.dts
index 9bdb828..ce0a119 100644
--- a/arch/powerpc/boot/dts/sbc8548.dts
+++ b/arch/powerpc/boot/dts/sbc8548.dts
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SBC8548 Device Tree Source
  *
  * Copyright 2007 Wind River Systems Inc.
  *
  * Paul Gortmaker (see MAINTAINERS for contact information)
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 
diff --git a/arch/powerpc/boot/dts/socrates.dts b/arch/powerpc/boot/dts/socrates.dts
index 134a5ff..00a56e8 100644
--- a/arch/powerpc/boot/dts/socrates.dts
+++ b/arch/powerpc/boot/dts/socrates.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Device Tree Source for the Socrates board (MPC8544).
  *
  * Copyright (c) 2008 Emcraft Systems.
  * Sergei Poselenov, <sposelenov@emcraft.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/stx_gp3_8560.dts b/arch/powerpc/boot/dts/stx_gp3_8560.dts
index 78a72ee..d1ab698 100644
--- a/arch/powerpc/boot/dts/stx_gp3_8560.dts
+++ b/arch/powerpc/boot/dts/stx_gp3_8560.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * STX GP3 - 8560 ADS Device Tree Source
  *
  * Copyright 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/stxssa8555.dts b/arch/powerpc/boot/dts/stxssa8555.dts
index 859f854..5dca2a9 100644
--- a/arch/powerpc/boot/dts/stxssa8555.dts
+++ b/arch/powerpc/boot/dts/stxssa8555.dts
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8555-based STx GP3 Device Tree Source
  *
  * Copyright 2006, 2008 Freescale Semiconductor Inc.
  *
  * Copyright 2010 Silicon Turnkey Express LLC.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/tqm5200.dts b/arch/powerpc/boot/dts/tqm5200.dts
index 1db07f6..9ed0bc7 100644
--- a/arch/powerpc/boot/dts/tqm5200.dts
+++ b/arch/powerpc/boot/dts/tqm5200.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * TQM5200 board Device Tree Source
  *
  * Copyright (C) 2007 Semihalf
  * Marian Balakowicz <m8@semihalf.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/tqm8540.dts b/arch/powerpc/boot/dts/tqm8540.dts
index 91cbd7a..9c1eb97 100644
--- a/arch/powerpc/boot/dts/tqm8540.dts
+++ b/arch/powerpc/boot/dts/tqm8540.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * TQM 8540 Device Tree Source
  *
  * Copyright 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/tqm8541.dts b/arch/powerpc/boot/dts/tqm8541.dts
index 84dce2d..44595cf 100644
--- a/arch/powerpc/boot/dts/tqm8541.dts
+++ b/arch/powerpc/boot/dts/tqm8541.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * TQM 8541 Device Tree Source
  *
  * Copyright 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/tqm8548-bigflash.dts b/arch/powerpc/boot/dts/tqm8548-bigflash.dts
index 7a333dd..caa36c5 100644
--- a/arch/powerpc/boot/dts/tqm8548-bigflash.dts
+++ b/arch/powerpc/boot/dts/tqm8548-bigflash.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * TQM8548 Device Tree Source
  *
  * Copyright 2006 Freescale Semiconductor Inc.
  * Copyright 2008 Wolfgang Grandegger <wg@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/tqm8548.dts b/arch/powerpc/boot/dts/tqm8548.dts
index c737caf..12a6441 100644
--- a/arch/powerpc/boot/dts/tqm8548.dts
+++ b/arch/powerpc/boot/dts/tqm8548.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * TQM8548 Device Tree Source
  *
  * Copyright 2006 Freescale Semiconductor Inc.
  * Copyright 2008 Wolfgang Grandegger <wg@denx.de>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/tqm8555.dts b/arch/powerpc/boot/dts/tqm8555.dts
index d0416a5..54f3e82 100644
--- a/arch/powerpc/boot/dts/tqm8555.dts
+++ b/arch/powerpc/boot/dts/tqm8555.dts
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * TQM 8555 Device Tree Source
  *
  * Copyright 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/tqm8560.dts b/arch/powerpc/boot/dts/tqm8560.dts
index f9a11eb..7415cb6 100644
--- a/arch/powerpc/boot/dts/tqm8560.dts
+++ b/arch/powerpc/boot/dts/tqm8560.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * TQM 8560 Device Tree Source
  *
  * Copyright 2008 Freescale Semiconductor Inc.
  * Copyright 2008 Wolfgang Grandegger <wg@grandegger.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/tqm8xx.dts b/arch/powerpc/boot/dts/tqm8xx.dts
index 3d1446b..d16cdfd 100644
--- a/arch/powerpc/boot/dts/tqm8xx.dts
+++ b/arch/powerpc/boot/dts/tqm8xx.dts
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * TQM8XX Device Tree Source
  *
  * Heiko Schocher <hs@denx.de>
  * 2010 DENX Software Engineering GmbH
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/uc101.dts b/arch/powerpc/boot/dts/uc101.dts
index 5c46219..2e34d01 100644
--- a/arch/powerpc/boot/dts/uc101.dts
+++ b/arch/powerpc/boot/dts/uc101.dts
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Manroland uc101 board Device Tree Source
  *
  * Copyright (C) 2009 DENX Software Engineering GmbH
  * Heiko Schocher <hs@denx.de>
  * Copyright 2006-2007 Secret Lab Technologies Ltd.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 /include/ "mpc5200b.dtsi"
diff --git a/arch/powerpc/boot/dts/wii.dts b/arch/powerpc/boot/dts/wii.dts
index 104b1d6..aaa381d 100644
--- a/arch/powerpc/boot/dts/wii.dts
+++ b/arch/powerpc/boot/dts/wii.dts
@@ -1,19 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/boot/dts/wii.dts
  *
  * Nintendo Wii platform device tree source
  * Copyright (C) 2008-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 /dts-v1/;
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
 
 /*
  * This is commented-out for now.
@@ -187,6 +183,11 @@
 				"DEBUG0", "DEBUG1", "DEBUG2", "DEBUG3",
 				"DEBUG4", "DEBUG5", "DEBUG6", "DEBUG7";
 
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupts = <10>;
+			interrupt-parent = <&PIC1>;
+
 			/*
 			 * This is commented out while a standard binding
 			 * for i2c over gpio is defined.
@@ -235,5 +236,21 @@
 			panic-indicator;
 		};
 	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		power {
+			label = "Power Button";
+			gpios = <&GPIO 0 GPIO_ACTIVE_HIGH>;
+			linux,code = <KEY_POWER>;
+		};
+
+		eject {
+			label = "Eject Button";
+			gpios = <&GPIO 6 GPIO_ACTIVE_HIGH>;
+			linux,code = <KEY_EJECTCD>;
+		};
+	};
 };
 
diff --git a/arch/powerpc/boot/dts/xcalibur1501.dts b/arch/powerpc/boot/dts/xcalibur1501.dts
index 1f2952d..46c25bd 100644
--- a/arch/powerpc/boot/dts/xcalibur1501.dts
+++ b/arch/powerpc/boot/dts/xcalibur1501.dts
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008 Extreme Engineering Solutions, Inc.
  * Based on MPC8572DS device tree from Freescale Semiconductor, Inc.
  *
  * XCalibur1501 6U CompactPCI single-board computer based on MPC8572E
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/xpedite5200.dts b/arch/powerpc/boot/dts/xpedite5200.dts
index 5b10e56..840ea84 100644
--- a/arch/powerpc/boot/dts/xpedite5200.dts
+++ b/arch/powerpc/boot/dts/xpedite5200.dts
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2009 Extreme Engineering Solutions, Inc.
  * Based on TQM8548 device tree
  *
  * XPedite5200 PrPMC/XMC module based on MPC8548E
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/xpedite5200_xmon.dts b/arch/powerpc/boot/dts/xpedite5200_xmon.dts
index d5e1442..449fc1b 100644
--- a/arch/powerpc/boot/dts/xpedite5200_xmon.dts
+++ b/arch/powerpc/boot/dts/xpedite5200_xmon.dts
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2009 Extreme Engineering Solutions, Inc.
  * Based on TQM8548 device tree
  *
  * XPedite5200 PrPMC/XMC module based on MPC8548E.  This dts is for the
  * xMon boot loader memory map which differs from U-Boot's.
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/xpedite5301.dts b/arch/powerpc/boot/dts/xpedite5301.dts
index 7bcc94f..12184e1 100644
--- a/arch/powerpc/boot/dts/xpedite5301.dts
+++ b/arch/powerpc/boot/dts/xpedite5301.dts
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008 Extreme Engineering Solutions, Inc.
  * Based on MPC8572DS device tree from Freescale Semiconductor, Inc.
  *
  * XPedite5301 PMC/XMC module based on MPC8572E
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/xpedite5330.dts b/arch/powerpc/boot/dts/xpedite5330.dts
index 86df8bc..e8fc90c 100644
--- a/arch/powerpc/boot/dts/xpedite5330.dts
+++ b/arch/powerpc/boot/dts/xpedite5330.dts
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008 Extreme Engineering Solutions, Inc.
  * Based on MPC8572DS device tree from Freescale Semiconductor, Inc.
  *
  * XPedite5330 3U CompactPCI module based on MPC8572E
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/dts/xpedite5370.dts b/arch/powerpc/boot/dts/xpedite5370.dts
index b8ade09..2b5aa2f 100644
--- a/arch/powerpc/boot/dts/xpedite5370.dts
+++ b/arch/powerpc/boot/dts/xpedite5370.dts
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008 Extreme Engineering Solutions, Inc.
  * Based on MPC8572DS device tree from Freescale Semiconductor, Inc.
  *
  * XPedite5370 3U VPX single-board computer based on MPC8572E
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /dts-v1/;
diff --git a/arch/powerpc/boot/ebony.c b/arch/powerpc/boot/ebony.c
index 5532ab3..add2316 100644
--- a/arch/powerpc/boot/ebony.c
+++ b/arch/powerpc/boot/ebony.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2007 David Gibson, IBM Corporation.
  *
@@ -9,11 +10,6 @@
  *
  *   Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
  *   Copyright (c) 2003, 2004 Zultys Technologies
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/elf_util.c b/arch/powerpc/boot/elf_util.c
index 316552d..9e6cbdf 100644
--- a/arch/powerpc/boot/elf_util.c
+++ b/arch/powerpc/boot/elf_util.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) Paul Mackerras 1997.
  *
  * Updates for PPC64 by Todd Inglett, Dave Engebretsen & Peter Bergner.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/ep405.c b/arch/powerpc/boot/ep405.c
index 2d08a86..f9ad1e6 100644
--- a/arch/powerpc/boot/ep405.c
+++ b/arch/powerpc/boot/ep405.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Embedded Planet EP405 with PlanetCore firmware
  *
@@ -8,10 +9,6 @@
  * Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/ep8248e.c b/arch/powerpc/boot/ep8248e.c
index f57d14d..2ab9e0d 100644
--- a/arch/powerpc/boot/ep8248e.c
+++ b/arch/powerpc/boot/ep8248e.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Embedded Planet EP8248E with PlanetCore firmware
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/ep88xc.c b/arch/powerpc/boot/ep88xc.c
index a400f54..1c277a1 100644
--- a/arch/powerpc/boot/ep88xc.c
+++ b/arch/powerpc/boot/ep88xc.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Embedded Planet EP88xC with PlanetCore firmware
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/epapr.c b/arch/powerpc/boot/epapr.c
index 02e91aa..7c5b26a 100644
--- a/arch/powerpc/boot/epapr.c
+++ b/arch/powerpc/boot/epapr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Bootwrapper for ePAPR compliant firmwares
  *
@@ -8,10 +9,6 @@
  *   and
  * Scott Wood <scottwood@freescale.com>
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/fsl-soc.c b/arch/powerpc/boot/fsl-soc.c
index b835ed6..01bad8e 100644
--- a/arch/powerpc/boot/fsl-soc.c
+++ b/arch/powerpc/boot/fsl-soc.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Freescale SOC support functions
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/gamecube-head.S b/arch/powerpc/boot/gamecube-head.S
index 65a9b2a..ccf5f10 100644
--- a/arch/powerpc/boot/gamecube-head.S
+++ b/arch/powerpc/boot/gamecube-head.S
@@ -1,15 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * arch/powerpc/boot/gamecube-head.S
  *
  * Nintendo GameCube bootwrapper entry.
  * Copyright (C) 2004-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #include "ppc_asm.h"
diff --git a/arch/powerpc/boot/gamecube.c b/arch/powerpc/boot/gamecube.c
index 28ae705..d030612 100644
--- a/arch/powerpc/boot/gamecube.c
+++ b/arch/powerpc/boot/gamecube.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/boot/gamecube.c
  *
  * Nintendo GameCube bootwrapper support
  * Copyright (C) 2004-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #include <stddef.h>
diff --git a/arch/powerpc/boot/hack-coff.c b/arch/powerpc/boot/hack-coff.c
index 5e5a657..a010e12 100644
--- a/arch/powerpc/boot/hack-coff.c
+++ b/arch/powerpc/boot/hack-coff.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * hack-coff.c - hack the header of an xcoff file to fill in
  * a few fields needed by the Open Firmware xcoff loader on
  * Power Macs but not initialized by objcopy.
  *
  * Copyright (C) Paul Mackerras 1997.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/arch/powerpc/boot/holly.c b/arch/powerpc/boot/holly.c
index 58013b9..557c7a0 100644
--- a/arch/powerpc/boot/holly.c
+++ b/arch/powerpc/boot/holly.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2007 IBM Corporation
  *
@@ -6,10 +7,6 @@
  *
  * Based on earlier code:
  * Copyright (C) Paul Mackerras 1997.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/libfdt-wrapper.c b/arch/powerpc/boot/libfdt-wrapper.c
index 535e8fd..217d0d7 100644
--- a/arch/powerpc/boot/libfdt-wrapper.c
+++ b/arch/powerpc/boot/libfdt-wrapper.c
@@ -1,24 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file does the necessary interface mapping between the bootwrapper
  * device tree operations and the interface provided by shared source
  * files flatdevicetree.[ch].
  *
  * Copyright 2007 David Gibson, IBM Corporation.
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version.
- *
- * This library 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 library; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <stddef.h>
diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h
index 2a0c8b1..2abc8e8 100644
--- a/arch/powerpc/boot/libfdt_env.h
+++ b/arch/powerpc/boot/libfdt_env.h
@@ -5,6 +5,8 @@
 #include <types.h>
 #include <string.h>
 
+#define INT_MAX			((int)(~0U>>1))
+
 #include "of.h"
 
 typedef unsigned long uintptr_t;
diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c
index 78aaf4f..a9d2091 100644
--- a/arch/powerpc/boot/main.c
+++ b/arch/powerpc/boot/main.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) Paul Mackerras 1997.
  *
  * Updates for PPC64 by Todd Inglett, Dave Engebretsen & Peter Bergner.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdarg.h>
 #include <stddef.h>
@@ -150,6 +146,46 @@
 	return (struct addr_range){(void *)initrd_addr, initrd_size};
 }
 
+#ifdef __powerpc64__
+static void prep_esm_blob(struct addr_range vmlinux, void *chosen)
+{
+	unsigned long esm_blob_addr, esm_blob_size;
+
+	/* Do we have an ESM (Enter Secure Mode) blob? */
+	if (_esm_blob_end <= _esm_blob_start)
+		return;
+
+	printf("Attached ESM blob at 0x%p-0x%p\n\r",
+	       _esm_blob_start, _esm_blob_end);
+	esm_blob_addr = (unsigned long)_esm_blob_start;
+	esm_blob_size = _esm_blob_end - _esm_blob_start;
+
+	/*
+	 * If the ESM blob is too low it will be clobbered when the
+	 * kernel relocates to its final location.  In this case,
+	 * allocate a safer place and move it.
+	 */
+	if (esm_blob_addr < vmlinux.size) {
+		void *old_addr = (void *)esm_blob_addr;
+
+		printf("Allocating 0x%lx bytes for esm_blob ...\n\r",
+		       esm_blob_size);
+		esm_blob_addr = (unsigned long)malloc(esm_blob_size);
+		if (!esm_blob_addr)
+			fatal("Can't allocate memory for ESM blob !\n\r");
+		printf("Relocating ESM blob 0x%lx <- 0x%p (0x%lx bytes)\n\r",
+		       esm_blob_addr, old_addr, esm_blob_size);
+		memmove((void *)esm_blob_addr, old_addr, esm_blob_size);
+	}
+
+	/* Tell the kernel ESM blob address via device tree. */
+	setprop_val(chosen, "linux,esm-blob-start", (u32)(esm_blob_addr));
+	setprop_val(chosen, "linux,esm-blob-end", (u32)(esm_blob_addr + esm_blob_size));
+}
+#else
+static inline void prep_esm_blob(struct addr_range vmlinux, void *chosen) { }
+#endif
+
 /* 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.
@@ -218,6 +254,7 @@
 	vmlinux = prep_kernel();
 	initrd = prep_initrd(vmlinux, chosen,
 			     loader_info.initrd_addr, loader_info.initrd_size);
+	prep_esm_blob(vmlinux, chosen);
 	prep_cmdline(chosen);
 
 	printf("Finalizing device tree...");
diff --git a/arch/powerpc/boot/mpc8xx.c b/arch/powerpc/boot/mpc8xx.c
index c9bd928..e19ef64 100644
--- a/arch/powerpc/boot/mpc8xx.c
+++ b/arch/powerpc/boot/mpc8xx.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * MPC8xx support functions
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/mvme5100.c b/arch/powerpc/boot/mvme5100.c
index cb865f8..51453d0 100644
--- a/arch/powerpc/boot/mvme5100.c
+++ b/arch/powerpc/boot/mvme5100.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Motorola/Emerson MVME5100 with PPCBug firmware.
  *
  * Author: Stephen Chivers <schivers@csc.com>
  *
  * Copyright 2013 CSC Australia Pty. Ltd.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
  */
 #include "types.h"
 #include "ops.h"
diff --git a/arch/powerpc/boot/mvme7100.c b/arch/powerpc/boot/mvme7100.c
index 8b0a932..1e21845 100644
--- a/arch/powerpc/boot/mvme7100.c
+++ b/arch/powerpc/boot/mvme7100.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Motload compatibility for the Emerson/Artesyn MVME7100
  *
  * Copyright 2016 Elettra-Sincrotrone Trieste S.C.p.A.
  *
  * Author: Alessio Igor Bogani <alessio.bogani@elettra.eu>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/of.c b/arch/powerpc/boot/of.c
index 7ca910c..2fbd4ae 100644
--- a/arch/powerpc/boot/of.c
+++ b/arch/powerpc/boot/of.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) Paul Mackerras 1997.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/ofconsole.c b/arch/powerpc/boot/ofconsole.c
index 8b75470..8eb0f1c 100644
--- a/arch/powerpc/boot/ofconsole.c
+++ b/arch/powerpc/boot/ofconsole.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * OF console routines
  *
  * Copyright (C) Paul Mackerras 1997.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stddef.h>
 #include "types.h"
diff --git a/arch/powerpc/boot/oflib.c b/arch/powerpc/boot/oflib.c
index 46c98a4..8759c98 100644
--- a/arch/powerpc/boot/oflib.c
+++ b/arch/powerpc/boot/oflib.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) Paul Mackerras 1997.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stddef.h>
 #include "types.h"
diff --git a/arch/powerpc/boot/opal-calls.S b/arch/powerpc/boot/opal-calls.S
index 2a99fc9..ad0e15d 100644
--- a/arch/powerpc/boot/opal-calls.S
+++ b/arch/powerpc/boot/opal-calls.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2016 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include "ppc_asm.h"
diff --git a/arch/powerpc/boot/opal.c b/arch/powerpc/boot/opal.c
index 0272570..b69818c 100644
--- a/arch/powerpc/boot/opal.c
+++ b/arch/powerpc/boot/opal.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2016 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include "ops.h"
@@ -13,8 +9,6 @@
 #include <libfdt.h>
 #include "../include/asm/opal-api.h"
 
-#ifdef CONFIG_PPC64_BOOT_WRAPPER
-
 /* Global OPAL struct used by opal-call.S */
 struct opal {
 	u64 base;
@@ -101,9 +95,3 @@
 
 	return 0;
 }
-#else
-int opal_console_init(void *devp, struct serial_console_data *scdp)
-{
-	return -1;
-}
-#endif /* __powerpc64__ */
diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h
index cd04372..e060676 100644
--- a/arch/powerpc/boot/ops.h
+++ b/arch/powerpc/boot/ops.h
@@ -251,6 +251,8 @@
 extern char _initrd_end[];
 extern char _dtb_start[];
 extern char _dtb_end[];
+extern char _esm_blob_start[];
+extern char _esm_blob_end[];
 
 static inline __attribute__((const))
 int __ilog2_u32(u32 n)
diff --git a/arch/powerpc/boot/page.h b/arch/powerpc/boot/page.h
index 87c42d7..c3d55fc 100644
--- a/arch/powerpc/boot/page.h
+++ b/arch/powerpc/boot/page.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _PPC_BOOT_PAGE_H
 #define _PPC_BOOT_PAGE_H
 /*
  * Copyright (C) 2001 PPC64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifdef __ASSEMBLY__
diff --git a/arch/powerpc/boot/planetcore.c b/arch/powerpc/boot/planetcore.c
index 75117e6..d5f391e 100644
--- a/arch/powerpc/boot/planetcore.c
+++ b/arch/powerpc/boot/planetcore.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * PlanetCore configuration data support functions
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "stdio.h"
diff --git a/arch/powerpc/boot/ppc_asm.h b/arch/powerpc/boot/ppc_asm.h
index c63299f..192b975 100644
--- a/arch/powerpc/boot/ppc_asm.h
+++ b/arch/powerpc/boot/ppc_asm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _PPC64_PPC_ASM_H
 #define _PPC64_PPC_ASM_H
 /*
@@ -5,11 +6,6 @@
  * Definitions used by various bits of low-level assembly code on PowerPC.
  *
  * Copyright (C) 1995-1999 Gary Thomas, Paul Mackerras, Cort Dougan.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 /* Condition Register Bit Fields */
diff --git a/arch/powerpc/boot/ppcboot-hotfoot.h b/arch/powerpc/boot/ppcboot-hotfoot.h
index 1a3e80b..4728db9 100644
--- a/arch/powerpc/boot/ppcboot-hotfoot.h
+++ b/arch/powerpc/boot/ppcboot-hotfoot.h
@@ -1,3 +1,4 @@
+/* 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.
@@ -18,21 +19,6 @@
 /*
  * (C) Copyright 2000, 2001
  * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
  */
 
 #ifndef __PPCBOOT_H__
diff --git a/arch/powerpc/boot/ppcboot.h b/arch/powerpc/boot/ppcboot.h
index 453df42..a78b0b2 100644
--- a/arch/powerpc/boot/ppcboot.h
+++ b/arch/powerpc/boot/ppcboot.h
@@ -1,3 +1,4 @@
+/* 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.
@@ -6,21 +7,6 @@
 /*
  * (C) Copyright 2000, 2001
  * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
  */
 
 #ifndef __PPCBOOT_H__
diff --git a/arch/powerpc/boot/pq2.c b/arch/powerpc/boot/pq2.c
index f6d1185..de27f1c 100644
--- a/arch/powerpc/boot/pq2.c
+++ b/arch/powerpc/boot/pq2.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * PowerQUICC II support functions
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/ps3-head.S b/arch/powerpc/boot/ps3-head.S
index 3dc44b0..0a4ebfc 100644
--- a/arch/powerpc/boot/ps3-head.S
+++ b/arch/powerpc/boot/ps3-head.S
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  PS3 bootwrapper entry.
  *
  *  Copyright (C) 2007 Sony Computer Entertainment Inc.
  *  Copyright 2007 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include "ppc_asm.h"
diff --git a/arch/powerpc/boot/ps3-hvcall.S b/arch/powerpc/boot/ps3-hvcall.S
index d6068f1..ff74102 100644
--- a/arch/powerpc/boot/ps3-hvcall.S
+++ b/arch/powerpc/boot/ps3-hvcall.S
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  PS3 bootwrapper hvcalls.
  *
  *  Copyright (C) 2007 Sony Computer Entertainment Inc.
  *  Copyright 2007 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include "ppc_asm.h"
diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c
index a05558a..c52552a 100644
--- a/arch/powerpc/boot/ps3.c
+++ b/arch/powerpc/boot/ps3.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 bootwrapper support.
  *
  *  Copyright (C) 2007 Sony Computer Entertainment Inc.
  *  Copyright 2007 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <stdarg.h>
diff --git a/arch/powerpc/boot/redboot-83xx.c b/arch/powerpc/boot/redboot-83xx.c
index 79aa9e1..b610e78 100644
--- a/arch/powerpc/boot/redboot-83xx.c
+++ b/arch/powerpc/boot/redboot-83xx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * RedBoot firmware support
  *
@@ -5,10 +6,6 @@
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
  * Copyright (c) 2008 Codehermit
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/redboot-8xx.c b/arch/powerpc/boot/redboot-8xx.c
index f7945ad..d7006ee 100644
--- a/arch/powerpc/boot/redboot-8xx.c
+++ b/arch/powerpc/boot/redboot-8xx.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * RedBoot firmware support
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/reg.h b/arch/powerpc/boot/reg.h
index 9c2c997..fd8f4fc 100644
--- a/arch/powerpc/boot/reg.h
+++ b/arch/powerpc/boot/reg.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _PPC_BOOT_REG_H
 #define _PPC_BOOT_REG_H
 /*
  * Copyright 2007 Davud Gibson, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 static inline u32 mfpvr(void)
diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c
index 48e3743..9457863 100644
--- a/arch/powerpc/boot/serial.c
+++ b/arch/powerpc/boot/serial.c
@@ -92,7 +92,8 @@
 	if (devp == NULL)
 		goto err_out;
 
-	if (getprop(devp, "linux,stdout-path", path, MAX_PATH_LEN) > 0) {
+	if (getprop(devp, "linux,stdout-path", path, MAX_PATH_LEN) > 0 ||
+		getprop(devp, "stdout-path", path, MAX_PATH_LEN) > 0) {
 		devp = finddevice(path);
 		if (devp == NULL)
 			goto err_out;
diff --git a/arch/powerpc/boot/simpleboot.c b/arch/powerpc/boot/simpleboot.c
index 9f8c678..c80691d 100644
--- a/arch/powerpc/boot/simpleboot.c
+++ b/arch/powerpc/boot/simpleboot.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * The simple platform -- for booting when firmware doesn't supply a device
  *                        tree or any platform configuration information.
@@ -9,10 +10,6 @@
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
  * Copyright (c) 2008 Secret Lab Technologies Ltd.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/stdbool.h b/arch/powerpc/boot/stdbool.h
index f818efb..2dfe247 100644
--- a/arch/powerpc/boot/stdbool.h
+++ b/arch/powerpc/boot/stdbool.h
@@ -1,14 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) IBM Corporation 2016.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * This file is only necessary because some of the pre-boot decompressors
  * expect stdbool.h to be available.
- *
  */
 
 #include "types.h"
diff --git a/arch/powerpc/boot/stdint.h b/arch/powerpc/boot/stdint.h
index c1c853b..5cc5e87 100644
--- a/arch/powerpc/boot/stdint.h
+++ b/arch/powerpc/boot/stdint.h
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) IBM Corporation 2016.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * This file is only necessary because some of the pre-boot decompressors
  * expect stdint.h to be available.
  */
diff --git a/arch/powerpc/boot/stdio.c b/arch/powerpc/boot/stdio.c
index 98042ef..31eece2 100644
--- a/arch/powerpc/boot/stdio.c
+++ b/arch/powerpc/boot/stdio.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) Paul Mackerras 1997.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/stdlib.c b/arch/powerpc/boot/stdlib.c
index e00d58c..868b019 100644
--- a/arch/powerpc/boot/stdlib.c
+++ b/arch/powerpc/boot/stdlib.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * stdlib functions
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "stdlib.h"
diff --git a/arch/powerpc/boot/string.S b/arch/powerpc/boot/string.S
index acc9428..d2a2dbf 100644
--- a/arch/powerpc/boot/string.S
+++ b/arch/powerpc/boot/string.S
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) Paul Mackerras 1997.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * NOTE: this code runs in 32 bit mode and is packaged as ELF32.
  */
 
diff --git a/arch/powerpc/boot/treeboot-akebono.c b/arch/powerpc/boot/treeboot-akebono.c
index bcc5902..e3cc259 100644
--- a/arch/powerpc/boot/treeboot-akebono.c
+++ b/arch/powerpc/boot/treeboot-akebono.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright © 2013 Tony Breeds IBM Corporation
  * Copyright © 2013 Alistair Popple IBM Corporation
@@ -14,11 +15,6 @@
  *    Copyright 2007 David Gibson, IBM Corporation.
  *    Copyright 2010 Ben. Herrenschmidt, IBM Corporation.
  *    Copyright © 2011 David Kleikamp IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/treeboot-bamboo.c b/arch/powerpc/boot/treeboot-bamboo.c
index 9eee48f..97b5b16 100644
--- a/arch/powerpc/boot/treeboot-bamboo.c
+++ b/arch/powerpc/boot/treeboot-bamboo.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright IBM Corporation, 2007
  * Josh Boyer <jwboyer@linux.vnet.ibm.com>
  *
  * Based on ebony wrapper:
  * Copyright 2007 David Gibson, IBM 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
  */
 #include "ops.h"
 #include "stdio.h"
diff --git a/arch/powerpc/boot/treeboot-currituck.c b/arch/powerpc/boot/treeboot-currituck.c
index 303d207..d53e8a5 100644
--- a/arch/powerpc/boot/treeboot-currituck.c
+++ b/arch/powerpc/boot/treeboot-currituck.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright © 2011 Tony Breeds IBM Corporation
  *
@@ -13,11 +14,6 @@
  *    Copyright 2007 David Gibson, IBM Corporation.
  *    Copyright 2010 Ben. Herrenschmidt, IBM Corporation.
  *    Copyright © 2011 David Kleikamp IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/treeboot-ebony.c b/arch/powerpc/boot/treeboot-ebony.c
index 21cc483..332e286 100644
--- a/arch/powerpc/boot/treeboot-ebony.c
+++ b/arch/powerpc/boot/treeboot-ebony.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Ebony
  *
@@ -6,10 +7,6 @@
  * Copyright 2007 David Gibson, IBM Corporatio.
  *   Based on cuboot-83xx.c, which is:
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/treeboot-iss4xx.c b/arch/powerpc/boot/treeboot-iss4xx.c
index 733f8bf..9ab5560 100644
--- a/arch/powerpc/boot/treeboot-iss4xx.c
+++ b/arch/powerpc/boot/treeboot-iss4xx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2010 Ben. Herrenschmidt, IBM Corporation.
  *
@@ -11,11 +12,6 @@
  *   Copyright (c) 2003, 2004 Zultys Technologies
  *
  *    Copyright 2007 David Gibson, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <stdarg.h>
 #include <stddef.h>
diff --git a/arch/powerpc/boot/treeboot-walnut.c b/arch/powerpc/boot/treeboot-walnut.c
index 097974e..623f58e 100644
--- a/arch/powerpc/boot/treeboot-walnut.c
+++ b/arch/powerpc/boot/treeboot-walnut.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Old U-boot compatibility for Walnut
  *
@@ -6,10 +7,6 @@
  * Copyright 2007 IBM Corporation
  *   Based on cuboot-83xx.c, which is:
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/ugecon.c b/arch/powerpc/boot/ugecon.c
index 8f2a6b3..938a38b 100644
--- a/arch/powerpc/boot/ugecon.c
+++ b/arch/powerpc/boot/ugecon.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/boot/ugecon.c
  *
  * USB Gecko bootwrapper console.
  * Copyright (C) 2008-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #include <stddef.h>
diff --git a/arch/powerpc/boot/ugecon.h b/arch/powerpc/boot/ugecon.h
index 4373753..291f33f 100644
--- a/arch/powerpc/boot/ugecon.h
+++ b/arch/powerpc/boot/ugecon.h
@@ -1,15 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * arch/powerpc/boot/ugecon.h
  *
  * USB Gecko early bootwrapper console.
  * Copyright (C) 2008-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #ifndef __UGECON_H
diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S
index ec06917..f11f058 100644
--- a/arch/powerpc/boot/util.S
+++ b/arch/powerpc/boot/util.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copied from <file:arch/powerpc/kernel/misc_32.S>
  *
@@ -10,12 +11,6 @@
  * kexec bits:
  * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
  * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 #include "ppc_asm.h"
 
diff --git a/arch/powerpc/boot/virtex.c b/arch/powerpc/boot/virtex.c
index f622805..f731cbb 100644
--- a/arch/powerpc/boot/virtex.c
+++ b/arch/powerpc/boot/virtex.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * The platform specific code for virtex devices since a boot loader is not
  * always used.
  *
  * (C) Copyright 2008 Xilinx, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include "ops.h"
diff --git a/arch/powerpc/boot/wii-head.S b/arch/powerpc/boot/wii-head.S
index edd79b8..7b1e5a0 100644
--- a/arch/powerpc/boot/wii-head.S
+++ b/arch/powerpc/boot/wii-head.S
@@ -1,15 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * arch/powerpc/boot/wii-head.S
  *
  * Nintendo Wii bootwrapper entry.
  * Copyright (C) 2008-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #include "ppc_asm.h"
diff --git a/arch/powerpc/boot/wii.c b/arch/powerpc/boot/wii.c
index 2ebaec0..59406ad 100644
--- a/arch/powerpc/boot/wii.c
+++ b/arch/powerpc/boot/wii.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/boot/wii.c
  *
  * Nintendo Wii bootwrapper support
  * Copyright (C) 2008-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #include <stddef.h>
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index f9141ea..ed62663 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -1,8 +1,7 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
 
 # Copyright (C) 2006 Paul Mackerras, IBM Corporation <paulus@samba.org>
-# This program may be used under the terms of version 2 of the GNU
-# General Public License.
 
 # This script takes a kernel binary and optionally an initrd image
 # and/or a device-tree blob, and creates a bootable zImage for a
@@ -14,6 +13,7 @@
 # -i initrd	specify initrd file
 # -d devtree	specify device-tree blob
 # -s tree.dts	specify device-tree source file (needs dtc installed)
+# -e esm_blob   specify ESM blob for secure images
 # -c		cache $kernel.strip.gz (use if present & newer, else make)
 # -C prefix	specify command prefix for cross-building tools
 #		(strip, objcopy, ld)
@@ -38,9 +38,11 @@
 initrd=
 dtb=
 dts=
+esm_blob=
 cacheit=
 binary=
 compression=.gz
+uboot_comp=gzip
 pie=
 format=
 
@@ -60,9 +62,9 @@
 
 usage() {
     echo 'Usage: wrapper [-o output] [-p platform] [-i initrd]' >&2
-    echo '       [-d devtree] [-s tree.dts] [-c] [-C cross-prefix]' >&2
-    echo '       [-D datadir] [-W workingdir] [-Z (gz|xz|none)]' >&2
-    echo '       [--no-compression] [vmlinux]' >&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
     exit 1
 }
 
@@ -105,6 +107,11 @@
 	[ "$#" -gt 0 ] || usage
 	dtb="$1"
 	;;
+    -e)
+	shift
+	[ "$#" -gt 0 ] || usage
+	esm_blob="$1"
+	;;
     -s)
 	shift
 	[ "$#" -gt 0 ] || usage
@@ -131,22 +138,29 @@
 	;;
     -z)
 	compression=.gz
+	uboot_comp=gzip
 	;;
     -Z)
 	shift
 	[ "$#" -gt 0 ] || usage
-        [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "none" ] || usage
+        [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "lzma" -o "$1" != "lzo" -o "$1" != "none" ] || usage
 
 	compression=".$1"
+	uboot_comp=$1
 
         if [ $compression = ".none" ]; then
                 compression=
+		uboot_comp=none
         fi
+	if [ $uboot_comp = "gz" ]; then
+		uboot_comp=gzip
+	fi
 	;;
     --no-gzip)
         # a "feature" of the the wrapper script is that it can be used outside
         # the kernel tree. So keeping this around for backwards compatibility.
         compression=
+	uboot_comp=none
         ;;
     -?)
 	usage
@@ -211,9 +225,16 @@
 tmp=$tmpdir/zImage.$$.o
 ksection=.kernel:vmlinux.strip
 isection=.kernel:initrd
+esection=.kernel:esm_blob
 link_address='0x400000'
 make_space=y
 
+
+if [ -n "$esm_blob" -a "$platform" != "pseries" ]; then
+    echo "ESM blob not support on non-pseries platforms" >&2
+    exit 1
+fi
+
 case "$platform" in
 of)
     platformo="$object/of.o $object/epapr.o"
@@ -366,9 +387,16 @@
     .gz)
         gzip -n -f -9 "$vmz.$$"
         ;;
+    .lzma)
+        xz --format=lzma -f -6 "$vmz.$$"
+	;;
+    .lzo)
+        lzop -f -9 "$vmz.$$"
+	;;
     *)
         # drop the compression suffix so the stripped vmlinux is used
         compression=
+	uboot_comp=none
 	;;
     esac
 
@@ -412,7 +440,7 @@
 case "$platform" in
 uboot)
     rm -f "$ofile"
-    ${MKIMAGE} -A ppc -O linux -T kernel -C gzip -a $membase -e $membase \
+    ${MKIMAGE} -A ppc -O linux -T kernel -C $uboot_comp -a $membase -e $membase \
 	$uboot_version -d "$vmz" "$ofile"
     if [ -z "$cacheit" ]; then
 	rm -f "$vmz"
@@ -463,6 +491,10 @@
     fi
 fi
 
+if [ -n "$esm_blob" ]; then
+    addsec $tmp "$esm_blob" $esection
+fi
+
 if [ "$platform" != "miboot" ]; then
     if [ -n "$link_address" ] ; then
         text_start="-Ttext $link_address"
diff --git a/arch/powerpc/boot/xz_config.h b/arch/powerpc/boot/xz_config.h
index e22e5b3..ebfadd3 100644
--- a/arch/powerpc/boot/xz_config.h
+++ b/arch/powerpc/boot/xz_config.h
@@ -20,10 +20,30 @@
 
 #ifdef __LITTLE_ENDIAN__
 #define get_le32(p) (*((uint32_t *) (p)))
+#define cpu_to_be32(x) swab32(x)
+static inline u32 be32_to_cpup(const u32 *p)
+{
+	return swab32p((u32 *)p);
+}
 #else
 #define get_le32(p) swab32p(p)
+#define cpu_to_be32(x) (x)
+static inline u32 be32_to_cpup(const u32 *p)
+{
+	return *p;
+}
 #endif
 
+static inline uint32_t get_unaligned_be32(const void *p)
+{
+	return be32_to_cpup(p);
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+	*((u32 *)p) = cpu_to_be32(val);
+}
+
 #define memeq(a, b, size) (memcmp(a, b, size) == 0)
 #define memzero(buf, size) memset(buf, 0, size)
 
diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S
index 4ac1e36..a21f3a7 100644
--- a/arch/powerpc/boot/zImage.lds.S
+++ b/arch/powerpc/boot/zImage.lds.S
@@ -68,6 +68,14 @@
     _initrd_end =  .;
   }
 
+  . = ALIGN(4096);
+  .kernel:esm_blob :
+  {
+    _esm_blob_start =  .;
+    *(.kernel:esm_blob)
+    _esm_blob_end =  .;
+  }
+
 #ifdef CONFIG_PPC64_BOOT_WRAPPER
   . = ALIGN(256);
   .got :
diff --git a/arch/powerpc/configs/40x/acadia_defconfig b/arch/powerpc/configs/40x/acadia_defconfig
index e57344c..5a75e4f 100644
--- a/arch/powerpc/configs/40x/acadia_defconfig
+++ b/arch/powerpc/configs/40x/acadia_defconfig
@@ -22,7 +22,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/40x/ep405_defconfig b/arch/powerpc/configs/40x/ep405_defconfig
index 0f66f8a..e2691c5 100644
--- a/arch/powerpc/configs/40x/ep405_defconfig
+++ b/arch/powerpc/configs/40x/ep405_defconfig
@@ -21,7 +21,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig
index b5cc742..949989e 100644
--- a/arch/powerpc/configs/40x/kilauea_defconfig
+++ b/arch/powerpc/configs/40x/kilauea_defconfig
@@ -24,7 +24,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -33,7 +32,7 @@
 CONFIG_MTD_JEDECPROBE=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_NDFC=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
diff --git a/arch/powerpc/configs/40x/klondike_defconfig b/arch/powerpc/configs/40x/klondike_defconfig
index caab658..4347a87 100644
--- a/arch/powerpc/configs/40x/klondike_defconfig
+++ b/arch/powerpc/configs/40x/klondike_defconfig
@@ -14,7 +14,6 @@
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_MATH_EMULATION=y
 # CONFIG_SUSPEND is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_SCSI=y
diff --git a/arch/powerpc/configs/40x/makalu_defconfig b/arch/powerpc/configs/40x/makalu_defconfig
index e0b1489..90b759b 100644
--- a/arch/powerpc/configs/40x/makalu_defconfig
+++ b/arch/powerpc/configs/40x/makalu_defconfig
@@ -21,7 +21,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/40x/obs600_defconfig b/arch/powerpc/configs/40x/obs600_defconfig
index aac06d2..881c300 100644
--- a/arch/powerpc/configs/40x/obs600_defconfig
+++ b/arch/powerpc/configs/40x/obs600_defconfig
@@ -24,7 +24,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -33,7 +32,7 @@
 CONFIG_MTD_JEDECPROBE=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_NDFC=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
diff --git a/arch/powerpc/configs/40x/virtex_defconfig b/arch/powerpc/configs/40x/virtex_defconfig
index a2b2770..5e7c61d 100644
--- a/arch/powerpc/configs/40x/virtex_defconfig
+++ b/arch/powerpc/configs/40x/virtex_defconfig
@@ -31,7 +31,6 @@
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
diff --git a/arch/powerpc/configs/40x/walnut_defconfig b/arch/powerpc/configs/40x/walnut_defconfig
index 6faa03c..0ed4670 100644
--- a/arch/powerpc/configs/40x/walnut_defconfig
+++ b/arch/powerpc/configs/40x/walnut_defconfig
@@ -19,7 +19,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig
index 9fcd361..2fa553e 100644
--- a/arch/powerpc/configs/44x/akebono_defconfig
+++ b/arch/powerpc/configs/44x/akebono_defconfig
@@ -33,7 +33,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/arches_defconfig b/arch/powerpc/configs/44x/arches_defconfig
index 6bba1a5..5a1b9ee 100644
--- a/arch/powerpc/configs/44x/arches_defconfig
+++ b/arch/powerpc/configs/44x/arches_defconfig
@@ -24,7 +24,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/44x/bamboo_defconfig b/arch/powerpc/configs/44x/bamboo_defconfig
index 6f3a6ec..22e1ef5 100644
--- a/arch/powerpc/configs/44x/bamboo_defconfig
+++ b/arch/powerpc/configs/44x/bamboo_defconfig
@@ -22,7 +22,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
diff --git a/arch/powerpc/configs/44x/bluestone_defconfig b/arch/powerpc/configs/44x/bluestone_defconfig
index 6b77aea..8006a57 100644
--- a/arch/powerpc/configs/44x/bluestone_defconfig
+++ b/arch/powerpc/configs/44x/bluestone_defconfig
@@ -20,7 +20,6 @@
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/44x/canyonlands_defconfig b/arch/powerpc/configs/44x/canyonlands_defconfig
index c8e6f04..86f34ea 100644
--- a/arch/powerpc/configs/44x/canyonlands_defconfig
+++ b/arch/powerpc/configs/44x/canyonlands_defconfig
@@ -24,7 +24,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -32,7 +31,7 @@
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_NDFC=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
diff --git a/arch/powerpc/configs/44x/currituck_defconfig b/arch/powerpc/configs/44x/currituck_defconfig
index 5f1df5f..ce3ec5a 100644
--- a/arch/powerpc/configs/44x/currituck_defconfig
+++ b/arch/powerpc/configs/44x/currituck_defconfig
@@ -31,7 +31,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/ebony_defconfig b/arch/powerpc/configs/44x/ebony_defconfig
index e2b6578..f67447c 100644
--- a/arch/powerpc/configs/44x/ebony_defconfig
+++ b/arch/powerpc/configs/44x/ebony_defconfig
@@ -20,7 +20,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/44x/eiger_defconfig b/arch/powerpc/configs/44x/eiger_defconfig
index f6dc23f..5dbd83a 100644
--- a/arch/powerpc/configs/44x/eiger_defconfig
+++ b/arch/powerpc/configs/44x/eiger_defconfig
@@ -25,7 +25,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -33,7 +32,7 @@
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_NDFC=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig
index bae6b26..e49114f 100644
--- a/arch/powerpc/configs/44x/fsp2_defconfig
+++ b/arch/powerpc/configs/44x/fsp2_defconfig
@@ -44,7 +44,6 @@
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_CONNECTOR=y
diff --git a/arch/powerpc/configs/44x/icon_defconfig b/arch/powerpc/configs/44x/icon_defconfig
index 4453a45..fa5378a 100644
--- a/arch/powerpc/configs/44x/icon_defconfig
+++ b/arch/powerpc/configs/44x/icon_defconfig
@@ -24,7 +24,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/44x/iss476-smp_defconfig b/arch/powerpc/configs/44x/iss476-smp_defconfig
index d24bfa6..aae879c 100644
--- a/arch/powerpc/configs/44x/iss476-smp_defconfig
+++ b/arch/powerpc/configs/44x/iss476-smp_defconfig
@@ -33,7 +33,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/44x/katmai_defconfig b/arch/powerpc/configs/44x/katmai_defconfig
index 5d3f685..56eddca 100644
--- a/arch/powerpc/configs/44x/katmai_defconfig
+++ b/arch/powerpc/configs/44x/katmai_defconfig
@@ -22,7 +22,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/44x/rainier_defconfig b/arch/powerpc/configs/44x/rainier_defconfig
index 7b8355a..369bfd2 100644
--- a/arch/powerpc/configs/44x/rainier_defconfig
+++ b/arch/powerpc/configs/44x/rainier_defconfig
@@ -23,7 +23,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/44x/redwood_defconfig b/arch/powerpc/configs/44x/redwood_defconfig
index 918cfb6..8be95f6 100644
--- a/arch/powerpc/configs/44x/redwood_defconfig
+++ b/arch/powerpc/configs/44x/redwood_defconfig
@@ -25,7 +25,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig
index 63302fb..974a4f0 100644
--- a/arch/powerpc/configs/44x/sam440ep_defconfig
+++ b/arch/powerpc/configs/44x/sam440ep_defconfig
@@ -27,7 +27,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/44x/sequoia_defconfig b/arch/powerpc/configs/44x/sequoia_defconfig
index 1e04122..10e517b 100644
--- a/arch/powerpc/configs/44x/sequoia_defconfig
+++ b/arch/powerpc/configs/44x/sequoia_defconfig
@@ -24,7 +24,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -33,7 +32,7 @@
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_NDFC=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
diff --git a/arch/powerpc/configs/44x/taishan_defconfig b/arch/powerpc/configs/44x/taishan_defconfig
index 42cc7b4..cd08f3d 100644
--- a/arch/powerpc/configs/44x/taishan_defconfig
+++ b/arch/powerpc/configs/44x/taishan_defconfig
@@ -22,7 +22,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/44x/virtex5_defconfig b/arch/powerpc/configs/44x/virtex5_defconfig
index 99cc3dc..1f74079 100644
--- a/arch/powerpc/configs/44x/virtex5_defconfig
+++ b/arch/powerpc/configs/44x/virtex5_defconfig
@@ -30,7 +30,6 @@
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig
index 6c02f53..af66c69 100644
--- a/arch/powerpc/configs/44x/warp_defconfig
+++ b/arch/powerpc/configs/44x/warp_defconfig
@@ -26,7 +26,6 @@
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
 CONFIG_VLAN_8021Q=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_STANDALONE is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -34,7 +33,7 @@
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_NDFC=y
 CONFIG_MTD_UBI=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/52xx/cm5200_defconfig b/arch/powerpc/configs/52xx/cm5200_defconfig
index 73948e8..2412a6b 100644
--- a/arch/powerpc/configs/52xx/cm5200_defconfig
+++ b/arch/powerpc/configs/52xx/cm5200_defconfig
@@ -23,7 +23,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/52xx/lite5200b_defconfig b/arch/powerpc/configs/52xx/lite5200b_defconfig
index 6fc7f78..63368e6 100644
--- a/arch/powerpc/configs/52xx/lite5200b_defconfig
+++ b/arch/powerpc/configs/52xx/lite5200b_defconfig
@@ -26,7 +26,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/52xx/motionpro_defconfig b/arch/powerpc/configs/52xx/motionpro_defconfig
index ae2a1f7..72762da 100644
--- a/arch/powerpc/configs/52xx/motionpro_defconfig
+++ b/arch/powerpc/configs/52xx/motionpro_defconfig
@@ -23,7 +23,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig
index 1554de6..303600f 100644
--- a/arch/powerpc/configs/52xx/pcm030_defconfig
+++ b/arch/powerpc/configs/52xx/pcm030_defconfig
@@ -36,7 +36,6 @@
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/52xx/tqm5200_defconfig b/arch/powerpc/configs/52xx/tqm5200_defconfig
index 0777e6e..a3c8ca7 100644
--- a/arch/powerpc/configs/52xx/tqm5200_defconfig
+++ b/arch/powerpc/configs/52xx/tqm5200_defconfig
@@ -27,7 +27,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/83xx/asp8347_defconfig b/arch/powerpc/configs/83xx/asp8347_defconfig
index dd884df..1019241 100644
--- a/arch/powerpc/configs/83xx/asp8347_defconfig
+++ b/arch/powerpc/configs/83xx/asp8347_defconfig
@@ -27,7 +27,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_REDBOOT_PARTS=y
diff --git a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig
index 1f69f4e..16a42e2 100644
--- a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig
@@ -24,14 +24,13 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig b/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig
index 797fc3f..80d40ae 100644
--- a/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig
@@ -24,14 +24,13 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=32768
diff --git a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig b/arch/powerpc/configs/83xx/mpc832x_mds_defconfig
index 4f91490..e945554 100644
--- a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig
+++ b/arch/powerpc/configs/83xx/mpc832x_mds_defconfig
@@ -26,7 +26,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
index a484eb8..1715ff5 100644
--- a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig
@@ -27,7 +27,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
index 37f4d93..e65c005 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
@@ -25,7 +25,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CFI=y
diff --git a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
index 7adb670..17714bf 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig
@@ -25,7 +25,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CFI=y
diff --git a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig b/arch/powerpc/configs/83xx/mpc834x_mds_defconfig
index d7ce355..e2ff684 100644
--- a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_mds_defconfig
@@ -26,7 +26,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig b/arch/powerpc/configs/83xx/mpc836x_mds_defconfig
index 92134ce..3eceb6d 100644
--- a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig
+++ b/arch/powerpc/configs/83xx/mpc836x_mds_defconfig
@@ -25,7 +25,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig b/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig
index 97f7ea5..093df33 100644
--- a/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig
+++ b/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig
@@ -24,7 +24,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig b/arch/powerpc/configs/83xx/mpc837x_mds_defconfig
index ee7510a..3f5e5d1 100644
--- a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig
+++ b/arch/powerpc/configs/83xx/mpc837x_mds_defconfig
@@ -24,7 +24,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
index 8966a9a..dad53ef 100644
--- a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
+++ b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig
@@ -26,7 +26,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config
index c03d0fb..9575a38 100644
--- a/arch/powerpc/configs/85xx-hw.config
+++ b/arch/powerpc/configs/85xx-hw.config
@@ -71,7 +71,7 @@
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_MTD_NAND_FSL_IFC=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_PLATRAM=y
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
index dd98f43..920f373 100644
--- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -65,7 +65,6 @@
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_TUNNEL=m
 CONFIG_NET_PKTGEN=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
@@ -73,7 +72,7 @@
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
diff --git a/arch/powerpc/configs/85xx/ksi8560_defconfig b/arch/powerpc/configs/85xx/ksi8560_defconfig
index 9ce6f48..9cb211f 100644
--- a/arch/powerpc/configs/85xx/ksi8560_defconfig
+++ b/arch/powerpc/configs/85xx/ksi8560_defconfig
@@ -23,7 +23,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig b/arch/powerpc/configs/85xx/mpc8540_ads_defconfig
index 5fbc3f9..618e03e 100644
--- a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig
+++ b/arch/powerpc/configs/85xx/mpc8540_ads_defconfig
@@ -24,7 +24,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig b/arch/powerpc/configs/85xx/mpc8560_ads_defconfig
index ff981d7..9bc6283 100644
--- a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig
+++ b/arch/powerpc/configs/85xx/mpc8560_ads_defconfig
@@ -23,7 +23,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig
index 974f070..0683d8c 100644
--- a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig
+++ b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig
@@ -25,7 +25,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/85xx/sbc8548_defconfig b/arch/powerpc/configs/85xx/sbc8548_defconfig
index 7e3e84a..2588817 100644
--- a/arch/powerpc/configs/85xx/sbc8548_defconfig
+++ b/arch/powerpc/configs/85xx/sbc8548_defconfig
@@ -22,7 +22,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/85xx/socrates_defconfig b/arch/powerpc/configs/85xx/socrates_defconfig
index 6106fad..7037a6d 100644
--- a/arch/powerpc/configs/85xx/socrates_defconfig
+++ b/arch/powerpc/configs/85xx/socrates_defconfig
@@ -31,7 +31,7 @@
 CONFIG_MTD_JEDECPROBE=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_SOCRATES=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/85xx/stx_gp3_defconfig b/arch/powerpc/configs/85xx/stx_gp3_defconfig
index 5b9cc01..ecbcc85 100644
--- a/arch/powerpc/configs/85xx/stx_gp3_defconfig
+++ b/arch/powerpc/configs/85xx/stx_gp3_defconfig
@@ -22,7 +22,6 @@
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_NET_PKTGEN=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_PARPORT=m
 CONFIG_PARPORT_PC=m
diff --git a/arch/powerpc/configs/85xx/tqm8548_defconfig b/arch/powerpc/configs/85xx/tqm8548_defconfig
index 2697e4e..afa1b9b 100644
--- a/arch/powerpc/configs/85xx/tqm8548_defconfig
+++ b/arch/powerpc/configs/85xx/tqm8548_defconfig
@@ -29,14 +29,13 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND_ECC_SMC=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_FSL_UPM=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index 6531139..d50aca6 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -54,7 +54,6 @@
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_REDBOOT_PARTS=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -65,7 +64,7 @@
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_CFI_STAA=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_MTD_NAND_FSL_UPM=y
 CONFIG_BLK_DEV_LOOP=y
diff --git a/arch/powerpc/configs/86xx-hw.config b/arch/powerpc/configs/86xx-hw.config
index d3dd6b8..151164c 100644
--- a/arch/powerpc/configs/86xx-hw.config
+++ b/arch/powerpc/configs/86xx-hw.config
@@ -47,7 +47,7 @@
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_JEDECPROBE=y
 CONFIG_MTD_NAND_FSL_ELBC=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_NETDEVICES=y
 CONFIG_NET_TULIP=y
diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig
index 935ea3a..f7a803a 100644
--- a/arch/powerpc/configs/adder875_defconfig
+++ b/arch/powerpc/configs/adder875_defconfig
@@ -26,7 +26,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig
index 12f397d..cf94d28 100644
--- a/arch/powerpc/configs/amigaone_defconfig
+++ b/arch/powerpc/configs/amigaone_defconfig
@@ -37,7 +37,6 @@
 # CONFIG_NETFILTER_XT_MATCH_CONNTRACK is not set
 # CONFIG_NETFILTER_XT_MATCH_STATE is not set
 # CONFIG_IP_NF_MANGLE is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_STANDALONE is not set
 CONFIG_PARPORT=y
 CONFIG_PARPORT_PC=y
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 560a93a..2dd1b58 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -102,7 +102,6 @@
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=131072
diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig
index a203b1c..9ff493d 100644
--- a/arch/powerpc/configs/chrp32_defconfig
+++ b/arch/powerpc/configs/chrp32_defconfig
@@ -38,7 +38,6 @@
 # CONFIG_NETFILTER_XT_MATCH_CONNTRACK is not set
 # CONFIG_NETFILTER_XT_MATCH_STATE is not set
 # CONFIG_IP_NF_MANGLE is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_STANDALONE is not set
 CONFIG_BLK_DEV_FD=y
 CONFIG_BLK_DEV_LOOP=y
diff --git a/arch/powerpc/configs/ep8248e_defconfig b/arch/powerpc/configs/ep8248e_defconfig
index 2e6c8a4..6e08d95 100644
--- a/arch/powerpc/configs/ep8248e_defconfig
+++ b/arch/powerpc/configs/ep8248e_defconfig
@@ -24,7 +24,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 CONFIG_NETFILTER=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig
index 7cb590e..b20bd0c 100644
--- a/arch/powerpc/configs/ep88xc_defconfig
+++ b/arch/powerpc/configs/ep88xc_defconfig
@@ -28,7 +28,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config
index e0567dc..3c7dad1 100644
--- a/arch/powerpc/configs/fsl-emb-nonhw.config
+++ b/arch/powerpc/configs/fsl-emb-nonhw.config
@@ -25,6 +25,7 @@
 CONFIG_CRYPTO_SHA512=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -117,7 +118,6 @@
 CONFIG_TMPFS=y
 CONFIG_UBIFS_FS=y
 CONFIG_UDF_FS=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_UFS_FS=m
 CONFIG_UIO=y
 CONFIG_UNIX=y
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 67c39f4..fbfcc85 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -52,7 +52,6 @@
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_BLK_DEV_LOOP=y
@@ -244,9 +243,7 @@
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
-CONFIG_LATENCYTOP=y
 CONFIG_BOOTX_TEXT=y
-CONFIG_PPC_EARLY_DEBUG=y
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
@@ -262,3 +259,4 @@
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 # CONFIG_CRYPTO_HW is not set
+CONFIG_PRINTK_TIME=y
diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig
index 805b0f8..85e73c3 100644
--- a/arch/powerpc/configs/gamecube_defconfig
+++ b/arch/powerpc/configs/gamecube_defconfig
@@ -35,7 +35,6 @@
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_STANDALONE is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
@@ -91,7 +90,6 @@
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_SPINLOCK=y
 CONFIG_DEBUG_MUTEXES=y
-CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_DMA_API_DEBUG=y
 CONFIG_PPC_EARLY_DEBUG=y
diff --git a/arch/powerpc/configs/guest.config b/arch/powerpc/configs/guest.config
new file mode 100644
index 0000000..8b8cd18
--- /dev/null
+++ b/arch/powerpc/configs/guest.config
@@ -0,0 +1,13 @@
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_BLK_SCSI=y
+CONFIG_SCSI_VIRTIO=y
+CONFIG_VIRTIO_NET=y
+CONFIG_NET_FAILOVER=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_KVM_GUEST=y
+CONFIG_EPAPR_PARAVIRT=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VHOST_NET=y
+CONFIG_VHOST=y
diff --git a/arch/powerpc/configs/holly_defconfig b/arch/powerpc/configs/holly_defconfig
index 71d8d24..067f433 100644
--- a/arch/powerpc/configs/holly_defconfig
+++ b/arch/powerpc/configs/holly_defconfig
@@ -27,7 +27,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig
index 477794c..ea59f3d 100644
--- a/arch/powerpc/configs/linkstation_defconfig
+++ b/arch/powerpc/configs/linkstation_defconfig
@@ -48,7 +48,6 @@
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig
index 59e47ec..2975e64 100644
--- a/arch/powerpc/configs/maple_defconfig
+++ b/arch/powerpc/configs/maple_defconfig
@@ -36,7 +36,6 @@
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
 # CONFIG_SCSI_PROC_FS is not set
@@ -104,11 +103,10 @@
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LATENCYTOP=y
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
 CONFIG_BOOTX_TEXT=y
-CONFIG_PPC_EARLY_DEBUG=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 5d5f08e..6ce4f20 100644
--- a/arch/powerpc/configs/mgcoge_defconfig
+++ b/arch/powerpc/configs/mgcoge_defconfig
@@ -30,7 +30,6 @@
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
 CONFIG_TIPC=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig
index c2b1c44..6203c10 100644
--- a/arch/powerpc/configs/mpc512x_defconfig
+++ b/arch/powerpc/configs/mpc512x_defconfig
@@ -35,7 +35,6 @@
 CONFIG_CAN_MSCAN=y
 CONFIG_CAN_DEBUG_DEVICES=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
@@ -46,7 +45,7 @@
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_ROM=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_MPC5121_NFC=y
 CONFIG_MTD_UBI=y
 CONFIG_BLK_DEV_RAM=y
@@ -120,6 +119,5 @@
 CONFIG_ROOT_NFS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 # CONFIG_CRYPTO_HW is not set
diff --git a/arch/powerpc/configs/mpc5200_defconfig b/arch/powerpc/configs/mpc5200_defconfig
index 7a2b2aa..6f87a5c 100644
--- a/arch/powerpc/configs/mpc5200_defconfig
+++ b/arch/powerpc/configs/mpc5200_defconfig
@@ -27,7 +27,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/mpc7448_hpc2_defconfig b/arch/powerpc/configs/mpc7448_hpc2_defconfig
index 4b14c02..19406a6 100644
--- a/arch/powerpc/configs/mpc7448_hpc2_defconfig
+++ b/arch/powerpc/configs/mpc7448_hpc2_defconfig
@@ -25,7 +25,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/mpc8272_ads_defconfig b/arch/powerpc/configs/mpc8272_ads_defconfig
index b1e88b6..00a4d2b 100644
--- a/arch/powerpc/configs/mpc8272_ads_defconfig
+++ b/arch/powerpc/configs/mpc8272_ads_defconfig
@@ -23,7 +23,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 CONFIG_NETFILTER=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig
index d1b8203..be12572 100644
--- a/arch/powerpc/configs/mpc83xx_defconfig
+++ b/arch/powerpc/configs/mpc83xx_defconfig
@@ -37,7 +37,6 @@
 CONFIG_SYN_COOKIES=y
 CONFIG_INET_ESP=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FW_LOADER is not set
@@ -46,7 +45,7 @@
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig
index ec3fcc2..285d506 100644
--- a/arch/powerpc/configs/mpc885_ads_defconfig
+++ b/arch/powerpc/configs/mpc885_ads_defconfig
@@ -27,7 +27,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/mvme5100_defconfig b/arch/powerpc/configs/mvme5100_defconfig
index 63e38c7..0a0d046 100644
--- a/arch/powerpc/configs/mvme5100_defconfig
+++ b/arch/powerpc/configs/mvme5100_defconfig
@@ -58,7 +58,6 @@
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_LAPB=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=2
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 6daa56f..4b6d31d 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -44,14 +44,13 @@
 CONFIG_INET_AH=y
 CONFIG_INET_ESP=y
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_SLRAM=y
 CONFIG_MTD_PHRAM=y
-CONFIG_MTD_NAND=y
+CONFIG_MTD_RAW_NAND=y
 CONFIG_MTD_NAND_PASEMI=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index 62948d1..4e6e95f 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -20,7 +20,6 @@
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_PMAC=y
-CONFIG_PPC601_SYNC_FIX=y
 CONFIG_GEN_RTC=y
 CONFIG_HIGHMEM=y
 CONFIG_BINFMT_MISC=m
@@ -112,7 +111,6 @@
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
 CONFIG_MAC80211_LEDS=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_STANDALONE is not set
 CONFIG_CONNECTOR=y
 CONFIG_MAC_FLOPPY=m
@@ -293,11 +291,9 @@
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
-CONFIG_LATENCYTOP=y
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
 CONFIG_BOOTX_TEXT=y
-CONFIG_PPC_EARLY_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_SHA512=m
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 6ab34e6..6658cce 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -38,12 +38,15 @@
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 CONFIG_PARTITION_ADVANCED=y
-CONFIG_SCOM_DEBUGFS=y
+# CONFIG_SCOM_DEBUGFS is not set
 CONFIG_OPAL_PRD=y
 CONFIG_PPC_MEMTRACE=y
 # CONFIG_PPC_PSERIES is not set
 # CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
 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_IDLE=y
 CONFIG_HZ_100=y
 CONFIG_BINFMT_MISC=m
@@ -95,7 +98,6 @@
 CONFIG_DNS_RESOLVER=y
 CONFIG_BPF_JIT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=y
@@ -314,7 +316,6 @@
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_HARDLOCKUP_DETECTOR=y
-CONFIG_LATENCYTOP=y
 CONFIG_FUNCTION_TRACER=y
 CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
@@ -350,3 +351,4 @@
 CONFIG_KVM_BOOK3S_64=m
 CONFIG_KVM_BOOK3S_64_HV=m
 CONFIG_VHOST_NET=m
+CONFIG_PRINTK_TIME=y
diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig
index 10fb1df..a5f683a 100644
--- a/arch/powerpc/configs/ppc40x_defconfig
+++ b/arch/powerpc/configs/ppc40x_defconfig
@@ -25,7 +25,6 @@
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index 66dd6bf..6795281 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -36,7 +36,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 CONFIG_BRIDGE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
@@ -44,7 +43,7 @@
 CONFIG_MTD_JEDECPROBE=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_NAND=m
+CONFIG_MTD_RAW_NAND=m
 CONFIG_MTD_NAND_NDFC=m
 CONFIG_MTD_UBI=m
 CONFIG_MTD_UBI_GLUEBI=m
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 5033e63..b250e6f 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -1,4 +1,3 @@
-CONFIG_PPC64=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_NO_HZ=y
@@ -9,26 +8,28 @@
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=18
 CONFIG_LOG_CPU_MAX_BUF_SHIFT=13
+CONFIG_NUMA_BALANCING=y
 CONFIG_CGROUPS=y
+CONFIG_MEMCG=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CGROUP_FREEZER=y
 CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
 CONFIG_CGROUP_BPF=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_BPF_SYSCALL=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_KPROBES=y
-CONFIG_JUMP_LABEL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_PARTITION_ADVANCED=y
+CONFIG_PPC64=y
+CONFIG_NR_CPUS=2048
 CONFIG_PPC_SPLPAR=y
 CONFIG_DTL=y
 CONFIG_SCANLOG=m
 CONFIG_PPC_SMLPAR=y
 CONFIG_IBMEBUS=y
+CONFIG_PPC_SVM=y
 CONFIG_PPC_MAPLE=y
 CONFIG_PPC_PASEMI=y
 CONFIG_PPC_PASEMI_IOMMU=y
@@ -40,16 +41,16 @@
 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_BINFMT_MISC=m
 CONFIG_PPC_TRANSACTIONAL_MEM=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_CRASH_DUMP=y
 CONFIG_IRQ_ALL_CPUS=y
-CONFIG_KSM=y
-CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_PPC_64K_PAGES=y
 CONFIG_SCHED_SMT=y
 CONFIG_HOTPLUG_PCI=y
@@ -57,6 +58,23 @@
 CONFIG_HOTPLUG_PCI_RPA_DLPAR=m
 CONFIG_PCCARD=y
 CONFIG_ELECTRA_CF=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM_BOOK3S_64=m
+CONFIG_KVM_BOOK3S_64_HV=m
+CONFIG_VHOST_NET=m
+CONFIG_OPROFILE=m
+CONFIG_KPROBES=y
+CONFIG_JUMP_LABEL=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_BINFMT_MISC=m
+CONFIG_MEMORY_HOTPLUG=y
+CONFIG_MEMORY_HOTREMOVE=y
+CONFIG_KSM=y
+CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -72,7 +90,7 @@
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
-# CONFIG_IPV6 is not set
+CONFIG_IPV6=y
 CONFIG_NETFILTER=y
 # CONFIG_NETFILTER_ADVANCED is not set
 CONFIG_BRIDGE=m
@@ -81,7 +99,6 @@
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_BPF=m
 CONFIG_BPF_JIT=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_BLK_DEV_FD=y
@@ -160,7 +177,6 @@
 CONFIG_BNX2X=m
 CONFIG_CHELSIO_T1=m
 CONFIG_BE2NET=m
-CONFIG_S2IO=m
 CONFIG_IBMVETH=m
 CONFIG_EHEA=m
 CONFIG_E100=y
@@ -171,6 +187,7 @@
 CONFIG_I40E=m
 CONFIG_MLX4_EN=m
 CONFIG_MYRI10GE=m
+CONFIG_S2IO=m
 CONFIG_PASEMI_MAC=y
 CONFIG_QLGE=m
 CONFIG_NETXEN_NIC=m
@@ -281,7 +298,7 @@
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
-CONFIG_XFS_FS=m
+CONFIG_XFS_FS=y
 CONFIG_XFS_POSIX_ACL=y
 CONFIG_BTRFS_FS=m
 CONFIG_BTRFS_FS_POSIX_ACL=y
@@ -320,25 +337,6 @@
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_STACK_USAGE=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_SOFTLOCKUP_DETECTOR=y
-CONFIG_HARDLOCKUP_DETECTOR=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_LATENCYTOP=y
-CONFIG_FTRACE=y
-CONFIG_FUNCTION_TRACER=y
-CONFIG_FUNCTION_GRAPH_TRACER=y
-CONFIG_SCHED_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_CODE_PATCHING_SELFTEST=y
-CONFIG_FTR_FIXUP_SELFTEST=y
-CONFIG_MSI_BITMAP_SELFTEST=y
-CONFIG_XMON=y
-CONFIG_BOOTX_TEXT=y
-CONFIG_PPC_EARLY_DEBUG=y
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
@@ -361,7 +359,19 @@
 CONFIG_CRYPTO_DEV_NX=y
 CONFIG_CRYPTO_DEV_NX_ENCRYPT=m
 CONFIG_CRYPTO_DEV_VMX=y
-CONFIG_VIRTUALIZATION=y
-CONFIG_KVM_BOOK3S_64=m
-CONFIG_KVM_BOOK3S_64_HV=m
-CONFIG_VHOST_NET=m
+CONFIG_PRINTK_TIME=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_STACK_USAGE=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_HARDLOCKUP_DETECTOR=y
+CONFIG_DEBUG_MUTEXES=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_SCHED_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_CODE_PATCHING_SELFTEST=y
+CONFIG_FTR_FIXUP_SELFTEST=y
+CONFIG_MSI_BITMAP_SELFTEST=y
+CONFIG_XMON=y
+CONFIG_BOOTX_TEXT=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 41d85cb..0d74677 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -50,7 +50,6 @@
 CONFIG_NETFILTER=y
 # CONFIG_NETFILTER_ADVANCED is not set
 CONFIG_BRIDGE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_BLK_DEV_FD=y
@@ -223,7 +222,6 @@
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_MUTEXES=y
-CONFIG_LATENCYTOP=y
 CONFIG_IRQSOFF_TRACER=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 7ee736f..9dca4cf 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -301,7 +301,6 @@
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
-CONFIG_NET_CLS_IND=y
 CONFIG_IRDA=m
 CONFIG_IRLAN=m
 CONFIG_IRNET=m
@@ -346,7 +345,6 @@
 CONFIG_MAC80211_DEBUGFS=y
 CONFIG_NET_9P=m
 CONFIG_NET_9P_VIRTIO=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEBUG_DEVRES=y
 CONFIG_CONNECTOR=y
 CONFIG_PARPORT=m
@@ -1123,8 +1121,8 @@
 CONFIG_NLS_KOI8_R=m
 CONFIG_NLS_KOI8_U=m
 CONFIG_DEBUG_INFO=y
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
 CONFIG_UNUSED_SYMBOLS=y
+CONFIG_HEADERS_INSTALL=y
 CONFIG_HEADERS_CHECK=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
@@ -1149,13 +1147,11 @@
 CONFIG_FAIL_IO_TIMEOUT=y
 CONFIG_FAULT_INJECTION_DEBUG_FS=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
-CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_XMON=y
 CONFIG_BOOTX_TEXT=y
-CONFIG_PPC_EARLY_DEBUG=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_SECURITY_NETWORK_XFRM=y
diff --git a/arch/powerpc/configs/pq2fads_defconfig b/arch/powerpc/configs/pq2fads_defconfig
index 0ededa8..9d8a768 100644
--- a/arch/powerpc/configs/pq2fads_defconfig
+++ b/arch/powerpc/configs/pq2fads_defconfig
@@ -24,7 +24,6 @@
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_SYN_COOKIES=y
 CONFIG_NETFILTER=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 187e2f7..314c639 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -63,7 +63,6 @@
 CONFIG_CFG80211_WEXT=y
 CONFIG_MAC80211=m
 # CONFIG_MAC80211_RC_MINSTREL is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=65535
@@ -171,3 +170,4 @@
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SALSA20=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_PRINTK_TIME=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 0dd5cf7..26126b4 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -42,6 +42,7 @@
 CONFIG_SCANLOG=m
 CONFIG_PPC_SMLPAR=y
 CONFIG_IBMEBUS=y
+CONFIG_PPC_SVM=y
 # CONFIG_PPC_PMAC is not set
 CONFIG_RTAS_FLASH=m
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
@@ -83,7 +84,6 @@
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_BPF=m
 CONFIG_BPF_JIT=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_PARPORT=m
@@ -217,6 +217,7 @@
 CONFIG_USB_EHCI_HCD=y
 # CONFIG_USB_EHCI_HCD_PPC_OF is not set
 CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_STORAGE=m
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=m
@@ -289,10 +290,7 @@
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_HARDLOCKUP_DETECTOR=y
-CONFIG_LATENCYTOP=y
-CONFIG_FTRACE=y
 CONFIG_FUNCTION_TRACER=y
-CONFIG_FUNCTION_GRAPH_TRACER=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_CODE_PATCHING_SELFTEST=y
@@ -325,3 +323,4 @@
 CONFIG_KVM_BOOK3S_64=m
 CONFIG_KVM_BOOK3S_64_HV=m
 CONFIG_VHOST_NET=m
+CONFIG_PRINTK_TIME=y
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 6bd5e72..1253482 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -3,20 +3,17 @@
 CONFIG_VSX=y
 CONFIG_NR_CPUS=2048
 CONFIG_CPU_LITTLE_ENDIAN=y
+CONFIG_KERNEL_XZ=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_DELAY_ACCT=y
-CONFIG_TASK_XACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
+# CONFIG_CPU_ISOLATION is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=20
-CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_RD_GZIP is not set
 # CONFIG_RD_BZIP2 is not set
@@ -24,8 +21,14 @@
 # CONFIG_RD_LZO is not set
 # CONFIG_RD_LZ4 is not set
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_EXPERT=y
+# CONFIG_SGETMASK_SYSCALL is not set
+# CONFIG_SYSFS_SYSCALL is not set
+# CONFIG_SHMEM is not set
+# CONFIG_AIO is not set
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB_FREELIST_HARDENED=y
 CONFIG_JUMP_LABEL=y
 CONFIG_STRICT_KERNEL_RWX=y
 CONFIG_MODULES=y
@@ -34,8 +37,11 @@
 CONFIG_MODULE_SIG_FORCE=y
 CONFIG_MODULE_SIG_SHA512=y
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_MQ_IOSCHED_DEADLINE is not set
+# CONFIG_MQ_IOSCHED_KYBER is not set
+# CONFIG_PPC_VAS is not set
 # CONFIG_PPC_PSERIES is not set
+# CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_IDLE=y
 CONFIG_HZ_100=y
@@ -44,12 +50,12 @@
 CONFIG_NUMA=y
 # CONFIG_COMPACTION is not set
 # CONFIG_MIGRATION is not set
-# CONFIG_BOUNCE is not set
 CONFIG_PPC_64K_PAGES=y
 CONFIG_SCHED_SMT=y
 CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=tty0 console=hvc0 powersave=off"
+CONFIG_CMDLINE="console=tty0 console=hvc0 ipr.fast_reboot=1 quiet"
 # CONFIG_SECCOMP is not set
+# CONFIG_PPC_MEM_KEYS is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -60,10 +66,8 @@
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_IPV6 is not set
 CONFIG_DNS_RESOLVER=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=m
@@ -73,8 +77,10 @@
 CONFIG_BLK_DEV_RAM_SIZE=65536
 CONFIG_VIRTIO_BLK=m
 CONFIG_BLK_DEV_NVME=m
-CONFIG_EEPROM_AT24=y
+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
 CONFIG_BLK_DEV_SR_VENDOR=y
@@ -85,7 +91,6 @@
 CONFIG_SCSI_CXGB3_ISCSI=m
 CONFIG_SCSI_CXGB4_ISCSI=m
 CONFIG_SCSI_BNX2_ISCSI=m
-CONFIG_BE2ISCSI=m
 CONFIG_SCSI_AACRAID=m
 CONFIG_MEGARAID_NEWGEN=y
 CONFIG_MEGARAID_MM=m
@@ -102,7 +107,7 @@
 CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_ALUA=m
 CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI=m
 # CONFIG_ATA_SFF is not set
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=m
@@ -119,25 +124,80 @@
 CONFIG_DM_MIRROR=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ADAPTEC is not set
+# CONFIG_NET_VENDOR_AGERE is not set
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 CONFIG_ACENIC=m
 CONFIG_ACENIC_OMIT_TIGON_I=y
-CONFIG_TIGON3=y
+# CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ATHEROS is not set
+# CONFIG_NET_VENDOR_AURORA is not set
+CONFIG_TIGON3=m
 CONFIG_BNX2X=m
-CONFIG_CHELSIO_T1=y
+# CONFIG_NET_VENDOR_BROCADE is not set
+# CONFIG_NET_VENDOR_CADENCE is not set
+# CONFIG_NET_CADENCE is not set
+# CONFIG_NET_VENDOR_CAVIUM is not set
+CONFIG_CHELSIO_T1=m
+# CONFIG_NET_VENDOR_CISCO is not set
+# CONFIG_NET_VENDOR_CORTINA is not set
+# CONFIG_NET_VENDOR_DEC is not set
+# CONFIG_NET_VENDOR_DLINK is not set
 CONFIG_BE2NET=m
-CONFIG_S2IO=m
-CONFIG_E100=m
+# CONFIG_NET_VENDOR_EZCHIP is not set
+# CONFIG_NET_VENDOR_HP is not set
+# CONFIG_NET_VENDOR_HUAWEI is not set
 CONFIG_E1000=m
 CONFIG_E1000E=m
+CONFIG_IGB=m
 CONFIG_IXGB=m
 CONFIG_IXGBE=m
+CONFIG_I40E=m
+CONFIG_S2IO=m
+# CONFIG_NET_VENDOR_MARVELL is not set
 CONFIG_MLX4_EN=m
+# CONFIG_MLX4_CORE_GEN2 is not set
 CONFIG_MLX5_CORE=m
 CONFIG_MLX5_CORE_EN=y
+# CONFIG_MLX5_EN_RXNFC is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 CONFIG_MYRI10GE=m
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
+# CONFIG_NET_VENDOR_NVIDIA is not set
+# CONFIG_NET_VENDOR_OKI is not set
+# CONFIG_NET_VENDOR_PACKET_ENGINES is not set
 CONFIG_QLGE=m
 CONFIG_NETXEN_NIC=m
+CONFIG_QED=m
+CONFIG_QEDE=m
+# CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
+# CONFIG_NET_VENDOR_ROCKER is not set
+# CONFIG_NET_VENDOR_SAMSUNG is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
 CONFIG_SFC=m
+# CONFIG_NET_VENDOR_SILAN is not set
+# CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+# CONFIG_NET_VENDOR_SOCIONEXT is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
+# CONFIG_NET_VENDOR_TEHUTI is not set
+# CONFIG_NET_VENDOR_TI is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_NET_VENDOR_XILINX is not set
+CONFIG_PHYLIB=y
 # CONFIG_USB_NET_DRIVERS is not set
 # CONFIG_WLAN is not set
 CONFIG_INPUT_EVDEV=y
@@ -149,39 +209,52 @@
 CONFIG_IPMI_HANDLER=y
 CONFIG_IPMI_DEVICE_INTERFACE=y
 CONFIG_IPMI_POWERNV=y
+CONFIG_IPMI_WATCHDOG=y
 CONFIG_HW_RANDOM=y
+CONFIG_TCG_TPM=y
 CONFIG_TCG_TIS_I2C_NUVOTON=y
+# CONFIG_DEVPORT is not set
+CONFIG_I2C=y
 # CONFIG_I2C_COMPAT is not set
 CONFIG_I2C_CHARDEV=y
 # CONFIG_I2C_HELPER_AUTO is not set
-CONFIG_DRM=y
-CONFIG_DRM_RADEON=y
+CONFIG_I2C_ALGOBIT=y
+CONFIG_I2C_OPAL=m
+CONFIG_PPS=y
+CONFIG_SENSORS_IBMPOWERNV=m
+CONFIG_DRM=m
 CONFIG_DRM_AST=m
+CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_OF=y
-CONFIG_FB_MATROX=y
-CONFIG_FB_MATROX_MILLENIUM=y
-CONFIG_FB_MATROX_MYSTIQUE=y
-CONFIG_FB_MATROX_G=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_GENERIC is not set
 # CONFIG_VGA_CONSOLE is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_HID_GENERIC=m
+CONFIG_HID_A4TECH=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_ITE=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
 CONFIG_USB_HIDDEV=y
-CONFIG_USB=y
-CONFIG_USB_MON=y
-CONFIG_USB_XHCI_HCD=y
-CONFIG_USB_EHCI_HCD=y
+CONFIG_USB=m
+CONFIG_USB_XHCI_HCD=m
+CONFIG_USB_EHCI_HCD=m
 # CONFIG_USB_EHCI_HCD_PPC_OF is not set
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_STORAGE=y
+CONFIG_USB_OHCI_HCD=m
+CONFIG_USB_STORAGE=m
 CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_OPAL=m
 CONFIG_RTC_DRV_GENERIC=m
 CONFIG_VIRT_DRIVERS=y
-CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_PCI=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT4_FS=m
 CONFIG_EXT4_FS_POSIX_ACL=y
@@ -195,10 +268,10 @@
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_NLS=y
 CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
@@ -207,26 +280,24 @@
 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
+# CONFIG_XZ_DEC_ARMTHUMB is not set
+# CONFIG_XZ_DEC_SPARC is not set
 CONFIG_PRINTK_TIME=y
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_SOFTLOCKUP_DETECTOR=y
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
 CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y
-CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
 CONFIG_WQ_WATCHDOG=y
-CONFIG_SCHEDSTATS=y
+# CONFIG_SCHED_DEBUG is not set
 # CONFIG_FTRACE is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
-CONFIG_SECURITY=y
-CONFIG_IMA=y
-CONFIG_EVM=y
+CONFIG_ENCRYPTED_KEYS=y
 # CONFIG_CRYPTO_ECHAINIV is not set
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_CMAC=y
-CONFIG_CRYPTO_MD4=y
-CONFIG_CRYPTO_ARC4=y
-CONFIG_CRYPTO_DES=y
 # CONFIG_CRYPTO_HW is not set
diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig
index 74bca2e..6c39c52 100644
--- a/arch/powerpc/configs/storcenter_defconfig
+++ b/arch/powerpc/configs/storcenter_defconfig
@@ -26,7 +26,6 @@
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig
index cd72193..7493f36 100644
--- a/arch/powerpc/configs/tqm8xx_defconfig
+++ b/arch/powerpc/configs/tqm8xx_defconfig
@@ -32,7 +32,6 @@
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index f5c366b..5a04448 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -41,7 +41,6 @@
 CONFIG_BT_HIDP=y
 CONFIG_CFG80211=y
 CONFIG_MAC80211=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_STANDALONE is not set
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
@@ -123,7 +122,6 @@
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_SPINLOCK=y
 CONFIG_DEBUG_MUTEXES=y
-CONFIG_LATENCYTOP=y
 CONFIG_SCHED_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_DMA_API_DEBUG=y
diff --git a/arch/powerpc/crypto/aes-spe-core.S b/arch/powerpc/crypto/aes-spe-core.S
index bc6ff43..8e00ecc 100644
--- a/arch/powerpc/crypto/aes-spe-core.S
+++ b/arch/powerpc/crypto/aes-spe-core.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Fast AES implementation for SPE instruction set (PPC)
  *
@@ -7,12 +8,6 @@
  * http://cache.freescale.com/files/32bit/doc/app_note/AN2665.pdf
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/crypto/aes-spe-glue.c b/arch/powerpc/crypto/aes-spe-glue.c
index 748fc00..3a4ca7d 100644
--- a/arch/powerpc/crypto/aes-spe-glue.c
+++ b/arch/powerpc/crypto/aes-spe-glue.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Glue code for AES implementation for SPE instructions (PPC)
  *
@@ -5,12 +6,6 @@
  * about the SPE registers so it can run from interrupt context.
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <crypto/aes.h>
diff --git a/arch/powerpc/crypto/aes-spe-keys.S b/arch/powerpc/crypto/aes-spe-keys.S
index be8090f..2e1bc0d 100644
--- a/arch/powerpc/crypto/aes-spe-keys.S
+++ b/arch/powerpc/crypto/aes-spe-keys.S
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Key handling functions for PPC AES implementation
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/crypto/aes-spe-modes.S b/arch/powerpc/crypto/aes-spe-modes.S
index ad48032..3f92a6a 100644
--- a/arch/powerpc/crypto/aes-spe-modes.S
+++ b/arch/powerpc/crypto/aes-spe-modes.S
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * AES modes (ECB/CBC/CTR/XTS) for PPC AES implementation
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/crypto/aes-spe-regs.h b/arch/powerpc/crypto/aes-spe-regs.h
index 2cc3a2c..2eb4c9b 100644
--- a/arch/powerpc/crypto/aes-spe-regs.h
+++ b/arch/powerpc/crypto/aes-spe-regs.h
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Common registers for PPC AES implementation
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #define rKS r0	/* copy of en-/decryption key pointer			*/
diff --git a/arch/powerpc/crypto/aes-tab-4k.S b/arch/powerpc/crypto/aes-tab-4k.S
index 701e602..ceb604b 100644
--- a/arch/powerpc/crypto/aes-tab-4k.S
+++ b/arch/powerpc/crypto/aes-tab-4k.S
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * 4K AES tables for PPC AES implementation
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 /*
diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c
index 0153a9c..4798521 100644
--- a/arch/powerpc/crypto/crc-vpmsum_test.c
+++ b/arch/powerpc/crypto/crc-vpmsum_test.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * CRC vpmsum tester
  * Copyright 2017 Daniel Axtens, IBM Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/crc-t10dif.h>
@@ -78,16 +75,12 @@
 
 		pr_info("crc-vpmsum_test begins, %lu iterations\n", iterations);
 		for (i=0; i<iterations; i++) {
-			size_t len, offset;
+			size_t offset = prandom_u32_max(16);
+			size_t len = prandom_u32_max(MAX_CRC_LENGTH);
 
-			get_random_bytes(data, MAX_CRC_LENGTH);
-			get_random_bytes(&len, sizeof(len));
-			get_random_bytes(&offset, sizeof(offset));
-
-			len %= MAX_CRC_LENGTH;
-			offset &= 15;
 			if (len <= offset)
 				continue;
+			prandom_bytes(data, len);
 			len -= offset;
 
 			crypto_shash_update(crct10dif_shash, data+offset, len);
diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/crypto/crc32-vpmsum_core.S
index aadb59c..c3524eb 100644
--- a/arch/powerpc/crypto/crc32-vpmsum_core.S
+++ b/arch/powerpc/crypto/crc32-vpmsum_core.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Core of the accelerated CRC algorithm.
  * In your file, define the constants and CRC_FUNCTION_NAME
@@ -21,11 +22,6 @@
  * http://en.wikipedia.org/wiki/Barrett_reduction
  *
  * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
 */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
index d2bea48..bf44200 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_asm.S
+++ b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Calculate a crc32c with vpmsum acceleration
  *
  * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 	.section	.rodata
 .balign 16
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index fd1d6c8..2c23289 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -1,10 +1,13 @@
+// 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
@@ -22,7 +25,7 @@
 	unsigned int prealign;
 	unsigned int tail;
 
-	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt())
+	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable())
 		return __crc32c_le(crc, p, len);
 
 	if ((unsigned long)p & VMX_ALIGN_MASK) {
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S b/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
index 5e3d81a..f0b93a0 100644
--- a/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
+++ b/arch/powerpc/crypto/crct10dif-vpmsum_asm.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Calculate a CRC T10DIF  with vpmsum acceleration
  *
@@ -6,12 +7,6 @@
  *
  * crc32-vpmsum is
  * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
- * and is available under the GPL v2 or later.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 	.section	.rodata
 .balign 16
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
index 02ea277..1dc8b69 100644
--- a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
@@ -1,22 +1,20 @@
+// 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]
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
  */
 
 #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
@@ -32,7 +30,7 @@
 	unsigned int tail;
 	u32 crc = crci;
 
-	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt())
+	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable())
 		return crc_t10dif_generic(crc, p, len);
 
 	if ((unsigned long)p & VMX_ALIGN_MASK) {
diff --git a/arch/powerpc/crypto/md5-asm.S b/arch/powerpc/crypto/md5-asm.S
index 1834065..948d100 100644
--- a/arch/powerpc/crypto/md5-asm.S
+++ b/arch/powerpc/crypto/md5-asm.S
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Fast MD5 implementation for PPC
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/powerpc/crypto/md5-glue.c b/arch/powerpc/crypto/md5-glue.c
index 7e44cec..7d1bf2f 100644
--- a/arch/powerpc/crypto/md5-glue.c
+++ b/arch/powerpc/crypto/md5-glue.c
@@ -1,15 +1,10 @@
+// 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>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <crypto/internal/hash.h>
diff --git a/arch/powerpc/crypto/sha1-spe-asm.S b/arch/powerpc/crypto/sha1-spe-asm.S
index fcb6cf0..0f44752 100644
--- a/arch/powerpc/crypto/sha1-spe-asm.S
+++ b/arch/powerpc/crypto/sha1-spe-asm.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Fast SHA-1 implementation for SPE instruction set (PPC)
  *
@@ -7,12 +8,6 @@
  * http://cache.freescale.com/files/32bit/doc/app_note/AN2665.pdf
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/crypto/sha1-spe-glue.c b/arch/powerpc/crypto/sha1-spe-glue.c
index 9e1814d..6379990 100644
--- a/arch/powerpc/crypto/sha1-spe-glue.c
+++ b/arch/powerpc/crypto/sha1-spe-glue.c
@@ -1,15 +1,10 @@
+// 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>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <crypto/internal/hash.h>
diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
index 3911d5c..7b43fc3 100644
--- a/arch/powerpc/crypto/sha1.c
+++ b/arch/powerpc/crypto/sha1.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Cryptographic API.
  *
@@ -10,12 +11,6 @@
  * Copyright (c) Alan Smithee.
  * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
  * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
diff --git a/arch/powerpc/crypto/sha256-spe-asm.S b/arch/powerpc/crypto/sha256-spe-asm.S
index 2d10e4c..cd99d71 100644
--- a/arch/powerpc/crypto/sha256-spe-asm.S
+++ b/arch/powerpc/crypto/sha256-spe-asm.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Fast SHA-256 implementation for SPE instruction set (PPC)
  *
@@ -7,12 +8,6 @@
  * http://cache.freescale.com/files/32bit/doc/app_note/AN2665.pdf
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/crypto/sha256-spe-glue.c b/arch/powerpc/crypto/sha256-spe-glue.c
index 6227888..84939e5 100644
--- a/arch/powerpc/crypto/sha256-spe-glue.c
+++ b/arch/powerpc/crypto/sha256-spe-glue.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Glue code for SHA-256 implementation for SPE instructions (PPC)
  *
@@ -5,12 +6,6 @@
  * about the SPE registers so it can run from interrupt context.
  *
  * Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
  */
 
 #include <crypto/internal/hash.h>
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 3196d22..64870c7 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,10 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+generated-y += syscall_table_32.h
+generated-y += syscall_table_64.h
+generated-y += syscall_table_c32.h
+generated-y += syscall_table_spu.h
 generic-y += div64.h
 generic-y += export.h
 generic-y += irq_regs.h
-generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += vtime.h
 generic-y += msi.h
diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h
index 3abcf98..6d79c31 100644
--- a/arch/powerpc/include/asm/accounting.h
+++ b/arch/powerpc/include/asm/accounting.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Common time accounting prototypes and such for all ppc machines.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef __POWERPC_ACCOUNTING_H
@@ -15,8 +11,10 @@
 	/* Accumulated cputime values to flush on ticks*/
 	unsigned long utime;
 	unsigned long stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 	unsigned long utime_scaled;
 	unsigned long stime_scaled;
+#endif
 	unsigned long gtime;
 	unsigned long hardirq_time;
 	unsigned long softirq_time;
@@ -25,8 +23,10 @@
 	/* Internal counters */
 	unsigned long starttime;	/* TB value snapshot */
 	unsigned long starttime_user;	/* TB value on exit to usermode */
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 	unsigned long startspurr;	/* SPURR value snapshot */
 	unsigned long utime_sspurr;	/* ->user_time when ->startspurr set */
+#endif
 };
 
 #endif
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 1f4691c..d84d141 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_ASM_PROTOTYPES_H
 #define _ASM_POWERPC_ASM_PROTOTYPES_H
 /*
@@ -5,11 +6,6 @@
  * from asm, and any associated variables.
  *
  * Copyright 2016, Daniel Axtens, IBM 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; either version 2
- * of the License, or (at your option) any later version.
  */
 
 #include <linux/threads.h>
@@ -19,12 +15,13 @@
 #include <asm/epapr_hcalls.h>
 #include <asm/dcr.h>
 #include <asm/mmu_context.h>
+#include <asm/ultravisor-api.h>
 
 #include <uapi/asm/ucontext.h>
 
 /* SMP */
-extern struct thread_info *current_set[NR_CPUS];
-extern struct thread_info *secondary_ti;
+extern struct task_struct *current_set[NR_CPUS];
+extern struct task_struct *secondary_current;
 void start_secondary(void *unused);
 
 /* kexec */
@@ -37,13 +34,21 @@
 extern struct static_key hcall_tracepoint_key;
 void __trace_hcall_entry(unsigned long opcode, unsigned long *args);
 void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf);
-/* OPAL tracing */
-#ifdef HAVE_JUMP_LABEL
-extern struct static_key opal_tracepoint_key;
+
+/* Ultravisor */
+#if defined(CONFIG_PPC_POWERNV) || defined(CONFIG_PPC_SVM)
+long ucall_norets(unsigned long opcode, ...);
+#else
+static inline long ucall_norets(unsigned long opcode, ...)
+{
+	return U_NOT_AVAILABLE;
+}
 #endif
 
-void __trace_opal_entry(unsigned long opcode, unsigned long *args);
-void __trace_opal_exit(long opcode, unsigned long retval);
+/* OPAL */
+int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3,
+		    int64_t a4, int64_t a5, int64_t a6, int64_t a7,
+		    int64_t opcode, uint64_t msr);
 
 /* VMX copying */
 int enter_vmx_usercopy(void);
@@ -61,9 +66,7 @@
 void single_step_exception(struct pt_regs *regs);
 void program_check_exception(struct pt_regs *regs);
 void alignment_exception(struct pt_regs *regs);
-void slb_miss_bad_addr(struct pt_regs *regs);
 void StackOverflow(struct pt_regs *regs);
-void nonrecoverable_exception(struct pt_regs *regs);
 void kernel_fp_unavailable_exception(struct pt_regs *regs);
 void altivec_unavailable_exception(struct pt_regs *regs);
 void vsx_unavailable_exception(struct pt_regs *regs);
@@ -78,6 +81,8 @@
 void system_reset_exception(struct pt_regs *regs);
 void machine_check_exception(struct pt_regs *regs);
 void emulation_assist_interrupt(struct pt_regs *regs);
+long do_slb_fault(struct pt_regs *regs, unsigned long ea);
+void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err);
 
 /* signals, syscalls and interrupts */
 long sys_swapcontext(struct ucontext __user *old_ctx,
@@ -129,7 +134,8 @@
 
 /* tracing */
 void _mcount(void);
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
+						unsigned long sp);
 
 void pnv_power9_force_smt4_catch(void);
 void pnv_power9_force_smt4_release(void);
@@ -146,8 +152,32 @@
 /* Patch sites */
 extern s32 patch__call_flush_count_cache;
 extern s32 patch__flush_count_cache_return;
+extern s32 patch__flush_link_stack_return;
+extern s32 patch__call_kvm_flush_link_stack;
 extern s32 patch__memset_nocache, patch__memcpy_nocache;
 
 extern long flush_count_cache;
+extern long kvm_flush_link_stack;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv);
+void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv);
+#else
+static inline void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr,
+				     bool preserve_nv) { }
+static inline void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr,
+					bool preserve_nv) { }
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+void kvmhv_save_host_pmu(void);
+void kvmhv_load_host_pmu(void);
+void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use);
+void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu);
+
+int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu);
+
+long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr);
+long kvmppc_h_set_xdabr(struct kvm_vcpu *vcpu, unsigned long dabr,
+			unsigned long dabrx);
 
 #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */
diff --git a/arch/powerpc/include/asm/async_tx.h b/arch/powerpc/include/asm/async_tx.h
index 8b2dc55..a147584 100644
--- a/arch/powerpc/include/asm/async_tx.h
+++ b/arch/powerpc/include/asm/async_tx.h
@@ -1,24 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2008-2009 DENX Software Engineering.
  *
  * Author: Yuri Tikhonov <yur@emcraft.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called COPYING.
  */
 #ifndef _ASM_POWERPC_ASYNC_TX_H_
 #define _ASM_POWERPC_ASYNC_TX_H_
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 52eafaf..31c231e 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -297,24 +297,24 @@
 
 #define ATOMIC64_INIT(i)	{ (i) }
 
-static __inline__ long atomic64_read(const atomic64_t *v)
+static __inline__ s64 atomic64_read(const atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m"(v->counter));
 
 	return t;
 }
 
-static __inline__ void atomic64_set(atomic64_t *v, long i)
+static __inline__ void atomic64_set(atomic64_t *v, s64 i)
 {
 	__asm__ __volatile__("std%U0%X0 %1,%0" : "=m"(v->counter) : "r"(i));
 }
 
 #define ATOMIC64_OP(op, asm_op)						\
-static __inline__ void atomic64_##op(long a, atomic64_t *v)		\
+static __inline__ void atomic64_##op(s64 a, atomic64_t *v)		\
 {									\
-	long t;								\
+	s64 t;								\
 									\
 	__asm__ __volatile__(						\
 "1:	ldarx	%0,0,%3		# atomic64_" #op "\n"			\
@@ -327,10 +327,10 @@
 }
 
 #define ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
-static inline long							\
-atomic64_##op##_return_relaxed(long a, atomic64_t *v)			\
+static inline s64							\
+atomic64_##op##_return_relaxed(s64 a, atomic64_t *v)			\
 {									\
-	long t;								\
+	s64 t;								\
 									\
 	__asm__ __volatile__(						\
 "1:	ldarx	%0,0,%3		# atomic64_" #op "_return_relaxed\n"	\
@@ -345,10 +345,10 @@
 }
 
 #define ATOMIC64_FETCH_OP_RELAXED(op, asm_op)				\
-static inline long							\
-atomic64_fetch_##op##_relaxed(long a, atomic64_t *v)			\
+static inline s64							\
+atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v)			\
 {									\
-	long res, t;							\
+	s64 res, t;							\
 									\
 	__asm__ __volatile__(						\
 "1:	ldarx	%0,0,%4		# atomic64_fetch_" #op "_relaxed\n"	\
@@ -396,7 +396,7 @@
 
 static __inline__ void atomic64_inc(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_inc\n\
@@ -409,9 +409,9 @@
 }
 #define atomic64_inc atomic64_inc
 
-static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
+static __inline__ s64 atomic64_inc_return_relaxed(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_inc_return_relaxed\n"
@@ -427,7 +427,7 @@
 
 static __inline__ void atomic64_dec(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_dec\n\
@@ -440,9 +440,9 @@
 }
 #define atomic64_dec atomic64_dec
 
-static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
+static __inline__ s64 atomic64_dec_return_relaxed(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_dec_return_relaxed\n"
@@ -463,9 +463,9 @@
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1.
  */
-static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
+static __inline__ s64 atomic64_dec_if_positive(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 	PPC_ATOMIC_ENTRY_BARRIER
@@ -502,9 +502,9 @@
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
+static __inline__ s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
@@ -534,7 +534,7 @@
  */
 static __inline__ int atomic64_inc_not_zero(atomic64_t *v)
 {
-	long t1, t2;
+	s64 t1, t2;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index ff71566..603aed2 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * PowerPC atomic bit operations.
  *
@@ -26,11 +27,6 @@
  * The main difference is that bit 3-5 (64b) or 3-4 (32b) in the bit
  * number field needs to be reversed compared to the big-endian bit
  * fields. This can be achieved by XOR with 0x38 (64b) or 0x18 (32b).
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_BITOPS_H
diff --git a/arch/powerpc/include/asm/book3s/32/hash.h b/arch/powerpc/include/asm/book3s/32/hash.h
index f2892c7..2a0a467 100644
--- a/arch/powerpc/include/asm/book3s/32/hash.h
+++ b/arch/powerpc/include/asm/book3s/32/hash.h
@@ -26,6 +26,7 @@
 #define _PAGE_WRITETHRU	0x040	/* W: cache write-through */
 #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_SPECIAL	0x800	/* software: Special page */
 
diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
new file mode 100644
index 0000000..f9dc597
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_32_KUP_H
+#define _ASM_POWERPC_BOOK3S_32_KUP_H
+
+#include <asm/book3s/32/mmu-hash.h>
+
+#ifdef __ASSEMBLY__
+
+.macro kuep_update_sr	gpr1, gpr2		/* NEVER use r0 as gpr2 due to addis */
+101:	mtsrin	\gpr1, \gpr2
+	addi	\gpr1, \gpr1, 0x111		/* next VSID */
+	rlwinm	\gpr1, \gpr1, 0, 0xf0ffffff	/* clear VSID overflow */
+	addis	\gpr2, \gpr2, 0x1000		/* address of next segment */
+	bdnz	101b
+	isync
+.endm
+
+.macro kuep_lock	gpr1, gpr2
+#ifdef CONFIG_PPC_KUEP
+	li	\gpr1, NUM_USER_SEGMENTS
+	li	\gpr2, 0
+	mtctr	\gpr1
+	mfsrin	\gpr1, \gpr2
+	oris	\gpr1, \gpr1, SR_NX@h		/* set Nx */
+	kuep_update_sr \gpr1, \gpr2
+#endif
+.endm
+
+.macro kuep_unlock	gpr1, gpr2
+#ifdef CONFIG_PPC_KUEP
+	li	\gpr1, NUM_USER_SEGMENTS
+	li	\gpr2, 0
+	mtctr	\gpr1
+	mfsrin	\gpr1, \gpr2
+	rlwinm	\gpr1, \gpr1, 0, ~SR_NX		/* Clear Nx */
+	kuep_update_sr \gpr1, \gpr2
+#endif
+.endm
+
+#ifdef CONFIG_PPC_KUAP
+
+.macro kuap_update_sr	gpr1, gpr2, gpr3	/* NEVER use r0 as gpr2 due to addis */
+101:	mtsrin	\gpr1, \gpr2
+	addi	\gpr1, \gpr1, 0x111		/* next VSID */
+	rlwinm	\gpr1, \gpr1, 0, 0xf0ffffff	/* clear VSID overflow */
+	addis	\gpr2, \gpr2, 0x1000		/* address of next segment */
+	cmplw	\gpr2, \gpr3
+	blt-	101b
+	isync
+.endm
+
+.macro kuap_save_and_lock	sp, thread, gpr1, gpr2, gpr3
+	lwz	\gpr2, KUAP(\thread)
+	rlwinm.	\gpr3, \gpr2, 28, 0xf0000000
+	stw	\gpr2, STACK_REGS_KUAP(\sp)
+	beq+	102f
+	li	\gpr1, 0
+	stw	\gpr1, KUAP(\thread)
+	mfsrin	\gpr1, \gpr2
+	oris	\gpr1, \gpr1, SR_KS@h	/* set Ks */
+	kuap_update_sr	\gpr1, \gpr2, \gpr3
+102:
+.endm
+
+.macro kuap_restore	sp, current, gpr1, gpr2, gpr3
+	lwz	\gpr2, STACK_REGS_KUAP(\sp)
+	rlwinm.	\gpr3, \gpr2, 28, 0xf0000000
+	stw	\gpr2, THREAD + KUAP(\current)
+	beq+	102f
+	mfsrin	\gpr1, \gpr2
+	rlwinm	\gpr1, \gpr1, 0, ~SR_KS	/* Clear Ks */
+	kuap_update_sr	\gpr1, \gpr2, \gpr3
+102:
+.endm
+
+.macro kuap_check	current, gpr
+#ifdef CONFIG_PPC_KUAP_DEBUG
+	lwz	\gpr2, KUAP(thread)
+999:	twnei	\gpr, 0
+	EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
+#endif
+.endm
+
+#endif /* CONFIG_PPC_KUAP */
+
+#else /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_PPC_KUAP
+
+#include <linux/sched.h>
+
+static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
+{
+	addr &= 0xf0000000;	/* align addr to start of segment */
+	barrier();	/* make sure thread.kuap is updated before playing with SRs */
+	while (addr < end) {
+		mtsrin(sr, addr);
+		sr += 0x111;		/* next VSID */
+		sr &= 0xf0ffffff;	/* clear VSID overflow */
+		addr += 0x10000000;	/* address of next segment */
+	}
+	isync();	/* Context sync required after mtsrin() */
+}
+
+static inline void allow_user_access(void __user *to, const void __user *from, u32 size)
+{
+	u32 addr, end;
+
+	if (__builtin_constant_p(to) && to == NULL)
+		return;
+
+	addr = (__force u32)to;
+
+	if (!addr || addr >= TASK_SIZE || !size)
+		return;
+
+	end = min(addr + size, TASK_SIZE);
+	current->thread.kuap = (addr & 0xf0000000) | ((((end - 1) >> 28) + 1) & 0xf);
+	kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end);	/* Clear Ks */
+}
+
+static inline void prevent_user_access(void __user *to, const void __user *from, u32 size)
+{
+	u32 addr = (__force u32)to;
+	u32 end = min(addr + size, TASK_SIZE);
+
+	if (!addr || addr >= TASK_SIZE || !size)
+		return;
+
+	current->thread.kuap = 0;
+	kuap_update_sr(mfsrin(addr) | SR_KS, addr, end);	/* set Ks */
+}
+
+static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+{
+	if (!is_write)
+		return false;
+
+	return WARN(!regs->kuap, "Bug: write fault blocked by segment registers !");
+}
+
+#endif /* CONFIG_PPC_KUAP */
+
+#endif /* __ASSEMBLY__ */
+
+#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 e38c913..2e277ca 100644
--- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_POWERPC_BOOK3S_32_MMU_HASH_H_
 #define _ASM_POWERPC_BOOK3S_32_MMU_HASH_H_
+
 /*
  * 32-bit hash table MMU support
  */
@@ -34,8 +35,12 @@
 #define BAT_PHYS_ADDR(x) ((u32)((x & 0x00000000fffe0000ULL) | \
 				((x & 0x0000000e00000000ULL) >> 24) | \
 				((x & 0x0000000100000000ULL) >> 30)))
+#define PHYS_BAT_ADDR(x) (((u64)(x) & 0x00000000fffe0000ULL) | \
+			  (((u64)(x) << 24) & 0x0000000e00000000ULL) | \
+			  (((u64)(x) << 30) & 0x0000000100000000ULL))
 #else
 #define BAT_PHYS_ADDR(x) (x)
+#define PHYS_BAT_ADDR(x) ((x) & 0xfffe0000)
 #endif
 
 struct ppc_bat {
@@ -54,6 +59,11 @@
 #define PP_RWRW 2	/* Supervisor read/write, User read/write */
 #define PP_RXRX 3	/* Supervisor read,       User read */
 
+/* Values for Segment Registers */
+#define SR_NX	0x10000000	/* No Execute */
+#define SR_KP	0x20000000	/* User key */
+#define SR_KS	0x40000000	/* Supervisor key */
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -83,6 +93,14 @@
 	unsigned long vdso_base;
 } mm_context_t;
 
+void update_bats(void);
+
+/* patch sites */
+extern s32 patch__hash_page_A0, patch__hash_page_A1, patch__hash_page_A2;
+extern s32 patch__hash_page_B, patch__hash_page_C;
+extern s32 patch__flush_hash_A0, patch__flush_hash_A1, patch__flush_hash_A2;
+extern s32 patch__flush_hash_B;
+
 #endif /* !__ASSEMBLY__ */
 
 /* We happily ignore the smaller BATs on 601, we don't actually use
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index 82e44b1..9983177 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -5,31 +5,6 @@
 #include <linux/threads.h>
 #include <linux/slab.h>
 
-/*
- * 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
- * handle allocation.  For PTE pages (which are linked to a struct
- * page for now, and drawn from the main get_free_pages() pool), the
- * allocation size will be (2^index_size * sizeof(pointer)) and
- * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
- *
- * The maximum index size needs to be big enough to allow any
- * pagetable sizes we need, but small enough to fit in the low bits of
- * any page table pointer.  In other words all pagetables, even tiny
- * ones, must be aligned to allow at least enough low 0 bits to
- * contain this value.  This value is also used as a mask, so it must
- * be one less than a power of two.
- */
-#define MAX_PGTABLE_INDEX_SIZE	0xf
-
-extern void __bad_pte(pmd_t *pmd);
-
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) ({				\
-			BUG_ON(!(shift));		\
-			pgtable_cache[(shift) - 1];	\
-		})
-
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
@@ -50,8 +25,6 @@
 #define __pmd_free_tlb(tlb,x,a)		do { } while (0)
 /* #define pgd_populate(mm, pmd, pte)      BUG() */
 
-#ifndef CONFIG_BOOKE
-
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
 				       pte_t *pte)
 {
@@ -61,53 +34,19 @@
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pte_page)
 {
-	*pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_PRESENT);
-}
-
-#define pmd_pgtable(pmd) pmd_page(pmd)
-#else
-
-static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
-				       pte_t *pte)
-{
-	*pmdp = __pmd((unsigned long)pte | _PMD_PRESENT);
-}
-
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
-				pgtable_t pte_page)
-{
-	*pmdp = __pmd((unsigned long)lowmem_page_address(pte_page) | _PMD_PRESENT);
-}
-
-#define pmd_pgtable(pmd) pmd_page(pmd)
-#endif
-
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
-extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-	pgtable_page_dtor(ptepage);
-	__free_page(ptepage);
+	*pmdp = __pmd(__pa(pte_page) | _PMD_PRESENT);
 }
 
 static inline void pgtable_free(void *table, unsigned index_size)
 {
 	if (!index_size) {
-		pgtable_page_dtor(virt_to_page(table));
-		free_page((unsigned long)table);
+		pte_fragment_free((unsigned long *)table, 0);
 	} else {
 		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
 		kmem_cache_free(PGT_CACHE(index_size), table);
 	}
 }
 
-#define check_pgt_cache()	do { } while (0)
 #define get_hugepd_cache_index(x)  (x)
 
 #ifdef CONFIG_SMP
@@ -138,6 +77,6 @@
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	pgtable_free_tlb(tlb, page_address(table), 0);
+	pgtable_free_tlb(tlb, table, 0);
 }
 #endif /* _ASM_POWERPC_BOOK3S_32_PGALLOC_H */
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 751cf93..0796533 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -8,7 +8,97 @@
 #include <asm/book3s/32/hash.h>
 
 /* And here we include common definitions */
-#include <asm/pte-common.h>
+
+#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).
+ * Platform who don't just pre-define the value so we don't override it here.
+ */
+#define PTE_RPN_SHIFT	(PAGE_SHIFT)
+
+/*
+ * The mask covered by the RPN must be a ULL on 32-bit platforms with
+ * 64-bit PTEs.
+ */
+#ifdef CONFIG_PTE_64BIT
+#define PTE_RPN_MASK	(~((1ULL << PTE_RPN_SHIFT) - 1))
+#else
+#define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
+#endif
+
+/*
+ * _PAGE_CHG_MASK masks of bits that are to be preserved across
+ * pgprot changes.
+ */
+#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HASHPTE | _PAGE_DIRTY | \
+			 _PAGE_ACCESSED | _PAGE_SPECIAL)
+
+/*
+ * We define 2 sets of base prot bits, one for basic pages (ie,
+ * cacheable kernel and user pages) and one for non cacheable
+ * 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)
+#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)
+
+/* 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)
+#define PAGE_KERNEL_NCG	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
+				 _PAGE_NO_CACHE | _PAGE_GUARDED)
+#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX)
+#define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)
+
+/*
+ * 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
+
+/* Advertise special mapping type for AGP */
+#define PAGE_AGP		(PAGE_KERNEL_NC)
+#define HAVE_PAGE_AGP
 
 #define PTE_INDEX_SIZE	PTE_SHIFT
 #define PMD_INDEX_SIZE	0
@@ -44,28 +134,35 @@
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
 #define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
+
+#ifndef __ASSEMBLY__
+
+int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
+
+#endif /* !__ASSEMBLY__ */
+
 /*
  * 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
  */
-#ifdef CONFIG_HIGHMEM
-#define KVIRT_TOP	PKMAP_BASE
-#else
-#define KVIRT_TOP	(0xfe000000UL)	/* for now, could be FIXMAP_BASE ? */
-#endif
+#include <asm/fixmap.h>
 
 /*
  * ioremap_bot starts at that address. Early ioremaps move down from there,
  * until mem_init() at which point this becomes the top of the vmalloc
  * and ioremap space
  */
-#ifdef CONFIG_NOT_COHERENT_CACHE
-#define IOREMAP_TOP	((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK)
+#ifdef CONFIG_HIGHMEM
+#define IOREMAP_TOP	PKMAP_BASE
 #else
-#define IOREMAP_TOP	KVIRT_TOP
+#define IOREMAP_TOP	FIXADDR_START
 #endif
 
+/* PPC32 shares vmalloc area with ioremap */
+#define IOREMAP_START	VMALLOC_START
+#define IOREMAP_END	VMALLOC_END
+
 /*
  * Just any arbitrary offset to the start of the vmalloc VM area: the
  * current 16MB value just means that there will be a 64MB "hole" after the
@@ -84,15 +181,24 @@
  * of RAM.  -- Cort
  */
 #define VMALLOC_OFFSET (0x1000000) /* 16M */
+
+/*
+ * With CONFIG_STRICT_KERNEL_RWX, kernel segments are set NX. But when modules
+ * are used, NX cannot be set on VMALLOC space. So vmalloc VM space and linear
+ * memory shall not share segments.
+ */
+#if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_MODULES)
+#define VMALLOC_START ((_ALIGN((long)high_memory, 256L << 20) + VMALLOC_OFFSET) & \
+		       ~(VMALLOC_OFFSET - 1))
+#else
 #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+#endif
 #define VMALLOC_END	ioremap_bot
 
 #ifndef __ASSEMBLY__
 #include <linux/sched.h>
 #include <linux/threads.h>
 
-extern unsigned long ioremap_bot;
-
 /* Bits to mask out from a PGD to get to the PUD page */
 #define PGD_MASKED_BITS		0
 
@@ -219,14 +325,8 @@
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO);
+	pte_update(ptep, _PAGE_RW, 0);
 }
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
 
 static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 					   pte_t *ptep, pte_t entry,
@@ -235,9 +335,8 @@
 {
 	unsigned long set = pte_val(entry) &
 		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
-	unsigned long clr = ~pte_val(entry) & _PAGE_RO;
 
-	pte_update(ptep, clr, set);
+	pte_update(ptep, 0, set);
 
 	flush_tlb_page(vma, address);
 }
@@ -245,24 +344,10 @@
 #define __HAVE_ARCH_PTE_SAME
 #define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0)
 
-/*
- * 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
- * handler).  On everything else the pmd contains the physical address
- * of the pte page.  -- paulus
- */
-#ifndef CONFIG_BOOKE
 #define pmd_page_vaddr(pmd)	\
-	((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+	((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1)))
 #define pmd_page(pmd)		\
 	pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
-#else
-#define pmd_page_vaddr(pmd)	\
-	((unsigned long) (pmd_val(pmd) & PAGE_MASK))
-#define pmd_page(pmd)		\
-	pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT))
-#endif
 
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
@@ -277,7 +362,8 @@
 #define pte_offset_kernel(dir, addr)	\
 	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr))
 #define pte_offset_map(dir, addr)		\
-	((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr))
+	((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \
+		   (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr))
 #define pte_unmap(pte)		kunmap_atomic(pte)
 
 /*
@@ -292,8 +378,6 @@
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
-int map_kernel_page(unsigned long va, phys_addr_t pa, int flags);
-
 /* 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; }
@@ -301,13 +385,28 @@
 static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
 static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
 static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
-static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
+static inline bool pte_exec(pte_t pte)		{ return pte_val(pte) & _PAGE_EXEC; }
 
 static inline int pte_present(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_PRESENT;
 }
 
+static inline bool pte_hw_valid(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+static inline bool pte_hashpte(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_HASHPTE);
+}
+
+static inline bool pte_ci(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_NO_CACHE);
+}
+
 /*
  * We only find page table entry in the last level
  * Hence no need for other accessors
@@ -315,17 +414,14 @@
 #define pte_access_permitted pte_access_permitted
 static inline bool pte_access_permitted(pte_t pte, bool write)
 {
-	unsigned long pteval = pte_val(pte);
 	/*
 	 * A read-only access is controlled by _PAGE_USER bit.
 	 * We have _PAGE_READ set for WRITE and EXECUTE
 	 */
-	unsigned long need_pte_bits = _PAGE_PRESENT | _PAGE_USER;
+	if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte))
+		return false;
 
-	if (write)
-		need_pte_bits |= _PAGE_WRITE;
-
-	if ((pteval & need_pte_bits) != need_pte_bits)
+	if (write && !pte_write(pte))
 		return false;
 
 	return true;
@@ -354,6 +450,11 @@
 	return __pte(pte_val(pte) & ~_PAGE_RW);
 }
 
+static inline pte_t pte_exprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_EXEC);
+}
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
 	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
@@ -364,6 +465,16 @@
 	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
 }
 
+static inline pte_t pte_mkexec(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_EXEC);
+}
+
+static inline pte_t pte_mkpte(pte_t pte)
+{
+	return pte;
+}
+
 static inline pte_t pte_mkwrite(pte_t pte)
 {
 	return __pte(pte_val(pte) | _PAGE_RW);
@@ -389,6 +500,16 @@
 	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));
@@ -404,7 +525,7 @@
 static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, pte_t pte, int percpu)
 {
-#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT)
+#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
@@ -417,7 +538,7 @@
 	else
 		pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte));
 
-#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
+#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,
@@ -440,7 +561,7 @@
 	: "=m" (*ptep), "=m" (*((unsigned char *)ptep+4))
 	: "r" (pte) : "memory");
 
-#elif defined(CONFIG_PPC_STD_MMU_32)
+#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())
@@ -448,9 +569,6 @@
 	 */
 	*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE)
 		      | (pte_val(pte) & ~_PAGE_HASHPTE));
-
-#else
-#error "Not supported "
 #endif
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 9a37986..8fd8599 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -1,15 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_POWERPC_BOOK3S_64_HASH_4K_H
 #define _ASM_POWERPC_BOOK3S_64_HASH_4K_H
-/*
- * Entries per page directory level.  The PTE level must use a 64b record
- * for each page table entry.  The PMD and PGD level use a 32b record for
- * each entry by assuming that each entry is page aligned.
- */
-#define H_PTE_INDEX_SIZE  9
-#define H_PMD_INDEX_SIZE  7
-#define H_PUD_INDEX_SIZE  9
-#define H_PGD_INDEX_SIZE  9
+
+#define H_PTE_INDEX_SIZE  9  // size: 8B << 9 = 4KB, maps: 2^9 x   4KB =   2MB
+#define H_PMD_INDEX_SIZE  7  // size: 8B << 7 = 1KB, maps: 2^7 x   2MB = 256MB
+#define H_PUD_INDEX_SIZE  9  // size: 8B << 9 = 4KB, maps: 2^9 x 256MB = 128GB
+#define H_PGD_INDEX_SIZE  9  // size: 8B << 9 = 4KB, maps: 2^9 x 128GB =  64TB
 
 /*
  * Each context is 512TB. But on 4k we restrict our max TASK size to 64TB
@@ -17,6 +13,21 @@
  */
 #define MAX_EA_BITS_PER_CONTEXT		46
 
+#define REGION_SHIFT		(MAX_EA_BITS_PER_CONTEXT - 2)
+
+/*
+ * Our page table limit us to 64TB. Hence for the kernel mapping,
+ * each MAP area is limited to 16 TB.
+ * The four map areas are:  linear mapping, vmap, IO and vmemmap
+ */
+#define H_KERN_MAP_SIZE		(ASM_CONST(1) << REGION_SHIFT)
+
+/*
+ * Define the address range of the kernel non-linear virtual area
+ * 16TB
+ */
+#define H_KERN_VIRT_START	ASM_CONST(0xc000100000000000)
+
 #ifndef __ASSEMBLY__
 #define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)
 #define H_PMD_TABLE_SIZE	(sizeof(pmd_t) << H_PMD_INDEX_SIZE)
@@ -66,7 +77,7 @@
 	 * if it is not a pte and have hugepd shift mask
 	 * set, then it is a hugepd directory pointer
 	 */
-	if (!(hpdval & _PAGE_PTE) &&
+	if (!(hpdval & _PAGE_PTE) && (hpdval & _PAGE_PRESENT) &&
 	    ((hpdval & HUGEPD_SHIFT_MASK) != 0))
 		return true;
 	return false;
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index f82ee8a..d1d9177 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -2,16 +2,29 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H
 #define _ASM_POWERPC_BOOK3S_64_HASH_64K_H
 
-#define H_PTE_INDEX_SIZE  8
-#define H_PMD_INDEX_SIZE  10
-#define H_PUD_INDEX_SIZE  10
-#define H_PGD_INDEX_SIZE  8
+#define H_PTE_INDEX_SIZE   8  // size: 8B <<  8 = 2KB, maps 2^8  x 64KB = 16MB
+#define H_PMD_INDEX_SIZE  10  // size: 8B << 10 = 8KB, maps 2^10 x 16MB = 16GB
+#define H_PUD_INDEX_SIZE  10  // size: 8B << 10 = 8KB, maps 2^10 x 16GB = 16TB
+#define H_PGD_INDEX_SIZE   8  // size: 8B <<  8 = 2KB, maps 2^8  x 16TB =  4PB
+
 
 /*
  * Each context is 512TB size. SLB miss for first context/default context
  * is handled in the hotpath.
  */
 #define MAX_EA_BITS_PER_CONTEXT		49
+#define REGION_SHIFT		MAX_EA_BITS_PER_CONTEXT
+
+/*
+ * We use one context for each MAP area.
+ */
+#define H_KERN_MAP_SIZE		(1UL << MAX_EA_BITS_PER_CONTEXT)
+
+/*
+ * Define the address range of the kernel non-linear virtual area
+ * 2PB
+ */
+#define H_KERN_VIRT_START	ASM_CONST(0xc008000000000000)
 
 /*
  * 64k aligned address free up few of the lower bits of RPN for us
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index d52a51b..2781ebf 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -18,12 +18,21 @@
 #include <asm/book3s/64/hash-4k.h>
 #endif
 
+/* Bits to set in a PMD/PUD/PGD entry valid bit*/
+#define HASH_PMD_VAL_BITS		(0x8000000000000000UL)
+#define HASH_PUD_VAL_BITS		(0x8000000000000000UL)
+#define HASH_PGD_VAL_BITS		(0x8000000000000000UL)
+
 /*
  * Size of EA range mapped by our pagetables.
  */
 #define H_PGTABLE_EADDR_SIZE	(H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + \
 				 H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT)
 #define H_PGTABLE_RANGE		(ASM_CONST(1) << H_PGTABLE_EADDR_SIZE)
+/*
+ * Top 2 bits are ignored in page table walk.
+ */
+#define EA_MASK			(~(0xcUL << 60))
 
 /*
  * We store the slot details in the second half of page table.
@@ -35,47 +44,66 @@
 #else
 #define H_PUD_CACHE_INDEX	(H_PUD_INDEX_SIZE)
 #endif
-/*
- * Define the address range of the kernel non-linear virtual area
- */
-#define H_KERN_VIRT_START ASM_CONST(0xD000000000000000)
-#define H_KERN_VIRT_SIZE  ASM_CONST(0x0000400000000000) /* 64T */
 
 /*
- * The vmalloc space starts at the beginning of that region, and
- * occupies half of it on hash CPUs and a quarter of it on Book3E
- * (we keep a quarter for the virtual memmap)
+ * +------------------------------+
+ * |                              |
+ * |                              |
+ * |                              |
+ * +------------------------------+  Kernel virtual map end (0xc00e000000000000)
+ * |                              |
+ * |                              |
+ * |      512TB/16TB of vmemmap   |
+ * |                              |
+ * |                              |
+ * +------------------------------+  Kernel vmemmap  start
+ * |                              |
+ * |      512TB/16TB of IO map    |
+ * |                              |
+ * +------------------------------+  Kernel IO map start
+ * |                              |
+ * |      512TB/16TB of vmap      |
+ * |                              |
+ * +------------------------------+  Kernel virt start (0xc008000000000000)
+ * |                              |
+ * |                              |
+ * |                              |
+ * +------------------------------+  Kernel linear (0xc.....)
  */
-#define H_VMALLOC_START	H_KERN_VIRT_START
-#define H_VMALLOC_SIZE	ASM_CONST(0x380000000000) /* 56T */
-#define H_VMALLOC_END	(H_VMALLOC_START + H_VMALLOC_SIZE)
 
-#define H_KERN_IO_START	H_VMALLOC_END
+#define H_VMALLOC_START		H_KERN_VIRT_START
+#define H_VMALLOC_SIZE		H_KERN_MAP_SIZE
+#define H_VMALLOC_END		(H_VMALLOC_START + H_VMALLOC_SIZE)
+
+#define H_KERN_IO_START		H_VMALLOC_END
+#define H_KERN_IO_SIZE		H_KERN_MAP_SIZE
+#define H_KERN_IO_END		(H_KERN_IO_START + H_KERN_IO_SIZE)
+
+#define H_VMEMMAP_START		H_KERN_IO_END
+#define H_VMEMMAP_SIZE		H_KERN_MAP_SIZE
+#define H_VMEMMAP_END		(H_VMEMMAP_START + H_VMEMMAP_SIZE)
+
+#define NON_LINEAR_REGION_ID(ea)	((((unsigned long)ea - H_KERN_VIRT_START) >> REGION_SHIFT) + 2)
 
 /*
  * Region IDs
  */
-#define REGION_SHIFT		60UL
-#define REGION_MASK		(0xfUL << REGION_SHIFT)
-#define REGION_ID(ea)		(((unsigned long)(ea)) >> REGION_SHIFT)
-
-#define VMALLOC_REGION_ID	(REGION_ID(H_VMALLOC_START))
-#define KERNEL_REGION_ID	(REGION_ID(PAGE_OFFSET))
-#define VMEMMAP_REGION_ID	(0xfUL)	/* Server only */
-#define USER_REGION_ID		(0UL)
+#define USER_REGION_ID		0
+#define LINEAR_MAP_REGION_ID	1
+#define VMALLOC_REGION_ID	NON_LINEAR_REGION_ID(H_VMALLOC_START)
+#define IO_REGION_ID		NON_LINEAR_REGION_ID(H_KERN_IO_START)
+#define VMEMMAP_REGION_ID	NON_LINEAR_REGION_ID(H_VMEMMAP_START)
+#define INVALID_REGION_ID	(VMEMMAP_REGION_ID + 1)
 
 /*
  * Defines the address of the vmemap area, in its own region on
  * hash table CPUs.
  */
-#define H_VMEMMAP_BASE		(VMEMMAP_REGION_ID << REGION_SHIFT)
-
 #ifdef CONFIG_PPC_MM_SLICES
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 #endif /* CONFIG_PPC_MM_SLICES */
 
-
 /* PTEIDX nibble */
 #define _PTEIDX_SECONDARY	0x8
 #define _PTEIDX_GROUP_IX	0x7
@@ -84,6 +112,26 @@
 #define H_PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
 
 #ifndef __ASSEMBLY__
+static inline int get_region_id(unsigned long ea)
+{
+	int region_id;
+	int id = (ea >> 60UL);
+
+	if (id == 0)
+		return USER_REGION_ID;
+
+	if (id != (PAGE_OFFSET >> 60))
+		return INVALID_REGION_ID;
+
+	if (ea < H_KERN_VIRT_START)
+		return LINEAR_MAP_REGION_ID;
+
+	BUILD_BUG_ON(NON_LINEAR_REGION_ID(H_VMALLOC_START) != 2);
+
+	region_id = NON_LINEAR_REGION_ID(ea);
+	return region_id;
+}
+
 #define	hash__pmd_bad(pmd)		(pmd_val(pmd) & H_PMD_BAD_BITS)
 #define	hash__pud_bad(pud)		(pud_val(pud) & H_PUD_BAD_BITS)
 static inline int hash__pgd_bad(pgd_t pgd)
@@ -196,8 +244,7 @@
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 
-extern int hash__map_kernel_page(unsigned long ea, unsigned long pa,
-			     unsigned long flags);
+int hash__map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot);
 extern int __meminit hash__vmemmap_create_mapping(unsigned long start,
 					      unsigned long page_size,
 					      unsigned long phys);
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index 5088838..12e150e 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -13,6 +13,10 @@
 				unsigned long len, unsigned long pgoff,
 				unsigned long flags);
 
+extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+						unsigned long addr, pte_t *ptep,
+						pte_t old_pte, pte_t pte);
+
 static inline int hstate_get_psize(struct hstate *hstate)
 {
 	unsigned long shift;
@@ -32,11 +36,101 @@
 	}
 }
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void)
+#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
+static inline bool gigantic_page_runtime_supported(void)
 {
+	/*
+	 * We used gigantic page reservation with hypervisor assist in some case.
+	 * We cannot use runtime allocation of gigantic pages in those platforms
+	 * This is hash translation mode LPARs.
+	 */
+	if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
+		return false;
+
 	return true;
 }
-#endif
+
+/* 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);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+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)
+{
+	if (radix_enabled())
+		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)
+{
+	int mmu_psize;
+
+	if (shift > SLICE_HIGH_SHIFT)
+		return -EINVAL;
+
+	mmu_psize = shift_to_mmu_psize(shift);
+
+	/*
+	 * We need to make sure that for different page sizes reported by
+	 * firmware we only add hugetlb support for page sizes that can be
+	 * supported by linux page table layout.
+	 * For now we have
+	 * Radix: 2M and 1G
+	 * Hash: 16M and 16G
+	 */
+	if (radix_enabled()) {
+		if (mmu_psize != MMU_PAGE_2M && mmu_psize != MMU_PAGE_1G)
+			return -EINVAL;
+	} else {
+		if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G)
+			return -EINVAL;
+	}
+	return mmu_psize;
+}
 
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h
new file mode 100644
index 0000000..f254de9
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
+#define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
+
+#include <linux/const.h>
+
+#define AMR_KUAP_BLOCK_READ	UL(0x4000000000000000)
+#define AMR_KUAP_BLOCK_WRITE	UL(0x8000000000000000)
+#define AMR_KUAP_BLOCKED	(AMR_KUAP_BLOCK_READ | AMR_KUAP_BLOCK_WRITE)
+#define AMR_KUAP_SHIFT		62
+
+#ifdef __ASSEMBLY__
+
+.macro kuap_restore_amr	gpr
+#ifdef CONFIG_PPC_KUAP
+	BEGIN_MMU_FTR_SECTION_NESTED(67)
+	ld	\gpr, STACK_REGS_KUAP(r1)
+	mtspr	SPRN_AMR, \gpr
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67)
+#endif
+.endm
+
+.macro kuap_check_amr gpr1, gpr2
+#ifdef CONFIG_PPC_KUAP_DEBUG
+	BEGIN_MMU_FTR_SECTION_NESTED(67)
+	mfspr	\gpr1, SPRN_AMR
+	li	\gpr2, (AMR_KUAP_BLOCKED >> AMR_KUAP_SHIFT)
+	sldi	\gpr2, \gpr2, AMR_KUAP_SHIFT
+999:	tdne	\gpr1, \gpr2
+	EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67)
+#endif
+.endm
+
+.macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr
+#ifdef CONFIG_PPC_KUAP
+	BEGIN_MMU_FTR_SECTION_NESTED(67)
+	.ifnb \msr_pr_cr
+	bne	\msr_pr_cr, 99f
+	.endif
+	mfspr	\gpr1, SPRN_AMR
+	std	\gpr1, STACK_REGS_KUAP(r1)
+	li	\gpr2, (AMR_KUAP_BLOCKED >> AMR_KUAP_SHIFT)
+	sldi	\gpr2, \gpr2, AMR_KUAP_SHIFT
+	cmpd	\use_cr, \gpr1, \gpr2
+	beq	\use_cr, 99f
+	// We don't isync here because we very recently entered via rfid
+	mtspr	SPRN_AMR, \gpr2
+	isync
+99:
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67)
+#endif
+.endm
+
+#else /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_PPC_KUAP
+
+#include <asm/reg.h>
+
+/*
+ * 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 void set_kuap(unsigned long value)
+{
+	if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP))
+		return;
+
+	/*
+	 * ISA v3.0B says we need a CSI (Context Synchronising Instruction) both
+	 * before and after the move to AMR. See table 6 on page 1134.
+	 */
+	isync();
+	mtspr(SPRN_AMR, value);
+	isync();
+}
+
+static inline void allow_user_access(void __user *to, const void __user *from,
+				     unsigned long size)
+{
+	// This is written so we can resolve to a single case at build time
+	if (__builtin_constant_p(to) && to == NULL)
+		set_kuap(AMR_KUAP_BLOCK_WRITE);
+	else if (__builtin_constant_p(from) && from == NULL)
+		set_kuap(AMR_KUAP_BLOCK_READ);
+	else
+		set_kuap(0);
+}
+
+static inline void prevent_user_access(void __user *to, const void __user *from,
+				       unsigned long size)
+{
+	set_kuap(AMR_KUAP_BLOCKED);
+}
+
+static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+{
+	return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) &&
+		    (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
+		    "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
+}
+#endif /* CONFIG_PPC_KUAP */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index b3520b5..15b7500 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_
 #define _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_
 /*
@@ -5,11 +6,6 @@
  *
  * Dave Engebretsen & Mike Corrigan <{engebret|mikejc}@us.ibm.com>
  *   PPC64 rework.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/page.h>
@@ -23,14 +19,14 @@
  */
 #include <asm/book3s/64/pgtable.h>
 #include <asm/bug.h>
-#include <asm/processor.h>
+#include <asm/task_size_64.h>
 #include <asm/cpu_has_feature.h>
 
 /*
  * SLB
  */
 
-#define SLB_NUM_BOLTED		3
+#define SLB_NUM_BOLTED		2
 #define SLB_CACHE_ENTRIES	8
 #define SLB_MIN_SIZE		32
 
@@ -203,6 +199,18 @@
 	BUG();
 }
 
+static inline unsigned int ap_to_shift(unsigned long ap)
+{
+	int psize;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+		if (mmu_psize_defs[psize].ap == ap)
+			return mmu_psize_defs[psize].shift;
+	}
+
+	return -1;
+}
+
 static inline unsigned long get_sllp_encoding(int psize)
 {
 	unsigned long sllp;
@@ -487,6 +495,8 @@
 extern void pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
 extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
+extern void hash__setup_new_exec(void);
+
 #ifdef CONFIG_PPC_PSERIES
 void hpte_init_pseries(void);
 #else
@@ -495,11 +505,18 @@
 
 extern void hpte_init_native(void);
 
+struct slb_entry {
+	u64	esid;
+	u64	vsid;
+};
+
 extern void slb_initialize(void);
-extern void slb_flush_and_rebolt(void);
+void slb_flush_and_restore_bolted(void);
 void slb_flush_all_realmode(void);
 void __slb_restore_bolted_realmode(void);
 void slb_restore_bolted_realmode(void);
+void slb_save_contents(struct slb_entry *slb_ptr);
+void slb_dump_contents(struct slb_entry *slb_ptr);
 
 extern void slb_vmalloc_update(void);
 extern void slb_set_size(u16 size);
@@ -512,13 +529,9 @@
  * from mmu context id and effective segment id of the address.
  *
  * For user processes max context id is limited to MAX_USER_CONTEXT.
-
- * For kernel space, we use context ids 1-4 to map addresses as below:
- * NOTE: each context only support 64TB now.
- * 0x00001 -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
- * 0x00002 -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
- * 0x00003 -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
- * 0x00004 -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
+ * more details in get_user_context
+ *
+ * For kernel space get_kernel_context
  *
  * The proto-VSIDs are then scrambled into real VSIDs with the
  * multiplicative hash:
@@ -559,6 +572,22 @@
 #define ESID_BITS_1T_MASK	((1 << ESID_BITS_1T) - 1)
 
 /*
+ * Now certain config support MAX_PHYSMEM more than 512TB. Hence we will need
+ * to use more than one context for linear mapping the kernel.
+ * For vmalloc and memmap, we use just one context with 512TB. With 64 byte
+ * struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)).
+ */
+#if (MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT)
+#define MAX_KERNEL_CTX_CNT	(1UL << (MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT))
+#else
+#define MAX_KERNEL_CTX_CNT	1
+#endif
+
+#define MAX_VMALLOC_CTX_CNT	1
+#define MAX_IO_CTX_CNT		1
+#define MAX_VMEMMAP_CTX_CNT	1
+
+/*
  * 256MB segment
  * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments
  * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts
@@ -568,13 +597,11 @@
  * We also need to avoid the last segment of the last context, because that
  * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
  * because of the modulo operation in vsid scramble.
+ *
  */
 #define MAX_USER_CONTEXT	((ASM_CONST(1) << CONTEXT_BITS) - 2)
-#define MIN_USER_CONTEXT	(5)
-
-/* Would be nice to use KERNEL_REGION_ID here */
-#define KERNEL_REGION_CONTEXT_OFFSET	(0xc - 1)
-
+#define MIN_USER_CONTEXT	(MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \
+				 MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT)
 /*
  * For platforms that support on 65bit VA we limit the context bits
  */
@@ -624,8 +651,8 @@
 
 /* 4 bits per slice and we have one slice per 1TB */
 #define SLICE_ARRAY_SIZE	(H_PGTABLE_RANGE >> 41)
-#define TASK_SLICE_ARRAY_SZ(x)	((x)->context.slb_addr_limit >> 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__
 
 #ifdef CONFIG_PPC_SUBPAGE_PROT
@@ -654,12 +681,41 @@
 #define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
 
 extern void subpage_prot_free(struct mm_struct *mm);
-extern void subpage_prot_init_new_context(struct mm_struct *mm);
 #else
 static inline void subpage_prot_free(struct mm_struct *mm) {}
-static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
 #endif /* CONFIG_PPC_SUBPAGE_PROT */
 
+/*
+ * One bit per slice. We have lower slices which cover 256MB segments
+ * upto 4G range. That gets us 16 low slices. For the rest we track slices
+ * in 1TB size.
+ */
+struct slice_mask {
+	u64 low_slices;
+	DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH);
+};
+
+struct hash_mm_context {
+	u16 user_psize; /* page size index */
+
+	/* SLB page size encodings*/
+	unsigned char low_slices_psize[LOW_SLICE_ARRAY_SZ];
+	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
+	unsigned long slb_addr_limit;
+#ifdef CONFIG_PPC_64K_PAGES
+	struct slice_mask mask_64k;
+#endif
+	struct slice_mask mask_4k;
+#ifdef CONFIG_HUGETLB_PAGE
+	struct slice_mask mask_16m;
+	struct slice_mask mask_16g;
+#endif
+
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+	struct subpage_prot_table *spt;
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
+};
+
 #if 0
 /*
  * The code below is equivalent to this function for arguments
@@ -714,7 +770,7 @@
 	/*
 	 * Bad address. We return VSID 0 for that
 	 */
-	if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
+	if ((ea & EA_MASK)  >= H_PGTABLE_RANGE)
 		return 0;
 
 	if (!mmu_has_feature(MMU_FTR_68_BIT_VA))
@@ -734,6 +790,40 @@
 }
 
 /*
+ * For kernel space, we use context ids as below
+ * below. Range is 512TB per context.
+ *
+ * 0x00001 -  [ 0xc000000000000000 - 0xc001ffffffffffff]
+ * 0x00002 -  [ 0xc002000000000000 - 0xc003ffffffffffff]
+ * 0x00003 -  [ 0xc004000000000000 - 0xc005ffffffffffff]
+ * 0x00004 -  [ 0xc006000000000000 - 0xc007ffffffffffff]
+ *
+ * vmap, IO, vmemap
+ *
+ * 0x00005 -  [ 0xc008000000000000 - 0xc009ffffffffffff]
+ * 0x00006 -  [ 0xc00a000000000000 - 0xc00bffffffffffff]
+ * 0x00007 -  [ 0xc00c000000000000 - 0xc00dffffffffffff]
+ *
+ */
+static inline unsigned long get_kernel_context(unsigned long ea)
+{
+	unsigned long region_id = get_region_id(ea);
+	unsigned long ctx;
+	/*
+	 * Depending on Kernel config, kernel region can have one context
+	 * or more.
+	 */
+	if (region_id == LINEAR_MAP_REGION_ID) {
+		/*
+		 * We already verified ea to be not beyond the addr limit.
+		 */
+		ctx =  1 + ((ea & EA_MASK) >> MAX_EA_BITS_PER_CONTEXT);
+	} else
+		ctx = region_id + MAX_KERNEL_CTX_CNT - 1;
+	return ctx;
+}
+
+/*
  * This is only valid for addresses >= PAGE_OFFSET
  */
 static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
@@ -743,20 +833,7 @@
 	if (!is_kernel_addr(ea))
 		return 0;
 
-	/*
-	 * For kernel space, we use context ids 1-4 to map the address space as
-	 * below:
-	 *
-	 * 0x00001 -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
-	 * 0x00002 -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
-	 * 0x00003 -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
-	 * 0x00004 -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
-	 *
-	 * So we can compute the context from the region (top nibble) by
-	 * subtracting 11, or 0xc - 1.
-	 */
-	context = (ea >> 60) - KERNEL_REGION_CONTEXT_OFFSET;
-
+	context = get_kernel_context(ea);
 	return get_vsid(context, ea, ssize);
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 9c8c669..bb3deb7 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_MMU_H_
 #define _ASM_POWERPC_BOOK3S_64_MMU_H_
 
+#include <asm/page.h>
+
 #ifndef __ASSEMBLY__
 /*
  * Page size definition
@@ -23,9 +25,23 @@
 	};
 };
 extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
-
 #endif /* __ASSEMBLY__ */
 
+/*
+ * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS
+ * if we increase SECTIONS_WIDTH we will not store node details in page->flags and
+ * page_to_nid does a page->section->node lookup
+ * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce
+ * memory requirements with large number of sections.
+ * 51 bits is the max physical real address on POWER9
+ */
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) &&  \
+	defined(CONFIG_PPC_64K_PAGES)
+#define MAX_PHYSMEM_BITS 51
+#else
+#define MAX_PHYSMEM_BITS 46
+#endif
+
 /* 64-bit classic hash table MMU */
 #include <asm/book3s/64/mmu-hash.h>
 
@@ -80,16 +96,6 @@
 /* Maximum possible number of NPUs in a system. */
 #define NV_MAX_NPUS 8
 
-/*
- * One bit per slice. We have lower slices which cover 256MB segments
- * upto 4G range. That gets us 16 low slices. For the rest we track slices
- * in 1TB size.
- */
-struct slice_mask {
-	u64 low_slices;
-	DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH);
-};
-
 typedef struct {
 	union {
 		/*
@@ -103,7 +109,6 @@
 		mm_context_id_t id;
 		mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE];
 	};
-	u16 user_psize;		/* page size index */
 
 	/* Number of bits in the mm_cpumask */
 	atomic_t active_cpus;
@@ -111,29 +116,9 @@
 	/* Number of users of the external (Nest) MMU */
 	atomic_t copros;
 
-	/* NPU NMMU context */
-	struct npu_context *npu_context;
+	struct hash_mm_context *hash_context;
 
-#ifdef CONFIG_PPC_MM_SLICES
-	 /* SLB page size encodings*/
-	unsigned char low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE];
-	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
-	unsigned long slb_addr_limit;
-# ifdef CONFIG_PPC_64K_PAGES
-	struct slice_mask mask_64k;
-# endif
-	struct slice_mask mask_4k;
-# ifdef CONFIG_HUGETLB_PAGE
-	struct slice_mask mask_16m;
-	struct slice_mask mask_16g;
-# endif
-#else
-	u16 sllp;		/* SLB page size encoding */
-#endif
 	unsigned long vdso_base;
-#ifdef CONFIG_PPC_SUBPAGE_PROT
-	struct subpage_prot_table spt;
-#endif /* CONFIG_PPC_SUBPAGE_PROT */
 	/*
 	 * pagetable fragment support
 	 */
@@ -154,6 +139,60 @@
 #endif
 } mm_context_t;
 
+static inline u16 mm_ctx_user_psize(mm_context_t *ctx)
+{
+	return ctx->hash_context->user_psize;
+}
+
+static inline void mm_ctx_set_user_psize(mm_context_t *ctx, u16 user_psize)
+{
+	ctx->hash_context->user_psize = user_psize;
+}
+
+static inline unsigned char *mm_ctx_low_slices(mm_context_t *ctx)
+{
+	return ctx->hash_context->low_slices_psize;
+}
+
+static inline unsigned char *mm_ctx_high_slices(mm_context_t *ctx)
+{
+	return ctx->hash_context->high_slices_psize;
+}
+
+static inline unsigned long mm_ctx_slb_addr_limit(mm_context_t *ctx)
+{
+	return ctx->hash_context->slb_addr_limit;
+}
+
+static inline void mm_ctx_set_slb_addr_limit(mm_context_t *ctx, unsigned long limit)
+{
+	ctx->hash_context->slb_addr_limit = limit;
+}
+
+static inline struct slice_mask *slice_mask_for_size(mm_context_t *ctx, int psize)
+{
+#ifdef CONFIG_PPC_64K_PAGES
+	if (psize == MMU_PAGE_64K)
+		return &ctx->hash_context->mask_64k;
+#endif
+#ifdef CONFIG_HUGETLB_PAGE
+	if (psize == MMU_PAGE_16M)
+		return &ctx->hash_context->mask_16m;
+	if (psize == MMU_PAGE_16G)
+		return &ctx->hash_context->mask_16g;
+#endif
+	BUG_ON(psize != MMU_PAGE_4K);
+
+	return &ctx->hash_context->mask_4k;
+}
+
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+static inline struct subpage_prot_table *mm_ctx_subpage_prot(mm_context_t *ctx)
+{
+	return ctx->hash_context->spt;
+}
+#endif
+
 /*
  * The current system page and segment sizes
  */
@@ -167,7 +206,6 @@
 void mmu_early_init_devtree(void);
 void hash__early_init_devtree(void);
 void radix__early_init_devtree(void);
-extern void radix_init_native(void);
 extern void hash__early_init_mmu(void);
 extern void radix__early_init_mmu(void);
 static inline void early_init_mmu(void)
@@ -199,16 +237,13 @@
 					   first_memblock_size);
 }
 
-extern int (*register_process_table)(unsigned long base, unsigned long page_size,
-				     unsigned long tbl_size);
-
 #ifdef CONFIG_PPC_PSERIES
 extern void radix_init_pseries(void);
 #else
 static inline void radix_init_pseries(void) { };
 #endif
 
-static inline int get_ea_context(mm_context_t *ctx, unsigned long ea)
+static inline int get_user_context(mm_context_t *ctx, unsigned long ea)
 {
 	int index = ea >> MAX_EA_BITS_PER_CONTEXT;
 
@@ -223,7 +258,7 @@
 static inline unsigned long get_user_vsid(mm_context_t *ctx,
 					  unsigned long ea, int ssize)
 {
-	unsigned long context = get_ea_context(ctx, ea);
+	unsigned long context = get_user_context(ctx, ea);
 
 	return get_vsid(context, ea, ssize);
 }
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 391ed2c..d5a4491 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_BOOK3S_64_PGALLOC_H
 #define _ASM_POWERPC_BOOK3S_64_PGALLOC_H
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/slab.h>
@@ -19,37 +16,13 @@
 };
 extern struct vmemmap_backing *vmemmap_list;
 
-/*
- * 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
- * handle allocation.  For PTE pages (which are linked to a struct
- * page for now, and drawn from the main get_free_pages() pool), the
- * allocation size will be (2^index_size * sizeof(pointer)) and
- * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
- *
- * The maximum index size needs to be big enough to allow any
- * pagetable sizes we need, but small enough to fit in the low bits of
- * any page table pointer.  In other words all pagetables, even tiny
- * ones, must be aligned to allow at least enough low 0 bits to
- * contain this value.  This value is also used as a mask, so it must
- * be one less than a power of two.
- */
-#define MAX_PGTABLE_INDEX_SIZE	0xf
-
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) ({				\
-			BUG_ON(!(shift));		\
-			pgtable_cache[(shift) - 1];	\
-		})
-
-extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int);
 extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long);
-extern void pte_fragment_free(unsigned long *, int);
 extern void pmd_fragment_free(unsigned long *);
 extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
 #ifdef CONFIG_SMP
 extern void __tlb_remove_table(void *_table);
 #endif
+void pte_frag_destroy(void *pte_frag);
 
 static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
 {
@@ -83,6 +56,9 @@
 
 	pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
 			       pgtable_gfp_flags(mm, GFP_KERNEL));
+	if (unlikely(!pgd))
+		return pgd;
+
 	/*
 	 * Don't scan the PGD for pointers, it contains references to PUDs but
 	 * those references are not full pointers and so can't be recognised by
@@ -113,7 +89,7 @@
 
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 {
-	pgd_set(pgd, __pgtable_ptr_val(pud) | PGD_VAL_BITS);
+	*pgd =  __pgd(__pgtable_ptr_val(pud) | PGD_VAL_BITS);
 }
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
@@ -140,7 +116,7 @@
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
-	pud_set(pud, __pgtable_ptr_val(pmd) | PUD_VAL_BITS);
+	*pud = __pud(__pgtable_ptr_val(pmd) | PUD_VAL_BITS);
 }
 
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
@@ -178,40 +154,13 @@
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 				       pte_t *pte)
 {
-	pmd_set(pmd, __pgtable_ptr_val(pte) | PMD_VAL_BITS);
+	*pmd = __pmd(__pgtable_ptr_val(pte) | PMD_VAL_BITS);
 }
 
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 				pgtable_t pte_page)
 {
-	pmd_set(pmd, __pgtable_ptr_val(pte_page) | PMD_VAL_BITS);
-}
-
-static inline pgtable_t pmd_pgtable(pmd_t pmd)
-{
-	return (pgtable_t)pmd_page_vaddr(pmd);
-}
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
-					  unsigned long address)
-{
-	return (pte_t *)pte_fragment_alloc(mm, address, 1);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
-				      unsigned long address)
-{
-	return (pgtable_t)pte_fragment_alloc(mm, address, 0);
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	pte_fragment_free((unsigned long *)pte, 1);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-	pte_fragment_free((unsigned long *)ptepage, 0);
+	*pmd = __pmd(__pgtable_ptr_val(pte_page) | PMD_VAL_BITS);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
@@ -225,8 +174,6 @@
 	pgtable_free_tlb(tlb, table, PTE_INDEX);
 }
 
-#define check_pgt_cache()	do { } while (0)
-
 extern atomic_long_t direct_pages_count[MMU_PAGE_COUNT];
 static inline void update_page_count(int psize, long count)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
index d7ee249..e3d4dd4 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
@@ -10,6 +10,9 @@
  *
  * 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)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 2a24865..b01624e 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -14,10 +14,6 @@
  */
 #define _PAGE_BIT_SWAP_TYPE	0
 
-#define _PAGE_NA		0
-#define _PAGE_RO		0
-#define _PAGE_USER		0
-
 #define _PAGE_EXEC		0x00001 /* execute permission */
 #define _PAGE_WRITE		0x00002 /* write access allowed */
 #define _PAGE_READ		0x00004	/* read access allowed */
@@ -94,7 +90,6 @@
 #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 */
-#define __HAVE_ARCH_PTE_DEVMAP
 
 /*
  * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE
@@ -123,10 +118,6 @@
 #define _PAGE_KERNEL_RWX	(_PAGE_PRIVILEGED | _PAGE_DIRTY |	\
 				 _PAGE_RW | _PAGE_EXEC)
 /*
- * No page size encoding in the linux PTE
- */
-#define _PAGE_PSIZE		0
-/*
  * _PAGE_CHG_MASK masks of bits that are to be preserved across
  * pgprot changes
  */
@@ -137,19 +128,12 @@
 #define H_PTE_PKEY  (H_PTE_PKEY_BIT0 | H_PTE_PKEY_BIT1 | H_PTE_PKEY_BIT2 | \
 		     H_PTE_PKEY_BIT3 | H_PTE_PKEY_BIT4)
 /*
- * Mask of bits returned by pte_pgprot()
- */
-#define PAGE_PROT_BITS  (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT | \
-			 H_PAGE_4K_PFN | _PAGE_PRIVILEGED | _PAGE_ACCESSED | \
-			 _PAGE_READ | _PAGE_WRITE |  _PAGE_DIRTY | _PAGE_EXEC | \
-			 _PAGE_SOFT_DIRTY | H_PTE_PKEY)
-/*
  * We define 2 sets of base prot bits, one for basic pages (ie,
  * cacheable kernel and user pages) and one for non cacheable
  * 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)
 #define _PAGE_BASE	(_PAGE_BASE_NC)
 
 /* Permission masks used to generate the __P and __S table,
@@ -159,8 +143,6 @@
  * 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
- *
- * Note due to the way vm flags are laid out, the bits are XWR
  */
 #define PAGE_NONE	__pgprot(_PAGE_BASE | _PAGE_PRIVILEGED)
 #define PAGE_SHARED	__pgprot(_PAGE_BASE | _PAGE_RW)
@@ -170,24 +152,6 @@
 #define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_READ)
 #define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
 
-#define __P000	PAGE_NONE
-#define __P001	PAGE_READONLY
-#define __P010	PAGE_COPY
-#define __P011	PAGE_COPY
-#define __P100	PAGE_READONLY_X
-#define __P101	PAGE_READONLY_X
-#define __P110	PAGE_COPY_X
-#define __P111	PAGE_COPY_X
-
-#define __S000	PAGE_NONE
-#define __S001	PAGE_READONLY
-#define __S010	PAGE_SHARED
-#define __S011	PAGE_SHARED
-#define __S100	PAGE_READONLY_X
-#define __S101	PAGE_READONLY_X
-#define __S110	PAGE_SHARED_X
-#define __S111	PAGE_SHARED_X
-
 /* 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 | \
@@ -309,14 +273,22 @@
 #define VMALLOC_START	__vmalloc_start
 #define VMALLOC_END	__vmalloc_end
 
+static inline unsigned int ioremap_max_order(void)
+{
+	if (radix_enabled())
+		return PUD_SHIFT;
+	return 7 + PAGE_SHIFT; /* default from linux/vmalloc.h */
+}
+#define IOREMAP_MAX_ORDER ioremap_max_order()
+
 extern unsigned long __kernel_virt_start;
-extern unsigned long __kernel_virt_size;
 extern unsigned long __kernel_io_start;
+extern unsigned long __kernel_io_end;
 #define KERN_VIRT_START __kernel_virt_start
-#define KERN_VIRT_SIZE  __kernel_virt_size
 #define KERN_IO_START  __kernel_io_start
+#define KERN_IO_END __kernel_io_end
+
 extern struct page *vmemmap;
-extern unsigned long ioremap_bot;
 extern unsigned long pci_io_base;
 #endif /* __ASSEMBLY__ */
 
@@ -331,8 +303,7 @@
 
 #include <asm/barrier.h>
 /*
- * The second half of the kernel virtual space is used for IO mappings,
- * it's itself carved into the PIO region (ISA and PHB IO space) and
+ * IO space itself carved into the PIO region (ISA and PHB IO space) and
  * the ioremap space
  *
  *  ISA_IO_BASE = KERN_IO_START, 64K reserved area
@@ -345,7 +316,8 @@
 #define  PHB_IO_BASE	(ISA_IO_END)
 #define  PHB_IO_END	(KERN_IO_START + FULL_IO_SIZE)
 #define IOREMAP_BASE	(PHB_IO_END)
-#define IOREMAP_END	(KERN_VIRT_START + KERN_VIRT_SIZE)
+#define IOREMAP_START	(ioremap_bot)
+#define IOREMAP_END	(KERN_IO_END)
 
 /* Advertise special mapping type for AGP */
 #define HAVE_PAGE_AGP
@@ -461,6 +433,7 @@
 		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 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)
 {
@@ -519,7 +492,11 @@
 	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SPECIAL));
 }
 
-static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
+static inline bool pte_exec(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_EXEC));
+}
+
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline bool pte_soft_dirty(pte_t pte)
@@ -529,12 +506,12 @@
 
 static inline pte_t pte_mksoft_dirty(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
+	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SOFT_DIRTY));
 }
 
 static inline pte_t pte_clear_soft_dirty(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_SOFT_DIRTY);
+	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SOFT_DIRTY));
 }
 #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
 
@@ -555,7 +532,7 @@
 	 */
 	VM_BUG_ON((pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_RWX | _PAGE_PRIVILEGED)) !=
 		  cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED));
-	return __pte(pte_val(pte) & ~_PAGE_PRIVILEGED);
+	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED));
 }
 
 #define pte_clear_savedwrite pte_clear_savedwrite
@@ -565,14 +542,14 @@
 	 * Used by KSM subsystem to make a protnone pte readonly.
 	 */
 	VM_BUG_ON(!pte_protnone(pte));
-	return __pte(pte_val(pte) | _PAGE_PRIVILEGED);
+	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED));
 }
 #else
 #define pte_clear_savedwrite pte_clear_savedwrite
 static inline pte_t pte_clear_savedwrite(pte_t pte)
 {
 	VM_WARN_ON(1);
-	return __pte(pte_val(pte) & ~_PAGE_WRITE);
+	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE));
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
@@ -587,6 +564,11 @@
 	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID));
 }
 
+static inline bool pte_hw_valid(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT));
+}
+
 #ifdef CONFIG_PPC_MEM_KEYS
 extern bool arch_pte_access_permitted(u64 pte, bool write, bool execute);
 #else
@@ -596,25 +578,22 @@
 }
 #endif /* CONFIG_PPC_MEM_KEYS */
 
+static inline bool pte_user(pte_t pte)
+{
+	return !(pte_raw(pte) & cpu_to_be64(_PAGE_PRIVILEGED));
+}
+
 #define pte_access_permitted pte_access_permitted
 static inline bool pte_access_permitted(pte_t pte, bool write)
 {
-	unsigned long pteval = pte_val(pte);
-	/* Also check for pte_user */
-	unsigned long clear_pte_bits = _PAGE_PRIVILEGED;
 	/*
 	 * _PAGE_READ is needed for any access and will be
 	 * cleared for PROT_NONE
 	 */
-	unsigned long need_pte_bits = _PAGE_PRESENT | _PAGE_READ;
-
-	if (write)
-		need_pte_bits |= _PAGE_WRITE;
-
-	if ((pteval & need_pte_bits) != need_pte_bits)
+	if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte))
 		return false;
 
-	if ((pteval & clear_pte_bits) == clear_pte_bits)
+	if (write && !pte_write(pte))
 		return false;
 
 	return arch_pte_access_permitted(pte_val(pte), write, 0);
@@ -629,8 +608,10 @@
  */
 static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
 {
-	return __pte((((pte_basic_t)(pfn) << PAGE_SHIFT) & PTE_RPN_MASK) |
-		     pgprot_val(pgprot));
+	VM_BUG_ON(pfn >> (64 - PAGE_SHIFT));
+	VM_BUG_ON((pfn << PAGE_SHIFT) & ~PTE_RPN_MASK);
+
+	return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot));
 }
 
 static inline unsigned long pte_pfn(pte_t pte)
@@ -643,17 +624,32 @@
 {
 	if (unlikely(pte_savedwrite(pte)))
 		return pte_clear_savedwrite(pte);
-	return __pte(pte_val(pte) & ~_PAGE_WRITE);
+	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE));
+}
+
+static inline pte_t pte_exprotect(pte_t pte)
+{
+	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_EXEC));
 }
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_DIRTY));
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_ACCESSED));
+}
+
+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_mkpte(pte_t pte)
+{
+	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PTE));
 }
 
 static inline pte_t pte_mkwrite(pte_t pte)
@@ -661,22 +657,22 @@
 	/*
 	 * write implies read, hence set both
 	 */
-	return __pte(pte_val(pte) | _PAGE_RW);
+	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_RW));
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_DIRTY | _PAGE_SOFT_DIRTY));
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_ACCESSED));
 }
 
 static inline pte_t pte_mkspecial(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL));
 }
 
 static inline pte_t pte_mkhuge(pte_t pte)
@@ -686,7 +682,17 @@
 
 static inline pte_t pte_mkdevmap(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_SPECIAL|_PAGE_DEVMAP);
+	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));
 }
 
 /*
@@ -705,12 +711,8 @@
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	/* FIXME!! check whether this need to be a conditional */
-	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
-}
-
-static inline bool pte_user(pte_t pte)
-{
-	return !(pte_raw(pte) & cpu_to_be64(_PAGE_PRIVILEGED));
+	return __pte_raw((pte_raw(pte) & cpu_to_be64(_PAGE_CHG_MASK)) |
+			 cpu_to_be64(pgprot_val(newprot)));
 }
 
 /* Encode and de-code a swap entry */
@@ -723,9 +725,7 @@
 	BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
 	BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY);	\
 	} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
 				& ((1UL << SWP_TYPE_BITS) - 1))
@@ -741,6 +741,8 @@
  */
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE })
 #define __swp_entry_to_pte(x)	__pte((x).val | _PAGE_PTE)
+#define __pmd_to_swp_entry(pmd)	(__pte_to_swp_entry(pmd_pte(pmd)))
+#define __swp_entry_to_pmd(x)	(pte_pmd(__swp_entry_to_pte(x)))
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _PAGE_SWP_SOFT_DIRTY   (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE))
@@ -751,7 +753,7 @@
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
+	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_SOFT_DIRTY));
 }
 
 static inline bool pte_swp_soft_dirty(pte_t pte)
@@ -761,7 +763,7 @@
 
 static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~_PAGE_SWP_SOFT_DIRTY);
+	return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SWP_SOFT_DIRTY));
 }
 #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
 
@@ -818,7 +820,7 @@
 	return hash__set_pte_at(mm, addr, ptep, pte, percpu);
 }
 
-#define _PAGE_CACHE_CTL	(_PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT)
+#define _PAGE_CACHE_CTL	(_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT)
 
 #define pgprot_noncached pgprot_noncached
 static inline pgprot_t pgprot_noncached(pgprot_t prot)
@@ -850,19 +852,14 @@
  */
 static inline bool pte_ci(pte_t pte)
 {
-	unsigned long pte_v = pte_val(pte);
+	__be64 pte_v = pte_raw(pte);
 
-	if (((pte_v & _PAGE_CACHE_CTL) == _PAGE_TOLERANT) ||
-	    ((pte_v & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT))
+	if (((pte_v & cpu_to_be64(_PAGE_CACHE_CTL)) == cpu_to_be64(_PAGE_TOLERANT)) ||
+	    ((pte_v & cpu_to_be64(_PAGE_CACHE_CTL)) == cpu_to_be64(_PAGE_NON_IDEMPOTENT)))
 		return true;
 	return false;
 }
 
-static inline void pmd_set(pmd_t *pmdp, unsigned long val)
-{
-	*pmdp = __pmd(val);
-}
-
 static inline void pmd_clear(pmd_t *pmdp)
 {
 	*pmdp = __pmd(0);
@@ -875,8 +872,33 @@
 
 static inline int pmd_present(pmd_t pmd)
 {
+	/*
+	 * A pmd is considerent present if _PAGE_PRESENT is set.
+	 * We also need to consider the pmd present which is marked
+	 * invalid during a split. Hence we look for _PAGE_INVALID
+	 * if we find _PAGE_PRESENT cleared.
+	 */
+	if (pmd_raw(pmd) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID))
+		return true;
 
-	return !pmd_none(pmd);
+	return false;
+}
+
+static inline int pmd_is_serializing(pmd_t pmd)
+{
+	/*
+	 * If the pmd is undergoing a split, the _PAGE_PRESENT bit is clear
+	 * and _PAGE_INVALID is set (see pmd_present, pmdp_invalidate).
+	 *
+	 * This condition may also occur when flushing a pmd while flushing
+	 * it (see ptep_modify_prot_start), so callers must ensure this
+	 * case is fine as well.
+	 */
+	if ((pmd_raw(pmd) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID)) ==
+						cpu_to_be64(_PAGE_INVALID))
+		return true;
+
+	return false;
 }
 
 static inline int pmd_bad(pmd_t pmd)
@@ -886,11 +908,6 @@
 	return hash__pmd_bad(pmd);
 }
 
-static inline void pud_set(pud_t *pudp, unsigned long val)
-{
-	*pudp = __pud(val);
-}
-
 static inline void pud_clear(pud_t *pudp)
 {
 	*pudp = __pud(0);
@@ -903,7 +920,7 @@
 
 static inline int pud_present(pud_t pud)
 {
-	return !pud_none(pud);
+	return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT));
 }
 
 extern struct page *pud_page(pud_t pud);
@@ -933,10 +950,6 @@
 }
 
 #define pgd_write(pgd)		pte_write(pgd_pte(pgd))
-static inline void pgd_set(pgd_t *pgdp, unsigned long val)
-{
-	*pgdp = __pgd(val);
-}
 
 static inline void pgd_clear(pgd_t *pgdp)
 {
@@ -950,7 +963,7 @@
 
 static inline int pgd_present(pgd_t pgd)
 {
-	return !pgd_none(pgd);
+	return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT));
 }
 
 static inline pte_t pgd_pte(pgd_t pgd)
@@ -1005,7 +1018,8 @@
 	(((pte_t *) pmd_page_vaddr(*(dir))) + pte_index(addr))
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_unmap(pte)			do { } while(0)
+
+static inline void pte_unmap(pte_t *pte) { }
 
 /* to find an entry in a kernel page-table-directory */
 /* This now only contains the vmalloc pages */
@@ -1020,17 +1034,16 @@
 #define pgd_ERROR(e) \
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
-static inline int map_kernel_page(unsigned long ea, unsigned long pa,
-				  unsigned long flags)
+static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
 {
 	if (radix_enabled()) {
 #if defined(CONFIG_PPC_RADIX_MMU) && defined(DEBUG_VM)
 		unsigned long page_size = 1 << mmu_psize_defs[mmu_io_psize].shift;
 		WARN((page_size != PAGE_SIZE), "I/O page size != PAGE_SIZE");
 #endif
-		return radix__map_kernel_page(ea, pa, __pgprot(flags), PAGE_SIZE);
+		return radix__map_kernel_page(ea, pa, prot, PAGE_SIZE);
 	}
-	return hash__map_kernel_page(ea, pa, flags);
+	return hash__map_kernel_page(ea, pa, prot);
 }
 
 static inline int __meminit vmemmap_create_mapping(unsigned long start,
@@ -1082,6 +1095,12 @@
 #define pmd_soft_dirty(pmd)    pte_soft_dirty(pmd_pte(pmd))
 #define pmd_mksoft_dirty(pmd)  pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)))
 #define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd)))
+
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+#define pmd_swp_mksoft_dirty(pmd)	pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd)))
+#define pmd_swp_soft_dirty(pmd)		pte_swp_soft_dirty(pmd_pte(pmd))
+#define pmd_swp_clear_soft_dirty(pmd)	pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd)))
+#endif
 #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -1098,6 +1117,19 @@
 #define pmd_access_permitted pmd_access_permitted
 static inline bool pmd_access_permitted(pmd_t pmd, bool write)
 {
+	/*
+	 * pmdp_invalidate sets this combination (which is not caught by
+	 * !pte_present() check in pte_access_permitted), to prevent
+	 * lock-free lookups, as part of the serialize_against_pte_lookup()
+	 * synchronisation.
+	 *
+	 * This also catches the case where the PTE's hardware PRESENT bit is
+	 * cleared while TLB is flushed, which is suboptimal but should not
+	 * be frequent.
+	 */
+	if (pmd_is_serializing(pmd))
+		return false;
+
 	return pte_access_permitted(pmd_pte(pmd), write);
 }
 
@@ -1127,6 +1159,10 @@
 	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)
 {
 	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
@@ -1161,8 +1197,22 @@
 		pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
 }
 
+/*
+ * Only returns true for a THP. False for pmd migration entry.
+ * We also need to return true when we come across a pte that
+ * in between a thp split. While splitting THP, we mark the pmd
+ * invalid (pmdp_invalidate()) before we set it with pte page
+ * address. A pmd_trans_huge() check against a pmd entry during that time
+ * should return true.
+ * We should not call this on a hugetlb entry. We should check for HugeTLB
+ * entry using vma->vm_flags
+ * The page table walk rule is explained in Documentation/vm/transhuge.rst
+ */
 static inline int pmd_trans_huge(pmd_t pmd)
 {
+	if (!pmd_present(pmd))
+		return false;
+
 	if (radix_enabled())
 		return radix__pmd_trans_huge(pmd);
 	return hash__pmd_trans_huge(pmd);
@@ -1234,21 +1284,13 @@
 
 #define pmd_move_must_withdraw pmd_move_must_withdraw
 struct spinlock;
-static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
-					 struct spinlock *old_pmd_ptl,
-					 struct vm_area_struct *vma)
-{
-	if (radix_enabled())
-		return false;
-	/*
-	 * Archs like ppc64 use pgtable to store per pmd
-	 * specific information. So when we switch the pmd,
-	 * we should also withdraw and deposit the pgtable
-	 */
-	return true;
-}
-
-
+extern int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
+				  struct spinlock *old_pmd_ptl,
+				  struct vm_area_struct *vma);
+/*
+ * Hash translation mode use the deposited table to store hash pte
+ * slot information.
+ */
 #define arch_needs_pgtable_deposit arch_needs_pgtable_deposit
 static inline bool arch_needs_pgtable_deposit(void)
 {
@@ -1280,7 +1322,7 @@
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline const int pud_pfn(pud_t pud)
+static inline int pud_pfn(pud_t pud)
 {
 	/*
 	 * Currently all calls to pud_pfn() are gated around a pud_devmap()
@@ -1290,6 +1332,45 @@
 	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,
+			     pte_t *, pte_t, pte_t);
+
+/*
+ * Returns true for a R -> RW upgrade of pte
+ */
+static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_val)
+{
+	if (!(old_val & _PAGE_READ))
+		return false;
+
+	if ((!(old_val & _PAGE_WRITE)) && (new_val & _PAGE_WRITE))
+		return true;
+
+	return false;
+}
+
+/*
+ * Like pmd_huge() and pmd_large(), but works regardless of config options
+ */
+#define pmd_is_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
+static inline bool pud_is_leaf(pud_t pud)
+{
+	return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
+}
+
+#define pgd_is_leaf pgd_is_leaf
+static inline bool pgd_is_leaf(pgd_t pgd)
+{
+	return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE));
+}
 
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */
diff --git a/arch/powerpc/include/asm/book3s/64/radix-4k.h b/arch/powerpc/include/asm/book3s/64/radix-4k.h
index 863c3e8..d5f5ab7 100644
--- a/arch/powerpc/include/asm/book3s/64/radix-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/radix-4k.h
@@ -5,10 +5,11 @@
 /*
  * For 4K page size supported index is 13/9/9/9
  */
-#define RADIX_PTE_INDEX_SIZE  9  /* 2MB huge page */
-#define RADIX_PMD_INDEX_SIZE  9  /* 1G huge page */
-#define RADIX_PUD_INDEX_SIZE	 9
-#define RADIX_PGD_INDEX_SIZE  13
+#define RADIX_PTE_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x    4K =   2MB
+#define RADIX_PMD_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x   2MB =   1GB
+#define RADIX_PUD_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x   1GB = 512GB
+#define RADIX_PGD_INDEX_SIZE  13  // size: 8B << 13 = 64KB, maps 2^13 x 512GB =   4PB
+
 /*
  * One fragment per per page
  */
diff --git a/arch/powerpc/include/asm/book3s/64/radix-64k.h b/arch/powerpc/include/asm/book3s/64/radix-64k.h
index ccb78ca..54e3382 100644
--- a/arch/powerpc/include/asm/book3s/64/radix-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/radix-64k.h
@@ -5,10 +5,10 @@
 /*
  * For 64K page size supported index is 13/9/9/5
  */
-#define RADIX_PTE_INDEX_SIZE  5  /* 2MB huge page */
-#define RADIX_PMD_INDEX_SIZE  9  /* 1G huge page */
-#define RADIX_PUD_INDEX_SIZE	 9
-#define RADIX_PGD_INDEX_SIZE  13
+#define RADIX_PTE_INDEX_SIZE   5  // size: 8B <<  5 = 256B, maps 2^5  x   64K =   2MB
+#define RADIX_PMD_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x   2MB =   1GB
+#define RADIX_PUD_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x   1GB = 512GB
+#define RADIX_PGD_INDEX_SIZE  13  // size: 8B << 13 = 64KB, maps 2^13 x 512GB =   4PB
 
 /*
  * We use a 256 byte PTE page fragment in radix
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 7d1a3d1..d97db3a 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -72,19 +72,17 @@
  * |                              |
  * |                              |
  * |                              |
- * +------------------------------+  Kernel IO map end (0xc010000000000000)
+ * +------------------------------+  Kernel vmemmap end (0xc010000000000000)
  * |                              |
+ * |           512TB		  |
  * |                              |
- * |      1/2 of virtual map      |
+ * +------------------------------+  Kernel IO map end/vmemap start
  * |                              |
+ * |           512TB		  |
  * |                              |
- * +------------------------------+  Kernel IO map start
+ * +------------------------------+  Kernel vmap end/ IO map start
  * |                              |
- * |      1/4 of virtual map      |
- * |                              |
- * +------------------------------+  Kernel vmemap start
- * |                              |
- * |     1/4 of virtual map       |
+ * |           512TB		  |
  * |                              |
  * +------------------------------+  Kernel virt start (0xc008000000000000)
  * |                              |
@@ -93,24 +91,24 @@
  * +------------------------------+  Kernel linear (0xc.....)
  */
 
-#define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000)
-#define RADIX_KERN_VIRT_SIZE  ASM_CONST(0x0008000000000000)
-
+#define RADIX_KERN_VIRT_START	ASM_CONST(0xc008000000000000)
 /*
- * The vmalloc space starts at the beginning of that region, and
- * occupies a quarter of it on radix config.
- * (we keep a quarter for the virtual memmap)
+ * 49 =  MAX_EA_BITS_PER_CONTEXT (hash specific). To make sure we pick
+ * the same value as hash.
  */
+#define RADIX_KERN_MAP_SIZE	(1UL << 49)
+
 #define RADIX_VMALLOC_START	RADIX_KERN_VIRT_START
-#define RADIX_VMALLOC_SIZE	(RADIX_KERN_VIRT_SIZE >> 2)
+#define RADIX_VMALLOC_SIZE	RADIX_KERN_MAP_SIZE
 #define RADIX_VMALLOC_END	(RADIX_VMALLOC_START + RADIX_VMALLOC_SIZE)
-/*
- * Defines the address of the vmemap area, in its own region on
- * hash table CPUs.
- */
-#define RADIX_VMEMMAP_BASE		(RADIX_VMALLOC_END)
 
-#define RADIX_KERN_IO_START	(RADIX_KERN_VIRT_START + (RADIX_KERN_VIRT_SIZE >> 1))
+#define RADIX_KERN_IO_START	RADIX_VMALLOC_END
+#define RADIX_KERN_IO_SIZE	RADIX_KERN_MAP_SIZE
+#define RADIX_KERN_IO_END	(RADIX_KERN_IO_START + RADIX_KERN_IO_SIZE)
+
+#define RADIX_VMEMMAP_START	RADIX_KERN_IO_END
+#define RADIX_VMEMMAP_SIZE	RADIX_KERN_MAP_SIZE
+#define RADIX_VMEMMAP_END	(RADIX_VMEMMAP_START + RADIX_VMEMMAP_SIZE)
 
 #ifndef __ASSEMBLY__
 #define RADIX_PTE_TABLE_SIZE	(sizeof(pte_t) << RADIX_PTE_INDEX_SIZE)
@@ -127,6 +125,10 @@
 					 pte_t entry, unsigned long address,
 					 int psize);
 
+extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
+					   unsigned long addr, pte_t *ptep,
+					   pte_t old_pte, pte_t pte);
+
 static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
 					       unsigned long set)
 {
@@ -252,7 +254,13 @@
 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);
-extern int radix__has_transparent_hugepage(void);
+static inline int radix__has_transparent_hugepage(void)
+{
+	/* For radix 2M at PMD level means thp */
+	if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT)
+		return 1;
+	return 0;
+}
 #endif
 
 extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
diff --git a/arch/powerpc/include/asm/book3s/64/slice.h b/arch/powerpc/include/asm/book3s/64/slice.h
index db0deda..f0d3194 100644
--- a/arch/powerpc/include/asm/book3s/64/slice.h
+++ b/arch/powerpc/include/asm/book3s/64/slice.h
@@ -2,8 +2,6 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H
 #define _ASM_POWERPC_BOOK3S_64_SLICE_H
 
-#ifdef CONFIG_PPC_MM_SLICES
-
 #define SLICE_LOW_SHIFT		28
 #define SLICE_LOW_TOP		(0x100000000ul)
 #define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
@@ -13,15 +11,6 @@
 #define SLICE_NUM_HIGH		(H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT)
 #define GET_HIGH_SLICE_INDEX(addr)	((addr) >> SLICE_HIGH_SHIFT)
 
-#else /* CONFIG_PPC_MM_SLICES */
-
-#define get_slice_psize(mm, addr)	((mm)->context.user_psize)
-#define slice_set_user_psize(mm, psize)		\
-do {						\
-	(mm)->context.user_psize = (psize);	\
-	(mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \
-} while (0)
-
-#endif /* CONFIG_PPC_MM_SLICES */
+#define SLB_ADDR_LIMIT_DEFAULT	DEFAULT_MAP_WINDOW_USER64
 
 #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 1154a6d..ca8db19 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -13,8 +13,32 @@
 
 #ifdef CONFIG_PPC_RADIX_MMU
 extern void radix__tlbiel_all(unsigned int action);
+extern void radix__flush_tlb_lpid_page(unsigned int lpid,
+					unsigned long addr,
+					unsigned long page_size);
+extern void radix__flush_pwc_lpid(unsigned int lpid);
+extern void radix__flush_all_lpid(unsigned int lpid);
+extern void radix__flush_all_lpid_guest(unsigned int lpid);
 #else
 static inline void radix__tlbiel_all(unsigned int action) { WARN_ON(1); };
+static inline void radix__flush_tlb_lpid_page(unsigned int lpid,
+					unsigned long addr,
+					unsigned long page_size)
+{
+	WARN_ON(1);
+}
+static inline void radix__flush_pwc_lpid(unsigned int lpid)
+{
+	WARN_ON(1);
+}
+static inline void radix__flush_all_lpid(unsigned int lpid)
+{
+	WARN_ON(1);
+}
+static inline void radix__flush_all_lpid_guest(unsigned int lpid)
+{
+	WARN_ON(1);
+}
 #endif
 
 extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma,
@@ -49,11 +73,4 @@
 extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr);
 extern void radix__flush_tlb_all(void);
 
-extern void radix__flush_tlb_lpid_page(unsigned int lpid,
-					unsigned long addr,
-					unsigned long page_size);
-extern void radix__flush_pwc_lpid(unsigned int lpid);
-extern void radix__local_flush_tlb_lpid(unsigned int lpid);
-extern void radix__local_flush_tlb_lpid_guest(unsigned int lpid);
-
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index ebf572e..7aa8195 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -162,4 +162,13 @@
 
 	radix__flush_tlb_pwc(tlb, address);
 }
+
+extern bool tlbie_capable;
+extern bool tlbie_enabled;
+
+static inline bool cputlb_use_tlbie(void)
+{
+	return tlbie_enabled;
+}
+
 #endif /*  _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */
diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h
index 6436b65..0e12634 100644
--- a/arch/powerpc/include/asm/book3s/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/pgtable.h
@@ -26,5 +26,16 @@
 				     unsigned long size, pgprot_t vma_prot);
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 
+/*
+ * 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.
+ */
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep);
+
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/powerpc/include/asm/btext.h b/arch/powerpc/include/asm/btext.h
index 3ffad03..461b0f1 100644
--- a/arch/powerpc/include/asm/btext.h
+++ b/arch/powerpc/include/asm/btext.h
@@ -13,7 +13,11 @@
 				 int depth, int pitch);
 extern void btext_setup_display(int width, int height, int depth, int pitch,
 				unsigned long address);
+#ifdef CONFIG_PPC32
 extern void btext_prepare_BAT(void);
+#else
+static inline void btext_prepare_BAT(void) { }
+#endif
 extern void btext_map(void);
 extern void btext_unmap(void);
 
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index fd06dbe..f47e6ff 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -5,14 +5,6 @@
 
 #include <asm/asm-compat.h>
 
-/*
- * Define an illegal instr to trap on the bug.
- * We don't use 0 because that marks the end of a function
- * in the ELF ABI.  That's "Boo Boo" in case you wonder...
- */
-#define BUG_OPCODE .long 0x00b00b00  /* For asm */
-#define BUG_ILLEGAL_INSTR "0x00b00b00" /* For BUG macro */
-
 #ifdef CONFIG_BUG
 
 #ifdef __ASSEMBLY__
@@ -133,7 +125,7 @@
 extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
 extern void bad_page_fault(struct pt_regs *, unsigned long, int);
 extern void _exception(int, struct pt_regs *, int, unsigned long);
-extern void _exception_pkey(int, struct pt_regs *, int, unsigned long, int);
+extern void _exception_pkey(struct pt_regs *, unsigned long, int);
 extern void die(const char *, struct pt_regs *, long);
 extern bool die_will_crash(void);
 extern void panic_flush_kmsg_start(void);
diff --git a/arch/powerpc/include/asm/bugs.h b/arch/powerpc/include/asm/bugs.h
index 42fdb73..01b8f6c 100644
--- a/arch/powerpc/include/asm/bugs.h
+++ b/arch/powerpc/include/asm/bugs.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_BUGS_H
 #define _ASM_POWERPC_BUGS_H
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /*
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 6629846..45e3137 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -33,7 +33,8 @@
 
 #define IFETCH_ALIGN_BYTES	(1 << IFETCH_ALIGN_SHIFT)
 
-#if defined(__powerpc64__) && !defined(__ASSEMBLY__)
+#if !defined(__ASSEMBLY__)
+#ifdef CONFIG_PPC64
 
 struct ppc_cache_info {
 	u32 size;
@@ -53,7 +54,28 @@
 };
 
 extern struct ppc64_caches ppc64_caches;
-#endif /* __powerpc64__ && ! __ASSEMBLY__ */
+
+static inline u32 l1_cache_shift(void)
+{
+	return ppc64_caches.l1d.log_block_size;
+}
+
+static inline u32 l1_cache_bytes(void)
+{
+	return ppc64_caches.l1d.block_size;
+}
+#else
+static inline u32 l1_cache_shift(void)
+{
+	return L1_CACHE_SHIFT;
+}
+
+static inline u32 l1_cache_bytes(void)
+{
+	return L1_CACHE_BYTES;
+}
+#endif
+#endif /* ! __ASSEMBLY__ */
 
 #if defined(__ASSEMBLY__)
 /*
@@ -71,7 +93,7 @@
 #else
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
 
-#ifdef CONFIG_6xx
+#ifdef CONFIG_PPC_BOOK3S_32
 extern long _get_L2CR(void);
 extern long _get_L3CR(void);
 extern void _set_L2CR(unsigned long);
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index d5a8d7b..eef388f 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -1,8 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_CACHEFLUSH_H
 #define _ASM_POWERPC_CACHEFLUSH_H
@@ -32,9 +29,12 @@
  * not expect this type of fault. flush_cache_vmap is not exactly the right
  * place to put this, but it seems to work well enough.
  */
-#define flush_cache_vmap(start, end)		do { asm volatile("ptesync" ::: "memory"); } while (0)
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	asm volatile("ptesync" ::: "memory");
+}
 #else
-#define flush_cache_vmap(start, end)		do { } while (0)
+static inline void flush_cache_vmap(unsigned long start, unsigned long end) { }
 #endif
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
@@ -57,20 +57,29 @@
 }
 #endif
 
-#ifdef CONFIG_PPC32
 /*
  * Write any modified data cache blocks out to memory and invalidate them.
  * Does not invalidate the corresponding instruction cache blocks.
  */
 static inline void flush_dcache_range(unsigned long start, unsigned long stop)
 {
-	void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1));
-	unsigned long size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1);
+	unsigned long shift = l1_cache_shift();
+	unsigned long bytes = l1_cache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
 	unsigned long i;
 
-	for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES)
+	if (IS_ENABLED(CONFIG_PPC64)) {
+		mb();	/* sync */
+		isync();
+	}
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
 		dcbf(addr);
 	mb();	/* sync */
+
+	if (IS_ENABLED(CONFIG_PPC64))
+		isync();
 }
 
 /*
@@ -80,11 +89,13 @@
  */
 static inline void clean_dcache_range(unsigned long start, unsigned long stop)
 {
-	void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1));
-	unsigned long size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1);
+	unsigned long shift = l1_cache_shift();
+	unsigned long bytes = l1_cache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
 	unsigned long i;
 
-	for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES)
+	for (i = 0; i < size >> shift; i++, addr += bytes)
 		dcbst(addr);
 	mb();	/* sync */
 }
@@ -97,21 +108,17 @@
 static inline void invalidate_dcache_range(unsigned long start,
 					   unsigned long stop)
 {
-	void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1));
-	unsigned long size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1);
+	unsigned long shift = l1_cache_shift();
+	unsigned long bytes = l1_cache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
 	unsigned long i;
 
-	for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES)
+	for (i = 0; i < size >> shift; i++, addr += bytes)
 		dcbi(addr);
 	mb();	/* sync */
 }
 
-#endif /* CONFIG_PPC32 */
-#ifdef CONFIG_PPC64
-extern void flush_dcache_range(unsigned long start, unsigned long stop);
-extern void flush_inval_dcache_range(unsigned long start, unsigned long stop);
-#endif
-
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
 	do { \
 		memcpy(dst, src, len); \
diff --git a/arch/powerpc/include/asm/cell-pmu.h b/arch/powerpc/include/asm/cell-pmu.h
index b4b7338..6a79b5d 100644
--- a/arch/powerpc/include/asm/cell-pmu.h
+++ b/arch/powerpc/include/asm/cell-pmu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Cell Broadband Engine Performance Monitor
  *
@@ -6,20 +7,6 @@
  * Author:
  *   David Erb (djerb@us.ibm.com)
  *   Kevin Corry (kevcorry@us.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __ASM_CELL_PMU_H__
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index a78a57e..9cce061 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -1,17 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_CHECKSUM_H
 #define _ASM_POWERPC_CHECKSUM_H
 #ifdef __KERNEL__
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
-#ifdef CONFIG_GENERIC_CSUM
-#include <asm-generic/checksum.h>
-#else
 #include <linux/bitops.h>
 #include <linux/in6.h>
 /*
@@ -217,6 +211,5 @@
 			const struct in6_addr *daddr,
 			__u32 len, __u8 proto, __wsum sum);
 
-#endif
 #endif /* __KERNEL__ */
 #endif
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 31733a9..898b542 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_CODE_PATCHING_H
 #define _ASM_POWERPC_CODE_PATCHING_H
 
 /*
  * Copyright 2008, Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/types.h>
@@ -33,8 +29,32 @@
 int patch_branch(unsigned int *addr, unsigned long target, int flags);
 int patch_instruction(unsigned int *addr, unsigned int instr);
 int raw_patch_instruction(unsigned int *addr, unsigned int instr);
-int patch_instruction_site(s32 *addr, unsigned int instr);
-int patch_branch_site(s32 *site, unsigned long target, int flags);
+
+static inline unsigned long patch_site_addr(s32 *site)
+{
+	return (unsigned long)site + *site;
+}
+
+static inline int patch_instruction_site(s32 *site, unsigned int instr)
+{
+	return patch_instruction((unsigned int *)patch_site_addr(site), instr);
+}
+
+static inline int patch_branch_site(s32 *site, unsigned long target, int flags)
+{
+	return patch_branch((unsigned int *)patch_site_addr(site), target, flags);
+}
+
+static inline int modify_instruction(unsigned int *addr, unsigned int clr,
+				     unsigned int set)
+{
+	return patch_instruction(addr, (*addr & ~clr) | set);
+}
+
+static inline int modify_instruction_site(s32 *site, unsigned int clr, unsigned int set)
+{
+	return modify_instruction((unsigned int *)patch_site_addr(site), clr, set);
+}
 
 int instr_is_relative_branch(unsigned int instr);
 int instr_is_relative_link_branch(unsigned int instr);
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 85c8af2..74d0db5 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -8,6 +8,8 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 
+#include <asm-generic/compat.h>
+
 #define COMPAT_USER_HZ		100
 #ifdef __BIG_ENDIAN__
 #define COMPAT_UTS_MACHINE	"ppc\0\0"
@@ -15,34 +17,18 @@
 #define COMPAT_UTS_MACHINE	"ppcle\0\0"
 #endif
 
-typedef u32		compat_size_t;
-typedef s32		compat_ssize_t;
-typedef s32		compat_clock_t;
-typedef s32		compat_pid_t;
 typedef u32		__compat_uid_t;
 typedef u32		__compat_gid_t;
 typedef u32		__compat_uid32_t;
 typedef u32		__compat_gid32_t;
 typedef u32		compat_mode_t;
-typedef u32		compat_ino_t;
 typedef u32		compat_dev_t;
-typedef s32		compat_off_t;
-typedef s64		compat_loff_t;
 typedef s16		compat_nlink_t;
 typedef u16		compat_ipc_pid_t;
-typedef s32		compat_daddr_t;
 typedef u32		compat_caddr_t;
 typedef __kernel_fsid_t	compat_fsid_t;
-typedef s32		compat_key_t;
-typedef s32		compat_timer_t;
-
-typedef s32		compat_int_t;
-typedef s32		compat_long_t;
 typedef s64		compat_s64;
-typedef u32		compat_uint_t;
-typedef u32		compat_ulong_t;
 typedef u64		compat_u64;
-typedef u32		compat_uptr_t;
 
 struct compat_stat {
 	compat_dev_t	st_dev;
@@ -55,11 +41,11 @@
 	compat_off_t	st_size;
 	compat_off_t	st_blksize;
 	compat_off_t	st_blocks;
-	compat_time_t	st_atime;
+	old_time32_t	st_atime;
 	u32		st_atime_nsec;
-	compat_time_t	st_mtime;
+	old_time32_t	st_mtime;
 	u32		st_mtime_nsec;
-	compat_time_t	st_ctime;
+	old_time32_t	st_ctime;
 	u32		st_ctime_nsec;
 	u32		__unused4[2];
 };
diff --git a/arch/powerpc/include/asm/copro.h b/arch/powerpc/include/asm/copro.h
index 48616fe..fd2e166 100644
--- a/arch/powerpc/include/asm/copro.h
+++ b/arch/powerpc/include/asm/copro.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2014 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_COPRO_H
diff --git a/arch/powerpc/include/asm/cpufeature.h b/arch/powerpc/include/asm/cpufeature.h
index 19e6290..f6f790a 100644
--- a/arch/powerpc/include/asm/cpufeature.h
+++ b/arch/powerpc/include/asm/cpufeature.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * CPU feature definitions for module loading, used by
  * module_cpu_feature_match(), see asm/cputable.h for powerpc CPU features.
  *
  * Copyright 2016 Alastair D'Silva, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef __ASM_POWERPC_CPUFEATURE_H
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index 43e5f31..9844b3d 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -27,10 +27,11 @@
  * the THREAD_WINKLE_BITS are set, which indicate which threads have not
  * yet woken from the winkle state.
  */
-#define PNV_CORE_IDLE_LOCK_BIT			0x10000000
+#define NR_PNV_CORE_IDLE_LOCK_BIT		28
+#define PNV_CORE_IDLE_LOCK_BIT			(1ULL << NR_PNV_CORE_IDLE_LOCK_BIT)
 
+#define PNV_CORE_IDLE_WINKLE_COUNT_SHIFT	16
 #define PNV_CORE_IDLE_WINKLE_COUNT		0x00010000
-#define PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT	0x00080000
 #define PNV_CORE_IDLE_WINKLE_COUNT_BITS		0x000F0000
 #define PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT	8
 #define PNV_CORE_IDLE_THREAD_WINKLE_BITS	0x0000FF00
@@ -68,16 +69,6 @@
 #define ERR_DEEP_STATE_ESL_MISMATCH	-2
 
 #ifndef __ASSEMBLY__
-/* Additional SPRs that need to be saved/restored during stop */
-struct stop_sprs {
-	u64 pid;
-	u64 ldbar;
-	u64 fscr;
-	u64 hfscr;
-	u64 mmcr1;
-	u64 mmcr2;
-	u64 mmcra;
-};
 
 #define PNV_IDLE_NAME_LEN    16
 struct pnv_idle_states_t {
@@ -92,10 +83,6 @@
 
 extern struct pnv_idle_states_t *pnv_idle_states;
 extern int nr_pnv_idle_states;
-extern u32 pnv_fastsleep_workaround_at_entry[];
-extern u32 pnv_fastsleep_workaround_at_exit[];
-
-extern u64 pnv_first_deep_stop_state;
 
 unsigned long pnv_cpu_offline(unsigned int cpu);
 int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags);
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 29f49a3..cf00ff0 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -44,6 +44,7 @@
 extern int machine_check_e200(struct pt_regs *regs);
 extern int machine_check_47x(struct pt_regs *regs);
 int machine_check_8xx(struct pt_regs *regs);
+int machine_check_83xx(struct pt_regs *regs);
 
 extern void cpu_down_flush_e500v2(void);
 extern void cpu_down_flush_e500mc(void);
@@ -144,12 +145,10 @@
 
 /* Definitions for features that only exist on 32-bit chips */
 #ifdef CONFIG_PPC32
-#define CPU_FTR_601			ASM_CONST(0x00001000)
 #define CPU_FTR_L2CR			ASM_CONST(0x00002000)
 #define CPU_FTR_SPEC7450		ASM_CONST(0x00004000)
 #define CPU_FTR_TAU			ASM_CONST(0x00008000)
 #define CPU_FTR_CAN_DOZE		ASM_CONST(0x00010000)
-#define CPU_FTR_USE_RTC			ASM_CONST(0x00020000)
 #define CPU_FTR_L3CR			ASM_CONST(0x00040000)
 #define CPU_FTR_L3_DISABLE_NAP		ASM_CONST(0x00080000)
 #define CPU_FTR_NAP_DISABLE_L2_PR	ASM_CONST(0x00100000)
@@ -159,14 +158,12 @@
 #define CPU_FTR_NEED_COHERENT		ASM_CONST(0x01000000)
 #define CPU_FTR_NO_BTIC			ASM_CONST(0x02000000)
 #define CPU_FTR_PPC_LE			ASM_CONST(0x04000000)
-#define CPU_FTR_UNIFIED_ID_CACHE	ASM_CONST(0x08000000)
 #define CPU_FTR_SPE			ASM_CONST(0x10000000)
 #define CPU_FTR_NEED_PAIRED_STWCX	ASM_CONST(0x20000000)
 #define CPU_FTR_INDEXED_DCR		ASM_CONST(0x40000000)
 
 #else	/* CONFIG_PPC32 */
 /* Define these to 0 for the sake of tests in common code */
-#define CPU_FTR_601			(0)
 #define CPU_FTR_PPC_LE			(0)
 #endif
 
@@ -212,8 +209,9 @@
 #define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x0000080000000000)
 #define CPU_FTR_P9_TM_HV_ASSIST		LONG_ASM_CONST(0x0000100000000000)
 #define CPU_FTR_P9_TM_XER_SO_BUG	LONG_ASM_CONST(0x0000200000000000)
-#define CPU_FTR_P9_TLBIE_BUG		LONG_ASM_CONST(0x0000400000000000)
+#define CPU_FTR_P9_TLBIE_STQ_BUG	LONG_ASM_CONST(0x0000400000000000)
 #define CPU_FTR_P9_TIDR			LONG_ASM_CONST(0x0000800000000000)
+#define CPU_FTR_P9_TLBIE_ERAT_BUG	LONG_ASM_CONST(0x0001000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -293,10 +291,10 @@
 #define CPU_FTR_MAYBE_CAN_NAP	0
 #endif
 
-#define CPU_FTRS_PPC601	(CPU_FTR_COMMON | CPU_FTR_601 | \
-	CPU_FTR_COHERENT_ICACHE | CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_USE_RTC)
+#define CPU_FTRS_PPC601	(CPU_FTR_COMMON | \
+	CPU_FTR_COHERENT_ICACHE)
 #define CPU_FTRS_603	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \
-	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_604	(CPU_FTR_COMMON | CPU_FTR_PPC_LE)
 #define CPU_FTRS_740_NOTAU	(CPU_FTR_COMMON | \
 	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
@@ -367,15 +365,15 @@
 	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
 	    CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
 	    CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
-#define CPU_FTRS_82XX	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE)
+#define CPU_FTRS_82XX	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_G2_LE	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \
 	    CPU_FTR_MAYBE_CAN_NAP)
 #define CPU_FTRS_E300	(CPU_FTR_MAYBE_CAN_DOZE | \
 	    CPU_FTR_MAYBE_CAN_NAP | \
-	    CPU_FTR_COMMON)
+	    CPU_FTR_COMMON  | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E300C2	(CPU_FTR_MAYBE_CAN_DOZE | \
 	    CPU_FTR_MAYBE_CAN_NAP | \
-	    CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE)
+	    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_NODSISRALIGN | CPU_FTR_NOEXECUTE)
@@ -385,7 +383,7 @@
 #define CPU_FTRS_47X	(CPU_FTRS_440x6)
 #define CPU_FTRS_E200	(CPU_FTR_SPE_COMP | \
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \
-	    CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DEBUG_LVL_EXC)
 #define CPU_FTRS_E500	(CPU_FTR_MAYBE_CAN_DOZE | \
 	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
@@ -460,7 +458,7 @@
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
 	    CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \
-	    CPU_FTR_P9_TLBIE_BUG | CPU_FTR_P9_TIDR)
+	    CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR)
 #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
 #define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1)
 #define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \
@@ -497,7 +495,9 @@
 #else
 enum {
 	CPU_FTRS_POSSIBLE =
-#ifdef CONFIG_PPC_BOOK3S_32
+#ifdef CONFIG_PPC_BOOK3S_601
+	    CPU_FTRS_PPC601 |
+#elif defined(CONFIG_PPC_BOOK3S_32)
 	    CPU_FTRS_PPC601 | CPU_FTRS_603 | CPU_FTRS_604 | CPU_FTRS_740_NOTAU |
 	    CPU_FTRS_740 | CPU_FTRS_750 | CPU_FTRS_750FX1 |
 	    CPU_FTRS_750FX2 | CPU_FTRS_750FX | CPU_FTRS_750GX |
@@ -573,8 +573,10 @@
 #else
 enum {
 	CPU_FTRS_ALWAYS =
-#ifdef CONFIG_PPC_BOOK3S_32
-	    CPU_FTRS_PPC601 & CPU_FTRS_603 & CPU_FTRS_604 & CPU_FTRS_740_NOTAU &
+#ifdef CONFIG_PPC_BOOK3S_601
+	    CPU_FTRS_PPC601 &
+#elif defined(CONFIG_PPC_BOOK3S_32)
+	    CPU_FTRS_603 & CPU_FTRS_604 & CPU_FTRS_740_NOTAU &
 	    CPU_FTRS_740 & CPU_FTRS_750 & CPU_FTRS_750FX1 &
 	    CPU_FTRS_750FX2 & CPU_FTRS_750FX & CPU_FTRS_750GX &
 	    CPU_FTRS_7400_NOTAU & CPU_FTRS_7400 & CPU_FTRS_7450_20 &
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index d71a909..deb99fd 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -23,11 +23,13 @@
 extern int threads_per_core;
 extern int threads_per_subcore;
 extern int threads_shift;
+extern bool has_big_cores;
 extern cpumask_t threads_core_mask;
 #else
 #define threads_per_core	1
 #define threads_per_subcore	1
 #define threads_shift		0
+#define has_big_cores		0
 #define threads_core_mask	(*get_cpu_mask(0))
 #endif
 
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 1336727..2431b4a 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Definitions for measuring cputime on powerpc machines.
  *
  * Copyright (C) 2006 Paul Mackerras, IBM Corp.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * If we have CONFIG_VIRT_CPU_ACCOUNTING_NATIVE, we measure cpu time in
  * the same units as the timebase.  Otherwise we measure cpu time
  * in jiffies using the generic definitions.
@@ -61,7 +57,6 @@
 	struct cpu_accounting_data *acct0 = get_accounting(prev);
 
 	acct->starttime = acct0->starttime;
-	acct->startspurr = acct0->startspurr;
 }
 #endif
 
diff --git a/arch/powerpc/include/asm/current.h b/arch/powerpc/include/asm/current.h
index e2c7f06..bbfb948 100644
--- a/arch/powerpc/include/asm/current.h
+++ b/arch/powerpc/include/asm/current.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_CURRENT_H
 #define _ASM_POWERPC_CURRENT_H
 #ifdef __KERNEL__
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 struct task_struct;
@@ -19,7 +16,8 @@
 {
 	struct task_struct *task;
 
-	__asm__ __volatile__("ld %0,%1(13)"
+	/* get_current can be cached by the compiler, so no volatile */
+	asm ("ld %0,%1(13)"
 	: "=r" (task)
 	: "i" (offsetof(struct paca_struct, __current)));
 
diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index 99b84db..4ce6808 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2009 Freescale Semiconductor, Inc.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * provides masks and opcode images for use by code generation, emulation
  * and for instructions that older assemblers might not know about
  */
diff --git a/arch/powerpc/include/asm/dcr-generic.h b/arch/powerpc/include/asm/dcr-generic.h
index 35b7159..099c28d 100644
--- a/arch/powerpc/include/asm/dcr-generic.h
+++ b/arch/powerpc/include/asm/dcr-generic.h
@@ -1,20 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
  *                    <benh@kernel.crashing.org>
- *
- *   This program is free software;  you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
- *   the GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program;  if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #ifndef _ASM_POWERPC_DCR_GENERIC_H
diff --git a/arch/powerpc/include/asm/dcr-mmio.h b/arch/powerpc/include/asm/dcr-mmio.h
index 93a68b2..fc6d93e 100644
--- a/arch/powerpc/include/asm/dcr-mmio.h
+++ b/arch/powerpc/include/asm/dcr-mmio.h
@@ -1,20 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
  *                    <benh@kernel.crashing.org>
- *
- *   This program is free software;  you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
- *   the GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program;  if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #ifndef _ASM_POWERPC_DCR_MMIO_H
diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h
index 151dff5..7141cce 100644
--- a/arch/powerpc/include/asm/dcr-native.h
+++ b/arch/powerpc/include/asm/dcr-native.h
@@ -1,20 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
  *                    <benh@kernel.crashing.org>
- *
- *   This program is free software;  you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
- *   the GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program;  if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #ifndef _ASM_POWERPC_DCR_NATIVE_H
diff --git a/arch/powerpc/include/asm/dcr.h b/arch/powerpc/include/asm/dcr.h
index 9d6851c..64030e3 100644
--- a/arch/powerpc/include/asm/dcr.h
+++ b/arch/powerpc/include/asm/dcr.h
@@ -1,20 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
  *                    <benh@kernel.crashing.org>
- *
- *   This program is free software;  you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
- *   the GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program;  if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #ifndef _ASM_POWERPC_DCR_H
diff --git a/arch/powerpc/include/asm/debugfs.h b/arch/powerpc/include/asm/debugfs.h
index 4f3b39f..2c5c485 100644
--- a/arch/powerpc/include/asm/debugfs.h
+++ b/arch/powerpc/include/asm/debugfs.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_DEBUGFS_H
 #define _ASM_POWERPC_DEBUGFS_H
 
 /*
  * Copyright 2017, Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/debugfs.h>
diff --git a/arch/powerpc/include/asm/delay.h b/arch/powerpc/include/asm/delay.h
index 3df4417..66963f7 100644
--- a/arch/powerpc/include/asm/delay.h
+++ b/arch/powerpc/include/asm/delay.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_DELAY_H
 #define _ASM_POWERPC_DELAY_H
 #ifdef __KERNEL__
@@ -9,11 +10,6 @@
  * Copyright 1996, Paul Mackerras.
  * Copyright (C) 2009 Freescale Semiconductor, Inc. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * PPC64 Support added by Dave Engebretsen, Todd Inglett, Mike Corrigan,
  * Anton Blanchard.
  */
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 0245bfc..2665427 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -1,7 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
  */
 #ifndef _ASM_POWERPC_DEVICE_H
 #define _ASM_POWERPC_DEVICE_H
@@ -20,6 +19,11 @@
  */
 struct dev_archdata {
 	/*
+	 * Set to %true if the dma_iommu_ops are requested to use a direct
+	 * window instead of dynamically mapping memory.
+	 */
+	bool			iommu_bypass : 1;
+	/*
 	 * These two used to be a union. However, with the hybrid ops we need
 	 * both so here we store both a DMA offset for direct mappings and
 	 * an iommu_table for remapped DMA.
@@ -33,9 +37,6 @@
 #ifdef CONFIG_IOMMU_API
 	void			*iommu_domain;
 #endif
-#ifdef CONFIG_SWIOTLB
-	dma_addr_t		max_direct_dma_addr;
-#endif
 #ifdef CONFIG_PPC64
 	struct pci_dn		*pci_data;
 #endif
@@ -54,6 +55,4 @@
 	u64 dma_mask;
 };
 
-#define ARCH_HAS_DMA_GET_REQUIRED_MASK
-
 #endif /* _ASM_POWERPC_DEVICE_H */
diff --git a/arch/powerpc/include/asm/disassemble.h b/arch/powerpc/include/asm/disassemble.h
index c0a5505..8d2ebc3 100644
--- a/arch/powerpc/include/asm/disassemble.h
+++ b/arch/powerpc/include/asm/disassemble.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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
  *
diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h
index 7702875..a2912b4 100644
--- a/arch/powerpc/include/asm/dma-direct.h
+++ b/arch/powerpc/include/asm/dma-direct.h
@@ -4,26 +4,24 @@
 
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
-#ifdef CONFIG_SWIOTLB
-	struct dev_archdata *sd = &dev->archdata;
-
-	if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr)
-		return false;
-#endif
-
 	if (!dev->dma_mask)
 		return false;
 
-	return addr + size - 1 <= *dev->dma_mask;
+	return addr + size - 1 <=
+		min_not_zero(*dev->dma_mask, dev->bus_dma_mask);
 }
 
 static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	return paddr + get_dma_offset(dev);
+	if (!dev)
+		return paddr + PCI_DRAM_OFFSET;
+	return paddr + dev->archdata.dma_offset;
 }
 
 static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-	return daddr - get_dma_offset(dev);
+	if (!dev)
+		return daddr - PCI_DRAM_OFFSET;
+	return daddr - dev->archdata.dma_offset;
 }
 #endif /* ASM_POWERPC_DMA_DIRECT_H */
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 8fa3945..565d6f7 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -1,79 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2004 IBM
- *
- * Implements the generic device dma API for powerpc.
- * the pci and vio busses
  */
 #ifndef _ASM_DMA_MAPPING_H
 #define _ASM_DMA_MAPPING_H
-#ifdef __KERNEL__
-
-#include <linux/types.h>
-#include <linux/cache.h>
-/* need struct page definitions */
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-#include <asm/io.h>
-#include <asm/swiotlb.h>
-
-/* Some dma direct funcs must be visible for use in other dma_ops */
-extern void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
-					 dma_addr_t *dma_handle, gfp_t flag,
-					 unsigned long attrs);
-extern void __dma_nommu_free_coherent(struct device *dev, size_t size,
-				       void *vaddr, dma_addr_t dma_handle,
-				       unsigned long attrs);
-extern int dma_nommu_mmap_coherent(struct device *dev,
-				    struct vm_area_struct *vma,
-				    void *cpu_addr, dma_addr_t handle,
-				    size_t size, unsigned long attrs);
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
-/*
- * DMA-consistent mapping functions for PowerPCs that don't support
- * cache snooping.  These allocate/free a region of uncached mapped
- * memory space for use with DMA devices.  Alternatively, you could
- * allocate the space "normally" and use the cache management functions
- * to ensure it is consistent.
- */
-struct device;
-extern void *__dma_alloc_coherent(struct device *dev, size_t size,
-				  dma_addr_t *handle, gfp_t gfp);
-extern void __dma_free_coherent(size_t size, void *vaddr);
-extern void __dma_sync(void *vaddr, size_t size, int direction);
-extern void __dma_sync_page(struct page *page, unsigned long offset,
-				 size_t size, int direction);
-extern unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr);
-
-#else /* ! CONFIG_NOT_COHERENT_CACHE */
-/*
- * Cache coherent cores.
- */
-
-#define __dma_alloc_coherent(dev, gfp, size, handle)	NULL
-#define __dma_free_coherent(size, addr)		((void)0)
-#define __dma_sync(addr, size, rw)		((void)0)
-#define __dma_sync_page(pg, off, sz, rw)	((void)0)
-
-#endif /* ! CONFIG_NOT_COHERENT_CACHE */
-
-static inline unsigned long device_to_mask(struct device *dev)
-{
-	if (dev->dma_mask && *dev->dma_mask)
-		return *dev->dma_mask;
-	/* Assume devices without mask can take 32 bit addresses */
-	return 0xfffffffful;
-}
-
-/*
- * Available generic sets of operations
- */
-#ifdef CONFIG_PPC64
-extern struct dma_map_ops dma_iommu_ops;
-#endif
-extern const struct dma_map_ops dma_nommu_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
@@ -85,34 +15,4 @@
 	return NULL;
 }
 
-/*
- * get_dma_offset()
- *
- * Get the dma offset on configurations where the dma address can be determined
- * from the physical address by looking at a simple offset.  Direct dma and
- * swiotlb use this function, but it is typically not used by implementations
- * with an iommu.
- */
-static inline dma_addr_t get_dma_offset(struct device *dev)
-{
-	if (dev)
-		return dev->archdata.dma_offset;
-
-	return PCI_DRAM_OFFSET;
-}
-
-static inline void set_dma_offset(struct device *dev, dma_addr_t off)
-{
-	if (dev)
-		dev->archdata.dma_offset = off;
-}
-
-#define HAVE_ARCH_DMA_SET_MASK 1
-extern int dma_set_mask(struct device *dev, u64 dma_mask);
-
-extern u64 __dma_get_required_mask(struct device *dev);
-
-#define ARCH_HAS_DMA_MMAP_COHERENT
-
-#endif /* __KERNEL__ */
 #endif	/* _ASM_DMA_MAPPING_H */
diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h
index ce242b9..3d76e1c 100644
--- a/arch/powerpc/include/asm/drmem.h
+++ b/arch/powerpc/include/asm/drmem.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drmem.h: Power specific logical memory block representation
  *
  * Copyright 2017 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_LMB_H
@@ -17,6 +13,9 @@
 	u32     drc_index;
 	u32     aa_index;
 	u32     flags;
+#ifdef CONFIG_MEMORY_HOTPLUG
+	int	nid;
+#endif
 };
 
 struct drmem_lmb_info {
@@ -99,4 +98,27 @@
 			void (*func)(struct drmem_lmb *, const __be32 **));
 #endif
 
+static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb)
+{
+	lmb->aa_index = 0xffffffff;
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static inline void lmb_set_nid(struct drmem_lmb *lmb)
+{
+	lmb->nid = memory_add_physaddr_to_nid(lmb->base_addr);
+}
+static inline void lmb_clear_nid(struct drmem_lmb *lmb)
+{
+	lmb->nid = -1;
+}
+#else
+static inline void lmb_set_nid(struct drmem_lmb *lmb)
+{
+}
+static inline void lmb_clear_nid(struct drmem_lmb *lmb)
+{
+}
+#endif
+
 #endif /* _ASM_POWERPC_LMB_H */
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 219637e..6f9b2a1 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -1,20 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2001  Dave Engebretsen & Todd Inglett IBM Corporation.
  * Copyright 2001-2012 IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #ifndef _POWERPC_EEH_H
@@ -43,7 +30,6 @@
 #define EEH_VALID_PE_ZERO	0x10	/* PE#0 is valid		     */
 #define EEH_ENABLE_IO_FOR_LOG	0x20	/* Enable IO for log		     */
 #define EEH_EARLY_DUMP_LOG	0x40	/* Dump log immediately		     */
-#define EEH_POSTPONED_PROBE	0x80    /* Powernv may postpone device probe */
 
 /*
  * Delay for PE reset, all in ms
@@ -99,13 +85,26 @@
 	atomic_t pass_dev_cnt;		/* Count of passed through devs	*/
 	struct eeh_pe *parent;		/* Parent PE			*/
 	void *data;			/* PE auxillary data		*/
-	struct list_head child_list;	/* Link PE to the child list	*/
-	struct list_head edevs;		/* Link list of EEH devices	*/
-	struct list_head child;		/* Child PEs			*/
+	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	*/
+
+#ifdef CONFIG_STACKTRACE
+	/*
+	 * Saved stack trace. When we find a PE freeze in eeh_dev_check_failure
+	 * the stack trace is saved here so we can print it in the recovery
+	 * thread if it turns out to due to a real problem rather than
+	 * a hot-remove.
+	 *
+	 * A max of 64 entries might be overkill, but it also might not be.
+	 */
+	unsigned long stack_trace[64];
+	int trace_entries;
+#endif /* CONFIG_STACKTRACE */
 };
 
 #define eeh_pe_for_each_dev(pe, edev, tmp) \
-		list_for_each_entry_safe(edev, tmp, &pe->edevs, list)
+		list_for_each_entry_safe(edev, tmp, &pe->edevs, entry)
 
 #define eeh_for_each_pe(root, pe) \
 	for (pe = root; pe; pe = eeh_pe_next(pe, root))
@@ -135,6 +134,8 @@
 struct eeh_dev {
 	int mode;			/* EEH mode			*/
 	int class_code;			/* Class code of the device	*/
+	int bdfn;			/* bdfn of device (for cfg ops) */
+	struct pci_controller *controller;
 	int pe_config_addr;		/* PE config address		*/
 	u32 config_space[16];		/* Saved PCI config space	*/
 	int pcix_cap;			/* Saved PCIx capability	*/
@@ -142,15 +143,25 @@
 	int aer_cap;			/* Saved AER capability		*/
 	int af_cap;			/* Saved AF capability		*/
 	struct eeh_pe *pe;		/* Associated PE		*/
-	struct list_head list;		/* Form link list in the PE	*/
-	struct list_head rmv_list;	/* Record the removed edevs	*/
+	struct list_head entry;		/* Membership in eeh_pe.edevs	*/
+	struct list_head rmv_entry;	/* Membership in rmv_list	*/
 	struct pci_dn *pdn;		/* Associated PCI device node	*/
 	struct pci_dev *pdev;		/* Associated PCI device	*/
 	bool in_error;			/* Error flag for edev		*/
 	struct pci_dev *physfn;		/* Associated SRIOV PF		*/
-	struct pci_bus *bus;		/* PCI bus for partial hotplug	*/
 };
 
+/* "fmt" must be a simple literal string */
+#define EEH_EDEV_PRINT(level, edev, fmt, ...) \
+	pr_##level("PCI %04x:%02x:%02x.%x#%04x: EEH: " fmt, \
+	(edev)->controller->global_number, PCI_BUSNO((edev)->bdfn), \
+	PCI_SLOT((edev)->bdfn), PCI_FUNC((edev)->bdfn), \
+	((edev)->pe ? (edev)->pe_config_addr : 0xffff), ##__VA_ARGS__)
+#define eeh_edev_dbg(edev, fmt, ...) EEH_EDEV_PRINT(debug, (edev), fmt, ##__VA_ARGS__)
+#define eeh_edev_info(edev, fmt, ...) EEH_EDEV_PRINT(info, (edev), fmt, ##__VA_ARGS__)
+#define eeh_edev_warn(edev, fmt, ...) EEH_EDEV_PRINT(warn, (edev), fmt, ##__VA_ARGS__)
+#define eeh_edev_err(edev, fmt, ...) EEH_EDEV_PRINT(err, (edev), fmt, ##__VA_ARGS__)
+
 static inline struct pci_dn *eeh_dev_to_pdn(struct eeh_dev *edev)
 {
 	return edev ? edev->pdn : NULL;
@@ -207,9 +218,8 @@
 	void* (*probe)(struct pci_dn *pdn, void *data);
 	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_pe_addr)(struct eeh_pe *pe);
-	int (*get_state)(struct eeh_pe *pe, int *state);
+	int (*get_state)(struct eeh_pe *pe, int *delay);
 	int (*reset)(struct eeh_pe *pe, int option);
-	int (*wait_state)(struct eeh_pe *pe, int max_wait);
 	int (*get_log)(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len);
 	int (*configure_bridge)(struct eeh_pe *pe);
 	int (*err_inject)(struct eeh_pe *pe, int type, int func,
@@ -222,7 +232,8 @@
 };
 
 extern int eeh_subsystem_flags;
-extern int eeh_max_freezes;
+extern u32 eeh_max_freezes;
+extern bool eeh_debugfs_no_recover;
 extern struct eeh_ops *eeh_ops;
 extern raw_spinlock_t confirm_error_lock;
 
@@ -243,11 +254,7 @@
 
 static inline bool eeh_enabled(void)
 {
-	if (eeh_has_flag(EEH_FORCE_DISABLED) ||
-	    !eeh_has_flag(EEH_ENABLED))
-		return false;
-
-	return true;
+	return eeh_has_flag(EEH_ENABLED) && !eeh_has_flag(EEH_FORCE_DISABLED);
 }
 
 static inline void eeh_serialize_lock(unsigned long *flags)
@@ -266,10 +273,11 @@
 	== (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 }
 
-typedef void *(*eeh_edev_traverse_func)(struct eeh_dev *edev, void *flag);
+typedef void (*eeh_edev_traverse_func)(struct eeh_dev *edev, void *flag);
 typedef void *(*eeh_pe_traverse_func)(struct eeh_pe *pe, void *flag);
 void eeh_set_pe_aux_size(int size);
 int eeh_phb_pe_create(struct pci_controller *phb);
+int eeh_wait_state(struct eeh_pe *pe, int max_wait);
 struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
 struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, struct eeh_pe *root);
 struct eeh_pe *eeh_pe_get(struct pci_controller *phb,
@@ -279,34 +287,34 @@
 void eeh_pe_update_time_stamp(struct eeh_pe *pe);
 void *eeh_pe_traverse(struct eeh_pe *root,
 		      eeh_pe_traverse_func fn, void *flag);
-void *eeh_pe_dev_traverse(struct eeh_pe *root,
-			  eeh_edev_traverse_func fn, void *flag);
+void eeh_pe_dev_traverse(struct eeh_pe *root,
+			 eeh_edev_traverse_func fn, void *flag);
 void eeh_pe_restore_bars(struct eeh_pe *pe);
 const char *eeh_pe_loc_get(struct eeh_pe *pe);
 struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
 
 struct eeh_dev *eeh_dev_init(struct pci_dn *pdn);
 void eeh_dev_phb_init_dynamic(struct pci_controller *phb);
-void eeh_probe_devices(void);
+void eeh_show_enabled(void);
 int __init eeh_ops_register(struct eeh_ops *ops);
 int __exit eeh_ops_unregister(const char *name);
 int eeh_check_failure(const volatile void __iomem *token);
 int eeh_dev_check_failure(struct eeh_dev *edev);
-void eeh_addr_cache_build(void);
+void eeh_addr_cache_init(void);
 void eeh_add_device_early(struct pci_dn *);
 void eeh_add_device_tree_early(struct pci_dn *);
 void eeh_add_device_late(struct pci_dev *);
 void eeh_add_device_tree_late(struct pci_bus *);
 void eeh_add_sysfs_files(struct pci_bus *);
 void eeh_remove_device(struct pci_dev *);
-int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state);
+int eeh_unfreeze_pe(struct eeh_pe *pe);
 int eeh_pe_reset_and_recover(struct eeh_pe *pe);
 int eeh_dev_open(struct pci_dev *pdev);
 void eeh_dev_release(struct pci_dev *pdev);
 struct eeh_pe *eeh_iommu_group_to_pe(struct iommu_group *group);
 int eeh_pe_set_option(struct eeh_pe *pe, int option);
 int eeh_pe_get_state(struct eeh_pe *pe);
-int eeh_pe_reset(struct eeh_pe *pe, int option);
+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);
@@ -334,7 +342,7 @@
         return false;
 }
 
-static inline void eeh_probe_devices(void) { }
+static inline void eeh_show_enabled(void) { }
 
 static inline void *eeh_dev_init(struct pci_dn *pdn, void *data)
 {
@@ -350,7 +358,7 @@
 
 #define eeh_dev_check_failure(x) (0)
 
-static inline void eeh_addr_cache_build(void) { }
+static inline void eeh_addr_cache_init(void) { }
 
 static inline void eeh_add_device_early(struct pci_dn *pdn) { }
 
@@ -466,6 +474,9 @@
 		eeh_check_failure(addr);
 }
 
+
+void eeh_cache_debugfs_init(void);
+
 #endif /* CONFIG_PPC64 */
 #endif /* __KERNEL__ */
 #endif /* _POWERPC_EEH_H */
diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h
index 9884e87..dadde7d 100644
--- a/arch/powerpc/include/asm/eeh_event.h
+++ b/arch/powerpc/include/asm/eeh_event.h
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  *
  * Copyright (c) 2005 Linas Vepstas <linas@linas.org>
  */
@@ -33,6 +21,7 @@
 
 int eeh_event_init(void);
 int eeh_send_failure_event(struct eeh_pe *pe);
+int __eeh_send_failure_event(struct eeh_pe *pe);
 void eeh_remove_event(struct eeh_pe *pe, bool force);
 void eeh_handle_normal_event(struct eeh_pe *pe);
 void eeh_handle_special_event(void);
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 548d9a4..57c229a 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * ELF register definitions..
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_ELF_H
 #define _ASM_POWERPC_ELF_H
@@ -179,4 +175,7 @@
 	ARCH_DLINFO_CACHE_GEOMETRY;					\
 } while (0)
 
+/* Relocate the kernel image to @final_address */
+void relocate(unsigned long final_address);
+
 #endif /* _ASM_POWERPC_ELF_H */
diff --git a/arch/powerpc/include/asm/elfnote.h b/arch/powerpc/include/asm/elfnote.h
new file mode 100644
index 0000000..a201b6e
--- /dev/null
+++ b/arch/powerpc/include/asm/elfnote.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PowerPC ELF notes.
+ *
+ * Copyright 2019, IBM Corporation
+ */
+
+#ifndef __ASM_POWERPC_ELFNOTE_H__
+#define __ASM_POWERPC_ELFNOTE_H__
+
+/*
+ * These note types should live in a SHT_NOTE segment and have
+ * "PowerPC" in the name field.
+ */
+
+/*
+ * The capabilities supported/required by this kernel (bitmap).
+ *
+ * This type uses a bitmap as "desc" field. Each bit is described
+ * in arch/powerpc/kernel/note.S
+ */
+#define PPC_ELFNOTE_CAPABILITIES 1
+
+#endif /* __ASM_POWERPC_ELFNOTE_H__ */
diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h
index 651e135..800cb21 100644
--- a/arch/powerpc/include/asm/emulated_ops.h
+++ b/arch/powerpc/include/asm/emulated_ops.h
@@ -1,18 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright 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, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _ASM_POWERPC_EMULATED_OPS_H
diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h
index 555e22d..54a98ef 100644
--- a/arch/powerpc/include/asm/exception-64e.h
+++ b/arch/powerpc/include/asm/exception-64e.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  Definitions for use by exception code on Book3-E
  *
  *  Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_EXCEPTION_64E_H
 #define _ASM_POWERPC_EXCEPTION_64E_H
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index a86fedd..33f4f72 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_EXCEPTION_H
 #define _ASM_POWERPC_EXCEPTION_H
 /*
@@ -18,11 +19,6 @@
  *
  *  This file contains the low-level support and setup for the
  *  PowerPC-64 platform, including trap and interrupt dispatch.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 /*
  * The following macros define the code that appears as
@@ -34,25 +30,13 @@
  * exception handlers (including pSeries LPAR) and iSeries LPAR
  * implementations as possible.
  */
-#include <asm/head-64.h>
 #include <asm/feature-fixups.h>
 
-/* PACA save area offsets (exgen, exmc, etc) */
-#define EX_R9		0
-#define EX_R10		8
-#define EX_R11		16
-#define EX_R12		24
-#define EX_R13		32
-#define EX_DAR		40
-#define EX_DSISR	48
-#define EX_CCR		52
-#define EX_CFAR		56
-#define EX_PPR		64
+/* PACA save area size in u64 units (exgen, exmc, etc) */
 #if defined(CONFIG_RELOCATABLE)
-#define EX_CTR		72
-#define EX_SIZE		10	/* size in u64 units */
+#define EX_SIZE		10
 #else
-#define EX_SIZE		9	/* size in u64 units */
+#define EX_SIZE		9
 #endif
 
 /*
@@ -60,20 +44,7 @@
  */
 #define MAX_MCE_DEPTH	4
 
-/*
- * EX_LR is only used in EXSLB and where it does not overlap with EX_DAR
- * EX_CCR similarly with DSISR, but being 4 byte registers there is a hole
- * in the save area so it's not necessary to overlap them. Could be used
- * for future savings though if another 4 byte register was to be saved.
- */
-#define EX_LR		EX_DAR
-
-/*
- * EX_R3 is only used by the bad_stack handler. bad_stack reloads and
- * saves DAR from SPRN_DAR, and EX_DAR is not used. So EX_R3 can overlap
- * with EX_DAR.
- */
-#define EX_R3		EX_DAR
+#ifdef __ASSEMBLY__
 
 #define STF_ENTRY_BARRIER_SLOT						\
 	STF_ENTRY_BARRIER_FIXUP_SECTION;				\
@@ -156,587 +127,6 @@
 	hrfid;								\
 	b	hrfi_flush_fallback
 
-#ifdef CONFIG_RELOCATABLE
-#define __EXCEPTION_PROLOG_2_RELON(label, h)				\
-	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
-	LOAD_HANDLER(r12,label);					\
-	mtctr	r12;							\
-	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
-	li	r10,MSR_RI;						\
-	mtmsrd 	r10,1;			/* Set RI (EE=0) */		\
-	bctr;
-#else
-/* If not relocatable, we can jump directly -- and save messing with LR */
-#define __EXCEPTION_PROLOG_2_RELON(label, h)				\
-	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
-	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
-	li	r10,MSR_RI;						\
-	mtmsrd 	r10,1;			/* Set RI (EE=0) */		\
-	b	label;
-#endif
-#define EXCEPTION_PROLOG_2_RELON(label, h)				\
-	__EXCEPTION_PROLOG_2_RELON(label, h)
-
-/*
- * As EXCEPTION_PROLOG(), except we've already got relocation on so no need to
- * rfid. Save LR in case we're CONFIG_RELOCATABLE, in which case
- * EXCEPTION_PROLOG_2_RELON will be using LR.
- */
-#define EXCEPTION_RELON_PROLOG(area, label, h, extra, vec)		\
-	SET_SCRATCH0(r13);		/* save r13 */			\
-	EXCEPTION_PROLOG_0(area);					\
-	EXCEPTION_PROLOG_1(area, extra, vec);				\
-	EXCEPTION_PROLOG_2_RELON(label, h)
-
-/*
- * We're short on space and time in the exception prolog, so we can't
- * use the normal LOAD_REG_IMMEDIATE macro to load the address of label.
- * Instead we get the base of the kernel from paca->kernelbase and or in the low
- * part of label. This requires that the label be within 64KB of kernelbase, and
- * that kernelbase be 64K aligned.
- */
-#define LOAD_HANDLER(reg, label)					\
-	ld	reg,PACAKBASE(r13);	/* get high part of &label */	\
-	ori	reg,reg,FIXED_SYMBOL_ABS_ADDR(label);
-
-#define __LOAD_HANDLER(reg, label)					\
-	ld	reg,PACAKBASE(r13);					\
-	ori	reg,reg,(ABS_ADDR(label))@l;
-
-/*
- * Branches from unrelocated code (e.g., interrupts) to labels outside
- * head-y require >64K offsets.
- */
-#define __LOAD_FAR_HANDLER(reg, label)					\
-	ld	reg,PACAKBASE(r13);					\
-	ori	reg,reg,(ABS_ADDR(label))@l;				\
-	addis	reg,reg,(ABS_ADDR(label))@h;
-
-/* Exception register prefixes */
-#define EXC_HV	H
-#define EXC_STD
-
-#if defined(CONFIG_RELOCATABLE)
-/*
- * If we support interrupts with relocation on AND we're a relocatable kernel,
- * we need to use CTR to get to the 2nd level handler.  So, save/restore it
- * when required.
- */
-#define SAVE_CTR(reg, area)	mfctr	reg ; 	std	reg,area+EX_CTR(r13)
-#define GET_CTR(reg, area) 			ld	reg,area+EX_CTR(r13)
-#define RESTORE_CTR(reg, area)	ld	reg,area+EX_CTR(r13) ; mtctr reg
-#else
-/* ...else CTR is unused and in register. */
-#define SAVE_CTR(reg, area)
-#define GET_CTR(reg, area) 	mfctr	reg
-#define RESTORE_CTR(reg, area)
-#endif
-
-/*
- * PPR save/restore macros used in exceptions_64s.S  
- * Used for P7 or later processors
- */
-#define SAVE_PPR(area, ra, rb)						\
-BEGIN_FTR_SECTION_NESTED(940)						\
-	ld	ra,PACACURRENT(r13);					\
-	ld	rb,area+EX_PPR(r13);	/* Read PPR from paca */	\
-	std	rb,TASKTHREADPPR(ra);					\
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,940)
-
-#define RESTORE_PPR_PACA(area, ra)					\
-BEGIN_FTR_SECTION_NESTED(941)						\
-	ld	ra,area+EX_PPR(r13);					\
-	mtspr	SPRN_PPR,ra;						\
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941)
-
-/*
- * Get an SPR into a register if the CPU has the given feature
- */
-#define OPT_GET_SPR(ra, spr, ftr)					\
-BEGIN_FTR_SECTION_NESTED(943)						\
-	mfspr	ra,spr;							\
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
-/*
- * Set an SPR from a register if the CPU has the given feature
- */
-#define OPT_SET_SPR(ra, spr, ftr)					\
-BEGIN_FTR_SECTION_NESTED(943)						\
-	mtspr	spr,ra;							\
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
-/*
- * Save a register to the PACA if the CPU has the given feature
- */
-#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr)				\
-BEGIN_FTR_SECTION_NESTED(943)						\
-	std	ra,offset(r13);						\
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
-#define EXCEPTION_PROLOG_0(area)					\
-	GET_PACA(r13);							\
-	std	r9,area+EX_R9(r13);	/* save r9 */			\
-	OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR);			\
-	HMT_MEDIUM;							\
-	std	r10,area+EX_R10(r13);	/* save r10 - r12 */		\
-	OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
-
-#define __EXCEPTION_PROLOG_1_PRE(area)					\
-	OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR);		\
-	OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR);		\
-	INTERRUPT_TO_KERNEL;						\
-	SAVE_CTR(r10, area);						\
-	mfcr	r9;
-
-#define __EXCEPTION_PROLOG_1_POST(area)					\
-	std	r11,area+EX_R11(r13);					\
-	std	r12,area+EX_R12(r13);					\
-	GET_SCRATCH0(r10);						\
-	std	r10,area+EX_R13(r13)
-
-/*
- * This version of the EXCEPTION_PROLOG_1 will carry
- * addition parameter called "bitmask" to support
- * checking of the interrupt maskable level in the SOFTEN_TEST.
- * Intended to be used in MASKABLE_EXCPETION_* macros.
- */
-#define MASKABLE_EXCEPTION_PROLOG_1(area, extra, vec, bitmask)			\
-	__EXCEPTION_PROLOG_1_PRE(area);					\
-	extra(vec, bitmask);						\
-	__EXCEPTION_PROLOG_1_POST(area);
-
-/*
- * This version of the EXCEPTION_PROLOG_1 is intended
- * to be used in STD_EXCEPTION* macros
- */
-#define _EXCEPTION_PROLOG_1(area, extra, vec)				\
-	__EXCEPTION_PROLOG_1_PRE(area);					\
-	extra(vec);							\
-	__EXCEPTION_PROLOG_1_POST(area);
-
-#define EXCEPTION_PROLOG_1(area, extra, vec)				\
-	_EXCEPTION_PROLOG_1(area, extra, vec)
-
-#define __EXCEPTION_PROLOG_2(label, h)					\
-	ld	r10,PACAKMSR(r13);	/* get MSR value for kernel */	\
-	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
-	LOAD_HANDLER(r12,label)						\
-	mtspr	SPRN_##h##SRR0,r12;					\
-	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
-	mtspr	SPRN_##h##SRR1,r10;					\
-	h##RFI_TO_KERNEL;						\
-	b	.	/* prevent speculative execution */
-#define EXCEPTION_PROLOG_2(label, h)					\
-	__EXCEPTION_PROLOG_2(label, h)
-
-/* _NORI variant keeps MSR_RI clear */
-#define __EXCEPTION_PROLOG_2_NORI(label, h)				\
-	ld	r10,PACAKMSR(r13);	/* get MSR value for kernel */	\
-	xori	r10,r10,MSR_RI;		/* Clear MSR_RI */		\
-	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
-	LOAD_HANDLER(r12,label)						\
-	mtspr	SPRN_##h##SRR0,r12;					\
-	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
-	mtspr	SPRN_##h##SRR1,r10;					\
-	h##RFI_TO_KERNEL;						\
-	b	.	/* prevent speculative execution */
-
-#define EXCEPTION_PROLOG_2_NORI(label, h)				\
-	__EXCEPTION_PROLOG_2_NORI(label, h)
-
-#define EXCEPTION_PROLOG(area, label, h, extra, vec)			\
-	SET_SCRATCH0(r13);		/* save r13 */			\
-	EXCEPTION_PROLOG_0(area);					\
-	EXCEPTION_PROLOG_1(area, extra, vec);				\
-	EXCEPTION_PROLOG_2(label, h);
-
-#define __KVMTEST(h, n)							\
-	lbz	r10,HSTATE_IN_GUEST(r13);				\
-	cmpwi	r10,0;							\
-	bne	do_kvm_##h##n
-
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-/*
- * If hv is possible, interrupts come into to the hv version
- * of the kvmppc_interrupt code, which then jumps to the PR handler,
- * kvmppc_interrupt_pr, if the guest is a PR guest.
- */
-#define kvmppc_interrupt kvmppc_interrupt_hv
-#else
-#define kvmppc_interrupt kvmppc_interrupt_pr
-#endif
-
-/*
- * Branch to label using its 0xC000 address. This results in instruction
- * address suitable for MSR[IR]=0 or 1, which allows relocation to be turned
- * on using mtmsr rather than rfid.
- *
- * This could set the 0xc bits for !RELOCATABLE as an immediate, rather than
- * load KBASE for a slight optimisation.
- */
-#define BRANCH_TO_C000(reg, label)					\
-	__LOAD_HANDLER(reg, label);					\
-	mtctr	reg;							\
-	bctr
-
-#ifdef CONFIG_RELOCATABLE
-#define BRANCH_TO_COMMON(reg, label)					\
-	__LOAD_HANDLER(reg, label);					\
-	mtctr	reg;							\
-	bctr
-
-#define BRANCH_LINK_TO_FAR(label)					\
-	__LOAD_FAR_HANDLER(r12, label);					\
-	mtctr	r12;							\
-	bctrl
-
-/*
- * KVM requires __LOAD_FAR_HANDLER.
- *
- * __BRANCH_TO_KVM_EXIT branches are also a special case because they
- * explicitly use r9 then reload it from PACA before branching. Hence
- * the double-underscore.
- */
-#define __BRANCH_TO_KVM_EXIT(area, label)				\
-	mfctr	r9;							\
-	std	r9,HSTATE_SCRATCH1(r13);				\
-	__LOAD_FAR_HANDLER(r9, label);					\
-	mtctr	r9;							\
-	ld	r9,area+EX_R9(r13);					\
-	bctr
-
-#else
-#define BRANCH_TO_COMMON(reg, label)					\
-	b	label
-
-#define BRANCH_LINK_TO_FAR(label)					\
-	bl	label
-
-#define __BRANCH_TO_KVM_EXIT(area, label)				\
-	ld	r9,area+EX_R9(r13);					\
-	b	label
-
-#endif
-
-/* Do not enable RI */
-#define EXCEPTION_PROLOG_NORI(area, label, h, extra, vec)		\
-	EXCEPTION_PROLOG_0(area);					\
-	EXCEPTION_PROLOG_1(area, extra, vec);				\
-	EXCEPTION_PROLOG_2_NORI(label, h);
-
-
-#define __KVM_HANDLER(area, h, n)					\
-	BEGIN_FTR_SECTION_NESTED(947)					\
-	ld	r10,area+EX_CFAR(r13);					\
-	std	r10,HSTATE_CFAR(r13);					\
-	END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947);		\
-	BEGIN_FTR_SECTION_NESTED(948)					\
-	ld	r10,area+EX_PPR(r13);					\
-	std	r10,HSTATE_PPR(r13);					\
-	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
-	ld	r10,area+EX_R10(r13);					\
-	std	r12,HSTATE_SCRATCH0(r13);				\
-	sldi	r12,r9,32;						\
-	ori	r12,r12,(n);						\
-	/* This reloads r9 before branching to kvmppc_interrupt */	\
-	__BRANCH_TO_KVM_EXIT(area, kvmppc_interrupt)
-
-#define __KVM_HANDLER_SKIP(area, h, n)					\
-	cmpwi	r10,KVM_GUEST_MODE_SKIP;				\
-	beq	89f;							\
-	BEGIN_FTR_SECTION_NESTED(948)					\
-	ld	r10,area+EX_PPR(r13);					\
-	std	r10,HSTATE_PPR(r13);					\
-	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
-	ld	r10,area+EX_R10(r13);					\
-	std	r12,HSTATE_SCRATCH0(r13);				\
-	sldi	r12,r9,32;						\
-	ori	r12,r12,(n);						\
-	/* This reloads r9 before branching to kvmppc_interrupt */	\
-	__BRANCH_TO_KVM_EXIT(area, kvmppc_interrupt);			\
-89:	mtocrf	0x80,r9;						\
-	ld	r9,area+EX_R9(r13);					\
-	ld	r10,area+EX_R10(r13);					\
-	b	kvmppc_skip_##h##interrupt
-
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#define KVMTEST(h, n)			__KVMTEST(h, n)
-#define KVM_HANDLER(area, h, n)		__KVM_HANDLER(area, h, n)
-#define KVM_HANDLER_SKIP(area, h, n)	__KVM_HANDLER_SKIP(area, h, n)
-
-#else
-#define KVMTEST(h, n)
-#define KVM_HANDLER(area, h, n)
-#define KVM_HANDLER_SKIP(area, h, n)
-#endif
-
-#define NOTEST(n)
-
-#define EXCEPTION_PROLOG_COMMON_1()					   \
-	std	r9,_CCR(r1);		/* save CR in stackframe	*/ \
-	std	r11,_NIP(r1);		/* save SRR0 in stackframe	*/ \
-	std	r12,_MSR(r1);		/* save SRR1 in stackframe	*/ \
-	std	r10,0(r1);		/* make stack chain pointer	*/ \
-	std	r0,GPR0(r1);		/* save r0 in stackframe	*/ \
-	std	r10,GPR1(r1);		/* save r1 in stackframe	*/ \
-
-
-/*
- * The common exception prolog is used for all except a few exceptions
- * such as a segment miss on a kernel address.  We have to be prepared
- * to take another exception from the point where we first touch the
- * kernel stack onwards.
- *
- * On entry r13 points to the paca, r9-r13 are saved in the paca,
- * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
- * SRR1, and relocation is on.
- */
-#define EXCEPTION_PROLOG_COMMON(n, area)				   \
-	andi.	r10,r12,MSR_PR;		/* See if coming from user	*/ \
-	mr	r10,r1;			/* Save r1			*/ \
-	subi	r1,r1,INT_FRAME_SIZE;	/* alloc frame on kernel stack	*/ \
-	beq-	1f;							   \
-	ld	r1,PACAKSAVE(r13);	/* kernel stack to use		*/ \
-1:	cmpdi	cr1,r1,-INT_FRAME_SIZE;	/* check if r1 is in userspace	*/ \
-	blt+	cr1,3f;			/* abort if it is		*/ \
-	li	r1,(n);			/* will be reloaded later	*/ \
-	sth	r1,PACA_TRAP_SAVE(r13);					   \
-	std	r3,area+EX_R3(r13);					   \
-	addi	r3,r13,area;		/* r3 -> where regs are saved*/	   \
-	RESTORE_CTR(r1, area);						   \
-	b	bad_stack;						   \
-3:	EXCEPTION_PROLOG_COMMON_1();					   \
-	beq	4f;			/* if from kernel mode		*/ \
-	ACCOUNT_CPU_USER_ENTRY(r13, r9, r10);				   \
-	SAVE_PPR(area, r9, r10);					   \
-4:	EXCEPTION_PROLOG_COMMON_2(area)					   \
-	EXCEPTION_PROLOG_COMMON_3(n)					   \
-	ACCOUNT_STOLEN_TIME
-
-/* Save original regs values from save area to stack frame. */
-#define EXCEPTION_PROLOG_COMMON_2(area)					   \
-	ld	r9,area+EX_R9(r13);	/* move r9, r10 to stackframe	*/ \
-	ld	r10,area+EX_R10(r13);					   \
-	std	r9,GPR9(r1);						   \
-	std	r10,GPR10(r1);						   \
-	ld	r9,area+EX_R11(r13);	/* move r11 - r13 to stackframe	*/ \
-	ld	r10,area+EX_R12(r13);					   \
-	ld	r11,area+EX_R13(r13);					   \
-	std	r9,GPR11(r1);						   \
-	std	r10,GPR12(r1);						   \
-	std	r11,GPR13(r1);						   \
-	BEGIN_FTR_SECTION_NESTED(66);					   \
-	ld	r10,area+EX_CFAR(r13);					   \
-	std	r10,ORIG_GPR3(r1);					   \
-	END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66);		   \
-	GET_CTR(r10, area);						   \
-	std	r10,_CTR(r1);
-
-#define EXCEPTION_PROLOG_COMMON_3(n)					   \
-	std	r2,GPR2(r1);		/* save r2 in stackframe	*/ \
-	SAVE_4GPRS(3, r1);		/* save r3 - r6 in stackframe   */ \
-	SAVE_2GPRS(7, r1);		/* save r7, r8 in stackframe	*/ \
-	mflr	r9;			/* Get LR, later save to stack	*/ \
-	ld	r2,PACATOC(r13);	/* get kernel TOC into r2	*/ \
-	std	r9,_LINK(r1);						   \
-	lbz	r10,PACAIRQSOFTMASK(r13);				   \
-	mfspr	r11,SPRN_XER;		/* save XER in stackframe	*/ \
-	std	r10,SOFTE(r1);						   \
-	std	r11,_XER(r1);						   \
-	li	r9,(n)+1;						   \
-	std	r9,_TRAP(r1);		/* set trap number		*/ \
-	li	r10,0;							   \
-	ld	r11,exception_marker@toc(r2);				   \
-	std	r10,RESULT(r1);		/* clear regs->result		*/ \
-	std	r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame	*/
-
-/*
- * Exception vectors.
- */
-#define STD_EXCEPTION(vec, label)				\
-	EXCEPTION_PROLOG(PACA_EXGEN, label, EXC_STD, KVMTEST_PR, vec);
-
-/* Version of above for when we have to branch out-of-line */
-#define __OOL_EXCEPTION(vec, label, hdlr)			\
-	SET_SCRATCH0(r13)					\
-	EXCEPTION_PROLOG_0(PACA_EXGEN)				\
-	b hdlr;
-
-#define STD_EXCEPTION_OOL(vec, label)				\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec);	\
-	EXCEPTION_PROLOG_2(label, EXC_STD)
-
-#define STD_EXCEPTION_HV(loc, vec, label)			\
-	EXCEPTION_PROLOG(PACA_EXGEN, label, EXC_HV, KVMTEST_HV, vec);
-
-#define STD_EXCEPTION_HV_OOL(vec, label)			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, vec);	\
-	EXCEPTION_PROLOG_2(label, EXC_HV)
-
-#define STD_RELON_EXCEPTION(loc, vec, label)		\
-	/* No guest interrupts come through here */	\
-	EXCEPTION_RELON_PROLOG(PACA_EXGEN, label, EXC_STD, NOTEST, vec);
-
-#define STD_RELON_EXCEPTION_OOL(vec, label)			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec);		\
-	EXCEPTION_PROLOG_2_RELON(label, EXC_STD)
-
-#define STD_RELON_EXCEPTION_HV(loc, vec, label)		\
-	EXCEPTION_RELON_PROLOG(PACA_EXGEN, label, EXC_HV, KVMTEST_HV, vec);
-
-#define STD_RELON_EXCEPTION_HV_OOL(vec, label)			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, vec);	\
-	EXCEPTION_PROLOG_2_RELON(label, EXC_HV)
-
-/* This associate vector numbers with bits in paca->irq_happened */
-#define SOFTEN_VALUE_0x500	PACA_IRQ_EE
-#define SOFTEN_VALUE_0x900	PACA_IRQ_DEC
-#define SOFTEN_VALUE_0x980	PACA_IRQ_DEC
-#define SOFTEN_VALUE_0xa00	PACA_IRQ_DBELL
-#define SOFTEN_VALUE_0xe80	PACA_IRQ_DBELL
-#define SOFTEN_VALUE_0xe60	PACA_IRQ_HMI
-#define SOFTEN_VALUE_0xea0	PACA_IRQ_EE
-#define SOFTEN_VALUE_0xf00	PACA_IRQ_PMI
-
-#define __SOFTEN_TEST(h, vec, bitmask)					\
-	lbz	r10,PACAIRQSOFTMASK(r13);				\
-	andi.	r10,r10,bitmask;					\
-	li	r10,SOFTEN_VALUE_##vec;					\
-	bne	masked_##h##interrupt
-
-#define _SOFTEN_TEST(h, vec, bitmask)	__SOFTEN_TEST(h, vec, bitmask)
-
-#define SOFTEN_TEST_PR(vec, bitmask)					\
-	KVMTEST(EXC_STD, vec);						\
-	_SOFTEN_TEST(EXC_STD, vec, bitmask)
-
-#define SOFTEN_TEST_HV(vec, bitmask)					\
-	KVMTEST(EXC_HV, vec);						\
-	_SOFTEN_TEST(EXC_HV, vec, bitmask)
-
-#define KVMTEST_PR(vec)							\
-	KVMTEST(EXC_STD, vec)
-
-#define KVMTEST_HV(vec)							\
-	KVMTEST(EXC_HV, vec)
-
-#define SOFTEN_NOTEST_PR(vec, bitmask)	_SOFTEN_TEST(EXC_STD, vec, bitmask)
-#define SOFTEN_NOTEST_HV(vec, bitmask)	_SOFTEN_TEST(EXC_HV, vec, bitmask)
-
-#define __MASKABLE_EXCEPTION(vec, label, h, extra, bitmask)		\
-	SET_SCRATCH0(r13);    /* save r13 */				\
-	EXCEPTION_PROLOG_0(PACA_EXGEN);					\
-	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask);	\
-	EXCEPTION_PROLOG_2(label, h);
-
-#define MASKABLE_EXCEPTION(vec, label, bitmask)				\
-	__MASKABLE_EXCEPTION(vec, label, EXC_STD, SOFTEN_TEST_PR, bitmask)
-
-#define MASKABLE_EXCEPTION_OOL(vec, label, bitmask)			\
-	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_PR, vec, bitmask);\
-	EXCEPTION_PROLOG_2(label, EXC_STD)
-
-#define MASKABLE_EXCEPTION_HV(vec, label, bitmask)			\
-	__MASKABLE_EXCEPTION(vec, label, EXC_HV, SOFTEN_TEST_HV, bitmask)
-
-#define MASKABLE_EXCEPTION_HV_OOL(vec, label, bitmask)			\
-	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\
-	EXCEPTION_PROLOG_2(label, EXC_HV)
-
-#define __MASKABLE_RELON_EXCEPTION(vec, label, h, extra, bitmask)	\
-	SET_SCRATCH0(r13);    /* save r13 */				\
-	EXCEPTION_PROLOG_0(PACA_EXGEN);					\
-	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask);	\
-	EXCEPTION_PROLOG_2_RELON(label, h)
-
-#define MASKABLE_RELON_EXCEPTION(vec, label, bitmask)			\
-	__MASKABLE_RELON_EXCEPTION(vec, label, EXC_STD, SOFTEN_NOTEST_PR, bitmask)
-
-#define MASKABLE_RELON_EXCEPTION_OOL(vec, label, bitmask)		\
-	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_PR, vec, bitmask);\
-	EXCEPTION_PROLOG_2(label, EXC_STD);
-
-#define MASKABLE_RELON_EXCEPTION_HV(vec, label, bitmask)		\
-	__MASKABLE_RELON_EXCEPTION(vec, label, EXC_HV, SOFTEN_TEST_HV, bitmask)
-
-#define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask)		\
-	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\
-	EXCEPTION_PROLOG_2_RELON(label, EXC_HV)
-
-/*
- * Our exception common code can be passed various "additions"
- * to specify the behaviour of interrupts, whether to kick the
- * runlatch, etc...
- */
-
-/*
- * This addition reconciles our actual IRQ state with the various software
- * flags that track it. This may call C code.
- */
-#define ADD_RECONCILE	RECONCILE_IRQ_STATE(r10,r11)
-
-#define ADD_NVGPRS				\
-	bl	save_nvgprs
-
-#define RUNLATCH_ON				\
-BEGIN_FTR_SECTION				\
-	CURRENT_THREAD_INFO(r3, r1);		\
-	ld	r4,TI_LOCAL_FLAGS(r3);		\
-	andi.	r0,r4,_TLF_RUNLATCH;		\
-	beql	ppc64_runlatch_on_trampoline;	\
-END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
-
-#define EXCEPTION_COMMON(area, trap, label, hdlr, ret, additions) \
-	EXCEPTION_PROLOG_COMMON(trap, area);			\
-	/* Volatile regs are potentially clobbered here */	\
-	additions;						\
-	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
-	bl	hdlr;						\
-	b	ret
-
-/*
- * Exception where stack is already set in r1, r1 is saved in r10, and it
- * continues rather than returns.
- */
-#define EXCEPTION_COMMON_NORET_STACK(area, trap, label, hdlr, additions) \
-	EXCEPTION_PROLOG_COMMON_1();				\
-	EXCEPTION_PROLOG_COMMON_2(area);			\
-	EXCEPTION_PROLOG_COMMON_3(trap);			\
-	/* Volatile regs are potentially clobbered here */	\
-	additions;						\
-	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
-	bl	hdlr
-
-#define STD_EXCEPTION_COMMON(trap, label, hdlr)			\
-	EXCEPTION_COMMON(PACA_EXGEN, trap, label, hdlr,		\
-		ret_from_except, ADD_NVGPRS;ADD_RECONCILE)
-
-/*
- * Like STD_EXCEPTION_COMMON, but for exceptions that can occur
- * in the idle task and therefore need the special idle handling
- * (finish nap and runlatch)
- */
-#define STD_EXCEPTION_COMMON_ASYNC(trap, label, hdlr)		\
-	EXCEPTION_COMMON(PACA_EXGEN, trap, label, hdlr,		\
-		ret_from_except_lite, FINISH_NAP;ADD_RECONCILE;RUNLATCH_ON)
-
-/*
- * When the idle code in power4_idle puts the CPU into NAP mode,
- * it has to do so in a loop, and relies on the external interrupt
- * and decrementer interrupt entry code to get it out of the loop.
- * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags
- * to signal that it is in the loop and needs help to get out.
- */
-#ifdef CONFIG_PPC_970_NAP
-#define FINISH_NAP				\
-BEGIN_FTR_SECTION				\
-	CURRENT_THREAD_INFO(r11, r1);		\
-	ld	r9,TI_LOCAL_FLAGS(r11);		\
-	andi.	r10,r9,_TLF_NAPPING;		\
-	bnel	power4_fixup_nap;		\
-END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
-#else
-#define FINISH_NAP
-#endif
+#endif /* __ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_EXCEPTION_H */
diff --git a/arch/powerpc/include/asm/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h
new file mode 100644
index 0000000..c814a2b
--- /dev/null
+++ b/arch/powerpc/include/asm/fadump-internal.h
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Firmware-Assisted Dump internal code.
+ *
+ * Copyright 2011, Mahesh Salgaonkar, IBM Corporation.
+ * Copyright 2019, Hari Bathini, IBM Corporation.
+ */
+
+#ifndef _ASM_POWERPC_FADUMP_INTERNAL_H
+#define _ASM_POWERPC_FADUMP_INTERNAL_H
+
+/* Maximum number of memory regions kernel supports */
+#define FADUMP_MAX_MEM_REGS			128
+
+#ifndef CONFIG_PRESERVE_FA_DUMP
+
+/* The upper limit percentage for user specified boot memory size (25%) */
+#define MAX_BOOT_MEM_RATIO			4
+
+#define memblock_num_regions(memblock_type)	(memblock.memblock_type.cnt)
+
+/* Alignment per CMA requirement. */
+#define FADUMP_CMA_ALIGNMENT	(PAGE_SIZE <<				\
+				 max_t(unsigned long, MAX_ORDER - 1,	\
+				 pageblock_order))
+
+/* FAD commands */
+#define FADUMP_REGISTER			1
+#define FADUMP_UNREGISTER		2
+#define FADUMP_INVALIDATE		3
+
+/*
+ * Copy the ascii values for first 8 characters from a string into u64
+ * variable at their respective indexes.
+ * e.g.
+ *  The string "FADMPINF" will be converted into 0x4641444d50494e46
+ */
+static inline u64 fadump_str_to_u64(const char *str)
+{
+	u64 val = 0;
+	int i;
+
+	for (i = 0; i < sizeof(val); i++)
+		val = (*str) ? (val << 8) | *str++ : val << 8;
+	return val;
+}
+
+#define FADUMP_CPU_UNKNOWN		(~((u32)0))
+
+#define FADUMP_CRASH_INFO_MAGIC		fadump_str_to_u64("FADMPINF")
+
+/* fadump crash info structure */
+struct fadump_crash_info_header {
+	u64		magic_number;
+	u64		elfcorehdr_addr;
+	u32		crashing_cpu;
+	struct pt_regs	regs;
+	struct cpumask	online_mask;
+};
+
+struct fadump_memory_range {
+	u64	base;
+	u64	size;
+};
+
+/* fadump memory ranges info */
+struct fadump_mrange_info {
+	char				name[16];
+	struct fadump_memory_range	*mem_ranges;
+	u32				mem_ranges_sz;
+	u32				mem_range_cnt;
+	u32				max_mem_ranges;
+};
+
+/* Platform specific callback functions */
+struct fadump_ops;
+
+/* Firmware-assisted dump configuration details. */
+struct fw_dump {
+	unsigned long	reserve_dump_area_start;
+	unsigned long	reserve_dump_area_size;
+	/* cmd line option during boot */
+	unsigned long	reserve_bootvar;
+
+	unsigned long	cpu_state_data_size;
+	u64		cpu_state_dest_vaddr;
+	u32		cpu_state_data_version;
+	u32		cpu_state_entry_size;
+
+	unsigned long	hpte_region_size;
+
+	unsigned long	boot_memory_size;
+	u64		boot_mem_dest_addr;
+	u64		boot_mem_addr[FADUMP_MAX_MEM_REGS];
+	u64		boot_mem_sz[FADUMP_MAX_MEM_REGS];
+	u64		boot_mem_top;
+	u64		boot_mem_regs_cnt;
+
+	unsigned long	fadumphdr_addr;
+	unsigned long	cpu_notes_buf_vaddr;
+	unsigned long	cpu_notes_buf_size;
+
+	/*
+	 * Maximum size supported by firmware to copy from source to
+	 * destination address per entry.
+	 */
+	u64		max_copy_size;
+	u64		kernel_metadata;
+
+	int		ibm_configure_kernel_dump;
+
+	unsigned long	fadump_enabled:1;
+	unsigned long	fadump_supported:1;
+	unsigned long	dump_active:1;
+	unsigned long	dump_registered:1;
+	unsigned long	nocma:1;
+
+	struct fadump_ops	*ops;
+};
+
+struct fadump_ops {
+	u64	(*fadump_init_mem_struct)(struct fw_dump *fadump_conf);
+	u64	(*fadump_get_metadata_size)(void);
+	int	(*fadump_setup_metadata)(struct fw_dump *fadump_conf);
+	u64	(*fadump_get_bootmem_min)(void);
+	int	(*fadump_register)(struct fw_dump *fadump_conf);
+	int	(*fadump_unregister)(struct fw_dump *fadump_conf);
+	int	(*fadump_invalidate)(struct fw_dump *fadump_conf);
+	void	(*fadump_cleanup)(struct fw_dump *fadump_conf);
+	int	(*fadump_process)(struct fw_dump *fadump_conf);
+	void	(*fadump_region_show)(struct fw_dump *fadump_conf,
+				      struct seq_file *m);
+	void	(*fadump_trigger)(struct fadump_crash_info_header *fdh,
+				  const char *msg);
+};
+
+/* Helper functions */
+s32 fadump_setup_cpu_notes_buf(u32 num_cpus);
+void fadump_free_cpu_notes_buf(void);
+u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs);
+void 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 */
+
+/* Firmware-assisted dump configuration details. */
+struct fw_dump {
+	u64	boot_mem_top;
+	u64	dump_active;
+};
+
+#endif /* CONFIG_PRESERVE_FA_DUMP */
+
+#ifdef CONFIG_PPC_PSERIES
+extern void rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node);
+#else
+static inline void
+rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) { }
+#endif
+
+#ifdef CONFIG_PPC_POWERNV
+extern void opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node);
+#else
+static inline void
+opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) { }
+#endif
+
+#endif /* _ASM_POWERPC_FADUMP_INTERNAL_H */
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 1e7a335..526a6a6 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -1,209 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Firmware Assisted dump header file.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright 2011 IBM Corporation
  * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
  */
 
-#ifndef __PPC64_FA_DUMP_H__
-#define __PPC64_FA_DUMP_H__
+#ifndef _ASM_POWERPC_FADUMP_H
+#define _ASM_POWERPC_FADUMP_H
 
 #ifdef CONFIG_FA_DUMP
 
-/*
- * The RMA region will be saved for later dumping when kernel crashes.
- * RMA is Real Mode Area, the first block of logical memory address owned
- * by logical partition, containing the storage that may be accessed with
- * translate off.
- */
-#define RMA_START	0x0
-#define RMA_END		(ppc64_rma_size)
-
-/*
- * On some Power systems where RMO is 128MB, it still requires minimum of
- * 256MB for kernel to boot successfully. When kdump infrastructure is
- * configured to save vmcore over network, we run into OOM issue while
- * loading modules related to network setup. Hence we need aditional 64M
- * of memory to avoid OOM issue.
- */
-#define MIN_BOOT_MEM	(((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
-			+ (0x1UL << 26))
-
-/* The upper limit percentage for user specified boot memory size (25%) */
-#define MAX_BOOT_MEM_RATIO			4
-
-#define memblock_num_regions(memblock_type)	(memblock.memblock_type.cnt)
-
-/* Firmware provided dump sections */
-#define FADUMP_CPU_STATE_DATA	0x0001
-#define FADUMP_HPTE_REGION	0x0002
-#define FADUMP_REAL_MODE_REGION	0x0011
-
-/* Dump request flag */
-#define FADUMP_REQUEST_FLAG	0x00000001
-
-/* FAD commands */
-#define FADUMP_REGISTER		1
-#define FADUMP_UNREGISTER	2
-#define FADUMP_INVALIDATE	3
-
-/* Dump status flag */
-#define FADUMP_ERROR_FLAG	0x2000
-
-#define FADUMP_CPU_ID_MASK	((1UL << 32) - 1)
-
-#define CPU_UNKNOWN		(~((u32)0))
-
-/* Utility macros */
-#define SKIP_TO_NEXT_CPU(reg_entry)					\
-({									\
-	while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND"))	\
-		reg_entry++;						\
-	reg_entry++;							\
-})
-
 extern int crashing_cpu;
 
-/* Kernel Dump section info */
-struct fadump_section {
-	__be32	request_flag;
-	__be16	source_data_type;
-	__be16	error_flags;
-	__be64	source_address;
-	__be64	source_len;
-	__be64	bytes_dumped;
-	__be64	destination_address;
-};
-
-/* ibm,configure-kernel-dump header. */
-struct fadump_section_header {
-	__be32	dump_format_version;
-	__be16	dump_num_sections;
-	__be16	dump_status_flag;
-	__be32	offset_first_dump_section;
-
-	/* Fields for disk dump option. */
-	__be32	dd_block_size;
-	__be64	dd_block_offset;
-	__be64	dd_num_blocks;
-	__be32	dd_offset_disk_path;
-
-	/* Maximum time allowed to prevent an automatic dump-reboot. */
-	__be32	max_time_auto;
-};
-
-/*
- * 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.
- */
-struct fadump_mem_struct {
-	struct fadump_section_header	header;
-
-	/* Kernel dump sections */
-	struct fadump_section		cpu_state_data;
-	struct fadump_section		hpte_region;
-	struct fadump_section		rmr_region;
-};
-
-/* Firmware-assisted dump configuration details. */
-struct fw_dump {
-	unsigned long	cpu_state_data_size;
-	unsigned long	hpte_region_size;
-	unsigned long	boot_memory_size;
-	unsigned long	reserve_dump_area_start;
-	unsigned long	reserve_dump_area_size;
-	/* cmd line option during boot */
-	unsigned long	reserve_bootvar;
-
-	unsigned long	fadumphdr_addr;
-	unsigned long	cpu_notes_buf;
-	unsigned long	cpu_notes_buf_size;
-
-	int		ibm_configure_kernel_dump;
-
-	unsigned long	fadump_enabled:1;
-	unsigned long	fadump_supported:1;
-	unsigned long	dump_active:1;
-	unsigned long	dump_registered:1;
-};
-
-/*
- * Copy the ascii values for first 8 characters from a string into u64
- * variable at their respective indexes.
- * e.g.
- *  The string "FADMPINF" will be converted into 0x4641444d50494e46
- */
-static inline u64 str_to_u64(const char *str)
-{
-	u64 val = 0;
-	int i;
-
-	for (i = 0; i < sizeof(val); i++)
-		val = (*str) ? (val << 8) | *str++ : val << 8;
-	return val;
-}
-#define STR_TO_HEX(x)	str_to_u64(x)
-#define REG_ID(x)	str_to_u64(x)
-
-#define FADUMP_CRASH_INFO_MAGIC		STR_TO_HEX("FADMPINF")
-#define REGSAVE_AREA_MAGIC		STR_TO_HEX("REGSAVE")
-
-/* The firmware-assisted dump format.
- *
- * The register save area is an area in the partition's memory used to preserve
- * the register contents (CPU state data) for the active CPUs during a firmware
- * assisted dump. The dump format contains register save area header followed
- * by register entries. Each list of registers for a CPU starts with
- * "CPUSTRT" and ends with "CPUEND".
- */
-
-/* Register save area header. */
-struct fadump_reg_save_area_header {
-	__be64		magic_number;
-	__be32		version;
-	__be32		num_cpu_offset;
-};
-
-/* Register entry. */
-struct fadump_reg_entry {
-	__be64		reg_id;
-	__be64		reg_value;
-};
-
-/* fadump crash info structure */
-struct fadump_crash_info_header {
-	u64		magic_number;
-	u64		elfcorehdr_addr;
-	u32		crashing_cpu;
-	struct pt_regs	regs;
-	struct cpumask	online_mask;
-};
-
-struct fad_crash_memory_ranges {
-	unsigned long long	base;
-	unsigned long long	size;
-};
-
-extern int is_fadump_boot_memory_area(u64 addr, ulong size);
-extern int early_init_dt_scan_fw_dump(unsigned long node,
-		const char *uname, int depth, void *data);
-extern int fadump_reserve_mem(void);
+extern int is_fadump_memory_area(u64 addr, ulong size);
 extern int setup_fadump(void);
 extern int is_fadump_active(void);
 extern int should_fadump_crash(void);
@@ -214,5 +24,12 @@
 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) { }
+#endif /* !CONFIG_FA_DUMP */
+
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
+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
-#endif
+#endif /* _ASM_POWERPC_FADUMP_H */
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 33b6f9c..b0af97a 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef __ASM_POWERPC_FEATURE_FIXUPS_H
 #define __ASM_POWERPC_FEATURE_FIXUPS_H
 
 #include <asm/asm-const.h>
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /*
@@ -100,6 +97,9 @@
 #define END_MMU_FTR_SECTION(msk, val)		\
 	END_MMU_FTR_SECTION_NESTED(msk, val, 97)
 
+#define END_MMU_FTR_SECTION_NESTED_IFSET(msk, label)	\
+	END_MMU_FTR_SECTION_NESTED((msk), (msk), label)
+
 #define END_MMU_FTR_SECTION_IFSET(msk)	END_MMU_FTR_SECTION((msk), (msk))
 #define END_MMU_FTR_SECTION_IFCLR(msk)	END_MMU_FTR_SECTION((msk), 0)
 
@@ -221,6 +221,17 @@
 	FTR_ENTRY_OFFSET 953b-954b;			\
 	.popsection;
 
+#define START_BTB_FLUSH_SECTION			\
+955:							\
+
+#define END_BTB_FLUSH_SECTION			\
+956:							\
+	.pushsection __btb_flush_fixup,"a";	\
+	.align 2;							\
+957:						\
+	FTR_ENTRY_OFFSET 955b-957b;			\
+	FTR_ENTRY_OFFSET 956b-957b;			\
+	.popsection;
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
@@ -230,6 +241,7 @@
 extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
 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;
 
 void apply_feature_fixups(void);
 void setup_feature_keys(void);
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 7a051bd..b3e214a 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
  *
  *  Modifications for ppc64:
  *      Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 #ifndef __ASM_POWERPC_FIRMWARE_H
 #define __ASM_POWERPC_FIRMWARE_H
@@ -52,6 +48,9 @@
 #define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
 #define FW_FEATURE_DRMEM_V2	ASM_CONST(0x0000000400000000)
 #define FW_FEATURE_DRC_INFO	ASM_CONST(0x0000000800000000)
+#define FW_FEATURE_BLOCK_REMOVE ASM_CONST(0x0000001000000000)
+#define FW_FEATURE_PAPR_SCM 	ASM_CONST(0x0000002000000000)
+#define FW_FEATURE_ULTRAVISOR	ASM_CONST(0x0000004000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -69,9 +68,10 @@
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
 		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN |
 		FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 |
-		FW_FEATURE_DRC_INFO,
+		FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE |
+		FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
-	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL,
+	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR,
 	FW_FEATURE_POWERNV_ALWAYS = 0,
 	FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
 	FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index 41cc15c..0cfc365 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -22,7 +22,12 @@
 #include <asm/kmap_types.h>
 #endif
 
+#ifdef CONFIG_KASAN
+#include <asm/kasan.h>
+#define FIXADDR_TOP	(KASAN_SHADOW_START - PAGE_SIZE)
+#else
 #define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
+#endif
 
 /*
  * Here we define all the compile-time 'special' virtual
@@ -72,7 +77,7 @@
 static inline void __set_fixmap(enum fixed_addresses idx,
 				phys_addr_t phys, pgprot_t flags)
 {
-	map_kernel_page(fix_to_virt(idx), phys, pgprot_val(flags));
+	map_kernel_page(fix_to_virt(idx), phys, flags);
 }
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/fsl_85xx_cache_sram.h b/arch/powerpc/include/asm/fsl_85xx_cache_sram.h
index 2af2bdc..0235a04 100644
--- a/arch/powerpc/include/asm/fsl_85xx_cache_sram.h
+++ b/arch/powerpc/include/asm/fsl_85xx_cache_sram.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2009 Freescale Semiconductor, Inc.
  *
@@ -7,20 +8,6 @@
 
  * This file is derived from the original work done
  * by Sylvain Munaut for the Bestcomm SRAM allocator.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __ASM_POWERPC_FSL_85XX_CACHE_SRAM_H__
diff --git a/arch/powerpc/include/asm/fsl_gtm.h b/arch/powerpc/include/asm/fsl_gtm.h
index 3b05808..6ff6876 100644
--- a/arch/powerpc/include/asm/fsl_gtm.h
+++ b/arch/powerpc/include/asm/fsl_gtm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Freescale General-purpose Timers Module
  *
@@ -6,11 +7,6 @@
  *               Jerry Huang <Chang-Ming.Huang@freescale.com>
  * Copyright (c) MontaVista Software, Inc. 2008.
  *               Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef __ASM_FSL_GTM_H
diff --git a/arch/powerpc/include/asm/fsl_lbc.h b/arch/powerpc/include/asm/fsl_lbc.h
index c7240a0..c4af5ee 100644
--- a/arch/powerpc/include/asm/fsl_lbc.h
+++ b/arch/powerpc/include/asm/fsl_lbc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* Freescale Local Bus Controller
  *
  * Copyright © 2006-2007, 2010 Freescale Semiconductor
@@ -5,20 +6,6 @@
  * Authors: Nick Spence <nick.spence@freescale.com>,
  *          Scott Wood <scottwood@freescale.com>
  *          Jack Lan <jack.lan@freescale.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #ifndef __ASM_FSL_LBC_H
diff --git a/arch/powerpc/include/asm/fsl_pamu_stash.h b/arch/powerpc/include/asm/fsl_pamu_stash.h
index 38311c9..30a31ad 100644
--- a/arch/powerpc/include/asm/fsl_pamu_stash.h
+++ b/arch/powerpc/include/asm/fsl_pamu_stash.h
@@ -1,19 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 (C) 2013 Freescale Semiconductor, Inc.
- *
  */
 
 #ifndef __FSL_PAMU_STASH_H
diff --git a/arch/powerpc/include/asm/fsl_pm.h b/arch/powerpc/include/asm/fsl_pm.h
index 47df55e..61a4c97 100644
--- a/arch/powerpc/include/asm/fsl_pm.h
+++ b/arch/powerpc/include/asm/fsl_pm.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Support Power Management
  *
  * Copyright 2014-2015 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #ifndef __PPC_FSL_PM_H
 #define __PPC_FSL_PM_H
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 3dfb80b..f54a08a 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -8,6 +8,8 @@
 #define MCOUNT_ADDR		((unsigned long)(_mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
 #ifdef __ASSEMBLY__
 
 /* Based off of objdump optput from glibc */
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index 9454277..eea28ca 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -35,6 +35,7 @@
 {
 	int oldval = 0, ret;
 
+	allow_write_to_user(uaddr, sizeof(*uaddr));
 	pagefault_disable();
 
 	switch (op) {
@@ -59,9 +60,9 @@
 
 	pagefault_enable();
 
-	if (!ret)
-		*oval = oldval;
+	*oval = oldval;
 
+	prevent_write_to_user(uaddr, sizeof(*uaddr));
 	return ret;
 }
 
@@ -72,9 +73,10 @@
 	int ret = 0;
 	u32 prev;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+	if (!access_ok(uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	allow_write_to_user(uaddr, sizeof(*uaddr));
         __asm__ __volatile__ (
         PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\
@@ -95,6 +97,7 @@
         : "cc", "memory");
 
 	*uval = prev;
+	prevent_write_to_user(uaddr, sizeof(*uaddr));
         return ret;
 }
 
diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h
index a4f9478..2dabcf6 100644
--- a/arch/powerpc/include/asm/head-64.h
+++ b/arch/powerpc/include/asm/head-64.h
@@ -169,249 +169,6 @@
 
 #define ABS_ADDR(label) (label - fs_label + fs_start)
 
-/*
- * Following are the BOOK3S exception handler helper macros.
- * Handlers come in a number of types, and each type has a number of varieties.
- *
- * EXC_REAL_*     - real, unrelocated exception vectors
- * EXC_VIRT_*     - virt (AIL), unrelocated exception vectors
- * TRAMP_REAL_*   - real, unrelocated helpers (virt can call these)
- * TRAMP_VIRT_*   - virt, unreloc helpers (in practice, real can use)
- * TRAMP_KVM      - KVM handlers that get put into real, unrelocated
- * EXC_COMMON     - virt, relocated common handlers
- *
- * The EXC handlers are given a name, and branch to name_common, or the
- * appropriate KVM or masking function. Vector handler verieties are as
- * follows:
- *
- * EXC_{REAL|VIRT}_BEGIN/END - used to open-code the exception
- *
- * EXC_{REAL|VIRT}  - standard exception
- *
- * EXC_{REAL|VIRT}_suffix
- *     where _suffix is:
- *   - _MASKABLE               - maskable exception
- *   - _OOL                    - out of line with trampoline to common handler
- *   - _HV                     - HV exception
- *
- * There can be combinations, e.g., EXC_VIRT_OOL_MASKABLE_HV
- *
- * The one unusual case is __EXC_REAL_OOL_HV_DIRECT, which is
- * an OOL vector that branches to a specified handler rather than the usual
- * trampoline that goes to common. It, and other underscore macros, should
- * be used with care.
- *
- * KVM handlers come in the following verieties:
- * TRAMP_KVM
- * TRAMP_KVM_SKIP
- * TRAMP_KVM_HV
- * TRAMP_KVM_HV_SKIP
- *
- * COMMON handlers come in the following verieties:
- * EXC_COMMON_BEGIN/END - used to open-code the handler
- * EXC_COMMON
- * EXC_COMMON_ASYNC
- *
- * TRAMP_REAL and TRAMP_VIRT can be used with BEGIN/END. KVM
- * and OOL handlers are implemented as types of TRAMP and TRAMP_VIRT handlers.
- */
-
-#define EXC_REAL_BEGIN(name, start, size)			\
-	FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start, size)
-
-#define EXC_REAL_END(name, start, size)				\
-	FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##name, start, size)
-
-#define EXC_VIRT_BEGIN(name, start, size)			\
-	FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size)
-
-#define EXC_VIRT_END(name, start, size)				\
-	FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size)
-
-#define EXC_COMMON_BEGIN(name)					\
-	USE_TEXT_SECTION();					\
-	.balign IFETCH_ALIGN_BYTES;				\
-	.global name;						\
-	_ASM_NOKPROBE_SYMBOL(name);				\
-	DEFINE_FIXED_SYMBOL(name);				\
-name:
-
-#define TRAMP_REAL_BEGIN(name)					\
-	FIXED_SECTION_ENTRY_BEGIN(real_trampolines, name)
-
-#define TRAMP_VIRT_BEGIN(name)					\
-	FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name)
-
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#define TRAMP_KVM_BEGIN(name)					\
-	TRAMP_VIRT_BEGIN(name)
-#else
-#define TRAMP_KVM_BEGIN(name)
-#endif
-
-#define EXC_REAL_NONE(start, size)				\
-	FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start, size); \
-	FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, start, size)
-
-#define EXC_VIRT_NONE(start, size)				\
-	FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size); \
-	FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size);
-
-
-#define EXC_REAL(name, start, size)					\
-	EXC_REAL_BEGIN(name, start, size);				\
-	STD_EXCEPTION(start, name##_common);				\
-	EXC_REAL_END(name, start, size);
-
-#define EXC_VIRT(name, start, size, realvec)				\
-	EXC_VIRT_BEGIN(name, start, size);				\
-	STD_RELON_EXCEPTION(start, realvec, name##_common);		\
-	EXC_VIRT_END(name, start, size);
-
-#define EXC_REAL_MASKABLE(name, start, size, bitmask)			\
-	EXC_REAL_BEGIN(name, start, size);				\
-	MASKABLE_EXCEPTION(start, name##_common, bitmask);		\
-	EXC_REAL_END(name, start, size);
-
-#define EXC_VIRT_MASKABLE(name, start, size, realvec, bitmask)		\
-	EXC_VIRT_BEGIN(name, start, size);				\
-	MASKABLE_RELON_EXCEPTION(realvec, name##_common, bitmask);	\
-	EXC_VIRT_END(name, start, size);
-
-#define EXC_REAL_HV(name, start, size)					\
-	EXC_REAL_BEGIN(name, start, size);				\
-	STD_EXCEPTION_HV(start, start, name##_common);			\
-	EXC_REAL_END(name, start, size);
-
-#define EXC_VIRT_HV(name, start, size, realvec)				\
-	EXC_VIRT_BEGIN(name, start, size);				\
-	STD_RELON_EXCEPTION_HV(start, realvec, name##_common);		\
-	EXC_VIRT_END(name, start, size);
-
-#define __EXC_REAL_OOL(name, start, size)				\
-	EXC_REAL_BEGIN(name, start, size);				\
-	__OOL_EXCEPTION(start, label, tramp_real_##name);		\
-	EXC_REAL_END(name, start, size);
-
-#define __TRAMP_REAL_OOL(name, vec)					\
-	TRAMP_REAL_BEGIN(tramp_real_##name);				\
-	STD_EXCEPTION_OOL(vec, name##_common);
-
-#define EXC_REAL_OOL(name, start, size)					\
-	__EXC_REAL_OOL(name, start, size);				\
-	__TRAMP_REAL_OOL(name, start);
-
-#define __EXC_REAL_OOL_MASKABLE(name, start, size)			\
-	__EXC_REAL_OOL(name, start, size);
-
-#define __TRAMP_REAL_OOL_MASKABLE(name, vec, bitmask)			\
-	TRAMP_REAL_BEGIN(tramp_real_##name);				\
-	MASKABLE_EXCEPTION_OOL(vec, name##_common, bitmask);
-
-#define EXC_REAL_OOL_MASKABLE(name, start, size, bitmask)		\
-	__EXC_REAL_OOL_MASKABLE(name, start, size);			\
-	__TRAMP_REAL_OOL_MASKABLE(name, start, bitmask);
-
-#define __EXC_REAL_OOL_HV_DIRECT(name, start, size, handler)		\
-	EXC_REAL_BEGIN(name, start, size);				\
-	__OOL_EXCEPTION(start, label, handler);				\
-	EXC_REAL_END(name, start, size);
-
-#define __EXC_REAL_OOL_HV(name, start, size)				\
-	__EXC_REAL_OOL(name, start, size);
-
-#define __TRAMP_REAL_OOL_HV(name, vec)					\
-	TRAMP_REAL_BEGIN(tramp_real_##name);				\
-	STD_EXCEPTION_HV_OOL(vec, name##_common);			\
-
-#define EXC_REAL_OOL_HV(name, start, size)				\
-	__EXC_REAL_OOL_HV(name, start, size);				\
-	__TRAMP_REAL_OOL_HV(name, start);
-
-#define __EXC_REAL_OOL_MASKABLE_HV(name, start, size)			\
-	__EXC_REAL_OOL(name, start, size);
-
-#define __TRAMP_REAL_OOL_MASKABLE_HV(name, vec, bitmask)		\
-	TRAMP_REAL_BEGIN(tramp_real_##name);				\
-	MASKABLE_EXCEPTION_HV_OOL(vec, name##_common, bitmask);		\
-
-#define EXC_REAL_OOL_MASKABLE_HV(name, start, size, bitmask)		\
-	__EXC_REAL_OOL_MASKABLE_HV(name, start, size);			\
-	__TRAMP_REAL_OOL_MASKABLE_HV(name, start, bitmask);
-
-#define __EXC_VIRT_OOL(name, start, size)				\
-	EXC_VIRT_BEGIN(name, start, size);				\
-	__OOL_EXCEPTION(start, label, tramp_virt_##name);		\
-	EXC_VIRT_END(name, start, size);
-
-#define __TRAMP_VIRT_OOL(name, realvec)					\
-	TRAMP_VIRT_BEGIN(tramp_virt_##name);				\
-	STD_RELON_EXCEPTION_OOL(realvec, name##_common);
-
-#define EXC_VIRT_OOL(name, start, size, realvec)			\
-	__EXC_VIRT_OOL(name, start, size);				\
-	__TRAMP_VIRT_OOL(name, realvec);
-
-#define __EXC_VIRT_OOL_MASKABLE(name, start, size)			\
-	__EXC_VIRT_OOL(name, start, size);
-
-#define __TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask)		\
-	TRAMP_VIRT_BEGIN(tramp_virt_##name);				\
-	MASKABLE_RELON_EXCEPTION_OOL(realvec, name##_common, bitmask);
-
-#define EXC_VIRT_OOL_MASKABLE(name, start, size, realvec, bitmask)	\
-	__EXC_VIRT_OOL_MASKABLE(name, start, size);			\
-	__TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask);
-
-#define __EXC_VIRT_OOL_HV(name, start, size)				\
-	__EXC_VIRT_OOL(name, start, size);
-
-#define __TRAMP_VIRT_OOL_HV(name, realvec)				\
-	TRAMP_VIRT_BEGIN(tramp_virt_##name);				\
-	STD_RELON_EXCEPTION_HV_OOL(realvec, name##_common);		\
-
-#define EXC_VIRT_OOL_HV(name, start, size, realvec)			\
-	__EXC_VIRT_OOL_HV(name, start, size);				\
-	__TRAMP_VIRT_OOL_HV(name, realvec);
-
-#define __EXC_VIRT_OOL_MASKABLE_HV(name, start, size)			\
-	__EXC_VIRT_OOL(name, start, size);
-
-#define __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask)		\
-	TRAMP_VIRT_BEGIN(tramp_virt_##name);				\
-	MASKABLE_RELON_EXCEPTION_HV_OOL(realvec, name##_common, bitmask);\
-
-#define EXC_VIRT_OOL_MASKABLE_HV(name, start, size, realvec, bitmask)	\
-	__EXC_VIRT_OOL_MASKABLE_HV(name, start, size);			\
-	__TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask);
-
-#define TRAMP_KVM(area, n)						\
-	TRAMP_KVM_BEGIN(do_kvm_##n);					\
-	KVM_HANDLER(area, EXC_STD, n);					\
-
-#define TRAMP_KVM_SKIP(area, n)						\
-	TRAMP_KVM_BEGIN(do_kvm_##n);					\
-	KVM_HANDLER_SKIP(area, EXC_STD, n);				\
-
-/*
- * HV variant exceptions get the 0x2 bit added to their trap number.
- */
-#define TRAMP_KVM_HV(area, n)						\
-	TRAMP_KVM_BEGIN(do_kvm_H##n);					\
-	KVM_HANDLER(area, EXC_HV, n + 0x2);				\
-
-#define TRAMP_KVM_HV_SKIP(area, n)					\
-	TRAMP_KVM_BEGIN(do_kvm_H##n);					\
-	KVM_HANDLER_SKIP(area, EXC_HV, n + 0x2);			\
-
-#define EXC_COMMON(name, realvec, hdlr)					\
-	EXC_COMMON_BEGIN(name);						\
-	STD_EXCEPTION_COMMON(realvec, name, hdlr);			\
-
-#define EXC_COMMON_ASYNC(name, realvec, hdlr)				\
-	EXC_COMMON_BEGIN(name);						\
-	STD_EXCEPTION_COMMON_ASYNC(realvec, name, hdlr);		\
-
 #endif /* __ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_HEAD_64_H */
diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h
index 9c14f7b..1557484 100644
--- a/arch/powerpc/include/asm/hmi.h
+++ b/arch/powerpc/include/asm/hmi.h
@@ -1,19 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Hypervisor Maintenance Interrupt header file.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.
- *
  * Copyright 2015 IBM Corporation
  * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
  */
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 2d00cc5..bd6504c 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -4,85 +4,18 @@
 
 #ifdef CONFIG_HUGETLB_PAGE
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
-extern struct kmem_cache *hugepte_cache;
 
 #ifdef CONFIG_PPC_BOOK3S_64
-
 #include <asm/book3s/64/hugetlb.h>
-/*
- * 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)
-{
-	if (radix_enabled())
-		return radix__flush_hugetlb_page(vma, vmaddr);
-}
-
-#else
-
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
-	BUG_ON(!hugepd_ok(hpd));
-#ifdef CONFIG_PPC_8xx
-	return (pte_t *)__va(hpd_val(hpd) & ~HUGEPD_SHIFT_MASK);
-#else
-	return (pte_t *)((hpd_val(hpd) &
-			  ~HUGEPD_SHIFT_MASK) | PD_HUGE);
-#endif
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
-#ifdef CONFIG_PPC_8xx
-	return ((hpd_val(hpd) & _PMD_PAGE_MASK) >> 1) + 17;
-#else
-	return hpd_val(hpd) & HUGEPD_SHIFT_MASK;
-#endif
-}
-
+#elif defined(CONFIG_PPC_FSL_BOOK3E)
+#include <asm/nohash/hugetlb-book3e.h>
+#elif defined(CONFIG_PPC_8xx)
+#include <asm/nohash/32/hugetlb-8xx.h>
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
+extern bool hugetlb_disabled;
 
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
-				    unsigned 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.
-	 */
-	unsigned long idx = 0;
-
-	pte_t *dir = hugepd_page(hpd);
-#ifndef CONFIG_PPC_FSL_BOOK3E
-	idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd);
-#endif
-
-	return dir + idx;
-}
+void hugetlbpage_init_default(void);
 
 void flush_dcache_icache_hugepage(struct page *page);
 
@@ -98,43 +31,12 @@
 	return 0;
 }
 
-void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
-			    pte_t pte);
-#ifdef CONFIG_PPC_8xx
-static inline void flush_hugetlb_page(struct vm_area_struct *vma,
-				      unsigned long vmaddr)
-{
-	flush_tlb_page(vma, vmaddr);
-}
-#else
-void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
-#endif
-
+#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);
 
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
+#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)
 {
@@ -145,37 +47,25 @@
 #endif
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
-	pte_t pte;
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 	flush_hugetlb_page(vma, addr);
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
-extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-				      unsigned long addr, pte_t *ptep,
-				      pte_t pte, int dirty);
-
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+			       unsigned long addr, pte_t *ptep,
+			       pte_t pte, int dirty);
 
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#include <asm-generic/hugetlb.h>
+
 #else /* ! CONFIG_HUGETLB_PAGE */
 static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 				      unsigned long vmaddr)
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index a0b17f9..1111202 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -278,6 +278,7 @@
 #define H_COP			0x304
 #define H_GET_MPP_X		0x314
 #define H_SET_MODE		0x31C
+#define H_BLOCK_REMOVE		0x328
 #define H_CLEAR_HPT		0x358
 #define H_REQUEST_VMC		0x360
 #define H_RESIZE_HPT_PREPARE	0x36C
@@ -295,7 +296,20 @@
 #define H_INT_ESB               0x3C8
 #define H_INT_SYNC              0x3CC
 #define H_INT_RESET             0x3D0
-#define MAX_HCALL_OPCODE	H_INT_RESET
+#define H_SCM_READ_METADATA     0x3E4
+#define H_SCM_WRITE_METADATA    0x3E8
+#define H_SCM_BIND_MEM          0x3EC
+#define H_SCM_UNBIND_MEM        0x3F0
+#define H_SCM_QUERY_BLOCK_MEM_BINDING 0x3F4
+#define H_SCM_QUERY_LOGICAL_MEM_BINDING 0x3F8
+#define H_SCM_UNBIND_ALL        0x3FC
+#define H_SCM_HEALTH            0x400
+#define H_SCM_PERFORMANCE_STATS 0x418
+#define MAX_HCALL_OPCODE	H_SCM_PERFORMANCE_STATS
+
+/* Scope args for H_SCM_UNBIND_ALL */
+#define H_UNBIND_SCOPE_ALL (0x1)
+#define H_UNBIND_SCOPE_DRC (0x2)
 
 /* H_VIOCTL functions */
 #define H_GET_VIOA_DUMP_SIZE	0x01
@@ -322,6 +336,12 @@
 #define H_GET_24X7_DATA		0xF07C
 #define H_GET_PERF_COUNTER_INFO	0xF080
 
+/* Platform-specific hcalls used for nested HV KVM */
+#define H_SET_PARTITION_TABLE	0xF800
+#define H_ENTER_NESTED		0xF804
+#define H_TLB_INVALIDATE	0xF808
+#define H_COPY_TOFROM_GUEST	0xF80C
+
 /* Values for 2nd argument to H_SET_MODE */
 #define H_SET_MODE_RESOURCE_SET_CIABR		1
 #define H_SET_MODE_RESOURCE_SET_DAWR		2
@@ -461,6 +481,42 @@
 	u64 behaviour;
 };
 
+/* Register state for entering a nested guest with H_ENTER_NESTED */
+struct hv_guest_state {
+	u64 version;		/* version of this structure layout */
+	u32 lpid;
+	u32 vcpu_token;
+	/* These registers are hypervisor privileged (at least for writing) */
+	u64 lpcr;
+	u64 pcr;
+	u64 amor;
+	u64 dpdes;
+	u64 hfscr;
+	s64 tb_offset;
+	u64 dawr0;
+	u64 dawrx0;
+	u64 ciabr;
+	u64 hdec_expiry;
+	u64 purr;
+	u64 spurr;
+	u64 ic;
+	u64 vtb;
+	u64 hdar;
+	u64 hdsisr;
+	u64 heir;
+	u64 asdr;
+	/* These are OS privileged but need to be set late in guest entry */
+	u64 srr0;
+	u64 srr1;
+	u64 sprg[4];
+	u64 pidr;
+	u64 cfar;
+	u64 ppr;
+};
+
+/* Latest version of hv_guest_state structure */
+#define HV_GUEST_STATE_VERSION	1
+
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_HVCALL_H */
diff --git a/arch/powerpc/include/asm/hvconsole.h b/arch/powerpc/include/asm/hvconsole.h
index 35ea69e..999ed5a 100644
--- a/arch/powerpc/include/asm/hvconsole.h
+++ b/arch/powerpc/include/asm/hvconsole.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * hvconsole.h
  * Copyright (C) 2004 Ryan S Arnold, IBM Corporation
  *
  * LPAR console support.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #ifndef _PPC64_HVCONSOLE_H
diff --git a/arch/powerpc/include/asm/hvcserver.h b/arch/powerpc/include/asm/hvcserver.h
index 67d7da3..2b20403 100644
--- a/arch/powerpc/include/asm/hvcserver.h
+++ b/arch/powerpc/include/asm/hvcserver.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * hvcserver.h
  * Copyright (C) 2004 Ryan S Arnold, IBM Corporation
  *
  * PPC64 virtual I/O console server support.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #ifndef _PPC64_HVCSERVER_H
diff --git a/arch/powerpc/include/asm/hvsi.h b/arch/powerpc/include/asm/hvsi.h
index 3fdc54d..464a751 100644
--- a/arch/powerpc/include/asm/hvsi.h
+++ b/arch/powerpc/include/asm/hvsi.h
@@ -64,7 +64,7 @@
 	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 lenght from cursor */
+	unsigned int	inbuf_pktlen;	/* packet length from cursor */
 	atomic_t	seqno;		/* packet sequence number */
 	unsigned int	opened:1;	/* driver opened */
 	unsigned int	established:1;	/* protocol established */
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index ece4dc8..67e2da1 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -1,23 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * PowerPC BookIII S hardware breakpoint definitions
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright 2010, IBM Corporation.
  * Author: K.Prasad <prasad@linux.vnet.ibm.com>
- *
  */
 
 #ifndef _PPC_BOOK3S_64_HW_BREAKPOINT_H
@@ -94,6 +80,21 @@
 static inline void hw_breakpoint_disable(void) { }
 static inline void thread_change_pc(struct task_struct *tsk,
 					struct pt_regs *regs) { }
+
 #endif	/* CONFIG_HAVE_HW_BREAKPOINT */
+
+
+#ifdef CONFIG_PPC_DAWR
+extern bool dawr_force_enable;
+static inline bool dawr_enabled(void)
+{
+	return dawr_force_enable;
+}
+int set_dawr(struct arch_hw_breakpoint *brk);
+#else
+static inline bool dawr_enabled(void) { return false; }
+static inline int set_dawr(struct arch_hw_breakpoint *brk) { return -1; }
+#endif
+
 #endif	/* __KERNEL__ */
 #endif	/* _PPC_BOOK3S_64_HW_BREAKPOINT_H */
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
index 6a2c875..9872f85 100644
--- a/arch/powerpc/include/asm/icswx.h
+++ b/arch/powerpc/include/asm/icswx.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * ICSWX api
  *
  * Copyright (C) 2015 IBM Corp.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * This provides the Initiate Coprocessor Store Word Indexed (ICSWX)
  * instruction.  This instruction is used to communicate with PowerPC
  * coprocessors.  This also provides definitions of the structures used
diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h
index 69f516e..4da4fcb 100644
--- a/arch/powerpc/include/asm/imc-pmu.h
+++ b/arch/powerpc/include/asm/imc-pmu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef __ASM_POWERPC_IMC_PMU_H
 #define __ASM_POWERPC_IMC_PMU_H
 
@@ -7,11 +8,6 @@
  * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation.
  *           (C) 2017 Anju T Sudhakar, IBM Corporation.
  *           (C) 2017 Hemant K Shaw, IBM 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; either version
- * 2 of the License, or later version.
  */
 
 #include <linux/perf_event.h>
@@ -33,6 +29,7 @@
  */
 #define THREAD_IMC_LDBAR_MASK           0x0003ffffffffe000ULL
 #define THREAD_IMC_ENABLE               0x8000000000000000ULL
+#define TRACE_IMC_ENABLE		0x4000000000000000ULL
 
 /*
  * For debugfs interface for imc-mode and imc-command
@@ -59,6 +56,34 @@
 	char *scale;
 };
 
+/*
+ * Trace IMC hardware updates a 64bytes record on
+ * Core Performance Monitoring Counter (CPMC)
+ * overflow. Here is the layout for the trace imc record
+ *
+ * DW 0 : Timebase
+ * DW 1 : Program Counter
+ * DW 2 : PIDR information
+ * DW 3 : CPMC1
+ * DW 4 : CPMC2
+ * DW 5 : CPMC3
+ * Dw 6 : CPMC4
+ * DW 7 : Timebase
+ * .....
+ *
+ * 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;
+};
+
 /* Event attribute array index */
 #define IMC_FORMAT_ATTR		0
 #define IMC_EVENT_ATTR		1
@@ -69,6 +94,13 @@
 #define IMC_EVENT_OFFSET_MASK	0xffffffffULL
 
 /*
+ * Macro to mask bits 0:21 of first double word(which is the timebase) to
+ * compare with 8th double word (timebase) of trace imc record data.
+ */
+#define IMC_TRACE_RECORD_TB1_MASK      0x3ffffffffffULL
+
+
+/*
  * Device tree parser code detects IMC pmu support and
  * registers new IMC pmus. This structure will hold the
  * pmu functions, events, counter memory information
@@ -113,6 +145,7 @@
 
 enum {
 	IMC_TYPE_THREAD		= 0x1,
+	IMC_TYPE_TRACE		= 0x2,
 	IMC_TYPE_CORE		= 0x4,
 	IMC_TYPE_CHIP           = 0x10,
 };
@@ -123,6 +156,8 @@
 #define IMC_DOMAIN_NEST		1
 #define IMC_DOMAIN_CORE		2
 #define IMC_DOMAIN_THREAD	3
+/* For trace-imc the domain is still thread but it operates in trace-mode */
+#define IMC_DOMAIN_TRACE	4
 
 extern int init_imc_pmu(struct device_node *parent,
 				struct imc_pmu *pmu_ptr, int pmu_id);
diff --git a/arch/powerpc/include/asm/io-workarounds.h b/arch/powerpc/include/asm/io-workarounds.h
index f96dd09..3cce499 100644
--- a/arch/powerpc/include/asm/io-workarounds.h
+++ b/arch/powerpc/include/asm/io-workarounds.h
@@ -1,26 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Support PCI IO workaround
  *
  * (C) Copyright 2007-2008 TOSHIBA 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef _IO_WORKAROUNDS_H
 #define _IO_WORKAROUNDS_H
 
+#ifdef CONFIG_PPC_IO_WORKAROUNDS
 #include <linux/io.h>
 #include <asm/pci-bridge.h>
 
@@ -45,4 +33,23 @@
 #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 b855f56..a63ec93 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -1,14 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_IO_H
 #define _ASM_POWERPC_IO_H
 #ifdef __KERNEL__
 
 #define ARCH_HAS_IOREMAP_WC
+#ifdef CONFIG_PPC32
+#define ARCH_HAS_IOREMAP_WT
+#endif
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /* Check of existence of legacy devices */
@@ -26,16 +26,15 @@
 
 #include <linux/device.h>
 #include <linux/compiler.h>
+#include <linux/mm.h>
 #include <asm/page.h>
 #include <asm/byteorder.h>
 #include <asm/synch.h>
 #include <asm/delay.h>
+#include <asm/mmiowb.h>
 #include <asm/mmu.h>
 #include <asm/ppc_asm.h>
-
-#ifdef CONFIG_PPC64
-#include <asm/paca.h>
-#endif
+#include <asm/pgtable.h>
 
 #define SIO_CONFIG_RA	0x398
 #define SIO_CONFIG_RD	0x399
@@ -102,31 +101,6 @@
  *
  */
 
-#ifdef CONFIG_PPC64
-#define IO_SET_SYNC_FLAG()	do { local_paca->io_sync = 1; } while(0)
-#else
-#define IO_SET_SYNC_FLAG()
-#endif
-
-/* gcc 4.0 and older doesn't have 'Z' constraint */
-#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ == 0)
-#define DEF_MMIO_IN_X(name, size, insn)				\
-static inline u##size name(const volatile u##size __iomem *addr)	\
-{									\
-	u##size ret;							\
-	__asm__ __volatile__("sync;"#insn" %0,0,%1;twi 0,%0,0;isync"	\
-		: "=r" (ret) : "r" (addr), "m" (*addr) : "memory");	\
-	return ret;							\
-}
-
-#define DEF_MMIO_OUT_X(name, size, insn)				\
-static inline void name(volatile u##size __iomem *addr, u##size val)	\
-{									\
-	__asm__ __volatile__("sync;"#insn" %1,0,%2"			\
-		: "=m" (*addr) : "r" (val), "r" (addr) : "memory");	\
-	IO_SET_SYNC_FLAG();						\
-}
-#else /* newer gcc */
 #define DEF_MMIO_IN_X(name, size, insn)				\
 static inline u##size name(const volatile u##size __iomem *addr)	\
 {									\
@@ -141,9 +115,8 @@
 {									\
 	__asm__ __volatile__("sync;"#insn" %1,%y0"			\
 		: "=Z" (*addr) : "r" (val) : "memory");			\
-	IO_SET_SYNC_FLAG();						\
+	mmiowb_set_pending();						\
 }
-#endif
 
 #define DEF_MMIO_IN_D(name, size, insn)				\
 static inline u##size name(const volatile u##size __iomem *addr)	\
@@ -159,7 +132,7 @@
 {									\
 	__asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0"			\
 		: "=m" (*addr) : "r" (val) : "memory");			\
-	IO_SET_SYNC_FLAG();						\
+	mmiowb_set_pending();						\
 }
 
 DEF_MMIO_IN_D(in_8,     8, lbz);
@@ -667,24 +640,6 @@
 
 #include <asm-generic/iomap.h>
 
-#ifdef CONFIG_PPC32
-#define mmiowb()
-#else
-/*
- * Enforce synchronisation of stores vs. spin_unlock
- * (this does it explicitly, though our implementation of spin_unlock
- * does it implicitely too)
- */
-static inline void mmiowb(void)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__("sync; li %0,0; stb %0,%1(13)"
-	: "=&r" (tmp) : "i" (offsetof(struct paca_struct, io_sync))
-	: "memory");
-}
-#endif /* !CONFIG_PPC32 */
-
 static inline void iosync(void)
 {
         __asm__ __volatile__ ("sync" : : : "memory");
@@ -740,27 +695,26 @@
  *
  * * ioremap_wc enables write combining
  *
+ * * ioremap_wt enables write through
+ *
+ * * ioremap_coherent maps coherent cached memory
+ *
  * * iounmap undoes such a mapping and can be hooked
  *
  * * __ioremap_at (and the pending __iounmap_at) are low level functions to
  *   create hand-made mappings for use only by the PCI code and cannot
  *   currently be hooked. Must be page aligned.
  *
- * * __ioremap is the low level implementation used by ioremap and
- *   ioremap_prot and cannot be hooked (but can be used by a hook on one
- *   of the previous ones)
- *
  * * __ioremap_caller is the same as above but takes an explicit caller
  *   reference rather than using __builtin_return_address(0)
  *
- * * __iounmap, is the low level implementation used by iounmap and cannot
- *   be hooked (but can be used by a hook on iounmap)
- *
  */
 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);
 extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size);
+void __iomem *ioremap_wt(phys_addr_t address, unsigned long size);
+void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
 #define ioremap_nocache(addr, size)	ioremap((addr), (size))
 #define ioremap_uc(addr, size)		ioremap((addr), (size))
 #define ioremap_cache(addr, size) \
@@ -768,15 +722,16 @@
 
 extern void iounmap(volatile void __iomem *addr);
 
-extern void __iomem *__ioremap(phys_addr_t, unsigned long size,
-			       unsigned long flags);
-extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
-				      unsigned long flags, void *caller);
+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 __iounmap(volatile void __iomem *addr);
+extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
+				      pgprot_t prot, void *caller);
 
 extern void __iomem * __ioremap_at(phys_addr_t pa, void *ea,
-				   unsigned long size, unsigned long flags);
+				   unsigned long size, pgprot_t prot);
 extern void __iounmap_at(void *ea, unsigned long size);
 
 /*
@@ -792,8 +747,10 @@
 
 #define mmio_read16be(addr)		readw_be(addr)
 #define mmio_read32be(addr)		readl_be(addr)
+#define mmio_read64be(addr)		readq_be(addr)
 #define mmio_write16be(val, addr)	writew_be(val, addr)
 #define mmio_write32be(val, addr)	writel_be(val, addr)
+#define mmio_write64be(val, addr)	writeq_be(val, addr)
 #define mmio_insb(addr, dst, count)	readsb(addr, dst, count)
 #define mmio_insw(addr, dst, count)	readsw(addr, dst, count)
 #define mmio_insl(addr, dst, count)	readsl(addr, dst, count)
@@ -815,6 +772,8 @@
  */
 static inline unsigned long virt_to_phys(volatile void * address)
 {
+	WARN_ON(IS_ENABLED(CONFIG_DEBUG_VIRTUAL) && !virt_addr_valid(address));
+
 	return __pa((unsigned long)address);
 }
 
@@ -838,7 +797,14 @@
 /*
  * Change "struct page" to physical address.
  */
-#define page_to_phys(page)	((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+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
diff --git a/arch/powerpc/include/asm/io_event_irq.h b/arch/powerpc/include/asm/io_event_irq.h
index b1a9a1b..290c753 100644
--- a/arch/powerpc/include/asm/io_event_irq.h
+++ b/arch/powerpc/include/asm/io_event_irq.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2010, 2011 Mark Nelson and Tseng-Hui (Frank) Lin, IBM 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; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_IO_EVENT_IRQ_H
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 3d4b88c..350101e 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -1,21 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
  * Rewrite, cleanup:
  * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #ifndef _ASM_IOMMU_H
@@ -61,15 +48,16 @@
 	 * returns old TCE and DMA direction mask.
 	 * @tce is a physical address.
 	 */
-	int (*exchange)(struct iommu_table *tbl,
+	int (*xchg_no_kill)(struct iommu_table *tbl,
 			long index,
 			unsigned long *hpa,
-			enum dma_data_direction *direction);
-	/* Real mode */
-	int (*exchange_rm)(struct iommu_table *tbl,
-			long index,
-			unsigned long *hpa,
-			enum dma_data_direction *direction);
+			enum dma_data_direction *direction,
+			bool realmode);
+
+	void (*tce_kill)(struct iommu_table *tbl,
+			unsigned long index,
+			unsigned long pages,
+			bool realmode);
 
 	__be64 *(*useraddrptr)(struct iommu_table *tbl, long index, bool alloc);
 #endif
@@ -124,9 +112,11 @@
 	struct iommu_table_ops *it_ops;
 	struct kref    it_kref;
 	int it_nid;
+	unsigned long it_reserved_start; /* Start of not-DMA-able (MMIO) area */
+	unsigned long it_reserved_end;
 };
 
-#define IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry) \
+#define IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry) \
 		((tbl)->it_ops->useraddrptr((tbl), (entry), false))
 #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
 		((tbl)->it_ops->useraddrptr((tbl), (entry), true))
@@ -143,8 +133,6 @@
 
 #ifdef CONFIG_PPC64
 
-#define IOMMU_MAPPING_ERROR		(~(dma_addr_t)0x0)
-
 static inline void set_iommu_table_base(struct device *dev,
 					struct iommu_table *base)
 {
@@ -164,8 +152,9 @@
 /* Initializes an iommu_table based in values set in the passed-in
  * structure
  */
-extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
-					    int nid);
+extern struct iommu_table *iommu_init_table(struct iommu_table *tbl,
+		int nid, unsigned long res_start, unsigned long res_end);
+
 #define IOMMU_TABLE_GROUP_MAX_TABLES	2
 
 struct iommu_table_group;
@@ -215,11 +204,18 @@
 
 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 device *dev);
+extern int iommu_add_device(struct iommu_table_group *table_group,
+		struct device *dev);
 extern void iommu_del_device(struct device *dev);
-extern int __init tce_iommu_bus_notifier_init(void);
-extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
-		unsigned long *hpa, enum dma_data_direction *direction);
+extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl,
+		unsigned long entry, unsigned long *hpa,
+		enum dma_data_direction *direction);
+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);
+extern void iommu_tce_kill(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages);
 #else
 static inline void iommu_register_group(struct iommu_table_group *table_group,
 					int pci_domain_number,
@@ -227,7 +223,8 @@
 {
 }
 
-static inline int iommu_add_device(struct device *dev)
+static inline int iommu_add_device(struct iommu_table_group *table_group,
+		struct device *dev)
 {
 	return 0;
 }
@@ -235,15 +232,9 @@
 static inline void iommu_del_device(struct device *dev)
 {
 }
-
-static inline int __init tce_iommu_bus_notifier_init(void)
-{
-        return 0;
-}
 #endif /* !CONFIG_IOMMU_API */
 
-int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr);
-
+u64 dma_iommu_get_required_mask(struct device *dev);
 #else
 
 static inline void *get_iommu_table_base(struct device *dev)
@@ -325,5 +316,13 @@
 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__ */
 #endif /* _ASM_IOMMU_H */
diff --git a/arch/powerpc/include/asm/ipic.h b/arch/powerpc/include/asm/ipic.h
index fb59829..0524df3 100644
--- a/arch/powerpc/include/asm/ipic.h
+++ b/arch/powerpc/include/asm/ipic.h
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * IPIC external definitions and structure.
  *
  * Maintainer: Kumar Gala <galak@kernel.crashing.org>
  *
  * Copyright 2005 Freescale Semiconductor, Inc
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #ifdef __KERNEL__
 #ifndef __ASM_IPIC_H__
@@ -69,11 +65,7 @@
 	IPIC_MCP_MU   = 7,
 };
 
-extern int ipic_set_priority(unsigned int irq, unsigned int priority);
-extern void ipic_set_highest_priority(unsigned int irq);
 extern void ipic_set_default_priority(void);
-extern void ipic_enable_mcp(enum ipic_mcp_irq mcp_irq);
-extern void ipic_disable_mcp(enum ipic_mcp_irq mcp_irq);
 extern u32 ipic_get_mcp_status(void);
 extern void ipic_clear_mcp_status(u32 mask);
 
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index ee39ce5..814dfab 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifdef __KERNEL__
 #ifndef _ASM_POWERPC_IRQ_H
 #define _ASM_POWERPC_IRQ_H
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/irqdomain.h>
@@ -48,23 +45,19 @@
  * Per-cpu stacks for handling critical, debug and machine check
  * level interrupts.
  */
-extern struct thread_info *critirq_ctx[NR_CPUS];
-extern struct thread_info *dbgirq_ctx[NR_CPUS];
-extern struct thread_info *mcheckirq_ctx[NR_CPUS];
-extern void exc_lvl_ctx_init(void);
-#else
-#define exc_lvl_ctx_init()
+extern void *critirq_ctx[NR_CPUS];
+extern void *dbgirq_ctx[NR_CPUS];
+extern void *mcheckirq_ctx[NR_CPUS];
 #endif
 
 /*
  * Per-cpu stacks for handling hard and soft interrupts.
  */
-extern struct thread_info *hardirq_ctx[NR_CPUS];
-extern struct thread_info *softirq_ctx[NR_CPUS];
+extern void *hardirq_ctx[NR_CPUS];
+extern void *softirq_ctx[NR_CPUS];
 
-extern void irq_ctx_init(void);
-extern void call_do_softirq(struct thread_info *tp);
-extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp);
+void call_do_softirq(void *sp);
+void call_do_irq(struct pt_regs *regs, void *sp);
 extern void do_IRQ(struct pt_regs *regs);
 extern void __init init_IRQ(void);
 extern void __do_irq(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index a3b2cf9..09297ec 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_JUMP_LABEL_H
 #define _ASM_POWERPC_JUMP_LABEL_H
 
 /*
  * Copyright 2010 Michael Ellerman, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
new file mode 100644
index 0000000..296e51c
--- /dev/null
+++ b/arch/powerpc/include/asm/kasan.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifdef CONFIG_KASAN
+#define _GLOBAL_KASAN(fn)	_GLOBAL(__##fn)
+#define _GLOBAL_TOC_KASAN(fn)	_GLOBAL_TOC(__##fn)
+#define EXPORT_SYMBOL_KASAN(fn)	EXPORT_SYMBOL(__##fn)
+#else
+#define _GLOBAL_KASAN(fn)	_GLOBAL(fn)
+#define _GLOBAL_TOC_KASAN(fn)	_GLOBAL_TOC(fn)
+#define EXPORT_SYMBOL_KASAN(fn)
+#endif
+
+#ifndef __ASSEMBLY__
+
+#include <asm/page.h>
+
+#define KASAN_SHADOW_SCALE_SHIFT	3
+
+#define KASAN_SHADOW_START	(KASAN_SHADOW_OFFSET + \
+				 (PAGE_OFFSET >> KASAN_SHADOW_SCALE_SHIFT))
+
+#define KASAN_SHADOW_OFFSET	ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET)
+
+#define KASAN_SHADOW_END	0UL
+
+#define KASAN_SHADOW_SIZE	(KASAN_SHADOW_END - KASAN_SHADOW_START)
+
+#ifdef CONFIG_KASAN
+void kasan_early_init(void);
+void kasan_mmu_init(void);
+void kasan_init(void);
+#else
+static inline void kasan_init(void) { }
+static inline void kasan_mmu_init(void) { }
+#endif
+
+#endif /* __ASSEMBLY */
+#endif
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 4a585cb..c684768 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -94,6 +94,9 @@
 	return crashing_cpu >= 0;
 }
 
+void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_code_buffer,
+			 unsigned long start_address) __noreturn;
+
 #ifdef CONFIG_KEXEC_FILE
 extern const struct kexec_file_ops kexec_elf64_ops;
 
diff --git a/arch/powerpc/include/asm/kgdb.h b/arch/powerpc/include/asm/kgdb.h
index 9db24e7..a9e098a 100644
--- a/arch/powerpc/include/asm/kgdb.h
+++ b/arch/powerpc/include/asm/kgdb.h
@@ -26,9 +26,12 @@
 #define BREAK_INSTR_SIZE	4
 #define BUFMAX			((NUMREGBYTES * 2) + 512)
 #define OUTBUFMAX		((NUMREGBYTES * 2) + 512)
+
+#define BREAK_INSTR		0x7d821008	/* twge r2, r2 */
+
 static inline void arch_kgdb_breakpoint(void)
 {
-	asm(".long 0x7d821008"); /* twge r2, r2 */
+	asm(stringify_in_c(.long BREAK_INSTR));
 }
 #define CACHE_FLUSH_IS_SAFE	1
 #define DBG_MAX_REG_NUM     70
diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h
index 5acabbd..c8fa182 100644
--- a/arch/powerpc/include/asm/kmap_types.h
+++ b/arch/powerpc/include/asm/kmap_types.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_KMAP_TYPES_H
 #define _ASM_POWERPC_KMAP_TYPES_H
 
 #ifdef __KERNEL__
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define KM_TYPE_NR 16
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 785c464..66b3f29 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_KPROBES_H
 #define _ASM_POWERPC_KPROBES_H
 
@@ -7,20 +8,6 @@
 /*
  *  Kernel Probes (KProbes)
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright (C) IBM Corporation, 2002, 2004
  *
  * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
new file mode 100644
index 0000000..5b5e396
--- /dev/null
+++ b/arch/powerpc/include/asm/kup.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_KUP_H_
+#define _ASM_POWERPC_KUP_H_
+
+#ifdef CONFIG_PPC64
+#include <asm/book3s/64/kup-radix.h>
+#endif
+#ifdef CONFIG_PPC_8xx
+#include <asm/nohash/32/kup-8xx.h>
+#endif
+#ifdef CONFIG_PPC_BOOK3S_32
+#include <asm/book3s/32/kup.h>
+#endif
+
+#ifdef __ASSEMBLY__
+#ifndef CONFIG_PPC_KUAP
+.macro kuap_save_and_lock	sp, thread, gpr1, gpr2, gpr3
+.endm
+
+.macro kuap_restore	sp, current, gpr1, gpr2, gpr3
+.endm
+
+.macro kuap_check	current, gpr
+.endm
+
+#endif
+
+#else /* !__ASSEMBLY__ */
+
+#include <asm/pgtable.h>
+
+void setup_kup(void);
+
+#ifdef CONFIG_PPC_KUEP
+void setup_kuep(bool disabled);
+#else
+static inline void setup_kuep(bool disabled) { }
+#endif /* CONFIG_PPC_KUEP */
+
+#ifdef CONFIG_PPC_KUAP
+void setup_kuap(bool disabled);
+#else
+static inline void setup_kuap(bool disabled) { }
+static inline void allow_user_access(void __user *to, const void __user *from,
+				     unsigned long size) { }
+static inline void prevent_user_access(void __user *to, const void __user *from,
+				       unsigned long size) { }
+static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) { return false; }
+#endif /* CONFIG_PPC_KUAP */
+
+static inline void allow_read_from_user(const void __user *from, unsigned long size)
+{
+	allow_user_access(NULL, from, size);
+}
+
+static inline void allow_write_to_user(void __user *to, unsigned long size)
+{
+	allow_user_access(to, NULL, size);
+}
+
+static inline void prevent_read_from_user(const void __user *from, unsigned long size)
+{
+	prevent_user_access(NULL, from, size);
+}
+
+static inline void prevent_write_to_user(void __user *to, unsigned long size)
+{
+	prevent_user_access(to, NULL, size);
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_KUP_H_ */
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index a790d5c..635fb15 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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
  *
@@ -84,7 +73,6 @@
 #define BOOK3S_INTERRUPT_INST_STORAGE	0x400
 #define BOOK3S_INTERRUPT_INST_SEGMENT	0x480
 #define BOOK3S_INTERRUPT_EXTERNAL	0x500
-#define BOOK3S_INTERRUPT_EXTERNAL_LEVEL	0x501
 #define BOOK3S_INTERRUPT_EXTERNAL_HV	0x502
 #define BOOK3S_INTERRUPT_ALIGNMENT	0x600
 #define BOOK3S_INTERRUPT_PROGRAM	0x700
@@ -134,8 +122,7 @@
 #define BOOK3S_IRQPRIO_EXTERNAL			14
 #define BOOK3S_IRQPRIO_DECREMENTER		15
 #define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR	16
-#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL		17
-#define BOOK3S_IRQPRIO_MAX			18
+#define BOOK3S_IRQPRIO_MAX			17
 
 #define BOOK3S_HFLAG_DCBZ32			0x1
 #define BOOK3S_HFLAG_SLB			0x2
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 83a9aa3..506e4df 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
@@ -188,10 +177,39 @@
 extern int kvmppc_book3s_radix_page_fault(struct kvm_run *run,
 			struct kvm_vcpu *vcpu,
 			unsigned long ea, unsigned long dsisr);
+extern unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
+					gva_t eaddr, void *to, void *from,
+					unsigned long n);
+extern long kvmhv_copy_from_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
+					void *to, unsigned long n);
+extern long kvmhv_copy_to_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
+				      void *from, unsigned long n);
+extern int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
+				      struct kvmppc_pte *gpte, u64 root,
+				      u64 *pte_ret_p);
+extern int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
+			struct kvmppc_pte *gpte, u64 table,
+			int table_index, u64 *pte_ret_p);
 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);
+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);
+extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable,
+				    bool writing, unsigned long gpa,
+				    unsigned int lpid);
+extern int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
+				unsigned long gpa,
+				struct kvm_memory_slot *memslot,
+				bool writing, bool kvm_ro,
+				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);
 extern int kvmppc_radix_init(void);
 extern void kvmppc_radix_exit(void);
 extern int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
@@ -202,6 +220,8 @@
 			unsigned long gfn);
 extern long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm,
 			struct kvm_memory_slot *memslot, unsigned long *map);
+extern void kvmppc_radix_flush_memslot(struct kvm *kvm,
+			const struct kvm_memory_slot *memslot);
 extern int kvmhv_get_rmmu_info(struct kvm *kvm, struct kvm_ppc_rmmu_info *info);
 
 /* XXX remove this export when load_last_inst() is generic */
@@ -219,7 +239,7 @@
 			bool writing, bool *writable);
 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(struct kvm_memory_slot *memslot,
+extern void kvmppc_update_dirty_map(const struct kvm_memory_slot *memslot,
 			unsigned long gfn, unsigned long psize);
 extern void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
 			unsigned long pte_index);
@@ -271,6 +291,22 @@
 static inline void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu) {}
 #endif
 
+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_release_all_nested(struct kvm *kvm);
+long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
+long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
+int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu,
+			  u64 time_limit, unsigned long lpcr);
+void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
+void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
+				   struct hv_guest_state *hr);
+long int kvmhv_nested_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu);
+
 void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
 
 extern int kvm_irq_bypass;
@@ -301,12 +337,12 @@
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
 {
-	vcpu->arch.cr = val;
+	vcpu->arch.regs.ccr = val;
 }
 
 static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.cr;
+	return vcpu->arch.regs.ccr;
 }
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val)
@@ -384,9 +420,6 @@
 /* TO = 31 for unconditional trap */
 #define INS_TW				0x7fe00008
 
-/* LPIDs we support with this build -- runtime limit may be lower */
-#define KVMPPC_NR_LPIDS			(LPID_RSVD + 1)
-
 #define SPLIT_HACK_MASK			0xff000000
 #define SPLIT_HACK_OFFS			0xfb000000
 
diff --git a/arch/powerpc/include/asm/kvm_book3s_32.h b/arch/powerpc/include/asm/kvm_book3s_32.h
index c720e0b..e9d2e84 100644
--- a/arch/powerpc/include/asm/kvm_book3s_32.h
+++ b/arch/powerpc/include/asm/kvm_book3s_32.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2010
  *
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index dc435a5..04b2b92 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2010
  *
@@ -23,6 +12,109 @@
 #include <linux/string.h>
 #include <asm/bitops.h>
 #include <asm/book3s/64/mmu-hash.h>
+#include <asm/cpu_has_feature.h>
+#include <asm/ppc-opcode.h>
+
+#ifdef CONFIG_PPC_PSERIES
+static inline bool kvmhv_on_pseries(void)
+{
+	return !cpu_has_feature(CPU_FTR_HVMODE);
+}
+#else
+static inline bool kvmhv_on_pseries(void)
+{
+	return false;
+}
+#endif
+
+/*
+ * Structure for a nested guest, that is, for a guest that is managed by
+ * one of our guests.
+ */
+struct kvm_nested_guest {
+	struct kvm *l1_host;		/* L1 VM that owns this nested guest */
+	int l1_lpid;			/* lpid L1 guest thinks this guest is */
+	int shadow_lpid;		/* real lpid of this nested guest */
+	pgd_t *shadow_pgtable;		/* our page table for this guest */
+	u64 l1_gr_to_hr;		/* L1's addr of part'n-scoped table */
+	u64 process_table;		/* process table entry for this guest */
+	long refcnt;			/* number of pointers to this struct */
+	struct mutex tlb_lock;		/* serialize page faults and tlbies */
+	struct kvm_nested_guest *next;
+	cpumask_t need_tlb_flush;
+	cpumask_t cpu_in_guest;
+	short prev_cpu[NR_CPUS];
+	u8 radix;			/* is this nested guest radix */
+};
+
+/*
+ * We define a nested rmap entry as a single 64-bit quantity
+ * 0xFFF0000000000000	12-bit lpid field
+ * 0x000FFFFFFFFFF000	40-bit guest 4k page frame number
+ * 0x0000000000000001	1-bit  single entry flag
+ */
+#define RMAP_NESTED_LPID_MASK		0xFFF0000000000000UL
+#define RMAP_NESTED_LPID_SHIFT		(52)
+#define RMAP_NESTED_GPA_MASK		0x000FFFFFFFFFF000UL
+#define RMAP_NESTED_IS_SINGLE_ENTRY	0x0000000000000001UL
+
+/* Structure for a nested guest rmap entry */
+struct rmap_nested {
+	struct llist_node list;
+	u64 rmap;
+};
+
+/*
+ * for_each_nest_rmap_safe - iterate over the list of nested rmap entries
+ *			     safe against removal of the list entry or NULL list
+ * @pos:	a (struct rmap_nested *) to use as a loop cursor
+ * @node:	pointer to the first entry
+ *		NOTE: this can be NULL
+ * @rmapp:	an (unsigned long *) in which to return the rmap entries on each
+ *		iteration
+ *		NOTE: this must point to already allocated memory
+ *
+ * The nested_rmap is a llist of (struct rmap_nested) entries pointed to by the
+ * rmap entry in the memslot. The list is always terminated by a "single entry"
+ * stored in the list element of the final entry of the llist. If there is ONLY
+ * a single entry then this is itself in the rmap entry of the memslot, not a
+ * llist head pointer.
+ *
+ * Note that the iterator below assumes that a nested rmap entry is always
+ * non-zero.  This is true for our usage because the LPID field is always
+ * non-zero (zero is reserved for the host).
+ *
+ * This should be used to iterate over the list of rmap_nested entries with
+ * processing done on the u64 rmap value given by each iteration. This is safe
+ * against removal of list entries and it is always safe to call free on (pos).
+ *
+ * e.g.
+ * struct rmap_nested *cursor;
+ * struct llist_node *first;
+ * unsigned long rmap;
+ * for_each_nest_rmap_safe(cursor, first, &rmap) {
+ *	do_something(rmap);
+ *	free(cursor);
+ * }
+ */
+#define for_each_nest_rmap_safe(pos, node, rmapp)			       \
+	for ((pos) = llist_entry((node), typeof(*(pos)), list);		       \
+	     (node) &&							       \
+	     (*(rmapp) = ((RMAP_NESTED_IS_SINGLE_ENTRY & ((u64) (node))) ?     \
+			  ((u64) (node)) : ((pos)->rmap))) &&		       \
+	     (((node) = ((RMAP_NESTED_IS_SINGLE_ENTRY & ((u64) (node))) ?      \
+			 ((struct llist_node *) ((pos) = NULL)) :	       \
+			 (pos)->list.next)), true);			       \
+	     (pos) = llist_entry((node), typeof(*(pos)), list))
+
+struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
+					  bool create);
+void kvmhv_put_nested(struct kvm_nested_guest *gp);
+int kvmhv_nested_next_lpid(struct kvm *kvm, int lpid);
+
+/* Encoding of first parameter for H_TLB_INVALIDATE */
+#define H_TLBIE_P1_ENC(ric, prs, r)	(___PPC_RIC(ric) | ___PPC_PRS(prs) | \
+					 ___PPC_R(r))
 
 /* Power architecture requires HPT is at least 256kiB, at most 64TiB */
 #define PPC_MIN_HPT_ORDER	18
@@ -48,6 +140,18 @@
 	return kvm->arch.radix;
 }
 
+static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu)
+{
+	bool radix;
+
+	if (vcpu->arch.nested)
+		radix = vcpu->arch.nested->radix;
+	else
+		radix = kvm_is_radix(vcpu->kvm);
+
+	return radix;
+}
+
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
 #endif
 
@@ -431,10 +535,11 @@
  */
 static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
 {
-	return rcu_dereference_raw_notrace(kvm->memslots[0]);
+	return rcu_dereference_raw_check(kvm->memslots[0]);
 }
 
 extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
+extern void kvmhv_radix_debugfs_init(struct kvm *kvm);
 
 extern void kvmhv_rm_send_ipi(int cpu);
 
@@ -482,7 +587,7 @@
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 static inline void copy_from_checkpoint(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.cr  = vcpu->arch.cr_tm;
+	vcpu->arch.regs.ccr  = vcpu->arch.cr_tm;
 	vcpu->arch.regs.xer = vcpu->arch.xer_tm;
 	vcpu->arch.regs.link  = vcpu->arch.lr_tm;
 	vcpu->arch.regs.ctr = vcpu->arch.ctr_tm;
@@ -499,7 +604,7 @@
 
 static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.cr_tm  = vcpu->arch.cr;
+	vcpu->arch.cr_tm  = vcpu->arch.regs.ccr;
 	vcpu->arch.xer_tm = vcpu->arch.regs.xer;
 	vcpu->arch.lr_tm  = vcpu->arch.regs.link;
 	vcpu->arch.ctr_tm = vcpu->arch.regs.ctr;
@@ -515,6 +620,20 @@
 }
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
+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 *rmapp, struct rmap_nested **n_rmap);
+extern void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
+				   struct rmap_nested **n_rmap);
+extern void kvmhv_update_nest_rmap_rc_list(struct kvm *kvm, unsigned long *rmapp,
+					   unsigned long clr, unsigned long set,
+					   unsigned long hpa, unsigned long nbytes);
+extern void kvmhv_remove_nest_rmap_range(struct kvm *kvm,
+				const struct kvm_memory_slot *memslot,
+				unsigned long gpa, unsigned long hpa,
+				unsigned long nbytes);
+
 #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 d978fdf..45704f2 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
@@ -25,6 +14,9 @@
 #define XICS_MFRR		0xc
 #define XICS_IPI		2	/* interrupt source # for IPIs */
 
+/* LPIDs we support with this build -- runtime limit may be lower */
+#define KVMPPC_NR_LPIDS			(LPID_RSVD + 1)
+
 /* Maximum number of threads per physical core */
 #define MAX_SMT_THREADS		8
 
diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h
index d513e3e..310ba48 100644
--- a/arch/powerpc/include/asm/kvm_booke.h
+++ b/arch/powerpc/include/asm/kvm_booke.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2010
  *
@@ -46,12 +35,12 @@
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
 {
-	vcpu->arch.cr = val;
+	vcpu->arch.regs.ccr = val;
 }
 
 static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.cr;
+	return vcpu->arch.regs.ccr;
 }
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val)
diff --git a/arch/powerpc/include/asm/kvm_booke_hv_asm.h b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
index 931260b..7487ef5 100644
--- a/arch/powerpc/include/asm/kvm_booke_hv_asm.h
+++ b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright 2010-2011 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #ifndef ASM_KVM_BOOKE_HV_ASM_H
diff --git a/arch/powerpc/include/asm/kvm_fpu.h b/arch/powerpc/include/asm/kvm_fpu.h
index 92daae1..25df316 100644
--- a/arch/powerpc/include/asm/kvm_fpu.h
+++ b/arch/powerpc/include/asm/kvm_fpu.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 Novell Inc. 2010
  *
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 906bcbd..6fe6ad6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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
  *
@@ -46,6 +35,7 @@
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 #include <asm/kvm_book3s_asm.h>		/* for MAX_SMT_THREADS */
 #define KVM_MAX_VCPU_ID		(MAX_SMT_THREADS * KVM_MAX_VCORES)
+#define KVM_MAX_NESTED_GUESTS	KVMPPC_NR_LPIDS
 
 #else
 #define KVM_MAX_VCPU_ID		KVM_MAX_VCPUS
@@ -71,7 +61,7 @@
 			       unsigned long start, unsigned long end);
 extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
-extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
+extern int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 
 #define HPTEG_CACHE_NUM			(1 << 15)
 #define HPTEG_HASH_BITS_PTE		13
@@ -94,9 +84,12 @@
 
 struct kvmppc_vcpu_book3s;
 struct kvmppc_book3s_shadow_vcpu;
+struct kvm_nested_guest;
 
 struct kvm_vm_stat {
 	ulong remote_tlb_flush;
+	ulong num_2M_pages;
+	ulong num_1G_pages;
 };
 
 struct kvm_vcpu_stat {
@@ -197,6 +190,8 @@
 	struct kref kref;
 };
 
+#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
+
 struct kvmppc_spapr_tce_table {
 	struct list_head list;
 	struct kvm *kvm;
@@ -206,6 +201,7 @@
 	u64 offset;		/* in pages */
 	u64 size;		/* window size in pages */
 	struct list_head iommu_tables;
+	struct mutex alloc_lock;
 	struct page *pages[0];
 };
 
@@ -218,6 +214,7 @@
 struct kvmppc_xive;
 struct kvmppc_xive_vcpu;
 extern struct kvm_device_ops kvm_xive_ops;
+extern struct kvm_device_ops kvm_xive_native_ops;
 
 struct kvmppc_passthru_irqmap;
 
@@ -235,11 +232,25 @@
 };
 
 /*
- * We use the top bit of each memslot->arch.rmap entry as a lock bit,
- * and bit 32 as a present flag.  The bottom 32 bits are the
- * index in the guest HPT of a HPTE that points to the page.
+ * The rmap array of size number of guest pages is allocated for each memslot.
+ * This array is used to store usage specific information about the guest page.
+ * Below are the encodings of the various possible usage types.
  */
-#define KVMPPC_RMAP_LOCK_BIT	63
+/* Free bits which can be used to define a new usage */
+#define KVMPPC_RMAP_TYPE_MASK	0xff00000000000000
+#define KVMPPC_RMAP_NESTED	0xc000000000000000	/* Nested rmap array */
+#define KVMPPC_RMAP_HPT		0x0100000000000000	/* HPT guest */
+
+/*
+ * rmap usage definition for a hash page table (hpt) guest:
+ * 0x0000080000000000	Lock bit
+ * 0x0000018000000000	RC bits
+ * 0x0000000100000000	Present bit
+ * 0x00000000ffffffff	HPT index bits
+ * The bottom 32 bits are the index in the guest HPT of a HPTE that points to
+ * the page.
+ */
+#define KVMPPC_RMAP_LOCK_BIT	43
 #define KVMPPC_RMAP_RC_SHIFT	32
 #define KVMPPC_RMAP_REFERENCED	(HPTE_R_R << KVMPPC_RMAP_RC_SHIFT)
 #define KVMPPC_RMAP_PRESENT	0x100000000ul
@@ -286,11 +297,14 @@
 	cpumask_t cpu_in_guest;
 	u8 radix;
 	u8 fwnmi_enabled;
+	u8 secure_guest;
 	bool threads_indep;
+	bool nested_enable;
 	pgd_t *pgtable;
 	u64 process_table;
 	struct dentry *debugfs_dir;
 	struct dentry *htab_dentry;
+	struct dentry *radix_dentry;
 	struct kvm_resize_hpt *resize_hpt; /* protected by kvm->lock */
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@@ -299,6 +313,7 @@
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
 	struct list_head rtas_tokens;
+	struct mutex rtas_token_lock;
 	DECLARE_BITMAP(enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
 #endif
 #ifdef CONFIG_KVM_MPIC
@@ -306,11 +321,19 @@
 #endif
 #ifdef CONFIG_KVM_XICS
 	struct kvmppc_xics *xics;
-	struct kvmppc_xive *xive;
+	struct kvmppc_xive *xive;    /* Current XIVE device in use */
+	struct {
+		struct kvmppc_xive *native;
+		struct kvmppc_xive *xics_on_xive;
+	} xive_devices;
 	struct kvmppc_passthru_irqmap *pimap;
 #endif
 	struct kvmppc_ops *kvm_ops;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	struct mutex mmu_setup_lock;	/* nests inside vcpu mutexes */
+	u64 l1_ptcr;
+	int max_nested_lpid;
+	struct kvm_nested_guest *nested_guests[KVM_MAX_NESTED_GUESTS];
 	/* This array can grow quite large, keep it at the end */
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 #endif
@@ -360,7 +383,9 @@
 	bool may_write		: 1;
 	bool may_execute	: 1;
 	unsigned long wimg;
+	unsigned long rc;
 	u8 page_size;		/* MMU_PAGE_xxx */
+	u8 page_shift;
 };
 
 struct kvmppc_mmu {
@@ -368,6 +393,7 @@
 	void (*slbmte)(struct kvm_vcpu *vcpu, u64 rb, u64 rs);
 	u64  (*slbmfee)(struct kvm_vcpu *vcpu, u64 slb_nr);
 	u64  (*slbmfev)(struct kvm_vcpu *vcpu, u64 slb_nr);
+	int  (*slbfee)(struct kvm_vcpu *vcpu, gva_t eaddr, ulong *ret_slb);
 	void (*slbie)(struct kvm_vcpu *vcpu, u64 slb_nr);
 	void (*slbia)(struct kvm_vcpu *vcpu);
 	/* book3s */
@@ -437,6 +463,7 @@
 #define KVMPPC_IRQ_DEFAULT	0
 #define KVMPPC_IRQ_MPIC		1
 #define KVMPPC_IRQ_XICS		2 /* Includes a XIVE option */
+#define KVMPPC_IRQ_XIVE		3 /* XIVE native exploitation mode */
 
 #define MMIO_HPTE_CACHE_SIZE	4
 
@@ -537,8 +564,6 @@
 	ulong tar;
 #endif
 
-	u32 cr;
-
 #ifdef CONFIG_PPC_BOOK3S
 	ulong hflags;
 	ulong guest_owned_ext;
@@ -707,6 +732,7 @@
 	u8 hcall_needed;
 	u8 epr_flags; /* KVMPPC_EPR_xxx */
 	u8 epr_needed;
+	u8 external_oneshot;	/* clear external irq after delivery */
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 
@@ -781,6 +807,11 @@
 	u32 emul_inst;
 
 	u32 online;
+
+	/* For support of nested guests */
+	struct kvm_nested_guest *nested;
+	u32 nested_vcpu_id;
+	gpa_t nested_io_gpr;
 #endif
 
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
@@ -815,6 +846,8 @@
 #define KVM_MMIO_REG_FQPR	0x00c0
 #define KVM_MMIO_REG_VSX	0x0100
 #define KVM_MMIO_REG_VMX	0x0180
+#define KVM_MMIO_REG_NESTED_GPR	0xffc0
+
 
 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE
@@ -822,7 +855,7 @@
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
+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_exit(void) {}
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 5ceb4ef..9c1f6b4 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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
  *
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index e991821..ee62776 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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
  *
@@ -36,6 +25,8 @@
 #endif
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 #include <asm/paca.h>
+#include <asm/xive.h>
+#include <asm/cpu_has_feature.h>
 #endif
 
 /*
@@ -141,6 +132,7 @@
 
 extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags);
 extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags);
 extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu);
@@ -194,12 +186,6 @@
 		(iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \
 				(stt)->size, (ioba), (npages)) ?        \
 				H_PARAMETER : H_SUCCESS)
-extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt,
-		unsigned long tce);
-extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
-		unsigned long *ua, unsigned long **prmap);
-extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
-		unsigned long idx, unsigned long tce);
 extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			     unsigned long ioba, unsigned long tce);
 extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
@@ -226,7 +212,8 @@
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new);
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change);
 extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
 				      struct kvm_ppc_smmu_info *info);
 extern void kvmppc_core_flush_memslot(struct kvm *kvm,
@@ -271,6 +258,7 @@
 		u64	addr;
 		u64	length;
 	}	vpaval;
+	u64	xive_timaval[2];
 };
 
 struct kvmppc_ops {
@@ -296,7 +284,8 @@
 	void (*commit_memory_region)(struct kvm *kvm,
 				     const struct kvm_userspace_memory_region *mem,
 				     const struct kvm_memory_slot *old,
-				     const struct kvm_memory_slot *new);
+				     const struct kvm_memory_slot *new,
+				     enum kvm_mr_change change);
 	int (*unmap_hva_range)(struct kvm *kvm, unsigned long start,
 			   unsigned long end);
 	int (*age_hva)(struct kvm *kvm, unsigned long start, unsigned long end);
@@ -327,6 +316,11 @@
 	int (*set_smt_mode)(struct kvm *kvm, unsigned long mode,
 			    unsigned long flags);
 	void (*giveup_ext)(struct kvm_vcpu *vcpu, ulong msr);
+	int (*enable_nested)(struct kvm *kvm);
+	int (*load_from_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
+			       int size);
+	int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
+			      int size);
 };
 
 extern struct kvmppc_ops *kvmppc_hv_ops;
@@ -458,9 +452,100 @@
 	return xirr;
 }
 
-static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
+/*
+ * To avoid the need to unnecessarily exit fully to the host kernel, an IPI to
+ * a CPU thread that's running/napping inside of a guest is by default regarded
+ * as a request to wake the CPU (if needed) and continue execution within the
+ * guest, potentially to process new state like externally-generated
+ * interrupts or IPIs sent from within the guest itself (e.g. H_PROD/H_IPI).
+ *
+ * To force an exit to the host kernel, kvmppc_set_host_ipi() must be called
+ * prior to issuing the IPI to set the corresponding 'host_ipi' flag in the
+ * target CPU's PACA. To avoid unnecessary exits to the host, this flag should
+ * be immediately cleared via kvmppc_clear_host_ipi() by the IPI handler on
+ * the receiving side prior to processing the IPI work.
+ *
+ * NOTE:
+ *
+ * We currently issue an smp_mb() at the beginning of kvmppc_set_host_ipi().
+ * This is to guard against sequences such as the following:
+ *
+ *      CPU
+ *        X: smp_muxed_ipi_set_message():
+ *        X:   smp_mb()
+ *        X:   message[RESCHEDULE] = 1
+ *        X: doorbell_global_ipi(42):
+ *        X:   kvmppc_set_host_ipi(42)
+ *        X:   ppc_msgsnd_sync()/smp_mb()
+ *        X:   ppc_msgsnd() -> 42
+ *       42: doorbell_exception(): // from CPU X
+ *       42:   ppc_msgsync()
+ *      105: smp_muxed_ipi_set_message():
+ *      105:   smb_mb()
+ *           // STORE DEFERRED DUE TO RE-ORDERING
+ *    --105:   message[CALL_FUNCTION] = 1
+ *    | 105: doorbell_global_ipi(42):
+ *    | 105:   kvmppc_set_host_ipi(42)
+ *    |  42:   kvmppc_clear_host_ipi(42)
+ *    |  42: smp_ipi_demux_relaxed()
+ *    |  42: // returns to executing guest
+ *    |      // RE-ORDERED STORE COMPLETES
+ *    ->105:   message[CALL_FUNCTION] = 1
+ *      105:   ppc_msgsnd_sync()/smp_mb()
+ *      105:   ppc_msgsnd() -> 42
+ *       42: local_paca->kvm_hstate.host_ipi == 0 // IPI ignored
+ *      105: // hangs waiting on 42 to process messages/call_single_queue
+ *
+ * We also issue an smp_mb() at the end of kvmppc_clear_host_ipi(). This is
+ * to guard against sequences such as the following (as well as to create
+ * a read-side pairing with the barrier in kvmppc_set_host_ipi()):
+ *
+ *      CPU
+ *        X: smp_muxed_ipi_set_message():
+ *        X:   smp_mb()
+ *        X:   message[RESCHEDULE] = 1
+ *        X: doorbell_global_ipi(42):
+ *        X:   kvmppc_set_host_ipi(42)
+ *        X:   ppc_msgsnd_sync()/smp_mb()
+ *        X:   ppc_msgsnd() -> 42
+ *       42: doorbell_exception(): // from CPU X
+ *       42:   ppc_msgsync()
+ *           // STORE DEFERRED DUE TO RE-ORDERING
+ *    -- 42:   kvmppc_clear_host_ipi(42)
+ *    |  42: smp_ipi_demux_relaxed()
+ *    | 105: smp_muxed_ipi_set_message():
+ *    | 105:   smb_mb()
+ *    | 105:   message[CALL_FUNCTION] = 1
+ *    | 105: doorbell_global_ipi(42):
+ *    | 105:   kvmppc_set_host_ipi(42)
+ *    |      // RE-ORDERED STORE COMPLETES
+ *    -> 42:   kvmppc_clear_host_ipi(42)
+ *       42: // returns to executing guest
+ *      105:   ppc_msgsnd_sync()/smp_mb()
+ *      105:   ppc_msgsnd() -> 42
+ *       42: local_paca->kvm_hstate.host_ipi == 0 // IPI ignored
+ *      105: // hangs waiting on 42 to process messages/call_single_queue
+ */
+static inline void kvmppc_set_host_ipi(int cpu)
 {
-	paca_ptrs[cpu]->kvm_hstate.host_ipi = host_ipi;
+	/*
+	 * order stores of IPI messages vs. setting of host_ipi flag
+	 *
+	 * pairs with the barrier in kvmppc_clear_host_ipi()
+	 */
+	smp_mb();
+	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;
+	/*
+	 * order clearing of host_ipi flag vs. processing of IPI messages
+	 *
+	 * pairs with the barrier in kvmppc_set_host_ipi()
+	 */
+	smp_mb();
 }
 
 static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
@@ -472,6 +557,9 @@
 extern void kvm_hv_vm_deactivated(void);
 extern bool kvm_hv_mode_active(void);
 
+extern void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
+					struct kvm_nested_guest *nested);
+
 #else
 static inline void __init kvm_cma_reserve(void)
 {}
@@ -489,7 +577,10 @@
 	return 0;
 }
 
-static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
+static inline void kvmppc_set_host_ipi(int cpu)
+{}
+
+static inline void kvmppc_clear_host_ipi(int cpu)
 {}
 
 static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
@@ -585,6 +676,24 @@
 
 extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
 			       int level, bool line_status);
+extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
+
+static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.irq_type == KVMPPC_IRQ_XIVE;
+}
+
+extern int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
+					   struct kvm_vcpu *vcpu, u32 cpu);
+extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu);
+extern void kvmppc_xive_native_init_module(void);
+extern void kvmppc_xive_native_exit_module(void);
+extern int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
+				     union kvmppc_one_reg *val);
+extern int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu,
+				     union kvmppc_one_reg *val);
+extern bool kvmppc_xive_native_supported(void);
+
 #else
 static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
 				       u32 priority) { return -1; }
@@ -607,8 +716,36 @@
 
 static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
 				      int level, bool line_status) { return -ENODEV; }
+static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
+
+static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
+	{ return 0; }
+static inline int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
+			  struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
+static inline void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { }
+static inline void kvmppc_xive_native_init_module(void) { }
+static inline void kvmppc_xive_native_exit_module(void) { }
+static inline int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
+					    union kvmppc_one_reg *val)
+{ return 0; }
+static inline int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu,
+					    union kvmppc_one_reg *val)
+{ return -ENOENT; }
+
 #endif /* CONFIG_KVM_XIVE */
 
+#if defined(CONFIG_PPC_POWERNV) && defined(CONFIG_KVM_BOOK3S_64_HANDLER)
+static inline bool xics_on_xive(void)
+{
+	return xive_enabled() && cpu_has_feature(CPU_FTR_HVMODE);
+}
+#else
+static inline bool xics_on_xive(void)
+{
+	return false;
+}
+#endif
+
 /*
  * Prototypes for functions called only from assembler code.
  * Having prototypes reduces sparse errors.
@@ -625,7 +762,7 @@
                             unsigned int yield_count);
 long kvmppc_h_random(struct kvm_vcpu *vcpu);
 void kvmhv_commence_exit(int trap);
-long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu);
+void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu);
 void kvmppc_subcore_enter_guest(void);
 void kvmppc_subcore_exit_guest(void);
 long kvmppc_realmode_hmi_handler(void);
@@ -643,6 +780,8 @@
                         unsigned long pte_index);
 long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
                         unsigned long pte_index);
+long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			   unsigned long dest, unsigned long src);
 long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
                           unsigned long slb_v, unsigned int status, bool data);
 unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu);
@@ -652,6 +791,7 @@
                     unsigned long mfrr);
 int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
 int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
+void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu);
 
 /*
  * Host-side operations we want to set up while running in real
diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h
index 47a03b9..4a3d5d2 100644
--- a/arch/powerpc/include/asm/livepatch.h
+++ b/arch/powerpc/include/asm/livepatch.h
@@ -1,33 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * livepatch.h - powerpc-specific Kernel Live Patching Core
  *
  * Copyright (C) 2015-2016, SUSE, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 #ifndef _ASM_POWERPC_LIVEPATCH_H
 #define _ASM_POWERPC_LIVEPATCH_H
 
 #include <linux/module.h>
 #include <linux/ftrace.h>
+#include <linux/sched/task_stack.h>
 
 #ifdef CONFIG_LIVEPATCH
-static inline int klp_check_compiler_support(void)
-{
-	return 0;
-}
-
 static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 {
 	regs->nip = ip;
@@ -43,13 +27,13 @@
 	return ftrace_location_range(faddr, faddr + 16);
 }
 
-static inline void klp_init_thread_info(struct thread_info *ti)
+static inline void klp_init_thread_info(struct task_struct *p)
 {
 	/* + 1 to account for STACK_END_MAGIC */
-	ti->livepatch_sp = (unsigned long *)(ti + 1) + 1;
+	task_thread_info(p)->livepatch_sp = end_of_stack(p) + 1;
 }
 #else
-static void klp_init_thread_info(struct thread_info *ti) { }
+static inline void klp_init_thread_info(struct task_struct *p) { }
 #endif /* CONFIG_LIVEPATCH */
 
 #endif /* _ASM_POWERPC_LIVEPATCH_H */
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 7c23ce8..3b4b305 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -1,23 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * lppaca.h
  * Copyright (C) 2001  Mike Corrigan IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 #ifndef _ASM_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__
 
 /*
@@ -32,6 +42,7 @@
  */
 #include <linux/cache.h>
 #include <linux/threads.h>
+#include <linux/spinlock_types.h>
 #include <asm/types.h>
 #include <asm/mmu.h>
 #include <asm/firmware.h>
@@ -154,7 +165,19 @@
 #define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
 #define N_DISPATCH_LOG		(DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
 
+/*
+ * Dispatch trace log event enable mask:
+ *   0x1: voluntary virtual processor waits
+ *   0x2: time-slice preempts
+ *   0x4: virtual partition memory page faults
+ */
+#define DTL_LOG_CEDE		0x1
+#define DTL_LOG_PREEMPT		0x2
+#define DTL_LOG_FAULT		0x4
+#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;
 
 /*
  * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls
@@ -164,6 +187,10 @@
  */
 extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index);
 
+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 /* 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 f511767..b11501b 100644
--- a/arch/powerpc/include/asm/lv1call.h
+++ b/arch/powerpc/include/asm/lv1call.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  PS3 hvcall interface.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
  *  Copyright 2003, 2004 (c) MontaVista Software, Inc.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #if !defined(_ASM_POWERPC_LV1CALL_H)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index a47de82..7bcb644 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -1,14 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_MACHDEP_H
 #define _ASM_POWERPC_MACHDEP_H
 #ifdef __KERNEL__
 
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
@@ -34,10 +28,6 @@
 struct machdep_calls {
 	char		*name;
 #ifdef CONFIG_PPC64
-	void __iomem *	(*ioremap)(phys_addr_t addr, unsigned long size,
-				   unsigned long flags, void *caller);
-	void		(*iounmap)(volatile void __iomem *token);
-
 #ifdef CONFIG_PM
 	void		(*iommu_save)(void);
 	void		(*iommu_restore)(void);
@@ -47,9 +37,7 @@
 #endif
 #endif /* CONFIG_PPC64 */
 
-	/* Platform set_dma_mask and dma_get_required_mask overrides */
-	int		(*dma_set_mask)(struct device *dev, u64 dma_mask);
-	u64		(*dma_get_required_mask)(struct device *dev);
+	void		(*dma_set_mask)(struct device *dev, u64 dma_mask);
 
 	int		(*probe)(void);
 	void		(*setup_arch)(void); /* Optional, may be NULL */
@@ -108,6 +96,7 @@
 
 	/* Early exception handlers called in realmode */
 	int		(*hmi_exception_early)(struct pt_regs *regs);
+	long		(*machine_check_early)(struct pt_regs *regs);
 
 	/* Called during machine check exception to retrive fixup address. */
 	bool		(*mce_check_early_recovery)(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/mc146818rtc.h b/arch/powerpc/include/asm/mc146818rtc.h
index f2741c8..d9e4ecd 100644
--- a/arch/powerpc/include/asm/mc146818rtc.h
+++ b/arch/powerpc/include/asm/mc146818rtc.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_MC146818RTC_H
 #define _ASM_POWERPC_MC146818RTC_H
 
 /*
  * Machine dependent access functions for RTC registers.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifdef __KERNEL__
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 3a1226e..6a6ddaa 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -1,20 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Machine check exception header file.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright 2013 IBM Corporation
  * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
  */
@@ -31,7 +18,7 @@
 enum MCE_Severity {
 	MCE_SEV_NO_ERROR = 0,
 	MCE_SEV_WARNING = 1,
-	MCE_SEV_ERROR_SYNC = 2,
+	MCE_SEV_SEVERE = 2,
 	MCE_SEV_FATAL = 3,
 };
 
@@ -43,6 +30,10 @@
 enum MCE_Initiator {
 	MCE_INITIATOR_UNKNOWN = 0,
 	MCE_INITIATOR_CPU = 1,
+	MCE_INITIATOR_PCI = 2,
+	MCE_INITIATOR_ISA = 3,
+	MCE_INITIATOR_MEMORY= 4,
+	MCE_INITIATOR_POWERMGM = 5,
 };
 
 enum MCE_ErrorType {
@@ -54,6 +45,16 @@
 	MCE_ERROR_TYPE_USER = 5,
 	MCE_ERROR_TYPE_RA = 6,
 	MCE_ERROR_TYPE_LINK = 7,
+	MCE_ERROR_TYPE_DCACHE = 8,
+	MCE_ERROR_TYPE_ICACHE = 9,
+};
+
+enum MCE_ErrorClass {
+	MCE_ECLASS_UNKNOWN = 0,
+	MCE_ECLASS_HARDWARE,
+	MCE_ECLASS_HARD_INDETERMINATE,
+	MCE_ECLASS_SOFTWARE,
+	MCE_ECLASS_SOFT_INDETERMINATE,
 };
 
 enum MCE_UeErrorType {
@@ -110,73 +111,76 @@
 };
 
 struct machine_check_event {
-	enum MCE_Version	version:8;	/* 0x00 */
-	uint8_t			in_use;		/* 0x01 */
-	enum MCE_Severity	severity:8;	/* 0x02 */
-	enum MCE_Initiator	initiator:8;	/* 0x03 */
-	enum MCE_ErrorType	error_type:8;	/* 0x04 */
-	enum MCE_Disposition	disposition:8;	/* 0x05 */
-	uint8_t			reserved_1[2];	/* 0x06 */
-	uint64_t		gpr3;		/* 0x08 */
-	uint64_t		srr0;		/* 0x10 */
-	uint64_t		srr1;		/* 0x18 */
-	union {					/* 0x20 */
+	enum MCE_Version	version:8;
+	u8			in_use;
+	enum MCE_Severity	severity:8;
+	enum MCE_Initiator	initiator:8;
+	enum MCE_ErrorType	error_type:8;
+	enum MCE_ErrorClass	error_class:8;
+	enum MCE_Disposition	disposition:8;
+	bool			sync_error;
+	u16			cpu;
+	u64			gpr3;
+	u64			srr0;
+	u64			srr1;
+	union {
 		struct {
 			enum MCE_UeErrorType ue_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		physical_address_provided;
-			uint8_t		reserved_1[5];
-			uint64_t	effective_address;
-			uint64_t	physical_address;
-			uint8_t		reserved_2[8];
+			u8		effective_address_provided;
+			u8		physical_address_provided;
+			u8		ignore_event;
+			u8		reserved_1[4];
+			u64		effective_address;
+			u64		physical_address;
+			u8		reserved_2[8];
 		} ue_error;
 
 		struct {
 			enum MCE_SlbErrorType slb_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
+			u8		effective_address_provided;
+			u8		reserved_1[6];
+			u64		effective_address;
+			u8		reserved_2[16];
 		} slb_error;
 
 		struct {
 			enum MCE_EratErrorType erat_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
+			u8		effective_address_provided;
+			u8		reserved_1[6];
+			u64		effective_address;
+			u8		reserved_2[16];
 		} erat_error;
 
 		struct {
 			enum MCE_TlbErrorType tlb_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
+			u8		effective_address_provided;
+			u8		reserved_1[6];
+			u64		effective_address;
+			u8		reserved_2[16];
 		} tlb_error;
 
 		struct {
 			enum MCE_UserErrorType user_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
+			u8		effective_address_provided;
+			u8		reserved_1[6];
+			u64		effective_address;
+			u8		reserved_2[16];
 		} user_error;
 
 		struct {
 			enum MCE_RaErrorType ra_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
+			u8		effective_address_provided;
+			u8		reserved_1[6];
+			u64		effective_address;
+			u8		reserved_2[16];
 		} ra_error;
 
 		struct {
 			enum MCE_LinkErrorType link_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
+			u8		effective_address_provided;
+			u8		reserved_1[6];
+			u64		effective_address;
+			u8		reserved_2[16];
 		} link_error;
 	} u;
 };
@@ -194,6 +198,9 @@
 	} u;
 	enum MCE_Severity	severity:8;
 	enum MCE_Initiator	initiator:8;
+	enum MCE_ErrorClass	error_class:8;
+	bool			sync_error;
+	bool			ignore_event;
 };
 
 #define MAX_MC_EVT	100
@@ -209,5 +216,9 @@
 extern void release_mce_event(void);
 extern void machine_check_queue_event(void);
 extern void machine_check_print_event_info(struct machine_check_event *evt,
-					   bool user_mode);
+					   bool user_mode, bool in_guest);
+unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr);
+#ifdef CONFIG_PPC_BOOK3S_64
+void flush_and_reload_slb(void);
+#endif /* CONFIG_PPC_BOOK3S_64 */
 #endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/include/asm/mem_encrypt.h b/arch/powerpc/include/asm/mem_encrypt.h
new file mode 100644
index 0000000..ba9dab0
--- /dev/null
+++ b/arch/powerpc/include/asm/mem_encrypt.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * SVM helper functions
+ *
+ * Copyright 2018 IBM Corporation
+ */
+
+#ifndef _ASM_POWERPC_MEM_ENCRYPT_H
+#define _ASM_POWERPC_MEM_ENCRYPT_H
+
+#include <asm/svm.h>
+
+static inline bool mem_encrypt_active(void)
+{
+	return is_secure_guest();
+}
+
+static inline bool force_dma_unencrypted(struct device *dev)
+{
+	return is_secure_guest();
+}
+
+int set_memory_encrypted(unsigned long addr, int numpages);
+int set_memory_decrypted(unsigned long addr, int numpages);
+
+#endif /* _ASM_POWERPC_MEM_ENCRYPT_H */
diff --git a/arch/powerpc/include/asm/mm-arch-hooks.h b/arch/powerpc/include/asm/mm-arch-hooks.h
index f2a2da8..dce274b 100644
--- a/arch/powerpc/include/asm/mm-arch-hooks.h
+++ b/arch/powerpc/include/asm/mm-arch-hooks.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Architecture specific mm hooks
  *
  * Copyright (C) 2015, IBM Corporation
  * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef _ASM_POWERPC_MM_ARCH_HOOKS_H
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index e3f1b5b..d610c2e 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -1,8 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_MMAN_H
 #define _ASM_POWERPC_MMAN_H
diff --git a/arch/powerpc/include/asm/mmiowb.h b/arch/powerpc/include/asm/mmiowb.h
new file mode 100644
index 0000000..74a0012
--- /dev/null
+++ b/arch/powerpc/include/asm/mmiowb.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_MMIOWB_H
+#define _ASM_POWERPC_MMIOWB_H
+
+#ifdef CONFIG_MMIOWB
+
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+#include <asm/paca.h>
+
+#define arch_mmiowb_state()	(&local_paca->mmiowb_state)
+#define mmiowb()		mb()
+
+#endif /* CONFIG_MMIOWB */
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* _ASM_POWERPC_MMIOWB_H */
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 13ea441..0699cfe 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -48,7 +48,7 @@
 #define MMU_FTR_USE_HIGH_BATS		ASM_CONST(0x00010000)
 
 /* Enable >32-bit physical addresses on 32-bit processor, only used
- * by CONFIG_6xx currently as BookE supports that from day 1
+ * by CONFIG_PPC_BOOK3S_32 currently as BookE supports that from day 1
  */
 #define MMU_FTR_BIG_PHYS		ASM_CONST(0x00020000)
 
@@ -107,6 +107,11 @@
  */
 #define MMU_FTR_1T_SEGMENT		ASM_CONST(0x40000000)
 
+/*
+ * Supports KUAP (key 0 controlling userspace addresses) on radix
+ */
+#define MMU_FTR_RADIX_KUAP		ASM_CONST(0x80000000)
+
 /* MMU feature bit sets for various CPUs */
 #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2	\
 	MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2
@@ -124,6 +129,9 @@
 #ifndef __ASSEMBLY__
 #include <linux/bug.h>
 #include <asm/cputable.h>
+#include <asm/page.h>
+
+typedef pte_t *pgtable_t;
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
 #include <asm/percpu.h>
@@ -131,19 +139,43 @@
 #endif
 
 enum {
-	MMU_FTRS_POSSIBLE = MMU_FTR_HPTE_TABLE | MMU_FTR_TYPE_8xx |
-		MMU_FTR_TYPE_40x | MMU_FTR_TYPE_44x | MMU_FTR_TYPE_FSL_E |
-		MMU_FTR_TYPE_47x | MMU_FTR_USE_HIGH_BATS | MMU_FTR_BIG_PHYS |
-		MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_USE_TLBILX |
-		MMU_FTR_LOCK_BCAST_INVAL | MMU_FTR_NEED_DTLB_SW_LRU |
+	MMU_FTRS_POSSIBLE =
+#ifdef CONFIG_PPC_BOOK3S
+		MMU_FTR_HPTE_TABLE |
+#endif
+#ifdef CONFIG_PPC_8xx
+		MMU_FTR_TYPE_8xx |
+#endif
+#ifdef CONFIG_40x
+		MMU_FTR_TYPE_40x |
+#endif
+#ifdef CONFIG_44x
+		MMU_FTR_TYPE_44x |
+#endif
+#if defined(CONFIG_E200) || defined(CONFIG_E500)
+		MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX |
+#endif
+#ifdef CONFIG_PPC_47x
+		MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL |
+#endif
+#ifdef CONFIG_PPC_BOOK3S_32
+		MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU |
+#endif
+#ifdef CONFIG_PPC_BOOK3E_64
 		MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS |
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
 		MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL |
 		MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE |
 		MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA |
 		MMU_FTR_KERNEL_RO | MMU_FTR_68_BIT_VA |
+#endif
 #ifdef CONFIG_PPC_RADIX_MMU
 		MMU_FTR_TYPE_RADIX |
-#endif
+#ifdef CONFIG_PPC_KUAP
+		MMU_FTR_RADIX_KUAP |
+#endif /* CONFIG_PPC_KUAP */
+#endif /* CONFIG_PPC_RADIX_MMU */
 		0,
 };
 
@@ -225,7 +257,7 @@
 /* Functions for creating and updating partition table on POWER9 */
 extern void mmu_partition_table_init(void);
 extern void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
-					  unsigned long dw1);
+					  unsigned long dw1, bool flush);
 #endif /* CONFIG_PPC64 */
 
 struct mm_struct;
@@ -268,6 +300,17 @@
 }
 #endif /* CONFIG_PPC_MEM_KEYS */
 
+#ifdef CONFIG_STRICT_KERNEL_RWX
+static inline bool strict_kernel_rwx_enabled(void)
+{
+	return rodata_enabled;
+}
+#else
+static inline bool strict_kernel_rwx_enabled(void)
+{
+	return false;
+}
+#endif
 #endif /* !__ASSEMBLY__ */
 
 /* The kernel use the constants below to index in the page sizes array.
@@ -320,24 +363,16 @@
 extern void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 				       phys_addr_t first_memblock_size);
 static inline void mmu_early_init_devtree(void) { }
+
+extern void *abatron_pteptrs[2];
 #endif /* __ASSEMBLY__ */
 #endif
 
-#if defined(CONFIG_PPC_STD_MMU_32)
+#if defined(CONFIG_PPC_BOOK3S_32)
 /* 32-bit classic hash table MMU */
 #include <asm/book3s/32/mmu-hash.h>
-#elif defined(CONFIG_40x)
-/* 40x-style software loaded TLB */
-#  include <asm/mmu-40x.h>
-#elif defined(CONFIG_44x)
-/* 44x-style software loaded TLB */
-#  include <asm/mmu-44x.h>
-#elif defined(CONFIG_PPC_BOOK3E_MMU)
-/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */
-#  include <asm/mmu-book3e.h>
-#elif defined (CONFIG_PPC_8xx)
-/* Motorola/Freescale 8xx software loaded TLB */
-#  include <asm/mmu-8xx.h>
+#elif defined(CONFIG_PPC_MMU_NOHASH)
+#include <asm/nohash/mmu.h>
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b694d6a..58efca9 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -21,9 +21,12 @@
 
 extern int isolate_lru_page(struct page *page);	/* from internal.h */
 extern bool mm_iommu_preregistered(struct mm_struct *mm);
-extern long mm_iommu_get(struct mm_struct *mm,
+extern long mm_iommu_new(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries,
 		struct mm_iommu_table_group_mem_t **pmem);
+extern long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua,
+		unsigned long entries, unsigned long dev_hpa,
+		struct mm_iommu_table_group_mem_t **pmem);
 extern long mm_iommu_put(struct mm_struct *mm,
 		struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_init(struct mm_struct *mm);
@@ -32,15 +35,24 @@
 		unsigned long ua, unsigned long size);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
 		struct mm_struct *mm, unsigned long ua, unsigned long size);
-extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
+extern struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua);
+extern bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa,
+		unsigned int pageshift, unsigned long *size);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
+#else
+static inline bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa,
+		unsigned int pageshift, unsigned long *size)
+{
+	return false;
+}
+static inline void mm_iommu_init(struct mm_struct *mm) { }
 #endif
 extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
 extern void set_context(unsigned long id, pgd_t *pgd);
@@ -82,7 +94,7 @@
 {
 	int context_id;
 
-	context_id = get_ea_context(&mm->context, ea);
+	context_id = get_user_context(&mm->context, ea);
 	if (!context_id)
 		return true;
 	return false;
@@ -217,22 +229,9 @@
 #endif
 }
 
-static inline int arch_dup_mmap(struct mm_struct *oldmm,
-				struct mm_struct *mm)
-{
-	return 0;
-}
-
-#ifndef CONFIG_PPC_BOOK3S_64
-static inline void arch_exit_mmap(struct mm_struct *mm)
-{
-}
-#else
 extern void arch_exit_mmap(struct mm_struct *mm);
-#endif
 
 static inline void arch_unmap(struct mm_struct *mm,
-			      struct vm_area_struct *vma,
 			      unsigned long start, unsigned long end)
 {
 	if (start <= mm->context.vdso_base && mm->context.vdso_base < end)
@@ -247,6 +246,7 @@
 #ifdef CONFIG_PPC_MEM_KEYS
 bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
 			       bool execute, bool foreign);
+void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm);
 #else /* CONFIG_PPC_MEM_KEYS */
 static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 		bool write, bool execute, bool foreign)
@@ -259,6 +259,7 @@
 #define thread_pkey_regs_save(thread)
 #define thread_pkey_regs_restore(new_thread, old_thread)
 #define thread_pkey_regs_init(thread)
+#define arch_dup_pkeys(oldmm, mm)
 
 static inline u64 pte_to_hpte_pkey_bits(u64 pteflags)
 {
@@ -267,5 +268,12 @@
 
 #endif /* CONFIG_PPC_MEM_KEYS */
 
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
+{
+	arch_dup_pkeys(oldmm, mm);
+	return 0;
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_MMU_CONTEXT_H */
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index d61b081..3566587 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_MODULE_H
 #define _ASM_POWERPC_MODULE_H
 #ifdef __KERNEL__
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/list.h>
diff --git a/arch/powerpc/include/asm/mpc5121.h b/arch/powerpc/include/asm/mpc5121.h
index deaeb0b..9ae49e7 100644
--- a/arch/powerpc/include/asm/mpc5121.h
+++ b/arch/powerpc/include/asm/mpc5121.h
@@ -1,8 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * MPC5121 Prototypes and definitions
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.
  */
 
 #ifndef __ASM_POWERPC_MPC5121_H__
diff --git a/arch/powerpc/include/asm/mpc5xxx.h b/arch/powerpc/include/asm/mpc5xxx.h
index 5ce9c5f..2f60f5c 100644
--- a/arch/powerpc/include/asm/mpc5xxx.h
+++ b/arch/powerpc/include/asm/mpc5xxx.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -5,12 +6,6 @@
  *
  * Description:
  * MPC5xxx Prototypes and definitions
- *
- * This is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  */
 
 #ifndef __ASM_POWERPC_MPC5xxx_H__
diff --git a/arch/powerpc/include/asm/mpc85xx.h b/arch/powerpc/include/asm/mpc85xx.h
index 213f3a8..21aabc3 100644
--- a/arch/powerpc/include/asm/mpc85xx.h
+++ b/arch/powerpc/include/asm/mpc85xx.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * MPC85xx cpu type detection
  *
  * Copyright 2011-2012 Freescale Semiconductor, Inc.
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef __ASM_PPC_MPC85XX_H
diff --git a/arch/powerpc/include/asm/mpic_msgr.h b/arch/powerpc/include/asm/mpic_msgr.h
index 088420d..cd25eec 100644
--- a/arch/powerpc/include/asm/mpic_msgr.h
+++ b/arch/powerpc/include/asm/mpic_msgr.h
@@ -1,11 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright 2011-2012, Meador Inge, Mentor Graphics 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.
- *
  */
 
 #ifndef _ASM_MPIC_MSGR_H
diff --git a/arch/powerpc/include/asm/mpic_timer.h b/arch/powerpc/include/asm/mpic_timer.h
index 13e6702..d33e414 100644
--- a/arch/powerpc/include/asm/mpic_timer.h
+++ b/arch/powerpc/include/asm/mpic_timer.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * arch/powerpc/include/asm/mpic_timer.h
  *
@@ -7,11 +8,6 @@
  *
  * Author: Wang Dongsheng <Dongsheng.Wang@freescale.com>
  *	   Li Yang <leoli@freescale.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 #ifndef __MPIC_TIMER__
diff --git a/arch/powerpc/include/asm/msi_bitmap.h b/arch/powerpc/include/asm/msi_bitmap.h
index 1ec7125..55c2f7d 100644
--- a/arch/powerpc/include/asm/msi_bitmap.h
+++ b/arch/powerpc/include/asm/msi_bitmap.h
@@ -1,14 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 #ifndef _POWERPC_SYSDEV_MSI_BITMAP_H
 #define _POWERPC_SYSDEV_MSI_BITMAP_H
 
 /*
  * Copyright 2008, Michael Ellerman, IBM 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.
- *
  */
 
 #include <linux/of.h>
diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h
index bd9ba8d..84b4cfe 100644
--- a/arch/powerpc/include/asm/nmi.h
+++ b/arch/powerpc/include/asm/nmi.h
@@ -14,4 +14,6 @@
 #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
 #endif
 
+extern void hv_nmi_check_nonrecoverable(struct pt_regs *regs);
+
 #endif /* _ASM_NMI_H */
diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
new file mode 100644
index 0000000..a466169
--- /dev/null
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_NOHASH_32_HUGETLB_8XX_H
+#define _ASM_POWERPC_NOHASH_32_HUGETLB_8XX_H
+
+#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 ((hpd_val(hpd) & _PMD_PAGE_MASK) >> 1) + 17;
+}
+
+static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
+				    unsigned int pdshift)
+{
+	unsigned long idx = (addr & ((1UL << pdshift) - 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 |
+			 (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M : _PMD_PAGE_512K));
+}
+
+static inline int check_and_get_huge_psize(int shift)
+{
+	return shift_to_mmu_psize(shift);
+}
+
+#endif /* _ASM_POWERPC_NOHASH_32_HUGETLB_8XX_H */
diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
new file mode 100644
index 0000000..1c3133b
--- /dev/null
+++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_KUP_8XX_H_
+#define _ASM_POWERPC_KUP_8XX_H_
+
+#include <asm/bug.h>
+
+#ifdef CONFIG_PPC_KUAP
+
+#ifdef __ASSEMBLY__
+
+.macro kuap_save_and_lock	sp, thread, gpr1, gpr2, gpr3
+	lis	\gpr2, MD_APG_KUAP@h	/* only APG0 and APG1 are used */
+	mfspr	\gpr1, SPRN_MD_AP
+	mtspr	SPRN_MD_AP, \gpr2
+	stw	\gpr1, STACK_REGS_KUAP(\sp)
+.endm
+
+.macro kuap_restore	sp, current, gpr1, gpr2, gpr3
+	lwz	\gpr1, STACK_REGS_KUAP(\sp)
+	mtspr	SPRN_MD_AP, \gpr1
+.endm
+
+.macro kuap_check	current, gpr
+#ifdef CONFIG_PPC_KUAP_DEBUG
+	mfspr	\gpr, SPRN_MD_AP
+	rlwinm	\gpr, \gpr, 16, 0xffff
+999:	twnei	\gpr, MD_APG_KUAP@h
+	EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
+#endif
+.endm
+
+#else /* !__ASSEMBLY__ */
+
+#include <asm/reg.h>
+
+static inline void allow_user_access(void __user *to, const void __user *from,
+				     unsigned long size)
+{
+	mtspr(SPRN_MD_AP, MD_APG_INIT);
+}
+
+static inline void prevent_user_access(void __user *to, const void __user *from,
+				       unsigned long size)
+{
+	mtspr(SPRN_MD_AP, MD_APG_KUAP);
+}
+
+static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+{
+	return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000),
+		    "Bug: fault blocked by AP register !");
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* CONFIG_PPC_KUAP */
+
+#endif /* _ASM_POWERPC_KUP_8XX_H_ */
diff --git a/arch/powerpc/include/asm/mmu-40x.h b/arch/powerpc/include/asm/nohash/32/mmu-40x.h
similarity index 100%
rename from arch/powerpc/include/asm/mmu-40x.h
rename to arch/powerpc/include/asm/nohash/32/mmu-40x.h
diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/nohash/32/mmu-44x.h
similarity index 98%
rename from arch/powerpc/include/asm/mmu-44x.h
rename to arch/powerpc/include/asm/nohash/32/mmu-44x.h
index 295b3db..28aa3b3 100644
--- a/arch/powerpc/include/asm/mmu-44x.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-44x.h
@@ -111,6 +111,9 @@
 	unsigned long	vdso_base;
 } mm_context_t;
 
+/* patch sites */
+extern s32 patch__tlb_44x_hwater_D, patch__tlb_44x_hwater_I;
+
 #endif /* !__ASSEMBLY__ */
 
 #ifndef CONFIG_PPC_EARLY_DEBUG_44x
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
similarity index 78%
rename from arch/powerpc/include/asm/mmu-8xx.h
rename to arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index 193f531..76af5b0 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
@@ -35,11 +35,18 @@
  * Then we use the APG to say whether accesses are according to Page rules or
  * "all Supervisor" rules (Access to all)
  * Therefore, we define 2 APG groups. lsb is _PMD_USER
- * 0 => No user => 01 (all accesses performed according to page definition)
+ * 0 => Kernel => 01 (all accesses performed according to page definition)
  * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
- * We define all 16 groups so that all other bits of APG can take any value
+ * 2-16 => NA => 11 (all accesses performed as user iaw page definition)
  */
-#define MI_APG_INIT	0x44444444
+#define MI_APG_INIT	0x4fffffff
+
+/*
+ * 0 => Kernel => 01 (all accesses performed according to page definition)
+ * 1 => User => 10 (all accesses performed according to swaped page definition)
+ * 2-16 => NA => 11 (all accesses performed as user iaw page definition)
+ */
+#define MI_APG_KUEP	0x6fffffff
 
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MI_RPN is written, bits in
@@ -108,11 +115,18 @@
  * Then we use the APG to say whether accesses are according to Page rules or
  * "all Supervisor" rules (Access to all)
  * Therefore, we define 2 APG groups. lsb is _PMD_USER
- * 0 => No user => 01 (all accesses performed according to page definition)
+ * 0 => Kernel => 01 (all accesses performed according to page definition)
  * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
- * We define all 16 groups so that all other bits of APG can take any value
+ * 2-16 => NA => 11 (all accesses performed as user iaw page definition)
  */
-#define MD_APG_INIT	0x44444444
+#define MD_APG_INIT	0x4fffffff
+
+/*
+ * 0 => No user => 01 (all accesses performed according to page definition)
+ * 1 => User => 10 (all accesses performed according to swaped page definition)
+ * 2-16 => NA => 11 (all accesses performed as user iaw page definition)
+ */
+#define MD_APG_KUAP	0x6fffffff
 
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MD_RPN is written, bits in
@@ -167,9 +181,26 @@
 #ifdef CONFIG_PPC_MM_SLICES
 #include <asm/nohash/32/slice.h>
 #define SLICE_ARRAY_SIZE	(1 << (32 - SLICE_LOW_SHIFT - 1))
+#define LOW_SLICE_ARRAY_SZ	SLICE_ARRAY_SIZE
 #endif
 
+#if defined(CONFIG_PPC_4K_PAGES)
+#define mmu_virtual_psize	MMU_PAGE_4K
+#elif defined(CONFIG_PPC_16K_PAGES)
+#define mmu_virtual_psize	MMU_PAGE_16K
+#define PTE_FRAG_NR		4
+#define PTE_FRAG_SIZE_SHIFT	12
+#define PTE_FRAG_SIZE		(1UL << 12)
+#else
+#error "Unsupported PAGE_SIZE"
+#endif
+
+#define mmu_linear_psize	MMU_PAGE_8M
+
 #ifndef __ASSEMBLY__
+
+#include <linux/mmdebug.h>
+
 struct slice_mask {
 	u64 low_slices;
 	DECLARE_BITMAP(high_slices, 0);
@@ -185,13 +216,56 @@
 	unsigned char high_slices_psize[0];
 	unsigned long slb_addr_limit;
 	struct slice_mask mask_base_psize; /* 4k or 16k */
-# ifdef CONFIG_HUGETLB_PAGE
 	struct slice_mask mask_512k;
 	struct slice_mask mask_8m;
-# endif
 #endif
+	void *pte_frag;
 } mm_context_t;
 
+#ifdef CONFIG_PPC_MM_SLICES
+static inline u16 mm_ctx_user_psize(mm_context_t *ctx)
+{
+	return ctx->user_psize;
+}
+
+static inline void mm_ctx_set_user_psize(mm_context_t *ctx, u16 user_psize)
+{
+	ctx->user_psize = user_psize;
+}
+
+static inline unsigned char *mm_ctx_low_slices(mm_context_t *ctx)
+{
+	return ctx->low_slices_psize;
+}
+
+static inline unsigned char *mm_ctx_high_slices(mm_context_t *ctx)
+{
+	return ctx->high_slices_psize;
+}
+
+static inline unsigned long mm_ctx_slb_addr_limit(mm_context_t *ctx)
+{
+	return ctx->slb_addr_limit;
+}
+
+static inline void mm_ctx_set_slb_addr_limit(mm_context_t *ctx, unsigned long limit)
+{
+	ctx->slb_addr_limit = limit;
+}
+
+static inline struct slice_mask *slice_mask_for_size(mm_context_t *ctx, int psize)
+{
+	if (psize == MMU_PAGE_512K)
+		return &ctx->mask_512k;
+	if (psize == MMU_PAGE_8M)
+		return &ctx->mask_8m;
+
+	BUG_ON(psize != mmu_virtual_psize);
+
+	return &ctx->mask_base_psize;
+}
+#endif /* CONFIG_PPC_MM_SLICE */
+
 #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)
 #define VIRT_IMMR_BASE (__fix_to_virt(FIX_IMMR_BASE))
 
@@ -229,16 +303,16 @@
 	BUG();
 }
 
+/* patch sites */
+extern s32 patch__itlbmiss_linmem_top, patch__itlbmiss_linmem_top8;
+extern s32 patch__dtlbmiss_linmem_top, patch__dtlbmiss_immr_jmp;
+extern s32 patch__fixupdar_linmem_top;
+extern s32 patch__dtlbmiss_romem_top, patch__dtlbmiss_romem_top8;
+
+extern s32 patch__itlbmiss_exit_1, patch__itlbmiss_exit_2;
+extern s32 patch__dtlbmiss_exit_1, patch__dtlbmiss_exit_2, patch__dtlbmiss_exit_3;
+extern s32 patch__itlbmiss_perf, patch__dtlbmiss_perf;
+
 #endif /* !__ASSEMBLY__ */
 
-#if defined(CONFIG_PPC_4K_PAGES)
-#define mmu_virtual_psize	MMU_PAGE_4K
-#elif defined(CONFIG_PPC_16K_PAGES)
-#define mmu_virtual_psize	MMU_PAGE_16K
-#else
-#error "Unsupported PAGE_SIZE"
-#endif
-
-#define mmu_linear_psize	MMU_PAGE_8M
-
 #endif /* _ASM_POWERPC_MMU_8XX_H_ */
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 8825953..11eac37 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -6,42 +6,6 @@
 #include <linux/slab.h>
 
 /*
- * 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
- * handle allocation.  For PTE pages (which are linked to a struct
- * page for now, and drawn from the main get_free_pages() pool), the
- * allocation size will be (2^index_size * sizeof(pointer)) and
- * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
- *
- * The maximum index size needs to be big enough to allow any
- * pagetable sizes we need, but small enough to fit in the low bits of
- * any page table pointer.  In other words all pagetables, even tiny
- * ones, must be aligned to allow at least enough low 0 bits to
- * contain this value.  This value is also used as a mask, so it must
- * be one less than a power of two.
- */
-#define MAX_PGTABLE_INDEX_SIZE	0xf
-
-extern void __bad_pte(pmd_t *pmd);
-
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) ({				\
-			BUG_ON(!(shift));		\
-			pgtable_cache[(shift) - 1];	\
-		})
-
-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));
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
-}
-
-/*
  * We don't have any real pmd's, and this code never triggers because
  * the pgd will always be present..
  */
@@ -50,96 +14,22 @@
 #define __pmd_free_tlb(tlb,x,a)		do { } while (0)
 /* #define pgd_populate(mm, pmd, pte)      BUG() */
 
-#ifndef CONFIG_BOOKE
-
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
 				       pte_t *pte)
 {
-	*pmdp = __pmd(__pa(pte) | _PMD_PRESENT);
+	if (IS_ENABLED(CONFIG_BOOKE))
+		*pmdp = __pmd((unsigned long)pte | _PMD_PRESENT);
+	else
+		*pmdp = __pmd(__pa(pte) | _PMD_PRESENT);
 }
 
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pte_page)
 {
-	*pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_USER |
-		      _PMD_PRESENT);
+	if (IS_ENABLED(CONFIG_BOOKE))
+		*pmdp = __pmd((unsigned long)pte_page | _PMD_PRESENT);
+	else
+		*pmdp = __pmd(__pa(pte_page) | _PMD_USER | _PMD_PRESENT);
 }
 
-#define pmd_pgtable(pmd) pmd_page(pmd)
-#else
-
-static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
-				       pte_t *pte)
-{
-	*pmdp = __pmd((unsigned long)pte | _PMD_PRESENT);
-}
-
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
-				pgtable_t pte_page)
-{
-	*pmdp = __pmd((unsigned long)lowmem_page_address(pte_page) | _PMD_PRESENT);
-}
-
-#define pmd_pgtable(pmd) pmd_page(pmd)
-#endif
-
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
-extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-	pgtable_page_dtor(ptepage);
-	__free_page(ptepage);
-}
-
-static inline void pgtable_free(void *table, unsigned index_size)
-{
-	if (!index_size) {
-		pgtable_page_dtor(virt_to_page(table));
-		free_page((unsigned long)table);
-	} else {
-		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
-		kmem_cache_free(PGT_CACHE(index_size), table);
-	}
-}
-
-#define check_pgt_cache()	do { } while (0)
-#define get_hugepd_cache_index(x)	(x)
-
-#ifdef CONFIG_SMP
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
-				    void *table, int shift)
-{
-	unsigned long pgf = (unsigned long)table;
-	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-	pgf |= shift;
-	tlb_remove_table(tlb, (void *)pgf);
-}
-
-static inline void __tlb_remove_table(void *_table)
-{
-	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
-	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
-
-	pgtable_free(table, shift);
-}
-#else
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
-				    void *table, int shift)
-{
-	pgtable_free(table, shift);
-}
-#endif
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
-				  unsigned long address)
-{
-	tlb_flush_pgtable(tlb, address);
-	pgtable_free_tlb(tlb, page_address(table), 0);
-}
 #endif /* _ASM_POWERPC_PGALLOC_32_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index a507a65..552b96e 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -11,8 +11,6 @@
 #include <asm/mmu.h>			/* For sub-arch specific PPC_PIN_SIZE */
 #include <asm/asm-405.h>
 
-extern unsigned long ioremap_bot;
-
 #ifdef CONFIG_44x
 extern int icache_44x_need_flush;
 #endif
@@ -64,28 +62,35 @@
 #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);
+
+#endif /* !__ASSEMBLY__ */
+
+
 /*
  * 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
  */
-#ifdef CONFIG_HIGHMEM
-#define KVIRT_TOP	PKMAP_BASE
-#else
-#define KVIRT_TOP	(0xfe000000UL)	/* for now, could be FIXMAP_BASE ? */
-#endif
+#include <asm/fixmap.h>
 
 /*
  * ioremap_bot starts at that address. Early ioremaps move down from there,
  * until mem_init() at which point this becomes the top of the vmalloc
  * and ioremap space
  */
-#ifdef CONFIG_NOT_COHERENT_CACHE
-#define IOREMAP_TOP	((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK)
+#ifdef CONFIG_HIGHMEM
+#define IOREMAP_TOP	PKMAP_BASE
 #else
-#define IOREMAP_TOP	KVIRT_TOP
+#define IOREMAP_TOP	FIXADDR_START
 #endif
 
+/* PPC32 shares vmalloc area with ioremap */
+#define IOREMAP_START	VMALLOC_START
+#define IOREMAP_END	VMALLOC_END
+
 /*
  * Just any arbitrary offset to the start of the vmalloc VM area: the
  * current 16MB value just means that there will be a 64MB "hole" after the
@@ -128,14 +133,65 @@
 #include <asm/nohash/32/pte-8xx.h>
 #endif
 
-/* And here we include common definitions */
-#include <asm/pte-common.h>
+/*
+ * Location of the PFN in the PTE. Most 32-bit platforms use the same
+ * as _PAGE_SHIFT here (ie, naturally aligned).
+ * Platform who don't just pre-define the value so we don't override it here.
+ */
+#ifndef PTE_RPN_SHIFT
+#define PTE_RPN_SHIFT	(PAGE_SHIFT)
+#endif
+
+/*
+ * 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)
+#define PTE_RPN_MASK	(~((1ULL << PTE_RPN_SHIFT) - 1))
+#else
+#define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
+#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(ptep, ~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
+
+static inline pte_t pte_mkexec(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_EXEC);
+}
+
 #define pmd_none(pmd)		(!pmd_val(pmd))
 #define	pmd_bad(pmd)		(pmd_val(pmd) & _PMD_BAD)
 #define	pmd_present(pmd)	(pmd_val(pmd) & _PMD_PRESENT_MASK)
@@ -181,7 +237,13 @@
 	: "cc" );
 #else /* PTE_ATOMIC_UPDATES */
 	unsigned long old = pte_val(*p);
-	*p = __pte((old & ~clr) | set);
+	unsigned long new = (old & ~clr) | set;
+
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
+	p->pte = p->pte1 = p->pte2 = p->pte3 = new;
+#else
+	*p = __pte(new);
+#endif
 #endif /* !PTE_ATOMIC_UPDATES */
 
 #ifdef CONFIG_44x
@@ -244,23 +306,21 @@
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO);
-}
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
+	unsigned long clr = ~pte_val(pte_wrprotect(__pte(~0)));
+	unsigned long set = pte_val(pte_wrprotect(__pte(0)));
 
+	pte_update(ptep, clr, set);
+}
 
 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);
-	unsigned long clr = ~pte_val(entry) & (_PAGE_RO | _PAGE_NA);
+	pte_t pte_set = pte_mkyoung(pte_mkdirty(pte_mkwrite(pte_mkexec(__pte(0)))));
+	pte_t pte_clr = pte_mkyoung(pte_mkdirty(pte_mkwrite(pte_mkexec(__pte(~0)))));
+	unsigned long set = pte_val(entry) & pte_val(pte_set);
+	unsigned long clr = ~pte_val(entry) & ~pte_val(pte_clr);
 
 	pte_update(ptep, clr, set);
 
@@ -284,12 +344,12 @@
  */
 #ifndef CONFIG_BOOKE
 #define pmd_page_vaddr(pmd)	\
-	((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+	((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1)))
 #define pmd_page(pmd)		\
 	pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
 #else
 #define pmd_page_vaddr(pmd)	\
-	((unsigned long) (pmd_val(pmd) & PAGE_MASK))
+	((unsigned long)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1)))
 #define pmd_page(pmd)		\
 	pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT))
 #endif
@@ -308,7 +368,8 @@
 	(pmd_bad(*(dir)) ? NULL : (pte_t *)pmd_page_vaddr(*(dir)) + \
 				  pte_index(addr))
 #define pte_offset_map(dir, addr)		\
-	((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr))
+	((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \
+		   (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr))
 #define pte_unmap(pte)		kunmap_atomic(pte)
 
 /*
@@ -323,8 +384,6 @@
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
-int map_kernel_page(unsigned long va, phys_addr_t pa, int flags);
-
 #endif /* !__ASSEMBLY__ */
 
 #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
index bb4b3a4..12c6811 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-40x.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-40x.h
@@ -33,7 +33,7 @@
  *   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 use bits 21, 24, 25, and
+ *   software PTE bits.  We actually use bits 21, 24, 25, and
  *   30 respectively for the software bits: ACCESSED, DIRTY, RW, and
  *   PRESENT.
  */
@@ -50,13 +50,56 @@
 #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 | _PAGE_HWWRITE)
+#define _PAGE_KERNEL_RWX	(_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE | _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)
+
+#ifndef __ASSEMBLY__
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_RW | _PAGE_HWWRITE));
+}
+
+#define pte_wrprotect pte_wrprotect
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_DIRTY | _PAGE_HWWRITE));
+}
+
+#define pte_mkclean pte_mkclean
+#endif
+
 #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 f812c02..78bc304 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-44x.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h
@@ -85,14 +85,44 @@
 #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)
 #define _PMD_BAD	(~PAGE_MASK)
+#define _PMD_USER	0
 
 /* ERPN in a PTE never gets cleared, ignore it */
 #define _PTE_NONE_MASK	0xffffffff00000000ULL
 
+/*
+ * We define 2 sets of base prot bits, one for basic pages (ie,
+ * cacheable kernel and user pages) and one for non cacheable
+ * 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)
+#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_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_44x_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index f04cb46..c9e4b2d 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -29,10 +29,10 @@
  */
 
 /* Definitions for 8xx embedded chips. */
-#define _PAGE_PRESENT	0x0001	/* Page is valid */
-#define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
-#define _PAGE_PRIVILEGED	0x0004	/* No ASID (context) compare */
-#define _PAGE_HUGE	0x0008	/* SPS: Small Page Size (1 if 16k, 512k or 8M)*/
+#define _PAGE_PRESENT	0x0001	/* V: Page is valid */
+#define _PAGE_NO_CACHE	0x0002	/* CI: cache inhibit */
+#define _PAGE_SH	0x0004	/* SH: No ASID (context) compare */
+#define _PAGE_SPS	0x0008	/* SPS: Small Page Size (1 if 16k, 512k or 8M)*/
 #define _PAGE_DIRTY	0x0100	/* C: page changed */
 
 /* These 4 software bits must be masked out when the L2 entry is loaded
@@ -46,18 +46,92 @@
 #define _PAGE_NA	0x0200	/* Supervisor NA, User no access */
 #define _PAGE_RO	0x0600	/* Supervisor RO, User no access */
 
+/* cache related flags non existing on 8xx */
+#define _PAGE_COHERENT	0
+#define _PAGE_WRITETHRU	0
+
+#define _PAGE_KERNEL_RO		(_PAGE_SH | _PAGE_RO)
+#define _PAGE_KERNEL_ROX	(_PAGE_SH | _PAGE_RO | _PAGE_EXEC)
+#define _PAGE_KERNEL_RW		(_PAGE_SH | _PAGE_DIRTY)
+#define _PAGE_KERNEL_RWX	(_PAGE_SH | _PAGE_DIRTY | _PAGE_EXEC)
+
 #define _PMD_PRESENT	0x0001
+#define _PMD_PRESENT_MASK	_PMD_PRESENT
 #define _PMD_BAD	0x0fd0
 #define _PMD_PAGE_MASK	0x000c
 #define _PMD_PAGE_8M	0x000c
 #define _PMD_PAGE_512K	0x0004
 #define _PMD_USER	0x0020	/* APG 1 */
 
-/* Until my rework is finished, 8xx still needs atomic PTE updates */
-#define PTE_ATOMIC_UPDATES	1
+#define _PTE_NONE_MASK	0
 
 #ifdef CONFIG_PPC_16K_PAGES
-#define _PAGE_PSIZE	_PAGE_HUGE
+#define _PAGE_PSIZE	_PAGE_SPS
+#else
+#define _PAGE_PSIZE		0
+#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)
+
+#ifndef __ASSEMBLY__
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_RO);
+}
+
+#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)
+{
+	return __pte(pte_val(pte) & ~_PAGE_RO);
+}
+
+#define pte_mkwrite pte_mkwrite
+
+static inline bool pte_user(pte_t pte)
+{
+	return !(pte_val(pte) & _PAGE_SH);
+}
+
+#define pte_user pte_user
+
+static inline pte_t pte_mkprivileged(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SH);
+}
+
+#define pte_mkprivileged pte_mkprivileged
+
+static inline pte_t pte_mkuser(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_SH);
+}
+
+#define pte_mkuser pte_mkuser
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPS);
+}
+
+#define pte_mkhuge pte_mkhuge
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h b/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h
index d1ee24e..0fc1bd4 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h
@@ -31,11 +31,44 @@
 #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)
+#define _PMD_USER	0
+
+#define _PTE_NONE_MASK	0
 
 #define PTE_WIMGE_SHIFT (6)
 
+/*
+ * We define 2 sets of base prot bits, one for basic pages (ie,
+ * cacheable kernel and user pages) and one for non cacheable
+ * 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)
+#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
+#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_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_FSL_BOOKE_H */
diff --git a/arch/powerpc/include/asm/nohash/32/slice.h b/arch/powerpc/include/asm/nohash/32/slice.h
index 777d62e..39eb015 100644
--- a/arch/powerpc/include/asm/nohash/32/slice.h
+++ b/arch/powerpc/include/asm/nohash/32/slice.h
@@ -13,6 +13,8 @@
 #define SLICE_NUM_HIGH		0ul
 #define GET_HIGH_SLICE_INDEX(addr)	(addr & 0)
 
+#define SLB_ADDR_LIMIT_DEFAULT	DEFAULT_MAP_WINDOW
+
 #endif /* CONFIG_PPC_MM_SLICES */
 
 #endif /* _ASM_POWERPC_NOHASH_32_SLICE_H */
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index e2d62d0..b9534a7 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_PGALLOC_64_H
 #define _ASM_POWERPC_PGALLOC_64_H
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/slab.h>
@@ -18,40 +15,6 @@
 };
 extern struct vmemmap_backing *vmemmap_list;
 
-/*
- * 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
- * handle allocation.  For PTE pages (which are linked to a struct
- * page for now, and drawn from the main get_free_pages() pool), the
- * allocation size will be (2^index_size * sizeof(pointer)) and
- * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
- *
- * The maximum index size needs to be big enough to allow any
- * pagetable sizes we need, but small enough to fit in the low bits of
- * any page table pointer.  In other words all pagetables, even tiny
- * ones, must be aligned to allow at least enough low 0 bits to
- * contain this value.  This value is also used as a mask, so it must
- * be one less than a power of two.
- */
-#define MAX_PGTABLE_INDEX_SIZE	0xf
-
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) ({				\
-			BUG_ON(!(shift));		\
-			pgtable_cache[(shift) - 1];	\
-		})
-
-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));
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
-}
-
 #define pgd_populate(MM, PGD, PUD)	pgd_set(PGD, (unsigned long)PUD)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
@@ -79,11 +42,9 @@
 static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 				pgtable_t pte_page)
 {
-	pmd_set(pmd, (unsigned long)page_address(pte_page));
+	pmd_set(pmd, (unsigned long)pte_page);
 }
 
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
 	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
@@ -95,93 +56,9 @@
 	kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
 }
 
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
-					  unsigned long address)
-{
-	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
-				      unsigned long address)
-{
-	struct page *page;
-	pte_t *pte;
-
-	pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT);
-	if (!pte)
-		return NULL;
-	page = virt_to_page(pte);
-	if (!pgtable_page_ctor(page)) {
-		__free_page(page);
-		return NULL;
-	}
-	return page;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-	pgtable_page_dtor(ptepage);
-	__free_page(ptepage);
-}
-
-static inline void pgtable_free(void *table, int shift)
-{
-	if (!shift) {
-		pgtable_page_dtor(virt_to_page(table));
-		free_page((unsigned long)table);
-	} else {
-		BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-		kmem_cache_free(PGT_CACHE(shift), table);
-	}
-}
-
-#define get_hugepd_cache_index(x)	(x)
-#ifdef CONFIG_SMP
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
-{
-	unsigned long pgf = (unsigned long)table;
-
-	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-	pgf |= shift;
-	tlb_remove_table(tlb, (void *)pgf);
-}
-
-static inline void __tlb_remove_table(void *_table)
-{
-	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
-	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
-
-	pgtable_free(table, shift);
-}
-
-#else
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
-{
-	pgtable_free(table, shift);
-}
-#endif
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
-				  unsigned long address)
-{
-	tlb_flush_pgtable(tlb, address);
-	pgtable_free_tlb(tlb, page_address(table), 0);
-}
-
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
 	pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
-#ifndef CONFIG_PPC_64K_PAGES
 #define __pud_free_tlb(tlb, pud, addr)		      \
 	pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
 
-#endif /* CONFIG_PPC_64K_PAGES */
-
-#define check_pgt_cache()	do { } while (0)
-
 #endif /* _ASM_POWERPC_PGALLOC_64_H */
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 7cd6809..9a33b8b 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -10,10 +10,6 @@
 #include <asm/barrier.h>
 #include <asm/asm-const.h>
 
-#ifdef CONFIG_PPC_64K_PAGES
-#error "Page size not supported"
-#endif
-
 #define FIRST_USER_ADDRESS	0UL
 
 /*
@@ -23,11 +19,7 @@
 			    PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
 #define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE)
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define PMD_CACHE_INDEX	(PMD_INDEX_SIZE + 1)
-#else
 #define PMD_CACHE_INDEX	PMD_INDEX_SIZE
-#endif
 #define PUD_CACHE_INDEX PUD_INDEX_SIZE
 
 /*
@@ -61,6 +53,7 @@
 #define  PHB_IO_BASE	(ISA_IO_END)
 #define  PHB_IO_END	(KERN_IO_START + FULL_IO_SIZE)
 #define IOREMAP_BASE	(PHB_IO_END)
+#define IOREMAP_START	(ioremap_bot)
 #define IOREMAP_END	(KERN_VIRT_START + KERN_VIRT_SIZE)
 
 
@@ -73,7 +66,6 @@
 
 #define VMALLOC_REGION_ID	(REGION_ID(VMALLOC_START))
 #define KERNEL_REGION_ID	(REGION_ID(PAGE_OFFSET))
-#define VMEMMAP_REGION_ID	(0xfUL)	/* Server only */
 #define USER_REGION_ID		(0UL)
 
 /*
@@ -89,11 +81,47 @@
  * Include the PTE bits definitions
  */
 #include <asm/nohash/pte-book3e.h>
-#include <asm/pte-common.h>
+
+#define _PAGE_SAO	0
+
+#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__
 /* 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);
+}
+
+static inline pte_t pte_mkexec(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_EXEC);
+}
+
 #define PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
 #define PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
 
@@ -169,7 +197,8 @@
   (((pte_t *) pmd_page_vaddr(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)))
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_unmap(pte)			do { } while(0)
+
+static inline void pte_unmap(pte_t *pte) { }
 
 /* to find an entry in a kernel page-table-directory */
 /* This now only contains the vmalloc pages */
@@ -239,6 +268,7 @@
 	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)
 {
@@ -313,9 +343,7 @@
 #define MAX_SWAPFILES_CHECK() do { \
 	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \
 	} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
 				& ((1UL << SWP_TYPE_BITS) - 1))
@@ -327,8 +355,7 @@
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __swp_entry_to_pte(x)		__pte((x).val)
 
-extern int map_kernel_page(unsigned long ea, unsigned long pa,
-			   unsigned long flags);
+int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot);
 extern int __meminit vmemmap_create_mapping(unsigned long start,
 					    unsigned long page_size,
 					    unsigned long phys);
diff --git a/arch/powerpc/include/asm/nohash/64/slice.h b/arch/powerpc/include/asm/nohash/64/slice.h
deleted file mode 100644
index ad0d6e3..0000000
--- a/arch/powerpc/include/asm/nohash/64/slice.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_NOHASH_64_SLICE_H
-#define _ASM_POWERPC_NOHASH_64_SLICE_H
-
-#ifdef CONFIG_PPC_64K_PAGES
-#define get_slice_psize(mm, addr)	MMU_PAGE_64K
-#else /* CONFIG_PPC_64K_PAGES */
-#define get_slice_psize(mm, addr)	MMU_PAGE_4K
-#endif /* !CONFIG_PPC_64K_PAGES */
-#define slice_set_user_psize(mm, psize)	do { BUG(); } while (0)
-
-#endif /* _ASM_POWERPC_NOHASH_64_SLICE_H */
diff --git a/arch/powerpc/include/asm/nohash/hugetlb-book3e.h b/arch/powerpc/include/asm/nohash/hugetlb-book3e.h
new file mode 100644
index 0000000..ecd8694
--- /dev/null
+++ b/arch/powerpc/include/asm/nohash/hugetlb-book3e.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_NOHASH_HUGETLB_BOOK3E_H
+#define _ASM_POWERPC_NOHASH_HUGETLB_BOOK3E_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_FSL_BOOK3E */
+	*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 */
+		return -EINVAL;
+
+	return shift_to_mmu_psize(shift);
+}
+
+#endif /* _ASM_POWERPC_NOHASH_HUGETLB_BOOK3E_H */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/nohash/mmu-book3e.h
similarity index 99%
rename from arch/powerpc/include/asm/mmu-book3e.h
rename to arch/powerpc/include/asm/nohash/mmu-book3e.h
index e200729..4c9777d 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/nohash/mmu-book3e.h
@@ -306,6 +306,8 @@
 
 #define mmu_cleanup_all NULL
 
+#define MAX_PHYSMEM_BITS        44
+
 #endif
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/nohash/mmu.h b/arch/powerpc/include/asm/nohash/mmu.h
new file mode 100644
index 0000000..edc793e
--- /dev/null
+++ b/arch/powerpc/include/asm/nohash/mmu.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#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)
+/* 44x-style software loaded TLB */
+#include <asm/nohash/32/mmu-44x.h>
+#elif defined(CONFIG_PPC_BOOK3E_MMU)
+/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */
+#include <asm/nohash/mmu-book3e.h>
+#elif defined (CONFIG_PPC_8xx)
+/* Motorola/Freescale 8xx software loaded TLB */
+#include <asm/nohash/32/mmu-8xx.h>
+#endif
+
+#endif /* _ASM_POWERPC_NOHASH_MMU_H_ */
diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h
index 0634f29..332b13b 100644
--- a/arch/powerpc/include/asm/nohash/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/pgalloc.h
@@ -3,6 +3,7 @@
 #define _ASM_POWERPC_NOHASH_PGALLOC_H
 
 #include <linux/mm.h>
+#include <linux/slab.h>
 
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 #ifdef CONFIG_PPC64
@@ -16,9 +17,64 @@
 }
 #endif /* !CONFIG_PPC_BOOK3E */
 
+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));
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
+}
+
 #ifdef CONFIG_PPC64
 #include <asm/nohash/64/pgalloc.h>
 #else
 #include <asm/nohash/32/pgalloc.h>
 #endif
+
+static inline void pgtable_free(void *table, int shift)
+{
+	if (!shift) {
+		pte_fragment_free((unsigned long *)table, 0);
+	} else {
+		BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(shift), table);
+	}
+}
+
+#define get_hugepd_cache_index(x)	(x)
+
+#ifdef CONFIG_SMP
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+	unsigned long pgf = (unsigned long)table;
+
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+	pgf |= shift;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+	pgtable_free(table, shift);
+}
+
+#else
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+	pgtable_free(table, shift);
+}
+#endif
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+				  unsigned long address)
+{
+	tlb_flush_pgtable(tlb, address);
+	pgtable_free_tlb(tlb, table, 0);
+}
 #endif /* _ASM_POWERPC_NOHASH_PGALLOC_H */
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index b321c82..7fed9dc 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -8,18 +8,50 @@
 #include <asm/nohash/32/pgtable.h>
 #endif
 
+/* 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)
+#define PAGE_KERNEL_NCG	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
+				 _PAGE_NO_CACHE | _PAGE_GUARDED)
+#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX)
+#define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)
+
+/*
+ * 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
+
+/* Advertise special mapping type for AGP */
+#define PAGE_AGP		(PAGE_KERNEL_NC)
+#define HAVE_PAGE_AGP
+
 #ifndef __ASSEMBLY__
 
 /* Generic accessors to PTE bits */
+#ifndef pte_write
 static inline int pte_write(pte_t pte)
 {
-	return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO;
+	return pte_val(pte) & _PAGE_RW;
 }
+#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; }
-static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
+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
 /*
@@ -29,8 +61,7 @@
  */
 static inline int pte_protnone(pte_t pte)
 {
-	return (pte_val(pte) &
-		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
+	return pte_present(pte) && !pte_user(pte);
 }
 
 static inline int pmd_protnone(pmd_t pmd)
@@ -44,6 +75,23 @@
 	return pte_val(pte) & _PAGE_PRESENT;
 }
 
+static inline bool pte_hw_valid(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+/*
+ * Don't just check for any non zero bits in __PAGE_USER, 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.
+ */
+#ifndef pte_user
+static inline bool pte_user(pte_t pte)
+{
+	return (pte_val(pte) & _PAGE_USER) == _PAGE_USER;
+}
+#endif
+
 /*
  * We only find page table entry in the last level
  * Hence no need for other accessors
@@ -77,42 +125,26 @@
 	return pte_val(pte) >> PTE_RPN_SHIFT; }
 
 /* Generic modifiers for PTE bits */
-static inline pte_t pte_wrprotect(pte_t pte)
+static inline pte_t pte_exprotect(pte_t pte)
 {
-	pte_basic_t ptev;
-
-	ptev = pte_val(pte) & ~(_PAGE_RW | _PAGE_HWWRITE);
-	ptev |= _PAGE_RO;
-	return __pte(ptev);
+	return __pte(pte_val(pte) & ~_PAGE_EXEC);
 }
 
+#ifndef pte_mkclean
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	return __pte(pte_val(pte) & ~(_PAGE_DIRTY | _PAGE_HWWRITE));
+	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
 }
+#endif
 
 static inline pte_t pte_mkold(pte_t pte)
 {
 	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
 }
 
-static inline pte_t pte_mkwrite(pte_t pte)
+static inline pte_t pte_mkpte(pte_t pte)
 {
-	pte_basic_t ptev;
-
-	ptev = pte_val(pte) & ~_PAGE_RO;
-	ptev |= _PAGE_RW;
-	return __pte(ptev);
-}
-
-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);
+	return pte;
 }
 
 static inline pte_t pte_mkspecial(pte_t pte)
@@ -120,10 +152,26 @@
 	return __pte(pte_val(pte) | _PAGE_SPECIAL);
 }
 
+#ifndef pte_mkhuge
 static inline pte_t pte_mkhuge(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_HUGE);
+	return __pte(pte_val(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)
 {
@@ -161,7 +209,11 @@
 	/* Anything else just stores the PTE normally. That covers all 64-bit
 	 * cases, and 32-bit non-hash with 32-bit PTEs.
 	 */
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
+	ptep->pte = ptep->pte1 = ptep->pte2 = ptep->pte3 = pte_val(pte);
+#else
 	*ptep = pte;
+#endif
 
 	/*
 	 * With hardware tablewalk, a sync is needed to ensure that
@@ -197,6 +249,8 @@
 #if _PAGE_WRITETHRU != 0
 #define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \
 				            _PAGE_COHERENT | _PAGE_WRITETHRU))
+#else
+#define pgprot_cached_wthru(prot)	pgprot_noncached(prot)
 #endif
 
 #define pgprot_cached_noncoherent(prot) \
@@ -239,5 +293,18 @@
 #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_FSL_BOOK3E) && 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
+
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/powerpc/include/asm/nohash/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-book3e.h
index 12730b8..813918f 100644
--- a/arch/powerpc/include/asm/nohash/pte-book3e.h
+++ b/arch/powerpc/include/asm/nohash/pte-book3e.h
@@ -60,13 +60,8 @@
 #define _PAGE_SPECIAL	_PAGE_SW0
 
 /* Base page size */
-#ifdef CONFIG_PPC_64K_PAGES
-#define _PAGE_PSIZE	_PAGE_PSIZE_64K
-#define PTE_RPN_SHIFT	(28)
-#else
 #define _PAGE_PSIZE	_PAGE_PSIZE_4K
 #define	PTE_RPN_SHIFT	(24)
-#endif
 
 #define PTE_WIMGE_SHIFT (19)
 #define PTE_BAP_SHIFT	(2)
@@ -77,7 +72,48 @@
 #define _PMD_PRESENT	0
 #define _PMD_PRESENT_MASK (PAGE_MASK)
 #define _PMD_BAD	(~PAGE_MASK)
+#define _PMD_USER	0
+#else
+#define _PTE_NONE_MASK	0
 #endif
 
+/*
+ * We define 2 sets of base prot bits, one for basic pages (ie,
+ * cacheable kernel and user pages) and one for non cacheable
+ * 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)
+#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_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)
+
+#ifndef __ASSEMBLY__
+static inline pte_t pte_mkprivileged(pte_t pte)
+{
+	return __pte((pte_val(pte) & ~_PAGE_USER) | _PAGE_PRIVILEGED);
+}
+
+#define pte_mkprivileged pte_mkprivileged
+
+static inline pte_t pte_mkuser(pte_t pte)
+{
+	return __pte((pte_val(pte) & ~_PAGE_PRIVILEGED) | _PAGE_USER);
+}
+
+#define pte_mkuser pte_mkuser
+#endif /* __ASSEMBLY__ */
+
 #endif /* __KERNEL__ */
 #endif /*  _ASM_POWERPC_NOHASH_PTE_BOOK3E_H */
diff --git a/arch/powerpc/include/asm/nvram.h b/arch/powerpc/include/asm/nvram.h
index 09a518b..eda7fac 100644
--- a/arch/powerpc/include/asm/nvram.h
+++ b/arch/powerpc/include/asm/nvram.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * NVRAM definitions and access functions.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_NVRAM_H
 #define _ASM_POWERPC_NVRAM_H
@@ -78,9 +74,6 @@
 extern u8	pmac_xpram_read(int xpaddr);
 extern void	pmac_xpram_write(int xpaddr, u8 data);
 
-/* Synchronize NVRAM */
-extern void	nvram_sync(void);
-
 /* Initialize NVRAM OS partition */
 extern int __init nvram_init_os_partition(struct nvram_os_partition *part);
 
@@ -98,10 +91,4 @@
 				    unsigned int err_type,
 				    unsigned int error_log_cnt);
 
-/* Determine NVRAM size */
-extern ssize_t nvram_get_size(void);
-
-/* Normal access to NVRAM */
-extern unsigned char nvram_read_byte(int i);
-extern void nvram_write_byte(unsigned char c, int i);
 #endif /* _ASM_POWERPC_NVRAM_H */
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index 8365353..378e399 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * OPAL API definitions.
  *
  * Copyright 2011-2015 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef __OPAL_API_H
@@ -186,8 +182,8 @@
 #define OPAL_XIVE_FREE_IRQ			140
 #define OPAL_XIVE_SYNC				141
 #define OPAL_XIVE_DUMP				142
-#define OPAL_XIVE_RESERVED3			143
-#define OPAL_XIVE_RESERVED4			144
+#define OPAL_XIVE_GET_QUEUE_STATE		143
+#define OPAL_XIVE_SET_QUEUE_STATE		144
 #define OPAL_SIGNAL_SYSTEM_RESET		145
 #define OPAL_NPU_INIT_CONTEXT			146
 #define OPAL_NPU_DESTROY_CONTEXT		147
@@ -209,8 +205,13 @@
 #define OPAL_SENSOR_GROUP_ENABLE		163
 #define OPAL_PCI_GET_PBCQ_TUNNEL_BAR		164
 #define OPAL_PCI_SET_PBCQ_TUNNEL_BAR		165
+#define OPAL_HANDLE_HMI2			166
 #define	OPAL_NX_COPROC_INIT			167
-#define OPAL_LAST				167
+#define OPAL_XIVE_GET_VP_STATE			170
+#define OPAL_MPIPL_UPDATE			173
+#define OPAL_MPIPL_REGISTER_TAG			174
+#define OPAL_MPIPL_QUERY_TAG			175
+#define OPAL_LAST				175
 
 #define QUIESCE_HOLD			1 /* Spin all calls at entry */
 #define QUIESCE_REJECT			2 /* Fail all calls with OPAL_BUSY */
@@ -455,6 +456,7 @@
 	OPAL_MSG_DPO		= 5,
 	OPAL_MSG_PRD		= 6,
 	OPAL_MSG_OCC		= 7,
+	OPAL_MSG_PRD2		= 8,
 	OPAL_MSG_TYPE_MAX,
 };
 
@@ -566,6 +568,7 @@
 	CHECKSTOP_TYPE_UNKNOWN	=	0,
 	CHECKSTOP_TYPE_CORE	=	1,
 	CHECKSTOP_TYPE_NX	=	2,
+	CHECKSTOP_TYPE_NPU	=	3
 };
 
 enum OpalHMI_CoreXstopReason {
@@ -634,6 +637,15 @@
 	} u;
 };
 
+/* OPAL_HANDLE_HMI2 out_flags */
+enum {
+	OPAL_HMI_FLAGS_TB_RESYNC	= (1ull << 0), /* Timebase has been resynced */
+	OPAL_HMI_FLAGS_DEC_LOST		= (1ull << 1), /* DEC lost, needs to be reprogrammed */
+	OPAL_HMI_FLAGS_HDEC_LOST	= (1ull << 2), /* HDEC lost, needs to be reprogrammed */
+	OPAL_HMI_FLAGS_TOD_TB_FAIL	= (1ull << 3), /* TOD/TB recovery failed. */
+	OPAL_HMI_FLAGS_NEW_EVENT	= (1ull << 63), /* An event has been created */
+};
+
 enum {
 	OPAL_P7IOC_DIAG_TYPE_NONE	= 0,
 	OPAL_P7IOC_DIAG_TYPE_RGC	= 1,
@@ -1050,6 +1062,8 @@
 enum {
 	OPAL_REBOOT_NORMAL		= 0,
 	OPAL_REBOOT_PLATFORM_ERROR	= 1,
+	OPAL_REBOOT_FULL_IPL		= 2,
+	OPAL_REBOOT_MPIPL		= 3,
 };
 
 /* Argument to OPAL_PCI_TCE_KILL */
@@ -1117,6 +1131,7 @@
 enum {
 	OPAL_IMC_COUNTERS_NEST = 1,
 	OPAL_IMC_COUNTERS_CORE = 2,
+	OPAL_IMC_COUNTERS_TRACE = 3,
 };
 
 
@@ -1125,6 +1140,44 @@
 #define OPAL_PCI_P2P_LOAD		0x2
 #define OPAL_PCI_P2P_STORE		0x4
 
+/* MPIPL update operations */
+enum opal_mpipl_ops {
+	OPAL_MPIPL_ADD_RANGE			= 0,
+	OPAL_MPIPL_REMOVE_RANGE			= 1,
+	OPAL_MPIPL_REMOVE_ALL			= 2,
+	OPAL_MPIPL_FREE_PRESERVED_MEMORY	= 3,
+};
+
+/* Tag will point to various metadata area. Kernel will
+ * use tag to get metadata value.
+ */
+enum opal_mpipl_tags {
+	OPAL_MPIPL_TAG_CPU	= 0,
+	OPAL_MPIPL_TAG_OPAL	= 1,
+	OPAL_MPIPL_TAG_KERNEL	= 2,
+	OPAL_MPIPL_TAG_BOOT_MEM	= 3,
+};
+
+/* Preserved memory details */
+struct opal_mpipl_region {
+	__be64	src;
+	__be64	dest;
+	__be64	size;
+};
+
+/* Structure version */
+#define OPAL_MPIPL_VERSION		0x01
+
+struct opal_mpipl_fadump {
+	u8	version;
+	u8	reserved[7];
+	__be32	crashing_pir;	/* OPAL crashing CPU PIR */
+	__be32	cpu_data_version;
+	__be32	cpu_data_size;
+	__be32	region_cnt;
+	struct	opal_mpipl_region region[];
+} __packed;
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __OPAL_API_H */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index ff38664..a0cf8fb 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * PowerNV OPAL definitions.
  *
  * Copyright 2011 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_OPAL_H
@@ -43,6 +39,7 @@
 				uint64_t PE_handle);
 int64_t opal_npu_tl_set(uint64_t phb_id, uint32_t bdfn, long cap,
 			uint64_t rate_phys, uint32_t size);
+
 int64_t opal_console_write(int64_t term_number, __be64 *length,
 			   const uint8_t *buffer);
 int64_t opal_console_read(int64_t term_number, __be64 *length,
@@ -203,6 +200,7 @@
 int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data);
 int64_t opal_sensor_read_u64(u32 sensor_hndl, int token, __be64 *sensor_data);
 int64_t opal_handle_hmi(void);
+int64_t opal_handle_hmi2(__be64 *out_flags);
 int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end);
 int64_t opal_unregister_dump_region(uint32_t id);
 int64_t opal_slw_set_reg(uint64_t cpu_pir, uint64_t sprn, uint64_t val);
@@ -275,12 +273,17 @@
 int64_t opal_xive_set_vp_info(uint64_t vp,
 			      uint64_t flags,
 			      uint64_t report_cl_pair);
-int64_t opal_xive_allocate_irq(uint32_t chip_id);
+int64_t opal_xive_allocate_irq_raw(uint32_t chip_id);
 int64_t opal_xive_free_irq(uint32_t girq);
 int64_t opal_xive_sync(uint32_t type, uint32_t id);
 int64_t opal_xive_dump(uint32_t type, uint32_t id);
-int64_t opal_pci_set_p2p(uint64_t phb_init, uint64_t phb_target,
-			uint64_t desc, uint16_t pe_number);
+int64_t opal_xive_get_queue_state(uint64_t vp, uint32_t prio,
+				  __be32 *out_qtoggle,
+				  __be32 *out_qindex);
+int64_t opal_xive_set_queue_state(uint64_t vp, uint32_t prio,
+				  uint32_t qtoggle,
+				  uint32_t qindex);
+int64_t opal_xive_get_vp_state(uint64_t vp, __be64 *out_w01);
 
 int64_t opal_imc_counters_init(uint32_t type, uint64_t address,
 							uint64_t cpu_pir);
@@ -295,6 +298,10 @@
 int opal_sensor_group_enable(u32 group_hndl, int token, bool enable);
 int opal_nx_coproc_init(uint32_t chip_id, uint32_t ct);
 
+s64 opal_mpipl_update(enum opal_mpipl_ops op, u64 src, u64 dest, u64 size);
+s64 opal_mpipl_register_tag(enum opal_mpipl_tags tag, u64 addr);
+s64 opal_mpipl_query_tag(enum opal_mpipl_tags tag, u64 *addr);
+
 s64 opal_signal_system_reset(s32 cpu);
 s64 opal_quiesce(u64 shutdown_type, s32 cpu);
 
@@ -347,10 +354,12 @@
 extern int opal_sensor_init(void);
 extern int opal_hmi_handler_init(void);
 extern int opal_event_init(void);
+int opal_power_control_init(void);
 
 extern int opal_machine_check(struct pt_regs *regs);
 extern bool opal_mce_check_early_recovery(struct pt_regs *regs);
 extern int opal_hmi_exception_early(struct pt_regs *regs);
+extern int opal_hmi_exception_early2(struct pt_regs *regs);
 extern int opal_handle_hmi_exception(struct pt_regs *regs);
 
 extern void opal_shutdown(void);
diff --git a/arch/powerpc/include/asm/oprofile_impl.h b/arch/powerpc/include/asm/oprofile_impl.h
index 61fe5d6..2a166c2 100644
--- a/arch/powerpc/include/asm/oprofile_impl.h
+++ b/arch/powerpc/include/asm/oprofile_impl.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
  *
  * Based on alpha version.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_OPROFILE_IMPL_H
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index ad4f161..e3cc9eb 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This control block defines the PACA which defines the processor
  * specific data for each logical processor on the system.
  * There are some pointers defined that are utilized by PLIC.
  *
  * C 2001 PPC 64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_PACA_H
 #define _ASM_POWERPC_PACA_H
@@ -34,6 +30,8 @@
 #include <asm/cpuidle.h>
 #include <asm/atomic.h>
 
+#include <asm-generic/mmiowb_types.h>
+
 register struct paca_struct *local_paca asm("r13");
 
 #if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP)
@@ -113,7 +111,13 @@
  				 * on the linear mapping */
 	/* SLB related definitions */
 	u16 vmalloc_sllp;
-	u16 slb_cache_ptr;
+	u8 slb_cache_ptr;
+	u8 stab_rr;			/* stab/slb round-robin counter */
+#ifdef CONFIG_DEBUG_VM
+	u8 in_kernel_slb_handler;
+#endif
+	u32 slb_used_bitmap;		/* Bitmaps for first 32 SLB entries. */
+	u32 slb_kern_bitmap;
 	u32 slb_cache[SLB_CACHE_ENTRIES];
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
@@ -160,15 +164,14 @@
 	 */
 	struct task_struct *__current;	/* Pointer to current */
 	u64 kstack;			/* Saved Kernel stack addr */
-	u64 stab_rr;			/* stab/slb round-robin counter */
 	u64 saved_r1;			/* r1 save for RTAS calls or PM or EE=0 */
 	u64 saved_msr;			/* MSR saved here by enter_rtas */
+#ifdef CONFIG_PPC_BOOK3E
 	u16 trap_save;			/* Used when bad stack is encountered */
+#endif
 	u8 irq_soft_mask;		/* mask for irq soft masking */
 	u8 irq_happened;		/* irq happened while soft-disabled */
-	u8 io_sync;			/* writel() needs spin_unlock sync */
 	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
-	u8 nap_state_lost;		/* NV GPR values lost in power7_idle */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	u8 pmcregs_in_use;		/* pseries puts this in lppaca */
 #endif
@@ -178,23 +181,28 @@
 #endif
 
 #ifdef CONFIG_PPC_POWERNV
-	/* Per-core mask tracking idle threads and a lock bit-[L][TTTTTTTT] */
-	u32 *core_idle_state_ptr;
-	u8 thread_idle_state;		/* PNV_THREAD_RUNNING/NAP/SLEEP	*/
-	/* Mask to indicate thread id in core */
-	u8 thread_mask;
-	/* Mask to denote subcore sibling threads */
-	u8 subcore_sibling_mask;
-	/* Flag to request this thread not to stop */
-	atomic_t dont_stop;
-	/* The PSSCR value that the kernel requested before going to stop */
-	u64 requested_psscr;
+	/* PowerNV idle fields */
+	/* PNV_CORE_IDLE_* bits, all siblings work on thread 0 paca */
+	unsigned long idle_state;
+	union {
+		/* P7/P8 specific fields */
+		struct {
+			/* PNV_THREAD_RUNNING/NAP/SLEEP	*/
+			u8 thread_idle_state;
+			/* Mask to denote subcore sibling threads */
+			u8 subcore_sibling_mask;
+		};
 
-	/*
-	 * Save area for additional SPRs that need to be
-	 * saved/restored during cpuidle stop.
-	 */
-	struct stop_sprs stop_sprs;
+		/* P9 specific fields */
+		struct {
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+			/* The PSSCR value that the kernel requested before going to stop */
+			u64 requested_psscr;
+			/* Flag to request this thread not to stop */
+			atomic_t dont_stop;
+#endif
+		};
+	};
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -250,6 +258,18 @@
 #ifdef CONFIG_PPC_PSERIES
 	u8 *mce_data_buf;		/* buffer to hold per cpu rtas errlog */
 #endif /* CONFIG_PPC_PSERIES */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* Capture SLB related old contents in MCE handler. */
+	struct slb_entry *mce_faulty_slbs;
+	u16 slb_save_cache_ptr;
+#endif /* CONFIG_PPC_BOOK3S_64 */
+#ifdef CONFIG_STACKPROTECTOR
+	unsigned long canary;
+#endif
+#ifdef CONFIG_MMIOWB
+	struct mmiowb_state mmiowb_state;
+#endif
 } ____cacheline_aligned;
 
 extern void copy_mm_to_paca(struct mm_struct *mm);
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index f6a1265..c8bb14f 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_PAGE_H
 #define _ASM_POWERPC_PAGE_H
 
 /*
  * Copyright (C) 2001,2005 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef __ASSEMBLY__
@@ -20,28 +16,23 @@
 
 /*
  * On regular PPC32 page size is 4K (but we support 4K/16K/64K/256K pages
- * on PPC44x). For PPC64 we support either 4K or 64K software
+ * on PPC44x and 4K/16K on 8xx). For PPC64 we support either 4K or 64K software
  * page size. When using 64K pages however, whether we are really supporting
  * 64K pages in HW or not is irrelevant to those definitions.
  */
-#if defined(CONFIG_PPC_256K_PAGES)
-#define PAGE_SHIFT		18
-#elif defined(CONFIG_PPC_64K_PAGES)
-#define PAGE_SHIFT		16
-#elif defined(CONFIG_PPC_16K_PAGES)
-#define PAGE_SHIFT		14
-#else
-#define PAGE_SHIFT		12
-#endif
-
+#define PAGE_SHIFT		CONFIG_PPC_PAGE_SHIFT
 #define PAGE_SIZE		(ASM_CONST(1) << PAGE_SHIFT)
 
 #ifndef __ASSEMBLY__
-#ifdef CONFIG_HUGETLB_PAGE
-extern bool hugetlb_disabled;
-extern unsigned int HPAGE_SHIFT;
-#else
+#ifndef CONFIG_HUGETLB_PAGE
 #define HPAGE_SHIFT PAGE_SHIFT
+#elif defined(CONFIG_PPC_BOOK3S_64)
+extern unsigned int hpage_shift;
+#define HPAGE_SHIFT hpage_shift
+#elif defined(CONFIG_PPC_8xx)
+#define HPAGE_SHIFT		19	/* 512k pages */
+#elif defined(CONFIG_PPC_FSL_BOOK3E)
+#define HPAGE_SHIFT		22	/* 4M pages */
 #endif
 #define HPAGE_SIZE		((1UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
@@ -141,18 +132,7 @@
 #define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 
-#ifdef CONFIG_PPC_BOOK3S_64
-/*
- * On hash the vmalloc and other regions alias to the kernel region when passed
- * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can
- * return true for some vmalloc addresses, which is incorrect. So explicitly
- * check that the address is in the kernel region.
- */
-#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \
-				pfn_valid(virt_to_pfn(kaddr)))
-#else
 #define virt_addr_valid(kaddr)	pfn_valid(virt_to_pfn(kaddr))
-#endif
 
 /*
  * On Book-E parts we need __va to parse the device tree and we can't
@@ -235,9 +215,19 @@
 /*
  * gcc miscompiles (unsigned long)(&static_var) - PAGE_OFFSET
  * with -mcmodel=medium, so we use & and | instead of - and + on 64-bit.
+ * This also results in better code generation.
  */
-#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET))
-#define __pa(x) ((unsigned long)(x) & 0x0fffffffffffffffUL)
+#define __va(x)								\
+({									\
+	VIRTUAL_BUG_ON((unsigned long)(x) >= PAGE_OFFSET);		\
+	(void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET);	\
+})
+
+#define __pa(x)								\
+({									\
+	VIRTUAL_BUG_ON((unsigned long)(x) < PAGE_OFFSET);		\
+	(unsigned long)(x) & 0x0fffffffffffffffUL;			\
+})
 
 #else /* 32-bit, non book E */
 #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + PAGE_OFFSET - MEMORY_START))
@@ -289,7 +279,7 @@
  * page tables at arbitrary addresses, this breaks and will have to change.
  */
 #ifdef CONFIG_PPC64
-#define PD_HUGE 0x8000000000000000
+#define PD_HUGE 0x8000000000000000UL
 #else
 #define PD_HUGE 0x80000000
 #endif
@@ -326,7 +316,6 @@
 extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
 extern void copy_user_page(void *to, void *from, unsigned long vaddr,
 		struct page *p);
-extern int page_is_ram(unsigned long pfn);
 extern int devmem_is_allowed(unsigned long pfn);
 
 #ifdef CONFIG_PPC_SMLPAR
@@ -335,23 +324,18 @@
 #endif
 
 struct vm_area_struct;
-#ifdef CONFIG_PPC_BOOK3S_64
-/*
- * For BOOK3s 64 with 4k and 64K linux page size
- * we want to use pointers, because the page table
- * actually store pfn
- */
-typedef pte_t *pgtable_t;
-#else
-#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC64)
-typedef pte_t *pgtable_t;
-#else
-typedef struct page *pgtable_t;
-#endif
-#endif
 
 #include <asm-generic/memory_model.h>
 #endif /* __ASSEMBLY__ */
 #include <asm/slice.h>
 
+/*
+ * Allow 30-bit DMA for very limited Broadcom wifi chips on many powerbooks.
+ */
+#ifdef CONFIG_PPC32
+#define ARCH_ZONE_DMA_BITS 30
+#else
+#define ARCH_ZONE_DMA_BITS 31
+#endif
+
 #endif /* _ASM_POWERPC_PAGE_H */
diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h
index 5c378e9..d64dfe3 100644
--- a/arch/powerpc/include/asm/page_32.h
+++ b/arch/powerpc/include/asm/page_32.h
@@ -22,7 +22,8 @@
 #define PTE_FLAGS_OFFSET	0
 #endif
 
-#ifdef CONFIG_PPC_256K_PAGES
+#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 */
 #else
 #define PTE_SHIFT	(PAGE_SHIFT - PTE_T_LOG2)	/* full page */
@@ -39,6 +40,8 @@
 typedef unsigned long pte_basic_t;
 #endif
 
+#include <asm/bug.h>
+
 /*
  * Clear page using the dcbz instruction, which doesn't cause any
  * memory traffic (except to write out any cache lines which get
@@ -48,6 +51,8 @@
 {
 	unsigned int i;
 
+	WARN_ON((unsigned long)addr & (L1_CACHE_BYTES - 1));
+
 	for (i = 0; i < PAGE_SIZE / L1_CACHE_BYTES; i++, addr += L1_CACHE_BYTES)
 		dcbz(addr);
 }
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index c0ce17e..5962797 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_PAGE_64_H
 #define _ASM_POWERPC_PAGE_64_H
 
 /*
  * Copyright (C) 2001 PPC64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/asm-const.h>
diff --git a/arch/powerpc/include/asm/pasemi_dma.h b/arch/powerpc/include/asm/pasemi_dma.h
index eafa5a5..712a0b3 100644
--- a/arch/powerpc/include/asm/pasemi_dma.h
+++ b/arch/powerpc/include/asm/pasemi_dma.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2006-2008 PA Semi, Inc
  *
  * Hardware register layout and descriptor formats for the on-board
  * DMA engine on PA Semi PWRficient. Used by ethernet, function and security
  * drivers.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #ifndef ASM_PASEMI_DMA_H
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 94d4490..ea6ec65 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -1,15 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_PCI_BRIDGE_H
 #define _ASM_POWERPC_PCI_BRIDGE_H
 #ifdef __KERNEL__
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/pci.h>
 #include <linux/list.h>
 #include <linux/ioport.h>
+#include <linux/numa.h>
 
 struct device_node;
 
@@ -19,6 +17,8 @@
 struct pci_controller_ops {
 	void		(*dma_dev_setup)(struct pci_dev *pdev);
 	void		(*dma_bus_setup)(struct pci_bus *bus);
+	bool		(*iommu_bypass_supported)(struct pci_dev *pdev,
+				u64 mask);
 
 	int		(*probe_mode)(struct pci_bus *bus);
 
@@ -43,9 +43,6 @@
 	void		(*teardown_msi_irqs)(struct pci_dev *pdev);
 #endif
 
-	int             (*dma_set_mask)(struct pci_dev *pdev, u64 dma_mask);
-	u64		(*dma_get_required_mask)(struct pci_dev *pdev);
-
 	void		(*shutdown)(struct pci_controller *hose);
 };
 
@@ -129,6 +126,7 @@
 #endif	/* CONFIG_PPC64 */
 
 	void *private_data;
+	struct npu *npu;
 };
 
 /* These are used for config access before all the PCI probing
@@ -185,6 +183,7 @@
 struct pci_dn {
 	int     flags;
 #define PCI_DN_FLAG_IOV_VF	0x01
+#define PCI_DN_FLAG_DEAD	0x02    /* Device has been hot-removed */
 
 	int	busno;			/* pci bus number */
 	int	devfn;			/* pci device and function number */
@@ -264,7 +263,7 @@
 #ifdef CONFIG_NUMA
 #define PHB_SET_NODE(PHB, NODE)		((PHB)->node = (NODE))
 #else
-#define PHB_SET_NODE(PHB, NODE)		((PHB)->node = -1)
+#define PHB_SET_NODE(PHB, NODE)		((PHB)->node = NUMA_NO_NODE)
 #endif
 
 #endif	/* CONFIG_PPC64 */
@@ -273,6 +272,8 @@
 extern struct pci_controller *pci_find_hose_for_OF_device(
 			struct device_node* node);
 
+extern struct pci_controller *pci_find_controller_for_domain(int domain_nr);
+
 /* Fill up host controller resources from the OF node */
 extern void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			struct device_node *dev, int primary);
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 2af9ded..327567b 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef __ASM_POWERPC_PCI_H
 #define __ASM_POWERPC_PCI_H
 #ifdef __KERNEL__
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/types.h>
@@ -52,10 +49,8 @@
 
 #ifdef CONFIG_PCI
 extern void set_pci_dma_ops(const struct dma_map_ops *dma_ops);
-extern const struct dma_map_ops *get_pci_dma_ops(void);
 #else	/* CONFIG_PCI */
 #define set_pci_dma_ops(d)
-#define get_pci_dma_ops()	NULL
 #endif
 
 #ifdef CONFIG_PPC64
@@ -117,8 +112,6 @@
 					 unsigned long size,
 					 pgprot_t prot);
 
-#define HAVE_ARCH_PCI_RESOURCE_TO_USER
-
 extern resource_size_t pcibios_io_space_offset(struct pci_controller *hose);
 extern void pcibios_setup_bus_devices(struct pci_bus *bus);
 extern void pcibios_setup_bus_self(struct pci_bus *bus);
@@ -129,5 +122,9 @@
 
 extern struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev);
 extern struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index);
+extern int pnv_npu2_init(struct pci_controller *hose);
+extern int pnv_npu2_map_lpar_dev(struct pci_dev *gpdev, unsigned int lparid,
+		unsigned long msr);
+extern int pnv_npu2_unmap_lpar_dev(struct pci_dev *gpdev);
 
 #endif /* __ASM_POWERPC_PCI_H */
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 8bf1b63..7426d7a 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Performance event support - hardware-specific disambiguation
  *
@@ -7,11 +8,6 @@
  * devices other than the core which provide their own performance counters.
  *
  * Copyright 2010 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifdef CONFIG_PPC_PERF_CTRS
@@ -26,6 +22,8 @@
 #include <asm/ptrace.h>
 #include <asm/reg.h>
 
+#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
+
 /*
  * Overload regs->result to specify whether we should use the MSR (result
  * is zero) or the SIAR (result is non zero).
@@ -37,4 +35,7 @@
 		(regs)->gpr[1] = current_stack_pointer();	\
 		asm volatile("mfmsr %0" : "=r" ((regs)->msr));	\
 	} while (0)
+
+/* To support perf_regs sier update */
+extern bool is_sier_available(void);
 #endif
diff --git a/arch/powerpc/include/asm/perf_event_fsl_emb.h b/arch/powerpc/include/asm/perf_event_fsl_emb.h
index a581654..c4d9ceb 100644
--- a/arch/powerpc/include/asm/perf_event_fsl_emb.h
+++ b/arch/powerpc/include/asm/perf_event_fsl_emb.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Performance event support - Freescale embedded specific definitions.
  *
  * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
  * Copyright 2010 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/types.h>
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 67a8a95..3e9703f 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Performance event support - PowerPC classic/server specific definitions.
  *
  * Copyright 2008-2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/types.h>
@@ -41,6 +37,8 @@
 	void		(*get_mem_data_src)(union perf_mem_data_src *dsrc,
 				u32 flags, struct pt_regs *regs);
 	void		(*get_mem_weight)(u64 *weight);
+	unsigned long	group_constraint_mask;
+	unsigned long	group_constraint_val;
 	u64             (*bhrb_filter_map)(u64 branch_sample_type);
 	void            (*config_bhrb)(u64 pmu_bhrb_filter);
 	void		(*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index e11f030..6dd78a2 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -20,10 +20,59 @@
 
 #define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
 
+pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel);
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+{
+	return (pte_t *)pte_fragment_alloc(mm, 1);
+}
+
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
+{
+	return (pgtable_t)pte_fragment_alloc(mm, 0);
+}
+
+void pte_frag_destroy(void *pte_frag);
+void pte_fragment_free(unsigned long *table, int kernel);
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	pte_fragment_free((unsigned long *)pte, 1);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+	pte_fragment_free((unsigned long *)ptepage, 0);
+}
+
+/*
+ * 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
+ * handle allocation.  For PTE pages, the allocation size will be
+ * (2^index_size * sizeof(pointer)) and allocations are drawn from
+ * the kmem_cache in PGT_CACHE(index_size).
+ *
+ * The maximum index size needs to be big enough to allow any
+ * pagetable sizes we need, but small enough to fit in the low bits of
+ * any page table pointer.  In other words all pagetables, even tiny
+ * ones, must be aligned to allow at least enough low 0 bits to
+ * contain this value.  This value is also used as a mask, so it must
+ * be one less than a power of two.
+ */
+#define MAX_PGTABLE_INDEX_SIZE	0xf
+
+extern struct kmem_cache *pgtable_cache[];
+#define PGT_CACHE(shift) pgtable_cache[shift]
+
 #ifdef CONFIG_PPC_BOOK3S
 #include <asm/book3s/pgalloc.h>
 #else
 #include <asm/nohash/pgalloc.h>
 #endif
 
+static inline pgtable_t pmd_pgtable(pmd_t pmd)
+{
+	return (pgtable_t)pmd_page_vaddr(pmd);
+}
+
 #endif /* _ASM_POWERPC_PGALLOC_H */
diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h
index a89c67b..b169bbf 100644
--- a/arch/powerpc/include/asm/pgtable-be-types.h
+++ b/arch/powerpc/include/asm/pgtable-be-types.h
@@ -33,11 +33,7 @@
 	return x.pmd;
 }
 
-/*
- * 64 bit hash always use 4 level table. Everybody else use 4 level
- * only for 4K page size.
- */
-#if defined(CONFIG_PPC_BOOK3S_64) || !defined(CONFIG_PPC_64K_PAGES)
+/* 64 bit always use 4 level table. */
 typedef struct { __be64 pud; } pud_t;
 #define __pud(x)	((pud_t) { cpu_to_be64(x) })
 #define __pud_raw(x)	((pud_t) { (x) })
@@ -51,7 +47,6 @@
 	return x.pud;
 }
 
-#endif /* CONFIG_PPC_BOOK3S_64 || !CONFIG_PPC_64K_PAGES */
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
@@ -77,7 +72,7 @@
  * With hash config 64k pages additionally define a bigger "real PTE" type that
  * gathers the "second half" part of the PTE for pseudo 64k pages
  */
-#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_BOOK3S_64)
+#ifdef CONFIG_PPC_64K_PAGES
 typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
 #else
 typedef struct { pte_t pte; } real_pte_t;
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index eccb30b..d11b4c6 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -3,7 +3,11 @@
 #define _ASM_POWERPC_PGTABLE_TYPES_H
 
 /* PTE level */
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)
+typedef struct { pte_basic_t pte, pte1, pte2, pte3; } pte_t;
+#else
 typedef struct { pte_basic_t pte; } pte_t;
+#endif
 #define __pte(x)	((pte_t) { (x) })
 static inline pte_basic_t pte_val(pte_t x)
 {
@@ -19,18 +23,13 @@
 	return x.pmd;
 }
 
-/*
- * 64 bit hash always use 4 level table. Everybody else use 4 level
- * only for 4K page size.
- */
-#if defined(CONFIG_PPC_BOOK3S_64) || !defined(CONFIG_PPC_64K_PAGES)
+/* 64 bit always use 4 level table. */
 typedef struct { unsigned long pud; } pud_t;
 #define __pud(x)	((pud_t) { (x) })
 static inline unsigned long pud_val(pud_t x)
 {
 	return x.pud;
 }
-#endif /* CONFIG_PPC_BOOK3S_64 || !CONFIG_PPC_64K_PAGES */
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
@@ -50,7 +49,7 @@
  * With hash config 64k pages additionally define a bigger "real PTE" type that
  * gathers the "second half" part of the PTE for pseudo 64k pages
  */
-#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_BOOK3S_64)
+#ifdef CONFIG_PPC_64K_PAGES
 typedef struct { pte_t pte; unsigned long hidx; } real_pte_t;
 #else
 typedef struct { pte_t pte; } real_pte_t;
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 14c79a7..4053b2a 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -20,6 +20,25 @@
 #include <asm/nohash/pgtable.h>
 #endif /* !CONFIG_PPC_BOOK3S */
 
+/* Note due to the way vm flags are laid out, the bits are XWR */
+#define __P000	PAGE_NONE
+#define __P001	PAGE_READONLY
+#define __P010	PAGE_COPY
+#define __P011	PAGE_COPY
+#define __P100	PAGE_READONLY_X
+#define __P101	PAGE_READONLY_X
+#define __P110	PAGE_COPY_X
+#define __P111	PAGE_COPY_X
+
+#define __S000	PAGE_NONE
+#define __S001	PAGE_READONLY
+#define __S010	PAGE_SHARED
+#define __S011	PAGE_SHARED
+#define __S100	PAGE_READONLY_X
+#define __S101	PAGE_READONLY_X
+#define __S110	PAGE_SHARED_X
+#define __S111	PAGE_SHARED_X
+
 #ifndef __ASSEMBLY__
 
 #include <asm/tlbflush.h>
@@ -27,6 +46,16 @@
 /* Keep these as a macros 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))
+/*
+ * Select all bits except the pfn
+ */
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+	unsigned long pte_flags;
+
+	pte_flags = pte_val(pte) & ~PTE_RPN_MASK;
+	return __pgprot(pte_flags);
+}
 
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
@@ -37,10 +66,10 @@
 
 extern pgd_t swapper_pg_dir[];
 
-void limit_zone_pfn(enum zone_type zone, unsigned long max_pfn);
-int dma_pfn_limit_to_zone(u64 pfn_limit);
 extern void paging_init(void);
 
+extern unsigned long ioremap_bot;
+
 /*
  * kern_addr_valid is intended to indicate whether an address is a valid
  * kernel address.  Most 32-bit archs define it as always true (like this)
@@ -50,21 +79,6 @@
 
 #include <asm-generic/pgtable.h>
 
-
-/*
- * 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.
- */
-extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
-
-extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		       unsigned long end, int write,
-		       struct page **pages, int *nr);
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_large(pmd)		0
 #endif
@@ -72,8 +86,7 @@
 /* can we use this in kvm */
 unsigned long vmalloc_to_phys(void *vmalloc_addr);
 
-void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
-void pgtable_cache_init(void);
+void pgtable_cache_add(unsigned int shift);
 
 #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32)
 void mark_initmem_nx(void);
@@ -81,6 +94,79 @@
 static inline void mark_initmem_nx(void) { }
 #endif
 
+#ifdef CONFIG_PPC_DEBUG_WX
+void ptdump_check_wx(void);
+#else
+static inline void ptdump_check_wx(void) { }
+#endif
+
+/*
+ * When used, PTE_FRAG_NR is defined in subarch pgtable.h
+ * so we are sure it is included when arriving here.
+ */
+#ifdef PTE_FRAG_NR
+static inline void *pte_frag_get(mm_context_t *ctx)
+{
+	return ctx->pte_frag;
+}
+
+static inline void pte_frag_set(mm_context_t *ctx, void *p)
+{
+	ctx->pte_frag = p;
+}
+#else
+#define PTE_FRAG_NR		1
+#define PTE_FRAG_SIZE_SHIFT	PAGE_SHIFT
+#define PTE_FRAG_SIZE		(1UL << PTE_FRAG_SIZE_SHIFT)
+
+static inline void *pte_frag_get(mm_context_t *ctx)
+{
+	return NULL;
+}
+
+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 pgd_is_leaf
+#define pgd_is_leaf pgd_is_leaf
+static inline bool pgd_is_leaf(pgd_t pgd)
+{
+	return false;
+}
+#endif
+
+#ifdef CONFIG_PPC64
+#define is_ioremap_addr is_ioremap_addr
+static inline bool is_ioremap_addr(const void *x)
+{
+#ifdef CONFIG_MMU
+	unsigned long addr = (unsigned long)x;
+
+	return addr >= IOREMAP_BASE && addr < IOREMAP_END;
+#else
+	return false;
+#endif
+}
+#endif /* CONFIG_PPC64 */
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index cff5a41..4497c8a 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -340,6 +340,12 @@
 {
 	return 0;
 }
+
+static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex,
+				    unsigned long *ptes)
+{
+	return 0;
+}
 #endif /* CONFIG_PPC_PSERIES */
 
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
diff --git a/arch/powerpc/include/asm/pmac_low_i2c.h b/arch/powerpc/include/asm/pmac_low_i2c.h
index 01d7182..21bd729 100644
--- a/arch/powerpc/include/asm/pmac_low_i2c.h
+++ b/arch/powerpc/include/asm/pmac_low_i2c.h
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* 
  *  include/asm-ppc/pmac_low_i2c.h
  *
  *  Copyright (C) 2003 Ben. Herrenschmidt (benh@kernel.crashing.org)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 #ifndef __PMAC_LOW_I2C_H__
 #define __PMAC_LOW_I2C_H__
diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h
index 7ac3586..c6bbe97 100644
--- a/arch/powerpc/include/asm/pmc.h
+++ b/arch/powerpc/include/asm/pmc.h
@@ -1,20 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * pmc.h
  * Copyright (C) 2004  David Gibson, IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 #ifndef _POWERPC_PMC_H
 #define _POWERPC_PMC_H
@@ -40,11 +27,10 @@
 #ifdef CONFIG_PPC_PSERIES
 		get_lppaca()->pmcregs_in_use = inuse;
 #endif
-	} else {
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-		get_paca()->pmcregs_in_use = inuse;
-#endif
 	}
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	get_paca()->pmcregs_in_use = inuse;
+#endif
 #endif
 }
 
diff --git a/arch/powerpc/include/asm/pmi.h b/arch/powerpc/include/asm/pmi.h
index b4e91fb..478f0a2 100644
--- a/arch/powerpc/include/asm/pmi.h
+++ b/arch/powerpc/include/asm/pmi.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _POWERPC_PMI_H
 #define _POWERPC_PMI_H
 
@@ -11,20 +12,6 @@
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Christian Krafft <krafft@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifdef __KERNEL__
diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h
index 208b550..7de8264 100644
--- a/arch/powerpc/include/asm/pnv-ocxl.h
+++ b/arch/powerpc/include/asm/pnv-ocxl.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright 2017 IBM Corp.
 #ifndef _ASM_PNV_OCXL_H
 #define _ASM_PNV_OCXL_H
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
index 7f627e3..edcb1fc 100644
--- a/arch/powerpc/include/asm/pnv-pci.h
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2014 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_PNV_PCI_H
@@ -26,15 +22,9 @@
 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_p2p(struct pci_dev *initiator, struct pci_dev *target,
-			   u64 desc);
 
-extern int pnv_pci_enable_tunnel(struct pci_dev *dev, uint64_t *asnind);
-extern int pnv_pci_disable_tunnel(struct pci_dev *dev);
 extern int pnv_pci_set_tunnel_bar(struct pci_dev *dev, uint64_t addr,
 				  int enable);
-extern int pnv_pci_get_as_notify_info(struct task_struct *task, u32 *lpid,
-				      u32 *pid, u32 *tid);
 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);
@@ -54,7 +44,6 @@
 
 struct pnv_php_slot {
 	struct hotplug_slot		slot;
-	struct hotplug_slot_info	slot_info;
 	uint64_t			id;
 	char				*name;
 	int				slot_no;
@@ -72,6 +61,7 @@
 	struct pci_dev			*pdev;
 	struct pci_bus			*bus;
 	bool				power_state_check;
+	u8				attention_state;
 	void				*fdt;
 	void				*dt;
 	struct of_changeset		ocs;
diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h
index 2f3ff7a..e1a8587 100644
--- a/arch/powerpc/include/asm/powernv.h
+++ b/arch/powerpc/include/asm/powernv.h
@@ -1,46 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2017 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERNV_H
 #define _ASM_POWERNV_H
 
 #ifdef CONFIG_PPC_POWERNV
-#define NPU2_WRITE 1
 extern void powernv_set_nmmu_ptcr(unsigned long ptcr);
-extern struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
-			unsigned long flags,
-			void (*cb)(struct npu_context *, void *),
-			void *priv);
-extern void pnv_npu2_destroy_context(struct npu_context *context,
-				struct pci_dev *gpdev);
-extern int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea,
-				unsigned long *flags, unsigned long *status,
-				int count);
+
+void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val);
 
 void pnv_tm_init(void);
 #else
 static inline void powernv_set_nmmu_ptcr(unsigned long ptcr) { }
-static inline struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
-			unsigned long flags,
-			struct npu_context *(*cb)(struct npu_context *, void *),
-			void *priv) { return ERR_PTR(-ENODEV); }
-static inline void pnv_npu2_destroy_context(struct npu_context *context,
-					struct pci_dev *gpdev) { }
-
-static inline int pnv_npu2_handle_fault(struct npu_context *context,
-					uintptr_t *ea, unsigned long *flags,
-					unsigned long *status, int count) {
-	return -ENODEV;
-}
 
 static inline void pnv_tm_init(void) { }
-static inline void pnv_power9_force_smt4(void) { }
 #endif
 
 #endif /* _ASM_POWERNV_H */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 665af14..c1df75e 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2009 Freescale Semiconductor, Inc.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * provides masks and opcode images for use by code generation, emulation
  * and for instructions that older assemblers might not know about
  */
@@ -104,6 +100,7 @@
 #define OP_31_XOP_LHZUX     311
 #define OP_31_XOP_MSGSNDP   142
 #define OP_31_XOP_MSGCLRP   174
+#define OP_31_XOP_TLBIE     306
 #define OP_31_XOP_MFSPR     339
 #define OP_31_XOP_LWAX      341
 #define OP_31_XOP_LHAX      343
@@ -256,6 +253,7 @@
 #define PPC_INST_MTSPR_DSCR_USER_MASK	0xfc1ffffe
 #define PPC_INST_MFVSRD			0x7c000066
 #define PPC_INST_MTVSRD			0x7c000166
+#define PPC_INST_SC			0x44000002
 #define PPC_INST_SLBFEE			0x7c0007a7
 #define PPC_INST_SLBIA			0x7c0003e4
 
@@ -300,6 +298,7 @@
 /* Misc instructions for BPF compiler */
 #define PPC_INST_LBZ			0x88000000
 #define PPC_INST_LD			0xe8000000
+#define PPC_INST_LDX			0x7c00002a
 #define PPC_INST_LHZ			0xa0000000
 #define PPC_INST_LWZ			0x80000000
 #define PPC_INST_LHBRX			0x7c00062c
@@ -307,6 +306,7 @@
 #define PPC_INST_STB			0x98000000
 #define PPC_INST_STH			0xb0000000
 #define PPC_INST_STD			0xf8000000
+#define PPC_INST_STDX			0x7c00012a
 #define PPC_INST_STDU			0xf8000001
 #define PPC_INST_STW			0x90000000
 #define PPC_INST_STWU			0x94000000
@@ -324,6 +324,7 @@
 #define PPC_INST_ADDI			0x38000000
 #define PPC_INST_ADDIS			0x3c000000
 #define PPC_INST_ADD			0x7c000214
+#define PPC_INST_ADDC			0x7c000014
 #define PPC_INST_SUB			0x7c000050
 #define PPC_INST_BLR			0x4e800020
 #define PPC_INST_BLRL			0x4e800021
@@ -332,15 +333,22 @@
 #define PPC_INST_MULLW			0x7c0001d6
 #define PPC_INST_MULHWU			0x7c000016
 #define PPC_INST_MULLI			0x1c000000
+#define PPC_INST_MADDHD			0x10000030
+#define PPC_INST_MADDHDU		0x10000031
+#define PPC_INST_MADDLD			0x10000033
 #define PPC_INST_DIVWU			0x7c000396
 #define PPC_INST_DIVD			0x7c0003d2
+#define PPC_INST_DIVDU			0x7c000392
 #define PPC_INST_RLWINM			0x54000000
+#define PPC_INST_RLWINM_DOT		0x54000001
 #define PPC_INST_RLWIMI			0x50000000
 #define PPC_INST_RLDICL			0x78000000
 #define PPC_INST_RLDICR			0x78000004
 #define PPC_INST_SLW			0x7c000030
 #define PPC_INST_SLD			0x7c000036
 #define PPC_INST_SRW			0x7c000430
+#define PPC_INST_SRAW			0x7c000630
+#define PPC_INST_SRAWI			0x7c000670
 #define PPC_INST_SRD			0x7c000436
 #define PPC_INST_SRAD			0x7c000634
 #define PPC_INST_SRADI			0x7c000674
@@ -372,6 +380,7 @@
 /* macros to insert fields into opcodes */
 #define ___PPC_RA(a)	(((a) & 0x1f) << 16)
 #define ___PPC_RB(b)	(((b) & 0x1f) << 11)
+#define ___PPC_RC(c)	(((c) & 0x1f) << 6)
 #define ___PPC_RS(s)	(((s) & 0x1f) << 21)
 #define ___PPC_RT(t)	___PPC_RS(t)
 #define ___PPC_R(r)	(((r) & 0x1) << 16)
@@ -391,7 +400,7 @@
 #define __PPC_WS(w)	(((w) & 0x1f) << 11)
 #define __PPC_SH(s)	__PPC_WS(s)
 #define __PPC_SH64(s)	(__PPC_SH(s) | (((s) & 0x20) >> 4))
-#define __PPC_MB(s)	(((s) & 0x1f) << 6)
+#define __PPC_MB(s)	___PPC_RC(s)
 #define __PPC_ME(s)	(((s) & 0x1f) << 1)
 #define __PPC_MB64(s)	(__PPC_MB(s) | ((s) & 0x20))
 #define __PPC_ME64(s)	__PPC_MB64(s)
@@ -401,6 +410,15 @@
 #define __PPC_RC21	(0x1 << 10)
 
 /*
+ * Both low and high 16 bits are added as SIGNED additions, so if low 16 bits
+ * has high bit set, high 16 bits must be adjusted. These macros do that (stolen
+ * from binutils).
+ */
+#define PPC_LO(v)	((v) & 0xffff)
+#define PPC_HI(v)	(((v) >> 16) & 0xffff)
+#define PPC_HA(v)	PPC_HI((v) + 0x8000)
+
+/*
  * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a
  * larx with EH set as an illegal instruction.
  */
@@ -433,6 +451,15 @@
 #define PPC_STQCX(t, a, b)	stringify_in_c(.long PPC_INST_STQCX | \
 					___PPC_RT(t) | ___PPC_RA(a) | \
 					___PPC_RB(b))
+#define PPC_MADDHD(t, a, b, c)	stringify_in_c(.long PPC_INST_MADDHD | \
+					___PPC_RT(t) | ___PPC_RA(a)  | \
+					___PPC_RB(b) | ___PPC_RC(c))
+#define PPC_MADDHDU(t, a, b, c)	stringify_in_c(.long PPC_INST_MADDHDU | \
+					___PPC_RT(t) | ___PPC_RA(a)   | \
+					___PPC_RB(b) | ___PPC_RC(c))
+#define PPC_MADDLD(t, a, b, c)	stringify_in_c(.long PPC_INST_MADDLD | \
+					___PPC_RT(t) | ___PPC_RA(a)  | \
+					___PPC_RB(b) | ___PPC_RC(c))
 #define PPC_MSGSND(b)		stringify_in_c(.long PPC_INST_MSGSND | \
 					___PPC_RB(b))
 #define PPC_MSGSYNC		stringify_in_c(.long PPC_INST_MSGSYNC)
@@ -492,6 +519,8 @@
 					__PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_SLBFEE_DOT(t, b)	stringify_in_c(.long PPC_INST_SLBFEE | \
 					__PPC_RT(t) | __PPC_RB(b))
+#define __PPC_SLBFEE_DOT(t, b)	stringify_in_c(.long PPC_INST_SLBFEE |	\
+					       ___PPC_RT(t) | ___PPC_RB(b))
 #define PPC_ICBT(c,a,b)		stringify_in_c(.long PPC_INST_ICBT | \
 				       __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b))
 /* PASemi instructions */
@@ -568,7 +597,16 @@
 
 #define PPC_SLBIA(IH)	stringify_in_c(.long PPC_INST_SLBIA | \
 				       ((IH & 0x7) << 21))
-#define PPC_INVALIDATE_ERAT	PPC_SLBIA(7)
+
+/*
+ * These may only be used on ISA v3.0 or later (aka. CPU_FTR_ARCH_300, radix
+ * implies CPU_FTR_ARCH_300). USER/GUEST invalidates may only be used by radix
+ * mode (on HPT these would also invalidate various SLBEs which may not be
+ * desired).
+ */
+#define PPC_ISA_3_0_INVALIDATE_ERAT	PPC_SLBIA(7)
+#define PPC_RADIX_INVALIDATE_ERAT_USER	PPC_SLBIA(3)
+#define PPC_RADIX_INVALIDATE_ERAT_GUEST	PPC_SLBIA(6)
 
 #define VCMPEQUD_RC(vrt, vra, vrb)	stringify_in_c(.long PPC_INST_VCMPEQUD | \
 			      ___PPC_RT(vrt) | ___PPC_RA(vra) | \
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index 7262880..7f4be5a 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * c 2001 PPC 64 Team, IBM Corp
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_PPC_PCI_H
 #define _ASM_POWERPC_PPC_PCI_H
@@ -53,23 +49,19 @@
 struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr);
 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);
+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_state_clear(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);
 void eeh_pe_state_mark_with_cfg(struct eeh_pe *pe, int state);
 void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode);
 
 void eeh_sysfs_add_device(struct pci_dev *pdev);
 void eeh_sysfs_remove_device(struct pci_dev *pdev);
 
-static inline const char *eeh_pci_name(struct pci_dev *pdev) 
-{ 
-	return pdev ? pci_name(pdev) : "<null>";
-} 
-
 static inline const char *eeh_driver_name(struct pci_dev *pdev)
 {
 	return (pdev && pdev->driver) ? pdev->driver->name : "<null>";
@@ -77,6 +69,8 @@
 
 #endif /* CONFIG_EEH */
 
+#define PCI_BUSNO(bdfn) ((bdfn >> 8) & 0xff)
+
 #else /* CONFIG_PCI */
 static inline void init_pci_config_tokens(void) { }
 #endif /* !CONFIG_PCI */
diff --git a/arch/powerpc/include/asm/ppc4xx.h b/arch/powerpc/include/asm/ppc4xx.h
index 610a511..b37119e 100644
--- a/arch/powerpc/include/asm/ppc4xx.h
+++ b/arch/powerpc/include/asm/ppc4xx.h
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * PPC4xx Prototypes and definitions
  *
  * Copyright 2008 DENX Software Engineering, Stefan Roese <sr@denx.de>
- *
- * This is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  */
 
 #ifndef __ASM_POWERPC_PPC4xx_H__
diff --git a/arch/powerpc/include/asm/ppc4xx_ocm.h b/arch/powerpc/include/asm/ppc4xx_ocm.h
deleted file mode 100644
index 6ce9046..0000000
--- a/arch/powerpc/include/asm/ppc4xx_ocm.h
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- * PowerPC 4xx OCM memory allocation support
- *
- * (C) Copyright 2009, Applied Micro Circuits Corporation
- * Victor Gallardo (vgallardo@amcc.com)
- *
- * See file CREDITS for list of people who contributed to this
- * project.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- */
-
-#ifndef __ASM_POWERPC_PPC4XX_OCM_H__
-#define __ASM_POWERPC_PPC4XX_OCM_H__
-
-#define PPC4XX_OCM_NON_CACHED 0
-#define PPC4XX_OCM_CACHED     1
-
-#if defined(CONFIG_PPC4xx_OCM)
-
-void *ppc4xx_ocm_alloc(phys_addr_t *phys, int size, int align,
-		  int flags, const char *owner);
-void ppc4xx_ocm_free(const void *virt);
-
-#else
-
-#define ppc4xx_ocm_alloc(phys, size, align, flags, owner)	NULL
-#define ppc4xx_ocm_free(addr)	((void)0)
-
-#endif /* CONFIG_PPC4xx_OCM */
-
-#endif  /* __ASM_POWERPC_PPC4XX_OCM_H__ */
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index b5d0236..6b03dff 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -311,18 +311,48 @@
 	addis	reg,reg,(name - 0b)@ha;		\
 	addi	reg,reg,(name - 0b)@l;
 
-#ifdef __powerpc64__
-#ifdef HAVE_AS_ATHIGH
+#if defined(__powerpc64__) && defined(HAVE_AS_ATHIGH)
 #define __AS_ATHIGH high
 #else
 #define __AS_ATHIGH h
 #endif
-#define LOAD_REG_IMMEDIATE(reg,expr)		\
-	lis     reg,(expr)@highest;		\
-	ori     reg,reg,(expr)@higher;	\
-	rldicr  reg,reg,32,31;		\
-	oris    reg,reg,(expr)@__AS_ATHIGH;	\
-	ori     reg,reg,(expr)@l;
+
+.macro __LOAD_REG_IMMEDIATE_32 r, x
+	.if (\x) >= 0x8000 || (\x) < -0x8000
+		lis \r, (\x)@__AS_ATHIGH
+		.if (\x) & 0xffff != 0
+			ori \r, \r, (\x)@l
+		.endif
+	.else
+		li \r, (\x)@l
+	.endif
+.endm
+
+.macro __LOAD_REG_IMMEDIATE r, x
+	.if (\x) >= 0x80000000 || (\x) < -0x80000000
+		__LOAD_REG_IMMEDIATE_32 \r, (\x) >> 32
+		sldi	\r, \r, 32
+		.if (\x) & 0xffff0000 != 0
+			oris \r, \r, (\x)@__AS_ATHIGH
+		.endif
+		.if (\x) & 0xffff != 0
+			ori \r, \r, (\x)@l
+		.endif
+	.else
+		__LOAD_REG_IMMEDIATE_32 \r, \x
+	.endif
+.endm
+
+#ifdef __powerpc64__
+
+#define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE reg, expr
+
+#define LOAD_REG_IMMEDIATE_SYM(reg, tmp, expr)	\
+	lis	tmp, (expr)@highest;		\
+	lis	reg, (expr)@__AS_ATHIGH;	\
+	ori	tmp, tmp, (expr)@higher;	\
+	ori	reg, reg, (expr)@l;		\
+	rldimi	reg, tmp, 32, 0
 
 #define LOAD_REG_ADDR(reg,name)			\
 	ld	reg,name@got(r2)
@@ -335,11 +365,13 @@
 
 #else /* 32-bit */
 
-#define LOAD_REG_IMMEDIATE(reg,expr)		\
+#define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE_32 reg, expr
+
+#define LOAD_REG_IMMEDIATE_SYM(reg,expr)		\
 	lis	reg,(expr)@ha;		\
 	addi	reg,reg,(expr)@l;
 
-#define LOAD_REG_ADDR(reg,name)		LOAD_REG_IMMEDIATE(reg, name)
+#define LOAD_REG_ADDR(reg,name)		LOAD_REG_IMMEDIATE_SYM(reg, name)
 
 #define LOAD_REG_ADDRBASE(reg, name)	lis	reg,name@ha
 #define ADDROFF(name)			name@l
@@ -351,19 +383,9 @@
 
 /* various errata or part fixups */
 #ifdef CONFIG_PPC601_SYNC_FIX
-#define SYNC				\
-BEGIN_FTR_SECTION			\
-	sync;				\
-	isync;				\
-END_FTR_SECTION_IFSET(CPU_FTR_601)
-#define SYNC_601			\
-BEGIN_FTR_SECTION			\
-	sync;				\
-END_FTR_SECTION_IFSET(CPU_FTR_601)
-#define ISYNC_601			\
-BEGIN_FTR_SECTION			\
-	isync;				\
-END_FTR_SECTION_IFSET(CPU_FTR_601)
+#define SYNC		sync; isync
+#define SYNC_601	sync
+#define ISYNC_601	isync
 #else
 #define	SYNC
 #define SYNC_601
@@ -389,15 +411,11 @@
 #define MFTBU(dest)			mfspr dest, SPRN_TBRU
 #endif
 
-#ifndef CONFIG_SMP
-#define TLBSYNC
-#else /* CONFIG_SMP */
 /* tlbsync is not implemented on 601 */
-#define TLBSYNC				\
-BEGIN_FTR_SECTION			\
-	tlbsync;			\
-	sync;				\
-END_FTR_SECTION_IFCLR(CPU_FTR_601)
+#if !defined(CONFIG_SMP) || defined(CONFIG_PPC_BOOK3S_601)
+#define TLBSYNC
+#else
+#define TLBSYNC		tlbsync; sync
 #endif
 
 #ifdef CONFIG_PPC64
@@ -480,26 +498,11 @@
 	ori	rd,rd,((KERNELBASE>>48)&0xFFFF);\
 	rotldi	rd,rd,48
 #else
-/*
- * On APUS (Amiga PowerPC cpu upgrade board), we don't know the
- * physical base address of RAM at compile time.
- */
 #define toreal(rd)	tophys(rd,rd)
 #define fromreal(rd)	tovirt(rd,rd)
 
-#define tophys(rd,rs)				\
-0:	addis	rd,rs,-PAGE_OFFSET@h;		\
-	.section ".vtop_fixup","aw";		\
-	.align  1;				\
-	.long   0b;				\
-	.previous
-
-#define tovirt(rd,rs)				\
-0:	addis	rd,rs,PAGE_OFFSET@h;		\
-	.section ".ptov_fixup","aw";		\
-	.align  1;				\
-	.long   0b;				\
-	.previous
+#define tophys(rd, rs)	addis	rd, rs, -PAGE_OFFSET@h
+#define tovirt(rd, rs)	addis	rd, rs, PAGE_OFFSET@h
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -821,4 +824,14 @@
 	stringify_in_c(.long (_target) - . ;)	\
 	stringify_in_c(.previous)
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+#define BTB_FLUSH(reg)			\
+	lis reg,BUCSR_INIT@h;		\
+	ori reg,reg,BUCSR_INIT@l;	\
+	mtspr SPRN_BUCSR,reg;		\
+	isync;
+#else
+#define BTB_FLUSH(reg)
+#endif /* CONFIG_PPC_FSL_BOOK3E */
+
 #endif /* _ASM_POWERPC_PPC_ASM_H */
diff --git a/arch/powerpc/include/asm/probes.h b/arch/powerpc/include/asm/probes.h
index 3421637..84dd1ad 100644
--- a/arch/powerpc/include/asm/probes.h
+++ b/arch/powerpc/include/asm/probes.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_PROBES_H
 #define _ASM_POWERPC_PROBES_H
 #ifdef __KERNEL__
 /*
  * Definitions common to probes files
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright IBM Corporation, 2012
  */
 #include <linux/types.h>
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 52fadde..a9993e7 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_POWERPC_PROCESSOR_H
 #define _ASM_POWERPC_PROCESSOR_H
 
 /*
  * Copyright (C) 2001 PPC 64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/reg.h>
@@ -32,15 +28,15 @@
 /* Default SMT priority is set to 3. Use 11- 13bits to save priority. */
 #define PPR_PRIORITY 3
 #ifdef __ASSEMBLY__
-#define INIT_PPR (PPR_PRIORITY << 50)
+#define DEFAULT_PPR (PPR_PRIORITY << 50)
 #else
-#define INIT_PPR ((u64)PPR_PRIORITY << 50)
+#define DEFAULT_PPR ((u64)PPR_PRIORITY << 50)
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_PPC64 */
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
-#include <asm/thread_info.h>
+#include <linux/thread_info.h>
 #include <asm/ptrace.h>
 #include <asm/hw_breakpoint.h>
 
@@ -67,12 +63,6 @@
 
 #endif /* defined(__KERNEL__) && defined(CONFIG_PPC32) */
 
-/*
- * Default implementation of macro that returns current
- * instruction pointer ("program counter").
- */
-#define current_text_addr() ({ __label__ _l; _l: &&_l;})
-
 /* Macros for adjusting thread priority (hardware multi-threading) */
 #define HMT_very_low()   asm volatile("or 31,31,31   # very low priority")
 #define HMT_low()	 asm volatile("or 1,1,1	     # low priority")
@@ -83,106 +73,16 @@
 
 #ifdef __KERNEL__
 
+#ifdef CONFIG_PPC64
+#include <asm/task_size_64.h>
+#else
+#include <asm/task_size_32.h>
+#endif
+
 struct task_struct;
 void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp);
 void release_thread(struct task_struct *);
 
-#ifdef CONFIG_PPC32
-
-#if CONFIG_TASK_SIZE > CONFIG_KERNEL_START
-#error User TASK_SIZE overlaps with KERNEL_START address
-#endif
-#define TASK_SIZE	(CONFIG_TASK_SIZE)
-
-/* This decides where the kernel will search for a free chunk of vm
- * space during mmap's.
- */
-#define TASK_UNMAPPED_BASE	(TASK_SIZE / 8 * 3)
-#endif
-
-#ifdef CONFIG_PPC64
-/*
- * 64-bit user address space can have multiple limits
- * For now supported values are:
- */
-#define TASK_SIZE_64TB  (0x0000400000000000UL)
-#define TASK_SIZE_128TB (0x0000800000000000UL)
-#define TASK_SIZE_512TB (0x0002000000000000UL)
-#define TASK_SIZE_1PB   (0x0004000000000000UL)
-#define TASK_SIZE_2PB   (0x0008000000000000UL)
-/*
- * With 52 bits in the address we can support
- * upto 4PB of range.
- */
-#define TASK_SIZE_4PB   (0x0010000000000000UL)
-
-/*
- * For now 512TB is only supported with book3s and 64K linux page size.
- */
-#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
-/*
- * Max value currently used:
- */
-#define TASK_SIZE_USER64		TASK_SIZE_4PB
-#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_128TB
-#define TASK_CONTEXT_SIZE		TASK_SIZE_512TB
-#else
-#define TASK_SIZE_USER64		TASK_SIZE_64TB
-#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_64TB
-/*
- * We don't need to allocate extended context ids for 4K page size, because
- * we limit the max effective address on this config to 64TB.
- */
-#define TASK_CONTEXT_SIZE		TASK_SIZE_64TB
-#endif
-
-/*
- * 32-bit user address space is 4GB - 1 page
- * (this 1 page is needed so referencing of 0xFFFFFFFF generates EFAULT
- */
-#define TASK_SIZE_USER32 (0x0000000100000000UL - (1*PAGE_SIZE))
-
-#define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \
-		TASK_SIZE_USER32 : TASK_SIZE_USER64)
-#define TASK_SIZE	  TASK_SIZE_OF(current)
-/* This decides where the kernel will search for a free chunk of vm
- * space during mmap's.
- */
-#define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
-#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4))
-
-#define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \
-		TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
-#endif
-
-/*
- * Initial task size value for user applications. For book3s 64 we start
- * with 128TB and conditionally enable upto 512TB
- */
-#ifdef CONFIG_PPC_BOOK3S_64
-#define DEFAULT_MAP_WINDOW	((is_32bit_task()) ?			\
-				 TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64)
-#else
-#define DEFAULT_MAP_WINDOW	TASK_SIZE
-#endif
-
-#ifdef __powerpc64__
-
-#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64
-#define STACK_TOP_USER32 TASK_SIZE_USER32
-
-#define STACK_TOP (is_32bit_task() ? \
-		   STACK_TOP_USER32 : STACK_TOP_USER64)
-
-#define STACK_TOP_MAX TASK_SIZE_USER64
-
-#else /* __powerpc64__ */
-
-#define STACK_TOP TASK_SIZE
-#define STACK_TOP_MAX	STACK_TOP
-
-#endif /* __powerpc64__ */
-
 typedef struct {
 	unsigned long seg;
 } mm_segment_t;
@@ -256,6 +156,12 @@
 #ifdef CONFIG_PPC32
 	void		*pgdir;		/* root of page-table tree */
 	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
+#ifdef CONFIG_PPC_RTAS
+	unsigned long	rtas_sp;	/* stack pointer for when in RTAS */
+#endif
+#endif
+#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
+	unsigned long	kuap;		/* opened segments for user access */
 #endif
 	/* Debug Registers */
 	struct debug_reg debug;
@@ -273,6 +179,7 @@
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 	struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */
 	unsigned long	trap_nr;	/* last trap # on this thread */
+	u8 load_slb;			/* Ages out SLB preload cache entries */
 	u8 load_fp;
 #ifdef CONFIG_ALTIVEC
 	u8 load_vec;
@@ -341,7 +248,6 @@
 	 * onwards.
 	 */
 	int		dscr_inherit;
-	unsigned long	ppr;	/* used to save/restore SMT priority */
 	unsigned long	tidr;
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -363,8 +269,7 @@
 #define ARCH_MIN_TASKALIGN 16
 
 #define INIT_SP		(sizeof(init_stack) + (unsigned long) &init_stack)
-#define INIT_SP_LIMIT \
-	(_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack)
+#define INIT_SP_LIMIT	((unsigned long)&init_stack)
 
 #ifdef CONFIG_SPE
 #define SPEFSCR_INIT \
@@ -389,7 +294,6 @@
 	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.addr_limit = KERNEL_DS, \
 	.fpexc_mode = 0, \
-	.ppr = INIT_PPR, \
 	.fscr = FSCR_TAR | FSCR_EBB \
 }
 #endif
@@ -442,8 +346,6 @@
 
 #define spin_cpu_relax()	barrier()
 
-#define spin_cpu_yield()	spin_cpu_relax()
-
 #define spin_end()	HMT_medium()
 
 #define spin_until_cond(cond)					\
@@ -506,14 +408,17 @@
 }
 #endif
 
+/* asm stubs */
+extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
+extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
+extern unsigned long isa206_idle_insn_mayloss(unsigned long type);
+
 extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
-extern unsigned long power7_idle_insn(unsigned long type); /* PNV_THREAD_NAP/etc*/
+
 extern void power7_idle_type(unsigned long type);
-extern unsigned long power9_idle_stop(unsigned long psscr_val);
-extern unsigned long power9_offline_stop(unsigned long psscr_val);
 extern void power9_idle_type(unsigned long stop_psscr_val,
 			      unsigned long stop_psscr_mask);
 
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index b04c5ce..94e3fd5 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _POWERPC_PROM_H
 #define _POWERPC_PROM_H
 #ifdef __KERNEL__
@@ -9,11 +10,6 @@
  * Copyright (C) 1996-2005 Paul Mackerras.
  *
  * Updates for PPC64 by Peter Bergner & David Engebretsen, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/types.h>
 #include <asm/irq.h>
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index 17ee719..cb89e4b 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  PS3 platform declarations.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #if !defined(_ASM_POWERPC_PS3_H)
diff --git a/arch/powerpc/include/asm/ps3av.h b/arch/powerpc/include/asm/ps3av.h
index a1dc784..82db78f 100644
--- a/arch/powerpc/include/asm/ps3av.h
+++ b/arch/powerpc/include/asm/ps3av.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  PS3 AV backend support.
  *
  *  Copyright (C) 2007 Sony Computer Entertainment Inc.
  *  Copyright 2007 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #ifndef _ASM_POWERPC_PS3AV_H_
diff --git a/arch/powerpc/include/asm/ps3gpu.h b/arch/powerpc/include/asm/ps3gpu.h
index b2b8959..9645c30 100644
--- a/arch/powerpc/include/asm/ps3gpu.h
+++ b/arch/powerpc/include/asm/ps3gpu.h
@@ -1,20 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  PS3 GPU declarations.
  *
  *  Copyright 2009 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, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _ASM_POWERPC_PS3GPU_H
diff --git a/arch/powerpc/include/asm/ps3stor.h b/arch/powerpc/include/asm/ps3stor.h
index 6fcaf71..1d82790 100644
--- a/arch/powerpc/include/asm/ps3stor.h
+++ b/arch/powerpc/include/asm/ps3stor.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * PS3 Storage Devices
  *
  * Copyright (C) 2007 Sony Computer Entertainment Inc.
  * Copyright 2007 Sony Corp.
- *
- * 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_PS3STOR_H_
@@ -51,7 +39,7 @@
 	unsigned int num_regions;
 	unsigned long accessible_regions;
 	unsigned int region_idx;		/* first accessible region */
-	struct ps3_storage_region regions[0];	/* Must be last */
+	struct ps3_storage_region regions[];	/* Must be last */
 };
 
 static inline struct ps3_storage_device *to_ps3_storage_device(struct device *dev)
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
deleted file mode 100644
index bef5614..0000000
--- a/arch/powerpc/include/asm/pte-common.h
+++ /dev/null
@@ -1,219 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Included from asm/pgtable-*.h only ! */
-
-/*
- * Some bits are only used on some cpu families... Make sure that all
- * the undefined gets a sensible default
- */
-#ifndef _PAGE_HASHPTE
-#define _PAGE_HASHPTE	0
-#endif
-#ifndef _PAGE_HWWRITE
-#define _PAGE_HWWRITE	0
-#endif
-#ifndef _PAGE_EXEC
-#define _PAGE_EXEC	0
-#endif
-#ifndef _PAGE_ENDIAN
-#define _PAGE_ENDIAN	0
-#endif
-#ifndef _PAGE_COHERENT
-#define _PAGE_COHERENT	0
-#endif
-#ifndef _PAGE_WRITETHRU
-#define _PAGE_WRITETHRU	0
-#endif
-#ifndef _PAGE_4K_PFN
-#define _PAGE_4K_PFN		0
-#endif
-#ifndef _PAGE_SAO
-#define _PAGE_SAO	0
-#endif
-#ifndef _PAGE_PSIZE
-#define _PAGE_PSIZE		0
-#endif
-/* _PAGE_RO and _PAGE_RW shall not be defined at the same time */
-#ifndef _PAGE_RO
-#define _PAGE_RO 0
-#else
-#define _PAGE_RW 0
-#endif
-
-#ifndef _PAGE_PTE
-#define _PAGE_PTE 0
-#endif
-/* At least one of _PAGE_PRIVILEGED or _PAGE_USER must be defined */
-#ifndef _PAGE_PRIVILEGED
-#define _PAGE_PRIVILEGED 0
-#else
-#ifndef _PAGE_USER
-#define _PAGE_USER 0
-#endif
-#endif
-#ifndef _PAGE_NA
-#define _PAGE_NA 0
-#endif
-#ifndef _PAGE_HUGE
-#define _PAGE_HUGE 0
-#endif
-
-#ifndef _PMD_PRESENT_MASK
-#define _PMD_PRESENT_MASK	_PMD_PRESENT
-#endif
-#ifndef _PMD_USER
-#define _PMD_USER	0
-#endif
-#ifndef _PAGE_KERNEL_RO
-#define _PAGE_KERNEL_RO		(_PAGE_PRIVILEGED | _PAGE_RO)
-#endif
-#ifndef _PAGE_KERNEL_ROX
-#define _PAGE_KERNEL_ROX	(_PAGE_PRIVILEGED | _PAGE_RO | _PAGE_EXEC)
-#endif
-#ifndef _PAGE_KERNEL_RW
-#define _PAGE_KERNEL_RW		(_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | \
-				 _PAGE_HWWRITE)
-#endif
-#ifndef _PAGE_KERNEL_RWX
-#define _PAGE_KERNEL_RWX	(_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | \
-				 _PAGE_HWWRITE | _PAGE_EXEC)
-#endif
-#ifndef _PAGE_HPTEFLAGS
-#define _PAGE_HPTEFLAGS _PAGE_HASHPTE
-#endif
-#ifndef _PTE_NONE_MASK
-#define _PTE_NONE_MASK	_PAGE_HPTEFLAGS
-#endif
-
-#ifndef __ASSEMBLY__
-
-/*
- * Don't just check for any non zero bits in __PAGE_USER, 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.
- */
-static inline bool pte_user(pte_t pte)
-{
-	return (pte_val(pte) & (_PAGE_USER | _PAGE_PRIVILEGED)) == _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).
- * Platform who don't just pre-define the value so we don't override it here
- */
-#ifndef PTE_RPN_SHIFT
-#define PTE_RPN_SHIFT	(PAGE_SHIFT)
-#endif
-
-/* 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)
-#define PTE_RPN_MASK	(~((1ULL<<PTE_RPN_SHIFT)-1))
-#else
-#define PTE_RPN_MASK	(~((1UL<<PTE_RPN_SHIFT)-1))
-#endif
-
-/* _PAGE_CHG_MASK masks of bits that are to be preserved across
- * pgprot changes
- */
-#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
-                         _PAGE_ACCESSED | _PAGE_SPECIAL)
-
-/* Mask of bits returned by pte_pgprot() */
-#define PAGE_PROT_BITS	(_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \
-			 _PAGE_WRITETHRU | _PAGE_ENDIAN | _PAGE_4K_PFN | \
-			 _PAGE_USER | _PAGE_ACCESSED | _PAGE_RO | _PAGE_NA | \
-			 _PAGE_PRIVILEGED | \
-			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC)
-
-/*
- * We define 2 sets of base prot bits, one for basic pages (ie,
- * cacheable kernel and user pages) and one for non cacheable
- * 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)
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_STD_MMU) || \
-	defined(CONFIG_PPC_E500MC)
-#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,
- *
- * 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
- *
- * Note due to the way vm flags are laid out, the bits are XWR
- */
-#define PAGE_NONE	__pgprot(_PAGE_BASE | _PAGE_NA)
-#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 | _PAGE_RO)
-#define PAGE_COPY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RO | \
-				 _PAGE_EXEC)
-#define PAGE_READONLY	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RO)
-#define PAGE_READONLY_X	__pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RO | \
-				 _PAGE_EXEC)
-
-#define __P000	PAGE_NONE
-#define __P001	PAGE_READONLY
-#define __P010	PAGE_COPY
-#define __P011	PAGE_COPY
-#define __P100	PAGE_READONLY_X
-#define __P101	PAGE_READONLY_X
-#define __P110	PAGE_COPY_X
-#define __P111	PAGE_COPY_X
-
-#define __S000	PAGE_NONE
-#define __S001	PAGE_READONLY
-#define __S010	PAGE_SHARED
-#define __S011	PAGE_SHARED
-#define __S100	PAGE_READONLY_X
-#define __S101	PAGE_READONLY_X
-#define __S110	PAGE_SHARED_X
-#define __S111	PAGE_SHARED_X
-
-/* 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)
-#define PAGE_KERNEL_NCG	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \
-				 _PAGE_NO_CACHE | _PAGE_GUARDED)
-#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX)
-#define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
-#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)
-
-/* 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
-
-/* Advertise special mapping type for AGP */
-#define PAGE_AGP		(PAGE_KERNEL_NC)
-#define HAVE_PAGE_AGP
-
-#ifndef _PAGE_READ
-/* if not defined, we should not find _PAGE_WRITE too */
-#define _PAGE_READ 0
-#define _PAGE_WRITE _PAGE_RW
-#endif
-
-#ifndef H_PAGE_4K_PFN
-#define H_PAGE_4K_PFN 0
-#endif
diff --git a/arch/powerpc/include/asm/pte-walk.h b/arch/powerpc/include/asm/pte-walk.h
index 2d633e9..33fa5dd 100644
--- a/arch/powerpc/include/asm/pte-walk.h
+++ b/arch/powerpc/include/asm/pte-walk.h
@@ -10,8 +10,20 @@
 static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea,
 				    bool *is_thp, unsigned *hshift)
 {
+	pte_t *pte;
+
 	VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__);
-	return __find_linux_pte(pgdir, ea, is_thp, hshift);
+	pte = __find_linux_pte(pgdir, ea, is_thp, hshift);
+
+#if defined(CONFIG_DEBUG_VM) &&						\
+	!(defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE))
+	/*
+	 * We should not find huge page if these configs are not enabled.
+	 */
+	if (hshift)
+		WARN_ON(*hshift);
+#endif
+	return pte;
 }
 
 static inline pte_t *find_init_mm_pte(unsigned long ea, unsigned *hshift)
@@ -26,10 +38,22 @@
 static inline pte_t *find_current_mm_pte(pgd_t *pgdir, unsigned long ea,
 					 bool *is_thp, unsigned *hshift)
 {
+	pte_t *pte;
+
 	VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__);
 	VM_WARN(pgdir != current->mm->pgd,
 		"%s lock less page table lookup called on wrong mm\n", __func__);
-	return __find_linux_pte(pgdir, ea, is_thp, hshift);
+	pte = __find_linux_pte(pgdir, ea, is_thp, hshift);
+
+#if defined(CONFIG_DEBUG_VM) &&						\
+	!(defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE))
+	/*
+	 * We should not find huge page if these configs are not enabled.
+	 */
+	if (hshift)
+		WARN_ON(*hshift);
+#endif
+	return pte;
 }
 
 #endif /* _ASM_POWERPC_PTE_WALK_H */
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 447cbd1..ee3ada6 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2001 PPC64 Team, IBM Corp
  *
@@ -14,11 +15,6 @@
  *
  * Note that the offsets of the fields in this struct correspond with
  * the PT_* values below.  This simplifies arch/powerpc/kernel/ptrace.c.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_PTRACE_H
 #define _ASM_POWERPC_PTRACE_H
@@ -26,6 +22,45 @@
 #include <uapi/asm/ptrace.h>
 #include <asm/asm-const.h>
 
+#ifndef __ASSEMBLY__
+struct pt_regs
+{
+	union {
+		struct user_pt_regs user_regs;
+		struct {
+			unsigned long gpr[32];
+			unsigned long nip;
+			unsigned long msr;
+			unsigned long orig_gpr3;
+			unsigned long ctr;
+			unsigned long link;
+			unsigned long xer;
+			unsigned long ccr;
+#ifdef CONFIG_PPC64
+			unsigned long softe;
+#else
+			unsigned long mq;
+#endif
+			unsigned long trap;
+			unsigned long dar;
+			unsigned long dsisr;
+			unsigned long result;
+		};
+	};
+
+	union {
+		struct {
+#ifdef CONFIG_PPC64
+			unsigned long ppr;
+#endif
+#ifdef CONFIG_PPC_KUAP
+			unsigned long kuap;
+#endif
+		};
+		unsigned long __pad[2];	/* Maintain 16 byte interrupt stack alignment */
+	};
+};
+#endif
 
 #ifdef __powerpc64__
 
@@ -76,18 +111,33 @@
 
 #ifndef __ASSEMBLY__
 
-#define GET_IP(regs)		((regs)->nip)
-#define GET_USP(regs)		((regs)->gpr[1])
-#define GET_FP(regs)		(0)
-#define SET_FP(regs, val)
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+	return regs->nip;
+}
+
+static inline void instruction_pointer_set(struct pt_regs *regs,
+		unsigned long val)
+{
+	regs->nip = val;
+}
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+	return regs->gpr[1];
+}
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+	return 0;
+}
 
 #ifdef CONFIG_SMP
 extern unsigned long profile_pc(struct pt_regs *regs);
-#define profile_pc profile_pc
+#else
+#define profile_pc(regs) instruction_pointer(regs)
 #endif
 
-#include <asm-generic/ptrace.h>
-
 #define kernel_stack_pointer(regs) ((regs)->gpr[1])
 static inline int is_syscall_success(struct pt_regs *regs)
 {
@@ -102,6 +152,11 @@
 		return -regs->gpr[3];
 }
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->gpr[3] = rc;
+}
+
 #ifdef __powerpc64__
 #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1)
 #else
@@ -120,7 +175,7 @@
 			  unsigned long data);
 
 #define current_pt_regs() \
-	((struct pt_regs *)((unsigned long)current_thread_info() + THREAD_SIZE) - 1)
+	((struct pt_regs *)((unsigned long)task_stack_page(current) + THREAD_SIZE) - 1)
 /*
  * We use the least-significant bit of the trap field to indicate
  * whether we have saved the full set of registers, or only a
@@ -148,8 +203,12 @@
 #endif /* __powerpc64__ */
 
 #define arch_has_single_step()	(1)
-#define arch_has_block_step()	(!cpu_has_feature(CPU_FTR_601))
-#define ARCH_HAS_USER_SINGLE_STEP_INFO
+#ifndef CONFIG_BOOK3S_601
+#define arch_has_block_step()	(true)
+#else
+#define arch_has_block_step()	(false)
+#endif
+#define ARCH_HAS_USER_SINGLE_STEP_REPORT
 
 /*
  * kprobe-based event tracer support
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index e5b314e..b3cbb11 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -38,6 +38,7 @@
 #define MSR_TM_LG	32		/* Trans Mem Available */
 #define MSR_VEC_LG	25	        /* Enable AltiVec */
 #define MSR_VSX_LG	23		/* Enable VSX */
+#define MSR_S_LG	22		/* Secure state */
 #define MSR_POW_LG	18		/* Enable Power Management */
 #define MSR_WE_LG	18		/* Wait State Enable */
 #define MSR_TGPR_LG	17		/* TLB Update registers in use */
@@ -71,11 +72,13 @@
 #define MSR_SF		__MASK(MSR_SF_LG)	/* Enable 64 bit mode */
 #define MSR_ISF		__MASK(MSR_ISF_LG)	/* Interrupt 64b mode valid on 630 */
 #define MSR_HV 		__MASK(MSR_HV_LG)	/* Hypervisor state */
+#define MSR_S		__MASK(MSR_S_LG)	/* Secure state */
 #else
 /* so tests for these bits fail on 32-bit */
 #define MSR_SF		0
 #define MSR_ISF		0
 #define MSR_HV		0
+#define MSR_S		0
 #endif
 
 /*
@@ -118,11 +121,16 @@
 #define MSR_TS_S	__MASK(MSR_TS_S_LG)	/*  Transaction Suspended */
 #define MSR_TS_T	__MASK(MSR_TS_T_LG)	/*  Transaction Transactional */
 #define MSR_TS_MASK	(MSR_TS_T | MSR_TS_S)   /* Transaction State bits */
-#define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */
 #define MSR_TM_RESV(x) (((x) & MSR_TS_MASK) == MSR_TS_MASK) /* Reserved */
 #define MSR_TM_TRANSACTIONAL(x)	(((x) & MSR_TS_MASK) == MSR_TS_T)
 #define MSR_TM_SUSPENDED(x)	(((x) & MSR_TS_MASK) == MSR_TS_S)
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+#define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */
+#else
+#define MSR_TM_ACTIVE(x) 0
+#endif
+
 #if defined(CONFIG_PPC_BOOK3S_64)
 #define MSR_64BIT	MSR_SF
 
@@ -163,6 +171,7 @@
 #define PSSCR_ESL		0x00200000 /* Enable State Loss */
 #define PSSCR_SD		0x00400000 /* Status Disable */
 #define PSSCR_PLS	0xf000000000000000 /* Power-saving Level Status */
+#define PSSCR_PLS_SHIFT	60
 #define PSSCR_GUEST_VIS	0xf0000000000003ffUL /* Guest-visible PSSCR fields */
 #define PSSCR_FAKE_SUSPEND	0x00000400 /* Fake-suspend bit (P9 DD2.2) */
 #define PSSCR_FAKE_SUSPEND_LG	10	   /* Fake-suspend bit position */
@@ -415,6 +424,7 @@
 #define   HFSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define   HFSCR_VECVSX	__MASK(FSCR_VECVSX_LG)
 #define   HFSCR_FP	__MASK(FSCR_FP_LG)
+#define   HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56)	/* interrupt cause */
 #define SPRN_TAR	0x32f	/* Target Address Register */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
 #define   LPCR_VPM0		ASM_CONST(0x8000000000000000)
@@ -465,9 +475,10 @@
 #define   HMER_DEBUG_TRIG	(1ul << (63 - 17)) /* Debug trigger */
 #define	SPRN_HMEER	0x151	/* Hyp maintenance exception enable reg */
 #define SPRN_PCR	0x152	/* Processor compatibility register */
-#define   PCR_VEC_DIS	(1ul << (63-0))	/* Vec. disable (bit NA since POWER8) */
-#define   PCR_VSX_DIS	(1ul << (63-1))	/* VSX disable (bit NA since POWER8) */
-#define   PCR_TM_DIS	(1ul << (63-2))	/* Trans. memory disable (POWER8) */
+#define   PCR_VEC_DIS	(__MASK(63-0))	/* Vec. disable (bit NA since POWER8) */
+#define   PCR_VSX_DIS	(__MASK(63-1))	/* VSX disable (bit NA since POWER8) */
+#define   PCR_TM_DIS	(__MASK(63-2))	/* Trans. memory disable (POWER8) */
+#define   PCR_HIGH_BITS	(PCR_VEC_DIS | PCR_VSX_DIS | PCR_TM_DIS)
 /*
  * These bits are used in the function kvmppc_set_arch_compat() to specify and
  * determine both the compatibility level which we want to emulate and the
@@ -476,6 +487,8 @@
 #define   PCR_ARCH_207	0x8		/* Architecture 2.07 */
 #define   PCR_ARCH_206	0x4		/* Architecture 2.06 */
 #define   PCR_ARCH_205	0x2		/* Architecture 2.05 */
+#define   PCR_LOW_BITS	(PCR_ARCH_207 | PCR_ARCH_206 | PCR_ARCH_205)
+#define   PCR_MASK	~(PCR_HIGH_BITS | PCR_LOW_BITS)	/* PCR Reserved Bits */
 #define	SPRN_HEIR	0x153	/* Hypervisor Emulated Instruction Register */
 #define SPRN_TLBINDEXR	0x154	/* P7 TLB control register */
 #define SPRN_TLBVPNR	0x155	/* P7 TLB control register */
@@ -576,7 +589,7 @@
 #define HID0_POWER9_RADIX	__MASK(63 - 8)
 
 #define SPRN_HID1	0x3F1		/* Hardware Implementation Register 1 */
-#ifdef CONFIG_6xx
+#ifdef CONFIG_PPC_BOOK3S_32
 #define HID1_EMCP	(1<<31)		/* 7450 Machine Check Pin Enable */
 #define HID1_DFS	(1<<22)		/* 7447A Dynamic Frequency Scaling */
 #define HID1_PC0	(1<<16)		/* 7450 PLL_CFG[0] */
@@ -752,10 +765,9 @@
 #define	  SRR1_WAKERESET	0x00100000 /* System reset */
 #define   SRR1_WAKEHDBELL	0x000c0000 /* Hypervisor doorbell on P8 */
 #define	  SRR1_WAKESTATE	0x00030000 /* Powersave exit mask [46:47] */
-#define	  SRR1_WS_DEEPEST	0x00030000 /* Some resources not maintained,
-					  * may not be recoverable */
-#define	  SRR1_WS_DEEPER	0x00020000 /* Some resources not maintained */
-#define	  SRR1_WS_DEEP		0x00010000 /* All resources maintained */
+#define	  SRR1_WS_HVLOSS	0x00030000 /* HV resources not maintained */
+#define	  SRR1_WS_GPRLOSS	0x00020000 /* GPRs not maintained */
+#define	  SRR1_WS_NOLOSS	0x00010000 /* All resources maintained */
 #define   SRR1_PROGTM		0x00200000 /* TM Bad Thing */
 #define   SRR1_PROGFPE		0x00100000 /* Floating Point Enabled */
 #define   SRR1_PROGILL		0x00080000 /* Illegal instruction */
@@ -763,9 +775,12 @@
 #define   SRR1_PROGTRAP		0x00020000 /* Trap */
 #define   SRR1_PROGADDR		0x00010000 /* SRR0 contains subsequent addr */
 
+#define   SRR1_MCE_MCP		0x00080000 /* Machine check signal caused interrupt */
+
 #define SPRN_HSRR0	0x13A	/* Save/Restore Register 0 */
 #define SPRN_HSRR1	0x13B	/* Save/Restore Register 1 */
 #define   HSRR1_DENORM		0x00100000 /* Denorm exception */
+#define   HSRR1_HISI_WRITE	0x00010000 /* HISI bcs couldn't update mem */
 
 #define SPRN_TBCTL	0x35f	/* PA6T Timebase control register */
 #define   TBCTL_FREEZE		0x0000000000000000ull /* Freeze all tbs */
@@ -1053,7 +1068,7 @@
  *	- SPRG9 debug exception scratch
  *
  * All 32-bit:
- *	- SPRG3 current thread_info pointer
+ *	- SPRG3 current thread_struct physical addr pointer
  *        (virtual on BookE, physical on others)
  *
  * 32-bit classic:
@@ -1158,7 +1173,7 @@
 #ifdef CONFIG_PPC_BOOK3S_32
 #define SPRN_SPRG_SCRATCH0	SPRN_SPRG0
 #define SPRN_SPRG_SCRATCH1	SPRN_SPRG1
-#define SPRN_SPRG_RTAS		SPRN_SPRG2
+#define SPRN_SPRG_PGDIR		SPRN_SPRG2
 #define SPRN_SPRG_603_LRU	SPRN_SPRG4
 #endif
 
@@ -1416,6 +1431,11 @@
 #define mfsrin(v)	({unsigned int rval; \
 			asm volatile("mfsrin %0,%1" : "=r" (rval) : "r" (v)); \
 					rval;})
+
+static inline void mtsrin(u32 val, u32 idx)
+{
+	asm volatile("mtsrin %0, %1" : : "r" (val), "r" (idx));
+}
 #endif
 
 #define proc_trap()	asm volatile("trap")
diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h
index 74c2c57..74fba29 100644
--- a/arch/powerpc/include/asm/reg_a2.h
+++ b/arch/powerpc/include/asm/reg_a2.h
@@ -1,12 +1,8 @@
+/* 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.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #ifndef __ASM_POWERPC_REG_A2_H__
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index eb2a33d..f26fe48 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -1,3 +1,4 @@
+/* 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
@@ -5,10 +6,6 @@
  * before Book E was finalized, and are included here as well.  Unfortunately,
  * they sometimes used different locations than true Book E CPUs did.
  *
- * 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.
- *
  * Copyright 2009-2010 Freescale Semiconductor, Inc.
  */
 #ifdef __KERNEL__
@@ -41,7 +38,7 @@
 #if defined(CONFIG_PPC_BOOK3E_64)
 #define MSR_64BIT	MSR_CM
 
-#define MSR_		(MSR_ME | MSR_CE)
+#define MSR_		(MSR_ME | MSR_RI | MSR_CE)
 #define MSR_KERNEL	(MSR_ | MSR_64BIT)
 #define MSR_USER32	(MSR_ | MSR_PR | MSR_EE)
 #define MSR_USER64	(MSR_USER32 | MSR_64BIT)
diff --git a/arch/powerpc/include/asm/rio.h b/arch/powerpc/include/asm/rio.h
index ec800f2..0e57cda 100644
--- a/arch/powerpc/include/asm/rio.h
+++ b/arch/powerpc/include/asm/rio.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * RapidIO architecture support
  *
  * Copyright 2005 MontaVista Software, Inc.
  * Matt Porter <mporter@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef ASM_PPC_RIO_H
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 71e393c..3c18873 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _POWERPC_RTAS_H
 #define _POWERPC_RTAS_H
 #ifdef __KERNEL__
@@ -5,17 +6,13 @@
 #include <linux/spinlock.h>
 #include <asm/page.h>
 #include <linux/time.h>
+#include <linux/cpumask.h>
 
 /*
  * Definitions for talking to the RTAS on CHRP machines.
  *
  * Copyright (C) 2001 Peter Bergner
  * Copyright (C) 2001 PPC 64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define RTAS_UNKNOWN_SERVICE (-1)
@@ -125,6 +122,7 @@
 #define RTAS_TYPE_INFO			0xE2
 #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_PMGM_POWER_SW_ON	0x60
 #define RTAS_TYPE_PMGM_POWER_SW_OFF	0x61
@@ -185,11 +183,23 @@
 	return (elog->byte1 & 0x18) >> 3;
 }
 
+static inline
+void rtas_set_disposition_recovered(struct rtas_error_log *elog)
+{
+	elog->byte1 &= ~0x18;
+	elog->byte1 |= (RTAS_DISP_FULLY_RECOVERED << 3);
+}
+
 static inline uint8_t rtas_error_extended(const struct rtas_error_log *elog)
 {
 	return (elog->byte1 & 0x04) >> 2;
 }
 
+static inline uint8_t rtas_error_initiator(const struct rtas_error_log *elog)
+{
+	return (elog->byte2 & 0xf0) >> 4;
+}
+
 #define rtas_error_type(x)	((x)->byte3)
 
 static inline
@@ -275,6 +285,7 @@
 #define PSERIES_ELOG_SECT_ID_CALL_HOME		(('C' << 8) | 'H')
 #define PSERIES_ELOG_SECT_ID_USER_DEF		(('U' << 8) | 'D')
 #define PSERIES_ELOG_SECT_ID_HOTPLUG		(('H' << 8) | 'P')
+#define PSERIES_ELOG_SECT_ID_MCE		(('M' << 8) | 'C')
 
 /* Vendor specific Platform Event Log Format, Version 6, section header */
 struct pseries_errorlog {
@@ -316,6 +327,7 @@
 #define PSERIES_HP_ELOG_RESOURCE_MEM	2
 #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_ACTION_ADD	1
 #define PSERIES_HP_ELOG_ACTION_REMOVE	2
diff --git a/arch/powerpc/include/asm/scom.h b/arch/powerpc/include/asm/scom.h
deleted file mode 100644
index f5cde45..0000000
--- a/arch/powerpc/include/asm/scom.h
+++ /dev/null
@@ -1,167 +0,0 @@
-/*
- * Copyright 2010 Benjamin Herrenschmidt, IBM Corp
- *                <benh@kernel.crashing.org>
- *     and        David Gibson, IBM 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; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
- *   the GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program;  if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef _ASM_POWERPC_SCOM_H
-#define _ASM_POWERPC_SCOM_H
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_PPC_SCOM
-
-/*
- * The SCOM bus is a sideband bus used for accessing various internal
- * registers of the processor or the chipset. The implementation details
- * differ between processors and platforms, and the access method as
- * well.
- *
- * This API allows to "map" ranges of SCOM register numbers associated
- * with a given SCOM controller. The later must be represented by a
- * device node, though some implementations might support NULL if there
- * is no possible ambiguity
- *
- * Then, scom_read/scom_write can be used to accesses registers inside
- * that range. The argument passed is a register number relative to
- * the beginning of the range mapped.
- */
-
-typedef void *scom_map_t;
-
-/* Value for an invalid SCOM map */
-#define SCOM_MAP_INVALID	(NULL)
-
-/* The scom_controller data structure is what the platform passes
- * to the core code in scom_init, it provides the actual implementation
- * of all the SCOM functions
- */
-struct scom_controller {
-	scom_map_t (*map)(struct device_node *ctrl_dev, u64 reg, u64 count);
-	void (*unmap)(scom_map_t map);
-
-	int (*read)(scom_map_t map, u64 reg, u64 *value);
-	int (*write)(scom_map_t map, u64 reg, u64 value);
-};
-
-extern const struct scom_controller *scom_controller;
-
-/**
- * scom_init - Initialize the SCOM backend, called by the platform
- * @controller: The platform SCOM controller
- */
-static inline void scom_init(const struct scom_controller *controller)
-{
-	scom_controller = controller;
-}
-
-/**
- * scom_map_ok - Test is a SCOM mapping is successful
- * @map: The result of scom_map to test
- */
-static inline int scom_map_ok(scom_map_t map)
-{
-	return map != SCOM_MAP_INVALID;
-}
-
-/**
- * scom_map - Map a block of SCOM registers
- * @ctrl_dev: Device node of the SCOM controller
- *            some implementations allow NULL here
- * @reg: first SCOM register to map
- * @count: Number of SCOM registers to map
- */
-
-static inline scom_map_t scom_map(struct device_node *ctrl_dev,
-				  u64 reg, u64 count)
-{
-	return scom_controller->map(ctrl_dev, reg, count);
-}
-
-/**
- * scom_find_parent - Find the SCOM controller for a device
- * @dev: OF node of the device
- *
- * This is not meant for general usage, but in combination with
- * scom_map() allows to map registers not represented by the
- * device own scom-reg property. Useful for applying HW workarounds
- * on things not properly represented in the device-tree for example.
- */
-struct device_node *scom_find_parent(struct device_node *dev);
-
-
-/**
- * scom_map_device - Map a device's block of SCOM registers
- * @dev: OF node of the device
- * @index: Register bank index (index in "scom-reg" property)
- *
- * This function will use the device-tree binding for SCOM which
- * is to follow "scom-parent" properties until it finds a node with
- * a "scom-controller" property to find the controller. It will then
- * use the "scom-reg" property which is made of reg/count pairs,
- * each of them having a size defined by the controller's #scom-cells
- * property
- */
-extern scom_map_t scom_map_device(struct device_node *dev, int index);
-
-
-/**
- * scom_unmap - Unmap a block of SCOM registers
- * @map: Result of scom_map is to be unmapped
- */
-static inline void scom_unmap(scom_map_t map)
-{
-	if (scom_map_ok(map))
-		scom_controller->unmap(map);
-}
-
-/**
- * scom_read - Read a SCOM register
- * @map: Result of scom_map
- * @reg: Register index within that map
- * @value: Updated with the value read
- *
- * Returns 0 (success) or a negative error code
- */
-static inline int scom_read(scom_map_t map, u64 reg, u64 *value)
-{
-	int rc;
-
-	rc = scom_controller->read(map, reg, value);
-	if (rc)
-		*value = 0xfffffffffffffffful;
-	return rc;
-}
-
-/**
- * scom_write - Write to a SCOM register
- * @map: Result of scom_map
- * @reg: Register index within that map
- * @value: Value to write
- *
- * Returns 0 (success) or a negative error code
- */
-static inline int scom_write(scom_map_t map, u64 reg, u64 value)
-{
-	return scom_controller->write(map, reg, value);
-}
-
-
-#endif /* CONFIG_PPC_SCOM */
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_SCOM_H */
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index e335a8f..5a9b6eb 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -17,6 +17,13 @@
 extern char __prom_init_toc_start[];
 extern char __prom_init_toc_end[];
 
+#ifdef CONFIG_PPC_POWERNV
+extern char start_real_trampolines[];
+extern char end_real_trampolines[];
+extern char start_virt_trampolines[];
+extern char end_virt_trampolines[];
+#endif
+
 static inline int in_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_stext && addr < (unsigned long)__init_end)
@@ -54,17 +61,6 @@
 		(unsigned long)_stext < end;
 }
 
-static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end)
-{
-#ifdef CONFIG_KVM_GUEST
-	extern char kvm_tmp[];
-	return start < (unsigned long)kvm_tmp &&
-		(unsigned long)&kvm_tmp[1024 * 1024] < end;
-#else
-	return 0;
-#endif
-}
-
 #ifdef PPC64_ELF_ABI_v1
 
 #define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index 759597b..ccf44c1 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -81,6 +81,9 @@
 // Software required to flush count cache on context switch
 #define SEC_FTR_FLUSH_COUNT_CACHE	0x0000000000000400ull
 
+// Software required to flush link stack on context switch
+#define SEC_FTR_FLUSH_LINK_STACK	0x0000000000001000ull
+
 
 // Features enabled by default
 #define SEC_FTR_DEFAULT \
diff --git a/arch/powerpc/include/asm/serial.h b/arch/powerpc/include/asm/serial.h
index 3e8589b..cd6c18d 100644
--- a/arch/powerpc/include/asm/serial.h
+++ b/arch/powerpc/include/asm/serial.h
@@ -1,8 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_SERIAL_H
 #define _ASM_POWERPC_SERIAL_H
diff --git a/arch/powerpc/include/asm/setjmp.h b/arch/powerpc/include/asm/setjmp.h
index 279d03a..e9f81bb 100644
--- a/arch/powerpc/include/asm/setjmp.h
+++ b/arch/powerpc/include/asm/setjmp.h
@@ -1,18 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright © 2008 Michael Neuling IBM 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; either version
- *      2 of the License, or (at your option) any later version.
- *
  */
 #ifndef _ASM_POWERPC_SETJMP_H
 #define _ASM_POWERPC_SETJMP_H
 
 #define JMP_BUF_LEN    23
 
-extern long setjmp(long *);
-extern void longjmp(long *, long);
+extern long setjmp(long *) __attribute__((returns_twice));
+extern void longjmp(long *, long) __attribute__((noreturn));
 
 #endif /* _ASM_POWERPC_SETJMP_H */
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 1fffbba..65676e2 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -67,6 +67,13 @@
 static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { };
 #endif
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+void setup_spectre_v2(void);
+#else
+static inline void setup_spectre_v2(void) {};
+#endif
+void do_btb_flush_fixups(void);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_SETUP_H */
diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h
index d89beab..8b957aa 100644
--- a/arch/powerpc/include/asm/sfp-machine.h
+++ b/arch/powerpc/include/asm/sfp-machine.h
@@ -213,30 +213,18 @@
  * respectively.  The result is placed in HIGH_SUM and LOW_SUM.  Overflow
  * (i.e. carry out) is not stored anywhere, and is lost.
  */
-#define add_ssaaaa(sh, sl, ah, al, bh, bl)				\
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
   do {									\
     if (__builtin_constant_p (bh) && (bh) == 0)				\
-      __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2"		\
-	     : "=r" ((USItype)(sh)),					\
-	       "=&r" ((USItype)(sl))					\
-	     : "%r" ((USItype)(ah)),					\
-	       "%r" ((USItype)(al)),					\
-	       "rI" ((USItype)(bl)));					\
-    else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0)		\
-      __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2"		\
-	     : "=r" ((USItype)(sh)),					\
-	       "=&r" ((USItype)(sl))					\
-	     : "%r" ((USItype)(ah)),					\
-	       "%r" ((USItype)(al)),					\
-	       "rI" ((USItype)(bl)));					\
+      __asm__ ("add%I4c %1,%3,%4\n\taddze %0,%2"		\
+	     : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
+    else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0)		\
+      __asm__ ("add%I4c %1,%3,%4\n\taddme %0,%2"		\
+	     : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\
     else								\
-      __asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3"		\
-	     : "=r" ((USItype)(sh)),					\
-	       "=&r" ((USItype)(sl))					\
-	     : "%r" ((USItype)(ah)),					\
-	       "r" ((USItype)(bh)),					\
-	       "%r" ((USItype)(al)),					\
-	       "rI" ((USItype)(bl)));					\
+      __asm__ ("add%I5c %1,%4,%5\n\tadde %0,%2,%3"		\
+	     : "=r" (sh), "=&r" (sl)					\
+	     : "%r" (ah), "r" (bh), "%r" (al), "rI" (bl));		\
   } while (0)
 
 /* sub_ddmmss is used in op-2.h and udivmodti4.c and should be equivalent to
@@ -248,44 +236,24 @@
  * and LOW_DIFFERENCE.  Overflow (i.e. carry out) is not stored anywhere,
  * and is lost.
  */
-#define sub_ddmmss(sh, sl, ah, al, bh, bl)				\
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
   do {									\
     if (__builtin_constant_p (ah) && (ah) == 0)				\
-      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2"	\
-	       : "=r" ((USItype)(sh)),					\
-		 "=&r" ((USItype)(sl))					\
-	       : "r" ((USItype)(bh)),					\
-		 "rI" ((USItype)(al)),					\
-		 "r" ((USItype)(bl)));					\
-    else if (__builtin_constant_p (ah) && (ah) ==~(USItype) 0)		\
-      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2"	\
-	       : "=r" ((USItype)(sh)),					\
-		 "=&r" ((USItype)(sl))					\
-	       : "r" ((USItype)(bh)),					\
-		 "rI" ((USItype)(al)),					\
-		 "r" ((USItype)(bl)));					\
+      __asm__ ("subf%I3c %1,%4,%3\n\tsubfze %0,%2"	\
+	       : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
+    else if (__builtin_constant_p (ah) && (ah) == ~(USItype) 0)		\
+      __asm__ ("subf%I3c %1,%4,%3\n\tsubfme %0,%2"	\
+	       : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\
     else if (__builtin_constant_p (bh) && (bh) == 0)			\
-      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2"		\
-	       : "=r" ((USItype)(sh)),					\
-		 "=&r" ((USItype)(sl))					\
-	       : "r" ((USItype)(ah)),					\
-		 "rI" ((USItype)(al)),					\
-		 "r" ((USItype)(bl)));					\
-    else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0)		\
-      __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2"		\
-	       : "=r" ((USItype)(sh)),					\
-		 "=&r" ((USItype)(sl))					\
-	       : "r" ((USItype)(ah)),					\
-		 "rI" ((USItype)(al)),					\
-		 "r" ((USItype)(bl)));					\
+      __asm__ ("subf%I3c %1,%4,%3\n\taddme %0,%2"		\
+	       : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
+    else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0)		\
+      __asm__ ("subf%I3c %1,%4,%3\n\taddze %0,%2"		\
+	       : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\
     else								\
-      __asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2"	\
-	       : "=r" ((USItype)(sh)),					\
-		 "=&r" ((USItype)(sl))					\
-	       : "r" ((USItype)(ah)),					\
-		 "r" ((USItype)(bh)),					\
-		 "rI" ((USItype)(al)),					\
-		 "r" ((USItype)(bl)));					\
+      __asm__ ("subf%I4c %1,%5,%4\n\tsubfe %0,%3,%2"	\
+	       : "=r" (sh), "=&r" (sl)					\
+	       : "r" (ah), "r" (bh), "rI" (al), "r" (bl));		\
   } while (0)
 
 /* asm fragments for mul and div */
@@ -294,13 +262,10 @@
  * UWtype integers MULTIPLER and MULTIPLICAND, and generates a two UWtype
  * word product in HIGH_PROD and LOW_PROD.
  */
-#define umul_ppmm(ph, pl, m0, m1)					\
+#define umul_ppmm(ph, pl, m0, m1) \
   do {									\
     USItype __m0 = (m0), __m1 = (m1);					\
-    __asm__ ("mulhwu %0,%1,%2"						\
-	     : "=r" ((USItype)(ph))					\
-	     : "%r" (__m0),						\
-               "r" (__m1));						\
+    __asm__ ("mulhwu %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1));	\
     (pl) = __m0 * __m1;							\
   } while (0)
 
@@ -312,9 +277,10 @@
  * significant bit of DENOMINATOR must be 1, then the pre-processor symbol
  * UDIV_NEEDS_NORMALIZATION is defined to 1.
  */
-#define udiv_qrnnd(q, r, n1, n0, d)					\
+#define udiv_qrnnd(q, r, n1, n0, d) \
   do {									\
-    UWtype __d1, __d0, __q1, __q0, __r1, __r0, __m;			\
+    UWtype __d1, __d0, __q1, __q0;					\
+    UWtype __r1, __r0, __m;						\
     __d1 = __ll_highpart (d);						\
     __d0 = __ll_lowpart (d);						\
 									\
@@ -325,7 +291,7 @@
     if (__r1 < __m)							\
       {									\
 	__q1--, __r1 += (d);						\
-	if (__r1 >= (d)) /* we didn't get carry when adding to __r1 */	\
+	if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\
 	  if (__r1 < __m)						\
 	    __q1--, __r1 += (d);					\
       }									\
diff --git a/arch/powerpc/include/asm/slice.h b/arch/powerpc/include/asm/slice.h
index e40406c..c6f466f 100644
--- a/arch/powerpc/include/asm/slice.h
+++ b/arch/powerpc/include/asm/slice.h
@@ -4,12 +4,14 @@
 
 #ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/book3s/64/slice.h>
-#elif defined(CONFIG_PPC64)
-#include <asm/nohash/64/slice.h>
-#elif defined(CONFIG_PPC_MMU_NOHASH)
+#elif defined(CONFIG_PPC_MMU_NOHASH_32)
 #include <asm/nohash/32/slice.h>
 #endif
 
+#ifndef __ASSEMBLY__
+
+struct mm_struct;
+
 #ifdef CONFIG_PPC_MM_SLICES
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -18,10 +20,6 @@
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
-#ifndef __ASSEMBLY__
-
-struct mm_struct;
-
 unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 				      unsigned long flags, unsigned int psize,
 				      int topdown);
@@ -32,9 +30,19 @@
 			   unsigned long len, unsigned int psize);
 
 void slice_init_new_context_exec(struct mm_struct *mm);
+void slice_setup_new_exec(void);
 
-#endif /* __ASSEMBLY__ */
+#else /* CONFIG_PPC_MM_SLICES */
+
+static inline void slice_init_new_context_exec(struct mm_struct *mm) {}
+
+static inline unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
+{
+	return 0;
+}
 
 #endif /* CONFIG_PPC_MM_SLICES */
 
+#endif /* __ASSEMBLY__ */
+
 #endif /* _ASM_POWERPC_SLICE_H */
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 95b66a0..49a25e2 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* 
  * smp.h: PowerPC-specific SMP code.
  *
@@ -6,11 +7,6 @@
  *
  * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
  * Copyright (C) 1996-2001 Cort Dougan <cort@fsmlabs.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_SMP_H
@@ -83,7 +79,22 @@
 /* 32-bit */
 extern int smp_hw_index[];
 
-#define raw_smp_processor_id()	(current_thread_info()->cpu)
+/*
+ * This is particularly ugly: it appears we can't actually get the definition
+ * of task_struct here, but we need access to the CPU this task is running on.
+ * Instead of using task_struct we're using _TASK_CPU which is extracted from
+ * asm-offsets.h by kbuild to get the current processor ID.
+ *
+ * This also needs to be safeguarded when building asm-offsets.s because at
+ * that time _TASK_CPU is not defined yet. It could have been guarded by
+ * _TASK_CPU itself, but we want the build to fail if _TASK_CPU is missing
+ * when building something else than asm-offsets.s
+ */
+#ifdef GENERATING_ASM_OFFSETS
+#define raw_smp_processor_id()		(0)
+#else
+#define raw_smp_processor_id()		(*(unsigned int *)((void *)current + _TASK_CPU))
+#endif
 #define hard_smp_processor_id() 	(smp_hw_index[smp_processor_id()])
 
 static inline int get_hard_smp_processor_id(int cpu)
@@ -100,6 +111,7 @@
 DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
 DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
 
 static inline struct cpumask *cpu_sibling_mask(int cpu)
 {
@@ -116,6 +128,11 @@
 	return per_cpu(cpu_l2_cache_map, cpu);
 }
 
+static inline struct cpumask *cpu_smallcore_mask(int cpu)
+{
+	return per_cpu(cpu_smallcore_map, cpu);
+}
+
 extern int cpu_to_core_id(int cpu);
 
 /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers.
@@ -166,6 +183,11 @@
 	return cpumask_of(cpu);
 }
 
+static inline const struct cpumask *cpu_smallcore_mask(int cpu)
+{
+	return cpumask_of(cpu);
+}
+
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index 28f5dae..3192d45 100644
--- a/arch/powerpc/include/asm/sparsemem.h
+++ b/arch/powerpc/include/asm/sparsemem.h
@@ -9,17 +9,6 @@
  * MAX_PHYSMEM_BITS		2^N: how much memory we can have in that space
  */
 #define SECTION_SIZE_BITS       24
-/*
- * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS
- * if we increase SECTIONS_WIDTH we will not store node details in page->flags and
- * page_to_nid does a page->section->node lookup
- * Hence only increase for VMEMMAP.
- */
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-#define MAX_PHYSMEM_BITS        47
-#else
-#define MAX_PHYSMEM_BITS        46
-#endif
 
 #endif /* CONFIG_SPARSEMEM */
 
@@ -28,9 +17,9 @@
 extern int remove_section_mapping(unsigned long start, unsigned long end);
 
 #ifdef CONFIG_PPC_BOOK3S_64
-extern void resize_hpt_for_hotplug(unsigned long new_mem_size);
+extern int resize_hpt_for_hotplug(unsigned long new_mem_size);
 #else
-static inline void resize_hpt_for_hotplug(unsigned long new_mem_size) { }
+static inline int resize_hpt_for_hotplug(unsigned long new_mem_size) { return 0; }
 #endif
 
 #ifdef CONFIG_NUMA
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 685c723..e9a960e 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 #ifdef __KERNEL__
@@ -12,11 +13,6 @@
  *
  * Type of int is used as a full 64b word is not necessary.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * (the type definitions are in asm/spinlock_types.h)
  */
 #include <linux/irqflags.h>
@@ -39,19 +35,6 @@
 #define LOCK_TOKEN	1
 #endif
 
-#if defined(CONFIG_PPC64) && defined(CONFIG_SMP)
-#define CLEAR_IO_SYNC	(get_paca()->io_sync = 0)
-#define SYNC_IO		do {						\
-				if (unlikely(get_paca()->io_sync)) {	\
-					mb();				\
-					get_paca()->io_sync = 0;	\
-				}					\
-			} while (0)
-#else
-#define CLEAR_IO_SYNC
-#define SYNC_IO
-#endif
-
 #ifdef CONFIG_PPC_PSERIES
 #define vcpu_is_preempted vcpu_is_preempted
 static inline bool vcpu_is_preempted(int cpu)
@@ -99,7 +82,6 @@
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	CLEAR_IO_SYNC;
 	return __arch_spin_trylock(lock) == 0;
 }
 
@@ -119,25 +101,52 @@
 
 #if defined(CONFIG_PPC_SPLPAR)
 /* We only yield to the hypervisor if we are in shared processor mode */
-#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca->lppaca_ptr))
-extern void __spin_yield(arch_spinlock_t *lock);
-extern void __rw_yield(arch_rwlock_t *lock);
+void splpar_spin_yield(arch_spinlock_t *lock);
+void splpar_rw_yield(arch_rwlock_t *lock);
 #else /* SPLPAR */
-#define __spin_yield(x)	barrier()
-#define __rw_yield(x)	barrier()
-#define SHARED_PROCESSOR	0
+static inline void splpar_spin_yield(arch_spinlock_t *lock) {};
+static inline void splpar_rw_yield(arch_rwlock_t *lock) {};
 #endif
 
+static inline bool is_shared_processor(void)
+{
+/*
+ * LPPACA is only available on Pseries so guard anything LPPACA related to
+ * allow other platforms (which include this common header) to compile.
+ */
+#ifdef CONFIG_PPC_PSERIES
+	return (IS_ENABLED(CONFIG_PPC_SPLPAR) &&
+		lppaca_shared_proc(local_paca->lppaca_ptr));
+#else
+	return false;
+#endif
+}
+
+static inline void spin_yield(arch_spinlock_t *lock)
+{
+	if (is_shared_processor())
+		splpar_spin_yield(lock);
+	else
+		barrier();
+}
+
+static inline void rw_yield(arch_rwlock_t *lock)
+{
+	if (is_shared_processor())
+		splpar_rw_yield(lock);
+	else
+		barrier();
+}
+
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
-	CLEAR_IO_SYNC;
 	while (1) {
 		if (likely(__arch_spin_trylock(lock) == 0))
 			break;
 		do {
 			HMT_low();
-			if (SHARED_PROCESSOR)
-				__spin_yield(lock);
+			if (is_shared_processor())
+				splpar_spin_yield(lock);
 		} while (unlikely(lock->slock != 0));
 		HMT_medium();
 	}
@@ -148,7 +157,6 @@
 {
 	unsigned long flags_dis;
 
-	CLEAR_IO_SYNC;
 	while (1) {
 		if (likely(__arch_spin_trylock(lock) == 0))
 			break;
@@ -156,8 +164,8 @@
 		local_irq_restore(flags);
 		do {
 			HMT_low();
-			if (SHARED_PROCESSOR)
-				__spin_yield(lock);
+			if (is_shared_processor())
+				splpar_spin_yield(lock);
 		} while (unlikely(lock->slock != 0));
 		HMT_medium();
 		local_irq_restore(flags_dis);
@@ -167,7 +175,6 @@
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	SYNC_IO;
 	__asm__ __volatile__("# arch_spin_unlock\n\t"
 				PPC_RELEASE_BARRIER: : :"memory");
 	lock->slock = 0;
@@ -247,8 +254,8 @@
 			break;
 		do {
 			HMT_low();
-			if (SHARED_PROCESSOR)
-				__rw_yield(rw);
+			if (is_shared_processor())
+				splpar_rw_yield(rw);
 		} while (unlikely(rw->lock < 0));
 		HMT_medium();
 	}
@@ -261,8 +268,8 @@
 			break;
 		do {
 			HMT_low();
-			if (SHARED_PROCESSOR)
-				__rw_yield(rw);
+			if (is_shared_processor())
+				splpar_rw_yield(rw);
 		} while (unlikely(rw->lock != 0));
 		HMT_medium();
 	}
@@ -302,9 +309,9 @@
 	rw->lock = 0;
 }
 
-#define arch_spin_relax(lock)	__spin_yield(lock)
-#define arch_read_relax(lock)	__rw_yield(lock)
-#define arch_write_relax(lock)	__rw_yield(lock)
+#define arch_spin_relax(lock)	spin_yield(lock)
+#define arch_read_relax(lock)	rw_yield(lock)
+#define arch_write_relax(lock)	rw_yield(lock)
 
 /* See include/linux/spinlock.h */
 #define smp_mb__after_spinlock()   smp_mb()
diff --git a/arch/powerpc/include/asm/spu.h b/arch/powerpc/include/asm/spu.h
index a6e6e2b..9666491 100644
--- a/arch/powerpc/include/asm/spu.h
+++ b/arch/powerpc/include/asm/spu.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * SPU core / file system interface and HW structures
  *
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef _SPU_H
diff --git a/arch/powerpc/include/asm/spu_csa.h b/arch/powerpc/include/asm/spu_csa.h
index 51f80b4..c33df96 100644
--- a/arch/powerpc/include/asm/spu_csa.h
+++ b/arch/powerpc/include/asm/spu_csa.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * spu_csa.h: Definitions for SPU context save area (CSA).
  *
  * (C) Copyright IBM 2005
  *
  * Author: Mark Nutter <mnutter@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef _SPU_CSA_H_
diff --git a/arch/powerpc/include/asm/spu_info.h b/arch/powerpc/include/asm/spu_info.h
index 7146b78..7324310 100644
--- a/arch/powerpc/include/asm/spu_info.h
+++ b/arch/powerpc/include/asm/spu_info.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * SPU info structures
  *
  * (C) Copyright 2006 IBM Corp.
  *
  * Author: Dwayne Grant McConnell <decimal@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef _SPU_INFO_H
 #define _SPU_INFO_H
diff --git a/arch/powerpc/include/asm/spu_priv1.h b/arch/powerpc/include/asm/spu_priv1.h
index d8f5c60..2167d75 100644
--- a/arch/powerpc/include/asm/spu_priv1.h
+++ b/arch/powerpc/include/asm/spu_priv1.h
@@ -1,20 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Defines an spu hypervisor abstraction layer.
  *
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #if !defined(_SPU_PRIV1_H)
diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h
index 4547891..769f055 100644
--- a/arch/powerpc/include/asm/sstep.h
+++ b/arch/powerpc/include/asm/sstep.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2004 Paul Mackerras <paulus@au.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 struct pt_regs;
diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h
new file mode 100644
index 0000000..1c8460e
--- /dev/null
+++ b/arch/powerpc/include/asm/stackprotector.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * GCC stack protector support.
+ *
+ */
+
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H
+
+#include <linux/random.h>
+#include <linux/version.h>
+#include <asm/reg.h>
+#include <asm/current.h>
+#include <asm/paca.h>
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	unsigned long canary;
+
+	/* Try to get a semi random initial value. */
+	canary = get_random_canary();
+	canary ^= mftb();
+	canary ^= LINUX_VERSION_CODE;
+	canary &= CANARY_MASK;
+
+	current->stack_canary = canary;
+#ifdef CONFIG_PPC64
+	get_paca()->canary = canary;
+#endif
+}
+
+#endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 1647de1..b726927 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -4,14 +4,17 @@
 
 #ifdef __KERNEL__
 
+#ifndef CONFIG_KASAN
 #define __HAVE_ARCH_STRNCPY
 #define __HAVE_ARCH_STRNCMP
+#define __HAVE_ARCH_MEMCHR
+#define __HAVE_ARCH_MEMCMP
+#define __HAVE_ARCH_MEMSET16
+#endif
+
 #define __HAVE_ARCH_MEMSET
 #define __HAVE_ARCH_MEMCPY
 #define __HAVE_ARCH_MEMMOVE
-#define __HAVE_ARCH_MEMCMP
-#define __HAVE_ARCH_MEMCHR
-#define __HAVE_ARCH_MEMSET16
 #define __HAVE_ARCH_MEMCPY_FLUSHCACHE
 
 extern char * strcpy(char *,const char *);
@@ -27,10 +30,32 @@
 extern void * memchr(const void *,int,__kernel_size_t);
 extern void * memcpy_flushcache(void *,const void *,__kernel_size_t);
 
+void *__memset(void *s, int c, __kernel_size_t count);
+void *__memcpy(void *to, const void *from, __kernel_size_t n);
+void *__memmove(void *to, const void *from, __kernel_size_t n);
+
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * should use not instrumented version of mem* functions.
+ */
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
+#endif
+
 #ifdef CONFIG_PPC64
+#ifndef CONFIG_KASAN
 #define __HAVE_ARCH_MEMSET32
 #define __HAVE_ARCH_MEMSET64
+#define __HAVE_ARCH_MEMCPY_MCSAFE
 
+extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz);
 extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t);
 extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
 extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t);
@@ -49,8 +74,11 @@
 {
 	return __memset64(p, v, n * 8);
 }
+#endif
 #else
+#ifndef CONFIG_KASAN
 #define __HAVE_ARCH_STRLEN
+#endif
 
 extern void *memset16(uint16_t *, uint16_t, __kernel_size_t);
 #endif
diff --git a/arch/powerpc/include/asm/svm.h b/arch/powerpc/include/asm/svm.h
new file mode 100644
index 0000000..85580b3
--- /dev/null
+++ b/arch/powerpc/include/asm/svm.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * SVM helper functions
+ *
+ * Copyright 2018 Anshuman Khandual, IBM Corporation.
+ */
+
+#ifndef _ASM_POWERPC_SVM_H
+#define _ASM_POWERPC_SVM_H
+
+#ifdef CONFIG_PPC_SVM
+
+static inline bool is_secure_guest(void)
+{
+	return mfmsr() & MSR_S;
+}
+
+void dtl_cache_ctor(void *addr);
+#define get_dtl_cache_ctor()	(is_secure_guest() ? dtl_cache_ctor : NULL)
+
+#else /* CONFIG_PPC_SVM */
+
+static inline bool is_secure_guest(void)
+{
+	return false;
+}
+
+#define get_dtl_cache_ctor() NULL
+
+#endif /* CONFIG_PPC_SVM */
+#endif /* _ASM_POWERPC_SVM_H */
diff --git a/arch/powerpc/include/asm/swab.h b/arch/powerpc/include/asm/swab.h
index 487e090..f4cfdc1 100644
--- a/arch/powerpc/include/asm/swab.h
+++ b/arch/powerpc/include/asm/swab.h
@@ -1,8 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_SWAB_H
 #define _ASM_POWERPC_SWAB_H
diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h
index f65ecf5..3c1a1cd 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -1,11 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2009 Becky Bruce, Freescale Semiconductor
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 #ifndef __ASM_SWIOTLB_H
@@ -13,12 +8,7 @@
 
 #include <linux/swiotlb.h>
 
-extern const struct dma_map_ops powerpc_swiotlb_dma_ops;
-
 extern unsigned int ppc_swiotlb_enable;
-int __init swiotlb_setup_bus_notifier(void);
-
-extern void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev);
 
 #ifdef CONFIG_SWIOTLB
 void swiotlb_detect_4g(void);
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index ab9f3f0..38d62ac 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Access to user system call parameters and results
  *
  * Copyright (C) 2008 Red Hat, Inc.  All rights reserved.
  *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License v.2.
- *
  * See asm-generic/syscall.h for descriptions of what we must do here.
  */
 
@@ -18,9 +15,8 @@
 #include <linux/thread_info.h>
 
 /* ftrace syscalls requires exporting the sys_call_table */
-#ifdef CONFIG_FTRACE_SYSCALLS
 extern const unsigned long sys_call_table[];
-#endif /* CONFIG_FTRACE_SYSCALLS */
+extern const unsigned long compat_sys_call_table[];
 
 static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
@@ -39,6 +35,16 @@
 	regs->gpr[3] = regs->orig_gpr3;
 }
 
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	/*
+	 * If the system call failed,
+	 * regs->gpr[3] contains a positive ERRORCODE.
+	 */
+	return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0;
+}
+
 static inline long syscall_get_return_value(struct task_struct *task,
 					    struct pt_regs *regs)
 {
@@ -66,22 +72,20 @@
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
 	unsigned long val, mask = -1UL;
-
-	BUG_ON(i + n > 6);
+	unsigned int n = 6;
 
 #ifdef CONFIG_COMPAT
 	if (test_tsk_thread_flag(task, TIF_32BIT))
 		mask = 0xffffffff;
 #endif
 	while (n--) {
-		if (n == 0 && i == 0)
+		if (n == 0)
 			val = regs->orig_gpr3;
 		else
-			val = regs->gpr[3 + i + n];
+			val = regs->gpr[3 + n];
 
 		args[n] = val & mask;
 	}
@@ -89,20 +93,23 @@
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-	memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
+	memcpy(&regs->gpr[3], args, 6 * sizeof(args[0]));
 
 	/* Also copy the first argument into orig_gpr3 */
-	if (i == 0 && n > 0)
-		regs->orig_gpr3 = args[0];
+	regs->orig_gpr3 = args[0];
 }
 
-static inline int syscall_get_arch(void)
+static inline int syscall_get_arch(struct task_struct *task)
 {
-	int arch = is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64;
+	int arch;
+
+	if (IS_ENABLED(CONFIG_PPC64) && !test_tsk_thread_flag(task, TIF_32BIT))
+		arch = AUDIT_ARCH_PPC64;
+	else
+		arch = AUDIT_ARCH_PPC;
+
 #ifdef __LITTLE_ENDIAN__
 	arch |= __AUDIT_ARCH_LE;
 #endif
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
deleted file mode 100644
index 01b5171..0000000
--- a/arch/powerpc/include/asm/systbl.h
+++ /dev/null
@@ -1,396 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * List of powerpc syscalls. For the meaning of the _SPU suffix see
- * arch/powerpc/platforms/cell/spu_callbacks.c
- */
-
-SYSCALL(restart_syscall)
-SYSCALL(exit)
-PPC_SYS(fork)
-SYSCALL_SPU(read)
-SYSCALL_SPU(write)
-COMPAT_SYS_SPU(open)
-SYSCALL_SPU(close)
-SYSCALL_SPU(waitpid)
-SYSCALL_SPU(creat)
-SYSCALL_SPU(link)
-SYSCALL_SPU(unlink)
-COMPAT_SYS(execve)
-SYSCALL_SPU(chdir)
-COMPAT_SYS_SPU(time)
-SYSCALL_SPU(mknod)
-SYSCALL_SPU(chmod)
-SYSCALL_SPU(lchown)
-SYSCALL(ni_syscall)
-OLDSYS(stat)
-COMPAT_SYS_SPU(lseek)
-SYSCALL_SPU(getpid)
-COMPAT_SYS(mount)
-SYSX(sys_ni_syscall,sys_oldumount,sys_oldumount)
-SYSCALL_SPU(setuid)
-SYSCALL_SPU(getuid)
-COMPAT_SYS_SPU(stime)
-COMPAT_SYS(ptrace)
-SYSCALL_SPU(alarm)
-OLDSYS(fstat)
-SYSCALL(pause)
-COMPAT_SYS(utime)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL_SPU(access)
-SYSCALL_SPU(nice)
-SYSCALL(ni_syscall)
-SYSCALL_SPU(sync)
-SYSCALL_SPU(kill)
-SYSCALL_SPU(rename)
-SYSCALL_SPU(mkdir)
-SYSCALL_SPU(rmdir)
-SYSCALL_SPU(dup)
-SYSCALL_SPU(pipe)
-COMPAT_SYS_SPU(times)
-SYSCALL(ni_syscall)
-SYSCALL_SPU(brk)
-SYSCALL_SPU(setgid)
-SYSCALL_SPU(getgid)
-SYSCALL(signal)
-SYSCALL_SPU(geteuid)
-SYSCALL_SPU(getegid)
-SYSCALL(acct)
-SYSCALL(umount)
-SYSCALL(ni_syscall)
-COMPAT_SYS_SPU(ioctl)
-COMPAT_SYS_SPU(fcntl)
-SYSCALL(ni_syscall)
-SYSCALL_SPU(setpgid)
-SYSCALL(ni_syscall)
-SYSX(sys_ni_syscall,sys_olduname,sys_olduname)
-SYSCALL_SPU(umask)
-SYSCALL_SPU(chroot)
-COMPAT_SYS(ustat)
-SYSCALL_SPU(dup2)
-SYSCALL_SPU(getppid)
-SYSCALL_SPU(getpgrp)
-SYSCALL_SPU(setsid)
-SYS32ONLY(sigaction)
-SYSCALL_SPU(sgetmask)
-SYSCALL_SPU(ssetmask)
-SYSCALL_SPU(setreuid)
-SYSCALL_SPU(setregid)
-#define compat_sys_sigsuspend sys_sigsuspend
-SYS32ONLY(sigsuspend)
-SYSX(sys_ni_syscall,compat_sys_sigpending,sys_sigpending)
-SYSCALL_SPU(sethostname)
-COMPAT_SYS_SPU(setrlimit)
-SYSX(sys_ni_syscall,compat_sys_old_getrlimit,sys_old_getrlimit)
-COMPAT_SYS_SPU(getrusage)
-COMPAT_SYS_SPU(gettimeofday)
-COMPAT_SYS_SPU(settimeofday)
-SYSCALL_SPU(getgroups)
-SYSCALL_SPU(setgroups)
-SYSX(sys_ni_syscall,sys_ni_syscall,ppc_select)
-SYSCALL_SPU(symlink)
-OLDSYS(lstat)
-SYSCALL_SPU(readlink)
-SYSCALL(uselib)
-SYSCALL(swapon)
-SYSCALL(reboot)
-SYSX(sys_ni_syscall,compat_sys_old_readdir,sys_old_readdir)
-SYSCALL_SPU(mmap)
-SYSCALL_SPU(munmap)
-COMPAT_SYS_SPU(truncate)
-COMPAT_SYS_SPU(ftruncate)
-SYSCALL_SPU(fchmod)
-SYSCALL_SPU(fchown)
-SYSCALL_SPU(getpriority)
-SYSCALL_SPU(setpriority)
-SYSCALL(ni_syscall)
-COMPAT_SYS(statfs)
-COMPAT_SYS(fstatfs)
-SYSCALL(ni_syscall)
-COMPAT_SYS_SPU(socketcall)
-SYSCALL_SPU(syslog)
-COMPAT_SYS_SPU(setitimer)
-COMPAT_SYS_SPU(getitimer)
-COMPAT_SYS_SPU(newstat)
-COMPAT_SYS_SPU(newlstat)
-COMPAT_SYS_SPU(newfstat)
-SYSX(sys_ni_syscall,sys_uname,sys_uname)
-SYSCALL(ni_syscall)
-SYSCALL_SPU(vhangup)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-COMPAT_SYS_SPU(wait4)
-SYSCALL(swapoff)
-COMPAT_SYS_SPU(sysinfo)
-COMPAT_SYS(ipc)
-SYSCALL_SPU(fsync)
-SYS32ONLY(sigreturn)
-PPC_SYS(clone)
-SYSCALL_SPU(setdomainname)
-SYSCALL_SPU(newuname)
-SYSCALL(ni_syscall)
-COMPAT_SYS_SPU(adjtimex)
-SYSCALL_SPU(mprotect)
-SYSX(sys_ni_syscall,compat_sys_sigprocmask,sys_sigprocmask)
-SYSCALL(ni_syscall)
-SYSCALL(init_module)
-SYSCALL(delete_module)
-SYSCALL(ni_syscall)
-SYSCALL(quotactl)
-SYSCALL_SPU(getpgid)
-SYSCALL_SPU(fchdir)
-SYSCALL_SPU(bdflush)
-SYSCALL_SPU(sysfs)
-SYSX_SPU(ppc64_personality,ppc64_personality,sys_personality)
-SYSCALL(ni_syscall)
-SYSCALL_SPU(setfsuid)
-SYSCALL_SPU(setfsgid)
-SYSCALL_SPU(llseek)
-COMPAT_SYS_SPU(getdents)
-COMPAT_SPU_NEW(select)
-SYSCALL_SPU(flock)
-SYSCALL_SPU(msync)
-COMPAT_SYS_SPU(readv)
-COMPAT_SYS_SPU(writev)
-SYSCALL_SPU(getsid)
-SYSCALL_SPU(fdatasync)
-COMPAT_SYS(sysctl)
-SYSCALL_SPU(mlock)
-SYSCALL_SPU(munlock)
-SYSCALL_SPU(mlockall)
-SYSCALL_SPU(munlockall)
-SYSCALL_SPU(sched_setparam)
-SYSCALL_SPU(sched_getparam)
-SYSCALL_SPU(sched_setscheduler)
-SYSCALL_SPU(sched_getscheduler)
-SYSCALL_SPU(sched_yield)
-SYSCALL_SPU(sched_get_priority_max)
-SYSCALL_SPU(sched_get_priority_min)
-COMPAT_SYS_SPU(sched_rr_get_interval)
-COMPAT_SYS_SPU(nanosleep)
-SYSCALL_SPU(mremap)
-SYSCALL_SPU(setresuid)
-SYSCALL_SPU(getresuid)
-SYSCALL(ni_syscall)
-SYSCALL_SPU(poll)
-SYSCALL(ni_syscall)
-SYSCALL_SPU(setresgid)
-SYSCALL_SPU(getresgid)
-SYSCALL_SPU(prctl)
-COMPAT_SYS(rt_sigreturn)
-COMPAT_SYS(rt_sigaction)
-COMPAT_SYS(rt_sigprocmask)
-COMPAT_SYS(rt_sigpending)
-COMPAT_SYS(rt_sigtimedwait)
-COMPAT_SYS(rt_sigqueueinfo)
-COMPAT_SYS(rt_sigsuspend)
-COMPAT_SYS_SPU(pread64)
-COMPAT_SYS_SPU(pwrite64)
-SYSCALL_SPU(chown)
-SYSCALL_SPU(getcwd)
-SYSCALL_SPU(capget)
-SYSCALL_SPU(capset)
-COMPAT_SYS(sigaltstack)
-SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-PPC_SYS(vfork)
-COMPAT_SYS_SPU(getrlimit)
-COMPAT_SYS_SPU(readahead)
-SYS32ONLY(mmap2)
-SYS32ONLY(truncate64)
-SYS32ONLY(ftruncate64)
-SYSX(sys_ni_syscall,sys_stat64,sys_stat64)
-SYSX(sys_ni_syscall,sys_lstat64,sys_lstat64)
-SYSX(sys_ni_syscall,sys_fstat64,sys_fstat64)
-SYSCALL(pciconfig_read)
-SYSCALL(pciconfig_write)
-SYSCALL(pciconfig_iobase)
-SYSCALL(ni_syscall)
-SYSCALL_SPU(getdents64)
-SYSCALL_SPU(pivot_root)
-SYSX(sys_ni_syscall,compat_sys_fcntl64,sys_fcntl64)
-SYSCALL_SPU(madvise)
-SYSCALL_SPU(mincore)
-SYSCALL_SPU(gettid)
-SYSCALL_SPU(tkill)
-SYSCALL_SPU(setxattr)
-SYSCALL_SPU(lsetxattr)
-SYSCALL_SPU(fsetxattr)
-SYSCALL_SPU(getxattr)
-SYSCALL_SPU(lgetxattr)
-SYSCALL_SPU(fgetxattr)
-SYSCALL_SPU(listxattr)
-SYSCALL_SPU(llistxattr)
-SYSCALL_SPU(flistxattr)
-SYSCALL_SPU(removexattr)
-SYSCALL_SPU(lremovexattr)
-SYSCALL_SPU(fremovexattr)
-COMPAT_SYS_SPU(futex)
-COMPAT_SYS_SPU(sched_setaffinity)
-COMPAT_SYS_SPU(sched_getaffinity)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYS32ONLY(sendfile64)
-COMPAT_SYS_SPU(io_setup)
-SYSCALL_SPU(io_destroy)
-COMPAT_SYS_SPU(io_getevents)
-COMPAT_SYS_SPU(io_submit)
-SYSCALL_SPU(io_cancel)
-SYSCALL(set_tid_address)
-SYSX_SPU(sys_fadvise64,ppc32_fadvise64,sys_fadvise64)
-SYSCALL(exit_group)
-COMPAT_SYS(lookup_dcookie)
-SYSCALL_SPU(epoll_create)
-SYSCALL_SPU(epoll_ctl)
-SYSCALL_SPU(epoll_wait)
-SYSCALL_SPU(remap_file_pages)
-COMPAT_SYS_SPU(timer_create)
-COMPAT_SYS_SPU(timer_settime)
-COMPAT_SYS_SPU(timer_gettime)
-SYSCALL_SPU(timer_getoverrun)
-SYSCALL_SPU(timer_delete)
-COMPAT_SYS_SPU(clock_settime)
-COMPAT_SYS_SPU(clock_gettime)
-COMPAT_SYS_SPU(clock_getres)
-COMPAT_SYS_SPU(clock_nanosleep)
-SYSX(ppc64_swapcontext,ppc32_swapcontext,ppc_swapcontext)
-SYSCALL_SPU(tgkill)
-COMPAT_SYS_SPU(utimes)
-COMPAT_SYS_SPU(statfs64)
-COMPAT_SYS_SPU(fstatfs64)
-SYSX(sys_ni_syscall,ppc_fadvise64_64,ppc_fadvise64_64)
-SYSCALL_SPU(rtas)
-OLDSYS(debug_setcontext)
-SYSCALL(ni_syscall)
-COMPAT_SYS(migrate_pages)
-COMPAT_SYS(mbind)
-COMPAT_SYS(get_mempolicy)
-COMPAT_SYS(set_mempolicy)
-COMPAT_SYS(mq_open)
-SYSCALL(mq_unlink)
-COMPAT_SYS(mq_timedsend)
-COMPAT_SYS(mq_timedreceive)
-COMPAT_SYS(mq_notify)
-COMPAT_SYS(mq_getsetattr)
-COMPAT_SYS(kexec_load)
-SYSCALL(add_key)
-SYSCALL(request_key)
-COMPAT_SYS(keyctl)
-COMPAT_SYS(waitid)
-SYSCALL(ioprio_set)
-SYSCALL(ioprio_get)
-SYSCALL(inotify_init)
-SYSCALL(inotify_add_watch)
-SYSCALL(inotify_rm_watch)
-SYSCALL(spu_run)
-SYSCALL(spu_create)
-COMPAT_SYS(pselect6)
-COMPAT_SYS(ppoll)
-SYSCALL_SPU(unshare)
-SYSCALL_SPU(splice)
-SYSCALL_SPU(tee)
-COMPAT_SYS_SPU(vmsplice)
-COMPAT_SYS_SPU(openat)
-SYSCALL_SPU(mkdirat)
-SYSCALL_SPU(mknodat)
-SYSCALL_SPU(fchownat)
-COMPAT_SYS_SPU(futimesat)
-SYSX_SPU(sys_newfstatat,sys_fstatat64,sys_fstatat64)
-SYSCALL_SPU(unlinkat)
-SYSCALL_SPU(renameat)
-SYSCALL_SPU(linkat)
-SYSCALL_SPU(symlinkat)
-SYSCALL_SPU(readlinkat)
-SYSCALL_SPU(fchmodat)
-SYSCALL_SPU(faccessat)
-COMPAT_SYS_SPU(get_robust_list)
-COMPAT_SYS_SPU(set_robust_list)
-COMPAT_SYS_SPU(move_pages)
-SYSCALL_SPU(getcpu)
-COMPAT_SYS(epoll_pwait)
-COMPAT_SYS_SPU(utimensat)
-COMPAT_SYS_SPU(signalfd)
-SYSCALL_SPU(timerfd_create)
-SYSCALL_SPU(eventfd)
-COMPAT_SYS_SPU(sync_file_range2)
-COMPAT_SYS(fallocate)
-SYSCALL(subpage_prot)
-COMPAT_SYS_SPU(timerfd_settime)
-COMPAT_SYS_SPU(timerfd_gettime)
-COMPAT_SYS_SPU(signalfd4)
-SYSCALL_SPU(eventfd2)
-SYSCALL_SPU(epoll_create1)
-SYSCALL_SPU(dup3)
-SYSCALL_SPU(pipe2)
-SYSCALL(inotify_init1)
-SYSCALL_SPU(perf_event_open)
-COMPAT_SYS_SPU(preadv)
-COMPAT_SYS_SPU(pwritev)
-COMPAT_SYS(rt_tgsigqueueinfo)
-SYSCALL(fanotify_init)
-COMPAT_SYS(fanotify_mark)
-SYSCALL_SPU(prlimit64)
-SYSCALL_SPU(socket)
-SYSCALL_SPU(bind)
-SYSCALL_SPU(connect)
-SYSCALL_SPU(listen)
-SYSCALL_SPU(accept)
-SYSCALL_SPU(getsockname)
-SYSCALL_SPU(getpeername)
-SYSCALL_SPU(socketpair)
-SYSCALL_SPU(send)
-SYSCALL_SPU(sendto)
-COMPAT_SYS_SPU(recv)
-COMPAT_SYS_SPU(recvfrom)
-SYSCALL_SPU(shutdown)
-COMPAT_SYS_SPU(setsockopt)
-COMPAT_SYS_SPU(getsockopt)
-COMPAT_SYS_SPU(sendmsg)
-COMPAT_SYS_SPU(recvmsg)
-COMPAT_SYS_SPU(recvmmsg)
-SYSCALL_SPU(accept4)
-SYSCALL_SPU(name_to_handle_at)
-COMPAT_SYS_SPU(open_by_handle_at)
-COMPAT_SYS_SPU(clock_adjtime)
-SYSCALL_SPU(syncfs)
-COMPAT_SYS_SPU(sendmmsg)
-SYSCALL_SPU(setns)
-COMPAT_SYS(process_vm_readv)
-COMPAT_SYS(process_vm_writev)
-SYSCALL(finit_module)
-SYSCALL(kcmp) /* sys_kcmp */
-SYSCALL_SPU(sched_setattr)
-SYSCALL_SPU(sched_getattr)
-SYSCALL_SPU(renameat2)
-SYSCALL_SPU(seccomp)
-SYSCALL_SPU(getrandom)
-SYSCALL_SPU(memfd_create)
-SYSCALL_SPU(bpf)
-COMPAT_SYS(execveat)
-PPC64ONLY(switch_endian)
-SYSCALL_SPU(userfaultfd)
-SYSCALL_SPU(membarrier)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(ni_syscall)
-SYSCALL(mlock2)
-SYSCALL(copy_file_range)
-COMPAT_SYS_SPU(preadv2)
-COMPAT_SYS_SPU(pwritev2)
-SYSCALL(kexec_file_load)
-SYSCALL(statx)
-SYSCALL(pkey_alloc)
-SYSCALL(pkey_free)
-SYSCALL(pkey_mprotect)
-SYSCALL(rseq)
-COMPAT_SYS(io_pgetevents)
diff --git a/arch/powerpc/include/asm/task_size_32.h b/arch/powerpc/include/asm/task_size_32.h
new file mode 100644
index 0000000..de7290e
--- /dev/null
+++ b/arch/powerpc/include/asm/task_size_32.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_TASK_SIZE_32_H
+#define _ASM_POWERPC_TASK_SIZE_32_H
+
+#if CONFIG_TASK_SIZE > CONFIG_KERNEL_START
+#error User TASK_SIZE overlaps with KERNEL_START address
+#endif
+
+#define TASK_SIZE (CONFIG_TASK_SIZE)
+
+/*
+ * This decides where the kernel will search for a free chunk of vm space during
+ * mmap's.
+ */
+#define TASK_UNMAPPED_BASE (TASK_SIZE / 8 * 3)
+
+#define DEFAULT_MAP_WINDOW TASK_SIZE
+#define STACK_TOP TASK_SIZE
+#define STACK_TOP_MAX STACK_TOP
+
+#endif /* _ASM_POWERPC_TASK_SIZE_32_H */
diff --git a/arch/powerpc/include/asm/task_size_64.h b/arch/powerpc/include/asm/task_size_64.h
new file mode 100644
index 0000000..c993482
--- /dev/null
+++ b/arch/powerpc/include/asm/task_size_64.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_TASK_SIZE_64_H
+#define _ASM_POWERPC_TASK_SIZE_64_H
+
+/*
+ * 64-bit user address space can have multiple limits
+ * For now supported values are:
+ */
+#define TASK_SIZE_64TB  (0x0000400000000000UL)
+#define TASK_SIZE_128TB (0x0000800000000000UL)
+#define TASK_SIZE_512TB (0x0002000000000000UL)
+#define TASK_SIZE_1PB   (0x0004000000000000UL)
+#define TASK_SIZE_2PB   (0x0008000000000000UL)
+
+/*
+ * With 52 bits in the address we can support up to 4PB of range.
+ */
+#define TASK_SIZE_4PB   (0x0010000000000000UL)
+
+/*
+ * For now 512TB is only supported with book3s and 64K linux page size.
+ */
+#ifdef CONFIG_PPC_64K_PAGES
+/*
+ * Max value currently used:
+ */
+#define TASK_SIZE_USER64		TASK_SIZE_4PB
+#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_128TB
+#define TASK_CONTEXT_SIZE		TASK_SIZE_512TB
+#else
+#define TASK_SIZE_USER64		TASK_SIZE_64TB
+#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_64TB
+
+/*
+ * We don't need to allocate extended context ids for 4K page size, because we
+ * limit the max effective address on this config to 64TB.
+ */
+#define TASK_CONTEXT_SIZE TASK_SIZE_64TB
+#endif
+
+/*
+ * 32-bit user address space is 4GB - 1 page
+ * (this 1 page is needed so referencing of 0xFFFFFFFF generates EFAULT
+ */
+#define TASK_SIZE_USER32 (0x0000000100000000UL - (1 * PAGE_SIZE))
+
+#define TASK_SIZE_OF(tsk)						\
+	(test_tsk_thread_flag(tsk, TIF_32BIT) ? TASK_SIZE_USER32 :	\
+						TASK_SIZE_USER64)
+
+#define TASK_SIZE TASK_SIZE_OF(current)
+
+#define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
+#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4))
+
+/*
+ * This decides where the kernel will search for a free chunk of vm space during
+ * mmap's.
+ */
+#define TASK_UNMAPPED_BASE	\
+	((is_32bit_task()) ? TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64)
+
+/*
+ * Initial task size value for user applications. For book3s 64 we start
+ * with 128TB and conditionally enable upto 512TB
+ */
+#ifdef CONFIG_PPC_BOOK3S_64
+#define DEFAULT_MAP_WINDOW	\
+	((is_32bit_task()) ? TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64)
+#else
+#define DEFAULT_MAP_WINDOW	TASK_SIZE
+#endif
+
+#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64
+#define STACK_TOP_USER32 TASK_SIZE_USER32
+#define STACK_TOP_MAX TASK_SIZE_USER64
+#define STACK_TOP (is_32bit_task() ? STACK_TOP_USER32 : STACK_TOP_USER64)
+
+#endif /* _ASM_POWERPC_TASK_SIZE_64_H */
diff --git a/arch/powerpc/include/asm/tce.h b/arch/powerpc/include/asm/tce.h
index 12e3629..db5fc2f 100644
--- a/arch/powerpc/include/asm/tce.h
+++ b/arch/powerpc/include/asm/tce.h
@@ -1,21 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
  * Rewrite, cleanup:
  * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #ifndef _ASM_POWERPC_TCE_H
diff --git a/arch/powerpc/include/asm/termios.h b/arch/powerpc/include/asm/termios.h
index b8353e2..205de8f 100644
--- a/arch/powerpc/include/asm/termios.h
+++ b/arch/powerpc/include/asm/termios.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Liberally adapted from alpha/termios.h.  In particular, the c_cc[]
  * fields have been reordered so that termio & termios share the
  * common subset in the same order (for brain dead programs that don't
  * know or care about the differences).
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_TERMIOS_H
 #define _ASM_POWERPC_TERMIOS_H
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 3c00020..8e1d019 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -17,24 +17,17 @@
 
 #define THREAD_SIZE		(1 << THREAD_SHIFT)
 
-#ifdef CONFIG_PPC64
-#define CURRENT_THREAD_INFO(dest, sp)	stringify_in_c(clrrdi dest, sp, THREAD_SHIFT)
-#else
-#define CURRENT_THREAD_INFO(dest, sp)	stringify_in_c(rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT)
-#endif
-
 #ifndef __ASSEMBLY__
 #include <linux/cache.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/accounting.h>
 
+#define SLB_PRELOAD_NR	16U
 /*
  * low level task data.
  */
 struct thread_info {
-	struct task_struct *task;		/* main task structure */
-	int		cpu;			/* cpu we're on */
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
 	unsigned long	local_flags;		/* private flags for thread */
@@ -44,6 +37,10 @@
 #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC32)
 	struct cpu_accounting_data accounting;
 #endif
+	unsigned char slb_preload_nr;
+	unsigned char slb_preload_tail;
+	u32 slb_preload_esid[SLB_PRELOAD_NR];
+
 	/* low level flags - has atomic operations done on it */
 	unsigned long	flags ____cacheline_aligned_in_smp;
 };
@@ -53,8 +50,6 @@
  */
 #define INIT_THREAD_INFO(tsk)			\
 {						\
-	.task =		&tsk,			\
-	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.flags =	0,			\
 }
@@ -62,16 +57,13 @@
 #define THREAD_SIZE_ORDER	(THREAD_SHIFT - PAGE_SHIFT)
 
 /* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-	unsigned long val;
-
-	asm (CURRENT_THREAD_INFO(%0,1) : "=r" (val));
-
-	return (struct thread_info *)val;
-}
-
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+void arch_setup_new_exec(void);
+#define arch_setup_new_exec arch_setup_new_exec
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 /*
@@ -81,7 +73,7 @@
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
 #define TIF_FSCHECK		3	/* Check FS is USER_DS on return */
-#define TIF_32BIT		4	/* 32 bit binary */
+#define TIF_SYSCALL_EMU		4	/* syscall emulation active */
 #define TIF_RESTORE_TM		5	/* need to restore TM FP/VEC/VSX */
 #define TIF_PATCH_PENDING	6	/* pending live patching update */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
@@ -100,6 +92,7 @@
 #define TIF_ELF2ABI		18	/* function descriptors must die! */
 #endif
 #define TIF_POLLING_NRFLAG	19	/* true if poll_idle() is polling TIF_NEED_RESCHED */
+#define TIF_32BIT		20	/* 32 bit binary */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -120,9 +113,10 @@
 #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
 #define _TIF_NOHZ		(1<<TIF_NOHZ)
 #define _TIF_FSCHECK		(1<<TIF_FSCHECK)
+#define _TIF_SYSCALL_EMU	(1<<TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_DOTRACE	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
-				 _TIF_NOHZ)
+				 _TIF_NOHZ | _TIF_SYSCALL_EMU)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index b80d492..08dbe3e 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Common time prototypes and such for all ppc machines.
  *
  * Written by Cort Dougan (cort@cs.nmt.edu) to merge
  * Paul Mackerras' version and mine for PReP and Pmac.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef __POWERPC_TIME_H
@@ -36,6 +32,8 @@
 extern unsigned long ppc_tb_freq;
 #define DEFAULT_TB_FREQ		125000000UL
 
+extern bool tb_invalid;
+
 struct div_result {
 	u64 result_high;
 	u64 result_low;
@@ -43,11 +41,7 @@
 
 /* Accessor functions for the timebase (RTC on 601) registers. */
 /* If one day CONFIG_POWER is added just define __USE_RTC as 1 */
-#ifdef CONFIG_6xx
-#define __USE_RTC()	(cpu_has_feature(CPU_FTR_USE_RTC))
-#else
-#define __USE_RTC()	0
-#endif
+#define __USE_RTC()	(IS_ENABLED(CONFIG_PPC_BOOK3S_601))
 
 #ifdef CONFIG_PPC64
 
diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h
index 926b9f9..d2d2c4b 100644
--- a/arch/powerpc/include/asm/timex.h
+++ b/arch/powerpc/include/asm/timex.h
@@ -17,38 +17,10 @@
 
 static inline cycles_t get_cycles(void)
 {
-#ifdef __powerpc64__
+	if (IS_ENABLED(CONFIG_BOOK3S_601))
+		return 0;
+
 	return mftb();
-#else
-	cycles_t ret;
-
-	/*
-	 * For the "cycle" counter we use the timebase lower half.
-	 * Currently only used on SMP.
-	 */
-
-	ret = 0;
-
-	__asm__ __volatile__(
-#ifdef CONFIG_PPC_8xx
-		"97:	mftb %0\n"
-#else
-		"97:	mfspr %0, %2\n"
-#endif
-		"99:\n"
-		".section __ftr_fixup,\"a\"\n"
-		".align 2\n"
-		"98:\n"
-		"	.long %1\n"
-		"	.long 0\n"
-		"	.long 97b-98b\n"
-		"	.long 99b-98b\n"
-		"	.long 0\n"
-		"	.long 0\n"
-		".previous"
-		: "=r" (ret) : "i" (CPU_FTR_601), "i" (SPRN_TBRL));
-	return ret;
-#endif
 }
 
 #endif	/* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index f0e571b..b2c0be9 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *	TLB shootdown specifics for powerpc
  *
  * Copyright (C) 2002 Anton Blanchard, IBM Corp.
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_TLB_H
 #define _ASM_POWERPC_TLB_H
@@ -27,8 +23,8 @@
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
 #define __tlb_remove_tlb_entry	__tlb_remove_tlb_entry
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
 
+#define tlb_flush tlb_flush
 extern void tlb_flush(struct mmu_gather *tlb);
 
 /* Get the generic bits... */
@@ -40,28 +36,12 @@
 static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
 					  unsigned long address)
 {
-#ifdef CONFIG_PPC_STD_MMU_32
+#ifdef CONFIG_PPC_BOOK3S_32
 	if (pte_val(*ptep) & _PAGE_HASHPTE)
 		flush_hash_entry(tlb->mm, ptep, address);
 #endif
 }
 
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-	if (!tlb->page_size)
-		tlb->page_size = page_size;
-	else if (tlb->page_size != page_size) {
-		if (!tlb->fullmm)
-			tlb_flush_mmu(tlb);
-		/*
-		 * update the page size after flush for the new
-		 * mmu_gather.
-		 */
-		tlb->page_size = page_size;
-	}
-}
-
 #ifdef CONFIG_SMP
 static inline int mm_is_core_local(struct mm_struct *mm)
 {
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index a4a718d..2f7e1ea 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -35,6 +35,7 @@
 				 cpu_all_mask :				\
 				 cpumask_of_node(pcibus_to_node(bus)))
 
+extern int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc);
 extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 
@@ -84,6 +85,11 @@
 
 static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {}
 
+static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	return 0;
+}
+
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
@@ -132,6 +138,8 @@
 #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))
+
+int dlpar_cpu_readd(int cpu);
 #endif
 #endif
 
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index d018e86..08cd60c 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -54,6 +54,22 @@
 	TP_ARGS(regs)
 );
 
+#ifdef CONFIG_PPC_DOORBELL
+DEFINE_EVENT(ppc64_interrupt_class, doorbell_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs)
+);
+
+DEFINE_EVENT(ppc64_interrupt_class, doorbell_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs)
+);
+#endif
+
 #ifdef CONFIG_PPC_PSERIES
 extern int hcall_tracepoint_regfunc(void);
 extern void hcall_tracepoint_unregfunc(void);
@@ -201,6 +217,21 @@
 		__entry->r)
 );
 
+TRACE_EVENT(tlbia,
+
+	TP_PROTO(unsigned long id),
+	TP_ARGS(id),
+	TP_STRUCT__entry(
+		__field(unsigned long, id)
+		),
+
+	TP_fast_assign(
+		__entry->id = id;
+		),
+
+	TP_printk("ctx.id=0x%lx", __entry->id)
+);
+
 #endif /* _TRACE_POWERPC_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/powerpc/include/asm/trace_clock.h b/arch/powerpc/include/asm/trace_clock.h
index cf1ee75..ef70c2f 100644
--- a/arch/powerpc/include/asm/trace_clock.h
+++ b/arch/powerpc/include/asm/trace_clock.h
@@ -1,7 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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.
  *
  * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
  */
diff --git a/arch/powerpc/include/asm/tsi108.h b/arch/powerpc/include/asm/tsi108.h
index c2a955b..8a2b642 100644
--- a/arch/powerpc/include/asm/tsi108.h
+++ b/arch/powerpc/include/asm/tsi108.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * common routine and memory layout for Tundra TSI108(Grendel) host bridge
  * memory controller.
@@ -6,11 +7,6 @@
  *	   Alex Bounine (alexandreb@tundra.com)
  *
  * Copyright 2004-2006 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef __PPC_KERNEL_TSI108_H
diff --git a/arch/powerpc/include/asm/tsi108_irq.h b/arch/powerpc/include/asm/tsi108_irq.h
index 6ed9397..df602ca 100644
--- a/arch/powerpc/include/asm/tsi108_irq.h
+++ b/arch/powerpc/include/asm/tsi108_irq.h
@@ -1,24 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * (C) Copyright 2005 Tundra Semiconductor Corp.
  * Alex Bounine, <alexandreb at tundra.com).
  *
  * See file CREDITS for list of people who contributed to this
  * project.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
  */
 
 /*
diff --git a/arch/powerpc/include/asm/tsi108_pci.h b/arch/powerpc/include/asm/tsi108_pci.h
index ae59d5b..fb6f626 100644
--- a/arch/powerpc/include/asm/tsi108_pci.h
+++ b/arch/powerpc/include/asm/tsi108_pci.h
@@ -1,21 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2007 IBM Corp
- *
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
  */
 
 #ifndef _ASM_POWERPC_TSI108_PCI_H
diff --git a/arch/powerpc/include/asm/types.h b/arch/powerpc/include/asm/types.h
index 49a0678..f1630c5 100644
--- a/arch/powerpc/include/asm/types.h
+++ b/arch/powerpc/include/asm/types.h
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file is never included by application software unless
  * explicitly requested (e.g., via linux/types.h) in which case the
  * application is Linux specific so (user-) name space pollution is
  * not a major issue.  However, for interoperability, libraries still
  * need to be careful to avoid a name clashes.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_TYPES_H
 #define _ASM_POWERPC_TYPES_H
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index bac225b..15002b5 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -6,6 +6,7 @@
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/extable.h>
+#include <asm/kup.h>
 
 /*
  * The fs value determines whether argument validity checking should be
@@ -28,7 +29,6 @@
 #define USER_DS		MAKE_MM_SEG(TASK_SIZE - 1)
 #endif
 
-#define get_ds()	(KERNEL_DS)
 #define get_fs()	(current->thread.addr_limit)
 
 static inline void set_fs(mm_segment_t fs)
@@ -62,8 +62,8 @@
 
 #endif
 
-#define access_ok(type, addr, size)		\
-	(__chk_user_ptr(addr),			\
+#define access_ok(addr, size)		\
+	(__chk_user_ptr(addr),		\
 	 __access_ok((__force unsigned long)(addr), (size), get_fs()))
 
 /*
@@ -141,6 +141,7 @@
 #define __put_user_size(x, ptr, size, retval)			\
 do {								\
 	retval = 0;						\
+	allow_write_to_user(ptr, size);				\
 	switch (size) {						\
 	  case 1: __put_user_asm(x, ptr, retval, "stb"); break;	\
 	  case 2: __put_user_asm(x, ptr, retval, "sth"); break;	\
@@ -148,6 +149,7 @@
 	  case 8: __put_user_asm2(x, ptr, retval); break;	\
 	  default: __put_user_bad();				\
 	}							\
+	prevent_write_to_user(ptr, size);			\
 } while (0)
 
 #define __put_user_nocheck(x, ptr, size)			\
@@ -166,7 +168,7 @@
 	long __pu_err = -EFAULT;					\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);			\
 	might_fault();							\
-	if (access_ok(VERIFY_WRITE, __pu_addr, size))			\
+	if (access_ok(__pu_addr, size))			\
 		__put_user_size((x), __pu_addr, (size), __pu_err);	\
 	__pu_err;							\
 })
@@ -240,6 +242,7 @@
 	__chk_user_ptr(ptr);					\
 	if (size > sizeof(x))					\
 		(x) = __get_user_bad();				\
+	allow_read_from_user(ptr, size);			\
 	switch (size) {						\
 	case 1: __get_user_asm(x, ptr, retval, "lbz"); break;	\
 	case 2: __get_user_asm(x, ptr, retval, "lhz"); break;	\
@@ -247,6 +250,7 @@
 	case 8: __get_user_asm2(x, ptr, retval);  break;	\
 	default: (x) = __get_user_bad();			\
 	}							\
+	prevent_read_from_user(ptr, size);			\
 } while (0)
 
 /*
@@ -260,7 +264,7 @@
 ({								\
 	long __gu_err;						\
 	__long_type(*(ptr)) __gu_val;				\
-	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
+	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
 	__chk_user_ptr(ptr);					\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
@@ -274,9 +278,9 @@
 ({									\
 	long __gu_err = -EFAULT;					\
 	__long_type(*(ptr)) __gu_val = 0;				\
-	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
+	__typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
 	might_fault();							\
-	if (access_ok(VERIFY_READ, __gu_addr, (size))) {		\
+	if (access_ok(__gu_addr, (size))) {		\
 		barrier_nospec();					\
 		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
 	}								\
@@ -288,7 +292,7 @@
 ({								\
 	long __gu_err;						\
 	__long_type(*(ptr)) __gu_val;				\
-	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
+	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
 	__chk_user_ptr(ptr);					\
 	barrier_nospec();					\
 	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
@@ -306,15 +310,22 @@
 static inline unsigned long
 raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
-	return __copy_tofrom_user(to, from, n);
+	unsigned long ret;
+
+	barrier_nospec();
+	allow_user_access(to, from, n);
+	ret = __copy_tofrom_user(to, from, n);
+	prevent_user_access(to, from, n);
+	return ret;
 }
 #endif /* __powerpc64__ */
 
 static inline unsigned long raw_copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
+	unsigned long ret;
 	if (__builtin_constant_p(n) && (n <= 8)) {
-		unsigned long ret = 1;
+		ret = 1;
 
 		switch (n) {
 		case 1:
@@ -339,14 +350,18 @@
 	}
 
 	barrier_nospec();
-	return __copy_tofrom_user((__force void __user *)to, from, n);
+	allow_read_from_user(from, n);
+	ret = __copy_tofrom_user((__force void __user *)to, from, n);
+	prevent_read_from_user(from, n);
+	return ret;
 }
 
 static inline unsigned long raw_copy_to_user(void __user *to,
 		const void *from, unsigned long n)
 {
+	unsigned long ret;
 	if (__builtin_constant_p(n) && (n <= 8)) {
-		unsigned long ret = 1;
+		ret = 1;
 
 		switch (n) {
 		case 1:
@@ -366,17 +381,38 @@
 			return 0;
 	}
 
-	return __copy_tofrom_user(to, (__force const void __user *)from, n);
+	allow_write_to_user(to, n);
+	ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
+	prevent_write_to_user(to, n);
+	return ret;
+}
+
+static __always_inline unsigned long __must_check
+copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n)
+{
+	if (likely(check_copy_size(from, n, true))) {
+		if (access_ok(to, n)) {
+			allow_write_to_user(to, n);
+			n = memcpy_mcsafe((void *)to, from, n);
+			prevent_write_to_user(to, n);
+		}
+	}
+
+	return n;
 }
 
 extern unsigned long __clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
 {
+	unsigned long ret = size;
 	might_fault();
-	if (likely(access_ok(VERIFY_WRITE, addr, size)))
-		return __clear_user(addr, size);
-	return size;
+	if (likely(access_ok(addr, size))) {
+		allow_write_to_user(addr, size);
+		ret = __clear_user(addr, size);
+		prevent_write_to_user(addr, size);
+	}
+	return ret;
 }
 
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index 78f2675..0ea9e70 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * (c) 2001, 2006 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_UDBG_H
diff --git a/arch/powerpc/include/asm/uic.h b/arch/powerpc/include/asm/uic.h
index 597edfc..7b7bd15 100644
--- a/arch/powerpc/include/asm/uic.h
+++ b/arch/powerpc/include/asm/uic.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * IBM PPC4xx UIC external definitions and structure.
  *
  * Maintainer: David Gibson <dwg@au1.ibm.com>
  * Copyright 2007 IBM 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;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #ifndef _ASM_POWERPC_UIC_H
 #define _ASM_POWERPC_UIC_H
diff --git a/arch/powerpc/include/asm/ultravisor-api.h b/arch/powerpc/include/asm/ultravisor-api.h
new file mode 100644
index 0000000..4fcda1d
--- /dev/null
+++ b/arch/powerpc/include/asm/ultravisor-api.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ultravisor API.
+ *
+ * Copyright 2019, IBM Corporation.
+ *
+ */
+#ifndef _ASM_POWERPC_ULTRAVISOR_API_H
+#define _ASM_POWERPC_ULTRAVISOR_API_H
+
+#include <asm/hvcall.h>
+
+/* Return codes */
+#define U_BUSY			H_BUSY
+#define U_FUNCTION		H_FUNCTION
+#define U_NOT_AVAILABLE		H_NOT_AVAILABLE
+#define U_P2			H_P2
+#define U_P3			H_P3
+#define U_P4			H_P4
+#define U_P5			H_P5
+#define U_PARAMETER		H_PARAMETER
+#define U_PERMISSION		H_PERMISSION
+#define U_SUCCESS		H_SUCCESS
+
+/* opcodes */
+#define UV_WRITE_PATE			0xF104
+#define UV_RETURN			0xF11C
+#define UV_ESM				0xF110
+#define UV_SHARE_PAGE			0xF130
+#define UV_UNSHARE_PAGE			0xF134
+#define UV_UNSHARE_ALL_PAGES		0xF140
+
+#endif /* _ASM_POWERPC_ULTRAVISOR_API_H */
diff --git a/arch/powerpc/include/asm/ultravisor.h b/arch/powerpc/include/asm/ultravisor.h
new file mode 100644
index 0000000..b1bc2e0
--- /dev/null
+++ b/arch/powerpc/include/asm/ultravisor.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ultravisor definitions
+ *
+ * Copyright 2019, IBM Corporation.
+ *
+ */
+#ifndef _ASM_POWERPC_ULTRAVISOR_H
+#define _ASM_POWERPC_ULTRAVISOR_H
+
+#include <asm/asm-prototypes.h>
+#include <asm/ultravisor-api.h>
+#include <asm/firmware.h>
+
+int early_init_dt_scan_ultravisor(unsigned long node, const char *uname,
+				  int depth, void *data);
+
+/*
+ * In ultravisor enabled systems, PTCR becomes ultravisor privileged only for
+ * writing and an attempt to write to it will cause a Hypervisor Emulation
+ * Assistance interrupt.
+ */
+static inline void set_ptcr_when_no_uv(u64 val)
+{
+	if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
+		mtspr(SPRN_PTCR, val);
+}
+
+static inline int uv_register_pate(u64 lpid, u64 dw0, u64 dw1)
+{
+	return ucall_norets(UV_WRITE_PATE, lpid, dw0, dw1);
+}
+
+static inline int uv_share_page(u64 pfn, u64 npages)
+{
+	return ucall_norets(UV_SHARE_PAGE, pfn, npages);
+}
+
+static inline int uv_unshare_page(u64 pfn, u64 npages)
+{
+	return ucall_norets(UV_UNSHARE_PAGE, pfn, npages);
+}
+
+static inline int uv_unshare_all_pages(void)
+{
+	return ucall_norets(UV_UNSHARE_ALL_PAGES);
+}
+
+#endif	/* _ASM_POWERPC_ULTRAVISOR_H */
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index c19379f..b0720c7 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -1,18 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains the system call numbers.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_UNISTD_H_
 #define _ASM_POWERPC_UNISTD_H_
 
 #include <uapi/asm/unistd.h>
 
-
-#define NR_syscalls		389
+#define NR_syscalls	__NR_syscalls
 
 #define __NR__exit __NR_exit
 
@@ -22,6 +17,7 @@
 #include <linux/compiler.h>
 #include <linux/linkage.h>
 
+#define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_ALARM
@@ -29,13 +25,12 @@
 #define __ARCH_WANT_SYS_IPC
 #define __ARCH_WANT_SYS_PAUSE
 #define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
+#define __ARCH_WANT_SYS_TIME32
+#define __ARCH_WANT_SYS_UTIME32
 #define __ARCH_WANT_SYS_WAITPID
 #define __ARCH_WANT_SYS_SOCKETCALL
 #define __ARCH_WANT_SYS_FADVISE64
 #define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_NICE
 #define __ARCH_WANT_SYS_OLD_GETRLIMIT
 #define __ARCH_WANT_SYS_OLD_UNAME
@@ -46,13 +41,15 @@
 #define __ARCH_WANT_OLD_STAT
 #endif
 #ifdef CONFIG_PPC64
-#define __ARCH_WANT_COMPAT_SYS_TIME
+#define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_SYS_UTIME
 #define __ARCH_WANT_SYS_NEWFSTATAT
 #define __ARCH_WANT_COMPAT_SYS_SENDFILE
 #endif
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
 
 #endif		/* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h
index 7422a99..2bbdf27 100644
--- a/arch/powerpc/include/asm/uprobes.h
+++ b/arch/powerpc/include/asm/uprobes.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _ASM_UPROBES_H
 #define _ASM_UPROBES_H
 /*
  * User-space Probes (UProbes) for powerpc
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright IBM Corporation, 2007-2012
  *
  * Adapted from the x86 port by Ananth N Mavinakayanahalli <ananth@in.ibm.com>
diff --git a/arch/powerpc/include/asm/user.h b/arch/powerpc/include/asm/user.h
index 5c0e082..99443b8 100644
--- a/arch/powerpc/include/asm/user.h
+++ b/arch/powerpc/include/asm/user.h
@@ -31,7 +31,7 @@
  *	to write an integer number of pages.
  */
 struct user {
-	struct pt_regs	regs;			/* entire machine state */
+	struct user_pt_regs regs;		/* entire machine state */
 	size_t		u_tsize;		/* text size (pages) */
 	size_t		u_dsize;		/* data size (pages) */
 	size_t		u_ssize;		/* stack size (pages) */
diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h
index 7714562..f93e6b0 100644
--- a/arch/powerpc/include/asm/vas.h
+++ b/arch/powerpc/include/asm/vas.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2016-17 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_VAS_H
@@ -167,14 +163,4 @@
  */
 int vas_paste_crb(struct vas_window *win, int offset, bool re);
 
-/*
- * Return a system-wide unique id for the VAS window @win.
- */
-extern u32 vas_win_id(struct vas_window *win);
-
-/*
- * Return the power bus paste address associated with @win so the caller
- * can map that address into their address space.
- */
-extern u64 vas_win_paste_addr(struct vas_window *win);
 #endif /* __ASM_POWERPC_VAS_H */
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index 1afe90a..c61d59e 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _VDSO_DATAPAGE_H
 #define _VDSO_DATAPAGE_H
 #ifdef __KERNEL__
@@ -6,11 +7,6 @@
  * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM
  * Copyright (C) 2005 Benjamin Herrenschmidy <benh@kernel.crashing.org>,
  * 		      IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 
@@ -82,10 +78,10 @@
 	__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 */
-	__s32 wtom_clock_sec;			/* Wall to monotonic clock */
-	__s32 wtom_clock_nsec;
-	struct timespec stamp_xtime;	/* xtime as at tb_orig_stamp */
-	__u32 stamp_sec_fraction;	/* fractional seconds of stamp_xtime */
+	__u32 stamp_sec_fraction;		/* fractional seconds of stamp_xtime */
+	__s32 wtom_clock_nsec;			/* Wall to monotonic clock nsec */
+	__s64 wtom_clock_sec;			/* Wall to monotonic clock sec */
+	struct timespec stamp_xtime;		/* xtime as at tb_orig_stamp */
    	__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls  */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 };
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index 84286ec..0cf5274 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * IBM PowerPC Virtual I/O Infrastructure Support.
  *
  * Copyright (c) 2003 IBM Corp.
  *  Dave Engebretsen engebret@us.ibm.com
  *  Santiago Leon santil@us.ibm.com
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _ASM_POWERPC_VIO_H
diff --git a/arch/powerpc/include/asm/xilinx_intc.h b/arch/powerpc/include/asm/xilinx_intc.h
index 3192d7f..ca9aa16 100644
--- a/arch/powerpc/include/asm/xilinx_intc.h
+++ b/arch/powerpc/include/asm/xilinx_intc.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Xilinx intc external definitions
  *
  * Copyright 2007 Secret Lab Technologies Ltd.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #ifndef _ASM_POWERPC_XILINX_INTC_H
 #define _ASM_POWERPC_XILINX_INTC_H
diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h
index 6de989f..f2dfcd5 100644
--- a/arch/powerpc/include/asm/xive-regs.h
+++ b/arch/powerpc/include/asm/xive-regs.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2016,2017 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_XIVE_REGS_H
 #define _ASM_POWERPC_XIVE_REGS_H
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
index 3c704f5..24cdf97 100644
--- a/arch/powerpc/include/asm/xive.h
+++ b/arch/powerpc/include/asm/xive.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2016,2017 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef _ASM_POWERPC_XIVE_H
 #define _ASM_POWERPC_XIVE_H
@@ -23,6 +19,7 @@
  * same offset regardless of where the code is executing
  */
 extern void __iomem *xive_tima;
+extern unsigned long xive_tima_os;
 
 /*
  * Offset in the TM area of our current execution level (provided by
@@ -49,7 +46,15 @@
 
 	/* Setup/used by frontend */
 	int target;
+	/*
+	 * saved_p means that there is a queue entry for this interrupt
+	 * in some CPU's queue (not including guest vcpu queues), even
+	 * if P is not set in the source ESB.
+	 * stale_p means that there is no queue entry for this interrupt
+	 * in some CPU's queue, even if P is set in the source ESB.
+	 */
 	bool saved_p;
+	bool stale_p;
 };
 #define XIVE_IRQ_FLAG_STORE_EOI	0x01
 #define XIVE_IRQ_FLAG_LSI	0x02
@@ -73,6 +78,8 @@
 	u32			esc_irq;
 	atomic_t		count;
 	atomic_t		pending_count;
+	u64			guest_qaddr;
+	u32			guest_qshift;
 };
 
 /* Global enable flags for the XIVE support */
@@ -92,6 +99,7 @@
 
 /* xmon hook */
 extern void xmon_xive_do_dump(int cpu);
+extern int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d);
 
 /* APIs used by KVM */
 extern u32 xive_native_default_eq_shift(void);
@@ -109,12 +117,27 @@
 extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio);
 
 extern void xive_native_sync_source(u32 hw_irq);
+extern void xive_native_sync_queue(u32 hw_irq);
 extern bool is_xive_irq(struct irq_chip *chip);
 extern int xive_native_enable_vp(u32 vp_id, bool single_escalation);
 extern int xive_native_disable_vp(u32 vp_id);
 extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
 extern bool xive_native_has_single_escalation(void);
 
+extern int xive_native_get_queue_info(u32 vp_id, uint32_t prio,
+				      u64 *out_qpage,
+				      u64 *out_qsize,
+				      u64 *out_qeoi_page,
+				      u32 *out_escalate_irq,
+				      u64 *out_qflags);
+
+extern int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle,
+				       u32 *qindex);
+extern int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle,
+				       u32 qindex);
+extern int xive_native_get_vp_state(u32 vp_id, u64 *out_state);
+extern bool xive_native_has_queue_state_support(void);
+
 #else
 
 static inline bool xive_enabled(void) { return false; }
diff --git a/arch/powerpc/include/asm/xmon.h b/arch/powerpc/include/asm/xmon.h
index 30ff69b..454a7fc 100644
--- a/arch/powerpc/include/asm/xmon.h
+++ b/arch/powerpc/include/asm/xmon.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef __ASM_POWERPC_XMON_H
 #define __ASM_POWERPC_XMON_H
 
 /*
  * Copyrignt (C) 2006 IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifdef __KERNEL__
diff --git a/arch/powerpc/include/asm/xor.h b/arch/powerpc/include/asm/xor.h
index 7d6dc50..37d05c1 100644
--- a/arch/powerpc/include/asm/xor.h
+++ b/arch/powerpc/include/asm/xor.h
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index 1a6ed59..353b70b 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -1,9 +1,3 @@
-# UAPI Header export list
-include include/uapi/asm-generic/Kbuild.asm
-
-generic-y += bpf_perf_event.h
-generic-y += param.h
-generic-y += poll.h
-generic-y += resource.h
-generic-y += sockios.h
-generic-y += statfs.h
+# SPDX-License-Identifier: GPL-2.0
+generated-y += unistd_32.h
+generated-y += unistd_64.h
diff --git a/arch/powerpc/include/uapi/asm/bpf_perf_event.h b/arch/powerpc/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 0000000..5e1e648
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h
index 41b1a5c..2c145da 100644
--- a/arch/powerpc/include/uapi/asm/ioctls.h
+++ b/arch/powerpc/include/uapi/asm/ioctls.h
@@ -102,6 +102,8 @@
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 #define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
+#define TIOCGISO7816	_IOR('T', 0x42, struct serial_iso7816)
+#define TIOCSISO7816	_IOWR('T', 0x43, struct serial_iso7816)
 
 #define TIOCSERCONFIG	0x5453
 #define TIOCSERGWILD	0x5454
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 1b32b56..b0f72de 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -463,10 +463,12 @@
 #define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
 #define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
 #define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST	(1ull << 54)
 
 #define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
 #define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
 #define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE	(1ull << 58)
 
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
@@ -480,6 +482,8 @@
 #define  KVM_REG_PPC_ICP_PPRI_SHIFT	16	/* pending irq priority */
 #define  KVM_REG_PPC_ICP_PPRI_MASK	0xff
 
+#define KVM_REG_PPC_VP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x8d)
+
 /* Device control API: PPC-specific devices */
 #define KVM_DEV_MPIC_GRP_MISC		1
 #define   KVM_DEV_MPIC_BASE_ADDR	0	/* 64-bit */
@@ -634,6 +638,7 @@
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
 #define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
+#define KVM_REG_PPC_PTCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
@@ -674,4 +679,48 @@
 #define  KVM_XICS_PRESENTED		(1ULL << 43)
 #define  KVM_XICS_QUEUED		(1ULL << 44)
 
+/* POWER9 XIVE Native Interrupt Controller */
+#define KVM_DEV_XIVE_GRP_CTRL		1
+#define   KVM_DEV_XIVE_RESET		1
+#define   KVM_DEV_XIVE_EQ_SYNC		2
+#define KVM_DEV_XIVE_GRP_SOURCE		2	/* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_CONFIG	3	/* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_EQ_CONFIG	4	/* 64-bit EQ identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_SYNC	5       /* 64-bit source identifier */
+
+/* Layout of 64-bit XIVE source attribute values */
+#define KVM_XIVE_LEVEL_SENSITIVE	(1ULL << 0)
+#define KVM_XIVE_LEVEL_ASSERTED		(1ULL << 1)
+
+/* Layout of 64-bit XIVE source configuration attribute values */
+#define KVM_XIVE_SOURCE_PRIORITY_SHIFT	0
+#define KVM_XIVE_SOURCE_PRIORITY_MASK	0x7
+#define KVM_XIVE_SOURCE_SERVER_SHIFT	3
+#define KVM_XIVE_SOURCE_SERVER_MASK	0xfffffff8ULL
+#define KVM_XIVE_SOURCE_MASKED_SHIFT	32
+#define KVM_XIVE_SOURCE_MASKED_MASK	0x100000000ULL
+#define KVM_XIVE_SOURCE_EISN_SHIFT	33
+#define KVM_XIVE_SOURCE_EISN_MASK	0xfffffffe00000000ULL
+
+/* Layout of 64-bit EQ identifier */
+#define KVM_XIVE_EQ_PRIORITY_SHIFT	0
+#define KVM_XIVE_EQ_PRIORITY_MASK	0x7
+#define KVM_XIVE_EQ_SERVER_SHIFT	3
+#define KVM_XIVE_EQ_SERVER_MASK		0xfffffff8ULL
+
+/* Layout of EQ configuration values (64 bytes) */
+struct kvm_ppc_xive_eq {
+	__u32 flags;
+	__u32 qshift;
+	__u64 qaddr;
+	__u32 qtoggle;
+	__u32 qindex;
+	__u8  pad[40];
+};
+
+#define KVM_XIVE_EQ_ALWAYS_NOTIFY	0x00000001
+
+#define KVM_XIVE_TIMA_PAGE_OFFSET	0
+#define KVM_XIVE_ESB_PAGE_OFFSET	4
+
 #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 01555c6..be48c22 100644
--- a/arch/powerpc/include/uapi/asm/kvm_para.h
+++ b/arch/powerpc/include/uapi/asm/kvm_para.h
@@ -31,7 +31,7 @@
  * Struct fields are always 32 or 64 bit aligned, depending on them being 32
  * or 64 bit wide respectively.
  *
- * See Documentation/virtual/kvm/ppc-pv.txt
+ * See Documentation/virt/kvm/ppc-pv.txt
  */
 struct kvm_vcpu_arch_shared {
 	__u64 scratch1;
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index 65065ce..c0c7372 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -21,15 +21,11 @@
 #define MAP_DENYWRITE	0x0800		/* ETXTBSY */
 #define MAP_EXECUTABLE	0x1000		/* mark it as an executable */
 
+
 #define MCL_CURRENT     0x2000          /* lock all currently mapped pages */
 #define MCL_FUTURE      0x4000          /* lock all additions to address space */
 #define MCL_ONFAULT	0x8000		/* lock all pages that are faulted in */
 
-#define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
-#define MAP_NONBLOCK	0x10000		/* do not block on IO */
-#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
-#define MAP_HUGETLB	0x40000		/* create a huge page mapping */
-
 /* Override any generic PKEY permission defines */
 #define PKEY_DISABLE_EXECUTE   0x4
 #undef PKEY_ACCESS_MASK
diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h
index 9e52c86..f599064 100644
--- a/arch/powerpc/include/uapi/asm/perf_regs.h
+++ b/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -46,6 +46,8 @@
 	PERF_REG_POWERPC_TRAP,
 	PERF_REG_POWERPC_DAR,
 	PERF_REG_POWERPC_DSISR,
+	PERF_REG_POWERPC_SIER,
+	PERF_REG_POWERPC_MMCRA,
 	PERF_REG_POWERPC_MAX,
 };
 #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h
index 5e3edc2..f5f1ccc 100644
--- a/arch/powerpc/include/uapi/asm/ptrace.h
+++ b/arch/powerpc/include/uapi/asm/ptrace.h
@@ -29,7 +29,12 @@
 
 #ifndef __ASSEMBLY__
 
-struct pt_regs {
+#ifdef __KERNEL__
+struct user_pt_regs
+#else
+struct pt_regs
+#endif
+{
 	unsigned long gpr[32];
 	unsigned long nip;
 	unsigned long msr;
@@ -160,6 +165,10 @@
 #define PTRACE_GETVSRREGS	0x1b
 #define PTRACE_SETVSRREGS	0x1c
 
+/* Syscall emulation defines */
+#define PTRACE_SYSEMU			0x1d
+#define PTRACE_SYSEMU_SINGLESTEP	0x1e
+
 /*
  * Get or set a debug register. The first 16 are DABR registers and the
  * second 16 are IABR registers.
diff --git a/arch/powerpc/include/uapi/asm/sigcontext.h b/arch/powerpc/include/uapi/asm/sigcontext.h
index 2fbe485..630aeda 100644
--- a/arch/powerpc/include/uapi/asm/sigcontext.h
+++ b/arch/powerpc/include/uapi/asm/sigcontext.h
@@ -22,7 +22,11 @@
 #endif
 	unsigned long	handler;
 	unsigned long	oldmask;
-	struct pt_regs	__user *regs;
+#ifdef __KERNEL__
+	struct user_pt_regs __user *regs;
+#else
+	struct pt_regs	*regs;
+#endif
 #ifdef __powerpc64__
 	elf_gregset_t	gp_regs;
 	elf_fpregset_t	fp_regs;
diff --git a/arch/powerpc/include/uapi/asm/siginfo.h b/arch/powerpc/include/uapi/asm/siginfo.h
deleted file mode 100644
index 1d51d9b..0000000
--- a/arch/powerpc/include/uapi/asm/siginfo.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-#ifndef _ASM_POWERPC_SIGINFO_H
-#define _ASM_POWERPC_SIGINFO_H
-
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifdef __powerpc64__
-#    define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
-#endif
-
-#include <asm-generic/siginfo.h>
-
-#endif	/* _ASM_POWERPC_SIGINFO_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 94de465..12aa0c4 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -11,8 +11,8 @@
 
 #define SO_RCVLOWAT	16
 #define SO_SNDLOWAT	17
-#define SO_RCVTIMEO	18
-#define SO_SNDTIMEO	19
+#define SO_RCVTIMEO_OLD	18
+#define SO_SNDTIMEO_OLD	19
 #define SO_PASSCRED	20
 #define SO_PEERCRED	21
 
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 985534d..5f84e3d 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -10,395 +10,10 @@
 #ifndef _UAPI_ASM_POWERPC_UNISTD_H_
 #define _UAPI_ASM_POWERPC_UNISTD_H_
 
-
-#define __NR_restart_syscall	  0
-#define __NR_exit		  1
-#define __NR_fork		  2
-#define __NR_read		  3
-#define __NR_write		  4
-#define __NR_open		  5
-#define __NR_close		  6
-#define __NR_waitpid		  7
-#define __NR_creat		  8
-#define __NR_link		  9
-#define __NR_unlink		 10
-#define __NR_execve		 11
-#define __NR_chdir		 12
-#define __NR_time		 13
-#define __NR_mknod		 14
-#define __NR_chmod		 15
-#define __NR_lchown		 16
-#define __NR_break		 17
-#define __NR_oldstat		 18
-#define __NR_lseek		 19
-#define __NR_getpid		 20
-#define __NR_mount		 21
-#define __NR_umount		 22
-#define __NR_setuid		 23
-#define __NR_getuid		 24
-#define __NR_stime		 25
-#define __NR_ptrace		 26
-#define __NR_alarm		 27
-#define __NR_oldfstat		 28
-#define __NR_pause		 29
-#define __NR_utime		 30
-#define __NR_stty		 31
-#define __NR_gtty		 32
-#define __NR_access		 33
-#define __NR_nice		 34
-#define __NR_ftime		 35
-#define __NR_sync		 36
-#define __NR_kill		 37
-#define __NR_rename		 38
-#define __NR_mkdir		 39
-#define __NR_rmdir		 40
-#define __NR_dup		 41
-#define __NR_pipe		 42
-#define __NR_times		 43
-#define __NR_prof		 44
-#define __NR_brk		 45
-#define __NR_setgid		 46
-#define __NR_getgid		 47
-#define __NR_signal		 48
-#define __NR_geteuid		 49
-#define __NR_getegid		 50
-#define __NR_acct		 51
-#define __NR_umount2		 52
-#define __NR_lock		 53
-#define __NR_ioctl		 54
-#define __NR_fcntl		 55
-#define __NR_mpx		 56
-#define __NR_setpgid		 57
-#define __NR_ulimit		 58
-#define __NR_oldolduname	 59
-#define __NR_umask		 60
-#define __NR_chroot		 61
-#define __NR_ustat		 62
-#define __NR_dup2		 63
-#define __NR_getppid		 64
-#define __NR_getpgrp		 65
-#define __NR_setsid		 66
-#define __NR_sigaction		 67
-#define __NR_sgetmask		 68
-#define __NR_ssetmask		 69
-#define __NR_setreuid		 70
-#define __NR_setregid		 71
-#define __NR_sigsuspend		 72
-#define __NR_sigpending		 73
-#define __NR_sethostname	 74
-#define __NR_setrlimit		 75
-#define __NR_getrlimit		 76
-#define __NR_getrusage		 77
-#define __NR_gettimeofday	 78
-#define __NR_settimeofday	 79
-#define __NR_getgroups		 80
-#define __NR_setgroups		 81
-#define __NR_select		 82
-#define __NR_symlink		 83
-#define __NR_oldlstat		 84
-#define __NR_readlink		 85
-#define __NR_uselib		 86
-#define __NR_swapon		 87
-#define __NR_reboot		 88
-#define __NR_readdir		 89
-#define __NR_mmap		 90
-#define __NR_munmap		 91
-#define __NR_truncate		 92
-#define __NR_ftruncate		 93
-#define __NR_fchmod		 94
-#define __NR_fchown		 95
-#define __NR_getpriority	 96
-#define __NR_setpriority	 97
-#define __NR_profil		 98
-#define __NR_statfs		 99
-#define __NR_fstatfs		100
-#define __NR_ioperm		101
-#define __NR_socketcall		102
-#define __NR_syslog		103
-#define __NR_setitimer		104
-#define __NR_getitimer		105
-#define __NR_stat		106
-#define __NR_lstat		107
-#define __NR_fstat		108
-#define __NR_olduname		109
-#define __NR_iopl		110
-#define __NR_vhangup		111
-#define __NR_idle		112
-#define __NR_vm86		113
-#define __NR_wait4		114
-#define __NR_swapoff		115
-#define __NR_sysinfo		116
-#define __NR_ipc		117
-#define __NR_fsync		118
-#define __NR_sigreturn		119
-#define __NR_clone		120
-#define __NR_setdomainname	121
-#define __NR_uname		122
-#define __NR_modify_ldt		123
-#define __NR_adjtimex		124
-#define __NR_mprotect		125
-#define __NR_sigprocmask	126
-#define __NR_create_module	127
-#define __NR_init_module	128
-#define __NR_delete_module	129
-#define __NR_get_kernel_syms	130
-#define __NR_quotactl		131
-#define __NR_getpgid		132
-#define __NR_fchdir		133
-#define __NR_bdflush		134
-#define __NR_sysfs		135
-#define __NR_personality	136
-#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
-#define __NR_setfsuid		138
-#define __NR_setfsgid		139
-#define __NR__llseek		140
-#define __NR_getdents		141
-#define __NR__newselect		142
-#define __NR_flock		143
-#define __NR_msync		144
-#define __NR_readv		145
-#define __NR_writev		146
-#define __NR_getsid		147
-#define __NR_fdatasync		148
-#define __NR__sysctl		149
-#define __NR_mlock		150
-#define __NR_munlock		151
-#define __NR_mlockall		152
-#define __NR_munlockall		153
-#define __NR_sched_setparam		154
-#define __NR_sched_getparam		155
-#define __NR_sched_setscheduler		156
-#define __NR_sched_getscheduler		157
-#define __NR_sched_yield		158
-#define __NR_sched_get_priority_max	159
-#define __NR_sched_get_priority_min	160
-#define __NR_sched_rr_get_interval	161
-#define __NR_nanosleep		162
-#define __NR_mremap		163
-#define __NR_setresuid		164
-#define __NR_getresuid		165
-#define __NR_query_module	166
-#define __NR_poll		167
-#define __NR_nfsservctl		168
-#define __NR_setresgid		169
-#define __NR_getresgid		170
-#define __NR_prctl		171
-#define __NR_rt_sigreturn	172
-#define __NR_rt_sigaction	173
-#define __NR_rt_sigprocmask	174
-#define __NR_rt_sigpending	175
-#define __NR_rt_sigtimedwait	176
-#define __NR_rt_sigqueueinfo	177
-#define __NR_rt_sigsuspend	178
-#define __NR_pread64		179
-#define __NR_pwrite64		180
-#define __NR_chown		181
-#define __NR_getcwd		182
-#define __NR_capget		183
-#define __NR_capset		184
-#define __NR_sigaltstack	185
-#define __NR_sendfile		186
-#define __NR_getpmsg		187	/* some people actually want streams */
-#define __NR_putpmsg		188	/* some people actually want streams */
-#define __NR_vfork		189
-#define __NR_ugetrlimit		190	/* SuS compliant getrlimit */
-#define __NR_readahead		191
-#ifndef __powerpc64__			/* these are 32-bit only */
-#define __NR_mmap2		192
-#define __NR_truncate64		193
-#define __NR_ftruncate64	194
-#define __NR_stat64		195
-#define __NR_lstat64		196
-#define __NR_fstat64		197
-#endif
-#define __NR_pciconfig_read	198
-#define __NR_pciconfig_write	199
-#define __NR_pciconfig_iobase	200
-#define __NR_multiplexer	201
-#define __NR_getdents64		202
-#define __NR_pivot_root		203
 #ifndef __powerpc64__
-#define __NR_fcntl64		204
-#endif
-#define __NR_madvise		205
-#define __NR_mincore		206
-#define __NR_gettid		207
-#define __NR_tkill		208
-#define __NR_setxattr		209
-#define __NR_lsetxattr		210
-#define __NR_fsetxattr		211
-#define __NR_getxattr		212
-#define __NR_lgetxattr		213
-#define __NR_fgetxattr		214
-#define __NR_listxattr		215
-#define __NR_llistxattr		216
-#define __NR_flistxattr		217
-#define __NR_removexattr	218
-#define __NR_lremovexattr	219
-#define __NR_fremovexattr	220
-#define __NR_futex		221
-#define __NR_sched_setaffinity	222
-#define __NR_sched_getaffinity	223
-/* 224 currently unused */
-#define __NR_tuxcall		225
-#ifndef __powerpc64__
-#define __NR_sendfile64		226
-#endif
-#define __NR_io_setup		227
-#define __NR_io_destroy		228
-#define __NR_io_getevents	229
-#define __NR_io_submit		230
-#define __NR_io_cancel		231
-#define __NR_set_tid_address	232
-#define __NR_fadvise64		233
-#define __NR_exit_group		234
-#define __NR_lookup_dcookie	235
-#define __NR_epoll_create	236
-#define __NR_epoll_ctl		237
-#define __NR_epoll_wait		238
-#define __NR_remap_file_pages	239
-#define __NR_timer_create	240
-#define __NR_timer_settime	241
-#define __NR_timer_gettime	242
-#define __NR_timer_getoverrun	243
-#define __NR_timer_delete	244
-#define __NR_clock_settime	245
-#define __NR_clock_gettime	246
-#define __NR_clock_getres	247
-#define __NR_clock_nanosleep	248
-#define __NR_swapcontext	249
-#define __NR_tgkill		250
-#define __NR_utimes		251
-#define __NR_statfs64		252
-#define __NR_fstatfs64		253
-#ifndef __powerpc64__
-#define __NR_fadvise64_64	254
-#endif
-#define __NR_rtas		255
-#define __NR_sys_debug_setcontext 256
-/* Number 257 is reserved for vserver */
-#define __NR_migrate_pages	258
-#define __NR_mbind		259
-#define __NR_get_mempolicy	260
-#define __NR_set_mempolicy	261
-#define __NR_mq_open		262
-#define __NR_mq_unlink		263
-#define __NR_mq_timedsend	264
-#define __NR_mq_timedreceive	265
-#define __NR_mq_notify		266
-#define __NR_mq_getsetattr	267
-#define __NR_kexec_load		268
-#define __NR_add_key		269
-#define __NR_request_key	270
-#define __NR_keyctl		271
-#define __NR_waitid		272
-#define __NR_ioprio_set		273
-#define __NR_ioprio_get		274
-#define __NR_inotify_init	275
-#define __NR_inotify_add_watch	276
-#define __NR_inotify_rm_watch	277
-#define __NR_spu_run		278
-#define __NR_spu_create		279
-#define __NR_pselect6		280
-#define __NR_ppoll		281
-#define __NR_unshare		282
-#define __NR_splice		283
-#define __NR_tee		284
-#define __NR_vmsplice		285
-#define __NR_openat		286
-#define __NR_mkdirat		287
-#define __NR_mknodat		288
-#define __NR_fchownat		289
-#define __NR_futimesat		290
-#ifdef __powerpc64__
-#define __NR_newfstatat		291
+#include <asm/unistd_32.h>
 #else
-#define __NR_fstatat64		291
+#include <asm/unistd_64.h>
 #endif
-#define __NR_unlinkat		292
-#define __NR_renameat		293
-#define __NR_linkat		294
-#define __NR_symlinkat		295
-#define __NR_readlinkat		296
-#define __NR_fchmodat		297
-#define __NR_faccessat		298
-#define __NR_get_robust_list	299
-#define __NR_set_robust_list	300
-#define __NR_move_pages		301
-#define __NR_getcpu		302
-#define __NR_epoll_pwait	303
-#define __NR_utimensat		304
-#define __NR_signalfd		305
-#define __NR_timerfd_create	306
-#define __NR_eventfd		307
-#define __NR_sync_file_range2	308
-#define __NR_fallocate		309
-#define __NR_subpage_prot	310
-#define __NR_timerfd_settime	311
-#define __NR_timerfd_gettime	312
-#define __NR_signalfd4		313
-#define __NR_eventfd2		314
-#define __NR_epoll_create1	315
-#define __NR_dup3		316
-#define __NR_pipe2		317
-#define __NR_inotify_init1	318
-#define __NR_perf_event_open	319
-#define __NR_preadv		320
-#define __NR_pwritev		321
-#define __NR_rt_tgsigqueueinfo	322
-#define __NR_fanotify_init	323
-#define __NR_fanotify_mark	324
-#define __NR_prlimit64		325
-#define __NR_socket		326
-#define __NR_bind		327
-#define __NR_connect		328
-#define __NR_listen		329
-#define __NR_accept		330
-#define __NR_getsockname	331
-#define __NR_getpeername	332
-#define __NR_socketpair		333
-#define __NR_send		334
-#define __NR_sendto		335
-#define __NR_recv		336
-#define __NR_recvfrom		337
-#define __NR_shutdown		338
-#define __NR_setsockopt		339
-#define __NR_getsockopt		340
-#define __NR_sendmsg		341
-#define __NR_recvmsg		342
-#define __NR_recvmmsg		343
-#define __NR_accept4		344
-#define __NR_name_to_handle_at	345
-#define __NR_open_by_handle_at	346
-#define __NR_clock_adjtime	347
-#define __NR_syncfs		348
-#define __NR_sendmmsg		349
-#define __NR_setns		350
-#define __NR_process_vm_readv	351
-#define __NR_process_vm_writev	352
-#define __NR_finit_module	353
-#define __NR_kcmp		354
-#define __NR_sched_setattr	355
-#define __NR_sched_getattr	356
-#define __NR_renameat2		357
-#define __NR_seccomp		358
-#define __NR_getrandom		359
-#define __NR_memfd_create	360
-#define __NR_bpf		361
-#define __NR_execveat		362
-#define __NR_switch_endian	363
-#define __NR_userfaultfd	364
-#define __NR_membarrier		365
-#define __NR_mlock2		378
-#define __NR_copy_file_range	379
-#define __NR_preadv2		380
-#define __NR_pwritev2		381
-#define __NR_kexec_file_load	382
-#define __NR_statx		383
-#define __NR_pkey_alloc		384
-#define __NR_pkey_free		385
-#define __NR_pkey_mprotect	386
-#define __NR_rseq		387
-#define __NR_io_pgetevents	388
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/.gitignore b/arch/powerpc/kernel/.gitignore
index c5f676c..67ebd30 100644
--- a/arch/powerpc/kernel/.gitignore
+++ b/arch/powerpc/kernel/.gitignore
@@ -1 +1,2 @@
+prom_init_check
 vmlinux.lds
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 3b66f2c..a7ca8fe 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -5,7 +5,8 @@
 
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+# Disable clang warning for using setjmp without setjmp.h header
+CFLAGS_crash.o		+= $(call cc-disable-warning, builtin-requires-header)
 
 ifdef CONFIG_PPC64
 CFLAGS_prom_init.o	+= $(NO_MINIMAL_TOC)
@@ -20,12 +21,26 @@
 CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 
+CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector)
+
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
-CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_prom_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_btext.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_prom.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_cputable.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_prom_init.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_btext.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_prom.o = $(CC_FLAGS_FTRACE)
+endif
+
+KASAN_SANITIZE_early_32.o := n
+KASAN_SANITIZE_cputable.o := n
+KASAN_SANITIZE_prom_init.o := n
+KASAN_SANITIZE_btext.o := n
+
+ifdef CONFIG_KASAN
+CFLAGS_early_32.o += -DDISABLE_BRANCH_PROFILING
+CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING
+CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING
+CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
 endif
 
 obj-y				:= cputable.o ptrace.o syscalls.o \
@@ -33,14 +48,15 @@
 				   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 dma.o misc_$(BITS).o \
+				   udbg.o misc.o io.o misc_$(BITS).o \
 				   of_platform.o prom_parse.o
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
-				   paca.o nvram_64.o firmware.o
+				   paca.o nvram_64.o firmware.o note.o
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
 obj-$(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)	+= mce.o mce_power.o
@@ -62,11 +78,13 @@
 				  eeh_driver.o eeh_event.o eeh_sysfs.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
-obj-$(CONFIG_FA_DUMP)		+= fadump.o
+ifneq ($(CONFIG_FA_DUMP)$(CONFIG_PRESERVE_FA_DUMP),)
+obj-y				+= fadump.o
+endif
 ifdef CONFIG_PPC32
 obj-$(CONFIG_E500)		+= idle_e500.o
 endif
-obj-$(CONFIG_6xx)		+= idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o
+obj-$(CONFIG_PPC_BOOK3S_32)	+= idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o
 obj-$(CONFIG_TAU)		+= tau_6xx.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o suspend.o
 ifdef CONFIG_FSL_BOOKE
@@ -90,7 +108,7 @@
 
 obj-$(CONFIG_RELOCATABLE)	+= reloc_$(BITS).o
 
-obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o
+obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o early_32.o
 obj-$(CONFIG_PPC64)		+= dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_BOOTX_TEXT)	+= btext.o
@@ -102,6 +120,7 @@
 obj-$(CONFIG_PPC_UDBG_16550)	+= legacy_serial.o udbg_16550.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
+obj-$(CONFIG_ARCH_HAS_DMA_SET_MASK) += dma-mask.o
 
 pci64-$(CONFIG_PPC64)		+= pci_dn.o pci-hotplug.o isa-bridge.o
 obj-$(CONFIG_PCI)		+= pci_$(BITS).o $(pci64-y) \
@@ -138,44 +157,45 @@
 
 obj-$(CONFIG_EPAPR_PARAVIRT)	+= epapr_paravirt.o epapr_hcalls.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvm_emul.o
+ifneq ($(CONFIG_PPC_POWERNV)$(CONFIG_PPC_SVM),)
+obj-y				+= ucall.o
+endif
 
-# Disable GCOV & sanitizers in odd or sensitive code
+# Disable GCOV, KCOV & sanitizers in odd or sensitive code
 GCOV_PROFILE_prom_init.o := n
+KCOV_INSTRUMENT_prom_init.o := n
 UBSAN_SANITIZE_prom_init.o := n
 GCOV_PROFILE_machine_kexec_64.o := n
+KCOV_INSTRUMENT_machine_kexec_64.o := n
 UBSAN_SANITIZE_machine_kexec_64.o := n
 GCOV_PROFILE_machine_kexec_32.o := n
+KCOV_INSTRUMENT_machine_kexec_32.o := n
 UBSAN_SANITIZE_machine_kexec_32.o := n
 GCOV_PROFILE_kprobes.o := n
+KCOV_INSTRUMENT_kprobes.o := n
 UBSAN_SANITIZE_kprobes.o := n
 GCOV_PROFILE_kprobes-ftrace.o := n
+KCOV_INSTRUMENT_kprobes-ftrace.o := n
 UBSAN_SANITIZE_kprobes-ftrace.o := n
 UBSAN_SANITIZE_vdso.o := n
 
+# Necessary for booting with kcov enabled on book3e machines
+KCOV_INSTRUMENT_cputable.o := n
+KCOV_INSTRUMENT_setup_64.o := n
+KCOV_INSTRUMENT_paca.o := n
+
 extra-$(CONFIG_PPC_FPU)		+= fpu.o
 extra-$(CONFIG_ALTIVEC)		+= vector.o
 extra-$(CONFIG_PPC64)		+= entry_64.o
 extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE)	+= prom_init.o
 
-extra-y				+= systbl_chk.i
-$(obj)/systbl.o:		systbl_chk
+extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE)	+= prom_init_check
 
-quiet_cmd_systbl_chk = CALL    $<
-      cmd_systbl_chk = $(CONFIG_SHELL) $< $(obj)/systbl_chk.i
+quiet_cmd_prom_init_check = PROMCHK $@
+      cmd_prom_init_check = $(CONFIG_SHELL) $< "$(NM)" $(obj)/prom_init.o; touch $@
 
-PHONY += systbl_chk
-systbl_chk: $(src)/systbl_chk.sh $(obj)/systbl_chk.i
-	$(call cmd,systbl_chk)
-
-ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
-$(obj)/built-in.a:		prom_init_check
-
-quiet_cmd_prom_init_check = CALL    $<
-      cmd_prom_init_check = $(CONFIG_SHELL) $< "$(NM)" "$(obj)/prom_init.o"
-
-PHONY += prom_init_check
-prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o
-	$(call cmd,prom_init_check)
-endif
+$(obj)/prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o FORCE
+	$(call if_changed,prom_init_check)
+targets += prom_init_check
 
 clean-files := vmlinux.lds
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 11550a3..92045ed 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* align.c - handle alignment exceptions for the Power PC.
  *
  * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
@@ -10,11 +11,6 @@
  * Copyright (c) 2005 Benjamin Herrenschmidt, IBM Corp
  *                    <benh@kernel.crashing.org>
  *   Merge ppc32 and ppc64 implementations
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -131,8 +127,7 @@
 
 	/* Verify the address of the operand */
 	if (unlikely(user_mode(regs) &&
-		     !access_ok((flags & ST ? VERIFY_WRITE : VERIFY_READ),
-				addr, nb)))
+		     !access_ok(addr, nb)))
 		return -EFAULT;
 
 	/* userland only */
@@ -181,9 +176,11 @@
 			ret |= __get_user_inatomic(temp.v[1], p++);
 			ret |= __get_user_inatomic(temp.v[2], p++);
 			ret |= __get_user_inatomic(temp.v[3], p++);
+			/* fall through */
 		case 4:
 			ret |= __get_user_inatomic(temp.v[4], p++);
 			ret |= __get_user_inatomic(temp.v[5], p++);
+			/* fall through */
 		case 2:
 			ret |= __get_user_inatomic(temp.v[6], p++);
 			ret |= __get_user_inatomic(temp.v[7], p++);
@@ -264,9 +261,11 @@
 			ret |= __put_user_inatomic(data.v[1], p++);
 			ret |= __put_user_inatomic(data.v[2], p++);
 			ret |= __put_user_inatomic(data.v[3], p++);
+			/* fall through */
 		case 4:
 			ret |= __put_user_inatomic(data.v[4], p++);
 			ret |= __put_user_inatomic(data.v[5], p++);
+			/* fall through */
 		case 2:
 			ret |= __put_user_inatomic(data.v[6], p++);
 			ret |= __put_user_inatomic(data.v[7], p++);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 89cf155..484f54d 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This program is used to generate definitions needed by
  * assembly language modules.
@@ -6,13 +7,10 @@
  * generate asm statements containing #defines,
  * compile this file to assembler, and then extract the
  * #defines from the assembly-language output.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
+#define GENERATING_ASM_OFFSETS	/* asm/smp.h */
+
 #include <linux/compat.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
@@ -79,16 +77,26 @@
 {
 	OFFSET(THREAD, task_struct, thread);
 	OFFSET(MM, task_struct, mm);
+#ifdef CONFIG_STACKPROTECTOR
+	OFFSET(TASK_CANARY, task_struct, stack_canary);
+#ifdef CONFIG_PPC64
+	OFFSET(PACA_CANARY, paca_struct, canary);
+#endif
+#endif
 	OFFSET(MMCONTEXTID, mm_struct, context.id);
 #ifdef CONFIG_PPC64
 	DEFINE(SIGSEGV, SIGSEGV);
 	DEFINE(NMI_MASK, NMI_MASK);
-	OFFSET(TASKTHREADPPR, task_struct, thread.ppr);
 #else
-	OFFSET(THREAD_INFO, task_struct, stack);
-	DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
 	OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
+#ifdef CONFIG_PPC_RTAS
+	OFFSET(RTAS_SP, thread_struct, rtas_sp);
+#endif
 #endif /* CONFIG_PPC64 */
+	OFFSET(TASK_STACK, task_struct, stack);
+#ifdef CONFIG_SMP
+	OFFSET(TASK_CPU, task_struct, cpu);
+#endif
 
 #ifdef CONFIG_LIVEPATCH
 	OFFSET(TI_livepatch_sp, thread_info, livepatch_sp);
@@ -135,6 +143,9 @@
 #if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
 	OFFSET(THREAD_KVM_VCPU, thread_struct, kvm_vcpu);
 #endif
+#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
+	OFFSET(KUAP, thread_struct, kuap);
+#endif
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	OFFSET(PACATMSCRATCH, paca_struct, tm_scratch);
@@ -156,8 +167,6 @@
 	OFFSET(TI_FLAGS, thread_info, flags);
 	OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
 	OFFSET(TI_PREEMPT, thread_info, preempt_count);
-	OFFSET(TI_TASK, thread_info, task);
-	OFFSET(TI_CPU, thread_info, cpu);
 
 #ifdef CONFIG_PPC64
 	OFFSET(DCACHEL1BLOCKSIZE, ppc64_caches, l1d.block_size);
@@ -172,8 +181,9 @@
 	OFFSET(PACAPROCSTART, paca_struct, cpu_start);
 	OFFSET(PACAKSAVE, paca_struct, kstack);
 	OFFSET(PACACURRENT, paca_struct, __current);
+	DEFINE(PACA_THREAD_INFO, offsetof(struct paca_struct, __current) +
+				 offsetof(struct task_struct, thread_info));
 	OFFSET(PACASAVEDMSR, paca_struct, saved_msr);
-	OFFSET(PACASTABRR, paca_struct, stab_rr);
 	OFFSET(PACAR1, paca_struct, saved_r1);
 	OFFSET(PACATOC, paca_struct, kernel_toc);
 	OFFSET(PACAKBASE, paca_struct, kernelbase);
@@ -212,6 +222,7 @@
 #ifdef CONFIG_PPC_BOOK3S_64
 	OFFSET(PACASLBCACHE, paca_struct, slb_cache);
 	OFFSET(PACASLBCACHEPTR, paca_struct, slb_cache_ptr);
+	OFFSET(PACASTABRR, paca_struct, stab_rr);
 	OFFSET(PACAVMALLOCSLLP, paca_struct, vmalloc_sllp);
 #ifdef CONFIG_PPC_MM_SLICES
 	OFFSET(MMUPSIZESLLP, mmu_psize_def, sllp);
@@ -255,8 +266,9 @@
 	OFFSET(ACCOUNT_STARTTIME_USER, paca_struct, accounting.starttime_user);
 	OFFSET(ACCOUNT_USER_TIME, paca_struct, accounting.utime);
 	OFFSET(ACCOUNT_SYSTEM_TIME, paca_struct, accounting.stime);
+#ifdef CONFIG_PPC_BOOK3E
 	OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save);
-	OFFSET(PACA_NAPSTATELOST, paca_struct, nap_state_lost);
+#endif
 	OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso);
 #else /* CONFIG_PPC64 */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
@@ -274,11 +286,6 @@
 	/* Interrupt register frame */
 	DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE);
 	DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
-#ifdef CONFIG_PPC64
-	/* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */
-	DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
-	DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
-#endif /* CONFIG_PPC64 */
 	STACK_PT_REGS_OFFSET(GPR0, gpr[0]);
 	STACK_PT_REGS_OFFSET(GPR1, gpr[1]);
 	STACK_PT_REGS_OFFSET(GPR2, gpr[2]);
@@ -322,12 +329,13 @@
 	STACK_PT_REGS_OFFSET(_ESR, dsisr);
 #else /* CONFIG_PPC64 */
 	STACK_PT_REGS_OFFSET(SOFTE, softe);
-
-	/* These _only_ to be used with {PROM,RTAS}_FRAME_SIZE!!! */
-	DEFINE(_SRR0, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs));
-	DEFINE(_SRR1, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs)+8);
+	STACK_PT_REGS_OFFSET(_PPR, ppr);
 #endif /* CONFIG_PPC64 */
 
+#ifdef CONFIG_PPC_KUAP
+	STACK_PT_REGS_OFFSET(STACK_REGS_KUAP, kuap);
+#endif
+
 #if defined(CONFIG_PPC32)
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
 	DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE);
@@ -387,12 +395,12 @@
 	OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64);
 	OFFSET(TVAL64_TV_SEC, timeval, tv_sec);
 	OFFSET(TVAL64_TV_USEC, timeval, tv_usec);
-	OFFSET(TVAL32_TV_SEC, compat_timeval, tv_sec);
-	OFFSET(TVAL32_TV_USEC, compat_timeval, tv_usec);
+	OFFSET(TVAL32_TV_SEC, old_timeval32, tv_sec);
+	OFFSET(TVAL32_TV_USEC, old_timeval32, tv_usec);
 	OFFSET(TSPC64_TV_SEC, timespec, tv_sec);
 	OFFSET(TSPC64_TV_NSEC, timespec, tv_nsec);
-	OFFSET(TSPC32_TV_SEC, compat_timespec, tv_sec);
-	OFFSET(TSPC32_TV_NSEC, compat_timespec, tv_nsec);
+	OFFSET(TSPC32_TV_SEC, old_timespec32, tv_sec);
+	OFFSET(TSPC32_TV_NSEC, old_timespec32, tv_nsec);
 #else
 	OFFSET(TVAL32_TV_SEC, timeval, tv_sec);
 	OFFSET(TVAL32_TV_USEC, timeval, tv_usec);
@@ -438,7 +446,7 @@
 #ifdef CONFIG_PPC_BOOK3S
 	OFFSET(VCPU_TAR, kvm_vcpu, arch.tar);
 #endif
-	OFFSET(VCPU_CR, kvm_vcpu, arch.cr);
+	OFFSET(VCPU_CR, kvm_vcpu, arch.regs.ccr);
 	OFFSET(VCPU_PC, kvm_vcpu, arch.regs.nip);
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	OFFSET(VCPU_MSR, kvm_vcpu, arch.shregs.msr);
@@ -498,11 +506,13 @@
 	OFFSET(KVM_VRMA_SLB_V, kvm, arch.vrma_slb_v);
 	OFFSET(KVM_RADIX, kvm, arch.radix);
 	OFFSET(KVM_FWNMI, kvm, arch.fwnmi_enabled);
+	OFFSET(KVM_SECURE_GUEST, kvm, arch.secure_guest);
 	OFFSET(VCPU_DSISR, kvm_vcpu, arch.shregs.dsisr);
 	OFFSET(VCPU_DAR, kvm_vcpu, arch.shregs.dar);
 	OFFSET(VCPU_VPA, kvm_vcpu, arch.vpa.pinned_addr);
 	OFFSET(VCPU_VPA_DIRTY, kvm_vcpu, arch.vpa.dirty);
 	OFFSET(VCPU_HEIR, kvm_vcpu, arch.emul_inst);
+	OFFSET(VCPU_NESTED, kvm_vcpu, arch.nested);
 	OFFSET(VCPU_CPU, kvm_vcpu, cpu);
 	OFFSET(VCPU_THREAD_CPU, kvm_vcpu, arch.thread_cpu);
 #endif
@@ -695,7 +705,7 @@
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 #else /* CONFIG_PPC_BOOK3S */
-	OFFSET(VCPU_CR, kvm_vcpu, arch.cr);
+	OFFSET(VCPU_CR, kvm_vcpu, arch.regs.ccr);
 	OFFSET(VCPU_XER, kvm_vcpu, arch.regs.xer);
 	OFFSET(VCPU_LR, kvm_vcpu, arch.regs.link);
 	OFFSET(VCPU_CTR, kvm_vcpu, arch.regs.ctr);
@@ -761,23 +771,6 @@
 	OFFSET(VCPU_TIMING_LAST_ENTER_TBL, kvm_vcpu, arch.timing_last_enter.tv32.tbl);
 #endif
 
-#ifdef CONFIG_PPC_POWERNV
-	OFFSET(PACA_CORE_IDLE_STATE_PTR, paca_struct, core_idle_state_ptr);
-	OFFSET(PACA_THREAD_IDLE_STATE, paca_struct, thread_idle_state);
-	OFFSET(PACA_THREAD_MASK, paca_struct, thread_mask);
-	OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask);
-	OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr);
-	OFFSET(PACA_DONT_STOP, paca_struct, dont_stop);
-#define STOP_SPR(x, f)	OFFSET(x, paca_struct, stop_sprs.f)
-	STOP_SPR(STOP_PID, pid);
-	STOP_SPR(STOP_LDBAR, ldbar);
-	STOP_SPR(STOP_FSCR, fscr);
-	STOP_SPR(STOP_HFSCR, hfscr);
-	STOP_SPR(STOP_MMCR1, mmcr1);
-	STOP_SPR(STOP_MMCR2, mmcr2);
-	STOP_SPR(STOP_MMCRA, mmcra);
-#endif
-
 	DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
 	DEFINE(PPC_DBELL_MSGTYPE, PPC_DBELL_MSGTYPE);
 
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index b2072d5..6dfceaa 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -163,7 +163,7 @@
 	offset = ((unsigned long) dispDeviceBase) - base;
 	size = dispDeviceRowBytes * dispDeviceRect[3] + offset
 		+ dispDeviceRect[0];
-	vbase = __ioremap(base, size, pgprot_val(pgprot_noncached_wc(__pgprot(0))));
+	vbase = ioremap_wc(base, size);
 	if (!vbase)
 		return;
 	logicalDisplayBase = vbase + offset;
@@ -232,20 +232,12 @@
 
 int __init btext_find_display(int allow_nonstdout)
 {
-	const char *name;
-	struct device_node *np = NULL; 
+	struct device_node *np = of_stdout;
 	int rc = -ENODEV;
 
-	name = of_get_property(of_chosen, "linux,stdout-path", NULL);
-	if (name != NULL) {
-		np = of_find_node_by_path(name);
-		if (np != NULL) {
-			if (strcmp(np->type, "display") != 0) {
-				printk("boot stdout isn't a display !\n");
-				of_node_put(np);
-				np = NULL;
-			}
-		}
+	if (!of_node_is_type(np, "display")) {
+		printk("boot stdout isn't a display !\n");
+		np = NULL;
 	}
 	if (np)
 		rc = btext_initialize(np);
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index a8f20e5..4703362 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Processor cache information made available to userspace via sysfs;
  * intended to be compatible with x86 intel_cacheinfo implementation.
  *
  * Copyright 2008 IBM Corporation
  * Author: Nathan Lynch
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
  */
 
 #include <linux/cpu.h>
@@ -20,6 +17,8 @@
 #include <linux/percpu.h>
 #include <linux/slab.h>
 #include <asm/prom.h>
+#include <asm/cputhreads.h>
+#include <asm/smp.h>
 
 #include "cacheinfo.h"
 
@@ -351,8 +350,6 @@
 		CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED;
 }
 
-/*
- */
 static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level)
 {
 	pr_debug("creating L%d ucache for %pOF\n", level, node);
@@ -426,7 +423,7 @@
 static void do_subsidiary_caches_debugcheck(struct cache *cache)
 {
 	WARN_ON_ONCE(cache->level != 1);
-	WARN_ON_ONCE(strcmp(cache->ofnode->type, "cpu"));
+	WARN_ON_ONCE(!of_node_is_type(cache->ofnode, "cpu"));
 }
 
 static void do_subsidiary_caches(struct cache *cache)
@@ -627,17 +624,48 @@
 static struct kobj_attribute cache_level_attr =
 	__ATTR(level, 0444, level_show, NULL);
 
+static unsigned int index_dir_to_cpu(struct cache_index_dir *index)
+{
+	struct kobject *index_dir_kobj = &index->kobj;
+	struct kobject *cache_dir_kobj = index_dir_kobj->parent;
+	struct kobject *cpu_dev_kobj = cache_dir_kobj->parent;
+	struct device *dev = kobj_to_dev(cpu_dev_kobj);
+
+	return dev->id;
+}
+
+/*
+ * On big-core systems, each core has two groups of CPUs each of which
+ * has its own L1-cache. The thread-siblings which share l1-cache with
+ * @cpu can be obtained via cpu_smallcore_mask().
+ */
+static const struct cpumask *get_big_core_shared_cpu_map(int cpu, struct cache *cache)
+{
+	if (cache->level == 1)
+		return cpu_smallcore_mask(cpu);
+
+	return &cache->shared_cpu_map;
+}
+
 static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
 {
 	struct cache_index_dir *index;
 	struct cache *cache;
-	int ret;
+	const struct cpumask *mask;
+	int ret, cpu;
 
 	index = kobj_to_cache_index_dir(k);
 	cache = index->cache;
 
+	if (has_big_cores) {
+		cpu = index_dir_to_cpu(index);
+		mask = get_big_core_shared_cpu_map(cpu, cache);
+	} else {
+		mask  = &cache->shared_cpu_map;
+	}
+
 	ret = scnprintf(buf, PAGE_SIZE - 1, "%*pb\n",
-			cpumask_pr_args(&cache->shared_cpu_map));
+			cpumask_pr_args(mask));
 	buf[ret++] = '\n';
 	buf[ret] = '\0';
 	return ret;
@@ -726,23 +754,21 @@
 
 	index_dir = kzalloc(sizeof(*index_dir), GFP_KERNEL);
 	if (!index_dir)
-		goto err;
+		return;
 
 	index_dir->cache = cache;
 
 	rc = kobject_init_and_add(&index_dir->kobj, &cache_index_type,
 				  cache_dir->kobj, "index%d", index);
-	if (rc)
-		goto err;
+	if (rc) {
+		kobject_put(&index_dir->kobj);
+		return;
+	}
 
 	index_dir->next = cache_dir->index;
 	cache_dir->index = index_dir;
 
 	cacheinfo_create_index_opt_attrs(index_dir);
-
-	return;
-err:
-	kfree(index_dir);
 }
 
 static void cacheinfo_sysfs_populate(unsigned int cpu_id,
@@ -865,4 +891,25 @@
 	if (cache)
 		cache_cpu_clear(cache, cpu_id);
 }
+
+void cacheinfo_teardown(void)
+{
+	unsigned int cpu;
+
+	lockdep_assert_cpus_held();
+
+	for_each_online_cpu(cpu)
+		cacheinfo_cpu_offline(cpu);
+}
+
+void cacheinfo_rebuild(void)
+{
+	unsigned int cpu;
+
+	lockdep_assert_cpus_held();
+
+	for_each_online_cpu(cpu)
+		cacheinfo_cpu_online(cpu);
+}
+
 #endif /* (CONFIG_PPC_PSERIES && CONFIG_SUSPEND) || CONFIG_HOTPLUG_CPU */
diff --git a/arch/powerpc/kernel/cacheinfo.h b/arch/powerpc/kernel/cacheinfo.h
index 955f5e9..52bd3fc 100644
--- a/arch/powerpc/kernel/cacheinfo.h
+++ b/arch/powerpc/kernel/cacheinfo.h
@@ -6,4 +6,8 @@
 extern void cacheinfo_cpu_online(unsigned int cpu_id);
 extern void cacheinfo_cpu_offline(unsigned int cpu_id);
 
+/* Allow migration/suspend to tear down and rebuild the hierarchy. */
+extern void cacheinfo_teardown(void);
+extern void cacheinfo_rebuild(void);
+
 #endif /* _PPC_CACHEINFO_H */
diff --git a/arch/powerpc/kernel/cpu_setup_44x.S b/arch/powerpc/kernel/cpu_setup_44x.S
index e32b4a9..e1d705e 100644
--- a/arch/powerpc/kernel/cpu_setup_44x.S
+++ b/arch/powerpc/kernel/cpu_setup_44x.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains low level CPU setup functions.
  * Valentine Barshak <vbarshak@ru.mvista.com>
@@ -5,12 +6,6 @@
  *
  * Based on cpu_setup_6xx code by
  * Benjamin Herrenschmidt <benh@kernel.crashing.org>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/processor.h>
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index fa3c2c9..f6517f6 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -1,12 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains low level CPU setup functions.
  *    Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/processor.h>
@@ -24,6 +19,7 @@
 	li	r10,0
 	mtspr	SPRN_SPRG_603_LRU,r10		/* init SW LRU tracking */
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
+
 BEGIN_FTR_SECTION
 	bl	__init_fpu_registers
 END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
@@ -326,7 +322,7 @@
 	lis	r5,cpu_state_storage@h
 	ori	r5,r5,cpu_state_storage@l
 
-	/* Save HID0 (common to all CONFIG_6xx cpus) */
+	/* Save HID0 (common to all CONFIG_PPC_BOOK3S_32 cpus) */
 	mfspr	r3,SPRN_HID0
 	stw	r3,CS_HID0(r5)
 
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 8d142e5..2b4f3ec 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains low level CPU setup functions.
  * Kumar Gala <galak@kernel.crashing.org>
@@ -5,19 +6,13 @@
  *
  * Based on cpu_setup_6xx code by
  * Benjamin Herrenschmidt <benh@kernel.crashing.org>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/page.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>
 #include <asm/ppc_asm.h>
-#include <asm/mmu-book3e.h>
+#include <asm/nohash/mmu-book3e.h>
 #include <asm/asm-offsets.h>
 #include <asm/mpc85xx.h>
 
diff --git a/arch/powerpc/kernel/cpu_setup_pa6t.S b/arch/powerpc/kernel/cpu_setup_pa6t.S
index d62cb9c..e6bfd44 100644
--- a/arch/powerpc/kernel/cpu_setup_pa6t.S
+++ b/arch/powerpc/kernel/cpu_setup_pa6t.S
@@ -1,21 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2006-2007 PA Semi, Inc
  *
  * Maintained by: Olof Johansson <olof@lixom.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  */
 
 #include <asm/processor.h>
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 458b928..a460298 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -1,12 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains low level CPU setup functions.
  *    Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/processor.h>
@@ -28,6 +23,7 @@
 	beqlr
 	li	r0,0
 	mtspr	SPRN_LPID,r0
+	LOAD_REG_IMMEDIATE(r0, PCR_MASK)
 	mtspr	SPRN_PCR,r0
 	mfspr	r3,SPRN_LPCR
 	li	r4,(LPCR_LPES1 >> LPCR_LPES_SH)
@@ -42,6 +38,7 @@
 	beqlr
 	li	r0,0
 	mtspr	SPRN_LPID,r0
+	LOAD_REG_IMMEDIATE(r0, PCR_MASK)
 	mtspr	SPRN_PCR,r0
 	mfspr	r3,SPRN_LPCR
 	li	r4,(LPCR_LPES1 >> LPCR_LPES_SH)
@@ -59,6 +56,7 @@
 	beqlr
 	li	r0,0
 	mtspr	SPRN_LPID,r0
+	LOAD_REG_IMMEDIATE(r0, PCR_MASK)
 	mtspr	SPRN_PCR,r0
 	mfspr	r3,SPRN_LPCR
 	ori	r3, r3, LPCR_PECEDH
@@ -81,6 +79,7 @@
 	beqlr
 	li	r0,0
 	mtspr	SPRN_LPID,r0
+	LOAD_REG_IMMEDIATE(r0, PCR_MASK)
 	mtspr	SPRN_PCR,r0
 	mfspr   r3,SPRN_LPCR
 	ori	r3, r3, LPCR_PECEDH
@@ -103,6 +102,7 @@
 	mtspr	SPRN_PSSCR,r0
 	mtspr	SPRN_LPID,r0
 	mtspr	SPRN_PID,r0
+	LOAD_REG_IMMEDIATE(r0, PCR_MASK)
 	mtspr	SPRN_PCR,r0
 	mfspr	r3,SPRN_LPCR
 	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE  | LPCR_HEIC)
@@ -128,6 +128,7 @@
 	mtspr	SPRN_PSSCR,r0
 	mtspr	SPRN_LPID,r0
 	mtspr	SPRN_PID,r0
+	LOAD_REG_IMMEDIATE(r0, PCR_MASK)
 	mtspr	SPRN_PCR,r0
 	mfspr   r3,SPRN_LPCR
 	LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC)
@@ -147,8 +148,8 @@
 	rldicl.	r0,r3,4,63
 	bnelr
 	ld	r5,CPU_SPEC_FEATURES(r4)
-	LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE)
-	xor	r5,r5,r6
+	LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE | CPU_FTR_P9_TM_HV_ASSIST)
+	andc	r5,r5,r6
 	std	r5,CPU_SPEC_FEATURES(r4)
 	blr
 
diff --git a/arch/powerpc/kernel/cpu_setup_ppc970.S b/arch/powerpc/kernel/cpu_setup_ppc970.S
index 12fac8d..f0c07e7 100644
--- a/arch/powerpc/kernel/cpu_setup_ppc970.S
+++ b/arch/powerpc/kernel/cpu_setup_ppc970.S
@@ -1,12 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains low level CPU setup functions.
  *    Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/processor.h>
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 2da0134..e745abc 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
  *
  *  Modifications for ppc64:
  *      Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/string.h>
@@ -573,7 +569,7 @@
 #endif	/* CONFIG_PPC_BOOK3S_64 */
 
 #ifdef CONFIG_PPC32
-#ifdef CONFIG_PPC_BOOK3S_32
+#ifdef CONFIG_PPC_BOOK3S_601
 	{	/* 601 */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x00010000,
@@ -587,6 +583,8 @@
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc601",
 	},
+#endif /* CONFIG_PPC_BOOK3S_601 */
+#ifdef CONFIG_PPC_BOOK3S_6xx
 	{	/* 603 */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x00030000,
@@ -1141,6 +1139,7 @@
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc603",
 	},
+#ifdef CONFIG_PPC_83xx
 	{	/* e300c1 (a 603e core, plus some) on 83xx */
 		.pvr_mask		= 0x7fff0000,
 		.pvr_value		= 0x00830000,
@@ -1151,7 +1150,7 @@
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
-		.machine_check		= machine_check_generic,
+		.machine_check		= machine_check_83xx,
 		.platform		= "ppc603",
 	},
 	{	/* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */
@@ -1165,7 +1164,7 @@
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
-		.machine_check		= machine_check_generic,
+		.machine_check		= machine_check_83xx,
 		.platform		= "ppc603",
 	},
 	{	/* e300c3 (e300c1, plus one IU, half cache size) on 83xx */
@@ -1179,7 +1178,7 @@
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
-		.machine_check		= machine_check_generic,
+		.machine_check		= machine_check_83xx,
 		.num_pmcs		= 4,
 		.oprofile_cpu_type	= "ppc/e300",
 		.oprofile_type		= PPC_OPROFILE_FSL_EMB,
@@ -1196,12 +1195,13 @@
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
-		.machine_check		= machine_check_generic,
+		.machine_check		= machine_check_83xx,
 		.num_pmcs		= 4,
 		.oprofile_cpu_type	= "ppc/e300",
 		.oprofile_type		= PPC_OPROFILE_FSL_EMB,
 		.platform		= "ppc603",
 	},
+#endif
 	{	/* default match, we assume split I/D cache & TB (non-601)... */
 		.pvr_mask		= 0x00000000,
 		.pvr_value		= 0x00000000,
@@ -1214,7 +1214,7 @@
 		.machine_check		= machine_check_generic,
 		.platform		= "ppc603",
 	},
-#endif /* CONFIG_PPC_BOOK3S_32 */
+#endif /* CONFIG_PPC_BOOK3S_6xx */
 #ifdef CONFIG_PPC_8xx
 	{	/* 8xx */
 		.pvr_mask		= 0xffff0000,
@@ -2145,7 +2145,11 @@
 	struct cpu_spec *t = &the_cpu_spec;
 
 	t = PTRRELOC(t);
-	*t = *s;
+	/*
+	 * use memcpy() instead of *t = *s so that GCC replaces it
+	 * by __memcpy() when KASAN is active
+	 */
+	memcpy(t, s, sizeof(*t));
 
 	*PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
 }
@@ -2159,8 +2163,11 @@
 	t = PTRRELOC(t);
 	old = *t;
 
-	/* Copy everything, then do fixups */
-	*t = *s;
+	/*
+	 * Copy everything, then do fixups. Use memcpy() instead of *t = *s
+	 * so that GCC replaces it by __memcpy() when KASAN is active
+	 */
+	memcpy(t, s, sizeof(*t));
 
 	/*
 	 * If we are overriding a previous value derived from the real
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 43a3ce2..d488311 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Architecture specific (PPC64) functions for kexec based crash dumps.
  *
  * Copyright (C) 2005, IBM Corp.
  *
  * Created by: Haren Myneni
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2.  See the file COPYING for more details.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index d10ad25..05745dd 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -1,12 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Routines for doing kexec-based kdump.
  *
  * Copyright (C) 2005, IBM Corp.
  *
  * Created by: Michael Ellerman
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2.  See the file COPYING for more details.
  */
 
 #undef DEBUG
@@ -110,7 +108,7 @@
 		vaddr = __va(paddr);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 	} else {
-		vaddr = __ioremap(paddr, PAGE_SIZE, 0);
+		vaddr = ioremap_cache(paddr, PAGE_SIZE);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 		iounmap(vaddr);
 	}
diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c
new file mode 100644
index 0000000..5f66b95
--- /dev/null
+++ b/arch/powerpc/kernel/dawr.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * DAWR infrastructure
+ *
+ * Copyright 2019, Michael Neuling, IBM Corporation.
+ */
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <asm/debugfs.h>
+#include <asm/machdep.h>
+#include <asm/hvcall.h>
+
+bool dawr_force_enable;
+EXPORT_SYMBOL_GPL(dawr_force_enable);
+
+int set_dawr(struct arch_hw_breakpoint *brk)
+{
+	unsigned long dawr, dawrx, mrd;
+
+	dawr = brk->address;
+
+	dawrx  = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE))
+		<< (63 - 58);
+	dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) << (63 - 59);
+	dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) >> 3;
+	/*
+	 * DAWR length is stored in field MDR bits 48:53.  Matches range in
+	 * doublewords (64 bits) baised by -1 eg. 0b000000=1DW and
+	 * 0b111111=64DW.
+	 * brk->len is in bytes.
+	 * This aligns up to double word size, shifts and does the bias.
+	 */
+	mrd = ((brk->len + 7) >> 3) - 1;
+	dawrx |= (mrd & 0x3f) << (63 - 53);
+
+	if (ppc_md.set_dawr)
+		return ppc_md.set_dawr(dawr, dawrx);
+
+	mtspr(SPRN_DAWR, dawr);
+	mtspr(SPRN_DAWRX, dawrx);
+
+	return 0;
+}
+
+static void set_dawr_cb(void *info)
+{
+	set_dawr(info);
+}
+
+static ssize_t dawr_write_file_bool(struct file *file,
+				    const char __user *user_buf,
+				    size_t count, loff_t *ppos)
+{
+	struct arch_hw_breakpoint null_brk = {0, 0, 0};
+	size_t rc;
+
+	/* Send error to user if they hypervisor won't allow us to write DAWR */
+	if (!dawr_force_enable &&
+	    firmware_has_feature(FW_FEATURE_LPAR) &&
+	    set_dawr(&null_brk) != H_SUCCESS)
+		return -ENODEV;
+
+	rc = debugfs_write_file_bool(file, user_buf, count, ppos);
+	if (rc)
+		return rc;
+
+	/* If we are clearing, make sure all CPUs have the DAWR cleared */
+	if (!dawr_force_enable)
+		smp_call_function(set_dawr_cb, &null_brk, 0);
+
+	return rc;
+}
+
+static const struct file_operations dawr_enable_fops = {
+	.read =		debugfs_read_file_bool,
+	.write =	dawr_write_file_bool,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+static int __init dawr_force_setup(void)
+{
+	if (cpu_has_feature(CPU_FTR_DAWR)) {
+		/* Don't setup sysfs file for user control on P8 */
+		dawr_force_enable = true;
+		return 0;
+	}
+
+	if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) {
+		/* Turn DAWR off by default, but allow admin to turn it on */
+		debugfs_create_file_unsafe("dawr_enable_dangerous", 0600,
+					   powerpc_debugfs_root,
+					   &dawr_force_enable,
+					   &dawr_enable_fops);
+	}
+	return 0;
+}
+arch_initcall(dawr_force_setup);
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index b6fe883..f17ff12 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Author: Kumar Gala <galak@kernel.crashing.org>
  *
  * Copyright 2009 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -18,6 +14,7 @@
 #include <asm/dbell.h>
 #include <asm/irq_regs.h>
 #include <asm/kvm_ppc.h>
+#include <asm/trace.h>
 
 #ifdef CONFIG_SMP
 
@@ -36,7 +33,7 @@
 {
 	u32 tag = get_hard_smp_processor_id(cpu);
 
-	kvmppc_set_host_ipi(cpu, 1);
+	kvmppc_set_host_ipi(cpu);
 	/* Order previous accesses vs. msgsnd, which is treated as a store */
 	ppc_msgsnd_sync();
 	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
@@ -51,7 +48,7 @@
 {
 	u32 tag = cpu_thread_in_core(cpu);
 
-	kvmppc_set_host_ipi(cpu, 1);
+	kvmppc_set_host_ipi(cpu);
 	/* Order previous accesses vs. msgsnd, which is treated as a store */
 	ppc_msgsnd_sync();
 	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
@@ -81,16 +78,18 @@
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	irq_enter();
+	trace_doorbell_entry(regs);
 
 	ppc_msgsync();
 
 	may_hard_irq_enable();
 
-	kvmppc_set_host_ipi(smp_processor_id(), 0);
+	kvmppc_clear_host_ipi(smp_processor_id());
 	__this_cpu_inc(irq_stat.doorbell_irqs);
 
 	smp_ipi_demux_relaxed(); /* already performed the barrier */
 
+	trace_doorbell_exit(regs);
 	irq_exit();
 	set_irq_regs(old_regs);
 }
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index f9fe208..e486d1d 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -6,13 +6,31 @@
  * busses using the iommu infrastructure
  */
 
-#include <linux/export.h>
+#include <linux/dma-direct.h>
+#include <linux/pci.h>
 #include <asm/iommu.h>
 
 /*
  * Generic iommu implementation
  */
 
+/*
+ * The coherent mask may be smaller than the real mask, check if we can
+ * really use a direct window.
+ */
+static inline bool dma_iommu_alloc_bypass(struct device *dev)
+{
+	return dev->archdata.iommu_bypass && !iommu_fixed_is_weak &&
+		dma_direct_supported(dev, dev->coherent_dma_mask);
+}
+
+static inline bool dma_iommu_map_bypass(struct device *dev,
+		unsigned long attrs)
+{
+	return dev->archdata.iommu_bypass &&
+		(!iommu_fixed_is_weak || (attrs & DMA_ATTR_WEAK_ORDERING));
+}
+
 /* Allocates a contiguous real buffer and creates mappings over it.
  * Returns the virtual address of the buffer and sets dma_handle
  * to the dma address (mapping) of the first page.
@@ -21,6 +39,8 @@
 				      dma_addr_t *dma_handle, gfp_t flag,
 				      unsigned long attrs)
 {
+	if (dma_iommu_alloc_bypass(dev))
+		return dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
 				    dma_handle, dev->coherent_dma_mask, flag,
 				    dev_to_node(dev));
@@ -30,7 +50,11 @@
 				    void *vaddr, dma_addr_t dma_handle,
 				    unsigned long attrs)
 {
-	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
+	if (dma_iommu_alloc_bypass(dev))
+		dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+	else
+		iommu_free_coherent(get_iommu_table_base(dev), size, vaddr,
+				dma_handle);
 }
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
@@ -43,8 +67,11 @@
 				     enum dma_data_direction direction,
 				     unsigned long attrs)
 {
+	if (dma_iommu_map_bypass(dev, attrs))
+		return dma_direct_map_page(dev, page, offset, size, direction,
+				attrs);
 	return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
-			      size, device_to_mask(dev), direction, attrs);
+			      size, dma_get_mask(dev), direction, attrs);
 }
 
 
@@ -52,8 +79,11 @@
 				 size_t size, enum dma_data_direction direction,
 				 unsigned long attrs)
 {
-	iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
-			 attrs);
+	if (!dma_iommu_map_bypass(dev, attrs))
+		iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size,
+				direction,  attrs);
+	else
+		dma_direct_unmap_page(dev, dma_handle, size, direction, attrs);
 }
 
 
@@ -61,16 +91,30 @@
 			    int nelems, enum dma_data_direction direction,
 			    unsigned long attrs)
 {
+	if (dma_iommu_map_bypass(dev, attrs))
+		return dma_direct_map_sg(dev, sglist, nelems, direction, attrs);
 	return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
-				device_to_mask(dev), direction, attrs);
+				dma_get_mask(dev), direction, attrs);
 }
 
 static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		int nelems, enum dma_data_direction direction,
 		unsigned long attrs)
 {
-	ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
+	if (!dma_iommu_map_bypass(dev, attrs))
+		ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
 			   direction, attrs);
+	else
+		dma_direct_unmap_sg(dev, sglist, nelems, direction, attrs);
+}
+
+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);
+
+	return phb->controller_ops.iommu_bypass_supported &&
+		phb->controller_ops.iommu_bypass_supported(pdev, mask);
 }
 
 /* We support DMA to/from any memory page via the iommu */
@@ -78,9 +122,14 @@
 {
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
+	if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
+		dev->archdata.iommu_bypass = true;
+		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
+		return 1;
+	}
+
 	if (!tbl) {
-		dev_info(dev, "Warning: IOMMU dma not supported: mask 0x%08llx"
-			", table unavailable\n", mask);
+		dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask);
 		return 0;
 	}
 
@@ -89,38 +138,75 @@
 		dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
 				mask, tbl->it_offset << tbl->it_page_shift);
 		return 0;
-	} else
-		return 1;
+	}
+
+	dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
+	dev->archdata.iommu_bypass = false;
+	return 1;
 }
 
-static u64 dma_iommu_get_required_mask(struct device *dev)
+u64 dma_iommu_get_required_mask(struct device *dev)
 {
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 	u64 mask;
+
 	if (!tbl)
 		return 0;
 
+	if (dev_is_pci(dev)) {
+		u64 bypass_mask = dma_direct_get_required_mask(dev);
+
+		if (dma_iommu_bypass_supported(dev, bypass_mask))
+			return bypass_mask;
+	}
+
 	mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
 	mask += mask - 1;
 
 	return mask;
 }
 
-int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
+static void dma_iommu_sync_for_cpu(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir)
 {
-	return dma_addr == IOMMU_MAPPING_ERROR;
+	if (dma_iommu_alloc_bypass(dev))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
 }
 
-struct dma_map_ops dma_iommu_ops = {
+static void dma_iommu_sync_for_device(struct device *dev, dma_addr_t addr,
+		size_t sz, enum dma_data_direction dir)
+{
+	if (dma_iommu_alloc_bypass(dev))
+		dma_direct_sync_single_for_device(dev, addr, sz, dir);
+}
+
+extern void dma_iommu_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	if (dma_iommu_alloc_bypass(dev))
+		dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir);
+}
+
+extern void dma_iommu_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	if (dma_iommu_alloc_bypass(dev))
+		dma_direct_sync_sg_for_device(dev, sgl, nents, dir);
+}
+
+const struct dma_map_ops dma_iommu_ops = {
 	.alloc			= dma_iommu_alloc_coherent,
 	.free			= dma_iommu_free_coherent,
-	.mmap			= dma_nommu_mmap_coherent,
 	.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,
 	.get_required_mask	= dma_iommu_get_required_mask,
-	.mapping_error		= dma_iommu_mapping_error,
+	.sync_single_for_cpu	= dma_iommu_sync_for_cpu,
+	.sync_single_for_device	= dma_iommu_sync_for_device,
+	.sync_sg_for_cpu	= dma_iommu_sync_sg_for_cpu,
+	.sync_sg_for_device	= dma_iommu_sync_sg_for_device,
+	.mmap			= dma_common_mmap,
+	.get_sgtable		= dma_common_get_sgtable,
 };
-EXPORT_SYMBOL(dma_iommu_ops);
diff --git a/arch/powerpc/kernel/dma-mask.c b/arch/powerpc/kernel/dma-mask.c
new file mode 100644
index 0000000..ffbbbc4
--- /dev/null
+++ b/arch/powerpc/kernel/dma-mask.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/dma-mapping.h>
+#include <linux/export.h>
+#include <asm/machdep.h>
+
+void arch_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (ppc_md.dma_set_mask)
+		ppc_md.dma_set_mask(dev, dma_mask);
+}
+EXPORT_SYMBOL(arch_dma_set_mask);
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 88f3963..fc78161 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -1,119 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Contains routines needed to support swiotlb for ppc.
  *
  * Copyright (C) 2009-2010 Freescale Semiconductor, Inc.
  * Author: Becky Bruce
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
-
-#include <linux/dma-mapping.h>
 #include <linux/memblock.h>
-#include <linux/pfn.h>
-#include <linux/of_platform.h>
-#include <linux/platform_device.h>
-#include <linux/pci.h>
-
 #include <asm/machdep.h>
 #include <asm/swiotlb.h>
-#include <asm/dma.h>
 
 unsigned int ppc_swiotlb_enable;
 
-static u64 swiotlb_powerpc_get_required(struct device *dev)
-{
-	u64 end, mask, max_direct_dma_addr = dev->archdata.max_direct_dma_addr;
-
-	end = memblock_end_of_DRAM();
-	if (max_direct_dma_addr && end > max_direct_dma_addr)
-		end = max_direct_dma_addr;
-	end += get_dma_offset(dev);
-
-	mask = 1ULL << (fls64(end) - 1);
-	mask += mask - 1;
-
-	return mask;
-}
-
-/*
- * At the moment, all platforms that use this code only require
- * swiotlb to be used if we're operating on HIGHMEM.  Since
- * we don't ever call anything other than map_sg, unmap_sg,
- * map_page, and unmap_page on highmem, use normal dma_ops
- * for everything else.
- */
-const struct dma_map_ops powerpc_swiotlb_dma_ops = {
-	.alloc = __dma_nommu_alloc_coherent,
-	.free = __dma_nommu_free_coherent,
-	.mmap = dma_nommu_mmap_coherent,
-	.map_sg = swiotlb_map_sg_attrs,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
-	.dma_supported = swiotlb_dma_supported,
-	.map_page = swiotlb_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = swiotlb_sync_sg_for_device,
-	.mapping_error = swiotlb_dma_mapping_error,
-	.get_required_mask = swiotlb_powerpc_get_required,
-};
-
-void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
-{
-	struct pci_controller *hose;
-	struct dev_archdata *sd;
-
-	hose = pci_bus_to_host(pdev->bus);
-	sd = &pdev->dev.archdata;
-	sd->max_direct_dma_addr =
-		hose->dma_window_base_cur + hose->dma_window_size;
-}
-
-static int ppc_swiotlb_bus_notify(struct notifier_block *nb,
-				  unsigned long action, void *data)
-{
-	struct device *dev = data;
-	struct dev_archdata *sd;
-
-	/* We are only intereted in device addition */
-	if (action != BUS_NOTIFY_ADD_DEVICE)
-		return 0;
-
-	sd = &dev->archdata;
-	sd->max_direct_dma_addr = 0;
-
-	/* May need to bounce if the device can't address all of DRAM */
-	if ((dma_get_mask(dev) + 1) < memblock_end_of_DRAM())
-		set_dma_ops(dev, &powerpc_swiotlb_dma_ops);
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block ppc_swiotlb_plat_bus_notifier = {
-	.notifier_call = ppc_swiotlb_bus_notify,
-	.priority = 0,
-};
-
-int __init swiotlb_setup_bus_notifier(void)
-{
-	bus_register_notifier(&platform_bus_type,
-			      &ppc_swiotlb_plat_bus_notifier);
-	return 0;
-}
-
 void __init swiotlb_detect_4g(void)
 {
-	if ((memblock_end_of_DRAM() - 1) > 0xffffffff) {
+	if ((memblock_end_of_DRAM() - 1) > 0xffffffff)
 		ppc_swiotlb_enable = 1;
-#ifdef CONFIG_ZONE_DMA32
-		limit_zone_pfn(ZONE_DMA32, (1ULL << 32) >> PAGE_SHIFT);
-#endif
-	}
 }
 
 static int __init check_swiotlb_enabled(void)
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
deleted file mode 100644
index dbfc705..0000000
--- a/arch/powerpc/kernel/dma.c
+++ /dev/null
@@ -1,367 +0,0 @@
-/*
- * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
- *
- * Provide default implementations of the DMA mapping callbacks for
- * directly mapped busses.
- */
-
-#include <linux/device.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-debug.h>
-#include <linux/gfp.h>
-#include <linux/memblock.h>
-#include <linux/export.h>
-#include <linux/pci.h>
-#include <asm/vio.h>
-#include <asm/bug.h>
-#include <asm/machdep.h>
-#include <asm/swiotlb.h>
-#include <asm/iommu.h>
-
-/*
- * Generic direct DMA implementation
- *
- * This implementation supports a per-device offset that can be applied if
- * the address at which memory is visible to devices is not 0. Platform code
- * can set archdata.dma_data to an unsigned long holding the offset. By
- * default the offset is PCI_DRAM_OFFSET.
- */
-
-static u64 __maybe_unused get_pfn_limit(struct device *dev)
-{
-	u64 pfn = (dev->coherent_dma_mask >> PAGE_SHIFT) + 1;
-	struct dev_archdata __maybe_unused *sd = &dev->archdata;
-
-#ifdef CONFIG_SWIOTLB
-	if (sd->max_direct_dma_addr && dev->dma_ops == &powerpc_swiotlb_dma_ops)
-		pfn = min_t(u64, pfn, sd->max_direct_dma_addr >> PAGE_SHIFT);
-#endif
-
-	return pfn;
-}
-
-static int dma_nommu_dma_supported(struct device *dev, u64 mask)
-{
-#ifdef CONFIG_PPC64
-	u64 limit = get_dma_offset(dev) + (memblock_end_of_DRAM() - 1);
-
-	/* Limit fits in the mask, we are good */
-	if (mask >= limit)
-		return 1;
-
-#ifdef CONFIG_FSL_SOC
-	/* Freescale gets another chance via ZONE_DMA/ZONE_DMA32, however
-	 * that will have to be refined if/when they support iommus
-	 */
-	return 1;
-#endif
-	/* Sorry ... */
-	return 0;
-#else
-	return 1;
-#endif
-}
-
-void *__dma_nommu_alloc_coherent(struct device *dev, size_t size,
-				  dma_addr_t *dma_handle, gfp_t flag,
-				  unsigned long attrs)
-{
-	void *ret;
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	ret = __dma_alloc_coherent(dev, size, dma_handle, flag);
-	if (ret == NULL)
-		return NULL;
-	*dma_handle += get_dma_offset(dev);
-	return ret;
-#else
-	struct page *page;
-	int node = dev_to_node(dev);
-#ifdef CONFIG_FSL_SOC
-	u64 pfn = get_pfn_limit(dev);
-	int zone;
-
-	/*
-	 * This code should be OK on other platforms, but we have drivers that
-	 * don't set coherent_dma_mask. As a workaround we just ifdef it. This
-	 * whole routine needs some serious cleanup.
-	 */
-
-	zone = dma_pfn_limit_to_zone(pfn);
-	if (zone < 0) {
-		dev_err(dev, "%s: No suitable zone for pfn %#llx\n",
-			__func__, pfn);
-		return NULL;
-	}
-
-	switch (zone) {
-	case ZONE_DMA:
-		flag |= GFP_DMA;
-		break;
-#ifdef CONFIG_ZONE_DMA32
-	case ZONE_DMA32:
-		flag |= GFP_DMA32;
-		break;
-#endif
-	};
-#endif /* CONFIG_FSL_SOC */
-
-	page = alloc_pages_node(node, flag, get_order(size));
-	if (page == NULL)
-		return NULL;
-	ret = page_address(page);
-	memset(ret, 0, size);
-	*dma_handle = __pa(ret) + get_dma_offset(dev);
-
-	return ret;
-#endif
-}
-
-void __dma_nommu_free_coherent(struct device *dev, size_t size,
-				void *vaddr, dma_addr_t dma_handle,
-				unsigned long attrs)
-{
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	__dma_free_coherent(size, vaddr);
-#else
-	free_pages((unsigned long)vaddr, get_order(size));
-#endif
-}
-
-static void *dma_nommu_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag,
-				       unsigned long attrs)
-{
-	struct iommu_table *iommu;
-
-	/* The coherent mask may be smaller than the real mask, check if
-	 * we can really use the direct ops
-	 */
-	if (dma_nommu_dma_supported(dev, dev->coherent_dma_mask))
-		return __dma_nommu_alloc_coherent(dev, size, dma_handle,
-						   flag, attrs);
-
-	/* Ok we can't ... do we have an iommu ? If not, fail */
-	iommu = get_iommu_table_base(dev);
-	if (!iommu)
-		return NULL;
-
-	/* Try to use the iommu */
-	return iommu_alloc_coherent(dev, iommu, size, dma_handle,
-				    dev->coherent_dma_mask, flag,
-				    dev_to_node(dev));
-}
-
-static void dma_nommu_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dma_handle,
-				     unsigned long attrs)
-{
-	struct iommu_table *iommu;
-
-	/* See comments in dma_nommu_alloc_coherent() */
-	if (dma_nommu_dma_supported(dev, dev->coherent_dma_mask))
-		return __dma_nommu_free_coherent(dev, size, vaddr, dma_handle,
-						  attrs);
-	/* Maybe we used an iommu ... */
-	iommu = get_iommu_table_base(dev);
-
-	/* If we hit that we should have never allocated in the first
-	 * place so how come we are freeing ?
-	 */
-	if (WARN_ON(!iommu))
-		return;
-	iommu_free_coherent(iommu, size, vaddr, dma_handle);
-}
-
-int dma_nommu_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
-			     void *cpu_addr, dma_addr_t handle, size_t size,
-			     unsigned long attrs)
-{
-	unsigned long pfn;
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
-#else
-	pfn = page_to_pfn(virt_to_page(cpu_addr));
-#endif
-	return remap_pfn_range(vma, vma->vm_start,
-			       pfn + vma->vm_pgoff,
-			       vma->vm_end - vma->vm_start,
-			       vma->vm_page_prot);
-}
-
-static int dma_nommu_map_sg(struct device *dev, struct scatterlist *sgl,
-			     int nents, enum dma_data_direction direction,
-			     unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i) {
-		sg->dma_address = sg_phys(sg) + get_dma_offset(dev);
-		sg->dma_length = sg->length;
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
-	}
-
-	return nents;
-}
-
-static void dma_nommu_unmap_sg(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction,
-				unsigned long attrs)
-{
-}
-
-static u64 dma_nommu_get_required_mask(struct device *dev)
-{
-	u64 end, mask;
-
-	end = memblock_end_of_DRAM() + get_dma_offset(dev);
-
-	mask = 1ULL << (fls64(end) - 1);
-	mask += mask - 1;
-
-	return mask;
-}
-
-static inline dma_addr_t dma_nommu_map_page(struct device *dev,
-					     struct page *page,
-					     unsigned long offset,
-					     size_t size,
-					     enum dma_data_direction dir,
-					     unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync_page(page, offset, size, dir);
-
-	return page_to_phys(page) + offset + get_dma_offset(dev);
-}
-
-static inline void dma_nommu_unmap_page(struct device *dev,
-					 dma_addr_t dma_address,
-					 size_t size,
-					 enum dma_data_direction direction,
-					 unsigned long attrs)
-{
-}
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
-static inline void dma_nommu_sync_sg(struct device *dev,
-		struct scatterlist *sgl, int nents,
-		enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
-}
-
-static inline void dma_nommu_sync_single(struct device *dev,
-					  dma_addr_t dma_handle, size_t size,
-					  enum dma_data_direction direction)
-{
-	__dma_sync(bus_to_virt(dma_handle), size, direction);
-}
-#endif
-
-const struct dma_map_ops dma_nommu_ops = {
-	.alloc				= dma_nommu_alloc_coherent,
-	.free				= dma_nommu_free_coherent,
-	.mmap				= dma_nommu_mmap_coherent,
-	.map_sg				= dma_nommu_map_sg,
-	.unmap_sg			= dma_nommu_unmap_sg,
-	.dma_supported			= dma_nommu_dma_supported,
-	.map_page			= dma_nommu_map_page,
-	.unmap_page			= dma_nommu_unmap_page,
-	.get_required_mask		= dma_nommu_get_required_mask,
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	.sync_single_for_cpu 		= dma_nommu_sync_single,
-	.sync_single_for_device 	= dma_nommu_sync_single,
-	.sync_sg_for_cpu 		= dma_nommu_sync_sg,
-	.sync_sg_for_device 		= dma_nommu_sync_sg,
-#endif
-};
-EXPORT_SYMBOL(dma_nommu_ops);
-
-int dma_set_coherent_mask(struct device *dev, u64 mask)
-{
-	if (!dma_supported(dev, mask)) {
-		/*
-		 * We need to special case the direct DMA ops which can
-		 * support a fallback for coherent allocations. There
-		 * is no dma_op->set_coherent_mask() so we have to do
-		 * things the hard way:
-		 */
-		if (get_dma_ops(dev) != &dma_nommu_ops ||
-		    get_iommu_table_base(dev) == NULL ||
-		    !dma_iommu_dma_supported(dev, mask))
-			return -EIO;
-	}
-	dev->coherent_dma_mask = mask;
-	return 0;
-}
-EXPORT_SYMBOL(dma_set_coherent_mask);
-
-int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	if (ppc_md.dma_set_mask)
-		return ppc_md.dma_set_mask(dev, dma_mask);
-
-	if (dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-		struct pci_controller *phb = pci_bus_to_host(pdev->bus);
-		if (phb->controller_ops.dma_set_mask)
-			return phb->controller_ops.dma_set_mask(pdev, dma_mask);
-	}
-
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
-EXPORT_SYMBOL(dma_set_mask);
-
-u64 __dma_get_required_mask(struct device *dev)
-{
-	const struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	if (unlikely(dma_ops == NULL))
-		return 0;
-
-	if (dma_ops->get_required_mask)
-		return dma_ops->get_required_mask(dev);
-
-	return DMA_BIT_MASK(8 * sizeof(dma_addr_t));
-}
-
-u64 dma_get_required_mask(struct device *dev)
-{
-	if (ppc_md.dma_get_required_mask)
-		return ppc_md.dma_get_required_mask(dev);
-
-	if (dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-		struct pci_controller *phb = pci_bus_to_host(pdev->bus);
-		if (phb->controller_ops.dma_get_required_mask)
-			return phb->controller_ops.dma_get_required_mask(pdev);
-	}
-
-	return __dma_get_required_mask(dev);
-}
-EXPORT_SYMBOL_GPL(dma_get_required_mask);
-
-static int __init dma_init(void)
-{
-#ifdef CONFIG_IBMVIO
-	dma_debug_add_bus(&vio_bus_type);
-#endif
-
-       return 0;
-}
-fs_initcall(dma_init);
-
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index f432054..180b3a5 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -1,6 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2017, Nicholas Piggin, IBM Corporation
- * Licensed under GPLv2.
  */
 
 #define pr_fmt(fmt) "dt-cpu-ftrs: " fmt
@@ -101,7 +101,7 @@
 	if (hv_mode) {
 		mtspr(SPRN_LPID, 0);
 		mtspr(SPRN_HFSCR, system_registers.hfscr);
-		mtspr(SPRN_PCR, 0);
+		mtspr(SPRN_PCR, PCR_MASK);
 	}
 	mtspr(SPRN_FSCR, system_registers.fscr);
 
@@ -144,6 +144,7 @@
 		mtspr(SPRN_HFSCR, 0);
 	}
 	mtspr(SPRN_FSCR, 0);
+	mtspr(SPRN_PCR, PCR_MASK);
 
 	/*
 	 * LPCR does not get cleared, to match behaviour with secondaries
@@ -666,8 +667,10 @@
 		m = &dt_cpu_feature_match_table[i];
 		if (!strcmp(f->name, m->name)) {
 			known = true;
-			if (m->enable(f))
+			if (m->enable(f)) {
+				cur_cpu_spec->cpu_features |= m->cpu_ftr_bit_mask;
 				break;
+			}
 
 			pr_info("not enabling: %s (disabled or unsupported by kernel)\n",
 				f->name);
@@ -675,17 +678,12 @@
 		}
 	}
 
-	if (!known && enable_unknown) {
-		if (!feat_try_enable_unknown(f)) {
-			pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
-				f->name);
-			return false;
-		}
+	if (!known && (!enable_unknown || !feat_try_enable_unknown(f))) {
+		pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
+			f->name);
+		return false;
 	}
 
-	if (m->cpu_ftr_bit_mask)
-		cur_cpu_spec->cpu_features |= m->cpu_ftr_bit_mask;
-
 	if (known)
 		pr_debug("enabling: %s\n", f->name);
 	else
@@ -694,9 +692,37 @@
 	return true;
 }
 
+/*
+ * Handle POWER9 broadcast tlbie invalidation issue using
+ * cpu feature flag.
+ */
+static __init void update_tlbie_feature_flag(unsigned long pvr)
+{
+	if (PVR_VER(pvr) == PVR_POWER9) {
+		/*
+		 * Set the tlbie feature flag for anything below
+		 * Nimbus DD 2.3 and Cumulus DD 1.3
+		 */
+		if ((pvr & 0xe000) == 0) {
+			/* Nimbus */
+			if ((pvr & 0xfff) < 0x203)
+				cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+		} else if ((pvr & 0xc000) == 0) {
+			/* Cumulus */
+			if ((pvr & 0xfff) < 0x103)
+				cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+		} else {
+			WARN_ONCE(1, "Unknown PVR");
+			cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+		}
+
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_ERAT_BUG;
+	}
+}
+
 static __init void cpufeatures_cpu_quirks(void)
 {
-	int version = mfspr(SPRN_PVR);
+	unsigned long version = mfspr(SPRN_PVR);
 
 	/*
 	 * Not all quirks can be derived from the cpufeatures device tree.
@@ -715,10 +741,10 @@
 
 	if ((version & 0xffff0000) == 0x004e0000) {
 		cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR);
-		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG;
 		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TIDR;
 	}
 
+	update_tlbie_feature_flag(version);
 	/*
 	 * PKEY was not in the initial base or feature node
 	 * specification, but it should become optional in the next
@@ -813,7 +839,6 @@
 	int len;
 
 	f = &dt_cpu_features[i];
-	memset(f, 0, sizeof(struct dt_cpu_feature));
 
 	f->node = node;
 
@@ -1008,9 +1033,12 @@
 	/* Count and allocate space for cpu features */
 	of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes,
 						&nr_dt_cpu_features);
-	dt_cpu_features = __va(
-		memblock_alloc(sizeof(struct dt_cpu_feature)*
-				nr_dt_cpu_features, PAGE_SIZE));
+	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);
 
 	cpufeatures_setup_start(isa);
 
diff --git a/arch/powerpc/kernel/early_32.c b/arch/powerpc/kernel/early_32.c
new file mode 100644
index 0000000..3482118
--- /dev/null
+++ b/arch/powerpc/kernel/early_32.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Early init before relocation
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <asm/setup.h>
+#include <asm/sections.h>
+#include <asm/asm-prototypes.h>
+
+/*
+ * We're called here very early in the boot.
+ *
+ * Note that the kernel may be running at an address which is different
+ * from the address that it was linked at, so we must use RELOC/PTRRELOC
+ * to access static data (including strings).  -- paulus
+ */
+notrace unsigned long __init early_init(unsigned long dt_ptr)
+{
+	unsigned long offset = reloc_offset();
+
+	/* First zero the BSS */
+	memset(PTRRELOC(&__bss_start), 0, __bss_stop - __bss_start);
+
+	/*
+	 * Identify the CPU type and fix up code sections
+	 * that depend on which cpu we have.
+	 */
+	identify_cpu(offset, mfspr(SPRN_PVR));
+
+	apply_feature_fixups();
+
+	return KERNELBASE + offset;
+}
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index c72767a..bc8a551 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright IBM Corporation 2001, 2005, 2006
  * Copyright Dave Engebretsen & Todd Inglett 2001
  * Copyright Linas Vepstas 2005, 2006
  * Copyright 2001-2012 IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com>
  */
 
@@ -109,7 +96,14 @@
  * frozen count in last hour exceeds this limit, the PE will
  * be forced to be offline permanently.
  */
-int eeh_max_freezes = 5;
+u32 eeh_max_freezes = 5;
+
+/*
+ * Controls whether a recovery event should be scheduled when an
+ * isolated device is discovered. This is only really useful for
+ * debugging problems with the EEH core.
+ */
+bool eeh_debugfs_no_recover;
 
 /* Platform dependent EEH operations */
 struct eeh_ops *eeh_ops = NULL;
@@ -156,6 +150,16 @@
 }
 __setup("eeh=", eeh_setup);
 
+void eeh_show_enabled(void)
+{
+	if (eeh_has_flag(EEH_FORCE_DISABLED))
+		pr_info("EEH: Recovery disabled by kernel parameter.\n");
+	else if (eeh_has_flag(EEH_ENABLED))
+		pr_info("EEH: Capable adapter found: recovery enabled.\n");
+	else
+		pr_info("EEH: No capable adapters found: recovery disabled.\n");
+}
+
 /*
  * This routine captures assorted PCI configuration space data
  * for the indicated PCI device, and puts them into a buffer
@@ -360,10 +364,19 @@
 	ptep = find_init_mm_pte(token, &hugepage_shift);
 	if (!ptep)
 		return token;
-	WARN_ON(hugepage_shift);
-	pa = pte_pfn(*ptep) << PAGE_SHIFT;
 
-	return pa | (token & (PAGE_SIZE-1));
+	pa = pte_pfn(*ptep);
+
+	/* On radix we can do hugepage mappings for io, so handle that */
+	if (hugepage_shift) {
+		pa <<= hugepage_shift;
+		pa |= token & ((1ul << hugepage_shift) - 1);
+	} else {
+		pa <<= PAGE_SHIFT;
+		pa |= token & (PAGE_SIZE - 1);
+	}
+
+	return pa;
 }
 
 /*
@@ -404,14 +417,12 @@
 	}
 
 	/* Isolate the PHB and send event */
-	eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
+	eeh_pe_mark_isolated(phb_pe);
 	eeh_serialize_unlock(flags);
 
-	pr_err("EEH: PHB#%x failure detected, location: %s\n",
+	pr_debug("EEH: PHB#%x failure detected, location: %s\n",
 		phb_pe->phb->global_number, eeh_pe_loc_get(phb_pe));
-	dump_stack();
 	eeh_send_failure_event(phb_pe);
-
 	return 1;
 out:
 	eeh_serialize_unlock(flags);
@@ -438,7 +449,7 @@
 	unsigned long flags;
 	struct device_node *dn;
 	struct pci_dev *dev;
-	struct eeh_pe *pe, *parent_pe, *phb_pe;
+	struct eeh_pe *pe, *parent_pe;
 	int rc = 0;
 	const char *location = NULL;
 
@@ -457,8 +468,7 @@
 	/* Access to IO BARs might get this far and still not want checking. */
 	if (!pe) {
 		eeh_stats.ignored_check++;
-		pr_debug("EEH: Ignored check for %s\n",
-			eeh_pci_name(dev));
+		eeh_edev_dbg(edev, "Ignored check\n");
 		return 0;
 	}
 
@@ -498,12 +508,11 @@
 			if (dn)
 				location = of_get_property(dn, "ibm,loc-code",
 						NULL);
-			printk(KERN_ERR "EEH: %d reads ignored for recovering device at "
-				"location=%s driver=%s pci addr=%s\n",
+			eeh_edev_err(edev, "%d reads ignored for recovering device at location=%s driver=%s\n",
 				pe->check_count,
 				location ? location : "unknown",
-				eeh_driver_name(dev), eeh_pci_name(dev));
-			printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n",
+				eeh_driver_name(dev));
+			eeh_edev_err(edev, "Might be infinite loop in %s driver\n",
 				eeh_driver_name(dev));
 			dump_stack();
 		}
@@ -563,20 +572,15 @@
 	 * with other functions on this device, and functions under
 	 * bridges.
 	 */
-	eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+	eeh_pe_mark_isolated(pe);
 	eeh_serialize_unlock(flags);
 
 	/* Most EEH events are due to device driver bugs.  Having
 	 * a stack trace will help the device-driver authors figure
 	 * out what happened.  So print that out.
 	 */
-	phb_pe = eeh_phb_pe_get(pe->phb);
-	pr_err("EEH: Frozen PHB#%x-PE#%x detected\n",
-	       pe->phb->global_number, pe->addr);
-	pr_err("EEH: PE location: %s, PHB location: %s\n",
-	       eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe));
-	dump_stack();
-
+	pr_debug("EEH: %s: Frozen PHB#%x-PE#%x detected\n",
+		__func__, pe->phb->global_number, pe->addr);
 	eeh_send_failure_event(pe);
 
 	return 1;
@@ -681,7 +685,7 @@
 
 	/* Check if the request is finished successfully */
 	if (active_flag) {
-		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+		rc = eeh_wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
 		if (rc < 0)
 			return rc;
 
@@ -694,7 +698,7 @@
 	return rc;
 }
 
-static void *eeh_disable_and_save_dev_state(struct eeh_dev *edev,
+static void eeh_disable_and_save_dev_state(struct eeh_dev *edev,
 					    void *userdata)
 {
 	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
@@ -705,7 +709,7 @@
 	 * state for the specified device
 	 */
 	if (!pdev || pdev == dev)
-		return NULL;
+		return;
 
 	/* Ensure we have D0 power state */
 	pci_set_power_state(pdev, PCI_D0);
@@ -718,18 +722,16 @@
 	 * interrupt from the device
 	 */
 	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
-
-	return NULL;
 }
 
-static void *eeh_restore_dev_state(struct eeh_dev *edev, void *userdata)
+static void eeh_restore_dev_state(struct eeh_dev *edev, void *userdata)
 {
 	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
 	struct pci_dev *dev = userdata;
 
 	if (!pdev)
-		return NULL;
+		return;
 
 	/* Apply customization from firmware */
 	if (pdn && eeh_ops->restore_config)
@@ -738,8 +740,6 @@
 	/* The caller should restore state for the specified device */
 	if (pdev != dev)
 		pci_restore_state(pdev);
-
-	return NULL;
 }
 
 int eeh_restore_vf_config(struct pci_dn *pdn)
@@ -823,14 +823,15 @@
 	switch (state) {
 	case pcie_deassert_reset:
 		eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
-		eeh_unfreeze_pe(pe, false);
+		eeh_unfreeze_pe(pe);
 		if (!(pe->type & EEH_PE_VF))
-			eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+			eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, true);
 		eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev);
-		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+		eeh_pe_state_clear(pe, EEH_PE_ISOLATED, true);
 		break;
 	case pcie_hot_reset:
-		eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED);
+		eeh_pe_mark_isolated(pe);
+		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, true);
 		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
 		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		if (!(pe->type & EEH_PE_VF))
@@ -838,7 +839,8 @@
 		eeh_ops->reset(pe, EEH_RESET_HOT);
 		break;
 	case pcie_warm_reset:
-		eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED);
+		eeh_pe_mark_isolated(pe);
+		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, true);
 		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
 		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		if (!(pe->type & EEH_PE_VF))
@@ -846,7 +848,7 @@
 		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
 		break;
 	default:
-		eeh_pe_state_clear(pe, EEH_PE_ISOLATED | EEH_PE_CFG_BLOCKED);
+		eeh_pe_state_clear(pe, EEH_PE_ISOLATED | EEH_PE_CFG_BLOCKED, true);
 		return -EINVAL;
 	};
 
@@ -863,7 +865,7 @@
  * the indicated device and its children so that the bunch of the
  * devices could be reset properly.
  */
-static void *eeh_set_dev_freset(struct eeh_dev *edev, void *flag)
+static void eeh_set_dev_freset(struct eeh_dev *edev, void *flag)
 {
 	struct pci_dev *dev;
 	unsigned int *freset = (unsigned int *)flag;
@@ -871,8 +873,24 @@
 	dev = eeh_dev_to_pci_dev(edev);
 	if (dev)
 		*freset |= dev->needs_freset;
+}
 
-	return NULL;
+static void eeh_pe_refreeze_passed(struct eeh_pe *root)
+{
+	struct eeh_pe *pe;
+	int state;
+
+	eeh_for_each_pe(root, pe) {
+		if (eeh_pe_passed(pe)) {
+			state = eeh_ops->get_state(pe, NULL);
+			if (state &
+			   (EEH_STATE_MMIO_ACTIVE | EEH_STATE_MMIO_ENABLED)) {
+				pr_info("EEH: Passed-through PE PHB#%x-PE#%x was thawed by reset, re-freezing for safety.\n",
+					pe->phb->global_number, pe->addr);
+				eeh_pe_set_option(pe, EEH_OPT_FREEZE_PE);
+			}
+		}
+	}
 }
 
 /**
@@ -887,12 +905,12 @@
  *
  * This function will attempt to reset a PE three times before failing.
  */
-int eeh_pe_reset_full(struct eeh_pe *pe)
+int eeh_pe_reset_full(struct eeh_pe *pe, bool include_passed)
 {
 	int reset_state = (EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
 	int type = EEH_RESET_HOT;
 	unsigned int freset = 0;
-	int i, state, ret;
+	int i, state = 0, ret;
 
 	/*
 	 * Determine the type of reset to perform - hot or fundamental.
@@ -909,33 +927,42 @@
 
 	/* Make three attempts at resetting the bus */
 	for (i = 0; i < 3; i++) {
-		ret = eeh_pe_reset(pe, type);
-		if (ret)
-			break;
-
-		ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE);
-		if (ret)
-			break;
+		ret = eeh_pe_reset(pe, type, include_passed);
+		if (!ret)
+			ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE,
+					   include_passed);
+		if (ret) {
+			ret = -EIO;
+			pr_warn("EEH: Failure %d resetting PHB#%x-PE#%x (attempt %d)\n\n",
+				state, pe->phb->global_number, pe->addr, i + 1);
+			continue;
+		}
+		if (i)
+			pr_warn("EEH: PHB#%x-PE#%x: Successful reset (attempt %d)\n",
+				pe->phb->global_number, pe->addr, i + 1);
 
 		/* Wait until the PE is in a functioning state */
-		state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if (eeh_state_active(state))
-			break;
-
+		state = eeh_wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
 		if (state < 0) {
-			pr_warn("%s: Unrecoverable slot failure on PHB#%x-PE#%x",
-				__func__, pe->phb->global_number, pe->addr);
+			pr_warn("EEH: Unrecoverable slot failure on PHB#%x-PE#%x",
+				pe->phb->global_number, pe->addr);
 			ret = -ENOTRECOVERABLE;
 			break;
 		}
-
-		/* Set error in case this is our last attempt */
-		ret = -EIO;
-		pr_warn("%s: Failure %d resetting PHB#%x-PE#%x\n (%d)\n",
-			__func__, state, pe->phb->global_number, pe->addr, (i + 1));
+		if (eeh_state_active(state))
+			break;
+		else
+			pr_warn("EEH: PHB#%x-PE#%x: Slot inactive after reset: 0x%x (attempt %d)\n",
+				pe->phb->global_number, pe->addr, state, i + 1);
 	}
 
-	eeh_pe_state_clear(pe, reset_state);
+	/* Resetting the PE may have unfrozen child PEs. If those PEs have been
+	 * (potentially) passed through to a guest, re-freeze them:
+	 */
+	if (!include_passed)
+		eeh_pe_refreeze_passed(pe);
+
+	eeh_pe_state_clear(pe, reset_state, true);
 	return ret;
 }
 
@@ -1031,18 +1058,6 @@
 	.notifier_call = eeh_reboot_notifier,
 };
 
-void eeh_probe_devices(void)
-{
-	struct pci_controller *hose, *tmp;
-	struct pci_dn *pdn;
-
-	/* Enable EEH for all adapters */
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
-		pdn = hose->pci_data;
-		traverse_pci_dn(pdn, eeh_ops->probe, NULL);
-	}
-}
-
 /**
  * eeh_init - EEH initialization
  *
@@ -1083,19 +1098,10 @@
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
 		eeh_dev_phb_init_dynamic(hose);
 
+	eeh_addr_cache_init();
+
 	/* Initialize EEH event */
-	ret = eeh_event_init();
-	if (ret)
-		return ret;
-
-	eeh_probe_devices();
-
-	if (eeh_enabled())
-		pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
-	else if (!eeh_has_flag(EEH_POSTPONED_PROBE))
-		pr_info("EEH: No capable adapters found\n");
-
-	return ret;
+	return eeh_event_init();
 }
 
 core_initcall_sync(eeh_init);
@@ -1164,15 +1170,14 @@
 	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 
-	if (!dev || !eeh_enabled())
+	if (!dev)
 		return;
 
-	pr_debug("EEH: Adding device %s\n", pci_name(dev));
-
 	pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
 	edev = pdn_to_eeh_dev(pdn);
+	eeh_edev_dbg(edev, "Adding device\n");
 	if (edev->pdev == dev) {
-		pr_debug("EEH: Already referenced !\n");
+		eeh_edev_dbg(edev, "Device already referenced!\n");
 		return;
 	}
 
@@ -1220,6 +1225,8 @@
 {
 	struct pci_dev *dev;
 
+	if (eeh_has_flag(EEH_FORCE_DISABLED))
+		return;
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		eeh_add_device_late(dev);
 		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
@@ -1273,10 +1280,10 @@
 	edev = pci_dev_to_eeh_dev(dev);
 
 	/* Unregister the device with the EEH/PCI address search system */
-	pr_debug("EEH: Removing device %s\n", pci_name(dev));
+	dev_dbg(&dev->dev, "EEH: Removing device\n");
 
 	if (!edev || !edev->pdev || !edev->pe) {
-		pr_debug("EEH: Not referenced !\n");
+		dev_dbg(&dev->dev, "EEH: Device not referenced!\n");
 		return;
 	}
 
@@ -1314,7 +1321,7 @@
 	edev->mode &= ~EEH_DEV_SYSFS;
 }
 
-int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state)
+int eeh_unfreeze_pe(struct eeh_pe *pe)
 {
 	int ret;
 
@@ -1332,10 +1339,6 @@
 		return ret;
 	}
 
-	/* Clear software isolated state */
-	if (sw_state && (pe->state & EEH_PE_ISOLATED))
-		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
-
 	return ret;
 }
 
@@ -1387,7 +1390,10 @@
 		}
 	}
 
-	return eeh_unfreeze_pe(pe, true);
+	ret = eeh_unfreeze_pe(pe);
+	if (!ret)
+		eeh_pe_state_clear(pe, EEH_PE_ISOLATED, true);
+	return ret;
 }
 
 /**
@@ -1477,7 +1483,7 @@
 	if (!dev)
 		return 0;
 
-	if (dev->iommu_group) {
+	if (device_iommu_mapped(dev)) {
 		*ppdev = pdev;
 		return 1;
 	}
@@ -1617,13 +1623,12 @@
 }
 EXPORT_SYMBOL_GPL(eeh_pe_get_state);
 
-static int eeh_pe_reenable_devices(struct eeh_pe *pe)
+static int eeh_pe_reenable_devices(struct eeh_pe *pe, bool include_passed)
 {
 	struct eeh_dev *edev, *tmp;
 	struct pci_dev *pdev;
 	int ret = 0;
 
-	/* Restore config space */
 	eeh_pe_restore_bars(pe);
 
 	/*
@@ -1644,7 +1649,14 @@
 	}
 
 	/* The PE is still in frozen state */
-	return eeh_unfreeze_pe(pe, true);
+	if (include_passed || !eeh_pe_passed(pe)) {
+		ret = eeh_unfreeze_pe(pe);
+	} else
+		pr_info("EEH: Note: Leaving passthrough PHB#%x-PE#%x frozen.\n",
+			pe->phb->global_number, pe->addr);
+	if (!ret)
+		eeh_pe_state_clear(pe, EEH_PE_ISOLATED, include_passed);
+	return ret;
 }
 
 
@@ -1657,7 +1669,7 @@
  * indicated type, either fundamental reset or hot reset.
  * PE reset is the most important part for error recovery.
  */
-int eeh_pe_reset(struct eeh_pe *pe, int option)
+int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed)
 {
 	int ret = 0;
 
@@ -1671,11 +1683,11 @@
 	switch (option) {
 	case EEH_RESET_DEACTIVATE:
 		ret = eeh_ops->reset(pe, option);
-		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, include_passed);
 		if (ret)
 			break;
 
-		ret = eeh_pe_reenable_devices(pe);
+		ret = eeh_pe_reenable_devices(pe, include_passed);
 		break;
 	case EEH_RESET_HOT:
 	case EEH_RESET_FUNDAMENTAL:
@@ -1801,22 +1813,256 @@
 	return 0;
 }
 
-static int eeh_freeze_dbgfs_set(void *data, u64 val)
+DEFINE_DEBUGFS_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get,
+			 eeh_enable_dbgfs_set, "0x%llx\n");
+
+static ssize_t eeh_force_recover_write(struct file *filp,
+				const char __user *user_buf,
+				size_t count, loff_t *ppos)
 {
-	eeh_max_freezes = val;
+	struct pci_controller *hose;
+	uint32_t phbid, pe_no;
+	struct eeh_pe *pe;
+	char buf[20];
+	int ret;
+
+	ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
+	if (!ret)
+		return -EFAULT;
+
+	/*
+	 * When PE is NULL the event is a "special" event. Rather than
+	 * recovering a specific PE it forces the EEH core to scan for failed
+	 * PHBs and recovers each. This needs to be done before any device
+	 * recoveries can occur.
+	 */
+	if (!strncmp(buf, "hwcheck", 7)) {
+		__eeh_send_failure_event(NULL);
+		return count;
+	}
+
+	ret = sscanf(buf, "%x:%x", &phbid, &pe_no);
+	if (ret != 2)
+		return -EINVAL;
+
+	hose = pci_find_controller_for_domain(phbid);
+	if (!hose)
+		return -ENODEV;
+
+	/* Retrieve PE */
+	pe = eeh_pe_get(hose, pe_no, 0);
+	if (!pe)
+		return -ENODEV;
+
+	/*
+	 * We don't do any state checking here since the detection
+	 * process is async to the recovery process. The recovery
+	 * thread *should* not break even if we schedule a recovery
+	 * from an odd state (e.g. PE removed, or recovery of a
+	 * non-isolated PE)
+	 */
+	__eeh_send_failure_event(pe);
+
+	return ret < 0 ? ret : count;
+}
+
+static const struct file_operations eeh_force_recover_fops = {
+	.open	= simple_open,
+	.llseek	= no_llseek,
+	.write	= eeh_force_recover_write,
+};
+
+static ssize_t eeh_debugfs_dev_usage(struct file *filp,
+				char __user *user_buf,
+				size_t count, loff_t *ppos)
+{
+	static const char usage[] = "input format: <domain>:<bus>:<dev>.<fn>\n";
+
+	return simple_read_from_buffer(user_buf, count, ppos,
+				       usage, sizeof(usage) - 1);
+}
+
+static ssize_t eeh_dev_check_write(struct file *filp,
+				const char __user *user_buf,
+				size_t count, loff_t *ppos)
+{
+	uint32_t domain, bus, dev, fn;
+	struct pci_dev *pdev;
+	struct eeh_dev *edev;
+	char buf[20];
+	int ret;
+
+	memset(buf, 0, sizeof(buf));
+	ret = simple_write_to_buffer(buf, sizeof(buf)-1, ppos, user_buf, count);
+	if (!ret)
+		return -EFAULT;
+
+	ret = sscanf(buf, "%x:%x:%x.%x", &domain, &bus, &dev, &fn);
+	if (ret != 4) {
+		pr_err("%s: expected 4 args, got %d\n", __func__, ret);
+		return -EINVAL;
+	}
+
+	pdev = pci_get_domain_bus_and_slot(domain, bus, (dev << 3) | fn);
+	if (!pdev)
+		return -ENODEV;
+
+	edev = pci_dev_to_eeh_dev(pdev);
+	if (!edev) {
+		pci_err(pdev, "No eeh_dev for this device!\n");
+		pci_dev_put(pdev);
+		return -ENODEV;
+	}
+
+	ret = eeh_dev_check_failure(edev);
+	pci_info(pdev, "eeh_dev_check_failure(%04x:%02x:%02x.%01x) = %d\n",
+			domain, bus, dev, fn, ret);
+
+	pci_dev_put(pdev);
+
+	return count;
+}
+
+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 asyncronously 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 int eeh_freeze_dbgfs_get(void *data, u64 *val)
+static ssize_t eeh_dev_break_write(struct file *filp,
+				const char __user *user_buf,
+				size_t count, loff_t *ppos)
 {
-	*val = eeh_max_freezes;
-	return 0;
+	uint32_t domain, bus, dev, fn;
+	struct pci_dev *pdev;
+	char buf[20];
+	int ret;
+
+	memset(buf, 0, sizeof(buf));
+	ret = simple_write_to_buffer(buf, sizeof(buf)-1, ppos, user_buf, count);
+	if (!ret)
+		return -EFAULT;
+
+	ret = sscanf(buf, "%x:%x:%x.%x", &domain, &bus, &dev, &fn);
+	if (ret != 4) {
+		pr_err("%s: expected 4 args, got %d\n", __func__, ret);
+		return -EINVAL;
+	}
+
+	pdev = pci_get_domain_bus_and_slot(domain, bus, (dev << 3) | fn);
+	if (!pdev)
+		return -ENODEV;
+
+	ret = eeh_debugfs_break_device(pdev);
+	pci_dev_put(pdev);
+
+	if (ret < 0)
+		return ret;
+
+	return count;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get,
-			eeh_enable_dbgfs_set, "0x%llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(eeh_freeze_dbgfs_ops, eeh_freeze_dbgfs_get,
-			eeh_freeze_dbgfs_set, "0x%llx\n");
+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,
+};
+
 #endif
 
 static int __init eeh_init_proc(void)
@@ -1824,12 +2070,24 @@
 	if (machine_is(pseries) || machine_is(powernv)) {
 		proc_create_single("powerpc/eeh", 0, NULL, proc_eeh_show);
 #ifdef CONFIG_DEBUG_FS
-		debugfs_create_file("eeh_enable", 0600,
-                                    powerpc_debugfs_root, NULL,
-                                    &eeh_enable_dbgfs_ops);
-		debugfs_create_file("eeh_max_freezes", 0600,
-				    powerpc_debugfs_root, NULL,
-				    &eeh_freeze_dbgfs_ops);
+		debugfs_create_file_unsafe("eeh_enable", 0600,
+					   powerpc_debugfs_root, NULL,
+					   &eeh_enable_dbgfs_ops);
+		debugfs_create_u32("eeh_max_freezes", 0600,
+				powerpc_debugfs_root, &eeh_max_freezes);
+		debugfs_create_bool("eeh_disable_recovery", 0600,
+				powerpc_debugfs_root,
+				&eeh_debugfs_no_recover);
+		debugfs_create_file_unsafe("eeh_dev_check", 0600,
+				powerpc_debugfs_root, NULL,
+				&eeh_dev_check_fops);
+		debugfs_create_file_unsafe("eeh_dev_break", 0600,
+				powerpc_debugfs_root, NULL,
+				&eeh_dev_break_fops);
+		debugfs_create_file_unsafe("eeh_force_recover", 0600,
+				powerpc_debugfs_root, NULL,
+				&eeh_force_recover_fops);
+		eeh_cache_debugfs_init();
 #endif
 	}
 
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index 201943d..cf11277 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PCI address cache; allows the lookup of PCI devices based on I/O address
  *
  * Copyright IBM Corporation 2004
  * Copyright Linas Vepstas <linas@austin.ibm.com> 2004
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/list.h>
@@ -26,10 +13,13 @@
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
 #include <asm/pci-bridge.h>
+#include <asm/debugfs.h>
 #include <asm/ppc-pci.h>
 
 
 /**
+ * DOC: Overview
+ *
  * The pci address cache subsystem.  This subsystem places
  * PCI device address resources into a red-black tree, sorted
  * according to the address range, so that given only an i/o
@@ -46,6 +36,7 @@
  * than any hash algo I could think of for this problem, even
  * with the penalty of slow pointer chases for d-cache misses).
  */
+
 struct pci_io_addr_range {
 	struct rb_node rb_node;
 	resource_size_t addr_lo;
@@ -113,7 +104,7 @@
 	while (n) {
 		struct pci_io_addr_range *piar;
 		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
-		pr_debug("PCI: %s addr range %d [%pap-%pap]: %s\n",
+		pr_info("PCI: %s addr range %d [%pap-%pap]: %s\n",
 		       (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt,
 		       &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev));
 		cnt++;
@@ -157,10 +148,8 @@
 	piar->pcidev = dev;
 	piar->flags = flags;
 
-#ifdef DEBUG
-	pr_debug("PIAR: insert range=[%pap:%pap] dev=%s\n",
-		 &alo, &ahi, pci_name(dev));
-#endif
+	eeh_edev_dbg(piar->edev, "PIAR: insert range=[%pap:%pap]\n",
+		 &alo, &ahi);
 
 	rb_link_node(&piar->rb_node, parent, p);
 	rb_insert_color(&piar->rb_node, &pci_io_addr_cache_root.rb_root);
@@ -240,6 +229,8 @@
 		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
 
 		if (piar->pcidev == dev) {
+			eeh_edev_dbg(piar->edev, "PIAR: remove range=[%pap:%pap]\n",
+				 &piar->addr_lo, &piar->addr_hi);
 			rb_erase(n, &pci_io_addr_cache_root.rb_root);
 			kfree(piar);
 			goto restart;
@@ -267,40 +258,38 @@
 }
 
 /**
- * eeh_addr_cache_build - Build a cache of I/O addresses
+ * eeh_addr_cache_init - Initialize a cache of I/O addresses
  *
- * Build a cache of pci i/o addresses.  This cache will be used to
+ * Initialize a cache of pci i/o addresses.  This cache will be used to
  * find the pci device that corresponds to a given address.
- * This routine scans all pci busses to build the cache.
- * Must be run late in boot process, after the pci controllers
- * have been scanned for devices (after all device resources are known).
  */
-void eeh_addr_cache_build(void)
+void eeh_addr_cache_init(void)
 {
-	struct pci_dn *pdn;
-	struct eeh_dev *edev;
-	struct pci_dev *dev = NULL;
-
 	spin_lock_init(&pci_io_addr_cache_root.piar_lock);
+}
 
-	for_each_pci_dev(dev) {
-		pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
-		if (!pdn)
-			continue;
+static int eeh_addr_cache_show(struct seq_file *s, void *v)
+{
+	struct pci_io_addr_range *piar;
+	struct rb_node *n;
 
-		edev = pdn_to_eeh_dev(pdn);
-		if (!edev)
-			continue;
+	spin_lock(&pci_io_addr_cache_root.piar_lock);
+	for (n = rb_first(&pci_io_addr_cache_root.rb_root); n; n = rb_next(n)) {
+		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
 
-		dev->dev.archdata.edev = edev;
-		edev->pdev = dev;
-
-		eeh_addr_cache_insert_dev(dev);
-		eeh_sysfs_add_device(dev);
+		seq_printf(s, "%s addr range [%pap-%pap]: %s\n",
+		       (piar->flags & IORESOURCE_IO) ? "i/o" : "mem",
+		       &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev));
 	}
+	spin_unlock(&pci_io_addr_cache_root.piar_lock);
 
-#ifdef DEBUG
-	/* Verify tree built up above, echo back the list of addrs. */
-	eeh_addr_cache_print(&pci_io_addr_cache_root);
-#endif
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(eeh_addr_cache);
+
+void eeh_cache_debugfs_init(void)
+{
+	debugfs_create_file_unsafe("eeh_address_cache", 0400,
+			powerpc_debugfs_root, NULL,
+			&eeh_addr_cache_fops);
 }
diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c
index a34e691..7370185 100644
--- a/arch/powerpc/kernel/eeh_dev.c
+++ b/arch/powerpc/kernel/eeh_dev.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * The file intends to implement dynamic creation of EEH device, which will
  * be bound with OF node and PCI device simutaneously. The EEH devices would
@@ -15,20 +16,6 @@
  *    PHB is newly inserted, we also need create EEH devices accordingly.
  *
  * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/export.h>
@@ -60,8 +47,8 @@
 	/* Associate EEH device with OF node */
 	pdn->edev = edev;
 	edev->pdn = pdn;
-	INIT_LIST_HEAD(&edev->list);
-	INIT_LIST_HEAD(&edev->rmv_list);
+	edev->bdfn = (pdn->busno << 8) | pdn->devfn;
+	edev->controller = pdn->phb;
 
 	return edev;
 }
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 67619b4..d9279d0 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -27,6 +27,7 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pci_hotplug.h>
 #include <asm/eeh.h>
 #include <asm/eeh_event.h>
 #include <asm/ppc-pci.h>
@@ -35,8 +36,8 @@
 #include <asm/rtas.h>
 
 struct eeh_rmv_data {
-	struct list_head edev_list;
-	int removed;
+	struct list_head removed_vf_list;
+	int removed_dev_count;
 };
 
 static int eeh_result_priority(enum pci_ers_result result)
@@ -60,7 +61,7 @@
 	}
 };
 
-const char *pci_ers_result_name(enum pci_ers_result result)
+static const char *pci_ers_result_name(enum pci_ers_result result)
 {
 	switch (result) {
 	case PCI_ERS_RESULT_NONE:
@@ -81,23 +82,6 @@
 	}
 };
 
-static __printf(2, 3) void eeh_edev_info(const struct eeh_dev *edev,
-					 const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	printk(KERN_INFO "EEH: PE#%x (PCI %s): %pV\n", edev->pe_config_addr,
-	       edev->pdev ? dev_name(&edev->pdev->dev) : "none", &vaf);
-
-	va_end(args);
-}
-
 static enum pci_ers_result pci_ers_merge_result(enum pci_ers_result old,
 						enum pci_ers_result new)
 {
@@ -113,8 +97,16 @@
 
 static bool eeh_edev_actionable(struct eeh_dev *edev)
 {
-	return (edev->pdev && !eeh_dev_removed(edev) &&
-		!eeh_pe_passed(edev->pe));
+	if (!edev->pdev)
+		return false;
+	if (edev->pdev->error_state == pci_channel_io_perm_failure)
+		return false;
+	if (eeh_dev_removed(edev))
+		return false;
+	if (eeh_pe_passed(edev->pe))
+		return false;
+
+	return true;
 }
 
 /**
@@ -214,12 +206,12 @@
 	}
 }
 
-static void *eeh_dev_save_state(struct eeh_dev *edev, void *userdata)
+static void eeh_dev_save_state(struct eeh_dev *edev, void *userdata)
 {
 	struct pci_dev *pdev;
 
 	if (!edev)
-		return NULL;
+		return;
 
 	/*
 	 * We cannot access the config space on some adapters.
@@ -229,14 +221,13 @@
 	 * device is created.
 	 */
 	if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED))
-		return NULL;
+		return;
 
 	pdev = eeh_dev_to_pci_dev(edev);
 	if (!pdev)
-		return NULL;
+		return;
 
 	pci_save_state(pdev);
-	return NULL;
 }
 
 static void eeh_set_channel_state(struct eeh_pe *root, enum pci_channel_state s)
@@ -274,16 +265,27 @@
 }
 
 typedef enum pci_ers_result (*eeh_report_fn)(struct eeh_dev *,
+					     struct pci_dev *,
 					     struct pci_driver *);
 static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn,
 			       enum pci_ers_result *result)
 {
+	struct pci_dev *pdev;
 	struct pci_driver *driver;
 	enum pci_ers_result new_result;
 
-	device_lock(&edev->pdev->dev);
+	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");
+		return;
+	}
+	device_lock(&pdev->dev);
 	if (eeh_edev_actionable(edev)) {
-		driver = eeh_pcid_get(edev->pdev);
+		driver = eeh_pcid_get(pdev);
 
 		if (!driver)
 			eeh_edev_info(edev, "no driver");
@@ -292,7 +294,7 @@
 		else if (edev->mode & EEH_DEV_NO_HANDLER)
 			eeh_edev_info(edev, "driver bound too late");
 		else {
-			new_result = fn(edev, driver);
+			new_result = fn(edev, pdev, driver);
 			eeh_edev_info(edev, "%s driver reports: '%s'",
 				      driver->name,
 				      pci_ers_result_name(new_result));
@@ -301,12 +303,15 @@
 							       new_result);
 		}
 		if (driver)
-			eeh_pcid_put(edev->pdev);
+			eeh_pcid_put(pdev);
 	} else {
-		eeh_edev_info(edev, "not actionable (%d,%d,%d)", !!edev->pdev,
+		eeh_edev_info(edev, "not actionable (%d,%d,%d)", !!pdev,
 			      !eeh_dev_removed(edev), !eeh_pe_passed(edev->pe));
 	}
-	device_unlock(&edev->pdev->dev);
+	device_unlock(&pdev->dev);
+	if (edev->pdev != pdev)
+		eeh_edev_warn(edev, "Device changed during processing!\n");
+	put_device(&pdev->dev);
 }
 
 static void eeh_pe_report(const char *name, struct eeh_pe *root,
@@ -333,20 +338,20 @@
  * Report an EEH error to each device driver.
  */
 static enum pci_ers_result eeh_report_error(struct eeh_dev *edev,
+					    struct pci_dev *pdev,
 					    struct pci_driver *driver)
 {
 	enum pci_ers_result rc;
-	struct pci_dev *dev = edev->pdev;
 
 	if (!driver->err_handler->error_detected)
 		return PCI_ERS_RESULT_NONE;
 
 	eeh_edev_info(edev, "Invoking %s->error_detected(IO frozen)",
 		      driver->name);
-	rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
+	rc = driver->err_handler->error_detected(pdev, pci_channel_io_frozen);
 
 	edev->in_error = true;
-	pci_uevent_ers(dev, PCI_ERS_RESULT_NONE);
+	pci_uevent_ers(pdev, PCI_ERS_RESULT_NONE);
 	return rc;
 }
 
@@ -359,12 +364,13 @@
  * are now enabled.
  */
 static enum pci_ers_result eeh_report_mmio_enabled(struct eeh_dev *edev,
+						   struct pci_dev *pdev,
 						   struct pci_driver *driver)
 {
 	if (!driver->err_handler->mmio_enabled)
 		return PCI_ERS_RESULT_NONE;
 	eeh_edev_info(edev, "Invoking %s->mmio_enabled()", driver->name);
-	return driver->err_handler->mmio_enabled(edev->pdev);
+	return driver->err_handler->mmio_enabled(pdev);
 }
 
 /**
@@ -378,20 +384,21 @@
  * driver can work again while the device is recovered.
  */
 static enum pci_ers_result eeh_report_reset(struct eeh_dev *edev,
+					    struct pci_dev *pdev,
 					    struct pci_driver *driver)
 {
 	if (!driver->err_handler->slot_reset || !edev->in_error)
 		return PCI_ERS_RESULT_NONE;
 	eeh_edev_info(edev, "Invoking %s->slot_reset()", driver->name);
-	return driver->err_handler->slot_reset(edev->pdev);
+	return driver->err_handler->slot_reset(pdev);
 }
 
-static void *eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
+static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
 {
 	struct pci_dev *pdev;
 
 	if (!edev)
-		return NULL;
+		return;
 
 	/*
 	 * The content in the config space isn't saved because
@@ -400,18 +407,17 @@
 	 * EEH device is created.
 	 */
 	if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) {
-		if (list_is_last(&edev->list, &edev->pe->edevs))
+		if (list_is_last(&edev->entry, &edev->pe->edevs))
 			eeh_pe_restore_bars(edev->pe);
 
-		return NULL;
+		return;
 	}
 
 	pdev = eeh_dev_to_pci_dev(edev);
 	if (!pdev)
-		return NULL;
+		return;
 
 	pci_restore_state(pdev);
-	return NULL;
 }
 
 /**
@@ -424,13 +430,14 @@
  * to make the recovered device work again.
  */
 static enum pci_ers_result eeh_report_resume(struct eeh_dev *edev,
+					     struct pci_dev *pdev,
 					     struct pci_driver *driver)
 {
 	if (!driver->err_handler->resume || !edev->in_error)
 		return PCI_ERS_RESULT_NONE;
 
 	eeh_edev_info(edev, "Invoking %s->resume()", driver->name);
-	driver->err_handler->resume(edev->pdev);
+	driver->err_handler->resume(pdev);
 
 	pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_RECOVERED);
 #ifdef CONFIG_PCI_IOV
@@ -449,6 +456,7 @@
  * dead, and that no further recovery attempts will be made on it.
  */
 static enum pci_ers_result eeh_report_failure(struct eeh_dev *edev,
+					      struct pci_dev *pdev,
 					      struct pci_driver *driver)
 {
 	enum pci_ers_result rc;
@@ -458,24 +466,20 @@
 
 	eeh_edev_info(edev, "Invoking %s->error_detected(permanent failure)",
 		      driver->name);
-	rc = driver->err_handler->error_detected(edev->pdev,
+	rc = driver->err_handler->error_detected(pdev,
 						 pci_channel_io_perm_failure);
 
-	pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_DISCONNECT);
+	pci_uevent_ers(pdev, PCI_ERS_RESULT_DISCONNECT);
 	return rc;
 }
 
-static void *eeh_add_virt_device(void *data, void *userdata)
+static void *eeh_add_virt_device(struct eeh_dev *edev)
 {
 	struct pci_driver *driver;
-	struct eeh_dev *edev = (struct eeh_dev *)data;
 	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
-	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
 	if (!(edev->physfn)) {
-		pr_warn("%s: EEH dev %04x:%02x:%02x.%01x not for VF\n",
-			__func__, pdn->phb->global_number, pdn->busno,
-			PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+		eeh_edev_warn(edev, "Not for VF\n");
 		return NULL;
 	}
 
@@ -489,17 +493,16 @@
 	}
 
 #ifdef CONFIG_PCI_IOV
-	pci_iov_add_virtfn(edev->physfn, pdn->vf_index);
+	pci_iov_add_virtfn(edev->physfn, eeh_dev_to_pdn(edev)->vf_index);
 #endif
 	return NULL;
 }
 
-static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata)
+static void eeh_rmv_device(struct eeh_dev *edev, void *userdata)
 {
 	struct pci_driver *driver;
 	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
 	struct eeh_rmv_data *rmv_data = (struct eeh_rmv_data *)userdata;
-	int *removed = rmv_data ? &rmv_data->removed : NULL;
 
 	/*
 	 * Actually, we should remove the PCI bridges as well.
@@ -508,41 +511,29 @@
 	 * support EEH. So we just care about PCI devices for
 	 * simplicity here.
 	 */
-	if (!dev || (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE))
-		return NULL;
+	if (!eeh_edev_actionable(edev) ||
+	    (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE))
+		return;
 
-	/*
-	 * We rely on count-based pcibios_release_device() to
-	 * detach permanently offlined PEs. Unfortunately, that's
-	 * not reliable enough. We might have the permanently
-	 * offlined PEs attached, but we needn't take care of
-	 * them and their child devices.
-	 */
-	if (eeh_dev_removed(edev))
-		return NULL;
-
-	if (removed) {
-		if (eeh_pe_passed(edev->pe))
-			return NULL;
+	if (rmv_data) {
 		driver = eeh_pcid_get(dev);
 		if (driver) {
 			if (driver->err_handler &&
 			    driver->err_handler->error_detected &&
 			    driver->err_handler->slot_reset) {
 				eeh_pcid_put(dev);
-				return NULL;
+				return;
 			}
 			eeh_pcid_put(dev);
 		}
 	}
 
 	/* Remove it from PCI subsystem */
-	pr_debug("EEH: Removing %s without EEH sensitive driver\n",
-		 pci_name(dev));
-	edev->bus = dev->bus;
+	pr_info("EEH: Removing %s without EEH sensitive driver\n",
+		pci_name(dev));
 	edev->mode |= EEH_DEV_DISCONNECTED;
-	if (removed)
-		(*removed)++;
+	if (rmv_data)
+		rmv_data->removed_dev_count++;
 
 	if (edev->physfn) {
 #ifdef CONFIG_PCI_IOV
@@ -558,14 +549,12 @@
 		pdn->pe_number = IODA_INVALID_PE;
 #endif
 		if (rmv_data)
-			list_add(&edev->rmv_list, &rmv_data->edev_list);
+			list_add(&edev->rmv_entry, &rmv_data->removed_vf_list);
 	} else {
 		pci_lock_rescan_remove();
 		pci_stop_and_remove_bus_device(dev);
 		pci_unlock_rescan_remove();
 	}
-
-	return NULL;
 }
 
 static void *eeh_pe_detach_dev(struct eeh_pe *pe, void *userdata)
@@ -590,34 +579,22 @@
  * PE reset (for 3 times), we try to clear the frozen state
  * for 3 times as well.
  */
-static void *__eeh_clear_pe_frozen_state(struct eeh_pe *pe, void *flag)
+static int eeh_clear_pe_frozen_state(struct eeh_pe *root, bool include_passed)
 {
-	bool clear_sw_state = *(bool *)flag;
-	int i, rc = 1;
+	struct eeh_pe *pe;
+	int i;
 
-	for (i = 0; rc && i < 3; i++)
-		rc = eeh_unfreeze_pe(pe, clear_sw_state);
-
-	/* Stop immediately on any errors */
-	if (rc) {
-		pr_warn("%s: Failure %d unfreezing PHB#%x-PE#%x\n",
-			__func__, rc, pe->phb->global_number, pe->addr);
-		return (void *)pe;
+	eeh_for_each_pe(root, pe) {
+		if (include_passed || !eeh_pe_passed(pe)) {
+			for (i = 0; i < 3; i++)
+				if (!eeh_unfreeze_pe(pe))
+					break;
+			if (i >= 3)
+				return -EIO;
+		}
 	}
-
-	return NULL;
-}
-
-static int eeh_clear_pe_frozen_state(struct eeh_pe *pe,
-				     bool clear_sw_state)
-{
-	void *rc;
-
-	rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, &clear_sw_state);
-	if (!rc)
-		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
-
-	return rc ? -EIO : 0;
+	eeh_pe_state_clear(root, EEH_PE_ISOLATED, include_passed);
+	return 0;
 }
 
 int eeh_pe_reset_and_recover(struct eeh_pe *pe)
@@ -635,16 +612,16 @@
 	eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL);
 
 	/* Issue reset */
-	ret = eeh_pe_reset_full(pe);
+	ret = eeh_pe_reset_full(pe, true);
 	if (ret) {
-		eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
 		return ret;
 	}
 
 	/* Unfreeze the PE */
 	ret = eeh_clear_pe_frozen_state(pe, true);
 	if (ret) {
-		eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
 		return ret;
 	}
 
@@ -652,7 +629,7 @@
 	eeh_pe_dev_traverse(pe, eeh_dev_restore_state, NULL);
 
 	/* Clear recovery mode */
-	eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+	eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
 
 	return 0;
 }
@@ -675,6 +652,11 @@
 	time64_t tstamp;
 	int cnt, rc;
 	struct eeh_dev *edev;
+	struct eeh_pe *tmp_pe;
+	bool any_passed = false;
+
+	eeh_for_each_pe(pe, tmp_pe)
+		any_passed |= eeh_pe_passed(tmp_pe);
 
 	/* pcibios will clear the counter; save the value */
 	cnt = pe->freeze_count;
@@ -687,7 +669,7 @@
 	 * into pci_hp_add_devices().
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_KEEP);
-	if (driver_eeh_aware || (pe->type & EEH_PE_VF)) {
+	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();
@@ -704,7 +686,7 @@
 	 * config accesses. So we prefer to block them. However, controlled
 	 * PCI config accesses initiated from EEH itself are allowed.
 	 */
-	rc = eeh_pe_reset_full(pe);
+	rc = eeh_pe_reset_full(pe, false);
 	if (rc)
 		return rc;
 
@@ -727,7 +709,7 @@
 	 * the device up before the scripts have taken it down,
 	 * potentially weird things happen.
 	 */
-	if (!driver_eeh_aware || rmv_data->removed) {
+	if (!driver_eeh_aware || rmv_data->removed_dev_count) {
 		pr_info("EEH: Sleep 5s ahead of %s hotplug\n",
 			(driver_eeh_aware ? "partial" : "complete"));
 		ssleep(5);
@@ -737,17 +719,17 @@
 		 * PE. We should disconnect it so the binding can be
 		 * rebuilt when adding PCI devices.
 		 */
-		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
+		edev = list_first_entry(&pe->edevs, struct eeh_dev, entry);
 		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
 		if (pe->type & EEH_PE_VF) {
-			eeh_add_virt_device(edev, NULL);
+			eeh_add_virt_device(edev);
 		} else {
 			if (!driver_eeh_aware)
-				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
+				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
 			pci_hp_add_devices(bus);
 		}
 	}
-	eeh_pe_state_clear(pe, EEH_PE_KEEP);
+	eeh_pe_state_clear(pe, EEH_PE_KEEP, true);
 
 	pe->tstamp = tstamp;
 	pe->freeze_count = cnt;
@@ -761,6 +743,99 @@
  */
 #define MAX_WAIT_FOR_RECOVERY 300
 
+
+/* Walks the PE tree after processing an event to remove any stale PEs.
+ *
+ * NB: This needs to be recursive to ensure the leaf PEs get removed
+ * before their parents do. Although this is possible to do recursively
+ * we don't since this is easier to read and we need to garantee
+ * the leaf nodes will be handled first.
+ */
+static void eeh_pe_cleanup(struct eeh_pe *pe)
+{
+	struct eeh_pe *child_pe, *tmp;
+
+	list_for_each_entry_safe(child_pe, tmp, &pe->child_list, child)
+		eeh_pe_cleanup(child_pe);
+
+	if (pe->state & EEH_PE_KEEP)
+		return;
+
+	if (!(pe->state & EEH_PE_INVALID))
+		return;
+
+	if (list_empty(&pe->edevs) && list_empty(&pe->child_list)) {
+		list_del(&pe->child);
+		kfree(pe);
+	}
+}
+
+/**
+ * eeh_check_slot_presence - Check if a device is still present in a slot
+ * @pdev: pci_dev to check
+ *
+ * This function may return a false positive if we can't determine the slot's
+ * presence state. This might happen for for PCIe slots if the PE containing
+ * the upstream bridge is also frozen, or the bridge is part of the same PE
+ * as the device.
+ *
+ * This shouldn't happen often, but you might see it if you hotplug a PCIe
+ * switch.
+ */
+static bool eeh_slot_presence_check(struct pci_dev *pdev)
+{
+	const struct hotplug_slot_ops *ops;
+	struct pci_slot *slot;
+	u8 state;
+	int rc;
+
+	if (!pdev)
+		return false;
+
+	if (pdev->error_state == pci_channel_io_perm_failure)
+		return false;
+
+	slot = pdev->slot;
+	if (!slot || !slot->hotplug)
+		return true;
+
+	ops = slot->hotplug->ops;
+	if (!ops || !ops->get_adapter_status)
+		return true;
+
+	/* set the attention indicator while we've got the slot ops */
+	if (ops->set_attention_status)
+		ops->set_attention_status(slot->hotplug, 1);
+
+	rc = ops->get_adapter_status(slot->hotplug, &state);
+	if (rc)
+		return true;
+
+	return !!state;
+}
+
+static void eeh_clear_slot_attention(struct pci_dev *pdev)
+{
+	const struct hotplug_slot_ops *ops;
+	struct pci_slot *slot;
+
+	if (!pdev)
+		return;
+
+	if (pdev->error_state == pci_channel_io_perm_failure)
+		return;
+
+	slot = pdev->slot;
+	if (!slot || !slot->hotplug)
+		return;
+
+	ops = slot->hotplug->ops;
+	if (!ops || !ops->set_attention_status)
+		return;
+
+	ops->set_attention_status(slot->hotplug, 0);
+}
+
 /**
  * eeh_handle_normal_event - Handle EEH events on a specific PE
  * @pe: EEH PE - which should not be used after we return, as it may
@@ -789,7 +864,9 @@
 	struct eeh_pe *tmp_pe;
 	int rc = 0;
 	enum pci_ers_result result = PCI_ERS_RESULT_NONE;
-	struct eeh_rmv_data rmv_data = {LIST_HEAD_INIT(rmv_data.edev_list), 0};
+	struct eeh_rmv_data rmv_data =
+		{LIST_HEAD_INIT(rmv_data.removed_vf_list), 0};
+	int devices = 0;
 
 	bus = eeh_pe_bus_get(pe);
 	if (!bus) {
@@ -798,7 +875,59 @@
 		return;
 	}
 
-	eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+	/*
+	 * When devices are hot-removed we might get an EEH due to
+	 * a driver attempting to touch the MMIO space of a removed
+	 * device. In this case we don't have a device to recover
+	 * so suppress the event if we can't find any present devices.
+	 *
+	 * The hotplug driver should take care of tearing down the
+	 * device itself.
+	 */
+	eeh_for_each_pe(pe, tmp_pe)
+		eeh_pe_for_each_dev(tmp_pe, edev, tmp)
+			if (eeh_slot_presence_check(edev->pdev))
+				devices++;
+
+	if (!devices) {
+		pr_debug("EEH: Frozen PHB#%x-PE#%x is empty!\n",
+			pe->phb->global_number, pe->addr);
+		goto out; /* nothing to recover */
+	}
+
+	/* Log the event */
+	if (pe->type & EEH_PE_PHB) {
+		pr_err("EEH: PHB#%x failure detected, location: %s\n",
+			pe->phb->global_number, eeh_pe_loc_get(pe));
+	} else {
+		struct eeh_pe *phb_pe = eeh_phb_pe_get(pe->phb);
+
+		pr_err("EEH: Frozen PHB#%x-PE#%x detected\n",
+		       pe->phb->global_number, pe->addr);
+		pr_err("EEH: PE location: %s, PHB location: %s\n",
+		       eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe));
+	}
+
+#ifdef CONFIG_STACKTRACE
+	/*
+	 * Print the saved stack trace now that we've verified there's
+	 * something to recover.
+	 */
+	if (pe->trace_entries) {
+		void **ptrs = (void **) pe->stack_trace;
+		int i;
+
+		pr_err("EEH: Frozen PHB#%x-PE#%x detected\n",
+		       pe->phb->global_number, pe->addr);
+
+		/* 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]);
+
+		pe->trace_entries = 0;
+	}
+#endif /* CONFIG_STACKTRACE */
 
 	eeh_pe_update_time_stamp(pe);
 	pe->freeze_count++;
@@ -806,10 +935,12 @@
 		pr_err("EEH: PHB#%x-PE#%x has failed %d times in the last hour and has been permanently disabled.\n",
 		       pe->phb->global_number, pe->addr,
 		       pe->freeze_count);
-		goto hard_fail;
+		result = PCI_ERS_RESULT_DISCONNECT;
 	}
-	pr_warn("EEH: This PCI device has failed %d times in the last hour and will be permanently disabled after %d failures.\n",
-		pe->freeze_count, eeh_max_freezes);
+
+	eeh_for_each_pe(pe, tmp_pe)
+		eeh_pe_for_each_dev(tmp_pe, edev, tmp)
+			edev->mode &= ~EEH_DEV_NO_HANDLER;
 
 	/* Walk the various device drivers attached to this slot through
 	 * a reset sequence, giving each an opportunity to do what it needs
@@ -821,31 +952,39 @@
 	 * the error. Override the result if necessary to have partially
 	 * hotplug for this case.
 	 */
-	pr_info("EEH: Notify device drivers to shutdown\n");
-	eeh_set_channel_state(pe, pci_channel_io_frozen);
-	eeh_set_irq_state(pe, false);
-	eeh_pe_report("error_detected(IO frozen)", pe, eeh_report_error,
-		      &result);
-	if ((pe->type & EEH_PE_PHB) &&
-	    result != PCI_ERS_RESULT_NONE &&
-	    result != PCI_ERS_RESULT_NEED_RESET)
-		result = PCI_ERS_RESULT_NEED_RESET;
+	if (result != PCI_ERS_RESULT_DISCONNECT) {
+		pr_warn("EEH: This PCI device has failed %d times in the last hour and will be permanently disabled after %d failures.\n",
+			pe->freeze_count, eeh_max_freezes);
+		pr_info("EEH: Notify device drivers to shutdown\n");
+		eeh_set_channel_state(pe, pci_channel_io_frozen);
+		eeh_set_irq_state(pe, false);
+		eeh_pe_report("error_detected(IO frozen)", pe,
+			      eeh_report_error, &result);
+		if ((pe->type & EEH_PE_PHB) &&
+		    result != PCI_ERS_RESULT_NONE &&
+		    result != PCI_ERS_RESULT_NEED_RESET)
+			result = PCI_ERS_RESULT_NEED_RESET;
+	}
 
 	/* Get the current PCI slot state. This can take a long time,
 	 * sometimes over 300 seconds for certain systems.
 	 */
-	rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
-	if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
-		pr_warn("EEH: Permanent failure\n");
-		goto hard_fail;
+	if (result != PCI_ERS_RESULT_DISCONNECT) {
+		rc = eeh_wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
+		if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
+			pr_warn("EEH: Permanent failure\n");
+			result = PCI_ERS_RESULT_DISCONNECT;
+		}
 	}
 
 	/* Since rtas may enable MMIO when posting the error log,
 	 * don't post the error log until after all dev drivers
 	 * have been informed.
 	 */
-	pr_info("EEH: Collect temporary log\n");
-	eeh_slot_error_detail(pe, EEH_LOG_TEMP);
+	if (result != PCI_ERS_RESULT_DISCONNECT) {
+		pr_info("EEH: Collect temporary log\n");
+		eeh_slot_error_detail(pe, EEH_LOG_TEMP);
+	}
 
 	/* If all device drivers were EEH-unaware, then shut
 	 * down all of the device drivers, and hope they
@@ -857,7 +996,7 @@
 		if (rc) {
 			pr_warn("%s: Unable to reset, err=%d\n",
 				__func__, rc);
-			goto hard_fail;
+			result = PCI_ERS_RESULT_DISCONNECT;
 		}
 	}
 
@@ -866,9 +1005,9 @@
 		pr_info("EEH: Enable I/O for affected devices\n");
 		rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
-		if (rc < 0)
-			goto hard_fail;
-		if (rc) {
+		if (rc < 0) {
+			result = PCI_ERS_RESULT_DISCONNECT;
+		} else if (rc) {
 			result = PCI_ERS_RESULT_NEED_RESET;
 		} else {
 			pr_info("EEH: Notify device drivers to resume I/O\n");
@@ -882,9 +1021,9 @@
 		pr_info("EEH: Enabled DMA for affected devices\n");
 		rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
 
-		if (rc < 0)
-			goto hard_fail;
-		if (rc) {
+		if (rc < 0) {
+			result = PCI_ERS_RESULT_DISCONNECT;
+		} else if (rc) {
 			result = PCI_ERS_RESULT_NEED_RESET;
 		} else {
 			/*
@@ -892,17 +1031,11 @@
 			 * is still in frozen state. Clear it before
 			 * resuming the PE.
 			 */
-			eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+			eeh_pe_state_clear(pe, EEH_PE_ISOLATED, true);
 			result = PCI_ERS_RESULT_RECOVERED;
 		}
 	}
 
-	/* If any device has a hard failure, then shut off everything. */
-	if (result == PCI_ERS_RESULT_DISCONNECT) {
-		pr_warn("EEH: Device driver gave up\n");
-		goto hard_fail;
-	}
-
 	/* If any device called out for a reset, then reset the slot */
 	if (result == PCI_ERS_RESULT_NEED_RESET) {
 		pr_info("EEH: Reset without hotplug activity\n");
@@ -910,89 +1043,95 @@
 		if (rc) {
 			pr_warn("%s: Cannot reset, err=%d\n",
 				__func__, rc);
-			goto hard_fail;
+			result = PCI_ERS_RESULT_DISCONNECT;
+		} else {
+			result = PCI_ERS_RESULT_NONE;
+			eeh_set_channel_state(pe, pci_channel_io_normal);
+			eeh_set_irq_state(pe, true);
+			eeh_pe_report("slot_reset", pe, eeh_report_reset,
+				      &result);
+		}
+	}
+
+	if ((result == PCI_ERS_RESULT_RECOVERED) ||
+	    (result == PCI_ERS_RESULT_NONE)) {
+		/*
+		 * For those hot removed VFs, we should add back them after PF
+		 * get recovered properly.
+		 */
+		list_for_each_entry_safe(edev, tmp, &rmv_data.removed_vf_list,
+					 rmv_entry) {
+			eeh_add_virt_device(edev);
+			list_del(&edev->rmv_entry);
 		}
 
-		pr_info("EEH: Notify device drivers "
-			"the completion of reset\n");
-		result = PCI_ERS_RESULT_NONE;
+		/* Tell all device drivers that they can resume operations */
+		pr_info("EEH: Notify device driver to resume\n");
 		eeh_set_channel_state(pe, pci_channel_io_normal);
 		eeh_set_irq_state(pe, true);
-		eeh_pe_report("slot_reset", pe, eeh_report_reset, &result);
-	}
+		eeh_pe_report("resume", pe, eeh_report_resume, NULL);
+		eeh_for_each_pe(pe, tmp_pe) {
+			eeh_pe_for_each_dev(tmp_pe, edev, tmp) {
+				edev->mode &= ~EEH_DEV_NO_HANDLER;
+				edev->in_error = false;
+			}
+		}
 
-	/* All devices should claim they have recovered by now. */
-	if ((result != PCI_ERS_RESULT_RECOVERED) &&
-	    (result != PCI_ERS_RESULT_NONE)) {
-		pr_warn("EEH: Not recovered\n");
-		goto hard_fail;
-	}
+		pr_info("EEH: Recovery successful.\n");
+	} else  {
+		/*
+		 * About 90% of all real-life EEH failures in the field
+		 * are due to poorly seated PCI cards. Only 10% or so are
+		 * due to actual, failed cards.
+		 */
+		pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n"
+		       "Please try reseating or replacing it\n",
+			pe->phb->global_number, pe->addr);
 
-	/*
-	 * For those hot removed VFs, we should add back them after PF get
-	 * recovered properly.
-	 */
-	list_for_each_entry_safe(edev, tmp, &rmv_data.edev_list, rmv_list) {
-		eeh_add_virt_device(edev, NULL);
-		list_del(&edev->rmv_list);
-	}
+		eeh_slot_error_detail(pe, EEH_LOG_PERM);
 
-	/* Tell all device drivers that they can resume operations */
-	pr_info("EEH: Notify device driver to resume\n");
-	eeh_set_channel_state(pe, pci_channel_io_normal);
-	eeh_set_irq_state(pe, true);
-	eeh_pe_report("resume", pe, eeh_report_resume, NULL);
-	eeh_for_each_pe(pe, tmp_pe) {
-		eeh_pe_for_each_dev(tmp_pe, edev, tmp) {
-			edev->mode &= ~EEH_DEV_NO_HANDLER;
-			edev->in_error = false;
+		/* Notify all devices that they're about to go down. */
+		eeh_set_channel_state(pe, pci_channel_io_perm_failure);
+		eeh_set_irq_state(pe, false);
+		eeh_pe_report("error_detected(permanent failure)", pe,
+			      eeh_report_failure, NULL);
+
+		/* Mark the PE to be removed permanently */
+		eeh_pe_state_mark(pe, EEH_PE_REMOVED);
+
+		/*
+		 * Shut down the device drivers for good. We mark
+		 * all removed devices correctly to avoid access
+		 * the their PCI config any more.
+		 */
+		if (pe->type & EEH_PE_VF) {
+			eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
+			eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+		} else {
+			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();
+			/* The passed PE should no longer be used */
+			return;
 		}
 	}
 
-	pr_info("EEH: Recovery successful.\n");
-	goto final;
-
-hard_fail:
+out:
 	/*
-	 * About 90% of all real-life EEH failures in the field
-	 * are due to poorly seated PCI cards. Only 10% or so are
-	 * due to actual, failed cards.
+	 * Clean up any PEs without devices. While marked as EEH_PE_RECOVERYING
+	 * we don't want to modify the PE tree structure so we do it here.
 	 */
-	pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n"
-	       "Please try reseating or replacing it\n",
-		pe->phb->global_number, pe->addr);
+	eeh_pe_cleanup(pe);
 
-	eeh_slot_error_detail(pe, EEH_LOG_PERM);
+	/* clear the slot attention LED for all recovered devices */
+	eeh_for_each_pe(pe, tmp_pe)
+		eeh_pe_for_each_dev(tmp_pe, edev, tmp)
+			eeh_clear_slot_attention(edev->pdev);
 
-	/* Notify all devices that they're about to go down. */
-	eeh_set_channel_state(pe, pci_channel_io_perm_failure);
-	eeh_set_irq_state(pe, false);
-	eeh_pe_report("error_detected(permanent failure)", pe,
-		      eeh_report_failure, NULL);
-
-	/* Mark the PE to be removed permanently */
-	eeh_pe_state_mark(pe, EEH_PE_REMOVED);
-
-	/*
-	 * Shut down the device drivers for good. We mark
-	 * all removed devices correctly to avoid access
-	 * the their PCI config any more.
-	 */
-	if (pe->type & EEH_PE_VF) {
-		eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
-		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
-	} else {
-		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
-		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
-
-		pci_lock_rescan_remove();
-		pci_hp_remove_devices(bus);
-		pci_unlock_rescan_remove();
-		/* The passed PE should no longer be used */
-		return;
-	}
-final:
-	eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+	eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
 }
 
 /**
@@ -1004,7 +1143,8 @@
  */
 void eeh_handle_special_event(void)
 {
-	struct eeh_pe *pe, *phb_pe;
+	struct eeh_pe *pe, *phb_pe, *tmp_pe;
+	struct eeh_dev *edev, *tmp_edev;
 	struct pci_bus *bus;
 	struct pci_controller *hose;
 	unsigned long flags;
@@ -1026,7 +1166,7 @@
 				phb_pe = eeh_phb_pe_get(hose);
 				if (!phb_pe) continue;
 
-				eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
+				eeh_pe_mark_isolated(phb_pe);
 			}
 
 			eeh_serialize_unlock(flags);
@@ -1041,11 +1181,9 @@
 			/* Purge all events of the PHB */
 			eeh_remove_event(pe, true);
 
-			if (rc == EEH_NEXT_ERR_DEAD_PHB)
-				eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
-			else
-				eeh_pe_state_mark(pe,
-					EEH_PE_ISOLATED | EEH_PE_RECOVERING);
+			if (rc != EEH_NEXT_ERR_DEAD_PHB)
+				eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+			eeh_pe_mark_isolated(pe);
 
 			eeh_serialize_unlock(flags);
 
@@ -1065,6 +1203,7 @@
 		 */
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
+			eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
 			eeh_handle_normal_event(pe);
 		} else {
 			pci_lock_rescan_remove();
@@ -1075,8 +1214,12 @@
 				    (phb_pe->state & EEH_PE_RECOVERING))
 					continue;
 
+				eeh_for_each_pe(pe, tmp_pe)
+					eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
+						edev->mode &= ~EEH_DEV_NO_HANDLER;
+
 				/* Notify all devices to be down */
-				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
+				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
 				eeh_set_channel_state(pe, pci_channel_io_perm_failure);
 				eeh_pe_report(
 					"error_detected(permanent failure)", pe,
diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c
index 61c9356..a7a8dc1 100644
--- a/arch/powerpc/kernel/eeh_event.c
+++ b/arch/powerpc/kernel/eeh_event.c
@@ -1,17 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  *
  * Copyright (c) 2005 Linas Vepstas <linas@linas.org>
  */
@@ -35,7 +23,7 @@
  */
 
 static DEFINE_SPINLOCK(eeh_eventlist_lock);
-static struct semaphore eeh_eventlist_sem;
+static DECLARE_COMPLETION(eeh_eventlist_event);
 static LIST_HEAD(eeh_eventlist);
 
 /**
@@ -52,10 +40,9 @@
 {
 	unsigned long flags;
 	struct eeh_event *event;
-	struct eeh_pe *pe;
 
 	while (!kthread_should_stop()) {
-		if (down_interruptible(&eeh_eventlist_sem))
+		if (wait_for_completion_interruptible(&eeh_eventlist_event))
 			break;
 
 		/* Fetch EEH event from the queue */
@@ -71,19 +58,10 @@
 			continue;
 
 		/* We might have event without binding PE */
-		pe = event->pe;
-		if (pe) {
-			if (pe->type & EEH_PE_PHB)
-				pr_info("EEH: Detected error on PHB#%x\n",
-					 pe->phb->global_number);
-			else
-				pr_info("EEH: Detected PCI bus error on "
-					"PHB#%x-PE#%x\n",
-					pe->phb->global_number, pe->addr);
-			eeh_handle_normal_event(pe);
-		} else {
+		if (event->pe)
+			eeh_handle_normal_event(event->pe);
+		else
 			eeh_handle_special_event();
-		}
 
 		kfree(event);
 	}
@@ -102,9 +80,6 @@
 	struct task_struct *t;
 	int ret = 0;
 
-	/* Initialize semaphore */
-	sema_init(&eeh_eventlist_sem, 0);
-
 	t = kthread_run(eeh_event_handler, NULL, "eehd");
 	if (IS_ERR(t)) {
 		ret = PTR_ERR(t);
@@ -124,7 +99,7 @@
  * the actual event will be delivered in a normal context
  * (from a workqueue).
  */
-int eeh_send_failure_event(struct eeh_pe *pe)
+int __eeh_send_failure_event(struct eeh_pe *pe)
 {
 	unsigned long flags;
 	struct eeh_event *event;
@@ -136,17 +111,49 @@
 	}
 	event->pe = pe;
 
+	/*
+	 * Mark the PE as recovering before inserting it in the queue.
+	 * This prevents the PE from being free()ed by a hotplug driver
+	 * while the PE is sitting in the event queue.
+	 */
+	if (pe) {
+#ifdef CONFIG_STACKTRACE
+		/*
+		 * Save the current stack trace so we can dump it from the
+		 * event handler thread.
+		 */
+		pe->trace_entries = stack_trace_save(pe->stack_trace,
+					 ARRAY_SIZE(pe->stack_trace), 0);
+#endif /* CONFIG_STACKTRACE */
+
+		eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+	}
+
 	/* We may or may not be called in an interrupt context */
 	spin_lock_irqsave(&eeh_eventlist_lock, flags);
 	list_add(&event->list, &eeh_eventlist);
 	spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
 
 	/* For EEH deamon to knick in */
-	up(&eeh_eventlist_sem);
+	complete(&eeh_eventlist_event);
 
 	return 0;
 }
 
+int eeh_send_failure_event(struct eeh_pe *pe)
+{
+	/*
+	 * If we've manually supressed recovery events via debugfs
+	 * then just drop it on the floor.
+	 */
+	if (eeh_debugfs_no_recover) {
+		pr_err("EEH: Event dropped due to no_recover setting\n");
+		return 0;
+	}
+
+	return __eeh_send_failure_event(pe);
+}
+
 /**
  * eeh_remove_event - Remove EEH event from the queue
  * @pe: Event binding to the PE
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 1b238ec..177852e 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * The file intends to implement PE based on the information from
  * platforms. Basically, there have 3 types of PEs: PHB/Bus/Device.
@@ -6,20 +7,6 @@
  * PE is only meaningful in one PHB domain.
  *
  * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/delay.h>
@@ -75,7 +62,6 @@
 	pe->type = type;
 	pe->phb = phb;
 	INIT_LIST_HEAD(&pe->child_list);
-	INIT_LIST_HEAD(&pe->child);
 	INIT_LIST_HEAD(&pe->edevs);
 
 	pe->data = (void *)pe + ALIGN(sizeof(struct eeh_pe),
@@ -110,6 +96,57 @@
 }
 
 /**
+ * eeh_wait_state - Wait for PE state
+ * @pe: EEH PE
+ * @max_wait: maximal period in millisecond
+ *
+ * Wait for the state of associated PE. It might take some time
+ * to retrieve the PE's state.
+ */
+int eeh_wait_state(struct eeh_pe *pe, int max_wait)
+{
+	int ret;
+	int mwait;
+
+	/*
+	 * According to PAPR, the state of PE might be temporarily
+	 * unavailable. Under the circumstance, we have to wait
+	 * for indicated time determined by firmware. The maximal
+	 * wait time is 5 minutes, which is acquired from the original
+	 * EEH implementation. Also, the original implementation
+	 * also defined the minimal wait time as 1 second.
+	 */
+#define EEH_STATE_MIN_WAIT_TIME	(1000)
+#define EEH_STATE_MAX_WAIT_TIME	(300 * 1000)
+
+	while (1) {
+		ret = eeh_ops->get_state(pe, &mwait);
+
+		if (ret != EEH_STATE_UNAVAILABLE)
+			return ret;
+
+		if (max_wait <= 0) {
+			pr_warn("%s: Timeout when getting PE's state (%d)\n",
+				__func__, max_wait);
+			return EEH_STATE_NOT_SUPPORT;
+		}
+
+		if (mwait < EEH_STATE_MIN_WAIT_TIME) {
+			pr_warn("%s: Firmware returned bad wait value %d\n",
+				__func__, mwait);
+			mwait = EEH_STATE_MIN_WAIT_TIME;
+		} else if (mwait > EEH_STATE_MAX_WAIT_TIME) {
+			pr_warn("%s: Firmware returned too long wait value %d\n",
+				__func__, mwait);
+			mwait = EEH_STATE_MAX_WAIT_TIME;
+		}
+
+		msleep(min(mwait, max_wait));
+		max_wait -= mwait;
+	}
+}
+
+/**
  * eeh_phb_pe_get - Retrieve PHB PE based on the given PHB
  * @phb: PCI controller
  *
@@ -194,29 +231,22 @@
  * The function is used to traverse the devices of the specified
  * PE and its child PEs.
  */
-void *eeh_pe_dev_traverse(struct eeh_pe *root,
+void eeh_pe_dev_traverse(struct eeh_pe *root,
 			  eeh_edev_traverse_func fn, void *flag)
 {
 	struct eeh_pe *pe;
 	struct eeh_dev *edev, *tmp;
-	void *ret;
 
 	if (!root) {
 		pr_warn("%s: Invalid PE %p\n",
 			__func__, root);
-		return NULL;
+		return;
 	}
 
 	/* Traverse root PE */
-	eeh_for_each_pe(root, pe) {
-		eeh_pe_for_each_dev(pe, edev, tmp) {
-			ret = fn(edev, flag);
-			if (ret)
-				return ret;
-		}
-	}
-
-	return NULL;
+	eeh_for_each_pe(root, pe)
+		eeh_pe_for_each_dev(pe, edev, tmp)
+			fn(edev, flag);
 }
 
 /**
@@ -342,8 +372,7 @@
 
 	/* Check if the PE number is valid */
 	if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) {
-		pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%x\n",
-		       __func__, config_addr, pdn->phb->global_number);
+		eeh_edev_err(edev, "PE#0 is invalid for this PHB!\n");
 		return -EINVAL;
 	}
 
@@ -354,42 +383,34 @@
 	 * components.
 	 */
 	pe = eeh_pe_get(pdn->phb, edev->pe_config_addr, config_addr);
-	if (pe && !(pe->type & EEH_PE_INVALID)) {
-		/* Mark the PE as type of PCI bus */
-		pe->type = EEH_PE_BUS;
-		edev->pe = pe;
+	if (pe) {
+		if (pe->type & EEH_PE_INVALID) {
+			list_add_tail(&edev->entry, &pe->edevs);
+			edev->pe = pe;
+			/*
+			 * We're running to here because of PCI hotplug caused by
+			 * EEH recovery. We need clear EEH_PE_INVALID until the top.
+			 */
+			parent = pe;
+			while (parent) {
+				if (!(parent->type & EEH_PE_INVALID))
+					break;
+				parent->type &= ~EEH_PE_INVALID;
+				parent = parent->parent;
+			}
 
-		/* Put the edev to PE */
-		list_add_tail(&edev->list, &pe->edevs);
-		pr_debug("EEH: Add %04x:%02x:%02x.%01x to Bus PE#%x\n",
-			 pdn->phb->global_number,
-			 pdn->busno,
-			 PCI_SLOT(pdn->devfn),
-			 PCI_FUNC(pdn->devfn),
-			 pe->addr);
-		return 0;
-	} else if (pe && (pe->type & EEH_PE_INVALID)) {
-		list_add_tail(&edev->list, &pe->edevs);
-		edev->pe = pe;
-		/*
-		 * We're running to here because of PCI hotplug caused by
-		 * EEH recovery. We need clear EEH_PE_INVALID until the top.
-		 */
-		parent = pe;
-		while (parent) {
-			if (!(parent->type & EEH_PE_INVALID))
-				break;
-			parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP);
-			parent = parent->parent;
+			eeh_edev_dbg(edev,
+				     "Added to device PE (parent: PE#%x)\n",
+				     pe->parent->addr);
+		} else {
+			/* Mark the PE as type of PCI bus */
+			pe->type = EEH_PE_BUS;
+			edev->pe = pe;
+
+			/* Put the edev to PE */
+			list_add_tail(&edev->entry, &pe->edevs);
+			eeh_edev_dbg(edev, "Added to bus PE\n");
 		}
-
-		pr_debug("EEH: Add %04x:%02x:%02x.%01x to Device "
-			 "PE#%x, Parent PE#%x\n",
-			 pdn->phb->global_number,
-			 pdn->busno,
-			 PCI_SLOT(pdn->devfn),
-			 PCI_FUNC(pdn->devfn),
-			 pe->addr, pe->parent->addr);
 		return 0;
 	}
 
@@ -429,15 +450,10 @@
 	 * link the EEH device accordingly.
 	 */
 	list_add_tail(&pe->child, &parent->child_list);
-	list_add_tail(&edev->list, &pe->edevs);
+	list_add_tail(&edev->entry, &pe->edevs);
 	edev->pe = pe;
-	pr_debug("EEH: Add %04x:%02x:%02x.%01x to "
-		 "Device PE#%x, Parent PE#%x\n",
-		 pdn->phb->global_number,
-		 pdn->busno,
-		 PCI_SLOT(pdn->devfn),
-		 PCI_FUNC(pdn->devfn),
-		 pe->addr, pe->parent->addr);
+	eeh_edev_dbg(edev, "Added to device PE (parent: PE#%x)\n",
+		     pe->parent->addr);
 
 	return 0;
 }
@@ -454,22 +470,18 @@
 int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
 {
 	struct eeh_pe *pe, *parent, *child;
+	bool keep, recover;
 	int cnt;
-	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
-	if (!edev->pe) {
-		pr_debug("%s: No PE found for device %04x:%02x:%02x.%01x\n",
-			 __func__,  pdn->phb->global_number,
-			 pdn->busno,
-			 PCI_SLOT(pdn->devfn),
-			 PCI_FUNC(pdn->devfn));
+	pe = eeh_dev_to_pe(edev);
+	if (!pe) {
+		eeh_edev_dbg(edev, "No PE found for device.\n");
 		return -EEXIST;
 	}
 
 	/* Remove the EEH device */
-	pe = eeh_dev_to_pe(edev);
 	edev->pe = NULL;
-	list_del(&edev->list);
+	list_del(&edev->entry);
 
 	/*
 	 * Check if the parent PE includes any EEH devices.
@@ -479,10 +491,21 @@
 	 */
 	while (1) {
 		parent = pe->parent;
+
+		/* PHB PEs should never be removed */
 		if (pe->type & EEH_PE_PHB)
 			break;
 
-		if (!(pe->state & EEH_PE_KEEP)) {
+		/*
+		 * XXX: KEEP is set while resetting a PE. I don't think it's
+		 * ever set without RECOVERING also being set. I could
+		 * be wrong though so catch that with a WARN.
+		 */
+		keep = !!(pe->state & EEH_PE_KEEP);
+		recover = !!(pe->state & EEH_PE_RECOVERING);
+		WARN_ON(keep && !recover);
+
+		if (!keep && !recover) {
 			if (list_empty(&pe->edevs) &&
 			    list_empty(&pe->child_list)) {
 				list_del(&pe->child);
@@ -491,6 +514,15 @@
 				break;
 			}
 		} else {
+			/*
+			 * Mark the PE as invalid. At the end of the recovery
+			 * process any invalid PEs will be garbage collected.
+			 *
+			 * We need to delay the free()ing of them since we can
+			 * remove edev's while traversing the PE tree which
+			 * might trigger the removal of a PE and we can't
+			 * deal with that (yet).
+			 */
 			if (list_empty(&pe->edevs)) {
 				cnt = 0;
 				list_for_each_entry(child, &pe->child_list, child) {
@@ -541,44 +573,6 @@
 }
 
 /**
- * __eeh_pe_state_mark - Mark the state for the PE
- * @data: EEH PE
- * @flag: state
- *
- * The function is used to mark the indicated state for the given
- * PE. Also, the associated PCI devices will be put into IO frozen
- * state as well.
- */
-static void *__eeh_pe_state_mark(struct eeh_pe *pe, void *flag)
-{
-	int state = *((int *)flag);
-	struct eeh_dev *edev, *tmp;
-	struct pci_dev *pdev;
-
-	/* Keep the state of permanently removed PE intact */
-	if (pe->state & EEH_PE_REMOVED)
-		return NULL;
-
-	pe->state |= state;
-
-	/* Offline PCI devices if applicable */
-	if (!(state & EEH_PE_ISOLATED))
-		return NULL;
-
-	eeh_pe_for_each_dev(pe, edev, tmp) {
-		pdev = eeh_dev_to_pci_dev(edev);
-		if (pdev)
-			pdev->error_state = pci_channel_io_frozen;
-	}
-
-	/* Block PCI config access if required */
-	if (pe->state & EEH_PE_CFG_RESTRICTED)
-		pe->state |= EEH_PE_CFG_BLOCKED;
-
-	return NULL;
-}
-
-/**
  * eeh_pe_state_mark - Mark specified state for PE and its associated device
  * @pe: EEH PE
  *
@@ -586,19 +580,49 @@
  * is used to mark appropriate state for the affected PEs and the
  * associated devices.
  */
-void eeh_pe_state_mark(struct eeh_pe *pe, int state)
+void eeh_pe_state_mark(struct eeh_pe *root, int state)
 {
-	eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
+	struct eeh_pe *pe;
+
+	eeh_for_each_pe(root, pe)
+		if (!(pe->state & EEH_PE_REMOVED))
+			pe->state |= state;
 }
 EXPORT_SYMBOL_GPL(eeh_pe_state_mark);
 
-static void *__eeh_pe_dev_mode_mark(struct eeh_dev *edev, void *flag)
+/**
+ * eeh_pe_mark_isolated
+ * @pe: EEH PE
+ *
+ * Record that a PE has been isolated by marking the PE and it's children as
+ * EEH_PE_ISOLATED (and EEH_PE_CFG_BLOCKED, if required) and their PCI devices
+ * as pci_channel_io_frozen.
+ */
+void eeh_pe_mark_isolated(struct eeh_pe *root)
+{
+	struct eeh_pe *pe;
+	struct eeh_dev *edev;
+	struct pci_dev *pdev;
+
+	eeh_pe_state_mark(root, EEH_PE_ISOLATED);
+	eeh_for_each_pe(root, pe) {
+		list_for_each_entry(edev, &pe->edevs, entry) {
+			pdev = eeh_dev_to_pci_dev(edev);
+			if (pdev)
+				pdev->error_state = pci_channel_io_frozen;
+		}
+		/* Block PCI config access if required */
+		if (pe->state & EEH_PE_CFG_RESTRICTED)
+			pe->state |= EEH_PE_CFG_BLOCKED;
+	}
+}
+EXPORT_SYMBOL_GPL(eeh_pe_mark_isolated);
+
+static void __eeh_pe_dev_mode_mark(struct eeh_dev *edev, void *flag)
 {
 	int mode = *((int *)flag);
 
 	edev->mode |= mode;
-
-	return NULL;
 }
 
 /**
@@ -613,84 +637,52 @@
 }
 
 /**
- * __eeh_pe_state_clear - Clear state for the PE
+ * eeh_pe_state_clear - Clear state for the PE
  * @data: EEH PE
- * @flag: state
+ * @state: state
+ * @include_passed: include passed-through devices?
  *
  * The function is used to clear the indicated state from the
  * given PE. Besides, we also clear the check count of the PE
  * as well.
  */
-static void *__eeh_pe_state_clear(struct eeh_pe *pe, void *flag)
+void eeh_pe_state_clear(struct eeh_pe *root, int state, bool include_passed)
 {
-	int state = *((int *)flag);
+	struct eeh_pe *pe;
 	struct eeh_dev *edev, *tmp;
 	struct pci_dev *pdev;
 
-	/* Keep the state of permanently removed PE intact */
-	if (pe->state & EEH_PE_REMOVED)
-		return NULL;
-
-	pe->state &= ~state;
-
-	/*
-	 * Special treatment on clearing isolated state. Clear
-	 * check count since last isolation and put all affected
-	 * devices to normal state.
-	 */
-	if (!(state & EEH_PE_ISOLATED))
-		return NULL;
-
-	pe->check_count = 0;
-	eeh_pe_for_each_dev(pe, edev, tmp) {
-		pdev = eeh_dev_to_pci_dev(edev);
-		if (!pdev)
+	eeh_for_each_pe(root, pe) {
+		/* Keep the state of permanently removed PE intact */
+		if (pe->state & EEH_PE_REMOVED)
 			continue;
 
-		pdev->error_state = pci_channel_io_normal;
+		if (!include_passed && eeh_pe_passed(pe))
+			continue;
+
+		pe->state &= ~state;
+
+		/*
+		 * Special treatment on clearing isolated state. Clear
+		 * check count since last isolation and put all affected
+		 * devices to normal state.
+		 */
+		if (!(state & EEH_PE_ISOLATED))
+			continue;
+
+		pe->check_count = 0;
+		eeh_pe_for_each_dev(pe, edev, tmp) {
+			pdev = eeh_dev_to_pci_dev(edev);
+			if (!pdev)
+				continue;
+
+			pdev->error_state = pci_channel_io_normal;
+		}
+
+		/* Unblock PCI config access if required */
+		if (pe->state & EEH_PE_CFG_RESTRICTED)
+			pe->state &= ~EEH_PE_CFG_BLOCKED;
 	}
-
-	/* Unblock PCI config access if required */
-	if (pe->state & EEH_PE_CFG_RESTRICTED)
-		pe->state &= ~EEH_PE_CFG_BLOCKED;
-
-	return NULL;
-}
-
-/**
- * eeh_pe_state_clear - Clear state for the PE and its children
- * @pe: PE
- * @state: state to be cleared
- *
- * When the PE and its children has been recovered from error,
- * we need clear the error state for that. The function is used
- * for the purpose.
- */
-void eeh_pe_state_clear(struct eeh_pe *pe, int state)
-{
-	eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
-}
-
-/**
- * eeh_pe_state_mark_with_cfg - Mark PE state with unblocked config space
- * @pe: PE
- * @state: PE state to be set
- *
- * Set specified flag to PE and its child PEs. The PCI config space
- * of some PEs is blocked automatically when EEH_PE_ISOLATED is set,
- * which isn't needed in some situations. The function allows to set
- * the specified flag to indicated PEs without blocking their PCI
- * config space.
- */
-void eeh_pe_state_mark_with_cfg(struct eeh_pe *pe, int state)
-{
-	eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
-	if (!(state & EEH_PE_ISOLATED))
-		return;
-
-	/* Clear EEH_PE_CFG_BLOCKED, which might be set just now */
-	state = EEH_PE_CFG_BLOCKED;
-	eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
 }
 
 /*
@@ -718,17 +710,13 @@
 	if (!(edev->mode & (EEH_DEV_ROOT_PORT | EEH_DEV_DS_PORT)))
 		return;
 
-	pr_debug("%s: Check PCIe link for %04x:%02x:%02x.%01x ...\n",
-		 __func__, pdn->phb->global_number,
-		 pdn->busno,
-		 PCI_SLOT(pdn->devfn),
-		 PCI_FUNC(pdn->devfn));
+	eeh_edev_dbg(edev, "Checking PCIe link...\n");
 
 	/* Check slot status */
 	cap = edev->pcie_cap;
 	eeh_ops->read_config(pdn, cap + PCI_EXP_SLTSTA, 2, &val);
 	if (!(val & PCI_EXP_SLTSTA_PDS)) {
-		pr_debug("  No card in the slot (0x%04x) !\n", val);
+		eeh_edev_dbg(edev, "No card in the slot (0x%04x) !\n", val);
 		return;
 	}
 
@@ -737,7 +725,7 @@
 	if (val & PCI_EXP_SLTCAP_PCP) {
 		eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCTL, 2, &val);
 		if (val & PCI_EXP_SLTCTL_PCC) {
-			pr_debug("  In power-off state, power it on ...\n");
+			eeh_edev_dbg(edev, "In power-off state, power it on ...\n");
 			val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC);
 			val |= (0x0100 & PCI_EXP_SLTCTL_PIC);
 			eeh_ops->write_config(pdn, cap + PCI_EXP_SLTCTL, 2, val);
@@ -753,7 +741,7 @@
 	/* Check link */
 	eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCAP, 4, &val);
 	if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
-		pr_debug("  No link reporting capability (0x%08x) \n", val);
+		eeh_edev_dbg(edev, "No link reporting capability (0x%08x) \n", val);
 		msleep(1000);
 		return;
 	}
@@ -770,10 +758,10 @@
 	}
 
 	if (val & PCI_EXP_LNKSTA_DLLLA)
-		pr_debug("  Link up (%s)\n",
+		eeh_edev_dbg(edev, "Link up (%s)\n",
 			 (val & PCI_EXP_LNKSTA_CLS_2_5GB) ? "2.5GB" : "5GB");
 	else
-		pr_debug("  Link not ready (0x%04x)\n", val);
+		eeh_edev_dbg(edev, "Link not ready (0x%04x)\n", val);
 }
 
 #define BYTE_SWAP(OFF)	(8*((OFF)/4)+3-(OFF))
@@ -853,7 +841,7 @@
  * the expansion ROM base address, the latency timer, and etc.
  * from the saved values in the device node.
  */
-static void *eeh_restore_one_device_bars(struct eeh_dev *edev, void *flag)
+static void eeh_restore_one_device_bars(struct eeh_dev *edev, void *flag)
 {
 	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
@@ -865,8 +853,6 @@
 
 	if (eeh_ops->restore_config && pdn)
 		eeh_ops->restore_config(pdn);
-
-	return NULL;
 }
 
 /**
@@ -945,7 +931,7 @@
 		return pe->bus;
 
 	/* Retrieve the parent PCI bus of first (top) PCI device */
-	edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, list);
+	edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry);
 	pdev = eeh_dev_to_pci_dev(edev);
 	if (pdev)
 		return pdev->bus;
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index deed906..3fa04dd 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -82,8 +82,9 @@
 	if (!(edev->pe->state & EEH_PE_ISOLATED))
 		return count;
 
-	if (eeh_unfreeze_pe(edev->pe, true))
+	if (eeh_unfreeze_pe(edev->pe))
 		return -EIO;
+	eeh_pe_state_clear(edev->pe, EEH_PE_ISOLATED, true);
 
 	return count;
 }
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e58c3f4..d60908e 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -11,12 +12,6 @@
  *
  *  This file contains the system call entry code, context switch
  *  code, and exception/interrupt return code for PowerPC.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/errno.h>
@@ -36,15 +31,10 @@
 #include <asm/asm-405.h>
 #include <asm/feature-fixups.h>
 #include <asm/barrier.h>
+#include <asm/kup.h>
+#include <asm/bug.h>
 
-/*
- * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE.
- */
-#if MSR_KERNEL >= 0x10000
-#define LOAD_MSR_KERNEL(r, x)	lis r,(x)@h; ori r,r,(x)@l
-#else
-#define LOAD_MSR_KERNEL(r, x)	li r,(x)
-#endif
+#include "head_32.h"
 
 /*
  * Align to 4k in order to ensure that all functions modyfing srr0/srr1
@@ -97,14 +87,11 @@
 	mfspr	r0,SPRN_SRR1
 	stw	r0,_SRR1(r11)
 
-	/* set the stack limit to the current stack
-	 * and set the limit to protect the thread_info
-	 * struct
-	 */
+	/* set the stack limit to the current stack */
 	mfspr	r8,SPRN_SPRG_THREAD
 	lwz	r0,KSP_LIMIT(r8)
 	stw	r0,SAVED_KSP_LIMIT(r11)
-	rlwimi	r0,r1,0,0,(31-THREAD_SHIFT)
+	rlwinm	r0,r1,0,0,(31 - THREAD_SHIFT)
 	stw	r0,KSP_LIMIT(r8)
 	/* fall through */
 #endif
@@ -121,14 +108,11 @@
 	mfspr	r0,SPRN_SRR1
 	stw	r0,crit_srr1@l(0)
 
-	/* set the stack limit to the current stack
-	 * and set the limit to protect the thread_info
-	 * struct
-	 */
+	/* set the stack limit to the current stack */
 	mfspr	r8,SPRN_SPRG_THREAD
 	lwz	r0,KSP_LIMIT(r8)
 	stw	r0,saved_ksp_limit@l(0)
-	rlwimi	r0,r1,0,0,(31-THREAD_SHIFT)
+	rlwinm	r0,r1,0,0,(31 - THREAD_SHIFT)
 	stw	r0,KSP_LIMIT(r8)
 	/* fall through */
 #endif
@@ -156,9 +140,8 @@
 	stw	r12,_CTR(r11)
 	stw	r2,_XER(r11)
 	mfspr	r12,SPRN_SPRG_THREAD
-	addi	r2,r12,-THREAD
-	tovirt(r2,r2)			/* set r2 to current */
 	beq	2f			/* if from user, fix up THREAD.regs */
+	addi	r2, r12, -THREAD
 	addi	r11,r1,STACK_FRAME_OVERHEAD
 	stw	r11,PT_REGS(r12)
 #if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
@@ -166,6 +149,12 @@
 	   internal debug mode bit to do this. */
 	lwz	r12,THREAD_DBCR0(r12)
 	andis.	r12,r12,DBCR0_IDM@h
+#endif
+	ACCOUNT_CPU_USER_ENTRY(r2, r11, r12)
+#ifdef CONFIG_PPC_BOOK3S_32
+	kuep_lock r11, r12
+#endif
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
 	beq+	3f
 	/* From user and task is ptraced - load up global dbcr0 */
 	li	r12,-1			/* clear all pending debug events */
@@ -174,8 +163,7 @@
 	tophys(r11,r11)
 	addi	r11,r11,global_dbcr0@l
 #ifdef CONFIG_SMP
-	CURRENT_THREAD_INFO(r9, r1)
-	lwz	r9,TI_CPU(r9)
+	lwz	r9,TASK_CPU(r2)
 	slwi	r9,r9,3
 	add	r11,r11,r9
 #endif
@@ -185,59 +173,72 @@
 	addi	r12,r12,-1
 	stw	r12,4(r11)
 #endif
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	CURRENT_THREAD_INFO(r9, r1)
-	tophys(r9, r9)
-	ACCOUNT_CPU_USER_ENTRY(r9, r11, r12)
-#endif
 
 	b	3f
 
 2:	/* if from kernel, check interrupted DOZE/NAP mode and
          * check for stack overflow
          */
+	kuap_save_and_lock r11, r12, r9, r2, r0
+	addi	r2, r12, -THREAD
 	lwz	r9,KSP_LIMIT(r12)
 	cmplw	r1,r9			/* if r1 <= ksp_limit */
 	ble-	stack_ovf		/* then the kernel stack overflowed */
 5:
-#if defined(CONFIG_6xx) || defined(CONFIG_E500)
-	CURRENT_THREAD_INFO(r9, r1)
-	tophys(r9,r9)			/* check local flags */
-	lwz	r12,TI_LOCAL_FLAGS(r9)
+#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
+	lwz	r12,TI_LOCAL_FLAGS(r2)
 	mtcrf	0x01,r12
 	bt-	31-TLF_NAPPING,4f
 	bt-	31-TLF_SLEEPING,7f
-#endif /* CONFIG_6xx || CONFIG_E500 */
+#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_E500 */
 	.globl transfer_to_handler_cont
 transfer_to_handler_cont:
 3:
 	mflr	r9
+	tovirt(r2, r2)			/* set r2 to current */
 	lwz	r11,0(r9)		/* virtual address of handler */
 	lwz	r9,4(r9)		/* where to go when done */
 #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
 	mtspr	SPRN_NRI, r0
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
+	/*
+	 * When tracing IRQ state (lockdep) we enable the MMU before we call
+	 * the IRQ tracing functions as they might access vmalloc space or
+	 * perform IOs for console output.
+	 *
+	 * To speed up the syscall path where interrupts stay on, let's check
+	 * first if we are changing the MSR value at all.
+	 */
+	tophys(r12, r1)
+	lwz	r12,_MSR(r12)
+	andi.	r12,r12,MSR_EE
+	bne	1f
+
+	/* MSR isn't changing, just transition directly */
+#endif
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r10
+	mtlr	r9
+	SYNC
+	RFI				/* jump to handler, enable MMU */
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+1:	/* MSR is changing, re-enable MMU so we can notify lockdep. We need to
+	 * keep interrupts disabled at this point otherwise we might risk
+	 * taking an interrupt before we tell lockdep they are enabled.
+	 */
 	lis	r12,reenable_mmu@h
 	ori	r12,r12,reenable_mmu@l
+	LOAD_REG_IMMEDIATE(r0, MSR_KERNEL)
 	mtspr	SPRN_SRR0,r12
-	mtspr	SPRN_SRR1,r10
+	mtspr	SPRN_SRR1,r0
 	SYNC
 	RFI
-reenable_mmu:				/* re-enable mmu so we can */
-	mfmsr	r10
-	lwz	r12,_MSR(r1)
-	xor	r10,r10,r12
-	andi.	r10,r10,MSR_EE		/* Did EE change? */
-	beq	1f
 
+reenable_mmu:
 	/*
-	 * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
-	 * If from user mode there is only one stack frame on the stack, and
-	 * accessing CALLER_ADDR1 will cause oops. So we need create a dummy
-	 * stack frame to make trace_hardirqs_off happy.
-	 *
-	 * This is handy because we also need to save a bunch of GPRs,
+	 * We save a bunch of GPRs,
 	 * r3 can be different from GPR3(r1) at this point, r9 and r11
 	 * contains the old MSR and handler address respectively,
 	 * r4 & r5 can contain page fault arguments that need to be passed
@@ -245,14 +246,19 @@
 	 * they aren't useful past this point (aren't syscall arguments),
 	 * the rest is restored from the exception frame.
 	 */
+
 	stwu	r1,-32(r1)
 	stw	r9,8(r1)
 	stw	r11,12(r1)
 	stw	r3,16(r1)
 	stw	r4,20(r1)
 	stw	r5,24(r1)
-	bl	trace_hardirqs_off
-	lwz	r5,24(r1)
+
+	/* If we are disabling interrupts (normal case), simply log it with
+	 * lockdep
+	 */
+1:	bl	trace_hardirqs_off
+2:	lwz	r5,24(r1)
 	lwz	r4,20(r1)
 	lwz	r3,16(r1)
 	lwz	r11,12(r1)
@@ -262,27 +268,22 @@
 	lwz	r6,GPR6(r1)
 	lwz	r7,GPR7(r1)
 	lwz	r8,GPR8(r1)
-1:	mtctr	r11
+	mtctr	r11
 	mtlr	r9
 	bctr				/* jump to handler */
-#else /* CONFIG_TRACE_IRQFLAGS */
-	mtspr	SPRN_SRR0,r11
-	mtspr	SPRN_SRR1,r10
-	mtlr	r9
-	SYNC
-	RFI				/* jump to handler, enable MMU */
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
-#if defined (CONFIG_6xx) || defined(CONFIG_E500)
+#if defined (CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
 4:	rlwinm	r12,r12,0,~_TLF_NAPPING
-	stw	r12,TI_LOCAL_FLAGS(r9)
+	stw	r12,TI_LOCAL_FLAGS(r2)
 	b	power_save_ppc32_restore
 
 7:	rlwinm	r12,r12,0,~_TLF_SLEEPING
-	stw	r12,TI_LOCAL_FLAGS(r9)
+	stw	r12,TI_LOCAL_FLAGS(r2)
 	lwz	r9,_MSR(r11)		/* if sleeping, clear MSR.EE */
 	rlwinm	r9,r9,0,~MSR_EE
 	lwz	r12,_LINK(r11)		/* and return to address in LR */
+	kuap_restore r11, r2, r3, r4, r5
 	b	fast_exception_return
 #endif
 
@@ -303,7 +304,7 @@
 	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
 	lis	r9,StackOverflow@ha
 	addi	r9,r9,StackOverflow@l
-	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
 #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
 	mtspr	SPRN_NRI, r0
 #endif
@@ -312,6 +313,33 @@
 	SYNC
 	RFI
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+trace_syscall_entry_irq_off:
+	/*
+	 * Syscall shouldn't happen while interrupts are disabled,
+	 * so let's do a warning here.
+	 */
+0:	trap
+	EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
+	bl	trace_hardirqs_on
+
+	/* Now enable for real */
+	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL | MSR_EE)
+	mtmsr	r10
+
+	REST_GPR(0, r1)
+	REST_4GPRS(3, r1)
+	REST_2GPRS(7, r1)
+	b	DoSyscall
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
+	.globl	transfer_to_syscall
+transfer_to_syscall:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	andi.	r12,r9,MSR_EE
+	beq-	trace_syscall_entry_irq_off
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
 /*
  * Handle a system call.
  */
@@ -323,36 +351,16 @@
 	stw	r3,ORIG_GPR3(r1)
 	li	r12,0
 	stw	r12,RESULT(r1)
-	lwz	r11,_CCR(r1)	/* Clear SO bit in CR */
-	rlwinm	r11,r11,0,4,2
-	stw	r11,_CCR(r1)
 #ifdef CONFIG_TRACE_IRQFLAGS
-	/* Return from syscalls can (and generally will) hard enable
-	 * interrupts. You aren't supposed to call a syscall with
-	 * interrupts disabled in the first place. However, to ensure
-	 * that we get it right vs. lockdep if it happens, we force
-	 * that hard enable here with appropriate tracing if we see
-	 * that we have been called with interrupts off
-	 */
+	/* Make sure interrupts are enabled */
 	mfmsr	r11
 	andi.	r12,r11,MSR_EE
-	bne+	1f
-	/* We came in with interrupts disabled, we enable them now */
-	bl	trace_hardirqs_on
-	mfmsr	r11
-	lwz	r0,GPR0(r1)
-	lwz	r3,GPR3(r1)
-	lwz	r4,GPR4(r1)
-	ori	r11,r11,MSR_EE
-	lwz	r5,GPR5(r1)
-	lwz	r6,GPR6(r1)
-	lwz	r7,GPR7(r1)
-	lwz	r8,GPR8(r1)
-	mtmsr	r11
-1:
+	/* We came in with interrupts disabled, we WARN and mark them enabled
+	 * for lockdep now */
+0:	tweqi	r12, 0
+	EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
 #endif /* CONFIG_TRACE_IRQFLAGS */
-	CURRENT_THREAD_INFO(r10, r1)
-	lwz	r11,TI_FLAGS(r10)
+	lwz	r11,TI_FLAGS(r2)
 	andi.	r11,r11,_TIF_SYSCALL_DOTRACE
 	bne-	syscall_dotrace
 syscall_dotrace_cont:
@@ -385,13 +393,12 @@
 	lwz	r3,GPR3(r1)
 #endif
 	mr	r6,r3
-	CURRENT_THREAD_INFO(r12, r1)
 	/* disable interrupts so current_thread_info()->flags can't change */
-	LOAD_MSR_KERNEL(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
+	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
 	/* Note: We don't bother telling lockdep about it */
 	SYNC
 	MTMSRD(r10)
-	lwz	r9,TI_FLAGS(r12)
+	lwz	r9,TI_FLAGS(r2)
 	li	r8,-MAX_ERRNO
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	syscall_exit_work
@@ -405,8 +412,7 @@
 	lwz	r8,_MSR(r1)
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/* If we are going to return from the syscall with interrupts
-	 * off, we trace that here. It shouldn't happen though but we
-	 * want to catch the bugger if it does right ?
+	 * off, we trace that here. It shouldn't normally happen.
 	 */
 	andi.	r10,r8,MSR_EE
 	bne+	1f
@@ -435,13 +441,11 @@
 	lwarx	r7,0,r1
 END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	stwcx.	r0,0,r1			/* to clear the reservation */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	andi.	r4,r8,MSR_PR
-	beq	3f
-	CURRENT_THREAD_INFO(r4, r1)
-	ACCOUNT_CPU_USER_EXIT(r4, r5, r7)
-3:
+	ACCOUNT_CPU_USER_EXIT(r2, r5, r7)
+#ifdef CONFIG_PPC_BOOK3S_32
+	kuep_unlock r5, r7
 #endif
+	kuap_check r2, r4
 	lwz	r4,_LINK(r1)
 	lwz	r5,_CCR(r1)
 	mtlr	r4
@@ -532,7 +536,7 @@
 	/* Clear per-syscall TIF flags if any are set.  */
 
 	li	r11,_TIF_PERSYSCALL_MASK
-	addi	r12,r12,TI_FLAGS
+	addi	r12,r2,TI_FLAGS
 3:	lwarx	r8,0,r12
 	andc	r8,r8,r11
 #ifdef CONFIG_IBM405_ERR77
@@ -540,7 +544,6 @@
 #endif
 	stwcx.	r8,0,r12
 	bne-	3b
-	subi	r12,r12,TI_FLAGS
 	
 4:	/* Anything which requires enabling interrupts? */
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
@@ -594,6 +597,14 @@
 	stw	r0,_TRAP(r1)		/* register set saved */
 	b	sys_clone
 
+	.globl	ppc_clone3
+ppc_clone3:
+	SAVE_NVGPRS(r1)
+	lwz	r0,_TRAP(r1)
+	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
+	stw	r0,_TRAP(r1)		/* register set saved */
+	b	sys_clone3
+
 	.globl	ppc_swapcontext
 ppc_swapcontext:
 	SAVE_NVGPRS(r1)
@@ -612,7 +623,7 @@
 handle_page_fault:
 	stw	r4,_DAR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-#ifdef CONFIG_6xx
+#ifdef CONFIG_PPC_BOOK3S_32
 	andis.  r0,r5,DSISR_DABRMATCH@h
 	bne-    handle_dabr_fault
 #endif
@@ -629,7 +640,7 @@
 	bl	bad_page_fault
 	b	ret_from_except_full
 
-#ifdef CONFIG_6xx
+#ifdef CONFIG_PPC_BOOK3S_32
 	/* We have a data breakpoint exception - handle it */
 handle_dabr_fault:
 	SAVE_NVGPRS(r1)
@@ -693,6 +704,7 @@
 	stw	r10,_CCR(r1)
 	stw	r1,KSP(r3)	/* Set old stack pointer */
 
+	kuap_check r2, r4
 #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
@@ -745,6 +757,9 @@
 	mtcr	r10
 	lwz	r10,_LINK(r11)
 	mtlr	r10
+	/* 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
@@ -762,11 +777,19 @@
 1:	lis	r3,exc_exit_restart_end@ha
 	addi	r3,r3,exc_exit_restart_end@l
 	cmplw	r12,r3
+#if CONFIG_PPC_BOOK3S_601
+	bge	2b
+#else
 	bge	3f
+#endif
 	lis	r4,exc_exit_restart@ha
 	addi	r4,r4,exc_exit_restart@l
 	cmplw	r12,r4
+#if CONFIG_PPC_BOOK3S_601
+	blt	2b
+#else
 	blt	3f
+#endif
 	lis	r3,fee_restarts@ha
 	tophys(r3,r3)
 	lwz	r5,fee_restarts@l(r3)
@@ -785,16 +808,13 @@
 /* aargh, we don't know which trap this is */
 /* but the 601 doesn't implement the RI bit, so assume it's OK */
 3:
-BEGIN_FTR_SECTION
-	b	2b
-END_FTR_SECTION_IFSET(CPU_FTR_601)
 	li	r10,-1
 	stw	r10,_TRAP(r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	lis	r10,MSR_KERNEL@h
 	ori	r10,r10,MSR_KERNEL@l
 	bl	transfer_to_handler_full
-	.long	nonrecoverable_exception
+	.long	unrecoverable_exception
 	.long	ret_from_except
 #endif
 
@@ -809,7 +829,7 @@
 	 * can't change between when we test it and when we return
 	 * from the interrupt. */
 	/* Note: We don't bother telling lockdep about it */
-	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
 	SYNC			/* Some chip revs have problems here... */
 	MTMSRD(r10)		/* disable interrupts */
 
@@ -819,8 +839,7 @@
 
 user_exc_return:		/* r10 contains MSR_KERNEL here */
 	/* Check current_thread_info()->flags */
-	CURRENT_THREAD_INFO(r9, r1)
-	lwz	r9,TI_FLAGS(r9)
+	lwz	r9,TI_FLAGS(r2)
 	andi.	r0,r9,_TIF_USER_WORK_MASK
 	bne	do_work
 
@@ -832,9 +851,9 @@
 	andis.	r10,r0,DBCR0_IDM@h
 	bnel-	load_dbcr0
 #endif
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	CURRENT_THREAD_INFO(r9, r1)
-	ACCOUNT_CPU_USER_EXIT(r9, r10, r11)
+	ACCOUNT_CPU_USER_EXIT(r2, r10, r11)
+#ifdef CONFIG_PPC_BOOK3S_32
+	kuep_unlock	r10, r11
 #endif
 
 	b	restore
@@ -842,8 +861,7 @@
 /* N.B. the only way to get here is from the beq following ret_from_except. */
 resume_kernel:
 	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
-	CURRENT_THREAD_INFO(r9, r1)
-	lwz	r8,TI_FLAGS(r9)
+	lwz	r8,TI_FLAGS(r2)
 	andis.	r0,r8,_TIF_EMULATE_STACK_STORE@h
 	beq+	1f
 
@@ -869,7 +887,7 @@
 
 	/* Clear _TIF_EMULATE_STACK_STORE flag */
 	lis	r11,_TIF_EMULATE_STACK_STORE@h
-	addi	r5,r9,TI_FLAGS
+	addi	r5,r2,TI_FLAGS
 0:	lwarx	r8,0,r5
 	andc	r8,r8,r11
 #ifdef CONFIG_IBM405_ERR77
@@ -881,14 +899,14 @@
 
 #ifdef CONFIG_PREEMPT
 	/* check current_thread_info->preempt_count */
-	lwz	r0,TI_PREEMPT(r9)
+	lwz	r0,TI_PREEMPT(r2)
 	cmpwi	0,r0,0		/* if non-zero, just restore regs and return */
-	bne	restore
+	bne	restore_kuap
 	andi.	r8,r8,_TIF_NEED_RESCHED
-	beq+	restore
+	beq+	restore_kuap
 	lwz	r3,_MSR(r1)
 	andi.	r0,r3,MSR_EE	/* interrupts off? */
-	beq	restore		/* don't schedule if so */
+	beq	restore_kuap	/* don't schedule if so */
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/* Lockdep thinks irqs are enabled, we need to call
 	 * preempt_schedule_irq with IRQs off, so we inform lockdep
@@ -896,11 +914,7 @@
 	 */
 	bl	trace_hardirqs_off
 #endif
-1:	bl	preempt_schedule_irq
-	CURRENT_THREAD_INFO(r9, r1)
-	lwz	r3,TI_FLAGS(r9)
-	andi.	r0,r3,_TIF_NEED_RESCHED
-	bne-	1b
+	bl	preempt_schedule_irq
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/* And now, to properly rebalance the above, we tell lockdep they
 	 * are being turned back on, which will happen when we return
@@ -908,6 +922,8 @@
 	bl	trace_hardirqs_on
 #endif
 #endif /* CONFIG_PREEMPT */
+restore_kuap:
+	kuap_restore r1, r2, r9, r10, r0
 
 	/* interrupts are hard-disabled at this point */
 restore:
@@ -931,28 +947,14 @@
 	 * off in this assembly code while peeking at TI_FLAGS() and such. However
 	 * we need to inform it if the exception turned interrupts off, and we
 	 * are about to trun them back on.
-	 *
-	 * The problem here sadly is that we don't know whether the exceptions was
-	 * one that turned interrupts off or not. So we always tell lockdep about
-	 * turning them on here when we go back to wherever we came from with EE
-	 * on, even if that may meen some redudant calls being tracked. Maybe later
-	 * we could encode what the exception did somewhere or test the exception
-	 * type in the pt_regs but that sounds overkill
 	 */
 	andi.	r10,r9,MSR_EE
 	beq	1f
-	/*
-	 * Since the ftrace irqsoff latency trace checks CALLER_ADDR1,
-	 * which is the stack frame here, we need to force a stack frame
-	 * in case we came from user space.
-	 */
 	stwu	r1,-32(r1)
 	mflr	r0
 	stw	r0,4(r1)
-	stwu	r1,-32(r1)
 	bl	trace_hardirqs_on
-	lwz	r1,0(r1)
-	lwz	r1,0(r1)
+	addi	r1, r1, 32
 	lwz	r9,_MSR(r1)
 1:
 #endif /* CONFIG_TRACE_IRQFLAGS */
@@ -982,6 +984,9 @@
 	mtcrf	0xFF,r10
 	mtlr	r11
 
+	/* Clear the exception_marker on the stack to avoid confusing stacktrace */
+	li	r10, 0
+	stw	r10, 8(r1)
 	/*
 	 * Once we put values in SRR0 and SRR1, we are in a state
 	 * where exceptions are not recoverable, since taking an
@@ -991,15 +996,12 @@
 	 * can restart the exception exit path at the label
 	 * exc_exit_restart below.  -- paulus
 	 */
-	LOAD_MSR_KERNEL(r10,MSR_KERNEL & ~MSR_RI)
+	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI)
 	SYNC
 	MTMSRD(r10)		/* clear the RI bit */
 	.globl exc_exit_restart
 exc_exit_restart:
 	lwz	r12,_NIP(r1)
-#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
-	mtspr	SPRN_NRI, r0
-#endif
 	mtspr	SPRN_SRR0,r12
 	mtspr	SPRN_SRR1,r9
 	REST_4GPRS(9, r1)
@@ -1021,6 +1023,9 @@
 	mtlr	r11
 	lwz	r10,_CCR(r1)
 	mtcrf	0xff,r10
+	/* Clear the exception_marker on the stack to avoid confusing stacktrace */
+	li	r10, 0
+	stw	r10, 8(r1)
 	REST_2GPRS(9, r1)
 	.globl exc_exit_restart
 exc_exit_restart:
@@ -1066,7 +1071,7 @@
 	REST_NVGPRS(r1);						\
 	lwz	r3,_MSR(r1);						\
 	andi.	r3,r3,MSR_PR;						\
-	LOAD_MSR_KERNEL(r10,MSR_KERNEL);				\
+	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL);				\
 	bne	user_exc_return;					\
 	lwz	r0,GPR0(r1);						\
 	lwz	r2,GPR2(r1);						\
@@ -1166,10 +1171,6 @@
 	mfspr	r9,SPRN_SPRG_THREAD
 	lwz	r10,SAVED_KSP_LIMIT(r1)
 	stw	r10,KSP_LIMIT(r9)
-	lwz	r9,THREAD_INFO-THREAD(r9)
-	CURRENT_THREAD_INFO(r10, r1)
-	lwz	r10,TI_PREEMPT(r10)
-	stw	r10,TI_PREEMPT(r9)
 	RESTORE_xSRR(SRR0,SRR1);
 	RESTORE_xSRR(CSRR0,CSRR1);
 	RESTORE_MMU_REGS;
@@ -1201,8 +1202,7 @@
 	lis	r11,global_dbcr0@ha
 	addi	r11,r11,global_dbcr0@l
 #ifdef CONFIG_SMP
-	CURRENT_THREAD_INFO(r9, r1)
-	lwz	r9,TI_CPU(r9)
+	lwz	r9,TASK_CPU(r2)
 	slwi	r9,r9,3
 	add	r11,r11,r9
 #endif
@@ -1217,6 +1217,7 @@
 
 	.section .bss
 	.align	4
+	.global global_dbcr0
 global_dbcr0:
 	.space	8*NR_CPUS
 	.previous
@@ -1227,9 +1228,10 @@
 	beq	do_user_signal
 
 do_resched:			/* r10 contains MSR_KERNEL here */
-	/* Note: We don't need to inform lockdep that we are enabling
-	 * interrupts here. As far as it knows, they are already enabled
-	 */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_on
+	mfmsr	r10
+#endif
 	ori	r10,r10,MSR_EE
 	SYNC
 	MTMSRD(r10)		/* hard-enable interrupts */
@@ -1239,11 +1241,10 @@
 	 * neither. Those disable/enable cycles used to peek at
 	 * TI_FLAGS aren't advertised.
 	 */
-	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
 	SYNC
 	MTMSRD(r10)		/* disable interrupts */
-	CURRENT_THREAD_INFO(r9, r1)
-	lwz	r9,TI_FLAGS(r9)
+	lwz	r9,TI_FLAGS(r2)
 	andi.	r0,r9,_TIF_NEED_RESCHED
 	bne-	do_resched
 	andi.	r0,r9,_TIF_USER_WORK_MASK
@@ -1274,11 +1275,19 @@
 	lis	r10,exc_exit_restart_end@ha
 	addi	r10,r10,exc_exit_restart_end@l
 	cmplw	r12,r10
+#ifdef CONFIG_PPC_BOOK3S_601
+	bgelr
+#else
 	bge	3f
+#endif
 	lis	r11,exc_exit_restart@ha
 	addi	r11,r11,exc_exit_restart@l
 	cmplw	r12,r11
+#ifdef CONFIG_PPC_BOOK3S_601
+	bltlr
+#else
 	blt	3f
+#endif
 	lis	r10,ee_restarts@ha
 	lwz	r12,ee_restarts@l(r10)
 	addi	r12,r12,1
@@ -1287,17 +1296,17 @@
 	blr
 3:	/* OK, we can't recover, kill this process */
 	/* but the 601 doesn't implement the RI bit, so assume it's OK */
-BEGIN_FTR_SECTION
-	blr
-END_FTR_SECTION_IFSET(CPU_FTR_601)
 	lwz	r3,_TRAP(r1)
 	andi.	r0,r3,1
-	beq	4f
+	beq	5f
 	SAVE_NVGPRS(r1)
 	rlwinm	r3,r3,0,0,30
 	stw	r3,_TRAP(r1)
+5:	mfspr	r2,SPRN_SPRG_THREAD
+	addi	r2,r2,-THREAD
+	tovirt(r2,r2)			/* set back r2 to current */
 4:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	nonrecoverable_exception
+	bl	unrecoverable_exception
 	/* shouldn't return */
 	b	4b
 
@@ -1330,12 +1339,12 @@
 	lwz	r4,RTASBASE(r4)
 	mfmsr	r9
 	stw	r9,8(r1)
-	LOAD_MSR_KERNEL(r0,MSR_KERNEL)
+	LOAD_REG_IMMEDIATE(r0,MSR_KERNEL)
 	SYNC			/* disable interrupts so SRR0/1 */
 	MTMSRD(r0)		/* don't get trashed */
 	li	r9,MSR_KERNEL & ~(MSR_IR|MSR_DR)
 	mtlr	r6
-	mtspr	SPRN_SPRG_RTAS,r7
+	stw	r7, THREAD + RTAS_SP(r2)
 	mtspr	SPRN_SRR0,r8
 	mtspr	SPRN_SRR1,r9
 	RFI
@@ -1344,7 +1353,8 @@
 	lwz	r9,8(r9)	/* original msr value */
 	addi	r1,r1,INT_FRAME_SIZE
 	li	r0,0
-	mtspr	SPRN_SPRG_RTAS,r0
+	tophys(r7, r2)
+	stw	r0, THREAD + RTAS_SP(r7)
 	mtspr	SPRN_SRR0,r8
 	mtspr	SPRN_SRR1,r9
 	RFI			/* return to caller */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 2206912..3fd3ef3 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  PowerPC version 
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -11,11 +12,6 @@
  *
  *  This file contains the system call entry code, context switch
  *  code, and exception/interrupt return code for PowerPC.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/errno.h>
@@ -46,6 +42,7 @@
 #include <asm/exception-64e.h>
 #endif
 #include <asm/feature-fixups.h>
+#include <asm/kup.h>
 
 /*
  * System calls.
@@ -54,6 +51,9 @@
 SYS_CALL_TABLE:
 	.tc sys_call_table[TC],sys_call_table
 
+COMPAT_SYS_CALL_TABLE:
+	.tc compat_sys_call_table[TC],compat_sys_call_table
+
 /* This value is used to mark exception frames on the stack. */
 exception_marker:
 	.tc	ID_EXC_MARKER[TC],STACK_FRAME_REGS_MARKER
@@ -69,19 +69,20 @@
 	bne	.Ltabort_syscall
 END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
-	andi.	r10,r12,MSR_PR
 	mr	r10,r1
-	addi	r1,r1,-INT_FRAME_SIZE
-	beq-	1f
 	ld	r1,PACAKSAVE(r13)
-1:	std	r10,0(r1)
+	std	r10,0(r1)
 	std	r11,_NIP(r1)
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
-	beq	2f			/* if from kernel mode */
+#ifdef CONFIG_PPC_FSL_BOOK3E
+START_BTB_FLUSH_SECTION
+	BTB_FLUSH(r10)
+END_BTB_FLUSH_SECTION
+#endif
 	ACCOUNT_CPU_USER_ENTRY(r13, r10, r11)
-2:	std	r2,GPR2(r1)
+	std	r2,GPR2(r1)
 	std	r3,GPR3(r1)
 	mfcr	r2
 	std	r4,GPR4(r1)
@@ -112,16 +113,18 @@
 	addi	r9,r1,STACK_FRAME_OVERHEAD
 	ld	r11,exception_marker@toc(r2)
 	std	r11,-16(r9)		/* "regshere" marker */
+
+	kuap_check_amr r10, r11
+
 #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR)
 BEGIN_FW_FTR_SECTION
-	beq	33f
-	/* if from user, see if there are any DTL entries to process */
+	/* see if there are any DTL entries to process */
 	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
 	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
 	addi	r10,r10,LPPACA_DTLIDX
 	LDX_BE	r10,0,r10		/* get log write index */
-	cmpd	cr1,r11,r10
-	beq+	cr1,33f
+	cmpd	r11,r10
+	beq+	33f
 	bl	accumulate_stolen_time
 	REST_GPR(0,r1)
 	REST_4GPRS(3,r1)
@@ -158,7 +161,7 @@
 	li	r10,IRQS_ENABLED
 	std	r10,SOFTE(r1)
 
-	CURRENT_THREAD_INFO(r11, r1)
+	ld	r11, PACA_THREAD_INFO(r13)
 	ld	r10,TI_FLAGS(r11)
 	andi.	r11,r10,_TIF_SYSCALL_DOTRACE
 	bne	.Lsyscall_dotrace		/* does not return */
@@ -171,9 +174,9 @@
  * based on caller's run-mode / personality.
  */
 	ld	r11,SYS_CALL_TABLE@toc(2)
-	andi.	r10,r10,_TIF_32BIT
+	andis.	r10,r10,_TIF_32BIT@h
 	beq	15f
-	addi	r11,r11,8	/* use 32-bit syscall entries */
+	ld	r11,COMPAT_SYS_CALL_TABLE@toc(2)
 	clrldi	r3,r3,32
 	clrldi	r4,r4,32
 	clrldi	r5,r5,32
@@ -181,7 +184,7 @@
 	clrldi	r7,r7,32
 	clrldi	r8,r8,32
 15:
-	slwi	r0,r0,4
+	slwi	r0,r0,3
 
 	barrier_nospec_asm
 	/*
@@ -195,6 +198,7 @@
 	mtctr   r12
 	bctrl			/* Call handler */
 
+	/* syscall_exit can exit to kernel mode, via ret_from_kernel_thread */
 .Lsyscall_exit:
 	std	r3,RESULT(r1)
 
@@ -205,14 +209,9 @@
 	ld	r3,RESULT(r1)
 #endif
 
-	CURRENT_THREAD_INFO(r12, r1)
+	ld	r12, PACA_THREAD_INFO(r13)
 
 	ld	r8,_MSR(r1)
-#ifdef CONFIG_PPC_BOOK3S
-	/* No MSR:RI on BookE */
-	andi.	r10,r8,MSR_RI
-	beq-	.Lunrecov_restore
-#endif
 
 /*
  * This is a few instructions into the actual syscall exit path (which actually
@@ -228,18 +227,14 @@
 	/*
 	 * Disable interrupts so current_thread_info()->flags can't change,
 	 * and so that we don't get interrupted after loading SRR0/1.
+	 *
+	 * Leave MSR_RI enabled for now, because with THREAD_INFO_IN_TASK we
+	 * could fault on the load of the TI_FLAGS below.
 	 */
 #ifdef CONFIG_PPC_BOOK3E
 	wrteei	0
 #else
-	/*
-	 * For performance reasons we clear RI the same time that we
-	 * clear EE. We only need to clear RI just before we restore r13
-	 * below, but batching it with EE saves us one expensive mtmsrd call.
-	 * We have to be careful to restore RI if we branch anywhere from
-	 * here (eg syscall_exit_work).
-	 */
-	li	r11,0
+	li	r11,MSR_RI
 	mtmsrd	r11,1
 #endif /* CONFIG_PPC_BOOK3E */
 
@@ -255,15 +250,7 @@
 	bne	3f
 #endif
 2:	addi    r3,r1,STACK_FRAME_OVERHEAD
-#ifdef CONFIG_PPC_BOOK3S
-	li	r10,MSR_RI
-	mtmsrd	r10,1		/* Restore RI */
-#endif
 	bl	restore_math
-#ifdef CONFIG_PPC_BOOK3S
-	li	r11,0
-	mtmsrd	r11,1
-#endif
 	ld	r8,_MSR(r1)
 	ld	r3,RESULT(r1)
 	li	r11,-MAX_ERRNO
@@ -279,6 +266,18 @@
 	andi.	r6,r8,MSR_PR
 	ld	r4,_LINK(r1)
 
+	kuap_check_amr r10, r11
+
+#ifdef CONFIG_PPC_BOOK3S
+	/*
+	 * Clear MSR_RI, MSR_EE is already and remains disabled. We could do
+	 * this later, but testing shows that doing it here causes less slow
+	 * down than doing it closer to the rfid.
+	 */
+	li	r11,0
+	mtmsrd	r11,1
+#endif
+
 	beq-	1f
 	ACCOUNT_CPU_USER_EXIT(r13, r11, r12)
 
@@ -286,6 +285,14 @@
 	HMT_MEDIUM_LOW
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	std	r8, PACATMSCRATCH(r13)
+#endif
+
+	/*
+	 * We don't need to restore AMR on the way back to userspace for KUAP.
+	 * The value of AMR only matters while we're in the kernel.
+	 */
 	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
 	ld	r2,GPR2(r1)
 	ld	r1,GPR1(r1)
@@ -296,8 +303,10 @@
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 
-	/* exit to kernel */
-1:	ld	r2,GPR2(r1)
+1:	/* exit to kernel */
+	kuap_restore_amr r2
+
+	ld	r2,GPR2(r1)
 	ld	r1,GPR1(r1)
 	mtlr	r4
 	mtcr	r5
@@ -336,7 +345,7 @@
 
 	/* Repopulate r9 and r10 for the syscall path */
 	addi	r9,r1,STACK_FRAME_OVERHEAD
-	CURRENT_THREAD_INFO(r10, r1)
+	ld	r10, PACA_THREAD_INFO(r13)
 	ld	r10,TI_FLAGS(r10)
 
 	cmpldi	r0,NR_syscalls
@@ -351,10 +360,6 @@
 	b	.Lsyscall_exit
 	
 .Lsyscall_exit_work:
-#ifdef CONFIG_PPC_BOOK3S
-	li	r10,MSR_RI
-	mtmsrd	r10,1		/* Restore RI */
-#endif
 	/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
 	 If TIF_NOERROR is set, just save r3 as it is. */
 
@@ -386,10 +391,9 @@
 
 4:	/* Anything else left to do? */
 BEGIN_FTR_SECTION
-	lis	r3,INIT_PPR@highest	/* Set thread.ppr = 3 */
-	ld	r10,PACACURRENT(r13)
+	lis	r3,DEFAULT_PPR@highest	/* Set default PPR */
 	sldi	r3,r3,32	/* bits 11-13 are used for ppr */
-	std	r3,TASKTHREADPPR(r10)
+	std	r3,_PPR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
@@ -474,6 +478,11 @@
 	bl	sys_clone
 	b	.Lsyscall_exit
 
+_GLOBAL(ppc_clone3)
+       bl      save_nvgprs
+       bl      sys_clone3
+       b       .Lsyscall_exit
+
 _GLOBAL(ppc32_swapcontext)
 	bl	save_nvgprs
 	bl	compat_sys_swapcontext
@@ -528,6 +537,7 @@
 	/* Save LR into r9 */
 	mflr	r9
 
+	// Flush the link stack
 	.rept 64
 	bl	.+4
 	.endr
@@ -537,6 +547,11 @@
 	.balign 32
 	/* Restore LR */
 1:	mtlr	r9
+
+	// If we're just flushing the link stack, return here
+3:	nop
+	patch_site 3b patch__flush_link_stack_return
+
 	li	r9,0x7fff
 	mtctr	r9
 
@@ -589,6 +604,8 @@
 	std	r23,_CCR(r1)
 	std	r1,KSP(r3)	/* Set old stack pointer */
 
+	kuap_check_amr r9, r10
+
 	FLUSH_COUNT_CACHE
 
 	/*
@@ -624,6 +641,10 @@
 
 	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_BOOK3S_64
@@ -672,13 +693,15 @@
 
 	isync
 	slbie	r6
+BEGIN_FTR_SECTION
 	slbie	r6		/* Workaround POWER5 < DD2.1 issue */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	slbmte	r7,r0
 	isync
 2:
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
-	CURRENT_THREAD_INFO(r7, r8)  /* base of new stack */
+	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. */
@@ -729,7 +752,7 @@
 	mtmsrd	r10,1		  /* Update machine state */
 #endif /* CONFIG_PPC_BOOK3E */
 
-	CURRENT_THREAD_INFO(r9, r1)
+	ld	r9, PACA_THREAD_INFO(r13)
 	ld	r3,_MSR(r1)
 #ifdef CONFIG_PPC_BOOK3E
 	ld	r10,PACACURRENT(r13)
@@ -840,13 +863,7 @@
 	 * sure we are soft-disabled first and reconcile irq state.
 	 */
 	RECONCILE_IRQ_STATE(r3,r4)
-1:	bl	preempt_schedule_irq
-
-	/* Re-test flags and eventually loop */
-	CURRENT_THREAD_INFO(r9, r1)
-	ld	r4,TI_FLAGS(r9)
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	bne	1b
+	bl	preempt_schedule_irq
 
 	/*
 	 * arch_local_irq_restore() from preempt_schedule_irq above may
@@ -931,17 +948,13 @@
 	ld	r4,_XER(r1)
 	mtspr	SPRN_XER,r4
 
+	kuap_check_amr r5, r6
+
 	REST_8GPRS(5, r1)
 
 	andi.	r0,r3,MSR_RI
 	beq-	.Lunrecov_restore
 
-	/* Load PPR from thread struct before we clear MSR:RI */
-BEGIN_FTR_SECTION
-	ld	r2,PACACURRENT(r13)
-	ld	r2,TASKTHREADPPR(r2)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-
 	/*
 	 * Clear RI before restoring r13.  If we are returning to
 	 * userspace and we take an exception after restoring r13,
@@ -962,11 +975,17 @@
 	andi.	r0,r3,MSR_PR
 	beq	1f
 BEGIN_FTR_SECTION
-	mtspr	SPRN_PPR,r2	/* Restore PPR */
+	/* Restore PPR */
+	ld	r2,_PPR(r1)
+	mtspr	SPRN_PPR,r2
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
 	REST_GPR(13, r1)
 
+	/*
+	 * We don't need to restore AMR on the way back to userspace for KUAP.
+	 * The value of AMR only matters while we're in the kernel.
+	 */
 	mtspr	SPRN_SRR1,r3
 
 	ld	r2,_CCR(r1)
@@ -989,9 +1008,19 @@
 	ld	r2,_NIP(r1)
 	mtspr	SPRN_SRR0,r2
 
+	/*
+	 * Leaving a stale exception_marker on the stack can confuse
+	 * the reliable stack unwinder later on. Clear it.
+	 */
+	li	r2,0
+	std	r2,STACK_FRAME_OVERHEAD-16(r1)
+
 	ld	r0,GPR0(r1)
 	ld	r2,GPR2(r1)
 	ld	r3,GPR3(r1)
+
+	kuap_restore_amr r4
+
 	ld	r4,GPR4(r1)
 	ld	r1,GPR1(r1)
 	RFI_TO_KERNEL
@@ -1118,7 +1147,7 @@
 _GLOBAL(enter_rtas)
 	mflr	r0
 	std	r0,16(r1)
-        stdu	r1,-RTAS_FRAME_SIZE(r1)	/* Save SP and create stack space. */
+        stdu	r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space. */
 
 	/* Because RTAS is running in 32b mode, it clobbers the high order half
 	 * of all registers that it saves.  We therefore save those registers
@@ -1250,7 +1279,7 @@
 	ld	r8,_DSISR(r1)
 	mtdsisr	r8
 
-        addi	r1,r1,RTAS_FRAME_SIZE	/* Unstack our frame */
+        addi	r1,r1,SWITCH_FRAME_SIZE	/* Unstack our frame */
 	ld	r0,16(r1)		/* get return address */
 
 	mtlr    r0
@@ -1261,7 +1290,7 @@
 _GLOBAL(enter_prom)
 	mflr	r0
 	std	r0,16(r1)
-        stdu	r1,-PROM_FRAME_SIZE(r1)	/* Save SP and create stack space */
+        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
@@ -1318,8 +1347,8 @@
 	REST_10GPRS(22, r1)
 	ld	r4,_CCR(r1)
 	mtcr	r4
-	
-        addi	r1,r1,PROM_FRAME_SIZE
+
+        addi	r1,r1,SWITCH_FRAME_SIZE
 	ld	r0,16(r1)
 	mtlr    r0
         blr
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
index 52ca247..69a9125 100644
--- a/arch/powerpc/kernel/epapr_hcalls.S
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2012 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/threads.h>
@@ -21,10 +17,9 @@
 #ifndef CONFIG_PPC64
 /* epapr_ev_idle() was derived from e500_idle() */
 _GLOBAL(epapr_ev_idle)
-	CURRENT_THREAD_INFO(r3, r1)
-	PPC_LL	r4, TI_LOCAL_FLAGS(r3)	/* set napping bit */
+	PPC_LL	r4, TI_LOCAL_FLAGS(r2)	/* set napping bit */
 	ori	r4, r4,_TLF_NAPPING	/* so when we take an exception */
-	PPC_STL	r4, TI_LOCAL_FLAGS(r3)	/* it will return to our caller */
+	PPC_STL	r4, TI_LOCAL_FLAGS(r2)	/* it will return to our caller */
 
 	wrteei	1
 
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index 59e4ba7..9d32158 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * ePAPR para-virtualization support.
  *
- * 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 (C) 2012 Freescale Semiconductor, Inc.
  */
 
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 6d6e144..829950b 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  Boot code and exception vectors for Book3E processors
  *
  *  Copyright (C) 2007 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/threads.h>
@@ -77,17 +73,6 @@
 	andi.	r3,r3,MSR_PR
 	bnelr
 
-	/* Copy info into temporary exception thread info */
-	ld	r11,PACAKSAVE(r13)
-	CURRENT_THREAD_INFO(r11, r11)
-	CURRENT_THREAD_INFO(r12, r1)
-	ld	r10,TI_FLAGS(r11)
-	std	r10,TI_FLAGS(r12)
-	ld	r10,TI_PREEMPT(r11)
-	std	r10,TI_PREEMPT(r12)
-	ld	r10,TI_TASK(r11)
-	std	r10,TI_TASK(r12)
-
 	/*
 	 * Advance to the next TLB exception frame for handler
 	 * types that don't do it automatically.
@@ -296,7 +281,8 @@
 	andi.	r10,r11,MSR_PR;		/* save stack pointer */	    \
 	beq	1f;			/* branch around if supervisor */   \
 	ld	r1,PACAKSAVE(r13);	/* get kernel stack coming from usr */\
-1:	cmpdi	cr1,r1,0;		/* check if SP makes sense */	    \
+1:	type##_BTB_FLUSH		\
+	cmpdi	cr1,r1,0;		/* check if SP makes sense */	    \
 	bge-	cr1,exc_##n##_bad_stack;/* bad stack (TODO: out of line) */ \
 	mfspr	r10,SPRN_##type##_SRR0;	/* read SRR0 before touching stack */
 
@@ -328,6 +314,30 @@
 #define SPRN_MC_SRR0	SPRN_MCSRR0
 #define SPRN_MC_SRR1	SPRN_MCSRR1
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+#define GEN_BTB_FLUSH			\
+	START_BTB_FLUSH_SECTION		\
+		beq 1f;			\
+		BTB_FLUSH(r10)			\
+		1:		\
+	END_BTB_FLUSH_SECTION
+
+#define CRIT_BTB_FLUSH			\
+	START_BTB_FLUSH_SECTION		\
+		BTB_FLUSH(r10)		\
+	END_BTB_FLUSH_SECTION
+
+#define DBG_BTB_FLUSH CRIT_BTB_FLUSH
+#define MC_BTB_FLUSH CRIT_BTB_FLUSH
+#define GDBELL_BTB_FLUSH GEN_BTB_FLUSH
+#else
+#define GEN_BTB_FLUSH
+#define CRIT_BTB_FLUSH
+#define DBG_BTB_FLUSH
+#define MC_BTB_FLUSH
+#define GDBELL_BTB_FLUSH
+#endif
+
 #define NORMAL_EXCEPTION_PROLOG(n, intnum, addition)			    \
 	EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n))
 
@@ -480,7 +490,7 @@
  * interrupts happen before the wait instruction.
  */
 #define CHECK_NAPPING()							\
-	CURRENT_THREAD_INFO(r11, r1);					\
+	ld	r11, PACA_THREAD_INFO(r13);				\
 	ld	r10,TI_LOCAL_FLAGS(r11);				\
 	andi.	r9,r10,_TLF_NAPPING;					\
 	beq+	1f;							\
@@ -740,12 +750,14 @@
 	ld	r15,PACATOC(r13)
 	ld	r14,interrupt_base_book3e@got(r15)
 	ld	r15,__end_interrupts@got(r15)
-#else
-	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
-	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
-#endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
+#else
+	LOAD_REG_IMMEDIATE_SYM(r14, r15, interrupt_base_book3e)
+	cmpld	cr0, r10, r14
+	LOAD_REG_IMMEDIATE_SYM(r14, r15, __end_interrupts)
+	cmpld	cr1, r10, r14
+#endif
 	blt+	cr0,1f
 	bge+	cr1,1f
 
@@ -810,12 +822,14 @@
 	ld	r15,PACATOC(r13)
 	ld	r14,interrupt_base_book3e@got(r15)
 	ld	r15,__end_interrupts@got(r15)
-#else
-	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
-	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
-#endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
+#else
+	LOAD_REG_IMMEDIATE_SYM(r14, r15, interrupt_base_book3e)
+	cmpld	cr0, r10, r14
+	LOAD_REG_IMMEDIATE_SYM(r14, r15,__end_interrupts)
+	cmpld	cr1, r10, r14
+#endif
 	blt+	cr0,1f
 	bge+	cr1,1f
 
@@ -1439,7 +1453,7 @@
 a2_tlbinit_after_linear_map:
 
 	/* Now we branch the new virtual address mapped by this entry */
-	LOAD_REG_IMMEDIATE(r3,1f)
+	LOAD_REG_IMMEDIATE_SYM(r3, r5, 1f)
 	mtctr	r3
 	bctr
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 2d8fc8c..d0018dd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -19,6 +19,678 @@
 #include <asm/cpuidle.h>
 #include <asm/head-64.h>
 #include <asm/feature-fixups.h>
+#include <asm/kup.h>
+
+/* PACA save area offsets (exgen, exmc, etc) */
+#define EX_R9		0
+#define EX_R10		8
+#define EX_R11		16
+#define EX_R12		24
+#define EX_R13		32
+#define EX_DAR		40
+#define EX_DSISR	48
+#define EX_CCR		52
+#define EX_CFAR		56
+#define EX_PPR		64
+#if defined(CONFIG_RELOCATABLE)
+#define EX_CTR		72
+.if EX_SIZE != 10
+	.error "EX_SIZE is wrong"
+.endif
+#else
+.if EX_SIZE != 9
+	.error "EX_SIZE is wrong"
+.endif
+#endif
+
+/*
+ * Following are fixed section helper macros.
+ *
+ * EXC_REAL_BEGIN/END  - real, unrelocated exception vectors
+ * EXC_VIRT_BEGIN/END  - virt (AIL), unrelocated exception vectors
+ * TRAMP_REAL_BEGIN    - real, unrelocated helpers (virt may call these)
+ * TRAMP_VIRT_BEGIN    - virt, unreloc helpers (in practice, real can use)
+ * TRAMP_KVM_BEGIN     - KVM handlers, these are put into real, unrelocated
+ * EXC_COMMON          - After switching to virtual, relocated mode.
+ */
+
+#define EXC_REAL_BEGIN(name, start, size)			\
+	FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start, size)
+
+#define EXC_REAL_END(name, start, size)				\
+	FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##name, start, size)
+
+#define EXC_VIRT_BEGIN(name, start, size)			\
+	FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size)
+
+#define EXC_VIRT_END(name, start, size)				\
+	FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size)
+
+#define EXC_COMMON_BEGIN(name)					\
+	USE_TEXT_SECTION();					\
+	.balign IFETCH_ALIGN_BYTES;				\
+	.global name;						\
+	_ASM_NOKPROBE_SYMBOL(name);				\
+	DEFINE_FIXED_SYMBOL(name);				\
+name:
+
+#define TRAMP_REAL_BEGIN(name)					\
+	FIXED_SECTION_ENTRY_BEGIN(real_trampolines, name)
+
+#define TRAMP_VIRT_BEGIN(name)					\
+	FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name)
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#define TRAMP_KVM_BEGIN(name)					\
+	TRAMP_VIRT_BEGIN(name)
+#else
+#define TRAMP_KVM_BEGIN(name)
+#endif
+
+#define EXC_REAL_NONE(start, size)				\
+	FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start, size); \
+	FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, start, size)
+
+#define EXC_VIRT_NONE(start, size)				\
+	FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size); \
+	FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size)
+
+/*
+ * We're short on space and time in the exception prolog, so we can't
+ * use the normal LOAD_REG_IMMEDIATE macro to load the address of label.
+ * Instead we get the base of the kernel from paca->kernelbase and or in the low
+ * part of label. This requires that the label be within 64KB of kernelbase, and
+ * that kernelbase be 64K aligned.
+ */
+#define LOAD_HANDLER(reg, label)					\
+	ld	reg,PACAKBASE(r13);	/* get high part of &label */	\
+	ori	reg,reg,FIXED_SYMBOL_ABS_ADDR(label)
+
+#define __LOAD_HANDLER(reg, label)					\
+	ld	reg,PACAKBASE(r13);					\
+	ori	reg,reg,(ABS_ADDR(label))@l
+
+/*
+ * Branches from unrelocated code (e.g., interrupts) to labels outside
+ * head-y require >64K offsets.
+ */
+#define __LOAD_FAR_HANDLER(reg, label)					\
+	ld	reg,PACAKBASE(r13);					\
+	ori	reg,reg,(ABS_ADDR(label))@l;				\
+	addis	reg,reg,(ABS_ADDR(label))@h
+
+/* Exception register prefixes */
+#define EXC_HV_OR_STD	2 /* depends on HVMODE */
+#define EXC_HV		1
+#define EXC_STD		0
+
+#if defined(CONFIG_RELOCATABLE)
+/*
+ * If we support interrupts with relocation on AND we're a relocatable kernel,
+ * we need to use CTR to get to the 2nd level handler.  So, save/restore it
+ * when required.
+ */
+#define SAVE_CTR(reg, area)	mfctr	reg ; 	std	reg,area+EX_CTR(r13)
+#define GET_CTR(reg, area) 			ld	reg,area+EX_CTR(r13)
+#define RESTORE_CTR(reg, area)	ld	reg,area+EX_CTR(r13) ; mtctr reg
+#else
+/* ...else CTR is unused and in register. */
+#define SAVE_CTR(reg, area)
+#define GET_CTR(reg, area) 	mfctr	reg
+#define RESTORE_CTR(reg, area)
+#endif
+
+/*
+ * PPR save/restore macros used in exceptions-64s.S
+ * Used for P7 or later processors
+ */
+#define SAVE_PPR(area, ra)						\
+BEGIN_FTR_SECTION_NESTED(940)						\
+	ld	ra,area+EX_PPR(r13);	/* Read PPR from paca */	\
+	std	ra,_PPR(r1);						\
+END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,940)
+
+#define RESTORE_PPR_PACA(area, ra)					\
+BEGIN_FTR_SECTION_NESTED(941)						\
+	ld	ra,area+EX_PPR(r13);					\
+	mtspr	SPRN_PPR,ra;						\
+END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941)
+
+/*
+ * Get an SPR into a register if the CPU has the given feature
+ */
+#define OPT_GET_SPR(ra, spr, ftr)					\
+BEGIN_FTR_SECTION_NESTED(943)						\
+	mfspr	ra,spr;							\
+END_FTR_SECTION_NESTED(ftr,ftr,943)
+
+/*
+ * Set an SPR from a register if the CPU has the given feature
+ */
+#define OPT_SET_SPR(ra, spr, ftr)					\
+BEGIN_FTR_SECTION_NESTED(943)						\
+	mtspr	spr,ra;							\
+END_FTR_SECTION_NESTED(ftr,ftr,943)
+
+/*
+ * Save a register to the PACA if the CPU has the given feature
+ */
+#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr)				\
+BEGIN_FTR_SECTION_NESTED(943)						\
+	std	ra,offset(r13);						\
+END_FTR_SECTION_NESTED(ftr,ftr,943)
+
+/*
+ * Branch to label using its 0xC000 address. This results in instruction
+ * address suitable for MSR[IR]=0 or 1, which allows relocation to be turned
+ * on using mtmsr rather than rfid.
+ *
+ * This could set the 0xc bits for !RELOCATABLE as an immediate, rather than
+ * load KBASE for a slight optimisation.
+ */
+#define BRANCH_TO_C000(reg, label)					\
+	__LOAD_FAR_HANDLER(reg, label);					\
+	mtctr	reg;							\
+	bctr
+
+.macro INT_KVM_HANDLER name, vec, hsrr, area, skip
+	TRAMP_KVM_BEGIN(\name\()_kvm)
+	KVM_HANDLER \vec, \hsrr, \area, \skip
+.endm
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+/*
+ * If hv is possible, interrupts come into to the hv version
+ * of the kvmppc_interrupt code, which then jumps to the PR handler,
+ * kvmppc_interrupt_pr, if the guest is a PR guest.
+ */
+#define kvmppc_interrupt kvmppc_interrupt_hv
+#else
+#define kvmppc_interrupt kvmppc_interrupt_pr
+#endif
+
+.macro KVMTEST name, hsrr, n
+	lbz	r10,HSTATE_IN_GUEST(r13)
+	cmpwi	r10,0
+	bne	\name\()_kvm
+.endm
+
+.macro KVM_HANDLER vec, hsrr, area, skip
+	.if \skip
+	cmpwi	r10,KVM_GUEST_MODE_SKIP
+	beq	89f
+	.else
+BEGIN_FTR_SECTION_NESTED(947)
+	ld	r10,\area+EX_CFAR(r13)
+	std	r10,HSTATE_CFAR(r13)
+END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947)
+	.endif
+
+BEGIN_FTR_SECTION_NESTED(948)
+	ld	r10,\area+EX_PPR(r13)
+	std	r10,HSTATE_PPR(r13)
+END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
+	ld	r10,\area+EX_R10(r13)
+	std	r12,HSTATE_SCRATCH0(r13)
+	sldi	r12,r9,32
+	/* HSRR variants have the 0x2 bit added to their trap number */
+	.if \hsrr == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	ori	r12,r12,(\vec + 0x2)
+	FTR_SECTION_ELSE
+	ori	r12,r12,(\vec)
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif \hsrr
+	ori	r12,r12,(\vec + 0x2)
+	.else
+	ori	r12,r12,(\vec)
+	.endif
+
+#ifdef CONFIG_RELOCATABLE
+	/*
+	 * KVM requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives
+	 * outside the head section. CONFIG_RELOCATABLE KVM expects CTR
+	 * to be saved in HSTATE_SCRATCH1.
+	 */
+	mfctr	r9
+	std	r9,HSTATE_SCRATCH1(r13)
+	__LOAD_FAR_HANDLER(r9, kvmppc_interrupt)
+	mtctr	r9
+	ld	r9,\area+EX_R9(r13)
+	bctr
+#else
+	ld	r9,\area+EX_R9(r13)
+	b	kvmppc_interrupt
+#endif
+
+
+	.if \skip
+89:	mtocrf	0x80,r9
+	ld	r9,\area+EX_R9(r13)
+	ld	r10,\area+EX_R10(r13)
+	.if \hsrr == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	b	kvmppc_skip_Hinterrupt
+	FTR_SECTION_ELSE
+	b	kvmppc_skip_interrupt
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif \hsrr
+	b	kvmppc_skip_Hinterrupt
+	.else
+	b	kvmppc_skip_interrupt
+	.endif
+	.endif
+.endm
+
+#else
+.macro KVMTEST name, hsrr, n
+.endm
+.macro KVM_HANDLER name, vec, hsrr, area, skip
+.endm
+#endif
+
+.macro INT_SAVE_SRR_AND_JUMP label, hsrr, set_ri
+	ld	r10,PACAKMSR(r13)	/* get MSR value for kernel */
+	.if ! \set_ri
+	xori	r10,r10,MSR_RI		/* Clear MSR_RI */
+	.endif
+	.if \hsrr == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
+	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
+	mtspr	SPRN_HSRR1,r10
+	FTR_SECTION_ELSE
+	mfspr	r11,SPRN_SRR0		/* save SRR0 */
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	mtspr	SPRN_SRR1,r10
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif \hsrr
+	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
+	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
+	mtspr	SPRN_HSRR1,r10
+	.else
+	mfspr	r11,SPRN_SRR0		/* save SRR0 */
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	mtspr	SPRN_SRR1,r10
+	.endif
+	LOAD_HANDLER(r10, \label\())
+	.if \hsrr == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	mtspr	SPRN_HSRR0,r10
+	HRFI_TO_KERNEL
+	FTR_SECTION_ELSE
+	mtspr	SPRN_SRR0,r10
+	RFI_TO_KERNEL
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif \hsrr
+	mtspr	SPRN_HSRR0,r10
+	HRFI_TO_KERNEL
+	.else
+	mtspr	SPRN_SRR0,r10
+	RFI_TO_KERNEL
+	.endif
+	b	.	/* prevent speculative execution */
+.endm
+
+/* INT_SAVE_SRR_AND_JUMP works for real or virt, this is faster but virt only */
+.macro INT_VIRT_SAVE_SRR_AND_JUMP label, hsrr
+#ifdef CONFIG_RELOCATABLE
+	.if \hsrr == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	mfspr	r11,SPRN_HSRR0	/* save HSRR0 */
+	FTR_SECTION_ELSE
+	mfspr	r11,SPRN_SRR0	/* save SRR0 */
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif \hsrr
+	mfspr	r11,SPRN_HSRR0	/* save HSRR0 */
+	.else
+	mfspr	r11,SPRN_SRR0	/* save SRR0 */
+	.endif
+	LOAD_HANDLER(r12, \label\())
+	mtctr	r12
+	.if \hsrr == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	mfspr	r12,SPRN_HSRR1	/* and HSRR1 */
+	FTR_SECTION_ELSE
+	mfspr	r12,SPRN_SRR1	/* and HSRR1 */
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif \hsrr
+	mfspr	r12,SPRN_HSRR1	/* and HSRR1 */
+	.else
+	mfspr	r12,SPRN_SRR1	/* and HSRR1 */
+	.endif
+	li	r10,MSR_RI
+	mtmsrd 	r10,1		/* Set RI (EE=0) */
+	bctr
+#else
+	.if \hsrr == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
+	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
+	FTR_SECTION_ELSE
+	mfspr	r11,SPRN_SRR0		/* save SRR0 */
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif \hsrr
+	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
+	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
+	.else
+	mfspr	r11,SPRN_SRR0		/* save SRR0 */
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	.endif
+	li	r10,MSR_RI
+	mtmsrd 	r10,1			/* Set RI (EE=0) */
+	b	\label
+#endif
+.endm
+
+/*
+ * This is the BOOK3S interrupt entry code macro.
+ *
+ * This can result in one of several things happening:
+ * - Branch to the _common handler, relocated, in virtual mode.
+ *   These are normal interrupts (synchronous and asynchronous) handled by
+ *   the kernel.
+ * - Branch to KVM, relocated but real mode interrupts remain in real mode.
+ *   These occur when HSTATE_IN_GUEST is set. The interrupt may be caused by
+ *   / intended for host or guest kernel, but KVM must always be involved
+ *   because the machine state is set for guest execution.
+ * - Branch to the masked handler, unrelocated.
+ *   These occur when maskable asynchronous interrupts are taken with the
+ *   irq_soft_mask set.
+ * - Branch to an "early" handler in real mode but relocated.
+ *   This is done if early=1. MCE and HMI use these to handle errors in real
+ *   mode.
+ * - Fall through and continue executing in real, unrelocated mode.
+ *   This is done if early=2.
+ */
+.macro INT_HANDLER name, vec, ool=0, early=0, virt=0, hsrr=0, area=PACA_EXGEN, ri=1, dar=0, dsisr=0, bitmask=0, kvm=0
+	SET_SCRATCH0(r13)			/* save r13 */
+	GET_PACA(r13)
+	std	r9,\area\()+EX_R9(r13)		/* save r9 */
+	OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR)
+	HMT_MEDIUM
+	std	r10,\area\()+EX_R10(r13)	/* save r10 - r12 */
+	OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
+	.if \ool
+	.if !\virt
+	b	tramp_real_\name
+	.pushsection .text
+	TRAMP_REAL_BEGIN(tramp_real_\name)
+	.else
+	b	tramp_virt_\name
+	.pushsection .text
+	TRAMP_VIRT_BEGIN(tramp_virt_\name)
+	.endif
+	.endif
+
+	OPT_SAVE_REG_TO_PACA(\area\()+EX_PPR, r9, CPU_FTR_HAS_PPR)
+	OPT_SAVE_REG_TO_PACA(\area\()+EX_CFAR, r10, CPU_FTR_CFAR)
+	INTERRUPT_TO_KERNEL
+	SAVE_CTR(r10, \area\())
+	mfcr	r9
+	.if \kvm
+		KVMTEST \name \hsrr \vec
+	.endif
+	.if \bitmask
+		lbz	r10,PACAIRQSOFTMASK(r13)
+		andi.	r10,r10,\bitmask
+		/* Associate vector numbers with bits in paca->irq_happened */
+		.if \vec == 0x500 || \vec == 0xea0
+		li	r10,PACA_IRQ_EE
+		.elseif \vec == 0x900
+		li	r10,PACA_IRQ_DEC
+		.elseif \vec == 0xa00 || \vec == 0xe80
+		li	r10,PACA_IRQ_DBELL
+		.elseif \vec == 0xe60
+		li	r10,PACA_IRQ_HMI
+		.elseif \vec == 0xf00
+		li	r10,PACA_IRQ_PMI
+		.else
+		.abort "Bad maskable vector"
+		.endif
+
+		.if \hsrr == EXC_HV_OR_STD
+		BEGIN_FTR_SECTION
+		bne	masked_Hinterrupt
+		FTR_SECTION_ELSE
+		bne	masked_interrupt
+		ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+		.elseif \hsrr
+		bne	masked_Hinterrupt
+		.else
+		bne	masked_interrupt
+		.endif
+	.endif
+
+	std	r11,\area\()+EX_R11(r13)
+	std	r12,\area\()+EX_R12(r13)
+
+	/*
+	 * DAR/DSISR, SCRATCH0 must be read before setting MSR[RI],
+	 * because a d-side MCE will clobber those registers so is
+	 * not recoverable if they are live.
+	 */
+	GET_SCRATCH0(r10)
+	std	r10,\area\()+EX_R13(r13)
+	.if \dar
+	.if \hsrr
+	mfspr	r10,SPRN_HDAR
+	.else
+	mfspr	r10,SPRN_DAR
+	.endif
+	std	r10,\area\()+EX_DAR(r13)
+	.endif
+	.if \dsisr
+	.if \hsrr
+	mfspr	r10,SPRN_HDSISR
+	.else
+	mfspr	r10,SPRN_DSISR
+	.endif
+	stw	r10,\area\()+EX_DSISR(r13)
+	.endif
+
+	.if \early == 2
+	/* nothing more */
+	.elseif \early
+	mfctr	r10			/* save ctr, even for !RELOCATABLE */
+	BRANCH_TO_C000(r11, \name\()_early_common)
+	.elseif !\virt
+	INT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr, \ri
+	.else
+	INT_VIRT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr
+	.endif
+	.if \ool
+	.popsection
+	.endif
+.endm
+
+/*
+ * On entry r13 points to the paca, r9-r13 are saved in the paca,
+ * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
+ * SRR1, and relocation is on.
+ *
+ * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
+ * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ */
+.macro INT_COMMON vec, area, stack, kaup, reconcile, dar, dsisr
+	.if \stack
+	andi.	r10,r12,MSR_PR		/* See if coming from user	*/
+	mr	r10,r1			/* Save r1			*/
+	subi	r1,r1,INT_FRAME_SIZE	/* alloc frame on kernel stack	*/
+	beq-	100f
+	ld	r1,PACAKSAVE(r13)	/* kernel stack to use		*/
+100:	tdgei	r1,-INT_FRAME_SIZE	/* trap if r1 is in userspace	*/
+	EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0
+	.endif
+
+	std	r9,_CCR(r1)		/* save CR in stackframe	*/
+	std	r11,_NIP(r1)		/* save SRR0 in stackframe	*/
+	std	r12,_MSR(r1)		/* save SRR1 in stackframe	*/
+	std	r10,0(r1)		/* make stack chain pointer	*/
+	std	r0,GPR0(r1)		/* save r0 in stackframe	*/
+	std	r10,GPR1(r1)		/* save r1 in stackframe	*/
+
+	.if \stack
+	.if \kaup
+	kuap_save_amr_and_lock r9, r10, cr1, cr0
+	.endif
+	beq	101f			/* if from kernel mode		*/
+	ACCOUNT_CPU_USER_ENTRY(r13, r9, r10)
+	SAVE_PPR(\area, r9)
+101:
+	.else
+	.if \kaup
+	kuap_save_amr_and_lock r9, r10, cr1
+	.endif
+	.endif
+
+	/* Save original regs values from save area to stack frame. */
+	ld	r9,\area+EX_R9(r13)	/* move r9, r10 to stackframe	*/
+	ld	r10,\area+EX_R10(r13)
+	std	r9,GPR9(r1)
+	std	r10,GPR10(r1)
+	ld	r9,\area+EX_R11(r13)	/* move r11 - r13 to stackframe	*/
+	ld	r10,\area+EX_R12(r13)
+	ld	r11,\area+EX_R13(r13)
+	std	r9,GPR11(r1)
+	std	r10,GPR12(r1)
+	std	r11,GPR13(r1)
+	.if \dar
+	.if \dar == 2
+	ld	r10,_NIP(r1)
+	.else
+	ld	r10,\area+EX_DAR(r13)
+	.endif
+	std	r10,_DAR(r1)
+	.endif
+	.if \dsisr
+	.if \dsisr == 2
+	ld	r10,_MSR(r1)
+	lis	r11,DSISR_SRR1_MATCH_64S@h
+	and	r10,r10,r11
+	.else
+	lwz	r10,\area+EX_DSISR(r13)
+	.endif
+	std	r10,_DSISR(r1)
+	.endif
+BEGIN_FTR_SECTION_NESTED(66)
+	ld	r10,\area+EX_CFAR(r13)
+	std	r10,ORIG_GPR3(r1)
+END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66)
+	GET_CTR(r10, \area)
+	std	r10,_CTR(r1)
+	std	r2,GPR2(r1)		/* save r2 in stackframe	*/
+	SAVE_4GPRS(3, r1)		/* save r3 - r6 in stackframe   */
+	SAVE_2GPRS(7, r1)		/* save r7, r8 in stackframe	*/
+	mflr	r9			/* Get LR, later save to stack	*/
+	ld	r2,PACATOC(r13)		/* get kernel TOC into r2	*/
+	std	r9,_LINK(r1)
+	lbz	r10,PACAIRQSOFTMASK(r13)
+	mfspr	r11,SPRN_XER		/* save XER in stackframe	*/
+	std	r10,SOFTE(r1)
+	std	r11,_XER(r1)
+	li	r9,(\vec)+1
+	std	r9,_TRAP(r1)		/* set trap number		*/
+	li	r10,0
+	ld	r11,exception_marker@toc(r2)
+	std	r10,RESULT(r1)		/* clear regs->result		*/
+	std	r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame	*/
+
+	.if \stack
+	ACCOUNT_STOLEN_TIME
+	.endif
+
+	.if \reconcile
+	RECONCILE_IRQ_STATE(r10, r11)
+	.endif
+.endm
+
+/*
+ * Restore all registers including H/SRR0/1 saved in a stack frame of a
+ * standard exception.
+ */
+.macro EXCEPTION_RESTORE_REGS hsrr
+	/* Move original SRR0 and SRR1 into the respective regs */
+	ld	r9,_MSR(r1)
+	.if \hsrr == EXC_HV_OR_STD
+	.error "EXC_HV_OR_STD Not implemented for EXCEPTION_RESTORE_REGS"
+	.endif
+	.if \hsrr
+	mtspr	SPRN_HSRR1,r9
+	.else
+	mtspr	SPRN_SRR1,r9
+	.endif
+	ld	r9,_NIP(r1)
+	.if \hsrr
+	mtspr	SPRN_HSRR0,r9
+	.else
+	mtspr	SPRN_SRR0,r9
+	.endif
+	ld	r9,_CTR(r1)
+	mtctr	r9
+	ld	r9,_XER(r1)
+	mtxer	r9
+	ld	r9,_LINK(r1)
+	mtlr	r9
+	ld	r9,_CCR(r1)
+	mtcr	r9
+	REST_8GPRS(2, r1)
+	REST_4GPRS(10, r1)
+	REST_GPR(0, r1)
+	/* restore original r1. */
+	ld	r1,GPR1(r1)
+.endm
+
+#define RUNLATCH_ON				\
+BEGIN_FTR_SECTION				\
+	ld	r3, PACA_THREAD_INFO(r13);	\
+	ld	r4,TI_LOCAL_FLAGS(r3);		\
+	andi.	r0,r4,_TLF_RUNLATCH;		\
+	beql	ppc64_runlatch_on_trampoline;	\
+END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
+
+/*
+ * When the idle code in power4_idle puts the CPU into NAP mode,
+ * it has to do so in a loop, and relies on the external interrupt
+ * and decrementer interrupt entry code to get it out of the loop.
+ * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags
+ * to signal that it is in the loop and needs help to get out.
+ */
+#ifdef CONFIG_PPC_970_NAP
+#define FINISH_NAP				\
+BEGIN_FTR_SECTION				\
+	ld	r11, PACA_THREAD_INFO(r13);	\
+	ld	r9,TI_LOCAL_FLAGS(r11);		\
+	andi.	r10,r9,_TLF_NAPPING;		\
+	bnel	power4_fixup_nap;		\
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+#else
+#define FINISH_NAP
+#endif
+
+#define EXC_COMMON(name, realvec, hdlr)					\
+	EXC_COMMON_BEGIN(name);						\
+	INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ;			\
+	bl	save_nvgprs;						\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;				\
+	bl	hdlr;							\
+	b	ret_from_except
+
+/*
+ * Like EXC_COMMON, but for exceptions that can occur in the idle task and
+ * therefore need the special idle handling (finish nap and runlatch)
+ */
+#define EXC_COMMON_ASYNC(name, realvec, hdlr)				\
+	EXC_COMMON_BEGIN(name);						\
+	INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ;			\
+	FINISH_NAP;							\
+	RUNLATCH_ON;							\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;				\
+	bl	hdlr;							\
+	b	ret_from_except_lite
+
 
 /*
  * There are a few constraints to be concerned with.
@@ -68,6 +740,14 @@
 OPEN_FIXED_SECTION(real_trampolines,    0x1900, 0x4000)
 OPEN_FIXED_SECTION(virt_vectors,        0x4000, 0x5900)
 OPEN_FIXED_SECTION(virt_trampolines,    0x5900, 0x7000)
+
+#ifdef CONFIG_PPC_POWERNV
+	.globl start_real_trampolines
+	.globl end_real_trampolines
+	.globl start_virt_trampolines
+	.globl end_virt_trampolines
+#endif
+
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
  * Data area reserved for FWNMI option.
@@ -98,6 +778,7 @@
 EXC_VIRT_NONE(0x4000, 0x100)
 
 
+EXC_REAL_BEGIN(system_reset, 0x100, 0x100)
 #ifdef CONFIG_PPC_P7_NAP
 	/*
 	 * If running native on arch 2.06 or later, check if we are waking up
@@ -105,55 +786,67 @@
 	 * bits 46:47. A non-0 value indicates that we are coming from a power
 	 * saving state. The idle wakeup handler initially runs in real mode,
 	 * but we branch to the 0xc000... address so we can turn on relocation
-	 * with mtmsr.
+	 * with mtmsrd later, after SPRs are restored.
+	 *
+	 * Careful to minimise cost for the fast path (idle wakeup) while
+	 * also avoiding clobbering CFAR for the debug path (non-idle).
+	 *
+	 * For the idle wake case volatile registers can be clobbered, which
+	 * is why we use those initially. If it turns out to not be an idle
+	 * wake, carefully put everything back the way it was, so we can use
+	 * common exception macros to handle it.
 	 */
-#define IDLETEST(n)							\
-	BEGIN_FTR_SECTION ;						\
-	mfspr	r10,SPRN_SRR1 ;						\
-	rlwinm.	r10,r10,47-31,30,31 ;					\
-	beq-	1f ;							\
-	cmpwi	cr3,r10,2 ;						\
-	BRANCH_TO_C000(r10, system_reset_idle_common) ;			\
-1:									\
-	KVMTEST_PR(n) ;							\
-	END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-#else
-#define IDLETEST NOTEST
+BEGIN_FTR_SECTION
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r3,PACA_EXNMI+0*8(r13)
+	std	r4,PACA_EXNMI+1*8(r13)
+	std	r5,PACA_EXNMI+2*8(r13)
+	mfspr	r3,SPRN_SRR1
+	mfocrf	r4,0x80
+	rlwinm.	r5,r3,47-31,30,31
+	bne+	system_reset_idle_wake
+	/* Not powersave wakeup. Restore regs for regular interrupt handler. */
+	mtocrf	0x80,r4
+	ld	r3,PACA_EXNMI+0*8(r13)
+	ld	r4,PACA_EXNMI+1*8(r13)
+	ld	r5,PACA_EXNMI+2*8(r13)
+	GET_SCRATCH0(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 #endif
 
-EXC_REAL_BEGIN(system_reset, 0x100, 0x100)
-	SET_SCRATCH0(r13)
+	INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0, kvm=1
 	/*
 	 * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
 	 * being used, so a nested NMI exception would corrupt it.
+	 *
+	 * In theory, we should not enable relocation here if it was disabled
+	 * in SRR1, because the MMU may not be configured to support it (e.g.,
+	 * SLB may have been cleared). In practice, there should only be a few
+	 * small windows where that's the case, and sreset is considered to
+	 * be dangerous anyway.
 	 */
-	EXCEPTION_PROLOG_NORI(PACA_EXNMI, system_reset_common, EXC_STD,
-			      IDLETEST, 0x100)
-
 EXC_REAL_END(system_reset, 0x100, 0x100)
 EXC_VIRT_NONE(0x4100, 0x100)
-TRAMP_KVM(PACA_EXNMI, 0x100)
+INT_KVM_HANDLER system_reset 0x100, EXC_STD, PACA_EXNMI, 0
 
 #ifdef CONFIG_PPC_P7_NAP
-EXC_COMMON_BEGIN(system_reset_idle_common)
-	mfspr	r12,SPRN_SRR1
-	b	pnv_powersave_wakeup
+TRAMP_REAL_BEGIN(system_reset_idle_wake)
+	/* We are waking up from idle, so may clobber any volatile register */
+	cmpwi	cr1,r5,2
+	bltlr	cr1	/* no state loss, return to idle caller with r3=SRR1 */
+	BRANCH_TO_C000(r12, DOTSYM(idle_return_gpr_loss))
 #endif
 
+#ifdef CONFIG_PPC_PSERIES
 /*
- * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does
- * the right thing. We do not want to reconcile because that goes
- * through irq tracing which we don't want in NMI.
- *
- * Save PACAIRQHAPPENED because some code will do a hard disable
- * (e.g., xmon). So we want to restore this back to where it was
- * when we return. DAR is unused in the stack, so save it there.
+ * Vectors for the FWNMI option.  Share common code.
  */
-#define ADD_RECONCILE_NMI						\
-	li	r10,IRQS_ALL_DISABLED;					\
-	stb	r10,PACAIRQSOFTMASK(r13);				\
-	lbz	r10,PACAIRQHAPPENED(r13);				\
-	std	r10,_DAR(r1)
+TRAMP_REAL_BEGIN(system_reset_fwnmi)
+	/* See comment at system_reset exception, don't turn on RI */
+	INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0
+
+#endif /* CONFIG_PPC_PSERIES */
 
 EXC_COMMON_BEGIN(system_reset_common)
 	/*
@@ -171,15 +864,27 @@
 	mr	r10,r1
 	ld	r1,PACA_NMI_EMERG_SP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
-	EXCEPTION_COMMON_NORET_STACK(PACA_EXNMI, 0x100,
-			system_reset, system_reset_exception,
-			ADD_NVGPRS;ADD_RECONCILE_NMI)
+	INT_COMMON 0x100, PACA_EXNMI, 0, 1, 0, 0, 0
+	bl	save_nvgprs
+	/*
+	 * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does
+	 * the right thing. We do not want to reconcile because that goes
+	 * through irq tracing which we don't want in NMI.
+	 *
+	 * Save PACAIRQHAPPENED because some code will do a hard disable
+	 * (e.g., xmon). So we want to restore this back to where it was
+	 * when we return. DAR is unused in the stack, so save it there.
+	 */
+	li	r10,IRQS_ALL_DISABLED
+	stb	r10,PACAIRQSOFTMASK(r13)
+	lbz	r10,PACAIRQHAPPENED(r13)
+	std	r10,_DAR(r1)
 
-	/* This (and MCE) can be simplified with mtmsrd L=1 */
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	system_reset_exception
+
 	/* Clear MSR_RI before setting SRR0 and SRR1. */
-	li	r0,MSR_RI
-	mfmsr	r9
-	andc	r9,r9,r0
+	li	r9,0
 	mtmsrd	r9,1
 
 	/*
@@ -197,68 +902,44 @@
 	ld	r10,SOFTE(r1)
 	stb	r10,PACAIRQSOFTMASK(r13)
 
-	/*
-	 * Keep below code in synch with MACHINE_CHECK_HANDLER_WINDUP.
-	 * Should share common bits...
-	 */
-
-	/* Move original SRR0 and SRR1 into the respective regs */
-	ld	r9,_MSR(r1)
-	mtspr	SPRN_SRR1,r9
-	ld	r3,_NIP(r1)
-	mtspr	SPRN_SRR0,r3
-	ld	r9,_CTR(r1)
-	mtctr	r9
-	ld	r9,_XER(r1)
-	mtxer	r9
-	ld	r9,_LINK(r1)
-	mtlr	r9
-	REST_GPR(0, r1)
-	REST_8GPRS(2, r1)
-	REST_GPR(10, r1)
-	ld	r11,_CCR(r1)
-	mtcr	r11
-	REST_GPR(11, r1)
-	REST_2GPRS(12, r1)
-	/* restore original r1. */
-	ld	r1,GPR1(r1)
+	EXCEPTION_RESTORE_REGS EXC_STD
 	RFI_TO_USER_OR_KERNEL
 
-#ifdef CONFIG_PPC_PSERIES
-/*
- * Vectors for the FWNMI option.  Share common code.
- */
-TRAMP_REAL_BEGIN(system_reset_fwnmi)
-	SET_SCRATCH0(r13)		/* save r13 */
-	/* See comment at system_reset exception */
-	EXCEPTION_PROLOG_NORI(PACA_EXNMI, system_reset_common, EXC_STD,
-			      NOTEST, 0x100)
-#endif /* CONFIG_PPC_PSERIES */
-
 
 EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
-	/* This is moved out of line as it can be patched by FW, but
-	 * some code path might still want to branch into the original
-	 * vector
+	INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1
+	/*
+	 * MSR_RI is not enabled, because PACA_EXMC is being used, so a
+	 * nested machine check corrupts it. machine_check_common enables
+	 * MSR_RI.
 	 */
-	SET_SCRATCH0(r13)		/* save r13 */
-	EXCEPTION_PROLOG_0(PACA_EXMC)
-BEGIN_FTR_SECTION
-	b	machine_check_powernv_early
-FTR_SECTION_ELSE
-	b	machine_check_pSeries_0
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
 EXC_REAL_END(machine_check, 0x200, 0x100)
 EXC_VIRT_NONE(0x4200, 0x100)
-TRAMP_REAL_BEGIN(machine_check_powernv_early)
-BEGIN_FTR_SECTION
-	EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
+
+#ifdef CONFIG_PPC_PSERIES
+TRAMP_REAL_BEGIN(machine_check_fwnmi)
+	/* See comment at machine_check exception, don't turn on RI */
+	INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1
+#endif
+
+INT_KVM_HANDLER machine_check 0x200, EXC_STD, PACA_EXMC, 1
+
+#define MACHINE_CHECK_HANDLER_WINDUP			\
+	/* Clear MSR_RI before setting SRR0 and SRR1. */\
+	li	r9,0;					\
+	mtmsrd	r9,1;		/* Clear MSR_RI */	\
+	/* Decrement paca->in_mce now RI is clear. */	\
+	lhz	r12,PACA_IN_MCE(r13);			\
+	subi	r12,r12,1;				\
+	sth	r12,PACA_IN_MCE(r13);			\
+	EXCEPTION_RESTORE_REGS EXC_STD
+
+EXC_COMMON_BEGIN(machine_check_early_common)
+	mtctr	r10			/* Restore ctr */
+	mfspr	r11,SPRN_SRR0
+	mfspr	r12,SPRN_SRR1
+
 	/*
-	 * Register contents:
-	 * R13		= PACA
-	 * R9		= CR
-	 * Original R9 to R13 is saved on PACA_EXMC
-	 *
 	 * Switch to mc_emergency stack and handle re-entrancy (we limit
 	 * the nested MCE upto level 4 to avoid stack overflow).
 	 * Save MCE registers srr1, srr0, dar and dsisr and then set ME=1
@@ -279,124 +960,127 @@
 	 * the machine check is handled then the idle wakeup code is called
 	 * to restore state.
 	 */
-	mr	r11,r1			/* Save r1 */
 	lhz	r10,PACA_IN_MCE(r13)
 	cmpwi	r10,0			/* Are we in nested machine check */
-	bne	0f			/* Yes, we are. */
-	/* First machine check entry */
-	ld	r1,PACAMCEMERGSP(r13)	/* Use MC emergency stack */
-0:	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame */
+	cmpwi	cr1,r10,MAX_MCE_DEPTH	/* Are we at maximum nesting */
 	addi	r10,r10,1		/* increment paca->in_mce */
 	sth	r10,PACA_IN_MCE(r13)
-	/* Limit nested MCE to level 4 to avoid stack overflow */
-	cmpwi	r10,MAX_MCE_DEPTH
-	bgt	2f			/* Check if we hit limit of 4 */
-	std	r11,GPR1(r1)		/* Save r1 on the stack. */
-	std	r11,0(r1)		/* make stack chain pointer */
-	mfspr	r11,SPRN_SRR0		/* Save SRR0 */
-	std	r11,_NIP(r1)
-	mfspr	r11,SPRN_SRR1		/* Save SRR1 */
-	std	r11,_MSR(r1)
-	mfspr	r11,SPRN_DAR		/* Save DAR */
-	std	r11,_DAR(r1)
-	mfspr	r11,SPRN_DSISR		/* Save DSISR */
-	std	r11,_DSISR(r1)
-	std	r9,_CCR(r1)		/* Save CR in stackframe */
-	/* Save r9 through r13 from EXMC save area to stack frame. */
-	EXCEPTION_PROLOG_COMMON_2(PACA_EXMC)
-	mfmsr	r11			/* get MSR value */
-	ori	r11,r11,MSR_ME		/* turn on ME bit */
-	ori	r11,r11,MSR_RI		/* turn on RI bit */
-	LOAD_HANDLER(r12, machine_check_handle_early)
-1:	mtspr	SPRN_SRR0,r12
-	mtspr	SPRN_SRR1,r11
-	RFI_TO_KERNEL
-	b	.	/* prevent speculative execution */
-2:
-	/* Stack overflow. Stay on emergency stack and panic.
-	 * Keep the ME bit off while panic-ing, so that if we hit
-	 * another machine check we checkstop.
-	 */
-	addi	r1,r1,INT_FRAME_SIZE	/* go back to previous stack frame */
-	ld	r11,PACAKMSR(r13)
-	LOAD_HANDLER(r12, unrecover_mce)
-	li	r10,MSR_ME
-	andc	r11,r11,r10		/* Turn off MSR_ME */
-	b	1b
-	b	.	/* prevent speculative execution */
+
+	mr	r10,r1			/* Save r1 */
+	bne	1f
+	/* First machine check entry */
+	ld	r1,PACAMCEMERGSP(r13)	/* Use MC emergency stack */
+1:	/* Limit nested MCE to level 4 to avoid stack overflow */
+	bgt	cr1,unrecoverable_mce	/* Check if we hit limit of 4 */
+	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame */
+
+	/* We don't touch AMR here, we never go to virtual mode */
+	INT_COMMON 0x200, PACA_EXMC, 0, 0, 0, 1, 1
+
+BEGIN_FTR_SECTION
+	bl	enable_machine_check
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+	li	r10,MSR_RI
+	mtmsrd	r10,1
 
-TRAMP_REAL_BEGIN(machine_check_pSeries)
-	.globl machine_check_fwnmi
-machine_check_fwnmi:
-	SET_SCRATCH0(r13)		/* save r13 */
-	EXCEPTION_PROLOG_0(PACA_EXMC)
-machine_check_pSeries_0:
-	EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200)
+	bl	save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	machine_check_early
+	std	r3,RESULT(r1)	/* Save result */
+	ld	r12,_MSR(r1)
+
+#ifdef CONFIG_PPC_P7_NAP
 	/*
-	 * MSR_RI is not enabled, because PACA_EXMC is being used, so a
-	 * nested machine check corrupts it. machine_check_common enables
-	 * MSR_RI.
+	 * Check if thread was in power saving mode. We come here when any
+	 * of the following is true:
+	 * a. thread wasn't in power saving mode
+	 * b. thread was in power saving mode with no state loss,
+	 *    supervisor state loss or hypervisor state loss.
+	 *
+	 * Go back to nap/sleep/winkle mode again if (b) is true.
 	 */
-	EXCEPTION_PROLOG_2_NORI(machine_check_common, EXC_STD)
+BEGIN_FTR_SECTION
+	rlwinm.	r11,r12,47-31,30,31
+	bne	machine_check_idle_common
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+#endif
 
-TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	/*
+	 * Check if we are coming from guest. If yes, then run the normal
+	 * exception handler which will take the
+	 * machine_check_kvm->kvmppc_interrupt branch to deliver the MC event
+	 * to guest.
+	 */
+	lbz	r11,HSTATE_IN_GUEST(r13)
+	cmpwi	r11,0			/* Check if coming from guest */
+	bne	mce_deliver		/* continue if we are. */
+#endif
+
+	/*
+	 * Check if we are coming from userspace. If yes, then run the normal
+	 * exception handler which will deliver the MC event to this kernel.
+	 */
+	andi.	r11,r12,MSR_PR		/* See if coming from user. */
+	bne	mce_deliver		/* continue in V mode if we are. */
+
+	/*
+	 * At this point we are coming from kernel context.
+	 * Queue up the MCE event and return from the interrupt.
+	 * But before that, check if this is an un-recoverable exception.
+	 * If yes, then stay on emergency stack and panic.
+	 */
+	andi.	r11,r12,MSR_RI
+	beq	unrecoverable_mce
+
+	/*
+	 * Check if we have successfully handled/recovered from error, if not
+	 * then stay on emergency stack and panic.
+	 */
+	ld	r3,RESULT(r1)	/* Load result */
+	cmpdi	r3,0		/* see if we handled MCE successfully */
+	beq	unrecoverable_mce /* if !handled then panic */
+
+	/*
+	 * Return from MC interrupt.
+	 * Queue up the MCE event so that we can log it later, while
+	 * returning from kernel or opal call.
+	 */
+	bl	machine_check_queue_event
+	MACHINE_CHECK_HANDLER_WINDUP
+	RFI_TO_KERNEL
+
+mce_deliver:
+	/*
+	 * This is a host user or guest MCE. Restore all registers, then
+	 * run the "late" handler. For host user, this will run the
+	 * machine_check_exception handler in virtual mode like a normal
+	 * interrupt handler. For guest, this will trigger the KVM test
+	 * and branch to the KVM interrupt similarly to other interrupts.
+	 */
+BEGIN_FTR_SECTION
+	ld	r10,ORIG_GPR3(r1)
+	mtspr	SPRN_CFAR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+	MACHINE_CHECK_HANDLER_WINDUP
+	/* See comment at machine_check exception, don't turn on RI */
+	INT_HANDLER machine_check, 0x200, area=PACA_EXMC, ri=0, dar=1, dsisr=1, kvm=1
 
 EXC_COMMON_BEGIN(machine_check_common)
 	/*
 	 * Machine check is different because we use a different
 	 * save area: PACA_EXMC instead of PACA_EXGEN.
 	 */
-	mfspr	r10,SPRN_DAR
-	std	r10,PACA_EXMC+EX_DAR(r13)
-	mfspr	r10,SPRN_DSISR
-	stw	r10,PACA_EXMC+EX_DSISR(r13)
-	EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
+	INT_COMMON 0x200, PACA_EXMC, 1, 1, 1, 1, 1
 	FINISH_NAP
-	RECONCILE_IRQ_STATE(r10, r11)
-	ld	r3,PACA_EXMC+EX_DAR(r13)
-	lwz	r4,PACA_EXMC+EX_DSISR(r13)
 	/* Enable MSR_RI when finished with PACA_EXMC */
 	li	r10,MSR_RI
 	mtmsrd 	r10,1
-	std	r3,_DAR(r1)
-	std	r4,_DSISR(r1)
 	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	machine_check_exception
 	b	ret_from_except
 
-#define MACHINE_CHECK_HANDLER_WINDUP			\
-	/* Clear MSR_RI before setting SRR0 and SRR1. */\
-	li	r0,MSR_RI;				\
-	mfmsr	r9;		/* get MSR value */	\
-	andc	r9,r9,r0;				\
-	mtmsrd	r9,1;		/* Clear MSR_RI */	\
-	/* Move original SRR0 and SRR1 into the respective regs */	\
-	ld	r9,_MSR(r1);				\
-	mtspr	SPRN_SRR1,r9;				\
-	ld	r3,_NIP(r1);				\
-	mtspr	SPRN_SRR0,r3;				\
-	ld	r9,_CTR(r1);				\
-	mtctr	r9;					\
-	ld	r9,_XER(r1);				\
-	mtxer	r9;					\
-	ld	r9,_LINK(r1);				\
-	mtlr	r9;					\
-	REST_GPR(0, r1);				\
-	REST_8GPRS(2, r1);				\
-	REST_GPR(10, r1);				\
-	ld	r11,_CCR(r1);				\
-	mtcr	r11;					\
-	/* Decrement paca->in_mce. */			\
-	lhz	r12,PACA_IN_MCE(r13);			\
-	subi	r12,r12,1;				\
-	sth	r12,PACA_IN_MCE(r13);			\
-	REST_GPR(11, r1);				\
-	REST_2GPRS(12, r1);				\
-	/* restore original r1. */			\
-	ld	r1,GPR1(r1)
-
 #ifdef CONFIG_PPC_P7_NAP
 /*
  * This is an idle wakeup. Low level machine check has already been
@@ -416,79 +1100,20 @@
 	 * Then decrement MCE nesting after finishing with the stack.
 	 */
 	ld	r3,_MSR(r1)
+	ld	r4,_LINK(r1)
 
 	lhz	r11,PACA_IN_MCE(r13)
 	subi	r11,r11,1
 	sth	r11,PACA_IN_MCE(r13)
 
-	/* Turn off the RI bit because SRR1 is used by idle wakeup code. */
-	/* Recoverability could be improved by reducing the use of SRR1. */
-	li	r11,0
-	mtmsrd	r11,1
-
-	b	pnv_powersave_wakeup_mce
-#endif
-	/*
-	 * Handle machine check early in real mode. We come here with
-	 * ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack.
-	 */
-EXC_COMMON_BEGIN(machine_check_handle_early)
-	std	r0,GPR0(r1)	/* Save r0 */
-	EXCEPTION_PROLOG_COMMON_3(0x200)
-	bl	save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	machine_check_early
-	std	r3,RESULT(r1)	/* Save result */
-	ld	r12,_MSR(r1)
-
-#ifdef	CONFIG_PPC_P7_NAP
-	/*
-	 * Check if thread was in power saving mode. We come here when any
-	 * of the following is true:
-	 * a. thread wasn't in power saving mode
-	 * b. thread was in power saving mode with no state loss,
-	 *    supervisor state loss or hypervisor state loss.
-	 *
-	 * Go back to nap/sleep/winkle mode again if (b) is true.
-	 */
-	BEGIN_FTR_SECTION
-	rlwinm.	r11,r12,47-31,30,31
-	bne	machine_check_idle_common
-	END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	mtlr	r4
+	rlwinm	r10,r3,47-31,30,31
+	cmpwi	cr1,r10,2
+	bltlr	cr1	/* no state loss, return to idle caller */
+	b	idle_return_gpr_loss
 #endif
 
-	/*
-	 * Check if we are coming from hypervisor userspace. If yes then we
-	 * continue in host kernel in V mode to deliver the MC event.
-	 */
-	rldicl.	r11,r12,4,63		/* See if MC hit while in HV mode. */
-	beq	5f
-	andi.	r11,r12,MSR_PR		/* See if coming from user. */
-	bne	9f			/* continue in V mode if we are. */
-
-5:
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-	/*
-	 * We are coming from kernel context. Check if we are coming from
-	 * guest. if yes, then we can continue. We will fall through
-	 * do_kvm_200->kvmppc_interrupt to deliver the MC event to guest.
-	 */
-	lbz	r11,HSTATE_IN_GUEST(r13)
-	cmpwi	r11,0			/* Check if coming from guest */
-	bne	9f			/* continue if we are. */
-#endif
-	/*
-	 * At this point we are not sure about what context we come from.
-	 * Queue up the MCE event and return from the interrupt.
-	 * But before that, check if this is an un-recoverable exception.
-	 * If yes, then stay on emergency stack and panic.
-	 */
-	andi.	r11,r12,MSR_RI
-	bne	2f
-1:	mfspr	r11,SPRN_SRR0
-	LOAD_HANDLER(r10,unrecover_mce)
-	mtspr	SPRN_SRR0,r10
-	ld	r10,PACAKMSR(r13)
+EXC_COMMON_BEGIN(unrecoverable_mce)
 	/*
 	 * We are going down. But there are chances that we might get hit by
 	 * another MCE during panic path and we may run into unstable state
@@ -496,69 +1121,49 @@
 	 * when another MCE is hit during panic path, system will checkstop
 	 * and hypervisor will get restarted cleanly by SP.
 	 */
+BEGIN_FTR_SECTION
+	li	r10,0 /* clear MSR_RI */
+	mtmsrd	r10,1
+	bl	disable_machine_check
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+	ld	r10,PACAKMSR(r13)
 	li	r3,MSR_ME
-	andc	r10,r10,r3		/* Turn off MSR_ME */
-	mtspr	SPRN_SRR1,r10
-	RFI_TO_KERNEL
-	b	.
-2:
-	/*
-	 * Check if we have successfully handled/recovered from error, if not
-	 * then stay on emergency stack and panic.
-	 */
-	ld	r3,RESULT(r1)	/* Load result */
-	cmpdi	r3,0		/* see if we handled MCE successfully */
+	andc	r10,r10,r3
+	mtmsrd	r10
 
-	beq	1b		/* if !handled then panic */
-	/*
-	 * Return from MC interrupt.
-	 * Queue up the MCE event so that we can log it later, while
-	 * returning from kernel or opal call.
-	 */
-	bl	machine_check_queue_event
-	MACHINE_CHECK_HANDLER_WINDUP
-	RFI_TO_USER_OR_KERNEL
-9:
-	/* Deliver the machine check to host kernel in V mode. */
-	MACHINE_CHECK_HANDLER_WINDUP
-	b	machine_check_pSeries
-
-EXC_COMMON_BEGIN(unrecover_mce)
 	/* Invoke machine_check_exception to print MCE event and panic. */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	machine_check_exception
+
 	/*
-	 * We will not reach here. Even if we did, there is no way out. Call
-	 * unrecoverable_exception and die.
+	 * We will not reach here. Even if we did, there is no way out.
+	 * Call unrecoverable_exception and die.
 	 */
-1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	unrecoverable_exception
-	b	1b
+	b	.
 
 
-EXC_REAL(data_access, 0x300, 0x80)
-EXC_VIRT(data_access, 0x4300, 0x80, 0x300)
-TRAMP_KVM_SKIP(PACA_EXGEN, 0x300)
-
+EXC_REAL_BEGIN(data_access, 0x300, 0x80)
+	INT_HANDLER data_access, 0x300, ool=1, dar=1, dsisr=1, kvm=1
+EXC_REAL_END(data_access, 0x300, 0x80)
+EXC_VIRT_BEGIN(data_access, 0x4300, 0x80)
+	INT_HANDLER data_access, 0x300, virt=1, dar=1, dsisr=1
+EXC_VIRT_END(data_access, 0x4300, 0x80)
+INT_KVM_HANDLER data_access, 0x300, EXC_STD, PACA_EXGEN, 1
 EXC_COMMON_BEGIN(data_access_common)
 	/*
 	 * Here r13 points to the paca, r9 contains the saved CR,
 	 * SRR0 and SRR1 are saved in r11 and r12,
 	 * r9 - r13 are saved in paca->exgen.
+	 * EX_DAR and EX_DSISR have saved DAR/DSISR
 	 */
-	mfspr	r10,SPRN_DAR
-	std	r10,PACA_EXGEN+EX_DAR(r13)
-	mfspr	r10,SPRN_DSISR
-	stw	r10,PACA_EXGEN+EX_DSISR(r13)
-	EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN)
-	RECONCILE_IRQ_STATE(r10, r11)
-	ld	r12,_MSR(r1)
-	ld	r3,PACA_EXGEN+EX_DAR(r13)
-	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
-	li	r5,0x300
-	std	r3,_DAR(r1)
-	std	r4,_DSISR(r1)
+	INT_COMMON 0x300, PACA_EXGEN, 1, 1, 1, 1, 1
+	ld	r4,_DAR(r1)
+	ld	r5,_DSISR(r1)
 BEGIN_MMU_FTR_SECTION
+	ld	r6,_MSR(r1)
+	li	r3,0x300
 	b	do_hash_page		/* Try to handle as hpte fault */
 MMU_FTR_SECTION_ELSE
 	b	handle_page_fault
@@ -566,43 +1171,51 @@
 
 
 EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80)
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXSLB)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380)
-	mr	r12,r3	/* save r3 */
-	mfspr	r3,SPRN_DAR
-	mfspr	r11,SPRN_SRR1
-	crset	4*cr6+eq
-	BRANCH_TO_COMMON(r10, slb_miss_common)
+	INT_HANDLER data_access_slb, 0x380, ool=1, area=PACA_EXSLB, dar=1, kvm=1
 EXC_REAL_END(data_access_slb, 0x380, 0x80)
-
 EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80)
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXSLB)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380)
-	mr	r12,r3	/* save r3 */
-	mfspr	r3,SPRN_DAR
-	mfspr	r11,SPRN_SRR1
-	crset	4*cr6+eq
-	BRANCH_TO_COMMON(r10, slb_miss_common)
+	INT_HANDLER data_access_slb, 0x380, virt=1, area=PACA_EXSLB, dar=1
 EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
-TRAMP_KVM_SKIP(PACA_EXSLB, 0x380)
-
-
-EXC_REAL(instruction_access, 0x400, 0x80)
-EXC_VIRT(instruction_access, 0x4400, 0x80, 0x400)
-TRAMP_KVM(PACA_EXGEN, 0x400)
-
-EXC_COMMON_BEGIN(instruction_access_common)
-	EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN)
-	RECONCILE_IRQ_STATE(r10, r11)
-	ld	r12,_MSR(r1)
-	ld	r3,_NIP(r1)
-	andis.	r4,r12,DSISR_SRR1_MATCH_64S@h
-	li	r5,0x400
-	std	r3,_DAR(r1)
-	std	r4,_DSISR(r1)
+INT_KVM_HANDLER data_access_slb, 0x380, EXC_STD, PACA_EXSLB, 1
+EXC_COMMON_BEGIN(data_access_slb_common)
+	INT_COMMON 0x380, PACA_EXSLB, 1, 1, 0, 1, 0
+	ld	r4,_DAR(r1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 BEGIN_MMU_FTR_SECTION
+	/* HPT case, do SLB fault */
+	bl	do_slb_fault
+	cmpdi	r3,0
+	bne-	1f
+	b	fast_exception_return
+1:	/* Error case */
+MMU_FTR_SECTION_ELSE
+	/* Radix case, access is outside page table range */
+	li	r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+	std	r3,RESULT(r1)
+	bl	save_nvgprs
+	RECONCILE_IRQ_STATE(r10, r11)
+	ld	r4,_DAR(r1)
+	ld	r5,RESULT(r1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	do_bad_slb_fault
+	b	ret_from_except
+
+
+EXC_REAL_BEGIN(instruction_access, 0x400, 0x80)
+	INT_HANDLER instruction_access, 0x400, kvm=1
+EXC_REAL_END(instruction_access, 0x400, 0x80)
+EXC_VIRT_BEGIN(instruction_access, 0x4400, 0x80)
+	INT_HANDLER instruction_access, 0x400, virt=1
+EXC_VIRT_END(instruction_access, 0x4400, 0x80)
+INT_KVM_HANDLER instruction_access, 0x400, EXC_STD, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(instruction_access_common)
+	INT_COMMON 0x400, PACA_EXGEN, 1, 1, 1, 2, 2
+	ld	r4,_DAR(r1)
+	ld	r5,_DSISR(r1)
+BEGIN_MMU_FTR_SECTION
+	ld      r6,_MSR(r1)
+	li	r3,0x400
 	b	do_hash_page		/* Try to handle as hpte fault */
 MMU_FTR_SECTION_ELSE
 	b	handle_page_fault
@@ -610,210 +1223,68 @@
 
 
 EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80)
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXSLB)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
-	mr	r12,r3	/* save r3 */
-	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
-	mfspr	r11,SPRN_SRR1
-	crclr	4*cr6+eq
-	BRANCH_TO_COMMON(r10, slb_miss_common)
+	INT_HANDLER instruction_access_slb, 0x480, area=PACA_EXSLB, kvm=1
 EXC_REAL_END(instruction_access_slb, 0x480, 0x80)
-
 EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80)
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXSLB)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x480)
-	mr	r12,r3	/* save r3 */
-	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
-	mfspr	r11,SPRN_SRR1
-	crclr	4*cr6+eq
-	BRANCH_TO_COMMON(r10, slb_miss_common)
+	INT_HANDLER instruction_access_slb, 0x480, virt=1, area=PACA_EXSLB
 EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80)
-TRAMP_KVM(PACA_EXSLB, 0x480)
-
-
-/*
- * This handler is used by the 0x380 and 0x480 SLB miss interrupts, as well as
- * the virtual mode 0x4380 and 0x4480 interrupts if AIL is enabled.
- */
-EXC_COMMON_BEGIN(slb_miss_common)
-	/*
-	 * r13 points to the PACA, r9 contains the saved CR,
-	 * r12 contains the saved r3,
-	 * r11 contain the saved SRR1, SRR0 is still ready for return
-	 * r3 has the faulting address
-	 * r9 - r13 are saved in paca->exslb.
- 	 * cr6.eq is set for a D-SLB miss, clear for a I-SLB miss
-	 * We assume we aren't going to take any exceptions during this
-	 * procedure.
-	 */
-	mflr	r10
-	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
-	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
-
-	andi.	r9,r11,MSR_PR	// Check for exception from userspace
-	cmpdi	cr4,r9,MSR_PR	// And save the result in CR4 for later
-
-	/*
-	 * Test MSR_RI before calling slb_allocate_realmode, because the
-	 * MSR in r11 gets clobbered. However we still want to allocate
-	 * SLB in case MSR_RI=0, to minimise the risk of getting stuck in
-	 * recursive SLB faults. So use cr5 for this, which is preserved.
-	 */
-	andi.	r11,r11,MSR_RI	/* check for unrecoverable exception */
-	cmpdi	cr5,r11,MSR_RI
-
-	crset	4*cr0+eq
-#ifdef CONFIG_PPC_BOOK3S_64
+INT_KVM_HANDLER instruction_access_slb, 0x480, EXC_STD, PACA_EXSLB, 0
+EXC_COMMON_BEGIN(instruction_access_slb_common)
+	INT_COMMON 0x480, PACA_EXSLB, 1, 1, 0, 2, 0
+	ld	r4,_DAR(r1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 BEGIN_MMU_FTR_SECTION
-	bl	slb_allocate
-END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
-#endif
-
-	ld	r10,PACA_EXSLB+EX_LR(r13)
-	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
-	mtlr	r10
-
-	/*
-	 * Large address, check whether we have to allocate new contexts.
-	 */
-	beq-	8f
-
-	bne-	cr5,2f		/* if unrecoverable exception, oops */
-
-	/* All done -- return from exception. */
-
-	bne	cr4,1f		/* returning to kernel */
-
-	mtcrf	0x80,r9
-	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
-	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
-	mtcrf	0x02,r9		/* I/D indication is in cr6 */
-	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
-
-	RESTORE_CTR(r9, PACA_EXSLB)
-	RESTORE_PPR_PACA(PACA_EXSLB, r9)
-	mr	r3,r12
-	ld	r9,PACA_EXSLB+EX_R9(r13)
-	ld	r10,PACA_EXSLB+EX_R10(r13)
-	ld	r11,PACA_EXSLB+EX_R11(r13)
-	ld	r12,PACA_EXSLB+EX_R12(r13)
-	ld	r13,PACA_EXSLB+EX_R13(r13)
-	RFI_TO_USER
-	b	.	/* prevent speculative execution */
-1:
-	mtcrf	0x80,r9
-	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
-	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
-	mtcrf	0x02,r9		/* I/D indication is in cr6 */
-	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
-
-	RESTORE_CTR(r9, PACA_EXSLB)
-	RESTORE_PPR_PACA(PACA_EXSLB, r9)
-	mr	r3,r12
-	ld	r9,PACA_EXSLB+EX_R9(r13)
-	ld	r10,PACA_EXSLB+EX_R10(r13)
-	ld	r11,PACA_EXSLB+EX_R11(r13)
-	ld	r12,PACA_EXSLB+EX_R12(r13)
-	ld	r13,PACA_EXSLB+EX_R13(r13)
-	RFI_TO_KERNEL
-	b	.	/* prevent speculative execution */
-
-
-2:	std     r3,PACA_EXSLB+EX_DAR(r13)
-	mr	r3,r12
-	mfspr	r11,SPRN_SRR0
-	mfspr	r12,SPRN_SRR1
-	LOAD_HANDLER(r10,unrecov_slb)
-	mtspr	SPRN_SRR0,r10
-	ld	r10,PACAKMSR(r13)
-	mtspr	SPRN_SRR1,r10
-	RFI_TO_KERNEL
-	b	.
-
-8:	std     r3,PACA_EXSLB+EX_DAR(r13)
-	mr	r3,r12
-	mfspr	r11,SPRN_SRR0
-	mfspr	r12,SPRN_SRR1
-	LOAD_HANDLER(r10, large_addr_slb)
-	mtspr	SPRN_SRR0,r10
-	ld	r10,PACAKMSR(r13)
-	mtspr	SPRN_SRR1,r10
-	RFI_TO_KERNEL
-	b	.
-
-EXC_COMMON_BEGIN(unrecov_slb)
-	EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
-	RECONCILE_IRQ_STATE(r10, r11)
+	/* HPT case, do SLB fault */
+	bl	do_slb_fault
+	cmpdi	r3,0
+	bne-	1f
+	b	fast_exception_return
+1:	/* Error case */
+MMU_FTR_SECTION_ELSE
+	/* Radix case, access is outside page table range */
+	li	r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+	std	r3,RESULT(r1)
 	bl	save_nvgprs
-1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	unrecoverable_exception
-	b	1b
-
-EXC_COMMON_BEGIN(large_addr_slb)
-	EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB)
 	RECONCILE_IRQ_STATE(r10, r11)
-	ld	r3, PACA_EXSLB+EX_DAR(r13)
-	std	r3, _DAR(r1)
-	beq	cr6, 2f
-	li	r10, 0x481		/* fix trap number for I-SLB miss */
-	std	r10, _TRAP(r1)
-2:	bl	save_nvgprs
-	addi	r3, r1, STACK_FRAME_OVERHEAD
-	bl	slb_miss_large_addr
+	ld	r4,_DAR(r1)
+	ld	r5,RESULT(r1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	do_bad_slb_fault
 	b	ret_from_except
 
 EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
-	.globl hardware_interrupt_hv;
-hardware_interrupt_hv:
-	BEGIN_FTR_SECTION
-		MASKABLE_EXCEPTION_HV(0x500, hardware_interrupt_common, IRQS_DISABLED)
-	FTR_SECTION_ELSE
-		MASKABLE_EXCEPTION(0x500, hardware_interrupt_common, IRQS_DISABLED)
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	INT_HANDLER hardware_interrupt, 0x500, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1
 EXC_REAL_END(hardware_interrupt, 0x500, 0x100)
-
 EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
-	.globl hardware_interrupt_relon_hv;
-hardware_interrupt_relon_hv:
-	BEGIN_FTR_SECTION
-		MASKABLE_RELON_EXCEPTION_HV(0x500, hardware_interrupt_common,
-					    IRQS_DISABLED)
-	FTR_SECTION_ELSE
-		__MASKABLE_RELON_EXCEPTION(0x500, hardware_interrupt_common,
-					   EXC_STD, SOFTEN_TEST_PR, IRQS_DISABLED)
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
+	INT_HANDLER hardware_interrupt, 0x500, virt=1, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1
 EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
-
-TRAMP_KVM(PACA_EXGEN, 0x500)
-TRAMP_KVM_HV(PACA_EXGEN, 0x500)
+INT_KVM_HANDLER hardware_interrupt, 0x500, EXC_HV_OR_STD, PACA_EXGEN, 0
 EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ)
 
 
-EXC_REAL(alignment, 0x600, 0x100)
-EXC_VIRT(alignment, 0x4600, 0x100, 0x600)
-TRAMP_KVM(PACA_EXGEN, 0x600)
+EXC_REAL_BEGIN(alignment, 0x600, 0x100)
+	INT_HANDLER alignment, 0x600, dar=1, dsisr=1, kvm=1
+EXC_REAL_END(alignment, 0x600, 0x100)
+EXC_VIRT_BEGIN(alignment, 0x4600, 0x100)
+	INT_HANDLER alignment, 0x600, virt=1, dar=1, dsisr=1
+EXC_VIRT_END(alignment, 0x4600, 0x100)
+INT_KVM_HANDLER alignment, 0x600, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(alignment_common)
-	mfspr	r10,SPRN_DAR
-	std	r10,PACA_EXGEN+EX_DAR(r13)
-	mfspr	r10,SPRN_DSISR
-	stw	r10,PACA_EXGEN+EX_DSISR(r13)
-	EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN)
-	ld	r3,PACA_EXGEN+EX_DAR(r13)
-	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
-	std	r3,_DAR(r1)
-	std	r4,_DSISR(r1)
+	INT_COMMON 0x600, PACA_EXGEN, 1, 1, 1, 1, 1
 	bl	save_nvgprs
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	alignment_exception
 	b	ret_from_except
 
 
-EXC_REAL(program_check, 0x700, 0x100)
-EXC_VIRT(program_check, 0x4700, 0x100, 0x700)
-TRAMP_KVM(PACA_EXGEN, 0x700)
+EXC_REAL_BEGIN(program_check, 0x700, 0x100)
+	INT_HANDLER program_check, 0x700, kvm=1
+EXC_REAL_END(program_check, 0x700, 0x100)
+EXC_VIRT_BEGIN(program_check, 0x4700, 0x100)
+	INT_HANDLER program_check, 0x700, virt=1
+EXC_VIRT_END(program_check, 0x4700, 0x100)
+INT_KVM_HANDLER program_check, 0x700, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(program_check_common)
 	/*
 	 * It's possible to receive a TM Bad Thing type program check with
@@ -823,39 +1294,49 @@
 	 * we switch to the emergency stack if we're taking a TM Bad Thing from
 	 * the kernel.
 	 */
-	li	r10,MSR_PR		/* Build a mask of MSR_PR ..	*/
-	oris	r10,r10,0x200000@h	/* .. and SRR1_PROGTM		*/
-	and	r10,r10,r12		/* Mask SRR1 with that.		*/
-	srdi	r10,r10,8		/* Shift it so we can compare	*/
-	cmpldi	r10,(0x200000 >> 8)	/* .. with an immediate.	*/
-	bne 1f				/* If != go to normal path.	*/
 
-	/* SRR1 had PR=0 and SRR1_PROGTM=1, so use the emergency stack	*/
-	andi.	r10,r12,MSR_PR;		/* Set CR0 correctly for label	*/
+	andi.	r10,r12,MSR_PR
+	bne	2f			/* If userspace, go normal path */
+
+	andis.	r10,r12,(SRR1_PROGTM)@h
+	bne	1f			/* If TM, emergency		*/
+
+	cmpdi	r1,-INT_FRAME_SIZE	/* check if r1 is in userspace	*/
+	blt	2f			/* normal path if not		*/
+
+	/* Use the emergency stack					*/
+1:	andi.	r10,r12,MSR_PR		/* Set CR0 correctly for label	*/
 					/* 3 in EXCEPTION_PROLOG_COMMON	*/
 	mr	r10,r1			/* Save r1			*/
 	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack		*/
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
-	b 3f				/* Jump into the macro !!	*/
-1:	EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
+	INT_COMMON 0x700, PACA_EXGEN, 0, 1, 1, 0, 0
+	b 3f
+2:
+	INT_COMMON 0x700, PACA_EXGEN, 1, 1, 1, 0, 0
+3:
 	bl	save_nvgprs
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	program_check_exception
 	b	ret_from_except
 
 
-EXC_REAL(fp_unavailable, 0x800, 0x100)
-EXC_VIRT(fp_unavailable, 0x4800, 0x100, 0x800)
-TRAMP_KVM(PACA_EXGEN, 0x800)
+EXC_REAL_BEGIN(fp_unavailable, 0x800, 0x100)
+	INT_HANDLER fp_unavailable, 0x800, kvm=1
+EXC_REAL_END(fp_unavailable, 0x800, 0x100)
+EXC_VIRT_BEGIN(fp_unavailable, 0x4800, 0x100)
+	INT_HANDLER fp_unavailable, 0x800, virt=1
+EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
+INT_KVM_HANDLER fp_unavailable, 0x800, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(fp_unavailable_common)
-	EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN)
+	INT_COMMON 0x800, PACA_EXGEN, 1, 1, 0, 0, 0
 	bne	1f			/* if from user, just load it up */
 	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	kernel_fp_unavailable_exception
-	BUG_OPCODE
+0:	trap
+	EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
 1:
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
@@ -878,21 +1359,33 @@
 #endif
 
 
-EXC_REAL_OOL_MASKABLE(decrementer, 0x900, 0x80, IRQS_DISABLED)
-EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900, IRQS_DISABLED)
-TRAMP_KVM(PACA_EXGEN, 0x900)
+EXC_REAL_BEGIN(decrementer, 0x900, 0x80)
+	INT_HANDLER decrementer, 0x900, ool=1, bitmask=IRQS_DISABLED, kvm=1
+EXC_REAL_END(decrementer, 0x900, 0x80)
+EXC_VIRT_BEGIN(decrementer, 0x4900, 0x80)
+	INT_HANDLER decrementer, 0x900, virt=1, bitmask=IRQS_DISABLED
+EXC_VIRT_END(decrementer, 0x4900, 0x80)
+INT_KVM_HANDLER decrementer, 0x900, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt)
 
 
-EXC_REAL_HV(hdecrementer, 0x980, 0x80)
-EXC_VIRT_HV(hdecrementer, 0x4980, 0x80, 0x980)
-TRAMP_KVM_HV(PACA_EXGEN, 0x980)
+EXC_REAL_BEGIN(hdecrementer, 0x980, 0x80)
+	INT_HANDLER hdecrementer, 0x980, hsrr=EXC_HV, kvm=1
+EXC_REAL_END(hdecrementer, 0x980, 0x80)
+EXC_VIRT_BEGIN(hdecrementer, 0x4980, 0x80)
+	INT_HANDLER hdecrementer, 0x980, virt=1, hsrr=EXC_HV, kvm=1
+EXC_VIRT_END(hdecrementer, 0x4980, 0x80)
+INT_KVM_HANDLER hdecrementer, 0x980, EXC_HV, PACA_EXGEN, 0
 EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt)
 
 
-EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0x100, IRQS_DISABLED)
-EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x100, 0xa00, IRQS_DISABLED)
-TRAMP_KVM(PACA_EXGEN, 0xa00)
+EXC_REAL_BEGIN(doorbell_super, 0xa00, 0x100)
+	INT_HANDLER doorbell_super, 0xa00, bitmask=IRQS_DISABLED, kvm=1
+EXC_REAL_END(doorbell_super, 0xa00, 0x100)
+EXC_VIRT_BEGIN(doorbell_super, 0x4a00, 0x100)
+	INT_HANDLER doorbell_super, 0xa00, virt=1, bitmask=IRQS_DISABLED
+EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
+INT_KVM_HANDLER doorbell_super, 0xa00, EXC_STD, PACA_EXGEN, 0
 #ifdef CONFIG_PPC_DOORBELL
 EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception)
 #else
@@ -900,17 +1393,13 @@
 #endif
 
 
-EXC_REAL(trap_0b, 0xb00, 0x100)
-EXC_VIRT(trap_0b, 0x4b00, 0x100, 0xb00)
-TRAMP_KVM(PACA_EXGEN, 0xb00)
-EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
+EXC_REAL_NONE(0xb00, 0x100)
+EXC_VIRT_NONE(0x4b00, 0x100)
 
 /*
  * system call / hypercall (0xc00, 0x4c00)
  *
  * The system call exception is invoked with "sc 0" and does not alter HV bit.
- * There is support for kernel code to invoke system calls but there are no
- * in-tree users.
  *
  * The hypercall is invoked with "sc 1" and sets HV=1.
  *
@@ -919,7 +1408,7 @@
  *
  * Call convention:
  *
- * syscall register convention is in Documentation/powerpc/syscall64-abi.txt
+ * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
  *
  * For hypercalls, the register convention is as follows:
  * r0 volatile
@@ -941,6 +1430,7 @@
  * without saving, though xer is not a good idea to use, as hardware may
  * interpret some bits so it may be costly to change them.
  */
+.macro SYSTEM_CALL virt
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	/*
 	 * There is a little bit of juggling to get syscall and hcall
@@ -950,95 +1440,66 @@
 	 * Userspace syscalls have already saved the PPR, hcalls must save
 	 * it before setting HMT_MEDIUM.
 	 */
-#define SYSCALL_KVMTEST							\
-	mtctr	r13;							\
-	GET_PACA(r13);							\
-	std	r10,PACA_EXGEN+EX_R10(r13);				\
-	INTERRUPT_TO_KERNEL;						\
-	KVMTEST_PR(0xc00); /* uses r10, branch to do_kvm_0xc00_system_call */ \
-	HMT_MEDIUM;							\
-	mfctr	r9;
-
+	mtctr	r13
+	GET_PACA(r13)
+	std	r10,PACA_EXGEN+EX_R10(r13)
+	INTERRUPT_TO_KERNEL
+	KVMTEST system_call EXC_STD 0xc00 /* uses r10, branch to system_call_kvm */
+	mfctr	r9
 #else
-#define SYSCALL_KVMTEST							\
-	HMT_MEDIUM;							\
-	mr	r9,r13;							\
-	GET_PACA(r13);							\
-	INTERRUPT_TO_KERNEL;
+	mr	r9,r13
+	GET_PACA(r13)
+	INTERRUPT_TO_KERNEL
 #endif
-	
-#define LOAD_SYSCALL_HANDLER(reg)					\
-	__LOAD_HANDLER(reg, system_call_common)
-
-/*
- * After SYSCALL_KVMTEST, we reach here with PACA in r13, r13 in r9,
- * and HMT_MEDIUM.
- */
-#define SYSCALL_REAL	 					\
-	mfspr	r11,SPRN_SRR0 ;					\
-	mfspr	r12,SPRN_SRR1 ;					\
-	LOAD_SYSCALL_HANDLER(r10) ; 				\
-	mtspr	SPRN_SRR0,r10 ; 				\
-	ld	r10,PACAKMSR(r13) ;				\
-	mtspr	SPRN_SRR1,r10 ; 				\
-	RFI_TO_KERNEL ;						\
-	b	. ;	/* prevent speculative execution */
 
 #ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
-#define SYSCALL_FASTENDIAN_TEST					\
-BEGIN_FTR_SECTION						\
-	cmpdi	r0,0x1ebe ; 					\
-	beq-	1f ;						\
-END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
-
-#define SYSCALL_FASTENDIAN					\
-	/* 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 */
-#else
-#define SYSCALL_FASTENDIAN_TEST
-#define SYSCALL_FASTENDIAN
-#endif /* CONFIG_PPC_FAST_ENDIAN_SWITCH */
-
-#if defined(CONFIG_RELOCATABLE)
-	/*
-	 * We can't branch directly so we do it via the CTR which
-	 * is volatile across system calls.
-	 */
-#define SYSCALL_VIRT						\
-	LOAD_SYSCALL_HANDLER(r10) ;				\
-	mtctr	r10 ;						\
-	mfspr	r11,SPRN_SRR0 ;					\
-	mfspr	r12,SPRN_SRR1 ;					\
-	li	r10,MSR_RI ;					\
-	mtmsrd 	r10,1 ;						\
-	bctr ;
-#else
-	/* We can branch directly */
-#define SYSCALL_VIRT						\
-	mfspr	r11,SPRN_SRR0 ;					\
-	mfspr	r12,SPRN_SRR1 ;					\
-	li	r10,MSR_RI ;					\
-	mtmsrd 	r10,1 ;			/* Set RI (EE=0) */	\
-	b	system_call_common ;
+BEGIN_FTR_SECTION
+	cmpdi	r0,0x1ebe
+	beq-	1f
+END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 #endif
 
-EXC_REAL_BEGIN(system_call, 0xc00, 0x100)
-	SYSCALL_KVMTEST /* loads PACA into r13, and saves r13 to r9 */
-	SYSCALL_FASTENDIAN_TEST
-	SYSCALL_REAL
-	SYSCALL_FASTENDIAN
-EXC_REAL_END(system_call, 0xc00, 0x100)
+	/* We reach here with PACA in r13, r13 in r9. */
+	mfspr	r11,SPRN_SRR0
+	mfspr	r12,SPRN_SRR1
 
+	HMT_MEDIUM
+
+	.if ! \virt
+	__LOAD_HANDLER(r10, system_call_common)
+	mtspr	SPRN_SRR0,r10
+	ld	r10,PACAKMSR(r13)
+	mtspr	SPRN_SRR1,r10
+	RFI_TO_KERNEL
+	b	.	/* prevent speculative execution */
+	.else
+	li	r10,MSR_RI
+	mtmsrd 	r10,1			/* Set RI (EE=0) */
+#ifdef CONFIG_RELOCATABLE
+	__LOAD_HANDLER(r10, system_call_common)
+	mtctr	r10
+	bctr
+#else
+	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)
+	SYSTEM_CALL 0
+EXC_REAL_END(system_call, 0xc00, 0x100)
 EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100)
-	SYSCALL_KVMTEST /* loads PACA into r13, and saves r13 to r9 */
-	SYSCALL_FASTENDIAN_TEST
-	SYSCALL_VIRT
-	SYSCALL_FASTENDIAN
+	SYSTEM_CALL 1
 EXC_VIRT_END(system_call, 0x4c00, 0x100)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
@@ -1049,7 +1510,7 @@
 	 * ctr = orig r13
 	 * orig r10 saved in PACA
 	 */
-TRAMP_KVM_BEGIN(do_kvm_0xc00)
+TRAMP_KVM_BEGIN(system_call_kvm)
 	 /*
 	  * Save the PPR (on systems that support it) before changing to
 	  * HMT_MEDIUM. That allows the KVM code to save that value into the
@@ -1062,40 +1523,58 @@
 	SET_SCRATCH0(r10)
 	std	r9,PACA_EXGEN+EX_R9(r13)
 	mfcr	r9
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00)
+	KVM_HANDLER 0xc00, EXC_STD, PACA_EXGEN, 0
 #endif
 
 
-EXC_REAL(single_step, 0xd00, 0x100)
-EXC_VIRT(single_step, 0x4d00, 0x100, 0xd00)
-TRAMP_KVM(PACA_EXGEN, 0xd00)
+EXC_REAL_BEGIN(single_step, 0xd00, 0x100)
+	INT_HANDLER single_step, 0xd00, kvm=1
+EXC_REAL_END(single_step, 0xd00, 0x100)
+EXC_VIRT_BEGIN(single_step, 0x4d00, 0x100)
+	INT_HANDLER single_step, 0xd00, virt=1
+EXC_VIRT_END(single_step, 0x4d00, 0x100)
+INT_KVM_HANDLER single_step, 0xd00, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON(single_step_common, 0xd00, single_step_exception)
 
-EXC_REAL_OOL_HV(h_data_storage, 0xe00, 0x20)
-EXC_VIRT_OOL_HV(h_data_storage, 0x4e00, 0x20, 0xe00)
-TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0xe00)
+
+EXC_REAL_BEGIN(h_data_storage, 0xe00, 0x20)
+	INT_HANDLER h_data_storage, 0xe00, ool=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1
+EXC_REAL_END(h_data_storage, 0xe00, 0x20)
+EXC_VIRT_BEGIN(h_data_storage, 0x4e00, 0x20)
+	INT_HANDLER h_data_storage, 0xe00, ool=1, virt=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1
+EXC_VIRT_END(h_data_storage, 0x4e00, 0x20)
+INT_KVM_HANDLER h_data_storage, 0xe00, EXC_HV, PACA_EXGEN, 1
 EXC_COMMON_BEGIN(h_data_storage_common)
-	mfspr   r10,SPRN_HDAR
-	std     r10,PACA_EXGEN+EX_DAR(r13)
-	mfspr   r10,SPRN_HDSISR
-	stw     r10,PACA_EXGEN+EX_DSISR(r13)
-	EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN)
+	INT_COMMON 0xe00, PACA_EXGEN, 1, 1, 1, 1, 1
 	bl      save_nvgprs
-	RECONCILE_IRQ_STATE(r10, r11)
 	addi    r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+	ld	r4,_DAR(r1)
+	li	r5,SIGSEGV
+	bl      bad_page_fault
+MMU_FTR_SECTION_ELSE
 	bl      unknown_exception
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
 	b       ret_from_except
 
 
-EXC_REAL_OOL_HV(h_instr_storage, 0xe20, 0x20)
-EXC_VIRT_OOL_HV(h_instr_storage, 0x4e20, 0x20, 0xe20)
-TRAMP_KVM_HV(PACA_EXGEN, 0xe20)
+EXC_REAL_BEGIN(h_instr_storage, 0xe20, 0x20)
+	INT_HANDLER h_instr_storage, 0xe20, ool=1, hsrr=EXC_HV, kvm=1
+EXC_REAL_END(h_instr_storage, 0xe20, 0x20)
+EXC_VIRT_BEGIN(h_instr_storage, 0x4e20, 0x20)
+	INT_HANDLER h_instr_storage, 0xe20, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+EXC_VIRT_END(h_instr_storage, 0x4e20, 0x20)
+INT_KVM_HANDLER h_instr_storage, 0xe20, EXC_HV, PACA_EXGEN, 0
 EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception)
 
 
-EXC_REAL_OOL_HV(emulation_assist, 0xe40, 0x20)
-EXC_VIRT_OOL_HV(emulation_assist, 0x4e40, 0x20, 0xe40)
-TRAMP_KVM_HV(PACA_EXGEN, 0xe40)
+EXC_REAL_BEGIN(emulation_assist, 0xe40, 0x20)
+	INT_HANDLER emulation_assist, 0xe40, ool=1, hsrr=EXC_HV, kvm=1
+EXC_REAL_END(emulation_assist, 0xe40, 0x20)
+EXC_VIRT_BEGIN(emulation_assist, 0x4e40, 0x20)
+	INT_HANDLER emulation_assist, 0xe40, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+EXC_VIRT_END(emulation_assist, 0x4e40, 0x20)
+INT_KVM_HANDLER emulation_assist, 0xe40, EXC_HV, PACA_EXGEN, 0
 EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt)
 
 
@@ -1104,68 +1583,55 @@
  * first, and then eventaully from there to the trampoline to get into virtual
  * mode.
  */
-__EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0x20, hmi_exception_early)
-__TRAMP_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60, IRQS_DISABLED)
+EXC_REAL_BEGIN(hmi_exception, 0xe60, 0x20)
+	INT_HANDLER hmi_exception, 0xe60, ool=1, early=1, hsrr=EXC_HV, ri=0, kvm=1
+EXC_REAL_END(hmi_exception, 0xe60, 0x20)
 EXC_VIRT_NONE(0x4e60, 0x20)
-TRAMP_KVM_HV(PACA_EXGEN, 0xe60)
-TRAMP_REAL_BEGIN(hmi_exception_early)
-	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, 0xe60)
+INT_KVM_HANDLER hmi_exception, 0xe60, EXC_HV, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(hmi_exception_early_common)
+	mtctr	r10			/* Restore ctr */
+	mfspr	r11,SPRN_HSRR0		/* Save HSRR0 */
+	mfspr	r12,SPRN_HSRR1		/* Save HSRR1 */
 	mr	r10,r1			/* Save r1 */
 	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack for realmode */
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
-	mfspr	r11,SPRN_HSRR0		/* Save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* Save HSRR1 */
-	EXCEPTION_PROLOG_COMMON_1()
-	EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN)
-	EXCEPTION_PROLOG_COMMON_3(0xe60)
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	BRANCH_LINK_TO_FAR(hmi_exception_realmode) /* Function call ABI */
-	cmpdi	cr0,r3,0
 
-	/* Windup the stack. */
-	/* Move original HSRR0 and HSRR1 into the respective regs */
-	ld	r9,_MSR(r1)
-	mtspr	SPRN_HSRR1,r9
-	ld	r3,_NIP(r1)
-	mtspr	SPRN_HSRR0,r3
-	ld	r9,_CTR(r1)
-	mtctr	r9
-	ld	r9,_XER(r1)
-	mtxer	r9
-	ld	r9,_LINK(r1)
-	mtlr	r9
-	REST_GPR(0, r1)
-	REST_8GPRS(2, r1)
-	REST_GPR(10, r1)
-	ld	r11,_CCR(r1)
-	REST_2GPRS(12, r1)
+	/* We don't touch AMR here, we never go to virtual mode */
+	INT_COMMON 0xe60, PACA_EXGEN, 0, 0, 0, 0, 0
+
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	hmi_exception_realmode
+	cmpdi	cr0,r3,0
 	bne	1f
-	mtcr	r11
-	REST_GPR(11, r1)
-	ld	r1,GPR1(r1)
+
+	EXCEPTION_RESTORE_REGS EXC_HV
 	HRFI_TO_USER_OR_KERNEL
 
-1:	mtcr	r11
-	REST_GPR(11, r1)
-	ld	r1,GPR1(r1)
-
+1:
 	/*
 	 * Go to virtual mode and pull the HMI event information from
 	 * firmware.
 	 */
-	.globl hmi_exception_after_realmode
-hmi_exception_after_realmode:
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	tramp_real_hmi_exception
+	EXCEPTION_RESTORE_REGS EXC_HV
+	INT_HANDLER hmi_exception, 0xe60, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
 
 EXC_COMMON_BEGIN(hmi_exception_common)
-EXCEPTION_COMMON(PACA_EXGEN, 0xe60, hmi_exception_common, handle_hmi_exception,
-        ret_from_except, FINISH_NAP;ADD_NVGPRS;ADD_RECONCILE;RUNLATCH_ON)
+	INT_COMMON 0xe60, PACA_EXGEN, 1, 1, 1, 0, 0
+	FINISH_NAP
+	RUNLATCH_ON
+	bl	save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	handle_hmi_exception
+	b	ret_from_except
 
-EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0x20, IRQS_DISABLED)
-EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x20, 0xe80, IRQS_DISABLED)
-TRAMP_KVM_HV(PACA_EXGEN, 0xe80)
+
+EXC_REAL_BEGIN(h_doorbell, 0xe80, 0x20)
+	INT_HANDLER h_doorbell, 0xe80, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+EXC_REAL_END(h_doorbell, 0xe80, 0x20)
+EXC_VIRT_BEGIN(h_doorbell, 0x4e80, 0x20)
+	INT_HANDLER h_doorbell, 0xe80, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
+INT_KVM_HANDLER h_doorbell, 0xe80, EXC_HV, PACA_EXGEN, 0
 #ifdef CONFIG_PPC_DOORBELL
 EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception)
 #else
@@ -1173,9 +1639,13 @@
 #endif
 
 
-EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0x20, IRQS_DISABLED)
-EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x20, 0xea0, IRQS_DISABLED)
-TRAMP_KVM_HV(PACA_EXGEN, 0xea0)
+EXC_REAL_BEGIN(h_virt_irq, 0xea0, 0x20)
+	INT_HANDLER h_virt_irq, 0xea0, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+EXC_REAL_END(h_virt_irq, 0xea0, 0x20)
+EXC_VIRT_BEGIN(h_virt_irq, 0x4ea0, 0x20)
+	INT_HANDLER h_virt_irq, 0xea0, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
+INT_KVM_HANDLER h_virt_irq, 0xea0, EXC_HV, PACA_EXGEN, 0
 EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ)
 
 
@@ -1185,17 +1655,25 @@
 EXC_VIRT_NONE(0x4ee0, 0x20)
 
 
-EXC_REAL_OOL_MASKABLE(performance_monitor, 0xf00, 0x20, IRQS_PMI_DISABLED)
-EXC_VIRT_OOL_MASKABLE(performance_monitor, 0x4f00, 0x20, 0xf00, IRQS_PMI_DISABLED)
-TRAMP_KVM(PACA_EXGEN, 0xf00)
+EXC_REAL_BEGIN(performance_monitor, 0xf00, 0x20)
+	INT_HANDLER performance_monitor, 0xf00, ool=1, bitmask=IRQS_PMI_DISABLED, kvm=1
+EXC_REAL_END(performance_monitor, 0xf00, 0x20)
+EXC_VIRT_BEGIN(performance_monitor, 0x4f00, 0x20)
+	INT_HANDLER performance_monitor, 0xf00, ool=1, virt=1, bitmask=IRQS_PMI_DISABLED
+EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
+INT_KVM_HANDLER performance_monitor, 0xf00, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception)
 
 
-EXC_REAL_OOL(altivec_unavailable, 0xf20, 0x20)
-EXC_VIRT_OOL(altivec_unavailable, 0x4f20, 0x20, 0xf20)
-TRAMP_KVM(PACA_EXGEN, 0xf20)
+EXC_REAL_BEGIN(altivec_unavailable, 0xf20, 0x20)
+	INT_HANDLER altivec_unavailable, 0xf20, ool=1, kvm=1
+EXC_REAL_END(altivec_unavailable, 0xf20, 0x20)
+EXC_VIRT_BEGIN(altivec_unavailable, 0x4f20, 0x20)
+	INT_HANDLER altivec_unavailable, 0xf20, ool=1, virt=1
+EXC_VIRT_END(altivec_unavailable, 0x4f20, 0x20)
+INT_KVM_HANDLER altivec_unavailable, 0xf20, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(altivec_unavailable_common)
-	EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN)
+	INT_COMMON 0xf20, PACA_EXGEN, 1, 1, 0, 0, 0
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
 	beq	1f
@@ -1228,11 +1706,15 @@
 	b	ret_from_except
 
 
-EXC_REAL_OOL(vsx_unavailable, 0xf40, 0x20)
-EXC_VIRT_OOL(vsx_unavailable, 0x4f40, 0x20, 0xf40)
-TRAMP_KVM(PACA_EXGEN, 0xf40)
+EXC_REAL_BEGIN(vsx_unavailable, 0xf40, 0x20)
+	INT_HANDLER vsx_unavailable, 0xf40, ool=1, kvm=1
+EXC_REAL_END(vsx_unavailable, 0xf40, 0x20)
+EXC_VIRT_BEGIN(vsx_unavailable, 0x4f40, 0x20)
+	INT_HANDLER vsx_unavailable, 0xf40, ool=1, virt=1
+EXC_VIRT_END(vsx_unavailable, 0x4f40, 0x20)
+INT_KVM_HANDLER vsx_unavailable, 0xf40, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(vsx_unavailable_common)
-	EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN)
+	INT_COMMON 0xf40, PACA_EXGEN, 1, 1, 0, 0, 0
 #ifdef CONFIG_VSX
 BEGIN_FTR_SECTION
 	beq	1f
@@ -1264,15 +1746,23 @@
 	b	ret_from_except
 
 
-EXC_REAL_OOL(facility_unavailable, 0xf60, 0x20)
-EXC_VIRT_OOL(facility_unavailable, 0x4f60, 0x20, 0xf60)
-TRAMP_KVM(PACA_EXGEN, 0xf60)
+EXC_REAL_BEGIN(facility_unavailable, 0xf60, 0x20)
+	INT_HANDLER facility_unavailable, 0xf60, ool=1, kvm=1
+EXC_REAL_END(facility_unavailable, 0xf60, 0x20)
+EXC_VIRT_BEGIN(facility_unavailable, 0x4f60, 0x20)
+	INT_HANDLER facility_unavailable, 0xf60, ool=1, virt=1
+EXC_VIRT_END(facility_unavailable, 0x4f60, 0x20)
+INT_KVM_HANDLER facility_unavailable, 0xf60, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON(facility_unavailable_common, 0xf60, facility_unavailable_exception)
 
 
-EXC_REAL_OOL_HV(h_facility_unavailable, 0xf80, 0x20)
-EXC_VIRT_OOL_HV(h_facility_unavailable, 0x4f80, 0x20, 0xf80)
-TRAMP_KVM_HV(PACA_EXGEN, 0xf80)
+EXC_REAL_BEGIN(h_facility_unavailable, 0xf80, 0x20)
+	INT_HANDLER h_facility_unavailable, 0xf80, ool=1, hsrr=EXC_HV, kvm=1
+EXC_REAL_END(h_facility_unavailable, 0xf80, 0x20)
+EXC_VIRT_BEGIN(h_facility_unavailable, 0x4f80, 0x20)
+	INT_HANDLER h_facility_unavailable, 0xf80, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+EXC_VIRT_END(h_facility_unavailable, 0x4f80, 0x20)
+INT_KVM_HANDLER h_facility_unavailable, 0xf80, EXC_HV, PACA_EXGEN, 0
 EXC_COMMON(h_facility_unavailable_common, 0xf80, facility_unavailable_exception)
 
 
@@ -1289,9 +1779,11 @@
 EXC_VIRT_NONE(0x5100, 0x100)
 
 #ifdef CONFIG_CBE_RAS
-EXC_REAL_HV(cbe_system_error, 0x1200, 0x100)
+EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
+	INT_HANDLER cbe_system_error, 0x1200, ool=1, hsrr=EXC_HV, kvm=1
+EXC_REAL_END(cbe_system_error, 0x1200, 0x100)
 EXC_VIRT_NONE(0x5200, 0x100)
-TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1200)
+INT_KVM_HANDLER cbe_system_error, 0x1200, EXC_HV, PACA_EXGEN, 1
 EXC_COMMON(cbe_system_error_common, 0x1200, cbe_system_error_exception)
 #else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1200, 0x100)
@@ -1299,38 +1791,43 @@
 #endif
 
 
-EXC_REAL(instruction_breakpoint, 0x1300, 0x100)
-EXC_VIRT(instruction_breakpoint, 0x5300, 0x100, 0x1300)
-TRAMP_KVM_SKIP(PACA_EXGEN, 0x1300)
+EXC_REAL_BEGIN(instruction_breakpoint, 0x1300, 0x100)
+	INT_HANDLER instruction_breakpoint, 0x1300, kvm=1
+EXC_REAL_END(instruction_breakpoint, 0x1300, 0x100)
+EXC_VIRT_BEGIN(instruction_breakpoint, 0x5300, 0x100)
+	INT_HANDLER instruction_breakpoint, 0x1300, virt=1
+EXC_VIRT_END(instruction_breakpoint, 0x5300, 0x100)
+INT_KVM_HANDLER instruction_breakpoint, 0x1300, EXC_STD, PACA_EXGEN, 1
 EXC_COMMON(instruction_breakpoint_common, 0x1300, instruction_breakpoint_exception)
 
+
 EXC_REAL_NONE(0x1400, 0x100)
 EXC_VIRT_NONE(0x5400, 0x100)
 
 EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100)
-	mtspr	SPRN_SPRG_HSCRATCH0,r13
-	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500)
-
+	INT_HANDLER denorm_exception_hv, 0x1500, early=2, hsrr=EXC_HV
 #ifdef CONFIG_PPC_DENORMALISATION
 	mfspr	r10,SPRN_HSRR1
 	andis.	r10,r10,(HSRR1_DENORM)@h /* denorm? */
 	bne+	denorm_assist
 #endif
-
-	KVMTEST_HV(0x1500)
-	EXCEPTION_PROLOG_2(denorm_common, EXC_HV)
+	KVMTEST denorm_exception_hv, EXC_HV 0x1500
+	INT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV, 1
 EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100)
 
 #ifdef CONFIG_PPC_DENORMALISATION
 EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x100)
-	b	exc_real_0x1500_denorm_exception_hv
+	INT_HANDLER denorm_exception, 0x1500, 0, 2, 1, EXC_HV, PACA_EXGEN, 1, 0, 0, 0, 0
+	mfspr	r10,SPRN_HSRR1
+	andis.	r10,r10,(HSRR1_DENORM)@h /* denorm? */
+	bne+	denorm_assist
+	INT_VIRT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV
 EXC_VIRT_END(denorm_exception, 0x5500, 0x100)
 #else
 EXC_VIRT_NONE(0x5500, 0x100)
 #endif
 
-TRAMP_KVM_HV(PACA_EXGEN, 0x1500)
+INT_KVM_HANDLER denorm_exception_hv, 0x1500, EXC_HV, PACA_EXGEN, 0
 
 #ifdef CONFIG_PPC_DENORMALISATION
 TRAMP_REAL_BEGIN(denorm_assist)
@@ -1345,12 +1842,11 @@
 	mtmsrd	r10
 	sync
 
-#define FMR2(n)  fmr (n), (n) ; fmr n+1, n+1
-#define FMR4(n)  FMR2(n) ; FMR2(n+2)
-#define FMR8(n)  FMR4(n) ; FMR4(n+4)
-#define FMR16(n) FMR8(n) ; FMR8(n+8)
-#define FMR32(n) FMR16(n) ; FMR16(n+16)
-	FMR32(0)
+	.Lreg=0
+	.rept 32
+	fmr	.Lreg,.Lreg
+	.Lreg=.Lreg+1
+	.endr
 
 FTR_SECTION_ELSE
 /*
@@ -1362,12 +1858,11 @@
 	mtmsrd	r10
 	sync
 
-#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1)
-#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2)
-#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4)
-#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8)
-#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16)
-	XVCPSGNDP32(0)
+	.Lreg=0
+	.rept 32
+	XVCPSGNDP(.Lreg,.Lreg,.Lreg)
+	.Lreg=.Lreg+1
+	.endr
 
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206)
 
@@ -1378,7 +1873,12 @@
  * To denormalise we need to move a copy of the register to itself.
  * For POWER8 we need to do that for all 64 VSX registers
  */
-	XVCPSGNDP32(32)
+	.Lreg=32
+	.rept 32
+	XVCPSGNDP(.Lreg,.Lreg,.Lreg)
+	.Lreg=.Lreg+1
+	.endr
+
 denorm_done:
 	mfspr	r11,SPRN_HSRR0
 	subi	r11,r11,4
@@ -1402,9 +1902,11 @@
 
 
 #ifdef CONFIG_CBE_RAS
-EXC_REAL_HV(cbe_maintenance, 0x1600, 0x100)
+EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
+	INT_HANDLER cbe_maintenance, 0x1600, ool=1, hsrr=EXC_HV, kvm=1
+EXC_REAL_END(cbe_maintenance, 0x1600, 0x100)
 EXC_VIRT_NONE(0x5600, 0x100)
-TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1600)
+INT_KVM_HANDLER cbe_maintenance, 0x1600, EXC_HV, PACA_EXGEN, 1
 EXC_COMMON(cbe_maintenance_common, 0x1600, cbe_maintenance_exception)
 #else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1600, 0x100)
@@ -1412,9 +1914,13 @@
 #endif
 
 
-EXC_REAL(altivec_assist, 0x1700, 0x100)
-EXC_VIRT(altivec_assist, 0x5700, 0x100, 0x1700)
-TRAMP_KVM(PACA_EXGEN, 0x1700)
+EXC_REAL_BEGIN(altivec_assist, 0x1700, 0x100)
+	INT_HANDLER altivec_assist, 0x1700, kvm=1
+EXC_REAL_END(altivec_assist, 0x1700, 0x100)
+EXC_VIRT_BEGIN(altivec_assist, 0x5700, 0x100)
+	INT_HANDLER altivec_assist, 0x1700, virt=1
+EXC_VIRT_END(altivec_assist, 0x5700, 0x100)
+INT_KVM_HANDLER altivec_assist, 0x1700, EXC_STD, PACA_EXGEN, 0
 #ifdef CONFIG_ALTIVEC
 EXC_COMMON(altivec_assist_common, 0x1700, altivec_assist_exception)
 #else
@@ -1423,15 +1929,18 @@
 
 
 #ifdef CONFIG_CBE_RAS
-EXC_REAL_HV(cbe_thermal, 0x1800, 0x100)
+EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)
+	INT_HANDLER cbe_thermal, 0x1800, ool=1, hsrr=EXC_HV, kvm=1
+EXC_REAL_END(cbe_thermal, 0x1800, 0x100)
 EXC_VIRT_NONE(0x5800, 0x100)
-TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1800)
+INT_KVM_HANDLER cbe_thermal, 0x1800, EXC_HV, PACA_EXGEN, 1
 EXC_COMMON(cbe_thermal_common, 0x1800, cbe_thermal_exception)
 #else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1800, 0x100)
 EXC_VIRT_NONE(0x5800, 0x100)
 #endif
 
+
 #ifdef CONFIG_PPC_WATCHDOG
 
 #define MASKED_DEC_HANDLER_LABEL 3f
@@ -1441,7 +1950,7 @@
 	std	r12,PACA_EXGEN+EX_R12(r13);		\
 	GET_SCRATCH0(r10);				\
 	std	r10,PACA_EXGEN+EX_R13(r13);		\
-	EXCEPTION_PROLOG_2(soft_nmi_common, _H)
+	INT_SAVE_SRR_AND_JUMP soft_nmi_common, _H, 1
 
 /*
  * Branch to soft_nmi_interrupt using the emergency stack. The emergency
@@ -1456,9 +1965,10 @@
 	mr	r10,r1
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
-	EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900,
-			system_reset, soft_nmi_interrupt,
-			ADD_NVGPRS;ADD_RECONCILE)
+	INT_COMMON 0x900, PACA_EXGEN, 0, 1, 1, 0, 0
+	bl	save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	soft_nmi_interrupt
 	b	ret_from_except
 
 #else /* CONFIG_PPC_WATCHDOG */
@@ -1476,35 +1986,50 @@
  * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return.
  * This is called with r10 containing the value to OR to the paca field.
  */
-#define MASKED_INTERRUPT(_H)				\
-masked_##_H##interrupt:					\
-	std	r11,PACA_EXGEN+EX_R11(r13);		\
-	lbz	r11,PACAIRQHAPPENED(r13);		\
-	or	r11,r11,r10;				\
-	stb	r11,PACAIRQHAPPENED(r13);		\
-	cmpwi	r10,PACA_IRQ_DEC;			\
-	bne	1f;					\
-	lis	r10,0x7fff;				\
-	ori	r10,r10,0xffff;				\
-	mtspr	SPRN_DEC,r10;				\
-	b	MASKED_DEC_HANDLER_LABEL;		\
-1:	andi.	r10,r10,PACA_IRQ_MUST_HARD_MASK;	\
-	beq	2f;					\
-	mfspr	r10,SPRN_##_H##SRR1;			\
-	xori	r10,r10,MSR_EE; /* clear MSR_EE */	\
-	mtspr	SPRN_##_H##SRR1,r10;			\
-	ori	r11,r11,PACA_IRQ_HARD_DIS;		\
-	stb	r11,PACAIRQHAPPENED(r13);		\
-2:	/* done */					\
-	mtcrf	0x80,r9;				\
-	std	r1,PACAR1(r13);				\
-	ld	r9,PACA_EXGEN+EX_R9(r13);		\
-	ld	r10,PACA_EXGEN+EX_R10(r13);		\
-	ld	r11,PACA_EXGEN+EX_R11(r13);		\
-	/* returns to kernel where r13 must be set up, so don't restore it */ \
-	##_H##RFI_TO_KERNEL;				\
-	b	.;					\
-	MASKED_DEC_HANDLER(_H)
+.macro MASKED_INTERRUPT hsrr
+	.if \hsrr
+masked_Hinterrupt:
+	.else
+masked_interrupt:
+	.endif
+	std	r11,PACA_EXGEN+EX_R11(r13)
+	lbz	r11,PACAIRQHAPPENED(r13)
+	or	r11,r11,r10
+	stb	r11,PACAIRQHAPPENED(r13)
+	cmpwi	r10,PACA_IRQ_DEC
+	bne	1f
+	lis	r10,0x7fff
+	ori	r10,r10,0xffff
+	mtspr	SPRN_DEC,r10
+	b	MASKED_DEC_HANDLER_LABEL
+1:	andi.	r10,r10,PACA_IRQ_MUST_HARD_MASK
+	beq	2f
+	.if \hsrr
+	mfspr	r10,SPRN_HSRR1
+	xori	r10,r10,MSR_EE	/* clear MSR_EE */
+	mtspr	SPRN_HSRR1,r10
+	.else
+	mfspr	r10,SPRN_SRR1
+	xori	r10,r10,MSR_EE	/* clear MSR_EE */
+	mtspr	SPRN_SRR1,r10
+	.endif
+	ori	r11,r11,PACA_IRQ_HARD_DIS
+	stb	r11,PACAIRQHAPPENED(r13)
+2:	/* done */
+	mtcrf	0x80,r9
+	std	r1,PACAR1(r13)
+	ld	r9,PACA_EXGEN+EX_R9(r13)
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	ld	r11,PACA_EXGEN+EX_R11(r13)
+	/* returns to kernel where r13 must be set up, so don't restore it */
+	.if \hsrr
+	HRFI_TO_KERNEL
+	.else
+	RFI_TO_KERNEL
+	.endif
+	b	.
+	MASKED_DEC_HANDLER(\hsrr\())
+.endm
 
 TRAMP_REAL_BEGIN(stf_barrier_fallback)
 	std	r9,PACA_EXRFI+EX_R9(r13)
@@ -1611,8 +2136,8 @@
  * cannot reach these if they are put there.
  */
 USE_FIXED_SECTION(virt_trampolines)
-	MASKED_INTERRUPT()
-	MASKED_INTERRUPT(H)
+	MASKED_INTERRUPT EXC_STD
+	MASKED_INTERRUPT EXC_HV
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 TRAMP_REAL_BEGIN(kvmppc_skip_interrupt)
@@ -1698,6 +2223,35 @@
 
 USE_TEXT_SECTION()
 
+/* MSR[RI] should be clear because this uses SRR[01] */
+enable_machine_check:
+	mflr	r0
+	bcl	20,31,$+4
+0:	mflr	r3
+	addi	r3,r3,(1f - 0b)
+	mtspr	SPRN_SRR0,r3
+	mfmsr	r3
+	ori	r3,r3,MSR_ME
+	mtspr	SPRN_SRR1,r3
+	RFI_TO_KERNEL
+1:	mtlr	r0
+	blr
+
+/* MSR[RI] should be clear because this uses SRR[01] */
+disable_machine_check:
+	mflr	r0
+	bcl	20,31,$+4
+0:	mflr	r3
+	addi	r3,r3,(1f - 0b)
+	mtspr	SPRN_SRR0,r3
+	mfmsr	r3
+	li	r4,MSR_ME
+	andc	r3,r3,r4
+	mtspr	SPRN_SRR1,r3
+	RFI_TO_KERNEL
+1:	mtlr	r0
+	blr
+
 /*
  * Hash table stuff
  */
@@ -1706,23 +2260,21 @@
 #ifdef CONFIG_PPC_BOOK3S_64
 	lis	r0,(DSISR_BAD_FAULT_64S | DSISR_DABRMATCH | DSISR_KEYFAULT)@h
 	ori	r0,r0,DSISR_BAD_FAULT_64S@l
-	and.	r0,r4,r0		/* weird error? */
+	and.	r0,r5,r0		/* weird error? */
 	bne-	handle_page_fault	/* if not, try to insert a HPTE */
-	CURRENT_THREAD_INFO(r11, r1)
+	ld	r11, PACA_THREAD_INFO(r13)
 	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
 	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
 	bne	77f			/* then don't call hash_page now */
 
 	/*
-	 * r3 contains the faulting address
-	 * r4 msr
-	 * r5 contains the trap number
-	 * r6 contains dsisr
+	 * r3 contains the trap number
+	 * r4 contains the faulting address
+	 * r5 contains dsisr
+	 * r6 msr
 	 *
 	 * at return r3 = 0 for success, 1 for page fault, negative for error
 	 */
-        mr 	r4,r12
-	ld      r6,_DSISR(r1)
 	bl	__hash_page		/* build HPTE if possible */
         cmpdi	r3,0			/* see if __hash_page succeeded */
 
@@ -1732,24 +2284,23 @@
 	/* Error */
 	blt-	13f
 
-	/* Reload DSISR into r4 for the DABR check below */
-	ld      r4,_DSISR(r1)
+	/* Reload DAR/DSISR into r4/r5 for the DABR check below */
+	ld	r4,_DAR(r1)
+	ld      r5,_DSISR(r1)
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 /* Here we have a page fault that hash_page can't handle. */
 handle_page_fault:
-11:	andis.  r0,r4,DSISR_DABRMATCH@h
+11:	andis.  r0,r5,DSISR_DABRMATCH@h
 	bne-    handle_dabr_fault
-	ld	r4,_DAR(r1)
-	ld	r5,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_page_fault
 	cmpdi	r3,0
-	beq+	12f
+	beq+	ret_from_except_lite
 	bl	save_nvgprs
 	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	lwz	r4,_DAR(r1)
+	ld	r4,_DAR(r1)
 	bl	bad_page_fault
 	b	ret_from_except
 
@@ -1760,7 +2311,12 @@
 	ld      r5,_DSISR(r1)
 	addi    r3,r1,STACK_FRAME_OVERHEAD
 	bl      do_break
-12:	b       ret_from_except_lite
+	/*
+	 * do_break() may have changed the NV GPRS while handling a breakpoint.
+	 * If so, we need to restore them with their updated values. Don't use
+	 * ret_from_except_lite here.
+	 */
+	b       ret_from_except
 
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -1783,74 +2339,12 @@
  * the access, or panic if there isn't a handler.
  */
 77:	bl	save_nvgprs
-	mr	r4,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	li	r5,SIGSEGV
 	bl	bad_page_fault
 	b	ret_from_except
 
 /*
- * Here we have detected that the kernel stack pointer is bad.
- * R9 contains the saved CR, r13 points to the paca,
- * r10 contains the (bad) kernel stack pointer,
- * r11 and r12 contain the saved SRR0 and SRR1.
- * We switch to using an emergency stack, save the registers there,
- * and call kernel_bad_stack(), which panics.
- */
-bad_stack:
-	ld	r1,PACAEMERGSP(r13)
-	subi	r1,r1,64+INT_FRAME_SIZE
-	std	r9,_CCR(r1)
-	std	r10,GPR1(r1)
-	std	r11,_NIP(r1)
-	std	r12,_MSR(r1)
-	mfspr	r11,SPRN_DAR
-	mfspr	r12,SPRN_DSISR
-	std	r11,_DAR(r1)
-	std	r12,_DSISR(r1)
-	mflr	r10
-	mfctr	r11
-	mfxer	r12
-	std	r10,_LINK(r1)
-	std	r11,_CTR(r1)
-	std	r12,_XER(r1)
-	SAVE_GPR(0,r1)
-	SAVE_GPR(2,r1)
-	ld	r10,EX_R3(r3)
-	std	r10,GPR3(r1)
-	SAVE_GPR(4,r1)
-	SAVE_4GPRS(5,r1)
-	ld	r9,EX_R9(r3)
-	ld	r10,EX_R10(r3)
-	SAVE_2GPRS(9,r1)
-	ld	r9,EX_R11(r3)
-	ld	r10,EX_R12(r3)
-	ld	r11,EX_R13(r3)
-	std	r9,GPR11(r1)
-	std	r10,GPR12(r1)
-	std	r11,GPR13(r1)
-BEGIN_FTR_SECTION
-	ld	r10,EX_CFAR(r3)
-	std	r10,ORIG_GPR3(r1)
-END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
-	SAVE_8GPRS(14,r1)
-	SAVE_10GPRS(22,r1)
-	lhz	r12,PACA_TRAP_SAVE(r13)
-	std	r12,_TRAP(r1)
-	addi	r11,r1,INT_FRAME_SIZE
-	std	r11,0(r1)
-	li	r12,0
-	std	r12,0(r11)
-	ld	r2,PACATOC(r13)
-	ld	r11,exception_marker@toc(r2)
-	std	r12,RESULT(r1)
-	std	r11,STACK_FRAME_OVERHEAD-16(r1)
-1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	kernel_bad_stack
-	b	1b
-_ASM_NOKPROBE_SYMBOL(bad_stack);
-
-/*
  * When doorbell is triggered from system reset wakeup, the message is
  * not cleared, so it would fire again when EE is enabled.
  *
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index a711d22..ed59855 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Firmware Assisted dump: A robust mechanism to get reliable kernel crash
  * dump with assistance from firmware. This approach does not use kexec,
@@ -6,20 +7,6 @@
  * from phyp assisted dump implementation written by Linas Vepstas and
  * Manish Ahuja
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright 2011 IBM Corporation
  * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
  */
@@ -35,97 +22,128 @@
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/cma.h>
+#include <linux/hugetlb.h>
 
 #include <asm/debugfs.h>
 #include <asm/page.h>
 #include <asm/prom.h>
-#include <asm/rtas.h>
 #include <asm/fadump.h>
+#include <asm/fadump-internal.h>
 #include <asm/setup.h>
 
 static struct fw_dump fw_dump;
-static struct fadump_mem_struct fdm;
-static const struct fadump_mem_struct *fdm_active;
 
+static void __init fadump_reserve_crash_area(u64 base);
+
+#ifndef CONFIG_PRESERVE_FA_DUMP
 static DEFINE_MUTEX(fadump_mutex);
-struct fad_crash_memory_ranges *crash_memory_ranges;
-int crash_memory_ranges_size;
-int crash_mem_ranges;
-int max_crash_mem_ranges;
+struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0 };
+struct fadump_mrange_info reserved_mrange_info = { "reserved", NULL, 0, 0, 0 };
 
-/* 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)
+#ifdef CONFIG_CMA
+static struct cma *fadump_cma;
+
+/*
+ * fadump_cma_init() - Initialize CMA area from a fadump reserved memory
+ *
+ * This function initializes CMA area from fadump reserved memory.
+ * The total size of fadump reserved memory covers for boot memory size
+ * + cpu data size + hpte size and metadata.
+ * Initialize only the area equivalent to boot memory size for CMA use.
+ * The reamining portion of fadump reserved memory will be not given
+ * to CMA and pages for thoes will stay reserved. boot memory size is
+ * aligned per CMA requirement to satisy cma_init_reserved_mem() call.
+ * But for some reason even if it fails we still have the memory reservation
+ * with us and we can still continue doing fadump.
+ */
+int __init fadump_cma_init(void)
 {
-	const __be32 *sections;
-	int i, num_sections;
-	int size;
-	const __be32 *token;
+	unsigned long long base, size;
+	int rc;
 
-	if (depth != 1 || strcmp(uname, "rtas") != 0)
+	if (!fw_dump.fadump_enabled)
 		return 0;
 
 	/*
-	 * Check if Firmware Assisted dump is supported. if yes, check
-	 * if dump has been initiated on last reboot.
+	 * Do not use CMA if user has provided fadump=nocma kernel parameter.
+	 * Return 1 to continue with fadump old behaviour.
 	 */
-	token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
-	if (!token)
+	if (fw_dump.nocma)
 		return 1;
 
-	fw_dump.fadump_supported = 1;
-	fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token);
+	base = fw_dump.reserve_dump_area_start;
+	size = fw_dump.boot_memory_size;
 
-	/*
-	 * The 'ibm,kernel-dump' rtas node is present only if there is
-	 * dump data waiting for us.
-	 */
-	fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
-	if (fdm_active)
-		fw_dump.dump_active = 1;
+	if (!size)
+		return 0;
 
-	/* Get the sizes required to store dump data for the firmware provided
-	 * dump sections.
-	 * For each dump section type supported, a 32bit cell which defines
-	 * the ID of a supported section followed by two 32 bit cells which
-	 * gives teh size of the section in bytes.
-	 */
-	sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
-					&size);
-
-	if (!sections)
+	rc = cma_init_reserved_mem(base, size, 0, "fadump_cma", &fadump_cma);
+	if (rc) {
+		pr_err("Failed to init cma area for firmware-assisted dump,%d\n", rc);
+		/*
+		 * Though the CMA init has failed we still have memory
+		 * reservation with us. The reserved memory will be
+		 * blocked from production system usage.  Hence return 1,
+		 * so that we can continue with fadump.
+		 */
 		return 1;
-
-	num_sections = size / (3 * sizeof(u32));
-
-	for (i = 0; i < num_sections; i++, sections += 3) {
-		u32 type = (u32)of_read_number(sections, 1);
-
-		switch (type) {
-		case FADUMP_CPU_STATE_DATA:
-			fw_dump.cpu_state_data_size =
-					of_read_ulong(&sections[1], 2);
-			break;
-		case FADUMP_HPTE_REGION:
-			fw_dump.hpte_region_size =
-					of_read_ulong(&sections[1], 2);
-			break;
-		}
 	}
 
+	/*
+	 * So we now have successfully initialized cma area for fadump.
+	 */
+	pr_info("Initialized 0x%lx bytes cma area at %ldMB from 0x%lx "
+		"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;
 }
+#else
+static int __init fadump_cma_init(void) { return 1; }
+#endif /* CONFIG_CMA */
+
+/* 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)
+{
+	if (depth != 1)
+		return 0;
+
+	if (strcmp(uname, "rtas") == 0) {
+		rtas_fadump_dt_scan(&fw_dump, node);
+		return 1;
+	}
+
+	if (strcmp(uname, "ibm,opal") == 0) {
+		opal_fadump_dt_scan(&fw_dump, node);
+		return 1;
+	}
+
+	return 0;
+}
 
 /*
  * If fadump is registered, check if the memory provided
- * falls within boot memory area.
+ * falls within boot memory area and reserved memory area.
  */
-int is_fadump_boot_memory_area(u64 addr, ulong size)
+int is_fadump_memory_area(u64 addr, unsigned long size)
 {
+	u64 d_start, d_end;
+
 	if (!fw_dump.dump_registered)
 		return 0;
 
-	return (addr + size) > RMA_START && addr <= fw_dump.boot_memory_size;
+	if (!size)
+		return 0;
+
+	d_start = fw_dump.reserve_dump_area_start;
+	d_end = d_start + fw_dump.reserve_dump_area_size;
+	if (((addr + size) > d_start) && (addr <= d_end))
+		return 1;
+
+	return (addr <= fw_dump.boot_mem_top);
 }
 
 int should_fadump_crash(void)
@@ -141,40 +159,75 @@
 }
 
 /*
- * Returns 1, if there are no holes in boot memory area,
- * 0 otherwise.
+ * Returns true, if there are no holes in memory area between d_start to d_end,
+ * false otherwise.
  */
-static int is_boot_memory_area_contiguous(void)
+static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end)
 {
 	struct memblock_region *reg;
-	unsigned long tstart, tend;
-	unsigned long start_pfn = PHYS_PFN(RMA_START);
-	unsigned long end_pfn = PHYS_PFN(RMA_START + fw_dump.boot_memory_size);
-	unsigned int ret = 0;
+	bool ret = false;
+	u64 start, end;
 
 	for_each_memblock(memory, reg) {
-		tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
-		tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
-		if (tstart < tend) {
-			/* Memory hole from start_pfn to tstart */
-			if (tstart > start_pfn)
+		start = max_t(u64, d_start, reg->base);
+		end = min_t(u64, d_end, (reg->base + reg->size));
+		if (d_start < end) {
+			/* Memory hole from d_start to start */
+			if (start > d_start)
 				break;
 
-			if (tend == end_pfn) {
-				ret = 1;
+			if (end == d_end) {
+				ret = true;
 				break;
 			}
 
-			start_pfn = tend + 1;
+			d_start = end + 1;
 		}
 	}
 
 	return ret;
 }
 
+/*
+ * 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.
+ */
+bool is_fadump_reserved_mem_contiguous(void)
+{
+	u64 d_start, d_end;
+
+	d_start	= fw_dump.reserve_dump_area_start;
+	d_end	= d_start + fw_dump.reserve_dump_area_size;
+	return is_fadump_mem_area_contiguous(d_start, d_end);
+}
+
 /* Print firmware assisted dump configurations for debugging purpose. */
 static void fadump_show_config(void)
 {
+	int i;
+
 	pr_debug("Support for firmware-assisted dump (fadump): %s\n",
 			(fw_dump.fadump_supported ? "present" : "no support"));
 
@@ -188,62 +241,13 @@
 	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);
-	pr_debug("Boot memory size  : %lx\n", fw_dump.boot_memory_size);
-}
-
-static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
-				unsigned long addr)
-{
-	if (!fdm)
-		return 0;
-
-	memset(fdm, 0, sizeof(struct 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 fadump_mem_struct, cpu_state_data));
-
-	/*
-	 * Fields for disk dump option.
-	 * We are not using disk dump option, hence set these fields to 0.
-	 */
-	fdm->header.dd_block_size = 0;
-	fdm->header.dd_block_offset = 0;
-	fdm->header.dd_num_blocks = 0;
-	fdm->header.dd_offset_disk_path = 0;
-
-	/* set 0 to disable an automatic dump-reboot. */
-	fdm->header.max_time_auto = 0;
-
-	/* Kernel dump sections */
-	/* cpu state data section. */
-	fdm->cpu_state_data.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
-	fdm->cpu_state_data.source_data_type = cpu_to_be16(FADUMP_CPU_STATE_DATA);
-	fdm->cpu_state_data.source_address = 0;
-	fdm->cpu_state_data.source_len = cpu_to_be64(fw_dump.cpu_state_data_size);
-	fdm->cpu_state_data.destination_address = cpu_to_be64(addr);
-	addr += fw_dump.cpu_state_data_size;
-
-	/* hpte region section */
-	fdm->hpte_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
-	fdm->hpte_region.source_data_type = cpu_to_be16(FADUMP_HPTE_REGION);
-	fdm->hpte_region.source_address = 0;
-	fdm->hpte_region.source_len = cpu_to_be64(fw_dump.hpte_region_size);
-	fdm->hpte_region.destination_address = cpu_to_be64(addr);
-	addr += fw_dump.hpte_region_size;
-
-	/* RMA region section */
-	fdm->rmr_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
-	fdm->rmr_region.source_data_type = cpu_to_be16(FADUMP_REAL_MODE_REGION);
-	fdm->rmr_region.source_address = cpu_to_be64(RMA_START);
-	fdm->rmr_region.source_len = cpu_to_be64(fw_dump.boot_memory_size);
-	fdm->rmr_region.destination_address = cpu_to_be64(addr);
-	addr += fw_dump.boot_memory_size;
-
-	return addr;
+	pr_debug("    Boot memory size   : %lx\n", fw_dump.boot_memory_size);
+	pr_debug("    Boot memory top    : %llx\n", fw_dump.boot_mem_top);
+	pr_debug("Boot memory regions cnt: %llx\n", fw_dump.boot_mem_regs_cnt);
+	for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+		pr_debug("[%03d] base = %llx, size = %llx\n", i,
+			 fw_dump.boot_mem_addr[i], fw_dump.boot_mem_sz[i]);
+	}
 }
 
 /**
@@ -261,10 +265,10 @@
  * that is required for a kernel to boot successfully.
  *
  */
-static inline unsigned long fadump_calculate_reserve_size(void)
+static inline u64 fadump_calculate_reserve_size(void)
 {
+	u64 base, size, bootmem_min;
 	int ret;
-	unsigned long long base, size;
 
 	if (fw_dump.reserve_bootvar)
 		pr_warn("'fadump_reserve_mem=' parameter is deprecated in favor of 'crashkernel=' parameter.\n");
@@ -314,7 +318,8 @@
 	if (memory_limit && size > memory_limit)
 		size = memory_limit;
 
-	return (size > MIN_BOOT_MEM ? size : MIN_BOOT_MEM);
+	bootmem_min = fw_dump.ops->fadump_get_bootmem_min();
+	return (size > bootmem_min ? size : bootmem_min);
 }
 
 /*
@@ -335,51 +340,137 @@
 	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 ?
+		 fw_dump.ops->fadump_get_metadata_size() : 0);
 	return size;
 }
 
-static void __init fadump_reserve_crash_area(unsigned long base,
-					     unsigned long size)
+static int __init add_boot_mem_region(unsigned long rstart,
+				      unsigned long rsize)
 {
-	struct memblock_region *reg;
-	unsigned long mstart, mend, msize;
+	int i = fw_dump.boot_mem_regs_cnt++;
 
-	for_each_memblock(memory, reg) {
-		mstart = max_t(unsigned long, base, reg->base);
-		mend = reg->base + reg->size;
-		mend = min(base + size, mend);
-
-		if (mstart < mend) {
-			msize = mend - mstart;
-			memblock_reserve(mstart, msize);
-			pr_info("Reserved %ldMB of memory at %#016lx for saving crash dump\n",
-				(msize >> 20), mstart);
-		}
+	if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) {
+		fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS;
+		return 0;
 	}
+
+	pr_debug("Added boot memory range[%d] [%#016lx-%#016lx)\n",
+		 i, rstart, (rstart + rsize));
+	fw_dump.boot_mem_addr[i] = rstart;
+	fw_dump.boot_mem_sz[i] = rsize;
+	return 1;
+}
+
+/*
+ * Firmware usually has a hard limit on the data it can copy per region.
+ * Honour that by splitting a memory range into multiple regions.
+ */
+static int __init add_boot_mem_regions(unsigned long mstart,
+				       unsigned long msize)
+{
+	unsigned long rstart, rsize, max_size;
+	int ret = 1;
+
+	rstart = mstart;
+	max_size = fw_dump.max_copy_size ? fw_dump.max_copy_size : msize;
+	while (msize) {
+		if (msize > max_size)
+			rsize = max_size;
+		else
+			rsize = msize;
+
+		ret = add_boot_mem_region(rstart, rsize);
+		if (!ret)
+			break;
+
+		msize -= rsize;
+		rstart += rsize;
+	}
+
+	return ret;
+}
+
+static int __init fadump_get_boot_mem_regions(void)
+{
+	unsigned long base, size, cur_size, hole_size, last_end;
+	unsigned long mem_size = fw_dump.boot_memory_size;
+	struct memblock_region *reg;
+	int ret = 1;
+
+	fw_dump.boot_mem_regs_cnt = 0;
+
+	last_end = 0;
+	hole_size = 0;
+	cur_size = 0;
+	for_each_memblock(memory, reg) {
+		base = reg->base;
+		size = reg->size;
+		hole_size += (base - last_end);
+
+		if ((cur_size + size) >= mem_size) {
+			size = (mem_size - cur_size);
+			ret = add_boot_mem_regions(base, size);
+			break;
+		}
+
+		mem_size -= size;
+		cur_size += size;
+		ret = add_boot_mem_regions(base, size);
+		if (!ret)
+			break;
+
+		last_end = base + size;
+	}
+	fw_dump.boot_mem_top = PAGE_ALIGN(fw_dump.boot_memory_size + hole_size);
+
+	return ret;
 }
 
 int __init fadump_reserve_mem(void)
 {
-	unsigned long base, size, memory_boundary;
+	u64 base, size, mem_boundary, bootmem_min, align = PAGE_SIZE;
+	bool is_memblock_bottom_up = memblock_bottom_up();
+	int ret = 1;
 
 	if (!fw_dump.fadump_enabled)
 		return 0;
 
 	if (!fw_dump.fadump_supported) {
-		printk(KERN_INFO "Firmware-assisted dump is not supported on"
-				" this hardware\n");
-		fw_dump.fadump_enabled = 0;
-		return 0;
+		pr_info("Firmware-Assisted Dump is not supported on this hardware\n");
+		goto error_out;
 	}
+
 	/*
 	 * Initialize boot memory size
 	 * If dump is active then we have already calculated the size during
 	 * first kernel.
 	 */
-	if (fdm_active)
-		fw_dump.boot_memory_size = be64_to_cpu(fdm_active->rmr_region.source_len);
-	else
-		fw_dump.boot_memory_size = fadump_calculate_reserve_size();
+	if (!fw_dump.dump_active) {
+		fw_dump.boot_memory_size =
+			PAGE_ALIGN(fadump_calculate_reserve_size());
+#ifdef CONFIG_CMA
+		if (!fw_dump.nocma) {
+			align = FADUMP_CMA_ALIGNMENT;
+			fw_dump.boot_memory_size =
+				ALIGN(fw_dump.boot_memory_size, align);
+		}
+#endif
+
+		bootmem_min = fw_dump.ops->fadump_get_bootmem_min();
+		if (fw_dump.boot_memory_size < bootmem_min) {
+			pr_err("Can't enable fadump with boot memory size (0x%lx) less than 0x%llx\n",
+			       fw_dump.boot_memory_size, bootmem_min);
+			goto error_out;
+		}
+
+		if (!fadump_get_boot_mem_regions()) {
+			pr_err("Too many holes in boot memory area to enable fadump\n");
+			goto error_out;
+		}
+	}
 
 	/*
 	 * Calculate the memory boundary.
@@ -398,10 +489,13 @@
 				" dump, now %#016llx\n", memory_limit);
 	}
 	if (memory_limit)
-		memory_boundary = memory_limit;
+		mem_boundary = memory_limit;
 	else
-		memory_boundary = memblock_end_of_DRAM();
+		mem_boundary = memblock_end_of_DRAM();
 
+	base = fw_dump.boot_mem_top;
+	size = get_fadump_area_size();
+	fw_dump.reserve_dump_area_size = size;
 	if (fw_dump.dump_active) {
 		pr_info("Firmware-assisted dump is active.\n");
 
@@ -415,56 +509,55 @@
 #endif
 		/*
 		 * If last boot has crashed then reserve all the memory
-		 * above boot_memory_size so that we don't touch it until
+		 * above boot memory size so that we don't touch it until
 		 * dump is written to disk by userspace tool. This memory
-		 * will be released for general use once the dump is saved.
+		 * can be released for general use by invalidating fadump.
 		 */
-		base = fw_dump.boot_memory_size;
-		size = memory_boundary - base;
-		fadump_reserve_crash_area(base, size);
+		fadump_reserve_crash_area(base);
 
-		fw_dump.fadumphdr_addr =
-				be64_to_cpu(fdm_active->rmr_region.destination_address) +
-				be64_to_cpu(fdm_active->rmr_region.source_len);
-		pr_debug("fadumphdr_addr = %p\n",
-				(void *) fw_dump.fadumphdr_addr);
+		pr_debug("fadumphdr_addr = %#016lx\n", fw_dump.fadumphdr_addr);
+		pr_debug("Reserve dump area start address: 0x%lx\n",
+			 fw_dump.reserve_dump_area_start);
 	} else {
-		size = get_fadump_area_size();
-
 		/*
 		 * Reserve memory at an offset closer to bottom of the RAM to
-		 * minimize the impact of memory hot-remove operation. We can't
-		 * use memblock_find_in_range() here since it doesn't allocate
-		 * from bottom to top.
+		 * minimize the impact of memory hot-remove operation.
 		 */
-		for (base = fw_dump.boot_memory_size;
-		     base <= (memory_boundary - size);
-		     base += size) {
-			if (memblock_is_region_memory(base, size) &&
-			    !memblock_is_region_reserved(base, size))
-				break;
+		memblock_set_bottom_up(true);
+		base = memblock_find_in_range(base, mem_boundary, size, align);
+
+		/* Restore the previous allocation mode */
+		memblock_set_bottom_up(is_memblock_bottom_up);
+
+		if (!base) {
+			pr_err("Failed to find memory chunk for reservation!\n");
+			goto error_out;
 		}
-		if ((base > (memory_boundary - size)) ||
-		    memblock_reserve(base, size)) {
-			pr_err("Failed to reserve memory\n");
-			return 0;
+		fw_dump.reserve_dump_area_start = base;
+
+		/*
+		 * Calculate the kernel metadata address and register it with
+		 * f/w if the platform supports.
+		 */
+		if (fw_dump.ops->fadump_setup_metadata &&
+		    (fw_dump.ops->fadump_setup_metadata(&fw_dump) < 0))
+			goto error_out;
+
+		if (memblock_reserve(base, size)) {
+			pr_err("Failed to reserve memory!\n");
+			goto error_out;
 		}
 
-		pr_info("Reserved %ldMB of memory at %ldMB for firmware-"
-			"assisted dump (System RAM: %ldMB)\n",
-			(unsigned long)(size >> 20),
-			(unsigned long)(base >> 20),
-			(unsigned long)(memblock_phys_mem_size() >> 20));
+		pr_info("Reserved %lldMB of memory at %#016llx (System RAM: %lldMB)\n",
+			(size >> 20), base, (memblock_phys_mem_size() >> 20));
+
+		ret = fadump_cma_init();
 	}
 
-	fw_dump.reserve_dump_area_start = base;
-	fw_dump.reserve_dump_area_size = size;
-	return 1;
-}
-
-unsigned long __init arch_reserved_kernel_pages(void)
-{
-	return memblock_reserved_size() / PAGE_SIZE;
+	return ret;
+error_out:
+	fw_dump.fadump_enabled = 0;
+	return 0;
 }
 
 /* Look for fadump= cmdline option. */
@@ -477,6 +570,10 @@
 		fw_dump.fadump_enabled = 1;
 	else if (strncmp(p, "off", 3) == 0)
 		fw_dump.fadump_enabled = 0;
+	else if (strncmp(p, "nocma", 5) == 0) {
+		fw_dump.fadump_enabled = 1;
+		fw_dump.nocma = 1;
+	}
 
 	return 0;
 }
@@ -495,59 +592,6 @@
 }
 early_param("fadump_reserve_mem", early_fadump_reserve_mem);
 
-static int register_fw_dump(struct fadump_mem_struct *fdm)
-{
-	int rc, err;
-	unsigned int wait_time;
-
-	pr_debug("Registering for firmware-assisted kernel dump...\n");
-
-	/* TODO: Add upper time limit for the delay */
-	do {
-		rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
-			FADUMP_REGISTER, fdm,
-			sizeof(struct fadump_mem_struct));
-
-		wait_time = rtas_busy_delay_time(rc);
-		if (wait_time)
-			mdelay(wait_time);
-
-	} while (wait_time);
-
-	err = -EIO;
-	switch (rc) {
-	default:
-		pr_err("Failed to register. Unknown Error(%d).\n", rc);
-		break;
-	case -1:
-		printk(KERN_ERR "Failed to register firmware-assisted kernel"
-			" dump. Hardware Error(%d).\n", rc);
-		break;
-	case -3:
-		if (!is_boot_memory_area_contiguous())
-			pr_err("Can't have holes in boot memory area while "
-			       "registering fadump\n");
-
-		printk(KERN_ERR "Failed to register firmware-assisted kernel"
-			" dump. Parameter Error(%d).\n", rc);
-		err = -EINVAL;
-		break;
-	case -9:
-		printk(KERN_ERR "firmware-assisted kernel dump is already "
-			" registered.");
-		fw_dump.dump_registered = 1;
-		err = -EEXIST;
-		break;
-	case 0:
-		printk(KERN_INFO "firmware-assisted kernel dump registration"
-			" is successful\n");
-		fw_dump.dump_registered = 1;
-		err = 0;
-		break;
-	}
-	return err;
-}
-
 void crash_fadump(struct pt_regs *regs, const char *str)
 {
 	struct fadump_crash_info_header *fdh = NULL;
@@ -590,71 +634,10 @@
 
 	fdh->online_mask = *cpu_online_mask;
 
-	/* Call ibm,os-term rtas call to trigger firmware assisted dump */
-	rtas_os_term((char *)str);
+	fw_dump.ops->fadump_trigger(fdh, str);
 }
 
-#define GPR_MASK	0xffffff0000000000
-static inline int fadump_gpr_index(u64 id)
-{
-	int i = -1;
-	char str[3];
-
-	if ((id & GPR_MASK) == REG_ID("GPR")) {
-		/* get the digits at the end */
-		id &= ~GPR_MASK;
-		id >>= 24;
-		str[2] = '\0';
-		str[1] = id & 0xff;
-		str[0] = (id >> 8) & 0xff;
-		sscanf(str, "%d", &i);
-		if (i > 31)
-			i = -1;
-	}
-	return i;
-}
-
-static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id,
-								u64 reg_val)
-{
-	int i;
-
-	i = fadump_gpr_index(reg_id);
-	if (i >= 0)
-		regs->gpr[i] = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("NIA"))
-		regs->nip = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("MSR"))
-		regs->msr = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("CTR"))
-		regs->ctr = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("LR"))
-		regs->link = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("XER"))
-		regs->xer = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("CR"))
-		regs->ccr = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("DAR"))
-		regs->dar = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("DSISR"))
-		regs->dsisr = (unsigned long)reg_val;
-}
-
-static struct fadump_reg_entry*
-fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
-{
-	memset(regs, 0, sizeof(struct pt_regs));
-
-	while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) {
-		fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id),
-					be64_to_cpu(reg_entry->reg_value));
-		reg_entry++;
-	}
-	reg_entry++;
-	return reg_entry;
-}
-
-static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
+u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
 {
 	struct elf_prstatus prstatus;
 
@@ -669,7 +652,7 @@
 	return buf;
 }
 
-static void fadump_update_elfcore_header(char *bufp)
+void fadump_update_elfcore_header(char *bufp)
 {
 	struct elfhdr *elf;
 	struct elf_phdr *phdr;
@@ -681,7 +664,7 @@
 	phdr = (struct elf_phdr *)bufp;
 
 	if (phdr->p_type == PT_NOTE) {
-		phdr->p_paddr = fw_dump.cpu_notes_buf;
+		phdr->p_paddr	= __pa(fw_dump.cpu_notes_buf_vaddr);
 		phdr->p_offset	= phdr->p_paddr;
 		phdr->p_filesz	= fw_dump.cpu_notes_buf_size;
 		phdr->p_memsz = fw_dump.cpu_notes_buf_size;
@@ -689,228 +672,100 @@
 	return;
 }
 
-static void *fadump_cpu_notes_buf_alloc(unsigned long size)
+static void *fadump_alloc_buffer(unsigned long size)
 {
-	void *vaddr;
+	unsigned long count, i;
 	struct page *page;
-	unsigned long order, count, i;
+	void *vaddr;
 
-	order = get_order(size);
-	vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
+	vaddr = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
 	if (!vaddr)
 		return NULL;
 
-	count = 1 << order;
+	count = PAGE_ALIGN(size) / PAGE_SIZE;
 	page = virt_to_page(vaddr);
 	for (i = 0; i < count; i++)
-		SetPageReserved(page + i);
+		mark_page_reserved(page + i);
 	return vaddr;
 }
 
-static void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
+static void fadump_free_buffer(unsigned long vaddr, unsigned long size)
 {
-	struct page *page;
-	unsigned long order, count, i;
-
-	order = get_order(size);
-	count = 1 << order;
-	page = virt_to_page(vaddr);
-	for (i = 0; i < count; i++)
-		ClearPageReserved(page + i);
-	__free_pages(page, order);
+	free_reserved_area((void *)vaddr, (void *)(vaddr + size), -1, NULL);
 }
 
-/*
- * Read CPU state dump data and convert it into ELF notes.
- * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
- * used to access the data to allow for additional fields to be added without
- * affecting compatibility. Each list of registers for a CPU starts with
- * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
- * 8 Byte ASCII identifier and 8 Byte register value. The register entry
- * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
- * of register value. For more details refer to PAPR document.
- *
- * Only for the crashing cpu we ignore the CPU dump data and get exact
- * state from fadump crash info structure populated by first kernel at the
- * time of crash.
- */
-static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
+s32 fadump_setup_cpu_notes_buf(u32 num_cpus)
 {
-	struct fadump_reg_save_area_header *reg_header;
-	struct fadump_reg_entry *reg_entry;
-	struct fadump_crash_info_header *fdh = NULL;
-	void *vaddr;
-	unsigned long addr;
-	u32 num_cpus, *note_buf;
-	struct pt_regs regs;
-	int i, rc = 0, cpu = 0;
-
-	if (!fdm->cpu_state_data.bytes_dumped)
-		return -EINVAL;
-
-	addr = be64_to_cpu(fdm->cpu_state_data.destination_address);
-	vaddr = __va(addr);
-
-	reg_header = vaddr;
-	if (be64_to_cpu(reg_header->magic_number) != REGSAVE_AREA_MAGIC) {
-		printk(KERN_ERR "Unable to read register save area.\n");
-		return -ENOENT;
-	}
-	pr_debug("--------CPU State Data------------\n");
-	pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number));
-	pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset));
-
-	vaddr += be32_to_cpu(reg_header->num_cpu_offset);
-	num_cpus = be32_to_cpu(*((__be32 *)(vaddr)));
-	pr_debug("NumCpus     : %u\n", num_cpus);
-	vaddr += sizeof(u32);
-	reg_entry = (struct fadump_reg_entry *)vaddr;
-
 	/* Allocate buffer to hold cpu crash notes. */
 	fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
 	fw_dump.cpu_notes_buf_size = PAGE_ALIGN(fw_dump.cpu_notes_buf_size);
-	note_buf = fadump_cpu_notes_buf_alloc(fw_dump.cpu_notes_buf_size);
-	if (!note_buf) {
-		printk(KERN_ERR "Failed to allocate 0x%lx bytes for "
-			"cpu notes buffer\n", fw_dump.cpu_notes_buf_size);
+	fw_dump.cpu_notes_buf_vaddr =
+		(unsigned long)fadump_alloc_buffer(fw_dump.cpu_notes_buf_size);
+	if (!fw_dump.cpu_notes_buf_vaddr) {
+		pr_err("Failed to allocate %ld bytes for CPU notes buffer\n",
+		       fw_dump.cpu_notes_buf_size);
 		return -ENOMEM;
 	}
-	fw_dump.cpu_notes_buf = __pa(note_buf);
 
-	pr_debug("Allocated buffer for cpu notes of size %ld at %p\n",
-			(num_cpus * sizeof(note_buf_t)), note_buf);
-
-	if (fw_dump.fadumphdr_addr)
-		fdh = __va(fw_dump.fadumphdr_addr);
-
-	for (i = 0; i < num_cpus; i++) {
-		if (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUSTRT")) {
-			printk(KERN_ERR "Unable to read CPU state data\n");
-			rc = -ENOENT;
-			goto error_out;
-		}
-		/* Lower 4 bytes of reg_value contains logical cpu id */
-		cpu = be64_to_cpu(reg_entry->reg_value) & FADUMP_CPU_ID_MASK;
-		if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) {
-			SKIP_TO_NEXT_CPU(reg_entry);
-			continue;
-		}
-		pr_debug("Reading register data for cpu %d...\n", cpu);
-		if (fdh && fdh->crashing_cpu == cpu) {
-			regs = fdh->regs;
-			note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
-			SKIP_TO_NEXT_CPU(reg_entry);
-		} else {
-			reg_entry++;
-			reg_entry = fadump_read_registers(reg_entry, &regs);
-			note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
-		}
-	}
-	final_note(note_buf);
-
-	if (fdh) {
-		pr_debug("Updating elfcore header (%llx) with cpu notes\n",
-							fdh->elfcorehdr_addr);
-		fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
-	}
+	pr_debug("Allocated buffer for cpu notes of size %ld at 0x%lx\n",
+		 fw_dump.cpu_notes_buf_size,
+		 fw_dump.cpu_notes_buf_vaddr);
 	return 0;
+}
 
-error_out:
-	fadump_cpu_notes_buf_free((unsigned long)__va(fw_dump.cpu_notes_buf),
-					fw_dump.cpu_notes_buf_size);
-	fw_dump.cpu_notes_buf = 0;
+void fadump_free_cpu_notes_buf(void)
+{
+	if (!fw_dump.cpu_notes_buf_vaddr)
+		return;
+
+	fadump_free_buffer(fw_dump.cpu_notes_buf_vaddr,
+			   fw_dump.cpu_notes_buf_size);
+	fw_dump.cpu_notes_buf_vaddr = 0;
 	fw_dump.cpu_notes_buf_size = 0;
-	return rc;
+}
 
+static void fadump_free_mem_ranges(struct fadump_mrange_info *mrange_info)
+{
+	kfree(mrange_info->mem_ranges);
+	mrange_info->mem_ranges = NULL;
+	mrange_info->mem_ranges_sz = 0;
+	mrange_info->max_mem_ranges = 0;
 }
 
 /*
- * Validate and process the dump data stored by firmware before exporting
- * it through '/proc/vmcore'.
- */
-static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
-{
-	struct fadump_crash_info_header *fdh;
-	int rc = 0;
-
-	if (!fdm_active || !fw_dump.fadumphdr_addr)
-		return -EINVAL;
-
-	/* Check if the dump data is valid. */
-	if ((be16_to_cpu(fdm_active->header.dump_status_flag) == FADUMP_ERROR_FLAG) ||
-			(fdm_active->cpu_state_data.error_flags != 0) ||
-			(fdm_active->rmr_region.error_flags != 0)) {
-		printk(KERN_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) {
-		printk(KERN_ERR "Dump taken by platform is incomplete\n");
-		return -EINVAL;
-	}
-
-	/* Validate the fadump crash info header */
-	fdh = __va(fw_dump.fadumphdr_addr);
-	if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
-		printk(KERN_ERR "Crash info header is not valid.\n");
-		return -EINVAL;
-	}
-
-	rc = fadump_build_cpu_notes(fdm_active);
-	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;
-}
-
-static void free_crash_memory_ranges(void)
-{
-	kfree(crash_memory_ranges);
-	crash_memory_ranges = NULL;
-	crash_memory_ranges_size = 0;
-	max_crash_mem_ranges = 0;
-}
-
-/*
- * Allocate or reallocate crash memory ranges array in incremental units
+ * Allocate or reallocate mem_ranges array in incremental units
  * of PAGE_SIZE.
  */
-static int allocate_crash_memory_ranges(void)
+static int fadump_alloc_mem_ranges(struct fadump_mrange_info *mrange_info)
 {
-	struct fad_crash_memory_ranges *new_array;
+	struct fadump_memory_range *new_array;
 	u64 new_size;
 
-	new_size = crash_memory_ranges_size + PAGE_SIZE;
-	pr_debug("Allocating %llu bytes of memory for crash memory ranges\n",
-		 new_size);
+	new_size = mrange_info->mem_ranges_sz + PAGE_SIZE;
+	pr_debug("Allocating %llu bytes of memory for %s memory ranges\n",
+		 new_size, mrange_info->name);
 
-	new_array = krealloc(crash_memory_ranges, new_size, GFP_KERNEL);
+	new_array = krealloc(mrange_info->mem_ranges, new_size, GFP_KERNEL);
 	if (new_array == NULL) {
-		pr_err("Insufficient memory for setting up crash memory ranges\n");
-		free_crash_memory_ranges();
+		pr_err("Insufficient memory for setting up %s memory ranges\n",
+		       mrange_info->name);
+		fadump_free_mem_ranges(mrange_info);
 		return -ENOMEM;
 	}
 
-	crash_memory_ranges = new_array;
-	crash_memory_ranges_size = new_size;
-	max_crash_mem_ranges = (new_size /
-				sizeof(struct fad_crash_memory_ranges));
+	mrange_info->mem_ranges = new_array;
+	mrange_info->mem_ranges_sz = new_size;
+	mrange_info->max_mem_ranges = (new_size /
+				       sizeof(struct fadump_memory_range));
 	return 0;
 }
 
-static inline int fadump_add_crash_memory(unsigned long long base,
-					  unsigned long long end)
+static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info,
+				       u64 base, u64 end)
 {
-	u64  start, size;
+	struct fadump_memory_range *mem_ranges = mrange_info->mem_ranges;
 	bool is_adjacent = false;
+	u64 start, size;
 
 	if (base == end)
 		return 0;
@@ -919,38 +774,41 @@
 	 * Fold adjacent memory ranges to bring down the memory ranges/
 	 * PT_LOAD segments count.
 	 */
-	if (crash_mem_ranges) {
-		start = crash_memory_ranges[crash_mem_ranges - 1].base;
-		size = crash_memory_ranges[crash_mem_ranges - 1].size;
+	if (mrange_info->mem_range_cnt) {
+		start = mem_ranges[mrange_info->mem_range_cnt - 1].base;
+		size  = mem_ranges[mrange_info->mem_range_cnt - 1].size;
 
 		if ((start + size) == base)
 			is_adjacent = true;
 	}
 	if (!is_adjacent) {
 		/* resize the array on reaching the limit */
-		if (crash_mem_ranges == max_crash_mem_ranges) {
+		if (mrange_info->mem_range_cnt == mrange_info->max_mem_ranges) {
 			int ret;
 
-			ret = allocate_crash_memory_ranges();
+			ret = fadump_alloc_mem_ranges(mrange_info);
 			if (ret)
 				return ret;
+
+			/* Update to the new resized array */
+			mem_ranges = mrange_info->mem_ranges;
 		}
 
 		start = base;
-		crash_memory_ranges[crash_mem_ranges].base = start;
-		crash_mem_ranges++;
+		mem_ranges[mrange_info->mem_range_cnt].base = start;
+		mrange_info->mem_range_cnt++;
 	}
 
-	crash_memory_ranges[crash_mem_ranges - 1].size = (end - start);
-	pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
-		(crash_mem_ranges - 1), start, end - 1, (end - start));
+	mem_ranges[mrange_info->mem_range_cnt - 1].size = (end - start);
+	pr_debug("%s_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
+		 mrange_info->name, (mrange_info->mem_range_cnt - 1),
+		 start, end - 1, (end - start));
 	return 0;
 }
 
-static int fadump_exclude_reserved_area(unsigned long long start,
-					unsigned long long end)
+static int fadump_exclude_reserved_area(u64 start, u64 end)
 {
-	unsigned long long ra_start, ra_end;
+	u64 ra_start, ra_end;
 	int ret = 0;
 
 	ra_start = fw_dump.reserve_dump_area_start;
@@ -958,18 +816,22 @@
 
 	if ((ra_start < end) && (ra_end > start)) {
 		if ((start < ra_start) && (end > ra_end)) {
-			ret = fadump_add_crash_memory(start, ra_start);
+			ret = fadump_add_mem_range(&crash_mrange_info,
+						   start, ra_start);
 			if (ret)
 				return ret;
 
-			ret = fadump_add_crash_memory(ra_end, end);
+			ret = fadump_add_mem_range(&crash_mrange_info,
+						   ra_end, end);
 		} else if (start < ra_start) {
-			ret = fadump_add_crash_memory(start, ra_start);
+			ret = fadump_add_mem_range(&crash_mrange_info,
+						   start, ra_start);
 		} else if (ra_end < end) {
-			ret = fadump_add_crash_memory(ra_end, end);
+			ret = fadump_add_mem_range(&crash_mrange_info,
+						   ra_end, end);
 		}
 	} else
-		ret = fadump_add_crash_memory(start, end);
+		ret = fadump_add_mem_range(&crash_mrange_info, start, end);
 
 	return ret;
 }
@@ -1014,36 +876,36 @@
 static int fadump_setup_crash_memory_ranges(void)
 {
 	struct memblock_region *reg;
-	unsigned long long start, end;
-	int ret;
+	u64 start, end;
+	int i, ret;
 
 	pr_debug("Setup crash memory ranges.\n");
-	crash_mem_ranges = 0;
+	crash_mrange_info.mem_range_cnt = 0;
 
 	/*
-	 * add the first memory chunk (RMA_START through boot_memory_size) as
-	 * a separate memory chunk. The reason is, at the time crash firmware
-	 * will move the content of this memory chunk to different location
-	 * specified during fadump registration. We need to create a separate
-	 * program header for this chunk with the correct offset.
+	 * 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.
 	 */
-	ret = fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size);
-	if (ret)
-		return ret;
+	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_memblock(memory, reg) {
-		start = (unsigned long long)reg->base;
-		end = start + (unsigned long long)reg->size;
+		start = (u64)reg->base;
+		end = start + (u64)reg->size;
 
 		/*
-		 * skip the first memory chunk that is already added (RMA_START
-		 * through boot_memory_size). This logic needs a relook if and
-		 * when RMA_START changes to a non-zero value.
+		 * skip the memory chunk that is already added
+		 * (0 through boot_memory_top).
 		 */
-		BUILD_BUG_ON(RMA_START != 0);
-		if (start < fw_dump.boot_memory_size) {
-			if (end > fw_dump.boot_memory_size)
-				start = fw_dump.boot_memory_size;
+		if (start < fw_dump.boot_mem_top) {
+			if (end > fw_dump.boot_mem_top)
+				start = fw_dump.boot_mem_top;
 			else
 				continue;
 		}
@@ -1064,17 +926,35 @@
  */
 static inline unsigned long fadump_relocate(unsigned long paddr)
 {
-	if (paddr > RMA_START && paddr < fw_dump.boot_memory_size)
-		return be64_to_cpu(fdm.rmr_region.destination_address) + paddr;
-	else
-		return paddr;
+	unsigned long raddr, rstart, rend, rlast, hole_size;
+	int i;
+
+	hole_size = 0;
+	rlast = 0;
+	raddr = paddr;
+	for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+		rstart = fw_dump.boot_mem_addr[i];
+		rend = rstart + fw_dump.boot_mem_sz[i];
+		hole_size += (rstart - rlast);
+
+		if (paddr >= rstart && paddr < rend) {
+			raddr += fw_dump.boot_mem_dest_addr - hole_size;
+			break;
+		}
+
+		rlast = rend;
+	}
+
+	pr_debug("vmcoreinfo: paddr = 0x%lx, raddr = 0x%lx\n", paddr, raddr);
+	return raddr;
 }
 
 static int fadump_create_elfcore_headers(char *bufp)
 {
-	struct elfhdr *elf;
+	unsigned long long raddr, offset;
 	struct elf_phdr *phdr;
-	int i;
+	struct elfhdr *elf;
+	int i, j;
 
 	fadump_init_elfcore_header(bufp);
 	elf = (struct elfhdr *)bufp;
@@ -1117,12 +997,14 @@
 	(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;
 
-	for (i = 0; i < crash_mem_ranges; i++) {
-		unsigned long long mbase, msize;
-		mbase = crash_memory_ranges[i].base;
-		msize = crash_memory_ranges[i].size;
-
+		mbase = crash_mrange_info.mem_ranges[i].base;
+		msize = crash_mrange_info.mem_ranges[i].size;
 		if (!msize)
 			continue;
 
@@ -1132,13 +1014,17 @@
 		phdr->p_flags	= PF_R|PF_W|PF_X;
 		phdr->p_offset	= mbase;
 
-		if (mbase == RMA_START) {
+		if (mbase == raddr) {
 			/*
-			 * The entire RMA region will be moved by firmware
-			 * to the specified destination_address. Hence set
-			 * the correct offset.
+			 * The entire real memory region will be moved by
+			 * firmware to the specified destination_address.
+			 * Hence set the correct offset.
 			 */
-			phdr->p_offset = be64_to_cpu(fdm.rmr_region.destination_address);
+			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];
+			}
 		}
 
 		phdr->p_paddr = mbase;
@@ -1160,7 +1046,6 @@
 	if (!addr)
 		return 0;
 
-	fw_dump.fadumphdr_addr = addr;
 	fdh = __va(addr);
 	addr += sizeof(struct fadump_crash_info_header);
 
@@ -1168,7 +1053,7 @@
 	fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
 	fdh->elfcorehdr_addr = addr;
 	/* We will set the crashing cpu id in crash_fadump() during crash. */
-	fdh->crashing_cpu = CPU_UNKNOWN;
+	fdh->crashing_cpu = FADUMP_CPU_UNKNOWN;
 
 	return addr;
 }
@@ -1190,7 +1075,8 @@
 	if (ret)
 		return ret;
 
-	addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len);
+	addr = fw_dump.fadumphdr_addr;
+
 	/* Initialize fadump crash info header. */
 	addr = init_fadump_header(addr);
 	vaddr = __va(addr);
@@ -1199,75 +1085,27 @@
 	fadump_create_elfcore_headers(vaddr);
 
 	/* register the future kernel dump with firmware. */
-	return register_fw_dump(&fdm);
-}
-
-static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
-{
-	int rc = 0;
-	unsigned int wait_time;
-
-	pr_debug("Un-register firmware-assisted dump\n");
-
-	/* TODO: Add upper time limit for the delay */
-	do {
-		rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
-			FADUMP_UNREGISTER, fdm,
-			sizeof(struct fadump_mem_struct));
-
-		wait_time = rtas_busy_delay_time(rc);
-		if (wait_time)
-			mdelay(wait_time);
-	} while (wait_time);
-
-	if (rc) {
-		printk(KERN_ERR "Failed to un-register firmware-assisted dump."
-			" unexpected error(%d).\n", rc);
-		return rc;
-	}
-	fw_dump.dump_registered = 0;
-	return 0;
-}
-
-static int fadump_invalidate_dump(struct fadump_mem_struct *fdm)
-{
-	int rc = 0;
-	unsigned int wait_time;
-
-	pr_debug("Invalidating firmware-assisted dump registration\n");
-
-	/* TODO: Add upper time limit for the delay */
-	do {
-		rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
-			FADUMP_INVALIDATE, fdm,
-			sizeof(struct fadump_mem_struct));
-
-		wait_time = rtas_busy_delay_time(rc);
-		if (wait_time)
-			mdelay(wait_time);
-	} while (wait_time);
-
-	if (rc) {
-		pr_err("Failed to invalidate firmware-assisted dump registration. Unexpected error (%d).\n", rc);
-		return rc;
-	}
-	fw_dump.dump_active = 0;
-	fdm_active = NULL;
-	return 0;
+	pr_debug("Registering for firmware-assisted kernel dump...\n");
+	return fw_dump.ops->fadump_register(&fw_dump);
 }
 
 void fadump_cleanup(void)
 {
+	if (!fw_dump.fadump_supported)
+		return;
+
 	/* Invalidate the registration only if dump is active. */
 	if (fw_dump.dump_active) {
-		init_fadump_mem_struct(&fdm,
-			be64_to_cpu(fdm_active->cpu_state_data.destination_address));
-		fadump_invalidate_dump(&fdm);
+		pr_debug("Invalidating firmware-assisted dump registration\n");
+		fw_dump.ops->fadump_invalidate(&fw_dump);
 	} else if (fw_dump.dump_registered) {
 		/* Un-register Firmware-assisted dump if it was registered. */
-		fadump_unregister_dump(&fdm);
-		free_crash_memory_ranges();
+		fw_dump.ops->fadump_unregister(&fw_dump);
+		fadump_free_mem_ranges(&crash_mrange_info);
 	}
+
+	if (fw_dump.ops->fadump_cleanup)
+		fw_dump.ops->fadump_cleanup(&fw_dump);
 }
 
 static void fadump_free_reserved_memory(unsigned long start_pfn,
@@ -1292,90 +1130,197 @@
 /*
  * Skip memory holes and free memory that was actually reserved.
  */
-static void fadump_release_reserved_area(unsigned long start, unsigned long end)
+static void fadump_release_reserved_area(u64 start, u64 end)
 {
+	u64 tstart, tend, spfn, epfn;
 	struct memblock_region *reg;
-	unsigned long tstart, tend;
-	unsigned long start_pfn = PHYS_PFN(start);
-	unsigned long end_pfn = PHYS_PFN(end);
 
+	spfn = PHYS_PFN(start);
+	epfn = PHYS_PFN(end);
 	for_each_memblock(memory, reg) {
-		tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
-		tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
+		tstart = max_t(u64, spfn, memblock_region_memory_base_pfn(reg));
+		tend   = min_t(u64, epfn, memblock_region_memory_end_pfn(reg));
 		if (tstart < tend) {
 			fadump_free_reserved_memory(tstart, tend);
 
-			if (tend == end_pfn)
+			if (tend == epfn)
 				break;
 
-			start_pfn = tend + 1;
+			spfn = tend;
 		}
 	}
 }
 
 /*
- * Release the memory that was reserved in early boot to preserve the memory
- * contents. The released memory will be available for general use.
+ * Sort the mem ranges in-place and merge adjacent ranges
+ * to minimize the memory ranges count.
  */
-static void fadump_release_memory(unsigned long begin, unsigned long end)
+static void sort_and_merge_mem_ranges(struct fadump_mrange_info *mrange_info)
 {
-	unsigned long ra_start, ra_end;
+	struct fadump_memory_range *mem_ranges;
+	struct fadump_memory_range tmp_range;
+	u64 base, size;
+	int i, j, idx;
+
+	if (!reserved_mrange_info.mem_range_cnt)
+		return;
+
+	/* Sort the memory ranges */
+	mem_ranges = mrange_info->mem_ranges;
+	for (i = 0; i < mrange_info->mem_range_cnt; i++) {
+		idx = i;
+		for (j = (i + 1); j < mrange_info->mem_range_cnt; j++) {
+			if (mem_ranges[idx].base > mem_ranges[j].base)
+				idx = j;
+		}
+		if (idx != i) {
+			tmp_range = mem_ranges[idx];
+			mem_ranges[idx] = mem_ranges[i];
+			mem_ranges[i] = tmp_range;
+		}
+	}
+
+	/* Merge adjacent reserved ranges */
+	idx = 0;
+	for (i = 1; i < mrange_info->mem_range_cnt; i++) {
+		base = mem_ranges[i-1].base;
+		size = mem_ranges[i-1].size;
+		if (mem_ranges[i].base == (base + size))
+			mem_ranges[idx].size += mem_ranges[i].size;
+		else {
+			idx++;
+			if (i == idx)
+				continue;
+
+			mem_ranges[idx] = mem_ranges[i];
+		}
+	}
+	mrange_info->mem_range_cnt = idx + 1;
+}
+
+/*
+ * Scan reserved-ranges to consider them while reserving/releasing
+ * memory for FADump.
+ */
+static inline int fadump_scan_reserved_mem_ranges(void)
+{
+	struct device_node *root;
+	const __be32 *prop;
+	int len, ret = -1;
+	unsigned long i;
+
+	root = of_find_node_by_path("/");
+	if (!root)
+		return ret;
+
+	prop = of_get_property(root, "reserved-ranges", &len);
+	if (!prop)
+		return ret;
+
+	/*
+	 * Each reserved range is an (address,size) pair, 2 cells each,
+	 * totalling 4 cells per range.
+	 */
+	for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+		u64 base, size;
+
+		base = of_read_number(prop + (i * 4) + 0, 2);
+		size = of_read_number(prop + (i * 4) + 2, 2);
+
+		if (size) {
+			ret = fadump_add_mem_range(&reserved_mrange_info,
+						   base, base + size);
+			if (ret < 0) {
+				pr_warn("some reserved ranges are ignored!\n");
+				break;
+			}
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Release the memory that was reserved during early boot to preserve the
+ * crash'ed kernel's memory contents except reserved dump area (permanent
+ * reservation) and reserved ranges used by F/W. The released memory will
+ * be available for general use.
+ */
+static void fadump_release_memory(u64 begin, u64 end)
+{
+	u64 ra_start, ra_end, tstart;
+	int i, ret;
+
+	fadump_scan_reserved_mem_ranges();
 
 	ra_start = fw_dump.reserve_dump_area_start;
 	ra_end = ra_start + fw_dump.reserve_dump_area_size;
 
 	/*
-	 * exclude the dump reserve area. Will reuse it for next
-	 * fadump registration.
+	 * Add reserved dump area to reserved ranges list
+	 * and exclude all these ranges while releasing memory.
 	 */
-	if (begin < ra_end && end > ra_start) {
-		if (begin < ra_start)
-			fadump_release_reserved_area(begin, ra_start);
-		if (end > ra_end)
-			fadump_release_reserved_area(ra_end, end);
-	} else
-		fadump_release_reserved_area(begin, end);
+	ret = fadump_add_mem_range(&reserved_mrange_info, ra_start, ra_end);
+	if (ret != 0) {
+		/*
+		 * Not enough memory to setup reserved ranges but the system is
+		 * running shortage of memory. So, release all the memory except
+		 * Reserved dump area (reused for next fadump registration).
+		 */
+		if (begin < ra_end && end > ra_start) {
+			if (begin < ra_start)
+				fadump_release_reserved_area(begin, ra_start);
+			if (end > ra_end)
+				fadump_release_reserved_area(ra_end, end);
+		} else
+			fadump_release_reserved_area(begin, end);
+
+		return;
+	}
+
+	/* Get the reserved ranges list in order first. */
+	sort_and_merge_mem_ranges(&reserved_mrange_info);
+
+	/* Exclude reserved ranges and release remaining memory */
+	tstart = begin;
+	for (i = 0; i < reserved_mrange_info.mem_range_cnt; i++) {
+		ra_start = reserved_mrange_info.mem_ranges[i].base;
+		ra_end = ra_start + reserved_mrange_info.mem_ranges[i].size;
+
+		if (tstart >= ra_end)
+			continue;
+
+		if (tstart < ra_start)
+			fadump_release_reserved_area(tstart, ra_start);
+		tstart = ra_end;
+	}
+
+	if (tstart < end)
+		fadump_release_reserved_area(tstart, end);
 }
 
 static void fadump_invalidate_release_mem(void)
 {
-	unsigned long reserved_area_start, reserved_area_end;
-	unsigned long destination_address;
-
 	mutex_lock(&fadump_mutex);
 	if (!fw_dump.dump_active) {
 		mutex_unlock(&fadump_mutex);
 		return;
 	}
 
-	destination_address = be64_to_cpu(fdm_active->cpu_state_data.destination_address);
 	fadump_cleanup();
 	mutex_unlock(&fadump_mutex);
 
-	/*
-	 * Save the current reserved memory bounds we will require them
-	 * later for releasing the memory for general use.
-	 */
-	reserved_area_start = fw_dump.reserve_dump_area_start;
-	reserved_area_end = reserved_area_start +
-			fw_dump.reserve_dump_area_size;
-	/*
-	 * Setup reserve_dump_area_start and its size so that we can
-	 * reuse this reserved memory for Re-registration.
-	 */
-	fw_dump.reserve_dump_area_start = destination_address;
-	fw_dump.reserve_dump_area_size = get_fadump_area_size();
+	fadump_release_memory(fw_dump.boot_mem_top, memblock_end_of_DRAM());
+	fadump_free_cpu_notes_buf();
 
-	fadump_release_memory(reserved_area_start, reserved_area_end);
-	if (fw_dump.cpu_notes_buf) {
-		fadump_cpu_notes_buf_free(
-				(unsigned long)__va(fw_dump.cpu_notes_buf),
-				fw_dump.cpu_notes_buf_size);
-		fw_dump.cpu_notes_buf = 0;
-		fw_dump.cpu_notes_buf_size = 0;
-	}
-	/* Initialize the kernel dump memory structure for FAD registration. */
-	init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+	/*
+	 * Setup kernel metadata and initialize the kernel dump
+	 * memory structure for FADump re-registration.
+	 */
+	if (fw_dump.ops->fadump_setup_metadata &&
+	    (fw_dump.ops->fadump_setup_metadata(&fw_dump) < 0))
+		pr_warn("Failed to setup kernel metadata!\n");
+	fw_dump.ops->fadump_init_mem_struct(&fw_dump);
 }
 
 static ssize_t fadump_release_memory_store(struct kobject *kobj,
@@ -1426,7 +1371,7 @@
 	int ret = 0;
 	int input = -1;
 
-	if (!fw_dump.fadump_enabled || fdm_active)
+	if (!fw_dump.fadump_enabled || fw_dump.dump_active)
 		return -EPERM;
 
 	if (kstrtoint(buf, 0, &input))
@@ -1439,13 +1384,15 @@
 		if (fw_dump.dump_registered == 0) {
 			goto unlock_out;
 		}
+
 		/* Un-register Firmware-assisted dump */
-		fadump_unregister_dump(&fdm);
+		pr_debug("Un-register firmware-assisted dump\n");
+		fw_dump.ops->fadump_unregister(&fw_dump);
 		break;
 	case 1:
 		if (fw_dump.dump_registered == 1) {
-			ret = -EEXIST;
-			goto unlock_out;
+			/* Un-register Firmware-assisted dump */
+			fw_dump.ops->fadump_unregister(&fw_dump);
 		}
 		/* Register Firmware-assisted dump */
 		ret = register_fadump();
@@ -1462,62 +1409,12 @@
 
 static int fadump_region_show(struct seq_file *m, void *private)
 {
-	const struct fadump_mem_struct *fdm_ptr;
-
 	if (!fw_dump.fadump_enabled)
 		return 0;
 
 	mutex_lock(&fadump_mutex);
-	if (fdm_active)
-		fdm_ptr = fdm_active;
-	else {
-		mutex_unlock(&fadump_mutex);
-		fdm_ptr = &fdm;
-	}
-
-	seq_printf(m,
-			"CPU : [%#016llx-%#016llx] %#llx bytes, "
-			"Dumped: %#llx\n",
-			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address),
-			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) +
-			be64_to_cpu(fdm_ptr->cpu_state_data.source_len) - 1,
-			be64_to_cpu(fdm_ptr->cpu_state_data.source_len),
-			be64_to_cpu(fdm_ptr->cpu_state_data.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: [%#016llx-%#016llx] %#llx bytes, "
-			"Dumped: %#llx\n",
-			be64_to_cpu(fdm_ptr->rmr_region.destination_address),
-			be64_to_cpu(fdm_ptr->rmr_region.destination_address) +
-			be64_to_cpu(fdm_ptr->rmr_region.source_len) - 1,
-			be64_to_cpu(fdm_ptr->rmr_region.source_len),
-			be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped));
-
-	if (!fdm_active ||
-		(fw_dump.reserve_dump_area_start ==
-		be64_to_cpu(fdm_ptr->cpu_state_data.destination_address)))
-		goto out;
-
-	/* Dump is active. Show reserved memory region. */
-	seq_printf(m,
-			"    : [%#016llx-%#016llx] %#llx bytes, "
-			"Dumped: %#llx\n",
-			(unsigned long long)fw_dump.reserve_dump_area_start,
-			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - 1,
-			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) -
-			fw_dump.reserve_dump_area_start,
-			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) -
-			fw_dump.reserve_dump_area_start);
-out:
-	if (fdm_active)
-		mutex_unlock(&fadump_mutex);
+	fw_dump.ops->fadump_region_show(&fw_dump, m);
+	mutex_unlock(&fadump_mutex);
 	return 0;
 }
 
@@ -1531,17 +1428,7 @@
 						0644, fadump_register_show,
 						fadump_register_store);
 
-static int fadump_region_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, fadump_region_show, inode->i_private);
-}
-
-static const struct file_operations fadump_region_fops = {
-	.open    = fadump_region_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(fadump_region);
 
 static void fadump_init_files(void)
 {
@@ -1598,14 +1485,77 @@
 		 * if dump process fails then invalidate the registration
 		 * and release memory before proceeding for re-registration.
 		 */
-		if (process_fadump(fdm_active) < 0)
+		if (fw_dump.ops->fadump_process(&fw_dump) < 0)
 			fadump_invalidate_release_mem();
 	}
 	/* Initialize the kernel dump memory structure for FAD registration. */
 	else if (fw_dump.reserve_dump_area_size)
-		init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+		fw_dump.ops->fadump_init_mem_struct(&fw_dump);
+
 	fadump_init_files();
 
 	return 1;
 }
 subsys_initcall(setup_fadump);
+#else /* !CONFIG_PRESERVE_FA_DUMP */
+
+/* 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)
+{
+	if ((depth != 1) || (strcmp(uname, "ibm,opal") != 0))
+		return 0;
+
+	opal_fadump_dt_scan(&fw_dump, node);
+	return 1;
+}
+
+/*
+ * When dump is active but PRESERVE_FA_DUMP is enabled on the kernel,
+ * preserve crash data. The subsequent memory preserving kernel boot
+ * is likely to process this crash data.
+ */
+int __init fadump_reserve_mem(void)
+{
+	if (fw_dump.dump_active) {
+		/*
+		 * If last boot has crashed then reserve all the memory
+		 * above boot memory to preserve crash data.
+		 */
+		pr_info("Preserving crash data for processing in next boot.\n");
+		fadump_reserve_crash_area(fw_dump.boot_mem_top);
+	} else
+		pr_debug("FADump-aware kernel..\n");
+
+	return 1;
+}
+#endif /* CONFIG_PRESERVE_FA_DUMP */
+
+/* Preserve everything above the base address */
+static void __init fadump_reserve_crash_area(u64 base)
+{
+	struct memblock_region *reg;
+	u64 mstart, msize;
+
+	for_each_memblock(memory, reg) {
+		mstart = reg->base;
+		msize  = reg->size;
+
+		if ((mstart + msize) < base)
+			continue;
+
+		if (mstart < base) {
+			msize -= (base - mstart);
+			mstart = base;
+		}
+
+		pr_info("Reserving %lluMB of memory at %#016llx for preserving crash data",
+			(msize >> 20), mstart);
+		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 2eae447..cc4a5e3 100644
--- a/arch/powerpc/kernel/firmware.c
+++ b/arch/powerpc/kernel/firmware.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Extracted from cputable.c
  *
@@ -6,11 +7,6 @@
  *  Modifications for ppc64:
  *      Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
  *  Copyright (C) 2005 Stephen Rothwell, IBM 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; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/export.h>
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 529dcc2..0bb991d 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  FPU support code, moved here from head.S so that it can be used
  *  by chips which use other head-whatever.S files.
@@ -6,12 +7,6 @@
  *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
  *    Copyright (C) 1996 Paul Mackerras.
  *    Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/reg.h>
@@ -63,6 +58,7 @@
 	REST_32FPVSRS(0, R4, R3)
 	blr
 EXPORT_SYMBOL(load_fp_state)
+_ASM_NOKPROBE_SYMBOL(load_fp_state); /* used by restore_math */
 
 /*
  * Store FP state into memory, including FPSCR
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 61ca279..4a24f8f 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -13,12 +14,6 @@
  *  This file contains the low-level support and setup for the
  *  PowerPC platform, including trap and interrupt dispatch.
  *  (The PPC 8xx embedded CPUs use head_8xx.S instead.)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/init.h>
@@ -37,7 +32,18 @@
 #include <asm/export.h>
 #include <asm/feature-fixups.h>
 
-/* 601 only have IBAT; cr0.eq is set on 601 when using this macro */
+#include "head_32.h"
+
+/* 601 only have IBAT */
+#ifdef CONFIG_PPC_BOOK3S_601
+#define LOAD_BAT(n, reg, RA, RB)	\
+	li	RA,0;			\
+	mtspr	SPRN_IBAT##n##U,RA;	\
+	lwz	RA,(n*16)+0(reg);	\
+	lwz	RB,(n*16)+4(reg);	\
+	mtspr	SPRN_IBAT##n##U,RA;	\
+	mtspr	SPRN_IBAT##n##L,RB
+#else
 #define LOAD_BAT(n, reg, RA, RB)	\
 	/* see the comment for clear_bats() -- Cort */ \
 	li	RA,0;			\
@@ -47,12 +53,11 @@
 	lwz	RB,(n*16)+4(reg);	\
 	mtspr	SPRN_IBAT##n##U,RA;	\
 	mtspr	SPRN_IBAT##n##L,RB;	\
-	beq	1f;			\
 	lwz	RA,(n*16)+8(reg);	\
 	lwz	RB,(n*16)+12(reg);	\
 	mtspr	SPRN_DBAT##n##U,RA;	\
-	mtspr	SPRN_DBAT##n##L,RB;	\
-1:
+	mtspr	SPRN_DBAT##n##L,RB
+#endif
 
 	__HEAD
 	.stabs	"arch/powerpc/kernel/",N_SO,0,0,0f
@@ -160,6 +165,10 @@
 	bl	flush_tlbs
 
 	bl	initial_bats
+	bl	load_segment_registers
+#ifdef CONFIG_KASAN
+	bl	early_hash_table
+#endif
 #if defined(CONFIG_BOOTX_TEXT)
 	bl	setup_disp_bat
 #endif
@@ -176,10 +185,10 @@
 	bl	reloc_offset
 	li	r24,0			/* cpu# */
 	bl	call_setup_cpu		/* Call setup_cpu for this CPU */
-#ifdef CONFIG_6xx
+#ifdef CONFIG_PPC_BOOK3S_32
 	bl	reloc_offset
 	bl	init_idle_6xx
-#endif /* CONFIG_6xx */
+#endif /* CONFIG_PPC_BOOK3S_32 */
 
 
 /*
@@ -205,7 +214,7 @@
  */
 turn_on_mmu:
 	mfmsr	r0
-	ori	r0,r0,MSR_DR|MSR_IR
+	ori	r0,r0,MSR_DR|MSR_IR|MSR_RI
 	mtspr	SPRN_SRR1,r0
 	lis	r0,start_here@h
 	ori	r0,r0,start_here@l
@@ -242,103 +251,6 @@
 __secondary_hold_acknowledge:
 	.long	-1
 
-/*
- * Exception entry code.  This code runs with address translation
- * turned off, i.e. using physical addresses.
- * We assume sprg3 has the physical address of the current
- * task's thread_struct.
- */
-#define EXCEPTION_PROLOG	\
-	mtspr	SPRN_SPRG_SCRATCH0,r10;	\
-	mtspr	SPRN_SPRG_SCRATCH1,r11;	\
-	mfcr	r10;		\
-	EXCEPTION_PROLOG_1;	\
-	EXCEPTION_PROLOG_2
-
-#define EXCEPTION_PROLOG_1	\
-	mfspr	r11,SPRN_SRR1;		/* check whether user or kernel */ \
-	andi.	r11,r11,MSR_PR;	\
-	tophys(r11,r1);			/* use tophys(r1) if kernel */ \
-	beq	1f;		\
-	mfspr	r11,SPRN_SPRG_THREAD;	\
-	lwz	r11,THREAD_INFO-THREAD(r11);	\
-	addi	r11,r11,THREAD_SIZE;	\
-	tophys(r11,r11);	\
-1:	subi	r11,r11,INT_FRAME_SIZE	/* alloc exc. frame */
-
-
-#define EXCEPTION_PROLOG_2	\
-	stw	r10,_CCR(r11);		/* save registers */ \
-	stw	r12,GPR12(r11);	\
-	stw	r9,GPR9(r11);	\
-	mfspr	r10,SPRN_SPRG_SCRATCH0;	\
-	stw	r10,GPR10(r11);	\
-	mfspr	r12,SPRN_SPRG_SCRATCH1;	\
-	stw	r12,GPR11(r11);	\
-	mflr	r10;		\
-	stw	r10,_LINK(r11);	\
-	mfspr	r12,SPRN_SRR0;	\
-	mfspr	r9,SPRN_SRR1;	\
-	stw	r1,GPR1(r11);	\
-	stw	r1,0(r11);	\
-	tovirt(r1,r11);			/* set new kernel sp */	\
-	li	r10,MSR_KERNEL & ~(MSR_IR|MSR_DR); /* can take exceptions */ \
-	MTMSRD(r10);			/* (except for mach check in rtas) */ \
-	stw	r0,GPR0(r11);	\
-	lis	r10,STACK_FRAME_REGS_MARKER@ha; /* exception frame marker */ \
-	addi	r10,r10,STACK_FRAME_REGS_MARKER@l; \
-	stw	r10,8(r11);	\
-	SAVE_4GPRS(3, r11);	\
-	SAVE_2GPRS(7, r11)
-
-/*
- * Note: code which follows this uses cr0.eq (set if from kernel),
- * r11, r12 (SRR0), and r9 (SRR1).
- *
- * Note2: once we have set r1 we are in a position to take exceptions
- * again, and we could thus set MSR:RI at that point.
- */
-
-/*
- * Exception vectors.
- */
-#define EXCEPTION(n, label, hdlr, xfer)		\
-	. = n;					\
-	DO_KVM n;				\
-label:						\
-	EXCEPTION_PROLOG;			\
-	addi	r3,r1,STACK_FRAME_OVERHEAD;	\
-	xfer(n, hdlr)
-
-#define EXC_XFER_TEMPLATE(n, hdlr, trap, copyee, tfer, ret)	\
-	li	r10,trap;					\
-	stw	r10,_TRAP(r11);					\
-	li	r10,MSR_KERNEL;					\
-	copyee(r10, r9);					\
-	bl	tfer;						\
-i##n:								\
-	.long	hdlr;						\
-	.long	ret
-
-#define COPY_EE(d, s)		rlwimi d,s,0,16,16
-#define NOCOPY(d, s)
-
-#define EXC_XFER_STD(n, hdlr)		\
-	EXC_XFER_TEMPLATE(n, hdlr, n, NOCOPY, transfer_to_handler_full,	\
-			  ret_from_except_full)
-
-#define EXC_XFER_LITE(n, hdlr)		\
-	EXC_XFER_TEMPLATE(n, hdlr, n+1, NOCOPY, transfer_to_handler, \
-			  ret_from_except)
-
-#define EXC_XFER_EE(n, hdlr)		\
-	EXC_XFER_TEMPLATE(n, hdlr, n, COPY_EE, transfer_to_handler_full, \
-			  ret_from_except_full)
-
-#define EXC_XFER_EE_LITE(n, hdlr)	\
-	EXC_XFER_TEMPLATE(n, hdlr, n+1, COPY_EE, transfer_to_handler, \
-			  ret_from_except)
-
 /* System reset */
 /* core99 pmac starts the seconary here by changing the vector, and
    putting it back to what it was (unknown_exception) when done.  */
@@ -352,9 +264,8 @@
  * registers that might have bad values includes all the GPRs
  * and all the BATs.  We indicate that we are in RTAS by putting
  * a non-zero value, the address of the exception frame to use,
- * in SPRG2.  The machine check handler checks SPRG2 and uses its
- * value if it is non-zero.  If we ever needed to free up SPRG2,
- * we could use a field in the thread_info or thread_struct instead.
+ * in thread.rtas_sp.  The machine check handler checks thread.rtas_sp
+ * and uses its value if it is non-zero.
  * (Other exception handlers assume that r1 is a valid kernel stack
  * pointer when we take an exception from supervisor mode.)
  *	-- paulus.
@@ -365,16 +276,15 @@
 	mtspr	SPRN_SPRG_SCRATCH1,r11
 	mfcr	r10
 #ifdef CONFIG_PPC_CHRP
-	mfspr	r11,SPRN_SPRG_RTAS
-	cmpwi	0,r11,0
-	bne	7f
+	mfspr	r11, SPRN_SPRG_THREAD
+	lwz	r11, RTAS_SP(r11)
+	cmpwi	cr1, r11, 0
+	bne	cr1, 7f
 #endif /* CONFIG_PPC_CHRP */
 	EXCEPTION_PROLOG_1
 7:	EXCEPTION_PROLOG_2
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_PPC_CHRP
-	mfspr	r4,SPRN_SPRG_RTAS
-	cmpwi	cr1,r4,0
 	bne	cr1,1f
 #endif
 	EXC_XFER_STD(0x200, machine_check_exception)
@@ -389,11 +299,17 @@
 	EXCEPTION_PROLOG
 	mfspr	r10,SPRN_DSISR
 	stw	r10,_DSISR(r11)
+#ifdef CONFIG_PPC_KUAP
+	andis.	r0,r10,(DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
+#else
 	andis.	r0,r10,(DSISR_BAD_FAULT_32S|DSISR_DABRMATCH)@h
+#endif
 	bne	1f			/* if not, try to put a PTE */
 	mfspr	r4,SPRN_DAR		/* into the hash table */
 	rlwinm	r3,r10,32-15,21,21	/* DSISR_STORE -> _PAGE_RW */
+BEGIN_MMU_FTR_SECTION
 	bl	hash_page
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
 1:	lwz	r5,_DSISR(r11)		/* get DSISR value */
 	mfspr	r4,SPRN_DAR
 	EXC_XFER_LITE(0x300, handle_page_fault)
@@ -408,7 +324,9 @@
 	beq	1f			/* if so, try to put a PTE */
 	li	r3,0			/* into the hash table */
 	mr	r4,r12			/* SRR0 is fault address */
+BEGIN_MMU_FTR_SECTION
 	bl	hash_page
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
 1:	mr	r4,r12
 	andis.	r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
 	EXC_XFER_LITE(0x400, handle_page_fault)
@@ -426,7 +344,7 @@
 	mfspr	r5,SPRN_DSISR
 	stw	r5,_DSISR(r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_EE(0x600, alignment_exception)
+	EXC_XFER_STD(0x600, alignment_exception)
 
 /* Program check exception */
 	EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD)
@@ -447,24 +365,23 @@
 	bl	load_up_fpu		/* if from user, just load it up */
 	b	fast_exception_return
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_EE_LITE(0x800, kernel_fp_unavailable_exception)
+	EXC_XFER_LITE(0x800, kernel_fp_unavailable_exception)
 
 /* Decrementer */
 	EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE)
 
-	EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_STD)
 
 /* System call */
 	. = 0xc00
 	DO_KVM  0xc00
 SystemCall:
-	EXCEPTION_PROLOG
-	EXC_XFER_EE_LITE(0xc00, DoSyscall)
+	SYSCALL_ENTRY	0xc00
 
 /* Single step - not used on 601 */
 	EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD)
-	EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_STD)
 
 /*
  * The Altivec unavailable trap is at 0x0f20.  Foo.
@@ -496,18 +413,22 @@
  */
 	/* Get PTE (linux-style) and check access */
 	mfspr	r3,SPRN_IMISS
+#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
 	lis	r1,PAGE_OFFSET@h		/* check if kernel address */
 	cmplw	0,r1,r3
-	mfspr	r2,SPRN_SPRG_THREAD
-	li	r1,_PAGE_USER|_PAGE_PRESENT /* low addresses tested as user */
-	lwz	r2,PGDIR(r2)
+#endif
+	mfspr	r2, SPRN_SPRG_PGDIR
+#ifdef CONFIG_SWAP
+	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+#else
+	li	r1,_PAGE_PRESENT | _PAGE_EXEC
+#endif
+#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
 	bge-	112f
-	mfspr	r2,SPRN_SRR1		/* and MSR_PR bit from SRR1 */
-	rlwimi	r1,r2,32-12,29,29	/* shift MSR_PR to _PAGE_USER posn */
-	lis	r2,swapper_pg_dir@ha	/* if kernel address, use */
-	addi	r2,r2,swapper_pg_dir@l	/* kernel page table */
-112:	tophys(r2,r2)
-	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
+	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	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 */
 	lwz	r2,0(r2)		/* get pmd entry */
 	rlwinm.	r2,r2,0,0,19		/* extract address of pte page */
 	beq-	InstructionAddressInvalid	/* return if no mapping */
@@ -515,20 +436,10 @@
 	lwz	r0,0(r2)		/* get linux-style pte */
 	andc.	r1,r1,r0		/* check access & ~permission */
 	bne-	InstructionAddressInvalid /* return if access not permitted */
-	ori	r0,r0,_PAGE_ACCESSED	/* set _PAGE_ACCESSED in pte */
-	/*
-	 * NOTE! We are assuming this is not an SMP system, otherwise
-	 * we would need to update the pte atomically with lwarx/stwcx.
-	 */
-	stw	r0,0(r2)		/* update PTE (accessed bit) */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwinm	r1,r0,32-10,31,31	/* _PAGE_RW -> PP lsb */
-	rlwinm	r2,r0,32-7,31,31	/* _PAGE_DIRTY -> PP lsb */
-	and	r1,r1,r2		/* writable if _RW and _DIRTY */
-	rlwimi	r0,r0,32-1,30,30	/* _PAGE_USER -> PP msb */
-	rlwimi	r0,r0,32-1,31,31	/* _PAGE_USER -> PP lsb */
-	ori	r1,r1,0xe04		/* clear out reserved bits */
-	andc	r1,r0,r1		/* PP = user? (rw&dirty? 2: 3): 0 */
+	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
+	ori	r1, r1, 0xe06		/* clear out reserved bits */
+	andc	r1, r0, 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)
@@ -572,16 +483,16 @@
 	mfspr	r3,SPRN_DMISS
 	lis	r1,PAGE_OFFSET@h		/* check if kernel address */
 	cmplw	0,r1,r3
-	mfspr	r2,SPRN_SPRG_THREAD
-	li	r1,_PAGE_USER|_PAGE_PRESENT /* low addresses tested as user */
-	lwz	r2,PGDIR(r2)
+	mfspr	r2, SPRN_SPRG_PGDIR
+#ifdef CONFIG_SWAP
+	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED
+#else
+	li	r1, _PAGE_PRESENT
+#endif
 	bge-	112f
-	mfspr	r2,SPRN_SRR1		/* and MSR_PR bit from SRR1 */
-	rlwimi	r1,r2,32-12,29,29	/* shift MSR_PR to _PAGE_USER posn */
-	lis	r2,swapper_pg_dir@ha	/* if kernel address, use */
-	addi	r2,r2,swapper_pg_dir@l	/* kernel page table */
-112:	tophys(r2,r2)
-	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
+	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	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.	r2,r2,0,0,19		/* extract address of pte page */
 	beq-	DataAddressInvalid	/* return if no mapping */
@@ -589,20 +500,16 @@
 	lwz	r0,0(r2)		/* get linux-style pte */
 	andc.	r1,r1,r0		/* check access & ~permission */
 	bne-	DataAddressInvalid	/* return if access not permitted */
-	ori	r0,r0,_PAGE_ACCESSED	/* set _PAGE_ACCESSED in pte */
 	/*
 	 * NOTE! We are assuming this is not an SMP system, otherwise
 	 * we would need to update the pte atomically with lwarx/stwcx.
 	 */
-	stw	r0,0(r2)		/* update PTE (accessed bit) */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwinm	r1,r0,32-10,31,31	/* _PAGE_RW -> PP lsb */
-	rlwinm	r2,r0,32-7,31,31	/* _PAGE_DIRTY -> PP lsb */
-	and	r1,r1,r2		/* writable if _RW and _DIRTY */
+	rlwinm	r1,r0,32-9,30,30	/* _PAGE_RW -> PP msb */
 	rlwimi	r0,r0,32-1,30,30	/* _PAGE_USER -> PP msb */
 	rlwimi	r0,r0,32-1,31,31	/* _PAGE_USER -> PP lsb */
 	ori	r1,r1,0xe04		/* clear out reserved bits */
-	andc	r1,r0,r1		/* PP = user? (rw&dirty? 2: 3): 0 */
+	andc	r1,r0,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)
@@ -656,16 +563,16 @@
 	mfspr	r3,SPRN_DMISS
 	lis	r1,PAGE_OFFSET@h		/* check if kernel address */
 	cmplw	0,r1,r3
-	mfspr	r2,SPRN_SPRG_THREAD
-	li	r1,_PAGE_RW|_PAGE_USER|_PAGE_PRESENT /* access flags */
-	lwz	r2,PGDIR(r2)
+	mfspr	r2, SPRN_SPRG_PGDIR
+#ifdef CONFIG_SWAP
+	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
+#else
+	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT
+#endif
 	bge-	112f
-	mfspr	r2,SPRN_SRR1		/* and MSR_PR bit from SRR1 */
-	rlwimi	r1,r2,32-12,29,29	/* shift MSR_PR to _PAGE_USER posn */
-	lis	r2,swapper_pg_dir@ha	/* if kernel address, use */
-	addi	r2,r2,swapper_pg_dir@l	/* kernel page table */
-112:	tophys(r2,r2)
-	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
+	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	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.	r2,r2,0,0,19		/* extract address of pte page */
 	beq-	DataAddressInvalid	/* return if no mapping */
@@ -673,16 +580,14 @@
 	lwz	r0,0(r2)		/* get linux-style pte */
 	andc.	r1,r1,r0		/* check access & ~permission */
 	bne-	DataAddressInvalid	/* return if access not permitted */
-	ori	r0,r0,_PAGE_ACCESSED|_PAGE_DIRTY
 	/*
 	 * NOTE! We are assuming this is not an SMP system, otherwise
 	 * we would need to update the pte atomically with lwarx/stwcx.
 	 */
-	stw	r0,0(r2)		/* update PTE (accessed/dirty bits) */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwimi	r0,r0,32-1,30,30	/* _PAGE_USER -> PP msb */
-	li	r1,0xe05		/* clear out reserved bits & PP lsb */
-	andc	r1,r0,r1		/* PP = user? 2: 0 */
+	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
+	li	r1,0xe06		/* clear out reserved bits & PP msb */
+	andc	r1,r0,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)
@@ -708,35 +613,35 @@
 #define altivec_assist_exception	unknown_exception
 #endif
 
-	EXCEPTION(0x1300, Trap_13, instruction_breakpoint_exception, EXC_XFER_EE)
-	EXCEPTION(0x1400, SMI, SMIException, EXC_XFER_EE)
-	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1600, Trap_16, altivec_assist_exception, EXC_XFER_EE)
+	EXCEPTION(0x1300, Trap_13, instruction_breakpoint_exception, EXC_XFER_STD)
+	EXCEPTION(0x1400, SMI, SMIException, EXC_XFER_STD)
+	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1600, Trap_16, altivec_assist_exception, EXC_XFER_STD)
 	EXCEPTION(0x1700, Trap_17, TAUException, EXC_XFER_STD)
-	EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1c00, Trap_1c, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1e00, Trap_1e, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1f00, Trap_1f, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2000, RunMode, RunModeException, EXC_XFER_EE)
-	EXCEPTION(0x2100, Trap_21, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2200, Trap_22, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2300, Trap_23, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2400, Trap_24, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2500, Trap_25, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2600, Trap_26, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2700, Trap_27, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2800, Trap_28, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2900, Trap_29, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2a00, Trap_2a, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2b00, Trap_2b, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2c00, Trap_2c, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2d00, Trap_2d, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2e00, Trap_2e, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2f00, Trap_2f, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1c00, Trap_1c, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1e00, Trap_1e, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1f00, Trap_1f, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2000, RunMode, RunModeException, EXC_XFER_STD)
+	EXCEPTION(0x2100, Trap_21, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2200, Trap_22, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2300, Trap_23, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2400, Trap_24, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2500, Trap_25, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2600, Trap_26, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2700, Trap_27, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2800, Trap_28, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2900, Trap_29, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2a00, Trap_2a, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2b00, Trap_2b, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2c00, Trap_2c, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2d00, Trap_2d, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2e00, Trap_2e, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x2f00, Trap_2f, unknown_exception, EXC_XFER_STD)
 
 	. = 0x3000
 
@@ -748,7 +653,7 @@
 	b	fast_exception_return
 #endif /* CONFIG_ALTIVEC */
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_EE_LITE(0xf20, altivec_unavailable_exception)
+	EXC_XFER_LITE(0xf20, altivec_unavailable_exception)
 
 PerformanceMonitor:
 	EXCEPTION_PROLOG
@@ -836,17 +741,17 @@
 	lis	r3,-KERNELBASE@h
 	mr	r4,r24
 	bl	call_setup_cpu		/* Call setup_cpu for this CPU */
-#ifdef CONFIG_6xx
+#ifdef CONFIG_PPC_BOOK3S_32
 	lis	r3,-KERNELBASE@h
 	bl	init_idle_6xx
-#endif /* CONFIG_6xx */
+#endif /* CONFIG_PPC_BOOK3S_32 */
 
-	/* get current_thread_info and current */
-	lis	r1,secondary_ti@ha
-	tophys(r1,r1)
-	lwz	r1,secondary_ti@l(r1)
-	tophys(r2,r1)
-	lwz	r2,TI_TASK(r2)
+	/* get current's stack and current */
+	lis	r2,secondary_current@ha
+	tophys(r2,r2)
+	lwz	r2,secondary_current@l(r2)
+	tophys(r1,r2)
+	lwz	r1,TASK_STACK(r1)
 
 	/* stack */
 	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
@@ -855,14 +760,16 @@
 	stw	r0,0(r3)
 
 	/* load up the MMU */
+	bl	load_segment_registers
 	bl	load_up_mmu
 
 	/* ptr to phys current thread */
 	tophys(r4,r2)
 	addi	r4,r4,THREAD	/* phys address of our thread_struct */
 	mtspr	SPRN_SPRG_THREAD,r4
-	li	r3,0
-	mtspr	SPRN_SPRG_RTAS,r3	/* 0 => not in RTAS */
+	lis	r4, (swapper_pg_dir - PAGE_OFFSET)@h
+	ori	r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
+	mtspr	SPRN_SPRG_PGDIR, r4
 
 	/* enable MMU and jump to start_secondary */
 	li	r4,MSR_KERNEL
@@ -880,20 +787,33 @@
 
 /*
  * Those generic dummy functions are kept for CPUs not
- * included in CONFIG_6xx
+ * included in CONFIG_PPC_BOOK3S_32
  */
-#if !defined(CONFIG_6xx)
+#if !defined(CONFIG_PPC_BOOK3S_32)
 _ENTRY(__save_cpu_setup)
 	blr
 _ENTRY(__restore_cpu_setup)
 	blr
-#endif /* !defined(CONFIG_6xx) */
-
+#endif /* !defined(CONFIG_PPC_BOOK3S_32) */
 
 /*
  * Load stuff into the MMU.  Intended to be called with
  * IR=0 and DR=0.
  */
+#ifdef CONFIG_KASAN
+early_hash_table:
+	sync			/* Force all PTE updates to finish */
+	isync
+	tlbia			/* Clear all TLB entries */
+	sync			/* wait for tlbia/tlbie to finish */
+	TLBSYNC			/* ... on all CPUs */
+	/* Load the SDR1 register (hash table base & size) */
+	lis	r6, early_hash - PAGE_OFFSET@h
+	ori	r6, r6, 3	/* 256kB table */
+	mtspr	SPRN_SDR1, r6
+	blr
+#endif
+
 load_up_mmu:
 	sync			/* Force all PTE updates to finish */
 	isync
@@ -905,20 +825,9 @@
 	tophys(r6,r6)
 	lwz	r6,_SDR1@l(r6)
 	mtspr	SPRN_SDR1,r6
-	li	r0,16		/* load up segment register values */
-	mtctr	r0		/* for context 0 */
-	lis	r3,0x2000	/* Ku = 1, VSID = 0 */
-	li	r4,0
-3:	mtsrin	r3,r4
-	addi	r3,r3,0x111	/* increment VSID */
-	addis	r4,r4,0x1000	/* address of next segment */
-	bdnz	3b
 
 /* Load the BAT registers with the values set up by MMU_init.
    MMU_init takes care of whether we're on a 601 or not. */
-	mfpvr	r3
-	srwi	r3,r3,16
-	cmpwi	r3,1
 	lis	r3,BATS@ha
 	addi	r3,r3,BATS@l
 	tophys(r3,r3)
@@ -934,6 +843,32 @@
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 	blr
 
+load_segment_registers:
+	li	r0, NUM_USER_SEGMENTS /* load up user segment register values */
+	mtctr	r0		/* for context 0 */
+	li	r3, 0		/* Kp = 0, Ks = 0, VSID = 0 */
+#ifdef CONFIG_PPC_KUEP
+	oris	r3, r3, SR_NX@h	/* Set Nx */
+#endif
+#ifdef CONFIG_PPC_KUAP
+	oris	r3, r3, SR_KS@h	/* Set Ks */
+#endif
+	li	r4, 0
+3:	mtsrin	r3, r4
+	addi	r3, r3, 0x111	/* increment VSID */
+	addis	r4, r4, 0x1000	/* address of next segment */
+	bdnz	3b
+	li	r0, 16 - NUM_USER_SEGMENTS /* load up kernel segment registers */
+	mtctr	r0			/* for context 0 */
+	rlwinm	r3, r3, 0, ~SR_NX	/* Nx = 0 */
+	rlwinm	r3, r3, 0, ~SR_KS	/* Ks = 0 */
+	oris	r3, r3, SR_KP@h		/* Kp = 1 */
+3:	mtsrin	r3, r4
+	addi	r3, r3, 0x111	/* increment VSID */
+	addis	r4, r4, 0x1000	/* address of next segment */
+	bdnz	3b
+	blr
+
 /*
  * This is where the main kernel code starts.
  */
@@ -946,8 +881,9 @@
 	tophys(r4,r2)
 	addi	r4,r4,THREAD	/* init task's THREAD */
 	mtspr	SPRN_SPRG_THREAD,r4
-	li	r3,0
-	mtspr	SPRN_SPRG_RTAS,r3	/* 0 => not in RTAS */
+	lis	r4, (swapper_pg_dir - PAGE_OFFSET)@h
+	ori	r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
+	mtspr	SPRN_SPRG_PGDIR, r4
 
 	/* stack */
 	lis	r1,init_thread_union@ha
@@ -958,11 +894,19 @@
  * Do early platform-specific initialization,
  * and set up the MMU.
  */
+#ifdef CONFIG_KASAN
+	bl	kasan_early_init
+#endif
 	li	r3,0
 	mr	r4,r31
 	bl	machine_init
 	bl	__save_cpu_setup
 	bl	MMU_init
+#ifdef CONFIG_KASAN
+BEGIN_MMU_FTR_SECTION
+	bl	MMU_init_hw_patch
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+#endif
 
 /*
  * Go back to running unmapped so we can load up new values
@@ -1014,19 +958,25 @@
 	blt-	4f
 	mulli	r3,r3,897	/* multiply context by skew factor */
 	rlwinm	r3,r3,4,8,27	/* VSID = (context & 0xfffff) << 4 */
-	addis	r3,r3,0x6000	/* Set Ks, Ku bits */
+#ifdef CONFIG_PPC_KUEP
+	oris	r3, r3, SR_NX@h	/* Set Nx */
+#endif
+#ifdef CONFIG_PPC_KUAP
+	oris	r3, r3, SR_KS@h	/* Set Ks */
+#endif
 	li	r0,NUM_USER_SEGMENTS
 	mtctr	r0
 
+	lwz	r4, MM_PGD(r4)
 #ifdef CONFIG_BDI_SWITCH
 	/* Context switch the PTE pointer for the Abatron BDI2000.
 	 * The PGDIR is passed as second argument.
 	 */
-	lwz	r4,MM_PGD(r4)
-	lis	r5, KERNELBASE@h
-	lwz	r5, 0xf0(r5)
-	stw	r4, 0x4(r5)
+	lis	r5, abatron_pteptrs@ha
+	stw	r4, abatron_pteptrs@l + 0x4(r5)
 #endif
+	tophys(r4, r4)
+	mtspr	SPRN_SPRG_PGDIR, r4
 	li	r4,0
 	isync
 3:
@@ -1053,11 +1003,8 @@
  */
 clear_bats:
 	li	r10,0
-	mfspr	r9,SPRN_PVR
-	rlwinm	r9,r9,16,16,31		/* r9 = 1 for 601, 4 for 604 */
-	cmpwi	r9, 1
-	beq	1f
 
+#ifndef CONFIG_PPC_BOOK3S_601
 	mtspr	SPRN_DBAT0U,r10
 	mtspr	SPRN_DBAT0L,r10
 	mtspr	SPRN_DBAT1U,r10
@@ -1066,7 +1013,7 @@
 	mtspr	SPRN_DBAT2L,r10
 	mtspr	SPRN_DBAT3U,r10
 	mtspr	SPRN_DBAT3L,r10
-1:
+#endif
 	mtspr	SPRN_IBAT0U,r10
 	mtspr	SPRN_IBAT0L,r10
 	mtspr	SPRN_IBAT1U,r10
@@ -1101,6 +1048,41 @@
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 	blr
 
+_ENTRY(update_bats)
+	lis	r4, 1f@h
+	ori	r4, r4, 1f@l
+	tophys(r4, r4)
+	mfmsr	r6
+	mflr	r7
+	li	r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)
+	rlwinm	r0, r6, 0, ~MSR_RI
+	rlwinm	r0, r0, 0, ~MSR_EE
+	mtmsr	r0
+	mtspr	SPRN_SRR0, r4
+	mtspr	SPRN_SRR1, r3
+	SYNC
+	RFI
+1:	bl	clear_bats
+	lis	r3, BATS@ha
+	addi	r3, r3, BATS@l
+	tophys(r3, r3)
+	LOAD_BAT(0, r3, r4, r5)
+	LOAD_BAT(1, r3, r4, r5)
+	LOAD_BAT(2, r3, r4, r5)
+	LOAD_BAT(3, r3, r4, r5)
+BEGIN_MMU_FTR_SECTION
+	LOAD_BAT(4, r3, r4, r5)
+	LOAD_BAT(5, r3, r4, r5)
+	LOAD_BAT(6, r3, r4, r5)
+	LOAD_BAT(7, r3, r4, r5)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+	li	r3, MSR_KERNEL & ~(MSR_IR | MSR_DR | MSR_RI)
+	mtmsr	r3
+	mtspr	SPRN_SRR0, r7
+	mtspr	SPRN_SRR1, r6
+	SYNC
+	RFI
+
 flush_tlbs:
 	lis	r10, 0x40
 1:	addic.	r10, r10, -0x1000
@@ -1126,10 +1108,7 @@
  */
 initial_bats:
 	lis	r11,PAGE_OFFSET@h
-	mfspr	r9,SPRN_PVR
-	rlwinm	r9,r9,16,16,31		/* r9 = 1 for 601, 4 for 604 */
-	cmpwi	0,r9,1
-	bne	4f
+#ifdef CONFIG_PPC_BOOK3S_601
 	ori	r11,r11,4		/* set up BAT registers for 601 */
 	li	r8,0x7f			/* valid, block length = 8MB */
 	mtspr	SPRN_IBAT0U,r11		/* N.B. 601 has valid bit in */
@@ -1142,10 +1121,8 @@
 	addis	r8,r8,0x800000@h
 	mtspr	SPRN_IBAT2U,r11
 	mtspr	SPRN_IBAT2L,r8
-	isync
-	blr
-
-4:	tophys(r8,r11)
+#else
+	tophys(r8,r11)
 #ifdef CONFIG_SMP
 	ori	r8,r8,0x12		/* R/W access, M=1 */
 #else
@@ -1157,10 +1134,10 @@
 	mtspr	SPRN_DBAT0U,r11		/* bit in upper BAT register */
 	mtspr	SPRN_IBAT0L,r8
 	mtspr	SPRN_IBAT0U,r11
+#endif
 	isync
 	blr
 
-
 #ifdef CONFIG_BOOTX_TEXT
 setup_disp_bat:
 	/*
@@ -1175,15 +1152,13 @@
 	beqlr
 	lwz	r11,0(r8)
 	lwz	r8,4(r8)
-	mfspr	r9,SPRN_PVR
-	rlwinm	r9,r9,16,16,31		/* r9 = 1 for 601, 4 for 604 */
-	cmpwi	0,r9,1
-	beq	1f
+#ifndef CONFIG_PPC_BOOK3S_601
 	mtspr	SPRN_DBAT3L,r8
 	mtspr	SPRN_DBAT3U,r11
-	blr
-1:	mtspr	SPRN_IBAT3L,r8
+#else
+	mtspr	SPRN_IBAT3L,r8
 	mtspr	SPRN_IBAT3U,r11
+#endif
 	blr
 #endif /* CONFIG_BOOTX_TEXT */
 
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
new file mode 100644
index 0000000..8abc778
--- /dev/null
+++ b/arch/powerpc/kernel/head_32.h
@@ -0,0 +1,190 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __HEAD_32_H__
+#define __HEAD_32_H__
+
+#include <asm/ptrace.h>	/* for STACK_FRAME_REGS_MARKER */
+
+/*
+ * Exception entry code.  This code runs with address translation
+ * turned off, i.e. using physical addresses.
+ * We assume sprg3 has the physical address of the current
+ * task's thread_struct.
+ */
+
+.macro EXCEPTION_PROLOG
+	mtspr	SPRN_SPRG_SCRATCH0,r10
+	mtspr	SPRN_SPRG_SCRATCH1,r11
+	mfcr	r10
+	EXCEPTION_PROLOG_1
+	EXCEPTION_PROLOG_2
+.endm
+
+.macro EXCEPTION_PROLOG_1
+	mfspr	r11,SPRN_SRR1		/* check whether user or kernel */
+	andi.	r11,r11,MSR_PR
+	tophys(r11,r1)			/* use tophys(r1) if kernel */
+	beq	1f
+	mfspr	r11,SPRN_SPRG_THREAD
+	lwz	r11,TASK_STACK-THREAD(r11)
+	addi	r11,r11,THREAD_SIZE
+	tophys(r11,r11)
+1:	subi	r11,r11,INT_FRAME_SIZE	/* alloc exc. frame */
+.endm
+
+.macro EXCEPTION_PROLOG_2
+	stw	r10,_CCR(r11)		/* save registers */
+	stw	r12,GPR12(r11)
+	stw	r9,GPR9(r11)
+	mfspr	r10,SPRN_SPRG_SCRATCH0
+	stw	r10,GPR10(r11)
+	mfspr	r12,SPRN_SPRG_SCRATCH1
+	stw	r12,GPR11(r11)
+	mflr	r10
+	stw	r10,_LINK(r11)
+	mfspr	r12,SPRN_SRR0
+	mfspr	r9,SPRN_SRR1
+	stw	r1,GPR1(r11)
+	stw	r1,0(r11)
+	tovirt(r1,r11)			/* set new kernel sp */
+#ifdef CONFIG_40x
+	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
+#else
+	li	r10,MSR_KERNEL & ~(MSR_IR|MSR_DR) /* can take exceptions */
+	MTMSRD(r10)			/* (except for mach check in rtas) */
+#endif
+	stw	r0,GPR0(r11)
+	lis	r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
+	addi	r10,r10,STACK_FRAME_REGS_MARKER@l
+	stw	r10,8(r11)
+	SAVE_4GPRS(3, r11)
+	SAVE_2GPRS(7, r11)
+.endm
+
+.macro SYSCALL_ENTRY trapno
+	mfspr	r12,SPRN_SPRG_THREAD
+	mfcr	r10
+	lwz	r11,TASK_STACK-THREAD(r12)
+	mflr	r9
+	addi	r11,r11,THREAD_SIZE - INT_FRAME_SIZE
+	rlwinm	r10,r10,0,4,2	/* Clear SO bit in CR */
+	tophys(r11,r11)
+	stw	r10,_CCR(r11)		/* save registers */
+	mfspr	r10,SPRN_SRR0
+	stw	r9,_LINK(r11)
+	mfspr	r9,SPRN_SRR1
+	stw	r1,GPR1(r11)
+	stw	r1,0(r11)
+	tovirt(r1,r11)			/* set new kernel sp */
+	stw	r10,_NIP(r11)
+#ifdef CONFIG_40x
+	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
+#else
+	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */
+	MTMSRD(r10)			/* (except for mach check in rtas) */
+#endif
+	lis	r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
+	stw	r2,GPR2(r11)
+	addi	r10,r10,STACK_FRAME_REGS_MARKER@l
+	stw	r9,_MSR(r11)
+	li	r2, \trapno + 1
+	stw	r10,8(r11)
+	stw	r2,_TRAP(r11)
+	SAVE_GPR(0, r11)
+	SAVE_4GPRS(3, r11)
+	SAVE_2GPRS(7, r11)
+	addi	r11,r1,STACK_FRAME_OVERHEAD
+	addi	r2,r12,-THREAD
+	stw	r11,PT_REGS(r12)
+#if defined(CONFIG_40x)
+	/* Check to see if the dbcr0 register is set up to debug.  Use the
+	   internal debug mode bit to do this. */
+	lwz	r12,THREAD_DBCR0(r12)
+	andis.	r12,r12,DBCR0_IDM@h
+#endif
+	ACCOUNT_CPU_USER_ENTRY(r2, r11, r12)
+#if defined(CONFIG_40x)
+	beq+	3f
+	/* From user and task is ptraced - load up global dbcr0 */
+	li	r12,-1			/* clear all pending debug events */
+	mtspr	SPRN_DBSR,r12
+	lis	r11,global_dbcr0@ha
+	tophys(r11,r11)
+	addi	r11,r11,global_dbcr0@l
+	lwz	r12,0(r11)
+	mtspr	SPRN_DBCR0,r12
+	lwz	r12,4(r11)
+	addi	r12,r12,-1
+	stw	r12,4(r11)
+#endif
+
+3:
+	tovirt(r2, r2)			/* set r2 to current */
+	lis	r11, transfer_to_syscall@h
+	ori	r11, r11, transfer_to_syscall@l
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/*
+	 * If MSR is changing we need to keep interrupts disabled at this point
+	 * otherwise we might risk taking an interrupt before we tell lockdep
+	 * they are enabled.
+	 */
+	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL)
+	rlwimi	r10, r9, 0, MSR_EE
+#else
+	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL | MSR_EE)
+#endif
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
+	mtspr	SPRN_NRI, r0
+#endif
+	mtspr	SPRN_SRR1,r10
+	mtspr	SPRN_SRR0,r11
+	SYNC
+	RFI				/* jump to handler, enable MMU */
+.endm
+
+/*
+ * Note: code which follows this uses cr0.eq (set if from kernel),
+ * r11, r12 (SRR0), and r9 (SRR1).
+ *
+ * Note2: once we have set r1 we are in a position to take exceptions
+ * again, and we could thus set MSR:RI at that point.
+ */
+
+/*
+ * Exception vectors.
+ */
+#ifdef CONFIG_PPC_BOOK3S
+#define	START_EXCEPTION(n, label)		\
+	. = n;					\
+	DO_KVM n;				\
+label:
+
+#else
+#define	START_EXCEPTION(n, label)		\
+	. = n;					\
+label:
+
+#endif
+
+#define EXCEPTION(n, label, hdlr, xfer)		\
+	START_EXCEPTION(n, label)		\
+	EXCEPTION_PROLOG;			\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;	\
+	xfer(n, hdlr)
+
+#define EXC_XFER_TEMPLATE(hdlr, trap, msr, tfer, ret)		\
+	li	r10,trap;					\
+	stw	r10,_TRAP(r11);					\
+	LOAD_REG_IMMEDIATE(r10, msr);				\
+	bl	tfer;						\
+	.long	hdlr;						\
+	.long	ret
+
+#define EXC_XFER_STD(n, hdlr)		\
+	EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, transfer_to_handler_full,	\
+			  ret_from_except_full)
+
+#define EXC_XFER_LITE(n, hdlr)		\
+	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, transfer_to_handler, \
+			  ret_from_except)
+
+#endif /* __HEAD_32_H__ */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index b19d784..585ea19 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *    Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
  *      Initial PowerPC version.
@@ -18,17 +19,10 @@
  *         	frank_rowand@mvista.com or source@mvista.com
  * 	   	debbie_chu@mvista.com
  *
- *
  *    Module name: head_4xx.S
  *
  *    Description:
  *      Kernel execution entry point code.
- *
- *    This program is free software; you can redistribute it and/or
- *    modify it under the terms of the GNU General Public License
- *    as published by the Free Software Foundation; either version
- *    2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/init.h>
@@ -44,6 +38,8 @@
 #include <asm/export.h>
 #include <asm/asm-405.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:
@@ -99,46 +95,6 @@
 	.space	4
 
 /*
- * Exception vector entry code. This code runs with address translation
- * turned off (i.e. using physical addresses). We assume SPRG_THREAD has
- * the physical address of the current task thread_struct.
- * Note that we have to have decremented r1 before we write to any fields
- * of the exception frame, since a critical interrupt could occur at any
- * time, and it will write to the area immediately below the current r1.
- */
-#define NORMAL_EXCEPTION_PROLOG						     \
-	mtspr	SPRN_SPRG_SCRATCH0,r10;	/* save two registers to work with */\
-	mtspr	SPRN_SPRG_SCRATCH1,r11;					     \
-	mtspr	SPRN_SPRG_SCRATCH2,r1;					     \
-	mfcr	r10;			/* save CR in r10 for now	   */\
-	mfspr	r11,SPRN_SRR1;		/* check whether user or kernel    */\
-	andi.	r11,r11,MSR_PR;						     \
-	beq	1f;							     \
-	mfspr	r1,SPRN_SPRG_THREAD;	/* if from user, start at top of   */\
-	lwz	r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack   */\
-	addi	r1,r1,THREAD_SIZE;					     \
-1:	subi	r1,r1,INT_FRAME_SIZE;	/* Allocate an exception frame     */\
-	tophys(r11,r1);							     \
-	stw	r10,_CCR(r11);          /* save various registers	   */\
-	stw	r12,GPR12(r11);						     \
-	stw	r9,GPR9(r11);						     \
-	mfspr	r10,SPRN_SPRG_SCRATCH0;					     \
-	stw	r10,GPR10(r11);						     \
-	mfspr	r12,SPRN_SPRG_SCRATCH1;					     \
-	stw	r12,GPR11(r11);						     \
-	mflr	r10;							     \
-	stw	r10,_LINK(r11);						     \
-	mfspr	r10,SPRN_SPRG_SCRATCH2;					     \
-	mfspr	r12,SPRN_SRR0;						     \
-	stw	r10,GPR1(r11);						     \
-	mfspr	r9,SPRN_SRR1;						     \
-	stw	r10,0(r11);						     \
-	rlwinm	r9,r9,0,14,12;		/* clear MSR_WE (necessary?)	   */\
-	stw	r0,GPR0(r11);						     \
-	SAVE_4GPRS(3, r11);						     \
-	SAVE_2GPRS(7, r11)
-
-/*
  * 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.
@@ -158,7 +114,7 @@
 	beq	1f;							     \
 	/* COMING FROM USER MODE */					     \
 	mfspr	r11,SPRN_SPRG_THREAD;	/* if from user, start at top of   */\
-	lwz	r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+	lwz	r11,TASK_STACK-THREAD(r11); /* this thread's kernel stack */\
 1:	addi	r11,r11,THREAD_SIZE-INT_FRAME_SIZE; /* Alloc an excpt frm  */\
 	tophys(r11,r11);						     \
 	stw	r10,_CCR(r11);          /* save various registers	   */\
@@ -177,6 +133,9 @@
 	tovirt(r1,r11);							     \
 	rlwinm	r9,r9,0,14,12;		/* clear MSR_WE (necessary?)	   */\
 	stw	r0,GPR0(r11);						     \
+	lis	r10, STACK_FRAME_REGS_MARKER@ha; /* exception frame marker */\
+	addi	r10, r10, STACK_FRAME_REGS_MARKER@l;			     \
+	stw	r10, 8(r11);						     \
 	SAVE_4GPRS(3, r11);						     \
 	SAVE_2GPRS(7, r11)
 
@@ -196,53 +155,12 @@
 /*
  * Exception vectors.
  */
-#define	START_EXCEPTION(n, label)					     \
-	. = n;								     \
-label:
-
-#define EXCEPTION(n, label, hdlr, xfer)				\
-	START_EXCEPTION(n, label);				\
-	NORMAL_EXCEPTION_PROLOG;				\
-	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
-	xfer(n, hdlr)
-
 #define CRITICAL_EXCEPTION(n, label, hdlr)			\
 	START_EXCEPTION(n, label);				\
 	CRITICAL_EXCEPTION_PROLOG;				\
 	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
 	EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
-			  NOCOPY, crit_transfer_to_handler,	\
-			  ret_from_crit_exc)
-
-#define EXC_XFER_TEMPLATE(hdlr, trap, msr, copyee, tfer, ret)	\
-	li	r10,trap;					\
-	stw	r10,_TRAP(r11);					\
-	lis	r10,msr@h;					\
-	ori	r10,r10,msr@l;					\
-	copyee(r10, r9);					\
-	bl	tfer;		 				\
-	.long	hdlr;						\
-	.long	ret
-
-#define COPY_EE(d, s)		rlwimi d,s,0,16,16
-#define NOCOPY(d, s)
-
-#define EXC_XFER_STD(n, hdlr)		\
-	EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, NOCOPY, transfer_to_handler_full, \
-			  ret_from_except_full)
-
-#define EXC_XFER_LITE(n, hdlr)		\
-	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, NOCOPY, transfer_to_handler, \
-			  ret_from_except)
-
-#define EXC_XFER_EE(n, hdlr)		\
-	EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, COPY_EE, transfer_to_handler_full, \
-			  ret_from_except_full)
-
-#define EXC_XFER_EE_LITE(n, hdlr)	\
-	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, COPY_EE, transfer_to_handler, \
-			  ret_from_except)
-
+			  crit_transfer_to_handler, ret_from_crit_exc)
 
 /*
  * 0x0100 - Critical Interrupt Exception
@@ -393,7 +311,7 @@
  * This is caused by a fetch from non-execute or guarded pages.
  */
 	START_EXCEPTION(0x0400, InstructionAccess)
-	NORMAL_EXCEPTION_PROLOG
+	EXCEPTION_PROLOG
 	mr	r4,r12			/* Pass SRR0 as arg2 */
 	li	r5,0			/* Pass zero as arg3 */
 	EXC_XFER_LITE(0x400, handle_page_fault)
@@ -403,33 +321,32 @@
 
 /* 0x0600 - Alignment Exception */
 	START_EXCEPTION(0x0600, Alignment)
-	NORMAL_EXCEPTION_PROLOG
+	EXCEPTION_PROLOG
 	mfspr	r4,SPRN_DEAR		/* Grab the DEAR and save it */
 	stw	r4,_DEAR(r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_EE(0x600, alignment_exception)
+	EXC_XFER_STD(0x600, alignment_exception)
 
 /* 0x0700 - Program Exception */
 	START_EXCEPTION(0x0700, ProgramCheck)
-	NORMAL_EXCEPTION_PROLOG
+	EXCEPTION_PROLOG
 	mfspr	r4,SPRN_ESR		/* Grab the ESR and save it */
 	stw	r4,_ESR(r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_STD(0x700, program_check_exception)
 
-	EXCEPTION(0x0800, Trap_08, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x0900, Trap_09, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x0A00, Trap_0A, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x0B00, Trap_0B, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x0800, Trap_08, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x0900, Trap_09, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x0A00, Trap_0A, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x0B00, Trap_0B, unknown_exception, EXC_XFER_STD)
 
 /* 0x0C00 - System Call Exception */
 	START_EXCEPTION(0x0C00,	SystemCall)
-	NORMAL_EXCEPTION_PROLOG
-	EXC_XFER_EE_LITE(0xc00, DoSyscall)
+	SYSCALL_ENTRY	0xc00
 
-	EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x0E00, Trap_0E, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x0E00, Trap_0E, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_STD)
 
 /* 0x1000 - Programmable Interval Timer (PIT) Exception */
 	. = 0x1000
@@ -646,25 +563,25 @@
 	mfspr	r10, SPRN_SPRG_SCRATCH0
 	b	InstructionAccess
 
-	EXCEPTION(0x1300, Trap_13, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1400, Trap_14, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x1300, Trap_13, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1400, Trap_14, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_STD)
 #ifdef CONFIG_IBM405_ERR51
 	/* 405GP errata 51 */
 	START_EXCEPTION(0x1700, Trap_17)
 	b DTLBMiss
 #else
-	EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_STD)
 #endif
-	EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1A00, Trap_1A, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1B00, Trap_1B, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1C00, Trap_1C, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1D00, Trap_1D, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1E00, Trap_1E, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1F00, Trap_1F, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1A00, Trap_1A, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1B00, Trap_1B, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1C00, Trap_1C, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1D00, Trap_1D, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1E00, Trap_1E, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1F00, Trap_1F, unknown_exception, EXC_XFER_STD)
 
 /* Check for a single step debug exception while in an exception
  * handler before state has been saved.  This is to catch the case
@@ -726,11 +643,11 @@
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_TEMPLATE(DebugException, 0x2002, \
 		(MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
-		NOCOPY, crit_transfer_to_handler, ret_from_crit_exc)
+		crit_transfer_to_handler, ret_from_crit_exc)
 
 	/* Programmable Interval Timer (PIT) Exception. (from 0x1000) */
 Decrementer:
-	NORMAL_EXCEPTION_PROLOG
+	EXCEPTION_PROLOG
 	lis	r0,TSR_PIS@h
 	mtspr	SPRN_TSR,r0		/* Clear the PIT exception */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
@@ -738,9 +655,9 @@
 
 	/* Fixed Interval Timer (FIT) Exception. (from 0x1010) */
 FITException:
-	NORMAL_EXCEPTION_PROLOG
+	EXCEPTION_PROLOG
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	EXC_XFER_EE(0x1010, unknown_exception)
+	EXC_XFER_STD(0x1010, unknown_exception)
 
 	/* Watchdog Timer (WDT) Exception. (from 0x1020) */
 WDTException:
@@ -748,15 +665,14 @@
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
 	EXC_XFER_TEMPLATE(WatchdogException, 0x1020+2,
 	                  (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)),
-			  NOCOPY, crit_transfer_to_handler,
-			  ret_from_crit_exc)
+			  crit_transfer_to_handler, ret_from_crit_exc)
 
 /*
  * The other Data TLB exceptions bail out to this point
  * if they can't resolve the lightweight TLB fault.
  */
 DataAccess:
-	NORMAL_EXCEPTION_PROLOG
+	EXCEPTION_PROLOG
 	mfspr	r5,SPRN_ESR		/* Grab the ESR, save it, pass arg3 */
 	stw	r5,_ESR(r11)
 	mfspr	r4,SPRN_DEAR		/* Grab the DEAR, save it, pass arg2 */
@@ -848,6 +764,9 @@
 /*
  * 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
@@ -953,9 +872,8 @@
 	/* Context switch the PTE pointer for the Abatron BDI2000.
 	 * The PGDIR is the second parameter.
 	 */
-	lis	r5, KERNELBASE@h
-	lwz	r5, 0xf0(r5)
-	stw	r4, 0x4(r5)
+	lis	r5, abatron_pteptrs@ha
+	stw	r4, abatron_pteptrs@l + 0x4(r5)
 #endif
 	sync
 	mtspr	SPRN_PID,r3
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 37e4a7c..51dd01a 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Kernel execution entry point code.
  *
@@ -21,11 +22,6 @@
  * 	   	debbie_chu@mvista.com
  *    Copyright 2002-2005 MontaVista Software, Inc.
  *      PowerPC 44x support, Matt Porter <mporter@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
@@ -40,6 +36,7 @@
 #include <asm/ptrace.h>
 #include <asm/synch.h>
 #include <asm/export.h>
+#include <asm/code-patching-asm.h>
 #include "head_booke.h"
 
 
@@ -202,6 +199,9 @@
 /*
  * 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
@@ -277,16 +277,15 @@
 	FP_UNAVAILABLE_EXCEPTION
 #else
 	EXCEPTION(0x2010, BOOKE_INTERRUPT_FP_UNAVAIL, \
-		  FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
+		  FloatingPointUnavailable, unknown_exception, EXC_XFER_STD)
 #endif
 	/* System Call Interrupt */
 	START_EXCEPTION(SystemCall)
-	NORMAL_EXCEPTION_PROLOG(BOOKE_INTERRUPT_SYSCALL)
-	EXC_XFER_EE_LITE(0x0c00, DoSyscall)
+	SYSCALL_ENTRY   0xc00 BOOKE_INTERRUPT_SYSCALL
 
 	/* Auxiliary Processor Unavailable Interrupt */
 	EXCEPTION(0x2020, BOOKE_INTERRUPT_AP_UNAVAIL, \
-		  AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
+		  AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_STD)
 
 	/* Decrementer Interrupt */
 	DECREMENTER_EXCEPTION
@@ -294,7 +293,7 @@
 	/* Fixed Internal Timer Interrupt */
 	/* TODO: Add FIT support */
 	EXCEPTION(0x1010, BOOKE_INTERRUPT_FIT, FixedIntervalTimer, \
-		  unknown_exception, EXC_XFER_EE)
+		  unknown_exception, EXC_XFER_STD)
 
 	/* Watchdog Timer Interrupt */
 	/* TODO: Add watchdog support */
@@ -382,10 +381,9 @@
 	/* Increment, rollover, and store TLB index */
 	addi	r13,r13,1
 
+	patch_site 0f, patch__tlb_44x_hwater_D
 	/* Compare with watermark (instruction gets patched) */
-	.globl tlb_44x_patch_hwater_D
-tlb_44x_patch_hwater_D:
-	cmpwi	0,r13,1			/* reserve entries */
+0:	cmpwi	0,r13,1			/* reserve entries */
 	ble	5f
 	li	r13,0
 5:
@@ -478,10 +476,9 @@
 	/* Increment, rollover, and store TLB index */
 	addi	r13,r13,1
 
+	patch_site 0f, patch__tlb_44x_hwater_I
 	/* Compare with watermark (instruction gets patched) */
-	.globl tlb_44x_patch_hwater_I
-tlb_44x_patch_hwater_I:
-	cmpwi	0,r13,1			/* reserve entries */
+0:	cmpwi	0,r13,1			/* reserve entries */
 	ble	5f
 	li	r13,0
 5:
@@ -1020,10 +1017,10 @@
 
 	/* Now we can get our task struct and real stack pointer */
 
-	/* Get current_thread_info and current */
-	lis	r1,secondary_ti@ha
-	lwz	r1,secondary_ti@l(r1)
-	lwz	r2,TI_TASK(r1)
+	/* Get current's stack and current */
+	lis	r2,secondary_current@ha
+	lwz	r2,secondary_current@l(r2)
+	lwz	r1,TASK_STACK(r2)
 
 	/* Current stack pointer */
 	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 4898e94..ad79fdd 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -15,11 +16,6 @@
  *  This file contains the entry point for the 64-bit kernel along
  *  with some early initialization code common to all 64-bit powerpc
  *  variants.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/threads.h>
@@ -186,7 +182,8 @@
 	isync
 	bctr
 #else
-	BUG_OPCODE
+0:	trap
+	EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
 #endif
 CLOSE_FIXED_SECTION(first_256B)
 
@@ -639,7 +636,7 @@
 	sub	r5,r5,r11
 #else
 	/* just copy interrupts */
-	LOAD_REG_IMMEDIATE(r5, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
+	LOAD_REG_IMMEDIATE_SYM(r5, r11, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
 #endif
 	b	5f
 3:
@@ -801,21 +798,19 @@
 	/* Set thread priority to MEDIUM */
 	HMT_MEDIUM
 
-	/* Initialize the kernel stack */
-	LOAD_REG_ADDR(r3, current_set)
-	sldi	r28,r24,3		/* get current_set[cpu#]	 */
-	ldx	r14,r3,r28
-	addi	r14,r14,THREAD_SIZE-STACK_FRAME_OVERHEAD
-	std	r14,PACAKSAVE(r13)
-
-	/* Do early setup for that CPU (SLB and hash table pointer) */
+	/*
+	 * Do early setup for this CPU, in particular initialising the MMU so we
+	 * can turn it on below. This is a call to C, which is OK, we're still
+	 * running on the emergency stack.
+	 */
 	bl	early_setup_secondary
 
 	/*
-	 * setup the new stack pointer, but *don't* use this until
-	 * translation is on.
+	 * The primary has initialized our kernel stack for us in the paca, grab
+	 * it and put it in r1. We must *not* use it until we turn on the MMU
+	 * below, because it may not be inside the RMO.
 	 */
-	mr	r1, r14
+	ld	r1, PACAKSAVE(r13)
 
 	/* Clear backchain so we get nice backtraces */
 	li	r7,0
@@ -906,6 +901,7 @@
 /*
  * This is where the main kernel code starts.
  */
+__REF
 start_here_multiplatform:
 	/* set up the TOC */
 	bl      relative_toc
@@ -970,7 +966,9 @@
 
 	/* Restore parameters passed from prom_init/kexec */
 	mr	r3,r31
-	bl	early_setup		/* also sets r13 and SPRG_PACA */
+	LOAD_REG_ADDR(r12, DOTSYM(early_setup))
+	mtctr	r12
+	bctrl		/* also sets r13 and SPRG_PACA */
 
 	LOAD_REG_ADDR(r3, start_here_common)
 	ld	r4,PACAKMSR(r13)
@@ -979,6 +977,7 @@
 	RFI
 	b	.	/* prevent speculative execution */
 
+	.previous
 	/* This is where all platforms converge execution */
 
 start_here_common:
@@ -1000,7 +999,8 @@
 	bl	start_kernel
 
 	/* Not reached */
-	BUG_OPCODE
+	trap
+	EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
 
 /*
  * We put a few things here that have to be page-aligned.
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 81d4574..19f583e 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -11,15 +12,10 @@
  *
  *  This file contains low-level support and setup for PowerPC 8xx
  *  embedded processors, including trap and interrupt dispatch.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/init.h>
+#include <linux/magic.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
@@ -31,6 +27,9 @@
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 #include <asm/export.h>
+#include <asm/code-patching-asm.h>
+
+#include "head_32.h"
 
 #if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
 /* By simply checking Address >= 0x80000000, we know if its a kernel address */
@@ -105,98 +104,22 @@
 	mtspr	SPRN_SRR0,r0
 	rfi				/* enables MMU */
 
-/*
- * Exception entry code.  This code runs with address translation
- * turned off, i.e. using physical addresses.
- * We assume sprg3 has the physical address of the current
- * task's thread_struct.
- */
-#define EXCEPTION_PROLOG	\
-	mtspr	SPRN_SPRG_SCRATCH0, r10;	\
-	mtspr	SPRN_SPRG_SCRATCH1, r11;	\
-	mfcr	r10;		\
-	EXCEPTION_PROLOG_1;	\
-	EXCEPTION_PROLOG_2
 
-#define EXCEPTION_PROLOG_1	\
-	mfspr	r11,SPRN_SRR1;		/* check whether user or kernel */ \
-	andi.	r11,r11,MSR_PR;	\
-	tophys(r11,r1);			/* use tophys(r1) if kernel */ \
-	beq	1f;		\
-	mfspr	r11,SPRN_SPRG_THREAD;	\
-	lwz	r11,THREAD_INFO-THREAD(r11);	\
-	addi	r11,r11,THREAD_SIZE;	\
-	tophys(r11,r11);	\
-1:	subi	r11,r11,INT_FRAME_SIZE	/* alloc exc. frame */
+#ifdef CONFIG_PERF_EVENTS
+	.align	4
 
+	.globl	itlb_miss_counter
+itlb_miss_counter:
+	.space	4
 
-#define EXCEPTION_PROLOG_2	\
-	stw	r10,_CCR(r11);		/* save registers */ \
-	stw	r12,GPR12(r11);	\
-	stw	r9,GPR9(r11);	\
-	mfspr	r10,SPRN_SPRG_SCRATCH0;	\
-	stw	r10,GPR10(r11);	\
-	mfspr	r12,SPRN_SPRG_SCRATCH1;	\
-	stw	r12,GPR11(r11);	\
-	mflr	r10;		\
-	stw	r10,_LINK(r11);	\
-	mfspr	r12,SPRN_SRR0;	\
-	mfspr	r9,SPRN_SRR1;	\
-	stw	r1,GPR1(r11);	\
-	stw	r1,0(r11);	\
-	tovirt(r1,r11);			/* set new kernel sp */	\
-	li	r10,MSR_KERNEL & ~(MSR_IR|MSR_DR); /* can take exceptions */ \
-	mtmsr	r10;		\
-	stw	r0,GPR0(r11);	\
-	SAVE_4GPRS(3, r11);	\
-	SAVE_2GPRS(7, r11)
+	.globl	dtlb_miss_counter
+dtlb_miss_counter:
+	.space	4
 
-/*
- * Note: code which follows this uses cr0.eq (set if from kernel),
- * r11, r12 (SRR0), and r9 (SRR1).
- *
- * Note2: once we have set r1 we are in a position to take exceptions
- * again, and we could thus set MSR:RI at that point.
- */
-
-/*
- * Exception vectors.
- */
-#define EXCEPTION(n, label, hdlr, xfer)		\
-	. = n;					\
-label:						\
-	EXCEPTION_PROLOG;			\
-	addi	r3,r1,STACK_FRAME_OVERHEAD;	\
-	xfer(n, hdlr)
-
-#define EXC_XFER_TEMPLATE(n, hdlr, trap, copyee, tfer, ret)	\
-	li	r10,trap;					\
-	stw	r10,_TRAP(r11);					\
-	li	r10,MSR_KERNEL;					\
-	copyee(r10, r9);					\
-	bl	tfer;						\
-i##n:								\
-	.long	hdlr;						\
-	.long	ret
-
-#define COPY_EE(d, s)		rlwimi d,s,0,16,16
-#define NOCOPY(d, s)
-
-#define EXC_XFER_STD(n, hdlr)		\
-	EXC_XFER_TEMPLATE(n, hdlr, n, NOCOPY, transfer_to_handler_full,	\
-			  ret_from_except_full)
-
-#define EXC_XFER_LITE(n, hdlr)		\
-	EXC_XFER_TEMPLATE(n, hdlr, n+1, NOCOPY, transfer_to_handler, \
-			  ret_from_except)
-
-#define EXC_XFER_EE(n, hdlr)		\
-	EXC_XFER_TEMPLATE(n, hdlr, n, COPY_EE, transfer_to_handler_full, \
-			  ret_from_except_full)
-
-#define EXC_XFER_EE_LITE(n, hdlr)	\
-	EXC_XFER_TEMPLATE(n, hdlr, n+1, COPY_EE, transfer_to_handler, \
-			  ret_from_except)
+	.globl	instruction_counter
+instruction_counter:
+	.space	4
+#endif
 
 /* System reset */
 	EXCEPTION(0x100, Reset, system_reset_exception, EXC_XFER_STD)
@@ -240,7 +163,7 @@
 	mfspr	r5,SPRN_DSISR
 	stw	r5,_DSISR(r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_EE(0x600, alignment_exception)
+	EXC_XFER_STD(0x600, alignment_exception)
 
 /* Program check exception */
 	EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD)
@@ -252,29 +175,39 @@
 /* Decrementer */
 	EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE)
 
-	EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_STD)
 
 /* System call */
 	. = 0xc00
 SystemCall:
-	EXCEPTION_PROLOG
-	EXC_XFER_EE_LITE(0xc00, DoSyscall)
+	SYSCALL_ENTRY	0xc00
 
 /* Single step - not used on 601 */
 	EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD)
-	EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0xf00, Trap_0f, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0xf00, Trap_0f, unknown_exception, EXC_XFER_STD)
 
 /* On the MPC8xx, this is a software emulation interrupt.  It occurs
  * for all unimplemented and illegal instructions.
  */
 	EXCEPTION(0x1000, SoftEmu, program_check_exception, EXC_XFER_STD)
 
+/* Called from DataStoreTLBMiss when perf TLB misses events are activated */
+#ifdef CONFIG_PERF_EVENTS
+	patch_site	0f, patch__dtlbmiss_perf
+0:	lwz	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+	addi	r10, r10, 1
+	stw	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	rfi
+#endif
+
 	. = 0x1100
 /*
  * For the MPC8xx, this is a software tablewalk to load the instruction
- * TLB.  The task switch loads the M_TW register with the pointer to the first
+ * 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
  * is an invalid pte, we load that into the TLB, which causes another fault
@@ -284,185 +217,164 @@
  */
 
 #ifdef CONFIG_8xx_CPU15
-#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr)	\
-	addi	tmp, addr, PAGE_SIZE;	\
-	tlbie	tmp;			\
-	addi	tmp, addr, -PAGE_SIZE;	\
-	tlbie	tmp
+#define INVALIDATE_ADJACENT_PAGES_CPU15(addr)	\
+	addi	addr, addr, PAGE_SIZE;	\
+	tlbie	addr;			\
+	addi	addr, addr, -(PAGE_SIZE << 1);	\
+	tlbie	addr;			\
+	addi	addr, addr, PAGE_SIZE
 #else
-#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr)
+#define INVALIDATE_ADJACENT_PAGES_CPU15(addr)
 #endif
 
 InstructionTLBMiss:
 	mtspr	SPRN_SPRG_SCRATCH0, r10
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
 	mtspr	SPRN_SPRG_SCRATCH1, r11
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
-	mtspr	SPRN_SPRG_SCRATCH2, r12
 #endif
 
 	/* 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(r11, r10)
+	INVALIDATE_ADJACENT_PAGES_CPU15(r10)
+	mtspr	SPRN_MD_EPN, r10
 	/* Only modules will cause ITLB Misses as we always
 	 * pin the first 8MB of kernel memory */
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
-	mfcr	r12
-#endif
 #ifdef ITLB_MISS_KERNEL
+	mfcr	r11
 #if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT)
-	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
+	cmpi	cr0, r10, 0	/* Address >= 0x80000000 */
 #else
-	rlwinm	r11, r10, 16, 0xfff8
-	cmpli	cr0, r11, PAGE_OFFSET@h
+	rlwinm	r10, r10, 16, 0xfff8
+	cmpli	cr0, r10, PAGE_OFFSET@h
 #ifndef CONFIG_PIN_TLB_TEXT
-	/* It is assumed that kernel code fits into the first 8M page */
-_ENTRY(ITLBMiss_cmp)
-	cmpli	cr7, r11, (PAGE_OFFSET + 0x0800000)@h
+	/* It is assumed that kernel code fits into the first 32M */
+0:	cmpli	cr7, r10, (PAGE_OFFSET + 0x2000000)@h
+	patch_site	0b, patch__itlbmiss_linmem_top
 #endif
 #endif
 #endif
-	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
+	mfspr	r10, SPRN_M_TWB	/* Get level 1 table */
 #ifdef ITLB_MISS_KERNEL
 #if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT)
-	beq+	3f
+	bge+	3f
 #else
 	blt+	3f
 #endif
 #ifndef CONFIG_PIN_TLB_TEXT
 	blt	cr7, ITLBMissLinear
 #endif
-	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
+	rlwinm	r10, r10, 0, 20, 31
+	oris	r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
 3:
 #endif
-	/* Insert level 1 index */
-	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
-	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
+	lwz	r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
+	mtspr	SPRN_MI_TWC, r10	/* Set segment attributes */
 
-	/* Extract level 2 index */
-	rlwinm	r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
-#ifdef CONFIG_HUGETLB_PAGE
-	mtcr	r11
-	bt-	28, 10f		/* bit 28 = Large page (8M) */
-	bt-	29, 20f		/* bit 29 = Large page (8M or 512k) */
-#endif
-	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
+	mtspr	SPRN_MD_TWC, r10
+	mfspr	r10, SPRN_MD_TWC
 	lwz	r10, 0(r10)	/* Get the pte */
-4:
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
-	mtcr	r12
+#ifdef ITLB_MISS_KERNEL
+	mtcr	r11
 #endif
-	/* Load the MI_TWC with the attributes for this "segment." */
-	mtspr	SPRN_MI_TWC, r11	/* Set segment attributes */
-
 #ifdef CONFIG_SWAP
 	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
 	and	r11, r11, r10
 	rlwimi	r10, r11, 0, _PAGE_PRESENT
 #endif
-	li	r11, RPN_PATTERN | 0x200
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 20 and 23 must be clear.
 	 * Software indicator bits 22, 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-	rlwimi	r11, r10, 4, 0x0400	/* Copy _PAGE_EXEC into bit 21 */
-	rlwimi	r10, r11, 0, 0x0ff0	/* Set 22, 24-27, clear 20,23 */
+	rlwimi	r10, r10, 0, 0x0f00	/* Clear bits 20-23 */
+	rlwimi	r10, r10, 4, 0x0400	/* Copy _PAGE_EXEC into bit 21 */
+	ori	r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */
 	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
 
 	/* Restore registers */
-_ENTRY(itlb_miss_exit_1)
-	mfspr	r10, SPRN_SPRG_SCRATCH0
+0:	mfspr	r10, SPRN_SPRG_SCRATCH0
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
 	mfspr	r11, SPRN_SPRG_SCRATCH1
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
-	mfspr	r12, SPRN_SPRG_SCRATCH2
 #endif
 	rfi
+	patch_site	0b, patch__itlbmiss_exit_1
+
 #ifdef CONFIG_PERF_EVENTS
-_ENTRY(itlb_miss_perf)
-	lis	r10, (itlb_miss_counter - PAGE_OFFSET)@ha
-	lwz	r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
-	addi	r11, r11, 1
-	stw	r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10)
-#endif
+	patch_site	0f, patch__itlbmiss_perf
+0:	lwz	r10, (itlb_miss_counter - PAGE_OFFSET)@l(0)
+	addi	r10, r10, 1
+	stw	r10, (itlb_miss_counter - PAGE_OFFSET)@l(0)
 	mfspr	r10, SPRN_SPRG_SCRATCH0
+#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
 	mfspr	r11, SPRN_SPRG_SCRATCH1
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE)
-	mfspr	r12, SPRN_SPRG_SCRATCH2
 #endif
 	rfi
-
-#ifdef CONFIG_HUGETLB_PAGE
-10:	/* 8M pages */
-#ifdef CONFIG_PPC_16K_PAGES
-	/* Extract level 2 index */
-	rlwinm	r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29
-	/* Add level 2 base */
-	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1
-#else
-	/* Level 2 base */
-	rlwinm	r10, r11, 0, ~HUGEPD_SHIFT_MASK
 #endif
-	lwz	r10, 0(r10)	/* Get the pte */
-	b	4b
 
-20:	/* 512k pages */
-	/* Extract level 2 index */
-	rlwinm	r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29
-	/* Add level 2 base */
-	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1
-	lwz	r10, 0(r10)	/* Get the pte */
-	b	4b
+#ifndef CONFIG_PIN_TLB_TEXT
+ITLBMissLinear:
+	mtcr	r11
+#if defined(CONFIG_STRICT_KERNEL_RWX) && CONFIG_ETEXT_SHIFT < 23
+	patch_site	0f, patch__itlbmiss_linmem_top8
+
+	mfspr	r10, SPRN_SRR0
+0:	subis	r11, r10, (PAGE_OFFSET - 0x80000000)@ha
+	rlwinm	r11, r11, 4, MI_PS8MEG ^ MI_PS512K
+	ori	r11, r11, MI_PS512K | MI_SVALID
+	rlwinm	r10, r10, 0, 0x0ff80000	/* 8xx supports max 256Mb RAM */
+#else
+	/* Set 8M byte page and mark it valid */
+	li	r11, MI_PS8MEG | MI_SVALID
+	rlwinm	r10, r10, 20, 0x0f800000	/* 8xx supports max 256Mb RAM */
+#endif
+	mtspr	SPRN_MI_TWC, r11
+	ori	r10, r10, 0xf0 | MI_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
+			  _PAGE_PRESENT
+	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
+
+0:	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	rfi
+	patch_site	0b, patch__itlbmiss_exit_2
 #endif
 
 	. = 0x1200
 DataStoreTLBMiss:
 	mtspr	SPRN_SPRG_SCRATCH0, r10
 	mtspr	SPRN_SPRG_SCRATCH1, r11
-	mtspr	SPRN_SPRG_SCRATCH2, r12
-	mfcr	r12
+	mfcr	r11
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
 	mfspr	r10, SPRN_MD_EPN
-	rlwinm	r11, r10, 16, 0xfff8
-	cmpli	cr0, r11, PAGE_OFFSET@h
-	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
-	blt+	3f
-	rlwinm	r11, r10, 16, 0xfff8
+	rlwinm	r10, r10, 16, 0xfff8
+	cmpli	cr0, r10, PAGE_OFFSET@h
 #ifndef CONFIG_PIN_TLB_IMMR
-	cmpli	cr0, r11, VIRT_IMMR_BASE@h
+	cmpli	cr6, r10, VIRT_IMMR_BASE@h
 #endif
-_ENTRY(DTLBMiss_cmp)
-	cmpli	cr7, r11, (PAGE_OFFSET + 0x1800000)@h
+0:	cmpli	cr7, r10, (PAGE_OFFSET + 0x2000000)@h
+	patch_site	0b, patch__dtlbmiss_linmem_top
+
+	mfspr	r10, SPRN_M_TWB	/* Get level 1 table */
+	blt+	3f
 #ifndef CONFIG_PIN_TLB_IMMR
-_ENTRY(DTLBMiss_jmp)
-	beq-	DTLBMissIMMR
+0:	beq-	cr6, DTLBMissIMMR
+	patch_site	0b, patch__dtlbmiss_immr_jmp
 #endif
 	blt	cr7, DTLBMissLinear
-	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
+	rlwinm	r10, r10, 0, 20, 31
+	oris	r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
 3:
-
-	/* Insert level 1 index */
-	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
-	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
-
-	/* We have a pte table, so load fetch the pte from the table.
-	 */
-	/* Extract level 2 index */
-	rlwinm	r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
-#ifdef CONFIG_HUGETLB_PAGE
 	mtcr	r11
-	bt-	28, 10f		/* bit 28 = Large page (8M) */
-	bt-	29, 20f		/* bit 29 = Large page (8M or 512k) */
-#endif
-	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
+	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
+
+	mtspr	SPRN_MD_TWC, r11
+	mfspr	r10, SPRN_MD_TWC
 	lwz	r10, 0(r10)	/* Get the pte */
-4:
-	mtcr	r12
 
 	/* Insert the Guarded flag into the TWC from the Linux PTE.
 	 * It is bit 27 of both the Linux PTE and the TWC (at least
@@ -498,45 +410,67 @@
 
 	/* Restore registers */
 	mtspr	SPRN_DAR, r11	/* Tag DAR */
-_ENTRY(dtlb_miss_exit_1)
-	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
-	mfspr	r12, SPRN_SPRG_SCRATCH2
-	rfi
-#ifdef CONFIG_PERF_EVENTS
-_ENTRY(dtlb_miss_perf)
-	lis	r10, (dtlb_miss_counter - PAGE_OFFSET)@ha
-	lwz	r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
-	addi	r11, r11, 1
-	stw	r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10)
-#endif
-	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
-	mfspr	r12, SPRN_SPRG_SCRATCH2
-	rfi
 
-#ifdef CONFIG_HUGETLB_PAGE
-10:	/* 8M pages */
-	/* Extract level 2 index */
-#ifdef CONFIG_PPC_16K_PAGES
-	rlwinm	r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29
-	/* Add level 2 base */
-	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1
+0:	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	rfi
+	patch_site	0b, patch__dtlbmiss_exit_1
+
+DTLBMissIMMR:
+	mtcr	r11
+	/* Set 512k byte guarded page and mark it valid */
+	li	r10, MD_PS512K | MD_GUARDED | MD_SVALID
+	mtspr	SPRN_MD_TWC, r10
+	mfspr	r10, SPRN_IMMR			/* Get current IMMR */
+	rlwinm	r10, r10, 0, 0xfff80000		/* Get 512 kbytes boundary */
+	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
+			  _PAGE_PRESENT | _PAGE_NO_CACHE
+	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
+
+	li	r11, RPN_PATTERN
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+
+0:	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	rfi
+	patch_site	0b, patch__dtlbmiss_exit_2
+
+DTLBMissLinear:
+	mtcr	r11
+	rlwinm	r10, r10, 20, 0x0f800000	/* 8xx supports max 256Mb RAM */
+#if defined(CONFIG_STRICT_KERNEL_RWX) && CONFIG_DATA_SHIFT < 23
+	patch_site	0f, patch__dtlbmiss_romem_top8
+
+0:	subis	r11, r10, (PAGE_OFFSET - 0x80000000)@ha
+	rlwinm	r11, r11, 0, 0xff800000
+	neg	r10, r11
+	or	r11, r11, r10
+	rlwinm	r11, r11, 4, MI_PS8MEG ^ MI_PS512K
+	ori	r11, r11, MI_PS512K | MI_SVALID
+	mfspr	r10, SPRN_MD_EPN
+	rlwinm	r10, r10, 0, 0x0ff80000	/* 8xx supports max 256Mb RAM */
 #else
-	/* Level 2 base */
-	rlwinm	r10, r11, 0, ~HUGEPD_SHIFT_MASK
+	/* Set 8M byte page and mark it valid */
+	li	r11, MD_PS8MEG | MD_SVALID
 #endif
-	lwz	r10, 0(r10)	/* Get the pte */
-	b	4b
+	mtspr	SPRN_MD_TWC, r11
+#ifdef CONFIG_STRICT_KERNEL_RWX
+	patch_site	0f, patch__dtlbmiss_romem_top
 
-20:	/* 512k pages */
-	/* Extract level 2 index */
-	rlwinm	r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29
-	/* Add level 2 base */
-	rlwimi	r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1
-	lwz	r10, 0(r10)	/* Get the pte */
-	b	4b
+0:	subis	r11, r10, 0
+	rlwimi	r10, r11, 11, _PAGE_RO
 #endif
+	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
+			  _PAGE_PRESENT
+	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
+
+	li	r11, RPN_PATTERN
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+
+0:	mfspr	r10, SPRN_SPRG_SCRATCH0
+	mfspr	r11, SPRN_SPRG_SCRATCH1
+	rfi
+	patch_site	0b, patch__dtlbmiss_exit_3
 
 /* This is an instruction TLB error on the MPC8xx.  This could be due
  * to many reasons, such as executing guarded memory or illegal instruction
@@ -548,11 +482,11 @@
 	mr	r4,r12
 	andis.	r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
 	andis.	r10,r9,SRR1_ISI_NOPT@h
-	beq+	1f
+	beq+	.Litlbie
 	tlbie	r4
-itlbie:
 	/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
-1:	EXC_XFER_LITE(0x400, handle_page_fault)
+.Litlbie:
+	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* This is the data TLB error on the MPC8xx.  This could be due to
  * many reasons, including a dirty update to a pte.  We bail out to
@@ -574,21 +508,21 @@
 	stw	r5,_DSISR(r11)
 	mfspr	r4,SPRN_DAR
 	andis.	r10,r5,DSISR_NOHPTE@h
-	beq+	1f
+	beq+	.Ldtlbie
 	tlbie	r4
-dtlbie:
-1:	li	r10,RPN_PATTERN
+.Ldtlbie:
+	li	r10,RPN_PATTERN
 	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
 	/* 0x300 is DataAccess exception, needed by bad_page_fault() */
 	EXC_XFER_LITE(0x300, handle_page_fault)
 
-	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_STD)
 
 /* On the MPC8xx, these next four traps are used for development
  * support of breakpoints and such.  Someday I will get around to
@@ -600,8 +534,8 @@
 	mtspr	SPRN_SPRG_SCRATCH1, r11
 	mfcr	r10
 	mfspr	r11, SPRN_SRR0
-	cmplwi	cr0, r11, (dtlbie - PAGE_OFFSET)@l
-	cmplwi	cr7, r11, (itlbie - PAGE_OFFSET)@l
+	cmplwi	cr0, r11, (.Ldtlbie - PAGE_OFFSET)@l
+	cmplwi	cr7, r11, (.Litlbie - PAGE_OFFSET)@l
 	beq-	cr0, 11f
 	beq-	cr7, 11f
 	EXCEPTION_PROLOG_1
@@ -610,7 +544,7 @@
 	mfspr	r4,SPRN_BAR
 	stw	r4,_DAR(r11)
 	mfspr	r5,SPRN_DSISR
-	EXC_XFER_EE(0x1c00, do_break)
+	EXC_XFER_STD(0x1c00, do_break)
 11:
 	mtcr	r10
 	mfspr	r10, SPRN_SPRG_SCRATCH0
@@ -621,115 +555,54 @@
 	. = 0x1d00
 InstructionBreakpoint:
 	mtspr	SPRN_SPRG_SCRATCH0, r10
-	mtspr	SPRN_SPRG_SCRATCH1, r11
-	lis	r10, (instruction_counter - PAGE_OFFSET)@ha
-	lwz	r11, (instruction_counter - PAGE_OFFSET)@l(r10)
-	addi	r11, r11, -1
-	stw	r11, (instruction_counter - PAGE_OFFSET)@l(r10)
+	lwz	r10, (instruction_counter - PAGE_OFFSET)@l(0)
+	addi	r10, r10, -1
+	stw	r10, (instruction_counter - PAGE_OFFSET)@l(0)
 	lis	r10, 0xffff
 	ori	r10, r10, 0x01
 	mtspr	SPRN_COUNTA, r10
 	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
 	rfi
 #else
-	EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_STD)
 #endif
-	EXCEPTION(0x1e00, Trap_1e, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x1f00, Trap_1f, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x1e00, Trap_1e, unknown_exception, EXC_XFER_STD)
+	EXCEPTION(0x1f00, Trap_1f, unknown_exception, EXC_XFER_STD)
 
 	. = 0x2000
 
-/*
- * Bottom part of DataStoreTLBMiss handlers for IMMR area and linear RAM.
- * not enough space in the DataStoreTLBMiss area.
- */
-DTLBMissIMMR:
-	mtcr	r12
-	/* Set 512k byte guarded page and mark it valid */
-	li	r10, MD_PS512K | MD_GUARDED | MD_SVALID
-	mtspr	SPRN_MD_TWC, r10
-	mfspr	r10, SPRN_IMMR			/* Get current IMMR */
-	rlwinm	r10, r10, 0, 0xfff80000		/* Get 512 kbytes boundary */
-	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY | \
-			  _PAGE_PRESENT | _PAGE_NO_CACHE
-	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
-
-	li	r11, RPN_PATTERN
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
-_ENTRY(dtlb_miss_exit_2)
-	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
-	mfspr	r12, SPRN_SPRG_SCRATCH2
-	rfi
-
-DTLBMissLinear:
-	mtcr	r12
-	/* Set 8M byte page and mark it valid */
-	li	r11, MD_PS8MEG | MD_SVALID
-	mtspr	SPRN_MD_TWC, r11
-	rlwinm	r10, r10, 0, 0x0f800000	/* 8xx supports max 256Mb RAM */
-	ori	r10, r10, 0xf0 | MD_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY | \
-			  _PAGE_PRESENT
-	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
-
-	li	r11, RPN_PATTERN
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
-_ENTRY(dtlb_miss_exit_3)
-	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
-	mfspr	r12, SPRN_SPRG_SCRATCH2
-	rfi
-
-#ifndef CONFIG_PIN_TLB_TEXT
-ITLBMissLinear:
-	mtcr	r12
-	/* Set 8M byte page and mark it valid */
-	li	r11, MI_PS8MEG | MI_SVALID
-	mtspr	SPRN_MI_TWC, r11
-	rlwinm	r10, r10, 0, 0x0f800000	/* 8xx supports max 256Mb RAM */
-	ori	r10, r10, 0xf0 | MI_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY | \
-			  _PAGE_PRESENT
-	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
-
-_ENTRY(itlb_miss_exit_2)
-	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
-	mfspr	r12, SPRN_SPRG_SCRATCH2
-	rfi
-#endif
-
 /* 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.
  */
- /* define if you don't want to use self modifying code */
-#define NO_SELF_MODIFYING_CODE
 FixupDAR:/* Entry point for dcbx workaround. */
-	mtspr	SPRN_SPRG_SCRATCH2, r10
+	mtspr	SPRN_M_TW, r10
 	/* fetch instruction from memory. */
 	mfspr	r10, SPRN_SRR0
+	mtspr	SPRN_MD_EPN, r10
 	rlwinm	r11, r10, 16, 0xfff8
 	cmpli	cr0, r11, PAGE_OFFSET@h
-	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
+	mfspr	r11, SPRN_M_TWB	/* Get level 1 table */
 	blt+	3f
 	rlwinm	r11, r10, 16, 0xfff8
-_ENTRY(FixupDAR_cmp)
-	cmpli	cr7, r11, (PAGE_OFFSET + 0x1800000)@h
+
+0:	cmpli	cr7, r11, (PAGE_OFFSET + 0x1800000)@h
+	patch_site	0b, patch__fixupdar_linmem_top
+
 	/* create physical page address from effective address */
 	tophys(r11, r10)
 	blt-	cr7, 201f
-	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
-	/* Insert level 1 index */
-3:	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
+	mfspr	r11, SPRN_M_TWB	/* Get level 1 table */
+	rlwinm	r11, r11, 0, 20, 31
+	oris	r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha
+3:
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
+	mtspr	SPRN_MD_TWC, r11
 	mtcr	r11
+	mfspr	r11, SPRN_MD_TWC
+	lwz	r11, 0(r11)	/* Get the pte */
 	bt	28,200f		/* bit 28 = Large page (8M) */
 	bt	29,202f		/* bit 29 = Large page (8M or 512K) */
-	rlwinm	r11, r11,0,0,19	/* Extract page descriptor page address */
-	/* Insert level 2 index */
-	rlwimi	r11, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
-	lwz	r11, 0(r11)	/* Get the pte */
 	/* concat physical page address(r11) and page offset(r10) */
 	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT, 31
 201:	lwz	r11,0(r11)
@@ -748,26 +621,15 @@
 	beq+	142f
 	cmpwi	cr0, r10, 1964	/* Is icbi? */
 	beq+	142f
-141:	mfspr	r10,SPRN_SPRG_SCRATCH2
+141:	mfspr	r10,SPRN_M_TW
 	b	DARFixed	/* Nope, go back to normal TLB processing */
 
-	/* concat physical page address(r11) and page offset(r10) */
 200:
-#ifdef CONFIG_PPC_16K_PAGES
-	rlwinm	r11, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1
-	rlwimi	r11, r10, 32 - (PAGE_SHIFT_8M - 2), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29
-#else
-	rlwinm	r11, r10, 0, ~HUGEPD_SHIFT_MASK
-#endif
-	lwz	r11, 0(r11)	/* Get the pte */
 	/* concat physical page address(r11) and page offset(r10) */
 	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT_8M, 31
 	b	201b
 
 202:
-	rlwinm	r11, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1
-	rlwimi	r11, r10, 32 - (PAGE_SHIFT_512K - 2), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29
-	lwz	r11, 0(r11)	/* Get the pte */
 	/* concat physical page address(r11) and page offset(r10) */
 	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT_512K, 31
 	b	201b
@@ -776,27 +638,6 @@
 	rlwinm	r10, r10,0,7,5	/* Clear store bit for buggy dcbst insn */
 	mtspr	SPRN_DSISR, r10
 142:	/* continue, it was a dcbx, dcbi instruction. */
-#ifndef NO_SELF_MODIFYING_CODE
-	andis.	r10,r11,0x1f	/* test if reg RA is r0 */
-	li	r10,modified_instr@l
-	dcbtst	r0,r10		/* touch for store */
-	rlwinm	r11,r11,0,0,20	/* Zero lower 10 bits */
-	oris	r11,r11,640	/* Transform instr. to a "add r10,RA,RB" */
-	ori	r11,r11,532
-	stw	r11,0(r10)	/* store add/and instruction */
-	dcbf	0,r10		/* flush new instr. to memory. */
-	icbi	0,r10		/* invalidate instr. cache line */
-	mfspr	r11, SPRN_SPRG_SCRATCH1	/* restore r11 */
-	mfspr	r10, SPRN_SPRG_SCRATCH0	/* restore r10 */
-	isync			/* Wait until new instr is loaded from memory */
-modified_instr:
-	.space	4		/* this is where the add instr. is stored */
-	bne+	143f
-	subf	r10,r0,r10	/* r10=r10-r0, only if reg RA is r0 */
-143:	mtdar	r10		/* store faulting EA in DAR */
-	mfspr	r10,SPRN_SPRG_SCRATCH2
-	b	DARFixed	/* Go back to normal TLB handling */
-#else
 	mfctr	r10
 	mtdar	r10			/* save ctr reg in DAR */
 	rlwinm	r10, r11, 24, 24, 28	/* offset into jump table for reg RB */
@@ -848,7 +689,7 @@
 	mfdar	r11
 	mtctr	r11			/* restore ctr reg from DAR */
 	mtdar	r10			/* save fault EA to DAR */
-	mfspr	r10,SPRN_SPRG_SCRATCH2
+	mfspr	r10,SPRN_M_TW
 	b	DARFixed		/* Go back to normal TLB handling */
 
 	/* special handling for r10,r11 since these are modified already */
@@ -860,7 +701,6 @@
 	add	r10, r10, r11	/* add it */
 	mfctr	r11		/* restore r11 */
 	b	151b
-#endif
 
 /*
  * This is where the main kernel code starts.
@@ -878,18 +718,24 @@
 	/* stack */
 	lis	r1,init_thread_union@ha
 	addi	r1,r1,init_thread_union@l
+	lis	r0, STACK_END_MAGIC@h
+	ori	r0, r0, STACK_END_MAGIC@l
+	stw	r0, 0(r1)
 	li	r0,0
 	stwu	r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
 
 	lis	r6, swapper_pg_dir@ha
 	tophys(r6,r6)
-	mtspr	SPRN_M_TW, r6
+	mtspr	SPRN_M_TWB, r6
 
 	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
@@ -919,11 +765,12 @@
 
 	/* set up the PTE pointers for the Abatron bdiGDB.
 	*/
-	tovirt(r6,r6)
 	lis	r5, abatron_pteptrs@h
 	ori	r5, r5, abatron_pteptrs@l
 	stw	r5, 0xf0(0)	/* Must match your Abatron config file */
 	tophys(r5,r5)
+	lis	r6, swapper_pg_dir@h
+	ori	r6, r6, swapper_pg_dir@l
 	stw	r6, 0(r5)
 
 /* Now turn on the MMU for real! */
@@ -952,28 +799,11 @@
 	mtspr	SPRN_MD_CTR, r10	/* remove PINNED DTLB entries */
 
 	tlbia			/* Invalidate all TLB entries */
-#ifdef CONFIG_PIN_TLB_TEXT
-	lis	r8, MI_RSV4I@h
-	ori	r8, r8, 0x1c00
-
-	mtspr	SPRN_MI_CTR, r8	/* Set instruction MMU control */
-#endif
-
 #ifdef CONFIG_PIN_TLB_DATA
 	oris	r10, r10, MD_RSV4I@h
 	mtspr	SPRN_MD_CTR, r10	/* Set data TLB control */
 #endif
 
-	/* Now map the lower 8 Meg into the ITLB. */
-	lis	r8, KERNELBASE@h	/* Create vaddr for TLB */
-	ori	r8, r8, MI_EVALID	/* Mark it valid */
-	mtspr	SPRN_MI_EPN, r8
-	li	r8, MI_PS8MEG /* Set 8M byte page */
-	ori	r8, r8, MI_SVALID	/* Make it valid */
-	mtspr	SPRN_MI_TWC, r8
-	li	r8, MI_BOOTINIT		/* Create RPN for address 0 */
-	mtspr	SPRN_MI_RPN, r8		/* Store TLB entry */
-
 	lis	r8, MI_APG_INIT@h	/* Set protection modes */
 	ori	r8, r8, MI_APG_INIT@l
 	mtspr	SPRN_MI_AP, r8
@@ -1003,6 +833,34 @@
 	mtspr	SPRN_MD_RPN, r8
 #endif
 
+	/* Now map the lower RAM (up to 32 Mbytes) into the ITLB. */
+#ifdef CONFIG_PIN_TLB_TEXT
+	lis	r8, MI_RSV4I@h
+	ori	r8, r8, 0x1c00
+#endif
+	li	r9, 4				/* up to 4 pages of 8M */
+	mtctr	r9
+	lis	r9, KERNELBASE@h		/* Create vaddr for TLB */
+	li	r10, MI_PS8MEG | MI_SVALID	/* Set 8M byte page */
+	li	r11, MI_BOOTINIT		/* Create RPN for address 0 */
+	lis	r12, _einittext@h
+	ori	r12, r12, _einittext@l
+1:
+#ifdef CONFIG_PIN_TLB_TEXT
+	mtspr	SPRN_MI_CTR, r8	/* Set instruction MMU control */
+	addi	r8, r8, 0x100
+#endif
+
+	ori	r0, r9, MI_EVALID		/* Mark it valid */
+	mtspr	SPRN_MI_EPN, r0
+	mtspr	SPRN_MI_TWC, r10
+	mtspr	SPRN_MI_RPN, r11		/* Store TLB entry */
+	addis	r9, r9, 0x80
+	addis	r11, r11, 0x80
+
+	cmpl	cr0, r9, r12
+	bdnzf	gt, 1b
+
 	/* Since the cache is enabled according to the information we
 	 * just loaded into the TLB, invalidate and enable the caches here.
 	 * We should probably check/set other modes....later.
@@ -1055,19 +913,6 @@
 /* Room for two PTE table poiners, usually the kernel and current user
  * pointer to their respective root page table (pgdir).
  */
+	.globl	abatron_pteptrs
 abatron_pteptrs:
 	.space	8
-
-#ifdef CONFIG_PERF_EVENTS
-	.globl	itlb_miss_counter
-itlb_miss_counter:
-	.space	4
-
-	.globl	dtlb_miss_counter
-dtlb_miss_counter:
-	.space	4
-
-	.globl	instruction_counter
-instruction_counter:
-	.space	4
-#endif
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index d0862a1..2ae635d 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -6,6 +6,8 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_booke_hv_asm.h>
 
+#ifdef __ASSEMBLY__
+
 /*
  * Macros used for common Book-e exception handling
  */
@@ -32,6 +34,16 @@
  */
 #define THREAD_NORMSAVE(offset)	(THREAD_NORMSAVES + (offset * 4))
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+#define BOOKE_CLEAR_BTB(reg)									\
+START_BTB_FLUSH_SECTION								\
+	BTB_FLUSH(reg)									\
+END_BTB_FLUSH_SECTION
+#else
+#define BOOKE_CLEAR_BTB(reg)
+#endif
+
+
 #define NORMAL_EXCEPTION_PROLOG(intno)						     \
 	mtspr	SPRN_SPRG_WSCRATCH0, r10;	/* save one register */	     \
 	mfspr	r10, SPRN_SPRG_THREAD;					     \
@@ -43,8 +55,9 @@
 	andi.	r11, r11, MSR_PR;	/* check whether user or kernel    */\
 	mr	r11, r1;						     \
 	beq	1f;							     \
+	BOOKE_CLEAR_BTB(r11)						\
 	/* if from user, start at top of this thread's kernel stack */       \
-	lwz	r11, THREAD_INFO-THREAD(r10);				     \
+	lwz	r11, TASK_STACK - THREAD(r10);				     \
 	ALLOC_STACK_FRAME(r11, THREAD_SIZE);				     \
 1 :	subi	r11, r11, INT_FRAME_SIZE; /* Allocate exception frame */     \
 	stw	r13, _CCR(r11);		/* save various registers */	     \
@@ -70,6 +83,101 @@
 	SAVE_4GPRS(3, r11);						     \
 	SAVE_2GPRS(7, r11)
 
+.macro SYSCALL_ENTRY trapno intno srr1
+	mfspr	r10, SPRN_SPRG_THREAD
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+	mtspr	SPRN_SPRG_WSCRATCH0, r10
+	stw	r11, THREAD_NORMSAVE(0)(r10)
+	stw	r13, THREAD_NORMSAVE(2)(r10)
+	mfcr	r13			/* save CR in r13 for now	   */
+	mfspr	r11, SPRN_SRR1
+	mtocrf	0x80, r11	/* check MSR[GS] without clobbering reg */
+	bf	3, 1975f
+	b	kvmppc_handler_\intno\()_\srr1
+1975:
+	mr	r12, r13
+	lwz	r13, THREAD_NORMSAVE(2)(r10)
+FTR_SECTION_ELSE
+#endif
+	mfcr	r12
+#ifdef CONFIG_KVM_BOOKE_HV
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
+#endif
+	BOOKE_CLEAR_BTB(r11)
+	lwz	r11, TASK_STACK - THREAD(r10)
+	rlwinm	r12,r12,0,4,2	/* Clear SO bit in CR */
+	ALLOC_STACK_FRAME(r11, THREAD_SIZE - INT_FRAME_SIZE)
+	stw	r12, _CCR(r11)		/* save various registers */
+	mflr	r12
+	stw	r12,_LINK(r11)
+	mfspr	r12,SPRN_SRR0
+	stw	r1, GPR1(r11)
+	mfspr	r9,SPRN_SRR1
+	stw	r1, 0(r11)
+	mr	r1, r11
+	stw	r12,_NIP(r11)
+	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?)	   */
+	lis	r12, STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
+	stw	r2,GPR2(r11)
+	addi	r12, r12, STACK_FRAME_REGS_MARKER@l
+	stw	r9,_MSR(r11)
+	li	r2, \trapno + 1
+	stw	r12, 8(r11)
+	stw	r2,_TRAP(r11)
+	SAVE_GPR(0, r11)
+	SAVE_4GPRS(3, r11)
+	SAVE_2GPRS(7, r11)
+
+	addi	r11,r1,STACK_FRAME_OVERHEAD
+	addi	r2,r10,-THREAD
+	stw	r11,PT_REGS(r10)
+	/* Check to see if the dbcr0 register is set up to debug.  Use the
+	   internal debug mode bit to do this. */
+	lwz	r12,THREAD_DBCR0(r10)
+	andis.	r12,r12,DBCR0_IDM@h
+	ACCOUNT_CPU_USER_ENTRY(r2, r11, r12)
+	beq+	3f
+	/* From user and task is ptraced - load up global dbcr0 */
+	li	r12,-1			/* clear all pending debug events */
+	mtspr	SPRN_DBSR,r12
+	lis	r11,global_dbcr0@ha
+	tophys(r11,r11)
+	addi	r11,r11,global_dbcr0@l
+#ifdef CONFIG_SMP
+	lwz	r10, TASK_CPU(r2)
+	slwi	r10, r10, 3
+	add	r11, r11, r10
+#endif
+	lwz	r12,0(r11)
+	mtspr	SPRN_DBCR0,r12
+	lwz	r12,4(r11)
+	addi	r12,r12,-1
+	stw	r12,4(r11)
+
+3:
+	tovirt(r2, r2)			/* set r2 to current */
+	lis	r11, transfer_to_syscall@h
+	ori	r11, r11, transfer_to_syscall@l
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/*
+	 * If MSR is changing we need to keep interrupts disabled at this point
+	 * otherwise we might risk taking an interrupt before we tell lockdep
+	 * they are enabled.
+	 */
+	lis	r10, MSR_KERNEL@h
+	ori	r10, r10, MSR_KERNEL@l
+	rlwimi	r10, r9, 0, MSR_EE
+#else
+	lis	r10, (MSR_KERNEL | MSR_EE)@h
+	ori	r10, r10, (MSR_KERNEL | MSR_EE)@l
+#endif
+	mtspr	SPRN_SRR1,r10
+	mtspr	SPRN_SRR0,r11
+	SYNC
+	RFI				/* jump to handler, enable MMU */
+.endm
+
 /* To handle the additional exception priority levels on 40x and Book-E
  * processors we allocate a stack per additional priority level.
  *
@@ -128,9 +236,10 @@
 	stw	r9,_CCR(r8);		/* save CR on stack		   */\
 	mfspr	r11,exc_level_srr1;	/* check whether user or kernel    */\
 	DO_KVM	BOOKE_INTERRUPT_##intno exc_level_srr1;		             \
+	BOOKE_CLEAR_BTB(r10)						\
 	andi.	r11,r11,MSR_PR;						     \
 	mfspr	r11,SPRN_SPRG_THREAD;	/* if from user, start at top of   */\
-	lwz	r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+	lwz	r11, TASK_STACK - THREAD(r11); /* this thread's kernel stack */\
 	addi	r11,r11,EXC_LVL_FRAME_OVERHEAD;	/* allocate stack frame    */\
 	beq	1f;							     \
 	/* COMING FROM USER MODE */					     \
@@ -143,13 +252,7 @@
 	stw	r10,GPR11(r11);						     \
 	b	2f;							     \
 	/* COMING FROM PRIV MODE */					     \
-1:	lwz	r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r11);		     \
-	lwz	r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r11);		     \
-	stw	r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r8);			     \
-	stw	r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r8);		     \
-	lwz	r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r11);			     \
-	stw	r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r8);			     \
-	mr	r11,r8;							     \
+1:	mr	r11, r8;							     \
 2:	mfspr	r8,SPRN_SPRG_RSCRATCH_##exc_level;			     \
 	stw	r12,GPR12(r11);		/* save various registers	   */\
 	mflr	r10;							     \
@@ -211,8 +314,7 @@
 	CRITICAL_EXCEPTION_PROLOG(intno);				\
 	addi	r3,r1,STACK_FRAME_OVERHEAD;				\
 	EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
-			  NOCOPY, crit_transfer_to_handler, \
-			  ret_from_crit_exc)
+			  crit_transfer_to_handler, ret_from_crit_exc)
 
 #define MCHECK_EXCEPTION(n, label, hdlr)			\
 	START_EXCEPTION(label);					\
@@ -221,36 +323,23 @@
 	stw	r5,_ESR(r11);					\
 	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
 	EXC_XFER_TEMPLATE(hdlr, n+4, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
-			  NOCOPY, mcheck_transfer_to_handler,   \
-			  ret_from_mcheck_exc)
+			  mcheck_transfer_to_handler, ret_from_mcheck_exc)
 
-#define EXC_XFER_TEMPLATE(hdlr, trap, msr, copyee, tfer, ret)	\
+#define EXC_XFER_TEMPLATE(hdlr, trap, msr, tfer, ret)	\
 	li	r10,trap;					\
 	stw	r10,_TRAP(r11);					\
 	lis	r10,msr@h;					\
 	ori	r10,r10,msr@l;					\
-	copyee(r10, r9);					\
 	bl	tfer;		 				\
 	.long	hdlr;						\
 	.long	ret
 
-#define COPY_EE(d, s)		rlwimi d,s,0,16,16
-#define NOCOPY(d, s)
-
 #define EXC_XFER_STD(n, hdlr)		\
-	EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, NOCOPY, transfer_to_handler_full, \
+	EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, transfer_to_handler_full, \
 			  ret_from_except_full)
 
 #define EXC_XFER_LITE(n, hdlr)		\
-	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, NOCOPY, transfer_to_handler, \
-			  ret_from_except)
-
-#define EXC_XFER_EE(n, hdlr)		\
-	EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, COPY_EE, transfer_to_handler_full, \
-			  ret_from_except_full)
-
-#define EXC_XFER_EE_LITE(n, hdlr)	\
-	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, COPY_EE, transfer_to_handler, \
+	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, transfer_to_handler, \
 			  ret_from_except)
 
 /* Check for a single step debug exception while in an exception
@@ -317,7 +406,7 @@
 	/* continue normal handling for a debug exception... */		      \
 2:	mfspr	r4,SPRN_DBSR;						      \
 	addi	r3,r1,STACK_FRAME_OVERHEAD;				      \
-	EXC_XFER_TEMPLATE(DebugException, 0x2008, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), NOCOPY, debug_transfer_to_handler, ret_from_debug_exc)
+	EXC_XFER_TEMPLATE(DebugException, 0x2008, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), debug_transfer_to_handler, ret_from_debug_exc)
 
 #define DEBUG_CRIT_EXCEPTION						      \
 	START_EXCEPTION(DebugCrit);					      \
@@ -370,7 +459,7 @@
 	/* continue normal handling for a critical exception... */	      \
 2:	mfspr	r4,SPRN_DBSR;						      \
 	addi	r3,r1,STACK_FRAME_OVERHEAD;				      \
-	EXC_XFER_TEMPLATE(DebugException, 0x2002, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), NOCOPY, crit_transfer_to_handler, ret_from_crit_exc)
+	EXC_XFER_TEMPLATE(DebugException, 0x2002, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), crit_transfer_to_handler, ret_from_crit_exc)
 
 #define DATA_STORAGE_EXCEPTION						      \
 	START_EXCEPTION(DataStorage)					      \
@@ -395,7 +484,7 @@
 	mfspr   r4,SPRN_DEAR;           /* Grab the DEAR and save it */	      \
 	stw     r4,_DEAR(r11);						      \
 	addi    r3,r1,STACK_FRAME_OVERHEAD;				      \
-	EXC_XFER_EE(0x0600, alignment_exception)
+	EXC_XFER_STD(0x0600, alignment_exception)
 
 #define PROGRAM_EXCEPTION						      \
 	START_EXCEPTION(Program)					      \
@@ -420,9 +509,9 @@
 	bl	load_up_fpu;		/* if from user, just load it up */   \
 	b	fast_exception_return;					      \
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD;				      \
-	EXC_XFER_EE_LITE(0x800, kernel_fp_unavailable_exception)
+	EXC_XFER_STD(0x800, kernel_fp_unavailable_exception)
 
-#ifndef __ASSEMBLY__
+#else /* __ASSEMBLY__ */
 struct exception_regs {
 	unsigned long mas0;
 	unsigned long mas1;
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index e2750b8..adf0505 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Kernel execution entry point code.
  *
@@ -23,11 +24,6 @@
  *	PowerPC 44x support, Matt Porter <mporter@kernel.crashing.org>
  *    Copyright 2004 Freescale Semiconductor, Inc
  *	PowerPC e500 modifications, Kumar Gala <galak@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
@@ -194,13 +190,6 @@
 #endif
 	mtspr	SPRN_MAS4, r2
 
-#if 0
-	/* Enable DOZE */
-	mfspr	r2,SPRN_HID0
-	oris	r2,r2,HID0_DOZE@h
-	mtspr	SPRN_HID0, r2
-#endif
-
 #if !defined(CONFIG_BDI_SWITCH)
 	/*
 	 * The Abatron BDI JTAG debugger does not tolerate others
@@ -243,8 +232,9 @@
 	li	r0,0
 	stwu	r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
 
-	CURRENT_THREAD_INFO(r22, r1)
-	stw	r24, TI_CPU(r22)
+#ifdef CONFIG_SMP
+	stw	r24, TASK_CPU(r2)
+#endif
 
 	bl	early_init
 
@@ -274,6 +264,9 @@
 /*
  * Decide what sort of machine this is and initialize the MMU.
  */
+#ifdef CONFIG_KASAN
+	bl	kasan_early_init
+#endif
 	mr	r3,r30
 	mr	r4,r31
 	bl	machine_init
@@ -386,7 +379,7 @@
 	EXC_XFER_LITE(0x0300, handle_page_fault)
 1:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_EE_LITE(0x0300, CacheLockingException)
+	EXC_XFER_LITE(0x0300, CacheLockingException)
 
 	/* Instruction Storage Interrupt */
 	INSTRUCTION_STORAGE_EXCEPTION
@@ -407,21 +400,20 @@
 #ifdef CONFIG_E200
 	/* E200 treats 'normal' floating point instructions as FP Unavail exception */
 	EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
-		  program_check_exception, EXC_XFER_EE)
+		  program_check_exception, EXC_XFER_STD)
 #else
 	EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
-		  unknown_exception, EXC_XFER_EE)
+		  unknown_exception, EXC_XFER_STD)
 #endif
 #endif
 
 	/* System Call Interrupt */
 	START_EXCEPTION(SystemCall)
-	NORMAL_EXCEPTION_PROLOG(SYSCALL)
-	EXC_XFER_EE_LITE(0x0c00, DoSyscall)
+	SYSCALL_ENTRY   0xc00 BOOKE_INTERRUPT_SYSCALL SPRN_SRR1
 
 	/* Auxiliary Processor Unavailable Interrupt */
 	EXCEPTION(0x2900, AP_UNAVAIL, AuxillaryProcessorUnavailable, \
-		  unknown_exception, EXC_XFER_EE)
+		  unknown_exception, EXC_XFER_STD)
 
 	/* Decrementer Interrupt */
 	DECREMENTER_EXCEPTION
@@ -429,7 +421,7 @@
 	/* Fixed Internal Timer Interrupt */
 	/* TODO: Add FIT support */
 	EXCEPTION(0x3100, FIT, FixedIntervalTimer, \
-		  unknown_exception, EXC_XFER_EE)
+		  unknown_exception, EXC_XFER_STD)
 
 	/* Watchdog Timer Interrupt */
 #ifdef CONFIG_BOOKE_WDT
@@ -453,6 +445,13 @@
 	mfcr	r13
 	stw	r13, THREAD_NORMSAVE(3)(r10)
 	DO_KVM	BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1
+START_BTB_FLUSH_SECTION
+	mfspr r11, SPRN_SRR1
+	andi. r10,r11,MSR_PR
+	beq 1f
+	BTB_FLUSH(r10)
+1:
+END_BTB_FLUSH_SECTION
 	mfspr	r10, SPRN_DEAR		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the
@@ -547,6 +546,14 @@
 	mfcr	r13
 	stw	r13, THREAD_NORMSAVE(3)(r10)
 	DO_KVM	BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1
+START_BTB_FLUSH_SECTION
+	mfspr r11, SPRN_SRR1
+	andi. r10,r11,MSR_PR
+	beq 1f
+	BTB_FLUSH(r10)
+1:
+END_BTB_FLUSH_SECTION
+
 	mfspr	r10, SPRN_SRR0		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the
@@ -624,25 +631,25 @@
 	bl	load_up_spe
 	b	fast_exception_return
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_EE_LITE(0x2010, KernelSPE)
+	EXC_XFER_LITE(0x2010, KernelSPE)
 #elif defined(CONFIG_SPE_POSSIBLE)
 	EXCEPTION(0x2020, SPE_UNAVAIL, SPEUnavailable, \
-		  unknown_exception, EXC_XFER_EE)
+		  unknown_exception, EXC_XFER_STD)
 #endif /* CONFIG_SPE_POSSIBLE */
 
 	/* SPE Floating Point Data */
 #ifdef CONFIG_SPE
 	EXCEPTION(0x2030, SPE_FP_DATA, SPEFloatingPointData,
-		  SPEFloatingPointException, EXC_XFER_EE)
+		  SPEFloatingPointException, EXC_XFER_STD)
 
 	/* SPE Floating Point Round */
 	EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
-		  SPEFloatingPointRoundException, EXC_XFER_EE)
+		  SPEFloatingPointRoundException, EXC_XFER_STD)
 #elif defined(CONFIG_SPE_POSSIBLE)
 	EXCEPTION(0x2040, SPE_FP_DATA, SPEFloatingPointData,
-		  unknown_exception, EXC_XFER_EE)
+		  unknown_exception, EXC_XFER_STD)
 	EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
-		  unknown_exception, EXC_XFER_EE)
+		  unknown_exception, EXC_XFER_STD)
 #endif /* CONFIG_SPE_POSSIBLE */
 
 
@@ -665,10 +672,10 @@
 			   unknown_exception)
 
 	/* Hypercall */
-	EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception, EXC_XFER_STD)
 
 	/* Embedded Hypervisor Privilege */
-	EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_STD)
 
 interrupt_end:
 
@@ -702,8 +709,7 @@
 
 	/* Get the next_tlbcam_idx percpu var */
 #ifdef CONFIG_SMP
-	lwz	r12, THREAD_INFO-THREAD(r12)
-	lwz	r15, TI_CPU(r12)
+	lwz	r15, TASK_CPU-THREAD(r12)
 	lis     r14, __per_cpu_offset@h
 	ori     r14, r14, __per_cpu_offset@l
 	rlwinm  r15, r15, 2, 0, 29
@@ -1074,10 +1080,10 @@
 	mr	r4,r24		/* Why? */
 	bl	call_setup_cpu
 
-	/* get current_thread_info and current */
-	lis	r1,secondary_ti@ha
-	lwz	r1,secondary_ti@l(r1)
-	lwz	r2,TI_TASK(r1)
+	/* get current's stack and current */
+	lis	r2,secondary_current@ha
+	lwz	r2,secondary_current@l(r2)
+	lwz	r1,TASK_STACK(r2)
 
 	/* stack */
 	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index fec8a67..1007ec3 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -1,25 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
  * using the CPU's debug registers. Derived from
  * "arch/x86/kernel/hw_breakpoint.c"
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright 2010 IBM Corporation
  * Author: K.Prasad <prasad@linux.vnet.ibm.com>
- *
  */
 
 #include <linux/hw_breakpoint.h>
@@ -29,11 +15,15 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
 
 #include <asm/hw_breakpoint.h>
 #include <asm/processor.h>
 #include <asm/sstep.h>
 #include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/hvcall.h>
 #include <linux/uaccess.h>
 
 /*
@@ -174,7 +164,7 @@
 	if (!ppc_breakpoint_available())
 		return -ENODEV;
 	length_max = 8; /* DABR */
-	if (cpu_has_feature(CPU_FTR_DAWR)) {
+	if (dawr_enabled()) {
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
 		if ((attr->bp_addr >> 9) !=
@@ -205,18 +195,63 @@
 	tsk->thread.last_hit_ubp = NULL;
 }
 
+static bool is_larx_stcx_instr(struct pt_regs *regs, unsigned int instr)
+{
+	int ret, type;
+	struct instruction_op op;
+
+	ret = analyse_instr(&op, regs, instr);
+	type = GETTYPE(op.type);
+	return (!ret && (type == LARX || type == STCX));
+}
+
 /*
  * Handle debug exception notifications.
  */
+static bool stepping_handler(struct pt_regs *regs, struct perf_event *bp,
+			     unsigned long addr)
+{
+	unsigned int instr = 0;
+
+	if (__get_user_inatomic(instr, (unsigned int *)regs->nip))
+		goto fail;
+
+	if (is_larx_stcx_instr(regs, instr)) {
+		printk_ratelimited("Breakpoint hit on instruction that can't be emulated."
+				   " Breakpoint at 0x%lx will be disabled.\n", addr);
+		goto disable;
+	}
+
+	/* Do not emulate user-space instructions, instead single-step them */
+	if (user_mode(regs)) {
+		current->thread.last_hit_ubp = bp;
+		regs->msr |= MSR_SE;
+		return false;
+	}
+
+	if (!emulate_step(regs, instr))
+		goto fail;
+
+	return true;
+
+fail:
+	/*
+	 * We've failed in reliably handling the hw-breakpoint. Unregister
+	 * it and throw a warning message to let the user know about it.
+	 */
+	WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
+		"0x%lx will be disabled.", addr);
+
+disable:
+	perf_event_disable_inatomic(bp);
+	return false;
+}
+
 int hw_breakpoint_handler(struct die_args *args)
 {
 	int rc = NOTIFY_STOP;
 	struct perf_event *bp;
 	struct pt_regs *regs = args->regs;
-#ifndef CONFIG_PPC_8xx
-	int stepped = 1;
-	unsigned int instr;
-#endif
 	struct arch_hw_breakpoint *info;
 	unsigned long dar = regs->dar;
 
@@ -261,31 +296,9 @@
 	      (dar - bp->attr.bp_addr < bp->attr.bp_len)))
 		info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
 
-#ifndef CONFIG_PPC_8xx
-	/* Do not emulate user-space instructions, instead single-step them */
-	if (user_mode(regs)) {
-		current->thread.last_hit_ubp = bp;
-		regs->msr |= MSR_SE;
+	if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info->address))
 		goto out;
-	}
 
-	stepped = 0;
-	instr = 0;
-	if (!__get_user_inatomic(instr, (unsigned int *) regs->nip))
-		stepped = emulate_step(regs, instr);
-
-	/*
-	 * emulate_step() could not execute it. We've failed in reliably
-	 * handling the hw-breakpoint. Unregister it and throw a warning
-	 * message to let the user know about it.
-	 */
-	if (!stepped) {
-		WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
-			"0x%lx will be disabled.", info->address);
-		perf_event_disable_inatomic(bp);
-		goto out;
-	}
-#endif
 	/*
 	 * As a policy, the callback is invoked in a 'trigger-after-execute'
 	 * fashion
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index d7216c9..a36fd05 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Idle daemon for PowerPC.  Idle daemon will handle any action
  * that needs to be taken when the system becomes idle.
@@ -12,11 +13,6 @@
  *    Copyright (c) 2003 Dave Engebretsen <engebret@us.ibm.com>
  *
  * 32-bit and 64-bit versions merged by Paul Mackerras <paulus@samba.org>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/sched.h>
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index ff026c9..0ffdd18 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  This file contains the power_save function for 6xx & 7xxx CPUs
  *  rewritten in assembler
@@ -6,11 +7,6 @@
  *  it will have PLL 1 set to low speed mode (used during NAP/DOZE).
  *  if this is not the case some additional changes will have to
  *  be done to check a runtime var (a bit like powersave-nap)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/threads.h>
@@ -136,10 +132,9 @@
 	DSSALL
 	sync
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-	CURRENT_THREAD_INFO(r9, r1)
-	lwz	r8,TI_LOCAL_FLAGS(r9)	/* set napping bit */
+	lwz	r8,TI_LOCAL_FLAGS(r2)	/* set napping bit */
 	ori	r8,r8,_TLF_NAPPING	/* so when we take an exception */
-	stw	r8,TI_LOCAL_FLAGS(r9)	/* it will return to our caller */
+	stw	r8,TI_LOCAL_FLAGS(r2)	/* it will return to our caller */
 	mfmsr	r7
 	ori	r7,r7,MSR_EE
 	oris	r7,r7,MSR_POW@h
@@ -159,8 +154,7 @@
 	stw	r9,_NIP(r11)		/* make it do a blr */
 
 #ifdef CONFIG_SMP
-	CURRENT_THREAD_INFO(r12, r11)
-	lwz	r11,TI_CPU(r12)		/* get cpu number * 4 */
+	lwz	r11,TASK_CPU(r2)	/* get cpu number * 4 */
 	slwi	r11,r11,2
 #else
 	li	r11,0
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index 4e0d94d..cc008de 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2010 IBM Corp, Benjamin Herrenschmidt <benh@kernel.crashing.org>
  *
  * Generic idle routine for Book3E processors
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/threads.h>
@@ -63,7 +59,7 @@
 1:	/* Let's set the _TLF_NAPPING flag so interrupts make us return
 	 * to the right spot
 	*/
-	CURRENT_THREAD_INFO(r11, r1)
+	ld	r11, PACACURRENT(r13)
 	ld	r10,TI_LOCAL_FLAGS(r11)
 	ori	r10,r10,_TLF_NAPPING
 	std	r10,TI_LOCAL_FLAGS(r11)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 7f5ac2e..d327519 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -1,956 +1,184 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- *  This file contains idle entry/exit functions for POWER7,
- *  POWER8 and POWER9 CPUs.
+ *  Copyright 2018, IBM 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; either version
- *  2 of the License, or (at your option) any later version.
+ *  This file contains general idle entry/exit functions to save
+ *  and restore stack and NVGPRs which allows C code to call idle
+ *  states that lose GPRs, and it will return transparently with
+ *  SRR1 wakeup reason return value.
+ *
+ *  The platform / CPU caller must ensure SPRs and any other non-GPR
+ *  state is saved and restored correctly, handle KVM, interrupts, etc.
  */
 
-#include <linux/threads.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/cputable.h>
-#include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/ppc-opcode.h>
-#include <asm/hw_irq.h>
-#include <asm/kvm_book3s_asm.h>
-#include <asm/opal.h>
 #include <asm/cpuidle.h>
-#include <asm/exception-64s.h>
-#include <asm/book3s/64/mmu-hash.h>
-#include <asm/mmu.h>
-#include <asm/asm-compat.h>
-#include <asm/feature-fixups.h>
-
-#undef DEBUG
 
 /*
- * Use unused space in the interrupt stack to save and restore
- * registers for winkle support.
- */
-#define _MMCR0	GPR0
-#define _SDR1	GPR3
-#define _PTCR	GPR3
-#define _RPR	GPR4
-#define _SPURR	GPR5
-#define _PURR	GPR6
-#define _TSCR	GPR7
-#define _DSCR	GPR8
-#define _AMOR	GPR9
-#define _WORT	GPR10
-#define _WORC	GPR11
-#define _LPCR	GPR12
-
-#define PSSCR_EC_ESL_MASK_SHIFTED          (PSSCR_EC | PSSCR_ESL) >> 16
-
-	.text
-
-/*
- * Used by threads before entering deep idle states. Saves SPRs
- * in interrupt stack frame
- */
-save_sprs_to_stack:
-	/*
-	 * Note all register i.e per-core, per-subcore or per-thread is saved
-	 * here since any thread in the core might wake up first
-	 */
-BEGIN_FTR_SECTION
-	/*
-	 * Note - SDR1 is dropped in Power ISA v3. Hence not restoring
-	 * SDR1 here
-	 */
-	mfspr	r3,SPRN_PTCR
-	std	r3,_PTCR(r1)
-	mfspr	r3,SPRN_LPCR
-	std	r3,_LPCR(r1)
-FTR_SECTION_ELSE
-	mfspr	r3,SPRN_SDR1
-	std	r3,_SDR1(r1)
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
-	mfspr	r3,SPRN_RPR
-	std	r3,_RPR(r1)
-	mfspr	r3,SPRN_SPURR
-	std	r3,_SPURR(r1)
-	mfspr	r3,SPRN_PURR
-	std	r3,_PURR(r1)
-	mfspr	r3,SPRN_TSCR
-	std	r3,_TSCR(r1)
-	mfspr	r3,SPRN_DSCR
-	std	r3,_DSCR(r1)
-	mfspr	r3,SPRN_AMOR
-	std	r3,_AMOR(r1)
-	mfspr	r3,SPRN_WORT
-	std	r3,_WORT(r1)
-	mfspr	r3,SPRN_WORC
-	std	r3,_WORC(r1)
-/*
- * On POWER9, there are idle states such as stop4, invoked via cpuidle,
- * that lose hypervisor resources. In such cases, we need to save
- * additional SPRs before entering those idle states so that they can
- * be restored to their older values on wakeup from the idle state.
+ * Desired PSSCR in r3
  *
- * On POWER8, the only such deep idle state is winkle which is used
- * only in the context of CPU-Hotplug, where these additional SPRs are
- * reinitiazed to a sane value. Hence there is no need to save/restore
- * these SPRs.
- */
-BEGIN_FTR_SECTION
-	blr
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-
-power9_save_additional_sprs:
-	mfspr	r3, SPRN_PID
-	mfspr	r4, SPRN_LDBAR
-	std	r3, STOP_PID(r13)
-	std	r4, STOP_LDBAR(r13)
-
-	mfspr	r3, SPRN_FSCR
-	mfspr	r4, SPRN_HFSCR
-	std	r3, STOP_FSCR(r13)
-	std	r4, STOP_HFSCR(r13)
-
-	mfspr	r3, SPRN_MMCRA
-	mfspr	r4, SPRN_MMCR0
-	std	r3, STOP_MMCRA(r13)
-	std	r4, _MMCR0(r1)
-
-	mfspr	r3, SPRN_MMCR1
-	mfspr	r4, SPRN_MMCR2
-	std	r3, STOP_MMCR1(r13)
-	std	r4, STOP_MMCR2(r13)
-	blr
-
-power9_restore_additional_sprs:
-	ld	r3,_LPCR(r1)
-	ld	r4, STOP_PID(r13)
-	mtspr	SPRN_LPCR,r3
-	mtspr	SPRN_PID, r4
-
-	ld	r3, STOP_LDBAR(r13)
-	ld	r4, STOP_FSCR(r13)
-	mtspr	SPRN_LDBAR, r3
-	mtspr	SPRN_FSCR, r4
-
-	ld	r3, STOP_HFSCR(r13)
-	ld	r4, STOP_MMCRA(r13)
-	mtspr	SPRN_HFSCR, r3
-	mtspr	SPRN_MMCRA, r4
-
-	ld	r3, _MMCR0(r1)
-	ld	r4, STOP_MMCR1(r13)
-	mtspr	SPRN_MMCR0, r3
-	mtspr	SPRN_MMCR1, r4
-
-	ld	r3, STOP_MMCR2(r13)
-	ld	r4, PACA_SPRG_VDSO(r13)
-	mtspr	SPRN_MMCR2, r3
-	mtspr	SPRN_SPRG3, r4
-	blr
-
-/*
- * Used by threads when the lock bit of core_idle_state is set.
- * Threads will spin in HMT_LOW until the lock bit is cleared.
- * r14 - pointer to core_idle_state
- * r15 - used to load contents of core_idle_state
- * r9  - used as a temporary variable
- */
-
-core_idle_lock_held:
-	HMT_LOW
-3:	lwz	r15,0(r14)
-	andis.	r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	bne	3b
-	HMT_MEDIUM
-	lwarx	r15,0,r14
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	bne-	core_idle_lock_held
-	blr
-
-/*
- * Pass requested state in r3:
- *	r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8
- *	   - Requested PSSCR value in POWER9
+ * No state will be lost regardless of wakeup mechanism (interrupt or NIA).
  *
- * Address of idle handler to branch to in realmode in r4
+ * An EC=0 type wakeup will return with a value of 0. SRESET wakeup (which can
+ * happen with xscom SRESET and possibly MCE) may clobber volatiles except LR,
+ * and must blr, to return to caller with r3 set according to caller's expected
+ * return code (for Book3S/64 that is SRR1).
  */
-pnv_powersave_common:
-	/* Use r3 to pass state nap/sleep/winkle */
-	/* NAP is a state loss, we create a regs frame on the
-	 * stack, fill it up with the state we care about and
-	 * stick a pointer to it in PACAR1. We really only
-	 * need to save PC, some CR bits and the NV GPRs,
-	 * but for now an interrupt frame will do.
-	 */
-	mtctr	r4
+_GLOBAL(isa300_idle_stop_noloss)
+	mtspr 	SPRN_PSSCR,r3
+	PPC_STOP
+	li	r3,0
+	blr
 
-	mflr	r0
-	std	r0,16(r1)
-	stdu	r1,-INT_FRAME_SIZE(r1)
-	std	r0,_LINK(r1)
-	std	r0,_NIP(r1)
-
-	/* We haven't lost state ... yet */
-	li	r0,0
-	stb	r0,PACA_NAPSTATELOST(r13)
-
-	/* Continue saving state */
-	SAVE_GPR(2, r1)
-	SAVE_NVGPRS(r1)
-	mfcr	r5
-	std	r5,_CCR(r1)
+/*
+ * Desired PSSCR in r3
+ *
+ * GPRs may be lost, so they are saved here. Wakeup is by interrupt only.
+ * The SRESET wakeup returns to this function's caller by calling
+ * idle_return_gpr_loss with r3 set to desired return value.
+ *
+ * A wakeup without GPR loss may alteratively be handled as in
+ * isa300_idle_stop_noloss and blr directly, as an optimisation.
+ *
+ * The caller is responsible for saving/restoring SPRs, MSR, timebase,
+ * etc.
+ */
+_GLOBAL(isa300_idle_stop_mayloss)
+	mtspr 	SPRN_PSSCR,r3
 	std	r1,PACAR1(r13)
+	mflr	r4
+	mfcr	r5
+	/* use stack red zone rather than a new frame for saving regs */
+	std	r2,-8*0(r1)
+	std	r14,-8*1(r1)
+	std	r15,-8*2(r1)
+	std	r16,-8*3(r1)
+	std	r17,-8*4(r1)
+	std	r18,-8*5(r1)
+	std	r19,-8*6(r1)
+	std	r20,-8*7(r1)
+	std	r21,-8*8(r1)
+	std	r22,-8*9(r1)
+	std	r23,-8*10(r1)
+	std	r24,-8*11(r1)
+	std	r25,-8*12(r1)
+	std	r26,-8*13(r1)
+	std	r27,-8*14(r1)
+	std	r28,-8*15(r1)
+	std	r29,-8*16(r1)
+	std	r30,-8*17(r1)
+	std	r31,-8*18(r1)
+	std	r4,-8*19(r1)
+	std	r5,-8*20(r1)
+	/* 168 bytes */
+	PPC_STOP
+	b	.	/* catch bugs */
 
-BEGIN_FTR_SECTION
+/*
+ * Desired return value in r3
+ *
+ * The idle wakeup SRESET interrupt can call this after calling
+ * to return to the idle sleep function caller with r3 as the return code.
+ *
+ * This must not be used if idle was entered via a _noloss function (use
+ * a simple blr instead).
+ */
+_GLOBAL(idle_return_gpr_loss)
+	ld	r1,PACAR1(r13)
+	ld	r4,-8*19(r1)
+	ld	r5,-8*20(r1)
+	mtlr	r4
+	mtcr	r5
 	/*
-	 * POWER9 does not require real mode to stop, and presently does not
-	 * set hwthread_state for KVM (threads don't share MMU context), so
-	 * we can remain in virtual mode for this.
+	 * KVM nap requires r2 to be saved, rather than just restoring it
+	 * from PACATOC. This could be avoided for that less common case
+	 * if KVM saved its r2.
 	 */
-	bctr
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	/*
-	 * POWER8
-	 * Go to real mode to do the nap, as required by the architecture.
-	 * Also, we need to be in real mode before setting hwthread_state,
-	 * because as soon as we do that, another thread can switch
-	 * the MMU context to the guest.
-	 */
-	LOAD_REG_IMMEDIATE(r7, MSR_IDLE)
-	mtmsrd	r7,0
-	bctr
+	ld	r2,-8*0(r1)
+	ld	r14,-8*1(r1)
+	ld	r15,-8*2(r1)
+	ld	r16,-8*3(r1)
+	ld	r17,-8*4(r1)
+	ld	r18,-8*5(r1)
+	ld	r19,-8*6(r1)
+	ld	r20,-8*7(r1)
+	ld	r21,-8*8(r1)
+	ld	r22,-8*9(r1)
+	ld	r23,-8*10(r1)
+	ld	r24,-8*11(r1)
+	ld	r25,-8*12(r1)
+	ld	r26,-8*13(r1)
+	ld	r27,-8*14(r1)
+	ld	r28,-8*15(r1)
+	ld	r29,-8*16(r1)
+	ld	r30,-8*17(r1)
+	ld	r31,-8*18(r1)
+	blr
 
 /*
  * This is the sequence required to execute idle instructions, as
  * specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
+ *
+ * The 0(r1) slot is used to save r2 in isa206, so use that here.
  */
 #define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST)			\
 	/* Magic NAP/SLEEP/WINKLE mode enter sequence */	\
-	std	r0,0(r1);					\
+	std	r2,0(r1);					\
 	ptesync;						\
-	ld	r0,0(r1);					\
-236:	cmpd	cr0,r0,r0;					\
+	ld	r2,0(r1);					\
+236:	cmpd	cr0,r2,r2;					\
 	bne	236b;						\
-	IDLE_INST;
-
-
-	.globl pnv_enter_arch207_idle_mode
-pnv_enter_arch207_idle_mode:
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/* Tell KVM we're entering idle */
-	li	r4,KVM_HWTHREAD_IN_IDLE
-	/******************************************************/
-	/*  N O T E   W E L L    ! ! !    N O T E   W E L L   */
-	/* The following store to HSTATE_HWTHREAD_STATE(r13)  */
-	/* MUST occur in real mode, i.e. with the MMU off,    */
-	/* and the MMU must stay off until we clear this flag */
-	/* and test HSTATE_HWTHREAD_REQ(r13) in               */
-	/* pnv_powersave_wakeup in this file.                 */
-	/* The reason is that another thread can switch the   */
-	/* MMU to a guest context whenever this flag is set   */
-	/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on,    */
-	/* that would potentially cause this thread to start  */
-	/* executing instructions from guest memory in        */
-	/* hypervisor mode, leading to a host crash or data   */
-	/* corruption, or worse.                              */
-	/******************************************************/
-	stb	r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
-	stb	r3,PACA_THREAD_IDLE_STATE(r13)
-	cmpwi	cr3,r3,PNV_THREAD_SLEEP
-	bge	cr3,2f
-	IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
-	/* No return */
-2:
-	/* Sleep or winkle */
-	lbz	r7,PACA_THREAD_MASK(r13)
-	ld	r14,PACA_CORE_IDLE_STATE_PTR(r13)
-	li	r5,0
-	beq	cr3,3f
-	lis	r5,PNV_CORE_IDLE_WINKLE_COUNT@h
-3:
-lwarx_loop1:
-	lwarx	r15,0,r14
-
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	bnel-	core_idle_lock_held
-
-	add	r15,r15,r5			/* Add if winkle */
-	andc	r15,r15,r7			/* Clear thread bit */
-
-	andi.	r9,r15,PNV_CORE_IDLE_THREAD_BITS
+	IDLE_INST;						\
+	b	.	/* catch bugs */
 
 /*
- * If cr0 = 0, then current thread is the last thread of the core entering
- * sleep. Last thread needs to execute the hardware bug workaround code if
- * required by the platform.
- * Make the workaround call unconditionally here. The below branch call is
- * patched out when the idle states are discovered if the platform does not
- * require it.
- */
-.global pnv_fastsleep_workaround_at_entry
-pnv_fastsleep_workaround_at_entry:
-	beq	fastsleep_workaround_at_entry
-
-	stwcx.	r15,0,r14
-	bne-	lwarx_loop1
-	isync
-
-common_enter: /* common code for all the threads entering sleep or winkle */
-	bgt	cr3,enter_winkle
-	IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
-
-fastsleep_workaround_at_entry:
-	oris	r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	stwcx.	r15,0,r14
-	bne-	lwarx_loop1
-	isync
-
-	/* Fast sleep workaround */
-	li	r3,1
-	li	r4,1
-	bl	opal_config_cpu_idle_state
-
-	/* Unlock */
-	xoris	r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	lwsync
-	stw	r15,0(r14)
-	b	common_enter
-
-enter_winkle:
-	bl	save_sprs_to_stack
-
-	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
-
-/*
- * r3 - PSSCR value corresponding to the requested stop state.
- */
-power_enter_stop:
-/*
- * Check if we are executing the lite variant with ESL=EC=0
- */
-	andis.   r4,r3,PSSCR_EC_ESL_MASK_SHIFTED
-	clrldi   r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */
-	bne	 .Lhandle_esl_ec_set
-	PPC_STOP
-	li	r3,0  /* Since we didn't lose state, return 0 */
-	std	r3, PACA_REQ_PSSCR(r13)
-
-	/*
-	 * pnv_wakeup_noloss() expects r12 to contain the SRR1 value so
-	 * it can determine if the wakeup reason is an HMI in
-	 * CHECK_HMI_INTERRUPT.
-	 *
-	 * However, when we wakeup with ESL=0, SRR1 will not contain the wakeup
-	 * reason, so there is no point setting r12 to SRR1.
-	 *
-	 * Further, we clear r12 here, so that we don't accidentally enter the
-	 * HMI in pnv_wakeup_noloss() if the value of r12[42:45] == WAKE_HMI.
-	 */
-	li	r12, 0
-	b 	pnv_wakeup_noloss
-
-.Lhandle_esl_ec_set:
-BEGIN_FTR_SECTION
-	/*
-	 * POWER9 DD2.0 or earlier can incorrectly set PMAO when waking up after
-	 * a state-loss idle. Saving and restoring MMCR0 over idle is a
-	 * workaround.
-	 */
-	mfspr	r4,SPRN_MMCR0
-	std	r4,_MMCR0(r1)
-END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1)
-
-/*
- * Check if the requested state is a deep idle state.
- */
-	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
-	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
-	cmpd	r3,r4
-	bge	.Lhandle_deep_stop
-	PPC_STOP	/* Does not return (system reset interrupt) */
-
-.Lhandle_deep_stop:
-/*
- * Entering deep idle state.
- * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
- * stack and enter stop
- */
-	lbz     r7,PACA_THREAD_MASK(r13)
-	ld      r14,PACA_CORE_IDLE_STATE_PTR(r13)
-
-lwarx_loop_stop:
-	lwarx   r15,0,r14
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	bnel-	core_idle_lock_held
-	andc    r15,r15,r7                      /* Clear thread bit */
-
-	stwcx.  r15,0,r14
-	bne-    lwarx_loop_stop
-	isync
-
-	bl	save_sprs_to_stack
-
-	PPC_STOP	/* Does not return (system reset interrupt) */
-
-/*
- * Entered with MSR[EE]=0 and no soft-masked interrupts pending.
- * r3 contains desired idle state (PNV_THREAD_NAP/SLEEP/WINKLE).
- */
-_GLOBAL(power7_idle_insn)
-	/* Now check if user or arch enabled NAP mode */
-	LOAD_REG_ADDR(r4, pnv_enter_arch207_idle_mode)
-	b	pnv_powersave_common
-
-#define CHECK_HMI_INTERRUPT						\
-BEGIN_FTR_SECTION_NESTED(66);						\
-	rlwinm	r0,r12,45-31,0xf;  /* extract wake reason field (P8) */	\
-FTR_SECTION_ELSE_NESTED(66);						\
-	rlwinm	r0,r12,45-31,0xe;  /* P7 wake reason field is 3 bits */	\
-ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66);		\
-	cmpwi	r0,0xa;			/* Hypervisor maintenance ? */	\
-	bne+	20f;							\
-	/* Invoke opal call to handle hmi */				\
-	ld	r2,PACATOC(r13);					\
-	ld	r1,PACAR1(r13);						\
-	std	r3,ORIG_GPR3(r1);	/* Save original r3 */		\
-	li	r3,0;			/* NULL argument */		\
-	bl	hmi_exception_realmode;					\
-	nop;								\
-	ld	r3,ORIG_GPR3(r1);	/* Restore original r3 */	\
-20:	nop;
-
-/*
- * Entered with MSR[EE]=0 and no soft-masked interrupts pending.
- * r3 contains desired PSSCR register value.
+ * Desired instruction type in r3
  *
- * Offline (CPU unplug) case also must notify KVM that the CPU is
- * idle.
+ * GPRs may be lost, so they are saved here. Wakeup is by interrupt only.
+ * The SRESET wakeup returns to this function's caller by calling
+ * idle_return_gpr_loss with r3 set to desired return value.
+ *
+ * A wakeup without GPR loss may alteratively be handled as in
+ * isa300_idle_stop_noloss and blr directly, as an optimisation.
+ *
+ * The caller is responsible for saving/restoring SPRs, MSR, timebase,
+ * etc.
+ *
+ * This must be called in real-mode (MSR_IDLE).
  */
-_GLOBAL(power9_offline_stop)
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/*
-	 * Tell KVM we're entering idle.
-	 * This does not have to be done in real mode because the P9 MMU
-	 * is independent per-thread. Some steppings share radix/hash mode
-	 * between threads, but in that case KVM has a barrier sync in real
-	 * mode before and after switching between radix and hash.
-	 */
-	li	r4,KVM_HWTHREAD_IN_IDLE
-	stb	r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
-	/* fall through */
-
-_GLOBAL(power9_idle_stop)
-	std	r3, PACA_REQ_PSSCR(r13)
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-BEGIN_FTR_SECTION
-	sync
-	lwz	r5, PACA_DONT_STOP(r13)
-	cmpwi	r5, 0
+_GLOBAL(isa206_idle_insn_mayloss)
+	std	r1,PACAR1(r13)
+	mflr	r4
+	mfcr	r5
+	/* use stack red zone rather than a new frame for saving regs */
+	std	r2,-8*0(r1)
+	std	r14,-8*1(r1)
+	std	r15,-8*2(r1)
+	std	r16,-8*3(r1)
+	std	r17,-8*4(r1)
+	std	r18,-8*5(r1)
+	std	r19,-8*6(r1)
+	std	r20,-8*7(r1)
+	std	r21,-8*8(r1)
+	std	r22,-8*9(r1)
+	std	r23,-8*10(r1)
+	std	r24,-8*11(r1)
+	std	r25,-8*12(r1)
+	std	r26,-8*13(r1)
+	std	r27,-8*14(r1)
+	std	r28,-8*15(r1)
+	std	r29,-8*16(r1)
+	std	r30,-8*17(r1)
+	std	r31,-8*18(r1)
+	std	r4,-8*19(r1)
+	std	r5,-8*20(r1)
+	cmpwi	r3,PNV_THREAD_NAP
 	bne	1f
-END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
-#endif
-	mtspr 	SPRN_PSSCR,r3
-	LOAD_REG_ADDR(r4,power_enter_stop)
-	b	pnv_powersave_common
-	/* No return */
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-1:
-	/*
-	 * We get here when TM / thread reconfiguration bug workaround
-	 * code wants to get the CPU into SMT4 mode, and therefore
-	 * we are being asked not to stop.
-	 */
-	li	r3, 0
-	std	r3, PACA_REQ_PSSCR(r13)
-	blr		/* return 0 for wakeup cause / SRR1 value */
-#endif
-
-/*
- * Called from machine check handler for powersave wakeups.
- * Low level machine check processing has already been done. Now just
- * go through the wake up path to get everything in order.
- *
- * r3 - The original SRR1 value.
- * Original SRR[01] have been clobbered.
- * MSR_RI is clear.
- */
-.global pnv_powersave_wakeup_mce
-pnv_powersave_wakeup_mce:
-	/* Set cr3 for pnv_powersave_wakeup */
-	rlwinm	r11,r3,47-31,30,31
-	cmpwi	cr3,r11,2
-
-	/*
-	 * Now put the original SRR1 with SRR1_WAKEMCE_RESVD as the wake
-	 * reason into r12, which allows reuse of the system reset wakeup
-	 * code without being mistaken for another type of wakeup.
-	 */
-	oris	r12,r3,SRR1_WAKEMCE_RESVD@h
-
-	b	pnv_powersave_wakeup
-
-/*
- * Called from reset vector for powersave wakeups.
- * cr3 - set to gt if waking up with partial/complete hypervisor state loss
- * r12 - SRR1
- */
-.global pnv_powersave_wakeup
-pnv_powersave_wakeup:
-	ld	r2, PACATOC(r13)
-
-BEGIN_FTR_SECTION
-	bl	pnv_restore_hyp_resource_arch300
-FTR_SECTION_ELSE
-	bl	pnv_restore_hyp_resource_arch207
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
-
-	li	r0,PNV_THREAD_RUNNING
-	stb	r0,PACA_THREAD_IDLE_STATE(r13)	/* Clear thread state */
-
-	mr	r3,r12
-
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	lbz	r0,HSTATE_HWTHREAD_STATE(r13)
-	cmpwi	r0,KVM_HWTHREAD_IN_KERNEL
-	beq	0f
-	li	r0,KVM_HWTHREAD_IN_KERNEL
-	stb	r0,HSTATE_HWTHREAD_STATE(r13)
-	/* Order setting hwthread_state vs. testing hwthread_req */
-	sync
-0:	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
-	cmpwi	r0,0
-	beq	1f
-	b	kvm_start_guest
-1:
-#endif
-
-	/* Return SRR1 from power7_nap() */
-	blt	cr3,pnv_wakeup_noloss
-	b	pnv_wakeup_loss
-
-/*
- * Check whether we have woken up with hypervisor state loss.
- * If yes, restore hypervisor state and return back to link.
- *
- * cr3 - set to gt if waking up with partial/complete hypervisor state loss
- */
-pnv_restore_hyp_resource_arch300:
-	/*
-	 * Workaround for POWER9, if we lost resources, the ERAT
-	 * might have been mixed up and needs flushing. We also need
-	 * to reload MMCR0 (see comment above). We also need to set
-	 * then clear bit 60 in MMCRA to ensure the PMU starts running.
-	 */
-	blt	cr3,1f
-BEGIN_FTR_SECTION
-	PPC_INVALIDATE_ERAT
-	ld	r1,PACAR1(r13)
-	ld	r4,_MMCR0(r1)
-	mtspr	SPRN_MMCR0,r4
-END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1)
-	mfspr	r4,SPRN_MMCRA
-	ori	r4,r4,(1 << (63-60))
-	mtspr	SPRN_MMCRA,r4
-	xori	r4,r4,(1 << (63-60))
-	mtspr	SPRN_MMCRA,r4
-1:
-	/*
-	 * POWER ISA 3. Use PSSCR to determine if we
-	 * are waking up from deep idle state
-	 */
-	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
-	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
-
-	/*
-	 * 0-3 bits correspond to Power-Saving Level Status
-	 * which indicates the idle state we are waking up from
-	 */
-	mfspr	r5, SPRN_PSSCR
-	rldicl  r5,r5,4,60
-	li	r0, 0		/* clear requested_psscr to say we're awake */
-	std	r0, PACA_REQ_PSSCR(r13)
-	cmpd	cr4,r5,r4
-	bge	cr4,pnv_wakeup_tb_loss /* returns to caller */
-
-	blr	/* Waking up without hypervisor state loss. */
-
-/* Same calling convention as arch300 */
-pnv_restore_hyp_resource_arch207:
-	/*
-	 * POWER ISA 2.07 or less.
-	 * Check if we slept with sleep or winkle.
-	 */
-	lbz	r4,PACA_THREAD_IDLE_STATE(r13)
-	cmpwi	cr2,r4,PNV_THREAD_NAP
-	bgt	cr2,pnv_wakeup_tb_loss	/* Either sleep or Winkle */
-
-	/*
-	 * We fall through here if PACA_THREAD_IDLE_STATE shows we are waking
-	 * up from nap. At this stage CR3 shouldn't contains 'gt' since that
-	 * indicates we are waking with hypervisor state loss from nap.
-	 */
-	bgt	cr3,.
-
-	blr	/* Waking up without hypervisor state loss */
-
-/*
- * Called if waking up from idle state which can cause either partial or
- * complete hyp state loss.
- * In POWER8, called if waking up from fastsleep or winkle
- * In POWER9, called if waking up from stop state >= pnv_first_deep_stop_state
- *
- * r13 - PACA
- * cr3 - gt if waking up with partial/complete hypervisor state loss
- *
- * If ISA300:
- * cr4 - gt or eq if waking up from complete hypervisor state loss.
- *
- * If ISA207:
- * r4 - PACA_THREAD_IDLE_STATE
- */
-pnv_wakeup_tb_loss:
-	ld	r1,PACAR1(r13)
-	/*
-	 * Before entering any idle state, the NVGPRs are saved in the stack.
-	 * If there was a state loss, or PACA_NAPSTATELOST was set, then the
-	 * NVGPRs are restored. If we are here, it is likely that state is lost,
-	 * but not guaranteed -- neither ISA207 nor ISA300 tests to reach
-	 * here are the same as the test to restore NVGPRS:
-	 * PACA_THREAD_IDLE_STATE test for ISA207, PSSCR test for ISA300,
-	 * and SRR1 test for restoring NVGPRs.
-	 *
-	 * We are about to clobber NVGPRs now, so set NAPSTATELOST to
-	 * guarantee they will always be restored. This might be tightened
-	 * with careful reading of specs (particularly for ISA300) but this
-	 * is already a slow wakeup path and it's simpler to be safe.
-	 */
-	li	r0,1
-	stb	r0,PACA_NAPSTATELOST(r13)
-
-	/*
-	 *
-	 * Save SRR1 and LR in NVGPRs as they might be clobbered in
-	 * opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
-	 * to determine the wakeup reason if we branch to kvm_start_guest. LR
-	 * is required to return back to reset vector after hypervisor state
-	 * restore is complete.
-	 */
-	mr	r19,r12
-	mr	r18,r4
-	mflr	r17
-BEGIN_FTR_SECTION
-	CHECK_HMI_INTERRUPT
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
-
-	ld	r14,PACA_CORE_IDLE_STATE_PTR(r13)
-	lbz	r7,PACA_THREAD_MASK(r13)
-
-	/*
-	 * Take the core lock to synchronize against other threads.
-	 *
-	 * Lock bit is set in one of the 2 cases-
-	 * a. In the sleep/winkle enter path, the last thread is executing
-	 * fastsleep workaround code.
-	 * b. In the wake up path, another thread is executing fastsleep
-	 * workaround undo code or resyncing timebase or restoring context
-	 * In either case loop until the lock bit is cleared.
-	 */
-1:
-	lwarx	r15,0,r14
-	andis.	r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	bnel-	core_idle_lock_held
-	oris	r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	stwcx.	r15,0,r14
-	bne-	1b
-	isync
-
-	andi.	r9,r15,PNV_CORE_IDLE_THREAD_BITS
-	cmpwi	cr2,r9,0
-
-	/*
-	 * At this stage
-	 * cr2 - eq if first thread to wakeup in core
-	 * cr3-  gt if waking up with partial/complete hypervisor state loss
-	 * ISA300:
-	 * cr4 - gt or eq if waking up from complete hypervisor state loss.
-	 */
-
-BEGIN_FTR_SECTION
-	/*
-	 * Were we in winkle?
-	 * If yes, check if all threads were in winkle, decrement our
-	 * winkle count, set all thread winkle bits if all were in winkle.
-	 * Check if our thread has a winkle bit set, and set cr4 accordingly
-	 * (to match ISA300, above). Pseudo-code for core idle state
-	 * transitions for ISA207 is as follows (everything happens atomically
-	 * due to store conditional and/or lock bit):
-	 *
-	 * nap_idle() { }
-	 * nap_wake() { }
-	 *
-	 * sleep_idle()
-	 * {
-	 *	core_idle_state &= ~thread_in_core
-	 * }
-	 *
-	 * sleep_wake()
-	 * {
-	 *     bool first_in_core, first_in_subcore;
-	 *
-	 *     first_in_core = (core_idle_state & IDLE_THREAD_BITS) == 0;
-	 *     first_in_subcore = (core_idle_state & SUBCORE_SIBLING_MASK) == 0;
-	 *
-	 *     core_idle_state |= thread_in_core;
-	 * }
-	 *
-	 * winkle_idle()
-	 * {
-	 *	core_idle_state &= ~thread_in_core;
-	 *	core_idle_state += 1 << WINKLE_COUNT_SHIFT;
-	 * }
-	 *
-	 * winkle_wake()
-	 * {
-	 *     bool first_in_core, first_in_subcore, winkle_state_lost;
-	 *
-	 *     first_in_core = (core_idle_state & IDLE_THREAD_BITS) == 0;
-	 *     first_in_subcore = (core_idle_state & SUBCORE_SIBLING_MASK) == 0;
-	 *
-	 *     core_idle_state |= thread_in_core;
-	 *
-	 *     if ((core_idle_state & WINKLE_MASK) == (8 << WINKLE_COUNT_SIHFT))
-	 *         core_idle_state |= THREAD_WINKLE_BITS;
-	 *     core_idle_state -= 1 << WINKLE_COUNT_SHIFT;
-	 *
-	 *     winkle_state_lost = core_idle_state &
-	 *				(thread_in_core << WINKLE_THREAD_SHIFT);
-	 *     core_idle_state &= ~(thread_in_core << WINKLE_THREAD_SHIFT);
-	 * }
-	 *
-	 */
-	cmpwi	r18,PNV_THREAD_WINKLE
+	IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
+1:	cmpwi	r3,PNV_THREAD_SLEEP
 	bne	2f
-	andis.	r9,r15,PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT@h
-	subis	r15,r15,PNV_CORE_IDLE_WINKLE_COUNT@h
-	beq	2f
-	ori	r15,r15,PNV_CORE_IDLE_THREAD_WINKLE_BITS /* all were winkle */
-2:
-	/* Shift thread bit to winkle mask, then test if this thread is set,
-	 * and remove it from the winkle bits */
-	slwi	r8,r7,8
-	and	r8,r8,r15
-	andc	r15,r15,r8
-	cmpwi	cr4,r8,1 /* cr4 will be gt if our bit is set, lt if not */
+	IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
+2:	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
 
-	lbz	r4,PACA_SUBCORE_SIBLING_MASK(r13)
-	and	r4,r4,r15
-	cmpwi	r4,0	/* Check if first in subcore */
-
-	or	r15,r15,r7		/* Set thread bit */
-	beq	first_thread_in_subcore
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-
-	or	r15,r15,r7		/* Set thread bit */
-	beq	cr2,first_thread_in_core
-
-	/* Not first thread in core or subcore to wake up */
-	b	clear_lock
-
-first_thread_in_subcore:
-	/*
-	 * If waking up from sleep, subcore state is not lost. Hence
-	 * skip subcore state restore
-	 */
-	blt	cr4,subcore_state_restored
-
-	/* Restore per-subcore state */
-	ld      r4,_SDR1(r1)
-	mtspr   SPRN_SDR1,r4
-
-	ld      r4,_RPR(r1)
-	mtspr   SPRN_RPR,r4
-	ld	r4,_AMOR(r1)
-	mtspr	SPRN_AMOR,r4
-
-subcore_state_restored:
-	/*
-	 * Check if the thread is also the first thread in the core. If not,
-	 * skip to clear_lock.
-	 */
-	bne	cr2,clear_lock
-
-first_thread_in_core:
-
-	/*
-	 * First thread in the core waking up from any state which can cause
-	 * partial or complete hypervisor state loss. It needs to
-	 * call the fastsleep workaround code if the platform requires it.
-	 * Call it unconditionally here. The below branch instruction will
-	 * be patched out if the platform does not have fastsleep or does not
-	 * require the workaround. Patching will be performed during the
-	 * discovery of idle-states.
-	 */
-.global pnv_fastsleep_workaround_at_exit
-pnv_fastsleep_workaround_at_exit:
-	b	fastsleep_workaround_at_exit
-
-timebase_resync:
-	/*
-	 * Use cr3 which indicates that we are waking up with atleast partial
-	 * hypervisor state loss to determine if TIMEBASE RESYNC is needed.
-	 */
-	ble	cr3,.Ltb_resynced
-	/* Time base re-sync */
-	bl	opal_resync_timebase;
-	/*
-	 * If waking up from sleep (POWER8), per core state
-	 * is not lost, skip to clear_lock.
-	 */
-.Ltb_resynced:
-	blt	cr4,clear_lock
-
-	/*
-	 * First thread in the core to wake up and its waking up with
-	 * complete hypervisor state loss. Restore per core hypervisor
-	 * state.
-	 */
-BEGIN_FTR_SECTION
-	ld	r4,_PTCR(r1)
-	mtspr	SPRN_PTCR,r4
-	ld	r4,_RPR(r1)
-	mtspr	SPRN_RPR,r4
-	ld	r4,_AMOR(r1)
-	mtspr	SPRN_AMOR,r4
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
-	ld	r4,_TSCR(r1)
-	mtspr	SPRN_TSCR,r4
-	ld	r4,_WORC(r1)
-	mtspr	SPRN_WORC,r4
-
-clear_lock:
-	xoris	r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
-	lwsync
-	stw	r15,0(r14)
-
-common_exit:
-	/*
-	 * Common to all threads.
-	 *
-	 * If waking up from sleep, hypervisor state is not lost. Hence
-	 * skip hypervisor state restore.
-	 */
-	blt	cr4,hypervisor_state_restored
-
-	/* Waking up from winkle */
-
-BEGIN_MMU_FTR_SECTION
-	b	no_segments
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
-	/* Restore SLB  from PACA */
-	ld	r8,PACA_SLBSHADOWPTR(r13)
-
-	.rept	SLB_NUM_BOLTED
-	li	r3, SLBSHADOW_SAVEAREA
-	LDX_BE	r5, r8, r3
-	addi	r3, r3, 8
-	LDX_BE	r6, r8, r3
-	andis.	r7,r5,SLB_ESID_V@h
-	beq	1f
-	slbmte	r6,r5
-1:	addi	r8,r8,16
-	.endr
-no_segments:
-
-	/* Restore per thread state */
-
-	ld	r4,_SPURR(r1)
-	mtspr	SPRN_SPURR,r4
-	ld	r4,_PURR(r1)
-	mtspr	SPRN_PURR,r4
-	ld	r4,_DSCR(r1)
-	mtspr	SPRN_DSCR,r4
-	ld	r4,_WORT(r1)
-	mtspr	SPRN_WORT,r4
-
-	/* Call cur_cpu_spec->cpu_restore() */
-	LOAD_REG_ADDR(r4, cur_cpu_spec)
-	ld	r4,0(r4)
-	ld	r12,CPU_SPEC_RESTORE(r4)
-#ifdef PPC64_ELF_ABI_v1
-	ld	r12,0(r12)
-#endif
-	mtctr	r12
-	bctrl
-
-/*
- * On POWER9, we can come here on wakeup from a cpuidle stop state.
- * Hence restore the additional SPRs to the saved value.
- *
- * On POWER8, we come here only on winkle. Since winkle is used
- * only in the case of CPU-Hotplug, we don't need to restore
- * the additional SPRs.
- */
-BEGIN_FTR_SECTION
-	bl 	power9_restore_additional_sprs
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-hypervisor_state_restored:
-
-	mr	r12,r19
-	mtlr	r17
-	blr		/* return to pnv_powersave_wakeup */
-
-fastsleep_workaround_at_exit:
-	li	r3,1
-	li	r4,0
-	bl	opal_config_cpu_idle_state
-	b	timebase_resync
-
-/*
- * R3 here contains the value that will be returned to the caller
- * of power7_nap.
- * R12 contains SRR1 for CHECK_HMI_INTERRUPT.
- */
-.global pnv_wakeup_loss
-pnv_wakeup_loss:
-	ld	r1,PACAR1(r13)
-BEGIN_FTR_SECTION
-	CHECK_HMI_INTERRUPT
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
-	REST_NVGPRS(r1)
-	REST_GPR(2, r1)
-	ld	r4,PACAKMSR(r13)
-	ld	r5,_LINK(r1)
-	ld	r6,_CCR(r1)
-	addi	r1,r1,INT_FRAME_SIZE
-	mtlr	r5
-	mtcr	r6
-	mtmsrd	r4
-	blr
-
-/*
- * R3 here contains the value that will be returned to the caller
- * of power7_nap.
- * R12 contains SRR1 for CHECK_HMI_INTERRUPT.
- */
-pnv_wakeup_noloss:
-	lbz	r0,PACA_NAPSTATELOST(r13)
-	cmpwi	r0,0
-	bne	pnv_wakeup_loss
-	ld	r1,PACAR1(r13)
-BEGIN_FTR_SECTION
-	CHECK_HMI_INTERRUPT
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
-	ld	r4,PACAKMSR(r13)
-	ld	r5,_NIP(r1)
-	ld	r6,_CCR(r1)
-	addi	r1,r1,INT_FRAME_SIZE
-	mtlr	r5
-	mtcr	r6
-	mtmsrd	r4
-	blr
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 583e55a..308f499 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
  * Dave Liu <daveliu@freescale.com>
  * copy from idle_6xx.S and modify for e500 based processor,
  * implement the power_save function in idle.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/threads.h>
@@ -22,10 +18,9 @@
 	.text
 
 _GLOBAL(e500_idle)
-	CURRENT_THREAD_INFO(r3, r1)
-	lwz	r4,TI_LOCAL_FLAGS(r3)	/* set napping bit */
+	lwz	r4,TI_LOCAL_FLAGS(r2)	/* set napping bit */
 	ori	r4,r4,_TLF_NAPPING	/* so when we take an exception */
-	stw	r4,TI_LOCAL_FLAGS(r3)	/* it will return to our caller */
+	stw	r4,TI_LOCAL_FLAGS(r2)	/* it will return to our caller */
 
 #ifdef CONFIG_PPC_E500MC
 	wrteei	1
@@ -88,8 +83,7 @@
 	stw	r9,_NIP(r11)		/* make it do a blr */
 
 #ifdef CONFIG_SMP
-	CURRENT_THREAD_INFO(r12, r1)
-	lwz	r11,TI_CPU(r12)		/* get cpu number * 4 */
+	lwz	r11,TASK_CPU(r2)		/* get cpu number * 4 */
 	slwi	r11,r11,2
 #else
 	li	r11,0
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index a09b3c7..33c6253 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  This file contains the power_save function for 970-family CPUs.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/threads.h>
@@ -68,7 +64,7 @@
 	DSSALL
 	sync
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-	CURRENT_THREAD_INFO(r9, r1)
+	ld	r9, PACA_THREAD_INFO(r13)
 	ld	r8,TI_LOCAL_FLAGS(r9)	/* set napping bit */
 	ori	r8,r8,_TLF_NAPPING	/* so when we take an exception */
 	std	r8,TI_LOCAL_FLAGS(r9)	/* it will return to our caller */
diff --git a/arch/powerpc/kernel/ima_kexec.c b/arch/powerpc/kernel/ima_kexec.c
index 5ea42c9..720e50e 100644
--- a/arch/powerpc/kernel/ima_kexec.c
+++ b/arch/powerpc/kernel/ima_kexec.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2016 IBM Corporation
  *
  * Authors:
  * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/slab.h>
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index aa9f1b8..0276bc8 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -1,13 +1,10 @@
+// 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
- *
- * 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.
  */
 #undef DEBUG
 
@@ -152,11 +149,11 @@
 };
 
 #ifdef CONFIG_PPC_INDIRECT_MMIO
-static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
-				  unsigned long flags, void *caller)
+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, flags, caller);
+	void __iomem *res = __ioremap_caller(addr, size, prot, caller);
 	int busno;
 
 	bus = iowa_pci_find(0, (unsigned long)addr);
@@ -166,20 +163,17 @@
 	}
 	return res;
 }
-#else /* CONFIG_PPC_INDIRECT_MMIO */
-#define iowa_ioremap NULL
 #endif /* !CONFIG_PPC_INDIRECT_MMIO */
 
+bool io_workaround_inited;
+
 /* Enable IO workaround */
 static void io_workaround_init(void)
 {
-	static int io_workaround_inited;
-
 	if (io_workaround_inited)
 		return;
 	ppc_pci_io = iowa_pci_io;
-	ppc_md.ioremap = iowa_ioremap;
-	io_workaround_inited = 1;
+	io_workaround_inited = true;
 }
 
 /* Register new bus to support workaround */
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index 2a2b4ae..2f29b7d 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * I/O string operations
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -10,11 +11,6 @@
  * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
  *
  * Rewritten in C by Stephen Rothwell.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 19b4c62..9704f3f 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
  * 
@@ -6,20 +7,6 @@
  *               and  Ben. Herrenschmidt, IBM Corporation
  *
  * Dynamic DMA mapping support, bus-independent parts.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- * 
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- * 
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 
@@ -47,6 +34,7 @@
 #include <asm/fadump.h>
 #include <asm/vio.h>
 #include <asm/tce.h>
+#include <asm/mmu_context.h>
 
 #define DBG(...)
 
@@ -197,11 +185,11 @@
 	if (unlikely(npages == 0)) {
 		if (printk_ratelimit())
 			WARN_ON(1);
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	if (should_fail_iommu(dev))
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 
 	/*
 	 * We don't need to disable preemption here because any CPU can
@@ -277,7 +265,7 @@
 		} else {
 			/* Give up */
 			spin_unlock_irqrestore(&(pool->lock), flags);
-			return IOMMU_MAPPING_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 	}
 
@@ -309,13 +297,13 @@
 			      unsigned long attrs)
 {
 	unsigned long entry;
-	dma_addr_t ret = IOMMU_MAPPING_ERROR;
+	dma_addr_t ret = DMA_MAPPING_ERROR;
 	int build_fail;
 
 	entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order);
 
-	if (unlikely(entry == IOMMU_MAPPING_ERROR))
-		return IOMMU_MAPPING_ERROR;
+	if (unlikely(entry == DMA_MAPPING_ERROR))
+		return DMA_MAPPING_ERROR;
 
 	entry += tbl->it_offset;	/* Offset into real TCE table */
 	ret = entry << tbl->it_page_shift;	/* Set the return dma address */
@@ -327,12 +315,12 @@
 
 	/* tbl->it_ops->set() only returns non-zero for transient errors.
 	 * Clean up the table bitmap in this case and return
-	 * IOMMU_MAPPING_ERROR. For all other errors the functionality is
+	 * DMA_MAPPING_ERROR. For all other errors the functionality is
 	 * not altered.
 	 */
 	if (unlikely(build_fail)) {
 		__iommu_free(tbl, ret, npages);
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	/* Flush/invalidate TLB caches if necessary */
@@ -477,7 +465,7 @@
 		DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
 		/* Handle failure */
-		if (unlikely(entry == IOMMU_MAPPING_ERROR)) {
+		if (unlikely(entry == DMA_MAPPING_ERROR)) {
 			if (!(attrs & DMA_ATTR_NO_WARN) &&
 			    printk_ratelimit())
 				dev_info(dev, "iommu_alloc failed, tbl %p "
@@ -544,7 +532,7 @@
 	 */
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = IOMMU_MAPPING_ERROR;
+		outs->dma_address = DMA_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
@@ -562,7 +550,7 @@
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
 						 IOMMU_PAGE_SIZE(tbl));
 			__iommu_free(tbl, vaddr, npages);
-			s->dma_address = IOMMU_MAPPING_ERROR;
+			s->dma_address = DMA_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
@@ -645,11 +633,54 @@
 #endif
 }
 
+static void iommu_table_reserve_pages(struct iommu_table *tbl,
+		unsigned long res_start, unsigned long res_end)
+{
+	int i;
+
+	WARN_ON_ONCE(res_end < res_start);
+	/*
+	 * Reserve page 0 so it will not be used for any mappings.
+	 * This avoids buggy drivers that consider page 0 to be invalid
+	 * to crash the machine or even lose data.
+	 */
+	if (tbl->it_offset == 0)
+		set_bit(0, tbl->it_map);
+
+	tbl->it_reserved_start = res_start;
+	tbl->it_reserved_end = res_end;
+
+	/* Check if res_start..res_end isn't empty and overlaps the table */
+	if (res_start && res_end &&
+			(tbl->it_offset + tbl->it_size < res_start ||
+			 res_end < tbl->it_offset))
+		return;
+
+	for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i)
+		set_bit(i - tbl->it_offset, tbl->it_map);
+}
+
+static void iommu_table_release_pages(struct iommu_table *tbl)
+{
+	int i;
+
+	/*
+	 * In case we have reserved the first bit, we should not emit
+	 * the warning below.
+	 */
+	if (tbl->it_offset == 0)
+		clear_bit(0, tbl->it_map);
+
+	for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i)
+		clear_bit(i - tbl->it_offset, tbl->it_map);
+}
+
 /*
  * Build a iommu_table structure.  This contains a bit map which
  * is used to manage allocation of the tce space.
  */
-struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
+struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
+		unsigned long res_start, unsigned long res_end)
 {
 	unsigned long sz;
 	static int welcomed = 0;
@@ -668,13 +699,7 @@
 	tbl->it_map = page_address(page);
 	memset(tbl->it_map, 0, sz);
 
-	/*
-	 * Reserve page 0 so it will not be used for any mappings.
-	 * This avoids buggy drivers that consider page 0 to be invalid
-	 * to crash the machine or even lose data.
-	 */
-	if (tbl->it_offset == 0)
-		set_bit(0, tbl->it_map);
+	iommu_table_reserve_pages(tbl, res_start, res_end);
 
 	/* We only split the IOMMU table if we have 1GB or more of space */
 	if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024))
@@ -726,12 +751,7 @@
 		return;
 	}
 
-	/*
-	 * In case we have reserved the first bit, we should not emit
-	 * the warning below.
-	 */
-	if (tbl->it_offset == 0)
-		clear_bit(0, tbl->it_map);
+	iommu_table_release_pages(tbl);
 
 	/* verify that table contains no entries */
 	if (!bitmap_empty(tbl->it_map, tbl->it_size))
@@ -776,7 +796,7 @@
 			  unsigned long mask, enum dma_data_direction direction,
 			  unsigned long attrs)
 {
-	dma_addr_t dma_handle = IOMMU_MAPPING_ERROR;
+	dma_addr_t dma_handle = DMA_MAPPING_ERROR;
 	void *vaddr;
 	unsigned long uaddr;
 	unsigned int npages, align;
@@ -785,9 +805,9 @@
 
 	vaddr = page_address(page) + offset;
 	uaddr = (unsigned long)vaddr;
-	npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl));
 
 	if (tbl) {
+		npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl));
 		align = 0;
 		if (tbl->it_page_shift < PAGE_SHIFT && size >= PAGE_SIZE &&
 		    ((unsigned long)vaddr & ~PAGE_MASK) == 0)
@@ -796,7 +816,7 @@
 		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
 					 mask >> tbl->it_page_shift, align,
 					 attrs);
-		if (dma_handle == IOMMU_MAPPING_ERROR) {
+		if (dma_handle == DMA_MAPPING_ERROR) {
 			if (!(attrs & DMA_ATTR_NO_WARN) &&
 			    printk_ratelimit())  {
 				dev_info(dev, "iommu_alloc failed, tbl %p "
@@ -868,7 +888,7 @@
 	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);
-	if (mapping == IOMMU_MAPPING_ERROR) {
+	if (mapping == DMA_MAPPING_ERROR) {
 		free_pages((unsigned long)ret, order);
 		return NULL;
 	}
@@ -993,25 +1013,32 @@
 }
 EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
 
-long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
-		unsigned long *hpa, enum dma_data_direction *direction)
+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 ret;
+	unsigned long size = 0;
 
-	ret = tbl->it_ops->exchange(tbl, entry, hpa, direction);
-
+	ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, false);
 	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
-			(*direction == DMA_BIDIRECTIONAL)))
+			(*direction == DMA_BIDIRECTIONAL)) &&
+			!mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift,
+					&size))
 		SetPageDirty(pfn_to_page(*hpa >> PAGE_SHIFT));
 
-	/* if (unlikely(ret))
-		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
-			__func__, hwaddr, entry << tbl->it_page_shift,
-				hwaddr, ret); */
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_xchg);
+EXPORT_SYMBOL_GPL(iommu_tce_xchg_no_kill);
+
+void iommu_tce_kill(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages)
+{
+	if (tbl->it_ops->tce_kill)
+		tbl->it_ops->tce_kill(tbl, entry, pages, false);
+}
+EXPORT_SYMBOL_GPL(iommu_tce_kill);
 
 int iommu_take_ownership(struct iommu_table *tbl)
 {
@@ -1025,22 +1052,21 @@
 	 * requires exchange() callback defined so if it is not
 	 * implemented, we disallow taking ownership over the table.
 	 */
-	if (!tbl->it_ops->exchange)
+	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(&tbl->pools[i].lock);
 
-	if (tbl->it_offset == 0)
-		clear_bit(0, tbl->it_map);
+	iommu_table_release_pages(tbl);
 
 	if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
 		pr_err("iommu_tce: it_map is not empty");
 		ret = -EBUSY;
-		/* Restore bit#0 set by iommu_init_table() */
-		if (tbl->it_offset == 0)
-			set_bit(0, tbl->it_map);
+		/* Undo iommu_table_release_pages, i.e. restore bit#0, etc */
+		iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
+				tbl->it_reserved_end);
 	} else {
 		memset(tbl->it_map, 0xff, sz);
 	}
@@ -1063,9 +1089,8 @@
 
 	memset(tbl->it_map, 0, sz);
 
-	/* Restore bit#0 set by iommu_init_table() */
-	if (tbl->it_offset == 0)
-		set_bit(0, tbl->it_map);
+	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);
@@ -1073,11 +1098,8 @@
 }
 EXPORT_SYMBOL_GPL(iommu_release_ownership);
 
-int iommu_add_device(struct device *dev)
+int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 {
-	struct iommu_table *tbl;
-	struct iommu_table_group_link *tgl;
-
 	/*
 	 * The sysfs entries should be populated before
 	 * binding IOMMU group. If sysfs entries isn't
@@ -1086,39 +1108,17 @@
 	if (!device_is_registered(dev))
 		return -ENOENT;
 
-	if (dev->iommu_group) {
+	if (device_iommu_mapped(dev)) {
 		pr_debug("%s: Skipping device %s with iommu group %d\n",
 			 __func__, dev_name(dev),
 			 iommu_group_id(dev->iommu_group));
 		return -EBUSY;
 	}
 
-	tbl = get_iommu_table_base(dev);
-	if (!tbl) {
-		pr_debug("%s: Skipping device %s with no tbl\n",
-			 __func__, dev_name(dev));
-		return 0;
-	}
-
-	tgl = list_first_entry_or_null(&tbl->it_group_list,
-			struct iommu_table_group_link, next);
-	if (!tgl) {
-		pr_debug("%s: Skipping device %s with no group\n",
-			 __func__, dev_name(dev));
-		return 0;
-	}
 	pr_debug("%s: Adding %s to iommu group %d\n",
-		 __func__, dev_name(dev),
-		 iommu_group_id(tgl->table_group->group));
+		 __func__, dev_name(dev),  iommu_group_id(table_group->group));
 
-	if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) {
-		pr_err("%s: Invalid IOMMU page size %lx (%lx) on %s\n",
-		       __func__, IOMMU_PAGE_SIZE(tbl),
-		       PAGE_SIZE, dev_name(dev));
-		return -EINVAL;
-	}
-
-	return iommu_group_add_device(tgl->table_group->group, dev);
+	return iommu_group_add_device(table_group->group, dev);
 }
 EXPORT_SYMBOL_GPL(iommu_add_device);
 
@@ -1129,7 +1129,7 @@
 	 * and we needn't detach them from the associated
 	 * IOMMU groups
 	 */
-	if (!dev->iommu_group) {
+	if (!device_iommu_mapped(dev)) {
 		pr_debug("iommu_tce: skipping device %s with no tbl\n",
 			 dev_name(dev));
 		return;
@@ -1138,31 +1138,4 @@
 	iommu_group_remove_device(dev);
 }
 EXPORT_SYMBOL_GPL(iommu_del_device);
-
-static int tce_iommu_bus_notifier(struct notifier_block *nb,
-                unsigned long action, void *data)
-{
-        struct device *dev = data;
-
-        switch (action) {
-        case BUS_NOTIFY_ADD_DEVICE:
-                return iommu_add_device(dev);
-        case BUS_NOTIFY_DEL_DEVICE:
-                if (dev->iommu_group)
-                        iommu_del_device(dev);
-                return 0;
-        default:
-                return 0;
-        }
-}
-
-static struct notifier_block tce_iommu_bus_nb = {
-        .notifier_call = tce_iommu_bus_notifier,
-};
-
-int __init tce_iommu_bus_notifier_init(void)
-{
-        bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
-        return 0;
-}
 #endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 916ddc4..5645bc9 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Derived from arch/i386/kernel/irq.c
  *    Copyright (C) 1992 Linus Torvalds
@@ -8,11 +9,6 @@
  *  Adapted for Power Macintosh by Paul Mackerras
  *    Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * This file contains the code used by various IRQ handling routines:
  * asking for different IRQ's should be done through these routines
  * instead of just grabbing them. Thus setups with different IRQ numbers
@@ -81,10 +77,7 @@
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
-int __irq_offset_value;
-
 #ifdef CONFIG_PPC32
-EXPORT_SYMBOL(__irq_offset_value);
 atomic_t ppc_n_lost_interrupts;
 
 #ifdef CONFIG_TAU_INT
@@ -261,16 +254,9 @@
 	 */
 	irq_happened = get_irq_happened();
 	if (!irq_happened) {
-		/*
-		 * FIXME. Here we'd like to be able to do:
-		 *
-		 * #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
-		 *   WARN_ON(!(mfmsr() & MSR_EE));
-		 * #endif
-		 *
-		 * But currently it hits in a few paths, we should fix those and
-		 * enable the warning.
-		 */
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+		WARN_ON_ONCE(!(mfmsr() & MSR_EE));
+#endif
 		return;
 	}
 
@@ -282,7 +268,7 @@
 	 */
 	if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
 #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
-		WARN_ON(!(mfmsr() & MSR_EE));
+		WARN_ON_ONCE(!(mfmsr() & MSR_EE));
 #endif
 		__hard_irq_disable();
 #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
@@ -293,7 +279,7 @@
 		 * warn if we are wrong. Only do that when IRQ tracing
 		 * is enabled as mfmsr() can be costly.
 		 */
-		if (WARN_ON(mfmsr() & MSR_EE))
+		if (WARN_ON_ONCE(mfmsr() & MSR_EE))
 			__hard_irq_disable();
 #endif
 	}
@@ -618,9 +604,8 @@
 	sp = current_stack_pointer() & (THREAD_SIZE-1);
 
 	/* check for stack overflow: is there less than 2KB free? */
-	if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
-		pr_err("do_IRQ: stack overflow: %ld\n",
-			sp - sizeof(struct thread_info));
+	if (unlikely(sp < 2048)) {
+		pr_err("do_IRQ: stack overflow: %ld\n", sp);
 		dump_stack();
 	}
 #endif
@@ -660,36 +645,21 @@
 void do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct thread_info *curtp, *irqtp, *sirqtp;
+	void *cursp, *irqsp, *sirqsp;
 
 	/* Switch to the irq stack to handle this */
-	curtp = current_thread_info();
-	irqtp = hardirq_ctx[raw_smp_processor_id()];
-	sirqtp = softirq_ctx[raw_smp_processor_id()];
+	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 (unlikely(curtp == irqtp || curtp == sirqtp)) {
+	if (unlikely(cursp == irqsp || cursp == sirqsp)) {
 		__do_irq(regs);
 		set_irq_regs(old_regs);
 		return;
 	}
-
-	/* Prepare the thread_info in the irq stack */
-	irqtp->task = curtp->task;
-	irqtp->flags = 0;
-
-	/* Copy the preempt_count so that the [soft]irq checks work. */
-	irqtp->preempt_count = curtp->preempt_count;
-
 	/* Switch stack and call */
-	call_do_irq(regs, irqtp);
-
-	/* Restore stack limit */
-	irqtp->task = NULL;
-
-	/* Copy back updates to the thread_info */
-	if (irqtp->flags)
-		set_bits(irqtp->flags, &curtp->flags);
+	call_do_irq(regs, irqsp);
 
 	set_irq_regs(old_regs);
 }
@@ -698,90 +668,20 @@
 {
 	if (ppc_md.init_IRQ)
 		ppc_md.init_IRQ();
-
-	exc_lvl_ctx_init();
-
-	irq_ctx_init();
 }
 
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
-struct thread_info   *critirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info    *dbgirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
-
-void exc_lvl_ctx_init(void)
-{
-	struct thread_info *tp;
-	int i, cpu_nr;
-
-	for_each_possible_cpu(i) {
-#ifdef CONFIG_PPC64
-		cpu_nr = i;
-#else
-#ifdef CONFIG_SMP
-		cpu_nr = get_hard_smp_processor_id(i);
-#else
-		cpu_nr = 0;
-#endif
+void   *critirq_ctx[NR_CPUS] __read_mostly;
+void    *dbgirq_ctx[NR_CPUS] __read_mostly;
+void *mcheckirq_ctx[NR_CPUS] __read_mostly;
 #endif
 
-		memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
-		tp = critirq_ctx[cpu_nr];
-		tp->cpu = cpu_nr;
-		tp->preempt_count = 0;
-
-#ifdef CONFIG_BOOKE
-		memset((void *)dbgirq_ctx[cpu_nr], 0, THREAD_SIZE);
-		tp = dbgirq_ctx[cpu_nr];
-		tp->cpu = cpu_nr;
-		tp->preempt_count = 0;
-
-		memset((void *)mcheckirq_ctx[cpu_nr], 0, THREAD_SIZE);
-		tp = mcheckirq_ctx[cpu_nr];
-		tp->cpu = cpu_nr;
-		tp->preempt_count = HARDIRQ_OFFSET;
-#endif
-	}
-}
-#endif
-
-struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
-
-void irq_ctx_init(void)
-{
-	struct thread_info *tp;
-	int i;
-
-	for_each_possible_cpu(i) {
-		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
-		tp = softirq_ctx[i];
-		tp->cpu = i;
-		klp_init_thread_info(tp);
-
-		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
-		tp = hardirq_ctx[i];
-		tp->cpu = i;
-		klp_init_thread_info(tp);
-	}
-}
+void *softirq_ctx[NR_CPUS] __read_mostly;
+void *hardirq_ctx[NR_CPUS] __read_mostly;
 
 void do_softirq_own_stack(void)
 {
-	struct thread_info *curtp, *irqtp;
-
-	curtp = current_thread_info();
-	irqtp = softirq_ctx[smp_processor_id()];
-	irqtp->task = curtp->task;
-	irqtp->flags = 0;
-	call_do_softirq(irqtp);
-	irqtp->task = NULL;
-
-	/* Set any flag that may have been set on the
-	 * alternate stack
-	 */
-	if (irqtp->flags)
-		set_bits(irqtp->flags, &curtp->flags);
+	call_do_softirq(softirq_ctx[smp_processor_id()]);
 }
 
 irq_hw_number_t virq_to_hw(unsigned int virq)
@@ -827,11 +727,6 @@
 }
 #endif
 
-int arch_early_irq_init(void)
-{
-	return 0;
-}
-
 #ifdef CONFIG_PPC64
 static int __init setup_noirqdistrib(char *str)
 {
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index 1df6c74..773671b 100644
--- a/arch/powerpc/kernel/isa-bridge.c
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Routines for tracking a legacy ISA bridge
  *
@@ -6,11 +7,6 @@
  * Some bits and pieces moved over from pci_64.c
  *
  * Copyrigh 2003 Anton Blanchard <anton@au.ibm.com>, IBM Corp.
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #define DEBUG
@@ -110,14 +106,14 @@
 		size = 0x10000;
 
 	__ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE,
-		     size, pgprot_val(pgprot_noncached(__pgprot(0))));
+		     size, pgprot_noncached(PAGE_KERNEL));
 	return;
 
 inval_range:
 	printk(KERN_ERR "no ISA IO ranges or unexpected isa range, "
 	       "mapping 64k\n");
 	__ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE,
-		     0x10000, pgprot_val(pgprot_noncached(__pgprot(0))));
+		     0x10000, pgprot_noncached(PAGE_KERNEL));
 }
 
 
@@ -253,7 +249,7 @@
 	 */
 	isa_io_base = ISA_IO_BASE;
 	__ioremap_at(pbase, (void *)ISA_IO_BASE,
-		     size, pgprot_val(pgprot_noncached(__pgprot(0))));
+		     size, pgprot_noncached(PAGE_KERNEL));
 
 	pr_debug("ISA: Non-PCI bridge is %pOF\n", np);
 }
@@ -327,8 +323,7 @@
 		/* Check if we have no ISA device, and this happens to be one,
 		 * register it as such if it has an OF device
 		 */
-		if (!isa_bridge_devnode && devnode && devnode->type &&
-		    !strcmp(devnode->type, "isa"))
+		if (!isa_bridge_devnode && of_node_is_type(devnode, "isa"))
 			isa_bridge_find_late(pdev, devnode);
 
 		return 0;
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
index 6472472..ca37702 100644
--- a/arch/powerpc/kernel/jump_label.c
+++ b/arch/powerpc/kernel/jump_label.c
@@ -1,17 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2010 Michael Ellerman, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
 #include <linux/jump_label.h>
 #include <asm/code-patching.h>
 
-#ifdef HAVE_JUMP_LABEL
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
@@ -22,4 +17,3 @@
 	else
 		patch_instruction(addr, PPC_INST_NOP);
 }
-#endif
diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kernel/kexec_elf_64.c
index ba4f18a..3072fd6 100644
--- a/arch/powerpc/kernel/kexec_elf_64.c
+++ b/arch/powerpc/kernel/kexec_elf_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Load ELF vmlinux file for the kexec_file_load syscall.
  *
@@ -10,15 +11,6 @@
  * Based on kexec-tools' kexec-elf-exec.c and kexec-elf-ppc64.c.
  * Heavily modified for the kernel by
  * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation (version 2 of the License).
- *
- * 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.
  */
 
 #define pr_fmt(fmt)	"kexec_elf: " fmt
@@ -31,540 +23,6 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#define PURGATORY_STACK_SIZE	(16 * 1024)
-
-#define elf_addr_to_cpu	elf64_to_cpu
-
-#ifndef Elf_Rel
-#define Elf_Rel		Elf64_Rel
-#endif /* Elf_Rel */
-
-struct elf_info {
-	/*
-	 * Where the ELF binary contents are kept.
-	 * Memory managed by the user of the struct.
-	 */
-	const char *buffer;
-
-	const struct elfhdr *ehdr;
-	const struct elf_phdr *proghdrs;
-	struct elf_shdr *sechdrs;
-};
-
-static inline bool elf_is_elf_file(const struct elfhdr *ehdr)
-{
-       return memcmp(ehdr->e_ident, ELFMAG, SELFMAG) == 0;
-}
-
-static uint64_t elf64_to_cpu(const struct elfhdr *ehdr, uint64_t value)
-{
-	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
-		value = le64_to_cpu(value);
-	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
-		value = be64_to_cpu(value);
-
-	return value;
-}
-
-static uint16_t elf16_to_cpu(const struct elfhdr *ehdr, uint16_t value)
-{
-	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
-		value = le16_to_cpu(value);
-	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
-		value = be16_to_cpu(value);
-
-	return value;
-}
-
-static uint32_t elf32_to_cpu(const struct elfhdr *ehdr, uint32_t value)
-{
-	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
-		value = le32_to_cpu(value);
-	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
-		value = be32_to_cpu(value);
-
-	return value;
-}
-
-/**
- * elf_is_ehdr_sane - check that it is safe to use the ELF header
- * @buf_len:	size of the buffer in which the ELF file is loaded.
- */
-static bool elf_is_ehdr_sane(const struct elfhdr *ehdr, size_t buf_len)
-{
-	if (ehdr->e_phnum > 0 && ehdr->e_phentsize != sizeof(struct elf_phdr)) {
-		pr_debug("Bad program header size.\n");
-		return false;
-	} else if (ehdr->e_shnum > 0 &&
-		   ehdr->e_shentsize != sizeof(struct elf_shdr)) {
-		pr_debug("Bad section header size.\n");
-		return false;
-	} else if (ehdr->e_ident[EI_VERSION] != EV_CURRENT ||
-		   ehdr->e_version != EV_CURRENT) {
-		pr_debug("Unknown ELF version.\n");
-		return false;
-	}
-
-	if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) {
-		size_t phdr_size;
-
-		/*
-		 * e_phnum is at most 65535 so calculating the size of the
-		 * program header cannot overflow.
-		 */
-		phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum;
-
-		/* Sanity check the program header table location. */
-		if (ehdr->e_phoff + phdr_size < ehdr->e_phoff) {
-			pr_debug("Program headers at invalid location.\n");
-			return false;
-		} else if (ehdr->e_phoff + phdr_size > buf_len) {
-			pr_debug("Program headers truncated.\n");
-			return false;
-		}
-	}
-
-	if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) {
-		size_t shdr_size;
-
-		/*
-		 * e_shnum is at most 65536 so calculating
-		 * the size of the section header cannot overflow.
-		 */
-		shdr_size = sizeof(struct elf_shdr) * ehdr->e_shnum;
-
-		/* Sanity check the section header table location. */
-		if (ehdr->e_shoff + shdr_size < ehdr->e_shoff) {
-			pr_debug("Section headers at invalid location.\n");
-			return false;
-		} else if (ehdr->e_shoff + shdr_size > buf_len) {
-			pr_debug("Section headers truncated.\n");
-			return false;
-		}
-	}
-
-	return true;
-}
-
-static int elf_read_ehdr(const char *buf, size_t len, struct elfhdr *ehdr)
-{
-	struct elfhdr *buf_ehdr;
-
-	if (len < sizeof(*buf_ehdr)) {
-		pr_debug("Buffer is too small to hold ELF header.\n");
-		return -ENOEXEC;
-	}
-
-	memset(ehdr, 0, sizeof(*ehdr));
-	memcpy(ehdr->e_ident, buf, sizeof(ehdr->e_ident));
-	if (!elf_is_elf_file(ehdr)) {
-		pr_debug("No ELF header magic.\n");
-		return -ENOEXEC;
-	}
-
-	if (ehdr->e_ident[EI_CLASS] != ELF_CLASS) {
-		pr_debug("Not a supported ELF class.\n");
-		return -ENOEXEC;
-	} else  if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB &&
-		ehdr->e_ident[EI_DATA] != ELFDATA2MSB) {
-		pr_debug("Not a supported ELF data format.\n");
-		return -ENOEXEC;
-	}
-
-	buf_ehdr = (struct elfhdr *) buf;
-	if (elf16_to_cpu(ehdr, buf_ehdr->e_ehsize) != sizeof(*buf_ehdr)) {
-		pr_debug("Bad ELF header size.\n");
-		return -ENOEXEC;
-	}
-
-	ehdr->e_type      = elf16_to_cpu(ehdr, buf_ehdr->e_type);
-	ehdr->e_machine   = elf16_to_cpu(ehdr, buf_ehdr->e_machine);
-	ehdr->e_version   = elf32_to_cpu(ehdr, buf_ehdr->e_version);
-	ehdr->e_entry     = elf_addr_to_cpu(ehdr, buf_ehdr->e_entry);
-	ehdr->e_phoff     = elf_addr_to_cpu(ehdr, buf_ehdr->e_phoff);
-	ehdr->e_shoff     = elf_addr_to_cpu(ehdr, buf_ehdr->e_shoff);
-	ehdr->e_flags     = elf32_to_cpu(ehdr, buf_ehdr->e_flags);
-	ehdr->e_phentsize = elf16_to_cpu(ehdr, buf_ehdr->e_phentsize);
-	ehdr->e_phnum     = elf16_to_cpu(ehdr, buf_ehdr->e_phnum);
-	ehdr->e_shentsize = elf16_to_cpu(ehdr, buf_ehdr->e_shentsize);
-	ehdr->e_shnum     = elf16_to_cpu(ehdr, buf_ehdr->e_shnum);
-	ehdr->e_shstrndx  = elf16_to_cpu(ehdr, buf_ehdr->e_shstrndx);
-
-	return elf_is_ehdr_sane(ehdr, len) ? 0 : -ENOEXEC;
-}
-
-/**
- * elf_is_phdr_sane - check that it is safe to use the program header
- * @buf_len:	size of the buffer in which the ELF file is loaded.
- */
-static bool elf_is_phdr_sane(const struct elf_phdr *phdr, size_t buf_len)
-{
-
-	if (phdr->p_offset + phdr->p_filesz < phdr->p_offset) {
-		pr_debug("ELF segment location wraps around.\n");
-		return false;
-	} else if (phdr->p_offset + phdr->p_filesz > buf_len) {
-		pr_debug("ELF segment not in file.\n");
-		return false;
-	} else if (phdr->p_paddr + phdr->p_memsz < phdr->p_paddr) {
-		pr_debug("ELF segment address wraps around.\n");
-		return false;
-	}
-
-	return true;
-}
-
-static int elf_read_phdr(const char *buf, size_t len, struct elf_info *elf_info,
-			 int idx)
-{
-	/* Override the const in proghdrs, we are the ones doing the loading. */
-	struct elf_phdr *phdr = (struct elf_phdr *) &elf_info->proghdrs[idx];
-	const char *pbuf;
-	struct elf_phdr *buf_phdr;
-
-	pbuf = buf + elf_info->ehdr->e_phoff + (idx * sizeof(*buf_phdr));
-	buf_phdr = (struct elf_phdr *) pbuf;
-
-	phdr->p_type   = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_type);
-	phdr->p_offset = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_offset);
-	phdr->p_paddr  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_paddr);
-	phdr->p_vaddr  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr);
-	phdr->p_flags  = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_flags);
-
-	/*
-	 * The following fields have a type equivalent to Elf_Addr
-	 * both in 32 bit and 64 bit ELF.
-	 */
-	phdr->p_filesz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_filesz);
-	phdr->p_memsz  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_memsz);
-	phdr->p_align  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_align);
-
-	return elf_is_phdr_sane(phdr, len) ? 0 : -ENOEXEC;
-}
-
-/**
- * elf_read_phdrs - read the program headers from the buffer
- *
- * This function assumes that the program header table was checked for sanity.
- * Use elf_is_ehdr_sane() if it wasn't.
- */
-static int elf_read_phdrs(const char *buf, size_t len,
-			  struct elf_info *elf_info)
-{
-	size_t phdr_size, i;
-	const struct elfhdr *ehdr = elf_info->ehdr;
-
-	/*
-	 * e_phnum is at most 65535 so calculating the size of the
-	 * program header cannot overflow.
-	 */
-	phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum;
-
-	elf_info->proghdrs = kzalloc(phdr_size, GFP_KERNEL);
-	if (!elf_info->proghdrs)
-		return -ENOMEM;
-
-	for (i = 0; i < ehdr->e_phnum; i++) {
-		int ret;
-
-		ret = elf_read_phdr(buf, len, elf_info, i);
-		if (ret) {
-			kfree(elf_info->proghdrs);
-			elf_info->proghdrs = NULL;
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-/**
- * elf_is_shdr_sane - check that it is safe to use the section header
- * @buf_len:	size of the buffer in which the ELF file is loaded.
- */
-static bool elf_is_shdr_sane(const struct elf_shdr *shdr, size_t buf_len)
-{
-	bool size_ok;
-
-	/* SHT_NULL headers have undefined values, so we can't check them. */
-	if (shdr->sh_type == SHT_NULL)
-		return true;
-
-	/* Now verify sh_entsize */
-	switch (shdr->sh_type) {
-	case SHT_SYMTAB:
-		size_ok = shdr->sh_entsize == sizeof(Elf_Sym);
-		break;
-	case SHT_RELA:
-		size_ok = shdr->sh_entsize == sizeof(Elf_Rela);
-		break;
-	case SHT_DYNAMIC:
-		size_ok = shdr->sh_entsize == sizeof(Elf_Dyn);
-		break;
-	case SHT_REL:
-		size_ok = shdr->sh_entsize == sizeof(Elf_Rel);
-		break;
-	case SHT_NOTE:
-	case SHT_PROGBITS:
-	case SHT_HASH:
-	case SHT_NOBITS:
-	default:
-		/*
-		 * This is a section whose entsize requirements
-		 * I don't care about.  If I don't know about
-		 * the section I can't care about it's entsize
-		 * requirements.
-		 */
-		size_ok = true;
-		break;
-	}
-
-	if (!size_ok) {
-		pr_debug("ELF section with wrong entry size.\n");
-		return false;
-	} else if (shdr->sh_addr + shdr->sh_size < shdr->sh_addr) {
-		pr_debug("ELF section address wraps around.\n");
-		return false;
-	}
-
-	if (shdr->sh_type != SHT_NOBITS) {
-		if (shdr->sh_offset + shdr->sh_size < shdr->sh_offset) {
-			pr_debug("ELF section location wraps around.\n");
-			return false;
-		} else if (shdr->sh_offset + shdr->sh_size > buf_len) {
-			pr_debug("ELF section not in file.\n");
-			return false;
-		}
-	}
-
-	return true;
-}
-
-static int elf_read_shdr(const char *buf, size_t len, struct elf_info *elf_info,
-			 int idx)
-{
-	struct elf_shdr *shdr = &elf_info->sechdrs[idx];
-	const struct elfhdr *ehdr = elf_info->ehdr;
-	const char *sbuf;
-	struct elf_shdr *buf_shdr;
-
-	sbuf = buf + ehdr->e_shoff + idx * sizeof(*buf_shdr);
-	buf_shdr = (struct elf_shdr *) sbuf;
-
-	shdr->sh_name      = elf32_to_cpu(ehdr, buf_shdr->sh_name);
-	shdr->sh_type      = elf32_to_cpu(ehdr, buf_shdr->sh_type);
-	shdr->sh_addr      = elf_addr_to_cpu(ehdr, buf_shdr->sh_addr);
-	shdr->sh_offset    = elf_addr_to_cpu(ehdr, buf_shdr->sh_offset);
-	shdr->sh_link      = elf32_to_cpu(ehdr, buf_shdr->sh_link);
-	shdr->sh_info      = elf32_to_cpu(ehdr, buf_shdr->sh_info);
-
-	/*
-	 * The following fields have a type equivalent to Elf_Addr
-	 * both in 32 bit and 64 bit ELF.
-	 */
-	shdr->sh_flags     = elf_addr_to_cpu(ehdr, buf_shdr->sh_flags);
-	shdr->sh_size      = elf_addr_to_cpu(ehdr, buf_shdr->sh_size);
-	shdr->sh_addralign = elf_addr_to_cpu(ehdr, buf_shdr->sh_addralign);
-	shdr->sh_entsize   = elf_addr_to_cpu(ehdr, buf_shdr->sh_entsize);
-
-	return elf_is_shdr_sane(shdr, len) ? 0 : -ENOEXEC;
-}
-
-/**
- * elf_read_shdrs - read the section headers from the buffer
- *
- * This function assumes that the section header table was checked for sanity.
- * Use elf_is_ehdr_sane() if it wasn't.
- */
-static int elf_read_shdrs(const char *buf, size_t len,
-			  struct elf_info *elf_info)
-{
-	size_t shdr_size, i;
-
-	/*
-	 * e_shnum is at most 65536 so calculating
-	 * the size of the section header cannot overflow.
-	 */
-	shdr_size = sizeof(struct elf_shdr) * elf_info->ehdr->e_shnum;
-
-	elf_info->sechdrs = kzalloc(shdr_size, GFP_KERNEL);
-	if (!elf_info->sechdrs)
-		return -ENOMEM;
-
-	for (i = 0; i < elf_info->ehdr->e_shnum; i++) {
-		int ret;
-
-		ret = elf_read_shdr(buf, len, elf_info, i);
-		if (ret) {
-			kfree(elf_info->sechdrs);
-			elf_info->sechdrs = NULL;
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-/**
- * elf_read_from_buffer - read ELF file and sets up ELF header and ELF info
- * @buf:	Buffer to read ELF file from.
- * @len:	Size of @buf.
- * @ehdr:	Pointer to existing struct which will be populated.
- * @elf_info:	Pointer to existing struct which will be populated.
- *
- * This function allows reading ELF files with different byte order than
- * the kernel, byte-swapping the fields as needed.
- *
- * Return:
- * On success returns 0, and the caller should call elf_free_info(elf_info) to
- * free the memory allocated for the section and program headers.
- */
-int elf_read_from_buffer(const char *buf, size_t len, struct elfhdr *ehdr,
-			 struct elf_info *elf_info)
-{
-	int ret;
-
-	ret = elf_read_ehdr(buf, len, ehdr);
-	if (ret)
-		return ret;
-
-	elf_info->buffer = buf;
-	elf_info->ehdr = ehdr;
-	if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) {
-		ret = elf_read_phdrs(buf, len, elf_info);
-		if (ret)
-			return ret;
-	}
-	if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) {
-		ret = elf_read_shdrs(buf, len, elf_info);
-		if (ret) {
-			kfree(elf_info->proghdrs);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-/**
- * elf_free_info - free memory allocated by elf_read_from_buffer
- */
-void elf_free_info(struct elf_info *elf_info)
-{
-	kfree(elf_info->proghdrs);
-	kfree(elf_info->sechdrs);
-	memset(elf_info, 0, sizeof(*elf_info));
-}
-/**
- * build_elf_exec_info - read ELF executable and check that we can use it
- */
-static int build_elf_exec_info(const char *buf, size_t len, struct elfhdr *ehdr,
-			       struct elf_info *elf_info)
-{
-	int i;
-	int ret;
-
-	ret = elf_read_from_buffer(buf, len, ehdr, elf_info);
-	if (ret)
-		return ret;
-
-	/* Big endian vmlinux has type ET_DYN. */
-	if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN) {
-		pr_err("Not an ELF executable.\n");
-		goto error;
-	} else if (!elf_info->proghdrs) {
-		pr_err("No ELF program header.\n");
-		goto error;
-	}
-
-	for (i = 0; i < ehdr->e_phnum; i++) {
-		/*
-		 * Kexec does not support loading interpreters.
-		 * In addition this check keeps us from attempting
-		 * to kexec ordinay executables.
-		 */
-		if (elf_info->proghdrs[i].p_type == PT_INTERP) {
-			pr_err("Requires an ELF interpreter.\n");
-			goto error;
-		}
-	}
-
-	return 0;
-error:
-	elf_free_info(elf_info);
-	return -ENOEXEC;
-}
-
-static int elf64_probe(const char *buf, unsigned long len)
-{
-	struct elfhdr ehdr;
-	struct elf_info elf_info;
-	int ret;
-
-	ret = build_elf_exec_info(buf, len, &ehdr, &elf_info);
-	if (ret)
-		return ret;
-
-	elf_free_info(&elf_info);
-
-	return elf_check_arch(&ehdr) ? 0 : -ENOEXEC;
-}
-
-/**
- * elf_exec_load - load ELF executable image
- * @lowest_load_addr:	On return, will be the address where the first PT_LOAD
- *			section will be loaded in memory.
- *
- * Return:
- * 0 on success, negative value on failure.
- */
-static int elf_exec_load(struct kimage *image, struct elfhdr *ehdr,
-			 struct elf_info *elf_info,
-			 unsigned long *lowest_load_addr)
-{
-	unsigned long base = 0, lowest_addr = UINT_MAX;
-	int ret;
-	size_t i;
-	struct kexec_buf kbuf = { .image = image, .buf_max = ppc64_rma_size,
-				  .top_down = false };
-
-	/* Read in the PT_LOAD segments. */
-	for (i = 0; i < ehdr->e_phnum; i++) {
-		unsigned long load_addr;
-		size_t size;
-		const struct elf_phdr *phdr;
-
-		phdr = &elf_info->proghdrs[i];
-		if (phdr->p_type != PT_LOAD)
-			continue;
-
-		size = phdr->p_filesz;
-		if (size > phdr->p_memsz)
-			size = phdr->p_memsz;
-
-		kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset;
-		kbuf.bufsz = size;
-		kbuf.memsz = phdr->p_memsz;
-		kbuf.buf_align = phdr->p_align;
-		kbuf.buf_min = phdr->p_paddr + base;
-		ret = kexec_add_buffer(&kbuf);
-		if (ret)
-			goto out;
-		load_addr = kbuf.mem;
-
-		if (load_addr < lowest_addr)
-			lowest_addr = load_addr;
-	}
-
-	/* Update entry point to reflect new load address. */
-	ehdr->e_entry += base;
-
-	*lowest_load_addr = lowest_addr;
-	ret = 0;
- out:
-	return ret;
-}
-
 static void *elf64_load(struct kimage *image, char *kernel_buf,
 			unsigned long kernel_len, char *initrd,
 			unsigned long initrd_len, char *cmdline,
@@ -577,17 +35,18 @@
 	void *fdt;
 	const void *slave_code;
 	struct elfhdr ehdr;
-	struct elf_info elf_info;
+	struct kexec_elf_info elf_info;
 	struct kexec_buf kbuf = { .image = image, .buf_min = 0,
 				  .buf_max = ppc64_rma_size };
 	struct kexec_buf pbuf = { .image = image, .buf_min = 0,
-				  .buf_max = ppc64_rma_size, .top_down = true };
+				  .buf_max = ppc64_rma_size, .top_down = true,
+				  .mem = KEXEC_BUF_MEM_UNKNOWN };
 
-	ret = build_elf_exec_info(kernel_buf, kernel_len, &ehdr, &elf_info);
+	ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info);
 	if (ret)
 		goto out;
 
-	ret = elf_exec_load(image, &ehdr, &elf_info, &kernel_load_addr);
+	ret = kexec_elf_load(image, &ehdr, &elf_info, &kbuf, &kernel_load_addr);
 	if (ret)
 		goto out;
 
@@ -606,6 +65,7 @@
 		kbuf.bufsz = kbuf.memsz = initrd_len;
 		kbuf.buf_align = PAGE_SIZE;
 		kbuf.top_down = false;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 		ret = kexec_add_buffer(&kbuf);
 		if (ret)
 			goto out;
@@ -638,6 +98,7 @@
 	kbuf.bufsz = kbuf.memsz = fdt_size;
 	kbuf.buf_align = PAGE_SIZE;
 	kbuf.top_down = true;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret)
 		goto out;
@@ -652,13 +113,13 @@
 		pr_err("Error setting up the purgatory.\n");
 
 out:
-	elf_free_info(&elf_info);
+	kexec_free_elf_info(&elf_info);
 
 	/* Make kimage_file_post_load_cleanup free the fdt buffer for us. */
 	return ret ? ERR_PTR(ret) : fdt;
 }
 
 const struct kexec_file_ops kexec_elf64_ops = {
-	.probe = elf64_probe,
+	.probe = kexec_elf_probe,
 	.load = elf64_load,
 };
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 35e240a..7dd55eb 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -24,6 +24,7 @@
 #include <asm/processor.h>
 #include <asm/machdep.h>
 #include <asm/debug.h>
+#include <asm/code-patching.h>
 #include <linux/slab.h>
 
 /*
@@ -116,14 +117,14 @@
 	return kgdb_isremovedbreak(regs->nip);
 }
 
-static int kgdb_call_nmi_hook(struct pt_regs *regs)
+static int kgdb_debugger_ipi(struct pt_regs *regs)
 {
 	kgdb_nmicallback(raw_smp_processor_id(), regs);
 	return 0;
 }
 
 #ifdef CONFIG_SMP
-void kgdb_roundup_cpus(unsigned long flags)
+void kgdb_roundup_cpus(void)
 {
 	smp_send_debugger_break();
 }
@@ -144,47 +145,19 @@
 	if (kgdb_handle_exception(1, SIGTRAP, 0, regs) != 0)
 		return 0;
 
-	if (*(u32 *) (regs->nip) == *(u32 *) (&arch_kgdb_ops.gdb_bpt_instr))
+	if (*(u32 *)regs->nip == BREAK_INSTR)
 		regs->nip += BREAK_INSTR_SIZE;
 
 	return 1;
 }
 
-static DEFINE_PER_CPU(struct thread_info, kgdb_thread_info);
 static int kgdb_singlestep(struct pt_regs *regs)
 {
-	struct thread_info *thread_info, *exception_thread_info;
-	struct thread_info *backup_current_thread_info =
-		this_cpu_ptr(&kgdb_thread_info);
-
 	if (user_mode(regs))
 		return 0;
 
-	/*
-	 * On Book E and perhaps other processors, singlestep is handled on
-	 * the critical exception stack.  This causes current_thread_info()
-	 * to fail, since it it locates the thread_info by masking off
-	 * the low bits of the current stack pointer.  We work around
-	 * this issue by copying the thread_info from the kernel stack
-	 * before calling kgdb_handle_exception, and copying it back
-	 * afterwards.  On most processors the copy is avoided since
-	 * exception_thread_info == thread_info.
-	 */
-	thread_info = (struct thread_info *)(regs->gpr[1] & ~(THREAD_SIZE-1));
-	exception_thread_info = current_thread_info();
-
-	if (thread_info != exception_thread_info) {
-		/* Save the original current_thread_info. */
-		memcpy(backup_current_thread_info, exception_thread_info, sizeof *thread_info);
-		memcpy(exception_thread_info, thread_info, sizeof *thread_info);
-	}
-
 	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 
-	if (thread_info != exception_thread_info)
-		/* Restore current_thread_info lastly. */
-		memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info);
-
 	return 1;
 }
 
@@ -441,16 +414,42 @@
 	return -1;
 }
 
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+	int err;
+	unsigned int instr;
+	unsigned int *addr = (unsigned int *)bpt->bpt_addr;
+
+	err = probe_kernel_address(addr, instr);
+	if (err)
+		return err;
+
+	err = patch_instruction(addr, BREAK_INSTR);
+	if (err)
+		return -EFAULT;
+
+	*(unsigned int *)bpt->saved_instr = instr;
+
+	return 0;
+}
+
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+	int err;
+	unsigned int instr = *(unsigned int *)bpt->saved_instr;
+	unsigned int *addr = (unsigned int *)bpt->bpt_addr;
+
+	err = patch_instruction(addr, instr);
+	if (err)
+		return -EFAULT;
+
+	return 0;
+}
+
 /*
  * Global data
  */
-struct kgdb_arch arch_kgdb_ops = {
-#ifdef __LITTLE_ENDIAN__
-	.gdb_bpt_instr = {0x08, 0x10, 0x82, 0x7d},
-#else
-	.gdb_bpt_instr = {0x7d, 0x82, 0x10, 0x08},
-#endif
-};
+const struct kgdb_arch arch_kgdb_ops;
 
 static int kgdb_not_implemented(struct pt_regs *regs)
 {
@@ -475,7 +474,7 @@
 	old__debugger_break_match = __debugger_break_match;
 	old__debugger_fault_handler = __debugger_fault_handler;
 
-	__debugger_ipi = kgdb_call_nmi_hook;
+	__debugger_ipi = kgdb_debugger_ipi;
 	__debugger = kgdb_debugger;
 	__debugger_bpt = kgdb_handle_breakpoint;
 	__debugger_sstep = kgdb_singlestep;
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index e4a49c0..972cb28 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Dynamic Ftrace based Kprobes Optimization
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright (C) Hitachi Ltd., 2012
  * Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
  *		  IBM Corporation
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 5c60bb0..2d27ec4 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Kernel Probes (KProbes)
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright (C) IBM Corporation, 2002, 2004
  *
  * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 683b5b3..617eba8 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -1,27 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
  * Copyright 2010-2011 Freescale Semiconductor, Inc.
  *
  * Authors:
  *     Alexander Graf <agraf@suse.de>
- *
- * 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.
  */
 
 #include <linux/kvm_host.h>
 #include <linux/init.h>
 #include <linux/export.h>
+#include <linux/kmemleak.h>
 #include <linux/kvm_para.h>
 #include <linux/slab.h>
 #include <linux/of.h>
@@ -75,16 +64,17 @@
 #define KVM_INST_MTSRIN		0x7c0001e4
 
 static bool kvm_patching_worked = true;
-char kvm_tmp[1024 * 1024];
+extern char kvm_tmp[];
+extern char kvm_tmp_end[];
 static int kvm_tmp_index;
 
-static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
+static void __init kvm_patch_ins(u32 *inst, u32 new_inst)
 {
 	*inst = new_inst;
 	flush_icache_range((ulong)inst, (ulong)inst + 4);
 }
 
-static void kvm_patch_ins_ll(u32 *inst, long addr, u32 rt)
+static void __init kvm_patch_ins_ll(u32 *inst, long addr, u32 rt)
 {
 #ifdef CONFIG_64BIT
 	kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc));
@@ -93,7 +83,7 @@
 #endif
 }
 
-static void kvm_patch_ins_ld(u32 *inst, long addr, u32 rt)
+static void __init kvm_patch_ins_ld(u32 *inst, long addr, u32 rt)
 {
 #ifdef CONFIG_64BIT
 	kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc));
@@ -102,12 +92,12 @@
 #endif
 }
 
-static void kvm_patch_ins_lwz(u32 *inst, long addr, u32 rt)
+static void __init kvm_patch_ins_lwz(u32 *inst, long addr, u32 rt)
 {
 	kvm_patch_ins(inst, KVM_INST_LWZ | rt | (addr & 0x0000ffff));
 }
 
-static void kvm_patch_ins_std(u32 *inst, long addr, u32 rt)
+static void __init kvm_patch_ins_std(u32 *inst, long addr, u32 rt)
 {
 #ifdef CONFIG_64BIT
 	kvm_patch_ins(inst, KVM_INST_STD | rt | (addr & 0x0000fffc));
@@ -116,17 +106,17 @@
 #endif
 }
 
-static void kvm_patch_ins_stw(u32 *inst, long addr, u32 rt)
+static void __init kvm_patch_ins_stw(u32 *inst, long addr, u32 rt)
 {
 	kvm_patch_ins(inst, KVM_INST_STW | rt | (addr & 0x0000fffc));
 }
 
-static void kvm_patch_ins_nop(u32 *inst)
+static void __init kvm_patch_ins_nop(u32 *inst)
 {
 	kvm_patch_ins(inst, KVM_INST_NOP);
 }
 
-static void kvm_patch_ins_b(u32 *inst, int addr)
+static void __init kvm_patch_ins_b(u32 *inst, int addr)
 {
 #if defined(CONFIG_RELOCATABLE) && defined(CONFIG_PPC_BOOK3S)
 	/* On relocatable kernels interrupts handlers and our code
@@ -139,11 +129,11 @@
 	kvm_patch_ins(inst, KVM_INST_B | (addr & KVM_INST_B_MASK));
 }
 
-static u32 *kvm_alloc(int len)
+static u32 * __init kvm_alloc(int len)
 {
 	u32 *p;
 
-	if ((kvm_tmp_index + len) > ARRAY_SIZE(kvm_tmp)) {
+	if ((kvm_tmp_index + len) > (kvm_tmp_end - kvm_tmp)) {
 		printk(KERN_ERR "KVM: No more space (%d + %d)\n",
 				kvm_tmp_index, len);
 		kvm_patching_worked = false;
@@ -162,7 +152,7 @@
 extern u32 kvm_emulate_mtmsrd_len;
 extern u32 kvm_emulate_mtmsrd[];
 
-static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
+static void __init kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
 {
 	u32 *p;
 	int distance_start;
@@ -215,7 +205,7 @@
 extern u32 kvm_emulate_mtmsr_len;
 extern u32 kvm_emulate_mtmsr[];
 
-static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
+static void __init kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
 {
 	u32 *p;
 	int distance_start;
@@ -276,7 +266,7 @@
 extern u32 kvm_emulate_wrtee_len;
 extern u32 kvm_emulate_wrtee[];
 
-static void kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one)
+static void __init kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one)
 {
 	u32 *p;
 	int distance_start;
@@ -333,7 +323,7 @@
 extern u32 kvm_emulate_wrteei_0_len;
 extern u32 kvm_emulate_wrteei_0[];
 
-static void kvm_patch_ins_wrteei_0(u32 *inst)
+static void __init kvm_patch_ins_wrteei_0(u32 *inst)
 {
 	u32 *p;
 	int distance_start;
@@ -374,7 +364,7 @@
 extern u32 kvm_emulate_mtsrin_len;
 extern u32 kvm_emulate_mtsrin[];
 
-static void kvm_patch_ins_mtsrin(u32 *inst, u32 rt, u32 rb)
+static void __init kvm_patch_ins_mtsrin(u32 *inst, u32 rt, u32 rb)
 {
 	u32 *p;
 	int distance_start;
@@ -410,7 +400,7 @@
 
 #endif
 
-static void kvm_map_magic_page(void *data)
+static void __init kvm_map_magic_page(void *data)
 {
 	u32 *features = data;
 
@@ -425,7 +415,7 @@
 	*features = out[0];
 }
 
-static void kvm_check_ins(u32 *inst, u32 features)
+static void __init kvm_check_ins(u32 *inst, u32 features)
 {
 	u32 _inst = *inst;
 	u32 inst_no_rt = _inst & ~KVM_MASK_RT;
@@ -669,7 +659,7 @@
 extern u32 kvm_template_start[];
 extern u32 kvm_template_end[];
 
-static void kvm_use_magic_page(void)
+static void __init kvm_use_magic_page(void)
 {
 	u32 *p;
 	u32 *start, *end;
@@ -710,19 +700,13 @@
 			 kvm_patching_worked ? "worked" : "failed");
 }
 
-static __init void kvm_free_tmp(void)
-{
-	free_reserved_area(&kvm_tmp[kvm_tmp_index],
-			   &kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL);
-}
-
 static int __init kvm_guest_init(void)
 {
 	if (!kvm_para_available())
-		goto free_tmp;
+		return 0;
 
 	if (!epapr_paravirt_enabled)
-		goto free_tmp;
+		return 0;
 
 	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
 		kvm_use_magic_page();
@@ -732,9 +716,6 @@
 	powersave_nap = 1;
 #endif
 
-free_tmp:
-	kvm_free_tmp();
-
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index c005088..7af6f8b 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2010
  * Copyright 2010-2011 Freescale Semiconductor, Inc.
@@ -203,6 +192,8 @@
 kvm_emulate_mtmsr_len:
 	.long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
 
+#ifdef CONFIG_BOOKE
+
 /* also used for wrteei 1 */
 .global kvm_emulate_wrtee
 kvm_emulate_wrtee:
@@ -296,6 +287,10 @@
 kvm_emulate_wrteei_0_len:
 	.long (kvm_emulate_wrteei_0_end - kvm_emulate_wrteei_0) / 4
 
+#endif /* CONFIG_BOOKE */
+
+#ifdef CONFIG_PPC_BOOK3S_32
+
 .global kvm_emulate_mtsrin
 kvm_emulate_mtsrin:
 
@@ -345,5 +340,15 @@
 kvm_emulate_mtsrin_len:
 	.long (kvm_emulate_mtsrin_end - kvm_emulate_mtsrin) / 4
 
+#endif /* CONFIG_PPC_BOOK3S_32 */
+
+	.balign 4
+	.global kvm_tmp
+kvm_tmp:
+	.space	(64 * 1024)
+
+.global kvm_tmp_end
+kvm_tmp_end:
+
 .global kvm_template_end
 kvm_template_end:
diff --git a/arch/powerpc/kernel/l2cr_6xx.S b/arch/powerpc/kernel/l2cr_6xx.S
index 6e7dbb7..2020d25 100644
--- a/arch/powerpc/kernel/l2cr_6xx.S
+++ b/arch/powerpc/kernel/l2cr_6xx.S
@@ -1,20 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
 	L2CR functions
 	Copyright © 1997-1998 by PowerLogix R & D, Inc.
 
-	This program is free software; you can redistribute it and/or modify
-	it under the terms of the GNU General Public License as published by
-	the Free Software Foundation; either version 2 of the License, or
-	(at your option) any later version.
-
-	This program is distributed in the hope that it will be useful,
-	but WITHOUT ANY WARRANTY; without even the implied warranty of
-	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-	GNU General Public License for more details.
-
-	You should have received a copy of the GNU General Public License
-	along with this program; if not, write to the Free Software
-	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 /*
 	Thur, Dec. 12, 1998.
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 5b9dce1..7cea597 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -192,7 +192,7 @@
 	/* Add port, irq will be dealt with later. We passed a translated
 	 * IO port value. It will be fixed up later along with the irq
 	 */
-	if (tsi && !strcmp(tsi->type, "tsi-bridge"))
+	if (of_node_is_type(tsi, "tsi-bridge"))
 		return add_legacy_port(np, -1, UPIO_TSI, addr, addr,
 				       0, legacy_port_flags, 0);
 	else
@@ -400,8 +400,7 @@
 	/* Next, fill our array with ISA ports */
 	for_each_node_by_type(np, "serial") {
 		struct device_node *isa = of_get_parent(np);
-		if (isa && (!strcmp(isa->name, "isa") ||
-			    !strcmp(isa->name, "lpc"))) {
+		if (of_node_name_eq(isa, "isa") || of_node_name_eq(isa, "lpc")) {
 			if (of_device_is_available(np)) {
 				index = add_legacy_isa_port(np, isa);
 				if (index >= 0 && np == stdout)
@@ -415,11 +414,12 @@
 	/* Next, try to locate PCI ports */
 	for (np = NULL; (np = of_find_all_nodes(np));) {
 		struct device_node *pci, *parent = of_get_parent(np);
-		if (parent && !strcmp(parent->name, "isa")) {
+		if (of_node_name_eq(parent, "isa")) {
 			of_node_put(parent);
 			continue;
 		}
-		if (strcmp(np->name, "serial") && strcmp(np->type, "serial")) {
+		if (!of_node_name_eq(np, "serial") &&
+		    !of_node_is_type(np, "serial")) {
 			of_node_put(parent);
 			continue;
 		}
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 63f5a93..c4ed328 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -1,12 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Code to handle transition of Linux booting another kernel.
  *
  * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
  * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
  * Copyright (C) 2005 IBM Corporation.
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2.  See the file COPYING for more details.
  */
 
 #include <linux/kexec.h>
diff --git a/arch/powerpc/kernel/machine_kexec_32.c b/arch/powerpc/kernel/machine_kexec_32.c
index affe5dc..bf9f1f9 100644
--- a/arch/powerpc/kernel/machine_kexec_32.c
+++ b/arch/powerpc/kernel/machine_kexec_32.c
@@ -1,12 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * PPC32 code to handle Linux booting another kernel.
  *
  * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
  * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
  * Copyright (C) 2005 IBM Corporation.
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2.  See the file COPYING for more details.
  */
 
 #include <linux/kexec.h>
@@ -30,7 +28,6 @@
  */
 void default_machine_kexec(struct kimage *image)
 {
-	extern const unsigned char relocate_new_kernel[];
 	extern const unsigned int relocate_new_kernel_size;
 	unsigned long page_list;
 	unsigned long reboot_code_buffer, reboot_code_buffer_phys;
@@ -58,6 +55,9 @@
 				reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
 	printk(KERN_INFO "Bye!\n");
 
+	if (!IS_ENABLED(CONFIG_FSL_BOOKE) && !IS_ENABLED(CONFIG_44x))
+		relocate_new_kernel(page_list, reboot_code_buffer_phys, image->start);
+
 	/* now call it */
 	rnk = (relocate_new_kernel_t) reboot_code_buffer;
 	(*rnk)(page_list, reboot_code_buffer_phys, image->start);
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index a0f6f45..04a7cba 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -1,12 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * PPC64 code to handle Linux booting another kernel.
  *
  * Copyright (C) 2004-2005, IBM Corp.
  *
  * Created by: Milton D Miller II
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2.  See the file COPYING for more details.
  */
 
 
@@ -31,6 +29,8 @@
 #include <asm/smp.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/asm-prototypes.h>
+#include <asm/svm.h>
+#include <asm/ultravisor.h>
 
 int default_machine_kexec_prepare(struct kimage *image)
 {
@@ -317,10 +317,8 @@
 	 * We setup preempt_count to avoid using VMX in memcpy.
 	 * XXX: the task struct will likely be invalid once we do the copy!
 	 */
-	kexec_stack.thread_info.task = current_thread_info()->task;
-	kexec_stack.thread_info.flags = 0;
-	kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
-	kexec_stack.thread_info.cpu = current_thread_info()->cpu;
+	current_thread_info()->flags = 0;
+	current_thread_info()->preempt_count = HARDIRQ_OFFSET;
 
 	/* We need a static PACA, too; copy this CPU's PACA over and switch to
 	 * it. Also poison per_cpu_offset and NULL lppaca to catch anyone using
@@ -331,6 +329,13 @@
 #ifdef CONFIG_PPC_PSERIES
 	kexec_paca.lppaca_ptr = NULL;
 #endif
+
+	if (is_secure_guest() && !(image->preserve_context ||
+				   image->type == KEXEC_TYPE_CRASH)) {
+		uv_unshare_all_pages();
+		printk("kexec: Unshared all shared pages.\n");
+	}
+
 	paca_ptrs[kexec_paca.paca_index] = &kexec_paca;
 
 	setup_paca(&kexec_paca);
diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c
index c77e95e..143c917 100644
--- a/arch/powerpc/kernel/machine_kexec_file_64.c
+++ b/arch/powerpc/kernel/machine_kexec_file_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * ppc64 code to implement the kexec_file_load syscall
  *
@@ -11,20 +12,10 @@
  * Based on kexec-tools' kexec-elf-ppc64.c, fs2dt.c.
  * Heavily modified for the kernel by
  * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation (version 2 of the License).
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/slab.h>
 #include <linux/kexec.h>
-#include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
 #include <asm/ima.h>
@@ -47,59 +38,6 @@
 }
 
 /**
- * arch_kexec_walk_mem - call func(data) for each unreserved memory block
- * @kbuf:	Context info for the search. Also passed to @func.
- * @func:	Function to call for each memory block.
- *
- * This function is used by kexec_add_buffer and kexec_locate_mem_hole
- * to find unreserved memory to load kexec segments into.
- *
- * Return: The memory walk will stop when func returns a non-zero value
- * and that value will be returned. If all free regions are visited without
- * func returning non-zero, then zero will be returned.
- */
-int arch_kexec_walk_mem(struct kexec_buf *kbuf,
-			int (*func)(struct resource *, void *))
-{
-	int ret = 0;
-	u64 i;
-	phys_addr_t mstart, mend;
-	struct resource res = { };
-
-	if (kbuf->top_down) {
-		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0,
-						&mstart, &mend, NULL) {
-			/*
-			 * In memblock, end points to the first byte after the
-			 * range while in kexec, end points to the last byte
-			 * in the range.
-			 */
-			res.start = mstart;
-			res.end = mend - 1;
-			ret = func(&res, kbuf);
-			if (ret)
-				break;
-		}
-	} else {
-		for_each_free_mem_range(i, NUMA_NO_NODE, 0, &mstart, &mend,
-					NULL) {
-			/*
-			 * In memblock, end points to the first byte after the
-			 * range while in kexec, end points to the last byte
-			 * in the range.
-			 */
-			res.start = mstart;
-			res.end = mend - 1;
-			ret = func(&res, kbuf);
-			if (ret)
-				break;
-		}
-	}
-
-	return ret;
-}
-
-/**
  * setup_purgatory - initialize the purgatory's global variables
  * @image:		kexec image.
  * @slave_code:		Slave code for the purgatory.
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index efdd16a..34c1001 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Machine check exception handling.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright 2013 IBM Corporation
  * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
  */
@@ -31,6 +18,7 @@
 
 #include <asm/machdep.h>
 #include <asm/mce.h>
+#include <asm/nmi.h>
 
 static DEFINE_PER_CPU(int, mce_nest_count);
 static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
@@ -45,13 +33,18 @@
 					mce_ue_event_queue);
 
 static void machine_check_process_queued_event(struct irq_work *work);
-void machine_check_ue_event(struct machine_check_event *evt);
+static void machine_check_ue_irq_work(struct irq_work *work);
+static void machine_check_ue_event(struct machine_check_event *evt);
 static void machine_process_ue_event(struct work_struct *work);
 
 static struct irq_work mce_event_process_work = {
         .func = machine_check_process_queued_event,
 };
 
+static struct irq_work mce_ue_event_irq_work = {
+	.func = machine_check_ue_irq_work,
+};
+
 DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
 
 static void mce_set_error_info(struct machine_check_event *mce,
@@ -111,6 +104,7 @@
 	mce->srr1 = regs->msr;
 	mce->gpr3 = regs->gpr[3];
 	mce->in_use = 1;
+	mce->cpu = get_paca()->paca_index;
 
 	/* Mark it recovered if we have handled it and MSR(RI=1). */
 	if (handled && (regs->msr & MSR_RI))
@@ -120,6 +114,8 @@
 
 	mce->initiator = mce_err->initiator;
 	mce->severity = mce_err->severity;
+	mce->sync_error = mce_err->sync_error;
+	mce->error_class = mce_err->error_class;
 
 	/*
 	 * Populate the mce error_type and type-specific error_type.
@@ -153,6 +149,7 @@
 		if (phys_addr != ULONG_MAX) {
 			mce->u.ue_error.physical_address_provided = true;
 			mce->u.ue_error.physical_address = phys_addr;
+			mce->u.ue_error.ignore_event = mce_err->ignore_event;
 			machine_check_ue_event(mce);
 		}
 	}
@@ -208,11 +205,15 @@
 	get_mce_event(NULL, true);
 }
 
+static void machine_check_ue_irq_work(struct irq_work *work)
+{
+	schedule_work(&mce_ue_event_work);
+}
 
 /*
  * Queue up the MCE event which then can be handled later.
  */
-void machine_check_ue_event(struct machine_check_event *evt)
+static void machine_check_ue_event(struct machine_check_event *evt)
 {
 	int index;
 
@@ -225,7 +226,7 @@
 	memcpy(this_cpu_ptr(&mce_ue_event_queue[index]), evt, sizeof(*evt));
 
 	/* Queue work to process this event later. */
-	schedule_work(&mce_ue_event_work);
+	irq_work_queue(&mce_ue_event_irq_work);
 }
 
 /*
@@ -266,8 +267,17 @@
 		/*
 		 * This should probably queued elsewhere, but
 		 * oh! well
+		 *
+		 * Don't report this machine check because the caller has a
+		 * asked us to ignore the event, it has a fixup handler which
+		 * will do the appropriate error handling and reporting.
 		 */
 		if (evt->error_type == MCE_ERROR_TYPE_UE) {
+			if (evt->u.ue_error.ignore_event) {
+				__this_cpu_dec(mce_ue_count);
+				continue;
+			}
+
 			if (evt->u.ue_error.physical_address_provided) {
 				unsigned long pfn;
 
@@ -301,15 +311,25 @@
 	while (__this_cpu_read(mce_queue_count) > 0) {
 		index = __this_cpu_read(mce_queue_count) - 1;
 		evt = this_cpu_ptr(&mce_event_queue[index]);
-		machine_check_print_event_info(evt, false);
+
+		if (evt->error_type == MCE_ERROR_TYPE_UE &&
+		    evt->u.ue_error.ignore_event) {
+			__this_cpu_dec(mce_queue_count);
+			continue;
+		}
+		machine_check_print_event_info(evt, false, false);
 		__this_cpu_dec(mce_queue_count);
 	}
 }
 
 void machine_check_print_event_info(struct machine_check_event *evt,
-				    bool user_mode)
+				    bool user_mode, bool in_guest)
 {
-	const char *level, *sevstr, *subtype;
+	const char *level, *sevstr, *subtype, *err_type, *initiator;
+	uint64_t ea = 0, pa = 0;
+	int n = 0;
+	char dar_str[50];
+	char pa_str[50];
 	static const char *mc_ue_types[] = {
 		"Indeterminate",
 		"Instruction fetch",
@@ -356,6 +376,13 @@
 		"Store (timeout)",
 		"Page table walk Load/Store (timeout)",
 	};
+	static const char *mc_error_class[] = {
+		"Unknown",
+		"Hardware error",
+		"Probable Hardware error (some chance of software cause)",
+		"Software error",
+		"Probable Software error (some chance of hardware cause)",
+	};
 
 	/* Print things out */
 	if (evt->version != MCE_V1) {
@@ -370,9 +397,9 @@
 		break;
 	case MCE_SEV_WARNING:
 		level = KERN_WARNING;
-		sevstr = "";
+		sevstr = "Warning";
 		break;
-	case MCE_SEV_ERROR_SYNC:
+	case MCE_SEV_SEVERE:
 		level = KERN_ERR;
 		sevstr = "Severe";
 		break;
@@ -383,99 +410,145 @@
 		break;
 	}
 
-	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
-	       evt->disposition == MCE_DISPOSITION_RECOVERED ?
-	       "Recovered" : "Not recovered");
-
-	if (user_mode) {
-		printk("%s  NIP: [%016llx] PID: %d Comm: %s\n", level,
-			evt->srr0, current->pid, current->comm);
-	} else {
-		printk("%s  NIP [%016llx]: %pS\n", level, evt->srr0,
-		       (void *)evt->srr0);
+	switch(evt->initiator) {
+	case MCE_INITIATOR_CPU:
+		initiator = "CPU";
+		break;
+	case MCE_INITIATOR_PCI:
+		initiator = "PCI";
+		break;
+	case MCE_INITIATOR_ISA:
+		initiator = "ISA";
+		break;
+	case MCE_INITIATOR_MEMORY:
+		initiator = "Memory";
+		break;
+	case MCE_INITIATOR_POWERMGM:
+		initiator = "Power Management";
+		break;
+	case MCE_INITIATOR_UNKNOWN:
+	default:
+		initiator = "Unknown";
+		break;
 	}
 
-	printk("%s  Initiator: %s\n", level,
-	       evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
 	switch (evt->error_type) {
 	case MCE_ERROR_TYPE_UE:
+		err_type = "UE";
 		subtype = evt->u.ue_error.ue_error_type <
 			ARRAY_SIZE(mc_ue_types) ?
 			mc_ue_types[evt->u.ue_error.ue_error_type]
 			: "Unknown";
-		printk("%s  Error type: UE [%s]\n", level, subtype);
 		if (evt->u.ue_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt->u.ue_error.effective_address);
+			ea = evt->u.ue_error.effective_address;
 		if (evt->u.ue_error.physical_address_provided)
-			printk("%s    Physical address:  %016llx\n",
-			       level, evt->u.ue_error.physical_address);
+			pa = evt->u.ue_error.physical_address;
 		break;
 	case MCE_ERROR_TYPE_SLB:
+		err_type = "SLB";
 		subtype = evt->u.slb_error.slb_error_type <
 			ARRAY_SIZE(mc_slb_types) ?
 			mc_slb_types[evt->u.slb_error.slb_error_type]
 			: "Unknown";
-		printk("%s  Error type: SLB [%s]\n", level, subtype);
 		if (evt->u.slb_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt->u.slb_error.effective_address);
+			ea = evt->u.slb_error.effective_address;
 		break;
 	case MCE_ERROR_TYPE_ERAT:
+		err_type = "ERAT";
 		subtype = evt->u.erat_error.erat_error_type <
 			ARRAY_SIZE(mc_erat_types) ?
 			mc_erat_types[evt->u.erat_error.erat_error_type]
 			: "Unknown";
-		printk("%s  Error type: ERAT [%s]\n", level, subtype);
 		if (evt->u.erat_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt->u.erat_error.effective_address);
+			ea = evt->u.erat_error.effective_address;
 		break;
 	case MCE_ERROR_TYPE_TLB:
+		err_type = "TLB";
 		subtype = evt->u.tlb_error.tlb_error_type <
 			ARRAY_SIZE(mc_tlb_types) ?
 			mc_tlb_types[evt->u.tlb_error.tlb_error_type]
 			: "Unknown";
-		printk("%s  Error type: TLB [%s]\n", level, subtype);
 		if (evt->u.tlb_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt->u.tlb_error.effective_address);
+			ea = evt->u.tlb_error.effective_address;
 		break;
 	case MCE_ERROR_TYPE_USER:
+		err_type = "User";
 		subtype = evt->u.user_error.user_error_type <
 			ARRAY_SIZE(mc_user_types) ?
 			mc_user_types[evt->u.user_error.user_error_type]
 			: "Unknown";
-		printk("%s  Error type: User [%s]\n", level, subtype);
 		if (evt->u.user_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt->u.user_error.effective_address);
+			ea = evt->u.user_error.effective_address;
 		break;
 	case MCE_ERROR_TYPE_RA:
+		err_type = "Real address";
 		subtype = evt->u.ra_error.ra_error_type <
 			ARRAY_SIZE(mc_ra_types) ?
 			mc_ra_types[evt->u.ra_error.ra_error_type]
 			: "Unknown";
-		printk("%s  Error type: Real address [%s]\n", level, subtype);
 		if (evt->u.ra_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt->u.ra_error.effective_address);
+			ea = evt->u.ra_error.effective_address;
 		break;
 	case MCE_ERROR_TYPE_LINK:
+		err_type = "Link";
 		subtype = evt->u.link_error.link_error_type <
 			ARRAY_SIZE(mc_link_types) ?
 			mc_link_types[evt->u.link_error.link_error_type]
 			: "Unknown";
-		printk("%s  Error type: Link [%s]\n", level, subtype);
 		if (evt->u.link_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt->u.link_error.effective_address);
+			ea = evt->u.link_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_DCACHE:
+		err_type = "D-Cache";
+		subtype = "Unknown";
+		break;
+	case MCE_ERROR_TYPE_ICACHE:
+		err_type = "I-Cache";
+		subtype = "Unknown";
 		break;
 	default:
 	case MCE_ERROR_TYPE_UNKNOWN:
-		printk("%s  Error type: Unknown\n", level);
+		err_type = "Unknown";
+		subtype = "";
 		break;
 	}
+
+	dar_str[0] = pa_str[0] = '\0';
+	if (ea && evt->srr0 != ea) {
+		/* Load/Store address */
+		n = sprintf(dar_str, "DAR: %016llx ", ea);
+		if (pa)
+			sprintf(dar_str + n, "paddr: %016llx ", pa);
+	} else if (pa) {
+		sprintf(pa_str, " paddr: %016llx", pa);
+	}
+
+	printk("%sMCE: CPU%d: machine check (%s) %s %s %s %s[%s]\n",
+		level, evt->cpu, sevstr, in_guest ? "Guest" : "Host",
+		err_type, subtype, dar_str,
+		evt->disposition == MCE_DISPOSITION_RECOVERED ?
+		"Recovered" : "Not recovered");
+
+	if (in_guest || user_mode) {
+		printk("%sMCE: CPU%d: PID: %d Comm: %s %sNIP: [%016llx]%s\n",
+			level, evt->cpu, current->pid, current->comm,
+			in_guest ? "Guest " : "", evt->srr0, pa_str);
+	} else {
+		printk("%sMCE: CPU%d: NIP: [%016llx] %pS%s\n",
+			level, evt->cpu, evt->srr0, (void *)evt->srr0, pa_str);
+	}
+
+	printk("%sMCE: CPU%d: Initiator %s\n", level, evt->cpu, initiator);
+
+	subtype = evt->error_class < ARRAY_SIZE(mc_error_class) ?
+		mc_error_class[evt->error_class] : "Unknown";
+	printk("%sMCE: CPU%d: %s\n", level, evt->cpu, subtype);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* Display faulty slb contents for SLB errors. */
+	if (evt->error_type == MCE_ERROR_TYPE_SLB)
+		slb_dump_contents(local_paca->mce_faulty_slbs);
+#endif
 }
 EXPORT_SYMBOL_GPL(machine_check_print_event_info);
 
@@ -488,10 +561,13 @@
 {
 	long handled = 0;
 
-	__this_cpu_inc(irq_stat.mce_exceptions);
+	hv_nmi_check_nonrecoverable(regs);
 
-	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
-		handled = cur_cpu_spec->machine_check_early(regs);
+	/*
+	 * See if platform is capable of handling machine check.
+	 */
+	if (ppc_md.machine_check_early)
+		handled = ppc_md.machine_check_early(regs);
 	return handled;
 }
 
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 3022d67..1cbf7f1 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Machine check exception handling CPU-side for power7 and power8
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright 2013 IBM Corporation
  * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
  */
@@ -24,6 +11,7 @@
 
 #include <linux/types.h>
 #include <linux/ptrace.h>
+#include <linux/extable.h>
 #include <asm/mmu.h>
 #include <asm/mce.h>
 #include <asm/machdep.h>
@@ -31,15 +19,17 @@
 #include <asm/pte-walk.h>
 #include <asm/sstep.h>
 #include <asm/exception-64s.h>
+#include <asm/extable.h>
 
 /*
  * Convert an address related to an mm to a PFN. NOTE: we are in real
  * mode, we could potentially race with page table updates.
  */
-static unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
+unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
 {
 	pte_t *ptep;
-	unsigned long flags;
+	unsigned int shift;
+	unsigned long pfn, flags;
 	struct mm_struct *mm;
 
 	if (user_mode(regs))
@@ -48,19 +38,28 @@
 		mm = &init_mm;
 
 	local_irq_save(flags);
-	if (mm == current->mm)
-		ptep = find_current_mm_pte(mm->pgd, addr, NULL, NULL);
-	else
-		ptep = find_init_mm_pte(addr, NULL);
+	ptep = __find_linux_pte(mm->pgd, addr, NULL, &shift);
+
+	if (!ptep || pte_special(*ptep)) {
+		pfn = ULONG_MAX;
+		goto out;
+	}
+
+	if (shift <= PAGE_SHIFT)
+		pfn = pte_pfn(*ptep);
+	else {
+		unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
+		pfn = pte_pfn(__pte(pte_val(*ptep) | (addr & rpnmask)));
+	}
+
+out:
 	local_irq_restore(flags);
-	if (!ptep || pte_special(*ptep))
-		return ULONG_MAX;
-	return pte_pfn(*ptep);
+	return pfn;
 }
 
 /* flush SLBs and reload */
 #ifdef CONFIG_PPC_BOOK3S_64
-static void flush_and_reload_slb(void)
+void flush_and_reload_slb(void)
 {
 	/* Invalidate all SLBs */
 	slb_flush_all_realmode();
@@ -95,8 +94,7 @@
 		return;
 	}
 #endif
-	/* PPC_INVALIDATE_ERAT can only be used on ISA v3 and newer */
-	asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
+	asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
 }
 
 #define MCE_FLUSH_SLB 1
@@ -131,215 +129,234 @@
 	bool nip_valid; /* nip is a valid indicator of faulting address */
 	unsigned int error_type;
 	unsigned int error_subtype;
+	unsigned int error_class;
 	unsigned int initiator;
 	unsigned int severity;
+	bool sync_error;
 };
 
 static const struct mce_ierror_table mce_p7_ierror_table[] = {
 { 0x00000000001c0000, 0x0000000000040000, true,
-  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000001c0000, 0x0000000000080000, true,
-  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000001c0000, 0x00000000000c0000, true,
-  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_WARNING, true },
 { 0x00000000001c0000, 0x0000000000100000, true,
   MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_WARNING, true },
 { 0x00000000001c0000, 0x0000000000140000, true,
-  MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_WARNING, true },
 { 0x00000000001c0000, 0x0000000000180000, true,
-  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000001c0000, 0x00000000001c0000, true,
-  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
-{ 0, 0, 0, 0, 0, 0 } };
+  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
+{ 0, 0, 0, 0, 0, 0, 0 } };
 
 static const struct mce_ierror_table mce_p8_ierror_table[] = {
 { 0x00000000081c0000, 0x0000000000040000, true,
-  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x0000000000080000, true,
-  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x00000000000c0000, true,
-  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_WARNING, true },
 { 0x00000000081c0000, 0x0000000000100000, true,
-  MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_WARNING, true },
 { 0x00000000081c0000, 0x0000000000140000, true,
-  MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_WARNING, true },
 { 0x00000000081c0000, 0x0000000000180000, true,
   MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x00000000001c0000, true,
-  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x0000000008000000, true,
-  MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_IFETCH_TIMEOUT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_IFETCH_TIMEOUT, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x0000000008040000, true,
   MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
-{ 0, 0, 0, 0, 0, 0 } };
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
+{ 0, 0, 0, 0, 0, 0, 0 } };
 
 static const struct mce_ierror_table mce_p9_ierror_table[] = {
 { 0x00000000081c0000, 0x0000000000040000, true,
-  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x0000000000080000, true,
-  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x00000000000c0000, true,
-  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_WARNING, true },
 { 0x00000000081c0000, 0x0000000000100000, true,
-  MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_WARNING, true },
 { 0x00000000081c0000, 0x0000000000140000, true,
-  MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,  MCE_SEV_WARNING, true },
 { 0x00000000081c0000, 0x0000000000180000, true,
-  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x00000000001c0000, true,
-  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_IFETCH_FOREIGN,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_IFETCH_FOREIGN, MCE_ECLASS_SOFTWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x0000000008000000, true,
-  MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_IFETCH_TIMEOUT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_IFETCH_TIMEOUT, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x0000000008040000, true,
   MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x00000000080c0000, true,
-  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_IFETCH, MCE_ECLASS_SOFTWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x0000000008100000, true,
-  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_SOFTWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
 { 0x00000000081c0000, 0x0000000008140000, false,
-  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_STORE,
-  MCE_INITIATOR_CPU,  MCE_SEV_FATAL, }, /* ASYNC is fatal */
+  MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_STORE, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,  MCE_SEV_FATAL, false }, /* ASYNC is fatal */
 { 0x00000000081c0000, 0x0000000008180000, false,
   MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_STORE_TIMEOUT,
-  MCE_INITIATOR_CPU,  MCE_SEV_FATAL, }, /* ASYNC is fatal */
-{ 0x00000000081c0000, 0x00000000081c0000, true,
+  MCE_INITIATOR_CPU,  MCE_SEV_FATAL, false }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x00000000081c0000, true, MCE_ECLASS_HARDWARE,
   MCE_ERROR_TYPE_RA,  MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN,
-  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
-{ 0, 0, 0, 0, 0, 0 } };
+  MCE_INITIATOR_CPU,  MCE_SEV_SEVERE, true },
+{ 0, 0, 0, 0, 0, 0, 0 } };
 
 struct mce_derror_table {
 	unsigned long dsisr_value;
 	bool dar_valid; /* dar is a valid indicator of faulting address */
 	unsigned int error_type;
 	unsigned int error_subtype;
+	unsigned int error_class;
 	unsigned int initiator;
 	unsigned int severity;
+	bool sync_error;
 };
 
 static const struct mce_derror_table mce_p7_derror_table[] = {
 { 0x00008000, false,
-  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_LOAD_STORE,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00004000, true,
   MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00000800, true,
-  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000400, true,
-  MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000080, true,
-  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,	/* Before PARITY */
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000100, true,
-  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00000040, true,
   MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
-{ 0, false, 0, 0, 0, 0 } };
+  MCE_ECLASS_HARD_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
+{ 0, false, 0, 0, 0, 0, 0 } };
 
 static const struct mce_derror_table mce_p8_derror_table[] = {
 { 0x00008000, false,
-  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_LOAD_STORE,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00004000, true,
   MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00002000, true,
-  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00001000, true,
   MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00000800, true,
-  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000400, true,
-  MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000200, true,
   MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, /* SECONDARY ERAT */
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000080, true,
   MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,	/* Before PARITY */
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000100, true,
-  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
-{ 0, false, 0, 0, 0, 0 } };
+  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
+{ 0, false, 0, 0, 0, 0, 0 } };
 
 static const struct mce_derror_table mce_p9_derror_table[] = {
 { 0x00008000, false,
-  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_LOAD_STORE,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00004000, true,
   MCE_ERROR_TYPE_UE,   MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00002000, true,
-  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00001000, true,
   MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00000800, true,
-  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000400, true,
-  MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000200, false,
-  MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE, MCE_ECLASS_SOFTWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000080, true,
   MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,	/* Before PARITY */
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_SOFT_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_WARNING, true },
 { 0x00000100, true,
-  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00000040, true,
-  MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_LOAD,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_LOAD, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00000020, false,
   MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00000010, false,
   MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
+  MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0x00000008, false,
-  MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_LOAD_STORE_FOREIGN,
-  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
-{ 0, false, 0, 0, 0, 0 } };
+  MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_LOAD_STORE_FOREIGN, MCE_ECLASS_HARDWARE,
+  MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
+{ 0, false, 0, 0, 0, 0, 0 } };
 
-static int mce_find_instr_ea_and_pfn(struct pt_regs *regs, uint64_t *addr,
+static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr,
 					uint64_t *phys_addr)
 {
 	/*
@@ -392,6 +409,8 @@
 		/* attempt to correct the error */
 		switch (table[i].error_type) {
 		case MCE_ERROR_TYPE_SLB:
+			if (local_paca->in_mce == 1)
+				slb_save_contents(local_paca->mce_faulty_slbs);
 			handled = mce_flush(MCE_FLUSH_SLB);
 			break;
 		case MCE_ERROR_TYPE_ERAT:
@@ -404,6 +423,7 @@
 
 		/* now fill in mce_error_info */
 		mce_err->error_type = table[i].error_type;
+		mce_err->error_class = table[i].error_class;
 		switch (table[i].error_type) {
 		case MCE_ERROR_TYPE_UE:
 			mce_err->u.ue_error_type = table[i].error_subtype;
@@ -427,11 +447,12 @@
 			mce_err->u.link_error_type = table[i].error_subtype;
 			break;
 		}
+		mce_err->sync_error = table[i].sync_error;
 		mce_err->severity = table[i].severity;
 		mce_err->initiator = table[i].initiator;
 		if (table[i].nip_valid) {
 			*addr = regs->nip;
-			if (mce_err->severity == MCE_SEV_ERROR_SYNC &&
+			if (mce_err->sync_error &&
 				table[i].error_type == MCE_ERROR_TYPE_UE) {
 				unsigned long pfn;
 
@@ -448,8 +469,10 @@
 	}
 
 	mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
-	mce_err->severity = MCE_SEV_ERROR_SYNC;
+	mce_err->error_class = MCE_ECLASS_UNKNOWN;
+	mce_err->severity = MCE_SEV_SEVERE;
 	mce_err->initiator = MCE_INITIATOR_CPU;
+	mce_err->sync_error = true;
 
 	return 0;
 }
@@ -473,6 +496,8 @@
 		/* attempt to correct the error */
 		switch (table[i].error_type) {
 		case MCE_ERROR_TYPE_SLB:
+			if (local_paca->in_mce == 1)
+				slb_save_contents(local_paca->mce_faulty_slbs);
 			if (mce_flush(MCE_FLUSH_SLB))
 				handled = 1;
 			break;
@@ -496,6 +521,7 @@
 
 		/* now fill in mce_error_info */
 		mce_err->error_type = table[i].error_type;
+		mce_err->error_class = table[i].error_class;
 		switch (table[i].error_type) {
 		case MCE_ERROR_TYPE_UE:
 			mce_err->u.ue_error_type = table[i].error_subtype;
@@ -519,18 +545,20 @@
 			mce_err->u.link_error_type = table[i].error_subtype;
 			break;
 		}
+		mce_err->sync_error = table[i].sync_error;
 		mce_err->severity = table[i].severity;
 		mce_err->initiator = table[i].initiator;
 		if (table[i].dar_valid)
 			*addr = regs->dar;
-		else if (mce_err->severity == MCE_SEV_ERROR_SYNC &&
+		else if (mce_err->sync_error &&
 				table[i].error_type == MCE_ERROR_TYPE_UE) {
 			/*
 			 * We do a maximum of 4 nested MCE calls, see
 			 * kernel/exception-64s.h
 			 */
 			if (get_paca()->in_mce < MAX_MCE_DEPTH)
-				mce_find_instr_ea_and_pfn(regs, addr, phys_addr);
+				mce_find_instr_ea_and_phys(regs, addr,
+							   phys_addr);
 		}
 		found = 1;
 	}
@@ -539,15 +567,26 @@
 		return handled;
 
 	mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
-	mce_err->severity = MCE_SEV_ERROR_SYNC;
+	mce_err->error_class = MCE_ECLASS_UNKNOWN;
+	mce_err->severity = MCE_SEV_SEVERE;
 	mce_err->initiator = MCE_INITIATOR_CPU;
+	mce_err->sync_error = true;
 
 	return 0;
 }
 
-static long mce_handle_ue_error(struct pt_regs *regs)
+static long mce_handle_ue_error(struct pt_regs *regs,
+				struct mce_error_info *mce_err)
 {
 	long handled = 0;
+	const struct exception_table_entry *entry;
+
+	entry = search_kernel_exception_table(regs->nip);
+	if (entry) {
+		mce_err->ignore_event = true;
+		regs->nip = extable_fixup(entry);
+		return 1;
+	}
 
 	/*
 	 * On specific SCOM read via MMIO we may get a machine check
@@ -580,7 +619,7 @@
 				&phys_addr);
 
 	if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE)
-		handled = mce_handle_ue_error(regs);
+		handled = mce_handle_ue_error(regs, &mce_err);
 
 	save_mce_event(regs, handled, &mce_err, regs->nip, addr, phys_addr);
 
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 0b196cd..974f65f 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains miscellaneous low-level functions.
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -8,11 +9,6 @@
  * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
  *
  * setjmp/longjmp code by Paul Mackerras.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc_asm.h>
 #include <asm/unistd.h>
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 695b24a..82df4b0 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains miscellaneous low-level functions.
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -10,12 +11,6 @@
  * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
  * PPC44x port. Copyright (C) 2011,  IBM Corporation
  * 		Author: Suzuki Poulose <suzuki@in.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/sys.h>
@@ -46,11 +41,10 @@
 	mflr	r0
 	stw	r0,4(r1)
 	lwz	r10,THREAD+KSP_LIMIT(r2)
-	addi	r11,r3,THREAD_INFO_GAP
+	stw	r3, THREAD+KSP_LIMIT(r2)
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
 	mr	r1,r3
 	stw	r10,8(r1)
-	stw	r11,THREAD+KSP_LIMIT(r2)
 	bl	__do_softirq
 	lwz	r10,8(r1)
 	lwz	r1,0(r1)
@@ -60,17 +54,16 @@
 	blr
 
 /*
- * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
+ * void call_do_irq(struct pt_regs *regs, void *sp);
  */
 _GLOBAL(call_do_irq)
 	mflr	r0
 	stw	r0,4(r1)
 	lwz	r10,THREAD+KSP_LIMIT(r2)
-	addi	r11,r4,THREAD_INFO_GAP
+	stw	r4, THREAD+KSP_LIMIT(r2)
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
 	mr	r1,r4
 	stw	r10,8(r1)
-	stw	r11,THREAD+KSP_LIMIT(r2)
 	bl	__do_irq
 	lwz	r10,8(r1)
 	lwz	r1,0(r1)
@@ -153,7 +146,7 @@
 	mtctr	r5
 	bctr
 
-#if defined(CONFIG_CPU_FREQ_PMAC) && defined(CONFIG_6xx)
+#if defined(CONFIG_CPU_FREQ_PMAC) && defined(CONFIG_PPC_BOOK3S_32)
 
 /* This gets called by via-pmu.c to switch the PLL selection
  * on 750fx CPU. This function should really be moved to some
@@ -183,10 +176,13 @@
 	or	r4,r4,r5
 	mtspr	SPRN_HID1,r4
 
+#ifdef CONFIG_SMP
 	/* Store new HID1 image */
-	CURRENT_THREAD_INFO(r6, r1)
-	lwz	r6,TI_CPU(r6)
+	lwz	r6,TASK_CPU(r2)
 	slwi	r6,r6,2
+#else
+	li	r6, 0
+#endif
 	addis	r6,r6,nap_save_hid1@ha
 	stw	r4,nap_save_hid1@l(r6)
 
@@ -223,7 +219,7 @@
 	mtmsr	r7
 	blr
 
-#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_6xx */
+#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_PPC_BOOK3S_32 */
 
 /*
  * complement mask on the msr then "or" some values on.
@@ -296,22 +292,20 @@
 	iccci	0,r3
 #endif
 #elif defined(CONFIG_FSL_BOOKE)
-BEGIN_FTR_SECTION
+#ifdef CONFIG_E200
 	mfspr   r3,SPRN_L1CSR0
 	ori     r3,r3,L1CSR0_CFI|L1CSR0_CLFC
 	/* msync; isync recommended here */
 	mtspr   SPRN_L1CSR0,r3
 	isync
 	blr
-END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE)
+#endif
 	mfspr	r3,SPRN_L1CSR1
 	ori	r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR
 	mtspr	SPRN_L1CSR1,r3
+#elif defined(CONFIG_PPC_BOOK3S_601)
+	blr			/* for 601, do nothing */
 #else
-	mfspr	r3,SPRN_PVR
-	rlwinm	r3,r3,16,16,31
-	cmpwi	0,r3,1
-	beqlr			/* for 601, do nothing */
 	/* 603/604 processor - use invalidate-all bit in HID0 */
 	mfspr	r3,SPRN_HID0
 	ori	r3,r3,HID0_ICFI
@@ -330,10 +324,10 @@
  * flush_icache_range(unsigned long start, unsigned long stop)
  */
 _GLOBAL(flush_icache_range)
-BEGIN_FTR_SECTION
+#if defined(CONFIG_PPC_BOOK3S_601) || defined(CONFIG_E200)
 	PURGE_PREFETCHED_INS
-	blr				/* for 601, do nothing */
-END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
+	blr				/* for 601 and e200, do nothing */
+#else
 	rlwinm	r3,r3,0,0,31 - L1_CACHE_SHIFT
 	subf	r4,r3,r4
 	addi	r4,r4,L1_CACHE_BYTES - 1
@@ -359,6 +353,7 @@
 	sync				/* additional sync needed on g4 */
 	isync
 	blr
+#endif
 _ASM_NOKPROBE_SYMBOL(flush_icache_range)
 EXPORT_SYMBOL(flush_icache_range)
 
@@ -366,15 +361,15 @@
  * Flush a particular page from the data cache to RAM.
  * Note: this is necessary because the instruction cache does *not*
  * snoop from the data cache.
- * This is a no-op on the 601 which has a unified cache.
+ * This is a no-op on the 601 and e200 which have a unified cache.
  *
  *	void __flush_dcache_icache(void *page)
  */
 _GLOBAL(__flush_dcache_icache)
-BEGIN_FTR_SECTION
+#if defined(CONFIG_PPC_BOOK3S_601) || defined(CONFIG_E200)
 	PURGE_PREFETCHED_INS
 	blr
-END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
+#else
 	rlwinm	r3,r3,0,0,31-PAGE_SHIFT		/* Get page base address */
 	li	r4,PAGE_SIZE/L1_CACHE_BYTES	/* Number of lines in a page */
 	mtctr	r4
@@ -402,6 +397,7 @@
 	sync
 	isync
 	blr
+#endif
 
 #ifndef CONFIG_BOOKE
 /*
@@ -413,10 +409,10 @@
  *	void __flush_dcache_icache_phys(unsigned long physaddr)
  */
 _GLOBAL(__flush_dcache_icache_phys)
-BEGIN_FTR_SECTION
+#if defined(CONFIG_PPC_BOOK3S_601) || defined(CONFIG_E200)
 	PURGE_PREFETCHED_INS
-	blr					/* for 601, do nothing */
-END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
+	blr					/* for 601 and e200, do nothing */
+#else
 	mfmsr	r10
 	rlwinm	r0,r10,0,28,26			/* clear DR */
 	mtmsr	r0
@@ -437,6 +433,7 @@
 	mtmsr	r10				/* restore DR */
 	isync
 	blr
+#endif
 #endif /* CONFIG_BOOKE */
 
 /*
@@ -456,7 +453,12 @@
 	stwu	r9,16(r3)
 
 _GLOBAL(copy_page)
+	rlwinm	r5, r3, 0, L1_CACHE_BYTES - 1
 	addi	r3,r3,-4
+
+0:	twnei	r5, 0	/* WARN if r3 is not cache aligned */
+	EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
+
 	addi	r4,r4,-4
 
 	li	r5,4
@@ -599,7 +601,7 @@
 #ifdef CONFIG_SMP
 _GLOBAL(start_secondary_resume)
 	/* Reset stack */
-	CURRENT_THREAD_INFO(r1, r1)
+	rlwinm	r1, r1, 0, 0, 31 - THREAD_SHIFT
 	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
 	li	r3,0
 	stw	r3,0(r1)		/* Zero the stack frame pointer	*/
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 262ba94..b55a7b4 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains miscellaneous low-level functions.
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -6,12 +7,6 @@
  * and Paul Mackerras.
  * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
  * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/sys.h>
@@ -115,58 +110,6 @@
 EXPORT_SYMBOL(flush_icache_range)
 
 /*
- * Like above, but only do the D-cache.
- *
- * flush_dcache_range(unsigned long start, unsigned long stop)
- *
- *    flush all bytes from start to stop-1 inclusive
- */
-_GLOBAL_TOC(flush_dcache_range)
-
-/*
- * Flush the data cache to memory 
- * 
- * Different systems have different cache line sizes
- */
- 	ld	r10,PPC64_CACHES@toc(r2)
-	lwz	r7,DCACHEL1BLOCKSIZE(r10)	/* Get dcache block size */
-	addi	r5,r7,-1
-	andc	r6,r3,r5		/* round low to line bdy */
-	subf	r8,r6,r4		/* compute length */
-	add	r8,r8,r5		/* ensure we get enough */
-	lwz	r9,DCACHEL1LOGBLOCKSIZE(r10)	/* Get log-2 of dcache block size */
-	srw.	r8,r8,r9		/* compute line count */
-	beqlr				/* nothing to do? */
-	mtctr	r8
-0:	dcbst	0,r6
-	add	r6,r6,r7
-	bdnz	0b
-	sync
-	blr
-EXPORT_SYMBOL(flush_dcache_range)
-
-_GLOBAL(flush_inval_dcache_range)
- 	ld	r10,PPC64_CACHES@toc(r2)
-	lwz	r7,DCACHEL1BLOCKSIZE(r10)	/* Get dcache block size */
-	addi	r5,r7,-1
-	andc	r6,r3,r5		/* round low to line bdy */
-	subf	r8,r6,r4		/* compute length */
-	add	r8,r8,r5		/* ensure we get enough */
-	lwz	r9,DCACHEL1LOGBLOCKSIZE(r10)/* Get log-2 of dcache block size */
-	srw.	r8,r8,r9		/* compute line count */
-	beqlr				/* nothing to do? */
-	sync
-	isync
-	mtctr	r8
-0:	dcbf	0,r6
-	add	r6,r6,r7
-	bdnz	0b
-	sync
-	isync
-	blr
-
-
-/*
  * Flush a particular page from the data cache to RAM.
  * Note: this is necessary because the instruction cache does *not*
  * snoop from the data cache.
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index 2d861a3..df649ac 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*  Kernel module help for powerpc.
     Copyright (C) 2001, 2003 Rusty Russell IBM Corporation.
     Copyright (C) 2008 Freescale Semiconductor, Inc.
 
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with this program; if not, write to the Free Software
-    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
 #include <linux/elf.h>
 #include <linux/moduleloader.h>
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 88d8377..d7134c6 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*  Kernel module help for PPC.
     Copyright (C) 2001 Rusty Russell.
 
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with this program; if not, write to the Free Software
-    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -172,10 +160,12 @@
 
 static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
 {
-	if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16)
-	    && entry->jump[1] == 0x398c0000 + (val & 0xffff))
-		return 1;
-	return 0;
+	if (entry->jump[0] != (PPC_INST_ADDIS | __PPC_RT(R12) | PPC_HA(val)))
+		return 0;
+	if (entry->jump[1] != (PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12) |
+			       PPC_LO(val)))
+		return 0;
+	return 1;
 }
 
 /* Set up a trampoline in the PLT to bounce us to the distant function */
@@ -200,10 +190,16 @@
 		entry++;
 	}
 
-	entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */
-	entry->jump[1] = 0x398c0000 + (val&0xffff);     /* addi r12,r12,sym@l*/
-	entry->jump[2] = 0x7d8903a6;                    /* mtctr r12 */
-	entry->jump[3] = 0x4e800420;			/* bctr */
+	/*
+	 * lis r12, sym@ha
+	 * addi r12, r12, sym@l
+	 * mtctr r12
+	 * bctr
+	 */
+	entry->jump[0] = PPC_INST_ADDIS | __PPC_RT(R12) | PPC_HA(val);
+	entry->jump[1] = PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12) | PPC_LO(val);
+	entry->jump[2] = PPC_INST_MTCTR | __PPC_RS(R12);
+	entry->jump[3] = PPC_INST_BCTR;
 
 	pr_debug("Initialized plt for 0x%x at %p\n", val, entry);
 	return (uint32_t)entry;
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 8661eea..007606a 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*  Kernel module help for PPC64.
     Copyright (C) 2001, 2003 Rusty Russell IBM 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; either version 2 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with this program; if not, write to the Free Software
-    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -133,20 +121,27 @@
  * the stub, but it's significantly shorter to put these values at the
  * end of the stub code, and patch the stub address (32-bits relative
  * to the TOC ptr, r2) into the stub.
+ *
+ * addis   r11,r2, <high>
+ * addi    r11,r11, <low>
+ * std     r2,R2_STACK_OFFSET(r1)
+ * ld      r12,32(r11)
+ * ld      r2,40(r11)
+ * mtctr   r12
+ * bctr
  */
-
 static u32 ppc64_stub_insns[] = {
-	0x3d620000,			/* addis   r11,r2, <high> */
-	0x396b0000,			/* addi    r11,r11, <low> */
+	PPC_INST_ADDIS | __PPC_RT(R11) | __PPC_RA(R2),
+	PPC_INST_ADDI | __PPC_RT(R11) | __PPC_RA(R11),
 	/* Save current r2 value in magic place on the stack. */
-	0xf8410000|R2_STACK_OFFSET,	/* std     r2,R2_STACK_OFFSET(r1) */
-	0xe98b0020,			/* ld      r12,32(r11) */
+	PPC_INST_STD | __PPC_RS(R2) | __PPC_RA(R1) | R2_STACK_OFFSET,
+	PPC_INST_LD | __PPC_RT(R12) | __PPC_RA(R11) | 32,
 #ifdef PPC64_ELF_ABI_v1
 	/* Set up new r2 from function descriptor */
-	0xe84b0028,			/* ld      r2,40(r11) */
+	PPC_INST_LD | __PPC_RT(R2) | __PPC_RA(R11) | 40,
 #endif
-	0x7d8903a6,			/* mtctr   r12 */
-	0x4e800420			/* bctr */
+	PPC_INST_MTCTR | __PPC_RS(R12),
+	PPC_INST_BCTR,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -400,13 +395,6 @@
 	return (sechdrs[me->arch.toc_section].sh_addr & ~0xfful) + 0x8000;
 }
 
-/* Both low and high 16 bits are added as SIGNED additions, so if low
-   16 bits has high bit set, high 16 bits must be adjusted.  These
-   macros do that (stolen from binutils). */
-#define PPC_LO(v) ((v) & 0xffff)
-#define PPC_HI(v) (((v) >> 16) & 0xffff)
-#define PPC_HA(v) PPC_HI ((v) + 0x8000)
-
 /* Patch stub to reference function and correct r2 value. */
 static inline int create_stub(const Elf64_Shdr *sechdrs,
 			      struct ppc64_stub_entry *entry,
@@ -711,18 +699,21 @@
 		         *	ld r2, ...(r12)
 			 *	add r2, r2, r12
 			 */
-			if ((((uint32_t *)location)[0] & ~0xfffc)
-			    != 0xe84c0000)
+			if ((((uint32_t *)location)[0] & ~0xfffc) !=
+			    (PPC_INST_LD | __PPC_RT(R2) | __PPC_RA(R12)))
 				break;
-			if (((uint32_t *)location)[1] != 0x7c426214)
+			if (((uint32_t *)location)[1] !=
+			    (PPC_INST_ADD | __PPC_RT(R2) | __PPC_RA(R2) | __PPC_RB(R12)))
 				break;
 			/*
 			 * If found, replace it with:
 			 *	addis r2, r12, (.TOC.-func)@ha
-			 *	addi r2, r12, (.TOC.-func)@l
+			 *	addi  r2,  r2, (.TOC.-func)@l
 			 */
-			((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value);
-			((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value);
+			((uint32_t *)location)[0] = PPC_INST_ADDIS | __PPC_RT(R2) |
+						    __PPC_RA(R12) | PPC_HA(value);
+			((uint32_t *)location)[1] = PPC_INST_ADDI | __PPC_RT(R2) |
+						    __PPC_RA(R2) | PPC_LO(value);
 			break;
 
 		case R_PPC64_REL16_HA:
@@ -776,12 +767,19 @@
 {
 	struct ppc64_stub_entry *entry;
 	unsigned int i, num_stubs;
+	/*
+	 * ld      r12,PACATOC(r13)
+	 * addis   r12,r12,<high>
+	 * addi    r12,r12,<low>
+	 * mtctr   r12
+	 * bctr
+	 */
 	static u32 stub_insns[] = {
-		0xe98d0000 | PACATOC, 	/* ld      r12,PACATOC(r13)	*/
-		0x3d8c0000,		/* addis   r12,r12,<high>	*/
-		0x398c0000, 		/* addi    r12,r12,<low>	*/
-		0x7d8903a6, 		/* mtctr   r12			*/
-		0x4e800420, 		/* bctr				*/
+		PPC_INST_LD | __PPC_RT(R12) | __PPC_RA(R13) | PACATOC,
+		PPC_INST_ADDIS | __PPC_RT(R12) | __PPC_RA(R12),
+		PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12),
+		PPC_INST_MTCTR | __PPC_RS(R12),
+		PPC_INST_BCTR,
 	};
 	long reladdr;
 
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
index f219765..a5d25be 100644
--- a/arch/powerpc/kernel/msi.c
+++ b/arch/powerpc/kernel/msi.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2006-2007, Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/kernel/note.S b/arch/powerpc/kernel/note.S
new file mode 100644
index 0000000..bcdad15
--- /dev/null
+++ b/arch/powerpc/kernel/note.S
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PowerPC ELF notes.
+ *
+ * Copyright 2019, IBM Corporation
+ */
+
+#include <linux/elfnote.h>
+#include <asm/elfnote.h>
+
+/*
+ * Ultravisor-capable bit (PowerNV only).
+ *
+ * Bit 0 indicates that the powerpc kernel binary knows how to run in an
+ * ultravisor-enabled system.
+ *
+ * In an ultravisor-enabled system, some machine resources are now controlled
+ * by the ultravisor. If the kernel is not ultravisor-capable, but it ends up
+ * being run on a machine with ultravisor, the kernel will probably crash
+ * trying to access ultravisor resources. For instance, it may crash in early
+ * boot trying to set the partition table entry 0.
+ *
+ * In an ultravisor-enabled system, a bootloader could warn the user or prevent
+ * the kernel from being run if the PowerPC ultravisor capability doesn't exist
+ * or the Ultravisor-capable bit is not set.
+ */
+#ifdef CONFIG_PPC_POWERNV
+#define PPCCAP_ULTRAVISOR_BIT		(1 << 0)
+#else
+#define PPCCAP_ULTRAVISOR_BIT		0
+#endif
+
+/*
+ * Add the PowerPC Capabilities in the binary ELF note. It is a bitmap that
+ * can be used to advertise kernel capabilities to userland.
+ */
+#define PPC_CAPABILITIES_BITMAP (PPCCAP_ULTRAVISOR_BIT)
+
+ELFNOTE(PowerPC, PPC_ELFNOTE_CAPABILITIES,
+	.long PPC_CAPABILITIES_BITMAP)
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 22e9d28..fb4f610 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -1,18 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  c 2001 PPC 64 Team, IBM Corp
  *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- *
  * /dev/nvram driver for PPC64
- *
- * This perhaps should live in drivers/char
- *
- * TODO: Split the /dev/nvram part (that one can use
- *       drivers/char/generic_nvram.c) from the arch & partition
- *       parsing code.
  */
 
 #include <linux/types.h>
@@ -563,8 +553,6 @@
 	nvram_pstore_info.buf = oops_data;
 	nvram_pstore_info.bufsize = oops_data_sz;
 
-	spin_lock_init(&nvram_pstore_info.buf_lock);
-
 	rc = pstore_register(&nvram_pstore_info);
 	if (rc && (rc != -EPERM))
 		/* Print error only when pstore.backend == nvram */
@@ -716,136 +704,6 @@
 	spin_unlock_irqrestore(&lock, flags);
 }
 
-static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin)
-{
-	if (ppc_md.nvram_size == NULL)
-		return -ENODEV;
-	return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE,
-					ppc_md.nvram_size());
-}
-
-
-static ssize_t dev_nvram_read(struct file *file, char __user *buf,
-			  size_t count, loff_t *ppos)
-{
-	ssize_t ret;
-	char *tmp = NULL;
-	ssize_t size;
-
-	if (!ppc_md.nvram_size) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	size = ppc_md.nvram_size();
-	if (size < 0) {
-		ret = size;
-		goto out;
-	}
-
-	if (*ppos >= size) {
-		ret = 0;
-		goto out;
-	}
-
-	count = min_t(size_t, count, size - *ppos);
-	count = min(count, PAGE_SIZE);
-
-	tmp = kmalloc(count, GFP_KERNEL);
-	if (!tmp) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	ret = ppc_md.nvram_read(tmp, count, ppos);
-	if (ret <= 0)
-		goto out;
-
-	if (copy_to_user(buf, tmp, ret))
-		ret = -EFAULT;
-
-out:
-	kfree(tmp);
-	return ret;
-
-}
-
-static ssize_t dev_nvram_write(struct file *file, const char __user *buf,
-			  size_t count, loff_t *ppos)
-{
-	ssize_t ret;
-	char *tmp = NULL;
-	ssize_t size;
-
-	ret = -ENODEV;
-	if (!ppc_md.nvram_size)
-		goto out;
-
-	ret = 0;
-	size = ppc_md.nvram_size();
-	if (*ppos >= size || size < 0)
-		goto out;
-
-	count = min_t(size_t, count, size - *ppos);
-	count = min(count, PAGE_SIZE);
-
-	tmp = memdup_user(buf, count);
-	if (IS_ERR(tmp)) {
-		ret = PTR_ERR(tmp);
-		goto out;
-	}
-
-	ret = ppc_md.nvram_write(tmp, count, ppos);
-
-	kfree(tmp);
-out:
-	return ret;
-}
-
-static long dev_nvram_ioctl(struct file *file, unsigned int cmd,
-			    unsigned long arg)
-{
-	switch(cmd) {
-#ifdef CONFIG_PPC_PMAC
-	case OBSOLETE_PMAC_NVRAM_GET_OFFSET:
-		printk(KERN_WARNING "nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n");
-	case IOC_NVRAM_GET_OFFSET: {
-		int part, offset;
-
-		if (!machine_is(powermac))
-			return -EINVAL;
-		if (copy_from_user(&part, (void __user*)arg, sizeof(part)) != 0)
-			return -EFAULT;
-		if (part < pmac_nvram_OF || part > pmac_nvram_NR)
-			return -EINVAL;
-		offset = pmac_get_partition(part);
-		if (offset < 0)
-			return offset;
-		if (copy_to_user((void __user*)arg, &offset, sizeof(offset)) != 0)
-			return -EFAULT;
-		return 0;
-	}
-#endif /* CONFIG_PPC_PMAC */
-	default:
-		return -EINVAL;
-	}
-}
-
-static const struct file_operations nvram_fops = {
-	.owner		= THIS_MODULE,
-	.llseek		= dev_nvram_llseek,
-	.read		= dev_nvram_read,
-	.write		= dev_nvram_write,
-	.unlocked_ioctl	= dev_nvram_ioctl,
-};
-
-static struct miscdevice nvram_dev = {
-	NVRAM_MINOR,
-	"nvram",
-	&nvram_fops
-};
-
-
 #ifdef DEBUG_NVRAM
 static void __init nvram_print_partitions(char * label)
 {
@@ -993,6 +851,8 @@
 	long size = 0;
 	int rc;
 
+	BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16);
+
 	/* Convert sizes from bytes to blocks */
 	req_size = _ALIGN_UP(req_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
 	min_size = _ALIGN_UP(min_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
@@ -1193,22 +1053,3 @@
 	kfree(header);
 	return err;
 }
-
-static int __init nvram_init(void)
-{
-	int rc;
-	
-	BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16);
-
-	if (ppc_md.nvram_size == NULL || ppc_md.nvram_size() <= 0)
-		return  -ENODEV;
-
-  	rc = misc_register(&nvram_dev);
-	if (rc != 0) {
-		printk(KERN_ERR "nvram_init: failed to register device\n");
-		return rc;
-	}
-  	
-  	return rc;
-}
-device_initcall(nvram_init);
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index becaec9..427fc22 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *    Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp.
  *			 <benh@kernel.crashing.org>
  *    and		 Arnd Bergmann, IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
index 8237884..024f7aa 100644
--- a/arch/powerpc/kernel/optprobes.c
+++ b/arch/powerpc/kernel/optprobes.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Code for Kernel probes Jump optimization.
  *
  * Copyright 2017, Anju T, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kprobes.h>
diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S
index 98a3aee..cf38352 100644
--- a/arch/powerpc/kernel/optprobes_head.S
+++ b/arch/powerpc/kernel/optprobes_head.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Code to prepare detour buffer for optprobes in Kernel.
  *
  * Copyright 2017, Anju T, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 0ee3e6d..949eceb 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -1,22 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * c 2001 PPC 64 Team, IBM Corp
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <linux/smp.h>
 #include <linux/export.h>
 #include <linux/memblock.h>
 #include <linux/sched/task.h>
+#include <linux/numa.h>
 
 #include <asm/lppaca.h>
 #include <asm/paca.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
 #include <asm/kexec.h>
+#include <asm/svm.h>
+#include <asm/ultravisor.h>
 
 #include "setup.h"
 
@@ -27,7 +26,7 @@
 static void *__init alloc_paca_data(unsigned long size, unsigned long align,
 				unsigned long limit, int cpu)
 {
-	unsigned long pa;
+	void *ptr;
 	int nid;
 
 	/*
@@ -36,27 +35,62 @@
 	 * which will put its paca in the right place.
 	 */
 	if (cpu == boot_cpuid) {
-		nid = -1;
+		nid = NUMA_NO_NODE;
 		memblock_set_bottom_up(true);
 	} else {
 		nid = early_cpu_to_node(cpu);
 	}
 
-	pa = memblock_alloc_base_nid(size, align, limit, nid, MEMBLOCK_NONE);
-	if (!pa) {
-		pa = memblock_alloc_base(size, align, limit);
-		if (!pa)
-			panic("cannot allocate paca data");
-	}
+	ptr = memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
+				     limit, nid);
+	if (!ptr)
+		panic("cannot allocate paca data");
 
 	if (cpu == boot_cpuid)
 		memblock_set_bottom_up(false);
 
-	return __va(pa);
+	return ptr;
 }
 
 #ifdef CONFIG_PPC_PSERIES
 
+#define LPPACA_SIZE 0x400
+
+static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align,
+					unsigned long limit, int cpu)
+{
+	size_t shared_lppaca_total_size = PAGE_ALIGN(nr_cpu_ids * LPPACA_SIZE);
+	static unsigned long shared_lppaca_size;
+	static void *shared_lppaca;
+	void *ptr;
+
+	if (!shared_lppaca) {
+		memblock_set_bottom_up(true);
+
+		shared_lppaca =
+			memblock_alloc_try_nid(shared_lppaca_total_size,
+					       PAGE_SIZE, MEMBLOCK_LOW_LIMIT,
+					       limit, NUMA_NO_NODE);
+		if (!shared_lppaca)
+			panic("cannot allocate shared data");
+
+		memblock_set_bottom_up(false);
+		uv_share_page(PHYS_PFN(__pa(shared_lppaca)),
+			      shared_lppaca_total_size >> PAGE_SHIFT);
+	}
+
+	ptr = shared_lppaca + shared_lppaca_size;
+	shared_lppaca_size += size;
+
+	/*
+	 * This is very early in boot, so no harm done if the kernel crashes at
+	 * this point.
+	 */
+	BUG_ON(shared_lppaca_size >= shared_lppaca_total_size);
+
+	return ptr;
+}
+
 /*
  * See asm/lppaca.h for more detail.
  *
@@ -70,7 +104,7 @@
 
 	*lppaca = (struct lppaca) {
 		.desc = cpu_to_be32(0xd397d781),	/* "LpPa" */
-		.size = cpu_to_be16(0x400),
+		.size = cpu_to_be16(LPPACA_SIZE),
 		.fpregs_in_use = 1,
 		.slb_count = cpu_to_be16(64),
 		.vmxregs_in_use = 0,
@@ -80,19 +114,22 @@
 static struct lppaca * __init new_lppaca(int cpu, unsigned long limit)
 {
 	struct lppaca *lp;
-	size_t size = 0x400;
 
-	BUILD_BUG_ON(size < sizeof(struct lppaca));
+	BUILD_BUG_ON(sizeof(struct lppaca) > LPPACA_SIZE);
 
 	if (early_cpu_has_feature(CPU_FTR_HVMODE))
 		return NULL;
 
-	lp = alloc_paca_data(size, 0x400, limit, cpu);
+	if (is_secure_guest())
+		lp = alloc_shared_lppaca(LPPACA_SIZE, 0x400, limit, cpu);
+	else
+		lp = alloc_paca_data(LPPACA_SIZE, 0x400, limit, cpu);
+
 	init_lppaca(lp);
 
 	return lp;
 }
-#endif /* CONFIG_PPC_BOOK3S */
+#endif /* CONFIG_PPC_PSERIES */
 
 #ifdef CONFIG_PPC_BOOK3S_64
 
@@ -118,7 +155,6 @@
 	}
 
 	s = alloc_paca_data(sizeof(*s), L1_CACHE_BYTES, limit, cpu);
-	memset(s, 0, sizeof(*s));
 
 	s->persistent = cpu_to_be32(SLB_NUM_BOLTED);
 	s->buffer_length = cpu_to_be32(sizeof(*s));
@@ -198,7 +234,11 @@
 	paca_nr_cpu_ids = nr_cpu_ids;
 
 	paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
-	paca_ptrs = __va(memblock_alloc(paca_ptrs_size, 0));
+	paca_ptrs = memblock_alloc_raw(paca_ptrs_size, SMP_CACHE_BYTES);
+	if (!paca_ptrs)
+		panic("Failed to allocate %d bytes for paca pointers\n",
+		      paca_ptrs_size);
+
 	memset(paca_ptrs, 0x88, paca_ptrs_size);
 }
 
@@ -222,7 +262,6 @@
 	paca = alloc_paca_data(sizeof(struct paca_struct), L1_CACHE_BYTES,
 				limit, cpu);
 	paca_ptrs[cpu] = paca;
-	memset(paca, 0, sizeof(struct paca_struct));
 
 	initialise_paca(paca, cpu);
 #ifdef CONFIG_PPC_PSERIES
@@ -266,12 +305,12 @@
 
 	get_paca()->mm_ctx_id = context->id;
 #ifdef CONFIG_PPC_MM_SLICES
-	VM_BUG_ON(!mm->context.slb_addr_limit);
-	get_paca()->mm_ctx_slb_addr_limit = mm->context.slb_addr_limit;
-	memcpy(&get_paca()->mm_ctx_low_slices_psize,
-	       &context->low_slices_psize, sizeof(context->low_slices_psize));
-	memcpy(&get_paca()->mm_ctx_high_slices_psize,
-	       &context->high_slices_psize, TASK_SLICE_ARRAY_SZ(mm));
+	VM_BUG_ON(!mm_ctx_slb_addr_limit(context));
+	get_paca()->mm_ctx_slb_addr_limit = mm_ctx_slb_addr_limit(context);
+	memcpy(&get_paca()->mm_ctx_low_slices_psize, mm_ctx_low_slices(context),
+	       LOW_SLICE_ARRAY_SZ);
+	memcpy(&get_paca()->mm_ctx_high_slices_psize, mm_ctx_high_slices(context),
+	       TASK_SLICE_ARRAY_SZ(context));
 #else /* CONFIG_PPC_MM_SLICES */
 	get_paca()->mm_ctx_user_psize = context->user_psize;
 	get_paca()->mm_ctx_sllp = context->sllp;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 88e4f69..1c448cf 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Contains common pci routines for ALL ppc platform
  * (based on pci_32.c and pci_64.c)
@@ -9,11 +10,6 @@
  *   Rework, based on alpha PCI code.
  *
  * Common pmac/prep/chrp pci routines. -- Cort
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -32,6 +28,7 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/vgaarb.h>
+#include <linux/numa.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -62,19 +59,13 @@
 EXPORT_SYMBOL(isa_mem_base);
 
 
-static const struct dma_map_ops *pci_dma_ops = &dma_nommu_ops;
+static const struct dma_map_ops *pci_dma_ops;
 
 void set_pci_dma_ops(const struct dma_map_ops *dma_ops)
 {
 	pci_dma_ops = dma_ops;
 }
 
-const struct dma_map_ops *get_pci_dma_ops(void)
-{
-	return pci_dma_ops;
-}
-EXPORT_SYMBOL(get_pci_dma_ops);
-
 /*
  * This function should run under locking protection, specifically
  * hose_spinlock.
@@ -132,7 +123,7 @@
 		int nid = of_node_to_nid(dev);
 
 		if (nid < 0 || !node_online(nid))
-			nid = -1;
+			nid = NUMA_NO_NODE;
 
 		PHB_SET_NODE(phb, nid);
 	}
@@ -357,6 +348,17 @@
 	return NULL;
 }
 
+struct pci_controller *pci_find_controller_for_domain(int domain_nr)
+{
+	struct pci_controller *hose;
+
+	list_for_each_entry(hose, &hose_list, list_node)
+		if (hose->global_number == domain_nr)
+			return hose;
+
+	return NULL;
+}
+
 /*
  * Reads the interrupt pin to determine if interrupt is use by card.
  * If the interrupt is used, then gets the interrupt line from the
@@ -972,7 +974,7 @@
 
 	/* Hook up default DMA ops */
 	set_dma_ops(&dev->dev, pci_dma_ops);
-	set_dma_offset(&dev->dev, PCI_DRAM_OFFSET);
+	dev->dev.archdata.dma_offset = PCI_DRAM_OFFSET;
 
 	/* Additional platform DMA/iommu setup */
 	phb = pci_bus_to_host(dev->bus);
@@ -1377,10 +1379,6 @@
 		pr_debug("PCI: Assigning unassigned resources...\n");
 		pci_assign_unassigned_resources();
 	}
-
-	/* Call machine dependent fixup */
-	if (ppc_md.pcibios_fixup)
-		ppc_md.pcibios_fixup();
 }
 
 /* This is used by the PCI hotplug driver to allocate resource
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index cf47b1a..fc62c4b 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Derived from "arch/powerpc/platforms/pseries/pci_dlpar.c"
  *
@@ -7,11 +8,6 @@
  * Updates, 2005, John Rose <johnrose@austin.ibm.com>
  * Updates, 2005, Linas Vepstas <linas@austin.ibm.com>
  * Updates, 2013, Gavin Shan <shangw@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/pci.h>
@@ -59,11 +55,18 @@
 void pcibios_release_device(struct pci_dev *dev)
 {
 	struct pci_controller *phb = pci_bus_to_host(dev->bus);
+	struct pci_dn *pdn = pci_get_pdn(dev);
 
 	eeh_remove_device(dev);
 
 	if (phb->controller_ops.release_device)
 		phb->controller_ops.release_device(dev);
+
+	/* free()ing the pci_dn has been deferred to us, do it now */
+	if (pdn && (pdn->flags & PCI_DN_FLAG_DEAD)) {
+		pci_dbg(dev, "freeing dead pdn\n");
+		kfree(pdn);
+	}
 }
 
 /**
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index d63b488..b49e106 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Common pmac/prep/chrp pci routines. -- Cort
  */
@@ -10,14 +11,13 @@
 #include <linux/capability.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/syscalls.h>
 #include <linux/irq.h>
 #include <linux/list.h>
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/export.h>
-#include <linux/syscalls.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -204,7 +204,11 @@
 	struct property* of_prop;
 	struct device_node *dn;
 
-	of_prop = memblock_virt_alloc(sizeof(struct property) + 256, 0);
+	of_prop = memblock_alloc(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);
@@ -259,6 +263,10 @@
 	/* Call common code to handle resource allocation */
 	pcibios_resource_survey();
 
+	/* Call machine dependent fixup */
+	if (ppc_md.pcibios_fixup)
+		ppc_md.pcibios_fixup();
+
 	/* Call machine dependent post-init code */
 	if (ppc_md.pcibios_after_init)
 		ppc_md.pcibios_after_init();
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index dff28f9..f83d1f6 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Port for PPC64 David Engebretsen, IBM Corp.
  * Contains common pci routines for ppc64 platform, pSeries and iSeries brands.
  * 
  * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
  *   Rework, based on alpha PCI code.
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
@@ -58,14 +54,20 @@
 	pci_add_flags(PCI_ENABLE_PROC_DOMAINS | PCI_COMPAT_DOMAIN_0);
 
 	/* Scan all of the recorded PCI controllers.  */
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
 		pcibios_scan_phb(hose);
-		pci_bus_add_devices(hose->bus);
-	}
 
 	/* Call common code to handle resource allocation */
 	pcibios_resource_survey();
 
+	/* Add devices. */
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
+		pci_bus_add_devices(hose->bus);
+
+	/* Call machine dependent fixup */
+	if (ppc_md.pcibios_fixup)
+		ppc_md.pcibios_fixup();
+
 	printk(KERN_DEBUG "PCI: Probing PCI hardware done\n");
 
 	return 0;
@@ -159,7 +161,7 @@
 
 	/* Establish the mapping */
 	if (__ioremap_at(phys_page, area->addr, size_page,
-			 pgprot_val(pgprot_noncached(__pgprot(0)))) == NULL)
+			 pgprot_noncached(PAGE_KERNEL)) == NULL)
 		return -ENOMEM;
 
 	/* Fixup hose IO resource */
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index ab147a1..9524009 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * pci_dn.c
  *
  * Copyright (C) 2001 Todd Inglett, IBM Corporation
  *
  * PCI manipulation via device_nodes.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *    
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- * 
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 #include <linux/kernel.h>
 #include <linux/pci.h>
@@ -336,6 +323,7 @@
 {
 	struct pci_dn *pdn = dn ? PCI_DN(dn) : NULL;
 	struct device_node *parent;
+	struct pci_dev *pdev;
 #ifdef CONFIG_EEH
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 
@@ -349,12 +337,28 @@
 	WARN_ON(!list_empty(&pdn->child_list));
 	list_del(&pdn->list);
 
+	/* Drop the parent pci_dn's ref to our backing dt node */
 	parent = of_get_parent(dn);
 	if (parent)
 		of_node_put(parent);
 
-	dn->data = NULL;
-	kfree(pdn);
+	/*
+	 * At this point we *might* still have a pci_dev that was
+	 * instantiated from this pci_dn. So defer free()ing it until
+	 * the pci_dev's release function is called.
+	 */
+	pdev = pci_get_domain_bus_and_slot(pdn->phb->global_number,
+			pdn->busno, pdn->devfn);
+	if (pdev) {
+		/* NB: pdev has a ref to dn */
+		pci_dbg(pdev, "marked pdn (from %pOF) as dead\n", dn);
+		pdn->flags |= PCI_DN_FLAG_DEAD;
+	} else {
+		dn->data = NULL;
+		kfree(pdn);
+	}
+
+	pci_dev_put(pdev);
 }
 EXPORT_SYMBOL_GPL(pci_remove_device_node_info);
 
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 98f0472..f91d7e9 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Helper routines to scan the device tree for PCI devices and busses
  *
@@ -8,10 +9,6 @@
  * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
  *   Rework, based on alpha PCI code.
  * Copyright (c) 2009 Secret Lab Technologies Ltd.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
  */
 
 #include <linux/pci.h>
@@ -37,29 +34,75 @@
  * pci_parse_of_flags - Parse the flags cell of a device tree PCI address
  * @addr0: value of 1st cell of a device tree PCI address.
  * @bridge: Set this flag if the address is from a bridge 'ranges' property
+ *
+ * PCI Bus Binding to IEEE Std 1275-1994
+ *
+ * Bit#            33222222 22221111 11111100 00000000
+ *                 10987654 32109876 54321098 76543210
+ * phys.hi cell:   npt000ss bbbbbbbb dddddfff rrrrrrrr
+ * phys.mid cell:  hhhhhhhh hhhhhhhh hhhhhhhh hhhhhhhh
+ * phys.lo cell:   llllllll llllllll llllllll llllllll
+ *
+ * where:
+ * n        is 0 if the address is relocatable, 1 otherwise
+ * p        is 1 if the addressable region is "prefetchable", 0 otherwise
+ * t        is 1 if the address is aliased (for non-relocatable I/O),
+ *          below 1 MB (for Memory),or below 64 KB (for relocatable I/O).
+ * ss       is the space code, denoting the address space:
+ *              00 denotes Configuration Space
+ *              01 denotes I/O Space
+ *              10 denotes 32-bit-address Memory Space
+ *              11 denotes 64-bit-address Memory Space
+ * bbbbbbbb is the 8-bit Bus Number
+ * ddddd    is the 5-bit Device Number
+ * fff      is the 3-bit Function Number
+ * rrrrrrrr is the 8-bit Register Number
  */
+#define OF_PCI_ADDR0_SPACE(ss)		(((ss)&3)<<24)
+#define OF_PCI_ADDR0_SPACE_CFG		OF_PCI_ADDR0_SPACE(0)
+#define OF_PCI_ADDR0_SPACE_IO		OF_PCI_ADDR0_SPACE(1)
+#define OF_PCI_ADDR0_SPACE_MMIO32	OF_PCI_ADDR0_SPACE(2)
+#define OF_PCI_ADDR0_SPACE_MMIO64	OF_PCI_ADDR0_SPACE(3)
+#define OF_PCI_ADDR0_SPACE_MASK		OF_PCI_ADDR0_SPACE(3)
+#define OF_PCI_ADDR0_RELOC		(1UL<<31)
+#define OF_PCI_ADDR0_PREFETCH		(1UL<<30)
+#define OF_PCI_ADDR0_ALIAS		(1UL<<29)
+#define OF_PCI_ADDR0_BUS		0x00FF0000UL
+#define OF_PCI_ADDR0_DEV		0x0000F800UL
+#define OF_PCI_ADDR0_FN			0x00000700UL
+#define OF_PCI_ADDR0_BARREG		0x000000FFUL
+
 unsigned int pci_parse_of_flags(u32 addr0, int bridge)
 {
-	unsigned int flags = 0;
+	unsigned int flags = 0, as = addr0 & OF_PCI_ADDR0_SPACE_MASK;
 
-	if (addr0 & 0x02000000) {
+	if (as == OF_PCI_ADDR0_SPACE_MMIO32 || as == OF_PCI_ADDR0_SPACE_MMIO64) {
 		flags = IORESOURCE_MEM | PCI_BASE_ADDRESS_SPACE_MEMORY;
-		flags |= (addr0 >> 22) & PCI_BASE_ADDRESS_MEM_TYPE_64;
-		flags |= (addr0 >> 28) & PCI_BASE_ADDRESS_MEM_TYPE_1M;
-		if (addr0 & 0x40000000)
-			flags |= IORESOURCE_PREFETCH
-				 | PCI_BASE_ADDRESS_MEM_PREFETCH;
+
+		if (as == OF_PCI_ADDR0_SPACE_MMIO64)
+			flags |= PCI_BASE_ADDRESS_MEM_TYPE_64 | IORESOURCE_MEM_64;
+
+		if (addr0 & OF_PCI_ADDR0_ALIAS)
+			flags |= PCI_BASE_ADDRESS_MEM_TYPE_1M;
+
+		if (addr0 & OF_PCI_ADDR0_PREFETCH)
+			flags |= IORESOURCE_PREFETCH |
+				 PCI_BASE_ADDRESS_MEM_PREFETCH;
+
 		/* Note: We don't know whether the ROM has been left enabled
 		 * by the firmware or not. We mark it as disabled (ie, we do
 		 * not set the IORESOURCE_ROM_ENABLE flag) for now rather than
 		 * do a config space read, it will be force-enabled if needed
 		 */
-		if (!bridge && (addr0 & 0xff) == 0x30)
+		if (!bridge && (addr0 & OF_PCI_ADDR0_BARREG) == PCI_ROM_ADDRESS)
 			flags |= IORESOURCE_READONLY;
-	} else if (addr0 & 0x01000000)
+
+	} else if (as == OF_PCI_ADDR0_SPACE_IO)
 		flags = IORESOURCE_IO | PCI_BASE_ADDRESS_SPACE_IO;
+
 	if (flags)
 		flags |= IORESOURCE_SIZEALIGN;
+
 	return flags;
 }
 
@@ -80,10 +123,16 @@
 	const __be32 *addrs;
 	u32 i;
 	int proplen;
+	bool mark_unset = false;
 
 	addrs = of_get_property(node, "assigned-addresses", &proplen);
-	if (!addrs)
-		return;
+	if (!addrs || !proplen) {
+		addrs = of_get_property(node, "reg", &proplen);
+		if (!addrs || !proplen)
+			return;
+		mark_unset = true;
+	}
+
 	pr_debug("    parse addresses (%d bytes) @ %p\n", proplen, addrs);
 	for (; proplen >= 20; proplen -= 20, addrs += 5) {
 		flags = pci_parse_of_flags(of_read_number(addrs, 1), 0);
@@ -108,6 +157,8 @@
 			continue;
 		}
 		res->flags = flags;
+		if (mark_unset)
+			res->flags |= IORESOURCE_UNSET;
 		res->name = pci_name(dev);
 		region.start = base;
 		region.end = base + size - 1;
@@ -125,16 +176,13 @@
 				 struct pci_bus *bus, int devfn)
 {
 	struct pci_dev *dev;
-	const char *type;
 
 	dev = pci_alloc_dev(bus);
 	if (!dev)
 		return NULL;
-	type = of_get_property(node, "device_type", NULL);
-	if (type == NULL)
-		type = "";
 
-	pr_debug("    create device, devfn: %x, type: %s\n", devfn, type);
+	pr_debug("    create device, devfn: %x, type: %s\n", devfn,
+		 of_node_get_device_type(node));
 
 	dev->dev.of_node = of_node_get(node);
 	dev->dev.parent = bus->bridge;
@@ -167,12 +215,12 @@
 	/* Early fixups, before probing the BARs */
 	pci_fixup_device(pci_fixup_early, dev);
 
-	if (!strcmp(type, "pci") || !strcmp(type, "pciex")) {
+	if (of_node_is_type(node, "pci") || of_node_is_type(node, "pciex")) {
 		/* a PCI-PCI bridge */
 		dev->hdr_type = PCI_HEADER_TYPE_BRIDGE;
 		dev->rom_base_reg = PCI_ROM_ADDRESS1;
 		set_pcie_hotplug_bridge(dev);
-	} else if (!strcmp(type, "cardbus")) {
+	} else if (of_node_is_type(node, "cardbus")) {
 		dev->hdr_type = PCI_HEADER_TYPE_CARDBUS;
 	} else {
 		dev->hdr_type = PCI_HEADER_TYPE_NORMAL;
diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c
index 58eaa3d..15414c8 100644
--- a/arch/powerpc/kernel/pmc.c
+++ b/arch/powerpc/kernel/pmc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  arch/powerpc/kernel/pmc.c
  *
@@ -5,11 +6,6 @@
  *  Includes code formerly from arch/ppc/kernel/perfmon.c:
  *    Author: Andy Fleming
  *    Copyright (c) 2004 Freescale Semiconductor, Inc
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/errno.h>
@@ -29,7 +25,7 @@
 {
 #if defined(CONFIG_FSL_EMB_PERFMON)
 	mtpmr(PMRN_PMGC0, mfpmr(PMRN_PMGC0) & ~PMGC0_PMIE);
-#elif defined(CONFIG_PPC64) || defined(CONFIG_6xx)
+#elif defined(CONFIG_PPC64) || defined(CONFIG_PPC_BOOK3S_32)
 	if (cur_cpu_spec->pmc_type == PPC_PMC_IBM)
 		mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~(MMCR0_PMXE|MMCR0_PMAO));
 #else
diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/kernel/ppc32.h
index a27c914..2346f8c 100644
--- a/arch/powerpc/kernel/ppc32.h
+++ b/arch/powerpc/kernel/ppc32.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _PPC64_PPC32_H
 #define _PPC64_PPC32_H
 
@@ -7,11 +8,6 @@
 
 /*
  * Data types and macros for providing 32b PowerPC support.
- * 
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /* These are here to support 32-bit syscalls on a 64-bit kernel. */
diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S
index 6d1b42e..f3bd0bb 100644
--- a/arch/powerpc/kernel/ppc_save_regs.S
+++ b/arch/powerpc/kernel/ppc_save_regs.S
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 1996 Paul Mackerras.
  *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- *
  * NOTE: assert(sizeof(buf) > 23 * sizeof(long))
  */
 #include <asm/processor.h>
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index 9bfbd80..be3758d 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -1,19 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index bb6ac47..639ceae 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Derived from "arch/i386/kernel/process.c"
  *    Copyright (C) 1995  Linus Torvalds
@@ -7,11 +8,6 @@
  *
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/errno.h>
@@ -43,6 +39,7 @@
 #include <linux/uaccess.h>
 #include <linux/elf-randomize.h>
 #include <linux/pkeys.h>
+#include <linux/seq_buf.h>
 
 #include <asm/pgtable.h>
 #include <asm/io.h>
@@ -65,6 +62,8 @@
 #include <asm/livepatch.h>
 #include <asm/cpu_has_feature.h>
 #include <asm/asm-prototypes.h>
+#include <asm/stacktrace.h>
+#include <asm/hw_breakpoint.h>
 
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
@@ -102,27 +101,8 @@
 	}
 }
 
-static inline bool msr_tm_active(unsigned long msr)
-{
-	return MSR_TM_ACTIVE(msr);
-}
-
-static bool tm_active_with_fp(struct task_struct *tsk)
-{
-	return msr_tm_active(tsk->thread.regs->msr) &&
-		(tsk->thread.ckpt_regs.msr & MSR_FP);
-}
-
-static bool tm_active_with_altivec(struct task_struct *tsk)
-{
-	return msr_tm_active(tsk->thread.regs->msr) &&
-		(tsk->thread.ckpt_regs.msr & MSR_VEC);
-}
 #else
-static inline bool msr_tm_active(unsigned long msr) { return false; }
 static inline void check_if_tm_restore_required(struct task_struct *tsk) { }
-static inline bool tm_active_with_fp(struct task_struct *tsk) { return false; }
-static inline bool tm_active_with_altivec(struct task_struct *tsk) { return false; }
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
 bool strict_msr_control;
@@ -137,7 +117,8 @@
 }
 early_param("ppc_strict_facility_enable", enable_strict_msr_control);
 
-unsigned long msr_check_and_set(unsigned long bits)
+/* notrace because it's called by restore_math */
+unsigned long notrace msr_check_and_set(unsigned long bits)
 {
 	unsigned long oldmsr = mfmsr();
 	unsigned long newmsr;
@@ -156,7 +137,8 @@
 }
 EXPORT_SYMBOL_GPL(msr_check_and_set);
 
-void __msr_check_and_clear(unsigned long bits)
+/* notrace because it's called by restore_math */
+void notrace __msr_check_and_clear(unsigned long bits)
 {
 	unsigned long oldmsr = mfmsr();
 	unsigned long newmsr;
@@ -180,7 +162,7 @@
 
 	save_fpu(tsk);
 	msr = tsk->thread.regs->msr;
-	msr &= ~MSR_FP;
+	msr &= ~(MSR_FP|MSR_FE0|MSR_FE1);
 #ifdef CONFIG_VSX
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr &= ~MSR_VSX;
@@ -247,7 +229,8 @@
 		 * giveup as this would save  to the 'live' structure not the
 		 * checkpointed structure.
 		 */
-		if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr))
+		if (!MSR_TM_ACTIVE(cpumsr) &&
+		     MSR_TM_ACTIVE(current->thread.regs->msr))
 			return;
 		__giveup_fpu(current);
 	}
@@ -256,7 +239,7 @@
 
 static int restore_fp(struct task_struct *tsk)
 {
-	if (tsk->thread.load_fp || tm_active_with_fp(tsk)) {
+	if (tsk->thread.load_fp) {
 		load_fp_state(&current->thread.fp_state);
 		current->thread.load_fp++;
 		return 1;
@@ -311,7 +294,8 @@
 		 * giveup as this would save  to the 'live' structure not the
 		 * checkpointed structure.
 		 */
-		if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr))
+		if (!MSR_TM_ACTIVE(cpumsr) &&
+		     MSR_TM_ACTIVE(current->thread.regs->msr))
 			return;
 		__giveup_altivec(current);
 	}
@@ -337,8 +321,7 @@
 
 static int restore_altivec(struct task_struct *tsk)
 {
-	if (cpu_has_feature(CPU_FTR_ALTIVEC) &&
-		(tsk->thread.load_vec || tm_active_with_altivec(tsk))) {
+	if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
 		load_vr_state(&tsk->thread.vr_state);
 		tsk->thread.used_vr = 1;
 		tsk->thread.load_vec++;
@@ -397,7 +380,8 @@
 		 * giveup as this would save  to the 'live' structure not the
 		 * checkpointed structure.
 		 */
-		if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr))
+		if (!MSR_TM_ACTIVE(cpumsr) &&
+		     MSR_TM_ACTIVE(current->thread.regs->msr))
 			return;
 		__giveup_vsx(current);
 	}
@@ -499,13 +483,14 @@
 	if (!tsk->thread.regs)
 		return;
 
+	check_if_tm_restore_required(tsk);
+
 	usermsr = tsk->thread.regs->msr;
 
 	if ((usermsr & msr_all_available) == 0)
 		return;
 
 	msr_check_and_set(msr_all_available);
-	check_if_tm_restore_required(tsk);
 
 	WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));
 
@@ -526,11 +511,21 @@
 }
 EXPORT_SYMBOL(giveup_all);
 
-void restore_math(struct pt_regs *regs)
+/*
+ * The exception exit path calls restore_math() with interrupts hard disabled
+ * but the soft irq state not "reconciled". ftrace code that calls
+ * local_irq_save/restore causes warnings.
+ *
+ * Rather than complicate the exit path, just don't trace restore_math. This
+ * could be done by having ftrace entry code check for this un-reconciled
+ * condition where MSR[EE]=0 and PACA_IRQ_HARD_DIS is not set, and
+ * temporarily fix it up for the duration of the ftrace call.
+ */
+void notrace restore_math(struct pt_regs *regs)
 {
 	unsigned long msr;
 
-	if (!msr_tm_active(regs->msr) &&
+	if (!MSR_TM_ACTIVE(regs->msr) &&
 		!current->thread.load_fp && !loadvec(current->thread))
 		return;
 
@@ -591,12 +586,11 @@
 	if (tsk->thread.regs) {
 		preempt_disable();
 		BUG_ON(tsk != current);
-		save_all(tsk);
-
 #ifdef CONFIG_SPE
 		if (tsk->thread.regs->msr & MSR_SPE)
 			tsk->thread.spefscr = mfspr(SPRN_SPEFSCR);
 #endif
+		save_all(tsk);
 
 		preempt_enable();
 	}
@@ -620,8 +614,6 @@
 void do_break (struct pt_regs *regs, unsigned long address,
 		    unsigned long error_code)
 {
-	siginfo_t info;
-
 	current->thread.trap_nr = TRAP_HWBKPT;
 	if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
 			11, SIGSEGV) == NOTIFY_STOP)
@@ -634,12 +626,7 @@
 	hw_breakpoint_disable();
 
 	/* Deliver the signal to userspace */
-	clear_siginfo(&info);
-	info.si_signo = SIGTRAP;
-	info.si_errno = 0;
-	info.si_code = TRAP_HWBKPT;
-	info.si_addr = (void __user *)address;
-	force_sig_info(SIGTRAP, &info, current);
+	force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)address);
 }
 #endif	/* CONFIG_PPC_ADV_DEBUG_REGS */
 
@@ -793,39 +780,11 @@
 	return __set_dabr(dabr, dabrx);
 }
 
-static inline int set_dawr(struct arch_hw_breakpoint *brk)
-{
-	unsigned long dawr, dawrx, mrd;
-
-	dawr = brk->address;
-
-	dawrx  = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) \
-		                   << (63 - 58); //* read/write bits */
-	dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) \
-		                   << (63 - 59); //* translate */
-	dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) \
-		                   >> 3; //* PRIM bits */
-	/* dawr length is stored in field MDR bits 48:53.  Matches range in
-	   doublewords (64 bits) baised by -1 eg. 0b000000=1DW and
-	   0b111111=64DW.
-	   brk->len is in bytes.
-	   This aligns up to double word size, shifts and does the bias.
-	*/
-	mrd = ((brk->len + 7) >> 3) - 1;
-	dawrx |= (mrd & 0x3f) << (63 - 53);
-
-	if (ppc_md.set_dawr)
-		return ppc_md.set_dawr(dawr, dawrx);
-	mtspr(SPRN_DAWR, dawr);
-	mtspr(SPRN_DAWRX, dawrx);
-	return 0;
-}
-
 void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
 	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
 
-	if (cpu_has_feature(CPU_FTR_DAWR))
+	if (dawr_enabled())
 		// Power8 or later
 		set_dawr(brk);
 	else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
@@ -839,8 +798,8 @@
 /* Check if we have DAWR or DABR hardware */
 bool ppc_breakpoint_available(void)
 {
-	if (cpu_has_feature(CPU_FTR_DAWR))
-		return true; /* POWER8 DAWR */
+	if (dawr_enabled())
+		return true; /* POWER8 DAWR or POWER9 forced DAWR */
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		return false; /* POWER9 with DAWR disabled */
 	/* DABR: Everything but POWER8 and POWER9 */
@@ -1160,11 +1119,6 @@
 	thread_pkey_regs_restore(new_thread, old_thread);
 }
 
-#ifdef CONFIG_PPC_BOOK3S_64
-#define CP_SIZE 128
-static const u8 dummy_copy_buffer[CP_SIZE] __attribute__((aligned(CP_SIZE)));
-#endif
-
 struct task_struct *__switch_to(struct task_struct *prev,
 	struct task_struct *new)
 {
@@ -1240,8 +1194,8 @@
 		batch->active = 1;
 	}
 
-	if (current_thread_info()->task->thread.regs) {
-		restore_math(current_thread_info()->task->thread.regs);
+	if (current->thread.regs) {
+		restore_math(current->thread.regs);
 
 		/*
 		 * The copy-paste buffer can only store into foreign real
@@ -1251,7 +1205,7 @@
 		 * mappings, we must issue a cp_abort to clear any state and
 		 * prevent snooping, corruption or a covert channel.
 		 */
-		if (current_thread_info()->task->thread.used_vas)
+		if (current->thread.used_vas)
 			asm volatile(PPC_CP_ABORT);
 	}
 #endif /* CONFIG_PPC_BOOK3S_64 */
@@ -1259,17 +1213,16 @@
 	return last;
 }
 
-static int instructions_to_print = 16;
+#define NR_INSN_TO_PRINT	16
 
 static void show_instructions(struct pt_regs *regs)
 {
 	int i;
-	unsigned long pc = regs->nip - (instructions_to_print * 3 / 4 *
-			sizeof(int));
+	unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
 
 	printk("Instruction dump:");
 
-	for (i = 0; i < instructions_to_print; i++) {
+	for (i = 0; i < NR_INSN_TO_PRINT; i++) {
 		int instr;
 
 		if (!(i % 8))
@@ -1284,7 +1237,7 @@
 #endif
 
 		if (!__kernel_text_address(pc) ||
-		     probe_kernel_address((unsigned int __user *)pc, instr)) {
+		    probe_kernel_address((const void *)pc, instr)) {
 			pr_cont("XXXXXXXX ");
 		} else {
 			if (regs->nip == pc)
@@ -1302,43 +1255,43 @@
 void show_user_instructions(struct pt_regs *regs)
 {
 	unsigned long pc;
-	int i;
+	int n = NR_INSN_TO_PRINT;
+	struct seq_buf s;
+	char buf[96]; /* enough for 8 times 9 + 2 chars */
 
-	pc = regs->nip - (instructions_to_print * 3 / 4 * sizeof(int));
+	pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
 
 	/*
 	 * Make sure the NIP points at userspace, not kernel text/data or
 	 * elsewhere.
 	 */
-	if (!__access_ok(pc, instructions_to_print * sizeof(int), USER_DS)) {
+	if (!__access_ok(pc, NR_INSN_TO_PRINT * sizeof(int), USER_DS)) {
 		pr_info("%s[%d]: Bad NIP, not dumping instructions.\n",
 			current->comm, current->pid);
 		return;
 	}
 
-	pr_info("%s[%d]: code: ", current->comm, current->pid);
+	seq_buf_init(&s, buf, sizeof(buf));
 
-	for (i = 0; i < instructions_to_print; i++) {
-		int instr;
+	while (n) {
+		int i;
 
-		if (!(i % 8) && (i > 0)) {
-			pr_cont("\n");
-			pr_info("%s[%d]: code: ", current->comm, current->pid);
+		seq_buf_clear(&s);
+
+		for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) {
+			int instr;
+
+			if (probe_kernel_address((const void *)pc, instr)) {
+				seq_buf_printf(&s, "XXXXXXXX ");
+				continue;
+			}
+			seq_buf_printf(&s, regs->nip == pc ? "<%08x> " : "%08x ", instr);
 		}
 
-		if (probe_kernel_address((unsigned int __user *)pc, instr)) {
-			pr_cont("XXXXXXXX ");
-		} else {
-			if (regs->nip == pc)
-				pr_cont("<%08x> ", instr);
-			else
-				pr_cont("%08x ", instr);
-		}
-
-		pc += sizeof(int);
+		if (!seq_buf_has_overflowed(&s))
+			pr_info("%s[%d]: code: %s\n", current->comm,
+				current->pid, s.buffer);
 	}
-
-	pr_cont("\n");
 }
 
 struct regbit {
@@ -1492,6 +1445,15 @@
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+void arch_setup_new_exec(void)
+{
+	if (radix_enabled())
+		return;
+	hash__setup_new_exec();
+}
+#endif
+
 int set_thread_uses_vas(void)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -1625,8 +1587,9 @@
 /*
  * Copy architecture-specific thread state
  */
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long kthread_arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+		unsigned long kthread_arg, struct task_struct *p,
+		unsigned long tls)
 {
 	struct pt_regs *childregs, *kregs;
 	extern void ret_from_fork(void);
@@ -1635,7 +1598,7 @@
 	unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
 	struct thread_info *ti = task_thread_info(p);
 
-	klp_init_thread_info(ti);
+	klp_init_thread_info(p);
 
 	/* Copy registers */
 	sp -= sizeof(struct pt_regs);
@@ -1667,10 +1630,10 @@
 		if (clone_flags & CLONE_SETTLS) {
 #ifdef CONFIG_PPC64
 			if (!is_32bit_task())
-				childregs->gpr[13] = childregs->gpr[6];
+				childregs->gpr[13] = tls;
 			else
 #endif
-				childregs->gpr[2] = childregs->gpr[6];
+				childregs->gpr[2] = tls;
 		}
 
 		f = ret_from_fork;
@@ -1692,8 +1655,7 @@
 	sp -= STACK_FRAME_OVERHEAD;
 	p->thread.ksp = sp;
 #ifdef CONFIG_PPC32
-	p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
-				_ALIGN_UP(sizeof(struct thread_info), 16);
+	p->thread.ksp_limit = (unsigned long)end_of_stack(p);
 #endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	p->thread.ptrace_bps[0] = NULL;
@@ -1712,7 +1674,7 @@
 		p->thread.dscr = mfspr(SPRN_DSCR);
 	}
 	if (cpu_has_feature(CPU_FTR_HAS_PPR))
-		p->thread.ppr = INIT_PPR;
+		childregs->ppr = DEFAULT_PPR;
 
 	p->thread.tidr = 0;
 #endif
@@ -1720,6 +1682,8 @@
 	return 0;
 }
 
+void preload_new_slb_context(unsigned long start, unsigned long sp);
+
 /*
  * Set up a thread for executing a new program
  */
@@ -1727,6 +1691,11 @@
 {
 #ifdef CONFIG_PPC64
 	unsigned long load_addr = regs->gpr[2];	/* saved by ELF_PLAT_INIT */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (!radix_enabled())
+		preload_new_slb_context(start, sp);
+#endif
 #endif
 
 	/*
@@ -1817,6 +1786,7 @@
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif
+	current->thread.load_slb = 0;
 	current->thread.load_fp = 0;
 	memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
 	current->thread.fp_save_area = NULL;
@@ -1989,21 +1959,14 @@
 	unsigned long stack_page;
 	unsigned long cpu = task_cpu(p);
 
-	/*
-	 * Avoid crashing if the stack has overflowed and corrupted
-	 * task_cpu(p), which is in the thread_info struct.
-	 */
-	if (cpu < NR_CPUS && cpu_possible(cpu)) {
-		stack_page = (unsigned long) hardirq_ctx[cpu];
-		if (sp >= stack_page + sizeof(struct thread_struct)
-		    && sp <= stack_page + THREAD_SIZE - nbytes)
-			return 1;
+	stack_page = (unsigned long)hardirq_ctx[cpu];
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+		return 1;
 
-		stack_page = (unsigned long) softirq_ctx[cpu];
-		if (sp >= stack_page + sizeof(struct thread_struct)
-		    && sp <= stack_page + THREAD_SIZE - nbytes)
-			return 1;
-	}
+	stack_page = (unsigned long)softirq_ctx[cpu];
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+		return 1;
+
 	return 0;
 }
 
@@ -2012,8 +1975,10 @@
 {
 	unsigned long stack_page = (unsigned long)task_stack_page(p);
 
-	if (sp >= stack_page + sizeof(struct thread_struct)
-	    && sp <= stack_page + THREAD_SIZE - nbytes)
+	if (sp < THREAD_SIZE)
+		return 0;
+
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
 		return 1;
 
 	return valid_irq_stack(sp, p, nbytes);
@@ -2021,7 +1986,7 @@
 
 EXPORT_SYMBOL(validate_sp);
 
-unsigned long get_wchan(struct task_struct *p)
+static unsigned long __get_wchan(struct task_struct *p)
 {
 	unsigned long ip, sp;
 	int count = 0;
@@ -2047,6 +2012,20 @@
 	return 0;
 }
 
+unsigned long get_wchan(struct task_struct *p)
+{
+	unsigned long ret;
+
+	if (!try_get_task_stack(p))
+		return 0;
+
+	ret = __get_wchan(p);
+
+	put_task_stack(p);
+
+	return ret;
+}
+
 static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
 
 void show_stack(struct task_struct *tsk, unsigned long *stack)
@@ -2055,14 +2034,17 @@
 	int count = 0;
 	int firstframe = 1;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	int curr_frame = current->curr_ret_stack;
-	extern void return_to_handler(void);
-	unsigned long rth = (unsigned long)return_to_handler;
+	unsigned long ret_addr;
+	int ftrace_idx = 0;
 #endif
 
-	sp = (unsigned long) stack;
 	if (tsk == NULL)
 		tsk = current;
+
+	if (!try_get_task_stack(tsk))
+		return;
+
+	sp = (unsigned long) stack;
 	if (sp == 0) {
 		if (tsk == current)
 			sp = current_stack_pointer();
@@ -2074,7 +2056,7 @@
 	printk("Call Trace:\n");
 	do {
 		if (!validate_sp(sp, tsk, STACK_FRAME_OVERHEAD))
-			return;
+			break;
 
 		stack = (unsigned long *) sp;
 		newsp = stack[0];
@@ -2082,11 +2064,10 @@
 		if (!firstframe || ip != lr) {
 			printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-			if ((ip == rth) && curr_frame >= 0) {
-				pr_cont(" (%pS)",
-				       (void *)current->ret_stack[curr_frame].ret);
-				curr_frame--;
-			}
+			ret_addr = ftrace_graph_ret_addr(current,
+						&ftrace_idx, ip, stack);
+			if (ret_addr != ip)
+				pr_cont(" (%pS)", (void *)ret_addr);
 #endif
 			if (firstframe)
 				pr_cont(" (unreliable)");
@@ -2110,6 +2091,8 @@
 
 		sp = newsp;
 	} while (count++ < kstack_depth_to_print);
+
+	put_task_stack(tsk);
 }
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index c4d7078..6620f37 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Procedures for creating, accessing and interpreting the device tree.
  *
@@ -6,11 +7,6 @@
  * 
  *  Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
  *    {engebret|bergner}@us.ibm.com 
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
@@ -59,6 +55,7 @@
 #include <asm/firmware.h>
 #include <asm/dt_cpu_ftrs.h>
 #include <asm/drmem.h>
+#include <asm/ultravisor.h>
 
 #include <mm/mmu_decl.h>
 
@@ -124,12 +121,15 @@
 	size = fdt_totalsize(initial_boot_params);
 
 	if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) ||
-			overlaps_crashkernel(start, size) ||
-			overlaps_initrd(start, size)) {
-		p = __va(memblock_alloc(size, PAGE_SIZE));
+	    !memblock_is_memory(start + size - 1) ||
+	    overlaps_crashkernel(start, size) || overlaps_initrd(start, size)) {
+		p = memblock_alloc_raw(size, PAGE_SIZE);
+		if (!p)
+			panic("Failed to allocate %lu bytes to move device tree\n",
+			      size);
 		memcpy(p, initial_boot_params, size);
 		initial_boot_params = p;
-		DBG("Moved device tree to 0x%p\n", p);
+		DBG("Moved device tree to 0x%px\n", p);
 	}
 
 	DBG("<- move_device_tree\n");
@@ -689,7 +689,7 @@
 {
 	phys_addr_t limit;
 
-	DBG(" -> early_init_devtree(%p)\n", params);
+	DBG(" -> early_init_devtree(%px)\n", params);
 
 	/* Too early to BUG_ON(), do it by hand */
 	if (!early_init_dt_verify(params))
@@ -703,9 +703,12 @@
 #ifdef CONFIG_PPC_POWERNV
 	/* Some machines might need OPAL info for debugging, grab it now. */
 	of_scan_flat_dt(early_init_dt_scan_opal, NULL);
+
+	/* Scan tree for ultravisor feature */
+	of_scan_flat_dt(early_init_dt_scan_ultravisor, NULL);
 #endif
 
-#ifdef CONFIG_FA_DUMP
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
 	/* scan tree to see if dump is active during last boot */
 	of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
 #endif
@@ -732,7 +735,7 @@
 	if (PHYSICAL_START > MEMORY_START)
 		memblock_reserve(MEMORY_START, 0x8000);
 	reserve_kdump_trampoline();
-#ifdef CONFIG_FA_DUMP
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
 	/*
 	 * If we fail to reserve memory for firmware-assisted dump then
 	 * fallback to kexec based kdump.
@@ -749,7 +752,7 @@
 	memblock_allow_resize();
 	memblock_dump_all();
 
-	DBG("Phys. mem: %llx\n", memblock_phys_mem_size());
+	DBG("Phys. mem: %llx\n", (unsigned long long)memblock_phys_mem_size());
 
 	/* We may need to relocate the flat tree, do it now.
 	 * FIXME .. and the initrd too? */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 9b38a2e..100f1b5 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Procedures for interfacing to Open Firmware.
  *
@@ -6,11 +7,6 @@
  * 
  *  Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
  *    {engebret|bergner}@us.ibm.com 
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG_PROM
@@ -43,11 +39,14 @@
 #include <asm/btext.h>
 #include <asm/sections.h>
 #include <asm/machdep.h>
-#include <asm/opal.h>
 #include <asm/asm-prototypes.h>
+#include <asm/ultravisor-api.h>
 
 #include <linux/linux_logo.h>
 
+/* All of prom_init bss lives here */
+#define __prombss __section(.bss.prominit)
+
 /*
  * Eventually bump that one up
  */
@@ -87,7 +86,7 @@
 #define OF_WORKAROUNDS	0
 #else
 #define OF_WORKAROUNDS	of_workarounds
-int of_workarounds;
+static int of_workarounds __prombss;
 #endif
 
 #define OF_WA_CLAIM	1	/* do phys/virt claim separately, then map */
@@ -96,7 +95,7 @@
 #define PROM_BUG() do {						\
         prom_printf("kernel BUG at %s line 0x%x!\n",		\
 		    __FILE__, __LINE__);			\
-        __asm__ __volatile__(".long " BUG_ILLEGAL_INSTR);	\
+	__builtin_trap();					\
 } while (0)
 
 #ifdef DEBUG_PROM
@@ -148,29 +147,34 @@
 			   unsigned long size, unsigned long offset);
 
 /* prom structure */
-static struct prom_t __initdata prom;
+static struct prom_t __prombss prom;
 
-static unsigned long prom_entry __initdata;
+static unsigned long __prombss prom_entry;
 
-#define PROM_SCRATCH_SIZE 256
+static char __prombss of_stdout_device[256];
+static char __prombss prom_scratch[256];
 
-static char __initdata of_stdout_device[256];
-static char __initdata prom_scratch[PROM_SCRATCH_SIZE];
+static unsigned long __prombss dt_header_start;
+static unsigned long __prombss dt_struct_start, dt_struct_end;
+static unsigned long __prombss dt_string_start, dt_string_end;
 
-static unsigned long __initdata dt_header_start;
-static unsigned long __initdata dt_struct_start, dt_struct_end;
-static unsigned long __initdata dt_string_start, dt_string_end;
-
-static unsigned long __initdata prom_initrd_start, prom_initrd_end;
+static unsigned long __prombss prom_initrd_start, prom_initrd_end;
 
 #ifdef CONFIG_PPC64
-static int __initdata prom_iommu_force_on;
-static int __initdata prom_iommu_off;
-static unsigned long __initdata prom_tce_alloc_start;
-static unsigned long __initdata prom_tce_alloc_end;
+static int __prombss prom_iommu_force_on;
+static int __prombss prom_iommu_off;
+static unsigned long __prombss prom_tce_alloc_start;
+static unsigned long __prombss prom_tce_alloc_end;
 #endif
 
-static bool prom_radix_disable __initdata = !IS_ENABLED(CONFIG_PPC_RADIX_MMU_DEFAULT);
+#ifdef CONFIG_PPC_PSERIES
+static bool __prombss prom_radix_disable;
+static bool __prombss prom_xive_disable;
+#endif
+
+#ifdef CONFIG_PPC_SVM
+static bool __prombss prom_svm_enable;
+#endif
 
 struct platform_support {
 	bool hash_mmu;
@@ -188,26 +192,25 @@
 #define PLATFORM_LPAR		0x0001
 #define PLATFORM_POWERMAC	0x0400
 #define PLATFORM_GENERIC	0x0500
-#define PLATFORM_OPAL		0x0600
 
-static int __initdata of_platform;
+static int __prombss of_platform;
 
-static char __initdata prom_cmd_line[COMMAND_LINE_SIZE];
+static char __prombss prom_cmd_line[COMMAND_LINE_SIZE];
 
-static unsigned long __initdata prom_memory_limit;
+static unsigned long __prombss prom_memory_limit;
 
-static unsigned long __initdata alloc_top;
-static unsigned long __initdata alloc_top_high;
-static unsigned long __initdata alloc_bottom;
-static unsigned long __initdata rmo_top;
-static unsigned long __initdata ram_top;
+static unsigned long __prombss alloc_top;
+static unsigned long __prombss alloc_top_high;
+static unsigned long __prombss alloc_bottom;
+static unsigned long __prombss rmo_top;
+static unsigned long __prombss ram_top;
 
-static struct mem_map_entry __initdata mem_reserve_map[MEM_RESERVE_MAP_SIZE];
-static int __initdata mem_reserve_cnt;
+static struct mem_map_entry __prombss mem_reserve_map[MEM_RESERVE_MAP_SIZE];
+static int __prombss mem_reserve_cnt;
 
-static cell_t __initdata regbuf[1024];
+static cell_t __prombss regbuf[1024];
 
-static bool rtas_has_query_cpu_stopped;
+static bool  __prombss rtas_has_query_cpu_stopped;
 
 
 /*
@@ -221,6 +224,135 @@
 #define PHANDLE_VALID(p)	((p) != 0 && (p) != PROM_ERROR)
 #define IHANDLE_VALID(i)	((i) != 0 && (i) != PROM_ERROR)
 
+/* Copied from lib/string.c and lib/kstrtox.c */
+
+static int __init prom_strcmp(const char *cs, const char *ct)
+{
+	unsigned char c1, c2;
+
+	while (1) {
+		c1 = *cs++;
+		c2 = *ct++;
+		if (c1 != c2)
+			return c1 < c2 ? -1 : 1;
+		if (!c1)
+			break;
+	}
+	return 0;
+}
+
+static char __init *prom_strcpy(char *dest, const char *src)
+{
+	char *tmp = dest;
+
+	while ((*dest++ = *src++) != '\0')
+		/* nothing */;
+	return tmp;
+}
+
+static int __init prom_strncmp(const char *cs, const char *ct, size_t count)
+{
+	unsigned char c1, c2;
+
+	while (count) {
+		c1 = *cs++;
+		c2 = *ct++;
+		if (c1 != c2)
+			return c1 < c2 ? -1 : 1;
+		if (!c1)
+			break;
+		count--;
+	}
+	return 0;
+}
+
+static size_t __init prom_strlen(const char *s)
+{
+	const char *sc;
+
+	for (sc = s; *sc != '\0'; ++sc)
+		/* nothing */;
+	return sc - s;
+}
+
+static int __init prom_memcmp(const void *cs, const void *ct, size_t count)
+{
+	const unsigned char *su1, *su2;
+	int res = 0;
+
+	for (su1 = cs, su2 = ct; 0 < count; ++su1, ++su2, count--)
+		if ((res = *su1 - *su2) != 0)
+			break;
+	return res;
+}
+
+static char __init *prom_strstr(const char *s1, const char *s2)
+{
+	size_t l1, l2;
+
+	l2 = prom_strlen(s2);
+	if (!l2)
+		return (char *)s1;
+	l1 = prom_strlen(s1);
+	while (l1 >= l2) {
+		l1--;
+		if (!prom_memcmp(s1, s2, l2))
+			return (char *)s1;
+		s1++;
+	}
+	return NULL;
+}
+
+static size_t __init prom_strlcpy(char *dest, const char *src, size_t size)
+{
+	size_t ret = prom_strlen(src);
+
+	if (size) {
+		size_t len = (ret >= size) ? size - 1 : ret;
+		memcpy(dest, src, len);
+		dest[len] = '\0';
+	}
+	return ret;
+}
+
+#ifdef CONFIG_PPC_PSERIES
+static int __init prom_strtobool(const char *s, bool *res)
+{
+	if (!s)
+		return -EINVAL;
+
+	switch (s[0]) {
+	case 'y':
+	case 'Y':
+	case '1':
+		*res = true;
+		return 0;
+	case 'n':
+	case 'N':
+	case '0':
+		*res = false;
+		return 0;
+	case 'o':
+	case 'O':
+		switch (s[1]) {
+		case 'n':
+		case 'N':
+			*res = true;
+			return 0;
+		case 'f':
+		case 'F':
+			*res = false;
+			return 0;
+		default:
+			break;
+		}
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+#endif
 
 /* This is the one and *ONLY* place where we actually call open
  * firmware.
@@ -498,14 +630,14 @@
 	}
 }
 
-static inline int prom_getprop(phandle node, const char *pname,
-			       void *value, size_t valuelen)
+static inline int __init prom_getprop(phandle node, const char *pname,
+				      void *value, size_t valuelen)
 {
 	return call_prom("getprop", 4, 1, node, ADDR(pname),
 			 (u32)(unsigned long) value, (u32) valuelen);
 }
 
-static inline int prom_getproplen(phandle node, const char *pname)
+static inline int __init prom_getproplen(phandle node, const char *pname)
 {
 	return call_prom("getproplen", 2, 1, node, ADDR(pname));
 }
@@ -522,8 +654,8 @@
 
 static char *tohex(unsigned int x)
 {
-	static char digits[] = "0123456789abcdef";
-	static char result[9];
+	static const char digits[] __initconst = "0123456789abcdef";
+	static char result[9] __prombss;
 	int i;
 
 	result[8] = 0;
@@ -552,7 +684,7 @@
 	add_string(&p, tohex((u32)(unsigned long) value));
 	add_string(&p, tohex(valuelen));
 	add_string(&p, tohex(ADDR(pname)));
-	add_string(&p, tohex(strlen(pname)));
+	add_string(&p, tohex(prom_strlen(pname)));
 	add_string(&p, "property");
 	*p = 0;
 	return call_prom("interpret", 1, 1, (u32)(unsigned long) cmd);
@@ -628,33 +760,30 @@
 	const char *opt;
 
 	char *p;
-	int l __maybe_unused = 0;
+	int l = 0;
 
 	prom_cmd_line[0] = 0;
 	p = prom_cmd_line;
 	if ((long)prom.chosen > 0)
 		l = prom_getprop(prom.chosen, "bootargs", p, COMMAND_LINE_SIZE-1);
-#ifdef CONFIG_CMDLINE
-	if (l <= 0 || p[0] == '\0') /* dbl check */
-		strlcpy(prom_cmd_line,
-			CONFIG_CMDLINE, sizeof(prom_cmd_line));
-#endif /* CONFIG_CMDLINE */
+	if (IS_ENABLED(CONFIG_CMDLINE_BOOL) && (l <= 0 || p[0] == '\0')) /* dbl check */
+		prom_strlcpy(prom_cmd_line, CONFIG_CMDLINE, sizeof(prom_cmd_line));
 	prom_printf("command line: %s\n", prom_cmd_line);
 
 #ifdef CONFIG_PPC64
-	opt = strstr(prom_cmd_line, "iommu=");
+	opt = prom_strstr(prom_cmd_line, "iommu=");
 	if (opt) {
 		prom_printf("iommu opt is: %s\n", opt);
 		opt += 6;
 		while (*opt && *opt == ' ')
 			opt++;
-		if (!strncmp(opt, "off", 3))
+		if (!prom_strncmp(opt, "off", 3))
 			prom_iommu_off = 1;
-		else if (!strncmp(opt, "force", 5))
+		else if (!prom_strncmp(opt, "force", 5))
 			prom_iommu_force_on = 1;
 	}
 #endif
-	opt = strstr(prom_cmd_line, "mem=");
+	opt = prom_strstr(prom_cmd_line, "mem=");
 	if (opt) {
 		opt += 4;
 		prom_memory_limit = prom_memparse(opt, (const char **)&opt);
@@ -664,13 +793,15 @@
 #endif
 	}
 
-	opt = strstr(prom_cmd_line, "disable_radix");
+#ifdef CONFIG_PPC_PSERIES
+	prom_radix_disable = !IS_ENABLED(CONFIG_PPC_RADIX_MMU_DEFAULT);
+	opt = prom_strstr(prom_cmd_line, "disable_radix");
 	if (opt) {
 		opt += 13;
 		if (*opt && *opt == '=') {
 			bool val;
 
-			if (kstrtobool(++opt, &val))
+			if (prom_strtobool(++opt, &val))
 				prom_radix_disable = false;
 			else
 				prom_radix_disable = val;
@@ -679,9 +810,27 @@
 	}
 	if (prom_radix_disable)
 		prom_debug("Radix disabled from cmdline\n");
+
+	opt = prom_strstr(prom_cmd_line, "xive=off");
+	if (opt) {
+		prom_xive_disable = true;
+		prom_debug("XIVE disabled from cmdline\n");
+	}
+#endif /* CONFIG_PPC_PSERIES */
+
+#ifdef CONFIG_PPC_SVM
+	opt = prom_strstr(prom_cmd_line, "svm=");
+	if (opt) {
+		bool val;
+
+		opt += sizeof("svm=") - 1;
+		if (!prom_strtobool(opt, &val))
+			prom_svm_enable = val;
+	}
+#endif /* CONFIG_PPC_SVM */
 }
 
-#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+#ifdef CONFIG_PPC_PSERIES
 /*
  * The architecture vector has an array of PVR mask/value pairs,
  * followed by # option vectors - 1, followed by the option vectors.
@@ -782,7 +931,7 @@
 	struct option_vector6 vec6;
 } __packed;
 
-struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
+static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 	.pvrs = {
 		{
 			.mask = cpu_to_be32(0xfffe0000), /* POWER5/POWER5+ */
@@ -920,9 +1069,11 @@
 	},
 };
 
+static struct ibm_arch_vec __prombss ibm_architecture_vec  ____cacheline_aligned;
+
 /* Old method - ELF header with PT_NOTE sections only works on BE */
 #ifdef __BIG_ENDIAN__
-static struct fake_elf {
+static const struct fake_elf {
 	Elf32_Ehdr	elfhdr;
 	Elf32_Phdr	phdr[2];
 	struct chrpnote {
@@ -955,7 +1106,7 @@
 			u32	ignore_me;
 		} rpadesc;
 	} rpanote;
-} fake_elf = {
+} fake_elf __initconst = {
 	.elfhdr = {
 		.e_ident = { 0x7f, 'E', 'L', 'F',
 			     ELFCLASS32, ELFDATA2MSB, EV_CURRENT },
@@ -1020,7 +1171,7 @@
 		type[0] = 0;
 		prom_getprop(node, "device_type", type, sizeof(type));
 
-		if (strcmp(type, "cpu"))
+		if (prom_strcmp(type, "cpu"))
 			continue;
 		/*
 		 * There is an entry for each smt thread, each entry being
@@ -1084,10 +1235,17 @@
 	switch (val) {
 	case OV5_FEAT(OV5_XIVE_EITHER): /* Either Available */
 		prom_debug("XIVE - either mode supported\n");
-		support->xive = true;
+		support->xive = !prom_xive_disable;
 		break;
 	case OV5_FEAT(OV5_XIVE_EXPLOIT): /* Only Exploitation mode */
 		prom_debug("XIVE - exploitation mode supported\n");
+		if (prom_xive_disable) {
+			/*
+			 * If we __have__ to do XIVE, we're better off ignoring
+			 * the command line rather than not booting.
+			 */
+			prom_printf("WARNING: Ignoring cmdline option xive=off\n");
+		}
 		support->xive = true;
 		break;
 	case OV5_FEAT(OV5_XIVE_LEGACY): /* Only Legacy mode */
@@ -1129,14 +1287,27 @@
 	};
 	int prop_len = prom_getproplen(prom.chosen,
 				       "ibm,arch-vec-5-platform-support");
+
+	/*
+	 * First copy the architecture vec template
+	 *
+	 * use memcpy() instead of *vec = *vec_template so that GCC replaces it
+	 * by __memcpy() when KASAN is active
+	 */
+	memcpy(&ibm_architecture_vec, &ibm_architecture_vec_template,
+	       sizeof(ibm_architecture_vec));
+
 	if (prop_len > 1) {
 		int i;
-		u8 vec[prop_len];
+		u8 vec[8];
 		prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n",
 			   prop_len);
+		if (prop_len > sizeof(vec))
+			prom_printf("WARNING: ibm,arch-vec-5-platform-support longer than expected (len: %d)\n",
+				    prop_len);
 		prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support",
 			     &vec, sizeof(vec));
-		for (i = 0; i < prop_len; i += 2) {
+		for (i = 0; i < sizeof(vec); i += 2) {
 			prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2
 								  , vec[i]
 								  , vec[i + 1]);
@@ -1225,7 +1396,7 @@
 	}
 #endif /* __BIG_ENDIAN__ */
 }
-#endif /* #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
+#endif /* CONFIG_PPC_PSERIES */
 
 /*
  * Memory allocation strategy... our layout is normally:
@@ -1421,9 +1592,6 @@
 static void __init prom_init_mem(void)
 {
 	phandle node;
-#ifdef DEBUG_PROM
-	char *path;
-#endif
 	char type[64];
 	unsigned int plen;
 	cell_t *p, *endp;
@@ -1445,9 +1613,6 @@
 	prom_debug("root_size_cells: %x\n", rsc);
 
 	prom_debug("scanning memory:\n");
-#ifdef DEBUG_PROM
-	path = prom_scratch;
-#endif
 
 	for (node = 0; prom_next_node(&node); ) {
 		type[0] = 0;
@@ -1460,7 +1625,7 @@
 			 */
 			prom_getprop(node, "name", type, sizeof(type));
 		}
-		if (strcmp(type, "memory"))
+		if (prom_strcmp(type, "memory"))
 			continue;
 
 		plen = prom_getprop(node, "reg", regbuf, sizeof(regbuf));
@@ -1472,9 +1637,10 @@
 		endp = p + (plen / sizeof(cell_t));
 
 #ifdef DEBUG_PROM
-		memset(path, 0, PROM_SCRATCH_SIZE);
-		call_prom("package-to-path", 3, 1, node, path, PROM_SCRATCH_SIZE-1);
-		prom_debug("  node %s :\n", path);
+		memset(prom_scratch, 0, sizeof(prom_scratch));
+		call_prom("package-to-path", 3, 1, node, prom_scratch,
+			  sizeof(prom_scratch) - 1);
+		prom_debug("  node %s :\n", prom_scratch);
 #endif /* DEBUG_PROM */
 
 		while ((endp - p) >= (rac + rsc)) {
@@ -1562,87 +1728,42 @@
 	}
 }
 
-#ifdef CONFIG_PPC_POWERNV
-
-#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
-static u64 __initdata prom_opal_base;
-static u64 __initdata prom_opal_entry;
-#endif
-
-/*
- * Allocate room for and instantiate OPAL
- */
-static void __init prom_instantiate_opal(void)
+#ifdef CONFIG_PPC_SVM
+static int prom_rtas_hcall(uint64_t args)
 {
-	phandle opal_node;
-	ihandle opal_inst;
-	u64 base, entry;
-	u64 size = 0, align = 0x10000;
-	__be64 val64;
-	u32 rets[2];
+	register uint64_t arg1 asm("r3") = H_RTAS;
+	register uint64_t arg2 asm("r4") = args;
 
-	prom_debug("prom_instantiate_opal: start...\n");
-
-	opal_node = call_prom("finddevice", 1, 1, ADDR("/ibm,opal"));
-	prom_debug("opal_node: %x\n", opal_node);
-	if (!PHANDLE_VALID(opal_node))
-		return;
-
-	val64 = 0;
-	prom_getprop(opal_node, "opal-runtime-size", &val64, sizeof(val64));
-	size = be64_to_cpu(val64);
-	if (size == 0)
-		return;
-	val64 = 0;
-	prom_getprop(opal_node, "opal-runtime-alignment", &val64,sizeof(val64));
-	align = be64_to_cpu(val64);
-
-	base = alloc_down(size, align, 0);
-	if (base == 0) {
-		prom_printf("OPAL allocation failed !\n");
-		return;
-	}
-
-	opal_inst = call_prom("open", 1, 1, ADDR("/ibm,opal"));
-	if (!IHANDLE_VALID(opal_inst)) {
-		prom_printf("opening opal package failed (%x)\n", opal_inst);
-		return;
-	}
-
-	prom_printf("instantiating opal at 0x%llx...", base);
-
-	if (call_prom_ret("call-method", 4, 3, rets,
-			  ADDR("load-opal-runtime"),
-			  opal_inst,
-			  base >> 32, base & 0xffffffff) != 0
-	    || (rets[0] == 0 && rets[1] == 0)) {
-		prom_printf(" failed\n");
-		return;
-	}
-	entry = (((u64)rets[0]) << 32) | rets[1];
-
-	prom_printf(" done\n");
-
-	reserve_mem(base, size);
-
-	prom_debug("opal base     = 0x%llx\n", base);
-	prom_debug("opal align    = 0x%llx\n", align);
-	prom_debug("opal entry    = 0x%llx\n", entry);
-	prom_debug("opal size     = 0x%llx\n", size);
-
-	prom_setprop(opal_node, "/ibm,opal", "opal-base-address",
-		     &base, sizeof(base));
-	prom_setprop(opal_node, "/ibm,opal", "opal-entry-address",
-		     &entry, sizeof(entry));
-
-#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
-	prom_opal_base = base;
-	prom_opal_entry = entry;
-#endif
-	prom_debug("prom_instantiate_opal: end...\n");
+	asm volatile("sc 1\n" : "=r" (arg1) :
+			"r" (arg1),
+			"r" (arg2) :);
+	return arg1;
 }
 
-#endif /* CONFIG_PPC_POWERNV */
+static struct rtas_args __prombss os_term_args;
+
+static void __init prom_rtas_os_term(char *str)
+{
+	phandle rtas_node;
+	__be32 val;
+	u32 token;
+
+	prom_debug("%s: start...\n", __func__);
+	rtas_node = call_prom("finddevice", 1, 1, ADDR("/rtas"));
+	prom_debug("rtas_node: %x\n", rtas_node);
+	if (!PHANDLE_VALID(rtas_node))
+		return;
+
+	val = 0;
+	prom_getprop(rtas_node, "ibm,os-term", &val, sizeof(val));
+	token = be32_to_cpu(val);
+	prom_debug("ibm,os-term: %x\n", token);
+	if (token == 0)
+		prom_panic("Could not get token for ibm,os-term\n");
+	os_term_args.token = cpu_to_be32(token);
+	prom_rtas_hcall((uint64_t)&os_term_args);
+}
+#endif /* CONFIG_PPC_SVM */
 
 /*
  * Allocate room for and instantiate RTAS
@@ -1823,19 +1944,19 @@
 		prom_getprop(node, "device_type", type, sizeof(type));
 		prom_getprop(node, "model", model, sizeof(model));
 
-		if ((type[0] == 0) || (strstr(type, "pci") == NULL))
+		if ((type[0] == 0) || (prom_strstr(type, "pci") == NULL))
 			continue;
 
 		/* Keep the old logic intact to avoid regression. */
 		if (compatible[0] != 0) {
-			if ((strstr(compatible, "python") == NULL) &&
-			    (strstr(compatible, "Speedwagon") == NULL) &&
-			    (strstr(compatible, "Winnipeg") == NULL))
+			if ((prom_strstr(compatible, "python") == NULL) &&
+			    (prom_strstr(compatible, "Speedwagon") == NULL) &&
+			    (prom_strstr(compatible, "Winnipeg") == NULL))
 				continue;
 		} else if (model[0] != 0) {
-			if ((strstr(model, "ython") == NULL) &&
-			    (strstr(model, "peedwagon") == NULL) &&
-			    (strstr(model, "innipeg") == NULL))
+			if ((prom_strstr(model, "ython") == NULL) &&
+			    (prom_strstr(model, "peedwagon") == NULL) &&
+			    (prom_strstr(model, "innipeg") == NULL))
 				continue;
 		}
 
@@ -1863,10 +1984,10 @@
 			local_alloc_bottom = base;
 
 		/* It seems OF doesn't null-terminate the path :-( */
-		memset(path, 0, PROM_SCRATCH_SIZE);
+		memset(path, 0, sizeof(prom_scratch));
 		/* Call OF to setup the TCE hardware */
 		if (call_prom("package-to-path", 3, 1, node,
-			      path, PROM_SCRATCH_SIZE-1) == PROM_ERROR) {
+			      path, sizeof(prom_scratch) - 1) == PROM_ERROR) {
 			prom_printf("package-to-path failed\n");
 		}
 
@@ -1984,12 +2105,12 @@
 
 		type[0] = 0;
 		prom_getprop(node, "device_type", type, sizeof(type));
-		if (strcmp(type, "cpu") != 0)
+		if (prom_strcmp(type, "cpu") != 0)
 			continue;
 
 		/* Skip non-configured cpus. */
 		if (prom_getprop(node, "status", type, sizeof(type)) > 0)
-			if (strcmp(type, "okay") != 0)
+			if (prom_strcmp(type, "okay") != 0)
 				continue;
 
 		reg = cpu_to_be32(-1); /* make sparse happy */
@@ -2065,9 +2186,9 @@
 		return;
 	version[sizeof(version) - 1] = 0;
 	/* XXX might need to add other versions here */
-	if (strcmp(version, "Open Firmware, 1.0.5") == 0)
+	if (prom_strcmp(version, "Open Firmware, 1.0.5") == 0)
 		of_workarounds = OF_WA_CLAIM;
-	else if (strncmp(version, "FirmWorks,3.", 12) == 0) {
+	else if (prom_strncmp(version, "FirmWorks,3.", 12) == 0) {
 		of_workarounds = OF_WA_CLAIM | OF_WA_LONGTRAIL;
 		call_prom("interpret", 1, 1, "dev /memory 0 to allow-reclaim");
 	} else
@@ -2100,7 +2221,7 @@
 	call_prom("instance-to-path", 3, 1, prom.stdout, path, 255);
 	prom_printf("OF stdout device is: %s\n", of_stdout_device);
 	prom_setprop(prom.chosen, "/chosen", "linux,stdout-path",
-		     path, strlen(path) + 1);
+		     path, prom_strlen(path) + 1);
 
 	/* instance-to-package fails on PA-Semi */
 	stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
@@ -2110,7 +2231,7 @@
 		/* If it's a display, note it */
 		memset(type, 0, sizeof(type));
 		prom_getprop(stdout_node, "device_type", type, sizeof(type));
-		if (strcmp(type, "display") == 0)
+		if (prom_strcmp(type, "display") == 0)
 			prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
 	}
 }
@@ -2131,29 +2252,25 @@
 		compat[len] = 0;
 		while (i < len) {
 			char *p = &compat[i];
-			int sl = strlen(p);
+			int sl = prom_strlen(p);
 			if (sl == 0)
 				break;
-			if (strstr(p, "Power Macintosh") ||
-			    strstr(p, "MacRISC"))
+			if (prom_strstr(p, "Power Macintosh") ||
+			    prom_strstr(p, "MacRISC"))
 				return PLATFORM_POWERMAC;
 #ifdef CONFIG_PPC64
 			/* We must make sure we don't detect the IBM Cell
 			 * blades as pSeries due to some firmware issues,
 			 * so we do it here.
 			 */
-			if (strstr(p, "IBM,CBEA") ||
-			    strstr(p, "IBM,CPBW-1.0"))
+			if (prom_strstr(p, "IBM,CBEA") ||
+			    prom_strstr(p, "IBM,CPBW-1.0"))
 				return PLATFORM_GENERIC;
 #endif /* CONFIG_PPC64 */
 			i += sl + 1;
 		}
 	}
 #ifdef CONFIG_PPC64
-	/* Try to detect OPAL */
-	if (PHANDLE_VALID(call_prom("finddevice", 1, 1, ADDR("/ibm,opal"))))
-		return PLATFORM_OPAL;
-
 	/* Try to figure out if it's an IBM pSeries or any other
 	 * PAPR compliant platform. We assume it is if :
 	 *  - /device_type is "chrp" (please, do NOT use that for future
@@ -2164,7 +2281,7 @@
 			   compat, sizeof(compat)-1);
 	if (len <= 0)
 		return PLATFORM_GENERIC;
-	if (strcmp(compat, "chrp"))
+	if (prom_strcmp(compat, "chrp"))
 		return PLATFORM_GENERIC;
 
 	/* Default to pSeries. We need to know if we are running LPAR */
@@ -2202,7 +2319,7 @@
 	ihandle ih;
 	int i;
 
-	static unsigned char default_colors[] = {
+	static const unsigned char default_colors[] __initconst = {
 		0x00, 0x00, 0x00,
 		0x00, 0x00, 0xaa,
 		0x00, 0xaa, 0x00,
@@ -2226,19 +2343,19 @@
 	for (node = 0; prom_next_node(&node); ) {
 		memset(type, 0, sizeof(type));
 		prom_getprop(node, "device_type", type, sizeof(type));
-		if (strcmp(type, "display") != 0)
+		if (prom_strcmp(type, "display") != 0)
 			continue;
 
 		/* It seems OF doesn't null-terminate the path :-( */
 		path = prom_scratch;
-		memset(path, 0, PROM_SCRATCH_SIZE);
+		memset(path, 0, sizeof(prom_scratch));
 
 		/*
 		 * leave some room at the end of the path for appending extra
 		 * arguments
 		 */
 		if (call_prom("package-to-path", 3, 1, node, path,
-			      PROM_SCRATCH_SIZE-10) == PROM_ERROR)
+			      sizeof(prom_scratch) - 10) == PROM_ERROR)
 			continue;
 		prom_printf("found display   : %s, opening... ", path);
 		
@@ -2281,6 +2398,7 @@
 			prom_printf("W=%d H=%d LB=%d addr=0x%x\n",
 				    width, height, pitch, addr);
 			btext_setup_display(width, height, 8, pitch, addr);
+			btext_prepare_BAT();
 		}
 #endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
 	}
@@ -2330,9 +2448,9 @@
 	s = os = (char *)dt_string_start;
 	s += 4;
 	while (s <  (char *)dt_string_end) {
-		if (strcmp(s, str) == 0)
+		if (prom_strcmp(s, str) == 0)
 			return s - os;
-		s += strlen(s) + 1;
+		s += prom_strlen(s) + 1;
 	}
 	return 0;
 }
@@ -2365,7 +2483,7 @@
 		}
 
  		/* skip "name" */
- 		if (strcmp(namep, "name") == 0) {
+		if (prom_strcmp(namep, "name") == 0) {
  			*mem_start = (unsigned long)namep;
  			prev_name = "name";
  			continue;
@@ -2377,7 +2495,7 @@
 			namep = sstart + soff;
 		} else {
 			/* Trim off some if we can */
-			*mem_start = (unsigned long)namep + strlen(namep) + 1;
+			*mem_start = (unsigned long)namep + prom_strlen(namep) + 1;
 			dt_string_end = *mem_start;
 		}
 		prev_name = namep;
@@ -2398,7 +2516,7 @@
 	char *namep, *prev_name, *sstart, *p, *ep, *lp, *path;
 	unsigned long soff;
 	unsigned char *valp;
-	static char pname[MAX_PROPERTY_NAME];
+	static char pname[MAX_PROPERTY_NAME] __prombss;
 	int l, room, has_phandle = 0;
 
 	dt_push_token(OF_DT_BEGIN_NODE, mem_start, mem_end);
@@ -2434,8 +2552,8 @@
 
 	/* get it again for debugging */
 	path = prom_scratch;
-	memset(path, 0, PROM_SCRATCH_SIZE);
-	call_prom("package-to-path", 3, 1, node, path, PROM_SCRATCH_SIZE-1);
+	memset(path, 0, sizeof(prom_scratch));
+	call_prom("package-to-path", 3, 1, node, path, sizeof(prom_scratch) - 1);
 
 	/* get and store all properties */
 	prev_name = "";
@@ -2446,7 +2564,7 @@
 			break;
 
  		/* skip "name" */
- 		if (strcmp(pname, "name") == 0) {
+		if (prom_strcmp(pname, "name") == 0) {
  			prev_name = "name";
  			continue;
  		}
@@ -2477,18 +2595,15 @@
 		call_prom("getprop", 4, 1, node, pname, valp, l);
 		*mem_start = _ALIGN(*mem_start, 4);
 
-		if (!strcmp(pname, "phandle"))
+		if (!prom_strcmp(pname, "phandle"))
 			has_phandle = 1;
 	}
 
-	/* Add a "linux,phandle" property if no "phandle" property already
-	 * existed (can happen with OPAL)
-	 */
+	/* Add a "phandle" property if none already exist */
 	if (!has_phandle) {
-		soff = dt_find_string("linux,phandle");
+		soff = dt_find_string("phandle");
 		if (soff == 0)
-			prom_printf("WARNING: Can't find string index for"
-				    " <linux-phandle> node %s\n", path);
+			prom_printf("WARNING: Can't find string index for <phandle> node %s\n", path);
 		else {
 			dt_push_token(OF_DT_PROP, mem_start, mem_end);
 			dt_push_token(4, mem_start, mem_end);
@@ -2548,10 +2663,10 @@
 	dt_string_start = mem_start;
 	mem_start += 4; /* hole */
 
-	/* Add "linux,phandle" in there, we'll need it */
+	/* Add "phandle" in there, we'll need it */
 	namep = make_room(&mem_start, &mem_end, 16, 1);
-	strcpy(namep, "linux,phandle");
-	mem_start = (unsigned long)namep + strlen(namep) + 1;
+	prom_strcpy(namep, "phandle");
+	mem_start = (unsigned long)namep + prom_strlen(namep) + 1;
 
 	/* Build string array */
 	prom_printf("Building dt strings...\n"); 
@@ -2873,7 +2988,7 @@
 	rv = prom_getprop(node, "model", prop, sizeof(prop));
 	if (rv == PROM_ERROR)
 		return;
-	if (strcmp(prop, "EFIKA5K2"))
+	if (prom_strcmp(prop, "EFIKA5K2"))
 		return;
 
 	prom_printf("Applying EFIKA device tree fixups\n");
@@ -2881,13 +2996,13 @@
 	/* Claiming to be 'chrp' is death */
 	node = call_prom("finddevice", 1, 1, ADDR("/"));
 	rv = prom_getprop(node, "device_type", prop, sizeof(prop));
-	if (rv != PROM_ERROR && (strcmp(prop, "chrp") == 0))
+	if (rv != PROM_ERROR && (prom_strcmp(prop, "chrp") == 0))
 		prom_setprop(node, "/", "device_type", "efika", sizeof("efika"));
 
 	/* CODEGEN,description is exposed in /proc/cpuinfo so
 	   fix that too */
 	rv = prom_getprop(node, "CODEGEN,description", prop, sizeof(prop));
-	if (rv != PROM_ERROR && (strstr(prop, "CHRP")))
+	if (rv != PROM_ERROR && (prom_strstr(prop, "CHRP")))
 		prom_setprop(node, "/", "CODEGEN,description",
 			     "Efika 5200B PowerPC System",
 			     sizeof("Efika 5200B PowerPC System"));
@@ -3106,6 +3221,59 @@
 #endif
 #endif
 
+#ifdef CONFIG_PPC_SVM
+/*
+ * Perform the Enter Secure Mode ultracall.
+ */
+static int enter_secure_mode(unsigned long kbase, unsigned long fdt)
+{
+	register unsigned long r3 asm("r3") = UV_ESM;
+	register unsigned long r4 asm("r4") = kbase;
+	register unsigned long r5 asm("r5") = fdt;
+
+	asm volatile("sc 2" : "+r"(r3) : "r"(r4), "r"(r5));
+
+	return r3;
+}
+
+/*
+ * Call the Ultravisor to transfer us to secure memory if we have an ESM blob.
+ */
+static void setup_secure_guest(unsigned long kbase, unsigned long fdt)
+{
+	int ret;
+
+	if (!prom_svm_enable)
+		return;
+
+	/* Switch to secure mode. */
+	prom_printf("Switching to secure mode.\n");
+
+	/*
+	 * The ultravisor will do an integrity check of the kernel image but we
+	 * relocated it so the check will fail. Restore the original image by
+	 * relocating it back to the kernel virtual base address.
+	 */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(KERNELBASE);
+
+	ret = enter_secure_mode(kbase, fdt);
+
+	/* Relocate the kernel again. */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(kbase);
+
+	if (ret != U_SUCCESS) {
+		prom_printf("Returned %d from switching to secure mode.\n", ret);
+		prom_rtas_os_term("Switch to secure mode failed.\n");
+	}
+}
+#else
+static void setup_secure_guest(unsigned long kbase, unsigned long fdt)
+{
+}
+#endif /* CONFIG_PPC_SVM */
+
 /*
  * We enter here early on, when the Open Firmware prom is still
  * handling exceptions and the MMU hash table for us.
@@ -3172,7 +3340,7 @@
 	 */
 	early_cmdline_parse();
 
-#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+#ifdef CONFIG_PPC_PSERIES
 	/*
 	 * On pSeries, inform the firmware about our capabilities
 	 */
@@ -3216,15 +3384,9 @@
 	 * On non-powermacs, try to instantiate RTAS. PowerMacs don't
 	 * have a usable RTAS implementation.
 	 */
-	if (of_platform != PLATFORM_POWERMAC &&
-	    of_platform != PLATFORM_OPAL)
+	if (of_platform != PLATFORM_POWERMAC)
 		prom_instantiate_rtas();
 
-#ifdef CONFIG_PPC_POWERNV
-	if (of_platform == PLATFORM_OPAL)
-		prom_instantiate_opal();
-#endif /* CONFIG_PPC_POWERNV */
-
 #ifdef CONFIG_PPC64
 	/* instantiate sml */
 	prom_instantiate_sml();
@@ -3237,8 +3399,7 @@
 	 *
 	 * (This must be done after instanciating RTAS)
 	 */
-	if (of_platform != PLATFORM_POWERMAC &&
-	    of_platform != PLATFORM_OPAL)
+	if (of_platform != PLATFORM_POWERMAC)
 		prom_hold_cpus();
 
 	/*
@@ -3282,11 +3443,9 @@
 	/*
 	 * in case stdin is USB and still active on IBM machines...
 	 * Unfortunately quiesce crashes on some powermacs if we have
-	 * closed stdin already (in particular the powerbook 101). It
-	 * appears that the OPAL version of OFW doesn't like it either.
+	 * closed stdin already (in particular the powerbook 101).
 	 */
-	if (of_platform != PLATFORM_POWERMAC &&
-	    of_platform != PLATFORM_OPAL)
+	if (of_platform != PLATFORM_POWERMAC)
 		prom_close_stdin();
 
 	/*
@@ -3304,10 +3463,8 @@
 	hdr = dt_header_start;
 
 	/* Don't print anything after quiesce under OPAL, it crashes OFW */
-	if (of_platform != PLATFORM_OPAL) {
-		prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase);
-		prom_debug("->dt_header_start=0x%lx\n", hdr);
-	}
+	prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase);
+	prom_debug("->dt_header_start=0x%lx\n", hdr);
 
 #ifdef CONFIG_PPC32
 	reloc_got2(-offset);
@@ -3315,13 +3472,10 @@
 	unreloc_toc();
 #endif
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
-	/* OPAL early debug gets the OPAL base & entry in r8 and r9 */
-	__start(hdr, kbase, 0, 0, 0,
-		prom_opal_base, prom_opal_entry);
-#else
+	/* Move to secure memory if we're supposed to be secure guests. */
+	setup_secure_guest(kbase, hdr);
+
 	__start(hdr, kbase, 0, 0, 0, 0, 0);
-#endif
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index acb6b92..b183ab9 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -1,11 +1,8 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
 #
 # Copyright © 2008 IBM 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; either version
-# 2 of the License, or (at your option) any later version.
 
 # This script checks prom_init.o to see what external symbols it
 # is using, if it finds symbols not in the whitelist it returns
@@ -16,18 +13,39 @@
 # If you really need to reference something from prom_init.o add
 # it to the list below:
 
+grep "^CONFIG_KASAN=y$" .config >/dev/null
+if [ $? -eq 0 ]
+then
+	MEM_FUNCS="__memcpy __memset"
+else
+	MEM_FUNCS="memcpy memset"
+fi
+
 WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush
-_end enter_prom memcpy memset reloc_offset __secondary_hold
+_end enter_prom $MEM_FUNCS reloc_offset __secondary_hold
 __secondary_hold_acknowledge __secondary_hold_spinloop __start
-strcmp strcpy strlcpy strlen strncmp strstr kstrtobool logo_linux_clut224
+logo_linux_clut224 btext_prepare_BAT
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
-__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC."
+__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC.
+relocate"
 
 NM="$1"
 OBJ="$2"
 
 ERROR=0
 
+check_section()
+{
+    file=$1
+    section=$2
+    size=$(objdump -h -j $section $file 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
+    size=${size:-0}
+    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}')
 do
 	# On 64-bit nm gives us the function descriptors, which have
@@ -66,4 +84,8 @@
 	fi
 done
 
+check_section $OBJ .data
+check_section $OBJ .bss
+check_section $OBJ .init.data
+
 exit $ERROR
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 9667666..8c92feb 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -33,6 +33,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
 #include <linux/context_tracking.h>
+#include <linux/nospec.h>
 
 #include <linux/uaccess.h>
 #include <linux/pkeys.h>
@@ -42,6 +43,7 @@
 #include <asm/tm.h>
 #include <asm/asm-prototypes.h>
 #include <asm/debug.h>
+#include <asm/hw_breakpoint.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -274,6 +276,8 @@
  */
 int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data)
 {
+	unsigned int regs_max;
+
 	if ((task->thread.regs == NULL) || !data)
 		return -EIO;
 
@@ -297,7 +301,9 @@
 	}
 #endif
 
-	if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) {
+	regs_max = sizeof(struct user_pt_regs) / sizeof(unsigned long);
+	if (regno < regs_max) {
+		regno = array_index_nospec(regno, regs_max);
 		*data = ((unsigned long *)task->thread.regs)[regno];
 		return 0;
 	}
@@ -321,6 +327,7 @@
 		return set_user_dscr(task, data);
 
 	if (regno <= PT_MAX_PUT_REG) {
+		regno = array_index_nospec(regno, PT_MAX_PUT_REG + 1);
 		((unsigned long *)task->thread.regs)[regno] = data;
 		return 0;
 	}
@@ -360,10 +367,10 @@
 		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 					  &target->thread.regs->orig_gpr3,
 					  offsetof(struct pt_regs, orig_gpr3),
-					  sizeof(struct pt_regs));
+					  sizeof(struct user_pt_regs));
 	if (!ret)
 		ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
-					       sizeof(struct pt_regs), -1);
+					       sizeof(struct user_pt_regs), -1);
 
 	return ret;
 }
@@ -561,6 +568,7 @@
 		/*
 		 * Copy out only the low-order word of vrsave.
 		 */
+		int start, end;
 		union {
 			elf_vrreg_t reg;
 			u32 word;
@@ -569,8 +577,10 @@
 
 		vrsave.word = target->thread.vrsave;
 
+		start = 33 * sizeof(vector128);
+		end = start + sizeof(vrsave);
 		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave,
-					  33 * sizeof(vector128), -1);
+					  start, end);
 	}
 
 	return ret;
@@ -608,6 +618,7 @@
 		/*
 		 * We use only the first word of vrsave.
 		 */
+		int start, end;
 		union {
 			elf_vrreg_t reg;
 			u32 word;
@@ -616,8 +627,10 @@
 
 		vrsave.word = target->thread.vrsave;
 
+		start = 33 * sizeof(vector128);
+		end = start + sizeof(vrsave);
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
-					 33 * sizeof(vector128), -1);
+					 start, end);
 		if (!ret)
 			target->thread.vrsave = vrsave.word;
 	}
@@ -853,10 +866,10 @@
 		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 					  &target->thread.ckpt_regs.orig_gpr3,
 					  offsetof(struct pt_regs, orig_gpr3),
-					  sizeof(struct pt_regs));
+					  sizeof(struct user_pt_regs));
 	if (!ret)
 		ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
-					       sizeof(struct pt_regs), -1);
+					       sizeof(struct user_pt_regs), -1);
 
 	return ret;
 }
@@ -1609,7 +1622,7 @@
 		      void *kbuf, void __user *ubuf)
 {
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.ppr, 0, sizeof(u64));
+				   &target->thread.regs->ppr, 0, sizeof(u64));
 }
 
 static int ppr_set(struct task_struct *target,
@@ -1618,7 +1631,7 @@
 		      const void *kbuf, const void __user *ubuf)
 {
 	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.ppr, 0, sizeof(u64));
+				  &target->thread.regs->ppr, 0, sizeof(u64));
 }
 
 static int dscr_get(struct task_struct *target,
@@ -3075,7 +3088,7 @@
 		dbginfo.sizeof_condition = 0;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		dbginfo.features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
-		if (cpu_has_feature(CPU_FTR_DAWR))
+		if (dawr_enabled())
 			dbginfo.features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR;
 #else
 		dbginfo.features = 0;
@@ -3130,7 +3143,7 @@
 	case PTRACE_GETREGS:	/* Get all pt_regs from the child. */
 		return copy_regset_to_user(child, &user_ppc_native_view,
 					   REGSET_GPR,
-					   0, sizeof(struct pt_regs),
+					   0, sizeof(struct user_pt_regs),
 					   datavp);
 
 #ifdef CONFIG_PPC64
@@ -3139,7 +3152,7 @@
 	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
 		return copy_regset_from_user(child, &user_ppc_native_view,
 					     REGSET_GPR,
-					     0, sizeof(struct pt_regs),
+					     0, sizeof(struct user_pt_regs),
 					     datavp);
 
 	case PTRACE_GETFPREGS: /* Get the child FPU state (FPR0...31 + FPSCR) */
@@ -3262,17 +3275,40 @@
  */
 long do_syscall_trace_enter(struct pt_regs *regs)
 {
+	u32 flags;
+
 	user_exit();
 
-	/*
-	 * The tracer may decide to abort the syscall, if so tracehook
-	 * will return !0. Note that the tracer may also just change
-	 * regs->gpr[0] to an invalid syscall number, that is handled
-	 * below on the exit path.
-	 */
-	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    tracehook_report_syscall_entry(regs))
-		goto skip;
+	flags = READ_ONCE(current_thread_info()->flags) &
+		(_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
+
+	if (flags) {
+		int rc = tracehook_report_syscall_entry(regs);
+
+		if (unlikely(flags & _TIF_SYSCALL_EMU)) {
+			/*
+			 * A nonzero return code from
+			 * tracehook_report_syscall_entry() tells us to prevent
+			 * the syscall execution, but we are not going to
+			 * execute it anyway.
+			 *
+			 * Returning -1 will skip the syscall execution. We want
+			 * to avoid clobbering any registers, so we don't goto
+			 * the skip label below.
+			 */
+			return -1;
+		}
+
+		if (rc) {
+			/*
+			 * The tracer decided to abort the syscall. Note that
+			 * the tracer may also just change regs->gpr[0] to an
+			 * invalid syscall number, that is handled below on the
+			 * exit path.
+			 */
+			goto skip;
+		}
+	}
 
 	/* Run seccomp after ptrace; allow it to set gpr[3]. */
 	if (do_seccomp(regs))
@@ -3324,3 +3360,42 @@
 
 	user_enter();
 }
+
+void __init pt_regs_check(void)
+{
+	BUILD_BUG_ON(offsetof(struct pt_regs, gpr) !=
+		     offsetof(struct user_pt_regs, gpr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, nip) !=
+		     offsetof(struct user_pt_regs, nip));
+	BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
+		     offsetof(struct user_pt_regs, msr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
+		     offsetof(struct user_pt_regs, msr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+		     offsetof(struct user_pt_regs, orig_gpr3));
+	BUILD_BUG_ON(offsetof(struct pt_regs, ctr) !=
+		     offsetof(struct user_pt_regs, ctr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, link) !=
+		     offsetof(struct user_pt_regs, link));
+	BUILD_BUG_ON(offsetof(struct pt_regs, xer) !=
+		     offsetof(struct user_pt_regs, xer));
+	BUILD_BUG_ON(offsetof(struct pt_regs, ccr) !=
+		     offsetof(struct user_pt_regs, ccr));
+#ifdef __powerpc64__
+	BUILD_BUG_ON(offsetof(struct pt_regs, softe) !=
+		     offsetof(struct user_pt_regs, softe));
+#else
+	BUILD_BUG_ON(offsetof(struct pt_regs, mq) !=
+		     offsetof(struct user_pt_regs, mq));
+#endif
+	BUILD_BUG_ON(offsetof(struct pt_regs, trap) !=
+		     offsetof(struct user_pt_regs, trap));
+	BUILD_BUG_ON(offsetof(struct pt_regs, dar) !=
+		     offsetof(struct user_pt_regs, dar));
+	BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
+		     offsetof(struct user_pt_regs, dsisr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, result) !=
+		     offsetof(struct user_pt_regs, result));
+
+	BUILD_BUG_ON(sizeof(struct user_pt_regs) > sizeof(struct pt_regs));
+}
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
index f366fed..10e96f3 100644
--- a/arch/powerpc/kernel/reloc_32.S
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Code to process dynamic relocations for PPC32.
  *
@@ -5,11 +6,6 @@
  *	Author: Suzuki Poulose <suzuki@in.ibm.com>
  *
  *  - Based on ppc64 code - reloc_64.S
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index e8cfc69..02d4719 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Code to process dynamic relocations in the kernel.
  *
  * Copyright 2008 Paul Mackerras, IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 8afd146..c5fa251 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *
  * Procedures for interfacing to the RTAS on CHRP machines.
  *
  * Peter Bergner, IBM	March 2001.
  * Copyright (C) 2001 IBM.
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <stdarg.h>
@@ -20,6 +16,7 @@
 #include <linux/capability.h>
 #include <linux/delay.h>
 #include <linux/cpu.h>
+#include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/completion.h>
 #include <linux/cpumask.h>
@@ -875,15 +872,17 @@
 		return 0;
 
 	for_each_cpu(cpu, cpus) {
+		struct device *dev = get_cpu_device(cpu);
+
 		switch (state) {
 		case DOWN:
-			cpuret = cpu_down(cpu);
+			cpuret = device_offline(dev);
 			break;
 		case UP:
-			cpuret = cpu_up(cpu);
+			cpuret = device_online(dev);
 			break;
 		}
-		if (cpuret) {
+		if (cpuret < 0) {
 			pr_debug("%s: cpu_%s for cpu#%d returned %d.\n",
 					__func__,
 					((state == UP) ? "up" : "down"),
@@ -900,6 +899,7 @@
 				cpumask_clear_cpu(cpu, cpus);
 			}
 		}
+		cond_resched();
 	}
 
 	return ret;
@@ -926,13 +926,11 @@
 
 	return ret;
 }
-EXPORT_SYMBOL(rtas_online_cpus_mask);
 
 int rtas_offline_cpus_mask(cpumask_var_t cpus)
 {
 	return rtas_cpu_state_change_mask(DOWN, cpus);
 }
-EXPORT_SYMBOL(rtas_offline_cpus_mask);
 
 int rtas_ibm_suspend_me(u64 handle)
 {
@@ -972,6 +970,8 @@
 	data.token = rtas_token("ibm,suspend-me");
 	data.complete = &done;
 
+	lock_device_hotplug();
+
 	/* All present CPUs must be online */
 	cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask);
 	cpuret = rtas_online_cpus_mask(offline_mask);
@@ -981,20 +981,27 @@
 		goto out;
 	}
 
-	stop_topology_update();
+	cpu_hotplug_disable();
+
+	/* Check if we raced with a CPU-Offline Operation */
+	if (!cpumask_equal(cpu_present_mask, cpu_online_mask)) {
+		pr_info("%s: Raced against a concurrent CPU-Offline\n", __func__);
+		atomic_set(&data.error, -EAGAIN);
+		goto out_hotplug_enable;
+	}
 
 	/* Call function on all CPUs.  One of us will make the
 	 * rtas call
 	 */
-	if (on_each_cpu(rtas_percpu_suspend_me, &data, 0))
-		atomic_set(&data.error, -EINVAL);
+	on_each_cpu(rtas_percpu_suspend_me, &data, 0);
 
 	wait_for_completion(&done);
 
 	if (atomic_read(&data.error) != 0)
 		printk(KERN_ERR "Error doing global join\n");
 
-	start_topology_update();
+out_hotplug_enable:
+	cpu_hotplug_enable();
 
 	/* Take down CPUs not online prior to suspend */
 	cpuret = rtas_offline_cpus_mask(offline_mask);
@@ -1003,6 +1010,7 @@
 				__func__);
 
 out:
+	unlock_device_hotplug();
 	free_cpumask_var(offline_mask);
 	return atomic_read(&data.error);
 }
@@ -1178,7 +1186,11 @@
 		ibm_suspend_me_token = rtas_token("ibm,suspend-me");
 	}
 #endif
-	rtas_rmo_buf = memblock_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region);
+	rtas_rmo_buf = memblock_phys_alloc_range(RTAS_RMOBUF_MAX, PAGE_SIZE,
+						 0, rtas_region);
+	if (!rtas_rmo_buf)
+		panic("ERROR: RTAS: Failed to allocate %lx bytes below %pa\n",
+		      PAGE_SIZE, &rtas_region);
 
 #ifdef CONFIG_RTAS_ERROR_LOGGING
 	rtas_last_error_token = rtas_token("rtas-last-error");
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 10fabae..84f7947 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  c 2001 PPC 64 Team, IBM Corp
  *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- *
  * /proc/powerpc/rtas/firmware_flash interface
  *
  * This file implements a firmware_flash interface to pump a firmware
@@ -523,7 +519,7 @@
 		args_buf->status = VALIDATE_INCOMPLETE;
 	}
 
-	if (!access_ok(VERIFY_READ, buf, count)) {
+	if (!access_ok(buf, count)) {
 		rc = -EFAULT;
 		goto done;
 	}
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index c2b148b..ae5e43e 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2001 Dave Engebretsen, IBM Corporation
  * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
@@ -5,20 +6,6 @@
  * RTAS specific routines for PCI.
  *
  * Based on code from pci.c, chrp_pci.c and pSeries_pci.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 44d66c3..8d02e04 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * Communication to userspace based on kernel/printk.c
  */
 
@@ -91,6 +87,8 @@
 			return "Dump Notification Event";
 		case RTAS_TYPE_PRRN:
 			return "Platform Resource Reassignment Event";
+		case RTAS_TYPE_HOTPLUG:
+			return "Hotplug Event";
 	}
 
 	return rtas_type[0];
@@ -150,8 +148,10 @@
 	} else {
 		struct rtas_error_log *errlog = (struct rtas_error_log *)buf;
 
-		printk(RTAS_DEBUG "event: %d, Type: %s, Severity: %d\n",
-		       error_log_cnt, rtas_event_type(rtas_error_type(errlog)),
+		printk(RTAS_DEBUG "event: %d, Type: %s (%d), Severity: %d\n",
+		       error_log_cnt,
+		       rtas_event_type(rtas_error_type(errlog)),
+		       rtas_error_type(errlog),
 		       rtas_error_severity(errlog));
 	}
 }
@@ -274,27 +274,16 @@
 }
 
 #ifdef CONFIG_PPC_PSERIES
-static s32 prrn_update_scope;
-
-static void prrn_work_fn(struct work_struct *work)
+static void handle_prrn_event(s32 scope)
 {
 	/*
 	 * For PRRN, we must pass the negative of the scope value in
 	 * the RTAS event.
 	 */
-	pseries_devicetree_update(-prrn_update_scope);
+	pseries_devicetree_update(-scope);
 	numa_update_cpu_topology(false);
 }
 
-static DECLARE_WORK(prrn_work, prrn_work_fn);
-
-static void prrn_schedule_update(u32 scope)
-{
-	flush_work(&prrn_work);
-	prrn_update_scope = scope;
-	schedule_work(&prrn_work);
-}
-
 static void handle_rtas_event(const struct rtas_error_log *log)
 {
 	if (rtas_error_type(log) != RTAS_TYPE_PRRN || !prrn_is_enabled())
@@ -303,7 +292,7 @@
 	/* For PRRN Events the extended log length is used to denote
 	 * the scope for calling rtas update-nodes.
 	 */
-	prrn_schedule_update(rtas_error_extended_log_length(log));
+	handle_prrn_event(rtas_error_extended_log_length(log));
 }
 
 #else
@@ -342,7 +331,7 @@
 
 	count = rtas_error_log_buffer_max;
 
-	if (!access_ok(VERIFY_WRITE, buf, count))
+	if (!access_ok(buf, count))
 		return -EFAULT;
 
 	tmp = kmalloc(count, GFP_KERNEL);
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index f6f469f..bd91dce 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -4,6 +4,7 @@
 //
 // Copyright 2018, Michael Ellerman, IBM Corporation.
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/device.h>
 #include <linux/seq_buf.h>
@@ -22,10 +23,15 @@
 	COUNT_CACHE_FLUSH_SW	= 0x2,
 	COUNT_CACHE_FLUSH_HW	= 0x4,
 };
-static enum count_cache_flush_type count_cache_flush_type;
+static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
+static bool link_stack_flush_enabled;
 
 bool barrier_nospec_enabled;
 static bool no_nospec;
+static bool btb_flush_enabled;
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64)
+static bool no_spectrev2;
+#endif
 
 static void enable_barrier_nospec(bool enable)
 {
@@ -52,7 +58,7 @@
 	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
 		 security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR);
 
-	if (!no_nospec)
+	if (!no_nospec && !cpu_mitigations_off())
 		enable_barrier_nospec(enable);
 }
 
@@ -99,8 +105,36 @@
 	return 0;
 }
 device_initcall(barrier_nospec_debugfs_init);
+
+static __init int security_feature_debugfs_init(void)
+{
+	debugfs_create_x64("security_features", 0400, powerpc_debugfs_root,
+			   (u64 *)&powerpc_security_features);
+	return 0;
+}
+device_initcall(security_feature_debugfs_init);
 #endif /* CONFIG_DEBUG_FS */
 
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64)
+static int __init handle_nospectre_v2(char *p)
+{
+	no_spectrev2 = true;
+
+	return 0;
+}
+early_param("nospectre_v2", handle_nospectre_v2);
+#endif /* CONFIG_PPC_FSL_BOOK3E || CONFIG_PPC_BOOK3S_64 */
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+void setup_spectre_v2(void)
+{
+	if (no_spectrev2 || cpu_mitigations_off())
+		do_btb_flush_fixups();
+	else
+		btb_flush_enabled = true;
+}
+#endif /* CONFIG_PPC_FSL_BOOK3E */
+
 #ifdef CONFIG_PPC_BOOK3S_64
 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
 {
@@ -168,31 +202,35 @@
 	bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED);
 	ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED);
 
-	if (bcs || ccd || count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) {
-		bool comma = false;
+	if (bcs || ccd) {
 		seq_buf_printf(&s, "Mitigation: ");
 
-		if (bcs) {
+		if (bcs)
 			seq_buf_printf(&s, "Indirect branch serialisation (kernel only)");
-			comma = true;
-		}
 
-		if (ccd) {
-			if (comma)
-				seq_buf_printf(&s, ", ");
-			seq_buf_printf(&s, "Indirect branch cache disabled");
-			comma = true;
-		}
-
-		if (comma)
+		if (bcs && ccd)
 			seq_buf_printf(&s, ", ");
 
-		seq_buf_printf(&s, "Software count cache flush");
+		if (ccd)
+			seq_buf_printf(&s, "Indirect branch cache disabled");
+
+		if (link_stack_flush_enabled)
+			seq_buf_printf(&s, ", Software link stack flush");
+
+	} else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) {
+		seq_buf_printf(&s, "Mitigation: Software count cache flush");
 
 		if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW)
-			seq_buf_printf(&s, "(hardware accelerated)");
-	} else
+			seq_buf_printf(&s, " (hardware accelerated)");
+
+		if (link_stack_flush_enabled)
+			seq_buf_printf(&s, ", Software link stack flush");
+
+	} else if (btb_flush_enabled) {
+		seq_buf_printf(&s, "Mitigation: Branch predictor state flush");
+	} else {
 		seq_buf_printf(&s, "Vulnerable");
+	}
 
 	seq_buf_printf(&s, "\n");
 
@@ -282,7 +320,7 @@
 
 	stf_enabled_flush_types = type;
 
-	if (!no_stf_barrier)
+	if (!no_stf_barrier && !cpu_mitigations_off())
 		stf_barrier_enable(enable);
 }
 
@@ -348,18 +386,49 @@
 device_initcall(stf_barrier_debugfs_init);
 #endif /* CONFIG_DEBUG_FS */
 
+static void no_count_cache_flush(void)
+{
+	count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
+	pr_info("count-cache-flush: software flush disabled.\n");
+}
+
 static void toggle_count_cache_flush(bool enable)
 {
-	if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+	if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) &&
+	    !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK))
+		enable = false;
+
+	if (!enable) {
 		patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP);
-		count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
-		pr_info("count-cache-flush: software flush disabled.\n");
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		patch_instruction_site(&patch__call_kvm_flush_link_stack, PPC_INST_NOP);
+#endif
+		pr_info("link-stack-flush: software flush disabled.\n");
+		link_stack_flush_enabled = false;
+		no_count_cache_flush();
 		return;
 	}
 
+	// This enables the branch from _switch to flush_count_cache
 	patch_branch_site(&patch__call_flush_count_cache,
 			  (u64)&flush_count_cache, BRANCH_SET_LINK);
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	// This enables the branch from guest_exit_cont to kvm_flush_link_stack
+	patch_branch_site(&patch__call_kvm_flush_link_stack,
+			  (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
+#endif
+
+	pr_info("link-stack-flush: software flush enabled.\n");
+	link_stack_flush_enabled = true;
+
+	// If we just need to flush the link stack, patch an early return
+	if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+		patch_instruction_site(&patch__flush_link_stack_return, PPC_INST_BLR);
+		no_count_cache_flush();
+		return;
+	}
+
 	if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) {
 		count_cache_flush_type = COUNT_CACHE_FLUSH_SW;
 		pr_info("count-cache-flush: full software flush sequence enabled.\n");
@@ -373,7 +442,26 @@
 
 void setup_count_cache_flush(void)
 {
-	toggle_count_cache_flush(true);
+	bool enable = true;
+
+	if (no_spectrev2 || cpu_mitigations_off()) {
+		if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) ||
+		    security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED))
+			pr_warn("Spectre v2 mitigations not fully under software control, can't disable\n");
+
+		enable = false;
+	}
+
+	/*
+	 * There's no firmware feature flag/hypervisor bit to tell us we need to
+	 * flush the link stack on context switch. So we set it here if we see
+	 * either of the Spectre v2 mitigations that aim to protect userspace.
+	 */
+	if (security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED) ||
+	    security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE))
+		security_ftr_set(SEC_FTR_FLUSH_LINK_STACK);
+
+	toggle_count_cache_flush(enable);
 }
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 93fa0c9..25aaa39 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Common boot and setup code for both 32-bit and 64-bit.
  * Extracted from arch/powerpc/kernel/setup_64.c.
  *
  * Copyright (C) 2001 PPC64 Team, IBM Corp
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
@@ -67,6 +63,7 @@
 #include <asm/livepatch.h>
 #include <asm/mmu_context.h>
 #include <asm/cpu_has_feature.h>
+#include <asm/kasan.h>
 
 #include "setup.h"
 
@@ -133,13 +130,11 @@
 /* also used by kexec */
 void machine_shutdown(void)
 {
-#ifdef CONFIG_FA_DUMP
 	/*
 	 * if fadump is active, cleanup the fadump registration before we
 	 * shutdown.
 	 */
 	fadump_cleanup();
-#endif
 
 	if (ppc_md.machine_shutdown)
 		ppc_md.machine_shutdown();
@@ -200,14 +195,15 @@
 {
 	struct device_node *root;
 	const char *model = NULL;
-#if defined(CONFIG_SMP) && defined(CONFIG_PPC32)
 	unsigned long bogosum = 0;
 	int i;
-	for_each_online_cpu(i)
-		bogosum += loops_per_jiffy;
-	seq_printf(m, "total bogomips\t: %lu.%02lu\n",
-		   bogosum/(500000/HZ), bogosum/(5000/HZ) % 100);
-#endif /* CONFIG_SMP && CONFIG_PPC32 */
+
+	if (IS_ENABLED(CONFIG_SMP) && IS_ENABLED(CONFIG_PPC32)) {
+		for_each_online_cpu(i)
+			bogosum += loops_per_jiffy;
+		seq_printf(m, "total bogomips\t: %lu.%02lu\n",
+			   bogosum / (500000 / HZ), bogosum / (5000 / HZ) % 100);
+	}
 	seq_printf(m, "timebase\t: %lu\n", ppc_tb_freq);
 	if (ppc_md.name)
 		seq_printf(m, "platform\t: %s\n", ppc_md.name);
@@ -221,11 +217,10 @@
 	if (ppc_md.show_cpuinfo != NULL)
 		ppc_md.show_cpuinfo(m);
 
-#ifdef CONFIG_PPC32
 	/* Display the amount of memory */
-	seq_printf(m, "Memory\t\t: %d MB\n",
-		   (unsigned int)(total_memory / (1024 * 1024)));
-#endif
+	if (IS_ENABLED(CONFIG_PPC32))
+		seq_printf(m, "Memory\t\t: %d MB\n",
+			   (unsigned int)(total_memory / (1024 * 1024)));
 }
 
 static int show_cpuinfo(struct seq_file *m, void *v)
@@ -252,26 +247,24 @@
 	else
 		seq_printf(m, "unknown (%08x)", pvr);
 
-#ifdef CONFIG_ALTIVEC
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		seq_printf(m, ", altivec supported");
-#endif /* CONFIG_ALTIVEC */
 
 	seq_printf(m, "\n");
 
 #ifdef CONFIG_TAU
-	if (cur_cpu_spec->cpu_features & CPU_FTR_TAU) {
-#ifdef CONFIG_TAU_AVERAGE
-		/* more straightforward, but potentially misleading */
-		seq_printf(m,  "temperature \t: %u C (uncalibrated)\n",
-			   cpu_temp(cpu_id));
-#else
-		/* show the actual temp sensor range */
-		u32 temp;
-		temp = cpu_temp_both(cpu_id);
-		seq_printf(m, "temperature \t: %u-%u C (uncalibrated)\n",
-			   temp & 0xff, temp >> 16);
-#endif
+	if (cpu_has_feature(CPU_FTR_TAU)) {
+		if (IS_ENABLED(CONFIG_TAU_AVERAGE)) {
+			/* more straightforward, but potentially misleading */
+			seq_printf(m,  "temperature \t: %u C (uncalibrated)\n",
+				   cpu_temp(cpu_id));
+		} else {
+			/* show the actual temp sensor range */
+			u32 temp;
+			temp = cpu_temp_both(cpu_id);
+			seq_printf(m, "temperature \t: %u-%u C (uncalibrated)\n",
+				   temp & 0xff, temp >> 16);
+		}
 	}
 #endif /* CONFIG_TAU */
 
@@ -335,11 +328,10 @@
 	seq_printf(m, "revision\t: %hd.%hd (pvr %04x %04x)\n",
 		   maj, min, PVR_VER(pvr), PVR_REV(pvr));
 
-#ifdef CONFIG_PPC32
-	seq_printf(m, "bogomips\t: %lu.%02lu\n",
-		   loops_per_jiffy / (500000/HZ),
-		   (loops_per_jiffy / (5000/HZ)) % 100);
-#endif
+	if (IS_ENABLED(CONFIG_PPC32))
+		seq_printf(m, "bogomips\t: %lu.%02lu\n", loops_per_jiffy / (500000 / HZ),
+			   (loops_per_jiffy / (5000 / HZ)) % 100);
+
 	seq_printf(m, "\n");
 
 	/* If this is the last cpu, print the summary */
@@ -401,8 +393,8 @@
 
 #ifdef CONFIG_SMP
 
-int threads_per_core, threads_per_subcore, threads_shift;
-cpumask_t threads_core_mask;
+int threads_per_core, threads_per_subcore, threads_shift __read_mostly;
+cpumask_t threads_core_mask __read_mostly;
 EXPORT_SYMBOL_GPL(threads_per_core);
 EXPORT_SYMBOL_GPL(threads_per_subcore);
 EXPORT_SYMBOL_GPL(threads_shift);
@@ -459,9 +451,11 @@
 
 	DBG("smp_setup_cpu_maps()\n");
 
-	cpu_to_phys_id = __va(memblock_alloc(nr_cpu_ids * sizeof(u32),
-							__alignof__(u32)));
-	memset(cpu_to_phys_id, 0, nr_cpu_ids * sizeof(u32));
+	cpu_to_phys_id = memblock_alloc(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;
@@ -635,7 +629,7 @@
 	}
 	/* What can we do if we didn't find ? */
 	if (machine_id >= &__machine_desc_end) {
-		DBG("No suitable machine found !\n");
+		pr_err("No suitable machine description found !\n");
 		for (;;);
 	}
 
@@ -688,7 +682,7 @@
 		return ret;
 	parent = of_get_parent(np);
 	if (parent) {
-		if (strcmp(parent->type, "isa") == 0)
+		if (of_node_is_type(parent, "isa"))
 			ret = 0;
 		of_node_put(parent);
 	}
@@ -738,23 +732,19 @@
  * BUG() in that case.
  */
 
-#ifdef CONFIG_NOT_COHERENT_CACHE
-#define KERNEL_COHERENCY	0
-#else
-#define KERNEL_COHERENCY	1
-#endif
+#define KERNEL_COHERENCY	(!IS_ENABLED(CONFIG_NOT_COHERENT_CACHE))
 
 static int __init check_cache_coherency(void)
 {
 	struct device_node *np;
 	const void *prop;
-	int devtree_coherency;
+	bool devtree_coherency;
 
 	np = of_find_node_by_path("/");
 	prop = of_get_property(np, "coherency-off", NULL);
 	of_node_put(np);
 
-	devtree_coherency = prop ? 0 : 1;
+	devtree_coherency = prop ? false : true;
 
 	if (devtree_coherency != KERNEL_COHERENCY) {
 		printk(KERN_ERR
@@ -788,22 +778,9 @@
 	pr_info("%s\n", s);
 }
 
-void arch_setup_pdev_archdata(struct platform_device *pdev)
-{
-	pdev->archdata.dma_mask = DMA_BIT_MASK(32);
-	pdev->dev.dma_mask = &pdev->archdata.dma_mask;
- 	set_dma_ops(&pdev->dev, &dma_nommu_ops);
-}
-
 static __init void print_system_info(void)
 {
 	pr_info("-----------------------------------------------------\n");
-#ifdef CONFIG_PPC_BOOK3S_64
-	pr_info("ppc64_pft_size    = 0x%llx\n", ppc64_pft_size);
-#endif
-#ifdef CONFIG_PPC_STD_MMU_32
-	pr_info("Hash_size         = 0x%lx\n", Hash_size);
-#endif
 	pr_info("phys_mem_size     = 0x%llx\n",
 		(unsigned long long)memblock_phys_mem_size());
 
@@ -823,20 +800,15 @@
 	pr_info("mmu_features      = 0x%08x\n", cur_cpu_spec->mmu_features);
 #ifdef CONFIG_PPC64
 	pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features);
+#ifdef CONFIG_PPC_BOOK3S
+	pr_info("vmalloc start     = 0x%lx\n", KERN_VIRT_START);
+	pr_info("IO start          = 0x%lx\n", KERN_IO_START);
+	pr_info("vmemmap start     = 0x%lx\n", (unsigned long)vmemmap);
+#endif
 #endif
 
-#ifdef CONFIG_PPC_BOOK3S_64
-	if (htab_address)
-		pr_info("htab_address      = 0x%p\n", htab_address);
-	if (htab_hash_mask)
-		pr_info("htab_hash_mask    = 0x%lx\n", htab_hash_mask);
-#endif
-#ifdef CONFIG_PPC_STD_MMU_32
-	if (Hash)
-		pr_info("Hash              = 0x%p\n", Hash);
-	if (Hash_mask)
-		pr_info("Hash_mask         = 0x%lx\n", Hash_mask);
-#endif
+	if (!early_radix_enabled())
+		print_system_hash_info();
 
 	if (PHYSICAL_START > 0)
 		pr_info("physical_start    = 0x%llx\n",
@@ -867,6 +839,8 @@
  */
 void __init setup_arch(char **cmdline_p)
 {
+	kasan_init();
+
 	*cmdline_p = boot_command_line;
 
 	/* Set a half-reasonable default so udelay does something sensible */
@@ -939,50 +913,38 @@
 	/* Reserve large chunks of memory for use by CMA for KVM. */
 	kvm_cma_reserve();
 
-	klp_init_thread_info(&init_thread_info);
+	klp_init_thread_info(&init_task);
 
 	init_mm.start_code = (unsigned long)_stext;
 	init_mm.end_code = (unsigned long) _etext;
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = klimit;
 
-#ifdef CONFIG_PPC_MM_SLICES
-#ifdef CONFIG_PPC64
-	if (!radix_enabled())
-		init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
-#elif defined(CONFIG_PPC_8xx)
-	init_mm.context.slb_addr_limit = DEFAULT_MAP_WINDOW;
-#else
-#error	"context.addr_limit not initialized."
-#endif
-#endif
-
-#ifdef CONFIG_SPAPR_TCE_IOMMU
 	mm_iommu_init(&init_mm);
-#endif
 	irqstack_early_init();
 	exc_lvl_early_init();
 	emergency_stack_init();
 
 	initmem_init();
 
-#ifdef CONFIG_DUMMY_CONSOLE
-	conswitchp = &dummy_con;
-#endif
+	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
+
+	if (IS_ENABLED(CONFIG_DUMMY_CONSOLE))
+		conswitchp = &dummy_con;
+
 	if (ppc_md.setup_arch)
 		ppc_md.setup_arch();
 
 	setup_barrier_nospec();
+	setup_spectre_v2();
 
 	paging_init();
 
 	/* Initialize the MMU context management stuff. */
 	mmu_context_init();
 
-#ifdef CONFIG_PPC64
 	/* Interrupt code needs to be 64K-aligned. */
-	if ((unsigned long)_stext & 0xffff)
+	if (IS_ENABLED(CONFIG_PPC64) && (unsigned long)_stext & 0xffff)
 		panic("Kernelbase not 64K-aligned (0x%lx)!\n",
 		      (unsigned long)_stext);
-#endif
 }
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
index c6a592b..c82577c 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Prototypes for functions that are shared between setup_(32|64|common).c
  *
  * Copyright 2016 Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef __ARCH_POWERPC_KERNEL_SETUP_H
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 8c507be..a7541ed 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Common prep/pmac/chrp boot and setup code.
  */
@@ -17,6 +18,7 @@
 #include <linux/console.h>
 #include <linux/memblock.h>
 #include <linux/export.h>
+#include <linux/nvram.h>
 
 #include <asm/io.h>
 #include <asm/prom.h>
@@ -59,39 +61,10 @@
 unsigned int DMA_MODE_READ;
 unsigned int DMA_MODE_WRITE;
 
-EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
 EXPORT_SYMBOL(DMA_MODE_READ);
 EXPORT_SYMBOL(DMA_MODE_WRITE);
 
 /*
- * We're called here very early in the boot.
- *
- * Note that the kernel may be running at an address which is different
- * from the address that it was linked at, so we must use RELOC/PTRRELOC
- * to access static data (including strings).  -- paulus
- */
-notrace unsigned long __init early_init(unsigned long dt_ptr)
-{
-	unsigned long offset = reloc_offset();
-
-	/* First zero the BSS -- use memset_io, some platforms don't have
-	 * caches on yet */
-	memset_io((void __iomem *)PTRRELOC(&__bss_start), 0,
-			__bss_stop - __bss_start);
-
-	/*
-	 * Identify the CPU type and fix up code sections
-	 * that depend on which cpu we have.
-	 */
-	identify_cpu(offset, mfspr(SPRN_PVR));
-
-	apply_feature_fixups();
-
-	return KERNELBASE + offset;
-}
-
-
-/*
  * This is run before start_kernel(), the kernel has been relocated
  * and we are running with enough of the MMU enabled to have our
  * proper kernel virtual addresses
@@ -101,8 +74,7 @@
  */
 notrace void __init machine_init(u64 dt_ptr)
 {
-	unsigned int *addr = (unsigned int *)((unsigned long)&patch__memset_nocache +
-					       patch__memset_nocache);
+	unsigned int *addr = (unsigned int *)patch_site_addr(&patch__memset_nocache);
 	unsigned long insn;
 
 	/* Configure static keys first, now that we're relocated. */
@@ -149,41 +121,6 @@
 }
 __setup("l3cr=", ppc_setup_l3cr);
 
-#ifdef CONFIG_GENERIC_NVRAM
-
-/* Generic nvram hooks used by drivers/char/gen_nvram.c */
-unsigned char nvram_read_byte(int addr)
-{
-	if (ppc_md.nvram_read_val)
-		return ppc_md.nvram_read_val(addr);
-	return 0xff;
-}
-EXPORT_SYMBOL(nvram_read_byte);
-
-void nvram_write_byte(unsigned char val, int addr)
-{
-	if (ppc_md.nvram_write_val)
-		ppc_md.nvram_write_val(addr, val);
-}
-EXPORT_SYMBOL(nvram_write_byte);
-
-ssize_t nvram_get_size(void)
-{
-	if (ppc_md.nvram_size)
-		return ppc_md.nvram_size();
-	return -1;
-}
-EXPORT_SYMBOL(nvram_get_size);
-
-void nvram_sync(void)
-{
-	if (ppc_md.nvram_sync)
-		ppc_md.nvram_sync();
-}
-EXPORT_SYMBOL(nvram_sync);
-
-#endif /* CONFIG_NVRAM */
-
 static int __init ppc_init(void)
 {
 	/* clear the progress line */
@@ -198,6 +135,17 @@
 }
 arch_initcall(ppc_init);
 
+static void *__init alloc_stack(void)
+{
+	void *ptr = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
+
+	if (!ptr)
+		panic("cannot allocate %d bytes for stack at %pS\n",
+		      THREAD_SIZE, (void *)_RET_IP_);
+
+	return ptr;
+}
+
 void __init irqstack_early_init(void)
 {
 	unsigned int i;
@@ -205,10 +153,8 @@
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
 	 * as the memblock is limited to lowmem by default */
 	for_each_possible_cpu(i) {
-		softirq_ctx[i] = (struct thread_info *)
-			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
-		hardirq_ctx[i] = (struct thread_info *)
-			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+		softirq_ctx[i] = alloc_stack();
+		hardirq_ctx[i] = alloc_stack();
 	}
 }
 
@@ -226,13 +172,10 @@
 		hw_cpu = 0;
 #endif
 
-		critirq_ctx[hw_cpu] = (struct thread_info *)
-			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+		critirq_ctx[hw_cpu] = alloc_stack();
 #ifdef CONFIG_BOOKE
-		dbgirq_ctx[hw_cpu] = (struct thread_info *)
-			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
-		mcheckirq_ctx[hw_cpu] = (struct thread_info *)
-			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
+		dbgirq_ctx[hw_cpu] = alloc_stack();
+		mcheckirq_ctx[hw_cpu] = alloc_stack();
 #endif
 	}
 }
@@ -240,7 +183,7 @@
 
 void __init setup_power_save(void)
 {
-#ifdef CONFIG_6xx
+#ifdef CONFIG_PPC_BOOK3S_32
 	if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
 	    cpu_has_feature(CPU_FTR_CAN_NAP))
 		ppc_md.power_save = ppc6xx_idle;
@@ -263,6 +206,6 @@
 	dcache_bsize = cur_cpu_spec->dcache_bsize;
 	icache_bsize = cur_cpu_spec->icache_bsize;
 	ucache_bsize = 0;
-	if (cpu_has_feature(CPU_FTR_UNIFIED_ID_CACHE))
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601) || IS_ENABLED(CONFIG_E200))
 		ucache_bsize = icache_bsize = dcache_bsize;
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index faf0022..44b4c43 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * 
  * Common boot and setup code.
  *
  * Copyright (C) 2001 PPC64 Team, IBM Corp
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <linux/export.h>
@@ -29,10 +25,9 @@
 #include <linux/unistd.h>
 #include <linux/serial.h>
 #include <linux/serial_8250.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/pci.h>
 #include <linux/lockdep.h>
-#include <linux/memblock.h>
 #include <linux/memory.h>
 #include <linux/nmi.h>
 
@@ -69,6 +64,7 @@
 #include <asm/cputhreads.h>
 #include <asm/hw_irq.h>
 #include <asm/feature-fixups.h>
+#include <asm/kup.h>
 
 #include "setup.h"
 
@@ -332,6 +328,12 @@
 	 */
 	configure_exceptions();
 
+	/*
+	 * Configure Kernel Userspace Protection. This needs to happen before
+	 * feature fixups for platforms that implement this using features.
+	 */
+	setup_kup();
+
 	/* Apply all the dynamic patching */
 	apply_feature_fixups();
 	setup_feature_keys();
@@ -384,6 +386,9 @@
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu_secondary();
 
+	/* Perform any KUP setup that is per-cpu */
+	setup_kup();
+
 	/*
 	 * At this point, we can let interrupts switch to virtual mode
 	 * (the MMU has been setup), so adjust the MSR in the PACA to
@@ -635,17 +640,17 @@
 
 static void *__init alloc_stack(unsigned long limit, int cpu)
 {
-	unsigned long pa;
+	void *ptr;
 
-	pa = memblock_alloc_base_nid(THREAD_SIZE, THREAD_SIZE, limit,
-					early_cpu_to_node(cpu), MEMBLOCK_NONE);
-	if (!pa) {
-		pa = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
-		if (!pa)
-			panic("cannot allocate stacks");
-	}
+	BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16);
 
-	return __va(pa);
+	ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_SIZE,
+				     MEMBLOCK_LOW_LIMIT, limit,
+				     early_cpu_to_node(cpu));
+	if (!ptr)
+		panic("cannot allocate stacks");
+
+	return ptr;
 }
 
 void __init irqstack_early_init(void)
@@ -691,24 +696,6 @@
 #endif
 
 /*
- * Emergency stacks are used for a range of things, from asynchronous
- * NMIs (system reset, machine check) to synchronous, process context.
- * We set preempt_count to zero, even though that isn't necessarily correct. To
- * get the right value we'd need to copy it from the previous thread_info, but
- * doing that might fault causing more problems.
- * TODO: what to do with accounting?
- */
-static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
-{
-	ti->task = NULL;
-	ti->cpu = cpu;
-	ti->preempt_count = 0;
-	ti->local_flags = 0;
-	ti->flags = 0;
-	klp_init_thread_info(ti);
-}
-
-/*
  * Stack space used when we detect a bad kernel stack pointer, and
  * early in SMP boots before relocation is enabled. Exclusive emergency
  * stack for machine checks.
@@ -735,25 +722,14 @@
 	limit = min(ppc64_bolted_size(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
-		struct thread_info *ti;
-
-		ti = alloc_stack(limit, i);
-		memset(ti, 0, THREAD_SIZE);
-		emerg_stack_init_thread_info(ti, i);
-		paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
-		ti = alloc_stack(limit, i);
-		memset(ti, 0, THREAD_SIZE);
-		emerg_stack_init_thread_info(ti, i);
-		paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->nmi_emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
-		ti = alloc_stack(limit, i);
-		memset(ti, 0, THREAD_SIZE);
-		emerg_stack_init_thread_info(ti, i);
-		paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->mc_emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
 #endif
 	}
 }
@@ -763,13 +739,15 @@
 
 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
-				    __pa(MAX_DMA_ADDRESS));
+	return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS),
+				      MEMBLOCK_ALLOC_ACCESSIBLE,
+				      early_cpu_to_node(cpu));
+
 }
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	free_bootmem(__pa(ptr), size);
+	memblock_free(__pa(ptr), size);
 }
 
 static int pcpu_cpu_distance(unsigned int from, unsigned int to)
@@ -930,8 +908,13 @@
 	 * hardware prefetch runoff. We don't have a recipe for load patterns to
 	 * reliably avoid the prefetcher.
 	 */
-	l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit));
-	memset(l1d_flush_fallback_area, 0, l1d_size * 2);
+	l1d_flush_fallback_area = memblock_alloc_try_nid(l1d_size * 2,
+						l1d_size, MEMBLOCK_LOW_LIMIT,
+						limit, NUMA_NO_NODE);
+	if (!l1d_flush_fallback_area)
+		panic("%s: Failed to allocate %llu bytes align=0x%llx max_addr=%pa\n",
+		      __func__, l1d_size * 2, l1d_size, &limit);
+
 
 	for_each_possible_cpu(cpu) {
 		struct paca_struct *paca = paca_ptrs[cpu];
@@ -955,7 +938,7 @@
 
 	enabled_flush_types = types;
 
-	if (!no_rfi_flush)
+	if (!no_rfi_flush && !cpu_mitigations_off())
 		rfi_flush_enable(enable);
 }
 
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index b3e8db3..e6c30ce 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -44,7 +44,7 @@
 	newsp = (oldsp - frame_size) & ~0xFUL;
 
 	/* Check access */
-	if (!access_ok(VERIFY_WRITE, (void __user *)newsp, oldsp - newsp))
+	if (!access_ok((void __user *)newsp, oldsp - newsp))
 		return NULL;
 
         return (void __user *)newsp;
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index e6474a4..98600b2 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Signal handling for 32bit PPC and 32bit tasks on 64bit PPC
  *
@@ -10,11 +11,6 @@
  *  Derived from "arch/i386/kernel/signal.c"
  *    Copyright (C) 1991, 1992 Linus Torvalds
  *    1997-11-28  Modified for POSIX.1b signals by Richard Henderson
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/sched.h>
@@ -470,9 +466,9 @@
 		return 1;
 
 	if (sigret) {
-		/* Set up the sigreturn trampoline: li r0,sigret; sc */
-		if (__put_user(0x38000000UL + sigret, &frame->tramp[0])
-		    || __put_user(0x44000002UL, &frame->tramp[1]))
+		/* Set up the sigreturn trampoline: li 0,sigret; sc */
+		if (__put_user(PPC_INST_ADDI + sigret, &frame->tramp[0])
+		    || __put_user(PPC_INST_SC, &frame->tramp[1]))
 			return 1;
 		flush_icache_range((unsigned long) &frame->tramp[0],
 				   (unsigned long) &frame->tramp[2]);
@@ -619,9 +615,9 @@
 	if (__put_user(msr, &frame->mc_gregs[PT_MSR]))
 		return 1;
 	if (sigret) {
-		/* Set up the sigreturn trampoline: li r0,sigret; sc */
-		if (__put_user(0x38000000UL + sigret, &frame->tramp[0])
-		    || __put_user(0x44000002UL, &frame->tramp[1]))
+		/* Set up the sigreturn trampoline: li 0,sigret; sc */
+		if (__put_user(PPC_INST_ADDI + sigret, &frame->tramp[0])
+		    || __put_user(PPC_INST_SC, &frame->tramp[1]))
 			return 1;
 		flush_icache_range((unsigned long) &frame->tramp[0],
 				   (unsigned long) &frame->tramp[2]);
@@ -848,7 +844,23 @@
 	/* If TM bits are set to the reserved value, it's an invalid context */
 	if (MSR_TM_RESV(msr_hi))
 		return 1;
-	/* Pull in the MSR TM bits from the user context */
+
+	/*
+	 * Disabling preemption, since it is unsafe to be preempted
+	 * with MSR[TS] set without recheckpointing.
+	 */
+	preempt_disable();
+
+	/*
+	 * CAUTION:
+	 * After regs->MSR[TS] being updated, make sure that get_user(),
+	 * put_user() or similar functions are *not* called. These
+	 * functions can generate page faults which will cause the process
+	 * to be de-scheduled with MSR[TS] set but without calling
+	 * tm_recheckpoint(). This can cause a bug.
+	 *
+	 * Pull in the MSR TM bits from the user context
+	 */
 	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK);
 	/* Now, recheckpoint.  This loads up all of the checkpointed (older)
 	 * registers, including FP and V[S]Rs.  After recheckpointing, the
@@ -873,6 +885,8 @@
 	}
 #endif
 
+	preempt_enable();
+
 	return 0;
 }
 #endif
@@ -999,7 +1013,7 @@
 #else
 	if (__get_user(mcp, &ucp->uc_regs))
 		return -EFAULT;
-	if (!access_ok(VERIFY_READ, mcp, sizeof(*mcp)))
+	if (!access_ok(mcp, sizeof(*mcp)))
 		return -EFAULT;
 #endif
 	set_current_blocked(&set);
@@ -1102,7 +1116,7 @@
 		 */
 		mctx = (struct mcontext __user *)
 			((unsigned long) &old_ctx->uc_mcontext & ~0xfUL);
-		if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size)
+		if (!access_ok(old_ctx, ctx_size)
 		    || save_user_regs(regs, mctx, NULL, 0, ctx_has_vsx_region)
 		    || put_sigset_t(&old_ctx->uc_sigmask, &current->blocked)
 		    || __put_user(to_user_ptr(mctx), &old_ctx->uc_regs))
@@ -1110,7 +1124,7 @@
 	}
 	if (new_ctx == NULL)
 		return 0;
-	if (!access_ok(VERIFY_READ, new_ctx, ctx_size) ||
+	if (!access_ok(new_ctx, ctx_size) ||
 	    fault_in_pages_readable((u8 __user *)new_ctx, ctx_size))
 		return -EFAULT;
 
@@ -1140,18 +1154,18 @@
 {
 	struct rt_sigframe __user *rt_sf;
 	struct pt_regs *regs = current_pt_regs();
+	int tm_restore = 0;
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	struct ucontext __user *uc_transact;
 	unsigned long msr_hi;
 	unsigned long tmp;
-	int tm_restore = 0;
 #endif
 	/* Always make any pending restarted system calls return -EINTR */
 	current->restart_block.fn = do_no_restart_syscall;
 
 	rt_sf = (struct rt_sigframe __user *)
 		(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
-	if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf)))
+	if (!access_ok(rt_sf, sizeof(*rt_sf)))
 		goto bad;
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1184,6 +1198,9 @@
 			goto bad;
 
 		if (MSR_TM_ACTIVE(msr_hi<<32)) {
+			/* Trying to start TM on non TM system */
+			if (!cpu_has_feature(CPU_FTR_TM))
+				goto bad;
 			/* We only recheckpoint on return if we're
 			 * transaction.
 			 */
@@ -1192,11 +1209,19 @@
 				goto bad;
 		}
 	}
-	if (!tm_restore)
-		/* Fall through, for non-TM restore */
+	if (!tm_restore) {
+		/*
+		 * Unset regs->msr because ucontext MSR TS is not
+		 * set, and recheckpoint was not called. This avoid
+		 * hitting a TM Bad thing at RFID
+		 */
+		regs->msr &= ~MSR_TS_MASK;
+	}
+	/* Fall through, for non-TM restore */
 #endif
-	if (do_setcontext(&rt_sf->uc, regs, 1))
-		goto bad;
+	if (!tm_restore)
+		if (do_setcontext(&rt_sf->uc, regs, 1))
+			goto bad;
 
 	/*
 	 * It's not clear whether or why it is desirable to save the
@@ -1223,7 +1248,7 @@
 				   current->comm, current->pid,
 				   rt_sf, regs->nip, regs->link);
 
-	force_sig(SIGSEGV, current);
+	force_sig(SIGSEGV);
 	return 0;
 }
 
@@ -1289,7 +1314,7 @@
 	current->thread.debug.dbcr0 = new_dbcr0;
 #endif
 
-	if (!access_ok(VERIFY_READ, ctx, sizeof(*ctx)) ||
+	if (!access_ok(ctx, sizeof(*ctx)) ||
 	    fault_in_pages_readable((u8 __user *)ctx, sizeof(*ctx)))
 		return -EFAULT;
 
@@ -1312,7 +1337,7 @@
 					   current->comm, current->pid,
 					   ctx, regs->nip, regs->link);
 
-		force_sig(SIGSEGV, current);
+		force_sig(SIGSEGV);
 		goto out;
 	}
 
@@ -1474,7 +1499,7 @@
 	{
 		sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
 		addr = sr;
-		if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
+		if (!access_ok(sr, sizeof(*sr))
 		    || restore_user_regs(regs, sr, 1))
 			goto badframe;
 	}
@@ -1490,6 +1515,6 @@
 				   current->comm, current->pid,
 				   addr, regs->nip, regs->link);
 
-	force_sig(SIGSEGV, current);
+	force_sig(SIGSEGV);
 	return 0;
 }
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 83d51bf..1175155 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  PowerPC version 
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -5,11 +6,6 @@
  *  Derived from "arch/i386/kernel/signal.c"
  *    Copyright (C) 1991, 1992 Linus Torvalds
  *    1997-11-28  Modified for POSIX.1b signals by Richard Henderson
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/sched.h>
@@ -383,7 +379,7 @@
 	err |= __get_user(v_regs, &sc->v_regs);
 	if (err)
 		return err;
-	if (v_regs && !access_ok(VERIFY_READ, v_regs, 34 * sizeof(vector128)))
+	if (v_regs && !access_ok(v_regs, 34 * sizeof(vector128)))
 		return -EFAULT;
 	/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
 	if (v_regs != NULL && (msr & MSR_VEC) != 0) {
@@ -467,20 +463,6 @@
 	if (MSR_TM_RESV(msr))
 		return -EINVAL;
 
-	/* pull in MSR TS bits from user context */
-	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
-
-	/*
-	 * Ensure that TM is enabled in regs->msr before we leave the signal
-	 * handler. It could be the case that (a) user disabled the TM bit
-	 * through the manipulation of the MSR bits in uc_mcontext or (b) the
-	 * TM bit was disabled because a sufficient number of context switches
-	 * happened whilst in the signal handler and load_tm overflowed,
-	 * disabling the TM bit. In either case we can end up with an illegal
-	 * TM state leading to a TM Bad Thing when we return to userspace.
-	 */
-	regs->msr |= MSR_TM;
-
 	/* pull in MSR LE from user context */
 	regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
 
@@ -516,10 +498,9 @@
 	err |= __get_user(tm_v_regs, &tm_sc->v_regs);
 	if (err)
 		return err;
-	if (v_regs && !access_ok(VERIFY_READ, v_regs, 34 * sizeof(vector128)))
+	if (v_regs && !access_ok(v_regs, 34 * sizeof(vector128)))
 		return -EFAULT;
-	if (tm_v_regs && !access_ok(VERIFY_READ,
-				    tm_v_regs, 34 * sizeof(vector128)))
+	if (tm_v_regs && !access_ok(tm_v_regs, 34 * sizeof(vector128)))
 		return -EFAULT;
 	/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
 	if (v_regs != NULL && tm_v_regs != NULL && (msr & MSR_VEC) != 0) {
@@ -572,6 +553,34 @@
 	tm_enable();
 	/* Make sure the transaction is marked as failed */
 	tsk->thread.tm_texasr |= TEXASR_FS;
+
+	/*
+	 * Disabling preemption, since it is unsafe to be preempted
+	 * with MSR[TS] set without recheckpointing.
+	 */
+	preempt_disable();
+
+	/* pull in MSR TS bits from user context */
+	regs->msr |= msr & MSR_TS_MASK;
+
+	/*
+	 * Ensure that TM is enabled in regs->msr before we leave the signal
+	 * handler. It could be the case that (a) user disabled the TM bit
+	 * through the manipulation of the MSR bits in uc_mcontext or (b) the
+	 * TM bit was disabled because a sufficient number of context switches
+	 * happened whilst in the signal handler and load_tm overflowed,
+	 * disabling the TM bit. In either case we can end up with an illegal
+	 * TM state leading to a TM Bad Thing when we return to userspace.
+	 *
+	 * CAUTION:
+	 * After regs->MSR[TS] being updated, make sure that get_user(),
+	 * put_user() or similar functions are *not* called. These
+	 * functions can generate page faults which will cause the process
+	 * to be de-scheduled with MSR[TS] set but without calling
+	 * tm_recheckpoint(). This can cause a bug.
+	 */
+	regs->msr |= MSR_TM;
+
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&tsk->thread);
 
@@ -585,6 +594,8 @@
 		regs->msr |= MSR_VEC;
 	}
 
+	preempt_enable();
+
 	return err;
 }
 #endif
@@ -598,11 +609,12 @@
 	long err = 0;
 
 	/* addi r1, r1, __SIGNAL_FRAMESIZE  # Pop the dummy stackframe */
-	err |= __put_user(0x38210000UL | (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]);
+	err |= __put_user(PPC_INST_ADDI | __PPC_RT(R1) | __PPC_RA(R1) |
+			  (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]);
 	/* li r0, __NR_[rt_]sigreturn| */
-	err |= __put_user(0x38000000UL | (syscall & 0xffff), &tramp[1]);
+	err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[1]);
 	/* sc */
-	err |= __put_user(0x44000002UL, &tramp[2]);
+	err |= __put_user(PPC_INST_SC, &tramp[2]);
 
 	/* Minimal traceback info */
 	for (i=TRAMP_TRACEBACK; i < TRAMP_SIZE ;i++)
@@ -654,7 +666,7 @@
 		ctx_has_vsx_region = 1;
 
 	if (old_ctx != NULL) {
-		if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size)
+		if (!access_ok(old_ctx, ctx_size)
 		    || setup_sigcontext(&old_ctx->uc_mcontext, current, 0, NULL, 0,
 					ctx_has_vsx_region)
 		    || __copy_to_user(&old_ctx->uc_sigmask,
@@ -663,7 +675,7 @@
 	}
 	if (new_ctx == NULL)
 		return 0;
-	if (!access_ok(VERIFY_READ, new_ctx, ctx_size)
+	if (!access_ok(new_ctx, ctx_size)
 	    || __get_user(tmp, (u8 __user *) new_ctx)
 	    || __get_user(tmp, (u8 __user *) new_ctx + ctx_size - 1))
 		return -EFAULT;
@@ -708,7 +720,7 @@
 	/* Always make any pending restarted system calls return -EINTR */
 	current->restart_block.fn = do_no_restart_syscall;
 
-	if (!access_ok(VERIFY_READ, uc, sizeof(*uc)))
+	if (!access_ok(uc, sizeof(*uc)))
 		goto badframe;
 
 	if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
@@ -729,22 +741,65 @@
 	if (MSR_TM_SUSPENDED(mfmsr()))
 		tm_reclaim_current(0);
 
+	/*
+	 * Disable MSR[TS] bit also, so, if there is an exception in the
+	 * code below (as a page fault in copy_ckvsx_to_user()), it does
+	 * not recheckpoint this task if there was a context switch inside
+	 * the exception.
+	 *
+	 * A major page fault can indirectly call schedule(). A reschedule
+	 * process in the middle of an exception can have a side effect
+	 * (Changing the CPU MSR[TS] state), since schedule() is called
+	 * with the CPU MSR[TS] disable and returns with MSR[TS]=Suspended
+	 * (switch_to() calls tm_recheckpoint() for the 'new' process). In
+	 * this case, the process continues to be the same in the CPU, but
+	 * the CPU state just changed.
+	 *
+	 * This can cause a TM Bad Thing, since the MSR in the stack will
+	 * have the MSR[TS]=0, and this is what will be used to RFID.
+	 *
+	 * Clearing MSR[TS] state here will avoid a recheckpoint if there
+	 * is any process reschedule in kernel space. The MSR[TS] state
+	 * does not need to be saved also, since it will be replaced with
+	 * the MSR[TS] that came from user context later, at
+	 * restore_tm_sigcontexts.
+	 */
+	regs->msr &= ~MSR_TS_MASK;
+
 	if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
 		goto badframe;
 	if (MSR_TM_ACTIVE(msr)) {
 		/* We recheckpoint on return. */
 		struct ucontext __user *uc_transact;
+
+		/* Trying to start TM on non TM system */
+		if (!cpu_has_feature(CPU_FTR_TM))
+			goto badframe;
+
 		if (__get_user(uc_transact, &uc->uc_link))
 			goto badframe;
 		if (restore_tm_sigcontexts(current, &uc->uc_mcontext,
 					   &uc_transact->uc_mcontext))
 			goto badframe;
-	}
-	else
-	/* Fall through, for non-TM restore */
+	} else
 #endif
-	if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext))
-		goto badframe;
+	{
+		/*
+		 * Fall through, for non-TM restore
+		 *
+		 * Unset MSR[TS] on the thread regs since MSR from user
+		 * context does not have MSR active, and recheckpoint was
+		 * not called since restore_tm_sigcontexts() was not called
+		 * also.
+		 *
+		 * If not unsetting it, the code can RFID to userspace with
+		 * MSR[TS] set, but without CPU in the proper state,
+		 * causing a TM bad thing.
+		 */
+		current->thread.regs->msr &= ~MSR_TS_MASK;
+		if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext))
+			goto badframe;
+	}
 
 	if (restore_altstack(&uc->uc_stack))
 		goto badframe;
@@ -758,7 +813,7 @@
 				   current->comm, current->pid, "rt_sigreturn",
 				   (long)uc, regs->nip, regs->link);
 
-	force_sig(SIGSEGV, current);
+	force_sig(SIGSEGV);
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 61c1fad..ea6adbf 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SMP support for ppc.
  *
@@ -8,11 +9,6 @@
  *
  * PowerPC-64 Support added by Dave Engebretsen, Peter Bergner, and
  * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
@@ -20,6 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
 #include <linux/sched/topology.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
@@ -34,6 +31,8 @@
 #include <linux/topology.h>
 #include <linux/profile.h>
 #include <linux/processor.h>
+#include <linux/random.h>
+#include <linux/stackprotector.h>
 
 #include <asm/ptrace.h>
 #include <linux/atomic.h>
@@ -73,15 +72,33 @@
 static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 #endif
 
-struct thread_info *secondary_ti;
+struct task_struct *secondary_current;
+bool has_big_cores;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
 
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
+EXPORT_SYMBOL_GPL(has_big_cores);
+
+#define MAX_THREAD_LIST_SIZE	8
+#define THREAD_GROUP_SHARE_L1   1
+struct thread_groups {
+	unsigned int property;
+	unsigned int nr_groups;
+	unsigned int threads_per_group;
+	unsigned int thread_list[MAX_THREAD_LIST_SIZE];
+};
+
+/*
+ * On big-cores system, cpu_l1_cache_map for each CPU corresponds to
+ * the set its siblings that share the L1-cache.
+ */
+DEFINE_PER_CPU(cpumask_var_t, cpu_l1_cache_map);
 
 /* SMP operations for this machine */
 struct smp_ops_t *smp_ops;
@@ -338,13 +355,12 @@
  * NMI IPIs may not be recoverable, so should not be used as ongoing part of
  * a running system. They can be used for crash, debug, halt/reboot, etc.
  *
- * NMI IPIs are globally single threaded. No more than one in progress at
- * any time.
- *
  * The IPI call waits with interrupts disabled until all targets enter the
- * NMI handler, then the call returns.
+ * NMI handler, then returns. Subsequent IPIs can be issued before targets
+ * have returned from their handlers, so there is no guarantee about
+ * concurrency or re-entrancy.
  *
- * No new NMI can be initiated until targets exit the handler.
+ * A new NMI can be issued before all targets exit the handler.
  *
  * The IPI call may time out without all targets entering the NMI handler.
  * In that case, there is some logic to recover (and ignore subsequent
@@ -355,7 +371,7 @@
 
 static atomic_t __nmi_ipi_lock = ATOMIC_INIT(0);
 static struct cpumask nmi_ipi_pending_mask;
-static int nmi_ipi_busy_count = 0;
+static bool nmi_ipi_busy = false;
 static void (*nmi_ipi_function)(struct pt_regs *) = NULL;
 
 static void nmi_ipi_lock_start(unsigned long *flags)
@@ -394,7 +410,7 @@
  */
 int smp_handle_nmi_ipi(struct pt_regs *regs)
 {
-	void (*fn)(struct pt_regs *);
+	void (*fn)(struct pt_regs *) = NULL;
 	unsigned long flags;
 	int me = raw_smp_processor_id();
 	int ret = 0;
@@ -405,29 +421,17 @@
 	 * because the caller may have timed out.
 	 */
 	nmi_ipi_lock_start(&flags);
-	if (!nmi_ipi_busy_count)
-		goto out;
-	if (!cpumask_test_cpu(me, &nmi_ipi_pending_mask))
-		goto out;
-
-	fn = nmi_ipi_function;
-	if (!fn)
-		goto out;
-
-	cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
-	nmi_ipi_busy_count++;
-	nmi_ipi_unlock();
-
-	ret = 1;
-
-	fn(regs);
-
-	nmi_ipi_lock();
-	if (nmi_ipi_busy_count > 1) /* Can race with caller time-out */
-		nmi_ipi_busy_count--;
-out:
+	if (cpumask_test_cpu(me, &nmi_ipi_pending_mask)) {
+		cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
+		fn = READ_ONCE(nmi_ipi_function);
+		WARN_ON_ONCE(!fn);
+		ret = 1;
+	}
 	nmi_ipi_unlock_end(&flags);
 
+	if (fn)
+		fn(regs);
+
 	return ret;
 }
 
@@ -453,9 +457,10 @@
  * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS.
  * - fn is the target callback function.
  * - delay_us > 0 is the delay before giving up waiting for targets to
- *   complete executing the handler, == 0 specifies indefinite delay.
+ *   begin executing the handler, == 0 specifies indefinite delay.
  */
-int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool safe)
+static int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *),
+				u64 delay_us, bool safe)
 {
 	unsigned long flags;
 	int me = raw_smp_processor_id();
@@ -467,31 +472,33 @@
 	if (unlikely(!smp_ops))
 		return 0;
 
-	/* Take the nmi_ipi_busy count/lock with interrupts hard disabled */
 	nmi_ipi_lock_start(&flags);
-	while (nmi_ipi_busy_count) {
+	while (nmi_ipi_busy) {
 		nmi_ipi_unlock_end(&flags);
-		spin_until_cond(nmi_ipi_busy_count == 0);
+		spin_until_cond(!nmi_ipi_busy);
 		nmi_ipi_lock_start(&flags);
 	}
-
+	nmi_ipi_busy = true;
 	nmi_ipi_function = fn;
 
+	WARN_ON_ONCE(!cpumask_empty(&nmi_ipi_pending_mask));
+
 	if (cpu < 0) {
 		/* ALL_OTHERS */
 		cpumask_copy(&nmi_ipi_pending_mask, cpu_online_mask);
 		cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
 	} else {
-		/* cpumask starts clear */
 		cpumask_set_cpu(cpu, &nmi_ipi_pending_mask);
 	}
-	nmi_ipi_busy_count++;
+
 	nmi_ipi_unlock();
 
+	/* Interrupts remain hard disabled */
+
 	do_smp_send_nmi_ipi(cpu, safe);
 
 	nmi_ipi_lock();
-	/* nmi_ipi_busy_count is held here, so unlock/lock is okay */
+	/* nmi_ipi_busy is set here, so unlock/lock is okay */
 	while (!cpumask_empty(&nmi_ipi_pending_mask)) {
 		nmi_ipi_unlock();
 		udelay(1);
@@ -503,29 +510,15 @@
 		}
 	}
 
-	while (nmi_ipi_busy_count > 1) {
-		nmi_ipi_unlock();
-		udelay(1);
-		nmi_ipi_lock();
-		if (delay_us) {
-			delay_us--;
-			if (!delay_us)
-				break;
-		}
-	}
-
 	if (!cpumask_empty(&nmi_ipi_pending_mask)) {
 		/* Timeout waiting for CPUs to call smp_handle_nmi_ipi */
 		ret = 0;
 		cpumask_clear(&nmi_ipi_pending_mask);
 	}
-	if (nmi_ipi_busy_count > 1) {
-		/* Timeout waiting for CPUs to execute fn */
-		ret = 0;
-		nmi_ipi_busy_count = 1;
-	}
 
-	nmi_ipi_busy_count--;
+	nmi_ipi_function = NULL;
+	nmi_ipi_busy = false;
+
 	nmi_ipi_unlock_end(&flags);
 
 	return ret;
@@ -593,17 +586,8 @@
 static void nmi_stop_this_cpu(struct pt_regs *regs)
 {
 	/*
-	 * This is a special case because it never returns, so the NMI IPI
-	 * handling would never mark it as done, which makes any later
-	 * smp_send_nmi_ipi() call spin forever. Mark it done now.
-	 *
 	 * IRQs are already hard disabled by the smp_handle_nmi_ipi.
 	 */
-	nmi_ipi_lock();
-	if (nmi_ipi_busy_count > 1)
-		nmi_ipi_busy_count--;
-	nmi_ipi_unlock();
-
 	spin_begin();
 	while (1)
 		spin_cpu_relax();
@@ -643,7 +627,7 @@
 }
 #endif /* CONFIG_NMI_IPI */
 
-struct thread_info *current_set[NR_CPUS];
+struct task_struct *current_set[NR_CPUS];
 
 static void smp_store_cpu_info(int id)
 {
@@ -674,6 +658,185 @@
 }
 #endif
 
+/*
+ * parse_thread_groups: Parses the "ibm,thread-groups" device tree
+ *                      property for the CPU device node @dn and stores
+ *                      the parsed output in the thread_groups
+ *                      structure @tg if the ibm,thread-groups[0]
+ *                      matches @property.
+ *
+ * @dn: The device node of the CPU device.
+ * @tg: Pointer to a thread group structure into which the parsed
+ *      output of "ibm,thread-groups" is stored.
+ * @property: The property of the thread-group that the caller is
+ *            interested in.
+ *
+ * ibm,thread-groups[0..N-1] array defines which group of threads in
+ * the CPU-device node can be grouped together based on the property.
+ *
+ * ibm,thread-groups[0] tells us the property based on which the
+ * threads are being grouped together. If this value is 1, it implies
+ * that the threads in the same group share L1, translation cache.
+ *
+ * ibm,thread-groups[1] tells us how many such thread groups exist.
+ *
+ * ibm,thread-groups[2] tells us the number of threads in each such
+ * group.
+ *
+ * ibm,thread-groups[3..N-1] is the list of threads identified by
+ * "ibm,ppc-interrupt-server#s" arranged as per their membership in
+ * the grouping.
+ *
+ * Example: If ibm,thread-groups = [1,2,4,5,6,7,8,9,10,11,12] it
+ * implies that there are 2 groups of 4 threads each, where each group
+ * of threads share L1, translation cache.
+ *
+ * The "ibm,ppc-interrupt-server#s" of the first group is {5,6,7,8}
+ * and the "ibm,ppc-interrupt-server#s" of the second group is {9, 10,
+ * 11, 12} structure
+ *
+ * Returns 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ */
+static int parse_thread_groups(struct device_node *dn,
+			       struct thread_groups *tg,
+			       unsigned int property)
+{
+	int i;
+	u32 thread_group_array[3 + MAX_THREAD_LIST_SIZE];
+	u32 *thread_list;
+	size_t total_threads;
+	int ret;
+
+	ret = of_property_read_u32_array(dn, "ibm,thread-groups",
+					 thread_group_array, 3);
+	if (ret)
+		return ret;
+
+	tg->property = thread_group_array[0];
+	tg->nr_groups = thread_group_array[1];
+	tg->threads_per_group = thread_group_array[2];
+	if (tg->property != property ||
+	    tg->nr_groups < 1 ||
+	    tg->threads_per_group < 1)
+		return -ENODATA;
+
+	total_threads = tg->nr_groups * tg->threads_per_group;
+
+	ret = of_property_read_u32_array(dn, "ibm,thread-groups",
+					 thread_group_array,
+					 3 + total_threads);
+	if (ret)
+		return ret;
+
+	thread_list = &thread_group_array[3];
+
+	for (i = 0 ; i < total_threads; i++)
+		tg->thread_list[i] = thread_list[i];
+
+	return 0;
+}
+
+/*
+ * get_cpu_thread_group_start : Searches the thread group in tg->thread_list
+ *                              that @cpu belongs to.
+ *
+ * @cpu : The logical CPU whose thread group is being searched.
+ * @tg : The thread-group structure of the CPU node which @cpu belongs
+ *       to.
+ *
+ * Returns the index to tg->thread_list that points to the the start
+ * of the thread_group that @cpu belongs to.
+ *
+ * Returns -1 if cpu doesn't belong to any of the groups pointed to by
+ * tg->thread_list.
+ */
+static int get_cpu_thread_group_start(int cpu, struct thread_groups *tg)
+{
+	int hw_cpu_id = get_hard_smp_processor_id(cpu);
+	int i, j;
+
+	for (i = 0; i < tg->nr_groups; i++) {
+		int group_start = i * tg->threads_per_group;
+
+		for (j = 0; j < tg->threads_per_group; j++) {
+			int idx = group_start + j;
+
+			if (tg->thread_list[idx] == hw_cpu_id)
+				return group_start;
+		}
+	}
+
+	return -1;
+}
+
+static int init_cpu_l1_cache_map(int cpu)
+
+{
+	struct device_node *dn = of_get_cpu_node(cpu, NULL);
+	struct thread_groups tg = {.property = 0,
+				   .nr_groups = 0,
+				   .threads_per_group = 0};
+	int first_thread = cpu_first_thread_sibling(cpu);
+	int i, cpu_group_start = -1, err = 0;
+
+	if (!dn)
+		return -ENODATA;
+
+	err = parse_thread_groups(dn, &tg, THREAD_GROUP_SHARE_L1);
+	if (err)
+		goto out;
+
+	zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu),
+				GFP_KERNEL,
+				cpu_to_node(cpu));
+
+	cpu_group_start = get_cpu_thread_group_start(cpu, &tg);
+
+	if (unlikely(cpu_group_start == -1)) {
+		WARN_ON_ONCE(1);
+		err = -ENODATA;
+		goto out;
+	}
+
+	for (i = first_thread; i < first_thread + threads_per_core; i++) {
+		int i_group_start = get_cpu_thread_group_start(i, &tg);
+
+		if (unlikely(i_group_start == -1)) {
+			WARN_ON_ONCE(1);
+			err = -ENODATA;
+			goto out;
+		}
+
+		if (i_group_start == cpu_group_start)
+			cpumask_set_cpu(i, per_cpu(cpu_l1_cache_map, cpu));
+	}
+
+out:
+	of_node_put(dn);
+	return err;
+}
+
+static int init_big_cores(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		int err = init_cpu_l1_cache_map(cpu);
+
+		if (err)
+			return err;
+
+		zalloc_cpumask_var_node(&per_cpu(cpu_smallcore_map, cpu),
+					GFP_KERNEL,
+					cpu_to_node(cpu));
+	}
+
+	has_big_cores = true;
+	return 0;
+}
+
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned int cpu;
@@ -712,6 +875,12 @@
 	cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid));
 	cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));
 
+	init_big_cores();
+	if (has_big_cores) {
+		cpumask_set_cpu(boot_cpuid,
+				cpu_smallcore_mask(boot_cpuid));
+	}
+
 	if (smp_ops && smp_ops->probe)
 		smp_ops->probe();
 }
@@ -723,7 +892,7 @@
 	paca_ptrs[boot_cpuid]->__current = current;
 #endif
 	set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
-	current_set[boot_cpuid] = task_thread_info(current);
+	current_set[boot_cpuid] = current;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -808,14 +977,13 @@
 
 static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
 {
-	struct thread_info *ti = task_thread_info(idle);
-
 #ifdef CONFIG_PPC64
 	paca_ptrs[cpu]->__current = idle;
-	paca_ptrs[cpu]->kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
+	paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
+				 THREAD_SIZE - STACK_FRAME_OVERHEAD;
 #endif
-	ti->cpu = cpu;
-	secondary_ti = current_set[cpu] = ti;
+	idle->cpu = cpu;
+	secondary_current = current_set[cpu] = idle;
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
@@ -995,10 +1163,28 @@
 		set_cpus_unrelated(cpu, i, cpu_core_mask);
 		set_cpus_unrelated(cpu, i, cpu_l2_cache_mask);
 		set_cpus_unrelated(cpu, i, cpu_sibling_mask);
+		if (has_big_cores)
+			set_cpus_unrelated(cpu, i, cpu_smallcore_mask);
 	}
 }
 #endif
 
+static inline void add_cpu_to_smallcore_masks(int cpu)
+{
+	struct cpumask *this_l1_cache_map = per_cpu(cpu_l1_cache_map, cpu);
+	int i, first_thread = cpu_first_thread_sibling(cpu);
+
+	if (!has_big_cores)
+		return;
+
+	cpumask_set_cpu(cpu, cpu_smallcore_mask(cpu));
+
+	for (i = first_thread; i < first_thread + threads_per_core; i++) {
+		if (cpu_online(i) && cpumask_test_cpu(i, this_l1_cache_map))
+			set_cpus_related(i, cpu, cpu_smallcore_mask);
+	}
+}
+
 static void add_cpu_to_masks(int cpu)
 {
 	int first_thread = cpu_first_thread_sibling(cpu);
@@ -1015,6 +1201,7 @@
 		if (cpu_online(i))
 			set_cpus_related(i, cpu, cpu_sibling_mask);
 
+	add_cpu_to_smallcore_masks(cpu);
 	/*
 	 * Copy the thread sibling mask into the cache sibling mask
 	 * and mark any CPUs that share an L2 with this CPU.
@@ -1044,6 +1231,7 @@
 void start_secondary(void *unused)
 {
 	unsigned int cpu = smp_processor_id();
+	struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
 
 	mmgrab(&init_mm);
 	current->active_mm = &init_mm;
@@ -1069,11 +1257,13 @@
 	/* Update topology CPU masks */
 	add_cpu_to_masks(cpu);
 
+	if (has_big_cores)
+		sibling_mask = cpu_smallcore_mask;
 	/*
 	 * Check for any shared caches. Note that this must be done on a
 	 * per-core basis because one core in the pair might be disabled.
 	 */
-	if (!cpumask_equal(cpu_l2_cache_mask(cpu), cpu_sibling_mask(cpu)))
+	if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu)))
 		shared_caches = true;
 
 	set_numa_node(numa_cpu_lookup_table[cpu]);
@@ -1083,6 +1273,8 @@
 	notify_cpu_starting(cpu);
 	set_cpu_online(cpu, true);
 
+	boot_init_stack_canary();
+
 	local_irq_enable();
 
 	/* We can enable ftrace for secondary cpus now */
@@ -1140,6 +1332,13 @@
 	return cpu_l2_cache_mask(cpu);
 }
 
+#ifdef CONFIG_SCHED_SMT
+static const struct cpumask *smallcore_smt_mask(int cpu)
+{
+	return cpu_smallcore_mask(cpu);
+}
+#endif
+
 static struct sched_domain_topology_level power9_topology[] = {
 #ifdef CONFIG_SCHED_SMT
 	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
@@ -1167,6 +1366,13 @@
 	shared_proc_topology_init();
 	dump_numa_cpu_topology();
 
+#ifdef CONFIG_SCHED_SMT
+	if (has_big_cores) {
+		pr_info("Using small cores at SMT level\n");
+		power9_topology[0].mask = smallcore_smt_mask;
+		powerpc_topology[0].mask = smallcore_smt_mask;
+	}
+#endif
 	/*
 	 * If any CPU detects that it's sharing a cache with another CPU then
 	 * use the deeper topology that is aware of this sharing.
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index e2c50b5..e2a46cf 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -67,12 +67,17 @@
 {
 	unsigned long sp;
 
+	if (!try_get_task_stack(tsk))
+		return;
+
 	if (tsk == current)
 		sp = current_stack_pointer();
 	else
 		sp = tsk->thread.ksp;
 
 	save_context_stack(trace, sp, tsk, 0);
+
+	put_task_stack(tsk);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
@@ -84,25 +89,21 @@
 EXPORT_SYMBOL_GPL(save_stack_trace_regs);
 
 #ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
-int
-save_stack_trace_tsk_reliable(struct task_struct *tsk,
-				struct stack_trace *trace)
+/*
+ * This function returns an error if it detects any unreliable features of the
+ * stack.  Otherwise it guarantees that the stack trace is reliable.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+static int __save_stack_trace_tsk_reliable(struct task_struct *tsk,
+					   struct stack_trace *trace)
 {
 	unsigned long sp;
+	unsigned long newsp;
 	unsigned long stack_page = (unsigned long)task_stack_page(tsk);
 	unsigned long stack_end;
 	int graph_idx = 0;
-
-	/*
-	 * The last frame (unwinding first) may not yet have saved
-	 * its LR onto the stack.
-	 */
-	int firstframe = 1;
-
-	if (tsk == current)
-		sp = current_stack_pointer();
-	else
-		sp = tsk->thread.ksp;
+	bool firstframe;
 
 	stack_end = stack_page + THREAD_SIZE;
 	if (!is_idle_task(tsk)) {
@@ -129,71 +130,96 @@
 		stack_end -= STACK_FRAME_OVERHEAD;
 	}
 
+	if (tsk == current)
+		sp = current_stack_pointer();
+	else
+		sp = tsk->thread.ksp;
+
 	if (sp < stack_page + sizeof(struct thread_struct) ||
 	    sp > stack_end - STACK_FRAME_MIN_SIZE) {
-		return 1;
+		return -EINVAL;
 	}
 
-	for (;;) {
+	for (firstframe = true; sp != stack_end;
+	     firstframe = false, sp = newsp) {
 		unsigned long *stack = (unsigned long *) sp;
-		unsigned long newsp, ip;
+		unsigned long ip;
 
 		/* sanity check: ABI requires SP to be aligned 16 bytes. */
 		if (sp & 0xF)
-			return 1;
-
-		/* Mark stacktraces with exception frames as unreliable. */
-		if (sp <= stack_end - STACK_INT_FRAME_SIZE &&
-		    stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
-			return 1;
-		}
+			return -EINVAL;
 
 		newsp = stack[0];
 		/* Stack grows downwards; unwinder may only go up. */
 		if (newsp <= sp)
-			return 1;
+			return -EINVAL;
 
 		if (newsp != stack_end &&
 		    newsp > stack_end - STACK_FRAME_MIN_SIZE) {
-			return 1; /* invalid backlink, too far up. */
+			return -EINVAL; /* invalid backlink, too far up. */
+		}
+
+		/*
+		 * We can only trust the bottom frame's backlink, the
+		 * rest of the frame may be uninitialized, continue to
+		 * the next.
+		 */
+		if (firstframe)
+			continue;
+
+		/* Mark stacktraces with exception frames as unreliable. */
+		if (sp <= stack_end - STACK_INT_FRAME_SIZE &&
+		    stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
+			return -EINVAL;
 		}
 
 		/* Examine the saved LR: it must point into kernel code. */
 		ip = stack[STACK_FRAME_LR_SAVE];
-		if (!firstframe && !__kernel_text_address(ip))
-			return 1;
-		firstframe = 0;
+		if (!__kernel_text_address(ip))
+			return -EINVAL;
 
 		/*
 		 * FIXME: IMHO these tests do not belong in
 		 * arch-dependent code, they are generic.
 		 */
-		ip = ftrace_graph_ret_addr(tsk, &graph_idx, ip, NULL);
+		ip = ftrace_graph_ret_addr(tsk, &graph_idx, ip, stack);
 #ifdef CONFIG_KPROBES
 		/*
 		 * Mark stacktraces with kretprobed functions on them
 		 * as unreliable.
 		 */
 		if (ip == (unsigned long)kretprobe_trampoline)
-			return 1;
+			return -EINVAL;
 #endif
 
+		if (trace->nr_entries >= trace->max_entries)
+			return -E2BIG;
 		if (!trace->skip)
 			trace->entries[trace->nr_entries++] = ip;
 		else
 			trace->skip--;
-
-		if (newsp == stack_end)
-			break;
-
-		if (trace->nr_entries >= trace->max_entries)
-			return -E2BIG;
-
-		sp = newsp;
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable);
+
+int save_stack_trace_tsk_reliable(struct task_struct *tsk,
+				  struct stack_trace *trace)
+{
+	int ret;
+
+	/*
+	 * If the task doesn't have a stack (e.g., a zombie), the stack is
+	 * "reliably" empty.
+	 */
+	if (!try_get_task_stack(tsk))
+		return 0;
+
+	ret = __save_stack_trace_tsk_reliable(tsk, trace);
+
+	put_task_stack(tsk);
+
+	return ret;
+}
 #endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
 
 #if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI)
diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c
index a531154..b84992c 100644
--- a/arch/powerpc/kernel/suspend.c
+++ b/arch/powerpc/kernel/suspend.c
@@ -1,13 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Suspend support specific for power.
  *
- * Distribute under GPLv2
- *
  * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz>
  * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
  */
 
 #include <linux/mm.h>
+#include <linux/suspend.h>
 #include <asm/page.h>
 #include <asm/sections.h>
 
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index 0050b2d..41dcb21 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Common powerpc suspend code for 32 and 64 bits
  *
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/sched.h>
diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S
index 7a919e9..cbdf862 100644
--- a/arch/powerpc/kernel/swsusp_32.S
+++ b/arch/powerpc/kernel/swsusp_32.S
@@ -25,11 +25,19 @@
 #define SL_IBAT2	0x48
 #define SL_DBAT3	0x50
 #define SL_IBAT3	0x58
-#define SL_TB		0x60
-#define SL_R2		0x68
-#define SL_CR		0x6c
-#define SL_LR		0x70
-#define SL_R12		0x74	/* r12 to r31 */
+#define SL_DBAT4	0x60
+#define SL_IBAT4	0x68
+#define SL_DBAT5	0x70
+#define SL_IBAT5	0x78
+#define SL_DBAT6	0x80
+#define SL_IBAT6	0x88
+#define SL_DBAT7	0x90
+#define SL_IBAT7	0x98
+#define SL_TB		0xa0
+#define SL_R2		0xa8
+#define SL_CR		0xac
+#define SL_LR		0xb0
+#define SL_R12		0xb4	/* r12 to r31 */
 #define SL_SIZE		(SL_R12 + 80)
 
 	.section .data
@@ -114,6 +122,41 @@
 	mfibatl	r4,3
 	stw	r4,SL_IBAT3+4(r11)
 
+BEGIN_MMU_FTR_SECTION
+	mfspr	r4,SPRN_DBAT4U
+	stw	r4,SL_DBAT4(r11)
+	mfspr	r4,SPRN_DBAT4L
+	stw	r4,SL_DBAT4+4(r11)
+	mfspr	r4,SPRN_DBAT5U
+	stw	r4,SL_DBAT5(r11)
+	mfspr	r4,SPRN_DBAT5L
+	stw	r4,SL_DBAT5+4(r11)
+	mfspr	r4,SPRN_DBAT6U
+	stw	r4,SL_DBAT6(r11)
+	mfspr	r4,SPRN_DBAT6L
+	stw	r4,SL_DBAT6+4(r11)
+	mfspr	r4,SPRN_DBAT7U
+	stw	r4,SL_DBAT7(r11)
+	mfspr	r4,SPRN_DBAT7L
+	stw	r4,SL_DBAT7+4(r11)
+	mfspr	r4,SPRN_IBAT4U
+	stw	r4,SL_IBAT4(r11)
+	mfspr	r4,SPRN_IBAT4L
+	stw	r4,SL_IBAT4+4(r11)
+	mfspr	r4,SPRN_IBAT5U
+	stw	r4,SL_IBAT5(r11)
+	mfspr	r4,SPRN_IBAT5L
+	stw	r4,SL_IBAT5+4(r11)
+	mfspr	r4,SPRN_IBAT6U
+	stw	r4,SL_IBAT6(r11)
+	mfspr	r4,SPRN_IBAT6L
+	stw	r4,SL_IBAT6+4(r11)
+	mfspr	r4,SPRN_IBAT7U
+	stw	r4,SL_IBAT7(r11)
+	mfspr	r4,SPRN_IBAT7L
+	stw	r4,SL_IBAT7+4(r11)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
 #if  0
 	/* Backup various CPU config stuffs */
 	bl	__save_cpu_setup
@@ -279,27 +322,41 @@
 	mtibatu	3,r4
 	lwz	r4,SL_IBAT3+4(r11)
 	mtibatl	3,r4
-#endif
-
 BEGIN_MMU_FTR_SECTION
-	li	r4,0
+	lwz	r4,SL_DBAT4(r11)
 	mtspr	SPRN_DBAT4U,r4
+	lwz	r4,SL_DBAT4+4(r11)
 	mtspr	SPRN_DBAT4L,r4
+	lwz	r4,SL_DBAT5(r11)
 	mtspr	SPRN_DBAT5U,r4
+	lwz	r4,SL_DBAT5+4(r11)
 	mtspr	SPRN_DBAT5L,r4
+	lwz	r4,SL_DBAT6(r11)
 	mtspr	SPRN_DBAT6U,r4
+	lwz	r4,SL_DBAT6+4(r11)
 	mtspr	SPRN_DBAT6L,r4
+	lwz	r4,SL_DBAT7(r11)
 	mtspr	SPRN_DBAT7U,r4
+	lwz	r4,SL_DBAT7+4(r11)
 	mtspr	SPRN_DBAT7L,r4
+	lwz	r4,SL_IBAT4(r11)
 	mtspr	SPRN_IBAT4U,r4
+	lwz	r4,SL_IBAT4+4(r11)
 	mtspr	SPRN_IBAT4L,r4
+	lwz	r4,SL_IBAT5(r11)
 	mtspr	SPRN_IBAT5U,r4
+	lwz	r4,SL_IBAT5+4(r11)
 	mtspr	SPRN_IBAT5L,r4
+	lwz	r4,SL_IBAT6(r11)
 	mtspr	SPRN_IBAT6U,r4
+	lwz	r4,SL_IBAT6+4(r11)
 	mtspr	SPRN_IBAT6L,r4
+	lwz	r4,SL_IBAT7(r11)
 	mtspr	SPRN_IBAT7U,r4
+	lwz	r4,SL_IBAT7+4(r11)
 	mtspr	SPRN_IBAT7L,r4
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+#endif
 
 	/* Flush all TLBs */
 	lis	r4,0x1000
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
index 51db012..aeea97a 100644
--- a/arch/powerpc/kernel/swsusp_64.c
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * PowerPC 64-bit swsusp implementation
  *
  * Copyright 2006 Johannes Berg <johannes@sipsolutions.net>
- *
- * GPLv2
  */
 
 #include <asm/iommu.h>
diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S
index f83bf6f..6d31898 100644
--- a/arch/powerpc/kernel/swsusp_asm64.S
+++ b/arch/powerpc/kernel/swsusp_asm64.S
@@ -1,9 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * PowerPC 64-bit swsusp implementation
  *
  * Copyright 2006 Johannes Berg <johannes@sipsolutions.net>
- *
- * GPLv2
  */
 
 #include <linux/threads.h>
@@ -262,7 +261,7 @@
 
 	addi	r1,r1,-128
 #ifdef CONFIG_PPC_BOOK3S_64
-	bl	slb_flush_and_rebolt
+	bl	slb_flush_and_restore_bolted
 #endif
 	bl	do_after_copyback
 	addi	r1,r1,128
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index bdf58ba..d36c639 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * sys_ppc32.c: Conversion between 32bit and 64bit native syscalls.
  *
@@ -7,11 +8,6 @@
  *
  * These routines maintain argument size conversion between 32bit and 64bit
  * environment.
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index 4662165..3bfb388 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Implementation of various system calls for Linux/PowerPC
  *
@@ -11,12 +12,6 @@
  * This file contains various random system calls that
  * have a non-standard calling sequence on the Linux/PPC
  * platform.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/errno.h>
@@ -89,7 +84,7 @@
 	if ( (unsigned long)n >= 4096 )
 	{
 		unsigned long __user *buffer = (unsigned long __user *)n;
-		if (!access_ok(VERIFY_READ, buffer, 5*sizeof(unsigned long))
+		if (!access_ok(buffer, 5*sizeof(unsigned long))
 		    || __get_user(n, buffer)
 		    || __get_user(inp, ((fd_set __user * __user *)(buffer+1)))
 		    || __get_user(outp, ((fd_set  __user * __user *)(buffer+2)))
@@ -123,7 +118,7 @@
 				 (u64)len_high << 32 | len_low, advice);
 }
 
-long sys_switch_endian(void)
+SYSCALL_DEFINE0(switch_endian)
 {
 	struct thread_info *ti;
 
diff --git a/arch/powerpc/kernel/syscalls/Makefile b/arch/powerpc/kernel/syscalls/Makefile
new file mode 100644
index 0000000..27b4895
--- /dev/null
+++ b/arch/powerpc/kernel/syscalls/Makefile
@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: GPL-2.0
+kapi := arch/$(SRCARCH)/include/generated/asm
+uapi := arch/$(SRCARCH)/include/generated/uapi/asm
+
+_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)')	\
+	  $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)')
+
+syscall := $(srctree)/$(src)/syscall.tbl
+syshdr := $(srctree)/$(src)/syscallhdr.sh
+systbl := $(srctree)/$(src)/syscalltbl.sh
+
+quiet_cmd_syshdr = SYSHDR  $@
+      cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@'	\
+		   '$(syshdr_abis_$(basetarget))'		\
+		   '$(syshdr_pfx_$(basetarget))'		\
+		   '$(syshdr_offset_$(basetarget))'
+
+quiet_cmd_systbl = SYSTBL  $@
+      cmd_systbl = $(CONFIG_SHELL) '$(systbl)' '$<' '$@'	\
+		   '$(systbl_abis_$(basetarget))'		\
+		   '$(systbl_abi_$(basetarget))'		\
+		   '$(systbl_offset_$(basetarget))'
+
+syshdr_abis_unistd_32 := common,nospu,32
+$(uapi)/unistd_32.h: $(syscall) $(syshdr)
+	$(call if_changed,syshdr)
+
+syshdr_abis_unistd_64 := common,nospu,64
+$(uapi)/unistd_64.h: $(syscall) $(syshdr)
+	$(call if_changed,syshdr)
+
+systbl_abis_syscall_table_32 := common,nospu,32
+systbl_abi_syscall_table_32 := 32
+$(kapi)/syscall_table_32.h: $(syscall) $(systbl)
+	$(call if_changed,systbl)
+
+systbl_abis_syscall_table_64 := common,nospu,64
+systbl_abi_syscall_table_64 := 64
+$(kapi)/syscall_table_64.h: $(syscall) $(systbl)
+	$(call if_changed,systbl)
+
+systbl_abis_syscall_table_c32 := common,nospu,32
+systbl_abi_syscall_table_c32 := c32
+$(kapi)/syscall_table_c32.h: $(syscall) $(systbl)
+	$(call if_changed,systbl)
+
+systbl_abis_syscall_table_spu := common,spu
+systbl_abi_syscall_table_spu := spu
+$(kapi)/syscall_table_spu.h: $(syscall) $(systbl)
+	$(call if_changed,systbl)
+
+uapisyshdr-y		+= unistd_32.h unistd_64.h
+kapisyshdr-y		+= syscall_table_32.h		\
+			   syscall_table_64.h		\
+			   syscall_table_c32.h		\
+			   syscall_table_spu.h
+
+targets	+= $(uapisyshdr-y) $(kapisyshdr-y)
+
+PHONY += all
+all: $(addprefix $(uapi)/,$(uapisyshdr-y))
+all: $(addprefix $(kapi)/,$(kapisyshdr-y))
+	@:
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
new file mode 100644
index 0000000..43f736e
--- /dev/null
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -0,0 +1,519 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# system call numbers and entry vectors for powerpc
+#
+# The format is:
+# <number> <abi> <name> <entry point> <compat entry point>
+#
+# The <abi> can be common, spu, nospu, 64, or 32 for this file.
+#
+0	nospu	restart_syscall			sys_restart_syscall
+1	nospu	exit				sys_exit
+2	nospu	fork				ppc_fork
+3	common	read				sys_read
+4	common	write				sys_write
+5	common	open				sys_open			compat_sys_open
+6	common	close				sys_close
+7	common	waitpid				sys_waitpid
+8	common	creat				sys_creat
+9	common	link				sys_link
+10	common	unlink				sys_unlink
+11	nospu	execve				sys_execve			compat_sys_execve
+12	common	chdir				sys_chdir
+13	32	time				sys_time32
+13	64	time				sys_time
+13	spu	time				sys_time
+14	common	mknod				sys_mknod
+15	common	chmod				sys_chmod
+16	common	lchown				sys_lchown
+17	common	break				sys_ni_syscall
+18	32	oldstat				sys_stat			sys_ni_syscall
+18	64	oldstat				sys_ni_syscall
+18	spu	oldstat				sys_ni_syscall
+19	common	lseek				sys_lseek			compat_sys_lseek
+20	common	getpid				sys_getpid
+21	nospu	mount				sys_mount			compat_sys_mount
+22	32	umount				sys_oldumount
+22	64	umount				sys_ni_syscall
+22	spu	umount				sys_ni_syscall
+23	common	setuid				sys_setuid
+24	common	getuid				sys_getuid
+25	32	stime				sys_stime32
+25	64	stime				sys_stime
+25	spu	stime				sys_stime
+26	nospu	ptrace				sys_ptrace			compat_sys_ptrace
+27	common	alarm				sys_alarm
+28	32	oldfstat			sys_fstat			sys_ni_syscall
+28	64	oldfstat			sys_ni_syscall
+28	spu	oldfstat			sys_ni_syscall
+29	nospu	pause				sys_pause
+30	32	utime				sys_utime32
+30	64	utime				sys_utime
+31	common	stty				sys_ni_syscall
+32	common	gtty				sys_ni_syscall
+33	common	access				sys_access
+34	common	nice				sys_nice
+35	common	ftime				sys_ni_syscall
+36	common	sync				sys_sync
+37	common	kill				sys_kill
+38	common	rename				sys_rename
+39	common	mkdir				sys_mkdir
+40	common	rmdir				sys_rmdir
+41	common	dup				sys_dup
+42	common	pipe				sys_pipe
+43	common	times				sys_times			compat_sys_times
+44	common	prof				sys_ni_syscall
+45	common	brk				sys_brk
+46	common	setgid				sys_setgid
+47	common	getgid				sys_getgid
+48	nospu	signal				sys_signal
+49	common	geteuid				sys_geteuid
+50	common	getegid				sys_getegid
+51	nospu	acct				sys_acct
+52	nospu	umount2				sys_umount
+53	common	lock				sys_ni_syscall
+54	common	ioctl				sys_ioctl			compat_sys_ioctl
+55	common	fcntl				sys_fcntl			compat_sys_fcntl
+56	common	mpx				sys_ni_syscall
+57	common	setpgid				sys_setpgid
+58	common	ulimit				sys_ni_syscall
+59	32	oldolduname			sys_olduname
+59	64	oldolduname			sys_ni_syscall
+59	spu	oldolduname			sys_ni_syscall
+60	common	umask				sys_umask
+61	common	chroot				sys_chroot
+62	nospu	ustat				sys_ustat			compat_sys_ustat
+63	common	dup2				sys_dup2
+64	common	getppid				sys_getppid
+65	common	getpgrp				sys_getpgrp
+66	common	setsid				sys_setsid
+67	32	sigaction			sys_sigaction			compat_sys_sigaction
+67	64	sigaction			sys_ni_syscall
+67	spu	sigaction			sys_ni_syscall
+68	common	sgetmask			sys_sgetmask
+69	common	ssetmask			sys_ssetmask
+70	common	setreuid			sys_setreuid
+71	common	setregid			sys_setregid
+72	32	sigsuspend			sys_sigsuspend
+72	64	sigsuspend			sys_ni_syscall
+72	spu	sigsuspend			sys_ni_syscall
+73	32	sigpending			sys_sigpending			compat_sys_sigpending
+73	64	sigpending			sys_ni_syscall
+73	spu	sigpending			sys_ni_syscall
+74	common	sethostname			sys_sethostname
+75	common	setrlimit			sys_setrlimit			compat_sys_setrlimit
+76	32	getrlimit			sys_old_getrlimit		compat_sys_old_getrlimit
+76	64	getrlimit			sys_ni_syscall
+76	spu	getrlimit			sys_ni_syscall
+77	common	getrusage			sys_getrusage			compat_sys_getrusage
+78	common	gettimeofday			sys_gettimeofday		compat_sys_gettimeofday
+79	common	settimeofday			sys_settimeofday		compat_sys_settimeofday
+80	common	getgroups			sys_getgroups
+81	common	setgroups			sys_setgroups
+82	32	select				ppc_select			sys_ni_syscall
+82	64	select				sys_ni_syscall
+82	spu	select				sys_ni_syscall
+83	common	symlink				sys_symlink
+84	32	oldlstat			sys_lstat			sys_ni_syscall
+84	64	oldlstat			sys_ni_syscall
+84	spu	oldlstat			sys_ni_syscall
+85	common	readlink			sys_readlink
+86	nospu	uselib				sys_uselib
+87	nospu	swapon				sys_swapon
+88	nospu	reboot				sys_reboot
+89	32	readdir				sys_old_readdir			compat_sys_old_readdir
+89	64	readdir				sys_ni_syscall
+89	spu	readdir				sys_ni_syscall
+90	common	mmap				sys_mmap
+91	common	munmap				sys_munmap
+92	common	truncate			sys_truncate			compat_sys_truncate
+93	common	ftruncate			sys_ftruncate			compat_sys_ftruncate
+94	common	fchmod				sys_fchmod
+95	common	fchown				sys_fchown
+96	common	getpriority			sys_getpriority
+97	common	setpriority			sys_setpriority
+98	common	profil				sys_ni_syscall
+99	nospu	statfs				sys_statfs			compat_sys_statfs
+100	nospu	fstatfs				sys_fstatfs			compat_sys_fstatfs
+101	common	ioperm				sys_ni_syscall
+102	common	socketcall			sys_socketcall			compat_sys_socketcall
+103	common	syslog				sys_syslog
+104	common	setitimer			sys_setitimer			compat_sys_setitimer
+105	common	getitimer			sys_getitimer			compat_sys_getitimer
+106	common	stat				sys_newstat			compat_sys_newstat
+107	common	lstat				sys_newlstat			compat_sys_newlstat
+108	common	fstat				sys_newfstat			compat_sys_newfstat
+109	32	olduname			sys_uname
+109	64	olduname			sys_ni_syscall
+109	spu	olduname			sys_ni_syscall
+110	common	iopl				sys_ni_syscall
+111	common	vhangup				sys_vhangup
+112	common	idle				sys_ni_syscall
+113	common	vm86				sys_ni_syscall
+114	common	wait4				sys_wait4			compat_sys_wait4
+115	nospu	swapoff				sys_swapoff
+116	common	sysinfo				sys_sysinfo			compat_sys_sysinfo
+117	nospu	ipc				sys_ipc				compat_sys_ipc
+118	common	fsync				sys_fsync
+119	32	sigreturn			sys_sigreturn			compat_sys_sigreturn
+119	64	sigreturn			sys_ni_syscall
+119	spu	sigreturn			sys_ni_syscall
+120	nospu	clone				ppc_clone
+121	common	setdomainname			sys_setdomainname
+122	common	uname				sys_newuname
+123	common	modify_ldt			sys_ni_syscall
+124	32	adjtimex			sys_adjtimex_time32
+124	64	adjtimex			sys_adjtimex
+124	spu	adjtimex			sys_adjtimex
+125	common	mprotect			sys_mprotect
+126	32	sigprocmask			sys_sigprocmask			compat_sys_sigprocmask
+126	64	sigprocmask			sys_ni_syscall
+126	spu	sigprocmask			sys_ni_syscall
+127	common	create_module			sys_ni_syscall
+128	nospu	init_module			sys_init_module
+129	nospu	delete_module			sys_delete_module
+130	common	get_kernel_syms			sys_ni_syscall
+131	nospu	quotactl			sys_quotactl
+132	common	getpgid				sys_getpgid
+133	common	fchdir				sys_fchdir
+134	common	bdflush				sys_bdflush
+135	common	sysfs				sys_sysfs
+136	32	personality			sys_personality			ppc64_personality
+136	64	personality			ppc64_personality
+136	spu	personality			ppc64_personality
+137	common	afs_syscall			sys_ni_syscall
+138	common	setfsuid			sys_setfsuid
+139	common	setfsgid			sys_setfsgid
+140	common	_llseek				sys_llseek
+141	common	getdents			sys_getdents			compat_sys_getdents
+142	common	_newselect			sys_select			compat_sys_select
+143	common	flock				sys_flock
+144	common	msync				sys_msync
+145	common	readv				sys_readv			compat_sys_readv
+146	common	writev				sys_writev			compat_sys_writev
+147	common	getsid				sys_getsid
+148	common	fdatasync			sys_fdatasync
+149	nospu	_sysctl				sys_sysctl			compat_sys_sysctl
+150	common	mlock				sys_mlock
+151	common	munlock				sys_munlock
+152	common	mlockall			sys_mlockall
+153	common	munlockall			sys_munlockall
+154	common	sched_setparam			sys_sched_setparam
+155	common	sched_getparam			sys_sched_getparam
+156	common	sched_setscheduler		sys_sched_setscheduler
+157	common	sched_getscheduler		sys_sched_getscheduler
+158	common	sched_yield			sys_sched_yield
+159	common	sched_get_priority_max		sys_sched_get_priority_max
+160	common	sched_get_priority_min		sys_sched_get_priority_min
+161	32	sched_rr_get_interval		sys_sched_rr_get_interval_time32
+161	64	sched_rr_get_interval		sys_sched_rr_get_interval
+161	spu	sched_rr_get_interval		sys_sched_rr_get_interval
+162	32	nanosleep			sys_nanosleep_time32
+162	64	nanosleep			sys_nanosleep
+162	spu	nanosleep			sys_nanosleep
+163	common	mremap				sys_mremap
+164	common	setresuid			sys_setresuid
+165	common	getresuid			sys_getresuid
+166	common	query_module			sys_ni_syscall
+167	common	poll				sys_poll
+168	common	nfsservctl			sys_ni_syscall
+169	common	setresgid			sys_setresgid
+170	common	getresgid			sys_getresgid
+171	common	prctl				sys_prctl
+172	nospu	rt_sigreturn			sys_rt_sigreturn		compat_sys_rt_sigreturn
+173	nospu	rt_sigaction			sys_rt_sigaction		compat_sys_rt_sigaction
+174	nospu	rt_sigprocmask			sys_rt_sigprocmask		compat_sys_rt_sigprocmask
+175	nospu	rt_sigpending			sys_rt_sigpending		compat_sys_rt_sigpending
+176	32	rt_sigtimedwait			sys_rt_sigtimedwait_time32	compat_sys_rt_sigtimedwait_time32
+176	64	rt_sigtimedwait			sys_rt_sigtimedwait
+177	nospu 	rt_sigqueueinfo			sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
+178	nospu 	rt_sigsuspend			sys_rt_sigsuspend		compat_sys_rt_sigsuspend
+179	common	pread64				sys_pread64			compat_sys_pread64
+180	common	pwrite64			sys_pwrite64			compat_sys_pwrite64
+181	common	chown				sys_chown
+182	common	getcwd				sys_getcwd
+183	common	capget				sys_capget
+184	common	capset				sys_capset
+185	nospu	sigaltstack			sys_sigaltstack			compat_sys_sigaltstack
+186	32	sendfile			sys_sendfile			compat_sys_sendfile
+186	64	sendfile			sys_sendfile64
+186	spu	sendfile			sys_sendfile64
+187	common	getpmsg				sys_ni_syscall
+188	common 	putpmsg				sys_ni_syscall
+189	nospu	vfork				ppc_vfork
+190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
+191	common	readahead			sys_readahead			compat_sys_readahead
+192	32	mmap2				sys_mmap2			compat_sys_mmap2
+193	32	truncate64			sys_truncate64			compat_sys_truncate64
+194	32	ftruncate64			sys_ftruncate64			compat_sys_ftruncate64
+195	32	stat64				sys_stat64
+196	32	lstat64				sys_lstat64
+197	32	fstat64				sys_fstat64
+198	nospu 	pciconfig_read			sys_pciconfig_read
+199	nospu 	pciconfig_write			sys_pciconfig_write
+200	nospu 	pciconfig_iobase		sys_pciconfig_iobase
+201	common 	multiplexer			sys_ni_syscall
+202	common	getdents64			sys_getdents64
+203	common	pivot_root			sys_pivot_root
+204	32	fcntl64				sys_fcntl64			compat_sys_fcntl64
+205	common	madvise				sys_madvise
+206	common	mincore				sys_mincore
+207	common	gettid				sys_gettid
+208	common	tkill				sys_tkill
+209	common	setxattr			sys_setxattr
+210	common	lsetxattr			sys_lsetxattr
+211	common	fsetxattr			sys_fsetxattr
+212	common	getxattr			sys_getxattr
+213	common	lgetxattr			sys_lgetxattr
+214	common	fgetxattr			sys_fgetxattr
+215	common	listxattr			sys_listxattr
+216	common	llistxattr			sys_llistxattr
+217	common	flistxattr			sys_flistxattr
+218	common	removexattr			sys_removexattr
+219	common	lremovexattr			sys_lremovexattr
+220	common	fremovexattr			sys_fremovexattr
+221	32	futex				sys_futex_time32
+221	64	futex				sys_futex
+221	spu	futex				sys_futex
+222	common	sched_setaffinity		sys_sched_setaffinity		compat_sys_sched_setaffinity
+223	common	sched_getaffinity		sys_sched_getaffinity		compat_sys_sched_getaffinity
+# 224 unused
+225	common	tuxcall				sys_ni_syscall
+226	32	sendfile64			sys_sendfile64			compat_sys_sendfile64
+227	common	io_setup			sys_io_setup			compat_sys_io_setup
+228	common	io_destroy			sys_io_destroy
+229	32	io_getevents			sys_io_getevents_time32
+229	64	io_getevents			sys_io_getevents
+229	spu	io_getevents			sys_io_getevents
+230	common	io_submit			sys_io_submit			compat_sys_io_submit
+231	common	io_cancel			sys_io_cancel
+232	nospu	set_tid_address			sys_set_tid_address
+233	common	fadvise64			sys_fadvise64			ppc32_fadvise64
+234	nospu	exit_group			sys_exit_group
+235	nospu	lookup_dcookie			sys_lookup_dcookie		compat_sys_lookup_dcookie
+236	common	epoll_create			sys_epoll_create
+237	common	epoll_ctl			sys_epoll_ctl
+238	common	epoll_wait			sys_epoll_wait
+239	common	remap_file_pages		sys_remap_file_pages
+240	common	timer_create			sys_timer_create		compat_sys_timer_create
+241	32	timer_settime			sys_timer_settime32
+241	64	timer_settime			sys_timer_settime
+241	spu	timer_settime			sys_timer_settime
+242	32	timer_gettime			sys_timer_gettime32
+242	64	timer_gettime			sys_timer_gettime
+242	spu	timer_gettime			sys_timer_gettime
+243	common	timer_getoverrun		sys_timer_getoverrun
+244	common	timer_delete			sys_timer_delete
+245	32	clock_settime			sys_clock_settime32
+245	64	clock_settime			sys_clock_settime
+245	spu	clock_settime			sys_clock_settime
+246	32	clock_gettime			sys_clock_gettime32
+246	64	clock_gettime			sys_clock_gettime
+246	spu	clock_gettime			sys_clock_gettime
+247	32	clock_getres			sys_clock_getres_time32
+247	64	clock_getres			sys_clock_getres
+247	spu	clock_getres			sys_clock_getres
+248	32	clock_nanosleep			sys_clock_nanosleep_time32
+248	64	clock_nanosleep			sys_clock_nanosleep
+248	spu	clock_nanosleep			sys_clock_nanosleep
+249	32	swapcontext			ppc_swapcontext			ppc32_swapcontext
+249	64	swapcontext			ppc64_swapcontext
+249	spu	swapcontext			sys_ni_syscall
+250	common	tgkill				sys_tgkill
+251	32	utimes				sys_utimes_time32
+251	64	utimes				sys_utimes
+251	spu	utimes				sys_utimes
+252	common	statfs64			sys_statfs64			compat_sys_statfs64
+253	common	fstatfs64			sys_fstatfs64			compat_sys_fstatfs64
+254	32	fadvise64_64			ppc_fadvise64_64
+254	spu	fadvise64_64			sys_ni_syscall
+255	common	rtas				sys_rtas
+256	32	sys_debug_setcontext		sys_debug_setcontext		sys_ni_syscall
+256	64	sys_debug_setcontext		sys_ni_syscall
+256	spu	sys_debug_setcontext		sys_ni_syscall
+# 257 reserved for vserver
+258	nospu	migrate_pages			sys_migrate_pages		compat_sys_migrate_pages
+259	nospu	mbind				sys_mbind			compat_sys_mbind
+260	nospu	get_mempolicy			sys_get_mempolicy		compat_sys_get_mempolicy
+261	nospu	set_mempolicy			sys_set_mempolicy		compat_sys_set_mempolicy
+262	nospu	mq_open				sys_mq_open			compat_sys_mq_open
+263	nospu	mq_unlink			sys_mq_unlink
+264	32	mq_timedsend			sys_mq_timedsend_time32
+264	64	mq_timedsend			sys_mq_timedsend
+265	32	mq_timedreceive			sys_mq_timedreceive_time32
+265	64	mq_timedreceive			sys_mq_timedreceive
+266	nospu	mq_notify			sys_mq_notify			compat_sys_mq_notify
+267	nospu	mq_getsetattr			sys_mq_getsetattr		compat_sys_mq_getsetattr
+268	nospu	kexec_load			sys_kexec_load			compat_sys_kexec_load
+269	nospu	add_key				sys_add_key
+270	nospu	request_key			sys_request_key
+271	nospu	keyctl				sys_keyctl			compat_sys_keyctl
+272	nospu	waitid				sys_waitid			compat_sys_waitid
+273	nospu	ioprio_set			sys_ioprio_set
+274	nospu	ioprio_get			sys_ioprio_get
+275	nospu	inotify_init			sys_inotify_init
+276	nospu	inotify_add_watch		sys_inotify_add_watch
+277	nospu	inotify_rm_watch		sys_inotify_rm_watch
+278	nospu	spu_run				sys_spu_run
+279	nospu	spu_create			sys_spu_create
+280	32	pselect6			sys_pselect6_time32		compat_sys_pselect6_time32
+280	64	pselect6			sys_pselect6
+281	32	ppoll				sys_ppoll_time32		compat_sys_ppoll_time32
+281	64	ppoll				sys_ppoll
+282	common	unshare				sys_unshare
+283	common	splice				sys_splice
+284	common	tee				sys_tee
+285	common	vmsplice			sys_vmsplice			compat_sys_vmsplice
+286	common	openat				sys_openat			compat_sys_openat
+287	common	mkdirat				sys_mkdirat
+288	common	mknodat				sys_mknodat
+289	common	fchownat			sys_fchownat
+290	32	futimesat			sys_futimesat_time32
+290	64	futimesat			sys_futimesat
+290	spu	utimesat			sys_futimesat
+291	32	fstatat64			sys_fstatat64
+291	64	newfstatat			sys_newfstatat
+291	spu	newfstatat			sys_newfstatat
+292	common	unlinkat			sys_unlinkat
+293	common	renameat			sys_renameat
+294	common	linkat				sys_linkat
+295	common	symlinkat			sys_symlinkat
+296	common	readlinkat			sys_readlinkat
+297	common	fchmodat			sys_fchmodat
+298	common	faccessat			sys_faccessat
+299	common	get_robust_list			sys_get_robust_list		compat_sys_get_robust_list
+300	common	set_robust_list			sys_set_robust_list		compat_sys_set_robust_list
+301	common	move_pages			sys_move_pages			compat_sys_move_pages
+302	common	getcpu				sys_getcpu
+303	nospu	epoll_pwait			sys_epoll_pwait			compat_sys_epoll_pwait
+304	32	utimensat			sys_utimensat_time32
+304	64	utimensat			sys_utimensat
+304	spu	utimensat			sys_utimensat
+305	common	signalfd			sys_signalfd			compat_sys_signalfd
+306	common	timerfd_create			sys_timerfd_create
+307	common	eventfd				sys_eventfd
+308	common	sync_file_range2		sys_sync_file_range2		compat_sys_sync_file_range2
+309	nospu	fallocate			sys_fallocate			compat_sys_fallocate
+310	nospu	subpage_prot			sys_subpage_prot
+311	32	timerfd_settime			sys_timerfd_settime32
+311	64	timerfd_settime			sys_timerfd_settime
+311	spu	timerfd_settime			sys_timerfd_settime
+312	32	timerfd_gettime			sys_timerfd_gettime32
+312	64	timerfd_gettime			sys_timerfd_gettime
+312	spu	timerfd_gettime			sys_timerfd_gettime
+313	common	signalfd4			sys_signalfd4			compat_sys_signalfd4
+314	common	eventfd2			sys_eventfd2
+315	common	epoll_create1			sys_epoll_create1
+316	common	dup3				sys_dup3
+317	common	pipe2				sys_pipe2
+318	nospu	inotify_init1			sys_inotify_init1
+319	common	perf_event_open			sys_perf_event_open
+320	common	preadv				sys_preadv			compat_sys_preadv
+321	common	pwritev				sys_pwritev			compat_sys_pwritev
+322	nospu	rt_tgsigqueueinfo		sys_rt_tgsigqueueinfo		compat_sys_rt_tgsigqueueinfo
+323	nospu	fanotify_init			sys_fanotify_init
+324	nospu	fanotify_mark			sys_fanotify_mark		compat_sys_fanotify_mark
+325	common	prlimit64			sys_prlimit64
+326	common	socket				sys_socket
+327	common	bind				sys_bind
+328	common	connect				sys_connect
+329	common	listen				sys_listen
+330	common	accept				sys_accept
+331	common	getsockname			sys_getsockname
+332	common	getpeername			sys_getpeername
+333	common	socketpair			sys_socketpair
+334	common	send				sys_send
+335	common	sendto				sys_sendto
+336	common	recv				sys_recv			compat_sys_recv
+337	common	recvfrom			sys_recvfrom			compat_sys_recvfrom
+338	common	shutdown			sys_shutdown
+339	common	setsockopt			sys_setsockopt			compat_sys_setsockopt
+340	common	getsockopt			sys_getsockopt			compat_sys_getsockopt
+341	common	sendmsg				sys_sendmsg			compat_sys_sendmsg
+342	common	recvmsg				sys_recvmsg			compat_sys_recvmsg
+343	32	recvmmsg			sys_recvmmsg_time32		compat_sys_recvmmsg_time32
+343	64	recvmmsg			sys_recvmmsg
+343	spu	recvmmsg			sys_recvmmsg
+344	common	accept4				sys_accept4
+345	common	name_to_handle_at		sys_name_to_handle_at
+346	common	open_by_handle_at		sys_open_by_handle_at		compat_sys_open_by_handle_at
+347	32	clock_adjtime			sys_clock_adjtime32
+347	64	clock_adjtime			sys_clock_adjtime
+347	spu	clock_adjtime			sys_clock_adjtime
+348	common	syncfs				sys_syncfs
+349	common	sendmmsg			sys_sendmmsg			compat_sys_sendmmsg
+350	common	setns				sys_setns
+351	nospu	process_vm_readv		sys_process_vm_readv		compat_sys_process_vm_readv
+352	nospu	process_vm_writev		sys_process_vm_writev		compat_sys_process_vm_writev
+353	nospu	finit_module			sys_finit_module
+354	nospu	kcmp				sys_kcmp
+355	common	sched_setattr			sys_sched_setattr
+356	common	sched_getattr			sys_sched_getattr
+357	common	renameat2			sys_renameat2
+358	common	seccomp				sys_seccomp
+359	common	getrandom			sys_getrandom
+360	common	memfd_create			sys_memfd_create
+361	common	bpf				sys_bpf
+362	nospu	execveat			sys_execveat			compat_sys_execveat
+363	32	switch_endian			sys_ni_syscall
+363	64	switch_endian			ppc_switch_endian
+363	spu	switch_endian			sys_ni_syscall
+364	common	userfaultfd			sys_userfaultfd
+365	common	membarrier			sys_membarrier
+# 366-377 originally left for IPC, now unused
+378	nospu	mlock2				sys_mlock2
+379	nospu	copy_file_range			sys_copy_file_range
+380	common	preadv2				sys_preadv2			compat_sys_preadv2
+381	common	pwritev2			sys_pwritev2			compat_sys_pwritev2
+382	nospu	kexec_file_load			sys_kexec_file_load
+383	nospu	statx				sys_statx
+384	nospu	pkey_alloc			sys_pkey_alloc
+385	nospu	pkey_free			sys_pkey_free
+386	nospu	pkey_mprotect			sys_pkey_mprotect
+387	nospu	rseq				sys_rseq
+388	32	io_pgetevents			sys_io_pgetevents_time32	compat_sys_io_pgetevents
+388	64	io_pgetevents			sys_io_pgetevents
+# room for arch specific syscalls
+392	64	semtimedop			sys_semtimedop
+393	common	semget				sys_semget
+394	common	semctl				sys_semctl			compat_sys_semctl
+395	common	shmget				sys_shmget
+396	common	shmctl				sys_shmctl			compat_sys_shmctl
+397	common	shmat				sys_shmat			compat_sys_shmat
+398	common	shmdt				sys_shmdt
+399	common	msgget				sys_msgget
+400	common	msgsnd				sys_msgsnd			compat_sys_msgsnd
+401	common	msgrcv				sys_msgrcv			compat_sys_msgrcv
+402	common	msgctl				sys_msgctl			compat_sys_msgctl
+403	32	clock_gettime64			sys_clock_gettime		sys_clock_gettime
+404	32	clock_settime64			sys_clock_settime		sys_clock_settime
+405	32	clock_adjtime64			sys_clock_adjtime		sys_clock_adjtime
+406	32	clock_getres_time64		sys_clock_getres		sys_clock_getres
+407	32	clock_nanosleep_time64		sys_clock_nanosleep		sys_clock_nanosleep
+408	32	timer_gettime64			sys_timer_gettime		sys_timer_gettime
+409	32	timer_settime64			sys_timer_settime		sys_timer_settime
+410	32	timerfd_gettime64		sys_timerfd_gettime		sys_timerfd_gettime
+411	32	timerfd_settime64		sys_timerfd_settime		sys_timerfd_settime
+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
+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
+420	32	semtimedop_time64		sys_semtimedop			sys_semtimedop
+421	32	rt_sigtimedwait_time64		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait_time64
+422	32	futex_time64			sys_futex			sys_futex
+423	32	sched_rr_get_interval_time64	sys_sched_rr_get_interval	sys_sched_rr_get_interval
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
+428	common	open_tree			sys_open_tree
+429	common	move_mount			sys_move_mount
+430	common	fsopen				sys_fsopen
+431	common	fsconfig			sys_fsconfig
+432	common	fsmount				sys_fsmount
+433	common	fspick				sys_fspick
+434	common	pidfd_open			sys_pidfd_open
+435	nospu	clone3				ppc_clone3
diff --git a/arch/powerpc/kernel/syscalls/syscallhdr.sh b/arch/powerpc/kernel/syscalls/syscallhdr.sh
new file mode 100644
index 0000000..c0a9a32
--- /dev/null
+++ b/arch/powerpc/kernel/syscalls/syscallhdr.sh
@@ -0,0 +1,37 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+in="$1"
+out="$2"
+my_abis=`echo "($3)" | tr ',' '|'`
+prefix="$4"
+offset="$5"
+
+fileguard=_UAPI_ASM_POWERPC_`basename "$out" | sed \
+	-e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \
+	-e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'`
+grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
+	printf "#ifndef %s\n" "${fileguard}"
+	printf "#define %s\n" "${fileguard}"
+	printf "\n"
+
+	nxt=0
+	while read nr abi name entry compat ; do
+		if [ -z "$offset" ]; then
+			printf "#define __NR_%s%s\t%s\n" \
+				"${prefix}" "${name}" "${nr}"
+		else
+			printf "#define __NR_%s%s\t(%s + %s)\n" \
+				"${prefix}" "${name}" "${offset}" "${nr}"
+		fi
+		nxt=$((nr+1))
+	done
+
+	printf "\n"
+	printf "#ifdef __KERNEL__\n"
+	printf "#define __NR_syscalls\t%s\n" "${nxt}"
+	printf "#endif\n"
+	printf "\n"
+	printf "#endif /* %s */" "${fileguard}"
+	printf "\n"
+) > "$out"
diff --git a/arch/powerpc/kernel/syscalls/syscalltbl.sh b/arch/powerpc/kernel/syscalls/syscalltbl.sh
new file mode 100644
index 0000000..f7393a7
--- /dev/null
+++ b/arch/powerpc/kernel/syscalls/syscalltbl.sh
@@ -0,0 +1,36 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+in="$1"
+out="$2"
+my_abis=`echo "($3)" | tr ',' '|'`
+my_abi="$4"
+offset="$5"
+
+emit() {
+	t_nxt="$1"
+	t_nr="$2"
+	t_entry="$3"
+
+	while [ $t_nxt -lt $t_nr ]; do
+		printf "__SYSCALL(%s,sys_ni_syscall)\n" "${t_nxt}"
+		t_nxt=$((t_nxt+1))
+	done
+	printf "__SYSCALL(%s,%s)\n" "${t_nxt}" "${t_entry}"
+}
+
+grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
+	nxt=0
+	if [ -z "$offset" ]; then
+		offset=0
+	fi
+
+	while read nr abi name entry compat ; do
+		if [ "$my_abi" = "c32" ] && [ ! -z "$compat" ]; then
+			emit $((nxt+offset)) $((nr+offset)) $compat
+		else
+			emit $((nxt+offset)) $((nr+offset)) $entry
+		fi
+		nxt=$((nr+1))
+	done
+) > "$out"
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 755dc98..80a676d 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 #include <linux/device.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
@@ -18,6 +19,7 @@
 #include <asm/smp.h>
 #include <asm/pmc.h>
 #include <asm/firmware.h>
+#include <asm/svm.h>
 
 #include "cacheinfo.h"
 #include "setup.h"
@@ -457,7 +459,7 @@
 #define HAS_PPC_PMC_CLASSIC	1
 #define HAS_PPC_PMC_IBM		1
 #define HAS_PPC_PMC_PA6T	1
-#elif defined(CONFIG_6xx)
+#elif defined(CONFIG_PPC_BOOK3S_32)
 #define HAS_PPC_PMC_CLASSIC	1
 #define HAS_PPC_PMC_IBM		1
 #define HAS_PPC_PMC_G4		1
@@ -610,7 +612,7 @@
 SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3);
 SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4);
 SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5);
-#ifdef CONFIG_DEBUG_KERNEL
+#ifdef CONFIG_DEBUG_MISC
 SYSFS_SPRSETUP(hid0, SPRN_HID0);
 SYSFS_SPRSETUP(hid1, SPRN_HID1);
 SYSFS_SPRSETUP(hid4, SPRN_HID4);
@@ -639,7 +641,7 @@
 SYSFS_SPRSETUP(tsr1, SPRN_PA6T_TSR1);
 SYSFS_SPRSETUP(tsr2, SPRN_PA6T_TSR2);
 SYSFS_SPRSETUP(tsr3, SPRN_PA6T_TSR3);
-#endif /* CONFIG_DEBUG_KERNEL */
+#endif /* CONFIG_DEBUG_MISC */
 #endif /* HAS_PPC_PMC_PA6T */
 
 #ifdef HAS_PPC_PMC_IBM
@@ -680,7 +682,7 @@
 	__ATTR(pmc3, 0600, show_pa6t_pmc3, store_pa6t_pmc3),
 	__ATTR(pmc4, 0600, show_pa6t_pmc4, store_pa6t_pmc4),
 	__ATTR(pmc5, 0600, show_pa6t_pmc5, store_pa6t_pmc5),
-#ifdef CONFIG_DEBUG_KERNEL
+#ifdef CONFIG_DEBUG_MISC
 	__ATTR(hid0, 0600, show_hid0, store_hid0),
 	__ATTR(hid1, 0600, show_hid1, store_hid1),
 	__ATTR(hid4, 0600, show_hid4, store_hid4),
@@ -709,11 +711,28 @@
 	__ATTR(tsr1, 0600, show_tsr1, store_tsr1),
 	__ATTR(tsr2, 0600, show_tsr2, store_tsr2),
 	__ATTR(tsr3, 0600, show_tsr3, store_tsr3),
-#endif /* CONFIG_DEBUG_KERNEL */
+#endif /* CONFIG_DEBUG_MISC */
 };
 #endif /* HAS_PPC_PMC_PA6T */
 #endif /* HAS_PPC_PMC_CLASSIC */
 
+#ifdef CONFIG_PPC_SVM
+static ssize_t show_svm(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", is_secure_guest());
+}
+static DEVICE_ATTR(svm, 0444, show_svm, NULL);
+
+static void create_svm_file(void)
+{
+	device_create_file(cpu_subsys.dev_root, &dev_attr_svm);
+}
+#else
+static void create_svm_file(void)
+{
+}
+#endif /* CONFIG_PPC_SVM */
+
 static int register_cpu_online(unsigned int cpu)
 {
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
@@ -1057,6 +1076,8 @@
 	sysfs_create_dscr_default();
 #endif /* CONFIG_PPC64 */
 
+	create_svm_file();
+
 	return 0;
 }
 subsys_initcall(topology_init);
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index 919a327..5b905a2 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains the table of syscall-handling functions.
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -7,37 +8,10 @@
  *
  * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
  * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com) 
- * 
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/ppc_asm.h>
 
-#ifdef CONFIG_PPC64
-#define SYSCALL(func)		.8byte	DOTSYM(sys_##func),DOTSYM(sys_##func)
-#define COMPAT_SYS(func)	.8byte	DOTSYM(sys_##func),DOTSYM(compat_sys_##func)
-#define PPC_SYS(func)		.8byte	DOTSYM(ppc_##func),DOTSYM(ppc_##func)
-#define OLDSYS(func)		.8byte	DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall)
-#define SYS32ONLY(func)		.8byte	DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func)
-#define PPC64ONLY(func)		.8byte	DOTSYM(ppc_##func),DOTSYM(sys_ni_syscall)
-#define SYSX(f, f3264, f32)	.8byte	DOTSYM(f),DOTSYM(f3264)
-#else
-#define SYSCALL(func)		.long	sys_##func
-#define COMPAT_SYS(func)	.long	sys_##func
-#define PPC_SYS(func)		.long	ppc_##func
-#define OLDSYS(func)		.long	sys_##func
-#define SYS32ONLY(func)		.long	sys_##func
-#define PPC64ONLY(func)		.long	sys_ni_syscall
-#define SYSX(f, f3264, f32)	.long	f32
-#endif
-#define SYSCALL_SPU(func)	SYSCALL(func)
-#define COMPAT_SYS_SPU(func)	COMPAT_SYS(func)
-#define COMPAT_SPU_NEW(func)	COMPAT_SYS(func)
-#define SYSX_SPU(f, f3264, f32)	SYSX(f, f3264, f32)
-
 .section .rodata,"a"
 
 #ifdef CONFIG_PPC64
@@ -46,5 +20,21 @@
 
 .globl sys_call_table
 sys_call_table:
+#ifdef CONFIG_PPC64
+#define __SYSCALL(nr, entry)	.8byte DOTSYM(entry)
+#include <asm/syscall_table_64.h>
+#undef __SYSCALL
+#else
+#define __SYSCALL(nr, entry)	.long entry
+#include <asm/syscall_table_32.h>
+#undef __SYSCALL
+#endif
 
-#include <asm/systbl.h>
+#ifdef CONFIG_COMPAT
+.globl compat_sys_call_table
+compat_sys_call_table:
+#define compat_sys_sigsuspend	sys_sigsuspend
+#define __SYSCALL(nr, entry)	.8byte DOTSYM(entry)
+#include <asm/syscall_table_c32.h>
+#undef __SYSCALL
+#endif
diff --git a/arch/powerpc/kernel/systbl_chk.c b/arch/powerpc/kernel/systbl_chk.c
deleted file mode 100644
index 4653258..0000000
--- a/arch/powerpc/kernel/systbl_chk.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * This file, when run through CPP produces a list of syscall numbers
- * in the order of systbl.h.  That way we can check for gaps and syscalls
- * that are out of order.
- *
- * Unfortunately, we cannot check for the correct ordering of entries
- * using SYSX().
- *
- * Copyright © IBM 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; either version
- * 2 of the License, or (at your option) any later version.
- */
-#include <asm/unistd.h>
-
-#define SYSCALL(func)		__NR_##func
-#define COMPAT_SYS(func)	__NR_##func
-#define PPC_SYS(func)		__NR_##func
-#ifdef CONFIG_PPC64
-#define OLDSYS(func)		-1
-#define SYS32ONLY(func)		-1
-#define PPC64ONLY(func)		__NR_##func
-#else
-#define OLDSYS(func)		__NR_old##func
-#define SYS32ONLY(func)		__NR_##func
-#define PPC64ONLY(func)		-1
-#endif
-#define SYSX(f, f3264, f32)	-1
-
-#define SYSCALL_SPU(func)	SYSCALL(func)
-#define COMPAT_SYS_SPU(func)	COMPAT_SYS(func)
-#define COMPAT_SPU_NEW(func)	COMPAT_SYS(_new##func)
-#define SYSX_SPU(f, f3264, f32)	SYSX(f, f3264, f32)
-
-/* Just insert a marker for ni_syscalls */
-#define	__NR_ni_syscall		-1
-
-/*
- * These are the known exceptions.
- * Hopefully, there will be no more.
- */
-#define	__NR_llseek		__NR__llseek
-#undef	__NR_umount
-#define	__NR_umount		__NR_umount2
-#define	__NR_old_getrlimit	__NR_getrlimit
-#define	__NR_newstat		__NR_stat
-#define	__NR_newlstat		__NR_lstat
-#define	__NR_newfstat		__NR_fstat
-#define	__NR_newuname		__NR_uname
-#define	__NR_sysctl		__NR__sysctl
-#define __NR_olddebug_setcontext	__NR_sys_debug_setcontext
-
-/* We call sys_ugetrlimit for syscall number __NR_getrlimit */
-#define getrlimit		ugetrlimit
-
-START_TABLE
-#include <asm/systbl.h>
-END_TABLE NR_syscalls
diff --git a/arch/powerpc/kernel/systbl_chk.sh b/arch/powerpc/kernel/systbl_chk.sh
index f2e356c..c7ac3ed 100644
--- a/arch/powerpc/kernel/systbl_chk.sh
+++ b/arch/powerpc/kernel/systbl_chk.sh
@@ -1,14 +1,11 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
 #
 # Just process the CPP output from systbl_chk.c and complain
 # if anything is out of order.
 #
 # Copyright © 2008 IBM 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; either version
-# 2 of the License, or (at your option) any later version.
 
 awk	'BEGIN { num = -1; }	# Ignore the beginning of the file
 	/^#/ { next; }
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 70f145e..6945223 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Common time routines among all ppc machines.
  *
@@ -24,11 +25,6 @@
  *
  * 1997-09-10  Updated NTP code according to technical memorandum Jan '96
  *             "A Kernel Model for Precision Timekeeping" by Dave Mills
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <linux/errno.h>
@@ -43,7 +39,6 @@
 #include <linux/timex.h>
 #include <linux/kernel_stat.h>
 #include <linux/time.h>
-#include <linux/clockchips.h>
 #include <linux/init.h>
 #include <linux/profile.h>
 #include <linux/cpu.h>
@@ -57,7 +52,6 @@
 #include <linux/irq_work.h>
 #include <linux/clk-provider.h>
 #include <linux/suspend.h>
-#include <linux/rtc.h>
 #include <linux/sched/cputime.h>
 #include <linux/processor.h>
 #include <asm/trace.h>
@@ -111,6 +105,7 @@
 	.rating			= 200,
 	.irq			= 0,
 	.set_next_event		= decrementer_set_next_event,
+	.set_state_oneshot_stopped = decrementer_shutdown,
 	.set_state_shutdown	= decrementer_shutdown,
 	.tick_resume		= decrementer_shutdown,
 	.features		= CLOCK_EVT_FEAT_ONESHOT |
@@ -151,6 +146,8 @@
 unsigned long ppc_tb_freq;
 EXPORT_SYMBOL_GPL(ppc_tb_freq);
 
+bool tb_invalid;
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /*
  * Factor for converting from cputime_t (timebase ticks) to
@@ -175,7 +172,7 @@
  * Read the SPURR on systems that have it, otherwise the PURR,
  * or if that doesn't exist return the timebase value passed in.
  */
-static unsigned long read_spurr(unsigned long tb)
+static inline unsigned long read_spurr(unsigned long tb)
 {
 	if (cpu_has_feature(CPU_FTR_SPURR))
 		return mfspr(SPRN_SPURR);
@@ -281,26 +278,17 @@
  * Account time for a transition between system, hard irq
  * or soft irq state.
  */
-static unsigned long vtime_delta(struct task_struct *tsk,
-				 unsigned long *stime_scaled,
-				 unsigned long *steal_time)
+static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct,
+					unsigned long now, unsigned long stime)
 {
-	unsigned long now, nowscaled, deltascaled;
-	unsigned long stime;
+	unsigned long stime_scaled = 0;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+	unsigned long nowscaled, deltascaled;
 	unsigned long utime, utime_scaled;
-	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	WARN_ON_ONCE(!irqs_disabled());
-
-	now = mftb();
 	nowscaled = read_spurr(now);
-	stime = now - acct->starttime;
-	acct->starttime = now;
 	deltascaled = nowscaled - acct->startspurr;
 	acct->startspurr = nowscaled;
-
-	*steal_time = calculate_stolen_time(now);
-
 	utime = acct->utime - acct->utime_sspurr;
 	acct->utime_sspurr = acct->utime;
 
@@ -314,17 +302,38 @@
 	 * the user ticks get saved up in paca->user_time_scaled to be
 	 * used by account_process_tick.
 	 */
-	*stime_scaled = stime;
+	stime_scaled = stime;
 	utime_scaled = utime;
 	if (deltascaled != stime + utime) {
 		if (utime) {
-			*stime_scaled = deltascaled * stime / (stime + utime);
-			utime_scaled = deltascaled - *stime_scaled;
+			stime_scaled = deltascaled * stime / (stime + utime);
+			utime_scaled = deltascaled - stime_scaled;
 		} else {
-			*stime_scaled = deltascaled;
+			stime_scaled = deltascaled;
 		}
 	}
 	acct->utime_scaled += utime_scaled;
+#endif
+
+	return stime_scaled;
+}
+
+static unsigned long vtime_delta(struct task_struct *tsk,
+				 unsigned long *stime_scaled,
+				 unsigned long *steal_time)
+{
+	unsigned long now, stime;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	now = mftb();
+	stime = now - acct->starttime;
+	acct->starttime = now;
+
+	*stime_scaled = vtime_delta_scaled(acct, now, stime);
+
+	*steal_time = calculate_stolen_time(now);
 
 	return stime;
 }
@@ -341,7 +350,9 @@
 
 	if ((tsk->flags & PF_VCPU) && !irq_count()) {
 		acct->gtime += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 		acct->utime_scaled += stime_scaled;
+#endif
 	} else {
 		if (hardirq_count())
 			acct->hardirq_time += stime;
@@ -350,7 +361,9 @@
 		else
 			acct->stime += stime;
 
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 		acct->stime_scaled += stime_scaled;
+#endif
 	}
 }
 EXPORT_SYMBOL_GPL(vtime_account_system);
@@ -364,6 +377,21 @@
 	acct->idle_time += stime + steal_time;
 }
 
+static void vtime_flush_scaled(struct task_struct *tsk,
+			       struct cpu_accounting_data *acct)
+{
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+	if (acct->utime_scaled)
+		tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
+	if (acct->stime_scaled)
+		tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
+
+	acct->utime_scaled = 0;
+	acct->utime_sspurr = 0;
+	acct->stime_scaled = 0;
+#endif
+}
+
 /*
  * Account the whole cputime accumulated in the paca
  * Must be called with interrupts disabled.
@@ -378,14 +406,13 @@
 	if (acct->utime)
 		account_user_time(tsk, cputime_to_nsecs(acct->utime));
 
-	if (acct->utime_scaled)
-		tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
-
 	if (acct->gtime)
 		account_guest_time(tsk, cputime_to_nsecs(acct->gtime));
 
-	if (acct->steal_time)
+	if (IS_ENABLED(CONFIG_PPC_SPLPAR) && acct->steal_time) {
 		account_steal_time(cputime_to_nsecs(acct->steal_time));
+		acct->steal_time = 0;
+	}
 
 	if (acct->idle_time)
 		account_idle_time(cputime_to_nsecs(acct->idle_time));
@@ -393,8 +420,6 @@
 	if (acct->stime)
 		account_system_index_time(tsk, cputime_to_nsecs(acct->stime),
 					  CPUTIME_SYSTEM);
-	if (acct->stime_scaled)
-		tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
 
 	if (acct->hardirq_time)
 		account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time),
@@ -403,14 +428,12 @@
 		account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time),
 					  CPUTIME_SOFTIRQ);
 
+	vtime_flush_scaled(tsk, acct);
+
 	acct->utime = 0;
-	acct->utime_scaled = 0;
-	acct->utime_sspurr = 0;
 	acct->gtime = 0;
-	acct->steal_time = 0;
 	acct->idle_time = 0;
 	acct->stime = 0;
-	acct->stime_scaled = 0;
 	acct->hardirq_time = 0;
 	acct->softirq_time = 0;
 }
@@ -434,6 +457,13 @@
 				diff += 1000000000;
 			spin_cpu_relax();
 		} while (diff < loops);
+	} else if (tb_invalid) {
+		/*
+		 * TB is in error state and isn't ticking anymore.
+		 * HMI handler was unable to recover from TB error.
+		 * Return immediately, so that kernel won't get stuck here.
+		 */
+		spin_cpu_relax();
 	} else {
 		start = get_tbl();
 		while (get_tbl() - start < loops)
@@ -984,10 +1014,14 @@
 	*dec = decrementer_clockevent;
 	dec->cpumask = cpumask_of(cpu);
 
+	clockevents_config_and_register(dec, ppc_tb_freq, 2, decrementer_max);
+
 	printk_once(KERN_DEBUG "clockevent: %s mult[%x] shift[%d] cpu[%d]\n",
 		    dec->name, dec->mult, dec->shift, cpu);
 
-	clockevents_register_device(dec);
+	/* Set values for KVM, see kvm_emulate_dec() */
+	decrementer_clockevent.mult = dec->mult;
+	decrementer_clockevent.shift = dec->shift;
 }
 
 static void enable_large_decrementer(void)
@@ -1035,18 +1069,7 @@
 
 static void __init init_decrementer_clockevent(void)
 {
-	int cpu = smp_processor_id();
-
-	clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4);
-
-	decrementer_clockevent.max_delta_ns =
-		clockevent_delta2ns(decrementer_max, &decrementer_clockevent);
-	decrementer_clockevent.max_delta_ticks = decrementer_max;
-	decrementer_clockevent.min_delta_ns =
-		clockevent_delta2ns(2, &decrementer_clockevent);
-	decrementer_clockevent.min_delta_ticks = 2;
-
-	register_decrementer_clockevent(cpu);
+	register_decrementer_clockevent(smp_processor_id());
 }
 
 void secondary_cpu_time_init(void)
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 7716374..6ba0fdd 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -92,13 +92,14 @@
 	blr
 EXPORT_SYMBOL_GPL(tm_abort);
 
-/* void tm_reclaim(struct thread_struct *thread,
+/*
+ * void tm_reclaim(struct thread_struct *thread,
  *		   uint8_t cause)
  *
  *	- Performs a full reclaim.  This destroys outstanding
- *	  transactions and updates thread->regs.tm_ckpt_* with the
- *	  original checkpointed state.  Note that thread->regs is
- *	  unchanged.
+ *	  transactions and updates thread.ckpt_regs, thread.ckfp_state and
+ *	  thread.ckvr_state with the original checkpointed state.  Note that
+ *	  thread->regs is unchanged.
  *
  * Purpose is to both abort transactions of, and preserve the state of,
  * a transactions at a context switch. We preserve/restore both sets of process
@@ -147,7 +148,7 @@
 	/* Stash the stack pointer away for use after reclaim */
 	std	r1, PACAR1(r13)
 
-	/* Clear MSR RI since we are about to change r1, EE is already off. */
+	/* Clear MSR RI since we are about to use SCRATCH0, EE is already off */
 	li	r5, 0
 	mtmsrd	r5, 1
 
@@ -163,15 +164,16 @@
 	 */
 	TRECLAIM(R4)				/* Cause in r4 */
 
-	/* ******************** GPRs ******************** */
-	/* Stash the checkpointed r13 away in the scratch SPR and get the real
-	 *  paca
+	/*
+	 * ******************** GPRs ********************
+	 * Stash the checkpointed r13 in the scratch SPR and get the real paca.
 	 */
 	SET_SCRATCH0(r13)
 	GET_PACA(r13)
 
-	/* Stash the checkpointed r1 away in paca tm_scratch and get the real
-	 * stack pointer back
+	/*
+	 * Stash the checkpointed r1 away in paca->tm_scratch and get the real
+	 * stack pointer back into r1.
 	 */
 	std	r1, PACATMSCRATCH(r13)
 	ld	r1, PACAR1(r13)
@@ -209,14 +211,15 @@
 
 	addi	r7, r12, PT_CKPT_REGS		/* Thread's ckpt_regs */
 
-	/* Make r7 look like an exception frame so that we
-	 * can use the neat GPRx(n) macros.  r7 is NOT a pt_regs ptr!
+	/*
+	 * Make r7 look like an exception frame so that we can use the neat
+	 * GPRx(n) macros. r7 is NOT a pt_regs ptr!
 	 */
 	subi	r7, r7, STACK_FRAME_OVERHEAD
 
 	/* Sync the userland GPRs 2-12, 14-31 to thread->regs: */
 	SAVE_GPR(0, r7)				/* user r0 */
-	SAVE_GPR(2, r7)			/* user r2 */
+	SAVE_GPR(2, r7)				/* user r2 */
 	SAVE_4GPRS(3, r7)			/* user r3-r6 */
 	SAVE_GPR(8, r7)				/* user r8 */
 	SAVE_GPR(9, r7)				/* user r9 */
@@ -237,7 +240,8 @@
 	/* ******************** NIP ******************** */
 	mfspr	r3, SPRN_TFHAR
 	std	r3, _NIP(r7)			/* Returns to failhandler */
-	/* The checkpointed NIP is ignored when rescheduling/rechkpting,
+	/*
+	 * The checkpointed NIP is ignored when rescheduling/rechkpting,
 	 * but is used in signal return to 'wind back' to the abort handler.
 	 */
 
@@ -260,12 +264,13 @@
 	std	r3, THREAD_TM_TAR(r12)
 	std	r4, THREAD_TM_DSCR(r12)
 
-	/* MSR and flags:  We don't change CRs, and we don't need to alter
-	 * MSR.
+	/*
+	 * MSR and flags: We don't change CRs, and we don't need to alter MSR.
 	 */
 
 
-	/* ******************** FPR/VR/VSRs ************
+	/*
+	 * ******************** FPR/VR/VSRs ************
 	 * After reclaiming, capture the checkpointed FPRs/VRs.
 	 *
 	 * We enabled VEC/FP/VSX in the msr above, so we can execute these
@@ -275,7 +280,7 @@
 
 	/* Altivec (VEC/VMX/VR)*/
 	addi	r7, r3, THREAD_CKVRSTATE
-	SAVE_32VRS(0, r6, r7)	/* r6 scratch, r7 transact vr state */
+	SAVE_32VRS(0, r6, r7)	/* r6 scratch, r7 ckvr_state */
 	mfvscr	v0
 	li	r6, VRSTATE_VSCR
 	stvx	v0, r7, r6
@@ -286,12 +291,13 @@
 
 	/* Floating Point (FP) */
 	addi	r7, r3, THREAD_CKFPSTATE
-	SAVE_32FPRS_VSRS(0, R6, R7)	/* r6 scratch, r7 transact fp state */
+	SAVE_32FPRS_VSRS(0, R6, R7)	/* r6 scratch, r7 ckfp_state */
 	mffs    fr0
 	stfd    fr0,FPSTATE_FPSCR(r7)
 
 
-	/* TM regs, incl TEXASR -- these live in thread_struct.  Note they've
+	/*
+	 * TM regs, incl TEXASR -- these live in thread_struct.  Note they've
 	 * been updated by the treclaim, to explain to userland the failure
 	 * cause (aborted).
 	 */
@@ -327,7 +333,7 @@
 	blr
 
 
-       /*
+	/*
 	 * void __tm_recheckpoint(struct thread_struct *thread)
 	 *	- Restore the checkpointed register state saved by tm_reclaim
 	 *	  when we switch_to a process.
@@ -343,7 +349,8 @@
 	std	r2, STK_GOT(r1)
 	stdu	r1, -TM_FRAME_SIZE(r1)
 
-	/* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD].
+	/*
+	 * We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD].
 	 * This is used for backing up the NVGPRs:
 	 */
 	SAVE_NVGPRS(r1)
@@ -352,8 +359,9 @@
 
 	addi	r7, r3, PT_CKPT_REGS		/* Thread's ckpt_regs */
 
-	/* Make r7 look like an exception frame so that we
-	 * can use the neat GPRx(n) macros.  r7 is now NOT a pt_regs ptr!
+	/*
+	 * Make r7 look like an exception frame so that we can use the neat
+	 * GPRx(n) macros. r7 is now NOT a pt_regs ptr!
 	 */
 	subi	r7, r7, STACK_FRAME_OVERHEAD
 
@@ -421,14 +429,15 @@
 
 	REST_NVGPRS(r7)				/* GPR14-31 */
 
-	/* Load up PPR and DSCR here so we don't run with user values for long
-	 */
+	/* Load up PPR and DSCR here so we don't run with user values for long */
 	mtspr	SPRN_DSCR, r5
 	mtspr	SPRN_PPR, r6
 
-	/* Do final sanity check on TEXASR to make sure FS is set.  Do this
+	/*
+	 * Do final sanity check on TEXASR to make sure FS is set. Do this
 	 * here before we load up the userspace r1 so any bugs we hit will get
-	 * a call chain */
+	 * a call chain.
+	 */
 	mfspr	r5, SPRN_TEXASR
 	srdi	r5, r5, 16
 	li	r6, (TEXASR_FS)@h
@@ -436,8 +445,9 @@
 1:	tdeqi	r6, 0
 	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
 
-	/* Do final sanity check on MSR to make sure we are not transactional
-	 * or suspended
+	/*
+	 * Do final sanity check on MSR to make sure we are not transactional
+	 * or suspended.
 	 */
 	mfmsr   r6
 	li	r5, (MSR_TS_MASK)@higher
@@ -453,8 +463,8 @@
 	REST_GPR(6, r7)
 
 	/*
-	 * Store r1 and r5 on the stack so that we can access them
-	 * after we clear MSR RI.
+	 * Store r1 and r5 on the stack so that we can access them after we
+	 * clear MSR RI.
 	 */
 
 	REST_GPR(5, r7)
@@ -464,7 +474,7 @@
 
 	REST_GPR(7, r7)
 
-	/* Clear MSR RI since we are about to change r1. EE is already off */
+	/* Clear MSR RI since we are about to use SCRATCH0. EE is already off */
 	li	r5, 0
 	mtmsrd	r5, 1
 
@@ -484,7 +494,8 @@
 
 	HMT_MEDIUM
 
-	/* Our transactional state has now changed.
+	/*
+	 * Our transactional state has now changed.
 	 *
 	 * Now just get out of here.  Transactional (current) state will be
 	 * updated once restore is called on the return path in the _switch-ed
diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
index d22d8ba..8585037 100644
--- a/arch/powerpc/kernel/trace/Makefile
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -3,11 +3,9 @@
 # Makefile for the powerpc trace subsystem
 #
 
-subdir-ccflags-$(CONFIG_PPC_WERROR)	:= -Werror
-
 ifdef CONFIG_FUNCTION_TRACER
 # do not trace tracer code
-CFLAGS_REMOVE_ftrace.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
 endif
 
 obj32-$(CONFIG_FUNCTION_TRACER)		+= ftrace_32.o
@@ -25,6 +23,7 @@
 obj-$(CONFIG_PPC64)			+= $(obj64-y)
 obj-$(CONFIG_PPC32)			+= $(obj32-y)
 
-# Disable GCOV & sanitizers in odd or sensitive code
+# Disable GCOV, KCOV & sanitizers in odd or sensitive code
 GCOV_PROFILE_ftrace.o := n
+KCOV_INSTRUMENT_ftrace.o := n
 UBSAN_SANITIZE_ftrace.o := n
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 19ef4f5..7ea0ca0 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -30,6 +30,16 @@
 
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+
+/*
+ * 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];
+
 static unsigned int
 ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
 {
@@ -85,16 +95,19 @@
 	return create_branch((unsigned int *)ip, addr, 0);
 }
 
-#ifdef CONFIG_MODULES
-
 static int is_bl_op(unsigned int op)
 {
 	return (op & 0xfc000003) == 0x48000001;
 }
 
+static int is_b_op(unsigned int op)
+{
+	return (op & 0xfc000003) == 0x48000000;
+}
+
 static unsigned long find_bl_target(unsigned long ip, unsigned int op)
 {
-	static int offset;
+	int offset;
 
 	offset = (op & 0x03fffffc);
 	/* make it signed */
@@ -104,6 +117,7 @@
 	return ip + (long)offset;
 }
 
+#ifdef CONFIG_MODULES
 #ifdef CONFIG_PPC64
 static int
 __ftrace_make_nop(struct module *mod,
@@ -270,6 +284,146 @@
 #endif /* PPC64 */
 #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 (create_branch((void *)ip, ftrace_tramps[i], 0))
+			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, op;
+	unsigned long ptr;
+	static unsigned long ftrace_plt_tramps[NUM_FTRACE_TRAMPS];
+
+	/* Is this a known long jump tramp? */
+	for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+		if (!ftrace_tramps[i])
+			break;
+		else if (ftrace_tramps[i] == tramp)
+			return 0;
+
+	/* Is this a known plt tramp? */
+	for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+		if (!ftrace_plt_tramps[i])
+			break;
+		else if (ftrace_plt_tramps[i] == tramp)
+			return -1;
+
+	/* New trampoline -- read where this goes */
+	if (probe_kernel_read(&op, (void *)tramp, sizeof(int))) {
+		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 */
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+	ptr = ppc_global_function_entry((void *)ftrace_regs_caller);
+#else
+	ptr = ppc_global_function_entry((void *)ftrace_caller);
+#endif
+	if (!create_branch((void *)tramp, ptr, 0)) {
+		pr_debug("%ps is not reachable from existing mcount tramp\n",
+				(void *)ptr);
+		return -1;
+	}
+
+	if (patch_branch((unsigned int *)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;
+	unsigned int op;
+
+	/* Read where this goes */
+	if (probe_kernel_read(&op, (void *)ip, sizeof(int))) {
+		pr_err("Fetching opcode failed.\n");
+		return -EFAULT;
+	}
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(op)) {
+		pr_err("Not expected bl: opcode is %x\n", 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((unsigned int *)ip, PPC_INST_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)
 {
@@ -286,7 +440,8 @@
 		old = ftrace_call_replace(ip, addr, 1);
 		new = PPC_INST_NOP;
 		return ftrace_modify_code(ip, old, new);
-	}
+	} else if (core_kernel_text(ip))
+		return __ftrace_make_nop_kernel(rec, addr);
 
 #ifdef CONFIG_MODULES
 	/*
@@ -456,6 +611,53 @@
 #endif /* CONFIG_PPC64 */
 #endif /* CONFIG_MODULES */
 
+static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int 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) {
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+		entry = ppc_global_function_entry((void *)ftrace_regs_caller);
+		if (ptr != entry) {
+#endif
+			pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr);
+			return -EINVAL;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+		}
+#endif
+	}
+
+	/* Make sure we have a nop */
+	if (probe_kernel_read(&op, ip, sizeof(op))) {
+		pr_err("Unable to read ftrace location %p\n", ip);
+		return -EFAULT;
+	}
+
+	if (op != PPC_INST_NOP) {
+		pr_err("Unexpected call sequence at %p: %x\n", ip, 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;
@@ -471,7 +673,8 @@
 		old = PPC_INST_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);
 
 #ifdef CONFIG_MODULES
 	/*
@@ -603,6 +806,12 @@
 		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;
 	}
 
 #ifdef CONFIG_MODULES
@@ -654,10 +863,50 @@
 	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[];
+
+int __init ftrace_dyn_arch_init(void)
+{
+	int i;
+	unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
+	u32 stub_insns[] = {
+		0xe98d0000 | PACATOC,	/* ld      r12,PACATOC(r13)	*/
+		0x3d8c0000,		/* addis   r12,r12,<high>	*/
+		0x398c0000,		/* addi    r12,r12,<low>	*/
+		0x7d8903a6,		/* mtctr   r12			*/
+		0x4e800420,		/* bctr				*/
+	};
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+	unsigned long addr = ppc_global_function_entry((void *)ftrace_regs_caller);
+#else
+	unsigned long addr = ppc_global_function_entry((void *)ftrace_caller);
+#endif
+	long reladdr = addr - kernel_toc_addr();
+
+	if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+		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;
+}
+#else
 int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
+#endif
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -695,7 +944,8 @@
  * 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.
  */
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
+						unsigned long sp)
 {
 	unsigned long return_hooker;
 
@@ -707,20 +957,13 @@
 
 	return_hooker = ppc_function_entry(return_to_handler);
 
-	if (!function_graph_enter(parent, ip, 0, NULL))
+	if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
 		parent = return_hooker;
 out:
 	return parent;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64)
-unsigned long __init arch_syscall_addr(int nr)
-{
-	return sys_call_table[nr*2];
-}
-#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */
-
 #ifdef PPC64_ELF_ABI_v1
 char *arch_ftrace_match_adjust(char *str, const char *search)
 {
diff --git a/arch/powerpc/kernel/trace/ftrace_32.S b/arch/powerpc/kernel/trace/ftrace_32.S
index 2c29098..e023ae5 100644
--- a/arch/powerpc/kernel/trace/ftrace_32.S
+++ b/arch/powerpc/kernel/trace/ftrace_32.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Split from entry_32.S
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/magic.h>
@@ -54,6 +50,7 @@
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 _GLOBAL(ftrace_graph_caller)
+	addi	r5, r1, 48
 	/* load r4 with local address */
 	lwz	r4, 44(r1)
 	subi	r4, r4, MCOUNT_INSN_SIZE
diff --git a/arch/powerpc/kernel/trace/ftrace_64.S b/arch/powerpc/kernel/trace/ftrace_64.S
index e25f77c..25e5b9e 100644
--- a/arch/powerpc/kernel/trace/ftrace_64.S
+++ b/arch/powerpc/kernel/trace/ftrace_64.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Split from entry_64.S
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/magic.h>
@@ -14,6 +10,18 @@
 #include <asm/ppc-opcode.h>
 #include <asm/export.h>
 
+.pushsection ".tramp.ftrace.text","aw",@progbits;
+.globl ftrace_tramp_text
+ftrace_tramp_text:
+	.space 64
+.popsection
+
+.pushsection ".tramp.ftrace.init","aw",@progbits;
+.globl ftrace_tramp_init
+ftrace_tramp_init:
+	.space 64
+.popsection
+
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
 EXPORT_SYMBOL(_mcount)
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 32476a6..f9fd5f7 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Split from ftrace_64.S
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/magic.h>
@@ -229,7 +225,7 @@
 	 *  - r0, r11 & r12 are free
 	 */
 livepatch_handler:
-	CURRENT_THREAD_INFO(r12, r1)
+	ld	r12, PACA_THREAD_INFO(r13)
 
 	/* Allocate 3 x 8 bytes */
 	ld	r11, TI_livepatch_sp(r12)
@@ -256,7 +252,7 @@
 	 * restore it.
 	 */
 
-	CURRENT_THREAD_INFO(r12, r1)
+	ld	r12, PACA_THREAD_INFO(r13)
 
 	ld	r11, TI_livepatch_sp(r12)
 
@@ -273,7 +269,7 @@
 	ld	r2,  -24(r11)
 
 	/* Pop livepatch stack frame */
-	CURRENT_THREAD_INFO(r12, r1)
+	ld	r12, PACA_THREAD_INFO(r13)
 	subi	r11, r11, 24
 	std	r11, TI_livepatch_sp(r12)
 
@@ -298,6 +294,7 @@
 	std	r2, 24(r1)
 	ld	r2, PACATOC(r13)	/* get kernel TOC in r2 */
 
+	addi	r5, r1, 112
 	mfctr	r4		/* ftrace_caller has moved local addr here */
 	std	r4, 40(r1)
 	mflr	r3		/* ftrace_caller has restored LR from stack */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.S b/arch/powerpc/kernel/trace/ftrace_64_pg.S
index 4c515c4..6708e24 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Split from ftrace_64.S
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/magic.h>
@@ -45,6 +41,7 @@
 
 #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
diff --git a/arch/powerpc/kernel/trace/trace_clock.c b/arch/powerpc/kernel/trace/trace_clock.c
index 4917069..b0143a3 100644
--- a/arch/powerpc/kernel/trace/trace_clock.c
+++ b/arch/powerpc/kernel/trace/trace_clock.c
@@ -1,7 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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.
  *
  * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
  */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 8689a02..82f4353 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 1995-1996  Gary Thomas (gdt@linuxppc.org)
  *  Copyright 2007-2010 Freescale Semiconductor, Inc.
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  *  Modified by Cort Dougan (cort@cs.nmt.edu)
  *  and Paul Mackerras (paulus@samba.org)
  */
@@ -71,6 +67,7 @@
 #include <sysdev/fsl_pci.h>
 #include <asm/kprobes.h>
 #include <asm/stacktrace.h>
+#include <asm/nmi.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -178,7 +175,7 @@
 	kmsg_dump(KMSG_DUMP_PANIC);
 	bust_spinlocks(0);
 	debug_locks_off();
-	console_flush_on_panic();
+	console_flush_on_panic(CONSOLE_FLUSH_PENDING);
 }
 
 static unsigned long oops_begin(struct pt_regs *regs)
@@ -247,8 +244,6 @@
 		mdelay(MSEC_PER_SEC);
 	}
 
-	if (in_interrupt())
-		panic("Fatal exception in interrupt");
 	if (panic_on_oops)
 		panic("Fatal exception");
 	do_exit(signr);
@@ -259,24 +254,17 @@
 {
 	printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
 
-	if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN))
-		printk("LE ");
-	else
-		printk("BE ");
-
-	if (IS_ENABLED(CONFIG_PREEMPT))
-		pr_cont("PREEMPT ");
-
-	if (IS_ENABLED(CONFIG_SMP))
-		pr_cont("SMP NR_CPUS=%d ", NR_CPUS);
-
-	if (debug_pagealloc_enabled())
-		pr_cont("DEBUG_PAGEALLOC ");
-
-	if (IS_ENABLED(CONFIG_NUMA))
-		pr_cont("NUMA ");
-
-	pr_cont("%s\n", ppc_md.name ? ppc_md.name : "");
+	printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s%s %s\n",
+	       IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
+	       PAGE_SIZE / 1024,
+	       early_radix_enabled() ? " MMU=Radix" : "",
+	       early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ? " MMU=Hash" : "",
+	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
+	       IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
+	       IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
+	       debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
+	       IS_ENABLED(CONFIG_NUMA) ? " NUMA" : "",
+	       ppc_md.name ? ppc_md.name : "");
 
 	if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP)
 		return 1;
@@ -307,12 +295,9 @@
 }
 NOKPROBE_SYMBOL(die);
 
-void user_single_step_siginfo(struct task_struct *tsk,
-				struct pt_regs *regs, siginfo_t *info)
+void user_single_step_report(struct pt_regs *regs)
 {
-	info->si_signo = SIGTRAP;
-	info->si_code = TRAP_TRACE;
-	info->si_addr = (void __user *)regs->nip;
+	force_sig_fault(SIGTRAP, TRAP_TRACE, (void __user *)regs->nip);
 }
 
 static void show_signal_msg(int signr, struct pt_regs *regs, int code,
@@ -341,14 +326,12 @@
 	show_user_instructions(regs);
 }
 
-void _exception_pkey(int signr, struct pt_regs *regs, int code,
-		     unsigned long addr, int key)
+static bool exception_common(int signr, struct pt_regs *regs, int code,
+			      unsigned long addr)
 {
-	siginfo_t info;
-
 	if (!user_mode(regs)) {
 		die("Exception in kernel mode", regs, signr);
-		return;
+		return false;
 	}
 
 	show_signal_msg(signr, regs, code, addr);
@@ -364,30 +347,120 @@
 	 */
 	thread_pkey_regs_save(&current->thread);
 
-	clear_siginfo(&info);
-	info.si_signo = signr;
-	info.si_code = code;
-	info.si_addr = (void __user *) addr;
-	info.si_pkey = key;
+	return true;
+}
 
-	force_sig_info(signr, &info, current);
+void _exception_pkey(struct pt_regs *regs, unsigned long addr, int key)
+{
+	if (!exception_common(SIGSEGV, regs, SEGV_PKUERR, addr))
+		return;
+
+	force_sig_pkuerr((void __user *) addr, key);
 }
 
 void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 {
-	_exception_pkey(signr, regs, code, addr, 0);
+	if (!exception_common(signr, regs, code, addr))
+		return;
+
+	force_sig_fault(signr, code, (void __user *)addr);
+}
+
+/*
+ * The interrupt architecture has a quirk in that the HV interrupts excluding
+ * the NMIs (0x100 and 0x200) do not clear MSR[RI] at entry. The first thing
+ * that an interrupt handler must do is save off a GPR into a scratch register,
+ * and all interrupts on POWERNV (HV=1) use the HSPRG1 register as scratch.
+ * Therefore an NMI can clobber an HV interrupt's live HSPRG1 without noticing
+ * that it is non-reentrant, which leads to random data corruption.
+ *
+ * The solution is for NMI interrupts in HV mode to check if they originated
+ * from these critical HV interrupt regions. If so, then mark them not
+ * recoverable.
+ *
+ * An alternative would be for HV NMIs to use SPRG for scratch to avoid the
+ * HSPRG1 clobber, however this would cause guest SPRG to be clobbered. Linux
+ * guests should always have MSR[RI]=0 when its scratch SPRG is in use, so
+ * that would work. However any other guest OS that may have the SPRG live
+ * and MSR[RI]=1 could encounter silent corruption.
+ *
+ * Builds that do not support KVM could take this second option to increase
+ * the recoverability of NMIs.
+ */
+void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_POWERNV
+	unsigned long kbase = (unsigned long)_stext;
+	unsigned long nip = regs->nip;
+
+	if (!(regs->msr & MSR_RI))
+		return;
+	if (!(regs->msr & MSR_HV))
+		return;
+	if (regs->msr & MSR_PR)
+		return;
+
+	/*
+	 * Now test if the interrupt has hit a range that may be using
+	 * HSPRG1 without having RI=0 (i.e., an HSRR interrupt). The
+	 * problem ranges all run un-relocated. Test real and virt modes
+	 * at the same time by droping the high bit of the nip (virt mode
+	 * entry points still have the +0x4000 offset).
+	 */
+	nip &= ~0xc000000000000000ULL;
+	if ((nip >= 0x500 && nip < 0x600) || (nip >= 0x4500 && nip < 0x4600))
+		goto nonrecoverable;
+	if ((nip >= 0x980 && nip < 0xa00) || (nip >= 0x4980 && nip < 0x4a00))
+		goto nonrecoverable;
+	if ((nip >= 0xe00 && nip < 0xec0) || (nip >= 0x4e00 && nip < 0x4ec0))
+		goto nonrecoverable;
+	if ((nip >= 0xf80 && nip < 0xfa0) || (nip >= 0x4f80 && nip < 0x4fa0))
+		goto nonrecoverable;
+
+	/* Trampoline code runs un-relocated so subtract kbase. */
+	if (nip >= (unsigned long)(start_real_trampolines - kbase) &&
+			nip < (unsigned long)(end_real_trampolines - kbase))
+		goto nonrecoverable;
+	if (nip >= (unsigned long)(start_virt_trampolines - kbase) &&
+			nip < (unsigned long)(end_virt_trampolines - kbase))
+		goto nonrecoverable;
+	return;
+
+nonrecoverable:
+	regs->msr &= ~MSR_RI;
+#endif
 }
 
 void system_reset_exception(struct pt_regs *regs)
 {
+	unsigned long hsrr0, hsrr1;
+	bool nested = in_nmi();
+	bool saved_hsrrs = false;
+
 	/*
 	 * Avoid crashes in case of nested NMI exceptions. Recoverability
 	 * is determined by RI and in_nmi
 	 */
-	bool nested = in_nmi();
 	if (!nested)
 		nmi_enter();
 
+	/*
+	 * System reset can interrupt code where HSRRs are live and MSR[RI]=1.
+	 * The system reset interrupt itself may clobber HSRRs (e.g., to call
+	 * OPAL), so save them here and restore them before returning.
+	 *
+	 * Machine checks don't need to save HSRRs, as the real mode handler
+	 * is careful to avoid them, and the regular handler is not delivered
+	 * as an NMI.
+	 */
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		hsrr0 = mfspr(SPRN_HSRR0);
+		hsrr1 = mfspr(SPRN_HSRR1);
+		saved_hsrrs = true;
+	}
+
+	hv_nmi_check_nonrecoverable(regs);
+
 	__this_cpu_inc(irq_stat.sreset_irqs);
 
 	/* See if any machine dependent calls */
@@ -399,6 +472,7 @@
 	if (debugger(regs))
 		goto out;
 
+	kmsg_dump(KMSG_DUMP_OOPS);
 	/*
 	 * A system reset is a request to dump, so we always send
 	 * it through the crashdump code (if fadump or kdump are
@@ -435,6 +509,11 @@
 	if (!(regs->msr & MSR_RI))
 		nmi_panic(regs, "Unrecoverable System Reset");
 
+	if (saved_hsrrs) {
+		mtspr(SPRN_HSRR0, hsrr0);
+		mtspr(SPRN_HSRR1, hsrr1);
+	}
+
 	if (!nested)
 		nmi_exit();
 
@@ -535,10 +614,10 @@
 	printk("Caused by (from MCSR=%lx): ", reason);
 
 	if (reason & MCSR_MCP)
-		printk("Machine Check Signal\n");
+		pr_cont("Machine Check Signal\n");
 
 	if (reason & MCSR_ICPERR) {
-		printk("Instruction Cache Parity Error\n");
+		pr_cont("Instruction Cache Parity Error\n");
 
 		/*
 		 * This is recoverable by invalidating the i-cache.
@@ -556,7 +635,7 @@
 	}
 
 	if (reason & MCSR_DCPERR_MC) {
-		printk("Data Cache Parity Error\n");
+		pr_cont("Data Cache Parity Error\n");
 
 		/*
 		 * In write shadow mode we auto-recover from the error, but it
@@ -575,38 +654,38 @@
 	}
 
 	if (reason & MCSR_L2MMU_MHIT) {
-		printk("Hit on multiple TLB entries\n");
+		pr_cont("Hit on multiple TLB entries\n");
 		recoverable = 0;
 	}
 
 	if (reason & MCSR_NMI)
-		printk("Non-maskable interrupt\n");
+		pr_cont("Non-maskable interrupt\n");
 
 	if (reason & MCSR_IF) {
-		printk("Instruction Fetch Error Report\n");
+		pr_cont("Instruction Fetch Error Report\n");
 		recoverable = 0;
 	}
 
 	if (reason & MCSR_LD) {
-		printk("Load Error Report\n");
+		pr_cont("Load Error Report\n");
 		recoverable = 0;
 	}
 
 	if (reason & MCSR_ST) {
-		printk("Store Error Report\n");
+		pr_cont("Store Error Report\n");
 		recoverable = 0;
 	}
 
 	if (reason & MCSR_LDG) {
-		printk("Guarded Load Error Report\n");
+		pr_cont("Guarded Load Error Report\n");
 		recoverable = 0;
 	}
 
 	if (reason & MCSR_TLBSYNC)
-		printk("Simultaneous tlbsync operations\n");
+		pr_cont("Simultaneous tlbsync operations\n");
 
 	if (reason & MCSR_BSL2_ERR) {
-		printk("Level 2 Cache Error\n");
+		pr_cont("Level 2 Cache Error\n");
 		recoverable = 0;
 	}
 
@@ -616,7 +695,7 @@
 		addr = mfspr(SPRN_MCAR);
 		addr |= (u64)mfspr(SPRN_MCARU) << 32;
 
-		printk("Machine Check %s Address: %#llx\n",
+		pr_cont("Machine Check %s Address: %#llx\n",
 		       reason & MCSR_MEA ? "Effective" : "Physical", addr);
 	}
 
@@ -640,29 +719,29 @@
 	printk("Caused by (from MCSR=%lx): ", reason);
 
 	if (reason & MCSR_MCP)
-		printk("Machine Check Signal\n");
+		pr_cont("Machine Check Signal\n");
 	if (reason & MCSR_ICPERR)
-		printk("Instruction Cache Parity Error\n");
+		pr_cont("Instruction Cache Parity Error\n");
 	if (reason & MCSR_DCP_PERR)
-		printk("Data Cache Push Parity Error\n");
+		pr_cont("Data Cache Push Parity Error\n");
 	if (reason & MCSR_DCPERR)
-		printk("Data Cache Parity Error\n");
+		pr_cont("Data Cache Parity Error\n");
 	if (reason & MCSR_BUS_IAERR)
-		printk("Bus - Instruction Address Error\n");
+		pr_cont("Bus - Instruction Address Error\n");
 	if (reason & MCSR_BUS_RAERR)
-		printk("Bus - Read Address Error\n");
+		pr_cont("Bus - Read Address Error\n");
 	if (reason & MCSR_BUS_WAERR)
-		printk("Bus - Write Address Error\n");
+		pr_cont("Bus - Write Address Error\n");
 	if (reason & MCSR_BUS_IBERR)
-		printk("Bus - Instruction Data Error\n");
+		pr_cont("Bus - Instruction Data Error\n");
 	if (reason & MCSR_BUS_RBERR)
-		printk("Bus - Read Data Bus Error\n");
+		pr_cont("Bus - Read Data Bus Error\n");
 	if (reason & MCSR_BUS_WBERR)
-		printk("Bus - Write Data Bus Error\n");
+		pr_cont("Bus - Write Data Bus Error\n");
 	if (reason & MCSR_BUS_IPERR)
-		printk("Bus - Instruction Parity Error\n");
+		pr_cont("Bus - Instruction Parity Error\n");
 	if (reason & MCSR_BUS_RPERR)
-		printk("Bus - Read Parity Error\n");
+		pr_cont("Bus - Read Parity Error\n");
 
 	return 0;
 }
@@ -680,19 +759,19 @@
 	printk("Caused by (from MCSR=%lx): ", reason);
 
 	if (reason & MCSR_MCP)
-		printk("Machine Check Signal\n");
+		pr_cont("Machine Check Signal\n");
 	if (reason & MCSR_CP_PERR)
-		printk("Cache Push Parity Error\n");
+		pr_cont("Cache Push Parity Error\n");
 	if (reason & MCSR_CPERR)
-		printk("Cache Parity Error\n");
+		pr_cont("Cache Parity Error\n");
 	if (reason & MCSR_EXCP_ERR)
-		printk("ISI, ITLB, or Bus Error on first instruction fetch for an exception handler\n");
+		pr_cont("ISI, ITLB, or Bus Error on first instruction fetch for an exception handler\n");
 	if (reason & MCSR_BUS_IRERR)
-		printk("Bus - Read Bus Error on instruction fetch\n");
+		pr_cont("Bus - Read Bus Error on instruction fetch\n");
 	if (reason & MCSR_BUS_DRERR)
-		printk("Bus - Read Bus Error on data load\n");
+		pr_cont("Bus - Read Bus Error on data load\n");
 	if (reason & MCSR_BUS_WRERR)
-		printk("Bus - Write Bus Error on buffered store or cache line push\n");
+		pr_cont("Bus - Write Bus Error on buffered store or cache line push\n");
 
 	return 0;
 }
@@ -705,30 +784,30 @@
 	printk("Caused by (from SRR1=%lx): ", reason);
 	switch (reason & 0x601F0000) {
 	case 0x80000:
-		printk("Machine check signal\n");
+		pr_cont("Machine check signal\n");
 		break;
 	case 0:		/* for 601 */
 	case 0x40000:
 	case 0x140000:	/* 7450 MSS error and TEA */
-		printk("Transfer error ack signal\n");
+		pr_cont("Transfer error ack signal\n");
 		break;
 	case 0x20000:
-		printk("Data parity error signal\n");
+		pr_cont("Data parity error signal\n");
 		break;
 	case 0x10000:
-		printk("Address parity error signal\n");
+		pr_cont("Address parity error signal\n");
 		break;
 	case 0x20000000:
-		printk("L1 Data Cache error\n");
+		pr_cont("L1 Data Cache error\n");
 		break;
 	case 0x40000000:
-		printk("L1 Instruction Cache error\n");
+		pr_cont("L1 Instruction Cache error\n");
 		break;
 	case 0x00100000:
-		printk("L2 data cache parity error\n");
+		pr_cont("L2 data cache parity error\n");
 		break;
 	default:
-		printk("Unknown values in msr\n");
+		pr_cont("Unknown values in msr\n");
 	}
 	return 0;
 }
@@ -741,9 +820,7 @@
 	if (!nested)
 		nmi_enter();
 
-	/* 64s accounts the mce in machine_check_early when in HVMODE */
-	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !cpu_has_feature(CPU_FTR_HVMODE))
-		__this_cpu_inc(irq_stat.mce_exceptions);
+	__this_cpu_inc(irq_stat.mce_exceptions);
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
@@ -767,15 +844,15 @@
 	if (check_io_access(regs))
 		goto bail;
 
-	/* Must die if the interrupt is not recoverable */
-	if (!(regs->msr & MSR_RI))
-		nmi_panic(regs, "Unrecoverable Machine check");
-
 	if (!nested)
 		nmi_exit();
 
 	die("Machine check", regs, SIGBUS);
 
+	/* Must die if the interrupt is not recoverable */
+	if (!(regs->msr & MSR_RI))
+		nmi_panic(regs, "Unrecoverable Machine check");
+
 	return;
 
 bail:
@@ -841,7 +918,7 @@
 	addr = (__force const void __user *)ea;
 
 	/* Check it */
-	if (!access_ok(VERIFY_READ, addr, 16)) {
+	if (!access_ok(addr, 16)) {
 		pr_devel("HMI vec emu: bad access %i:%s[%d] nip=%016lx"
 			 " instr=%08x addr=%016lx\n",
 			 smp_processor_id(), current->comm, current->pid,
@@ -1438,7 +1515,8 @@
 			goto bail;
 		} else {
 			printk(KERN_EMERG "Unexpected TM Bad Thing exception "
-			       "at %lx (msr 0x%x)\n", regs->nip, reason);
+			       "at %lx (msr 0x%lx) tm_scratch=%llx\n",
+			       regs->nip, regs->msr, get_paca()->tm_scratch);
 			die("Unrecoverable exception", regs, SIGABRT);
 		}
 	}
@@ -1545,21 +1623,13 @@
 
 void StackOverflow(struct pt_regs *regs)
 {
-	printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n",
-	       current, regs->gpr[1]);
+	pr_crit("Kernel stack overflow in process %s[%d], r1=%lx\n",
+		current->comm, task_pid_nr(current), regs->gpr[1]);
 	debugger(regs);
 	show_regs(regs);
 	panic("kernel stack overflow");
 }
 
-void nonrecoverable_exception(struct pt_regs *regs)
-{
-	printk(KERN_ERR "Non-recoverable exception at PC=%lx MSR=%lx\n",
-	       regs->nip, regs->msr);
-	debugger(regs);
-	die("nonrecoverable exception", regs, SIGKILL);
-}
-
 void kernel_fp_unavailable_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -1755,16 +1825,20 @@
          * checkpointed FP registers need to be loaded.
 	 */
 	tm_reclaim_current(TM_CAUSE_FAC_UNAV);
-	/* Reclaim didn't save out any FPRs to transact_fprs. */
+
+	/*
+	 * Reclaim initially saved out bogus (lazy) FPRs to ckfp_state, and
+	 * then it was overwrite by the thr->fp_state by tm_reclaim_thread().
+	 *
+	 * At this point, ck{fp,vr}_state contains the exact values we want to
+	 * recheckpoint.
+	 */
 
 	/* Enable FP for the task: */
 	current->thread.load_fp = 1;
 
-	/* This loads and recheckpoints the FP registers from
-	 * thread.fpr[].  They will remain in registers after the
-	 * checkpoint so we don't need to reload them after.
-	 * If VMX is in use, the VRs now hold checkpointed values,
-	 * so we don't want to load the VRs from the thread_struct.
+	/*
+	 * Recheckpoint all the checkpointed ckpt, ck{fp, vr}_state registers.
 	 */
 	tm_recheckpoint(&current->thread);
 }
@@ -2011,6 +2085,10 @@
 	int code = FPE_FLTUNK;
 	int err;
 
+	/* We restore the interrupt state now */
+	if (!arch_irq_disabled_regs(regs))
+		local_irq_enable();
+
 	flush_spe_to_thread(current);
 
 	spefscr = current->thread.spefscr;
@@ -2056,6 +2134,10 @@
 	extern int speround_handler(struct pt_regs *regs);
 	int err;
 
+	/* We restore the interrupt state now */
+	if (!arch_irq_disabled_regs(regs))
+		local_irq_enable();
+
 	preempt_disable();
 	if (regs->msr & MSR_SPE)
 		giveup_spe(current);
@@ -2091,8 +2173,8 @@
  */
 void unrecoverable_exception(struct pt_regs *regs)
 {
-	printk(KERN_EMERG "Unrecoverable exception %lx at %lx\n",
-	       regs->trap, regs->nip);
+	pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
+		 regs->trap, regs->nip, regs->msr);
 	die("Unrecoverable exception", regs, SIGABRT);
 }
 NOKPROBE_SYMBOL(unrecoverable_exception);
diff --git a/arch/powerpc/kernel/ucall.S b/arch/powerpc/kernel/ucall.S
new file mode 100644
index 0000000..07296bc
--- /dev/null
+++ b/arch/powerpc/kernel/ucall.S
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Generic code to perform an ultravisor call.
+ *
+ * Copyright 2019, IBM Corporation.
+ *
+ */
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+
+_GLOBAL(ucall_norets)
+EXPORT_SYMBOL_GPL(ucall_norets)
+	sc	2	/* Invoke the ultravisor */
+	blr		/* Return r3 = status */
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 7cc38b5..a384e7c 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * polling mode stateless debugging stuff, originally for NS16550 Serial Ports
  *
  * c 2001 PPC 64 Team, IBM Corp
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <stdarg.h>
@@ -74,7 +70,7 @@
 #endif
 
 #ifdef CONFIG_PPC_EARLY_DEBUG
-	console_loglevel = 10;
+	console_loglevel = CONSOLE_LOGLEVEL_DEBUG;
 
 	register_early_udbg_console();
 #endif
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 411116c..9356b60 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * udbg for NS16550 compatible serial ports
  *
  * Copyright (C) 2001-2005 PPC 64 Team, IBM Corp
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 #include <linux/types.h>
 #include <asm/udbg.h>
diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c
index 5d105b8..1cfef0e 100644
--- a/arch/powerpc/kernel/uprobes.c
+++ b/arch/powerpc/kernel/uprobes.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * User-space Probes (UProbes) for powerpc
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright IBM Corporation, 2007-2012
  *
  * Adapted from the x86 port by Ananth N Mavinakayanahalli <ananth@in.ibm.com>
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 65b3bdb..eae9dda 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 
 /*
  *    Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
  *			 <benh@kernel.crashing.org>
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/errno.h>
@@ -98,28 +94,6 @@
 		CPU_FTR_COHERENT_ICACHE, CPU_FTR_COHERENT_ICACHE,
 		"__kernel_sync_dicache", "__kernel_sync_dicache_p5"
 	},
-#ifdef CONFIG_PPC32
-	{
-		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
-		"__kernel_gettimeofday", NULL
-	},
-	{
-		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
-		"__kernel_clock_gettime", NULL
-	},
-	{
-		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
-		"__kernel_clock_getres", NULL
-	},
-	{
-		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
-		"__kernel_get_tbfreq", NULL
-	},
-	{
-		CPU_FTR_USE_RTC, CPU_FTR_USE_RTC,
-		"__kernel_time", NULL
-	},
-#endif
 };
 
 /*
@@ -671,15 +645,18 @@
 {
 	unsigned int i;
 	extern unsigned long *sys_call_table;
+#ifdef CONFIG_PPC64
+	extern unsigned long *compat_sys_call_table;
+#endif
 	extern unsigned long sys_ni_syscall;
 
 
 	for (i = 0; i < NR_syscalls; i++) {
 #ifdef CONFIG_PPC64
-		if (sys_call_table[i*2] != sys_ni_syscall)
+		if (sys_call_table[i] != sys_ni_syscall)
 			vdso_data->syscall_map_64[i >> 5] |=
 				0x80000000UL >> (i & 0x1f);
-		if (sys_call_table[i*2+1] != sys_ni_syscall)
+		if (compat_sys_call_table[i] != sys_ni_syscall)
 			vdso_data->syscall_map_32[i >> 5] |=
 				0x80000000UL >> (i & 0x1f);
 #else /* CONFIG_PPC64 */
@@ -795,7 +772,6 @@
 	BUG_ON(vdso32_pagelist == NULL);
 	for (i = 0; i < vdso32_pages; i++) {
 		struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
-		ClearPageReserved(pg);
 		get_page(pg);
 		vdso32_pagelist[i] = pg;
 	}
@@ -809,7 +785,6 @@
 	BUG_ON(vdso64_pagelist == NULL);
 	for (i = 0; i < vdso64_pages; i++) {
 		struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
-		ClearPageReserved(pg);
 		get_page(pg);
 		vdso64_pagelist[i] = pg;
 	}
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 50112d4..06f54d9 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -23,11 +23,11 @@
 obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
 
 GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
 UBSAN_SANITIZE := n
 
-ccflags-y := -shared -fno-common -fno-builtin
-ccflags-y += -nostdlib -Wl,-soname=linux-vdso32.so.1 \
-		$(call cc-ldoption, -Wl$(comma)--hash-style=both)
+ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
+	-Wl,-soname=linux-vdso32.so.1 -Wl,--hash-style=both
 asflags-y := -D__VDSO32__ -s
 
 obj-y += vdso32_wrapper.o
diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S
index 1ba6feb..7f882e7 100644
--- a/arch/powerpc/kernel/vdso32/cacheflush.S
+++ b/arch/powerpc/kernel/vdso32/cacheflush.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * vDSO provided cache flush routines
  *
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org),
  *                    IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S
index 3745113..6c7401b 100644
--- a/arch/powerpc/kernel/vdso32/datapage.S
+++ b/arch/powerpc/kernel/vdso32/datapage.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Access to the shared data page by the vDSO & syscall map
  *
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/processor.h>
@@ -37,6 +33,7 @@
 	mtlr	r0
 	addi	r3, r3, __kernel_datapage_offset-data_page_branch
 	lwz	r0,0(r3)
+  .cfi_restore lr
 	add	r3,r0,r3
 	blr
   .cfi_endproc
@@ -73,6 +70,7 @@
  *
  * returns the timebase frequency in HZ
  */
+#ifndef CONFIG_PPC_BOOK3S_601
 V_FUNCTION_BEGIN(__kernel_get_tbfreq)
   .cfi_startproc
 	mflr	r12
@@ -85,3 +83,4 @@
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_get_tbfreq)
+#endif
diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S
index c62be60..63e9145 100644
--- a/arch/powerpc/kernel/vdso32/getcpu.S
+++ b/arch/powerpc/kernel/vdso32/getcpu.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 769c262..becd9f8 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Userland implementation of gettimeofday() for 32 bits processes in a
  * ppc64 kernel for use in the vDSO
  *
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org,
  *                    IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
@@ -98,7 +94,7 @@
 	 * can be used, r7 contains NSEC_PER_SEC.
 	 */
 
-	lwz	r5,WTOM_CLOCK_SEC(r9)
+	lwz	r5,(WTOM_CLOCK_SEC+LOPART)(r9)
 	lwz	r6,WTOM_CLOCK_NSEC(r9)
 
 	/* We now have our offset in r5,r6. We create a fake dependency
@@ -139,6 +135,7 @@
 	 */
 99:
 	li	r0,__NR_clock_gettime
+  .cfi_restore lr
 	sc
 	blr
   .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso32/sigtramp.S b/arch/powerpc/kernel/vdso32/sigtramp.S
index cf0c9c9..0bcc5e5 100644
--- a/arch/powerpc/kernel/vdso32/sigtramp.S
+++ b/arch/powerpc/kernel/vdso32/sigtramp.S
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Signal trampolines for 32 bits processes in a ppc64 kernel for
  * use in the vDSO
  *
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
  * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 099a6db..00c025b 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -144,10 +144,13 @@
 		__kernel_datapage_offset;
 
 		__kernel_get_syscall_map;
+#ifndef CONFIG_PPC_BOOK3S_601
 		__kernel_gettimeofday;
 		__kernel_clock_gettime;
 		__kernel_clock_getres;
+		__kernel_time;
 		__kernel_get_tbfreq;
+#endif
 		__kernel_sync_dicache;
 		__kernel_sync_dicache_p5;
 		__kernel_sigtramp32;
@@ -155,7 +158,6 @@
 #ifdef CONFIG_PPC64
 		__kernel_getcpu;
 #endif
-		__kernel_time;
 
 	local: *;
 	};
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index 69cecb3..32ebb35 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -9,11 +9,11 @@
 obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
 
 GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
 UBSAN_SANITIZE := n
 
-ccflags-y := -shared -fno-common -fno-builtin
-ccflags-y += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
-		$(call cc-ldoption, -Wl$(comma)--hash-style=both)
+ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
+	-Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both
 asflags-y := -D__VDSO64__ -s
 
 obj-y += vdso64_wrapper.o
diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S
index 69c5af2..3f92561 100644
--- a/arch/powerpc/kernel/vdso64/cacheflush.S
+++ b/arch/powerpc/kernel/vdso64/cacheflush.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * vDSO provided cache flush routines
  *
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org),
  *                    IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S
index abf17fe..dc84f5a 100644
--- a/arch/powerpc/kernel/vdso64/datapage.S
+++ b/arch/powerpc/kernel/vdso64/datapage.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Access to the shared data page by the vDSO & syscall map
  *
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/processor.h>
@@ -37,6 +33,7 @@
 	mtlr	r0
 	addi	r3, r3, __kernel_datapage_offset-data_page_branch
 	lwz	r0,0(r3)
+  .cfi_restore lr
 	add	r3,r0,r3
 	blr
   .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso64/getcpu.S b/arch/powerpc/kernel/vdso64/getcpu.S
index 23eb9a9..12bbf23 100644
--- a/arch/powerpc/kernel/vdso64/getcpu.S
+++ b/arch/powerpc/kernel/vdso64/getcpu.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index c002adc..07bfe33 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Userland implementation of gettimeofday() for 64 bits processes in a
  * ppc64 kernel for use in the vDSO
  *
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org),
  *                    IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
@@ -92,7 +88,7 @@
 	 * At this point, r4,r5 contain our sec/nsec values.
 	 */
 
-	lwa	r6,WTOM_CLOCK_SEC(r3)
+	ld	r6,WTOM_CLOCK_SEC(r3)
 	lwa	r9,WTOM_CLOCK_NSEC(r3)
 
 	/* We now have our result in r6,r9. We create a fake dependency
@@ -125,7 +121,7 @@
 	bne     cr6,75f
 
 	/* CLOCK_MONOTONIC_COARSE */
-	lwa     r6,WTOM_CLOCK_SEC(r3)
+	ld	r6,WTOM_CLOCK_SEC(r3)
 	lwa     r9,WTOM_CLOCK_NSEC(r3)
 
 	/* check if counter has updated */
@@ -169,6 +165,7 @@
 	 */
 99:
 	li	r0,__NR_clock_gettime
+  .cfi_restore lr
 	sc
 	blr
   .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S
index 542c6f4..a8cc040 100644
--- a/arch/powerpc/kernel/vdso64/sigtramp.S
+++ b/arch/powerpc/kernel/vdso64/sigtramp.S
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Signal trampoline for 64 bits processes in a ppc64 kernel for
  * use in the vDSO
  *
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
  * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 21165da..8eb867d 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -21,6 +21,7 @@
 	REST_32VRS(0,r4,r3)
 	blr
 EXPORT_SYMBOL(load_vr_state)
+_ASM_NOKPROBE_SYMBOL(load_vr_state); /* used by restore_math */
 
 /*
  * Store VMX state into memory, including VSCR.
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 07ae018..060a1ac 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -4,16 +4,16 @@
 #else
 #define PROVIDE32(x)	PROVIDE(x)
 #endif
+
+#define BSS_FIRST_SECTIONS *(.bss.prominit)
+
 #include <asm/page.h>
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 
-#if defined(CONFIG_STRICT_KERNEL_RWX) && !defined(CONFIG_PPC32)
-#define STRICT_ALIGN_SIZE	(1 << 24)
-#else
-#define STRICT_ALIGN_SIZE	PAGE_SIZE
-#endif
+#define STRICT_ALIGN_SIZE	(1 << CONFIG_DATA_SHIFT)
+#define ETEXT_ALIGN_SIZE	(1 << CONFIG_ETEXT_SHIFT)
 
 ENTRY(_stext)
 
@@ -83,11 +83,11 @@
 
 #ifdef CONFIG_PPC64
 	/*
-	 * BLOCK(0) overrides the default output section alignment because
+	 * ALIGN(0) overrides the default output section alignment because
 	 * this needs to start right after .head.text in order for fixed
 	 * section placement to work.
 	 */
-	.text BLOCK(0) : AT(ADDR(.text) - LOAD_OFFSET) {
+	.text ALIGN(0) : AT(ADDR(.text) - LOAD_OFFSET) {
 #ifdef CONFIG_LD_HEAD_STUB_CATCH
 		KEEP(*(.linker_stub_catch));
 		. = . ;
@@ -99,6 +99,9 @@
 #endif
 		/* careful! __ftr_alt_* sections need to be close to .text */
 		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text);
+#ifdef CONFIG_PPC64
+		*(.tramp.ftrace.text);
+#endif
 		SCHED_TEXT
 		CPUIDLE_TEXT
 		LOCK_TEXT
@@ -125,7 +128,7 @@
 
 	} :kernel
 
-	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(ETEXT_ALIGN_SIZE);
 	_etext = .;
 	PROVIDE32 (etext = .);
 
@@ -164,6 +167,14 @@
 	}
 #endif /* CONFIG_PPC_BARRIER_NOSPEC */
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	. = ALIGN(8);
+	__spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) {
+		__start__btb_flush_fixup = .;
+		*(__btb_flush_fixup)
+		__stop__btb_flush_fixup = .;
+	}
+#endif
 	EXCEPTION_TABLE(0)
 
 	NOTES :kernel :notes
@@ -181,7 +192,15 @@
  */
 	. = ALIGN(STRICT_ALIGN_SIZE);
 	__init_begin = .;
-	INIT_TEXT_SECTION(PAGE_SIZE) :kernel
+	. = ALIGN(PAGE_SIZE);
+	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+		_sinittext = .;
+		INIT_TEXT
+		_einittext = .;
+#ifdef CONFIG_PPC64
+		*(.tramp.ftrace.init);
+#endif
+	} :kernel
 
 	/* .exit.text is discarded at runtime, not link time,
 	 * to deal with references from __bug_table
@@ -192,12 +211,6 @@
 
 	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
 		INIT_DATA
-		__vtop_table_begin = .;
-		KEEP(*(.vtop_fixup));
-		__vtop_table_end = .;
-		__ptov_table_begin = .;
-		KEEP(*(.ptov_fixup));
-		__ptov_table_end = .;
 	}
 
 	.init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
@@ -212,8 +225,6 @@
 		CON_INITCALL
 	}
 
-	SECURITY_INIT
-
 	. = ALIGN(8);
 	__ftr_fixup : AT(ADDR(__ftr_fixup) - LOAD_OFFSET) {
 		__start___ftr_fixup = .;
@@ -296,11 +307,16 @@
 #ifdef CONFIG_PPC32
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
 		DATA_DATA
+#ifdef CONFIG_UBSAN
+		*(.data..Lubsan_data*)
+		*(.data..Lubsan_type*)
+#endif
 		*(.data.rel*)
 		*(SDATA_MAIN)
 		*(.sdata2)
 		*(.got.plt) *(.got)
 		*(.plt)
+		*(.branch_lt)
 	}
 #else
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 3c6ab22..af3c15a 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -77,7 +77,7 @@
 
 static u64 wd_timer_period_ms __read_mostly;  /* interval between heartbeat */
 
-static DEFINE_PER_CPU(struct timer_list, wd_timer);
+static DEFINE_PER_CPU(struct hrtimer, wd_hrtimer);
 static DEFINE_PER_CPU(u64, wd_timer_tb);
 
 /* SMP checker bits */
@@ -293,21 +293,21 @@
 	nmi_exit();
 }
 
-static void wd_timer_reset(unsigned int cpu, struct timer_list *t)
-{
-	t->expires = jiffies + msecs_to_jiffies(wd_timer_period_ms);
-	if (wd_timer_period_ms > 1000)
-		t->expires = __round_jiffies_up(t->expires, cpu);
-	add_timer_on(t, cpu);
-}
-
-static void wd_timer_fn(struct timer_list *t)
+static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
 	int cpu = smp_processor_id();
 
+	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+		return HRTIMER_NORESTART;
+
+	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
+		return HRTIMER_NORESTART;
+
 	watchdog_timer_interrupt(cpu);
 
-	wd_timer_reset(cpu, t);
+	hrtimer_forward_now(hrtimer, ms_to_ktime(wd_timer_period_ms));
+
+	return HRTIMER_RESTART;
 }
 
 void arch_touch_nmi_watchdog(void)
@@ -323,37 +323,22 @@
 }
 EXPORT_SYMBOL(arch_touch_nmi_watchdog);
 
-static void start_watchdog_timer_on(unsigned int cpu)
+static void start_watchdog(void *arg)
 {
-	struct timer_list *t = per_cpu_ptr(&wd_timer, cpu);
-
-	per_cpu(wd_timer_tb, cpu) = get_tb();
-
-	timer_setup(t, wd_timer_fn, TIMER_PINNED);
-	wd_timer_reset(cpu, t);
-}
-
-static void stop_watchdog_timer_on(unsigned int cpu)
-{
-	struct timer_list *t = per_cpu_ptr(&wd_timer, cpu);
-
-	del_timer_sync(t);
-}
-
-static int start_wd_on_cpu(unsigned int cpu)
-{
+	struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer);
+	int cpu = smp_processor_id();
 	unsigned long flags;
 
 	if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) {
 		WARN_ON(1);
-		return 0;
+		return;
 	}
 
 	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
-		return 0;
+		return;
 
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
-		return 0;
+		return;
 
 	wd_smp_lock(&flags);
 	cpumask_set_cpu(cpu, &wd_cpus_enabled);
@@ -363,27 +348,40 @@
 	}
 	wd_smp_unlock(&flags);
 
-	start_watchdog_timer_on(cpu);
+	*this_cpu_ptr(&wd_timer_tb) = get_tb();
 
-	return 0;
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer->function = watchdog_timer_fn;
+	hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
-static int stop_wd_on_cpu(unsigned int cpu)
+static int start_watchdog_on_cpu(unsigned int cpu)
 {
+	return smp_call_function_single(cpu, start_watchdog, NULL, true);
+}
+
+static void stop_watchdog(void *arg)
+{
+	struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer);
+	int cpu = smp_processor_id();
 	unsigned long flags;
 
 	if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
-		return 0; /* Can happen in CPU unplug case */
+		return; /* Can happen in CPU unplug case */
 
-	stop_watchdog_timer_on(cpu);
+	hrtimer_cancel(hrtimer);
 
 	wd_smp_lock(&flags);
 	cpumask_clear_cpu(cpu, &wd_cpus_enabled);
 	wd_smp_unlock(&flags);
 
 	wd_smp_clear_cpu_pending(cpu, get_tb());
+}
 
-	return 0;
+static int stop_watchdog_on_cpu(unsigned int cpu)
+{
+	return smp_call_function_single(cpu, stop_watchdog, NULL, true);
 }
 
 static void watchdog_calc_timeouts(void)
@@ -402,7 +400,7 @@
 	int cpu;
 
 	for_each_cpu(cpu, &wd_cpus_enabled)
-		stop_wd_on_cpu(cpu);
+		stop_watchdog_on_cpu(cpu);
 }
 
 void watchdog_nmi_start(void)
@@ -411,7 +409,7 @@
 
 	watchdog_calc_timeouts();
 	for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask)
-		start_wd_on_cpu(cpu);
+		start_watchdog_on_cpu(cpu);
 }
 
 /*
@@ -423,7 +421,8 @@
 
 	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
 					"powerpc/watchdog:online",
-					start_wd_on_cpu, stop_wd_on_cpu);
+					start_watchdog_on_cpu,
+					stop_watchdog_on_cpu);
 	if (err < 0) {
 		pr_warn("could not be initialized");
 		return err;
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 68a0e9d..711fca9 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -20,7 +20,6 @@
 config KVM
 	bool
 	select PREEMPT_NOTIFIERS
-	select ANON_INODES
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select SRCU
@@ -39,6 +38,7 @@
 config KVM_BOOK3S_64_HANDLER
 	bool
 	select KVM_BOOK3S_HANDLER
+	select PPC_DAWR_FORCE_ENABLE
 
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
@@ -184,9 +184,9 @@
 	select HAVE_KVM_MSI
 	help
 	  Enable support for emulating MPIC devices inside the
-          host kernel, rather than relying on userspace to emulate.
-          Currently, support is limited to certain versions of
-          Freescale's MPIC implementation.
+	  host kernel, rather than relying on userspace to emulate.
+	  Currently, support is limited to certain versions of
+	  Freescale's MPIC implementation.
 
 config KVM_XICS
 	bool "KVM in-kernel XICS emulation"
@@ -204,6 +204,6 @@
 	default y
 	depends on KVM_XICS && PPC_XIVE_NATIVE && KVM_BOOK3S_HV_POSSIBLE
 
-source drivers/vhost/Kconfig
+source "drivers/vhost/Kconfig"
 
 endif # VIRTUALIZATION
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index f872c04..4c67cc7 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -3,8 +3,6 @@
 # Makefile for Kernel-based Virtual Machine module
 #
 
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
-
 ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm
 KVM := ../../../virt/kvm
 
@@ -12,11 +10,6 @@
 common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o
 common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o
 
-CFLAGS_e500_mmu.o := -I.
-CFLAGS_e500_mmu_host.o := -I.
-CFLAGS_emulate.o  := -I.
-CFLAGS_emulate_loadstore.o  := -I.
-
 common-objs-y += powerpc.o emulate_loadstore.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o
 obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o
@@ -75,7 +68,8 @@
 	book3s_hv.o \
 	book3s_hv_interrupts.o \
 	book3s_64_mmu_hv.o \
-	book3s_64_mmu_radix.o
+	book3s_64_mmu_radix.o \
+	book3s_hv_nested.o
 
 kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
 	book3s_hv_tm.o
@@ -100,7 +94,7 @@
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
 	book3s_xics.o
 
-kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o book3s_xive_native.o
 kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o
 
 kvm-book3s_64-module-objs := \
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 87348e4..ec2547c 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
  *
@@ -8,10 +9,6 @@
  * Description:
  * This file is derived from arch/powerpc/kvm/44x.c,
  * by Hollis Blanchard <hollisb@us.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kvm_host.h>
@@ -39,7 +36,8 @@
 #include "book3s.h"
 #include "trace.h"
 
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
+#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
 /* #define EXIT_DEBUG */
 
@@ -71,6 +69,8 @@
 	{ "pthru_all",       VCPU_STAT(pthru_all) },
 	{ "pthru_host",      VCPU_STAT(pthru_host) },
 	{ "pthru_bad_aff",   VCPU_STAT(pthru_bad_aff) },
+	{ "largepages_2M",    VM_STAT(num_2M_pages, .mode = 0444) },
+	{ "largepages_1G",    VM_STAT(num_1G_pages, .mode = 0444) },
 	{ NULL }
 };
 
@@ -78,8 +78,11 @@
 {
 	if (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) {
 		ulong pc = kvmppc_get_pc(vcpu);
+		ulong lr = kvmppc_get_lr(vcpu);
 		if ((pc & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS)
 			kvmppc_set_pc(vcpu, pc & ~SPLIT_HACK_MASK);
+		if ((lr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS)
+			kvmppc_set_lr(vcpu, lr & ~SPLIT_HACK_MASK);
 		vcpu->arch.hflags &= ~BOOK3S_HFLAG_SPLIT_HACK;
 	}
 }
@@ -150,7 +153,6 @@
 	case 0x400: prio = BOOK3S_IRQPRIO_INST_STORAGE;		break;
 	case 0x480: prio = BOOK3S_IRQPRIO_INST_SEGMENT;		break;
 	case 0x500: prio = BOOK3S_IRQPRIO_EXTERNAL;		break;
-	case 0x501: prio = BOOK3S_IRQPRIO_EXTERNAL_LEVEL;	break;
 	case 0x600: prio = BOOK3S_IRQPRIO_ALIGNMENT;		break;
 	case 0x700: prio = BOOK3S_IRQPRIO_PROGRAM;		break;
 	case 0x800: prio = BOOK3S_IRQPRIO_FP_UNAVAIL;		break;
@@ -190,6 +192,13 @@
 }
 EXPORT_SYMBOL_GPL(kvmppc_book3s_queue_irqprio);
 
+void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags)
+{
+	/* might as well deliver this straight away */
+	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_MACHINE_CHECK, flags);
+}
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_machine_check);
+
 void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
 {
 	/* might as well deliver this straight away */
@@ -236,18 +245,35 @@
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
 {
-	unsigned int vec = BOOK3S_INTERRUPT_EXTERNAL;
+	/*
+	 * This case (KVM_INTERRUPT_SET) should never actually arise for
+	 * a pseries guest (because pseries guests expect their interrupt
+	 * controllers to continue asserting an external interrupt request
+	 * until it is acknowledged at the interrupt controller), but is
+	 * included to avoid ABI breakage and potentially for other
+	 * sorts of guest.
+	 *
+	 * There is a subtlety here: HV KVM does not test the
+	 * external_oneshot flag in the code that synthesizes
+	 * external interrupts for the guest just before entering
+	 * the guest.  That is OK even if userspace did do a
+	 * KVM_INTERRUPT_SET on a pseries guest vcpu, because the
+	 * caller (kvm_vcpu_ioctl_interrupt) does a kvm_vcpu_kick()
+	 * which ends up doing a smp_send_reschedule(), which will
+	 * pull the guest all the way out to the host, meaning that
+	 * we will call kvmppc_core_prepare_to_enter() before entering
+	 * the guest again, and that will handle the external_oneshot
+	 * flag correctly.
+	 */
+	if (irq->irq == KVM_INTERRUPT_SET)
+		vcpu->arch.external_oneshot = 1;
 
-	if (irq->irq == KVM_INTERRUPT_SET_LEVEL)
-		vec = BOOK3S_INTERRUPT_EXTERNAL_LEVEL;
-
-	kvmppc_book3s_queue_irqprio(vcpu, vec);
+	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 }
 
 void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu)
 {
 	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
-	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
 }
 
 void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong dar,
@@ -278,7 +304,6 @@
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
-	case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
 		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
@@ -352,8 +377,16 @@
 		case BOOK3S_IRQPRIO_DECREMENTER:
 			/* DEC interrupts get cleared by mtdec */
 			return false;
-		case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
-			/* External interrupts get cleared by userspace */
+		case BOOK3S_IRQPRIO_EXTERNAL:
+			/*
+			 * External interrupts get cleared by userspace
+			 * except when set by the KVM_INTERRUPT ioctl with
+			 * KVM_INTERRUPT_SET (not KVM_INTERRUPT_SET_LEVEL).
+			 */
+			if (vcpu->arch.external_oneshot) {
+				vcpu->arch.external_oneshot = 0;
+				return true;
+			}
 			return false;
 	}
 
@@ -609,12 +642,24 @@
 				r = -ENXIO;
 				break;
 			}
-			if (xive_enabled())
+			if (xics_on_xive())
 				*val = get_reg_val(id, kvmppc_xive_get_icp(vcpu));
 			else
 				*val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
 			break;
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+		case KVM_REG_PPC_VP_STATE:
+			if (!vcpu->arch.xive_vcpu) {
+				r = -ENXIO;
+				break;
+			}
+			if (xive_enabled())
+				r = kvmppc_xive_native_get_vp(vcpu, val);
+			else
+				r = -ENXIO;
+			break;
+#endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
 			*val = get_reg_val(id, vcpu->arch.fscr);
 			break;
@@ -682,12 +727,24 @@
 				r = -ENXIO;
 				break;
 			}
-			if (xive_enabled())
+			if (xics_on_xive())
 				r = kvmppc_xive_set_icp(vcpu, set_reg_val(id, *val));
 			else
 				r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val));
 			break;
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+		case KVM_REG_PPC_VP_STATE:
+			if (!vcpu->arch.xive_vcpu) {
+				r = -ENXIO;
+				break;
+			}
+			if (xive_enabled())
+				r = kvmppc_xive_native_set_vp(vcpu, val);
+			else
+				r = -ENXIO;
+			break;
+#endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
 			vcpu->arch.fscr = set_reg_val(id, *val);
 			break;
@@ -804,9 +861,10 @@
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
-	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new);
+	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change);
 }
 
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
@@ -824,9 +882,10 @@
 	return kvm->arch.kvm_ops->test_age_hva(kvm, hva);
 }
 
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	kvm->arch.kvm_ops->set_spte_hva(kvm, hva, pte);
+	return 0;
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
@@ -840,6 +899,7 @@
 #ifdef CONFIG_PPC64
 	INIT_LIST_HEAD_RCU(&kvm->arch.spapr_tce_tables);
 	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
+	mutex_init(&kvm->arch.rtas_token_lock);
 #endif
 
 	return kvm->arch.kvm_ops->init_vm(kvm);
@@ -853,6 +913,17 @@
 	kvmppc_rtas_tokens_free(kvm);
 	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
 #endif
+
+#ifdef CONFIG_KVM_XICS
+	/*
+	 * Free the XIVE devices which are not directly freed by the
+	 * device 'release' method
+	 */
+	kfree(kvm->arch.xive_devices.native);
+	kvm->arch.xive_devices.native = NULL;
+	kfree(kvm->arch.xive_devices.xics_on_xive);
+	kvm->arch.xive_devices.xics_on_xive = NULL;
+#endif /* CONFIG_KVM_XICS */
 }
 
 int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu)
@@ -956,7 +1027,7 @@
 int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 		bool line_status)
 {
-	if (xive_enabled())
+	if (xics_on_xive())
 		return kvmppc_xive_set_irq(kvm, irq_source_id, irq, level,
 					   line_status);
 	else
@@ -1009,9 +1080,14 @@
 
 #ifdef CONFIG_KVM_XICS
 #ifdef CONFIG_KVM_XIVE
-	if (xive_enabled()) {
+	if (xics_on_xive()) {
 		kvmppc_xive_init_module();
 		kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
+		if (kvmppc_xive_native_supported()) {
+			kvmppc_xive_native_init_module();
+			kvm_register_device_ops(&kvm_xive_native_ops,
+						KVM_DEV_TYPE_XIVE);
+		}
 	} else
 #endif
 		kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
@@ -1022,8 +1098,10 @@
 static void kvmppc_book3s_exit(void)
 {
 #ifdef CONFIG_KVM_XICS
-	if (xive_enabled())
+	if (xics_on_xive()) {
 		kvmppc_xive_exit_module();
+		kvmppc_xive_native_exit_module();
+	}
 #endif
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kvmppc_book3s_exit_pr();
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index 14ef035..2ef1311 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -1,12 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright IBM Corporation, 2013
  * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License or (at your optional) any later version of the license.
- *
  */
 
 #ifndef __POWERPC_KVM_BOOK3S_H__
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 6121699..18f244a 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
@@ -250,6 +239,7 @@
 				case 2:
 				case 6:
 					pte->may_write = true;
+					/* fall through */
 				case 3:
 				case 5:
 				case 7:
@@ -425,6 +415,7 @@
 	mmu->slbmte = NULL;
 	mmu->slbmfee = NULL;
 	mmu->slbmfev = NULL;
+	mmu->slbfee = NULL;
 	mmu->slbie = NULL;
 	mmu->slbia = NULL;
 }
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 9991069..d4cb3bc 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
  *
  * Authors:
  *     Alexander Graf <agraf@suse.de>
- *
- * 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.
  */
 
 #include <linux/kvm_host.h>
diff --git a/arch/powerpc/kvm/book3s_32_sr.S b/arch/powerpc/kvm/book3s_32_sr.S
index 7e06a6f..e3ab9df 100644
--- a/arch/powerpc/kvm/book3s_32_sr.S
+++ b/arch/powerpc/kvm/book3s_32_sr.S
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index c92dd25..5f63a5f 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
@@ -435,6 +424,19 @@
 	kvmppc_mmu_map_segment(vcpu, esid << SID_SHIFT);
 }
 
+static int kvmppc_mmu_book3s_64_slbfee(struct kvm_vcpu *vcpu, gva_t eaddr,
+				       ulong *ret_slb)
+{
+	struct kvmppc_slb *slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu, eaddr);
+
+	if (slbe) {
+		*ret_slb = slbe->origv;
+		return 0;
+	}
+	*ret_slb = 0;
+	return -ENOENT;
+}
+
 static u64 kvmppc_mmu_book3s_64_slbmfee(struct kvm_vcpu *vcpu, u64 slb_nr)
 {
 	struct kvmppc_slb *slbe;
@@ -670,6 +672,7 @@
 	mmu->slbmte = kvmppc_mmu_book3s_64_slbmte;
 	mmu->slbmfee = kvmppc_mmu_book3s_64_slbmfee;
 	mmu->slbmfev = kvmppc_mmu_book3s_64_slbmfev;
+	mmu->slbfee = kvmppc_mmu_book3s_64_slbfee;
 	mmu->slbie = kvmppc_mmu_book3s_64_slbie;
 	mmu->slbia = kvmppc_mmu_book3s_64_slbia;
 	mmu->xlate = kvmppc_mmu_book3s_64_xlate;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 9a4614c..044dd49 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2009 SUSE Linux Products GmbH. All rights reserved.
  *
  * Authors:
  *     Alexander Graf <agraf@suse.de>
  *     Kevin Wolf <mail@kevin-wolf.de>
- *
- * 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.
  */
 
 #include <linux/kvm_host.h>
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 68e14af..9a75f0e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  */
@@ -63,7 +52,7 @@
 	struct work_struct work;
 	u32 order;
 
-	/* These fields protected by kvm->lock */
+	/* These fields protected by kvm->arch.mmu_setup_lock */
 
 	/* Possible values and their usage:
 	 *  <0     an error occurred during allocation,
@@ -73,7 +62,7 @@
 	int error;
 
 	/* Private to the work thread, until error != -EBUSY,
-	 * then protected by kvm->lock.
+	 * then protected by kvm->arch.mmu_setup_lock.
 	 */
 	struct kvm_hpt_info hpt;
 };
@@ -139,7 +128,7 @@
 	long err = -EBUSY;
 	struct kvm_hpt_info info;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	if (kvm->arch.mmu_ready) {
 		kvm->arch.mmu_ready = 0;
 		/* order mmu_ready vs. vcpus_running */
@@ -183,7 +172,7 @@
 		/* Ensure that each vcpu will flush its TLB on next entry. */
 		cpumask_setall(&kvm->arch.need_tlb_flush);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return err;
 }
 
@@ -268,14 +257,13 @@
 {
 	unsigned long host_lpid, rsvd_lpid;
 
-	if (!cpu_has_feature(CPU_FTR_HVMODE))
-		return -EINVAL;
-
 	if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE))
 		return -EINVAL;
 
 	/* POWER7 has 10-bit LPIDs (12-bit in POWER8) */
-	host_lpid = mfspr(SPRN_LPID);
+	host_lpid = 0;
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		host_lpid = mfspr(SPRN_LPID);
 	rsvd_lpid = LPID_RSVD;
 
 	kvmppc_init_lpid(rsvd_lpid + 1);
@@ -443,6 +431,24 @@
 	u32 last_inst;
 
 	/*
+	 * Fast path - check if the guest physical address corresponds to a
+	 * device on the FAST_MMIO_BUS, if so we can avoid loading the
+	 * instruction all together, then we can just handle it and return.
+	 */
+	if (is_store) {
+		int idx, ret;
+
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		ret = kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, (gpa_t) gpa, 0,
+				       NULL);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		if (!ret) {
+			kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4);
+			return RESUME_GUEST;
+		}
+	}
+
+	/*
 	 * If we fail, we just return to the guest and try executing it again.
 	 */
 	if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) !=
@@ -583,7 +589,7 @@
 	/* If writing != 0, then the HPTE must allow writing, if we get here */
 	write_ok = writing;
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	npages = get_user_pages_fast(hva, 1, writing, pages);
+	npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages);
 	if (npages < 1) {
 		/* Check if it's an I/O mapping */
 		down_read(&current->mm->mmap_sem);
@@ -744,12 +750,15 @@
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, slots) {
+		/* Mutual exclusion with kvm_unmap_hva_range etc. */
+		spin_lock(&kvm->mmu_lock);
 		/*
 		 * This assumes it is acceptable to lose reference and
 		 * change bits across a reset.
 		 */
 		memset(memslot->arch.rmap, 0,
 		       memslot->npages * sizeof(*memslot->arch.rmap));
+		spin_unlock(&kvm->mmu_lock);
 	}
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 }
@@ -897,11 +906,12 @@
 
 	gfn = memslot->base_gfn;
 	rmapp = memslot->arch.rmap;
+	if (kvm_is_radix(kvm)) {
+		kvmppc_radix_flush_memslot(kvm, memslot);
+		return;
+	}
+
 	for (n = memslot->npages; n; --n, ++gfn) {
-		if (kvm_is_radix(kvm)) {
-			kvm_unmap_radix(kvm, memslot, gfn);
-			continue;
-		}
 		/*
 		 * Testing the present bit without locking is OK because
 		 * the memslot has been marked invalid already, and hence
@@ -1172,7 +1182,7 @@
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
 		goto err;
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	npages = get_user_pages_fast(hva, 1, 1, pages);
+	npages = get_user_pages_fast(hva, 1, FOLL_WRITE, pages);
 	if (npages < 1)
 		goto err;
 	page = pages[0];
@@ -1426,7 +1436,7 @@
 
 static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize)
 {
-	if (WARN_ON(!mutex_is_locked(&kvm->lock)))
+	if (WARN_ON(!mutex_is_locked(&kvm->arch.mmu_setup_lock)))
 		return;
 
 	if (!resize)
@@ -1453,14 +1463,14 @@
 	if (WARN_ON(resize->error != -EBUSY))
 		return;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 
 	/* Request is still current? */
 	if (kvm->arch.resize_hpt == resize) {
 		/* We may request large allocations here:
-		 * do not sleep with kvm->lock held for a while.
+		 * do not sleep with kvm->arch.mmu_setup_lock held for a while.
 		 */
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.mmu_setup_lock);
 
 		resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
 				 resize->order);
@@ -1473,9 +1483,9 @@
 		if (WARN_ON(err == -EBUSY))
 			err = -EINPROGRESS;
 
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.mmu_setup_lock);
 		/* It is possible that kvm->arch.resize_hpt != resize
-		 * after we grab kvm->lock again.
+		 * after we grab kvm->arch.mmu_setup_lock again.
 		 */
 	}
 
@@ -1484,7 +1494,7 @@
 	if (kvm->arch.resize_hpt != resize)
 		resize_hpt_release(kvm, resize);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 }
 
 long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
@@ -1501,7 +1511,7 @@
 	if (shift && ((shift < 18) || (shift > 46)))
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 
 	resize = kvm->arch.resize_hpt;
 
@@ -1544,7 +1554,7 @@
 	ret = 100; /* estimated time in ms */
 
 out:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return ret;
 }
 
@@ -1567,7 +1577,7 @@
 	if (shift && ((shift < 18) || (shift > 46)))
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 
 	resize = kvm->arch.resize_hpt;
 
@@ -1604,7 +1614,7 @@
 	smp_mb();
 out_no_hpt:
 	resize_hpt_release(kvm, resize);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return ret;
 }
 
@@ -1741,7 +1751,7 @@
 	int first_pass;
 	unsigned long hpte[2];
 
-	if (!access_ok(VERIFY_WRITE, buf, count))
+	if (!access_ok(buf, count))
 		return -EFAULT;
 	if (kvm_is_radix(kvm))
 		return 0;
@@ -1841,13 +1851,13 @@
 	int mmu_ready;
 	int pshift;
 
-	if (!access_ok(VERIFY_READ, buf, count))
+	if (!access_ok(buf, count))
 		return -EFAULT;
 	if (kvm_is_radix(kvm))
 		return -EINVAL;
 
 	/* lock out vcpus from running while we're doing this */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	mmu_ready = kvm->arch.mmu_ready;
 	if (mmu_ready) {
 		kvm->arch.mmu_ready = 0;	/* temporarily */
@@ -1855,7 +1865,7 @@
 		smp_mb();
 		if (atomic_read(&kvm->arch.vcpus_running)) {
 			kvm->arch.mmu_ready = 1;
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->arch.mmu_setup_lock);
 			return -EBUSY;
 		}
 	}
@@ -1942,7 +1952,7 @@
 	/* Order HPTE updates vs. mmu_ready */
 	smp_wmb();
 	kvm->arch.mmu_ready = mmu_ready;
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 
 	if (err)
 		return err;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 998f8d0..2d415c3 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -1,7 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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.
  *
  * Copyright 2016 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  */
@@ -10,6 +8,9 @@
 #include <linux/string.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/debugfs.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -26,18 +27,231 @@
  */
 static int p9_supported_radix_bits[4] = { 5, 9, 9, 13 };
 
+unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
+					      gva_t eaddr, void *to, void *from,
+					      unsigned long n)
+{
+	int uninitialized_var(old_pid), old_lpid;
+	unsigned long quadrant, ret = n;
+	bool is_load = !!to;
+
+	/* 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,
+					  __pa(to), __pa(from), n);
+
+	quadrant = 1;
+	if (!pid)
+		quadrant = 2;
+	if (is_load)
+		from = (void *) (eaddr | (quadrant << 62));
+	else
+		to = (void *) (eaddr | (quadrant << 62));
+
+	preempt_disable();
+
+	/* switch the lpid first to avoid running host with unallocated pid */
+	old_lpid = mfspr(SPRN_LPID);
+	if (old_lpid != lpid)
+		mtspr(SPRN_LPID, lpid);
+	if (quadrant == 1) {
+		old_pid = mfspr(SPRN_PID);
+		if (old_pid != pid)
+			mtspr(SPRN_PID, pid);
+	}
+	isync();
+
+	pagefault_disable();
+	if (is_load)
+		ret = raw_copy_from_user(to, from, n);
+	else
+		ret = raw_copy_to_user(to, from, n);
+	pagefault_enable();
+
+	/* switch the pid first to avoid running host with unallocated pid */
+	if (quadrant == 1 && pid != old_pid)
+		mtspr(SPRN_PID, old_pid);
+	if (lpid != old_lpid)
+		mtspr(SPRN_LPID, old_lpid);
+	isync();
+
+	preempt_enable();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__kvmhv_copy_tofrom_guest_radix);
+
+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;
+
+	/* This would cause a data segment intr so don't allow the access */
+	if (eaddr & (0x3FFUL << 52))
+		return -EINVAL;
+
+	/* Should we be using the nested lpid */
+	if (vcpu->arch.nested)
+		lpid = vcpu->arch.nested->shadow_lpid;
+
+	/* If accessing quadrant 3 then pid is expected to be 0 */
+	if (((eaddr >> 62) & 0x3) == 0x3)
+		pid = 0;
+
+	eaddr &= ~(0xFFFUL << 52);
+
+	return __kvmhv_copy_tofrom_guest_radix(lpid, pid, eaddr, to, from, n);
+}
+
+long kvmhv_copy_from_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *to,
+				 unsigned long n)
+{
+	long ret;
+
+	ret = kvmhv_copy_tofrom_guest_radix(vcpu, eaddr, to, NULL, n);
+	if (ret > 0)
+		memset(to + (n - ret), 0, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvmhv_copy_from_guest_radix);
+
+long kvmhv_copy_to_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *from,
+			       unsigned long n)
+{
+	return kvmhv_copy_tofrom_guest_radix(vcpu, eaddr, NULL, from, n);
+}
+EXPORT_SYMBOL_GPL(kvmhv_copy_to_guest_radix);
+
+int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
+			       struct kvmppc_pte *gpte, u64 root,
+			       u64 *pte_ret_p)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int ret, level, ps;
+	unsigned long rts, bits, offset, index;
+	u64 pte, base, gpa;
+	__be64 rpte;
+
+	rts = ((root & RTS1_MASK) >> (RTS1_SHIFT - 3)) |
+		((root & RTS2_MASK) >> RTS2_SHIFT);
+	bits = root & RPDS_MASK;
+	base = root & RPDB_MASK;
+
+	offset = rts + 31;
+
+	/* Current implementations only support 52-bit space */
+	if (offset != 52)
+		return -EINVAL;
+
+	/* Walk each level of the radix tree */
+	for (level = 3; level >= 0; --level) {
+		u64 addr;
+		/* Check a valid size */
+		if (level && bits != p9_supported_radix_bits[level])
+			return -EINVAL;
+		if (level == 0 && !(bits == 5 || bits == 9))
+			return -EINVAL;
+		offset -= bits;
+		index = (eaddr >> offset) & ((1UL << bits) - 1);
+		/* Check that low bits of page table base are zero */
+		if (base & ((1UL << (bits + 3)) - 1))
+			return -EINVAL;
+		/* Read the entry from guest memory */
+		addr = base + (index * sizeof(rpte));
+		ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte));
+		if (ret) {
+			if (pte_ret_p)
+				*pte_ret_p = addr;
+			return ret;
+		}
+		pte = __be64_to_cpu(rpte);
+		if (!(pte & _PAGE_PRESENT))
+			return -ENOENT;
+		/* Check if a leaf entry */
+		if (pte & _PAGE_PTE)
+			break;
+		/* Get ready to walk the next level */
+		base = pte & RPDB_MASK;
+		bits = pte & RPDS_MASK;
+	}
+
+	/* Need a leaf at lowest level; 512GB pages not supported */
+	if (level < 0 || level == 3)
+		return -EINVAL;
+
+	/* We found a valid leaf PTE */
+	/* Offset is now log base 2 of the page size */
+	gpa = pte & 0x01fffffffffff000ul;
+	if (gpa & ((1ul << offset) - 1))
+		return -EINVAL;
+	gpa |= eaddr & ((1ul << offset) - 1);
+	for (ps = MMU_PAGE_4K; ps < MMU_PAGE_COUNT; ++ps)
+		if (offset == mmu_psize_defs[ps].shift)
+			break;
+	gpte->page_size = ps;
+	gpte->page_shift = offset;
+
+	gpte->eaddr = eaddr;
+	gpte->raddr = gpa;
+
+	/* Work out permissions */
+	gpte->may_read = !!(pte & _PAGE_READ);
+	gpte->may_write = !!(pte & _PAGE_WRITE);
+	gpte->may_execute = !!(pte & _PAGE_EXEC);
+
+	gpte->rc = pte & (_PAGE_ACCESSED | _PAGE_DIRTY);
+
+	if (pte_ret_p)
+		*pte_ret_p = pte;
+
+	return 0;
+}
+
+/*
+ * Used to walk a partition or process table radix tree in guest memory
+ * Note: We exploit the fact that a partition table and a process
+ * table have the same layout, a partition-scoped page table and a
+ * process-scoped page table have the same layout, and the 2nd
+ * doubleword of a partition table entry has the same layout as
+ * the PTCR register.
+ */
+int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
+				     struct kvmppc_pte *gpte, u64 table,
+				     int table_index, u64 *pte_ret_p)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int ret;
+	unsigned long size, ptbl, root;
+	struct prtb_entry entry;
+
+	if ((table & PRTS_MASK) > 24)
+		return -EINVAL;
+	size = 1ul << ((table & PRTS_MASK) + 12);
+
+	/* Is the table big enough to contain this entry? */
+	if ((table_index * sizeof(entry)) >= size)
+		return -EINVAL;
+
+	/* Read the table to find the root of the radix tree */
+	ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry));
+	ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry));
+	if (ret)
+		return ret;
+
+	/* Root is stored in the first double word */
+	root = be64_to_cpu(entry.prtb0);
+
+	return kvmppc_mmu_walk_radix_tree(vcpu, eaddr, gpte, root, pte_ret_p);
+}
+
 int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 			   struct kvmppc_pte *gpte, bool data, bool iswrite)
 {
-	struct kvm *kvm = vcpu->kvm;
 	u32 pid;
-	int ret, level, ps;
-	__be64 prte, rpte;
-	unsigned long ptbl;
-	unsigned long root, pte, index;
-	unsigned long rts, bits, offset;
-	unsigned long gpa;
-	unsigned long proc_tbl_size;
+	u64 pte;
+	int ret;
 
 	/* Work out effective PID */
 	switch (eaddr >> 62) {
@@ -50,71 +264,13 @@
 	default:
 		return -EINVAL;
 	}
-	proc_tbl_size = 1 << ((kvm->arch.process_table & PRTS_MASK) + 12);
-	if (pid * 16 >= proc_tbl_size)
-		return -EINVAL;
 
-	/* Read partition table to find root of tree for effective PID */
-	ptbl = (kvm->arch.process_table & PRTB_MASK) + (pid * 16);
-	ret = kvm_read_guest(kvm, ptbl, &prte, sizeof(prte));
+	ret = kvmppc_mmu_radix_translate_table(vcpu, eaddr, gpte,
+				vcpu->kvm->arch.process_table, pid, &pte);
 	if (ret)
 		return ret;
 
-	root = be64_to_cpu(prte);
-	rts = ((root & RTS1_MASK) >> (RTS1_SHIFT - 3)) |
-		((root & RTS2_MASK) >> RTS2_SHIFT);
-	bits = root & RPDS_MASK;
-	root = root & RPDB_MASK;
-
-	offset = rts + 31;
-
-	/* current implementations only support 52-bit space */
-	if (offset != 52)
-		return -EINVAL;
-
-	for (level = 3; level >= 0; --level) {
-		if (level && bits != p9_supported_radix_bits[level])
-			return -EINVAL;
-		if (level == 0 && !(bits == 5 || bits == 9))
-			return -EINVAL;
-		offset -= bits;
-		index = (eaddr >> offset) & ((1UL << bits) - 1);
-		/* check that low bits of page table base are zero */
-		if (root & ((1UL << (bits + 3)) - 1))
-			return -EINVAL;
-		ret = kvm_read_guest(kvm, root + index * 8,
-				     &rpte, sizeof(rpte));
-		if (ret)
-			return ret;
-		pte = __be64_to_cpu(rpte);
-		if (!(pte & _PAGE_PRESENT))
-			return -ENOENT;
-		if (pte & _PAGE_PTE)
-			break;
-		bits = pte & 0x1f;
-		root = pte & 0x0fffffffffffff00ul;
-	}
-	/* need a leaf at lowest level; 512GB pages not supported */
-	if (level < 0 || level == 3)
-		return -EINVAL;
-
-	/* offset is now log base 2 of the page size */
-	gpa = pte & 0x01fffffffffff000ul;
-	if (gpa & ((1ul << offset) - 1))
-		return -EINVAL;
-	gpa += eaddr & ((1ul << offset) - 1);
-	for (ps = MMU_PAGE_4K; ps < MMU_PAGE_COUNT; ++ps)
-		if (offset == mmu_psize_defs[ps].shift)
-			break;
-	gpte->page_size = ps;
-
-	gpte->eaddr = eaddr;
-	gpte->raddr = gpa;
-
-	/* Work out permissions */
-	gpte->may_read = !!(pte & _PAGE_READ);
-	gpte->may_write = !!(pte & _PAGE_WRITE);
-	gpte->may_execute = !!(pte & _PAGE_EXEC);
+	/* Check privilege (applies only to process scoped translations) */
 	if (kvmppc_get_msr(vcpu) & MSR_PR) {
 		if (pte & _PAGE_PRIVILEGED) {
 			gpte->may_read = 0;
@@ -136,21 +292,47 @@
 	return 0;
 }
 
-static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
-				    unsigned int pshift)
+void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
+			     unsigned int pshift, unsigned int lpid)
 {
 	unsigned long psize = PAGE_SIZE;
+	int psi;
+	long rc;
+	unsigned long rb;
 
 	if (pshift)
 		psize = 1UL << pshift;
+	else
+		pshift = PAGE_SHIFT;
 
 	addr &= ~(psize - 1);
-	radix__flush_tlb_lpid_page(kvm->arch.lpid, addr, psize);
+
+	if (!kvmhv_on_pseries()) {
+		radix__flush_tlb_lpid_page(lpid, addr, psize);
+		return;
+	}
+
+	psi = shift_to_mmu_psize(pshift);
+	rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58));
+	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1),
+				lpid, rb);
+	if (rc)
+		pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc);
 }
 
-static void kvmppc_radix_flush_pwc(struct kvm *kvm)
+static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
 {
-	radix__flush_pwc_lpid(kvm->arch.lpid);
+	long rc;
+
+	if (!kvmhv_on_pseries()) {
+		radix__flush_pwc_lpid(lpid);
+		return;
+	}
+
+	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1),
+				lpid, TLBIEL_INVAL_SET_LPID);
+	if (rc)
+		pr_err("KVM: TLB PWC invalidation hcall failed, rc=%ld\n", rc);
 }
 
 static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
@@ -179,12 +361,6 @@
 	kmem_cache_free(kvm_pte_cache, ptep);
 }
 
-/* Like pmd_huge() and pmd_large(), but works regardless of config options */
-static inline int pmd_is_leaf(pmd_t pmd)
-{
-	return !!(pmd_val(pmd) & _PAGE_PTE);
-}
-
 static pmd_t *kvmppc_pmd_alloc(void)
 {
 	return kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL);
@@ -195,23 +371,44 @@
 	kmem_cache_free(kvm_pmd_cache, pmdp);
 }
 
-static void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
-			     unsigned long gpa, unsigned int shift)
+/* Called with kvm->mmu_lock held */
+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)
 
 {
-	unsigned long page_size = 1ul << shift;
 	unsigned long old;
+	unsigned long gfn = gpa >> PAGE_SHIFT;
+	unsigned long page_size = PAGE_SIZE;
+	unsigned long hpa;
 
 	old = kvmppc_radix_update_pte(kvm, pte, ~0UL, 0, gpa, shift);
-	kvmppc_radix_tlbie_page(kvm, gpa, shift);
-	if (old & _PAGE_DIRTY) {
-		unsigned long gfn = gpa >> PAGE_SHIFT;
-		struct kvm_memory_slot *memslot;
+	kvmppc_radix_tlbie_page(kvm, gpa, shift, lpid);
 
+	/* The following only applies to L1 entries */
+	if (lpid != kvm->arch.lpid)
+		return;
+
+	if (!memslot) {
 		memslot = gfn_to_memslot(kvm, gfn);
-		if (memslot && memslot->dirty_bitmap)
-			kvmppc_update_dirty_map(memslot, gfn, page_size);
+		if (!memslot)
+			return;
 	}
+	if (shift) { /* 1GB or 2MB page */
+		page_size = 1ul << shift;
+		if (shift == PMD_SHIFT)
+			kvm->stat.num_2M_pages--;
+		else if (shift == PUD_SHIFT)
+			kvm->stat.num_1G_pages--;
+	}
+
+	gpa &= ~(page_size - 1);
+	hpa = old & PTE_RPN_MASK;
+	kvmhv_remove_nest_rmap_range(kvm, memslot, gpa, hpa, page_size);
+
+	if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap)
+		kvmppc_update_dirty_map(memslot, gfn, page_size);
 }
 
 /*
@@ -224,7 +421,8 @@
  * and emit a warning if encountered, but there may already be data
  * corruption due to the unexpected mappings.
  */
-static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full)
+static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
+				  unsigned int lpid)
 {
 	if (full) {
 		memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE);
@@ -238,14 +436,15 @@
 			WARN_ON_ONCE(1);
 			kvmppc_unmap_pte(kvm, p,
 					 pte_pfn(*p) << PAGE_SHIFT,
-					 PAGE_SHIFT);
+					 PAGE_SHIFT, NULL, lpid);
 		}
 	}
 
 	kvmppc_pte_free(pte);
 }
 
-static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full)
+static void kvmppc_unmap_free_pmd(struct kvm *kvm, pmd_t *pmd, bool full,
+				  unsigned int lpid)
 {
 	unsigned long im;
 	pmd_t *p = pmd;
@@ -260,20 +459,21 @@
 				WARN_ON_ONCE(1);
 				kvmppc_unmap_pte(kvm, (pte_t *)p,
 					 pte_pfn(*(pte_t *)p) << PAGE_SHIFT,
-					 PMD_SHIFT);
+					 PMD_SHIFT, NULL, lpid);
 			}
 		} else {
 			pte_t *pte;
 
 			pte = pte_offset_map(p, 0);
-			kvmppc_unmap_free_pte(kvm, pte, full);
+			kvmppc_unmap_free_pte(kvm, pte, full, lpid);
 			pmd_clear(p);
 		}
 	}
 	kvmppc_pmd_free(pmd);
 }
 
-static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud)
+static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
+				  unsigned int lpid)
 {
 	unsigned long iu;
 	pud_t *p = pud;
@@ -281,42 +481,46 @@
 	for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++p) {
 		if (!pud_present(*p))
 			continue;
-		if (pud_huge(*p)) {
+		if (pud_is_leaf(*p)) {
 			pud_clear(p);
 		} else {
 			pmd_t *pmd;
 
 			pmd = pmd_offset(p, 0);
-			kvmppc_unmap_free_pmd(kvm, pmd, true);
+			kvmppc_unmap_free_pmd(kvm, pmd, true, lpid);
 			pud_clear(p);
 		}
 	}
 	pud_free(kvm->mm, pud);
 }
 
-void kvmppc_free_radix(struct kvm *kvm)
+void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, unsigned int lpid)
 {
 	unsigned long ig;
-	pgd_t *pgd;
 
-	if (!kvm->arch.pgtable)
-		return;
-	pgd = kvm->arch.pgtable;
 	for (ig = 0; ig < PTRS_PER_PGD; ++ig, ++pgd) {
 		pud_t *pud;
 
 		if (!pgd_present(*pgd))
 			continue;
 		pud = pud_offset(pgd, 0);
-		kvmppc_unmap_free_pud(kvm, pud);
+		kvmppc_unmap_free_pud(kvm, pud, lpid);
 		pgd_clear(pgd);
 	}
-	pgd_free(kvm->mm, kvm->arch.pgtable);
-	kvm->arch.pgtable = NULL;
+}
+
+void kvmppc_free_radix(struct kvm *kvm)
+{
+	if (kvm->arch.pgtable) {
+		kvmppc_free_pgtable_radix(kvm, kvm->arch.pgtable,
+					  kvm->arch.lpid);
+		pgd_free(kvm->mm, kvm->arch.pgtable);
+		kvm->arch.pgtable = NULL;
+	}
 }
 
 static void kvmppc_unmap_free_pmd_entry_table(struct kvm *kvm, pmd_t *pmd,
-					      unsigned long gpa)
+					unsigned long gpa, unsigned int lpid)
 {
 	pte_t *pte = pte_offset_kernel(pmd, 0);
 
@@ -326,13 +530,13 @@
 	 * flushing the PWC again.
 	 */
 	pmd_clear(pmd);
-	kvmppc_radix_flush_pwc(kvm);
+	kvmppc_radix_flush_pwc(kvm, lpid);
 
-	kvmppc_unmap_free_pte(kvm, pte, false);
+	kvmppc_unmap_free_pte(kvm, pte, false, lpid);
 }
 
 static void kvmppc_unmap_free_pud_entry_table(struct kvm *kvm, pud_t *pud,
-					unsigned long gpa)
+					unsigned long gpa, unsigned int lpid)
 {
 	pmd_t *pmd = pmd_offset(pud, 0);
 
@@ -342,9 +546,9 @@
 	 * so can be freed without flushing the PWC again.
 	 */
 	pud_clear(pud);
-	kvmppc_radix_flush_pwc(kvm);
+	kvmppc_radix_flush_pwc(kvm, lpid);
 
-	kvmppc_unmap_free_pmd(kvm, pmd, false);
+	kvmppc_unmap_free_pmd(kvm, pmd, false, lpid);
 }
 
 /*
@@ -356,8 +560,10 @@
  */
 #define PTE_BITS_MUST_MATCH (~(_PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED))
 
-static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
-			     unsigned int level, unsigned long mmu_seq)
+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 *rmapp, struct rmap_nested **n_rmap)
 {
 	pgd_t *pgd;
 	pud_t *pud, *new_pud = NULL;
@@ -366,7 +572,7 @@
 	int ret;
 
 	/* Traverse the guest's 2nd-level tree, allocate new levels needed */
-	pgd = kvm->arch.pgtable + pgd_index(gpa);
+	pgd = pgtable + pgd_index(gpa);
 	pud = NULL;
 	if (pgd_present(*pgd))
 		pud = pud_offset(pgd, gpa);
@@ -374,7 +580,7 @@
 		new_pud = pud_alloc_one(kvm->mm, gpa);
 
 	pmd = NULL;
-	if (pud && pud_present(*pud) && !pud_huge(*pud))
+	if (pud && pud_present(*pud) && !pud_is_leaf(*pud))
 		pmd = pmd_offset(pud, gpa);
 	else if (level <= 1)
 		new_pmd = kvmppc_pmd_alloc();
@@ -397,7 +603,7 @@
 		new_pud = NULL;
 	}
 	pud = pud_offset(pgd, gpa);
-	if (pud_huge(*pud)) {
+	if (pud_is_leaf(*pud)) {
 		unsigned long hgpa = gpa & PUD_MASK;
 
 		/* Check if we raced and someone else has set the same thing */
@@ -423,7 +629,8 @@
 			goto out_unlock;
 		}
 		/* Valid 1GB page here already, remove it */
-		kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT);
+		kvmppc_unmap_pte(kvm, (pte_t *)pud, hgpa, PUD_SHIFT, NULL,
+				 lpid);
 	}
 	if (level == 2) {
 		if (!pud_none(*pud)) {
@@ -432,9 +639,11 @@
 			 * install a large page, so remove and free the page
 			 * table page.
 			 */
-			kvmppc_unmap_free_pud_entry_table(kvm, pud, gpa);
+			kvmppc_unmap_free_pud_entry_table(kvm, pud, gpa, lpid);
 		}
 		kvmppc_radix_set_pte_at(kvm, gpa, (pte_t *)pud, pte);
+		if (rmapp && n_rmap)
+			kvmhv_insert_nest_rmap(kvm, rmapp, n_rmap);
 		ret = 0;
 		goto out_unlock;
 	}
@@ -458,7 +667,7 @@
 			WARN_ON_ONCE((pmd_val(*pmd) ^ pte_val(pte)) &
 							PTE_BITS_MUST_MATCH);
 			kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
-					      0, pte_val(pte), lgpa, PMD_SHIFT);
+					0, pte_val(pte), lgpa, PMD_SHIFT);
 			ret = 0;
 			goto out_unlock;
 		}
@@ -472,7 +681,8 @@
 			goto out_unlock;
 		}
 		/* Valid 2MB page here already, remove it */
-		kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT);
+		kvmppc_unmap_pte(kvm, pmdp_ptep(pmd), lgpa, PMD_SHIFT, NULL,
+				 lpid);
 	}
 	if (level == 1) {
 		if (!pmd_none(*pmd)) {
@@ -481,9 +691,11 @@
 			 * install a large page, so remove and free the page
 			 * table page.
 			 */
-			kvmppc_unmap_free_pmd_entry_table(kvm, pmd, gpa);
+			kvmppc_unmap_free_pmd_entry_table(kvm, pmd, gpa, lpid);
 		}
 		kvmppc_radix_set_pte_at(kvm, gpa, pmdp_ptep(pmd), pte);
+		if (rmapp && n_rmap)
+			kvmhv_insert_nest_rmap(kvm, rmapp, n_rmap);
 		ret = 0;
 		goto out_unlock;
 	}
@@ -508,6 +720,8 @@
 		goto out_unlock;
 	}
 	kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
+	if (rmapp && n_rmap)
+		kvmhv_insert_nest_rmap(kvm, rmapp, n_rmap);
 	ret = 0;
 
  out_unlock:
@@ -521,95 +735,50 @@
 	return ret;
 }
 
-int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
-				   unsigned long ea, unsigned long dsisr)
+bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable, bool writing,
+			     unsigned long gpa, unsigned int lpid)
+{
+	unsigned long pgflags;
+	unsigned int shift;
+	pte_t *ptep;
+
+	/*
+	 * Need to set an R or C bit in the 2nd-level tables;
+	 * since we are just helping out the hardware here,
+	 * it is sufficient to do what the hardware does.
+	 */
+	pgflags = _PAGE_ACCESSED;
+	if (writing)
+		pgflags |= _PAGE_DIRTY;
+	/*
+	 * We are walking the secondary (partition-scoped) page table here.
+	 * We can do this without disabling irq because the Linux MM
+	 * subsystem doesn't do THP splits and collapses on this tree.
+	 */
+	ptep = __find_linux_pte(pgtable, gpa, NULL, &shift);
+	if (ptep && pte_present(*ptep) && (!writing || pte_write(*ptep))) {
+		kvmppc_radix_update_pte(kvm, ptep, 0, pgflags, gpa, shift);
+		return true;
+	}
+	return false;
+}
+
+int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
+				   unsigned long gpa,
+				   struct kvm_memory_slot *memslot,
+				   bool writing, bool kvm_ro,
+				   pte_t *inserted_pte, unsigned int *levelp)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long mmu_seq;
-	unsigned long gpa, gfn, hva;
-	struct kvm_memory_slot *memslot;
 	struct page *page = NULL;
-	long ret;
-	bool writing;
+	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 long pgflags;
 	unsigned int shift, level;
-
-	/* Check for unusual errors */
-	if (dsisr & DSISR_UNSUPP_MMU) {
-		pr_err("KVM: Got unsupported MMU fault\n");
-		return -EFAULT;
-	}
-	if (dsisr & DSISR_BADACCESS) {
-		/* Reflect to the guest as DSI */
-		pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
-		kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
-		return RESUME_GUEST;
-	}
-
-	/* Translate the logical address and get the page */
-	gpa = vcpu->arch.fault_gpa & ~0xfffUL;
-	gpa &= ~0xF000000000000000ul;
-	gfn = gpa >> PAGE_SHIFT;
-	if (!(dsisr & DSISR_PRTABLE_FAULT))
-		gpa |= ea & 0xfff;
-	memslot = gfn_to_memslot(kvm, gfn);
-
-	/* No memslot means it's an emulated MMIO region */
-	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
-		if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
-			     DSISR_SET_RC)) {
-			/*
-			 * Bad address in guest page table tree, or other
-			 * unusual error - reflect it to the guest as DSI.
-			 */
-			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
-			return RESUME_GUEST;
-		}
-		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
-					      dsisr & DSISR_ISSTORE);
-	}
-
-	writing = (dsisr & DSISR_ISSTORE) != 0;
-	if (memslot->flags & KVM_MEM_READONLY) {
-		if (writing) {
-			/* give the guest a DSI */
-			dsisr = DSISR_ISSTORE | DSISR_PROTFAULT;
-			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
-			return RESUME_GUEST;
-		}
-		upgrade_p = NULL;
-	}
-
-	if (dsisr & DSISR_SET_RC) {
-		/*
-		 * Need to set an R or C bit in the 2nd-level tables;
-		 * since we are just helping out the hardware here,
-		 * it is sufficient to do what the hardware does.
-		 */
-		pgflags = _PAGE_ACCESSED;
-		if (writing)
-			pgflags |= _PAGE_DIRTY;
-		/*
-		 * We are walking the secondary page table here. We can do this
-		 * without disabling irq.
-		 */
-		spin_lock(&kvm->mmu_lock);
-		ptep = __find_linux_pte(kvm->arch.pgtable,
-					gpa, NULL, &shift);
-		if (ptep && pte_present(*ptep) &&
-		    (!writing || pte_write(*ptep))) {
-			kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
-						gpa, shift);
-			dsisr &= ~DSISR_SET_RC;
-		}
-		spin_unlock(&kvm->mmu_lock);
-		if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
-			       DSISR_PROTFAULT | DSISR_SET_RC)))
-			return RESUME_GUEST;
-	}
+	int ret;
+	bool large_enable;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_notifier_seq;
@@ -622,7 +791,7 @@
 	 * is that the page is writable.
 	 */
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
+	if (!kvm_ro && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
 		upgrade_write = true;
 	} else {
 		unsigned long pfn;
@@ -659,12 +828,15 @@
 	pte = *ptep;
 	local_irq_enable();
 
+	/* If we're logging dirty pages, always map single pages */
+	large_enable = !(memslot->flags & KVM_MEM_LOG_DIRTY_PAGES);
+
 	/* Get pte level from shift/size */
-	if (shift == PUD_SHIFT &&
+	if (large_enable && shift == PUD_SHIFT &&
 	    (gpa & (PUD_SIZE - PAGE_SIZE)) ==
 	    (hva & (PUD_SIZE - PAGE_SIZE))) {
 		level = 2;
-	} else if (shift == PMD_SHIFT &&
+	} else if (large_enable && shift == PMD_SHIFT &&
 		   (gpa & (PMD_SIZE - PAGE_SIZE)) ==
 		   (hva & (PMD_SIZE - PAGE_SIZE))) {
 		level = 1;
@@ -690,7 +862,12 @@
 	}
 
 	/* Allocate space in the tree and write the PTE */
-	ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
+	ret = kvmppc_create_pte(kvm, kvm->arch.pgtable, pte, gpa, level,
+				mmu_seq, kvm->arch.lpid, NULL, NULL);
+	if (inserted_pte)
+		*inserted_pte = pte;
+	if (levelp)
+		*levelp = level;
 
 	if (page) {
 		if (!ret && (pte_val(pte) & _PAGE_WRITE))
@@ -698,36 +875,111 @@
 		put_page(page);
 	}
 
+	/* Increment number of large pages if we (successfully) inserted one */
+	if (!ret) {
+		if (level == 1)
+			kvm->stat.num_2M_pages++;
+		else if (level == 2)
+			kvm->stat.num_1G_pages++;
+	}
+
+	return ret;
+}
+
+int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				   unsigned long ea, unsigned long dsisr)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long gpa, gfn;
+	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) {
+		pr_err("KVM: Got unsupported MMU fault\n");
+		return -EFAULT;
+	}
+	if (dsisr & DSISR_BADACCESS) {
+		/* Reflect to the guest as DSI */
+		pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr);
+		kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+		return RESUME_GUEST;
+	}
+
+	/* Translate the logical address */
+	gpa = vcpu->arch.fault_gpa & ~0xfffUL;
+	gpa &= ~0xF000000000000000ul;
+	gfn = gpa >> PAGE_SHIFT;
+	if (!(dsisr & DSISR_PRTABLE_FAULT))
+		gpa |= ea & 0xfff;
+
+	/* Get the corresponding memslot */
+	memslot = gfn_to_memslot(kvm, gfn);
+
+	/* No memslot means it's an emulated MMIO region */
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
+		if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
+			     DSISR_SET_RC)) {
+			/*
+			 * Bad address in guest page table tree, or other
+			 * unusual error - reflect it to the guest as DSI.
+			 */
+			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+			return RESUME_GUEST;
+		}
+		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea, writing);
+	}
+
+	if (memslot->flags & KVM_MEM_READONLY) {
+		if (writing) {
+			/* give the guest a DSI */
+			kvmppc_core_queue_data_storage(vcpu, ea, DSISR_ISSTORE |
+						       DSISR_PROTFAULT);
+			return RESUME_GUEST;
+		}
+		kvm_ro = true;
+	}
+
+	/* Failed to set the reference/change bits */
+	if (dsisr & DSISR_SET_RC) {
+		spin_lock(&kvm->mmu_lock);
+		if (kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable,
+					    writing, gpa, kvm->arch.lpid))
+			dsisr &= ~DSISR_SET_RC;
+		spin_unlock(&kvm->mmu_lock);
+
+		if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
+			       DSISR_PROTFAULT | DSISR_SET_RC)))
+			return RESUME_GUEST;
+	}
+
+	/* Try to insert a pte */
+	ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot, writing,
+					     kvm_ro, NULL, NULL);
+
 	if (ret == 0 || ret == -EAGAIN)
 		ret = RESUME_GUEST;
 	return ret;
 }
 
-/* Called with kvm->lock held */
+/* Called with kvm->mmu_lock held */
 int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		    unsigned long gfn)
 {
 	pte_t *ptep;
 	unsigned long gpa = gfn << PAGE_SHIFT;
 	unsigned int shift;
-	unsigned long old;
 
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
-	if (ptep && pte_present(*ptep)) {
-		old = kvmppc_radix_update_pte(kvm, ptep, ~0UL, 0,
-					      gpa, shift);
-		kvmppc_radix_tlbie_page(kvm, gpa, shift);
-		if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) {
-			unsigned long psize = PAGE_SIZE;
-			if (shift)
-				psize = 1ul << shift;
-			kvmppc_update_dirty_map(memslot, gfn, psize);
-		}
-	}
+	if (ptep && pte_present(*ptep))
+		kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
+				 kvm->arch.lpid);
 	return 0;				
 }
 
-/* Called with kvm->lock held */
+/* Called with kvm->mmu_lock held */
 int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		  unsigned long gfn)
 {
@@ -735,18 +987,24 @@
 	unsigned long gpa = gfn << PAGE_SHIFT;
 	unsigned int shift;
 	int ref = 0;
+	unsigned long old, *rmapp;
 
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_young(*ptep)) {
-		kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
-					gpa, shift);
+		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
+					      gpa, shift);
 		/* XXX need to flush tlb here? */
+		/* Also clear bit in ptes in shadow pgtable for nested guests */
+		rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
+		kvmhv_update_nest_rmap_rc_list(kvm, rmapp, _PAGE_ACCESSED, 0,
+					       old & PTE_RPN_MASK,
+					       1UL << shift);
 		ref = 1;
 	}
 	return ref;
 }
 
-/* Called with kvm->lock held */
+/* Called with kvm->mmu_lock held */
 int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		       unsigned long gfn)
 {
@@ -770,15 +1028,23 @@
 	pte_t *ptep;
 	unsigned int shift;
 	int ret = 0;
+	unsigned long old, *rmapp;
 
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) {
 		ret = 1;
 		if (shift)
 			ret = 1 << (shift - PAGE_SHIFT);
-		kvmppc_radix_update_pte(kvm, ptep, _PAGE_DIRTY, 0,
-					gpa, shift);
-		kvmppc_radix_tlbie_page(kvm, gpa, shift);
+		spin_lock(&kvm->mmu_lock);
+		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_DIRTY, 0,
+					      gpa, shift);
+		kvmppc_radix_tlbie_page(kvm, gpa, shift, kvm->arch.lpid);
+		/* Also clear bit in ptes in shadow pgtable for nested guests */
+		rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
+		kvmhv_update_nest_rmap_rc_list(kvm, rmapp, _PAGE_DIRTY, 0,
+					       old & PTE_RPN_MASK,
+					       1UL << shift);
+		spin_unlock(&kvm->mmu_lock);
 	}
 	return ret;
 }
@@ -808,6 +1074,26 @@
 	return 0;
 }
 
+void kvmppc_radix_flush_memslot(struct kvm *kvm,
+				const struct kvm_memory_slot *memslot)
+{
+	unsigned long n;
+	pte_t *ptep;
+	unsigned long gpa;
+	unsigned int shift;
+
+	gpa = memslot->base_gfn << PAGE_SHIFT;
+	spin_lock(&kvm->mmu_lock);
+	for (n = memslot->npages; n; --n) {
+		ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
+		if (ptep && pte_present(*ptep))
+			kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
+					 kvm->arch.lpid);
+		gpa += PAGE_SIZE;
+	}
+	spin_unlock(&kvm->mmu_lock);
+}
+
 static void add_rmmu_ap_encoding(struct kvm_ppc_rmmu_info *info,
 				 int psize, int *indexp)
 {
@@ -863,6 +1149,215 @@
 	memset(addr, 0, RADIX_PMD_TABLE_SIZE);
 }
 
+struct debugfs_radix_state {
+	struct kvm	*kvm;
+	struct mutex	mutex;
+	unsigned long	gpa;
+	int		lpid;
+	int		chars_left;
+	int		buf_index;
+	char		buf[128];
+	u8		hdr;
+};
+
+static int debugfs_radix_open(struct inode *inode, struct file *file)
+{
+	struct kvm *kvm = inode->i_private;
+	struct debugfs_radix_state *p;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	kvm_get_kvm(kvm);
+	p->kvm = kvm;
+	mutex_init(&p->mutex);
+	file->private_data = p;
+
+	return nonseekable_open(inode, file);
+}
+
+static int debugfs_radix_release(struct inode *inode, struct file *file)
+{
+	struct debugfs_radix_state *p = file->private_data;
+
+	kvm_put_kvm(p->kvm);
+	kfree(p);
+	return 0;
+}
+
+static ssize_t debugfs_radix_read(struct file *file, char __user *buf,
+				 size_t len, loff_t *ppos)
+{
+	struct debugfs_radix_state *p = file->private_data;
+	ssize_t ret, r;
+	unsigned long n;
+	struct kvm *kvm;
+	unsigned long gpa;
+	pgd_t *pgt;
+	struct kvm_nested_guest *nested;
+	pgd_t pgd, *pgdp;
+	pud_t pud, *pudp;
+	pmd_t pmd, *pmdp;
+	pte_t *ptep;
+	int shift;
+	unsigned long pte;
+
+	kvm = p->kvm;
+	if (!kvm_is_radix(kvm))
+		return 0;
+
+	ret = mutex_lock_interruptible(&p->mutex);
+	if (ret)
+		return ret;
+
+	if (p->chars_left) {
+		n = p->chars_left;
+		if (n > len)
+			n = len;
+		r = copy_to_user(buf, p->buf + p->buf_index, n);
+		n -= r;
+		p->chars_left -= n;
+		p->buf_index += n;
+		buf += n;
+		len -= n;
+		ret = n;
+		if (r) {
+			if (!n)
+				ret = -EFAULT;
+			goto out;
+		}
+	}
+
+	gpa = p->gpa;
+	nested = NULL;
+	pgt = NULL;
+	while (len != 0 && p->lpid >= 0) {
+		if (gpa >= RADIX_PGTABLE_RANGE) {
+			gpa = 0;
+			pgt = NULL;
+			if (nested) {
+				kvmhv_put_nested(nested);
+				nested = NULL;
+			}
+			p->lpid = kvmhv_nested_next_lpid(kvm, p->lpid);
+			p->hdr = 0;
+			if (p->lpid < 0)
+				break;
+		}
+		if (!pgt) {
+			if (p->lpid == 0) {
+				pgt = kvm->arch.pgtable;
+			} else {
+				nested = kvmhv_get_nested(kvm, p->lpid, false);
+				if (!nested) {
+					gpa = RADIX_PGTABLE_RANGE;
+					continue;
+				}
+				pgt = nested->shadow_pgtable;
+			}
+		}
+		n = 0;
+		if (!p->hdr) {
+			if (p->lpid > 0)
+				n = scnprintf(p->buf, sizeof(p->buf),
+					      "\nNested LPID %d: ", p->lpid);
+			n += scnprintf(p->buf + n, sizeof(p->buf) - n,
+				      "pgdir: %lx\n", (unsigned long)pgt);
+			p->hdr = 1;
+			goto copy;
+		}
+
+		pgdp = pgt + pgd_index(gpa);
+		pgd = READ_ONCE(*pgdp);
+		if (!(pgd_val(pgd) & _PAGE_PRESENT)) {
+			gpa = (gpa & PGDIR_MASK) + PGDIR_SIZE;
+			continue;
+		}
+
+		pudp = pud_offset(&pgd, gpa);
+		pud = READ_ONCE(*pudp);
+		if (!(pud_val(pud) & _PAGE_PRESENT)) {
+			gpa = (gpa & PUD_MASK) + PUD_SIZE;
+			continue;
+		}
+		if (pud_val(pud) & _PAGE_PTE) {
+			pte = pud_val(pud);
+			shift = PUD_SHIFT;
+			goto leaf;
+		}
+
+		pmdp = pmd_offset(&pud, gpa);
+		pmd = READ_ONCE(*pmdp);
+		if (!(pmd_val(pmd) & _PAGE_PRESENT)) {
+			gpa = (gpa & PMD_MASK) + PMD_SIZE;
+			continue;
+		}
+		if (pmd_val(pmd) & _PAGE_PTE) {
+			pte = pmd_val(pmd);
+			shift = PMD_SHIFT;
+			goto leaf;
+		}
+
+		ptep = pte_offset_kernel(&pmd, gpa);
+		pte = pte_val(READ_ONCE(*ptep));
+		if (!(pte & _PAGE_PRESENT)) {
+			gpa += PAGE_SIZE;
+			continue;
+		}
+		shift = PAGE_SHIFT;
+	leaf:
+		n = scnprintf(p->buf, sizeof(p->buf),
+			      " %lx: %lx %d\n", gpa, pte, shift);
+		gpa += 1ul << shift;
+	copy:
+		p->chars_left = n;
+		if (n > len)
+			n = len;
+		r = copy_to_user(buf, p->buf, n);
+		n -= r;
+		p->chars_left -= n;
+		p->buf_index = n;
+		buf += n;
+		len -= n;
+		ret += n;
+		if (r) {
+			if (!ret)
+				ret = -EFAULT;
+			break;
+		}
+	}
+	p->gpa = gpa;
+	if (nested)
+		kvmhv_put_nested(nested);
+
+ out:
+	mutex_unlock(&p->mutex);
+	return ret;
+}
+
+static ssize_t debugfs_radix_write(struct file *file, const char __user *buf,
+			   size_t len, loff_t *ppos)
+{
+	return -EACCES;
+}
+
+static const struct file_operations debugfs_radix_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = debugfs_radix_open,
+	.release = debugfs_radix_release,
+	.read	 = debugfs_radix_read,
+	.write	 = debugfs_radix_write,
+	.llseek	 = generic_file_llseek,
+};
+
+void kvmhv_radix_debugfs_init(struct kvm *kvm)
+{
+	kvm->arch.radix_dentry = debugfs_create_file("radix", 0400,
+						     kvm->arch.debugfs_dir, kvm,
+						     &debugfs_radix_fops);
+}
+
 int kvmppc_radix_init(void)
 {
 	unsigned long size = sizeof(void *) << RADIX_PTE_INDEX_SIZE;
diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index 066c665..4d958dd 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 9a3f264..5834db0 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
@@ -30,6 +19,7 @@
 #include <linux/anon_inodes.h>
 #include <linux/iommu.h>
 #include <linux/file.h>
+#include <linux/mm.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -56,43 +46,6 @@
 	return tce_pages + ALIGN(stt_bytes, PAGE_SIZE) / PAGE_SIZE;
 }
 
-static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
-{
-	long ret = 0;
-
-	if (!current || !current->mm)
-		return ret; /* process exited */
-
-	down_write(&current->mm->mmap_sem);
-
-	if (inc) {
-		unsigned long locked, lock_limit;
-
-		locked = current->mm->locked_vm + stt_pages;
-		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			ret = -ENOMEM;
-		else
-			current->mm->locked_vm += stt_pages;
-	} else {
-		if (WARN_ON_ONCE(stt_pages > current->mm->locked_vm))
-			stt_pages = current->mm->locked_vm;
-
-		current->mm->locked_vm -= stt_pages;
-	}
-
-	pr_debug("[%d] RLIMIT_MEMLOCK KVM %c%ld %ld/%ld%s\n", current->pid,
-			inc ? '+' : '-',
-			stt_pages << PAGE_SHIFT,
-			current->mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK),
-			ret ? " - exceeded" : "");
-
-	up_write(&current->mm->mmap_sem);
-
-	return ret;
-}
-
 static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
 {
 	struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
@@ -133,7 +86,6 @@
 					continue;
 
 				kref_put(&stit->kref, kvm_spapr_tce_liobn_put);
-				return;
 			}
 		}
 	}
@@ -229,11 +181,33 @@
 	unsigned long i, npages = kvmppc_tce_pages(stt->size);
 
 	for (i = 0; i < npages; i++)
-		__free_page(stt->pages[i]);
+		if (stt->pages[i])
+			__free_page(stt->pages[i]);
 
 	kfree(stt);
 }
 
+static struct page *kvm_spapr_get_tce_page(struct kvmppc_spapr_tce_table *stt,
+		unsigned long sttpage)
+{
+	struct page *page = stt->pages[sttpage];
+
+	if (page)
+		return page;
+
+	mutex_lock(&stt->alloc_lock);
+	page = stt->pages[sttpage];
+	if (!page) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		WARN_ON_ONCE(!page);
+		if (page)
+			stt->pages[sttpage] = page;
+	}
+	mutex_unlock(&stt->alloc_lock);
+
+	return page;
+}
+
 static vm_fault_t kvm_spapr_tce_fault(struct vm_fault *vmf)
 {
 	struct kvmppc_spapr_tce_table *stt = vmf->vma->vm_file->private_data;
@@ -242,7 +216,10 @@
 	if (vmf->pgoff >= kvmppc_tce_pages(stt->size))
 		return VM_FAULT_SIGBUS;
 
-	page = stt->pages[vmf->pgoff];
+	page = kvm_spapr_get_tce_page(stt, vmf->pgoff);
+	if (!page)
+		return VM_FAULT_OOM;
+
 	get_page(page);
 	vmf->page = page;
 	return 0;
@@ -278,7 +255,7 @@
 
 	kvm_put_kvm(stt->kvm);
 
-	kvmppc_account_memlimit(
+	account_locked_vm(current->mm,
 		kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false);
 	call_rcu(&stt->rcu, release_spapr_tce_table);
 
@@ -297,14 +274,13 @@
 	struct kvmppc_spapr_tce_table *siter;
 	unsigned long npages, size = args->size;
 	int ret = -ENOMEM;
-	int i;
 
 	if (!args->size || args->page_shift < 12 || args->page_shift > 34 ||
 		(args->offset + args->size > (ULLONG_MAX >> args->page_shift)))
 		return -EINVAL;
 
 	npages = kvmppc_tce_pages(size);
-	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
+	ret = account_locked_vm(current->mm, kvmppc_stt_pages(npages), true);
 	if (ret)
 		return ret;
 
@@ -319,14 +295,9 @@
 	stt->offset = args->offset;
 	stt->size = size;
 	stt->kvm = kvm;
+	mutex_init(&stt->alloc_lock);
 	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
 
-	for (i = 0; i < npages; i++) {
-		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!stt->pages[i])
-			goto fail;
-	}
-
 	mutex_lock(&kvm->lock);
 
 	/* Check this LIOBN hasn't been previously allocated */
@@ -338,37 +309,114 @@
 		}
 	}
 
+	kvm_get_kvm(kvm);
 	if (!ret)
 		ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
 				       stt, O_RDWR | O_CLOEXEC);
 
-	if (ret >= 0) {
+	if (ret >= 0)
 		list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
-		kvm_get_kvm(kvm);
-	}
+	else
+		kvm_put_kvm(kvm);
 
 	mutex_unlock(&kvm->lock);
 
 	if (ret >= 0)
 		return ret;
 
- fail:
-	for (i = 0; i < npages; i++)
-		if (stt->pages[i])
-			__free_page(stt->pages[i]);
-
 	kfree(stt);
  fail_acct:
-	kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
+	account_locked_vm(current->mm, kvmppc_stt_pages(npages), false);
 	return ret;
 }
 
-static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry)
+static long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
+		unsigned long *ua)
+{
+	unsigned long gfn = tce >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots(kvm), gfn);
+	if (!memslot)
+		return -EINVAL;
+
+	*ua = __gfn_to_hva_memslot(memslot, gfn) |
+		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+	return 0;
+}
+
+static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
+		unsigned long tce)
+{
+	unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+	enum dma_data_direction dir = iommu_tce_direction(tce);
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	unsigned long ua = 0;
+
+	/* Allow userspace to poison TCE table */
+	if (dir == DMA_NONE)
+		return H_SUCCESS;
+
+	if (iommu_tce_check_gpa(stt->page_shift, gpa))
+		return H_TOO_HARD;
+
+	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua))
+		return H_TOO_HARD;
+
+	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
+		unsigned long hpa = 0;
+		struct mm_iommu_table_group_mem_t *mem;
+		long shift = stit->tbl->it_page_shift;
+
+		mem = mm_iommu_lookup(stt->kvm->mm, ua, 1ULL << shift);
+		if (!mem)
+			return H_TOO_HARD;
+
+		if (mm_iommu_ua_to_hpa(mem, ua, shift, &hpa))
+			return H_TOO_HARD;
+	}
+
+	return H_SUCCESS;
+}
+
+/*
+ * Handles TCE requests for emulated devices.
+ * Puts guest TCE values to the table and expects user space to convert them.
+ * Cannot fail so kvmppc_tce_validate must be called before it.
+ */
+static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+		unsigned long idx, unsigned long tce)
+{
+	struct page *page;
+	u64 *tbl;
+	unsigned long sttpage;
+
+	idx -= stt->offset;
+	sttpage = idx / TCES_PER_PAGE;
+	page = stt->pages[sttpage];
+
+	if (!page) {
+		/* We allow any TCE, not just with read|write permissions */
+		if (!tce)
+			return;
+
+		page = kvm_spapr_get_tce_page(stt, sttpage);
+		if (!page)
+			return;
+	}
+	tbl = page_to_virt(page);
+
+	tbl[idx % TCES_PER_PAGE] = tce;
+}
+
+static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl,
+		unsigned long entry)
 {
 	unsigned long hpa = 0;
 	enum dma_data_direction dir = DMA_NONE;
 
-	iommu_tce_xchg(tbl, entry, &hpa, &dir);
+	iommu_tce_xchg_no_kill(mm, tbl, entry, &hpa, &dir);
 }
 
 static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
@@ -376,11 +424,10 @@
 {
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
-	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
 
 	if (!pua)
-		/* it_userspace allocation might be delayed */
-		return H_TOO_HARD;
+		return H_SUCCESS;
 
 	mem = mm_iommu_lookup(kvm->mm, be64_to_cpu(*pua), pgsize);
 	if (!mem)
@@ -400,15 +447,16 @@
 	unsigned long hpa = 0;
 	long ret;
 
-	if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir)))
-		return H_HARDWARE;
+	if (WARN_ON_ONCE(iommu_tce_xchg_no_kill(kvm->mm, tbl, entry, &hpa,
+					&dir)))
+		return H_TOO_HARD;
 
 	if (dir == DMA_NONE)
 		return H_SUCCESS;
 
 	ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
 	if (ret != H_SUCCESS)
-		iommu_tce_xchg(tbl, entry, &hpa, &dir);
+		iommu_tce_xchg_no_kill(kvm->mm, tbl, entry, &hpa, &dir);
 
 	return ret;
 }
@@ -449,15 +497,15 @@
 		return H_TOO_HARD;
 
 	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa)))
-		return H_HARDWARE;
+		return H_TOO_HARD;
 
 	if (mm_iommu_mapped_inc(mem))
-		return H_CLOSED;
+		return H_TOO_HARD;
 
-	ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
+	ret = iommu_tce_xchg_no_kill(kvm->mm, tbl, entry, &hpa, &dir);
 	if (WARN_ON_ONCE(ret)) {
 		mm_iommu_mapped_dec(mem);
-		return H_HARDWARE;
+		return H_TOO_HARD;
 	}
 
 	if (dir != DMA_NONE)
@@ -509,16 +557,15 @@
 	if (ret != H_SUCCESS)
 		return ret;
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	ret = kvmppc_tce_validate(stt, tce);
 	if (ret != H_SUCCESS)
-		return ret;
+		goto unlock_exit;
 
 	dir = iommu_tce_direction(tce);
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-
-	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
-			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) {
+	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) {
 		ret = H_PARAMETER;
 		goto unlock_exit;
 	}
@@ -533,14 +580,12 @@
 			ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl,
 					entry, ua, dir);
 
-		if (ret == H_SUCCESS)
-			continue;
+		iommu_tce_kill(stit->tbl, entry, 1);
 
-		if (ret == H_TOO_HARD)
+		if (ret != H_SUCCESS) {
+			kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry);
 			goto unlock_exit;
-
-		WARN_ON_ONCE(1);
-		kvmppc_clear_tce(stit->tbl, entry);
+		}
 	}
 
 	kvmppc_tce_put(stt, entry, tce);
@@ -583,7 +628,7 @@
 		return ret;
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL)) {
+	if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua)) {
 		ret = H_TOO_HARD;
 		goto unlock_exit;
 	}
@@ -599,30 +644,49 @@
 		ret = kvmppc_tce_validate(stt, tce);
 		if (ret != H_SUCCESS)
 			goto unlock_exit;
+	}
 
-		if (kvmppc_gpa_to_ua(vcpu->kvm,
-				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
-				&ua, NULL))
-			return H_PARAMETER;
+	for (i = 0; i < npages; ++i) {
+		/*
+		 * This looks unsafe, because we validate, then regrab
+		 * the TCE from userspace which could have been changed by
+		 * another thread.
+		 *
+		 * But it actually is safe, because the relevant checks will be
+		 * re-executed in the following code.  If userspace tries to
+		 * change this dodgily it will result in a messier failure mode
+		 * but won't threaten the host.
+		 */
+		if (get_user(tce, tces + i)) {
+			ret = H_TOO_HARD;
+			goto invalidate_exit;
+		}
+		tce = be64_to_cpu(tce);
+
+		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) {
+			ret = H_PARAMETER;
+			goto invalidate_exit;
+		}
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
 			ret = kvmppc_tce_iommu_map(vcpu->kvm, stt,
 					stit->tbl, entry + i, ua,
 					iommu_tce_direction(tce));
 
-			if (ret == H_SUCCESS)
-				continue;
-
-			if (ret == H_TOO_HARD)
-				goto unlock_exit;
-
-			WARN_ON_ONCE(1);
-			kvmppc_clear_tce(stit->tbl, entry);
+			if (ret != H_SUCCESS) {
+				kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl,
+						entry);
+				goto invalidate_exit;
+			}
 		}
 
 		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
+invalidate_exit:
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
+		iommu_tce_kill(stit->tbl, entry, npages);
+
 unlock_exit:
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
@@ -661,16 +725,20 @@
 				continue;
 
 			if (ret == H_TOO_HARD)
-				return ret;
+				goto invalidate_exit;
 
 			WARN_ON_ONCE(1);
-			kvmppc_clear_tce(stit->tbl, entry);
+			kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry);
 		}
 	}
 
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
-	return H_SUCCESS;
+invalidate_exit:
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
+		iommu_tce_kill(stit->tbl, ioba >> stt->page_shift, npages);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce);
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 6821ead..ab6eeb8 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
@@ -66,8 +55,6 @@
 
 #endif
 
-#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
-
 /*
  * Finds a TCE table descriptor by LIOBN.
  *
@@ -87,6 +74,26 @@
 }
 EXPORT_SYMBOL_GPL(kvmppc_find_table);
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static long kvmppc_rm_tce_to_ua(struct kvm *kvm, unsigned long tce,
+		unsigned long *ua, unsigned long **prmap)
+{
+	unsigned long gfn = tce >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots_raw(kvm), gfn);
+	if (!memslot)
+		return -EINVAL;
+
+	*ua = __gfn_to_hva_memslot(memslot, gfn) |
+		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+	if (prmap)
+		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
+
+	return 0;
+}
+
 /*
  * Validates TCE address.
  * At the moment flags and page mask are validated.
@@ -94,14 +101,14 @@
  * to the table and user space is supposed to process them), we can skip
  * checking other things (such as TCE is a guest RAM address or the page
  * was actually allocated).
- *
- * WARNING: This will be called in real-mode on HV KVM and virtual
- *          mode on PR KVM
  */
-long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, unsigned long tce)
+static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt,
+		unsigned long tce)
 {
 	unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
 	enum dma_data_direction dir = iommu_tce_direction(tce);
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	unsigned long ua = 0;
 
 	/* Allow userspace to poison TCE table */
 	if (dir == DMA_NONE)
@@ -110,9 +117,24 @@
 	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_PARAMETER;
 
+	if (kvmppc_rm_tce_to_ua(stt->kvm, tce, &ua, NULL))
+		return H_TOO_HARD;
+
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		unsigned long hpa = 0;
+		struct mm_iommu_table_group_mem_t *mem;
+		long shift = stit->tbl->it_page_shift;
+
+		mem = mm_iommu_lookup_rm(stt->kvm->mm, ua, 1ULL << shift);
+		if (!mem)
+			return H_TOO_HARD;
+
+		if (mm_iommu_ua_to_hpa_rm(mem, ua, shift, &hpa))
+			return H_TOO_HARD;
+	}
+
 	return H_SUCCESS;
 }
-EXPORT_SYMBOL_GPL(kvmppc_tce_validate);
 
 /* Note on the use of page_address() in real mode,
  *
@@ -144,13 +166,9 @@
 /*
  * Handles TCE requests for emulated devices.
  * Puts guest TCE values to the table and expects user space to convert them.
- * Called in both real and virtual modes.
- * Cannot fail so kvmppc_tce_validate must be called before it.
- *
- * WARNING: This will be called in real-mode on HV KVM and virtual
- *          mode on PR KVM
+ * Cannot fail so kvmppc_rm_tce_validate must be called before it.
  */
-void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+static void kvmppc_rm_tce_put(struct kvmppc_spapr_tce_table *stt,
 		unsigned long idx, unsigned long tce)
 {
 	struct page *page;
@@ -158,46 +176,60 @@
 
 	idx -= stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
+	/*
+	 * page must not be NULL in real mode,
+	 * kvmppc_rm_ioba_validate() must have taken care of this.
+	 */
+	WARN_ON_ONCE_RM(!page);
 	tbl = kvmppc_page_address(page);
 
 	tbl[idx % TCES_PER_PAGE] = tce;
 }
-EXPORT_SYMBOL_GPL(kvmppc_tce_put);
 
-long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
-		unsigned long *ua, unsigned long **prmap)
+/*
+ * TCEs pages are allocated in kvmppc_rm_tce_put() which won't be able to do so
+ * in real mode.
+ * Check if kvmppc_rm_tce_put() can succeed in real mode, i.e. a TCEs page is
+ * allocated or not required (when clearing a tce entry).
+ */
+static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt,
+		unsigned long ioba, unsigned long npages, bool clearing)
 {
-	unsigned long gfn = gpa >> PAGE_SHIFT;
-	struct kvm_memory_slot *memslot;
+	unsigned long i, idx, sttpage, sttpages;
+	unsigned long ret = kvmppc_ioba_validate(stt, ioba, npages);
 
-	memslot = search_memslots(kvm_memslots(kvm), gfn);
-	if (!memslot)
-		return -EINVAL;
+	if (ret)
+		return ret;
+	/*
+	 * clearing==true says kvmppc_rm_tce_put won't be allocating pages
+	 * for empty tces.
+	 */
+	if (clearing)
+		return H_SUCCESS;
 
-	*ua = __gfn_to_hva_memslot(memslot, gfn) |
-		(gpa & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+	idx = (ioba >> stt->page_shift) - stt->offset;
+	sttpage = idx / TCES_PER_PAGE;
+	sttpages = _ALIGN_UP(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) /
+			TCES_PER_PAGE;
+	for (i = sttpage; i < sttpage + sttpages; ++i)
+		if (!stt->pages[i])
+			return H_TOO_HARD;
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	if (prmap)
-		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
-#endif
-
-	return 0;
+	return H_SUCCESS;
 }
-EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl,
+static long iommu_tce_xchg_no_kill_rm(struct mm_struct *mm,
+		struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction)
 {
 	long ret;
 
-	ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+	ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, true);
 
 	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
 				(*direction == DMA_BIDIRECTIONAL))) {
-		__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
+		__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
 		/*
 		 * kvmppc_rm_tce_iommu_do_map() updates the UA cache after
 		 * calling this so we still get here a valid UA.
@@ -209,13 +241,20 @@
 	return ret;
 }
 
+extern void iommu_tce_kill_rm(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages)
+{
+	if (tbl->it_ops->tce_kill)
+		tbl->it_ops->tce_kill(tbl, entry, pages, true);
+}
+
 static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl,
 		unsigned long entry)
 {
 	unsigned long hpa = 0;
 	enum dma_data_direction dir = DMA_NONE;
 
-	iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
+	iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);
 }
 
 static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
@@ -223,7 +262,7 @@
 {
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
-	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
 
 	if (!pua)
 		/* it_userspace allocation might be delayed */
@@ -247,7 +286,7 @@
 	unsigned long hpa = 0;
 	long ret;
 
-	if (iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir))
+	if (iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir))
 		/*
 		 * real mode xchg can fail if struct page crosses
 		 * a page boundary
@@ -259,7 +298,7 @@
 
 	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
 	if (ret)
-		iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
+		iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);
 
 	return ret;
 }
@@ -287,7 +326,7 @@
 {
 	long ret;
 	unsigned long hpa = 0;
-	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
 	struct mm_iommu_table_group_mem_t *mem;
 
 	if (!pua)
@@ -300,12 +339,12 @@
 
 	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
 			&hpa)))
-		return H_HARDWARE;
+		return H_TOO_HARD;
 
 	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
-		return H_CLOSED;
+		return H_TOO_HARD;
 
-	ret = iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
+	ret = iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);
 	if (ret) {
 		mm_iommu_mapped_dec(mem);
 		/*
@@ -364,17 +403,16 @@
 	if (!stt)
 		return H_TOO_HARD;
 
-	ret = kvmppc_ioba_validate(stt, ioba, 1);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, 1, tce == 0);
 	if (ret != H_SUCCESS)
 		return ret;
 
-	ret = kvmppc_tce_validate(stt, tce);
+	ret = kvmppc_rm_tce_validate(stt, tce);
 	if (ret != H_SUCCESS)
 		return ret;
 
 	dir = iommu_tce_direction(tce);
-	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
-			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+	if ((dir != DMA_NONE) && kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
 		return H_PARAMETER;
 
 	entry = ioba >> stt->page_shift;
@@ -387,17 +425,15 @@
 			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
 					stit->tbl, entry, ua, dir);
 
-		if (ret == H_SUCCESS)
-			continue;
+		iommu_tce_kill_rm(stit->tbl, entry, 1);
 
-		if (ret == H_TOO_HARD)
+		if (ret != H_SUCCESS) {
+			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
 			return ret;
-
-		WARN_ON_ONCE_RM(1);
-		kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
+		}
 	}
 
-	kvmppc_tce_put(stt, entry, tce);
+	kvmppc_rm_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -468,7 +504,7 @@
 	if (tce_list & (SZ_4K - 1))
 		return H_PARAMETER;
 
-	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, false);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -480,7 +516,7 @@
 		 */
 		struct mm_iommu_table_group_mem_t *mem;
 
-		if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL))
 			return H_TOO_HARD;
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
@@ -496,12 +532,12 @@
 		 * We do not require memory to be preregistered in this case
 		 * so lock rmap and do __find_linux_pte_or_hugepte().
 		 */
-		if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
 			return H_TOO_HARD;
 
 		rmap = (void *) vmalloc_to_phys(rmap);
 		if (WARN_ON_ONCE_RM(!rmap))
-			return H_HARDWARE;
+			return H_TOO_HARD;
 
 		/*
 		 * Synchronize with the MMU notifier callbacks in
@@ -521,34 +557,39 @@
 	for (i = 0; i < npages; ++i) {
 		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
 
-		ret = kvmppc_tce_validate(stt, tce);
+		ret = kvmppc_rm_tce_validate(stt, tce);
 		if (ret != H_SUCCESS)
 			goto unlock_exit;
+	}
+
+	for (i = 0; i < npages; ++i) {
+		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
 
 		ua = 0;
-		if (kvmppc_gpa_to_ua(vcpu->kvm,
-				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
-				&ua, NULL))
-			return H_PARAMETER;
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
+			ret = H_PARAMETER;
+			goto invalidate_exit;
+		}
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
 			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
 					stit->tbl, entry + i, ua,
 					iommu_tce_direction(tce));
 
-			if (ret == H_SUCCESS)
-				continue;
-
-			if (ret == H_TOO_HARD)
-				goto unlock_exit;
-
-			WARN_ON_ONCE_RM(1);
-			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
+			if (ret != H_SUCCESS) {
+				kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl,
+						entry);
+				goto invalidate_exit;
+			}
 		}
 
-		kvmppc_tce_put(stt, entry + i, tce);
+		kvmppc_rm_tce_put(stt, entry + i, tce);
 	}
 
+invalidate_exit:
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
+		iommu_tce_kill_rm(stit->tbl, entry, npages);
+
 unlock_exit:
 	if (rmap)
 		unlock_rmap(rmap);
@@ -572,7 +613,7 @@
 	if (!stt)
 		return H_TOO_HARD;
 
-	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, tce_value == 0);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -591,7 +632,7 @@
 				continue;
 
 			if (ret == H_TOO_HARD)
-				return ret;
+				goto invalidate_exit;
 
 			WARN_ON_ONCE_RM(1);
 			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
@@ -599,9 +640,13 @@
 	}
 
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
-		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
+		kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
-	return H_SUCCESS;
+invalidate_exit:
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
+		iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages);
+
+	return ret;
 }
 
 /* This can be called in either virtual mode or real mode */
@@ -624,6 +669,10 @@
 
 	idx = (ioba >> stt->page_shift) - stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
+	if (!page) {
+		vcpu->arch.regs.gpr[4] = 0;
+		return H_SUCCESS;
+	}
 	tbl = (u64 *)page_address(page);
 
 	vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 36b11c5..dad71d2 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
@@ -36,7 +25,6 @@
 #define OP_31_XOP_MTSR		210
 #define OP_31_XOP_MTSRIN	242
 #define OP_31_XOP_TLBIEL	274
-#define OP_31_XOP_TLBIE		306
 /* Opcode is officially reserved, reuse it as sc 1 when sc 1 doesn't trap */
 #define OP_31_XOP_FAKE_SC1	308
 #define OP_31_XOP_SLBMTE	402
@@ -48,6 +36,7 @@
 #define OP_31_XOP_SLBMFEV	851
 #define OP_31_XOP_EIOIO		854
 #define OP_31_XOP_SLBMFEE	915
+#define OP_31_XOP_SLBFEE	979
 
 #define OP_31_XOP_TBEGIN	654
 #define OP_31_XOP_TABORT	910
@@ -110,7 +99,7 @@
 	vcpu->arch.ctr_tm = vcpu->arch.regs.ctr;
 	vcpu->arch.tar_tm = vcpu->arch.tar;
 	vcpu->arch.lr_tm = vcpu->arch.regs.link;
-	vcpu->arch.cr_tm = vcpu->arch.cr;
+	vcpu->arch.cr_tm = vcpu->arch.regs.ccr;
 	vcpu->arch.xer_tm = vcpu->arch.regs.xer;
 	vcpu->arch.vrsave_tm = vcpu->arch.vrsave;
 }
@@ -129,7 +118,7 @@
 	vcpu->arch.regs.ctr = vcpu->arch.ctr_tm;
 	vcpu->arch.tar = vcpu->arch.tar_tm;
 	vcpu->arch.regs.link = vcpu->arch.lr_tm;
-	vcpu->arch.cr = vcpu->arch.cr_tm;
+	vcpu->arch.regs.ccr = vcpu->arch.cr_tm;
 	vcpu->arch.regs.xer = vcpu->arch.xer_tm;
 	vcpu->arch.vrsave = vcpu->arch.vrsave_tm;
 }
@@ -141,7 +130,7 @@
 	uint64_t texasr;
 
 	/* CR0 = 0 | MSR[TS] | 0 */
-	vcpu->arch.cr = (vcpu->arch.cr & ~(CR0_MASK << CR0_SHIFT)) |
+	vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & ~(CR0_MASK << CR0_SHIFT)) |
 		(((guest_msr & MSR_TS_MASK) >> (MSR_TS_S_LG - 1))
 		 << CR0_SHIFT);
 
@@ -220,7 +209,7 @@
 	tm_abort(ra_val);
 
 	/* CR0 = 0 | MSR[TS] | 0 */
-	vcpu->arch.cr = (vcpu->arch.cr & ~(CR0_MASK << CR0_SHIFT)) |
+	vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & ~(CR0_MASK << CR0_SHIFT)) |
 		(((guest_msr & MSR_TS_MASK) >> (MSR_TS_S_LG - 1))
 		 << CR0_SHIFT);
 
@@ -417,6 +406,23 @@
 
 			vcpu->arch.mmu.slbia(vcpu);
 			break;
+		case OP_31_XOP_SLBFEE:
+			if (!(inst & 1) || !vcpu->arch.mmu.slbfee) {
+				return EMULATE_FAIL;
+			} else {
+				ulong b, t;
+				ulong cr = kvmppc_get_cr(vcpu) & ~CR0_MASK;
+
+				b = kvmppc_get_gpr(vcpu, rb);
+				if (!vcpu->arch.mmu.slbfee(vcpu, b, &t))
+					cr |= 2 << CR0_SHIFT;
+				kvmppc_set_gpr(vcpu, rt, t);
+				/* copy XER[SO] bit to CR0[SO] */
+				cr |= (vcpu->arch.regs.xer & 0x80000000) >>
+					(31 - CR0_SHIFT);
+				kvmppc_set_cr(vcpu, cr);
+			}
+			break;
 		case OP_31_XOP_SLBMFEE:
 			if (!vcpu->arch.mmu.slbmfee) {
 				emulated = EMULATE_FAIL;
@@ -494,8 +500,8 @@
 
 			if (!(kvmppc_get_msr(vcpu) & MSR_PR)) {
 				preempt_disable();
-				vcpu->arch.cr = (CR0_TBEGIN_FAILURE |
-				  (vcpu->arch.cr & ~(CR0_MASK << CR0_SHIFT)));
+				vcpu->arch.regs.ccr = (CR0_TBEGIN_FAILURE |
+				  (vcpu->arch.regs.ccr & ~(CR0_MASK << CR0_SHIFT)));
 
 				vcpu->arch.texasr = (TEXASR_FS | TEXASR_EXACT |
 					(((u64)(TM_CAUSE_EMULATE | TM_CAUSE_PERSISTENT))
diff --git a/arch/powerpc/kvm/book3s_exports.c b/arch/powerpc/kvm/book3s_exports.c
index 0d013fb..f085658 100644
--- a/arch/powerpc/kvm/book3s_exports.c
+++ b/arch/powerpc/kvm/book3s_exports.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3e3a715..709cf1f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
@@ -12,10 +13,6 @@
  *
  * This file is derived from arch/powerpc/kvm/book3s.c,
  * by Alexander Graf <agraf@suse.de>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kvm_host.h>
@@ -50,6 +47,7 @@
 #include <asm/reg.h>
 #include <asm/ppc-opcode.h>
 #include <asm/asm-prototypes.h>
+#include <asm/archrandom.h>
 #include <asm/debug.h>
 #include <asm/disassemble.h>
 #include <asm/cputable.h>
@@ -73,6 +71,7 @@
 #include <asm/opal.h>
 #include <asm/xics.h>
 #include <asm/xive.h>
+#include <asm/hw_breakpoint.h>
 
 #include "book3s.h"
 
@@ -104,6 +103,10 @@
 module_param(indep_threads_mode, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(indep_threads_mode, "Independent-threads mode (only on POWER9)");
 
+static bool one_vm_per_core;
+module_param(one_vm_per_core, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires indep_threads_mode=N)");
+
 #ifdef CONFIG_KVM_XICS
 static struct kernel_param_ops module_param_ops = {
 	.set = param_set_int,
@@ -117,6 +120,16 @@
 MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
 #endif
 
+/* If set, guests are allowed to create and control nested guests */
+static bool nested = true;
+module_param(nested, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(nested, "Enable nested virtualization (only on POWER9)");
+
+static inline bool nesting_enabled(struct kvm *kvm)
+{
+	return kvm->arch.nested_enable && kvm_is_radix(kvm);
+}
+
 /* If set, the threads on each CPU core have to be in the same MMU mode */
 static bool no_mixing_hpt_and_radix;
 
@@ -173,6 +186,10 @@
 {
 	unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 
+	/* If we're a nested hypervisor, fall back to ordinary IPIs for now */
+	if (kvmhv_on_pseries())
+		return false;
+
 	/* On POWER9 we can use msgsnd to IPI any cpu */
 	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
 		msg |= get_hard_smp_processor_id(cpu);
@@ -384,8 +401,11 @@
 
 	spin_lock(&vc->lock);
 	vc->arch_compat = arch_compat;
-	/* Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit */
-	vc->pcr = host_pcr_bit - guest_pcr_bit;
+	/*
+	 * Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit
+	 * Also set all reserved PCR bits
+	 */
+	vc->pcr = (host_pcr_bit - guest_pcr_bit) | PCR_MASK;
 	spin_unlock(&vc->lock);
 
 	return 0;
@@ -410,8 +430,8 @@
 	       vcpu->arch.shregs.sprg0, vcpu->arch.shregs.sprg1);
 	pr_err("sprg2 = %.16llx sprg3 = %.16llx\n",
 	       vcpu->arch.shregs.sprg2, vcpu->arch.shregs.sprg3);
-	pr_err("cr = %.8x  xer = %.16lx  dsisr = %.8x\n",
-	       vcpu->arch.cr, vcpu->arch.regs.xer, vcpu->arch.shregs.dsisr);
+	pr_err("cr = %.8lx  xer = %.16lx  dsisr = %.8x\n",
+	       vcpu->arch.regs.ccr, vcpu->arch.regs.xer, vcpu->arch.shregs.dsisr);
 	pr_err("dar = %.16llx\n", vcpu->arch.shregs.dar);
 	pr_err("fault dar = %.16lx dsisr = %.8x\n",
 	       vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
@@ -426,12 +446,7 @@
 
 static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
 {
-	struct kvm_vcpu *ret;
-
-	mutex_lock(&kvm->lock);
-	ret = kvm_get_vcpu_by_id(kvm, id);
-	mutex_unlock(&kvm->lock);
-	return ret;
+	return kvm_get_vcpu_by_id(kvm, id);
 }
 
 static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
@@ -730,8 +745,7 @@
 	/*
 	 * Ensure that the read of vcore->dpdes comes after the read
 	 * of vcpu->doorbell_request.  This barrier matches the
-	 * lwsync in book3s_hv_rmhandlers.S just before the
-	 * fast_guest_return label.
+	 * smp_wmb() in kvmppc_guest_entry_inject().
 	 */
 	smp_rmb();
 	vc = vcpu->arch.vcore;
@@ -783,6 +797,80 @@
 	}
 }
 
+/* Copy guest memory in place - must reside within a single memslot */
+static int kvmppc_copy_guest(struct kvm *kvm, gpa_t to, gpa_t from,
+				  unsigned long len)
+{
+	struct kvm_memory_slot *to_memslot = NULL;
+	struct kvm_memory_slot *from_memslot = NULL;
+	unsigned long to_addr, from_addr;
+	int r;
+
+	/* Get HPA for from address */
+	from_memslot = gfn_to_memslot(kvm, from >> PAGE_SHIFT);
+	if (!from_memslot)
+		return -EFAULT;
+	if ((from + len) >= ((from_memslot->base_gfn + from_memslot->npages)
+			     << PAGE_SHIFT))
+		return -EINVAL;
+	from_addr = gfn_to_hva_memslot(from_memslot, from >> PAGE_SHIFT);
+	if (kvm_is_error_hva(from_addr))
+		return -EFAULT;
+	from_addr |= (from & (PAGE_SIZE - 1));
+
+	/* Get HPA for to address */
+	to_memslot = gfn_to_memslot(kvm, to >> PAGE_SHIFT);
+	if (!to_memslot)
+		return -EFAULT;
+	if ((to + len) >= ((to_memslot->base_gfn + to_memslot->npages)
+			   << PAGE_SHIFT))
+		return -EINVAL;
+	to_addr = gfn_to_hva_memslot(to_memslot, to >> PAGE_SHIFT);
+	if (kvm_is_error_hva(to_addr))
+		return -EFAULT;
+	to_addr |= (to & (PAGE_SIZE - 1));
+
+	/* Perform copy */
+	r = raw_copy_in_user((void __user *)to_addr, (void __user *)from_addr,
+			     len);
+	if (r)
+		return -EFAULT;
+	mark_page_dirty(kvm, to >> PAGE_SHIFT);
+	return 0;
+}
+
+static long kvmppc_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			       unsigned long dest, unsigned long src)
+{
+	u64 pg_sz = SZ_4K;		/* 4K page size */
+	u64 pg_mask = SZ_4K - 1;
+	int ret;
+
+	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
+	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
+		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
+		return H_PARAMETER;
+
+	/* dest (and src if copy_page flag set) must be page aligned */
+	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
+		return H_PARAMETER;
+
+	/* zero and/or copy the page as determined by the flags */
+	if (flags & H_COPY_PAGE) {
+		ret = kvmppc_copy_guest(vcpu->kvm, dest, src, pg_sz);
+		if (ret < 0)
+			return H_PARAMETER;
+	} else if (flags & H_ZERO_PAGE) {
+		ret = kvm_clear_guest(vcpu->kvm, dest, pg_sz);
+		if (ret < 0)
+			return H_PARAMETER;
+	}
+
+	/* We can ignore the remaining flags */
+
+	return H_SUCCESS;
+}
+
 static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target)
 {
 	struct kvmppc_vcore *vcore = target->arch.vcore;
@@ -904,7 +992,7 @@
 	case H_IPOLL:
 	case H_XIRR_X:
 		if (kvmppc_xics_enabled(vcpu)) {
-			if (xive_enabled()) {
+			if (xics_on_xive()) {
 				ret = H_NOT_AVAILABLE;
 				return RESUME_GUEST;
 			}
@@ -912,6 +1000,20 @@
 			break;
 		}
 		return RESUME_HOST;
+	case H_SET_DABR:
+		ret = kvmppc_h_set_dabr(vcpu, kvmppc_get_gpr(vcpu, 4));
+		break;
+	case H_SET_XDABR:
+		ret = kvmppc_h_set_xdabr(vcpu, kvmppc_get_gpr(vcpu, 4),
+						kvmppc_get_gpr(vcpu, 5));
+		break;
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	case H_GET_TCE:
+		ret = kvmppc_h_get_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+						kvmppc_get_gpr(vcpu, 5));
+		if (ret == H_TOO_HARD)
+			return RESUME_HOST;
+		break;
 	case H_PUT_TCE:
 		ret = kvmppc_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
 						kvmppc_get_gpr(vcpu, 5),
@@ -935,6 +1037,47 @@
 		if (ret == H_TOO_HARD)
 			return RESUME_HOST;
 		break;
+#endif
+	case H_RANDOM:
+		if (!powernv_get_random_long(&vcpu->arch.regs.gpr[4]))
+			ret = H_HARDWARE;
+		break;
+
+	case H_SET_PARTITION_TABLE:
+		ret = H_FUNCTION;
+		if (nesting_enabled(vcpu->kvm))
+			ret = kvmhv_set_partition_table(vcpu);
+		break;
+	case H_ENTER_NESTED:
+		ret = H_FUNCTION;
+		if (!nesting_enabled(vcpu->kvm))
+			break;
+		ret = kvmhv_enter_nested_guest(vcpu);
+		if (ret == H_INTERRUPT) {
+			kvmppc_set_gpr(vcpu, 3, 0);
+			vcpu->arch.hcall_needed = 0;
+			return -EINTR;
+		} else if (ret == H_TOO_HARD) {
+			kvmppc_set_gpr(vcpu, 3, 0);
+			vcpu->arch.hcall_needed = 0;
+			return RESUME_HOST;
+		}
+		break;
+	case H_TLB_INVALIDATE:
+		ret = H_FUNCTION;
+		if (nesting_enabled(vcpu->kvm))
+			ret = kvmhv_do_nested_tlbie(vcpu);
+		break;
+	case H_COPY_TOFROM_GUEST:
+		ret = H_FUNCTION;
+		if (nesting_enabled(vcpu->kvm))
+			ret = kvmhv_copy_tofrom_guest_nested(vcpu);
+		break;
+	case H_PAGE_INIT:
+		ret = kvmppc_h_page_init(vcpu, kvmppc_get_gpr(vcpu, 4),
+					 kvmppc_get_gpr(vcpu, 5),
+					 kvmppc_get_gpr(vcpu, 6));
+		break;
 	default:
 		return RESUME_HOST;
 	}
@@ -943,6 +1086,24 @@
 	return RESUME_GUEST;
 }
 
+/*
+ * Handle H_CEDE in the nested virtualization case where we haven't
+ * called the real-mode hcall handlers in book3s_hv_rmhandlers.S.
+ * This has to be done early, not in kvmppc_pseries_do_hcall(), so
+ * that the cede logic in kvmppc_run_single_vcpu() works properly.
+ */
+static void kvmppc_nested_cede(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.shregs.msr |= MSR_EE;
+	vcpu->arch.ceded = 1;
+	smp_mb();
+	if (vcpu->arch.prodded) {
+		vcpu->arch.prodded = 0;
+		smp_mb();
+		vcpu->arch.ceded = 0;
+	}
+}
+
 static int kvmppc_hcall_impl_hv(unsigned long cmd)
 {
 	switch (cmd) {
@@ -961,6 +1122,7 @@
 	case H_IPOLL:
 	case H_XIRR_X:
 #endif
+	case H_PAGE_INIT:
 		return 1;
 	}
 
@@ -1085,7 +1247,6 @@
 	return RESUME_GUEST;
 }
 
-/* Called with vcpu->arch.vcore->lock held */
 static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				 struct task_struct *tsk)
 {
@@ -1132,6 +1293,22 @@
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_MACHINE_CHECK:
+		/* Print the MCE event to host console. */
+		machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
+
+		/*
+		 * If the guest can do FWNMI, exit to userspace so it can
+		 * deliver a FWNMI to the guest.
+		 * Otherwise we synthesize a machine check for the guest
+		 * so that it knows that the machine check occurred.
+		 */
+		if (!vcpu->kvm->arch.fwnmi_enabled) {
+			ulong flags = vcpu->arch.shregs.msr & 0x083c0000;
+			kvmppc_core_queue_machine_check(vcpu, flags);
+			r = RESUME_GUEST;
+			break;
+		}
+
 		/* Exit to guest with KVM_EXIT_NMI as exit reason */
 		run->exit_reason = KVM_EXIT_NMI;
 		run->hw.hardware_exit_reason = vcpu->arch.trap;
@@ -1144,8 +1321,6 @@
 			run->flags |= KVM_RUN_PPC_NMI_DISP_NOT_RECOV;
 
 		r = RESUME_HOST;
-		/* Print the MCE event to host console. */
-		machine_check_print_event_info(&vcpu->arch.mce_evt, false);
 		break;
 	case BOOK3S_INTERRUPT_PROGRAM:
 	{
@@ -1190,7 +1365,10 @@
 		break;
 	case BOOK3S_INTERRUPT_H_INST_STORAGE:
 		vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
-		vcpu->arch.fault_dsisr = 0;
+		vcpu->arch.fault_dsisr = vcpu->arch.shregs.msr &
+			DSISR_SRR1_MATCH_64S;
+		if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE)
+			vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
 		r = RESUME_PAGE_FAULT;
 		break;
 	/*
@@ -1206,10 +1384,7 @@
 				swab32(vcpu->arch.emul_inst) :
 				vcpu->arch.emul_inst;
 		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) {
-			/* Need vcore unlocked to call kvmppc_get_last_inst */
-			spin_unlock(&vcpu->arch.vcore->lock);
 			r = kvmppc_emulate_debug_inst(run, vcpu);
-			spin_lock(&vcpu->arch.vcore->lock);
 		} else {
 			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
 			r = RESUME_GUEST;
@@ -1225,12 +1400,8 @@
 	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
 		r = EMULATE_FAIL;
 		if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) &&
-		    cpu_has_feature(CPU_FTR_ARCH_300)) {
-			/* Need vcore unlocked to call kvmppc_get_last_inst */
-			spin_unlock(&vcpu->arch.vcore->lock);
+		    cpu_has_feature(CPU_FTR_ARCH_300))
 			r = kvmppc_emulate_doorbell_instr(vcpu);
-			spin_lock(&vcpu->arch.vcore->lock);
-		}
 		if (r == EMULATE_FAIL) {
 			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
 			r = RESUME_GUEST;
@@ -1265,6 +1436,104 @@
 	return r;
 }
 
+static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	int r;
+	int srcu_idx;
+
+	vcpu->stat.sum_exits++;
+
+	/*
+	 * This can happen if an interrupt occurs in the last stages
+	 * of guest entry or the first stages of guest exit (i.e. after
+	 * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV
+	 * and before setting it to KVM_GUEST_MODE_HOST_HV).
+	 * 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) {
+		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_dump_regs(vcpu);
+		return RESUME_HOST;
+	}
+	switch (vcpu->arch.trap) {
+	/* We're good on these - the host merely wanted to get our attention */
+	case BOOK3S_INTERRUPT_HV_DECREMENTER:
+		vcpu->stat.dec_exits++;
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_EXTERNAL:
+		vcpu->stat.ext_intr_exits++;
+		r = RESUME_HOST;
+		break;
+	case BOOK3S_INTERRUPT_H_DOORBELL:
+	case BOOK3S_INTERRUPT_H_VIRT:
+		vcpu->stat.ext_intr_exits++;
+		r = RESUME_GUEST;
+		break;
+	/* SR/HMI/PMI are HV interrupts that host has handled. Resume guest.*/
+	case BOOK3S_INTERRUPT_HMI:
+	case BOOK3S_INTERRUPT_PERFMON:
+	case BOOK3S_INTERRUPT_SYSTEM_RESET:
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_MACHINE_CHECK:
+		/* Pass the machine check to the L1 guest */
+		r = RESUME_HOST;
+		/* Print the MCE event to host console. */
+		machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
+		break;
+	/*
+	 * We get these next two if the guest accesses a page which it thinks
+	 * it has mapped but which is not actually present, either because
+	 * it is for an emulated I/O device or because the corresonding
+	 * host page has been paged out.
+	 */
+	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
+		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		r = kvmhv_nested_page_fault(run, vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+		break;
+	case BOOK3S_INTERRUPT_H_INST_STORAGE:
+		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)
+			vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
+		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		r = kvmhv_nested_page_fault(run, vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+		break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+		/*
+		 * This occurs for various TM-related instructions that
+		 * we need to emulate on POWER9 DD2.2.  We have already
+		 * handled the cases where the guest was in real-suspend
+		 * mode and was transitioning to transactional state.
+		 */
+		r = kvmhv_p9_tm_emulation(vcpu);
+		break;
+#endif
+
+	case BOOK3S_INTERRUPT_HV_RM_HARD:
+		vcpu->arch.trap = 0;
+		r = RESUME_GUEST;
+		if (!xics_on_xive())
+			kvmppc_xics_rm_complete(vcpu, 0);
+		break;
+	default:
+		r = RESUME_HOST;
+		break;
+	}
+
+	return r;
+}
+
 static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu,
 					    struct kvm_sregs *sregs)
 {
@@ -1309,7 +1578,6 @@
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	u64 mask;
 
-	mutex_lock(&kvm->lock);
 	spin_lock(&vc->lock);
 	/*
 	 * If ILE (interrupt little-endian) has changed, update the
@@ -1349,7 +1617,6 @@
 		mask &= 0xFFFFFFFF;
 	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
 	spin_unlock(&vc->lock);
-	mutex_unlock(&kvm->lock);
 }
 
 static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
@@ -1414,7 +1681,14 @@
 		*val = get_reg_val(id, vcpu->arch.pspb);
 		break;
 	case KVM_REG_PPC_DPDES:
-		*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
+		/*
+		 * On POWER9, where we are emulating msgsndp etc.,
+		 * we return 1 bit for each vcpu, which can come from
+		 * either vcore->dpdes or doorbell_request.
+		 * On POWER8, doorbell_request is 0.
+		 */
+		*val = get_reg_val(id, vcpu->arch.vcore->dpdes |
+				   vcpu->arch.doorbell_request);
 		break;
 	case KVM_REG_PPC_VTB:
 		*val = get_reg_val(id, vcpu->arch.vcore->vtb);
@@ -1555,6 +1829,9 @@
 	case KVM_REG_PPC_ONLINE:
 		*val = get_reg_val(id, vcpu->arch.online);
 		break;
+	case KVM_REG_PPC_PTCR:
+		*val = get_reg_val(id, vcpu->kvm->arch.l1_ptcr);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -1786,6 +2063,9 @@
 			atomic_dec(&vcpu->arch.vcore->online_count);
 		vcpu->arch.online = i;
 		break;
+	case KVM_REG_PPC_PTCR:
+		vcpu->kvm->arch.l1_ptcr = set_reg_val(id, *val);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -2019,15 +2299,18 @@
 	 * Set the default HFSCR for the guest from the host value.
 	 * This value is only used on POWER9.
 	 * On POWER9, we want to virtualize the doorbell facility, so we
-	 * turn off the HFSCR bit, which causes those instructions to trap.
+	 * don't set the HFSCR_MSGP bit, and that causes those instructions
+	 * to trap and then we emulate them.
 	 */
-	vcpu->arch.hfscr = mfspr(SPRN_HFSCR);
-	if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+	vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB |
+		HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP;
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		vcpu->arch.hfscr &= mfspr(SPRN_HFSCR);
+		if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+			vcpu->arch.hfscr |= HFSCR_TM;
+	}
+	if (cpu_has_feature(CPU_FTR_TM_COMP))
 		vcpu->arch.hfscr |= HFSCR_TM;
-	else if (!cpu_has_feature(CPU_FTR_TM_COMP))
-		vcpu->arch.hfscr &= ~HFSCR_TM;
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		vcpu->arch.hfscr &= ~HFSCR_MSGP;
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
@@ -2055,11 +2338,17 @@
 			pr_devel("KVM: collision on id %u", id);
 			vcore = NULL;
 		} else if (!vcore) {
+			/*
+			 * Take mmu_setup_lock for mutual exclusion
+			 * with kvmppc_update_lpcr().
+			 */
 			err = -ENOMEM;
 			vcore = kvmppc_vcore_create(kvm,
 					id & ~(kvm->arch.smt_mode - 1));
+			mutex_lock(&kvm->arch.mmu_setup_lock);
 			kvm->arch.vcores[core] = vcore;
 			kvm->arch.online_vcores++;
+			mutex_unlock(&kvm->arch.mmu_setup_lock);
 		}
 	}
 	mutex_unlock(&kvm->lock);
@@ -2160,8 +2449,7 @@
 		kvmppc_core_prepare_to_enter(vcpu);
 		return;
 	}
-	dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC
-		   / tb_ticks_per_sec;
+	dec_nsec = tb_to_ns(vcpu->arch.dec_expires - now);
 	hrtimer_start(&vcpu->arch.dec_timer, dec_nsec, HRTIMER_MODE_REL);
 	vcpu->arch.timer_running = 1;
 }
@@ -2242,10 +2530,18 @@
 
 static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
 {
+	struct kvm_nested_guest *nested = vcpu->arch.nested;
+	cpumask_t *cpu_in_guest;
 	int i;
 
 	cpu = cpu_first_thread_sibling(cpu);
-	cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush);
+	if (nested) {
+		cpumask_set_cpu(cpu, &nested->need_tlb_flush);
+		cpu_in_guest = &nested->cpu_in_guest;
+	} else {
+		cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush);
+		cpu_in_guest = &kvm->arch.cpu_in_guest;
+	}
 	/*
 	 * Make sure setting of bit in need_tlb_flush precedes
 	 * testing of cpu_in_guest bits.  The matching barrier on
@@ -2253,13 +2549,23 @@
 	 */
 	smp_mb();
 	for (i = 0; i < threads_per_core; ++i)
-		if (cpumask_test_cpu(cpu + i, &kvm->arch.cpu_in_guest))
+		if (cpumask_test_cpu(cpu + i, cpu_in_guest))
 			smp_call_function_single(cpu + i, do_nothing, NULL, 1);
 }
 
 static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
 {
+	struct kvm_nested_guest *nested = vcpu->arch.nested;
 	struct kvm *kvm = vcpu->kvm;
+	int prev_cpu;
+
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return;
+
+	if (nested)
+		prev_cpu = nested->prev_cpu[vcpu->arch.nested_vcpu_id];
+	else
+		prev_cpu = vcpu->arch.prev_cpu;
 
 	/*
 	 * With radix, the guest can do TLB invalidations itself,
@@ -2273,12 +2579,15 @@
 	 * ran to flush the TLB.  The TLB is shared between threads,
 	 * so we use a single bit in .need_tlb_flush for all 4 threads.
 	 */
-	if (vcpu->arch.prev_cpu != pcpu) {
-		if (vcpu->arch.prev_cpu >= 0 &&
-		    cpu_first_thread_sibling(vcpu->arch.prev_cpu) !=
+	if (prev_cpu != pcpu) {
+		if (prev_cpu >= 0 &&
+		    cpu_first_thread_sibling(prev_cpu) !=
 		    cpu_first_thread_sibling(pcpu))
-			radix_flush_cpu(kvm, vcpu->arch.prev_cpu, vcpu);
-		vcpu->arch.prev_cpu = pcpu;
+			radix_flush_cpu(kvm, prev_cpu, vcpu);
+		if (nested)
+			nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu;
+		else
+			vcpu->arch.prev_cpu = pcpu;
 	}
 }
 
@@ -2493,6 +2802,10 @@
 	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
 		return false;
 
+	/* In one_vm_per_core mode, require all vcores to be from the same vm */
+	if (one_vm_per_core && vc->kvm != cip->vc[0]->kvm)
+		return false;
+
 	/* Some POWER9 chips require all threads to be in the same MMU mode */
 	if (no_mixing_hpt_and_radix &&
 	    kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm))
@@ -2557,7 +2870,7 @@
 		if (!spin_trylock(&pvc->lock))
 			continue;
 		prepare_threads(pvc);
-		if (!pvc->n_runnable) {
+		if (!pvc->n_runnable || !pvc->kvm->arch.mmu_ready) {
 			list_del_init(&pvc->preempt_list);
 			if (pvc->runner == NULL) {
 				pvc->vcore_state = VCORE_INACTIVE;
@@ -2578,15 +2891,20 @@
 	spin_unlock(&lp->lock);
 }
 
-static bool recheck_signals(struct core_info *cip)
+static bool recheck_signals_and_mmu(struct core_info *cip)
 {
 	int sub, i;
 	struct kvm_vcpu *vcpu;
+	struct kvmppc_vcore *vc;
 
-	for (sub = 0; sub < cip->n_subcores; ++sub)
-		for_each_runnable_thread(i, vcpu, cip->vc[sub])
+	for (sub = 0; sub < cip->n_subcores; ++sub) {
+		vc = cip->vc[sub];
+		if (!vc->kvm->arch.mmu_ready)
+			return true;
+		for_each_runnable_thread(i, vcpu, vc)
 			if (signal_pending(vcpu->arch.run_task))
 				return true;
+	}
 	return false;
 }
 
@@ -2600,6 +2918,14 @@
 	spin_lock(&vc->lock);
 	now = get_tb();
 	for_each_runnable_thread(i, vcpu, vc) {
+		/*
+		 * It's safe to unlock the vcore in the loop here, because
+		 * for_each_runnable_thread() is safe against removal of
+		 * the vcpu, and the vcore state is VCORE_EXITING here,
+		 * so any vcpus becoming runnable will have their arch.trap
+		 * set to zero and can't actually run in the guest.
+		 */
+		spin_unlock(&vc->lock);
 		/* cancel pending dec exception if dec is positive */
 		if (now < vcpu->arch.dec_expires &&
 		    kvmppc_core_pending_dec(vcpu))
@@ -2615,6 +2941,7 @@
 		vcpu->arch.ret = ret;
 		vcpu->arch.trap = 0;
 
+		spin_lock(&vc->lock);
 		if (is_kvmppc_resume_guest(vcpu->arch.ret)) {
 			if (vcpu->arch.pending_exceptions)
 				kvmppc_core_prepare_to_enter(vcpu);
@@ -2807,7 +3134,7 @@
 	local_irq_disable();
 	hard_irq_disable();
 	if (lazy_irq_pending() || need_resched() ||
-	    recheck_signals(&core_info) || !vc->kvm->arch.mmu_ready) {
+	    recheck_signals_and_mmu(&core_info)) {
 		local_irq_enable();
 		vc->vcore_state = VCORE_INACTIVE;
 		/* Unlock all except the primary vcore */
@@ -2962,31 +3289,11 @@
 	for (sub = 0; sub < core_info.n_subcores; ++sub)
 		spin_unlock(&core_info.vc[sub]->lock);
 
-	if (kvm_is_radix(vc->kvm)) {
-		int tmp = pcpu;
+	guest_enter_irqoff();
 
-		/*
-		 * Do we need to flush the process scoped TLB for the LPAR?
-		 *
-		 * On POWER9, individual threads can come in here, but the
-		 * TLB is shared between the 4 threads in a core, hence
-		 * invalidating on one thread invalidates for all.
-		 * Thus we make all 4 threads use the same bit here.
-		 *
-		 * Hash must be flushed in realmode in order to use tlbiel.
-		 */
-		mtspr(SPRN_LPID, vc->kvm->arch.lpid);
-		isync();
+	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
 
-		if (cpu_has_feature(CPU_FTR_ARCH_300))
-			tmp &= ~0x3UL;
-
-		if (cpumask_test_cpu(tmp, &vc->kvm->arch.need_tlb_flush)) {
-			radix__local_flush_tlb_lpid_guest(vc->kvm->arch.lpid);
-			/* Clear the bit after the TLB flush */
-			cpumask_clear_cpu(tmp, &vc->kvm->arch.need_tlb_flush);
-		}
-	}
+	this_cpu_disable_ftrace();
 
 	/*
 	 * Interrupts will be enabled once we get into the guest,
@@ -2994,19 +3301,14 @@
 	 */
 	trace_hardirqs_on();
 
-	guest_enter_irqoff();
-
-	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
-
-	this_cpu_disable_ftrace();
-
 	trap = __kvmppc_vcore_entry();
 
+	trace_hardirqs_off();
+
 	this_cpu_enable_ftrace();
 
 	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
 
-	trace_hardirqs_off();
 	set_irq_happened(trap);
 
 	spin_lock(&vc->lock);
@@ -3080,6 +3382,323 @@
 }
 
 /*
+ * Load up hypervisor-mode registers on P9.
+ */
+static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
+				     unsigned long lpcr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	s64 hdec;
+	u64 tb, purr, spurr;
+	int trap;
+	unsigned long host_hfscr = mfspr(SPRN_HFSCR);
+	unsigned long host_ciabr = mfspr(SPRN_CIABR);
+	unsigned long host_dawr = mfspr(SPRN_DAWR);
+	unsigned long host_dawrx = mfspr(SPRN_DAWRX);
+	unsigned long host_psscr = mfspr(SPRN_PSSCR);
+	unsigned long host_pidr = mfspr(SPRN_PID);
+
+	hdec = time_limit - mftb();
+	if (hdec < 0)
+		return BOOK3S_INTERRUPT_HV_DECREMENTER;
+	mtspr(SPRN_HDEC, hdec);
+
+	if (vc->tb_offset) {
+		u64 new_tb = mftb() + vc->tb_offset;
+		mtspr(SPRN_TBU40, new_tb);
+		tb = mftb();
+		if ((tb & 0xffffff) < (new_tb & 0xffffff))
+			mtspr(SPRN_TBU40, new_tb + 0x1000000);
+		vc->tb_offset_applied = vc->tb_offset;
+	}
+
+	if (vc->pcr)
+		mtspr(SPRN_PCR, vc->pcr | PCR_MASK);
+	mtspr(SPRN_DPDES, vc->dpdes);
+	mtspr(SPRN_VTB, vc->vtb);
+
+	local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR);
+	local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR);
+	mtspr(SPRN_PURR, vcpu->arch.purr);
+	mtspr(SPRN_SPURR, vcpu->arch.spurr);
+
+	if (dawr_enabled()) {
+		mtspr(SPRN_DAWR, vcpu->arch.dawr);
+		mtspr(SPRN_DAWRX, vcpu->arch.dawrx);
+	}
+	mtspr(SPRN_CIABR, vcpu->arch.ciabr);
+	mtspr(SPRN_IC, vcpu->arch.ic);
+	mtspr(SPRN_PID, vcpu->arch.pid);
+
+	mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC |
+	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
+
+	mtspr(SPRN_HFSCR, vcpu->arch.hfscr);
+
+	mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0);
+	mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1);
+	mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2);
+	mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3);
+
+	mtspr(SPRN_AMOR, ~0UL);
+
+	mtspr(SPRN_LPCR, lpcr);
+	isync();
+
+	kvmppc_xive_push_vcpu(vcpu);
+
+	mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
+	mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1);
+
+	trap = __kvmhv_vcpu_entry_p9(vcpu);
+
+	/* Advance host PURR/SPURR by the amount used by guest */
+	purr = mfspr(SPRN_PURR);
+	spurr = mfspr(SPRN_SPURR);
+	mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr +
+	      purr - vcpu->arch.purr);
+	mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr +
+	      spurr - vcpu->arch.spurr);
+	vcpu->arch.purr = purr;
+	vcpu->arch.spurr = spurr;
+
+	vcpu->arch.ic = mfspr(SPRN_IC);
+	vcpu->arch.pid = mfspr(SPRN_PID);
+	vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS;
+
+	vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0);
+	vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1);
+	vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
+	vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
+
+	/* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
+	mtspr(SPRN_PSSCR, host_psscr |
+	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
+	mtspr(SPRN_HFSCR, host_hfscr);
+	mtspr(SPRN_CIABR, host_ciabr);
+	mtspr(SPRN_DAWR, host_dawr);
+	mtspr(SPRN_DAWRX, host_dawrx);
+	mtspr(SPRN_PID, host_pidr);
+
+	/*
+	 * Since this is radix, do a eieio; tlbsync; ptesync sequence in
+	 * case we interrupted the guest between a tlbie and a ptesync.
+	 */
+	asm volatile("eieio; tlbsync; ptesync");
+
+	mtspr(SPRN_LPID, vcpu->kvm->arch.host_lpid);	/* restore host LPID */
+	isync();
+
+	vc->dpdes = mfspr(SPRN_DPDES);
+	vc->vtb = mfspr(SPRN_VTB);
+	mtspr(SPRN_DPDES, 0);
+	if (vc->pcr)
+		mtspr(SPRN_PCR, PCR_MASK);
+
+	if (vc->tb_offset_applied) {
+		u64 new_tb = mftb() - vc->tb_offset_applied;
+		mtspr(SPRN_TBU40, new_tb);
+		tb = mftb();
+		if ((tb & 0xffffff) < (new_tb & 0xffffff))
+			mtspr(SPRN_TBU40, new_tb + 0x1000000);
+		vc->tb_offset_applied = 0;
+	}
+
+	mtspr(SPRN_HDEC, 0x7fffffff);
+	mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr);
+
+	return trap;
+}
+
+/*
+ * Virtual-mode guest entry for POWER9 and later when the host and
+ * guest are both using the radix MMU.  The LPIDR has already been set.
+ */
+int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
+			 unsigned long lpcr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long host_dscr = mfspr(SPRN_DSCR);
+	unsigned long host_tidr = mfspr(SPRN_TIDR);
+	unsigned long host_iamr = mfspr(SPRN_IAMR);
+	unsigned long host_amr = mfspr(SPRN_AMR);
+	s64 dec;
+	u64 tb;
+	int trap, save_pmu;
+
+	dec = mfspr(SPRN_DEC);
+	tb = mftb();
+	if (dec < 512)
+		return BOOK3S_INTERRUPT_HV_DECREMENTER;
+	local_paca->kvm_hstate.dec_expires = dec + tb;
+	if (local_paca->kvm_hstate.dec_expires < time_limit)
+		time_limit = local_paca->kvm_hstate.dec_expires;
+
+	vcpu->arch.ceded = 0;
+
+	kvmhv_save_host_pmu();		/* saves it to PACA kvm_hstate */
+
+	kvmppc_subcore_enter_guest();
+
+	vc->entry_exit_map = 1;
+	vc->in_guest = 1;
+
+	if (vcpu->arch.vpa.pinned_addr) {
+		struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
+		u32 yield_count = be32_to_cpu(lp->yield_count) + 1;
+		lp->yield_count = cpu_to_be32(yield_count);
+		vcpu->arch.vpa.dirty = 1;
+	}
+
+	if (cpu_has_feature(CPU_FTR_TM) ||
+	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+		kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
+
+	kvmhv_load_guest_pmu(vcpu);
+
+	msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
+	load_fp_state(&vcpu->arch.fp);
+#ifdef CONFIG_ALTIVEC
+	load_vr_state(&vcpu->arch.vr);
+#endif
+	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
+
+	mtspr(SPRN_DSCR, vcpu->arch.dscr);
+	mtspr(SPRN_IAMR, vcpu->arch.iamr);
+	mtspr(SPRN_PSPB, vcpu->arch.pspb);
+	mtspr(SPRN_FSCR, vcpu->arch.fscr);
+	mtspr(SPRN_TAR, vcpu->arch.tar);
+	mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
+	mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
+	mtspr(SPRN_BESCR, vcpu->arch.bescr);
+	mtspr(SPRN_WORT, vcpu->arch.wort);
+	mtspr(SPRN_TIDR, vcpu->arch.tid);
+	mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
+	mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
+	mtspr(SPRN_AMR, vcpu->arch.amr);
+	mtspr(SPRN_UAMOR, vcpu->arch.uamor);
+
+	if (!(vcpu->arch.ctrl & 1))
+		mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
+
+	mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb());
+
+	if (kvmhv_on_pseries()) {
+		/*
+		 * We need to save and restore the guest visible part of the
+		 * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor
+		 * doesn't do this for us. Note only required if pseries since
+		 * this is done in kvmhv_load_hv_regs_and_go() below otherwise.
+		 */
+		unsigned long host_psscr;
+		/* call our hypervisor to load up HV regs and go */
+		struct hv_guest_state hvregs;
+
+		host_psscr = mfspr(SPRN_PSSCR_PR);
+		mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr);
+		kvmhv_save_hv_regs(vcpu, &hvregs);
+		hvregs.lpcr = lpcr;
+		vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
+		hvregs.version = HV_GUEST_STATE_VERSION;
+		if (vcpu->arch.nested) {
+			hvregs.lpid = vcpu->arch.nested->shadow_lpid;
+			hvregs.vcpu_token = vcpu->arch.nested_vcpu_id;
+		} else {
+			hvregs.lpid = vcpu->kvm->arch.lpid;
+			hvregs.vcpu_token = vcpu->vcpu_id;
+		}
+		hvregs.hdec_expiry = time_limit;
+		trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs),
+					  __pa(&vcpu->arch.regs));
+		kvmhv_restore_hv_return_state(vcpu, &hvregs);
+		vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
+		vcpu->arch.shregs.dar = mfspr(SPRN_DAR);
+		vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);
+		vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR);
+		mtspr(SPRN_PSSCR_PR, host_psscr);
+
+		/* H_CEDE has to be handled now, not later */
+		if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
+		    kvmppc_get_gpr(vcpu, 3) == H_CEDE) {
+			kvmppc_nested_cede(vcpu);
+			trap = 0;
+		}
+	} else {
+		trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr);
+	}
+
+	vcpu->arch.slb_max = 0;
+	dec = mfspr(SPRN_DEC);
+	if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */
+		dec = (s32) dec;
+	tb = mftb();
+	vcpu->arch.dec_expires = dec + tb;
+	vcpu->cpu = -1;
+	vcpu->arch.thread_cpu = -1;
+	vcpu->arch.ctrl = mfspr(SPRN_CTRLF);
+
+	vcpu->arch.iamr = mfspr(SPRN_IAMR);
+	vcpu->arch.pspb = mfspr(SPRN_PSPB);
+	vcpu->arch.fscr = mfspr(SPRN_FSCR);
+	vcpu->arch.tar = mfspr(SPRN_TAR);
+	vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
+	vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
+	vcpu->arch.bescr = mfspr(SPRN_BESCR);
+	vcpu->arch.wort = mfspr(SPRN_WORT);
+	vcpu->arch.tid = mfspr(SPRN_TIDR);
+	vcpu->arch.amr = mfspr(SPRN_AMR);
+	vcpu->arch.uamor = mfspr(SPRN_UAMOR);
+	vcpu->arch.dscr = mfspr(SPRN_DSCR);
+
+	mtspr(SPRN_PSPB, 0);
+	mtspr(SPRN_WORT, 0);
+	mtspr(SPRN_UAMOR, 0);
+	mtspr(SPRN_DSCR, host_dscr);
+	mtspr(SPRN_TIDR, host_tidr);
+	mtspr(SPRN_IAMR, host_iamr);
+	mtspr(SPRN_PSPB, 0);
+
+	if (host_amr != vcpu->arch.amr)
+		mtspr(SPRN_AMR, host_amr);
+
+	msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
+	store_fp_state(&vcpu->arch.fp);
+#ifdef CONFIG_ALTIVEC
+	store_vr_state(&vcpu->arch.vr);
+#endif
+	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
+
+	if (cpu_has_feature(CPU_FTR_TM) ||
+	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
+		kvmppc_save_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
+
+	save_pmu = 1;
+	if (vcpu->arch.vpa.pinned_addr) {
+		struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
+		u32 yield_count = be32_to_cpu(lp->yield_count) + 1;
+		lp->yield_count = cpu_to_be32(yield_count);
+		vcpu->arch.vpa.dirty = 1;
+		save_pmu = lp->pmcregs_in_use;
+	}
+	/* Must save pmu if this guest is capable of running nested guests */
+	save_pmu |= nesting_enabled(vcpu->kvm);
+
+	kvmhv_save_guest_pmu(vcpu, save_pmu);
+
+	vc->entry_exit_map = 0x101;
+	vc->in_guest = 0;
+
+	mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb());
+	mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
+
+	kvmhv_load_host_pmu();
+
+	kvmppc_subcore_exit_guest();
+
+	return trap;
+}
+
+/*
  * Wait for some other vcpu thread to execute us, and
  * wake us up when we need to handle something in the host.
  */
@@ -3099,11 +3718,12 @@
 
 static void grow_halt_poll_ns(struct kvmppc_vcore *vc)
 {
-	/* 10us base */
-	if (vc->halt_poll_ns == 0 && halt_poll_ns_grow)
-		vc->halt_poll_ns = 10000;
-	else
-		vc->halt_poll_ns *= halt_poll_ns_grow;
+	if (!halt_poll_ns_grow)
+		return;
+
+	vc->halt_poll_ns *= halt_poll_ns_grow;
+	if (vc->halt_poll_ns < halt_poll_ns_grow_start)
+		vc->halt_poll_ns = halt_poll_ns_grow_start;
 }
 
 static void shrink_halt_poll_ns(struct kvmppc_vcore *vc)
@@ -3117,7 +3737,7 @@
 #ifdef CONFIG_KVM_XICS
 static inline bool xive_interrupt_pending(struct kvm_vcpu *vcpu)
 {
-	if (!xive_enabled())
+	if (!xics_on_xive())
 		return false;
 	return vcpu->arch.irq_pending || vcpu->arch.xive_saved_state.pipr <
 		vcpu->arch.xive_saved_state.cppr;
@@ -3256,12 +3876,17 @@
 	trace_kvmppc_vcore_wakeup(do_sleep, block_ns);
 }
 
+/*
+ * This never fails for a radix guest, as none of the operations it does
+ * for a radix guest can fail or have a way to report failure.
+ * kvmhv_run_single_vcpu() relies on this fact.
+ */
 static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu)
 {
 	int r = 0;
 	struct kvm *kvm = vcpu->kvm;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	if (!kvm->arch.mmu_ready) {
 		if (!kvm_is_radix(kvm))
 			r = kvmppc_hv_setup_htab_rma(vcpu);
@@ -3271,7 +3896,7 @@
 			kvm->arch.mmu_ready = 1;
 		}
 	}
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return r;
 }
 
@@ -3405,6 +4030,185 @@
 	return vcpu->arch.ret;
 }
 
+int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
+			  struct kvm_vcpu *vcpu, u64 time_limit,
+			  unsigned long lpcr)
+{
+	int trap, r, pcpu;
+	int srcu_idx, lpid;
+	struct kvmppc_vcore *vc;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *nested = vcpu->arch.nested;
+
+	trace_kvmppc_run_vcpu_enter(vcpu);
+
+	kvm_run->exit_reason = 0;
+	vcpu->arch.ret = RESUME_GUEST;
+	vcpu->arch.trap = 0;
+
+	vc = vcpu->arch.vcore;
+	vcpu->arch.ceded = 0;
+	vcpu->arch.run_task = current;
+	vcpu->arch.kvm_run = kvm_run;
+	vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb());
+	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
+	vcpu->arch.busy_preempt = TB_NIL;
+	vcpu->arch.last_inst = KVM_INST_FETCH_FAILED;
+	vc->runnable_threads[0] = vcpu;
+	vc->n_runnable = 1;
+	vc->runner = vcpu;
+
+	/* See if the MMU is ready to go */
+	if (!kvm->arch.mmu_ready)
+		kvmhv_setup_mmu(vcpu);
+
+	if (need_resched())
+		cond_resched();
+
+	kvmppc_update_vpas(vcpu);
+
+	init_vcore_to_run(vc);
+	vc->preempt_tb = TB_NIL;
+
+	preempt_disable();
+	pcpu = smp_processor_id();
+	vc->pcpu = pcpu;
+	kvmppc_prepare_radix_vcpu(vcpu, pcpu);
+
+	local_irq_disable();
+	hard_irq_disable();
+	if (signal_pending(current))
+		goto sigpend;
+	if (lazy_irq_pending() || need_resched() || !kvm->arch.mmu_ready)
+		goto out;
+
+	if (!nested) {
+		kvmppc_core_prepare_to_enter(vcpu);
+		if (vcpu->arch.doorbell_request) {
+			vc->dpdes = 1;
+			smp_wmb();
+			vcpu->arch.doorbell_request = 0;
+		}
+		if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
+			     &vcpu->arch.pending_exceptions))
+			lpcr |= LPCR_MER;
+	} else if (vcpu->arch.pending_exceptions ||
+		   vcpu->arch.doorbell_request ||
+		   xive_interrupt_pending(vcpu)) {
+		vcpu->arch.ret = RESUME_HOST;
+		goto out;
+	}
+
+	kvmppc_clear_host_core(pcpu);
+
+	local_paca->kvm_hstate.tid = 0;
+	local_paca->kvm_hstate.napping = 0;
+	local_paca->kvm_hstate.kvm_split_mode = NULL;
+	kvmppc_start_thread(vcpu, vc);
+	kvmppc_create_dtl_entry(vcpu, vc);
+	trace_kvm_guest_enter(vcpu);
+
+	vc->vcore_state = VCORE_RUNNING;
+	trace_kvmppc_run_core(vc, 0);
+
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
+		mtspr(SPRN_LPID, lpid);
+		isync();
+		kvmppc_check_need_tlb_flush(kvm, pcpu, nested);
+	}
+
+	guest_enter_irqoff();
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	this_cpu_disable_ftrace();
+
+	/* Tell lockdep that we're about to enable interrupts */
+	trace_hardirqs_on();
+
+	trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr);
+	vcpu->arch.trap = trap;
+
+	trace_hardirqs_off();
+
+	this_cpu_enable_ftrace();
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		mtspr(SPRN_LPID, kvm->arch.host_lpid);
+		isync();
+	}
+
+	set_irq_happened(trap);
+
+	kvmppc_set_host_core(pcpu);
+
+	local_irq_enable();
+	guest_exit();
+
+	cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest);
+
+	preempt_enable();
+
+	/*
+	 * cancel pending decrementer exception if DEC is now positive, or if
+	 * entering a nested guest in which case the decrementer is now owned
+	 * by L2 and the L1 decrementer is provided in hdec_expires
+	 */
+	if (kvmppc_core_pending_dec(vcpu) &&
+			((get_tb() < vcpu->arch.dec_expires) ||
+			 (trap == BOOK3S_INTERRUPT_SYSCALL &&
+			  kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED)))
+		kvmppc_core_dequeue_dec(vcpu);
+
+	trace_kvm_guest_exit(vcpu);
+	r = RESUME_GUEST;
+	if (trap) {
+		if (!nested)
+			r = kvmppc_handle_exit_hv(kvm_run, vcpu, current);
+		else
+			r = kvmppc_handle_nested_exit(kvm_run, vcpu);
+	}
+	vcpu->arch.ret = r;
+
+	if (is_kvmppc_resume_guest(r) && vcpu->arch.ceded &&
+	    !kvmppc_vcpu_woken(vcpu)) {
+		kvmppc_set_timer(vcpu);
+		while (vcpu->arch.ceded && !kvmppc_vcpu_woken(vcpu)) {
+			if (signal_pending(current)) {
+				vcpu->stat.signal_exits++;
+				kvm_run->exit_reason = KVM_EXIT_INTR;
+				vcpu->arch.ret = -EINTR;
+				break;
+			}
+			spin_lock(&vc->lock);
+			kvmppc_vcore_blocked(vc);
+			spin_unlock(&vc->lock);
+		}
+	}
+	vcpu->arch.ceded = 0;
+
+	vc->vcore_state = VCORE_INACTIVE;
+	trace_kvmppc_run_core(vc, 1);
+
+ done:
+	kvmppc_remove_runnable(vc, vcpu);
+	trace_kvmppc_run_vcpu_exit(vcpu, kvm_run);
+
+	return vcpu->arch.ret;
+
+ sigpend:
+	vcpu->stat.signal_exits++;
+	kvm_run->exit_reason = KVM_EXIT_INTR;
+	vcpu->arch.ret = -EINTR;
+ out:
+	local_irq_enable();
+	preempt_enable();
+	goto done;
+}
+
 static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -3480,7 +4284,20 @@
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 
 	do {
-		r = kvmppc_run_vcpu(run, vcpu);
+		/*
+		 * The early POWER9 chips that can't mix radix and HPT threads
+		 * on the same core also need the workaround for the problem
+		 * where the TLB would prefetch entries in the guest exit path
+		 * for radix guests using the guest PIDR value and LPID 0.
+		 * The workaround is in the old path (kvmppc_run_vcpu())
+		 * but not the new path (kvmhv_run_single_vcpu()).
+		 */
+		if (kvm->arch.threads_indep && kvm_is_radix(kvm) &&
+		    !no_mixing_hpt_and_radix)
+			r = kvmhv_run_single_vcpu(run, vcpu, ~(u64)0,
+						  vcpu->arch.vcore->lpcr);
+		else
+			r = kvmppc_run_vcpu(run, vcpu);
 
 		if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
 		    !(vcpu->arch.shregs.msr & MSR_PR)) {
@@ -3494,7 +4311,7 @@
 				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
 			srcu_read_unlock(&kvm->srcu, srcu_idx);
 		} else if (r == RESUME_PASSTHROUGH) {
-			if (WARN_ON(xive_enabled()))
+			if (WARN_ON(xics_on_xive()))
 				r = H_SUCCESS;
 			else
 				r = kvmppc_xics_rm_complete(vcpu, 0);
@@ -3559,6 +4376,10 @@
 	kvmppc_add_seg_page_size(&sps, 16, SLB_VSID_L | SLB_VSID_LP_01);
 	kvmppc_add_seg_page_size(&sps, 24, SLB_VSID_L);
 
+	/* If running as a nested hypervisor, we don't support HPT guests */
+	if (kvmhv_on_pseries())
+		info->flags |= KVM_PPC_NO_HASH;
+
 	return 0;
 }
 
@@ -3660,7 +4481,8 @@
 static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
 
@@ -3672,11 +4494,29 @@
 	 */
 	if (npages)
 		atomic64_inc(&kvm->arch.mmio_update);
+
+	/*
+	 * For change == KVM_MR_MOVE or KVM_MR_DELETE, higher levels
+	 * have already called kvm_arch_flush_shadow_memslot() to
+	 * flush shadow mappings.  For KVM_MR_CREATE we have no
+	 * previous mappings.  So the only case to handle is
+	 * KVM_MR_FLAGS_ONLY when the KVM_MEM_LOG_DIRTY_PAGES bit
+	 * has been changed.
+	 * For radix guests, we flush on setting KVM_MEM_LOG_DIRTY_PAGES
+	 * to get rid of any THP PTEs in the partition-scoped page tables
+	 * so we can track dirtiness at the page level; we flush when
+	 * clearing KVM_MEM_LOG_DIRTY_PAGES so that we can go back to
+	 * using THP PTEs.
+	 */
+	if (change == KVM_MR_FLAGS_ONLY && kvm_is_radix(kvm) &&
+	    ((new->flags ^ old->flags) & KVM_MEM_LOG_DIRTY_PAGES))
+		kvmppc_radix_flush_memslot(kvm, old);
 }
 
 /*
  * Update LPCR values in kvm->arch and in vcores.
- * Caller must hold kvm->lock.
+ * Caller must hold kvm->arch.mmu_setup_lock (for mutual exclusion
+ * of kvm->arch.lpcr update).
  */
 void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
 {
@@ -3723,13 +4563,12 @@
 			__pa(kvm->arch.pgtable) | RADIX_PGD_INDEX_SIZE;
 		dw1 = PATB_GR | kvm->arch.process_table;
 	}
-
-	mmu_partition_table_set_entry(kvm->arch.lpid, dw0, dw1);
+	kvmhv_set_ptbl_entry(kvm->arch.lpid, dw0, dw1);
 }
 
 /*
  * Set up HPT (hashed page table) and RMA (real-mode area).
- * Must be called with kvm->lock held.
+ * Must be called with kvm->arch.mmu_setup_lock held.
  */
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
@@ -3817,19 +4656,30 @@
 	goto out_srcu;
 }
 
-/* Must be called with kvm->lock held and mmu_ready = 0 and no vcpus running */
+/*
+ * Must be called with kvm->arch.mmu_setup_lock held and
+ * mmu_ready = 0 and no vcpus running.
+ */
 int kvmppc_switch_mmu_to_hpt(struct kvm *kvm)
 {
+	if (nesting_enabled(kvm))
+		kvmhv_release_all_nested(kvm);
+	kvmppc_rmap_reset(kvm);
+	kvm->arch.process_table = 0;
+	/* Mutual exclusion with kvm_unmap_hva_range etc. */
+	spin_lock(&kvm->mmu_lock);
+	kvm->arch.radix = 0;
+	spin_unlock(&kvm->mmu_lock);
 	kvmppc_free_radix(kvm);
 	kvmppc_update_lpcr(kvm, LPCR_VPM1,
 			   LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR);
-	kvmppc_rmap_reset(kvm);
-	kvm->arch.radix = 0;
-	kvm->arch.process_table = 0;
 	return 0;
 }
 
-/* Must be called with kvm->lock held and mmu_ready = 0 and no vcpus running */
+/*
+ * Must be called with kvm->arch.mmu_setup_lock held and
+ * mmu_ready = 0 and no vcpus running.
+ */
 int kvmppc_switch_mmu_to_radix(struct kvm *kvm)
 {
 	int err;
@@ -3837,11 +4687,14 @@
 	err = kvmppc_init_vm_radix(kvm);
 	if (err)
 		return err;
-
+	kvmppc_rmap_reset(kvm);
+	/* Mutual exclusion with kvm_unmap_hva_range etc. */
+	spin_lock(&kvm->mmu_lock);
+	kvm->arch.radix = 1;
+	spin_unlock(&kvm->mmu_lock);
 	kvmppc_free_hpt(&kvm->arch.hpt);
 	kvmppc_update_lpcr(kvm, LPCR_UPRT | LPCR_GTSE | LPCR_HR,
 			   LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR);
-	kvm->arch.radix = 1;
 	return 0;
 }
 
@@ -3931,6 +4784,8 @@
 	char buf[32];
 	int ret;
 
+	mutex_init(&kvm->arch.mmu_setup_lock);
+
 	/* Allocate the guest's logical partition ID */
 
 	lpid = kvmppc_alloc_lpid();
@@ -3940,6 +4795,8 @@
 
 	kvmppc_alloc_host_rm_ops();
 
+	kvmhv_vm_nested_init(kvm);
+
 	/*
 	 * Since we don't flush the TLB when tearing down a VM,
 	 * and this lpid might have previously been used,
@@ -3958,9 +4815,13 @@
 		kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
 
 	/* Init LPCR for virtual RMA mode */
-	kvm->arch.host_lpid = mfspr(SPRN_LPID);
-	kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
-	lpcr &= LPCR_PECE | LPCR_LPES;
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		kvm->arch.host_lpid = mfspr(SPRN_LPID);
+		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
+		lpcr &= LPCR_PECE | LPCR_LPES;
+	} else {
+		lpcr = 0;
+	}
 	lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
 		LPCR_VPM0 | LPCR_VPM1;
 	kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
@@ -3983,7 +4844,7 @@
 		 * If xive is enabled, we route 0x500 interrupts directly
 		 * to the guest.
 		 */
-		if (xive_enabled())
+		if (xics_on_xive())
 			lpcr |= LPCR_LPES;
 	}
 
@@ -4027,8 +4888,14 @@
 	 * On POWER9, we only need to do this if the "indep_threads_mode"
 	 * module parameter has been set to N.
 	 */
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		kvm->arch.threads_indep = indep_threads_mode;
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (!indep_threads_mode && !cpu_has_feature(CPU_FTR_HVMODE)) {
+			pr_warn("KVM: Ignoring indep_threads_mode=N in nested hypervisor\n");
+			kvm->arch.threads_indep = true;
+		} else {
+			kvm->arch.threads_indep = indep_threads_mode;
+		}
+	}
 	if (!kvm->arch.threads_indep)
 		kvm_hv_vm_activated();
 
@@ -4051,6 +4918,8 @@
 	snprintf(buf, sizeof(buf), "vm%d", current->pid);
 	kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir);
 	kvmppc_mmu_debugfs_init(kvm);
+	if (radix_enabled())
+		kvmhv_radix_debugfs_init(kvm);
 
 	return 0;
 }
@@ -4073,13 +4942,21 @@
 
 	kvmppc_free_vcores(kvm);
 
-	kvmppc_free_lpid(kvm->arch.lpid);
 
 	if (kvm_is_radix(kvm))
 		kvmppc_free_radix(kvm);
 	else
 		kvmppc_free_hpt(&kvm->arch.hpt);
 
+	/* Perform global invalidation and return lpid to the pool */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (nesting_enabled(kvm))
+			kvmhv_release_all_nested(kvm);
+		kvm->arch.process_table = 0;
+		kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
+	}
+	kvmppc_free_lpid(kvm->arch.lpid);
+
 	kvmppc_free_pimap(kvm);
 }
 
@@ -4104,11 +4981,15 @@
 
 static int kvmppc_core_check_processor_compat_hv(void)
 {
-	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
-	    !cpu_has_feature(CPU_FTR_ARCH_206))
-		return -EIO;
+	if (cpu_has_feature(CPU_FTR_HVMODE) &&
+	    cpu_has_feature(CPU_FTR_ARCH_206))
+		return 0;
 
-	return 0;
+	/* POWER9 in radix mode is capable of being a nested hypervisor. */
+	if (cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled())
+		return 0;
+
+	return -EIO;
 }
 
 #ifdef CONFIG_KVM_XICS
@@ -4199,7 +5080,7 @@
 	if (i == pimap->n_mapped)
 		pimap->n_mapped++;
 
-	if (xive_enabled())
+	if (xics_on_xive())
 		rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc);
 	else
 		kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
@@ -4240,7 +5121,7 @@
 		return -ENODEV;
 	}
 
-	if (xive_enabled())
+	if (xics_on_xive())
 		rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, pimap->mapped[i].desc);
 	else
 		kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
@@ -4426,7 +5307,11 @@
 	if (radix && !radix_enabled())
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	/* If we're a nested hypervisor, we currently only support radix */
+	if (kvmhv_on_pseries() && !radix)
+		return -EINVAL;
+
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	if (radix != kvm_is_radix(kvm)) {
 		if (kvm->arch.mmu_ready) {
 			kvm->arch.mmu_ready = 0;
@@ -4454,10 +5339,61 @@
 	err = 0;
 
  out_unlock:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return err;
 }
 
+static int kvmhv_enable_nested(struct kvm *kvm)
+{
+	if (!nested)
+		return -EPERM;
+	if (!cpu_has_feature(CPU_FTR_ARCH_300) || no_mixing_hpt_and_radix)
+		return -ENODEV;
+
+	/* kvm == NULL means the caller is testing if the capability exists */
+	if (kvm)
+		kvm->arch.nested_enable = true;
+	return 0;
+}
+
+static int kvmhv_load_from_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
+				 int size)
+{
+	int rc = -EINVAL;
+
+	if (kvmhv_vcpu_is_radix(vcpu)) {
+		rc = kvmhv_copy_from_guest_radix(vcpu, *eaddr, ptr, size);
+
+		if (rc > 0)
+			rc = -EINVAL;
+	}
+
+	/* For now quadrants are the only way to access nested guest memory */
+	if (rc && vcpu->arch.nested)
+		rc = -EAGAIN;
+
+	return rc;
+}
+
+static int kvmhv_store_to_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
+				int size)
+{
+	int rc = -EINVAL;
+
+	if (kvmhv_vcpu_is_radix(vcpu)) {
+		rc = kvmhv_copy_to_guest_radix(vcpu, *eaddr, ptr, size);
+
+		if (rc > 0)
+			rc = -EINVAL;
+	}
+
+	/* For now quadrants are the only way to access nested guest memory */
+	if (rc && vcpu->arch.nested)
+		rc = -EAGAIN;
+
+	return rc;
+}
+
 static struct kvmppc_ops kvm_ops_hv = {
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
@@ -4497,6 +5433,9 @@
 	.configure_mmu = kvmhv_configure_mmu,
 	.get_rmmu_info = kvmhv_get_rmmu_info,
 	.set_smt_mode = kvmhv_set_smt_mode,
+	.enable_nested = kvmhv_enable_nested,
+	.load_from_eaddr = kvmhv_load_from_eaddr,
+	.store_to_eaddr = kvmhv_store_to_eaddr,
 };
 
 static int kvm_init_subcore_bitmap(void)
@@ -4514,13 +5453,11 @@
 			continue;
 
 		sibling_subcore_state =
-			kmalloc_node(sizeof(struct sibling_subcore_state),
+			kzalloc_node(sizeof(struct sibling_subcore_state),
 							GFP_KERNEL, node);
 		if (!sibling_subcore_state)
 			return -ENOMEM;
 
-		memset(sibling_subcore_state, 0,
-				sizeof(struct sibling_subcore_state));
 
 		for (j = 0; j < threads_per_core; j++) {
 			int cpu = first_cpu + j;
@@ -4540,6 +5477,12 @@
 static int kvmppc_book3s_init_hv(void)
 {
 	int r;
+
+	if (!tlbie_capable) {
+		pr_err("KVM-HV: Host does not support TLBIE\n");
+		return -ENODEV;
+	}
+
 	/*
 	 * FIXME!! Do we need to check on all cpus ?
 	 */
@@ -4547,6 +5490,10 @@
 	if (r < 0)
 		return -ENODEV;
 
+	r = kvmhv_nested_init();
+	if (r)
+		return r;
+
 	r = kvm_init_subcore_bitmap();
 	if (r)
 		return r;
@@ -4557,7 +5504,8 @@
 	 * indirectly, via OPAL.
 	 */
 #ifdef CONFIG_SMP
-	if (!xive_enabled() && !local_paca->kvm_hstate.xics_phys) {
+	if (!xics_on_xive() && !kvmhv_on_pseries() &&
+	    !local_paca->kvm_hstate.xics_phys) {
 		struct device_node *np;
 
 		np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
@@ -4605,6 +5553,7 @@
 	if (kvmppc_radix_possible())
 		kvmppc_radix_exit();
 	kvmppc_hv_ops = NULL;
+	kvmhv_nested_exit();
 }
 
 module_init(kvmppc_book3s_init_hv);
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index fc6bb96..7c19096 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/cpu.h>
@@ -231,6 +228,15 @@
 	void __iomem *xics_phys;
 	unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 
+	/* For a nested hypervisor, use the XICS via hcall */
+	if (kvmhv_on_pseries()) {
+		unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+		plpar_hcall_raw(H_IPI, retbuf, get_hard_smp_processor_id(cpu),
+				IPI_PRIORITY);
+		return;
+	}
+
 	/* On POWER9 we can use msgsnd for any destination cpu. */
 	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
 		msg |= get_hard_smp_processor_id(cpu);
@@ -248,7 +254,7 @@
 	}
 
 	/* We should never reach this */
-	if (WARN_ON_ONCE(xive_enabled()))
+	if (WARN_ON_ONCE(xics_on_xive()))
 	    return;
 
 	/* Else poke the target with an IPI */
@@ -460,12 +466,19 @@
 		return 1;
 
 	/* Now read the interrupt from the ICP */
-	xics_phys = local_paca->kvm_hstate.xics_phys;
-	rc = 0;
-	if (!xics_phys)
-		rc = opal_int_get_xirr(&xirr, false);
-	else
-		xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
+	if (kvmhv_on_pseries()) {
+		unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+		rc = plpar_hcall_raw(H_XIRR, retbuf, 0xFF);
+		xirr = cpu_to_be32(retbuf[0]);
+	} else {
+		xics_phys = local_paca->kvm_hstate.xics_phys;
+		rc = 0;
+		if (!xics_phys)
+			rc = opal_int_get_xirr(&xirr, false);
+		else
+			xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
+	}
 	if (rc < 0)
 		return 1;
 
@@ -494,7 +507,13 @@
 	 */
 	if (xisr == XICS_IPI) {
 		rc = 0;
-		if (xics_phys) {
+		if (kvmhv_on_pseries()) {
+			unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+			plpar_hcall_raw(H_IPI, retbuf,
+					hard_smp_processor_id(), 0xff);
+			plpar_hcall_raw(H_EOI, retbuf, h_xirr);
+		} else if (xics_phys) {
 			__raw_rm_writeb(0xff, xics_phys + XICS_MFRR);
 			__raw_rm_writel(xirr, xics_phys + XICS_XIRR);
 		} else {
@@ -520,7 +539,13 @@
 			/* We raced with the host,
 			 * we need to resend that IPI, bummer
 			 */
-			if (xics_phys)
+			if (kvmhv_on_pseries()) {
+				unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+				plpar_hcall_raw(H_IPI, retbuf,
+						hard_smp_processor_id(),
+						IPI_PRIORITY);
+			} else if (xics_phys)
 				__raw_rm_writeb(IPI_PRIORITY,
 						xics_phys + XICS_MFRR);
 			else
@@ -549,7 +574,7 @@
 {
 	if (!kvmppc_xics_enabled(vcpu))
 		return H_TOO_HARD;
-	if (xive_enabled()) {
+	if (xics_on_xive()) {
 		if (is_rm())
 			return xive_rm_h_xirr(vcpu);
 		if (unlikely(!__xive_vm_h_xirr))
@@ -564,7 +589,7 @@
 	if (!kvmppc_xics_enabled(vcpu))
 		return H_TOO_HARD;
 	vcpu->arch.regs.gpr[5] = get_tb();
-	if (xive_enabled()) {
+	if (xics_on_xive()) {
 		if (is_rm())
 			return xive_rm_h_xirr(vcpu);
 		if (unlikely(!__xive_vm_h_xirr))
@@ -578,7 +603,7 @@
 {
 	if (!kvmppc_xics_enabled(vcpu))
 		return H_TOO_HARD;
-	if (xive_enabled()) {
+	if (xics_on_xive()) {
 		if (is_rm())
 			return xive_rm_h_ipoll(vcpu, server);
 		if (unlikely(!__xive_vm_h_ipoll))
@@ -593,7 +618,7 @@
 {
 	if (!kvmppc_xics_enabled(vcpu))
 		return H_TOO_HARD;
-	if (xive_enabled()) {
+	if (xics_on_xive()) {
 		if (is_rm())
 			return xive_rm_h_ipi(vcpu, server, mfrr);
 		if (unlikely(!__xive_vm_h_ipi))
@@ -607,7 +632,7 @@
 {
 	if (!kvmppc_xics_enabled(vcpu))
 		return H_TOO_HARD;
-	if (xive_enabled()) {
+	if (xics_on_xive()) {
 		if (is_rm())
 			return xive_rm_h_cppr(vcpu, cppr);
 		if (unlikely(!__xive_vm_h_cppr))
@@ -621,7 +646,7 @@
 {
 	if (!kvmppc_xics_enabled(vcpu))
 		return H_TOO_HARD;
-	if (xive_enabled()) {
+	if (xics_on_xive()) {
 		if (is_rm())
 			return xive_rm_h_eoi(vcpu, xirr);
 		if (unlikely(!__xive_vm_h_eoi))
@@ -729,3 +754,111 @@
 	smp_mb();
 	local_paca->kvm_hstate.kvm_split_mode = NULL;
 }
+
+/*
+ * Is there a PRIV_DOORBELL pending for the guest (on POWER9)?
+ * Can we inject a Decrementer or a External interrupt?
+ */
+void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
+{
+	int ext;
+	unsigned long vec = 0;
+	unsigned long lpcr;
+
+	/* Insert EXTERNAL bit into LPCR at the MER bit position */
+	ext = (vcpu->arch.pending_exceptions >> BOOK3S_IRQPRIO_EXTERNAL) & 1;
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |= ext << LPCR_MER_SH;
+	mtspr(SPRN_LPCR, lpcr);
+	isync();
+
+	if (vcpu->arch.shregs.msr & MSR_EE) {
+		if (ext) {
+			vec = BOOK3S_INTERRUPT_EXTERNAL;
+		} else {
+			long int dec = mfspr(SPRN_DEC);
+			if (!(lpcr & LPCR_LD))
+				dec = (int) dec;
+			if (dec < 0)
+				vec = BOOK3S_INTERRUPT_DECREMENTER;
+		}
+	}
+	if (vec) {
+		unsigned long msr, old_msr = vcpu->arch.shregs.msr;
+
+		kvmppc_set_srr0(vcpu, kvmppc_get_pc(vcpu));
+		kvmppc_set_srr1(vcpu, old_msr);
+		kvmppc_set_pc(vcpu, vec);
+		msr = vcpu->arch.intr_msr;
+		if (MSR_TM_ACTIVE(old_msr))
+			msr |= MSR_TS_S;
+		vcpu->arch.shregs.msr = msr;
+	}
+
+	if (vcpu->arch.doorbell_request) {
+		mtspr(SPRN_DPDES, 1);
+		vcpu->arch.vcore->dpdes = 1;
+		smp_wmb();
+		vcpu->arch.doorbell_request = 0;
+	}
+}
+
+static void flush_guest_tlb(struct kvm *kvm)
+{
+	unsigned long rb, set;
+
+	rb = PPC_BIT(52);	/* IS = 2 */
+	if (kvm_is_radix(kvm)) {
+		/* R=1 PRS=1 RIC=2 */
+		asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+			     : : "r" (rb), "i" (1), "i" (1), "i" (2),
+			       "r" (0) : "memory");
+		for (set = 1; set < kvm->arch.tlb_sets; ++set) {
+			rb += PPC_BIT(51);	/* increment set number */
+			/* R=1 PRS=1 RIC=0 */
+			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+				     : : "r" (rb), "i" (1), "i" (1), "i" (0),
+				       "r" (0) : "memory");
+		}
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory");
+	} else {
+		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
+			/* R=0 PRS=0 RIC=0 */
+			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+				     : : "r" (rb), "i" (0), "i" (0), "i" (0),
+				       "r" (0) : "memory");
+			rb += PPC_BIT(51);	/* increment set number */
+		}
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
+	}
+}
+
+void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
+				 struct kvm_nested_guest *nested)
+{
+	cpumask_t *need_tlb_flush;
+
+	/*
+	 * On POWER9, individual threads can come in here, but the
+	 * TLB is shared between the 4 threads in a core, hence
+	 * invalidating on one thread invalidates for all.
+	 * Thus we make all 4 threads use the same bit.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		pcpu = cpu_first_thread_sibling(pcpu);
+
+	if (nested)
+		need_tlb_flush = &nested->need_tlb_flush;
+	else
+		need_tlb_flush = &kvm->arch.need_tlb_flush;
+
+	if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
+		flush_guest_tlb(kvm);
+
+		/* Clear the bit after the TLB flush */
+		cpumask_clear_cpu(pcpu, need_tlb_flush);
+	}
+}
+EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush);
diff --git a/arch/powerpc/kvm/book3s_hv_hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c
index e3f738e..9af6604 100644
--- a/arch/powerpc/kvm/book3s_hv_hmi.c
+++ b/arch/powerpc/kvm/book3s_hv_hmi.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Hypervisor Maintenance Interrupt (HMI) handling.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.
- *
  * Copyright 2015 IBM Corporation
  * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
  */
@@ -24,6 +12,7 @@
 #include <linux/compiler.h>
 #include <asm/paca.h>
 #include <asm/hmi.h>
+#include <asm/processor.h>
 
 void wait_for_subcore_guest_exit(void)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 666b91c..63fd81f 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
@@ -64,52 +53,7 @@
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 	/* Save host PMU registers */
-BEGIN_FTR_SECTION
-	/* Work around P8 PMAE bug */
-	li	r3, -1
-	clrrdi	r3, r3, 10
-	mfspr	r8, SPRN_MMCR2
-	mtspr	SPRN_MMCR2, r3		/* freeze all counters using MMCR2 */
-	isync
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	li	r3, 1
-	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
-	mfspr	r7, SPRN_MMCR0		/* save MMCR0 */
-	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable interrupts */
-	mfspr	r6, SPRN_MMCRA
-	/* Clear MMCRA in order to disable SDAR updates */
-	li	r5, 0
-	mtspr	SPRN_MMCRA, r5
-	isync
-	lbz	r5, PACA_PMCINUSE(r13)	/* is the host using the PMU? */
-	cmpwi	r5, 0
-	beq	31f			/* skip if not */
-	mfspr	r5, SPRN_MMCR1
-	mfspr	r9, SPRN_SIAR
-	mfspr	r10, SPRN_SDAR
-	std	r7, HSTATE_MMCR0(r13)
-	std	r5, HSTATE_MMCR1(r13)
-	std	r6, HSTATE_MMCRA(r13)
-	std	r9, HSTATE_SIAR(r13)
-	std	r10, HSTATE_SDAR(r13)
-BEGIN_FTR_SECTION
-	mfspr	r9, SPRN_SIER
-	std	r8, HSTATE_MMCR2(r13)
-	std	r9, HSTATE_SIER(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	mfspr	r3, SPRN_PMC1
-	mfspr	r5, SPRN_PMC2
-	mfspr	r6, SPRN_PMC3
-	mfspr	r7, SPRN_PMC4
-	mfspr	r8, SPRN_PMC5
-	mfspr	r9, SPRN_PMC6
-	stw	r3, HSTATE_PMC1(r13)
-	stw	r5, HSTATE_PMC2(r13)
-	stw	r6, HSTATE_PMC3(r13)
-	stw	r7, HSTATE_PMC4(r13)
-	stw	r8, HSTATE_PMC5(r13)
-	stw	r9, HSTATE_PMC6(r13)
-31:
+	bl	kvmhv_save_host_pmu
 
 	/*
 	 * Put whatever is in the decrementer into the
@@ -161,3 +105,51 @@
 	ld	r0, PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr
+
+_GLOBAL(kvmhv_save_host_pmu)
+BEGIN_FTR_SECTION
+	/* Work around P8 PMAE bug */
+	li	r3, -1
+	clrrdi	r3, r3, 10
+	mfspr	r8, SPRN_MMCR2
+	mtspr	SPRN_MMCR2, r3		/* freeze all counters using MMCR2 */
+	isync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mfspr	r7, SPRN_MMCR0		/* save MMCR0 */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable interrupts */
+	mfspr	r6, SPRN_MMCRA
+	/* Clear MMCRA in order to disable SDAR updates */
+	li	r5, 0
+	mtspr	SPRN_MMCRA, r5
+	isync
+	lbz	r5, PACA_PMCINUSE(r13)	/* is the host using the PMU? */
+	cmpwi	r5, 0
+	beq	31f			/* skip if not */
+	mfspr	r5, SPRN_MMCR1
+	mfspr	r9, SPRN_SIAR
+	mfspr	r10, SPRN_SDAR
+	std	r7, HSTATE_MMCR0(r13)
+	std	r5, HSTATE_MMCR1(r13)
+	std	r6, HSTATE_MMCRA(r13)
+	std	r9, HSTATE_SIAR(r13)
+	std	r10, HSTATE_SDAR(r13)
+BEGIN_FTR_SECTION
+	mfspr	r9, SPRN_SIER
+	std	r8, HSTATE_MMCR2(r13)
+	std	r9, HSTATE_SIER(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	mfspr	r3, SPRN_PMC1
+	mfspr	r5, SPRN_PMC2
+	mfspr	r6, SPRN_PMC3
+	mfspr	r7, SPRN_PMC4
+	mfspr	r8, SPRN_PMC5
+	mfspr	r9, SPRN_PMC6
+	stw	r3, HSTATE_PMC1(r13)
+	stw	r5, HSTATE_PMC2(r13)
+	stw	r6, HSTATE_PMC3(r13)
+	stw	r7, HSTATE_PMC4(r13)
+	stw	r8, HSTATE_PMC5(r13)
+	stw	r9, HSTATE_PMC6(r13)
+31:	blr
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
new file mode 100644
index 0000000..cdf30c6
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -0,0 +1,1455 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corporation, 2018
+ * Authors Suraj Jitindar Singh <sjitindarsingh@gmail.com>
+ *	   Paul Mackerras <paulus@ozlabs.org>
+ *
+ * Description: KVM functions specific to running nested KVM-HV guests
+ * on Book3S processors (specifically POWER9 and later).
+ */
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/llist.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/pte-walk.h>
+#include <asm/reg.h>
+
+static struct patb_entry *pseries_partition_tb;
+
+static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp);
+static void kvmhv_free_memslot_nest_rmap(struct kvm_memory_slot *free);
+
+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->hfscr = vcpu->arch.hfscr;
+	hr->tb_offset = vc->tb_offset;
+	hr->dawr0 = vcpu->arch.dawr;
+	hr->dawrx0 = vcpu->arch.dawrx;
+	hr->ciabr = vcpu->arch.ciabr;
+	hr->purr = vcpu->arch.purr;
+	hr->spurr = vcpu->arch.spurr;
+	hr->ic = vcpu->arch.ic;
+	hr->vtb = vc->vtb;
+	hr->srr0 = vcpu->arch.shregs.srr0;
+	hr->srr1 = vcpu->arch.shregs.srr1;
+	hr->sprg[0] = vcpu->arch.shregs.sprg0;
+	hr->sprg[1] = vcpu->arch.shregs.sprg1;
+	hr->sprg[2] = vcpu->arch.shregs.sprg2;
+	hr->sprg[3] = vcpu->arch.shregs.sprg3;
+	hr->pidr = vcpu->arch.pid;
+	hr->cfar = vcpu->arch.cfar;
+	hr->ppr = vcpu->arch.ppr;
+}
+
+static void byteswap_pt_regs(struct pt_regs *regs)
+{
+	unsigned long *addr = (unsigned long *) regs;
+
+	for (; addr < ((unsigned long *) (regs + 1)); addr++)
+		*addr = swab64(*addr);
+}
+
+static void byteswap_hv_regs(struct hv_guest_state *hr)
+{
+	hr->version = swab64(hr->version);
+	hr->lpid = swab32(hr->lpid);
+	hr->vcpu_token = swab32(hr->vcpu_token);
+	hr->lpcr = swab64(hr->lpcr);
+	hr->pcr = swab64(hr->pcr) | PCR_MASK;
+	hr->amor = swab64(hr->amor);
+	hr->dpdes = swab64(hr->dpdes);
+	hr->hfscr = swab64(hr->hfscr);
+	hr->tb_offset = swab64(hr->tb_offset);
+	hr->dawr0 = swab64(hr->dawr0);
+	hr->dawrx0 = swab64(hr->dawrx0);
+	hr->ciabr = swab64(hr->ciabr);
+	hr->hdec_expiry = swab64(hr->hdec_expiry);
+	hr->purr = swab64(hr->purr);
+	hr->spurr = swab64(hr->spurr);
+	hr->ic = swab64(hr->ic);
+	hr->vtb = swab64(hr->vtb);
+	hr->hdar = swab64(hr->hdar);
+	hr->hdsisr = swab64(hr->hdsisr);
+	hr->heir = swab64(hr->heir);
+	hr->asdr = swab64(hr->asdr);
+	hr->srr0 = swab64(hr->srr0);
+	hr->srr1 = swab64(hr->srr1);
+	hr->sprg[0] = swab64(hr->sprg[0]);
+	hr->sprg[1] = swab64(hr->sprg[1]);
+	hr->sprg[2] = swab64(hr->sprg[2]);
+	hr->sprg[3] = swab64(hr->sprg[3]);
+	hr->pidr = swab64(hr->pidr);
+	hr->cfar = swab64(hr->cfar);
+	hr->ppr = swab64(hr->ppr);
+}
+
+static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
+				 struct hv_guest_state *hr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	hr->dpdes = vc->dpdes;
+	hr->hfscr = vcpu->arch.hfscr;
+	hr->purr = vcpu->arch.purr;
+	hr->spurr = vcpu->arch.spurr;
+	hr->ic = vcpu->arch.ic;
+	hr->vtb = vc->vtb;
+	hr->srr0 = vcpu->arch.shregs.srr0;
+	hr->srr1 = vcpu->arch.shregs.srr1;
+	hr->sprg[0] = vcpu->arch.shregs.sprg0;
+	hr->sprg[1] = vcpu->arch.shregs.sprg1;
+	hr->sprg[2] = vcpu->arch.shregs.sprg2;
+	hr->sprg[3] = vcpu->arch.shregs.sprg3;
+	hr->pidr = vcpu->arch.pid;
+	hr->cfar = vcpu->arch.cfar;
+	hr->ppr = vcpu->arch.ppr;
+	switch (trap) {
+	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
+		hr->hdar = vcpu->arch.fault_dar;
+		hr->hdsisr = vcpu->arch.fault_dsisr;
+		hr->asdr = vcpu->arch.fault_gpa;
+		break;
+	case BOOK3S_INTERRUPT_H_INST_STORAGE:
+		hr->asdr = vcpu->arch.fault_gpa;
+		break;
+	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
+		hr->heir = vcpu->arch.emul_inst;
+		break;
+	}
+}
+
+static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+{
+	/*
+	 * Don't let L1 enable features for L2 which we've disabled for L1,
+	 * but preserve the interrupt cause field.
+	 */
+	hr->hfscr &= (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
+
+	/* Don't let data address watchpoint match in hypervisor state */
+	hr->dawrx0 &= ~DAWRX_HYP;
+
+	/* Don't let completed instruction address breakpt match in HV state */
+	if ((hr->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+		hr->ciabr &= ~CIABR_PRIV;
+}
+
+static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	vc->pcr = hr->pcr | PCR_MASK;
+	vc->dpdes = hr->dpdes;
+	vcpu->arch.hfscr = hr->hfscr;
+	vcpu->arch.dawr = hr->dawr0;
+	vcpu->arch.dawrx = hr->dawrx0;
+	vcpu->arch.ciabr = hr->ciabr;
+	vcpu->arch.purr = hr->purr;
+	vcpu->arch.spurr = hr->spurr;
+	vcpu->arch.ic = hr->ic;
+	vc->vtb = hr->vtb;
+	vcpu->arch.shregs.srr0 = hr->srr0;
+	vcpu->arch.shregs.srr1 = hr->srr1;
+	vcpu->arch.shregs.sprg0 = hr->sprg[0];
+	vcpu->arch.shregs.sprg1 = hr->sprg[1];
+	vcpu->arch.shregs.sprg2 = hr->sprg[2];
+	vcpu->arch.shregs.sprg3 = hr->sprg[3];
+	vcpu->arch.pid = hr->pidr;
+	vcpu->arch.cfar = hr->cfar;
+	vcpu->arch.ppr = hr->ppr;
+}
+
+void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
+				   struct hv_guest_state *hr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	vc->dpdes = hr->dpdes;
+	vcpu->arch.hfscr = hr->hfscr;
+	vcpu->arch.purr = hr->purr;
+	vcpu->arch.spurr = hr->spurr;
+	vcpu->arch.ic = hr->ic;
+	vc->vtb = hr->vtb;
+	vcpu->arch.fault_dar = hr->hdar;
+	vcpu->arch.fault_dsisr = hr->hdsisr;
+	vcpu->arch.fault_gpa = hr->asdr;
+	vcpu->arch.emul_inst = hr->heir;
+	vcpu->arch.shregs.srr0 = hr->srr0;
+	vcpu->arch.shregs.srr1 = hr->srr1;
+	vcpu->arch.shregs.sprg0 = hr->sprg[0];
+	vcpu->arch.shregs.sprg1 = hr->sprg[1];
+	vcpu->arch.shregs.sprg2 = hr->sprg[2];
+	vcpu->arch.shregs.sprg3 = hr->sprg[3];
+	vcpu->arch.pid = hr->pidr;
+	vcpu->arch.cfar = hr->cfar;
+	vcpu->arch.ppr = hr->ppr;
+}
+
+static void kvmhv_nested_mmio_needed(struct kvm_vcpu *vcpu, u64 regs_ptr)
+{
+	/* No need to reflect the page fault to L1, we've handled it */
+	vcpu->arch.trap = 0;
+
+	/*
+	 * Since the L2 gprs have already been written back into L1 memory when
+	 * we complete the mmio, store the L1 memory location of the L2 gpr
+	 * being loaded into by the mmio so that the loaded value can be
+	 * written there in kvmppc_complete_mmio_load()
+	 */
+	if (((vcpu->arch.io_gpr & KVM_MMIO_REG_EXT_MASK) == KVM_MMIO_REG_GPR)
+	    && (vcpu->mmio_is_write == 0)) {
+		vcpu->arch.nested_io_gpr = (gpa_t) regs_ptr +
+					   offsetof(struct pt_regs,
+						    gpr[vcpu->arch.io_gpr]);
+		vcpu->arch.io_gpr = KVM_MMIO_REG_NESTED_GPR;
+	}
+}
+
+long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
+{
+	long int err, r;
+	struct kvm_nested_guest *l2;
+	struct pt_regs l2_regs, saved_l1_regs;
+	struct hv_guest_state l2_hv, saved_l1_hv;
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	u64 hv_ptr, regs_ptr;
+	u64 hdec_exp;
+	s64 delta_purr, delta_spurr, delta_ic, delta_vtb;
+	u64 mask;
+	unsigned long lpcr;
+
+	if (vcpu->kvm->arch.l1_ptcr == 0)
+		return H_NOT_AVAILABLE;
+
+	/* copy parameters in */
+	hv_ptr = kvmppc_get_gpr(vcpu, 4);
+	err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv,
+				  sizeof(struct hv_guest_state));
+	if (err)
+		return H_PARAMETER;
+	if (kvmppc_need_byteswap(vcpu))
+		byteswap_hv_regs(&l2_hv);
+	if (l2_hv.version != HV_GUEST_STATE_VERSION)
+		return H_P2;
+
+	regs_ptr = kvmppc_get_gpr(vcpu, 5);
+	err = kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs,
+				  sizeof(struct pt_regs));
+	if (err)
+		return H_PARAMETER;
+	if (kvmppc_need_byteswap(vcpu))
+		byteswap_pt_regs(&l2_regs);
+	if (l2_hv.vcpu_token >= NR_CPUS)
+		return H_PARAMETER;
+
+	/* translate lpid */
+	l2 = kvmhv_get_nested(vcpu->kvm, l2_hv.lpid, true);
+	if (!l2)
+		return H_PARAMETER;
+	if (!l2->l1_gr_to_hr) {
+		mutex_lock(&l2->tlb_lock);
+		kvmhv_update_ptbl_cache(l2);
+		mutex_unlock(&l2->tlb_lock);
+	}
+
+	/* save l1 values of things */
+	vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
+	saved_l1_regs = vcpu->arch.regs;
+	kvmhv_save_hv_regs(vcpu, &saved_l1_hv);
+
+	/* convert TB values/offsets to host (L0) values */
+	hdec_exp = l2_hv.hdec_expiry - vc->tb_offset;
+	vc->tb_offset += l2_hv.tb_offset;
+
+	/* set L1 state to L2 state */
+	vcpu->arch.nested = l2;
+	vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token;
+	vcpu->arch.regs = l2_regs;
+	vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
+	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
+		LPCR_LPES | LPCR_MER;
+	lpcr = (vc->lpcr & ~mask) | (l2_hv.lpcr & mask);
+	sanitise_hv_regs(vcpu, &l2_hv);
+	restore_hv_regs(vcpu, &l2_hv);
+
+	vcpu->arch.ret = RESUME_GUEST;
+	vcpu->arch.trap = 0;
+	do {
+		if (mftb() >= hdec_exp) {
+			vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER;
+			r = RESUME_HOST;
+			break;
+		}
+		r = kvmhv_run_single_vcpu(vcpu->arch.kvm_run, vcpu, hdec_exp,
+					  lpcr);
+	} while (is_kvmppc_resume_guest(r));
+
+	/* save L2 state for return */
+	l2_regs = vcpu->arch.regs;
+	l2_regs.msr = vcpu->arch.shregs.msr;
+	delta_purr = vcpu->arch.purr - l2_hv.purr;
+	delta_spurr = vcpu->arch.spurr - l2_hv.spurr;
+	delta_ic = vcpu->arch.ic - l2_hv.ic;
+	delta_vtb = vc->vtb - l2_hv.vtb;
+	save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv);
+
+	/* restore L1 state */
+	vcpu->arch.nested = NULL;
+	vcpu->arch.regs = saved_l1_regs;
+	vcpu->arch.shregs.msr = saved_l1_regs.msr & ~MSR_TS_MASK;
+	/* set L1 MSR TS field according to L2 transaction state */
+	if (l2_regs.msr & MSR_TS_MASK)
+		vcpu->arch.shregs.msr |= MSR_TS_S;
+	vc->tb_offset = saved_l1_hv.tb_offset;
+	restore_hv_regs(vcpu, &saved_l1_hv);
+	vcpu->arch.purr += delta_purr;
+	vcpu->arch.spurr += delta_spurr;
+	vcpu->arch.ic += delta_ic;
+	vc->vtb += delta_vtb;
+
+	kvmhv_put_nested(l2);
+
+	/* copy l2_hv_state and regs back to guest */
+	if (kvmppc_need_byteswap(vcpu)) {
+		byteswap_hv_regs(&l2_hv);
+		byteswap_pt_regs(&l2_regs);
+	}
+	err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv,
+				   sizeof(struct hv_guest_state));
+	if (err)
+		return H_AUTHORITY;
+	err = kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs,
+				   sizeof(struct pt_regs));
+	if (err)
+		return H_AUTHORITY;
+
+	if (r == -EINTR)
+		return H_INTERRUPT;
+
+	if (vcpu->mmio_needed) {
+		kvmhv_nested_mmio_needed(vcpu, regs_ptr);
+		return H_TOO_HARD;
+	}
+
+	return vcpu->arch.trap;
+}
+
+long kvmhv_nested_init(void)
+{
+	long int ptb_order;
+	unsigned long ptcr;
+	long rc;
+
+	if (!kvmhv_on_pseries())
+		return 0;
+	if (!radix_enabled())
+		return -ENODEV;
+
+	/* find log base 2 of KVMPPC_NR_LPIDS, rounding up */
+	ptb_order = __ilog2(KVMPPC_NR_LPIDS - 1) + 1;
+	if (ptb_order < 8)
+		ptb_order = 8;
+	pseries_partition_tb = kmalloc(sizeof(struct patb_entry) << ptb_order,
+				       GFP_KERNEL);
+	if (!pseries_partition_tb) {
+		pr_err("kvm-hv: failed to allocated nested partition table\n");
+		return -ENOMEM;
+	}
+
+	ptcr = __pa(pseries_partition_tb) | (ptb_order - 8);
+	rc = plpar_hcall_norets(H_SET_PARTITION_TABLE, ptcr);
+	if (rc != H_SUCCESS) {
+		pr_err("kvm-hv: Parent hypervisor does not support nesting (rc=%ld)\n",
+		       rc);
+		kfree(pseries_partition_tb);
+		pseries_partition_tb = NULL;
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+void kvmhv_nested_exit(void)
+{
+	/*
+	 * N.B. the kvmhv_on_pseries() test is there because it enables
+	 * the compiler to remove the call to plpar_hcall_norets()
+	 * when CONFIG_PPC_PSERIES=n.
+	 */
+	if (kvmhv_on_pseries() && pseries_partition_tb) {
+		plpar_hcall_norets(H_SET_PARTITION_TABLE, 0);
+		kfree(pseries_partition_tb);
+		pseries_partition_tb = NULL;
+	}
+}
+
+static void kvmhv_flush_lpid(unsigned int lpid)
+{
+	long rc;
+
+	if (!kvmhv_on_pseries()) {
+		radix__flush_all_lpid(lpid);
+		return;
+	}
+
+	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
+				lpid, TLBIEL_INVAL_SET_LPID);
+	if (rc)
+		pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc);
+}
+
+void kvmhv_set_ptbl_entry(unsigned int 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);
+}
+
+static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp)
+{
+	unsigned long dw0;
+
+	dw0 = PATB_HR | radix__get_tree_size() |
+		__pa(gp->shadow_pgtable) | RADIX_PGD_INDEX_SIZE;
+	kvmhv_set_ptbl_entry(gp->shadow_lpid, dw0, gp->process_table);
+}
+
+void kvmhv_vm_nested_init(struct kvm *kvm)
+{
+	kvm->arch.max_nested_lpid = -1;
+}
+
+/*
+ * Handle the H_SET_PARTITION_TABLE hcall.
+ * r4 = guest real address of partition table + log_2(size) - 12
+ * (formatted as for the PTCR).
+ */
+long kvmhv_set_partition_table(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long ptcr = kvmppc_get_gpr(vcpu, 4);
+	int srcu_idx;
+	long ret = H_SUCCESS;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	/*
+	 * Limit the partition table to 4096 entries (because that's what
+	 * hardware supports), and check the base address.
+	 */
+	if ((ptcr & PRTS_MASK) > 12 - 8 ||
+	    !kvm_is_visible_gfn(vcpu->kvm, (ptcr & PRTB_MASK) >> PAGE_SHIFT))
+		ret = H_PARAMETER;
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	if (ret == H_SUCCESS)
+		kvm->arch.l1_ptcr = ptcr;
+	return ret;
+}
+
+/*
+ * Handle the H_COPY_TOFROM_GUEST hcall.
+ * r4 = L1 lpid of nested guest
+ * r5 = pid
+ * r6 = eaddr to access
+ * r7 = to buffer (L1 gpa)
+ * r8 = from buffer (L1 gpa)
+ * r9 = n bytes to copy
+ */
+long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu)
+{
+	struct kvm_nested_guest *gp;
+	int l1_lpid = kvmppc_get_gpr(vcpu, 4);
+	int pid = kvmppc_get_gpr(vcpu, 5);
+	gva_t eaddr = kvmppc_get_gpr(vcpu, 6);
+	gpa_t gp_to = (gpa_t) kvmppc_get_gpr(vcpu, 7);
+	gpa_t gp_from = (gpa_t) kvmppc_get_gpr(vcpu, 8);
+	void *buf;
+	unsigned long n = kvmppc_get_gpr(vcpu, 9);
+	bool is_load = !!gp_to;
+	long rc;
+
+	if (gp_to && gp_from) /* One must be NULL to determine the direction */
+		return H_PARAMETER;
+
+	if (eaddr & (0xFFFUL << 52))
+		return H_PARAMETER;
+
+	buf = kzalloc(n, GFP_KERNEL);
+	if (!buf)
+		return H_NO_MEM;
+
+	gp = kvmhv_get_nested(vcpu->kvm, l1_lpid, false);
+	if (!gp) {
+		rc = H_PARAMETER;
+		goto out_free;
+	}
+
+	mutex_lock(&gp->tlb_lock);
+
+	if (is_load) {
+		/* Load from the nested guest into our buffer */
+		rc = __kvmhv_copy_tofrom_guest_radix(gp->shadow_lpid, pid,
+						     eaddr, buf, NULL, n);
+		if (rc)
+			goto not_found;
+
+		/* Write what was loaded into our buffer back to the L1 guest */
+		rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n);
+		if (rc)
+			goto not_found;
+	} else {
+		/* Load the data to be stored from the L1 guest into our buf */
+		rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n);
+		if (rc)
+			goto not_found;
+
+		/* Store from our buffer into the nested guest */
+		rc = __kvmhv_copy_tofrom_guest_radix(gp->shadow_lpid, pid,
+						     eaddr, NULL, buf, n);
+		if (rc)
+			goto not_found;
+	}
+
+out_unlock:
+	mutex_unlock(&gp->tlb_lock);
+	kvmhv_put_nested(gp);
+out_free:
+	kfree(buf);
+	return rc;
+not_found:
+	rc = H_NOT_FOUND;
+	goto out_unlock;
+}
+
+/*
+ * Reload the partition table entry for a guest.
+ * Caller must hold gp->tlb_lock.
+ */
+static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp)
+{
+	int ret;
+	struct patb_entry ptbl_entry;
+	unsigned long ptbl_addr;
+	struct kvm *kvm = gp->l1_host;
+
+	ret = -EFAULT;
+	ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4);
+	if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8)))
+		ret = kvm_read_guest(kvm, ptbl_addr,
+				     &ptbl_entry, sizeof(ptbl_entry));
+	if (ret) {
+		gp->l1_gr_to_hr = 0;
+		gp->process_table = 0;
+	} else {
+		gp->l1_gr_to_hr = be64_to_cpu(ptbl_entry.patb0);
+		gp->process_table = be64_to_cpu(ptbl_entry.patb1);
+	}
+	kvmhv_set_nested_ptbl(gp);
+}
+
+struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
+{
+	struct kvm_nested_guest *gp;
+	long shadow_lpid;
+
+	gp = kzalloc(sizeof(*gp), GFP_KERNEL);
+	if (!gp)
+		return NULL;
+	gp->l1_host = kvm;
+	gp->l1_lpid = lpid;
+	mutex_init(&gp->tlb_lock);
+	gp->shadow_pgtable = pgd_alloc(kvm->mm);
+	if (!gp->shadow_pgtable)
+		goto out_free;
+	shadow_lpid = kvmppc_alloc_lpid();
+	if (shadow_lpid < 0)
+		goto out_free2;
+	gp->shadow_lpid = shadow_lpid;
+	gp->radix = 1;
+
+	memset(gp->prev_cpu, -1, sizeof(gp->prev_cpu));
+
+	return gp;
+
+ out_free2:
+	pgd_free(kvm->mm, gp->shadow_pgtable);
+ out_free:
+	kfree(gp);
+	return NULL;
+}
+
+/*
+ * Free up any resources allocated for a nested guest.
+ */
+static void kvmhv_release_nested(struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = gp->l1_host;
+
+	if (gp->shadow_pgtable) {
+		/*
+		 * No vcpu is using this struct and no call to
+		 * kvmhv_get_nested can find this struct,
+		 * so we don't need to hold kvm->mmu_lock.
+		 */
+		kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
+					  gp->shadow_lpid);
+		pgd_free(kvm->mm, gp->shadow_pgtable);
+	}
+	kvmhv_set_ptbl_entry(gp->shadow_lpid, 0, 0);
+	kvmppc_free_lpid(gp->shadow_lpid);
+	kfree(gp);
+}
+
+static void kvmhv_remove_nested(struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = gp->l1_host;
+	int lpid = gp->l1_lpid;
+	long ref;
+
+	spin_lock(&kvm->mmu_lock);
+	if (gp == kvm->arch.nested_guests[lpid]) {
+		kvm->arch.nested_guests[lpid] = NULL;
+		if (lpid == kvm->arch.max_nested_lpid) {
+			while (--lpid >= 0 && !kvm->arch.nested_guests[lpid])
+				;
+			kvm->arch.max_nested_lpid = lpid;
+		}
+		--gp->refcnt;
+	}
+	ref = gp->refcnt;
+	spin_unlock(&kvm->mmu_lock);
+	if (ref == 0)
+		kvmhv_release_nested(gp);
+}
+
+/*
+ * Free up all nested resources allocated for this guest.
+ * This is called with no vcpus of the guest running, when
+ * switching the guest to HPT mode or when destroying the
+ * guest.
+ */
+void kvmhv_release_all_nested(struct kvm *kvm)
+{
+	int i;
+	struct kvm_nested_guest *gp;
+	struct kvm_nested_guest *freelist = NULL;
+	struct kvm_memory_slot *memslot;
+	int srcu_idx;
+
+	spin_lock(&kvm->mmu_lock);
+	for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
+		gp = kvm->arch.nested_guests[i];
+		if (!gp)
+			continue;
+		kvm->arch.nested_guests[i] = NULL;
+		if (--gp->refcnt == 0) {
+			gp->next = freelist;
+			freelist = gp;
+		}
+	}
+	kvm->arch.max_nested_lpid = -1;
+	spin_unlock(&kvm->mmu_lock);
+	while ((gp = freelist) != NULL) {
+		freelist = gp->next;
+		kvmhv_release_nested(gp);
+	}
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	kvm_for_each_memslot(memslot, kvm_memslots(kvm))
+		kvmhv_free_memslot_nest_rmap(memslot);
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+}
+
+/* caller must hold gp->tlb_lock */
+static void kvmhv_flush_nested(struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = gp->l1_host;
+
+	spin_lock(&kvm->mmu_lock);
+	kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable, gp->shadow_lpid);
+	spin_unlock(&kvm->mmu_lock);
+	kvmhv_flush_lpid(gp->shadow_lpid);
+	kvmhv_update_ptbl_cache(gp);
+	if (gp->l1_gr_to_hr == 0)
+		kvmhv_remove_nested(gp);
+}
+
+struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
+					  bool create)
+{
+	struct kvm_nested_guest *gp, *newgp;
+
+	if (l1_lpid >= KVM_MAX_NESTED_GUESTS ||
+	    l1_lpid >= (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 12 - 4)))
+		return NULL;
+
+	spin_lock(&kvm->mmu_lock);
+	gp = kvm->arch.nested_guests[l1_lpid];
+	if (gp)
+		++gp->refcnt;
+	spin_unlock(&kvm->mmu_lock);
+
+	if (gp || !create)
+		return gp;
+
+	newgp = kvmhv_alloc_nested(kvm, l1_lpid);
+	if (!newgp)
+		return NULL;
+	spin_lock(&kvm->mmu_lock);
+	if (kvm->arch.nested_guests[l1_lpid]) {
+		/* someone else beat us to it */
+		gp = kvm->arch.nested_guests[l1_lpid];
+	} else {
+		kvm->arch.nested_guests[l1_lpid] = newgp;
+		++newgp->refcnt;
+		gp = newgp;
+		newgp = NULL;
+		if (l1_lpid > kvm->arch.max_nested_lpid)
+			kvm->arch.max_nested_lpid = l1_lpid;
+	}
+	++gp->refcnt;
+	spin_unlock(&kvm->mmu_lock);
+
+	if (newgp)
+		kvmhv_release_nested(newgp);
+
+	return gp;
+}
+
+void kvmhv_put_nested(struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = gp->l1_host;
+	long ref;
+
+	spin_lock(&kvm->mmu_lock);
+	ref = --gp->refcnt;
+	spin_unlock(&kvm->mmu_lock);
+	if (ref == 0)
+		kvmhv_release_nested(gp);
+}
+
+static struct kvm_nested_guest *kvmhv_find_nested(struct kvm *kvm, int lpid)
+{
+	if (lpid > kvm->arch.max_nested_lpid)
+		return NULL;
+	return kvm->arch.nested_guests[lpid];
+}
+
+static inline bool kvmhv_n_rmap_is_equal(u64 rmap_1, u64 rmap_2)
+{
+	return !((rmap_1 ^ rmap_2) & (RMAP_NESTED_LPID_MASK |
+				       RMAP_NESTED_GPA_MASK));
+}
+
+void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
+			    struct rmap_nested **n_rmap)
+{
+	struct llist_node *entry = ((struct llist_head *) rmapp)->first;
+	struct rmap_nested *cursor;
+	u64 rmap, new_rmap = (*n_rmap)->rmap;
+
+	/* Are there any existing entries? */
+	if (!(*rmapp)) {
+		/* No -> use the rmap as a single entry */
+		*rmapp = new_rmap | RMAP_NESTED_IS_SINGLE_ENTRY;
+		return;
+	}
+
+	/* Do any entries match what we're trying to insert? */
+	for_each_nest_rmap_safe(cursor, entry, &rmap) {
+		if (kvmhv_n_rmap_is_equal(rmap, new_rmap))
+			return;
+	}
+
+	/* Do we need to create a list or just add the new entry? */
+	rmap = *rmapp;
+	if (rmap & RMAP_NESTED_IS_SINGLE_ENTRY) /* Not previously a list */
+		*rmapp = 0UL;
+	llist_add(&((*n_rmap)->list), (struct llist_head *) rmapp);
+	if (rmap & RMAP_NESTED_IS_SINGLE_ENTRY) /* Not previously a list */
+		(*n_rmap)->list.next = (struct llist_node *) rmap;
+
+	/* Set NULL so not freed by caller */
+	*n_rmap = NULL;
+}
+
+static void kvmhv_update_nest_rmap_rc(struct kvm *kvm, u64 n_rmap,
+				      unsigned long clr, unsigned long set,
+				      unsigned long hpa, unsigned long mask)
+{
+	struct kvm_nested_guest *gp;
+	unsigned long gpa;
+	unsigned int shift, lpid;
+	pte_t *ptep;
+
+	gpa = n_rmap & RMAP_NESTED_GPA_MASK;
+	lpid = (n_rmap & RMAP_NESTED_LPID_MASK) >> RMAP_NESTED_LPID_SHIFT;
+	gp = kvmhv_find_nested(kvm, lpid);
+	if (!gp)
+		return;
+
+	/* Find the pte */
+	ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
+	/*
+	 * If the pte is present and the pfn is still the same, update the pte.
+	 * If the pfn has changed then this is a stale rmap entry, the nested
+	 * gpa actually points somewhere else now, and there is nothing to do.
+	 * XXX A future optimisation would be to remove the rmap entry here.
+	 */
+	if (ptep && pte_present(*ptep) && ((pte_val(*ptep) & mask) == hpa)) {
+		__radix_pte_update(ptep, clr, set);
+		kvmppc_radix_tlbie_page(kvm, gpa, shift, lpid);
+	}
+}
+
+/*
+ * For a given list of rmap entries, update the rc bits in all ptes in shadow
+ * page tables for nested guests which are referenced by the rmap list.
+ */
+void kvmhv_update_nest_rmap_rc_list(struct kvm *kvm, unsigned long *rmapp,
+				    unsigned long clr, unsigned long set,
+				    unsigned long hpa, unsigned long nbytes)
+{
+	struct llist_node *entry = ((struct llist_head *) rmapp)->first;
+	struct rmap_nested *cursor;
+	unsigned long rmap, mask;
+
+	if ((clr | set) & ~(_PAGE_DIRTY | _PAGE_ACCESSED))
+		return;
+
+	mask = PTE_RPN_MASK & ~(nbytes - 1);
+	hpa &= mask;
+
+	for_each_nest_rmap_safe(cursor, entry, &rmap)
+		kvmhv_update_nest_rmap_rc(kvm, rmap, clr, set, hpa, mask);
+}
+
+static void kvmhv_remove_nest_rmap(struct kvm *kvm, u64 n_rmap,
+				   unsigned long hpa, unsigned long mask)
+{
+	struct kvm_nested_guest *gp;
+	unsigned long gpa;
+	unsigned int shift, lpid;
+	pte_t *ptep;
+
+	gpa = n_rmap & RMAP_NESTED_GPA_MASK;
+	lpid = (n_rmap & RMAP_NESTED_LPID_MASK) >> RMAP_NESTED_LPID_SHIFT;
+	gp = kvmhv_find_nested(kvm, lpid);
+	if (!gp)
+		return;
+
+	/* Find and invalidate the pte */
+	ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
+	/* Don't spuriously invalidate ptes if the pfn has changed */
+	if (ptep && pte_present(*ptep) && ((pte_val(*ptep) & mask) == hpa))
+		kvmppc_unmap_pte(kvm, ptep, gpa, shift, NULL, gp->shadow_lpid);
+}
+
+static void kvmhv_remove_nest_rmap_list(struct kvm *kvm, unsigned long *rmapp,
+					unsigned long hpa, unsigned long mask)
+{
+	struct llist_node *entry = llist_del_all((struct llist_head *) rmapp);
+	struct rmap_nested *cursor;
+	unsigned long rmap;
+
+	for_each_nest_rmap_safe(cursor, entry, &rmap) {
+		kvmhv_remove_nest_rmap(kvm, rmap, hpa, mask);
+		kfree(cursor);
+	}
+}
+
+/* called with kvm->mmu_lock held */
+void kvmhv_remove_nest_rmap_range(struct kvm *kvm,
+				  const struct kvm_memory_slot *memslot,
+				  unsigned long gpa, unsigned long hpa,
+				  unsigned long nbytes)
+{
+	unsigned long gfn, end_gfn;
+	unsigned long addr_mask;
+
+	if (!memslot)
+		return;
+	gfn = (gpa >> PAGE_SHIFT) - memslot->base_gfn;
+	end_gfn = gfn + (nbytes >> PAGE_SHIFT);
+
+	addr_mask = PTE_RPN_MASK & ~(nbytes - 1);
+	hpa &= addr_mask;
+
+	for (; gfn < end_gfn; gfn++) {
+		unsigned long *rmap = &memslot->arch.rmap[gfn];
+		kvmhv_remove_nest_rmap_list(kvm, rmap, hpa, addr_mask);
+	}
+}
+
+static void kvmhv_free_memslot_nest_rmap(struct kvm_memory_slot *free)
+{
+	unsigned long page;
+
+	for (page = 0; page < free->npages; page++) {
+		unsigned long rmap, *rmapp = &free->arch.rmap[page];
+		struct rmap_nested *cursor;
+		struct llist_node *entry;
+
+		entry = llist_del_all((struct llist_head *) rmapp);
+		for_each_nest_rmap_safe(cursor, entry, &rmap)
+			kfree(cursor);
+	}
+}
+
+static bool kvmhv_invalidate_shadow_pte(struct kvm_vcpu *vcpu,
+					struct kvm_nested_guest *gp,
+					long gpa, int *shift_ret)
+{
+	struct kvm *kvm = vcpu->kvm;
+	bool ret = false;
+	pte_t *ptep;
+	int shift;
+
+	spin_lock(&kvm->mmu_lock);
+	ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
+	if (!shift)
+		shift = PAGE_SHIFT;
+	if (ptep && pte_present(*ptep)) {
+		kvmppc_unmap_pte(kvm, ptep, gpa, shift, NULL, gp->shadow_lpid);
+		ret = true;
+	}
+	spin_unlock(&kvm->mmu_lock);
+
+	if (shift_ret)
+		*shift_ret = shift;
+	return ret;
+}
+
+static inline int get_ric(unsigned int instr)
+{
+	return (instr >> 18) & 0x3;
+}
+
+static inline int get_prs(unsigned int instr)
+{
+	return (instr >> 17) & 0x1;
+}
+
+static inline int get_r(unsigned int instr)
+{
+	return (instr >> 16) & 0x1;
+}
+
+static inline int get_lpid(unsigned long r_val)
+{
+	return r_val & 0xffffffff;
+}
+
+static inline int get_is(unsigned long r_val)
+{
+	return (r_val >> 10) & 0x3;
+}
+
+static inline int get_ap(unsigned long r_val)
+{
+	return (r_val >> 5) & 0x7;
+}
+
+static inline long get_epn(unsigned long r_val)
+{
+	return r_val >> 12;
+}
+
+static int kvmhv_emulate_tlbie_tlb_addr(struct kvm_vcpu *vcpu, int lpid,
+					int ap, long epn)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *gp;
+	long npages;
+	int shift, shadow_shift;
+	unsigned long addr;
+
+	shift = ap_to_shift(ap);
+	addr = epn << 12;
+	if (shift < 0)
+		/* Invalid ap encoding */
+		return -EINVAL;
+
+	addr &= ~((1UL << shift) - 1);
+	npages = 1UL << (shift - PAGE_SHIFT);
+
+	gp = kvmhv_get_nested(kvm, lpid, false);
+	if (!gp) /* No such guest -> nothing to do */
+		return 0;
+	mutex_lock(&gp->tlb_lock);
+
+	/* There may be more than one host page backing this single guest pte */
+	do {
+		kvmhv_invalidate_shadow_pte(vcpu, gp, addr, &shadow_shift);
+
+		npages -= 1UL << (shadow_shift - PAGE_SHIFT);
+		addr += 1UL << shadow_shift;
+	} while (npages > 0);
+
+	mutex_unlock(&gp->tlb_lock);
+	kvmhv_put_nested(gp);
+	return 0;
+}
+
+static void kvmhv_emulate_tlbie_lpid(struct kvm_vcpu *vcpu,
+				     struct kvm_nested_guest *gp, int ric)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	mutex_lock(&gp->tlb_lock);
+	switch (ric) {
+	case 0:
+		/* Invalidate TLB */
+		spin_lock(&kvm->mmu_lock);
+		kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
+					  gp->shadow_lpid);
+		kvmhv_flush_lpid(gp->shadow_lpid);
+		spin_unlock(&kvm->mmu_lock);
+		break;
+	case 1:
+		/*
+		 * Invalidate PWC
+		 * We don't cache this -> nothing to do
+		 */
+		break;
+	case 2:
+		/* Invalidate TLB, PWC and caching of partition table entries */
+		kvmhv_flush_nested(gp);
+		break;
+	default:
+		break;
+	}
+	mutex_unlock(&gp->tlb_lock);
+}
+
+static void kvmhv_emulate_tlbie_all_lpid(struct kvm_vcpu *vcpu, int ric)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *gp;
+	int i;
+
+	spin_lock(&kvm->mmu_lock);
+	for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
+		gp = kvm->arch.nested_guests[i];
+		if (gp) {
+			spin_unlock(&kvm->mmu_lock);
+			kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
+			spin_lock(&kvm->mmu_lock);
+		}
+	}
+	spin_unlock(&kvm->mmu_lock);
+}
+
+static int kvmhv_emulate_priv_tlbie(struct kvm_vcpu *vcpu, unsigned int instr,
+				    unsigned long rsval, unsigned long rbval)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *gp;
+	int r, ric, prs, is, ap;
+	int lpid;
+	long epn;
+	int ret = 0;
+
+	ric = get_ric(instr);
+	prs = get_prs(instr);
+	r = get_r(instr);
+	lpid = get_lpid(rsval);
+	is = get_is(rbval);
+
+	/*
+	 * These cases are invalid and are not handled:
+	 * r   != 1 -> Only radix supported
+	 * prs == 1 -> Not HV privileged
+	 * ric == 3 -> No cluster bombs for radix
+	 * is  == 1 -> Partition scoped translations not associated with pid
+	 * (!is) && (ric == 1 || ric == 2) -> Not supported by ISA
+	 */
+	if ((!r) || (prs) || (ric == 3) || (is == 1) ||
+	    ((!is) && (ric == 1 || ric == 2)))
+		return -EINVAL;
+
+	switch (is) {
+	case 0:
+		/*
+		 * We know ric == 0
+		 * Invalidate TLB for a given target address
+		 */
+		epn = get_epn(rbval);
+		ap = get_ap(rbval);
+		ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap, epn);
+		break;
+	case 2:
+		/* Invalidate matching LPID */
+		gp = kvmhv_get_nested(kvm, lpid, false);
+		if (gp) {
+			kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
+			kvmhv_put_nested(gp);
+		}
+		break;
+	case 3:
+		/* Invalidate ALL LPIDs */
+		kvmhv_emulate_tlbie_all_lpid(vcpu, ric);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * This handles the H_TLB_INVALIDATE hcall.
+ * Parameters are (r4) tlbie instruction code, (r5) rS contents,
+ * (r6) rB contents.
+ */
+long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	ret = kvmhv_emulate_priv_tlbie(vcpu, kvmppc_get_gpr(vcpu, 4),
+			kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6));
+	if (ret)
+		return H_PARAMETER;
+	return H_SUCCESS;
+}
+
+/* Used to convert a nested guest real address to a L1 guest real address */
+static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
+				       struct kvm_nested_guest *gp,
+				       unsigned long n_gpa, unsigned long dsisr,
+				       struct kvmppc_pte *gpte_p)
+{
+	u64 fault_addr, flags = dsisr & DSISR_ISSTORE;
+	int ret;
+
+	ret = kvmppc_mmu_walk_radix_tree(vcpu, n_gpa, gpte_p, gp->l1_gr_to_hr,
+					 &fault_addr);
+
+	if (ret) {
+		/* We didn't find a pte */
+		if (ret == -EINVAL) {
+			/* Unsupported mmu config */
+			flags |= DSISR_UNSUPP_MMU;
+		} else if (ret == -ENOENT) {
+			/* No translation found */
+			flags |= DSISR_NOHPTE;
+		} else if (ret == -EFAULT) {
+			/* Couldn't access L1 real address */
+			flags |= DSISR_PRTABLE_FAULT;
+			vcpu->arch.fault_gpa = fault_addr;
+		} else {
+			/* Unknown error */
+			return ret;
+		}
+		goto forward_to_l1;
+	} else {
+		/* We found a pte -> check permissions */
+		if (dsisr & DSISR_ISSTORE) {
+			/* Can we write? */
+			if (!gpte_p->may_write) {
+				flags |= DSISR_PROTFAULT;
+				goto forward_to_l1;
+			}
+		} else if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
+			/* Can we execute? */
+			if (!gpte_p->may_execute) {
+				flags |= SRR1_ISI_N_OR_G;
+				goto forward_to_l1;
+			}
+		} else {
+			/* Can we read? */
+			if (!gpte_p->may_read && !gpte_p->may_write) {
+				flags |= DSISR_PROTFAULT;
+				goto forward_to_l1;
+			}
+		}
+	}
+
+	return 0;
+
+forward_to_l1:
+	vcpu->arch.fault_dsisr = flags;
+	if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
+		vcpu->arch.shregs.msr &= ~0x783f0000ul;
+		vcpu->arch.shregs.msr |= flags;
+	}
+	return RESUME_HOST;
+}
+
+static long kvmhv_handle_nested_set_rc(struct kvm_vcpu *vcpu,
+				       struct kvm_nested_guest *gp,
+				       unsigned long n_gpa,
+				       struct kvmppc_pte gpte,
+				       unsigned long dsisr)
+{
+	struct kvm *kvm = vcpu->kvm;
+	bool writing = !!(dsisr & DSISR_ISSTORE);
+	u64 pgflags;
+	long ret;
+
+	/* Are the rc bits set in the L1 partition scoped pte? */
+	pgflags = _PAGE_ACCESSED;
+	if (writing)
+		pgflags |= _PAGE_DIRTY;
+	if (pgflags & ~gpte.rc)
+		return RESUME_HOST;
+
+	spin_lock(&kvm->mmu_lock);
+	/* Set the rc bit in the pte of our (L0) pgtable for the L1 guest */
+	ret = kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable, writing,
+				     gpte.raddr, kvm->arch.lpid);
+	if (!ret) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	/* Set the rc bit in the pte of the shadow_pgtable for the nest guest */
+	ret = kvmppc_hv_handle_set_rc(kvm, gp->shadow_pgtable, writing, n_gpa,
+				      gp->shadow_lpid);
+	if (!ret)
+		ret = -EINVAL;
+	else
+		ret = 0;
+
+out_unlock:
+	spin_unlock(&kvm->mmu_lock);
+	return ret;
+}
+
+static inline int kvmppc_radix_level_to_shift(int level)
+{
+	switch (level) {
+	case 2:
+		return PUD_SHIFT;
+	case 1:
+		return PMD_SHIFT;
+	default:
+		return PAGE_SHIFT;
+	}
+}
+
+static inline int kvmppc_radix_shift_to_level(int shift)
+{
+	if (shift == PUD_SHIFT)
+		return 2;
+	if (shift == PMD_SHIFT)
+		return 1;
+	if (shift == PAGE_SHIFT)
+		return 0;
+	WARN_ON_ONCE(1);
+	return 0;
+}
+
+/* called with gp->tlb_lock held */
+static long int __kvmhv_nested_page_fault(struct kvm_run *run,
+					  struct kvm_vcpu *vcpu,
+					  struct kvm_nested_guest *gp)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_memory_slot *memslot;
+	struct rmap_nested *n_rmap;
+	struct kvmppc_pte gpte;
+	pte_t pte, *pte_p;
+	unsigned long mmu_seq;
+	unsigned long dsisr = vcpu->arch.fault_dsisr;
+	unsigned long ea = vcpu->arch.fault_dar;
+	unsigned long *rmapp;
+	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) {
+		kvmhv_update_ptbl_cache(gp);
+		if (!gp->l1_gr_to_hr)
+			return RESUME_HOST;
+	}
+
+	/* Convert the nested guest real address into a L1 guest real address */
+
+	n_gpa = vcpu->arch.fault_gpa & ~0xF000000000000FFFULL;
+	if (!(dsisr & DSISR_PRTABLE_FAULT))
+		n_gpa |= ea & 0xFFF;
+	ret = kvmhv_translate_addr_nested(vcpu, gp, n_gpa, dsisr, &gpte);
+
+	/*
+	 * If the hardware found a translation but we don't now have a usable
+	 * translation in the l1 partition-scoped tree, remove the shadow pte
+	 * and let the guest retry.
+	 */
+	if (ret == RESUME_HOST &&
+	    (dsisr & (DSISR_PROTFAULT | DSISR_BADACCESS | DSISR_NOEXEC_OR_G |
+		      DSISR_BAD_COPYPASTE)))
+		goto inval;
+	if (ret)
+		return ret;
+
+	/* Failed to set the reference/change bits */
+	if (dsisr & DSISR_SET_RC) {
+		ret = kvmhv_handle_nested_set_rc(vcpu, gp, n_gpa, gpte, dsisr);
+		if (ret == RESUME_HOST)
+			return ret;
+		if (ret)
+			goto inval;
+		dsisr &= ~DSISR_SET_RC;
+		if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
+			       DSISR_PROTFAULT)))
+			return RESUME_GUEST;
+	}
+
+	/*
+	 * We took an HISI or HDSI while we were running a nested guest which
+	 * means we have no partition scoped translation for that. This means
+	 * we need to insert a pte for the mapping into our shadow_pgtable.
+	 */
+
+	l1_shift = gpte.page_shift;
+	if (l1_shift < PAGE_SHIFT) {
+		/* We don't support l1 using a page size smaller than our own */
+		pr_err("KVM: L1 guest page shift (%d) less than our own (%d)\n",
+			l1_shift, PAGE_SHIFT);
+		return -EINVAL;
+	}
+	gpa = gpte.raddr;
+	gfn = gpa >> PAGE_SHIFT;
+
+	/* 1. Get the corresponding host memslot */
+
+	memslot = gfn_to_memslot(kvm, gfn);
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
+		if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS)) {
+			/* unusual error -> reflect to the guest as a DSI */
+			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
+			return RESUME_GUEST;
+		}
+
+		/* passthrough of emulated MMIO case */
+		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea, writing);
+	}
+	if (memslot->flags & KVM_MEM_READONLY) {
+		if (writing) {
+			/* Give the guest a DSI */
+			kvmppc_core_queue_data_storage(vcpu, ea,
+					DSISR_ISSTORE | DSISR_PROTFAULT);
+			return RESUME_GUEST;
+		}
+		kvm_ro = true;
+	}
+
+	/* 2. Find the host pte for this L1 guest real address */
+
+	/* Used to check for invalidations in progress */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	/* See if can find translation in our partition scoped tables for L1 */
+	pte = __pte(0);
+	spin_lock(&kvm->mmu_lock);
+	pte_p = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
+	if (!shift)
+		shift = PAGE_SHIFT;
+	if (pte_p)
+		pte = *pte_p;
+	spin_unlock(&kvm->mmu_lock);
+
+	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);
+		if (ret == -EAGAIN)
+			return RESUME_GUEST;
+		else if (ret)
+			return ret;
+		shift = kvmppc_radix_level_to_shift(level);
+	}
+	/* Align gfn to the start of the page */
+	gfn = (gpa & ~((1UL << shift) - 1)) >> PAGE_SHIFT;
+
+	/* 3. Compute the pte we need to insert for nest_gpa -> host r_addr */
+
+	/* The permissions is the combination of the host and l1 guest ptes */
+	perm |= gpte.may_read ? 0UL : _PAGE_READ;
+	perm |= gpte.may_write ? 0UL : _PAGE_WRITE;
+	perm |= gpte.may_execute ? 0UL : _PAGE_EXEC;
+	/* Only set accessed/dirty (rc) bits if set in host and l1 guest ptes */
+	perm |= (gpte.rc & _PAGE_ACCESSED) ? 0UL : _PAGE_ACCESSED;
+	perm |= ((gpte.rc & _PAGE_DIRTY) && writing) ? 0UL : _PAGE_DIRTY;
+	pte = __pte(pte_val(pte) & ~perm);
+
+	/* What size pte can we insert? */
+	if (shift > l1_shift) {
+		u64 mask;
+		unsigned int actual_shift = PAGE_SHIFT;
+		if (PMD_SHIFT < l1_shift)
+			actual_shift = PMD_SHIFT;
+		mask = (1UL << shift) - (1UL << actual_shift);
+		pte = __pte(pte_val(pte) | (gpa & mask));
+		shift = actual_shift;
+	}
+	level = kvmppc_radix_shift_to_level(shift);
+	n_gpa &= ~((1UL << shift) - 1);
+
+	/* 4. Insert the pte into our shadow_pgtable */
+
+	n_rmap = kzalloc(sizeof(*n_rmap), GFP_KERNEL);
+	if (!n_rmap)
+		return RESUME_GUEST; /* Let the guest try again */
+	n_rmap->rmap = (n_gpa & RMAP_NESTED_GPA_MASK) |
+		(((unsigned long) gp->l1_lpid) << RMAP_NESTED_LPID_SHIFT);
+	rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
+	ret = kvmppc_create_pte(kvm, gp->shadow_pgtable, pte, n_gpa, level,
+				mmu_seq, gp->shadow_lpid, rmapp, &n_rmap);
+	if (n_rmap)
+		kfree(n_rmap);
+	if (ret == -EAGAIN)
+		ret = RESUME_GUEST;	/* Let the guest try again */
+
+	return ret;
+
+ inval:
+	kvmhv_invalidate_shadow_pte(vcpu, gp, n_gpa, NULL);
+	return RESUME_GUEST;
+}
+
+long int kvmhv_nested_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	struct kvm_nested_guest *gp = vcpu->arch.nested;
+	long int ret;
+
+	mutex_lock(&gp->tlb_lock);
+	ret = __kvmhv_nested_page_fault(run, vcpu, gp);
+	mutex_unlock(&gp->tlb_lock);
+	return ret;
+}
+
+int kvmhv_nested_next_lpid(struct kvm *kvm, int lpid)
+{
+	int ret = -1;
+
+	spin_lock(&kvm->mmu_lock);
+	while (++lpid <= kvm->arch.max_nested_lpid) {
+		if (kvm->arch.nested_guests[lpid]) {
+			ret = lpid;
+			break;
+		}
+	}
+	spin_unlock(&kvm->mmu_lock);
+	return ret;
+}
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index b11043b..79f7d07 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -1,7 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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.
  *
  * Copyright 2012 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  */
@@ -66,10 +64,8 @@
 /*
  * On POWER7, see if we can handle a machine check that occurred inside
  * the guest in real mode, without switching to the host partition.
- *
- * Returns: 0 => exit guest, 1 => deliver machine check to guest
  */
-static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
+static void kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 {
 	unsigned long srr1 = vcpu->arch.shregs.msr;
 	struct machine_check_event mce_evt;
@@ -111,52 +107,24 @@
 	}
 
 	/*
-	 * See if we have already handled the condition in the linux host.
-	 * We assume that if the condition is recovered then linux host
-	 * will have generated an error log event that we will pick
-	 * up and log later.
-	 * Don't release mce event now. We will queue up the event so that
-	 * we can log the MCE event info on host console.
+	 * Now get the event and stash it in the vcpu struct so it can
+	 * be handled by the primary thread in virtual mode.  We can't
+	 * call machine_check_queue_event() here if we are running on
+	 * an offline secondary thread.
 	 */
-	if (!get_mce_event(&mce_evt, MCE_EVENT_DONTRELEASE))
-		goto out;
+	if (get_mce_event(&mce_evt, MCE_EVENT_RELEASE)) {
+		if (handled && mce_evt.version == MCE_V1)
+			mce_evt.disposition = MCE_DISPOSITION_RECOVERED;
+	} else {
+		memset(&mce_evt, 0, sizeof(mce_evt));
+	}
 
-	if (mce_evt.version == MCE_V1 &&
-	    (mce_evt.severity == MCE_SEV_NO_ERROR ||
-	     mce_evt.disposition == MCE_DISPOSITION_RECOVERED))
-		handled = 1;
-
-out:
-	/*
-	 * For guest that supports FWNMI capability, hook the MCE event into
-	 * vcpu structure. We are going to exit the guest with KVM_EXIT_NMI
-	 * exit reason. On our way to exit we will pull this event from vcpu
-	 * structure and print it from thread 0 of the core/subcore.
-	 *
-	 * For guest that does not support FWNMI capability (old QEMU):
-	 * We are now going enter guest either through machine check
-	 * interrupt (for unhandled errors) or will continue from
-	 * current HSRR0 (for handled errors) in guest. Hence
-	 * queue up the event so that we can log it from host console later.
-	 */
-	if (vcpu->kvm->arch.fwnmi_enabled) {
-		/*
-		 * Hook up the mce event on to vcpu structure.
-		 * First clear the old event.
-		 */
-		memset(&vcpu->arch.mce_evt, 0, sizeof(vcpu->arch.mce_evt));
-		if (get_mce_event(&mce_evt, MCE_EVENT_RELEASE)) {
-			vcpu->arch.mce_evt = mce_evt;
-		}
-	} else
-		machine_check_queue_event();
-
-	return handled;
+	vcpu->arch.mce_evt = mce_evt;
 }
 
-long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
+void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
 {
-	return kvmppc_realmode_mc_power7(vcpu);
+	kvmppc_realmode_mc_power7(vcpu);
 }
 
 /* Check if dynamic split is in force and return subcore size accordingly. */
@@ -177,6 +145,7 @@
 
 	local_paca->sibling_subcore_state->in_guest[subcore_id] = 1;
 }
+EXPORT_SYMBOL_GPL(kvmppc_subcore_enter_guest);
 
 void kvmppc_subcore_exit_guest(void)
 {
@@ -187,6 +156,7 @@
 
 	local_paca->sibling_subcore_state->in_guest[subcore_id] = 0;
 }
+EXPORT_SYMBOL_GPL(kvmppc_subcore_exit_guest);
 
 static bool kvmppc_tb_resync_required(void)
 {
@@ -331,5 +301,13 @@
 	} else {
 		wait_for_tb_resync();
 	}
+
+	/*
+	 * Reset tb_offset_applied so the guest exit code won't try
+	 * to subtract the previous timebase offset from the timebase.
+	 */
+	if (local_paca->kvm_hstate.kvm_vcore)
+		local_paca->kvm_hstate.kvm_vcore->tb_offset_applied = 0;
+
 	return 0;
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index a67cf1c..2203054 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -1,7 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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.
  *
  * Copyright 2010-2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  */
@@ -13,6 +11,7 @@
 #include <linux/hugetlb.h>
 #include <linux/module.h>
 #include <linux/log2.h>
+#include <linux/sizes.h>
 
 #include <asm/trace.h>
 #include <asm/kvm_ppc.h>
@@ -100,14 +99,14 @@
 	} else {
 		rev->forw = rev->back = pte_index;
 		*rmap = (*rmap & ~KVMPPC_RMAP_INDEX) |
-			pte_index | KVMPPC_RMAP_PRESENT;
+			pte_index | KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_HPT;
 	}
 	unlock_rmap(rmap);
 }
 EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);
 
 /* Update the dirty bitmap of a memslot */
-void kvmppc_update_dirty_map(struct kvm_memory_slot *memslot,
+void kvmppc_update_dirty_map(const struct kvm_memory_slot *memslot,
 			     unsigned long gfn, unsigned long psize)
 {
 	unsigned long npages;
@@ -434,6 +433,37 @@
 		(HPTE_R_KEY_HI | HPTE_R_KEY_LO));
 }
 
+static inline void fixup_tlbie_lpid(unsigned long rb_value, unsigned long lpid)
+{
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		/* Radix flush for a hash guest */
+
+		unsigned long rb,rs,prs,r,ric;
+
+		rb = PPC_BIT(52); /* IS = 2 */
+		rs = 0;  /* lpid = 0 */
+		prs = 0; /* partition scoped */
+		r = 1;   /* radix format */
+		ric = 0; /* RIC_FLSUH_TLB */
+
+		/*
+		 * Need the extra ptesync to make sure we don't
+		 * re-order the tlbie
+		 */
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+			     : : "r"(rb), "i"(r), "i"(prs),
+			       "i"(ric), "r"(rs) : "memory");
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
+			     "r" (rb_value), "r" (lpid));
+	}
+}
+
 static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
 		      long npages, int global, bool need_sync)
 {
@@ -452,16 +482,7 @@
 				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
 		}
 
-		if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
-			/*
-			 * Need the extra ptesync to make sure we don't
-			 * re-order the tlbie
-			 */
-			asm volatile("ptesync": : :"memory");
-			asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
-				     "r" (rbvalues[0]), "r" (kvm->arch.lpid));
-		}
-
+		fixup_tlbie_lpid(rbvalues[i - 1], kvm->arch.lpid);
 		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 	} else {
 		if (need_sync)
@@ -867,6 +888,149 @@
 	return ret;
 }
 
+static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long gpa,
+			  int writing, unsigned long *hpa,
+			  struct kvm_memory_slot **memslot_p)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_memory_slot *memslot;
+	unsigned long gfn, hva, pa, psize = PAGE_SHIFT;
+	unsigned int shift;
+	pte_t *ptep, pte;
+
+	/* Find the memslot for this address */
+	gfn = gpa >> PAGE_SHIFT;
+	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+		return H_PARAMETER;
+
+	/* Translate to host virtual address */
+	hva = __gfn_to_hva_memslot(memslot, gfn);
+
+	/* Try to find the host pte for that virtual address */
+	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+	if (!ptep)
+		return H_TOO_HARD;
+	pte = kvmppc_read_update_linux_pte(ptep, writing);
+	if (!pte_present(pte))
+		return H_TOO_HARD;
+
+	/* Convert to a physical address */
+	if (shift)
+		psize = 1UL << shift;
+	pa = pte_pfn(pte) << PAGE_SHIFT;
+	pa |= hva & (psize - 1);
+	pa |= gpa & ~PAGE_MASK;
+
+	if (hpa)
+		*hpa = pa;
+	if (memslot_p)
+		*memslot_p = memslot;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_do_h_page_init_zero(struct kvm_vcpu *vcpu,
+				       unsigned long dest)
+{
+	struct kvm_memory_slot *memslot;
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long pa, mmu_seq;
+	long ret = H_SUCCESS;
+	int i;
+
+	/* Used later to detect if we might have been invalidated */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	ret = kvmppc_get_hpa(vcpu, dest, 1, &pa, &memslot);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	/* Check if we've been invalidated */
+	raw_spin_lock(&kvm->mmu_lock.rlock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = H_TOO_HARD;
+		goto out_unlock;
+	}
+
+	/* Zero the page */
+	for (i = 0; i < SZ_4K; i += L1_CACHE_BYTES, pa += L1_CACHE_BYTES)
+		dcbz((void *)pa);
+	kvmppc_update_dirty_map(memslot, dest >> PAGE_SHIFT, PAGE_SIZE);
+
+out_unlock:
+	raw_spin_unlock(&kvm->mmu_lock.rlock);
+	return ret;
+}
+
+static long kvmppc_do_h_page_init_copy(struct kvm_vcpu *vcpu,
+				       unsigned long dest, unsigned long src)
+{
+	unsigned long dest_pa, src_pa, mmu_seq;
+	struct kvm_memory_slot *dest_memslot;
+	struct kvm *kvm = vcpu->kvm;
+	long ret = H_SUCCESS;
+
+	/* Used later to detect if we might have been invalidated */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	ret = kvmppc_get_hpa(vcpu, dest, 1, &dest_pa, &dest_memslot);
+	if (ret != H_SUCCESS)
+		return ret;
+	ret = kvmppc_get_hpa(vcpu, src, 0, &src_pa, NULL);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	/* Check if we've been invalidated */
+	raw_spin_lock(&kvm->mmu_lock.rlock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = H_TOO_HARD;
+		goto out_unlock;
+	}
+
+	/* Copy the page */
+	memcpy((void *)dest_pa, (void *)src_pa, SZ_4K);
+
+	kvmppc_update_dirty_map(dest_memslot, dest >> PAGE_SHIFT, PAGE_SIZE);
+
+out_unlock:
+	raw_spin_unlock(&kvm->mmu_lock.rlock);
+	return ret;
+}
+
+long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			   unsigned long dest, unsigned long src)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 pg_mask = SZ_4K - 1;	/* 4K page size */
+	long ret = H_SUCCESS;
+
+	/* Don't handle radix mode here, go up to the virtual mode handler */
+	if (kvm_is_radix(kvm))
+		return H_TOO_HARD;
+
+	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
+	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
+		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
+		return H_PARAMETER;
+
+	/* dest (and src if copy_page flag set) must be page aligned */
+	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
+		return H_PARAMETER;
+
+	/* zero and/or copy the page as determined by the flags */
+	if (flags & H_COPY_PAGE)
+		ret = kvmppc_do_h_page_init_copy(vcpu, dest, src);
+	else if (flags & H_ZERO_PAGE)
+		ret = kvmppc_do_h_page_init_zero(vcpu, dest);
+
+	/* We can ignore the other flags */
+
+	return ret;
+}
+
 void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
 			unsigned long pte_index)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 758d1d2..287d591 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2012 Michael Ellerman, IBM Corporation.
  * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kernel.h>
@@ -61,7 +58,7 @@
 	hcpu = hcore << threads_shift;
 	kvmppc_host_rm_ops_hv->rm_core[hcore].rm_data = vcpu;
 	smp_muxed_ipi_set_message(hcpu, PPC_MSG_RM_HOST_ACTION);
-	kvmppc_set_host_ipi(hcpu, 1);
+	kvmppc_set_host_ipi(hcpu);
 	smp_mb();
 	kvmhv_rm_send_ipi(hcpu);
 }
@@ -136,7 +133,7 @@
 
 	/* Mark the target VCPU as having an interrupt pending */
 	vcpu->stat.queue_intr++;
-	set_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
+	set_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
 
 	/* Kick self ? Just set MER and return */
 	if (vcpu == this_vcpu) {
@@ -144,6 +141,13 @@
 		return;
 	}
 
+	if (xive_enabled() && kvmhv_on_pseries()) {
+		/* No XICS access or hypercalls available, too hard */
+		this_icp->rm_action |= XICS_RM_KICK_VCPU;
+		this_icp->rm_kick_target = vcpu;
+		return;
+	}
+
 	/*
 	 * Check if the core is loaded,
 	 * if not, find an available host core to post to wake the VCPU,
@@ -170,8 +174,7 @@
 static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu)
 {
 	/* Note: Only called on self ! */
-	clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
-		  &vcpu->arch.pending_exceptions);
+	clear_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_MER);
 }
 
@@ -768,6 +771,14 @@
 	void __iomem *xics_phys;
 	int64_t rc;
 
+	if (kvmhv_on_pseries()) {
+		unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+		iosync();
+		plpar_hcall_raw(H_EOI, retbuf, hwirq);
+		return;
+	}
+
 	rc = pnv_opal_pci_msi_eoi(c, hwirq);
 
 	if (rc)
@@ -808,7 +819,7 @@
 	raddr = per_cpu_ptr(addr, cpu);
 	l = (unsigned long)raddr;
 
-	if (REGION_ID(l) == VMALLOC_REGION_ID) {
+	if (get_region_id(l) == VMALLOC_REGION_ID) {
 		l = vmalloc_to_phys(raddr);
 		raddr = (unsigned int *)l;
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 1d14046..0496e66 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1,12 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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.
  *
  * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
@@ -18,6 +11,7 @@
  */
 
 #include <asm/ppc_asm.h>
+#include <asm/code-patching-asm.h>
 #include <asm/kvm_asm.h>
 #include <asm/reg.h>
 #include <asm/mmu.h>
@@ -28,12 +22,15 @@
 #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/xive-regs.h>
 #include <asm/thread_info.h>
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
+#include <asm/cpuidle.h>
+#include <asm/ultravisor-api.h>
 
 /* Sign-extend HDEC if not on POWER9 */
 #define EXTEND_HDEC(reg)			\
@@ -44,10 +41,12 @@
 /* Values in HSTATE_NAPPING(r13) */
 #define NAPPING_CEDE	1
 #define NAPPING_NOVCPU	2
+#define NAPPING_UNSPLIT	3
 
 /* Stack frame offsets for kvmppc_hv_entry */
-#define SFS			160
+#define SFS			208
 #define STACK_SLOT_TRAP		(SFS-4)
+#define STACK_SLOT_SHORT_PATH	(SFS-8)
 #define STACK_SLOT_TID		(SFS-16)
 #define STACK_SLOT_PSSCR	(SFS-24)
 #define STACK_SLOT_PID		(SFS-32)
@@ -56,6 +55,10 @@
 #define STACK_SLOT_DAWR		(SFS-56)
 #define STACK_SLOT_DAWRX	(SFS-64)
 #define STACK_SLOT_HFSCR	(SFS-72)
+#define STACK_SLOT_AMR		(SFS-80)
+#define STACK_SLOT_UAMOR	(SFS-88)
+/* the following is used by the P9 short path */
+#define STACK_SLOT_NVGPRS	(SFS-152)	/* 18 gprs */
 
 /*
  * Call kvmppc_hv_entry in real mode.
@@ -113,45 +116,7 @@
 	mtspr	SPRN_SPRG_VDSO_WRITE,r3
 
 	/* Reload the host's PMU registers */
-	lbz	r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
-	cmpwi	r4, 0
-	beq	23f			/* skip if not */
-BEGIN_FTR_SECTION
-	ld	r3, HSTATE_MMCR0(r13)
-	andi.	r4, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
-	cmpwi	r4, MMCR0_PMAO
-	beql	kvmppc_fix_pmao
-END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
-	lwz	r3, HSTATE_PMC1(r13)
-	lwz	r4, HSTATE_PMC2(r13)
-	lwz	r5, HSTATE_PMC3(r13)
-	lwz	r6, HSTATE_PMC4(r13)
-	lwz	r8, HSTATE_PMC5(r13)
-	lwz	r9, HSTATE_PMC6(r13)
-	mtspr	SPRN_PMC1, r3
-	mtspr	SPRN_PMC2, r4
-	mtspr	SPRN_PMC3, r5
-	mtspr	SPRN_PMC4, r6
-	mtspr	SPRN_PMC5, r8
-	mtspr	SPRN_PMC6, r9
-	ld	r3, HSTATE_MMCR0(r13)
-	ld	r4, HSTATE_MMCR1(r13)
-	ld	r5, HSTATE_MMCRA(r13)
-	ld	r6, HSTATE_SIAR(r13)
-	ld	r7, HSTATE_SDAR(r13)
-	mtspr	SPRN_MMCR1, r4
-	mtspr	SPRN_MMCRA, r5
-	mtspr	SPRN_SIAR, r6
-	mtspr	SPRN_SDAR, r7
-BEGIN_FTR_SECTION
-	ld	r8, HSTATE_MMCR2(r13)
-	ld	r9, HSTATE_SIER(r13)
-	mtspr	SPRN_MMCR2, r8
-	mtspr	SPRN_SIER, r9
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	mtspr	SPRN_MMCR0, r3
-	isync
-23:
+	bl	kvmhv_load_host_pmu
 
 	/*
 	 * Reload DEC.  HDEC interrupts were disabled when
@@ -322,17 +287,19 @@
 	b	kvmhv_switch_to_host
 
 /*
- * We come in here when wakened from nap mode.
- * Relocation is off and most register values are lost.
- * r13 points to the PACA.
+ * We come in here when wakened from Linux offline idle code.
+ * Relocation is off
  * r3 contains the SRR1 wakeup value, SRR1 is trashed.
  */
-	.globl	kvm_start_guest
-kvm_start_guest:
-	/* Set runlatch bit the minute you wake up from nap */
-	mfspr	r0, SPRN_CTRLF
-	ori 	r0, r0, 1
-	mtspr	SPRN_CTRLT, r0
+_GLOBAL(idle_kvm_start_guest)
+	ld	r4,PACAEMERGSP(r13)
+	mfcr	r5
+	mflr	r0
+	std	r1,0(r4)
+	std	r5,8(r4)
+	std	r0,16(r4)
+	subi	r1,r4,STACK_FRAME_OVERHEAD
+	SAVE_NVGPRS(r1)
 
 	/*
 	 * Could avoid this and pass it through in r3. For now,
@@ -340,27 +307,23 @@
 	 */
 	mtspr	SPRN_SRR1,r3
 
-	ld	r2,PACATOC(r13)
-
 	li	r0,0
 	stb	r0,PACA_FTRACE_ENABLED(r13)
 
 	li	r0,KVM_HWTHREAD_IN_KVM
 	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 
-	/* NV GPR values from power7_idle() will no longer be valid */
-	li	r0,1
-	stb	r0,PACA_NAPSTATELOST(r13)
-
-	/* were we napping due to cede? */
+	/* kvm cede / napping does not come through here */
 	lbz	r0,HSTATE_NAPPING(r13)
-	cmpwi	r0,NAPPING_CEDE
-	beq	kvm_end_cede
-	cmpwi	r0,NAPPING_NOVCPU
-	beq	kvm_novcpu_wakeup
+	twnei	r0,0
 
-	ld	r1,PACAEMERGSP(r13)
-	subi	r1,r1,STACK_FRAME_OVERHEAD
+	b	1f
+
+kvm_unsplit_wakeup:
+	li	r0, 0
+	stb	r0, HSTATE_NAPPING(r13)
+
+1:
 
 	/*
 	 * We weren't napping due to cede, so this must be a secondary
@@ -469,19 +432,25 @@
 	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
 	cmpwi	r3, 0
 	bne	54f
-/*
- * We jump to pnv_wakeup_loss, which will return to the caller
- * of power7_nap in the powernv cpu offline loop.  The value we
- * put in r3 becomes the return value for power7_nap. pnv_wakeup_loss
- * requires SRR1 in r12.
- */
+
+	/*
+	 * Jump to idle_return_gpr_loss, which returns to the
+	 * idle_kvm_start_guest caller.
+	 */
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
-	li	r3, 0
-	mfspr	r12,SPRN_SRR1
-	b	pnv_wakeup_loss
+	/* set up r3 for return */
+	mfspr	r3,SPRN_SRR1
+	REST_NVGPRS(r1)
+	addi	r1, r1, STACK_FRAME_OVERHEAD
+	ld	r0, 16(r1)
+	ld	r5, 8(r1)
+	ld	r1, 0(r1)
+	mtlr	r0
+	mtcr	r5
+	blr
 
 53:	HMT_LOW
 	ld	r5, HSTATE_KVM_VCORE(r13)
@@ -566,6 +535,8 @@
 	lbz	r0, KVM_SPLIT_DO_NAP(r3)
 	cmpwi	r0, 0
 	beq	57f
+	li	r3, NAPPING_UNSPLIT
+	stb	r3, HSTATE_NAPPING(r13)
 	li	r3, (LPCR_PECEDH | LPCR_PECE0) >> 4
 	mfspr	r5, SPRN_LPCR
 	rlwimi	r5, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
@@ -613,11 +584,8 @@
 1:
 #endif
 
-	/* Use cr7 as an indication of radix mode */
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	ld	r9, VCORE_KVM(r5)	/* pointer to struct kvm */
-	lbz	r0, KVM_RADIX(r9)
-	cmpwi	cr7, r0, 0
 
 	/*
 	 * POWER7/POWER8 host -> guest partition switch code.
@@ -640,9 +608,6 @@
 	cmpwi	r6,0
 	bne	10f
 
-	/* Radix has already switched LPID and flushed core TLB */
-	bne	cr7, 22f
-
 	lwz	r7,KVM_LPID(r9)
 BEGIN_FTR_SECTION
 	ld	r6,KVM_SDR1(r9)
@@ -654,41 +619,13 @@
 	mtspr	SPRN_LPID,r7
 	isync
 
-	/* See if we need to flush the TLB. Hash has to be done in RM */
-	lhz	r6,PACAPACAINDEX(r13)	/* test_bit(cpu, need_tlb_flush) */
-BEGIN_FTR_SECTION
-	/*
-	 * On POWER9, individual threads can come in here, but the
-	 * TLB is shared between the 4 threads in a core, hence
-	 * invalidating on one thread invalidates for all.
-	 * Thus we make all 4 threads use the same bit here.
-	 */
-	clrrdi	r6,r6,2
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	clrldi	r7,r6,64-6		/* extract bit number (6 bits) */
-	srdi	r6,r6,6			/* doubleword number */
-	sldi	r6,r6,3			/* address offset */
-	add	r6,r6,r9
-	addi	r6,r6,KVM_NEED_FLUSH	/* dword in kvm->arch.need_tlb_flush */
-	li	r8,1
-	sld	r8,r8,r7
-	ld	r7,0(r6)
-	and.	r7,r7,r8
-	beq	22f
-	/* Flush the TLB of any entries for this LPID */
-	lwz	r0,KVM_TLB_SETS(r9)
-	mtctr	r0
-	li	r7,0x800		/* IS field = 0b10 */
-	ptesync
-	li	r0,0			/* RS for P9 version of tlbiel */
-28:	tlbiel	r7			/* On P9, rs=0, RIC=0, PRS=0, R=0 */
-	addi	r7,r7,0x1000
-	bdnz	28b
-	ptesync
-23:	ldarx	r7,0,r6			/* clear the bit after TLB flushed */
-	andc	r7,r7,r8
-	stdcx.	r7,0,r6
-	bne	23b
+	/* See if we need to flush the TLB. */
+	mr	r3, r9			/* kvm pointer */
+	lhz	r4, PACAPACAINDEX(r13)	/* physical cpu number */
+	li	r5, 0			/* nested vcpu pointer */
+	bl	kvmppc_check_need_tlb_flush
+	nop
+	ld	r5, HSTATE_KVM_VCORE(r13)
 
 	/* Add timebase offset onto timebase */
 22:	ld	r8,VCORE_TB_OFFSET(r5)
@@ -708,8 +645,10 @@
 
 	/* Load guest PCR value to select appropriate compat mode */
 37:	ld	r7, VCORE_PCR(r5)
-	cmpdi	r7, 0
+	LOAD_REG_IMMEDIATE(r6, PCR_MASK)
+	cmpld	r7, r6
 	beq	38f
+	or	r7, r7, r6
 	mtspr	SPRN_PCR, r7
 38:
 
@@ -760,11 +699,9 @@
 	mfspr	r5, SPRN_TIDR
 	mfspr	r6, SPRN_PSSCR
 	mfspr	r7, SPRN_PID
-	mfspr	r8, SPRN_IAMR
 	std	r5, STACK_SLOT_TID(r1)
 	std	r6, STACK_SLOT_PSSCR(r1)
 	std	r7, STACK_SLOT_PID(r1)
-	std	r8, STACK_SLOT_IAMR(r1)
 	mfspr	r5, SPRN_HFSCR
 	std	r5, STACK_SLOT_HFSCR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
@@ -772,11 +709,18 @@
 	mfspr	r5, SPRN_CIABR
 	mfspr	r6, SPRN_DAWR
 	mfspr	r7, SPRN_DAWRX
+	mfspr	r8, SPRN_IAMR
 	std	r5, STACK_SLOT_CIABR(r1)
 	std	r6, STACK_SLOT_DAWR(r1)
 	std	r7, STACK_SLOT_DAWRX(r1)
+	std	r8, STACK_SLOT_IAMR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
+	mfspr	r5, SPRN_AMR
+	std	r5, STACK_SLOT_AMR(r1)
+	mfspr	r6, SPRN_UAMOR
+	std	r6, STACK_SLOT_UAMOR(r1)
+
 BEGIN_FTR_SECTION
 	/* Set partition DABR */
 	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -796,66 +740,23 @@
 	b	91f
 END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
-	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
+	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
 	 */
 	mr      r3, r4
 	ld      r4, VCPU_MSR(r3)
+	li	r5, 0			/* don't preserve non-vol regs */
 	bl	kvmppc_restore_tm_hv
+	nop
 	ld	r4, HSTATE_KVM_VCPU(r13)
 91:
 #endif
 
-	/* Load guest PMU registers */
-	/* R4 is live here (vcpu pointer) */
-	li	r3, 1
-	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
-	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
-	isync
-BEGIN_FTR_SECTION
-	ld	r3, VCPU_MMCR(r4)
-	andi.	r5, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
-	cmpwi	r5, MMCR0_PMAO
-	beql	kvmppc_fix_pmao
-END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
-	lwz	r3, VCPU_PMC(r4)	/* always load up guest PMU registers */
-	lwz	r5, VCPU_PMC + 4(r4)	/* to prevent information leak */
-	lwz	r6, VCPU_PMC + 8(r4)
-	lwz	r7, VCPU_PMC + 12(r4)
-	lwz	r8, VCPU_PMC + 16(r4)
-	lwz	r9, VCPU_PMC + 20(r4)
-	mtspr	SPRN_PMC1, r3
-	mtspr	SPRN_PMC2, r5
-	mtspr	SPRN_PMC3, r6
-	mtspr	SPRN_PMC4, r7
-	mtspr	SPRN_PMC5, r8
-	mtspr	SPRN_PMC6, r9
-	ld	r3, VCPU_MMCR(r4)
-	ld	r5, VCPU_MMCR + 8(r4)
-	ld	r6, VCPU_MMCR + 16(r4)
-	ld	r7, VCPU_SIAR(r4)
-	ld	r8, VCPU_SDAR(r4)
-	mtspr	SPRN_MMCR1, r5
-	mtspr	SPRN_MMCRA, r6
-	mtspr	SPRN_SIAR, r7
-	mtspr	SPRN_SDAR, r8
-BEGIN_FTR_SECTION
-	ld	r5, VCPU_MMCR + 24(r4)
-	ld	r6, VCPU_SIER(r4)
-	mtspr	SPRN_MMCR2, r5
-	mtspr	SPRN_SIER, r6
-BEGIN_FTR_SECTION_NESTED(96)
-	lwz	r7, VCPU_PMC + 24(r4)
-	lwz	r8, VCPU_PMC + 28(r4)
-	ld	r9, VCPU_MMCR + 32(r4)
-	mtspr	SPRN_SPMC1, r7
-	mtspr	SPRN_SPMC2, r8
-	mtspr	SPRN_MMCRS, r9
-END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	mtspr	SPRN_MMCR0, r3
-	isync
+	/* Load guest PMU registers; r4 = vcpu pointer here */
+	mr	r3, r4
+	bl	kvmhv_load_guest_pmu
 
 	/* Load up FP, VMX and VSX registers */
+	ld	r4, HSTATE_KVM_VCPU(r13)
 	bl	kvmppc_load_fp
 
 	ld	r14, VCPU_GPR(R14)(r4)
@@ -892,18 +793,21 @@
 	mtspr	SPRN_IAMR, r5
 	mtspr	SPRN_PSPB, r6
 	mtspr	SPRN_FSCR, r7
-	ld	r5, VCPU_DAWR(r4)
-	ld	r6, VCPU_DAWRX(r4)
-	ld	r7, VCPU_CIABR(r4)
-	ld	r8, VCPU_TAR(r4)
 	/*
 	 * Handle broken DAWR case by not writing it. This means we
 	 * can still store the DAWR register for migration.
 	 */
-BEGIN_FTR_SECTION
+	LOAD_REG_ADDR(r5, dawr_force_enable)
+	lbz	r5, 0(r5)
+	cmpdi	r5, 0
+	beq	1f
+	ld	r5, VCPU_DAWR(r4)
+	ld	r6, VCPU_DAWRX(r4)
 	mtspr	SPRN_DAWR, r5
 	mtspr	SPRN_DAWRX, r6
-END_FTR_SECTION_IFSET(CPU_FTR_DAWR)
+1:
+	ld	r7, VCPU_CIABR(r4)
+	ld	r8, VCPU_TAR(r4)
 	mtspr	SPRN_CIABR, r7
 	mtspr	SPRN_TAR, r8
 	ld	r5, VCPU_IC(r4)
@@ -1039,17 +943,29 @@
 
 #ifdef CONFIG_KVM_XICS
 	/* We are entering the guest on that thread, push VCPU to XIVE */
-	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
-	cmpldi	cr0, r10, 0
-	beq	no_xive
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
+	lwz	r8, VCPU_XIVE_CAM_WORD(r4)
+	cmpwi	r8, 0
+	beq	no_xive
+	li	r7, TM_QW1_OS + TM_WORD2
+	mfmsr	r0
+	andi.	r0, r0, MSR_DR		/* in real mode? */
+	beq	2f
+	ld	r10, HSTATE_XIVE_TIMA_VIRT(r13)
+	cmpldi	cr1, r10, 0
+	beq     cr1, no_xive
+	eieio
+	stdx	r11,r9,r10
+	stwx	r8,r7,r10
+	b	3f
+2:	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
+	cmpldi	cr1, r10, 0
+	beq	cr1, no_xive
 	eieio
 	stdcix	r11,r9,r10
-	lwz	r11, VCPU_XIVE_CAM_WORD(r4)
-	li	r9, TM_QW1_OS + TM_WORD2
-	stwcix	r11,r9,r10
-	li	r9, 1
+	stwcix	r8,r7,r10
+3:	li	r9, 1
 	stb	r9, VCPU_XIVE_PUSHED(r4)
 	eieio
 
@@ -1068,12 +984,16 @@
 	 * on, we mask it.
 	 */
 	lbz	r0, VCPU_XIVE_ESC_ON(r4)
-	cmpwi	r0,0
-	beq	1f
-	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
+	cmpwi	cr1, r0,0
+	beq	cr1, 1f
 	li	r9, XIVE_ESB_SET_PQ_01
+	beq	4f			/* in real mode? */
+	ld	r10, VCPU_XIVE_ESC_VADDR(r4)
+	ldx	r0, r10, r9
+	b	5f
+4:	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
 	ldcix	r0, r10, r9
-	sync
+5:	sync
 
 	/* We have a possible subtle race here: The escalation interrupt might
 	 * have fired and be on its way to the host queue while we mask it,
@@ -1100,73 +1020,40 @@
 no_xive:
 #endif /* CONFIG_KVM_XICS */
 
-deliver_guest_interrupt:
-	ld	r6, VCPU_CTR(r4)
-	ld	r7, VCPU_XER(r4)
+	li	r0, 0
+	stw	r0, STACK_SLOT_SHORT_PATH(r1)
 
-	mtctr	r6
-	mtxer	r7
-
-kvmppc_cede_reentry:		/* r4 = vcpu, r13 = paca */
-	ld	r10, VCPU_PC(r4)
-	ld	r11, VCPU_MSR(r4)
+deliver_guest_interrupt:	/* r4 = vcpu, r13 = paca */
+	/* Check if we can deliver an external or decrementer interrupt now */
+	ld	r0, VCPU_PENDING_EXC(r4)
+BEGIN_FTR_SECTION
+	/* On POWER9, also check for emulated doorbell interrupt */
+	lbz	r3, VCPU_DBELL_REQ(r4)
+	or	r0, r0, r3
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+	cmpdi	r0, 0
+	beq	71f
+	mr	r3, r4
+	bl	kvmppc_guest_entry_inject_int
+	ld	r4, HSTATE_KVM_VCPU(r13)
+71:
 	ld	r6, VCPU_SRR0(r4)
 	ld	r7, VCPU_SRR1(r4)
 	mtspr	SPRN_SRR0, r6
 	mtspr	SPRN_SRR1, r7
 
+fast_guest_entry_c:
+	ld	r10, VCPU_PC(r4)
+	ld	r11, VCPU_MSR(r4)
 	/* r11 = vcpu->arch.msr & ~MSR_HV */
 	rldicl	r11, r11, 63 - MSR_HV_LG, 1
 	rotldi	r11, r11, 1 + MSR_HV_LG
 	ori	r11, r11, MSR_ME
 
-	/* Check if we can deliver an external or decrementer interrupt now */
-	ld	r0, VCPU_PENDING_EXC(r4)
-	rldicl	r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
-	cmpdi	cr1, r0, 0
-	andi.	r8, r11, MSR_EE
-	mfspr	r8, SPRN_LPCR
-	/* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
-	rldimi	r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
-	mtspr	SPRN_LPCR, r8
-	isync
-	beq	5f
-	li	r0, BOOK3S_INTERRUPT_EXTERNAL
-	bne	cr1, 12f
-	mfspr	r0, SPRN_DEC
-BEGIN_FTR_SECTION
-	/* On POWER9 check whether the guest has large decrementer enabled */
-	andis.	r8, r8, LPCR_LD@h
-	bne	15f
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	extsw	r0, r0
-15:	cmpdi	r0, 0
-	li	r0, BOOK3S_INTERRUPT_DECREMENTER
-	bge	5f
-
-12:	mtspr	SPRN_SRR0, r10
-	mr	r10,r0
-	mtspr	SPRN_SRR1, r11
-	mr	r9, r4
-	bl	kvmppc_msr_interrupt
-5:
-BEGIN_FTR_SECTION
-	b	fast_guest_return
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-	/* On POWER9, check for pending doorbell requests */
-	lbz	r0, VCPU_DBELL_REQ(r4)
-	cmpwi	r0, 0
-	beq	fast_guest_return
-	ld	r5, HSTATE_KVM_VCORE(r13)
-	/* Set DPDES register so the CPU will take a doorbell interrupt */
-	li	r0, 1
-	mtspr	SPRN_DPDES, r0
-	std	r0, VCORE_DPDES(r5)
-	/* Make sure other cpus see vcore->dpdes set before dbell req clear */
-	lwsync
-	/* Clear the pending doorbell request */
-	li	r0, 0
-	stb	r0, VCPU_DBELL_REQ(r4)
+	ld	r6, VCPU_CTR(r4)
+	ld	r7, VCPU_XER(r4)
+	mtctr	r6
+	mtxer	r7
 
 /*
  * Required state:
@@ -1202,16 +1089,10 @@
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	ld	r5, VCPU_LR(r4)
-	lwz	r6, VCPU_CR(r4)
 	mtlr	r5
-	mtcr	r6
 
 	ld	r1, VCPU_GPR(R1)(r4)
-	ld	r2, VCPU_GPR(R2)(r4)
-	ld	r3, VCPU_GPR(R3)(r4)
 	ld	r5, VCPU_GPR(R5)(r4)
-	ld	r6, VCPU_GPR(R6)(r4)
-	ld	r7, VCPU_GPR(R7)(r4)
 	ld	r8, VCPU_GPR(R8)(r4)
 	ld	r9, VCPU_GPR(R9)(r4)
 	ld	r10, VCPU_GPR(R10)(r4)
@@ -1229,10 +1110,119 @@
 	mtspr	SPRN_HDSISR, r0
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
+	ld	r6, VCPU_KVM(r4)
+	lbz	r7, KVM_SECURE_GUEST(r6)
+	cmpdi	r7, 0
+	ld	r6, VCPU_GPR(R6)(r4)
+	ld	r7, VCPU_GPR(R7)(r4)
+	bne	ret_to_ultra
+
+	lwz	r0, VCPU_CR(r4)
+	mtcr	r0
+
 	ld	r0, VCPU_GPR(R0)(r4)
+	ld	r2, VCPU_GPR(R2)(r4)
+	ld	r3, VCPU_GPR(R3)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
 	HRFI_TO_GUEST
 	b	.
+/*
+ * Use UV_RETURN ultracall to return control back to the Ultravisor after
+ * processing an hypercall or interrupt that was forwarded (a.k.a. reflected)
+ * to the Hypervisor.
+ *
+ * All registers have already been loaded, except:
+ *   R0 = hcall result
+ *   R2 = SRR1, so UV can detect a synthesized interrupt (if any)
+ *   R3 = UV_RETURN
+ */
+ret_to_ultra:
+	lwz	r0, VCPU_CR(r4)
+	mtcr	r0
+
+	ld	r0, VCPU_GPR(R3)(r4)
+	mfspr	r2, SPRN_SRR1
+	li	r3, 0
+	ori	r3, r3, UV_RETURN
+	ld	r4, VCPU_GPR(R4)(r4)
+	sc	2
+
+/*
+ * Enter the guest on a P9 or later system where we have exactly
+ * one vcpu per vcore and we don't need to go to real mode
+ * (which implies that host and guest are both using radix MMU mode).
+ * r3 = vcpu pointer
+ * Most SPRs and all the VSRs have been loaded already.
+ */
+_GLOBAL(__kvmhv_vcpu_entry_p9)
+EXPORT_SYMBOL_GPL(__kvmhv_vcpu_entry_p9)
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu	r1, -SFS(r1)
+
+	li	r0, 1
+	stw	r0, STACK_SLOT_SHORT_PATH(r1)
+
+	std	r3, HSTATE_KVM_VCPU(r13)
+	mfcr	r4
+	stw	r4, SFS+8(r1)
+
+	std	r1, HSTATE_HOST_R1(r13)
+
+	reg = 14
+	.rept	18
+	std	reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1)
+	reg = reg + 1
+	.endr
+
+	reg = 14
+	.rept	18
+	ld	reg, __VCPU_GPR(reg)(r3)
+	reg = reg + 1
+	.endr
+
+	mfmsr	r10
+	std	r10, HSTATE_HOST_MSR(r13)
+
+	mr	r4, r3
+	b	fast_guest_entry_c
+guest_exit_short_path:
+
+	li	r0, KVM_GUEST_MODE_NONE
+	stb	r0, HSTATE_IN_GUEST(r13)
+
+	reg = 14
+	.rept	18
+	std	reg, __VCPU_GPR(reg)(r9)
+	reg = reg + 1
+	.endr
+
+	reg = 14
+	.rept	18
+	ld	reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1)
+	reg = reg + 1
+	.endr
+
+	lwz	r4, SFS+8(r1)
+	mtcr	r4
+
+	mr	r3, r12		/* trap number */
+
+	addi	r1, r1, SFS
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+
+	/* If we are in real mode, do a rfid to get back to the caller */
+	mfmsr	r4
+	andi.	r5, r4, MSR_IR
+	bnelr
+	rldicl	r5, r4, 64 - MSR_TS_S_LG, 62	/* extract TS field */
+	mtspr	SPRN_SRR0, r0
+	ld	r10, HSTATE_HOST_MSR(r13)
+	rldimi	r10, r5, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+	mtspr	SPRN_SRR1, r10
+	RFI_TO_KERNEL
+	b	.
 
 secondary_too_late:
 	li	r12, 0
@@ -1313,7 +1303,7 @@
 	std	r3, VCPU_GPR(R12)(r9)
 	/* CR is in the high half of r12 */
 	srdi	r4, r12, 32
-	stw	r4, VCPU_CR(r9)
+	std	r4, VCPU_CR(r9)
 BEGIN_FTR_SECTION
 	ld	r3, HSTATE_CFAR(r13)
 	std	r3, VCPU_CFAR(r9)
@@ -1387,18 +1377,26 @@
 	std	r3, VCPU_CTR(r9)
 	std	r4, VCPU_XER(r9)
 
+	/* Save more register state  */
+	mfdar	r3
+	mfdsisr	r4
+	std	r3, VCPU_DAR(r9)
+	stw	r4, VCPU_DSISR(r9)
+
+	/* If this is a page table miss then see if it's theirs or ours */
+	cmpwi	r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
+	beq	kvmppc_hdsi
+	std	r3, VCPU_FAULT_DAR(r9)
+	stw	r4, VCPU_FAULT_DSISR(r9)
+	cmpwi	r12, BOOK3S_INTERRUPT_H_INST_STORAGE
+	beq	kvmppc_hisi
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	/* For softpatch interrupt, go off and do TM instruction emulation */
 	cmpwi	r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
 	beq	kvmppc_tm_emul
 #endif
 
-	/* If this is a page table miss then see if it's theirs or ours */
-	cmpwi	r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
-	beq	kvmppc_hdsi
-	cmpwi	r12, BOOK3S_INTERRUPT_H_INST_STORAGE
-	beq	kvmppc_hisi
-
 	/* See if this is a leftover HDEC interrupt */
 	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
 	bne	2f
@@ -1418,10 +1416,14 @@
 BEGIN_FTR_SECTION
 	PPC_MSGSYNC
 	lwsync
+	/* always exit if we're running a nested guest */
+	ld	r0, VCPU_NESTED(r9)
+	cmpdi	r0, 0
+	bne	guest_exit_cont
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r0, HSTATE_HOST_IPI(r13)
 	cmpwi	r0, 0
-	beq	4f
+	beq	maybe_reenter_guest
 	b	guest_exit_cont
 3:
 	/* If it's a hypervisor facility unavailable interrupt, save HFSCR */
@@ -1433,82 +1435,16 @@
 14:
 	/* External interrupt ? */
 	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
-	bne+	guest_exit_cont
-
-	/* External interrupt, first check for host_ipi. If this is
-	 * set, we know the host wants us out so let's do it now
-	 */
-	bl	kvmppc_read_intr
-
-	/*
-	 * Restore the active volatile registers after returning from
-	 * a C function.
-	 */
-	ld	r9, HSTATE_KVM_VCPU(r13)
-	li	r12, BOOK3S_INTERRUPT_EXTERNAL
-
-	/*
-	 * kvmppc_read_intr return codes:
-	 *
-	 * Exit to host (r3 > 0)
-	 *   1 An interrupt is pending that needs to be handled by the host
-	 *     Exit guest and return to host by branching to guest_exit_cont
-	 *
-	 *   2 Passthrough that needs completion in the host
-	 *     Exit guest and return to host by branching to guest_exit_cont
-	 *     However, we also set r12 to BOOK3S_INTERRUPT_HV_RM_HARD
-	 *     to indicate to the host to complete handling the interrupt
-	 *
-	 * Before returning to guest, we check if any CPU is heading out
-	 * to the host and if so, we head out also. If no CPUs are heading
-	 * check return values <= 0.
-	 *
-	 * Return to guest (r3 <= 0)
-	 *  0 No external interrupt is pending
-	 * -1 A guest wakeup IPI (which has now been cleared)
-	 *    In either case, we return to guest to deliver any pending
-	 *    guest interrupts.
-	 *
-	 * -2 A PCI passthrough external interrupt was handled
-	 *    (interrupt was delivered directly to guest)
-	 *    Return to guest to deliver any pending guest interrupts.
-	 */
-
-	cmpdi	r3, 1
-	ble	1f
-
-	/* Return code = 2 */
-	li	r12, BOOK3S_INTERRUPT_HV_RM_HARD
-	stw	r12, VCPU_TRAP(r9)
-	b	guest_exit_cont
-
-1:	/* Return code <= 1 */
-	cmpdi	r3, 0
-	bgt	guest_exit_cont
-
-	/* Return code <= 0 */
-4:	ld	r5, HSTATE_KVM_VCORE(r13)
-	lwz	r0, VCORE_ENTRY_EXIT(r5)
-	cmpwi	r0, 0x100
-	mr	r4, r9
-	blt	deliver_guest_interrupt
-
-guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
-	/* Save more register state  */
-	mfdar	r6
-	mfdsisr	r7
-	std	r6, VCPU_DAR(r9)
-	stw	r7, VCPU_DSISR(r9)
-	/* don't overwrite fault_dar/fault_dsisr if HDSI */
-	cmpwi	r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
-	beq	mc_cont
-	std	r6, VCPU_FAULT_DAR(r9)
-	stw	r7, VCPU_FAULT_DSISR(r9)
-
+	beq	kvmppc_guest_external
 	/* See if it is a machine check */
 	cmpwi	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
 	beq	machine_check_realmode
-mc_cont:
+	/* Or a hypervisor maintenance interrupt */
+	cmpwi	r12, BOOK3S_INTERRUPT_HMI
+	beq	hmi_realmode
+
+guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
+
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
 	addi	r3, r9, VCPU_TB_RMEXIT
 	mr	r4, r9
@@ -1552,6 +1488,18 @@
 1:
 #endif /* CONFIG_KVM_XICS */
 
+	/*
+	 * Possibly flush the link stack here, before we do a blr in
+	 * guest_exit_short_path.
+	 */
+1:	nop
+	patch_site 1b patch__call_kvm_flush_link_stack
+
+	/* If we came in through the P9 short path, go back out to C now */
+	lwz	r0, STACK_SLOT_SHORT_PATH(r1)
+	cmpwi	r0, 0
+	bne	guest_exit_short_path
+
 	/* For hash guest, read the guest SLB and save it away */
 	ld	r5, VCPU_KVM(r9)
 	lbz	r0, KVM_RADIX(r5)
@@ -1713,22 +1661,25 @@
 	mtspr	SPRN_PSPB, r0
 	mtspr	SPRN_WORT, r0
 BEGIN_FTR_SECTION
-	mtspr	SPRN_IAMR, r0
 	mtspr	SPRN_TCSCR, r0
 	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
 	li	r0, 1
 	sldi	r0, r0, 31
 	mtspr	SPRN_MMCRS, r0
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-8:
 
-	/* Save and reset AMR and UAMOR before turning on the MMU */
+	/* Save and restore AMR, IAMR and UAMOR before turning on the MMU */
+	ld	r8, STACK_SLOT_IAMR(r1)
+	mtspr	SPRN_IAMR, r8
+
+8:	/* Power7 jumps back in here */
 	mfspr	r5,SPRN_AMR
 	mfspr	r6,SPRN_UAMOR
 	std	r5,VCPU_AMR(r9)
 	std	r6,VCPU_UAMOR(r9)
-	li	r6,0
-	mtspr	SPRN_AMR,r6
+	ld	r5,STACK_SLOT_AMR(r1)
+	ld	r6,STACK_SLOT_UAMOR(r1)
+	mtspr	SPRN_AMR, r5
 	mtspr	SPRN_UAMOR, r6
 
 	/* Switch DSCR back to host value */
@@ -1780,11 +1731,13 @@
 	b	91f
 END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
-	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
+	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
 	 */
 	mr      r3, r9
 	ld      r4, VCPU_MSR(r3)
+	li	r5, 0			/* don't preserve non-vol regs */
 	bl	kvmppc_save_tm_hv
+	nop
 	ld	r9, HSTATE_KVM_VCPU(r13)
 91:
 #endif
@@ -1802,83 +1755,12 @@
 25:
 	/* Save PMU registers if requested */
 	/* r8 and cr0.eq are live here */
-BEGIN_FTR_SECTION
-	/*
-	 * POWER8 seems to have a hardware bug where setting
-	 * MMCR0[PMAE] along with MMCR0[PMC1CE] and/or MMCR0[PMCjCE]
-	 * when some counters are already negative doesn't seem
-	 * to cause a performance monitor alert (and hence interrupt).
-	 * The effect of this is that when saving the PMU state,
-	 * if there is no PMU alert pending when we read MMCR0
-	 * before freezing the counters, but one becomes pending
-	 * before we read the counters, we lose it.
-	 * To work around this, we need a way to freeze the counters
-	 * before reading MMCR0.  Normally, freezing the counters
-	 * is done by writing MMCR0 (to set MMCR0[FC]) which
-	 * unavoidably writes MMCR0[PMA0] as well.  On POWER8,
-	 * we can also freeze the counters using MMCR2, by writing
-	 * 1s to all the counter freeze condition bits (there are
-	 * 9 bits each for 6 counters).
-	 */
-	li	r3, -1			/* set all freeze bits */
-	clrrdi	r3, r3, 10
-	mfspr	r10, SPRN_MMCR2
-	mtspr	SPRN_MMCR2, r3
-	isync
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	li	r3, 1
-	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
-	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
-	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
-	mfspr	r6, SPRN_MMCRA
-	/* Clear MMCRA in order to disable SDAR updates */
-	li	r7, 0
-	mtspr	SPRN_MMCRA, r7
-	isync
+	mr	r3, r9
+	li	r4, 1
 	beq	21f			/* if no VPA, save PMU stuff anyway */
-	lbz	r7, LPPACA_PMCINUSE(r8)
-	cmpwi	r7, 0			/* did they ask for PMU stuff to be saved? */
-	bne	21f
-	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
-	b	22f
-21:	mfspr	r5, SPRN_MMCR1
-	mfspr	r7, SPRN_SIAR
-	mfspr	r8, SPRN_SDAR
-	std	r4, VCPU_MMCR(r9)
-	std	r5, VCPU_MMCR + 8(r9)
-	std	r6, VCPU_MMCR + 16(r9)
-BEGIN_FTR_SECTION
-	std	r10, VCPU_MMCR + 24(r9)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-	std	r7, VCPU_SIAR(r9)
-	std	r8, VCPU_SDAR(r9)
-	mfspr	r3, SPRN_PMC1
-	mfspr	r4, SPRN_PMC2
-	mfspr	r5, SPRN_PMC3
-	mfspr	r6, SPRN_PMC4
-	mfspr	r7, SPRN_PMC5
-	mfspr	r8, SPRN_PMC6
-	stw	r3, VCPU_PMC(r9)
-	stw	r4, VCPU_PMC + 4(r9)
-	stw	r5, VCPU_PMC + 8(r9)
-	stw	r6, VCPU_PMC + 12(r9)
-	stw	r7, VCPU_PMC + 16(r9)
-	stw	r8, VCPU_PMC + 20(r9)
-BEGIN_FTR_SECTION
-	mfspr	r5, SPRN_SIER
-	std	r5, VCPU_SIER(r9)
-BEGIN_FTR_SECTION_NESTED(96)
-	mfspr	r6, SPRN_SPMC1
-	mfspr	r7, SPRN_SPMC2
-	mfspr	r8, SPRN_MMCRS
-	stw	r6, VCPU_PMC + 24(r9)
-	stw	r7, VCPU_PMC + 28(r9)
-	std	r8, VCPU_MMCR + 32(r9)
-	lis	r4, 0x8000
-	mtspr	SPRN_MMCRS, r4
-END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-22:
+	lbz	r4, LPPACA_PMCINUSE(r8)
+21:	bl	kvmhv_save_guest_pmu
+	ld	r9, HSTATE_KVM_VCPU(r13)
 
 	/* Restore host values of some registers */
 BEGIN_FTR_SECTION
@@ -1897,11 +1779,9 @@
 	ld	r5, STACK_SLOT_TID(r1)
 	ld	r6, STACK_SLOT_PSSCR(r1)
 	ld	r7, STACK_SLOT_PID(r1)
-	ld	r8, STACK_SLOT_IAMR(r1)
 	mtspr	SPRN_TIDR, r5
 	mtspr	SPRN_PSSCR, r6
 	mtspr	SPRN_PID, r7
-	mtspr	SPRN_IAMR, r8
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 #ifdef CONFIG_PPC_RADIX_MMU
@@ -2010,24 +1890,6 @@
 	mtspr	SPRN_DPDES, r8
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
-	/* If HMI, call kvmppc_realmode_hmi_handler() */
-	lwz	r12, STACK_SLOT_TRAP(r1)
-	cmpwi	r12, BOOK3S_INTERRUPT_HMI
-	bne	27f
-	bl	kvmppc_realmode_hmi_handler
-	nop
-	cmpdi	r3, 0
-	/*
-	 * At this point kvmppc_realmode_hmi_handler may have resync-ed
-	 * the TB, and if it has, we must not subtract the guest timebase
-	 * offset from the timebase. So, skip it.
-	 *
-	 * Also, do not call kvmppc_subcore_exit_guest() because it has
-	 * been invoked as part of kvmppc_realmode_hmi_handler().
-	 */
-	beq	30f
-
-27:
 	/* Subtract timebase offset from timebase */
 	ld	r8, VCORE_TB_OFFSET_APPL(r5)
 	cmpdi	r8,0
@@ -2045,19 +1907,29 @@
 	addis	r8,r8,0x100		/* if so, increment upper 40 bits */
 	mtspr	SPRN_TBU40,r8
 
-17:	bl	kvmppc_subcore_exit_guest
+17:
+	/*
+	 * If this is an HMI, we called kvmppc_realmode_hmi_handler
+	 * above, which may or may not have already called
+	 * kvmppc_subcore_exit_guest.  Fortunately, all that
+	 * kvmppc_subcore_exit_guest does is clear a flag, so calling
+	 * it again here is benign even if kvmppc_realmode_hmi_handler
+	 * has already called it.
+	 */
+	bl	kvmppc_subcore_exit_guest
 	nop
 30:	ld	r5,HSTATE_KVM_VCORE(r13)
 	ld	r4,VCORE_KVM(r5)	/* pointer to struct kvm */
 
 	/* Reset PCR */
 	ld	r0, VCORE_PCR(r5)
-	cmpdi	r0, 0
+	LOAD_REG_IMMEDIATE(r6, PCR_MASK)
+	cmpld	r0, r6
 	beq	18f
-	li	r0, 0
-	mtspr	SPRN_PCR, r0
+	mtspr	SPRN_PCR, r6
 18:
 	/* Signal secondary CPUs to continue */
+	li	r0, 0
 	stb	r0,VCORE_IN_GUEST(r5)
 19:	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
@@ -2099,6 +1971,89 @@
 	mtlr	r0
 	blr
 
+.balign 32
+.global kvm_flush_link_stack
+kvm_flush_link_stack:
+	/* Save LR into r0 */
+	mflr	r0
+
+	/* Flush the link stack. On Power8 it's up to 32 entries in size. */
+	.rept 32
+	bl	.+4
+	.endr
+
+	/* And on Power9 it's up to 64. */
+BEGIN_FTR_SECTION
+	.rept 32
+	bl	.+4
+	.endr
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+	/* Restore LR */
+	mtlr	r0
+	blr
+
+kvmppc_guest_external:
+	/* External interrupt, first check for host_ipi. If this is
+	 * set, we know the host wants us out so let's do it now
+	 */
+	bl	kvmppc_read_intr
+
+	/*
+	 * Restore the active volatile registers after returning from
+	 * a C function.
+	 */
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	li	r12, BOOK3S_INTERRUPT_EXTERNAL
+
+	/*
+	 * kvmppc_read_intr return codes:
+	 *
+	 * Exit to host (r3 > 0)
+	 *   1 An interrupt is pending that needs to be handled by the host
+	 *     Exit guest and return to host by branching to guest_exit_cont
+	 *
+	 *   2 Passthrough that needs completion in the host
+	 *     Exit guest and return to host by branching to guest_exit_cont
+	 *     However, we also set r12 to BOOK3S_INTERRUPT_HV_RM_HARD
+	 *     to indicate to the host to complete handling the interrupt
+	 *
+	 * Before returning to guest, we check if any CPU is heading out
+	 * to the host and if so, we head out also. If no CPUs are heading
+	 * check return values <= 0.
+	 *
+	 * Return to guest (r3 <= 0)
+	 *  0 No external interrupt is pending
+	 * -1 A guest wakeup IPI (which has now been cleared)
+	 *    In either case, we return to guest to deliver any pending
+	 *    guest interrupts.
+	 *
+	 * -2 A PCI passthrough external interrupt was handled
+	 *    (interrupt was delivered directly to guest)
+	 *    Return to guest to deliver any pending guest interrupts.
+	 */
+
+	cmpdi	r3, 1
+	ble	1f
+
+	/* Return code = 2 */
+	li	r12, BOOK3S_INTERRUPT_HV_RM_HARD
+	stw	r12, VCPU_TRAP(r9)
+	b	guest_exit_cont
+
+1:	/* Return code <= 1 */
+	cmpdi	r3, 0
+	bgt	guest_exit_cont
+
+	/* Return code <= 0 */
+maybe_reenter_guest:
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	lwz	r0, VCORE_ENTRY_EXIT(r5)
+	cmpwi	r0, 0x100
+	mr	r4, r9
+	blt	deliver_guest_interrupt
+	b	guest_exit_cont
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 /*
  * Softpatch interrupt for transactional memory emulation cases
@@ -2302,6 +2257,10 @@
 	andi.	r0,r11,MSR_PR
 	/* sc 1 from userspace - reflect to guest syscall */
 	bne	sc_1_fast_return
+	/* sc 1 from nested guest - give it to L1 to handle */
+	ld	r0, VCPU_NESTED(r9)
+	cmpdi	r0, 0
+	bne	guest_exit_cont
 	clrrdi	r3,r3,2
 	cmpldi	r3,hcall_real_table_end - hcall_real_table
 	bge	guest_exit_cont
@@ -2359,11 +2318,16 @@
 	.long	DOTSYM(kvmppc_h_clear_mod) - hcall_real_table
 	.long	DOTSYM(kvmppc_h_clear_ref) - hcall_real_table
 	.long	DOTSYM(kvmppc_h_protect) - hcall_real_table
+#ifdef CONFIG_SPAPR_TCE_IOMMU
 	.long	DOTSYM(kvmppc_h_get_tce) - hcall_real_table
 	.long	DOTSYM(kvmppc_rm_h_put_tce) - hcall_real_table
+#else
+	.long	0		/* 0x1c */
+	.long	0		/* 0x20 */
+#endif
 	.long	0		/* 0x24 - H_SET_SPRG0 */
 	.long	DOTSYM(kvmppc_h_set_dabr) - hcall_real_table
-	.long	0		/* 0x2c */
+	.long	DOTSYM(kvmppc_rm_h_page_init) - hcall_real_table
 	.long	0		/* 0x30 */
 	.long	0		/* 0x34 */
 	.long	0		/* 0x38 */
@@ -2438,8 +2402,13 @@
 	.long	0		/* 0x12c */
 	.long	0		/* 0x130 */
 	.long	DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
+#ifdef CONFIG_SPAPR_TCE_IOMMU
 	.long	DOTSYM(kvmppc_rm_h_stuff_tce) - hcall_real_table
 	.long	DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table
+#else
+	.long	0		/* 0x138 */
+	.long	0		/* 0x13c */
+#endif
 	.long	0		/* 0x140 */
 	.long	0		/* 0x144 */
 	.long	0		/* 0x148 */
@@ -2561,6 +2530,7 @@
 hcall_real_table_end:
 
 _GLOBAL(kvmppc_h_set_xdabr)
+EXPORT_SYMBOL_GPL(kvmppc_h_set_xdabr)
 	andi.	r0, r5, DABRX_USER | DABRX_KERNEL
 	beq	6f
 	li	r0, DABRX_USER | DABRX_KERNEL | DABRX_BTI
@@ -2570,6 +2540,7 @@
 	blr
 
 _GLOBAL(kvmppc_h_set_dabr)
+EXPORT_SYMBOL_GPL(kvmppc_h_set_dabr)
 	li	r5, DABRX_USER | DABRX_KERNEL
 3:
 BEGIN_FTR_SECTION
@@ -2588,20 +2559,31 @@
 	blr
 
 2:
-BEGIN_FTR_SECTION
-	/* POWER9 with disabled DAWR */
+	LOAD_REG_ADDR(r11, dawr_force_enable)
+	lbz	r11, 0(r11)
+	cmpdi	r11, 0
+	bne	3f
 	li	r3, H_HARDWARE
 	blr
-END_FTR_SECTION_IFCLR(CPU_FTR_DAWR)
+3:
 	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
 	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
 	rlwimi	r5, r4, 2, DAWRX_WT
 	clrrdi	r4, r4, 3
 	std	r4, VCPU_DAWR(r3)
 	std	r5, VCPU_DAWRX(r3)
+	/*
+	 * If came in through the real mode hcall handler then it is necessary
+	 * to write the registers since the return path won't. Otherwise it is
+	 * sufficient to store then in the vcpu struct as they will be loaded
+	 * next time the vcpu is run.
+	 */
+	mfmsr	r6
+	andi.	r6, r6, MSR_DR		/* in real mode? */
+	bne	4f
 	mtspr	SPRN_DAWR, r4
 	mtspr	SPRN_DAWRX, r5
-	li	r3, 0
+4:	li	r3, 0
 	blr
 
 _GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
@@ -2682,11 +2664,13 @@
 	b	91f
 END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
-	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
+	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
 	 */
 	ld	r3, HSTATE_KVM_VCPU(r13)
 	ld      r4, VCPU_MSR(r3)
+	li	r5, 0			/* don't preserve non-vol regs */
 	bl	kvmppc_save_tm_hv
+	nop
 91:
 #endif
 
@@ -2727,6 +2711,9 @@
 
 	lis	r3, LPCR_PECEDP@h	/* Do wake on privileged doorbell */
 
+	/* Go back to host stack */
+	ld	r1, HSTATE_HOST_R1(r13)
+
 	/*
 	 * Take a nap until a decrementer or external or doobell interrupt
 	 * occurs, with PECE1 and PECE0 set in LPCR.
@@ -2755,26 +2742,42 @@
 	 *		requested level = 0 (just stop dispatching)
 	 */
 	lis	r3, (PSSCR_EC | PSSCR_ESL)@h
-	mtspr	SPRN_PSSCR, r3
 	/* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */
 	li	r4, LPCR_PECE_HVEE@higher
 	sldi	r4, r4, 32
 	or	r5, r5, r4
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+FTR_SECTION_ELSE
+	li	r3, PNV_THREAD_NAP
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPCR,r5
 	isync
-	li	r0, 0
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
+
 BEGIN_FTR_SECTION
-	nap
+	bl	isa300_idle_stop_mayloss
 FTR_SECTION_ELSE
-	PPC_STOP
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
-	b	.
+	bl	isa206_idle_insn_mayloss
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
+
+	mfspr	r0, SPRN_CTRLF
+	ori	r0, r0, 1
+	mtspr	SPRN_CTRLT, r0
+
+	mtspr	SPRN_SRR1, r3
+
+	li	r0, 0
+	stb	r0, PACA_FTRACE_ENABLED(r13)
+
+	li	r0, KVM_HWTHREAD_IN_KVM
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+
+	lbz	r0, HSTATE_NAPPING(r13)
+	cmpwi	r0, NAPPING_CEDE
+	beq	kvm_end_cede
+	cmpwi	r0, NAPPING_NOVCPU
+	beq	kvm_novcpu_wakeup
+	cmpwi	r0, NAPPING_UNSPLIT
+	beq	kvm_unsplit_wakeup
+	twi	31,0,0 /* Nap state must not be zero */
 
 33:	mr	r4, r3
 	li	r3, 0
@@ -2782,12 +2785,11 @@
 	b	34f
 
 kvm_end_cede:
+	/* Woken by external or decrementer interrupt */
+
 	/* get vcpu pointer */
 	ld	r4, HSTATE_KVM_VCPU(r13)
 
-	/* Woken by external or decrementer interrupt */
-	ld	r1, HSTATE_HOST_R1(r13)
-
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
 	addi	r3, r4, VCPU_TB_RMINTR
 	bl	kvmhv_accumulate_time
@@ -2802,11 +2804,13 @@
 	b	91f
 END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
 	/*
-	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
+	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
 	 */
 	mr      r3, r4
 	ld      r4, VCPU_MSR(r3)
+	li	r5, 0			/* don't preserve non-vol regs */
 	bl	kvmppc_restore_tm_hv
+	nop
 	ld	r4, HSTATE_KVM_VCPU(r13)
 91:
 #endif
@@ -2874,13 +2878,7 @@
 	mr	r9, r4
 	cmpdi	r3, 0
 	bgt	guest_exit_cont
-
-	/* see if any other thread is already exiting */
-	lwz	r0,VCORE_ENTRY_EXIT(r5)
-	cmpwi	r0,0x100
-	bge	guest_exit_cont
-
-	b	kvmppc_cede_reentry	/* if not go back to guest */
+	b	maybe_reenter_guest
 
 	/* cede when already previously prodded case */
 kvm_cede_prodded:
@@ -2895,75 +2893,66 @@
 kvm_cede_exit:
 	ld	r9, HSTATE_KVM_VCPU(r13)
 #ifdef CONFIG_KVM_XICS
-	/* Abort if we still have a pending escalation */
-	lbz	r5, VCPU_XIVE_ESC_ON(r9)
-	cmpwi	r5, 0
-	beq	1f
-	li	r0, 0
-	stb	r0, VCPU_CEDED(r9)
-1:	/* Enable XIVE escalation */
-	li	r5, XIVE_ESB_SET_PQ_00
-	mfmsr	r0
-	andi.	r0, r0, MSR_DR		/* in real mode? */
-	beq	1f
+	/* are we using XIVE with single escalation? */
 	ld	r10, VCPU_XIVE_ESC_VADDR(r9)
 	cmpdi	r10, 0
 	beq	3f
-	ldx	r0, r10, r5
+	li	r6, XIVE_ESB_SET_PQ_00
+	/*
+	 * If we still have a pending escalation, abort the cede,
+	 * and we must set PQ to 10 rather than 00 so that we don't
+	 * potentially end up with two entries for the escalation
+	 * interrupt in the XIVE interrupt queue.  In that case
+	 * we also don't want to set xive_esc_on to 1 here in
+	 * case we race with xive_esc_irq().
+	 */
+	lbz	r5, VCPU_XIVE_ESC_ON(r9)
+	cmpwi	r5, 0
+	beq	4f
+	li	r0, 0
+	stb	r0, VCPU_CEDED(r9)
+	li	r6, XIVE_ESB_SET_PQ_10
+	b	5f
+4:	li	r0, 1
+	stb	r0, VCPU_XIVE_ESC_ON(r9)
+	/* make sure store to xive_esc_on is seen before xive_esc_irq runs */
+	sync
+5:	/* Enable XIVE escalation */
+	mfmsr	r0
+	andi.	r0, r0, MSR_DR		/* in real mode? */
+	beq	1f
+	ldx	r0, r10, r6
 	b	2f
 1:	ld	r10, VCPU_XIVE_ESC_RADDR(r9)
-	cmpdi	r10, 0
-	beq	3f
-	ldcix	r0, r10, r5
+	ldcix	r0, r10, r6
 2:	sync
-	li	r0, 1
-	stb	r0, VCPU_XIVE_ESC_ON(r9)
 #endif /* CONFIG_KVM_XICS */
 3:	b	guest_exit_cont
 
-	/* Try to handle a machine check in real mode */
+	/* Try to do machine check recovery in real mode */
 machine_check_realmode:
 	mr	r3, r9		/* get vcpu pointer */
 	bl	kvmppc_realmode_machine_check
 	nop
+	/* all machine checks go to virtual mode for further handling */
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	li	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
-	/*
-	 * For the guest that is FWNMI capable, deliver all the MCE errors
-	 * (handled/unhandled) by exiting the guest with KVM_EXIT_NMI exit
-	 * reason. This new approach injects machine check errors in guest
-	 * address space to guest with additional information in the form
-	 * of RTAS event, thus enabling guest kernel to suitably handle
-	 * such errors.
-	 *
-	 * For the guest that is not FWNMI capable (old QEMU) fallback
-	 * to old behaviour for backward compatibility:
-	 * Deliver unhandled/fatal (e.g. UE) MCE errors to guest either
-	 * through machine check interrupt (set HSRR0 to 0x200).
-	 * For handled errors (no-fatal), just go back to guest execution
-	 * with current HSRR0.
-	 * if we receive machine check with MSR(RI=0) then deliver it to
-	 * guest as machine check causing guest to crash.
-	 */
-	ld	r11, VCPU_MSR(r9)
-	rldicl.	r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */
-	bne	mc_cont			/* if so, exit to host */
-	/* Check if guest is capable of handling NMI exit */
-	ld	r10, VCPU_KVM(r9)
-	lbz	r10, KVM_FWNMI(r10)
-	cmpdi	r10, 1			/* FWNMI capable? */
-	beq	mc_cont			/* if so, exit with KVM_EXIT_NMI. */
+	b	guest_exit_cont
 
-	/* if not, fall through for backward compatibility. */
-	andi.	r10, r11, MSR_RI	/* check for unrecoverable exception */
-	beq	1f			/* Deliver a machine check to guest */
-	ld	r10, VCPU_PC(r9)
-	cmpdi	r3, 0		/* Did we handle MCE ? */
-	bne	2f	/* Continue guest execution. */
-	/* If not, deliver a machine check.  SRR0/1 are already set */
-1:	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
-	bl	kvmppc_msr_interrupt
-2:	b	fast_interrupt_c_return
+/*
+ * Call C code to handle a HMI in real mode.
+ * Only the primary thread does the call, secondary threads are handled
+ * by calling hmi_exception_realmode() after kvmppc_hv_entry returns.
+ * r9 points to the vcpu on entry
+ */
+hmi_realmode:
+	lbz	r0, HSTATE_PTID(r13)
+	cmpwi	r0, 0
+	bne	guest_exit_cont
+	bl	kvmppc_realmode_hmi_handler
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	li	r12, BOOK3S_INTERRUPT_HMI
+	b	guest_exit_cont
 
 /*
  * Check the reason we woke from nap, and take appropriate action.
@@ -3130,10 +3119,12 @@
  * Save transactional state and TM-related registers.
  * Called with r3 pointing to the vcpu struct and r4 containing
  * the guest MSR value.
- * This can modify all checkpointed registers, but
+ * r5 is non-zero iff non-volatile register state needs to be maintained.
+ * If r5 == 0, this can modify all checkpointed registers, but
  * restores r1 and r2 before exit.
  */
-kvmppc_save_tm_hv:
+_GLOBAL_TOC(kvmppc_save_tm_hv)
+EXPORT_SYMBOL_GPL(kvmppc_save_tm_hv)
 	/* See if we need to handle fake suspend mode */
 BEGIN_FTR_SECTION
 	b	__kvmppc_save_tm
@@ -3161,12 +3152,6 @@
 END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	nop
 
-	std	r1, HSTATE_HOST_R1(r13)
-
-	/* Clear the MSR RI since r1, r13 may be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
 	/* We have to treclaim here because that's the only way to do S->N */
 	li	r3, TM_CAUSE_KVM_RESCHED
 	TRECLAIM(R3)
@@ -3175,22 +3160,13 @@
 	 * We were in fake suspend, so we are not going to save the
 	 * register state as the guest checkpointed state (since
 	 * we already have it), therefore we can now use any volatile GPR.
+	 * In fact treclaim in fake suspend state doesn't modify
+	 * any registers.
 	 */
-	/* Reload PACA pointer, stack pointer and TOC. */
-	GET_PACA(r13)
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATOC(r13)
 
-	/* Set MSR RI now we have r1 and r13 back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-
-	HMT_MEDIUM
-	ld	r6, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r6
-BEGIN_FTR_SECTION_NESTED(96)
+BEGIN_FTR_SECTION
 	bl	pnv_power9_force_smt4_release
-END_FTR_SECTION_NESTED(CPU_FTR_P9_TM_XER_SO_BUG, CPU_FTR_P9_TM_XER_SO_BUG, 96)
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	nop
 
 4:
@@ -3216,10 +3192,12 @@
  * Restore transactional state and TM-related registers.
  * Called with r3 pointing to the vcpu struct
  * and r4 containing the guest MSR value.
+ * r5 is non-zero iff non-volatile register state needs to be maintained.
  * This potentially modifies all checkpointed registers.
  * It restores r1 and r2 from the PACA.
  */
-kvmppc_restore_tm_hv:
+_GLOBAL_TOC(kvmppc_restore_tm_hv)
+EXPORT_SYMBOL_GPL(kvmppc_restore_tm_hv)
 	/*
 	 * If we are doing TM emulation for the guest on a POWER9 DD2,
 	 * then we don't actually do a trechkpt -- we either set up
@@ -3424,6 +3402,194 @@
 	blr
 
 /*
+ * Load up guest PMU state.  R3 points to the vcpu struct.
+ */
+_GLOBAL(kvmhv_load_guest_pmu)
+EXPORT_SYMBOL_GPL(kvmhv_load_guest_pmu)
+	mr	r4, r3
+	mflr	r0
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	isync
+BEGIN_FTR_SECTION
+	ld	r3, VCPU_MMCR(r4)
+	andi.	r5, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
+	cmpwi	r5, MMCR0_PMAO
+	beql	kvmppc_fix_pmao
+END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
+	lwz	r3, VCPU_PMC(r4)	/* always load up guest PMU registers */
+	lwz	r5, VCPU_PMC + 4(r4)	/* to prevent information leak */
+	lwz	r6, VCPU_PMC + 8(r4)
+	lwz	r7, VCPU_PMC + 12(r4)
+	lwz	r8, VCPU_PMC + 16(r4)
+	lwz	r9, VCPU_PMC + 20(r4)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r5
+	mtspr	SPRN_PMC3, r6
+	mtspr	SPRN_PMC4, r7
+	mtspr	SPRN_PMC5, r8
+	mtspr	SPRN_PMC6, r9
+	ld	r3, VCPU_MMCR(r4)
+	ld	r5, VCPU_MMCR + 8(r4)
+	ld	r6, VCPU_MMCR + 16(r4)
+	ld	r7, VCPU_SIAR(r4)
+	ld	r8, VCPU_SDAR(r4)
+	mtspr	SPRN_MMCR1, r5
+	mtspr	SPRN_MMCRA, r6
+	mtspr	SPRN_SIAR, r7
+	mtspr	SPRN_SDAR, r8
+BEGIN_FTR_SECTION
+	ld	r5, VCPU_MMCR + 24(r4)
+	ld	r6, VCPU_SIER(r4)
+	mtspr	SPRN_MMCR2, r5
+	mtspr	SPRN_SIER, r6
+BEGIN_FTR_SECTION_NESTED(96)
+	lwz	r7, VCPU_PMC + 24(r4)
+	lwz	r8, VCPU_PMC + 28(r4)
+	ld	r9, VCPU_MMCR + 32(r4)
+	mtspr	SPRN_SPMC1, r7
+	mtspr	SPRN_SPMC2, r8
+	mtspr	SPRN_MMCRS, r9
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	mtspr	SPRN_MMCR0, r3
+	isync
+	mtlr	r0
+	blr
+
+/*
+ * Reload host PMU state saved in the PACA by kvmhv_save_host_pmu.
+ */
+_GLOBAL(kvmhv_load_host_pmu)
+EXPORT_SYMBOL_GPL(kvmhv_load_host_pmu)
+	mflr	r0
+	lbz	r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
+	cmpwi	r4, 0
+	beq	23f			/* skip if not */
+BEGIN_FTR_SECTION
+	ld	r3, HSTATE_MMCR0(r13)
+	andi.	r4, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
+	cmpwi	r4, MMCR0_PMAO
+	beql	kvmppc_fix_pmao
+END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
+	lwz	r3, HSTATE_PMC1(r13)
+	lwz	r4, HSTATE_PMC2(r13)
+	lwz	r5, HSTATE_PMC3(r13)
+	lwz	r6, HSTATE_PMC4(r13)
+	lwz	r8, HSTATE_PMC5(r13)
+	lwz	r9, HSTATE_PMC6(r13)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r4
+	mtspr	SPRN_PMC3, r5
+	mtspr	SPRN_PMC4, r6
+	mtspr	SPRN_PMC5, r8
+	mtspr	SPRN_PMC6, r9
+	ld	r3, HSTATE_MMCR0(r13)
+	ld	r4, HSTATE_MMCR1(r13)
+	ld	r5, HSTATE_MMCRA(r13)
+	ld	r6, HSTATE_SIAR(r13)
+	ld	r7, HSTATE_SDAR(r13)
+	mtspr	SPRN_MMCR1, r4
+	mtspr	SPRN_MMCRA, r5
+	mtspr	SPRN_SIAR, r6
+	mtspr	SPRN_SDAR, r7
+BEGIN_FTR_SECTION
+	ld	r8, HSTATE_MMCR2(r13)
+	ld	r9, HSTATE_SIER(r13)
+	mtspr	SPRN_MMCR2, r8
+	mtspr	SPRN_SIER, r9
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	mtspr	SPRN_MMCR0, r3
+	isync
+	mtlr	r0
+23:	blr
+
+/*
+ * Save guest PMU state into the vcpu struct.
+ * r3 = vcpu, r4 = full save flag (PMU in use flag set in VPA)
+ */
+_GLOBAL(kvmhv_save_guest_pmu)
+EXPORT_SYMBOL_GPL(kvmhv_save_guest_pmu)
+	mr	r9, r3
+	mr	r8, r4
+BEGIN_FTR_SECTION
+	/*
+	 * POWER8 seems to have a hardware bug where setting
+	 * MMCR0[PMAE] along with MMCR0[PMC1CE] and/or MMCR0[PMCjCE]
+	 * when some counters are already negative doesn't seem
+	 * to cause a performance monitor alert (and hence interrupt).
+	 * The effect of this is that when saving the PMU state,
+	 * if there is no PMU alert pending when we read MMCR0
+	 * before freezing the counters, but one becomes pending
+	 * before we read the counters, we lose it.
+	 * To work around this, we need a way to freeze the counters
+	 * before reading MMCR0.  Normally, freezing the counters
+	 * is done by writing MMCR0 (to set MMCR0[FC]) which
+	 * unavoidably writes MMCR0[PMA0] as well.  On POWER8,
+	 * we can also freeze the counters using MMCR2, by writing
+	 * 1s to all the counter freeze condition bits (there are
+	 * 9 bits each for 6 counters).
+	 */
+	li	r3, -1			/* set all freeze bits */
+	clrrdi	r3, r3, 10
+	mfspr	r10, SPRN_MMCR2
+	mtspr	SPRN_MMCR2, r3
+	isync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	mfspr	r6, SPRN_MMCRA
+	/* Clear MMCRA in order to disable SDAR updates */
+	li	r7, 0
+	mtspr	SPRN_MMCRA, r7
+	isync
+	cmpwi	r8, 0			/* did they ask for PMU stuff to be saved? */
+	bne	21f
+	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
+	b	22f
+21:	mfspr	r5, SPRN_MMCR1
+	mfspr	r7, SPRN_SIAR
+	mfspr	r8, SPRN_SDAR
+	std	r4, VCPU_MMCR(r9)
+	std	r5, VCPU_MMCR + 8(r9)
+	std	r6, VCPU_MMCR + 16(r9)
+BEGIN_FTR_SECTION
+	std	r10, VCPU_MMCR + 24(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	std	r7, VCPU_SIAR(r9)
+	std	r8, VCPU_SDAR(r9)
+	mfspr	r3, SPRN_PMC1
+	mfspr	r4, SPRN_PMC2
+	mfspr	r5, SPRN_PMC3
+	mfspr	r6, SPRN_PMC4
+	mfspr	r7, SPRN_PMC5
+	mfspr	r8, SPRN_PMC6
+	stw	r3, VCPU_PMC(r9)
+	stw	r4, VCPU_PMC + 4(r9)
+	stw	r5, VCPU_PMC + 8(r9)
+	stw	r6, VCPU_PMC + 12(r9)
+	stw	r7, VCPU_PMC + 16(r9)
+	stw	r8, VCPU_PMC + 20(r9)
+BEGIN_FTR_SECTION
+	mfspr	r5, SPRN_SIER
+	std	r5, VCPU_SIER(r9)
+BEGIN_FTR_SECTION_NESTED(96)
+	mfspr	r6, SPRN_SPMC1
+	mfspr	r7, SPRN_SPMC2
+	mfspr	r8, SPRN_MMCRS
+	stw	r6, VCPU_PMC + 24(r9)
+	stw	r7, VCPU_PMC + 28(r9)
+	std	r8, VCPU_MMCR + 32(r9)
+	lis	r4, 0x8000
+	mtspr	SPRN_MMCRS, r4
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+22:	blr
+
+/*
  * This works around a hardware bug on POWER8E processors, where
  * writing a 1 to the MMCR0[PMAO] bit doesn't generate a
  * performance monitor interrupt.  Instead, when we need to have
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index 0082850..0db9374 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kvm_host.h>
@@ -130,8 +127,8 @@
 			return RESUME_GUEST;
 		}
 		/* Set CR0 to indicate previous transactional state */
-		vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
-			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
+			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		/* L=1 => tresume, L=0 => tsuspend */
 		if (instr & (1 << 21)) {
 			if (MSR_TM_SUSPENDED(msr))
@@ -174,8 +171,8 @@
 		copy_from_checkpoint(vcpu);
 
 		/* Set CR0 to indicate previous transactional state */
-		vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
-			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
+			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
 		return RESUME_GUEST;
 
@@ -204,8 +201,8 @@
 		copy_to_checkpoint(vcpu);
 
 		/* Set CR0 to indicate previous transactional state */
-		vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
-			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
+			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr = msr | MSR_TS_S;
 		return RESUME_GUEST;
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c
index b2c7c6f..2172462 100644
--- a/arch/powerpc/kvm/book3s_hv_tm_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kvm_host.h>
@@ -89,7 +86,8 @@
 		if (instr & (1 << 21))
 			vcpu->arch.shregs.msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
 		/* Set CR0 to 0b0010 */
-		vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0x20000000;
+		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
+			0x20000000;
 		return 1;
 	}
 
@@ -105,5 +103,5 @@
 	vcpu->arch.shregs.msr &= ~MSR_TS_MASK;	/* go to N state */
 	vcpu->arch.regs.nip = vcpu->arch.tfhar;
 	copy_from_checkpoint(vcpu);
-	vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0xa0000000;
+	vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) | 0xa0000000;
 }
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index d71dab1..f7ad99d 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index 905a934..ce79ac3 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
  *
  * Authors:
  *     Alexander Graf <agraf@suse.de>
- *
- * 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.
  */
 
 #include <linux/kvm_host.h>
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index eab96cf..bf02827 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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 Novell Inc 2010
  *
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 614ebb4..cc65af8 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
  *
@@ -13,10 +14,6 @@
  *
  * This file is derived from arch/powerpc/kvm/44x.c,
  * by Hollis Blanchard <hollisb@us.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kvm_host.h>
@@ -167,7 +164,7 @@
 	svcpu->gpr[11] = vcpu->arch.regs.gpr[11];
 	svcpu->gpr[12] = vcpu->arch.regs.gpr[12];
 	svcpu->gpr[13] = vcpu->arch.regs.gpr[13];
-	svcpu->cr  = vcpu->arch.cr;
+	svcpu->cr  = vcpu->arch.regs.ccr;
 	svcpu->xer = vcpu->arch.regs.xer;
 	svcpu->ctr = vcpu->arch.regs.ctr;
 	svcpu->lr  = vcpu->arch.regs.link;
@@ -249,7 +246,7 @@
 	vcpu->arch.regs.gpr[11] = svcpu->gpr[11];
 	vcpu->arch.regs.gpr[12] = svcpu->gpr[12];
 	vcpu->arch.regs.gpr[13] = svcpu->gpr[13];
-	vcpu->arch.cr  = svcpu->cr;
+	vcpu->arch.regs.ccr  = svcpu->cr;
 	vcpu->arch.regs.xer = svcpu->xer;
 	vcpu->arch.regs.ctr = svcpu->ctr;
 	vcpu->arch.regs.link  = svcpu->lr;
@@ -587,6 +584,7 @@
 	case PVR_POWER8:
 	case PVR_POWER8E:
 	case PVR_POWER8NVL:
+	case PVR_POWER9:
 		vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
 			BOOK3S_HFLAG_NEW_TLBIE;
 		break;
@@ -1246,7 +1244,6 @@
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_EXTERNAL:
-	case BOOK3S_INTERRUPT_EXTERNAL_LEVEL:
 	case BOOK3S_INTERRUPT_EXTERNAL_HV:
 	case BOOK3S_INTERRUPT_H_VIRT:
 		vcpu->stat.ext_intr_exits++;
@@ -1914,7 +1911,8 @@
 static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 	return;
 }
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index dae3be5..031c801 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2011. Freescale Inc. All rights reserved.
  *
@@ -9,10 +10,6 @@
  *
  * Hypercall handling for running PAPR guests in PR KVM on Book 3S
  * processors.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/anon_inodes.h>
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index b0089e0..3dc129a 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2009
  *
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index 2d3b2b1..26b2599 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2012 Michael Ellerman, IBM Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kernel.h>
@@ -33,7 +30,7 @@
 	server = be32_to_cpu(args->args[1]);
 	priority = be32_to_cpu(args->args[2]);
 
-	if (xive_enabled())
+	if (xics_on_xive())
 		rc = kvmppc_xive_set_xive(vcpu->kvm, irq, server, priority);
 	else
 		rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
@@ -56,7 +53,7 @@
 	irq = be32_to_cpu(args->args[0]);
 
 	server = priority = 0;
-	if (xive_enabled())
+	if (xics_on_xive())
 		rc = kvmppc_xive_get_xive(vcpu->kvm, irq, &server, &priority);
 	else
 		rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
@@ -83,7 +80,7 @@
 
 	irq = be32_to_cpu(args->args[0]);
 
-	if (xive_enabled())
+	if (xics_on_xive())
 		rc = kvmppc_xive_int_off(vcpu->kvm, irq);
 	else
 		rc = kvmppc_xics_int_off(vcpu->kvm, irq);
@@ -105,7 +102,7 @@
 
 	irq = be32_to_cpu(args->args[0]);
 
-	if (xive_enabled())
+	if (xics_on_xive())
 		rc = kvmppc_xive_int_on(vcpu->kvm, irq);
 	else
 		rc = kvmppc_xics_int_on(vcpu->kvm, irq);
@@ -146,7 +143,7 @@
 {
 	struct rtas_token_definition *d, *tmp;
 
-	lockdep_assert_held(&kvm->lock);
+	lockdep_assert_held(&kvm->arch.rtas_token_lock);
 
 	list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) {
 		if (rtas_name_matches(d->handler->name, name)) {
@@ -167,7 +164,7 @@
 	bool found;
 	int i;
 
-	lockdep_assert_held(&kvm->lock);
+	lockdep_assert_held(&kvm->arch.rtas_token_lock);
 
 	list_for_each_entry(d, &kvm->arch.rtas_tokens, list) {
 		if (d->token == token)
@@ -206,14 +203,14 @@
 	if (copy_from_user(&args, argp, sizeof(args)))
 		return -EFAULT;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.rtas_token_lock);
 
 	if (args.token)
 		rc = rtas_token_define(kvm, args.name, args.token);
 	else
 		rc = rtas_token_undefine(kvm, args.name);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.rtas_token_lock);
 
 	return rc;
 }
@@ -245,7 +242,7 @@
 	orig_rets = args.rets;
 	args.rets = &args.args[be32_to_cpu(args.nargs)];
 
-	mutex_lock(&vcpu->kvm->lock);
+	mutex_lock(&vcpu->kvm->arch.rtas_token_lock);
 
 	rc = -ENOENT;
 	list_for_each_entry(d, &vcpu->kvm->arch.rtas_tokens, list) {
@@ -256,7 +253,7 @@
 		}
 	}
 
-	mutex_unlock(&vcpu->kvm->lock);
+	mutex_unlock(&vcpu->kvm->arch.rtas_token_lock);
 
 	if (rc == 0) {
 		args.rets = orig_rets;
@@ -282,8 +279,6 @@
 {
 	struct rtas_token_definition *d, *tmp;
 
-	lockdep_assert_held(&kvm->lock);
-
 	list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) {
 		list_del(&d->list);
 		kfree(d);
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index e5c542a..0169bab 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 SUSE Linux Products GmbH 2010
  *
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index b8356cd..381bf8d 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2012 Michael Ellerman, IBM Corporation.
  * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kernel.h>
@@ -310,7 +307,7 @@
 	 */
 	if (new.out_ee) {
 		kvmppc_book3s_queue_irqprio(icp->vcpu,
-					    BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+					    BOOK3S_INTERRUPT_EXTERNAL);
 		if (!change_self)
 			kvmppc_fast_vcpu_kick(icp->vcpu);
 	}
@@ -593,8 +590,7 @@
 	u32 xirr;
 
 	/* First, remove EE from the processor */
-	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
-				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 
 	/*
 	 * ICP State: Accept_Interrupt
@@ -754,8 +750,7 @@
 	 * We can remove EE from the current processor, the update
 	 * transaction will set it again if needed
 	 */
-	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
-				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 
 	do {
 		old_state = new_state = READ_ONCE(icp->state);
@@ -832,7 +827,7 @@
 	 *
 	 * Note: If EOI is incorrectly used by SW to lower the CPPR
 	 * value (ie more favored), we do not check for rejection of
-	 * a pending interrupt, this is a SW error and PAPR sepcifies
+	 * a pending interrupt, this is a SW error and PAPR specifies
 	 * that we don't have to deal with it.
 	 *
 	 * The sending of an EOI to the ICS is handled after the
@@ -1017,17 +1012,7 @@
 	return 0;
 }
 
-static int xics_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, xics_debug_show, inode->i_private);
-}
-
-static const struct file_operations xics_debug_fops = {
-	.open = xics_debug_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(xics_debug);
 
 static void xics_debugfs_init(struct kvmppc_xics *xics)
 {
@@ -1167,8 +1152,7 @@
 	 * Deassert the CPU interrupt request.
 	 * icp_try_update will reassert it if necessary.
 	 */
-	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
-				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 
 	/*
 	 * Note that if we displace an interrupt from old_state.xisr,
@@ -1393,7 +1377,8 @@
 	}
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+	if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+	    cpu_has_feature(CPU_FTR_HVMODE)) {
 		/* Enable real mode support */
 		xics->real_mode = ENABLE_REALMODE;
 		xics->real_mode_dbg = DEBUG_REALMODE;
diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h
index 453c9e5..6231f76 100644
--- a/arch/powerpc/kvm/book3s_xics.h
+++ b/arch/powerpc/kvm/book3s_xics.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright 2012 Michael Ellerman, IBM Corporation.
  * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #ifndef _KVM_PPC_BOOK3S_XICS_H
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 30c2eb7..a3f9c66 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation.
- *
- * 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.
  */
 
 #define pr_fmt(fmt) "xive-kvm: " fmt
@@ -62,6 +59,75 @@
 #define XIVE_Q_GAP	2
 
 /*
+ * Push a vcpu's context to the XIVE on guest entry.
+ * This assumes we are in virtual mode (MMU on)
+ */
+void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu)
+{
+	void __iomem *tima = local_paca->kvm_hstate.xive_tima_virt;
+	u64 pq;
+
+	/*
+	 * Nothing to do if the platform doesn't have a XIVE
+	 * or this vCPU doesn't have its own XIVE context
+	 * (e.g. because it's not using an in-kernel interrupt controller).
+	 */
+	if (!tima || !vcpu->arch.xive_cam_word)
+		return;
+
+	eieio();
+	__raw_writeq(vcpu->arch.xive_saved_state.w01, tima + TM_QW1_OS);
+	__raw_writel(vcpu->arch.xive_cam_word, tima + TM_QW1_OS + TM_WORD2);
+	vcpu->arch.xive_pushed = 1;
+	eieio();
+
+	/*
+	 * We clear the irq_pending flag. There is a small chance of a
+	 * race vs. the escalation interrupt happening on another
+	 * processor setting it again, but the only consequence is to
+	 * cause a spurious wakeup on the next H_CEDE, which is not an
+	 * issue.
+	 */
+	vcpu->arch.irq_pending = 0;
+
+	/*
+	 * In single escalation mode, if the escalation interrupt is
+	 * on, we mask it.
+	 */
+	if (vcpu->arch.xive_esc_on) {
+		pq = __raw_readq((void __iomem *)(vcpu->arch.xive_esc_vaddr +
+						  XIVE_ESB_SET_PQ_01));
+		mb();
+
+		/*
+		 * We have a possible subtle race here: The escalation
+		 * interrupt might have fired and be on its way to the
+		 * host queue while we mask it, and if we unmask it
+		 * early enough (re-cede right away), there is a
+		 * theorical possibility that it fires again, thus
+		 * landing in the target queue more than once which is
+		 * a big no-no.
+		 *
+		 * Fortunately, solving this is rather easy. If the
+		 * above load setting PQ to 01 returns a previous
+		 * value where P is set, then we know the escalation
+		 * interrupt is somewhere on its way to the host. In
+		 * that case we simply don't clear the xive_esc_on
+		 * flag below. It will be eventually cleared by the
+		 * handler for the escalation interrupt.
+		 *
+		 * Then, when doing a cede, we check that flag again
+		 * before re-enabling the escalation interrupt, and if
+		 * set, we abort the cede.
+		 */
+		if (!(pq & XIVE_ESB_VAL_P))
+			/* Now P is 0, we can clear the flag */
+			vcpu->arch.xive_esc_on = 0;
+	}
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_push_vcpu);
+
+/*
  * This is a simple trigger for a generic XIVE IRQ. This must
  * only be called for interrupts that support a trigger page
  */
@@ -100,10 +166,14 @@
 	 */
 	vcpu->arch.xive_esc_on = false;
 
+	/* This orders xive_esc_on = false vs. subsequent stale_p = true */
+	smp_wmb();	/* goes with smp_mb() in cleanup_single_escalation */
+
 	return IRQ_HANDLED;
 }
 
-static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
+int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
+				  bool single_escalation)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
 	struct xive_q *q = &xc->queues[prio];
@@ -122,7 +192,7 @@
 		return -EIO;
 	}
 
-	if (xc->xive->single_escalation)
+	if (single_escalation)
 		name = kasprintf(GFP_KERNEL, "kvm-%d-%d",
 				 vcpu->kvm->arch.lpid, xc->server_num);
 	else
@@ -154,7 +224,7 @@
 	 * interrupt, thus leaving it effectively masked after
 	 * it fires once.
 	 */
-	if (xc->xive->single_escalation) {
+	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);
 
@@ -207,14 +277,14 @@
 	return rc;
 }
 
-/* Called with kvm_lock held */
+/* Called with xive->lock held */
 static int xive_check_provisioning(struct kvm *kvm, u8 prio)
 {
 	struct kvmppc_xive *xive = kvm->arch.xive;
 	struct kvm_vcpu *vcpu;
 	int i, rc;
 
-	lockdep_assert_held(&kvm->lock);
+	lockdep_assert_held(&xive->lock);
 
 	/* Already provisioned ? */
 	if (xive->qmap & (1 << prio))
@@ -228,7 +298,8 @@
 			continue;
 		rc = xive_provision_queue(vcpu, prio);
 		if (rc == 0 && !xive->single_escalation)
-			xive_attach_escalation(vcpu, prio);
+			kvmppc_xive_attach_escalation(vcpu, prio,
+						      xive->single_escalation);
 		if (rc)
 			return rc;
 	}
@@ -279,7 +350,7 @@
 	return atomic_add_unless(&q->count, 1, max) ? 0 : -EBUSY;
 }
 
-static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
+int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
 {
 	struct kvm_vcpu *vcpu;
 	int i, rc;
@@ -317,11 +388,6 @@
 	return -EBUSY;
 }
 
-static u32 xive_vp(struct kvmppc_xive *xive, u32 server)
-{
-	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
-}
-
 static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 			     struct kvmppc_xive_src_block *sb,
 			     struct kvmppc_xive_irq_state *state)
@@ -367,8 +433,8 @@
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive_vp(xive, state->act_server),
-					  MASKED, state->number);
+				kvmppc_xive_vp(xive, state->act_server),
+				MASKED, state->number);
 		/* set old_p so we can track if an H_EOI was done */
 		state->old_p = true;
 		state->old_q = false;
@@ -423,8 +489,8 @@
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive_vp(xive, state->act_server),
-					  state->act_priority, state->number);
+				kvmppc_xive_vp(xive, state->act_server),
+				state->act_priority, state->number);
 		/* If an EOI is needed, do it here */
 		if (!state->old_p)
 			xive_vm_source_eoi(hw_num, xd);
@@ -472,7 +538,7 @@
 	 * priority. The count for that new target will have
 	 * already been incremented.
 	 */
-	rc = xive_select_target(kvm, &server, prio);
+	rc = kvmppc_xive_select_target(kvm, &server, prio);
 
 	/*
 	 * We failed to find a target ? Not much we can do
@@ -500,7 +566,7 @@
 	kvmppc_xive_select_irq(state, &hw_num, NULL);
 
 	return xive_native_configure_irq(hw_num,
-					 xive_vp(xive, server),
+					 kvmppc_xive_vp(xive, server),
 					 prio, state->number);
 }
 
@@ -561,9 +627,12 @@
 		 irq, server, priority);
 
 	/* First, check provisioning of queues */
-	if (priority != MASKED)
+	if (priority != MASKED) {
+		mutex_lock(&xive->lock);
 		rc = xive_check_provisioning(xive->kvm,
 			      xive_prio_from_guest(priority));
+		mutex_unlock(&xive->lock);
+	}
 	if (rc) {
 		pr_devel("  provisioning failure %d !\n", rc);
 		return rc;
@@ -786,7 +855,8 @@
 
 	/*
 	 * We can't update the state of a "pushed" VCPU, but that
-	 * shouldn't happen.
+	 * shouldn't happen because the vcpu->mutex makes running a
+	 * vcpu mutually exclusive with doing one_reg get/set on it.
 	 */
 	if (WARN_ON(vcpu->arch.xive_pushed))
 		return -EIO;
@@ -877,6 +947,13 @@
 	/* Turn the IPI hard off */
 	xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
 
+	/*
+	 * Reset ESB guest mapping. Needed when ESB pages are exposed
+	 * to the guest in XIVE native mode
+	 */
+	if (xive->ops && xive->ops->reset_mapped)
+		xive->ops->reset_mapped(kvm, guest_irq);
+
 	/* Grab info about irq */
 	state->pt_number = hw_irq;
 	state->pt_data = irq_data_get_irq_handler_data(host_data);
@@ -888,7 +965,7 @@
 	 * which is fine for a never started interrupt.
 	 */
 	xive_native_configure_irq(hw_irq,
-				  xive_vp(xive, state->act_server),
+				  kvmppc_xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);
 
 	/*
@@ -962,9 +1039,17 @@
 	state->pt_number = 0;
 	state->pt_data = NULL;
 
+	/*
+	 * Reset ESB guest mapping. Needed when ESB pages are exposed
+	 * to the guest in XIVE native mode
+	 */
+	if (xive->ops && xive->ops->reset_mapped) {
+		xive->ops->reset_mapped(kvm, guest_irq);
+	}
+
 	/* Reconfigure the IPI */
 	xive_native_configure_irq(state->ipi_number,
-				  xive_vp(xive, state->act_server),
+				  kvmppc_xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);
 
 	/*
@@ -986,7 +1071,7 @@
 }
 EXPORT_SYMBOL_GPL(kvmppc_xive_clr_mapped);
 
-static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
+void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
 	struct kvm *kvm = vcpu->kvm;
@@ -1020,14 +1105,60 @@
 			arch_spin_unlock(&sb->lock);
 		}
 	}
+
+	/* Disable vcpu's escalation interrupt */
+	if (vcpu->arch.xive_esc_on) {
+		__raw_readq((void __iomem *)(vcpu->arch.xive_esc_vaddr +
+					     XIVE_ESB_SET_PQ_01));
+		vcpu->arch.xive_esc_on = false;
+	}
+
+	/*
+	 * Clear pointers to escalation interrupt ESB.
+	 * This is safe because the vcpu->mutex is held, preventing
+	 * any other CPU from concurrently executing a KVM_RUN ioctl.
+	 */
+	vcpu->arch.xive_esc_vaddr = 0;
+	vcpu->arch.xive_esc_raddr = 0;
+}
+
+/*
+ * In single escalation mode, the escalation interrupt is marked so
+ * that EOI doesn't re-enable it, but just sets the stale_p flag to
+ * indicate that the P bit has already been dealt with.  However, the
+ * assembly code that enters the guest sets PQ to 00 without clearing
+ * stale_p (because it has no easy way to address it).  Hence we have
+ * to adjust stale_p before shutting down the interrupt.
+ */
+void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu,
+				    struct kvmppc_xive_vcpu *xc, int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+	struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+
+	/*
+	 * This slightly odd sequence gives the right result
+	 * (i.e. stale_p set if xive_esc_on is false) even if
+	 * we race with xive_esc_irq() and xive_irq_eoi().
+	 */
+	xd->stale_p = false;
+	smp_mb();		/* paired with smb_wmb in xive_esc_irq */
+	if (!vcpu->arch.xive_esc_on)
+		xd->stale_p = true;
 }
 
 void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
-	struct kvmppc_xive *xive = xc->xive;
+	struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
 	int i;
 
+	if (!kvmppc_xics_enabled(vcpu))
+		return;
+
+	if (!xc)
+		return;
+
 	pr_devel("cleanup_vcpu(cpu=%d)\n", xc->server_num);
 
 	/* Ensure no interrupt is still routed to that VP */
@@ -1037,20 +1168,28 @@
 	/* Mask the VP IPI */
 	xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_01);
 
-	/* Disable the VP */
-	xive_native_disable_vp(xc->vp_id);
-
-	/* Free the queues & associated interrupts */
+	/* Free escalations */
 	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
-		struct xive_q *q = &xc->queues[i];
-
-		/* Free the escalation irq */
 		if (xc->esc_virq[i]) {
+			if (xc->xive->single_escalation)
+				xive_cleanup_single_escalation(vcpu, xc,
+							xc->esc_virq[i]);
 			free_irq(xc->esc_virq[i], vcpu);
 			irq_dispose_mapping(xc->esc_virq[i]);
 			kfree(xc->esc_virq_names[i]);
 		}
-		/* Free the queue */
+	}
+
+	/* Disable the VP */
+	xive_native_disable_vp(xc->vp_id);
+
+	/* Clear the cam word so guest entry won't try to push context */
+	vcpu->arch.xive_cam_word = 0;
+
+	/* Free the queues */
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		struct xive_q *q = &xc->queues[i];
+
 		xive_native_disable_queue(xc->vp_id, q, i);
 		if (q->qpage) {
 			free_pages((unsigned long)q->qpage,
@@ -1066,6 +1205,10 @@
 	}
 	/* Free the VP */
 	kfree(xc);
+
+	/* Cleanup the vcpu */
+	vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
+	vcpu->arch.xive_vcpu = NULL;
 }
 
 int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
@@ -1074,6 +1217,7 @@
 	struct kvmppc_xive *xive = dev->private;
 	struct kvmppc_xive_vcpu *xc;
 	int i, r = -EBUSY;
+	u32 vp_id;
 
 	pr_devel("connect_vcpu(cpu=%d)\n", cpu);
 
@@ -1083,27 +1227,34 @@
 	}
 	if (xive->kvm != vcpu->kvm)
 		return -EPERM;
-	if (vcpu->arch.irq_type)
+	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
-	if (kvmppc_xive_find_server(vcpu->kvm, cpu)) {
-		pr_devel("Duplicate !\n");
-		return -EEXIST;
-	}
 	if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
 		pr_devel("Out of bounds !\n");
 		return -EINVAL;
 	}
-	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
-	if (!xc)
-		return -ENOMEM;
 
 	/* We need to synchronize with queue provisioning */
-	mutex_lock(&vcpu->kvm->lock);
+	mutex_lock(&xive->lock);
+
+	vp_id = kvmppc_xive_vp(xive, cpu);
+	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
+		pr_devel("Duplicate !\n");
+		r = -EEXIST;
+		goto bail;
+	}
+
+	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+	if (!xc) {
+		r = -ENOMEM;
+		goto bail;
+	}
+
 	vcpu->arch.xive_vcpu = xc;
 	xc->xive = xive;
 	xc->vcpu = vcpu;
 	xc->server_num = cpu;
-	xc->vp_id = xive_vp(xive, cpu);
+	xc->vp_id = vp_id;
 	xc->mfrr = 0xff;
 	xc->valid = true;
 
@@ -1156,7 +1307,8 @@
 		if (xive->qmap & (1 << i)) {
 			r = xive_provision_queue(vcpu, i);
 			if (r == 0 && !xive->single_escalation)
-				xive_attach_escalation(vcpu, i);
+				kvmppc_xive_attach_escalation(
+					vcpu, i, xive->single_escalation);
 			if (r)
 				goto bail;
 		} else {
@@ -1171,7 +1323,7 @@
 	}
 
 	/* If not done above, attach priority 0 escalation */
-	r = xive_attach_escalation(vcpu, 0);
+	r = kvmppc_xive_attach_escalation(vcpu, 0, xive->single_escalation);
 	if (r)
 		goto bail;
 
@@ -1181,7 +1333,7 @@
 		xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_00);
 
 bail:
-	mutex_unlock(&vcpu->kvm->lock);
+	mutex_unlock(&xive->lock);
 	if (r) {
 		kvmppc_xive_cleanup_vcpu(vcpu);
 		return r;
@@ -1422,16 +1574,15 @@
 	return 0;
 }
 
-static struct kvmppc_xive_src_block *xive_create_src_block(struct kvmppc_xive *xive,
-							   int irq)
+struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
+	struct kvmppc_xive *xive, int irq)
 {
-	struct kvm *kvm = xive->kvm;
 	struct kvmppc_xive_src_block *sb;
 	int i, bid;
 
 	bid = irq >> KVMPPC_XICS_ICS_SHIFT;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&xive->lock);
 
 	/* block already exists - somebody else got here first */
 	if (xive->src_blocks[bid])
@@ -1446,6 +1597,7 @@
 
 	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
 		sb->irq_state[i].number = (bid << KVMPPC_XICS_ICS_SHIFT) | i;
+		sb->irq_state[i].eisn = 0;
 		sb->irq_state[i].guest_priority = MASKED;
 		sb->irq_state[i].saved_priority = MASKED;
 		sb->irq_state[i].act_priority = MASKED;
@@ -1457,7 +1609,7 @@
 		xive->max_sbid = bid;
 
 out:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&xive->lock);
 	return xive->src_blocks[bid];
 }
 
@@ -1502,7 +1654,7 @@
 	sb = kvmppc_xive_find_source(xive, irq, &idx);
 	if (!sb) {
 		pr_devel("No source, creating source block...\n");
-		sb = xive_create_src_block(xive, irq);
+		sb = kvmppc_xive_create_src_block(xive, irq);
 		if (!sb) {
 			pr_devel("Failed to create block...\n");
 			return -ENOMEM;
@@ -1567,9 +1719,9 @@
 	/* If we have a priority target the interrupt */
 	if (act_prio != MASKED) {
 		/* First, check provisioning of queues */
-		mutex_lock(&xive->kvm->lock);
+		mutex_lock(&xive->lock);
 		rc = xive_check_provisioning(xive->kvm, act_prio);
-		mutex_unlock(&xive->kvm->lock);
+		mutex_unlock(&xive->lock);
 
 		/* Target interrupt */
 		if (rc == 0)
@@ -1723,10 +1875,9 @@
 {
 	xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01);
 	xive_native_configure_irq(hw_num, 0, MASKED, 0);
-	xive_cleanup_irq_data(xd);
 }
 
-static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
+void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
 {
 	int i;
 
@@ -1737,9 +1888,10 @@
 			continue;
 
 		kvmppc_xive_cleanup_irq(state->ipi_number, &state->ipi_data);
+		xive_cleanup_irq_data(&state->ipi_data);
 		xive_native_free_irq(state->ipi_number);
 
-		/* Pass-through, cleanup too */
+		/* Pass-through, cleanup too but keep IRQ hw data */
 		if (state->pt_number)
 			kvmppc_xive_cleanup_irq(state->pt_number, state->pt_data);
 
@@ -1747,16 +1899,53 @@
 	}
 }
 
-static void kvmppc_xive_free(struct kvm_device *dev)
+/*
+ * Called when device fd is closed.  kvm->lock is held.
+ */
+static void kvmppc_xive_release(struct kvm_device *dev)
 {
 	struct kvmppc_xive *xive = dev->private;
 	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
 	int i;
 
+	pr_devel("Releasing xive device\n");
+
+	/*
+	 * Since this is the device release function, we know that
+	 * userspace does not have any open fd referring to the
+	 * device.  Therefore there can not be any of the device
+	 * attribute set/get functions being executed concurrently,
+	 * and similarly, the connect_vcpu and set/clr_mapped
+	 * functions also cannot be being executed.
+	 */
+
 	debugfs_remove(xive->dentry);
 
-	if (kvm)
-		kvm->arch.xive = NULL;
+	/*
+	 * We should clean up the vCPU interrupt presenters first.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		/*
+		 * Take vcpu->mutex to ensure that no one_reg get/set ioctl
+		 * (i.e. kvmppc_xive_[gs]et_icp) can be done concurrently.
+		 * Holding the vcpu->mutex also means that the vcpu cannot
+		 * be executing the KVM_RUN ioctl, and therefore it cannot
+		 * be executing the XIVE push or pull code or accessing
+		 * the XIVE MMIO regions.
+		 */
+		mutex_lock(&vcpu->mutex);
+		kvmppc_xive_cleanup_vcpu(vcpu);
+		mutex_unlock(&vcpu->mutex);
+	}
+
+	/*
+	 * Now that we have cleared vcpu->arch.xive_vcpu, vcpu->arch.irq_type
+	 * and vcpu->arch.xive_esc_[vr]addr on each vcpu, we are safe
+	 * against xive code getting called during vcpu execution or
+	 * set/get one_reg operations.
+	 */
+	kvm->arch.xive = NULL;
 
 	/* Mask and free interrupts */
 	for (i = 0; i <= xive->max_sbid; i++) {
@@ -1769,11 +1958,45 @@
 	if (xive->vp_base != XIVE_INVALID_VP)
 		xive_native_free_vp_block(xive->vp_base);
 
+	/*
+	 * A reference of the kvmppc_xive pointer is now kept under
+	 * the xive_devices struct of the machine for reuse. It is
+	 * freed when the VM is destroyed for now until we fix all the
+	 * execution paths.
+	 */
 
-	kfree(xive);
 	kfree(dev);
 }
 
+/*
+ * When the guest chooses the interrupt mode (XICS legacy or XIVE
+ * native), the VM will switch of KVM device. The previous device will
+ * be "released" before the new one is created.
+ *
+ * Until we are sure all execution paths are well protected, provide a
+ * fail safe (transitional) method for device destruction, in which
+ * the XIVE device pointer is recycled and not directly freed.
+ */
+struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type)
+{
+	struct kvmppc_xive **kvm_xive_device = type == KVM_DEV_TYPE_XIVE ?
+		&kvm->arch.xive_devices.native :
+		&kvm->arch.xive_devices.xics_on_xive;
+	struct kvmppc_xive *xive = *kvm_xive_device;
+
+	if (!xive) {
+		xive = kzalloc(sizeof(*xive), GFP_KERNEL);
+		*kvm_xive_device = xive;
+	} else {
+		memset(xive, 0, sizeof(*xive));
+	}
+
+	return xive;
+}
+
+/*
+ * Create a XICS device with XIVE backend.  kvm->lock is held.
+ */
 static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 {
 	struct kvmppc_xive *xive;
@@ -1782,13 +2005,14 @@
 
 	pr_devel("Creating xive for partition\n");
 
-	xive = kzalloc(sizeof(*xive), GFP_KERNEL);
+	xive = kvmppc_xive_get_device(kvm, type);
 	if (!xive)
 		return -ENOMEM;
 
 	dev->private = xive;
 	xive->dev = dev;
 	xive->kvm = kvm;
+	mutex_init(&xive->lock);
 
 	/* Already there ? */
 	if (kvm->arch.xive)
@@ -1812,14 +2036,49 @@
 
 	xive->single_escalation = xive_native_has_single_escalation();
 
-	if (ret) {
-		kfree(xive);
+	if (ret)
 		return ret;
-	}
 
 	return 0;
 }
 
+int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	unsigned int i;
+
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		struct xive_q *q = &xc->queues[i];
+		u32 i0, i1, idx;
+
+		if (!q->qpage && !xc->esc_virq[i])
+			continue;
+
+		seq_printf(m, " [q%d]: ", i);
+
+		if (q->qpage) {
+			idx = q->idx;
+			i0 = be32_to_cpup(q->qpage + idx);
+			idx = (idx + 1) & q->msk;
+			i1 = be32_to_cpup(q->qpage + idx);
+			seq_printf(m, "T=%d %08x %08x...\n", q->toggle,
+				   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);
+			u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
+
+			seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
+				   (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
+				   (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
+				   xc->esc_virq[i], pq, xd->eoi_page);
+			seq_puts(m, "\n");
+		}
+	}
+	return 0;
+}
 
 static int xive_debug_show(struct seq_file *m, void *private)
 {
@@ -1845,7 +2104,6 @@
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
-		unsigned int i;
 
 		if (!xc)
 			continue;
@@ -1855,33 +2113,8 @@
 			   xc->server_num, xc->cppr, xc->hw_cppr,
 			   xc->mfrr, xc->pending,
 			   xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
-		for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
-			struct xive_q *q = &xc->queues[i];
-			u32 i0, i1, idx;
 
-			if (!q->qpage && !xc->esc_virq[i])
-				continue;
-
-			seq_printf(m, " [q%d]: ", i);
-
-			if (q->qpage) {
-				idx = q->idx;
-				i0 = be32_to_cpup(q->qpage + idx);
-				idx = (idx + 1) & q->msk;
-				i1 = be32_to_cpup(q->qpage + idx);
-				seq_printf(m, "T=%d %08x %08x... \n", q->toggle, 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);
-				u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
-				seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
-					   (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
-					   (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
-					   xc->esc_virq[i], pq, xd->eoi_page);
-				seq_printf(m, "\n");
-			}
-		}
+		kvmppc_xive_debug_show_queues(m, vcpu);
 
 		t_rm_h_xirr += xc->stat_rm_h_xirr;
 		t_rm_h_ipoll += xc->stat_rm_h_ipoll;
@@ -1905,17 +2138,7 @@
 	return 0;
 }
 
-static int xive_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, xive_debug_show, inode->i_private);
-}
-
-static const struct file_operations xive_debug_fops = {
-	.open = xive_debug_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(xive_debug);
 
 static void xive_debugfs_init(struct kvmppc_xive *xive)
 {
@@ -1946,7 +2169,7 @@
 	.name = "kvm-xive",
 	.create = kvmppc_xive_create,
 	.init = kvmppc_xive_init,
-	.destroy = kvmppc_xive_free,
+	.release = kvmppc_xive_release,
 	.set_attr = xive_set_attr,
 	.get_attr = xive_get_attr,
 	.has_attr = xive_has_attr,
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index a08ae6f..fe3ed50 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #ifndef _KVM_PPC_BOOK3S_XIVE_H
@@ -13,6 +10,13 @@
 #include "book3s_xics.h"
 
 /*
+ * The XIVE Interrupt source numbers are within the range 0 to
+ * KVMPPC_XICS_NR_IRQS.
+ */
+#define KVMPPC_XIVE_FIRST_IRQ	0
+#define KVMPPC_XIVE_NR_IRQS	KVMPPC_XICS_NR_IRQS
+
+/*
  * State for one guest irq source.
  *
  * For each guest source we allocate a HW interrupt in the XIVE
@@ -54,6 +58,9 @@
 	bool saved_p;
 	bool saved_q;
 	u8 saved_scan_prio;
+
+	/* Xive native */
+	u32 eisn;			/* Guest Effective IRQ number */
 };
 
 /* Select the "right" interrupt (IPI vs. passthrough) */
@@ -84,6 +91,11 @@
 	struct kvmppc_xive_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
 };
 
+struct kvmppc_xive;
+
+struct kvmppc_xive_ops {
+	int (*reset_mapped)(struct kvm *kvm, unsigned long guest_irq);
+};
 
 struct kvmppc_xive {
 	struct kvm *kvm;
@@ -122,6 +134,11 @@
 
 	/* Flags */
 	u8	single_escalation;
+
+	struct kvmppc_xive_ops *ops;
+	struct address_space   *mapping;
+	struct mutex mapping_lock;
+	struct mutex lock;
 };
 
 #define KVMPPC_XIVE_Q_COUNT	8
@@ -198,6 +215,23 @@
 	return xive->src_blocks[bid];
 }
 
+static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server)
+{
+	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
+}
+
+static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id)
+			return true;
+	}
+	return false;
+}
+
 /*
  * Mapping between guest priorities and host priorities
  * is as follow.
@@ -248,5 +282,20 @@
 extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
 extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
 
+/*
+ * Common Xive routines for XICS-over-XIVE and XIVE native
+ */
+void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu);
+int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu);
+struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
+	struct kvmppc_xive *xive, int irq);
+void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb);
+int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio);
+int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
+				  bool single_escalation);
+struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type);
+void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu,
+				    struct kvmppc_xive_vcpu *xc, int irq);
+
 #endif /* CONFIG_KVM_XICS */
 #endif /* _KVM_PPC_BOOK3S_XICS_H */
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
new file mode 100644
index 0000000..78b906f
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -0,0 +1,1278 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2019, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "xive-kvm: " fmt
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/gfp.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/file.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/opal.h>
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "book3s_xive.h"
+
+static u8 xive_vm_esb_load(struct xive_irq_data *xd, u32 offset)
+{
+	u64 val;
+
+	if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG)
+		offset |= offset << 4;
+
+	val = in_be64(xd->eoi_mmio + offset);
+	return (u8)val;
+}
+
+static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	struct xive_q *q = &xc->queues[prio];
+
+	xive_native_disable_queue(xc->vp_id, q, prio);
+	if (q->qpage) {
+		put_page(virt_to_page(q->qpage));
+		q->qpage = NULL;
+	}
+}
+
+void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	int i;
+
+	if (!kvmppc_xive_enabled(vcpu))
+		return;
+
+	if (!xc)
+		return;
+
+	pr_devel("native_cleanup_vcpu(cpu=%d)\n", xc->server_num);
+
+	/* Ensure no interrupt is still routed to that VP */
+	xc->valid = false;
+	kvmppc_xive_disable_vcpu_interrupts(vcpu);
+
+	/* Free escalations */
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		/* Free the escalation irq */
+		if (xc->esc_virq[i]) {
+			if (xc->xive->single_escalation)
+				xive_cleanup_single_escalation(vcpu, xc,
+							xc->esc_virq[i]);
+			free_irq(xc->esc_virq[i], vcpu);
+			irq_dispose_mapping(xc->esc_virq[i]);
+			kfree(xc->esc_virq_names[i]);
+			xc->esc_virq[i] = 0;
+		}
+	}
+
+	/* Disable the VP */
+	xive_native_disable_vp(xc->vp_id);
+
+	/* Clear the cam word so guest entry won't try to push context */
+	vcpu->arch.xive_cam_word = 0;
+
+	/* Free the queues */
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		kvmppc_xive_native_cleanup_queue(vcpu, i);
+	}
+
+	/* Free the VP */
+	kfree(xc);
+
+	/* Cleanup the vcpu */
+	vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
+	vcpu->arch.xive_vcpu = NULL;
+}
+
+int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
+				    struct kvm_vcpu *vcpu, u32 server_num)
+{
+	struct kvmppc_xive *xive = dev->private;
+	struct kvmppc_xive_vcpu *xc = NULL;
+	int rc;
+	u32 vp_id;
+
+	pr_devel("native_connect_vcpu(server=%d)\n", server_num);
+
+	if (dev->ops != &kvm_xive_native_ops) {
+		pr_devel("Wrong ops !\n");
+		return -EPERM;
+	}
+	if (xive->kvm != vcpu->kvm)
+		return -EPERM;
+	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
+		return -EBUSY;
+	if (server_num >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
+		pr_devel("Out of bounds !\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&xive->lock);
+
+	vp_id = kvmppc_xive_vp(xive, server_num);
+	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
+		pr_devel("Duplicate !\n");
+		rc = -EEXIST;
+		goto bail;
+	}
+
+	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+	if (!xc) {
+		rc = -ENOMEM;
+		goto bail;
+	}
+
+	vcpu->arch.xive_vcpu = xc;
+	xc->xive = xive;
+	xc->vcpu = vcpu;
+	xc->server_num = server_num;
+
+	xc->vp_id = vp_id;
+	xc->valid = true;
+	vcpu->arch.irq_type = KVMPPC_IRQ_XIVE;
+
+	rc = xive_native_get_vp_info(xc->vp_id, &xc->vp_cam, &xc->vp_chip_id);
+	if (rc) {
+		pr_err("Failed to get VP info from OPAL: %d\n", rc);
+		goto bail;
+	}
+
+	/*
+	 * Enable the VP first as the single escalation mode will
+	 * affect escalation interrupts numbering
+	 */
+	rc = xive_native_enable_vp(xc->vp_id, xive->single_escalation);
+	if (rc) {
+		pr_err("Failed to enable VP in OPAL: %d\n", rc);
+		goto bail;
+	}
+
+	/* Configure VCPU fields for use by assembly push/pull */
+	vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
+	vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
+
+	/* TODO: reset all queues to a clean state ? */
+bail:
+	mutex_unlock(&xive->lock);
+	if (rc)
+		kvmppc_xive_native_cleanup_vcpu(vcpu);
+
+	return rc;
+}
+
+/*
+ * Device passthrough support
+ */
+static int kvmppc_xive_native_reset_mapped(struct kvm *kvm, unsigned long irq)
+{
+	struct kvmppc_xive *xive = kvm->arch.xive;
+	pgoff_t esb_pgoff = KVM_XIVE_ESB_PAGE_OFFSET + irq * 2;
+
+	if (irq >= KVMPPC_XIVE_NR_IRQS)
+		return -EINVAL;
+
+	/*
+	 * Clear the ESB pages of the IRQ number being mapped (or
+	 * unmapped) into the guest and let the the VM fault handler
+	 * repopulate with the appropriate ESB pages (device or IC)
+	 */
+	pr_debug("clearing esb pages for girq 0x%lx\n", irq);
+	mutex_lock(&xive->mapping_lock);
+	if (xive->mapping)
+		unmap_mapping_range(xive->mapping,
+				    esb_pgoff << PAGE_SHIFT,
+				    2ull << PAGE_SHIFT, 1);
+	mutex_unlock(&xive->mapping_lock);
+	return 0;
+}
+
+static struct kvmppc_xive_ops kvmppc_xive_native_ops =  {
+	.reset_mapped = kvmppc_xive_native_reset_mapped,
+};
+
+static vm_fault_t xive_native_esb_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct kvm_device *dev = vma->vm_file->private_data;
+	struct kvmppc_xive *xive = dev->private;
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	struct xive_irq_data *xd;
+	u32 hw_num;
+	u16 src;
+	u64 page;
+	unsigned long irq;
+	u64 page_offset;
+
+	/*
+	 * Linux/KVM uses a two pages ESB setting, one for trigger and
+	 * one for EOI
+	 */
+	page_offset = vmf->pgoff - vma->vm_pgoff;
+	irq = page_offset / 2;
+
+	sb = kvmppc_xive_find_source(xive, irq, &src);
+	if (!sb) {
+		pr_devel("%s: source %lx not found !\n", __func__, irq);
+		return VM_FAULT_SIGBUS;
+	}
+
+	state = &sb->irq_state[src];
+	kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+	arch_spin_lock(&sb->lock);
+
+	/*
+	 * first/even page is for trigger
+	 * second/odd page is for EOI and management.
+	 */
+	page = page_offset % 2 ? xd->eoi_page : xd->trig_page;
+	arch_spin_unlock(&sb->lock);
+
+	if (WARN_ON(!page)) {
+		pr_err("%s: accessing invalid ESB page for source %lx !\n",
+		       __func__, irq);
+		return VM_FAULT_SIGBUS;
+	}
+
+	vmf_insert_pfn(vma, vmf->address, page >> PAGE_SHIFT);
+	return VM_FAULT_NOPAGE;
+}
+
+static const struct vm_operations_struct xive_native_esb_vmops = {
+	.fault = xive_native_esb_fault,
+};
+
+static vm_fault_t xive_native_tima_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+
+	switch (vmf->pgoff - vma->vm_pgoff) {
+	case 0: /* HW - forbid access */
+	case 1: /* HV - forbid access */
+		return VM_FAULT_SIGBUS;
+	case 2: /* OS */
+		vmf_insert_pfn(vma, vmf->address, xive_tima_os >> PAGE_SHIFT);
+		return VM_FAULT_NOPAGE;
+	case 3: /* USER - TODO */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+}
+
+static const struct vm_operations_struct xive_native_tima_vmops = {
+	.fault = xive_native_tima_fault,
+};
+
+static int kvmppc_xive_native_mmap(struct kvm_device *dev,
+				   struct vm_area_struct *vma)
+{
+	struct kvmppc_xive *xive = dev->private;
+
+	/* We only allow mappings at fixed offset for now */
+	if (vma->vm_pgoff == KVM_XIVE_TIMA_PAGE_OFFSET) {
+		if (vma_pages(vma) > 4)
+			return -EINVAL;
+		vma->vm_ops = &xive_native_tima_vmops;
+	} else if (vma->vm_pgoff == KVM_XIVE_ESB_PAGE_OFFSET) {
+		if (vma_pages(vma) > KVMPPC_XIVE_NR_IRQS * 2)
+			return -EINVAL;
+		vma->vm_ops = &xive_native_esb_vmops;
+	} else {
+		return -EINVAL;
+	}
+
+	vma->vm_flags |= VM_IO | VM_PFNMAP;
+	vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
+
+	/*
+	 * Grab the KVM device file address_space to be able to clear
+	 * the ESB pages mapping when a device is passed-through into
+	 * the guest.
+	 */
+	xive->mapping = vma->vm_file->f_mapping;
+	return 0;
+}
+
+static int kvmppc_xive_native_set_source(struct kvmppc_xive *xive, long irq,
+					 u64 addr)
+{
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	u64 __user *ubufp = (u64 __user *) addr;
+	u64 val;
+	u16 idx;
+	int rc;
+
+	pr_devel("%s irq=0x%lx\n", __func__, irq);
+
+	if (irq < KVMPPC_XIVE_FIRST_IRQ || irq >= KVMPPC_XIVE_NR_IRQS)
+		return -E2BIG;
+
+	sb = kvmppc_xive_find_source(xive, irq, &idx);
+	if (!sb) {
+		pr_debug("No source, creating source block...\n");
+		sb = kvmppc_xive_create_src_block(xive, irq);
+		if (!sb) {
+			pr_err("Failed to create block...\n");
+			return -ENOMEM;
+		}
+	}
+	state = &sb->irq_state[idx];
+
+	if (get_user(val, ubufp)) {
+		pr_err("fault getting user info !\n");
+		return -EFAULT;
+	}
+
+	arch_spin_lock(&sb->lock);
+
+	/*
+	 * If the source doesn't already have an IPI, allocate
+	 * one and get the corresponding data
+	 */
+	if (!state->ipi_number) {
+		state->ipi_number = xive_native_alloc_irq();
+		if (state->ipi_number == 0) {
+			pr_err("Failed to allocate IRQ !\n");
+			rc = -ENXIO;
+			goto unlock;
+		}
+		xive_native_populate_irq_data(state->ipi_number,
+					      &state->ipi_data);
+		pr_debug("%s allocated hw_irq=0x%x for irq=0x%lx\n", __func__,
+			 state->ipi_number, irq);
+	}
+
+	/* Restore LSI state */
+	if (val & KVM_XIVE_LEVEL_SENSITIVE) {
+		state->lsi = true;
+		if (val & KVM_XIVE_LEVEL_ASSERTED)
+			state->asserted = true;
+		pr_devel("  LSI ! Asserted=%d\n", state->asserted);
+	}
+
+	/* Mask IRQ to start with */
+	state->act_server = 0;
+	state->act_priority = MASKED;
+	xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+	xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
+
+	/* Increment the number of valid sources and mark this one valid */
+	if (!state->valid)
+		xive->src_count++;
+	state->valid = true;
+
+	rc = 0;
+
+unlock:
+	arch_spin_unlock(&sb->lock);
+
+	return rc;
+}
+
+static int kvmppc_xive_native_update_source_config(struct kvmppc_xive *xive,
+					struct kvmppc_xive_src_block *sb,
+					struct kvmppc_xive_irq_state *state,
+					u32 server, u8 priority, bool masked,
+					u32 eisn)
+{
+	struct kvm *kvm = xive->kvm;
+	u32 hw_num;
+	int rc = 0;
+
+	arch_spin_lock(&sb->lock);
+
+	if (state->act_server == server && state->act_priority == priority &&
+	    state->eisn == eisn)
+		goto unlock;
+
+	pr_devel("new_act_prio=%d new_act_server=%d mask=%d act_server=%d act_prio=%d\n",
+		 priority, server, masked, state->act_server,
+		 state->act_priority);
+
+	kvmppc_xive_select_irq(state, &hw_num, NULL);
+
+	if (priority != MASKED && !masked) {
+		rc = kvmppc_xive_select_target(kvm, &server, priority);
+		if (rc)
+			goto unlock;
+
+		state->act_priority = priority;
+		state->act_server = server;
+		state->eisn = eisn;
+
+		rc = xive_native_configure_irq(hw_num,
+					       kvmppc_xive_vp(xive, server),
+					       priority, eisn);
+	} else {
+		state->act_priority = MASKED;
+		state->act_server = 0;
+		state->eisn = 0;
+
+		rc = xive_native_configure_irq(hw_num, 0, MASKED, 0);
+	}
+
+unlock:
+	arch_spin_unlock(&sb->lock);
+	return rc;
+}
+
+static int kvmppc_xive_native_set_source_config(struct kvmppc_xive *xive,
+						long irq, u64 addr)
+{
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	u64 __user *ubufp = (u64 __user *) addr;
+	u16 src;
+	u64 kvm_cfg;
+	u32 server;
+	u8 priority;
+	bool masked;
+	u32 eisn;
+
+	sb = kvmppc_xive_find_source(xive, irq, &src);
+	if (!sb)
+		return -ENOENT;
+
+	state = &sb->irq_state[src];
+
+	if (!state->valid)
+		return -EINVAL;
+
+	if (get_user(kvm_cfg, ubufp))
+		return -EFAULT;
+
+	pr_devel("%s irq=0x%lx cfg=%016llx\n", __func__, irq, kvm_cfg);
+
+	priority = (kvm_cfg & KVM_XIVE_SOURCE_PRIORITY_MASK) >>
+		KVM_XIVE_SOURCE_PRIORITY_SHIFT;
+	server = (kvm_cfg & KVM_XIVE_SOURCE_SERVER_MASK) >>
+		KVM_XIVE_SOURCE_SERVER_SHIFT;
+	masked = (kvm_cfg & KVM_XIVE_SOURCE_MASKED_MASK) >>
+		KVM_XIVE_SOURCE_MASKED_SHIFT;
+	eisn = (kvm_cfg & KVM_XIVE_SOURCE_EISN_MASK) >>
+		KVM_XIVE_SOURCE_EISN_SHIFT;
+
+	if (priority != xive_prio_from_guest(priority)) {
+		pr_err("invalid priority for queue %d for VCPU %d\n",
+		       priority, server);
+		return -EINVAL;
+	}
+
+	return kvmppc_xive_native_update_source_config(xive, sb, state, server,
+						       priority, masked, eisn);
+}
+
+static int kvmppc_xive_native_sync_source(struct kvmppc_xive *xive,
+					  long irq, u64 addr)
+{
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	struct xive_irq_data *xd;
+	u32 hw_num;
+	u16 src;
+	int rc = 0;
+
+	pr_devel("%s irq=0x%lx", __func__, irq);
+
+	sb = kvmppc_xive_find_source(xive, irq, &src);
+	if (!sb)
+		return -ENOENT;
+
+	state = &sb->irq_state[src];
+
+	rc = -EINVAL;
+
+	arch_spin_lock(&sb->lock);
+
+	if (state->valid) {
+		kvmppc_xive_select_irq(state, &hw_num, &xd);
+		xive_native_sync_source(hw_num);
+		rc = 0;
+	}
+
+	arch_spin_unlock(&sb->lock);
+	return rc;
+}
+
+static int xive_native_validate_queue_size(u32 qshift)
+{
+	/*
+	 * We only support 64K pages for the moment. This is also
+	 * advertised in the DT property "ibm,xive-eq-sizes"
+	 */
+	switch (qshift) {
+	case 0: /* EQ reset */
+	case 16:
+		return 0;
+	case 12:
+	case 21:
+	case 24:
+	default:
+		return -EINVAL;
+	}
+}
+
+static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
+					       long eq_idx, u64 addr)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	struct kvmppc_xive_vcpu *xc;
+	void __user *ubufp = (void __user *) addr;
+	u32 server;
+	u8 priority;
+	struct kvm_ppc_xive_eq kvm_eq;
+	int rc;
+	__be32 *qaddr = 0;
+	struct page *page;
+	struct xive_q *q;
+	gfn_t gfn;
+	unsigned long page_size;
+	int srcu_idx;
+
+	/*
+	 * Demangle priority/server tuple from the EQ identifier
+	 */
+	priority = (eq_idx & KVM_XIVE_EQ_PRIORITY_MASK) >>
+		KVM_XIVE_EQ_PRIORITY_SHIFT;
+	server = (eq_idx & KVM_XIVE_EQ_SERVER_MASK) >>
+		KVM_XIVE_EQ_SERVER_SHIFT;
+
+	if (copy_from_user(&kvm_eq, ubufp, sizeof(kvm_eq)))
+		return -EFAULT;
+
+	vcpu = kvmppc_xive_find_server(kvm, server);
+	if (!vcpu) {
+		pr_err("Can't find server %d\n", server);
+		return -ENOENT;
+	}
+	xc = vcpu->arch.xive_vcpu;
+
+	if (priority != xive_prio_from_guest(priority)) {
+		pr_err("Trying to restore invalid queue %d for VCPU %d\n",
+		       priority, server);
+		return -EINVAL;
+	}
+	q = &xc->queues[priority];
+
+	pr_devel("%s VCPU %d priority %d fl:%x shift:%d addr:%llx g:%d idx:%d\n",
+		 __func__, server, priority, kvm_eq.flags,
+		 kvm_eq.qshift, kvm_eq.qaddr, kvm_eq.qtoggle, kvm_eq.qindex);
+
+	/* reset queue and disable queueing */
+	if (!kvm_eq.qshift) {
+		q->guest_qaddr  = 0;
+		q->guest_qshift = 0;
+
+		rc = xive_native_configure_queue(xc->vp_id, q, priority,
+						 NULL, 0, true);
+		if (rc) {
+			pr_err("Failed to reset queue %d for VCPU %d: %d\n",
+			       priority, xc->server_num, rc);
+			return rc;
+		}
+
+		if (q->qpage) {
+			put_page(virt_to_page(q->qpage));
+			q->qpage = NULL;
+		}
+
+		return 0;
+	}
+
+	/*
+	 * sPAPR specifies a "Unconditional Notify (n) flag" for the
+	 * H_INT_SET_QUEUE_CONFIG hcall which forces notification
+	 * without using the coalescing mechanisms provided by the
+	 * XIVE END ESBs. This is required on KVM as notification
+	 * using the END ESBs is not supported.
+	 */
+	if (kvm_eq.flags != KVM_XIVE_EQ_ALWAYS_NOTIFY) {
+		pr_err("invalid flags %d\n", kvm_eq.flags);
+		return -EINVAL;
+	}
+
+	rc = xive_native_validate_queue_size(kvm_eq.qshift);
+	if (rc) {
+		pr_err("invalid queue size %d\n", kvm_eq.qshift);
+		return rc;
+	}
+
+	if (kvm_eq.qaddr & ((1ull << kvm_eq.qshift) - 1)) {
+		pr_err("queue page is not aligned %llx/%llx\n", kvm_eq.qaddr,
+		       1ull << kvm_eq.qshift);
+		return -EINVAL;
+	}
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	gfn = gpa_to_gfn(kvm_eq.qaddr);
+	page = gfn_to_page(kvm, gfn);
+	if (is_error_page(page)) {
+		srcu_read_unlock(&kvm->srcu, srcu_idx);
+		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
+		return -EINVAL;
+	}
+
+	page_size = kvm_host_page_size(kvm, gfn);
+	if (1ull << kvm_eq.qshift > page_size) {
+		srcu_read_unlock(&kvm->srcu, srcu_idx);
+		pr_warn("Incompatible host page size %lx!\n", page_size);
+		return -EINVAL;
+	}
+
+	qaddr = page_to_virt(page) + (kvm_eq.qaddr & ~PAGE_MASK);
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	/*
+	 * Backup the queue page guest address to the mark EQ page
+	 * dirty for migration.
+	 */
+	q->guest_qaddr  = kvm_eq.qaddr;
+	q->guest_qshift = kvm_eq.qshift;
+
+	 /*
+	  * Unconditional Notification is forced by default at the
+	  * OPAL level because the use of END ESBs is not supported by
+	  * Linux.
+	  */
+	rc = xive_native_configure_queue(xc->vp_id, q, priority,
+					 (__be32 *) qaddr, kvm_eq.qshift, true);
+	if (rc) {
+		pr_err("Failed to configure queue %d for VCPU %d: %d\n",
+		       priority, xc->server_num, rc);
+		put_page(page);
+		return rc;
+	}
+
+	/*
+	 * Only restore the queue state when needed. When doing the
+	 * H_INT_SET_SOURCE_CONFIG hcall, it should not.
+	 */
+	if (kvm_eq.qtoggle != 1 || kvm_eq.qindex != 0) {
+		rc = xive_native_set_queue_state(xc->vp_id, priority,
+						 kvm_eq.qtoggle,
+						 kvm_eq.qindex);
+		if (rc)
+			goto error;
+	}
+
+	rc = kvmppc_xive_attach_escalation(vcpu, priority,
+					   xive->single_escalation);
+error:
+	if (rc)
+		kvmppc_xive_native_cleanup_queue(vcpu, priority);
+	return rc;
+}
+
+static int kvmppc_xive_native_get_queue_config(struct kvmppc_xive *xive,
+					       long eq_idx, u64 addr)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	struct kvmppc_xive_vcpu *xc;
+	struct xive_q *q;
+	void __user *ubufp = (u64 __user *) addr;
+	u32 server;
+	u8 priority;
+	struct kvm_ppc_xive_eq kvm_eq;
+	u64 qaddr;
+	u64 qshift;
+	u64 qeoi_page;
+	u32 escalate_irq;
+	u64 qflags;
+	int rc;
+
+	/*
+	 * Demangle priority/server tuple from the EQ identifier
+	 */
+	priority = (eq_idx & KVM_XIVE_EQ_PRIORITY_MASK) >>
+		KVM_XIVE_EQ_PRIORITY_SHIFT;
+	server = (eq_idx & KVM_XIVE_EQ_SERVER_MASK) >>
+		KVM_XIVE_EQ_SERVER_SHIFT;
+
+	vcpu = kvmppc_xive_find_server(kvm, server);
+	if (!vcpu) {
+		pr_err("Can't find server %d\n", server);
+		return -ENOENT;
+	}
+	xc = vcpu->arch.xive_vcpu;
+
+	if (priority != xive_prio_from_guest(priority)) {
+		pr_err("invalid priority for queue %d for VCPU %d\n",
+		       priority, server);
+		return -EINVAL;
+	}
+	q = &xc->queues[priority];
+
+	memset(&kvm_eq, 0, sizeof(kvm_eq));
+
+	if (!q->qpage)
+		return 0;
+
+	rc = xive_native_get_queue_info(xc->vp_id, priority, &qaddr, &qshift,
+					&qeoi_page, &escalate_irq, &qflags);
+	if (rc)
+		return rc;
+
+	kvm_eq.flags = 0;
+	if (qflags & OPAL_XIVE_EQ_ALWAYS_NOTIFY)
+		kvm_eq.flags |= KVM_XIVE_EQ_ALWAYS_NOTIFY;
+
+	kvm_eq.qshift = q->guest_qshift;
+	kvm_eq.qaddr  = q->guest_qaddr;
+
+	rc = xive_native_get_queue_state(xc->vp_id, priority, &kvm_eq.qtoggle,
+					 &kvm_eq.qindex);
+	if (rc)
+		return rc;
+
+	pr_devel("%s VCPU %d priority %d fl:%x shift:%d addr:%llx g:%d idx:%d\n",
+		 __func__, server, priority, kvm_eq.flags,
+		 kvm_eq.qshift, kvm_eq.qaddr, kvm_eq.qtoggle, kvm_eq.qindex);
+
+	if (copy_to_user(ubufp, &kvm_eq, sizeof(kvm_eq)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static void kvmppc_xive_reset_sources(struct kvmppc_xive_src_block *sb)
+{
+	int i;
+
+	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+		struct kvmppc_xive_irq_state *state = &sb->irq_state[i];
+
+		if (!state->valid)
+			continue;
+
+		if (state->act_priority == MASKED)
+			continue;
+
+		state->eisn = 0;
+		state->act_server = 0;
+		state->act_priority = MASKED;
+		xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+		xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
+		if (state->pt_number) {
+			xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_01);
+			xive_native_configure_irq(state->pt_number,
+						  0, MASKED, 0);
+		}
+	}
+}
+
+static int kvmppc_xive_reset(struct kvmppc_xive *xive)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned int i;
+
+	pr_devel("%s\n", __func__);
+
+	mutex_lock(&xive->lock);
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+		unsigned int prio;
+
+		if (!xc)
+			continue;
+
+		kvmppc_xive_disable_vcpu_interrupts(vcpu);
+
+		for (prio = 0; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
+
+			/* Single escalation, no queue 7 */
+			if (prio == 7 && xive->single_escalation)
+				break;
+
+			if (xc->esc_virq[prio]) {
+				free_irq(xc->esc_virq[prio], vcpu);
+				irq_dispose_mapping(xc->esc_virq[prio]);
+				kfree(xc->esc_virq_names[prio]);
+				xc->esc_virq[prio] = 0;
+			}
+
+			kvmppc_xive_native_cleanup_queue(vcpu, prio);
+		}
+	}
+
+	for (i = 0; i <= xive->max_sbid; i++) {
+		struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+		if (sb) {
+			arch_spin_lock(&sb->lock);
+			kvmppc_xive_reset_sources(sb);
+			arch_spin_unlock(&sb->lock);
+		}
+	}
+
+	mutex_unlock(&xive->lock);
+
+	return 0;
+}
+
+static void kvmppc_xive_native_sync_sources(struct kvmppc_xive_src_block *sb)
+{
+	int j;
+
+	for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++) {
+		struct kvmppc_xive_irq_state *state = &sb->irq_state[j];
+		struct xive_irq_data *xd;
+		u32 hw_num;
+
+		if (!state->valid)
+			continue;
+
+		/*
+		 * The struct kvmppc_xive_irq_state reflects the state
+		 * of the EAS configuration and not the state of the
+		 * source. The source is masked setting the PQ bits to
+		 * '-Q', which is what is being done before calling
+		 * the KVM_DEV_XIVE_EQ_SYNC control.
+		 *
+		 * If a source EAS is configured, OPAL syncs the XIVE
+		 * IC of the source and the XIVE IC of the previous
+		 * target if any.
+		 *
+		 * So it should be fine ignoring MASKED sources as
+		 * they have been synced already.
+		 */
+		if (state->act_priority == MASKED)
+			continue;
+
+		kvmppc_xive_select_irq(state, &hw_num, &xd);
+		xive_native_sync_source(hw_num);
+		xive_native_sync_queue(hw_num);
+	}
+}
+
+static int kvmppc_xive_native_vcpu_eq_sync(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	unsigned int prio;
+	int srcu_idx;
+
+	if (!xc)
+		return -ENOENT;
+
+	for (prio = 0; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
+		struct xive_q *q = &xc->queues[prio];
+
+		if (!q->qpage)
+			continue;
+
+		/* Mark EQ page dirty for migration */
+		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		mark_page_dirty(vcpu->kvm, gpa_to_gfn(q->guest_qaddr));
+		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+	}
+	return 0;
+}
+
+static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned int i;
+
+	pr_devel("%s\n", __func__);
+
+	mutex_lock(&xive->lock);
+	for (i = 0; i <= xive->max_sbid; i++) {
+		struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+		if (sb) {
+			arch_spin_lock(&sb->lock);
+			kvmppc_xive_native_sync_sources(sb);
+			arch_spin_unlock(&sb->lock);
+		}
+	}
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		kvmppc_xive_native_vcpu_eq_sync(vcpu);
+	}
+	mutex_unlock(&xive->lock);
+
+	return 0;
+}
+
+static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
+				       struct kvm_device_attr *attr)
+{
+	struct kvmppc_xive *xive = dev->private;
+
+	switch (attr->group) {
+	case KVM_DEV_XIVE_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XIVE_RESET:
+			return kvmppc_xive_reset(xive);
+		case KVM_DEV_XIVE_EQ_SYNC:
+			return kvmppc_xive_native_eq_sync(xive);
+		}
+		break;
+	case KVM_DEV_XIVE_GRP_SOURCE:
+		return kvmppc_xive_native_set_source(xive, attr->attr,
+						     attr->addr);
+	case KVM_DEV_XIVE_GRP_SOURCE_CONFIG:
+		return kvmppc_xive_native_set_source_config(xive, attr->attr,
+							    attr->addr);
+	case KVM_DEV_XIVE_GRP_EQ_CONFIG:
+		return kvmppc_xive_native_set_queue_config(xive, attr->attr,
+							   attr->addr);
+	case KVM_DEV_XIVE_GRP_SOURCE_SYNC:
+		return kvmppc_xive_native_sync_source(xive, attr->attr,
+						      attr->addr);
+	}
+	return -ENXIO;
+}
+
+static int kvmppc_xive_native_get_attr(struct kvm_device *dev,
+				       struct kvm_device_attr *attr)
+{
+	struct kvmppc_xive *xive = dev->private;
+
+	switch (attr->group) {
+	case KVM_DEV_XIVE_GRP_EQ_CONFIG:
+		return kvmppc_xive_native_get_queue_config(xive, attr->attr,
+							   attr->addr);
+	}
+	return -ENXIO;
+}
+
+static int kvmppc_xive_native_has_attr(struct kvm_device *dev,
+				       struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_XIVE_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XIVE_RESET:
+		case KVM_DEV_XIVE_EQ_SYNC:
+			return 0;
+		}
+		break;
+	case KVM_DEV_XIVE_GRP_SOURCE:
+	case KVM_DEV_XIVE_GRP_SOURCE_CONFIG:
+	case KVM_DEV_XIVE_GRP_SOURCE_SYNC:
+		if (attr->attr >= KVMPPC_XIVE_FIRST_IRQ &&
+		    attr->attr < KVMPPC_XIVE_NR_IRQS)
+			return 0;
+		break;
+	case KVM_DEV_XIVE_GRP_EQ_CONFIG:
+		return 0;
+	}
+	return -ENXIO;
+}
+
+/*
+ * Called when device fd is closed.  kvm->lock is held.
+ */
+static void kvmppc_xive_native_release(struct kvm_device *dev)
+{
+	struct kvmppc_xive *xive = dev->private;
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	pr_devel("Releasing xive native device\n");
+
+	/*
+	 * Clear the KVM device file address_space which is used to
+	 * unmap the ESB pages when a device is passed-through.
+	 */
+	mutex_lock(&xive->mapping_lock);
+	xive->mapping = NULL;
+	mutex_unlock(&xive->mapping_lock);
+
+	/*
+	 * Since this is the device release function, we know that
+	 * userspace does not have any open fd or mmap referring to
+	 * the device.  Therefore there can not be any of the
+	 * device attribute set/get, mmap, or page fault functions
+	 * being executed concurrently, and similarly, the
+	 * connect_vcpu and set/clr_mapped functions also cannot
+	 * be being executed.
+	 */
+
+	debugfs_remove(xive->dentry);
+
+	/*
+	 * We should clean up the vCPU interrupt presenters first.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		/*
+		 * Take vcpu->mutex to ensure that no one_reg get/set ioctl
+		 * (i.e. kvmppc_xive_native_[gs]et_vp) can be being done.
+		 * Holding the vcpu->mutex also means that the vcpu cannot
+		 * be executing the KVM_RUN ioctl, and therefore it cannot
+		 * be executing the XIVE push or pull code or accessing
+		 * the XIVE MMIO regions.
+		 */
+		mutex_lock(&vcpu->mutex);
+		kvmppc_xive_native_cleanup_vcpu(vcpu);
+		mutex_unlock(&vcpu->mutex);
+	}
+
+	/*
+	 * Now that we have cleared vcpu->arch.xive_vcpu, vcpu->arch.irq_type
+	 * and vcpu->arch.xive_esc_[vr]addr on each vcpu, we are safe
+	 * against xive code getting called during vcpu execution or
+	 * set/get one_reg operations.
+	 */
+	kvm->arch.xive = NULL;
+
+	for (i = 0; i <= xive->max_sbid; i++) {
+		if (xive->src_blocks[i])
+			kvmppc_xive_free_sources(xive->src_blocks[i]);
+		kfree(xive->src_blocks[i]);
+		xive->src_blocks[i] = NULL;
+	}
+
+	if (xive->vp_base != XIVE_INVALID_VP)
+		xive_native_free_vp_block(xive->vp_base);
+
+	/*
+	 * A reference of the kvmppc_xive pointer is now kept under
+	 * the xive_devices struct of the machine for reuse. It is
+	 * freed when the VM is destroyed for now until we fix all the
+	 * execution paths.
+	 */
+
+	kfree(dev);
+}
+
+/*
+ * Create a XIVE device.  kvm->lock is held.
+ */
+static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
+{
+	struct kvmppc_xive *xive;
+	struct kvm *kvm = dev->kvm;
+	int ret = 0;
+
+	pr_devel("Creating xive native device\n");
+
+	if (kvm->arch.xive)
+		return -EEXIST;
+
+	xive = kvmppc_xive_get_device(kvm, type);
+	if (!xive)
+		return -ENOMEM;
+
+	dev->private = xive;
+	xive->dev = dev;
+	xive->kvm = kvm;
+	kvm->arch.xive = xive;
+	mutex_init(&xive->mapping_lock);
+	mutex_init(&xive->lock);
+
+	/*
+	 * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for
+	 * a default. Getting the max number of CPUs the VM was
+	 * configured with would improve our usage of the XIVE VP space.
+	 */
+	xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
+	pr_devel("VP_Base=%x\n", xive->vp_base);
+
+	if (xive->vp_base == XIVE_INVALID_VP)
+		ret = -ENXIO;
+
+	xive->single_escalation = xive_native_has_single_escalation();
+	xive->ops = &kvmppc_xive_native_ops;
+
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/*
+ * Interrupt Pending Buffer (IPB) offset
+ */
+#define TM_IPB_SHIFT 40
+#define TM_IPB_MASK  (((u64) 0xFF) << TM_IPB_SHIFT)
+
+int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	u64 opal_state;
+	int rc;
+
+	if (!kvmppc_xive_enabled(vcpu))
+		return -EPERM;
+
+	if (!xc)
+		return -ENOENT;
+
+	/* Thread context registers. We only care about IPB and CPPR */
+	val->xive_timaval[0] = vcpu->arch.xive_saved_state.w01;
+
+	/* Get the VP state from OPAL */
+	rc = xive_native_get_vp_state(xc->vp_id, &opal_state);
+	if (rc)
+		return rc;
+
+	/*
+	 * Capture the backup of IPB register in the NVT structure and
+	 * merge it in our KVM VP state.
+	 */
+	val->xive_timaval[0] |= cpu_to_be64(opal_state & TM_IPB_MASK);
+
+	pr_devel("%s NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x opal=%016llx\n",
+		 __func__,
+		 vcpu->arch.xive_saved_state.nsr,
+		 vcpu->arch.xive_saved_state.cppr,
+		 vcpu->arch.xive_saved_state.ipb,
+		 vcpu->arch.xive_saved_state.pipr,
+		 vcpu->arch.xive_saved_state.w01,
+		 (u32) vcpu->arch.xive_cam_word, opal_state);
+
+	return 0;
+}
+
+int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
+
+	pr_devel("%s w01=%016llx vp=%016llx\n", __func__,
+		 val->xive_timaval[0], val->xive_timaval[1]);
+
+	if (!kvmppc_xive_enabled(vcpu))
+		return -EPERM;
+
+	if (!xc || !xive)
+		return -ENOENT;
+
+	/* We can't update the state of a "pushed" VCPU	 */
+	if (WARN_ON(vcpu->arch.xive_pushed))
+		return -EBUSY;
+
+	/*
+	 * Restore the thread context registers. IPB and CPPR should
+	 * be the only ones that matter.
+	 */
+	vcpu->arch.xive_saved_state.w01 = val->xive_timaval[0];
+
+	/*
+	 * There is no need to restore the XIVE internal state (IPB
+	 * stored in the NVT) as the IPB register was merged in KVM VP
+	 * state when captured.
+	 */
+	return 0;
+}
+
+bool kvmppc_xive_native_supported(void)
+{
+	return xive_native_has_queue_state_support();
+}
+
+static int xive_native_debug_show(struct seq_file *m, void *private)
+{
+	struct kvmppc_xive *xive = m->private;
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned int i;
+
+	if (!kvm)
+		return 0;
+
+	seq_puts(m, "=========\nVCPU state\n=========\n");
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+		if (!xc)
+			continue;
+
+		seq_printf(m, "cpu server %#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n",
+			   xc->server_num,
+			   vcpu->arch.xive_saved_state.nsr,
+			   vcpu->arch.xive_saved_state.cppr,
+			   vcpu->arch.xive_saved_state.ipb,
+			   vcpu->arch.xive_saved_state.pipr,
+			   vcpu->arch.xive_saved_state.w01,
+			   (u32) vcpu->arch.xive_cam_word);
+
+		kvmppc_xive_debug_show_queues(m, vcpu);
+	}
+
+	return 0;
+}
+
+static int xive_native_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, xive_native_debug_show, inode->i_private);
+}
+
+static const struct file_operations xive_native_debug_fops = {
+	.open = xive_native_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static void xive_native_debugfs_init(struct kvmppc_xive *xive)
+{
+	char *name;
+
+	name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive);
+	if (!name) {
+		pr_err("%s: no memory for name\n", __func__);
+		return;
+	}
+
+	xive->dentry = debugfs_create_file(name, 0444, powerpc_debugfs_root,
+					   xive, &xive_native_debug_fops);
+
+	pr_debug("%s: created %s\n", __func__, name);
+	kfree(name);
+}
+
+static void kvmppc_xive_native_init(struct kvm_device *dev)
+{
+	struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private;
+
+	/* Register some debug interfaces */
+	xive_native_debugfs_init(xive);
+}
+
+struct kvm_device_ops kvm_xive_native_ops = {
+	.name = "kvm-xive-native",
+	.create = kvmppc_xive_native_create,
+	.init = kvmppc_xive_native_init,
+	.release = kvmppc_xive_native_release,
+	.set_attr = kvmppc_xive_native_set_attr,
+	.get_attr = kvmppc_xive_native_get_attr,
+	.has_attr = kvmppc_xive_native_has_attr,
+	.mmap = kvmppc_xive_native_mmap,
+};
+
+void kvmppc_xive_native_init_module(void)
+{
+	;
+}
+
+void kvmppc_xive_native_exit_module(void)
+{
+	;
+}
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
index 4171ede..a8a900a 100644
--- a/arch/powerpc/kvm/book3s_xive_template.c
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation
- *
- * 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.
  */
 
 /* File to be included by other .c files */
@@ -130,25 +127,15 @@
 		 */
 		prio = ffs(pending) - 1;
 
-		/*
-		 * If the most favoured prio we found pending is less
-		 * favored (or equal) than a pending IPI, we return
-		 * the IPI instead.
-		 *
-		 * Note: If pending was 0 and mfrr is 0xff, we will
-		 * not spurriously take an IPI because mfrr cannot
-		 * then be smaller than cppr.
-		 */
-		if (prio >= xc->mfrr && xc->mfrr < xc->cppr) {
-			prio = xc->mfrr;
-			hirq = XICS_IPI;
+		/* Don't scan past the guest cppr */
+		if (prio >= xc->cppr || prio > 7) {
+			if (xc->mfrr < xc->cppr) {
+				prio = xc->mfrr;
+				hirq = XICS_IPI;
+			}
 			break;
 		}
 
-		/* Don't scan past the guest cppr */
-		if (prio >= xc->cppr || prio > 7)
-			break;
-
 		/* Grab queue and pointers */
 		q = &xc->queues[prio];
 		idx = q->idx;
@@ -184,9 +171,12 @@
 		 * been set and another occurrence of the IPI will trigger.
 		 */
 		if (hirq == XICS_IPI || (prio == 0 && !qpage)) {
-			if (scan_type == scan_fetch)
+			if (scan_type == scan_fetch) {
 				GLUE(X_PFX,source_eoi)(xc->vp_ipi,
 						       &xc->vp_ipi_data);
+				q->idx = idx;
+				q->toggle = toggle;
+			}
 			/* Loop back on same queue with updated idx/toggle */
 #ifdef XIVE_RUNTIME_CHECKS
 			WARN_ON(hirq && hirq != XICS_IPI);
@@ -199,32 +189,41 @@
 		if (hirq == XICS_DUMMY)
 			goto skip_ipi;
 
+		/* Clear the pending bit if the queue is now empty */
+		if (!hirq) {
+			pending &= ~(1 << prio);
+
+			/*
+			 * Check if the queue count needs adjusting due to
+			 * interrupts being moved away.
+			 */
+			if (atomic_read(&q->pending_count)) {
+				int p = atomic_xchg(&q->pending_count, 0);
+				if (p) {
+#ifdef XIVE_RUNTIME_CHECKS
+					WARN_ON(p > atomic_read(&q->count));
+#endif
+					atomic_sub(p, &q->count);
+				}
+			}
+		}
+
+		/*
+		 * If the most favoured prio we found pending is less
+		 * favored (or equal) than a pending IPI, we return
+		 * the IPI instead.
+		 */
+		if (prio >= xc->mfrr && xc->mfrr < xc->cppr) {
+			prio = xc->mfrr;
+			hirq = XICS_IPI;
+			break;
+		}
+
 		/* If fetching, update queue pointers */
 		if (scan_type == scan_fetch) {
 			q->idx = idx;
 			q->toggle = toggle;
 		}
-
-		/* Something found, stop searching */
-		if (hirq)
-			break;
-
-		/* Clear the pending bit on the now empty queue */
-		pending &= ~(1 << prio);
-
-		/*
-		 * Check if the queue count needs adjusting due to
-		 * interrupts being moved away.
-		 */
-		if (atomic_read(&q->pending_count)) {
-			int p = atomic_xchg(&q->pending_count, 0);
-			if (p) {
-#ifdef XIVE_RUNTIME_CHECKS
-				WARN_ON(p > atomic_read(&q->count));
-#endif
-				atomic_sub(p, &q->count);
-			}
-		}
 	}
 
 	/* If we are just taking a "peek", do nothing else */
@@ -280,14 +279,6 @@
 	/* First collect pending bits from HW */
 	GLUE(X_PFX,ack_pending)(xc);
 
-	/*
-	 * Cleanup the old-style bits if needed (they may have been
-	 * set by pull or an escalation interrupts).
-	 */
-	if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions))
-		clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
-			  &vcpu->arch.pending_exceptions);
-
 	pr_devel(" new pending=0x%02x hw_cppr=%d cppr=%d\n",
 		 xc->pending, xc->hw_cppr, xc->cppr);
 
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index a9ca016..be9a458 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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
  * Copyright 2010-2011 Freescale Semiconductor, Inc.
@@ -1833,7 +1822,8 @@
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 }
 
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 22ba08e..9d3169f 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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
  *
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index d23e582..689ff5f 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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
  * Copyright 2011 Freescale Semiconductor, Inc.
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 84c308a..2e56ab5 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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
  * Copyright 2011 Freescale Semiconductor, Inc.
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index 81bd8a0..c577ba4 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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 (C) 2010-2011 Freescale Semiconductor, Inc.
  *
@@ -75,6 +64,10 @@
 	PPC_LL	r1, VCPU_HOST_STACK(r4)
 	PPC_LL	r2, HOST_R2(r1)
 
+START_BTB_FLUSH_SECTION
+	BTB_FLUSH(r10)
+END_BTB_FLUSH_SECTION
+
 	mfspr	r10, SPRN_PID
 	lwz	r8, VCPU_HOST_PID(r4)
 	PPC_LL	r11, VCPU_SHARED(r4)
@@ -182,7 +175,7 @@
 	 */
 	PPC_LL	r4, PACACURRENT(r13)
 	PPC_LL	r4, (THREAD + THREAD_KVM_VCPU)(r4)
-	stw	r10, VCPU_CR(r4)
+	PPC_STL	r10, VCPU_CR(r4)
 	PPC_STL r11, VCPU_GPR(R4)(r4)
 	PPC_STL	r5, VCPU_GPR(R5)(r4)
 	PPC_STL	r6, VCPU_GPR(R6)(r4)
@@ -292,7 +285,7 @@
 	PPC_STL	r4, VCPU_GPR(R4)(r11)
 	PPC_LL	r4, THREAD_NORMSAVE(0)(r10)
 	PPC_STL	r5, VCPU_GPR(R5)(r11)
-	stw	r13, VCPU_CR(r11)
+	PPC_STL	r13, VCPU_CR(r11)
 	mfspr	r5, \srr0
 	PPC_STL	r3, VCPU_GPR(R10)(r11)
 	PPC_LL	r3, THREAD_NORMSAVE(2)(r10)
@@ -319,7 +312,7 @@
 	PPC_STL	r4, VCPU_GPR(R4)(r11)
 	PPC_LL	r4, GPR9(r8)
 	PPC_STL	r5, VCPU_GPR(R5)(r11)
-	stw	r9, VCPU_CR(r11)
+	PPC_STL	r9, VCPU_CR(r11)
 	mfspr	r5, \srr0
 	PPC_STL	r3, VCPU_GPR(R8)(r11)
 	PPC_LL	r3, GPR10(r8)
@@ -643,7 +636,7 @@
 	PPC_LL	r3, VCPU_LR(r4)
 	PPC_LL	r5, VCPU_XER(r4)
 	PPC_LL	r6, VCPU_CTR(r4)
-	lwz	r7, VCPU_CR(r4)
+	PPC_LL	r7, VCPU_CR(r4)
 	PPC_LL	r8, VCPU_PC(r4)
 	PPC_LD(r9, VCPU_SHARED_MSR, r11)
 	PPC_LL	r0, VCPU_GPR(R0)(r4)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index afd3c25..00649ca 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -6,10 +7,6 @@
  * Description:
  * This file is derived from arch/powerpc/kvm/44x.c,
  * by Hollis Blanchard <hollisb@us.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kvm_host.h>
@@ -443,6 +440,9 @@
 	struct kvm_vcpu *vcpu;
 	int err;
 
+	BUILD_BUG_ON_MSG(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0,
+		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
+
 	vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu_e500) {
 		err = -ENOMEM;
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index 94f04fc..c3ef751 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -10,17 +11,13 @@
  * This file is based on arch/powerpc/kvm/44x_tlb.h and
  * arch/powerpc/include/asm/kvm_44x.h by Hollis Blanchard <hollisb@us.ibm.com>,
  * Copyright IBM Corp. 2007-2008
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #ifndef KVM_E500_H
 #define KVM_E500_H
 
 #include <linux/kvm_host.h>
-#include <asm/mmu-book3e.h>
+#include <asm/nohash/mmu-book3e.h>
 #include <asm/tlb.h>
 #include <asm/cputhreads.h>
 
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 3f8189e..3d0d3ec 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -6,10 +7,6 @@
  * Description:
  * This file is derived from arch/powerpc/kvm/44x_emulate.c,
  * by Hollis Blanchard <hollisb@us.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <asm/kvm_ppc.h>
@@ -277,6 +274,13 @@
 		vcpu->arch.pwrmgtcr0 = spr_val;
 		break;
 
+	case SPRN_BUCSR:
+		/*
+		 * If we are here, it means that we have already flushed the
+		 * branch predictor, so just return to guest.
+		 */
+		break;
+
 	/* extra exceptions */
 #ifdef CONFIG_SPE_POSSIBLE
 	case SPRN_IVOR32:
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index 24296f4..2d910b8 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -10,10 +11,6 @@
  * Description:
  * This file is based on arch/powerpc/kvm/44x_tlb.c,
  * by Hollis Blanchard <hollisb@us.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kernel.h>
@@ -783,7 +780,7 @@
 	if (!pages)
 		return -ENOMEM;
 
-	ret = get_user_pages_fast(cfg->array, num_pages, 1, pages);
+	ret = get_user_pages_fast(cfg->array, num_pages, FOLL_WRITE, pages);
 	if (ret < 0)
 		goto free_pages;
 
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 8f2985e..321db0f 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -10,10 +11,6 @@
  * Description:
  * This file is based on arch/powerpc/kvm/44x_tlb.c,
  * by Hollis Blanchard <hollisb@us.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kernel.h>
@@ -757,10 +754,11 @@
 	return 0;
 }
 
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	/* The page will get remapped properly on its next fault */
 	kvm_unmap_hva(kvm, hva);
+	return 0;
 }
 
 /*****************************************/
diff --git a/arch/powerpc/kvm/e500_mmu_host.h b/arch/powerpc/kvm/e500_mmu_host.h
index 7624835..d8178cc 100644
--- a/arch/powerpc/kvm/e500_mmu_host.h
+++ b/arch/powerpc/kvm/e500_mmu_host.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #ifndef KVM_E500_MMU_HOST_H
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index d316454..318e65c 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2010,2012 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -6,10 +7,6 @@
  * Description:
  * This file is derived from arch/powerpc/kvm/e500.c,
  * by Yu Liu <yu.liu@freescale.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/kvm_host.h>
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index fa888bf..6fca38c 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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
  * Copyright 2011 Freescale Semiconductor, Inc.
@@ -61,11 +50,10 @@
 
 	dec_time = vcpu->arch.dec;
 	/*
-	 * Guest timebase ticks at the same frequency as host decrementer.
-	 * So use the host decrementer calculations for decrementer emulation.
+	 * Guest timebase ticks at the same frequency as host timebase.
+	 * So use the host timebase calculations for decrementer emulation.
 	 */
-	dec_time = dec_time << decrementer_clockevent.shift;
-	do_div(dec_time, decrementer_clockevent.mult);
+	dec_time = tb_to_ns(dec_time);
 	dec_nsec = do_div(dec_time, NSEC_PER_SEC);
 	hrtimer_start(&vcpu->arch.dec_timer,
 		ktime_set(dec_time, dec_nsec), HRTIMER_MODE_REL);
@@ -283,6 +271,7 @@
 		 */
 		if (inst == KVMPPC_INST_SW_BREAKPOINT) {
 			run->exit_reason = KVM_EXIT_DEBUG;
+			run->debug.arch.status = 0;
 			run->debug.arch.address = kvmppc_get_pc(vcpu);
 			emulated = EMULATE_EXIT_USER;
 			advance = 0;
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 75dce1e..2e496eb 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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
  * Copyright 2011 Freescale Semiconductor, Inc.
@@ -100,12 +89,6 @@
 	rs = get_rs(inst);
 	rt = get_rt(inst);
 
-	/*
-	 * if mmio_vsx_tx_sx_enabled == 0, copy data between
-	 * VSR[0..31] and memory
-	 * if mmio_vsx_tx_sx_enabled == 1, copy data between
-	 * VSR[32..63] and memory
-	 */
 	vcpu->arch.mmio_vsx_copy_nums = 0;
 	vcpu->arch.mmio_vsx_offset = 0;
 	vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
@@ -117,7 +100,6 @@
 
 	emulated = EMULATE_FAIL;
 	vcpu->arch.regs.msr = vcpu->arch.shared->msr;
-	vcpu->arch.regs.ccr = vcpu->arch.cr;
 	if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) {
 		int type = op.type & INSTR_TYPE_MASK;
 		int size = GETSIZE(op.type);
diff --git a/arch/powerpc/kvm/fpu.S b/arch/powerpc/kvm/fpu.S
index bf68d59..3dfae0c 100644
--- a/arch/powerpc/kvm/fpu.S
+++ b/arch/powerpc/kvm/fpu.S
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  FPU helper code to use FPU operations from inside the kernel
  *
  *    Copyright (C) 2010 Alexander Graf (agraf@suse.de)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/reg.h>
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index eba5756..3a77bb6 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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
  *
@@ -61,6 +50,11 @@
 	return !!(v->arch.pending_exceptions) || kvm_request_pending(v);
 }
 
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+	return kvm_arch_vcpu_runnable(vcpu);
+}
+
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
 	return false;
@@ -331,10 +325,17 @@
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
 	struct kvmppc_pte pte;
-	int r;
+	int r = -EINVAL;
 
 	vcpu->stat.st++;
 
+	if (vcpu->kvm->arch.kvm_ops && vcpu->kvm->arch.kvm_ops->store_to_eaddr)
+		r = vcpu->kvm->arch.kvm_ops->store_to_eaddr(vcpu, eaddr, ptr,
+							    size);
+
+	if ((!r) || (r == -EAGAIN))
+		return r;
+
 	r = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
 			 XLATE_WRITE, &pte);
 	if (r < 0)
@@ -367,10 +368,17 @@
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
 	struct kvmppc_pte pte;
-	int rc;
+	int rc = -EINVAL;
 
 	vcpu->stat.ld++;
 
+	if (vcpu->kvm->arch.kvm_ops && vcpu->kvm->arch.kvm_ops->load_from_eaddr)
+		rc = vcpu->kvm->arch.kvm_ops->load_from_eaddr(vcpu, eaddr, ptr,
+							      size);
+
+	if ((!rc) || (rc == -EAGAIN))
+		return rc;
+
 	rc = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
 			  XLATE_READ, &pte);
 	if (rc)
@@ -411,9 +419,9 @@
 	return 0;
 }
 
-void kvm_arch_check_processor_compat(void *rtn)
+int kvm_arch_check_processor_compat(void)
 {
-	*(int *)rtn = kvmppc_core_check_processor_compat();
+	return kvmppc_core_check_processor_compat();
 }
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
@@ -449,16 +457,6 @@
 	return -EINVAL;
 }
 
-bool kvm_arch_has_vcpu_debugfs(void)
-{
-	return false;
-}
-
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	unsigned int i;
@@ -518,7 +516,6 @@
 	case KVM_CAP_PPC_UNSET_IRQ:
 	case KVM_CAP_PPC_IRQ_LEVEL:
 	case KVM_CAP_ENABLE_CAP:
-	case KVM_CAP_ENABLE_CAP_VM:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
@@ -543,8 +540,11 @@
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 	case KVM_CAP_SPAPR_TCE_64:
-		/* fallthrough */
+		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:
@@ -554,6 +554,17 @@
 	case KVM_CAP_PPC_GET_CPU_CHAR:
 		r = 1;
 		break;
+#ifdef CONFIG_KVM_XIVE
+	case KVM_CAP_PPC_IRQ_XIVE:
+		/*
+		 * We need XIVE to be enabled on the platform (implies
+		 * a POWER9 processor) and the PowerNV platform, as
+		 * nested is not yet supported.
+		 */
+		r = xive_enabled() && !!cpu_has_feature(CPU_FTR_HVMODE) &&
+			kvmppc_xive_native_supported();
+		break;
+#endif
 
 	case KVM_CAP_PPC_ALLOC_HTAB:
 		r = hv_enabled;
@@ -594,7 +605,12 @@
 		r = !!(hv_enabled && radix_enabled());
 		break;
 	case KVM_CAP_PPC_MMU_HASH_V3:
-		r = !!(hv_enabled && cpu_has_feature(CPU_FTR_ARCH_300));
+		r = !!(hv_enabled && cpu_has_feature(CPU_FTR_ARCH_300) &&
+		       cpu_has_feature(CPU_FTR_HVMODE));
+		break;
+	case KVM_CAP_PPC_NESTED_HV:
+		r = !!(hv_enabled && kvmppc_hv_ops->enable_nested &&
+		       !kvmppc_hv_ops->enable_nested(NULL));
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
@@ -623,12 +639,12 @@
 		else
 			r = num_online_cpus();
 		break;
-	case KVM_CAP_NR_MEMSLOTS:
-		r = KVM_USER_MEM_SLOTS;
-		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+	case KVM_CAP_MAX_VCPU_ID:
+		r = KVM_MAX_VCPU_ID;
+		break;
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_PPC_GET_SMMU_INFO:
 		r = 1;
@@ -691,7 +707,7 @@
 				   const struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
-	kvmppc_core_commit_memory_region(kvm, mem, old, new);
+	kvmppc_core_commit_memory_region(kvm, mem, old, new, change);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
@@ -727,11 +743,14 @@
 		kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu);
 		break;
 	case KVMPPC_IRQ_XICS:
-		if (xive_enabled())
+		if (xics_on_xive())
 			kvmppc_xive_cleanup_vcpu(vcpu);
 		else
 			kvmppc_xics_free_icp(vcpu);
 		break;
+	case KVMPPC_IRQ_XIVE:
+		kvmppc_xive_native_cleanup_vcpu(vcpu);
+		break;
 	}
 
 	kvmppc_core_vcpu_free(vcpu);
@@ -1187,6 +1206,14 @@
 			kvmppc_set_vmx_byte(vcpu, gpr);
 		break;
 #endif
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	case KVM_MMIO_REG_NESTED_GPR:
+		if (kvmppc_need_byteswap(vcpu))
+			gpr = swab64(gpr);
+		kvm_vcpu_write_guest(vcpu, vcpu->arch.nested_io_gpr, &gpr,
+				     sizeof(gpr));
+		break;
+#endif
 	default:
 		BUG();
 	}
@@ -1902,7 +1929,7 @@
 		r = -EPERM;
 		dev = kvm_device_from_filp(f.file);
 		if (dev) {
-			if (xive_enabled())
+			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]);
@@ -1912,6 +1939,30 @@
 		break;
 	}
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+	case KVM_CAP_PPC_IRQ_XIVE: {
+		struct fd f;
+		struct kvm_device *dev;
+
+		r = -EBADF;
+		f = fdget(cap->args[0]);
+		if (!f.file)
+			break;
+
+		r = -ENXIO;
+		if (!xive_enabled())
+			break;
+
+		r = -EPERM;
+		dev = kvm_device_from_filp(f.file);
+		if (dev)
+			r = kvmppc_xive_native_connect_vcpu(dev, vcpu,
+							    cap->args[1]);
+
+		fdput(f);
+		break;
+	}
+#endif /* CONFIG_KVM_XIVE */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_FWNMI:
 		r = -EINVAL;
@@ -2079,8 +2130,8 @@
 }
 
 
-static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
-				   struct kvm_enable_cap *cap)
+int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
+			    struct kvm_enable_cap *cap)
 {
 	int r;
 
@@ -2114,6 +2165,14 @@
 			r = kvm->arch.kvm_ops->set_smt_mode(kvm, mode, flags);
 		break;
 	}
+
+	case KVM_CAP_PPC_NESTED_HV:
+		r = -EINVAL;
+		if (!is_kvmppc_hv_enabled(kvm) ||
+		    !kvm->arch.kvm_ops->enable_nested)
+			break;
+		r = kvm->arch.kvm_ops->enable_nested(kvm);
+		break;
 #endif
 	default:
 		r = -EINVAL;
@@ -2152,10 +2211,12 @@
 			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
 			KVM_PPC_CPU_CHAR_BR_HINT_HONOURED |
 			KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF |
-			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS |
+			KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST;
 		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
 			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
-			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR |
+			KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE;
 	}
 	return 0;
 }
@@ -2214,12 +2275,16 @@
 		if (have_fw_feat(fw_features, "enabled",
 				 "fw-count-cache-disabled"))
 			cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-count-cache-flush-bcctr2,0,0"))
+			cp->character |= KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST;
 		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
 			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
 			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
 			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
 			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
-			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS |
+			KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST;
 
 		if (have_fw_feat(fw_features, "enabled",
 				 "speculation-policy-favor-security"))
@@ -2230,9 +2295,13 @@
 		if (!have_fw_feat(fw_features, "disabled",
 				  "needs-spec-barrier-for-bound-checks"))
 			cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+		if (have_fw_feat(fw_features, "enabled",
+				 "needs-count-cache-flush-on-context-switch"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE;
 		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
 			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
-			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR |
+			KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE;
 
 		of_node_put(fw_features);
 	}
@@ -2260,15 +2329,6 @@
 
 		break;
 	}
-	case KVM_ENABLE_CAP:
-	{
-		struct kvm_enable_cap cap;
-		r = -EFAULT;
-		if (copy_from_user(&cap, argp, sizeof(cap)))
-			goto out;
-		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
-		break;
-	}
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 	case KVM_CREATE_SPAPR_TCE_64: {
 		struct kvm_create_spapr_tce_64 create_tce_64;
diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c
index 1c03c97..bfe4f10 100644
--- a/arch/powerpc/kvm/timing.c
+++ b/arch/powerpc/kvm/timing.c
@@ -1,16 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * 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
  *
diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h
index 3123690..ace65f9 100644
--- a/arch/powerpc/kvm/timing.h
+++ b/arch/powerpc/kvm/timing.h
@@ -1,16 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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
  *
diff --git a/arch/powerpc/kvm/tm.S b/arch/powerpc/kvm/tm.S
index 90e330f..3bf17c8 100644
--- a/arch/powerpc/kvm/tm.S
+++ b/arch/powerpc/kvm/tm.S
@@ -1,17 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * 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.
  *
  * Derived from book3s_hv_rmhandlers.S, which is:
  *
  * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
  */
 
 #include <asm/reg.h>
@@ -28,17 +20,25 @@
  * Save transactional state and TM-related registers.
  * Called with:
  * - r3 pointing to the vcpu struct
- * - r4 points to the MSR with current TS bits:
+ * - r4 containing the MSR with current TS bits:
  * 	(For HV KVM, it is VCPU_MSR ; For PR KVM, it is host MSR).
- * This can modify all checkpointed registers, but
- * restores r1, r2 before exit.
+ * - r5 containing a flag indicating that non-volatile registers
+ *	must be preserved.
+ * If r5 == 0, this can modify all checkpointed registers, but
+ * restores r1, r2 before exit.  If r5 != 0, this restores the
+ * MSR TM/FP/VEC/VSX bits to their state on entry.
  */
 _GLOBAL(__kvmppc_save_tm)
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
+	stdu    r1, -SWITCH_FRAME_SIZE(r1)
+
+	mr	r9, r3
+	cmpdi	cr7, r5, 0
 
 	/* Turn on TM. */
 	mfmsr	r8
+	mr	r10, r8
 	li	r0, 1
 	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
 	ori     r8, r8, MSR_FP
@@ -51,6 +51,27 @@
 	std	r1, HSTATE_SCRATCH2(r13)
 	std	r3, HSTATE_SCRATCH1(r13)
 
+	/* Save CR on the stack - even if r5 == 0 we need to get cr7 back. */
+	mfcr	r6
+	SAVE_GPR(6, r1)
+
+	/* Save DSCR so we can restore it to avoid running with user value */
+	mfspr	r7, SPRN_DSCR
+	SAVE_GPR(7, r1)
+
+	/*
+	 * We are going to do treclaim., which will modify all checkpointed
+	 * registers.  Save the non-volatile registers on the stack if
+	 * preservation of non-volatile state has been requested.
+	 */
+	beq	cr7, 3f
+	SAVE_NVGPRS(r1)
+
+	/* MSR[TS] will be 0 (non-transactional) once we do treclaim. */
+	li	r0, 0
+	rldimi	r10, r0, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+	SAVE_GPR(10, r1)	/* final MSR value */
+3:
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 BEGIN_FTR_SECTION
 	/* Emulation of the treclaim instruction needs TEXASR before treclaim */
@@ -74,22 +95,25 @@
 	std	r9, PACATMSCRATCH(r13)
 	ld	r9, HSTATE_SCRATCH1(r13)
 
-	/* Get a few more GPRs free. */
-	std	r29, VCPU_GPRS_TM(29)(r9)
-	std	r30, VCPU_GPRS_TM(30)(r9)
-	std	r31, VCPU_GPRS_TM(31)(r9)
-
-	/* Save away PPR and DSCR soon so don't run with user values. */
-	mfspr	r31, SPRN_PPR
+	/* Save away PPR soon so we don't run with user value. */
+	std	r0, VCPU_GPRS_TM(0)(r9)
+	mfspr	r0, SPRN_PPR
 	HMT_MEDIUM
-	mfspr	r30, SPRN_DSCR
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-#endif
 
-	/* Save all but r9, r13 & r29-r31 */
-	reg = 0
+	/* Reload stack pointer. */
+	std	r1, VCPU_GPRS_TM(1)(r9)
+	ld	r1, HSTATE_SCRATCH2(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	std	r2, VCPU_GPRS_TM(2)(r9)
+	li	r2, MSR_RI
+	mtmsrd	r2, 1
+
+	/* Reload TOC pointer. */
+	ld	r2, PACATOC(r13)
+
+	/* Save all but r0-r2, r9 & r13 */
+	reg = 3
 	.rept	29
 	.if (reg != 9) && (reg != 13)
 	std	reg, VCPU_GPRS_TM(reg)(r9)
@@ -103,33 +127,29 @@
 	ld	r4, PACATMSCRATCH(r13)
 	std	r4, VCPU_GPRS_TM(9)(r9)
 
-	/* Reload stack pointer and TOC. */
-	ld	r1, HSTATE_SCRATCH2(r13)
-	ld	r2, PACATOC(r13)
-
-	/* Set MSR RI now we have r1 and r13 back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-
-	/* Save away checkpinted SPRs. */
-	std	r31, VCPU_PPR_TM(r9)
-	std	r30, VCPU_DSCR_TM(r9)
-	mflr	r5
+	/* Restore host DSCR and CR values, after saving guest values */
 	mfcr	r6
+	mfspr	r7, SPRN_DSCR
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_DSCR_TM(r9)
+	REST_GPR(6, r1)
+	REST_GPR(7, r1)
+	mtcr	r6
+	mtspr	SPRN_DSCR, r7
+
+	/* Save away checkpointed SPRs. */
+	std	r0, VCPU_PPR_TM(r9)
+	mflr	r5
 	mfctr	r7
 	mfspr	r8, SPRN_AMR
 	mfspr	r10, SPRN_TAR
 	mfxer	r11
 	std	r5, VCPU_LR_TM(r9)
-	stw	r6, VCPU_CR_TM(r9)
 	std	r7, VCPU_CTR_TM(r9)
 	std	r8, VCPU_AMR_TM(r9)
 	std	r10, VCPU_TAR_TM(r9)
 	std	r11, VCPU_XER_TM(r9)
 
-	/* Restore r12 as trap number. */
-	lwz	r12, VCPU_TRAP(r9)
-
 	/* Save FP/VSX. */
 	addi	r3, r9, VCPU_FPRS_TM
 	bl	store_fp_state
@@ -137,6 +157,11 @@
 	bl	store_vr_state
 	mfspr	r6, SPRN_VRSAVE
 	stw	r6, VCPU_VRSAVE_TM(r9)
+
+	/* Restore non-volatile registers if requested to */
+	beq	cr7, 1f
+	REST_NVGPRS(r1)
+	REST_GPR(10, r1)
 1:
 	/*
 	 * We need to save these SPRs after the treclaim so that the software
@@ -146,12 +171,16 @@
 	 */
 	mfspr	r7, SPRN_TEXASR
 	std	r7, VCPU_TEXASR(r9)
-11:
 	mfspr	r5, SPRN_TFHAR
 	mfspr	r6, SPRN_TFIAR
 	std	r5, VCPU_TFHAR(r9)
 	std	r6, VCPU_TFIAR(r9)
 
+	/* Restore MSR state if requested */
+	beq	cr7, 2f
+	mtmsrd	r10, 0
+2:
+	addi	r1, r1, SWITCH_FRAME_SIZE
 	ld	r0, PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr
@@ -161,49 +190,22 @@
  * be invoked from C function by PR KVM only.
  */
 _GLOBAL(_kvmppc_save_tm_pr)
-	mflr	r5
-	std	r5, PPC_LR_STKOFF(r1)
-	stdu    r1, -SWITCH_FRAME_SIZE(r1)
-	SAVE_NVGPRS(r1)
-
-	/* save MSR since TM/math bits might be impacted
-	 * by __kvmppc_save_tm().
-	 */
-	mfmsr	r5
-	SAVE_GPR(5, r1)
-
-	/* also save DSCR/CR/TAR so that it can be recovered later */
-	mfspr   r6, SPRN_DSCR
-	SAVE_GPR(6, r1)
-
-	mfcr    r7
-	stw     r7, _CCR(r1)
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu    r1, -PPC_MIN_STKFRM(r1)
 
 	mfspr   r8, SPRN_TAR
-	SAVE_GPR(8, r1)
+	std	r8, PPC_MIN_STKFRM-8(r1)
 
+	li	r5, 1		/* preserve non-volatile registers */
 	bl	__kvmppc_save_tm
 
-	REST_GPR(8, r1)
+	ld	r8, PPC_MIN_STKFRM-8(r1)
 	mtspr   SPRN_TAR, r8
 
-	ld      r7, _CCR(r1)
-	mtcr	r7
-
-	REST_GPR(6, r1)
-	mtspr   SPRN_DSCR, r6
-
-	/* need preserve current MSR's MSR_TS bits */
-	REST_GPR(5, r1)
-	mfmsr   r6
-	rldicl  r6, r6, 64 - MSR_TS_S_LG, 62
-	rldimi  r5, r6, MSR_TS_S_LG, 63 - MSR_TS_T_LG
-	mtmsrd  r5
-
-	REST_NVGPRS(r1)
-	addi    r1, r1, SWITCH_FRAME_SIZE
-	ld	r5, PPC_LR_STKOFF(r1)
-	mtlr	r5
+	addi    r1, r1, PPC_MIN_STKFRM
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
 	blr
 
 EXPORT_SYMBOL_GPL(_kvmppc_save_tm_pr);
@@ -215,15 +217,21 @@
  *  - r4 is the guest MSR with desired TS bits:
  * 	For HV KVM, it is VCPU_MSR
  * 	For PR KVM, it is provided by caller
- * This potentially modifies all checkpointed registers.
- * It restores r1, r2 from the PACA.
+ * - r5 containing a flag indicating that non-volatile registers
+ *	must be preserved.
+ * If r5 == 0, this potentially modifies all checkpointed registers, but
+ * restores r1, r2 from the PACA before exit.
+ * If r5 != 0, this restores the MSR TM/FP/VEC/VSX bits to their state on entry.
  */
 _GLOBAL(__kvmppc_restore_tm)
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
 
+	cmpdi	cr7, r5, 0
+
 	/* Turn on TM/FP/VSX/VMX so we can restore them. */
 	mfmsr	r5
+	mr	r10, r5
 	li	r6, MSR_TM >> 32
 	sldi	r6, r6, 32
 	or	r5, r5, r6
@@ -244,8 +252,7 @@
 
 	mr	r5, r4
 	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beqlr		/* TM not active in guest */
-	std	r1, HSTATE_SCRATCH2(r13)
+	beq	9f		/* TM not active in guest */
 
 	/* Make sure the failure summary is set, otherwise we'll program check
 	 * when we trechkpt.  It's possible that this might have been not set
@@ -256,6 +263,26 @@
 	mtspr	SPRN_TEXASR, r7
 
 	/*
+	 * Make a stack frame and save non-volatile registers if requested.
+	 */
+	stdu	r1, -SWITCH_FRAME_SIZE(r1)
+	std	r1, HSTATE_SCRATCH2(r13)
+
+	mfcr	r6
+	mfspr	r7, SPRN_DSCR
+	SAVE_GPR(2, r1)
+	SAVE_GPR(6, r1)
+	SAVE_GPR(7, r1)
+
+	beq	cr7, 4f
+	SAVE_NVGPRS(r1)
+
+	/* MSR[TS] will be 1 (suspended) once we do trechkpt */
+	li	r0, 1
+	rldimi	r10, r0, MSR_TS_S_LG, 63 - MSR_TS_T_LG
+	SAVE_GPR(10, r1)	/* final MSR value */
+4:
+	/*
 	 * We need to load up the checkpointed state for the guest.
 	 * We need to do this early as it will blow away any GPRs, VSRs and
 	 * some SPRs.
@@ -291,8 +318,6 @@
 	ld	r29, VCPU_DSCR_TM(r3)
 	ld	r30, VCPU_PPR_TM(r3)
 
-	std	r2, PACATMSCRATCH(r13) /* Save TOC */
-
 	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
 	li	r5, 0
 	mtmsrd	r5, 1
@@ -318,18 +343,31 @@
 	/* Now let's get back the state we need. */
 	HMT_MEDIUM
 	GET_PACA(r13)
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-#endif
 	ld	r1, HSTATE_SCRATCH2(r13)
-	ld	r2, PACATMSCRATCH(r13)
+	REST_GPR(7, r1)
+	mtspr	SPRN_DSCR, r7
 
 	/* Set the MSR RI since we have our registers back. */
 	li	r5, MSR_RI
 	mtmsrd	r5, 1
+
+	/* Restore TOC pointer and CR */
+	REST_GPR(2, r1)
+	REST_GPR(6, r1)
+	mtcr	r6
+
+	/* Restore non-volatile registers if requested to. */
+	beq	cr7, 5f
+	REST_GPR(10, r1)
+	REST_NVGPRS(r1)
+
+5:	addi	r1, r1, SWITCH_FRAME_SIZE
 	ld	r0, PPC_LR_STKOFF(r1)
 	mtlr	r0
+
+9:	/* Restore MSR bits if requested */
+	beqlr	cr7
+	mtmsrd	r10, 0
 	blr
 
 /*
@@ -337,47 +375,23 @@
  * can be invoked from C function by PR KVM only.
  */
 _GLOBAL(_kvmppc_restore_tm_pr)
-	mflr	r5
-	std	r5, PPC_LR_STKOFF(r1)
-	stdu    r1, -SWITCH_FRAME_SIZE(r1)
-	SAVE_NVGPRS(r1)
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu    r1, -PPC_MIN_STKFRM(r1)
 
-	/* save MSR to avoid TM/math bits change */
-	mfmsr	r5
-	SAVE_GPR(5, r1)
-
-	/* also save DSCR/CR/TAR so that it can be recovered later */
-	mfspr   r6, SPRN_DSCR
-	SAVE_GPR(6, r1)
-
-	mfcr    r7
-	stw     r7, _CCR(r1)
-
+	/* save TAR so that it can be recovered later */
 	mfspr   r8, SPRN_TAR
-	SAVE_GPR(8, r1)
+	std	r8, PPC_MIN_STKFRM-8(r1)
 
+	li	r5, 1
 	bl	__kvmppc_restore_tm
 
-	REST_GPR(8, r1)
+	ld	r8, PPC_MIN_STKFRM-8(r1)
 	mtspr   SPRN_TAR, r8
 
-	ld      r7, _CCR(r1)
-	mtcr	r7
-
-	REST_GPR(6, r1)
-	mtspr   SPRN_DSCR, r6
-
-	/* need preserve current MSR's MSR_TS bits */
-	REST_GPR(5, r1)
-	mfmsr   r6
-	rldicl  r6, r6, 64 - MSR_TS_S_LG, 62
-	rldimi  r5, r6, MSR_TS_S_LG, 63 - MSR_TS_T_LG
-	mtmsrd  r5
-
-	REST_NVGPRS(r1)
-	addi    r1, r1, SWITCH_FRAME_SIZE
-	ld	r5, PPC_LR_STKOFF(r1)
-	mtlr	r5
+	addi    r1, r1, PPC_MIN_STKFRM
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
 	blr
 
 EXPORT_SYMBOL_GPL(_kvmppc_restore_tm_pr);
diff --git a/arch/powerpc/kvm/trace_book3s.h b/arch/powerpc/kvm/trace_book3s.h
index f3b2375..372a82f 100644
--- a/arch/powerpc/kvm/trace_book3s.h
+++ b/arch/powerpc/kvm/trace_book3s.h
@@ -14,7 +14,6 @@
 	{0x400, "INST_STORAGE"}, \
 	{0x480, "INST_SEGMENT"}, \
 	{0x500, "EXTERNAL"}, \
-	{0x501, "EXTERNAL_LEVEL"}, \
 	{0x502, "EXTERNAL_HV"}, \
 	{0x600, "ALIGNMENT"}, \
 	{0x700, "PROGRAM"}, \
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 6702868..b8de3be 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -3,16 +3,29 @@
 # Makefile for ppc-specific library files..
 #
 
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
-
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
 CFLAGS_REMOVE_code-patching.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE)
 
-obj-y += string.o alloc.o code-patching.o feature-fixups.o
+KASAN_SANITIZE_code-patching.o := n
+KASAN_SANITIZE_feature-fixups.o := n
 
-obj-$(CONFIG_PPC32)	+= div64.o copy_32.o crtsavres.o strlen_32.o
+ifdef CONFIG_KASAN
+CFLAGS_code-patching.o += -DDISABLE_BRANCH_PROFILING
+CFLAGS_feature-fixups.o += -DDISABLE_BRANCH_PROFILING
+endif
+
+obj-y += alloc.o code-patching.o feature-fixups.o pmem.o
+
+ifndef CONFIG_KASAN
+obj-y	+=	string.o memcmp_$(BITS).o
+obj-$(CONFIG_PPC32)	+= strlen_32.o
+endif
+
+obj-$(CONFIG_PPC32)	+= div64.o copy_32.o crtsavres.o
+
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
 
 # See corresponding test in arch/powerpc/Makefile
 # 64-bit linker creates .sfpr on demand for final link (vmlinux),
@@ -26,16 +39,18 @@
 			       memcpy_power7.o
 
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
-	   memcpy_64.o pmem.o
+	   memcpy_64.o memcpy_mcsafe_64.o
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
-obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
+obj64-$(CONFIG_KPROBES_SANITY_TEST)	+= test_emulate_step.o \
+					   test_emulate_step_exec_instr.o
 
 obj-y			+= checksum_$(BITS).o checksum_wrappers.o \
-			   string_$(BITS).o memcmp_$(BITS).o
+			   string_$(BITS).o
 
-obj-y			+= sstep.o ldstfp.o quad.o
+obj-y			+= sstep.o
+obj-$(CONFIG_PPC_FPU)	+= ldstfp.o
 obj64-y			+= quad.o
 
 obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
index 06796de..ce18087 100644
--- a/arch/powerpc/lib/alloc.c
+++ b/arch/powerpc/lib/alloc.c
@@ -2,7 +2,7 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/string.h>
 #include <asm/setup.h>
 
@@ -14,7 +14,10 @@
 	if (slab_is_available())
 		p = kzalloc(size, mask);
 	else {
-		p = memblock_virt_alloc(size, 0);
+		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 aa22406..ecd150d 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains assembly-language implementations
  * of IP-style 1's complement checksum routines.
  *	
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au).
  */
 
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index d05c8af..514978f 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains assembly-language implementations
  * of IP-style 1's complement checksum routines.
  *	
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  * Severely hacked about by Paul Mackerras (paulus@cs.anu.edu.au).
  */
 
diff --git a/arch/powerpc/lib/checksum_wrappers.c b/arch/powerpc/lib/checksum_wrappers.c
index a0cb63f..fabe4db 100644
--- a/arch/powerpc/lib/checksum_wrappers.c
+++ b/arch/powerpc/lib/checksum_wrappers.c
@@ -1,17 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2010
  *
@@ -29,6 +17,7 @@
 	unsigned int csum;
 
 	might_sleep();
+	allow_read_from_user(src, len);
 
 	*err_ptr = 0;
 
@@ -37,7 +26,7 @@
 		goto out;
 	}
 
-	if (unlikely((len < 0) || !access_ok(VERIFY_READ, src, len))) {
+	if (unlikely((len < 0) || !access_ok(src, len))) {
 		*err_ptr = -EFAULT;
 		csum = (__force unsigned int)sum;
 		goto out;
@@ -60,6 +49,7 @@
 	}
 
 out:
+	prevent_read_from_user(src, len);
 	return (__force __wsum)csum;
 }
 EXPORT_SYMBOL(csum_and_copy_from_user);
@@ -70,6 +60,7 @@
 	unsigned int csum;
 
 	might_sleep();
+	allow_write_to_user(dst, len);
 
 	*err_ptr = 0;
 
@@ -78,7 +69,7 @@
 		goto out;
 	}
 
-	if (unlikely((len < 0) || !access_ok(VERIFY_WRITE, dst, len))) {
+	if (unlikely((len < 0) || !access_ok(dst, len))) {
 		*err_ptr = -EFAULT;
 		csum = -1; /* invalid checksum */
 		goto out;
@@ -97,6 +88,7 @@
 	}
 
 out:
+	prevent_write_to_user(dst, len);
 	return (__force __wsum)csum;
 }
 EXPORT_SYMBOL(csum_and_copy_to_user);
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 5ffee29..3345f03 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright 2008 Michael Ellerman, IBM 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; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -15,7 +11,6 @@
 #include <linux/cpuhotplug.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
-#include <linux/kprobes.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -26,9 +21,9 @@
 static int __patch_instruction(unsigned int *exec_addr, unsigned int instr,
 			       unsigned int *patch_addr)
 {
-	int err;
+	int err = 0;
 
-	__put_user_size(instr, patch_addr, 4, err);
+	__put_user_asm(instr, patch_addr, err, "stw");
 	if (err)
 		return err;
 
@@ -98,8 +93,7 @@
 	else
 		pfn = __pa_symbol(addr) >> PAGE_SHIFT;
 
-	err = map_kernel_page(text_poke_addr, (pfn << PAGE_SHIFT),
-				pgprot_val(PAGE_KERNEL));
+	err = map_kernel_page(text_poke_addr, (pfn << PAGE_SHIFT), PAGE_KERNEL);
 
 	pr_devel("Mapped addr %lx with pfn %lx:%d\n", text_poke_addr, pfn, err);
 	if (err)
@@ -205,22 +199,6 @@
 	return patch_instruction(addr, create_branch(addr, target, flags));
 }
 
-int patch_branch_site(s32 *site, unsigned long target, int flags)
-{
-	unsigned int *addr;
-
-	addr = (unsigned int *)((unsigned long)site + *site);
-	return patch_instruction(addr, create_branch(addr, target, flags));
-}
-
-int patch_instruction_site(s32 *site, unsigned int instr)
-{
-	unsigned int *addr;
-
-	addr = (unsigned int *)((unsigned long)site + *site);
-	return patch_instruction(addr, instr);
-}
-
 bool is_offset_in_branch_range(long offset)
 {
 	/*
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index ba66846..a3bcf47 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Memory copy functions for 32-bit PowerPC.
  *
  * Copyright (C) 1996-2005 Paul Mackerras.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/processor.h>
 #include <asm/cache.h>
@@ -14,6 +10,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/export.h>
 #include <asm/code-patching-asm.h>
+#include <asm/kasan.h>
 
 #define COPY_16_BYTES		\
 	lwz	r7,4(r4);	\
@@ -68,6 +65,7 @@
 LG_CACHELINE_BYTES = L1_CACHE_SHIFT
 CACHELINE_MASK = (L1_CACHE_BYTES-1)
 
+#ifndef CONFIG_KASAN
 _GLOBAL(memset16)
 	rlwinm.	r0 ,r5, 31, 1, 31
 	addi	r6, r3, -4
@@ -81,6 +79,7 @@
 	sth	r4, 4(r6)
 	blr
 EXPORT_SYMBOL(memset16)
+#endif
 
 /*
  * Use dcbz on the complete cache lines in the destination
@@ -91,7 +90,7 @@
  * We therefore skip the optimised bloc that uses dcbz. This jump is
  * replaced by a nop once cache is active. This is done in machine_init()
  */
-_GLOBAL(memset)
+_GLOBAL_KASAN(memset)
 	cmplwi	0,r5,4
 	blt	7f
 
@@ -151,6 +150,7 @@
 	bdnz	9b
 	blr
 EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL_KASAN(memset)
 
 /*
  * This version uses dcbz on the complete cache lines in the
@@ -163,12 +163,12 @@
  * We therefore jump to generic_memcpy which doesn't use dcbz. This jump is
  * replaced by a nop once cache is active. This is done in machine_init()
  */
-_GLOBAL(memmove)
+_GLOBAL_KASAN(memmove)
 	cmplw	0,r3,r4
 	bgt	backwards_memcpy
 	/* fall through */
 
-_GLOBAL(memcpy)
+_GLOBAL_KASAN(memcpy)
 1:	b	generic_memcpy
 	patch_site	1b, patch__memcpy_nocache
 
@@ -244,6 +244,8 @@
 65:	blr
 EXPORT_SYMBOL(memcpy)
 EXPORT_SYMBOL(memmove)
+EXPORT_SYMBOL_KASAN(memcpy)
+EXPORT_SYMBOL_KASAN(memmove)
 
 generic_memcpy:
 	srwi.	r7,r5,3
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
index 6943903..d1091b5 100644
--- a/arch/powerpc/lib/copypage_64.S
+++ b/arch/powerpc/lib/copypage_64.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2008 Mark Nelson, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/page.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
index e38f956..a9844c6 100644
--- a/arch/powerpc/lib/copypage_power7.S
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 96c514b..db8719a 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index 1a1fe18..28f0be5 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2011
  *
diff --git a/arch/powerpc/lib/div64.S b/arch/powerpc/lib/div64.S
index 83d9832..3d5426e 100644
--- a/arch/powerpc/lib/div64.S
+++ b/arch/powerpc/lib/div64.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Divide a 64-bit unsigned number by a 32-bit unsigned number.
  * This routine assumes that the top 32 bits of the dividend are
@@ -7,11 +8,6 @@
  * On exit, r3 contains the remainder.
  *
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc_asm.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/lib/error-inject.c b/arch/powerpc/lib/error-inject.c
new file mode 100644
index 0000000..407b992
--- /dev/null
+++ b/arch/powerpc/lib/error-inject.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	/*
+	 * Emulate 'blr'. 'regs' represents the state on entry of a predefined
+	 * function in the kernel/module, captured on a kprobe. We don't need
+	 * to worry about 32-bit userspace on a 64-bit kernel.
+	 */
+	regs->nip = regs->link;
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/powerpc/lib/feature-fixups-test.S b/arch/powerpc/lib/feature-fixups-test.S
index ee7c5fd..b12168c 100644
--- a/arch/powerpc/lib/feature-fixups-test.S
+++ b/arch/powerpc/lib/feature-fixups-test.S
@@ -1,11 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2008 Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/feature-fixups.h>
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index e613b02..4ba634b 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
  *
@@ -5,11 +6,6 @@
  *      Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
  *
  *  Copyright 2008 Michael Ellerman, IBM 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; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/types.h>
@@ -118,7 +114,7 @@
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
-void do_stf_entry_barrier_fixups(enum stf_barrier_type types)
+static void do_stf_entry_barrier_fixups(enum stf_barrier_type types)
 {
 	unsigned int instrs[3], *dest;
 	long *start, *end;
@@ -168,7 +164,7 @@
 		                                           : "unknown");
 }
 
-void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
+static void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
 {
 	unsigned int instrs[6], *dest;
 	long *start, *end;
@@ -347,6 +343,29 @@
 
 	printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i);
 }
+
+static void patch_btb_flush_section(long *curr)
+{
+	unsigned int *start, *end;
+
+	start = (void *)curr + *curr;
+	end = (void *)curr + *(curr + 1);
+	for (; start < end; start++) {
+		pr_devel("patching dest %lx\n", (unsigned long)start);
+		patch_instruction(start, PPC_INST_NOP);
+	}
+}
+
+void do_btb_flush_fixups(void)
+{
+	long *start, *end;
+
+	start = PTRRELOC(&__start__btb_flush_fixup);
+	end = PTRRELOC(&__stop__btb_flush_fixup);
+
+	for (; start < end; start += 2)
+		patch_btb_flush_section(start);
+}
 #endif /* CONFIG_PPC_FSL_BOOK3E */
 
 void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S
index 0526b22..6effad9 100644
--- a/arch/powerpc/lib/hweight_64.S
+++ b/arch/powerpc/lib/hweight_64.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2010
  *
diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S
index 32e9199..e00abea 100644
--- a/arch/powerpc/lib/ldstfp.S
+++ b/arch/powerpc/lib/ldstfp.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Floating-point, VMX/Altivec and VSX loads and stores
  * for use in instruction emulation.
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <asm/processor.h>
@@ -18,8 +14,6 @@
 #include <asm/asm-compat.h>
 #include <linux/errno.h>
 
-#ifdef CONFIG_PPC_FPU
-
 #define STKFRM	(PPC_MIN_STKFRM + 16)
 
 /* Get the contents of frN into *p; N is in r3 and p is in r4. */
@@ -241,5 +235,3 @@
 	MTMSRD(r6)
 	isync
 	blr
-
-#endif	/* CONFIG_PPC_FPU */
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index 35a0ef9..6440d59 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Spin and read/write lock operations.
  *
@@ -5,11 +6,6 @@
  * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
  * Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM
  *   Rework to support virtual processors
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -22,7 +18,7 @@
 #include <asm/hvcall.h>
 #include <asm/smp.h>
 
-void __spin_yield(arch_spinlock_t *lock)
+void splpar_spin_yield(arch_spinlock_t *lock)
 {
 	unsigned int lock_value, holder_cpu, yield_count;
 
@@ -40,14 +36,14 @@
 	plpar_hcall_norets(H_CONFER,
 		get_hard_smp_processor_id(holder_cpu), yield_count);
 }
-EXPORT_SYMBOL_GPL(__spin_yield);
+EXPORT_SYMBOL_GPL(splpar_spin_yield);
 
 /*
  * Waiting for a read lock or a write lock on a rwlock...
  * This turns out to be the same for read and write locks, since
  * we only know the holder if it is write-locked.
  */
-void __rw_yield(arch_rwlock_t *rw)
+void splpar_rw_yield(arch_rwlock_t *rw)
 {
 	int lock_value;
 	unsigned int holder_cpu, yield_count;
diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S
index ec531de..9351ffa 100644
--- a/arch/powerpc/lib/mem_64.S
+++ b/arch/powerpc/lib/mem_64.S
@@ -1,18 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * String handling functions for PowerPC.
  *
  * Copyright (C) 1996 Paul Mackerras.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/processor.h>
 #include <asm/errno.h>
 #include <asm/ppc_asm.h>
 #include <asm/export.h>
+#include <asm/kasan.h>
 
+#ifndef CONFIG_KASAN
 _GLOBAL(__memset16)
 	rlwimi	r4,r4,16,0,15
 	/* fall through */
@@ -29,8 +27,9 @@
 EXPORT_SYMBOL(__memset16)
 EXPORT_SYMBOL(__memset32)
 EXPORT_SYMBOL(__memset64)
+#endif
 
-_GLOBAL(memset)
+_GLOBAL_KASAN(memset)
 	neg	r0,r3
 	rlwimi	r4,r4,8,16,23
 	andi.	r0,r0,7			/* # bytes to be 8-byte aligned */
@@ -40,7 +39,7 @@
 .Lms:	PPC_MTOCRF(1,r0)
 	mr	r6,r3
 	blt	cr1,8f
-	beq+	3f			/* if already 8-byte aligned */
+	beq	3f			/* if already 8-byte aligned */
 	subf	r5,r0,r5
 	bf	31,1f
 	stb	r4,0(r6)
@@ -85,7 +84,7 @@
 	addi	r6,r6,8
 8:	cmpwi	r5,0
 	PPC_MTOCRF(1,r5)
-	beqlr+
+	beqlr
 	bf	29,9f
 	stw	r4,0(r6)
 	addi	r6,r6,4
@@ -96,8 +95,9 @@
 	stb	r4,0(r6)
 	blr
 EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL_KASAN(memset)
 
-_GLOBAL_TOC(memmove)
+_GLOBAL_TOC_KASAN(memmove)
 	cmplw	0,r3,r4
 	bgt	backwards_memcpy
 	b	memcpy
@@ -139,3 +139,4 @@
 	mtctr	r7
 	b	1b
 EXPORT_SYMBOL(memmove)
+EXPORT_SYMBOL_KASAN(memmove)
diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S
index 844d8e7..384218d 100644
--- a/arch/powerpc/lib/memcmp_64.S
+++ b/arch/powerpc/lib/memcmp_64.S
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Author: Anton Blanchard <anton@au.ibm.com>
  * Copyright 2015 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc_asm.h>
 #include <asm/export.h>
@@ -215,11 +211,20 @@
 	beq	.Lzero
 
 .Lcmp_rest_lt8bytes:
-	/* Here we have only less than 8 bytes to compare with. at least s1
-	 * Address is aligned with 8 bytes.
-	 * The next double words are load and shift right with appropriate
-	 * bits.
+	/*
+	 * Here we have less than 8 bytes to compare. At least s1 is aligned to
+	 * 8 bytes, but s2 may not be. We must make sure s2 + 7 doesn't cross a
+	 * page boundary, otherwise we might read past the end of the buffer and
+	 * trigger a page fault. We use 4K as the conservative minimum page
+	 * size. If we detect that case we go to the byte-by-byte loop.
+	 *
+	 * Otherwise the next double word is loaded from s1 and s2, and shifted
+	 * right to compare the appropriate bits.
 	 */
+	clrldi	r6,r4,(64-12)	// r6 = r4 & 0xfff
+	cmpdi	r6,0xff8
+	bgt	.Lshort
+
 	subfic  r6,r5,8
 	slwi	r6,r6,3
 	LD	rA,0,r3
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 273ea67..016c91e 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -1,16 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2002 Paul Mackerras, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #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>
 
 #ifndef SELFTEST_CASE
 /* For big-endian, 0 == most CPUs, 1 == POWER6, 2 == Cell */
@@ -18,7 +15,7 @@
 #endif
 
 	.align	7
-_GLOBAL_TOC(memcpy)
+_GLOBAL_TOC_KASAN(memcpy)
 BEGIN_FTR_SECTION
 #ifdef __LITTLE_ENDIAN__
 	cmpdi	cr7,r5,0
@@ -230,3 +227,4 @@
 	blr
 #endif
 EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL_KASAN(memcpy)
diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S
new file mode 100644
index 0000000..cb882d9
--- /dev/null
+++ b/arch/powerpc/lib/memcpy_mcsafe_64.S
@@ -0,0 +1,242 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) IBM Corporation, 2011
+ * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
+ * Author - Balbir Singh <bsingharora@gmail.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/errno.h>
+#include <asm/export.h>
+
+	.macro err1
+100:
+	EX_TABLE(100b,.Ldo_err1)
+	.endm
+
+	.macro err2
+200:
+	EX_TABLE(200b,.Ldo_err2)
+	.endm
+
+	.macro err3
+300:	EX_TABLE(300b,.Ldone)
+	.endm
+
+.Ldo_err2:
+	ld	r22,STK_REG(R22)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Ldo_err1:
+	/* Do a byte by byte copy to get the exact remaining size */
+	mtctr	r7
+46:
+err3;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err3;	stb	r0,0(r3)
+	addi	r3,r3,1
+	bdnz	46b
+	li	r3,0
+	blr
+
+.Ldone:
+	mfctr	r3
+	blr
+
+
+_GLOBAL(memcpy_mcsafe)
+	mr	r7,r5
+	cmpldi	r5,16
+	blt	.Lshort_copy
+
+.Lcopy:
+	/* Get the source 8B aligned */
+	neg	r6,r4
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	bf	cr7*4+3,1f
+err1;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err1;	stb	r0,0(r3)
+	addi	r3,r3,1
+	subi	r7,r7,1
+
+1:	bf	cr7*4+2,2f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+2:	bf	cr7*4+1,3f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+3:	sub	r5,r5,r6
+	cmpldi	r5,128
+
+	mflr	r0
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
+	std	r0,STACKFRAMESIZE+16(r1)
+
+	blt	5f
+	srdi	r6,r5,7
+	mtctr	r6
+
+	/* Now do cacheline (128B) sized loads and stores. */
+	.align	5
+4:
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+err2;	ld	r15,64(r4)
+err2;	ld	r16,72(r4)
+err2;	ld	r17,80(r4)
+err2;	ld	r18,88(r4)
+err2;	ld	r19,96(r4)
+err2;	ld	r20,104(r4)
+err2;	ld	r21,112(r4)
+err2;	ld	r22,120(r4)
+	addi	r4,r4,128
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+err2;	std	r15,64(r3)
+err2;	std	r16,72(r3)
+err2;	std	r17,80(r3)
+err2;	std	r18,88(r3)
+err2;	std	r19,96(r3)
+err2;	std	r20,104(r3)
+err2;	std	r21,112(r3)
+err2;	std	r22,120(r3)
+	addi	r3,r3,128
+	subi	r7,r7,128
+	bdnz	4b
+
+	clrldi	r5,r5,(64-7)
+
+	/* Up to 127B to go */
+5:	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+6:	bf	cr7*4+1,7f
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+	addi	r4,r4,64
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+	addi	r3,r3,64
+	subi	r7,r7,64
+
+7:	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	/* Up to 63B to go */
+	bf	cr7*4+2,8f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+err1;	ld	r8,16(r4)
+err1;	ld	r9,24(r4)
+	addi	r4,r4,32
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+err1;	std	r8,16(r3)
+err1;	std	r9,24(r3)
+	addi	r3,r3,32
+	subi	r7,r7,32
+
+	/* Up to 31B to go */
+8:	bf	cr7*4+3,9f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+	addi	r4,r4,16
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+	addi	r3,r3,16
+	subi	r7,r7,16
+
+9:	clrldi	r5,r5,(64-4)
+
+	/* Up to 15B to go */
+.Lshort_copy:
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+err1;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+err1;	lwz	r6,4(r4)
+	addi	r4,r4,8
+err1;	stw	r0,0(r3)
+err1;	stw	r6,4(r3)
+	addi	r3,r3,8
+	subi	r7,r7,8
+
+12:	bf	cr7*4+1,13f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+13:	bf	cr7*4+2,14f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+14:	bf	cr7*4+3,15f
+err1;	lbz	r0,0(r4)
+err1;	stb	r0,0(r3)
+
+15:	li	r3,0
+	blr
+
+EXPORT_SYMBOL_GPL(memcpy_mcsafe);
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index 89bfefc..54f2263 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c
index 53c0187..377712e 100644
--- a/arch/powerpc/lib/pmem.c
+++ b/arch/powerpc/lib/pmem.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright(c) 2017 IBM Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License 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.
  */
 
 #include <linux/string.h>
@@ -23,14 +15,14 @@
 void arch_wb_cache_pmem(void *addr, size_t size)
 {
 	unsigned long start = (unsigned long) addr;
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 }
 EXPORT_SYMBOL(arch_wb_cache_pmem);
 
 void arch_invalidate_pmem(void *addr, size_t size)
 {
 	unsigned long start = (unsigned long) addr;
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 }
 EXPORT_SYMBOL(arch_invalidate_pmem);
 
@@ -43,7 +35,7 @@
 	unsigned long copied, start = (unsigned long) dest;
 
 	copied = __copy_from_user(dest, src, size);
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 
 	return copied;
 }
@@ -53,7 +45,7 @@
 	unsigned long start = (unsigned long) dest;
 
 	memcpy(dest, src, size);
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 
 	return dest;
 }
diff --git a/arch/powerpc/lib/quad.S b/arch/powerpc/lib/quad.S
index c4d12fa..da71760 100644
--- a/arch/powerpc/lib/quad.S
+++ b/arch/powerpc/lib/quad.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Quadword loads and stores
  * for use in instruction emulation.
  *
  * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <asm/processor.h>
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index d81568f..c077acb 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Single-step support.
  *
  * Copyright (C) 2004 Paul Mackerras <paulus@au.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
@@ -1169,7 +1165,7 @@
 int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 		  unsigned int instr)
 {
-	unsigned int opcode, ra, rb, rd, spr, u;
+	unsigned int opcode, ra, rb, rc, rd, spr, u;
 	unsigned long int imm;
 	unsigned long int val, val2;
 	unsigned int mb, me, sh;
@@ -1292,6 +1288,7 @@
 	rd = (instr >> 21) & 0x1f;
 	ra = (instr >> 16) & 0x1f;
 	rb = (instr >> 11) & 0x1f;
+	rc = (instr >> 6) & 0x1f;
 
 	switch (opcode) {
 #ifdef __powerpc64__
@@ -1305,6 +1302,38 @@
 			goto trap;
 		return 1;
 
+#ifdef __powerpc64__
+	case 4:
+		if (!cpu_has_feature(CPU_FTR_ARCH_300))
+			return -1;
+
+		switch (instr & 0x3f) {
+		case 48:	/* maddhd */
+			asm volatile(PPC_MADDHD(%0, %1, %2, %3) :
+				     "=r" (op->val) : "r" (regs->gpr[ra]),
+				     "r" (regs->gpr[rb]), "r" (regs->gpr[rc]));
+			goto compute_done;
+
+		case 49:	/* maddhdu */
+			asm volatile(PPC_MADDHDU(%0, %1, %2, %3) :
+				     "=r" (op->val) : "r" (regs->gpr[ra]),
+				     "r" (regs->gpr[rb]), "r" (regs->gpr[rc]));
+			goto compute_done;
+
+		case 51:	/* maddld */
+			asm volatile(PPC_MADDLD(%0, %1, %2, %3) :
+				     "=r" (op->val) : "r" (regs->gpr[ra]),
+				     "r" (regs->gpr[rb]), "r" (regs->gpr[rc]));
+			goto compute_done;
+		}
+
+		/*
+		 * There are other instructions from ISA 3.0 with the same
+		 * primary opcode which do not have emulation support yet.
+		 */
+		return -1;
+#endif
+
 	case 7:		/* mulli */
 		op->val = regs->gpr[ra] * (short) instr;
 		goto compute_done;
@@ -1671,10 +1700,23 @@
 				(int) regs->gpr[rb];
 
 			goto arith_done;
-
+#ifdef __powerpc64__
+		case 265:	/* modud */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->val = regs->gpr[ra] % regs->gpr[rb];
+			goto compute_done;
+#endif
 		case 266:	/* add */
 			op->val = regs->gpr[ra] + regs->gpr[rb];
 			goto arith_done;
+
+		case 267:	/* moduw */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->val = (unsigned int) regs->gpr[ra] %
+				(unsigned int) regs->gpr[rb];
+			goto compute_done;
 #ifdef __powerpc64__
 		case 457:	/* divdu */
 			op->val = regs->gpr[ra] / regs->gpr[rb];
@@ -1695,6 +1737,42 @@
 				(int) regs->gpr[rb];
 			goto arith_done;
 
+		case 755:	/* darn */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			switch (ra & 0x3) {
+			case 0:
+				/* 32-bit conditioned */
+				asm volatile(PPC_DARN(%0, 0) : "=r" (op->val));
+				goto compute_done;
+
+			case 1:
+				/* 64-bit conditioned */
+				asm volatile(PPC_DARN(%0, 1) : "=r" (op->val));
+				goto compute_done;
+
+			case 2:
+				/* 64-bit raw */
+				asm volatile(PPC_DARN(%0, 2) : "=r" (op->val));
+				goto compute_done;
+			}
+
+			return -1;
+#ifdef __powerpc64__
+		case 777:	/* modsd */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->val = (long int) regs->gpr[ra] %
+				(long int) regs->gpr[rb];
+			goto compute_done;
+#endif
+		case 779:	/* modsw */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->val = (int) regs->gpr[ra] %
+				(int) regs->gpr[rb];
+			goto compute_done;
+
 
 /*
  * Logical instructions
@@ -1765,6 +1843,20 @@
 			do_popcnt(regs, op, regs->gpr[rd], 64);
 			goto logical_done_nocc;
 #endif
+		case 538:	/* cnttzw */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			val = (unsigned int) regs->gpr[rd];
+			op->val = (val ? __builtin_ctz(val) : 32);
+			goto logical_done;
+#ifdef __powerpc64__
+		case 570:	/* cnttzd */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			val = regs->gpr[rd];
+			op->val = (val ? __builtin_ctzl(val) : 64);
+			goto logical_done;
+#endif
 		case 922:	/* extsh */
 			op->val = (signed short) regs->gpr[rd];
 			goto logical_done;
@@ -1866,6 +1958,20 @@
 				op->xerval &= ~XER_CA;
 			set_ca32(op, op->xerval & XER_CA);
 			goto logical_done;
+
+		case 890:	/* extswsli with sh_5 = 0 */
+		case 891:	/* extswsli with sh_5 = 1 */
+			if (!cpu_has_feature(CPU_FTR_ARCH_300))
+				return -1;
+			op->type = COMPUTE + SETREG;
+			sh = rb | ((instr & 2) << 4);
+			val = (signed int) regs->gpr[rd];
+			if (sh)
+				op->val = ROTATE(val, sh) & MASK64(0, 63 - sh);
+			else
+				op->val = val;
+			goto logical_done;
+
 #endif /* __powerpc64__ */
 
 /*
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index 4b41970..2752b1c 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * String handling functions for PowerPC.
  *
  * Copyright (C) 1996 Paul Mackerras.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc_asm.h>
 #include <asm/export.h>
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
index 56aac4c..507b18b 100644
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -1,17 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
index 6c47daa..4234706 100644
--- a/arch/powerpc/lib/test_emulate_step.c
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * Simple sanity test for emulate_step load/store instructions.
+ * Simple sanity tests for instruction emulation infrastructure.
  *
  * Copyright IBM Corp. 2016
- *
- * This program is free software;  you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "emulate_step_test: " fmt
@@ -14,6 +10,7 @@
 #include <linux/ptrace.h>
 #include <asm/sstep.h>
 #include <asm/ppc-opcode.h>
+#include <asm/code-patching.h>
 
 #define IMM_L(i)		((uintptr_t)(i) & 0xffff)
 
@@ -48,7 +45,20 @@
 					___PPC_RA(a) | ___PPC_RB(b))
 #define TEST_LXVD2X(s, a, b)	(PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
 #define TEST_STXVD2X(s, a, b)	(PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
+#define TEST_ADD(t, a, b)	(PPC_INST_ADD | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_ADD_DOT(t, a, b)	(PPC_INST_ADD | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b) | 0x1)
+#define TEST_ADDC(t, a, b)	(PPC_INST_ADDC | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_ADDC_DOT(t, a, b)	(PPC_INST_ADDC | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b) | 0x1)
 
+#define MAX_SUBTESTS	16
+
+#define IGNORE_GPR(n)	(0x1UL << (n))
+#define IGNORE_XER	(0x1UL << 32)
+#define IGNORE_CCR	(0x1UL << 33)
 
 static void __init init_pt_regs(struct pt_regs *regs)
 {
@@ -72,9 +82,15 @@
 	msr_cached = true;
 }
 
-static void __init show_result(char *ins, char *result)
+static void __init show_result(char *mnemonic, char *result)
 {
-	pr_info("%-14s : %s\n", ins, result);
+	pr_info("%-14s : %s\n", mnemonic, result);
+}
+
+static void __init show_result_with_descr(char *mnemonic, char *descr,
+					  char *result)
+{
+	pr_info("%-14s : %-50s %s\n", mnemonic, descr, result);
 }
 
 static void __init test_ld(void)
@@ -426,7 +442,7 @@
 }
 #endif /* CONFIG_VSX */
 
-static int __init test_emulate_step(void)
+static void __init run_tests_load_store(void)
 {
 	test_ld();
 	test_lwz();
@@ -437,6 +453,513 @@
 	test_lfdx_stfdx();
 	test_lvx_stvx();
 	test_lxvd2x_stxvd2x();
+}
+
+struct compute_test {
+	char *mnemonic;
+	struct {
+		char *descr;
+		unsigned long flags;
+		unsigned int instr;
+		struct pt_regs regs;
+	} subtests[MAX_SUBTESTS + 1];
+};
+
+static struct compute_test compute_tests[] = {
+	{
+		.mnemonic = "nop",
+		.subtests = {
+			{
+				.descr = "R0 = LONG_MAX",
+				.instr = PPC_INST_NOP,
+				.regs = {
+					.gpr[0] = LONG_MAX,
+				}
+			}
+		}
+	},
+	{
+		.mnemonic = "add",
+		.subtests = {
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MIN",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MIN,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = LONG_MAX, RB = LONG_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MAX,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = ULONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = 0x1",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MIN",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MIN,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = INT_MAX, RB = INT_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MAX,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = UINT_MAX",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = UINT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = 0x1",
+				.instr = TEST_ADD(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = 0x1,
+				}
+			}
+		}
+	},
+	{
+		.mnemonic = "add.",
+		.subtests = {
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MIN",
+				.flags = IGNORE_CCR,
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MIN,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = LONG_MAX, RB = LONG_MAX",
+				.flags = IGNORE_CCR,
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MAX,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = ULONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = 0x1",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MIN",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MIN,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = INT_MAX, RB = INT_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MAX,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = UINT_MAX",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = UINT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = 0x1",
+				.instr = TEST_ADD_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = 0x1,
+				}
+			}
+		}
+	},
+	{
+		.mnemonic = "addc",
+		.subtests = {
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MIN",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MIN,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = LONG_MAX, RB = LONG_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MAX,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = ULONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = 0x1",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MIN",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MIN,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = INT_MAX, RB = INT_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MAX,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = UINT_MAX",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = UINT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = 0x1",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN | INT_MIN, RB = LONG_MIN | INT_MIN",
+				.instr = TEST_ADDC(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN | (uint)INT_MIN,
+					.gpr[22] = LONG_MIN | (uint)INT_MIN,
+				}
+			}
+		}
+	},
+	{
+		.mnemonic = "addc.",
+		.subtests = {
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MIN",
+				.flags = IGNORE_CCR,
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MIN,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN, RB = LONG_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = LONG_MAX, RB = LONG_MAX",
+				.flags = IGNORE_CCR,
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MAX,
+					.gpr[22] = LONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = ULONG_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = ULONG_MAX,
+				}
+			},
+			{
+				.descr = "RA = ULONG_MAX, RB = 0x1",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = ULONG_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MIN",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MIN,
+				}
+			},
+			{
+				.descr = "RA = INT_MIN, RB = INT_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MIN,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = INT_MAX, RB = INT_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = INT_MAX,
+					.gpr[22] = INT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = UINT_MAX",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = UINT_MAX,
+				}
+			},
+			{
+				.descr = "RA = UINT_MAX, RB = 0x1",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = UINT_MAX,
+					.gpr[22] = 0x1,
+				}
+			},
+			{
+				.descr = "RA = LONG_MIN | INT_MIN, RB = LONG_MIN | INT_MIN",
+				.instr = TEST_ADDC_DOT(20, 21, 22),
+				.regs = {
+					.gpr[21] = LONG_MIN | (uint)INT_MIN,
+					.gpr[22] = LONG_MIN | (uint)INT_MIN,
+				}
+			}
+		}
+	}
+};
+
+static int __init emulate_compute_instr(struct pt_regs *regs,
+					unsigned int instr)
+{
+	struct instruction_op op;
+
+	if (!regs || !instr)
+		return -EINVAL;
+
+	if (analyse_instr(&op, regs, instr) != 1 ||
+	    GETTYPE(op.type) != COMPUTE) {
+		pr_info("emulation failed, instruction = 0x%08x\n", instr);
+		return -EFAULT;
+	}
+
+	emulate_update_regs(regs, &op);
+	return 0;
+}
+
+static int __init execute_compute_instr(struct pt_regs *regs,
+					unsigned int instr)
+{
+	extern int exec_instr(struct pt_regs *regs);
+	extern s32 patch__exec_instr;
+
+	if (!regs || !instr)
+		return -EINVAL;
+
+	/* Patch the NOP with the actual instruction */
+	patch_instruction_site(&patch__exec_instr, instr);
+	if (exec_instr(regs)) {
+		pr_info("execution failed, instruction = 0x%08x\n", instr);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+#define gpr_mismatch(gprn, exp, got)	\
+	pr_info("GPR%u mismatch, exp = 0x%016lx, got = 0x%016lx\n",	\
+		gprn, exp, got)
+
+#define reg_mismatch(name, exp, got)	\
+	pr_info("%s mismatch, exp = 0x%016lx, got = 0x%016lx\n",	\
+		name, exp, got)
+
+static void __init run_tests_compute(void)
+{
+	unsigned long flags;
+	struct compute_test *test;
+	struct pt_regs *regs, exp, got;
+	unsigned int i, j, k, instr;
+	bool ignore_gpr, ignore_xer, ignore_ccr, passed;
+
+	for (i = 0; i < ARRAY_SIZE(compute_tests); i++) {
+		test = &compute_tests[i];
+
+		for (j = 0; j < MAX_SUBTESTS && test->subtests[j].descr; j++) {
+			instr = test->subtests[j].instr;
+			flags = test->subtests[j].flags;
+			regs = &test->subtests[j].regs;
+			ignore_xer = flags & IGNORE_XER;
+			ignore_ccr = flags & IGNORE_CCR;
+			passed = true;
+
+			memcpy(&exp, regs, sizeof(struct pt_regs));
+			memcpy(&got, regs, sizeof(struct pt_regs));
+
+			/*
+			 * Set a compatible MSR value explicitly to ensure
+			 * that XER and CR bits are updated appropriately
+			 */
+			exp.msr = MSR_KERNEL;
+			got.msr = MSR_KERNEL;
+
+			if (emulate_compute_instr(&got, instr) ||
+			    execute_compute_instr(&exp, instr)) {
+				passed = false;
+				goto print;
+			}
+
+			/* Verify GPR values */
+			for (k = 0; k < 32; k++) {
+				ignore_gpr = flags & IGNORE_GPR(k);
+				if (!ignore_gpr && exp.gpr[k] != got.gpr[k]) {
+					passed = false;
+					gpr_mismatch(k, exp.gpr[k], got.gpr[k]);
+				}
+			}
+
+			/* Verify LR value */
+			if (exp.link != got.link) {
+				passed = false;
+				reg_mismatch("LR", exp.link, got.link);
+			}
+
+			/* Verify XER value */
+			if (!ignore_xer && exp.xer != got.xer) {
+				passed = false;
+				reg_mismatch("XER", exp.xer, got.xer);
+			}
+
+			/* Verify CR value */
+			if (!ignore_ccr && exp.ccr != got.ccr) {
+				passed = false;
+				reg_mismatch("CR", exp.ccr, got.ccr);
+			}
+
+print:
+			show_result_with_descr(test->mnemonic,
+					       test->subtests[j].descr,
+					       passed ? "PASS" : "FAIL");
+		}
+	}
+}
+
+static int __init test_emulate_step(void)
+{
+	printk(KERN_INFO "Running instruction emulation self-tests ...\n");
+	run_tests_load_store();
+	run_tests_compute();
 
 	return 0;
 }
diff --git a/arch/powerpc/lib/test_emulate_step_exec_instr.S b/arch/powerpc/lib/test_emulate_step_exec_instr.S
new file mode 100644
index 0000000..1580f34
--- /dev/null
+++ b/arch/powerpc/lib/test_emulate_step_exec_instr.S
@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Non-emulated single-stepping support (currently limited to basic integer
+ * computations) used to validate the instruction emulation infrastructure.
+ *
+ * Copyright (C) 2019 IBM Corporation
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
+#include <asm/code-patching-asm.h>
+#include <linux/errno.h>
+
+/* int exec_instr(struct pt_regs *regs) */
+_GLOBAL(exec_instr)
+
+	/*
+	 * Stack frame layout (INT_FRAME_SIZE bytes)
+	 *   In-memory pt_regs	(SP + STACK_FRAME_OVERHEAD)
+	 *   Scratch space	(SP + 8)
+	 *   Back chain		(SP + 0)
+	 */
+
+	/*
+	 * Allocate a new stack frame with enough space to hold the register
+	 * states in an in-memory pt_regs and also create the back chain to
+	 * the caller's stack frame.
+	 */
+	stdu	r1, -INT_FRAME_SIZE(r1)
+
+	/*
+	 * Save non-volatile GPRs on stack. This includes TOC pointer (GPR2)
+	 * and local variables (GPR14 to GPR31). The register for the pt_regs
+	 * parameter (GPR3) is saved additionally to ensure that the resulting
+	 * register state can still be saved even if GPR3 gets overwritten
+	 * when loading the initial register state for the test instruction.
+	 * The stack pointer (GPR1) and the thread pointer (GPR13) are not
+	 * saved as these should not be modified anyway.
+	 */
+	SAVE_2GPRS(2, r1)
+	SAVE_NVGPRS(r1)
+
+	/*
+	 * Save LR on stack to ensure that the return address is available
+	 * even if it gets overwritten by the test instruction.
+	 */
+	mflr	r0
+	std	r0, _LINK(r1)
+
+	/*
+	 * Save CR on stack. For simplicity, the entire register is saved
+	 * even though only fields 2 to 4 are non-volatile.
+	 */
+	mfcr	r0
+	std	r0, _CCR(r1)
+
+	/*
+	 * Load register state for the test instruction without touching the
+	 * critical non-volatile registers. The register state is passed as a
+	 * pointer to a pt_regs instance.
+	 */
+	subi	r31, r3, GPR0
+
+	/* Load LR from pt_regs */
+	ld	r0, _LINK(r31)
+	mtlr	r0
+
+	/* Load CR from pt_regs */
+	ld	r0, _CCR(r31)
+	mtcr	r0
+
+	/* Load XER from pt_regs */
+	ld	r0, _XER(r31)
+	mtxer	r0
+
+	/* Load GPRs from pt_regs */
+	REST_GPR(0, r31)
+	REST_10GPRS(2, r31)
+	REST_GPR(12, r31)
+	REST_NVGPRS(r31)
+
+	/* Placeholder for the test instruction */
+1:	nop
+	patch_site 1b patch__exec_instr
+
+	/*
+	 * Since GPR3 is overwritten, temporarily restore it back to its
+	 * original state, i.e. the pointer to pt_regs, to ensure that the
+	 * resulting register state can be saved. Before doing this, a copy
+	 * of it is created in the scratch space which is used later on to
+	 * save it to pt_regs.
+	 */
+	std	r3, 8(r1)
+	REST_GPR(3, r1)
+
+	/* Save resulting GPR state to pt_regs */
+	subi	r3, r3, GPR0
+	SAVE_GPR(0, r3)
+	SAVE_GPR(2, r3)
+	SAVE_8GPRS(4, r3)
+	SAVE_GPR(12, r3)
+	SAVE_NVGPRS(r3)
+
+	/* Save resulting LR to pt_regs */
+	mflr	r0
+	std	r0, _LINK(r3)
+
+	/* Save resulting CR to pt_regs */
+	mfcr	r0
+	std	r0, _CCR(r3)
+
+	/* Save resulting XER to pt_regs */
+	mfxer	r0
+	std	r0, _XER(r3)
+
+	/* Restore resulting GPR3 from scratch space and save it to pt_regs */
+	ld	r0, 8(r1)
+	std	r0, GPR3(r3)
+
+	/* Set return value to denote execution success */
+	li	r3, 0
+
+	/* Continue */
+	b	3f
+
+	/* Set return value to denote execution failure */
+2:	li	r3, -EFAULT
+
+	/* Restore the non-volatile GPRs from stack */
+3:	REST_GPR(2, r1)
+	REST_NVGPRS(r1)
+
+	/* Restore LR from stack to be able to return */
+	ld	r0, _LINK(r1)
+	mtlr	r0
+
+	/* Restore CR from stack */
+	ld	r0, _CCR(r1)
+	mtcr	r0
+
+	/* Tear down stack frame */
+	addi	r1, r1, INT_FRAME_SIZE
+
+	/* Return */
+	blr
+
+	/* Setup exception table */
+	EX_TABLE(1b, 2b)
+
+_ASM_NOKPROBE_SYMBOL(exec_instr)
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 9f34049..62e6c30 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -1,17 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2011
  *
diff --git a/arch/powerpc/lib/xor_vmx.c b/arch/powerpc/lib/xor_vmx.c
index 4df240a..54e6197 100644
--- a/arch/powerpc/lib/xor_vmx.c
+++ b/arch/powerpc/lib/xor_vmx.c
@@ -1,17 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2012
  *
diff --git a/arch/powerpc/lib/xor_vmx_glue.c b/arch/powerpc/lib/xor_vmx_glue.c
index dab2b6b..80dba91 100644
--- a/arch/powerpc/lib/xor_vmx_glue.c
+++ b/arch/powerpc/lib/xor_vmx_glue.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Altivec XOR operations
  *
  * Copyright 2017 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/preempt.h>
diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile
index 494df26..a879403 100644
--- a/arch/powerpc/math-emu/Makefile
+++ b/arch/powerpc/math-emu/Makefile
@@ -17,4 +17,4 @@
 CFLAGS_fabs.o = -fno-builtin-fabs
 CFLAGS_math.o = -fno-builtin-fabs
 
-ccflags-y = -I. -Iinclude/math-emu -w
+ccflags-y = -w
diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c
index 581f404..0a05e51 100644
--- a/arch/powerpc/math-emu/math_efp.c
+++ b/arch/powerpc/math-emu/math_efp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/math-emu/math_efp.c
  *
@@ -12,11 +13,6 @@
  * Description:
  * This file is the exception handler to make E500 SPE instructions
  * fully comply with IEEE-754 floating point standard.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/types.h>
diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c
deleted file mode 100644
index 5d53684..0000000
--- a/arch/powerpc/mm/8xx_mmu.c
+++ /dev/null
@@ -1,205 +0,0 @@
-/*
- * This file contains the routines for initializing the MMU
- * on the 8xx series of chips.
- *  -- christophe
- *
- *  Derived from arch/powerpc/mm/40x_mmu.c:
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
- */
-
-#include <linux/memblock.h>
-#include <asm/fixmap.h>
-#include <asm/code-patching.h>
-
-#include "mmu_decl.h"
-
-#define IMMR_SIZE (FIX_IMMR_SIZE << PAGE_SHIFT)
-
-extern int __map_without_ltlbs;
-
-static unsigned long block_mapped_ram;
-
-/*
- * Return PA for this VA if it is in an area mapped with LTLBs.
- * Otherwise, returns 0
- */
-phys_addr_t v_block_mapped(unsigned long va)
-{
-	unsigned long p = PHYS_IMMR_BASE;
-
-	if (__map_without_ltlbs)
-		return 0;
-	if (va >= VIRT_IMMR_BASE && va < VIRT_IMMR_BASE + IMMR_SIZE)
-		return p + va - VIRT_IMMR_BASE;
-	if (va >= PAGE_OFFSET && va < PAGE_OFFSET + block_mapped_ram)
-		return __pa(va);
-	return 0;
-}
-
-/*
- * Return VA for a given PA mapped with LTLBs or 0 if not mapped
- */
-unsigned long p_block_mapped(phys_addr_t pa)
-{
-	unsigned long p = PHYS_IMMR_BASE;
-
-	if (__map_without_ltlbs)
-		return 0;
-	if (pa >= p && pa < p + IMMR_SIZE)
-		return VIRT_IMMR_BASE + pa - p;
-	if (pa < block_mapped_ram)
-		return (unsigned long)__va(pa);
-	return 0;
-}
-
-#define LARGE_PAGE_SIZE_8M	(1<<23)
-
-/*
- * MMU_init_hw does the chip-specific initialization of the MMU hardware.
- */
-void __init MMU_init_hw(void)
-{
-	/* PIN up to the 3 first 8Mb after IMMR in DTLB table */
-#ifdef CONFIG_PIN_TLB_DATA
-	unsigned long ctr = mfspr(SPRN_MD_CTR) & 0xfe000000;
-	unsigned long flags = 0xf0 | MD_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY;
-#ifdef CONFIG_PIN_TLB_IMMR
-	int i = 29;
-#else
-	int i = 28;
-#endif
-	unsigned long addr = 0;
-	unsigned long mem = total_lowmem;
-
-	for (; i < 32 && mem >= LARGE_PAGE_SIZE_8M; i++) {
-		mtspr(SPRN_MD_CTR, ctr | (i << 8));
-		mtspr(SPRN_MD_EPN, (unsigned long)__va(addr) | MD_EVALID);
-		mtspr(SPRN_MD_TWC, MD_PS8MEG | MD_SVALID);
-		mtspr(SPRN_MD_RPN, addr | flags | _PAGE_PRESENT);
-		addr += LARGE_PAGE_SIZE_8M;
-		mem -= LARGE_PAGE_SIZE_8M;
-	}
-#endif
-}
-
-static void __init mmu_mapin_immr(void)
-{
-	unsigned long p = PHYS_IMMR_BASE;
-	unsigned long v = VIRT_IMMR_BASE;
-	unsigned long f = pgprot_val(PAGE_KERNEL_NCG);
-	int offset;
-
-	for (offset = 0; offset < IMMR_SIZE; offset += PAGE_SIZE)
-		map_kernel_page(v + offset, p + offset, f);
-}
-
-/* Address of instructions to patch */
-#ifndef CONFIG_PIN_TLB_IMMR
-extern unsigned int DTLBMiss_jmp;
-#endif
-extern unsigned int DTLBMiss_cmp, FixupDAR_cmp;
-#ifndef CONFIG_PIN_TLB_TEXT
-extern unsigned int ITLBMiss_cmp;
-#endif
-
-static void __init mmu_patch_cmp_limit(unsigned int *addr, unsigned long mapped)
-{
-	unsigned int instr = *addr;
-
-	instr &= 0xffff0000;
-	instr |= (unsigned long)__va(mapped) >> 16;
-	patch_instruction(addr, instr);
-}
-
-unsigned long __init mmu_mapin_ram(unsigned long top)
-{
-	unsigned long mapped;
-
-	if (__map_without_ltlbs) {
-		mapped = 0;
-		mmu_mapin_immr();
-#ifndef CONFIG_PIN_TLB_IMMR
-		patch_instruction(&DTLBMiss_jmp, PPC_INST_NOP);
-#endif
-#ifndef CONFIG_PIN_TLB_TEXT
-		mmu_patch_cmp_limit(&ITLBMiss_cmp, 0);
-#endif
-	} else {
-		mapped = top & ~(LARGE_PAGE_SIZE_8M - 1);
-	}
-
-	mmu_patch_cmp_limit(&DTLBMiss_cmp, mapped);
-	mmu_patch_cmp_limit(&FixupDAR_cmp, mapped);
-
-	/* If the size of RAM is not an exact power of two, we may not
-	 * have covered RAM in its entirety with 8 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.
-	 */
-	if (mapped)
-		memblock_set_current_limit(mapped);
-
-	block_mapped_ram = mapped;
-
-	return mapped;
-}
-
-void __init 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);
-
-	/* 8xx can only access 24MB at the moment */
-	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01800000));
-}
-
-/*
- * Set up to use a given MMU context.
- * id is context number, pgd is PGD pointer.
- *
- * We place the physical address of the new task page directory loaded
- * into the MMU base register, and set the ASID compare register with
- * the new "context."
- */
-void set_context(unsigned long id, pgd_t *pgd)
-{
-	s16 offset = (s16)(__pa(swapper_pg_dir));
-
-#ifdef CONFIG_BDI_SWITCH
-	pgd_t	**ptr = *(pgd_t ***)(KERNELBASE + 0xf0);
-
-	/* Context switch the PTE pointer for the Abatron BDI2000.
-	 * The PGDIR is passed as second argument.
-	 */
-	*(ptr + 1) = pgd;
-#endif
-
-	/* Register M_TW 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_TW, __pa(pgd) - offset);
-
-	/* Update context */
-	mtspr(SPRN_M_CASID, id - 1);
-	/* sync */
-	mb();
-}
-
-void flush_instruction_cache(void)
-{
-	isync();
-	mtspr(SPRN_IC_CST, IDC_INVALL);
-	isync();
-}
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index cdf6a99..5e14798 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -3,45 +3,20 @@
 # Makefile for the linux ppc-specific parts of the memory manager.
 #
 
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
-
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
 obj-y				:= fault.o mem.o pgtable.o mmap.o \
 				   init_$(BITS).o pgtable_$(BITS).o \
+				   pgtable-frag.o ioremap.o ioremap_$(BITS).o \
 				   init-common.o mmu_context.o drmem.o
-obj-$(CONFIG_PPC_MMU_NOHASH)	+= mmu_context_nohash.o tlb_nohash.o \
-				   tlb_nohash_low.o
-obj-$(CONFIG_PPC_BOOK3E)	+= tlb_low_$(BITS)e.o
-hash64-$(CONFIG_PPC_NATIVE)	:= hash_native_64.o
-obj-$(CONFIG_PPC_BOOK3E_64)   += pgtable-book3e.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= pgtable-hash64.o hash_utils_64.o slb_low.o slb.o $(hash64-y) mmu_context_book3s64.o pgtable-book3s64.o
-obj-$(CONFIG_PPC_RADIX_MMU)	+= pgtable-radix.o tlb-radix.o
-obj-$(CONFIG_PPC_STD_MMU_32)	+= ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o
-obj-$(CONFIG_PPC_STD_MMU)	+= tlb_hash$(BITS).o
-ifdef CONFIG_PPC_BOOK3S_64
-obj-$(CONFIG_PPC_4K_PAGES)	+= hash64_4k.o
-obj-$(CONFIG_PPC_64K_PAGES)	+= hash64_64k.o
-endif
-obj-$(CONFIG_40x)		+= 40x_mmu.o
-obj-$(CONFIG_44x)		+= 44x_mmu.o
-obj-$(CONFIG_PPC_8xx)		+= 8xx_mmu.o
-obj-$(CONFIG_PPC_FSL_BOOK3E)	+= fsl_booke_mmu.o
+obj-$(CONFIG_PPC_MMU_NOHASH)	+= nohash/
+obj-$(CONFIG_PPC_BOOK3S_32)	+= book3s32/
+obj-$(CONFIG_PPC_BOOK3S_64)	+= book3s64/
 obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
-obj-$(CONFIG_PPC_SPLPAR)	+= vphn.o
 obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
-obj-y				+= hugetlbpage.o
-ifdef CONFIG_HUGETLB_PAGE
-obj-$(CONFIG_PPC_BOOK3S_64)	+= hugetlbpage-hash64.o
-obj-$(CONFIG_PPC_RADIX_MMU)	+= hugetlbpage-radix.o
-obj-$(CONFIG_PPC_BOOK3E_MMU)	+= hugetlbpage-book3e.o
-endif
-obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hugepage-hash64.o
-obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
+obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
-obj-$(CONFIG_SPAPR_TCE_IOMMU)	+= mmu_context_iommu.o
-obj-$(CONFIG_PPC_PTDUMP)	+= dump_linuxpagetables.o
-obj-$(CONFIG_PPC_HTDUMP)	+= dump_hashpagetable.o
-obj-$(CONFIG_PPC_MEM_KEYS)	+= pkeys.o
+obj-$(CONFIG_PPC_PTDUMP)	+= ptdump/
+obj-$(CONFIG_KASAN)		+= kasan/
diff --git a/arch/powerpc/mm/book3s32/Makefile b/arch/powerpc/mm/book3s32/Makefile
new file mode 100644
index 0000000..1732eaa
--- /dev/null
+++ b/arch/powerpc/mm/book3s32/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+KASAN_SANITIZE_mmu.o := n
+
+ifdef CONFIG_KASAN
+CFLAGS_mmu.o  		+= -DDISABLE_BRANCH_PROFILING
+endif
+
+obj-y += mmu.o hash_low.o mmu_context.o tlb.o
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/book3s32/hash_low.S
similarity index 86%
rename from arch/powerpc/mm/hash_low_32.S
rename to arch/powerpc/mm/book3s32/hash_low.S
index 26acf6c..8bbbd97 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -11,12 +12,6 @@
  *  This file contains low-level assembler routines for managing
  *  the PowerPC MMU hash table.  (PPC 8xx processors don't use a
  *  hash table, so this file is not used on them.)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/reg.h>
@@ -28,6 +23,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/export.h>
 #include <asm/feature-fixups.h>
+#include <asm/code-patching-asm.h>
 
 #ifdef CONFIG_SMP
 	.section .bss
@@ -46,14 +42,13 @@
  * Returns to the caller if the access is illegal or there is no
  * mapping for the address.  Otherwise it places an appropriate PTE
  * in the hash table and returns from the exception.
- * Uses r0, r3 - r8, r10, ctr, lr.
+ * Uses r0, r3 - r6, r8, r10, ctr, lr.
  */
 	.text
 _GLOBAL(hash_page)
-	tophys(r7,0)			/* gets -KERNELBASE into r7 */
 #ifdef CONFIG_SMP
-	addis	r8,r7,mmu_hash_lock@h
-	ori	r8,r8,mmu_hash_lock@l
+	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@h
+	ori	r8, r8, (mmu_hash_lock - PAGE_OFFSET)@l
 	lis	r0,0x0fff
 	b	10f
 11:	lwz	r6,0(r8)
@@ -69,14 +64,13 @@
 	/* Get PTE (linux-style) and check access */
 	lis	r0,KERNELBASE@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 */
+	mfspr	r5, SPRN_SPRG_PGDIR	/* phys page-table root */
 	blt+	112f			/* assume user more likely */
-	lis	r5,swapper_pg_dir@ha	/* if kernel address, use */
-	addi	r5,r5,swapper_pg_dir@l	/* kernel page table */
+	lis	r5, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
+	addi	r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 	rlwimi	r3,r9,32-12,29,29	/* MSR_PR -> _PAGE_USER */
-112:	add	r5,r5,r7		/* convert to phys addr */
+112:
 #ifndef CONFIG_PTE_64BIT
 	rlwimi	r5,r4,12,20,29		/* insert top 10 bits of address */
 	lwz	r8,0(r5)		/* get pmd entry */
@@ -143,25 +137,24 @@
 
 #ifdef CONFIG_SMP
 	eieio
-	addis	r8,r7,mmu_hash_lock@ha
+	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@ha
 	li	r0,0
-	stw	r0,mmu_hash_lock@l(r8)
+	stw	r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8)
 #endif
 
 	/* Return from the exception */
 	lwz	r5,_CTR(r11)
 	mtctr	r5
 	lwz	r0,GPR0(r11)
-	lwz	r7,GPR7(r11)
 	lwz	r8,GPR8(r11)
 	b	fast_exception_return
 
 #ifdef CONFIG_SMP
 hash_page_out:
 	eieio
-	addis	r8,r7,mmu_hash_lock@ha
+	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@ha
 	li	r0,0
-	stw	r0,mmu_hash_lock@l(r8)
+	stw	r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8)
 	blr
 #endif /* CONFIG_SMP */
 
@@ -185,8 +178,7 @@
 	add	r3,r3,r0		/* note create_hpte trims to 24 bits */
 
 #ifdef CONFIG_SMP
-	CURRENT_THREAD_INFO(r8, r1)	/* use cpu number to make tag */
-	lwz	r8,TI_CPU(r8)		/* to go in mmu_hash_lock */
+	lwz	r8,TASK_CPU(r2)		/* to go in mmu_hash_lock */
 	oris	r8,r8,12
 #endif /* CONFIG_SMP */
 
@@ -207,11 +199,9 @@
 	SYNC_601
 	isync
 
-	tophys(r7,0)
-
 #ifdef CONFIG_SMP
-	addis	r6,r7,mmu_hash_lock@ha
-	addi	r6,r6,mmu_hash_lock@l
+	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
 	bne-	11f
@@ -256,8 +246,8 @@
 
 9:
 #ifdef CONFIG_SMP
-	addis	r6,r7,mmu_hash_lock@ha
-	addi	r6,r6,mmu_hash_lock@l
+	lis	r6, (mmu_hash_lock - PAGE_OFFSET)@ha
+	addi	r6, r6, (mmu_hash_lock - PAGE_OFFSET)@l
 	eieio
 	li	r0,0
 	stw	r0,0(r6)		/* clear mmu_hash_lock */
@@ -277,10 +267,8 @@
  * It is designed to be called with the MMU either on or off.
  * r3 contains the VSID, r4 contains the virtual address,
  * r5 contains the linux PTE, r6 contains the old value of the
- * linux PTE (before setting _PAGE_HASHPTE) and r7 contains the
- * offset to be added to addresses (0 if the MMU is on,
- * -KERNELBASE if it is off).  r10 contains the upper half of
- * the PTE if CONFIG_PTE_64BIT.
+ * linux PTE (before setting _PAGE_HASHPTE). r10 contains the
+ * upper half of the PTE if CONFIG_PTE_64BIT.
  * On SMP, the caller should have the mmu_hash_lock held.
  * We assume that the caller has (or will) set the _PAGE_HASHPTE
  * bit in the linux PTE in memory.  The value passed in r6 should
@@ -316,13 +304,13 @@
 
 _GLOBAL(create_hpte)
 	/* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */
-	rlwinm	r8,r5,32-10,31,31	/* _PAGE_RW -> PP lsb */
-	rlwinm	r0,r5,32-7,31,31	/* _PAGE_DIRTY -> PP lsb */
+	rlwinm	r8,r5,32-9,30,30	/* _PAGE_RW -> 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 */
-	andc	r8,r5,r8		/* PP = user? (rw&dirty? 2: 3): 0 */
+	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) */
 END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
@@ -337,11 +325,13 @@
 	rlwimi	r5,r4,10,26,31		/* put in API (abbrev page index) */
 	SET_V(r5)			/* set V (valid) bit */
 
+	patch_site	0f, patch__hash_page_A0
+	patch_site	1f, patch__hash_page_A1
+	patch_site	2f, patch__hash_page_A2
 	/* Get the address of the primary PTE group in the hash table (r3) */
-_GLOBAL(hash_page_patch_A)
-	addis	r0,r7,Hash_base@h	/* base address of hash table */
-	rlwimi	r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT    /* VSID -> hash */
-	rlwinm	r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
+0:	lis	r0, (Hash_base - PAGE_OFFSET)@h	/* base address of hash table */
+1:	rlwimi	r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT    /* VSID -> hash */
+2:	rlwinm	r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
 	xor	r3,r3,r0		/* make primary hash */
 	li	r0,8			/* PTEs/group */
 
@@ -353,10 +343,10 @@
 	beq+	10f			/* no PTE: go look for an empty slot */
 	tlbie	r4
 
-	addis	r4,r7,htab_hash_searches@ha
-	lwz	r6,htab_hash_searches@l(r4)
+	lis	r4, (htab_hash_searches - PAGE_OFFSET)@ha
+	lwz	r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
 	addi	r6,r6,1			/* count how many searches we do */
-	stw	r6,htab_hash_searches@l(r4)
+	stw	r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
 
 	/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
 	mtctr	r0
@@ -366,10 +356,10 @@
 	bdnzf	2,1b			/* loop while ctr != 0 && !cr0.eq */
 	beq+	found_slot
 
+	patch_site	0f, patch__hash_page_B
 	/* Search the secondary PTEG for a matching PTE */
 	ori	r5,r5,PTE_H		/* set H (secondary hash) bit */
-_GLOBAL(hash_page_patch_B)
-	xoris	r4,r3,Hash_msk>>16	/* compute secondary hash */
+0:	xoris	r4,r3,Hash_msk>>16	/* compute secondary hash */
 	xori	r4,r4,(-PTEG_SIZE & 0xffff)
 	addi	r4,r4,-HPTE_SIZE
 	mtctr	r0
@@ -388,15 +378,15 @@
 	beq+	found_empty
 
 	/* update counter of times that the primary PTEG is full */
-	addis	r4,r7,primary_pteg_full@ha
-	lwz	r6,primary_pteg_full@l(r4)
+	lis	r4, (primary_pteg_full - PAGE_OFFSET)@ha
+	lwz	r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
 	addi	r6,r6,1
-	stw	r6,primary_pteg_full@l(r4)
+	stw	r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
 
+	patch_site	0f, patch__hash_page_C
 	/* Search the secondary PTEG for an empty slot */
 	ori	r5,r5,PTE_H		/* set H (secondary hash) bit */
-_GLOBAL(hash_page_patch_C)
-	xoris	r4,r3,Hash_msk>>16	/* compute secondary hash */
+0:	xoris	r4,r3,Hash_msk>>16	/* compute secondary hash */
 	xori	r4,r4,(-PTEG_SIZE & 0xffff)
 	addi	r4,r4,-HPTE_SIZE
 	mtctr	r0
@@ -425,8 +415,8 @@
 	 * lockup here but that shouldn't happen
 	 */
 
-1:	addis	r4,r7,next_slot@ha		/* get next evict slot */
-	lwz	r6,next_slot@l(r4)
+1:	lis	r4, (next_slot - PAGE_OFFSET)@ha	/* get next evict slot */
+	lwz	r6, (next_slot - PAGE_OFFSET)@l(r4)
 	addi	r6,r6,HPTE_SIZE			/* search for candidate */
 	andi.	r6,r6,7*HPTE_SIZE
 	stw	r6,next_slot@l(r4)
@@ -498,8 +488,6 @@
  * We assume that there is a hash table in use (Hash != 0).
  */
 _GLOBAL(flush_hash_pages)
-	tophys(r7,0)
-
 	/*
 	 * We disable interrupts here, even on UP, because we want
 	 * the _PAGE_HASHPTE bit to be a reliable indication of
@@ -544,11 +532,10 @@
 	SET_V(r11)			/* set V (valid) bit */
 
 #ifdef CONFIG_SMP
-	addis	r9,r7,mmu_hash_lock@ha
-	addi	r9,r9,mmu_hash_lock@l
-	CURRENT_THREAD_INFO(r8, r1)
-	add	r8,r8,r7
-	lwz	r8,TI_CPU(r8)
+	lis	r9, (mmu_hash_lock - PAGE_OFFSET)@ha
+	addi	r9, r9, (mmu_hash_lock - PAGE_OFFSET)@l
+	tophys	(r8, r2)
+	lwz	r8, TASK_CPU(r8)
 	oris	r8,r8,9
 10:	lwarx	r0,0,r9
 	cmpi	0,r0,0
@@ -577,11 +564,13 @@
 	stwcx.	r8,0,r5			/* update the pte */
 	bne-	33b
 
+	patch_site	0f, patch__flush_hash_A0
+	patch_site	1f, patch__flush_hash_A1
+	patch_site	2f, patch__flush_hash_A2
 	/* Get the address of the primary PTE group in the hash table (r3) */
-_GLOBAL(flush_hash_patch_A)
-	addis	r8,r7,Hash_base@h	/* base address of hash table */
-	rlwimi	r8,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT    /* VSID -> hash */
-	rlwinm	r0,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
+0:	lis	r8, (Hash_base - PAGE_OFFSET)@h	/* base address of hash table */
+1:	rlwimi	r8,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT    /* VSID -> hash */
+2:	rlwinm	r0,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
 	xor	r8,r0,r8		/* make primary hash */
 
 	/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
@@ -593,11 +582,11 @@
 	bdnzf	2,1b			/* loop while ctr != 0 && !cr0.eq */
 	beq+	3f
 
+	patch_site	0f, patch__flush_hash_B
 	/* Search the secondary PTEG for a matching PTE */
 	ori	r11,r11,PTE_H		/* set H (secondary hash) bit */
 	li	r0,8			/* PTEs/group */
-_GLOBAL(flush_hash_patch_B)
-	xoris	r12,r8,Hash_msk>>16	/* compute secondary hash */
+0:	xoris	r12,r8,Hash_msk>>16	/* compute secondary hash */
 	xori	r12,r12,(-PTEG_SIZE & 0xffff)
 	addi	r12,r12,-HPTE_SIZE
 	mtctr	r0
@@ -641,8 +630,7 @@
  */
 _GLOBAL(_tlbie)
 #ifdef CONFIG_SMP
-	CURRENT_THREAD_INFO(r8, r1)
-	lwz	r8,TI_CPU(r8)
+	lwz	r8,TASK_CPU(r2)
 	oris	r8,r8,11
 	mfmsr	r10
 	SYNC
@@ -679,8 +667,7 @@
  */
 _GLOBAL(_tlbia)
 #if defined(CONFIG_SMP)
-	CURRENT_THREAD_INFO(r8, r1)
-	lwz	r8,TI_CPU(r8)
+	lwz	r8,TASK_CPU(r2)
 	oris	r8,r8,10
 	mfmsr	r10
 	SYNC
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
new file mode 100644
index 0000000..84d5fab
--- /dev/null
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -0,0 +1,475 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * This file contains the routines for handling the MMU on those
+ * PowerPC implementations where the MMU substantially follows the
+ * architecture specification.  This includes the 6xx, 7xx, 7xxx,
+ * and 8260 implementations but excludes the 8xx and 4xx.
+ *  -- 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/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <linux/memblock.h>
+
+#include <asm/prom.h>
+#include <asm/mmu.h>
+#include <asm/machdep.h>
+#include <asm/code-patching.h>
+#include <asm/sections.h>
+
+#include <mm/mmu_decl.h>
+
+struct hash_pte *Hash;
+static unsigned long Hash_size, Hash_mask;
+unsigned long _SDR1;
+static unsigned int hash_mb, hash_mb2;
+
+struct ppc_bat BATS[8][2];	/* 8 pairs of IBAT, DBAT */
+
+struct batrange {		/* stores address ranges mapped by BATs */
+	unsigned long start;
+	unsigned long limit;
+	phys_addr_t phys;
+} bat_addrs[8];
+
+/*
+ * Return PA for this VA if it is mapped by a BAT, or 0
+ */
+phys_addr_t v_block_mapped(unsigned long va)
+{
+	int b;
+	for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b)
+		if (va >= bat_addrs[b].start && va < bat_addrs[b].limit)
+			return bat_addrs[b].phys + (va - bat_addrs[b].start);
+	return 0;
+}
+
+/*
+ * Return VA for a given PA or 0 if not mapped
+ */
+unsigned long p_block_mapped(phys_addr_t pa)
+{
+	int b;
+	for (b = 0; b < ARRAY_SIZE(bat_addrs); ++b)
+		if (pa >= bat_addrs[b].phys
+	    	    && pa < (bat_addrs[b].limit-bat_addrs[b].start)
+		              +bat_addrs[b].phys)
+			return bat_addrs[b].start+(pa-bat_addrs[b].phys);
+	return 0;
+}
+
+static int find_free_bat(void)
+{
+	int b;
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) {
+		for (b = 0; b < 4; b++) {
+			struct ppc_bat *bat = BATS[b];
+
+			if (!(bat[0].batl & 0x40))
+				return b;
+		}
+	} else {
+		int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
+
+		for (b = 0; b < n; b++) {
+			struct ppc_bat *bat = BATS[b];
+
+			if (!(bat[1].batu & 3))
+				return b;
+		}
+	}
+	return -1;
+}
+
+/*
+ * This function calculates the size of the larger block usable to map the
+ * beginning of an area based on the start address and size of that area:
+ * - max block size is 8M on 601 and 256 on other 6xx.
+ * - base address must be aligned to the block size. So the maximum block size
+ *   is identified by the lowest bit set to 1 in the base address (for instance
+ *   if base is 0x16000000, max size is 0x02000000).
+ * - block size has to be a power of two. This is calculated by finding the
+ *   highest bit set to 1.
+ */
+static unsigned int block_size(unsigned long base, unsigned long top)
+{
+	unsigned int max_size = IS_ENABLED(CONFIG_PPC_BOOK3S_601) ? SZ_8M : SZ_256M;
+	unsigned int base_shift = (ffs(base) - 1) & 31;
+	unsigned int block_shift = (fls(top - base) - 1) & 31;
+
+	return min3(max_size, 1U << base_shift, 1U << block_shift);
+}
+
+/*
+ * Set up one of the IBAT (block address translation) register pairs.
+ * The parameters are not checked; in particular size must be a power
+ * of 2 between 128k and 256M.
+ * Only for 603+ ...
+ */
+static void setibat(int index, unsigned long virt, phys_addr_t phys,
+		    unsigned int size, pgprot_t prot)
+{
+	unsigned int bl = (size >> 17) - 1;
+	int wimgxpp;
+	struct ppc_bat *bat = BATS[index];
+	unsigned long flags = pgprot_val(prot);
+
+	if (!cpu_has_feature(CPU_FTR_NEED_COHERENT))
+		flags &= ~_PAGE_COHERENT;
+
+	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)
+		bat[0].batu |= 1;	/* Vp = 1 */
+}
+
+static void clearibat(int index)
+{
+	struct ppc_bat *bat = BATS[index];
+
+	bat[0].batu = 0;
+	bat[0].batl = 0;
+}
+
+static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long top)
+{
+	int idx;
+
+	while ((idx = find_free_bat()) != -1 && base != top) {
+		unsigned int size = block_size(base, top);
+
+		if (size < 128 << 10)
+			break;
+		setbat(idx, PAGE_OFFSET + base, base, size, PAGE_KERNEL_X);
+		base += size;
+	}
+
+	return base;
+}
+
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
+{
+	unsigned long done;
+	unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
+
+	if (__map_without_bats) {
+		pr_debug("RAM mapped without BATs\n");
+		return base;
+	}
+
+	if (!strict_kernel_rwx_enabled() || base >= border || top <= border)
+		return __mmu_mapin_ram(base, top);
+
+	done = __mmu_mapin_ram(base, border);
+	if (done != border)
+		return done;
+
+	return __mmu_mapin_ram(border, top);
+}
+
+void mmu_mark_initmem_nx(void)
+{
+	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
+	int i;
+	unsigned long base = (unsigned long)_stext - PAGE_OFFSET;
+	unsigned long top = (unsigned long)_etext - PAGE_OFFSET;
+	unsigned long size;
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
+		return;
+
+	for (i = 0; i < nb - 1 && base < top && top - base > (128 << 10);) {
+		size = block_size(base, top);
+		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+		base += size;
+	}
+	if (base < top) {
+		size = block_size(base, top);
+		size = max(size, 128UL << 10);
+		if ((top - base) > size) {
+			if (strict_kernel_rwx_enabled())
+				pr_warn("Kernel _etext not properly aligned\n");
+			size <<= 1;
+		}
+		setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+		base += size;
+	}
+	for (; i < nb; i++)
+		clearibat(i);
+
+	update_bats();
+
+	for (i = TASK_SIZE >> 28; i < 16; i++) {
+		/* Do not set NX on VM space for modules */
+		if (IS_ENABLED(CONFIG_MODULES) &&
+		    (VMALLOC_START & 0xf0000000) == i << 28)
+			break;
+		mtsrin(mfsrin(i << 28) | 0x10000000, i << 28);
+	}
+}
+
+void mmu_mark_rodata_ro(void)
+{
+	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
+	int i;
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
+		return;
+
+	for (i = 0; i < nb; i++) {
+		struct ppc_bat *bat = BATS[i];
+
+		if (bat_addrs[i].start < (unsigned long)__init_begin)
+			bat[1].batl = (bat[1].batl & ~BPP_RW) | BPP_RX;
+	}
+
+	update_bats();
+}
+
+/*
+ * Set up one of the I/D BAT (block address translation) register pairs.
+ * The parameters are not checked; in particular size must be a power
+ * of 2 between 128k and 256M.
+ * On 603+, only set IBAT when _PAGE_EXEC is set
+ */
+void __init setbat(int index, unsigned long virt, phys_addr_t phys,
+		   unsigned int size, pgprot_t prot)
+{
+	unsigned int bl;
+	int wimgxpp;
+	struct ppc_bat *bat = BATS[index];
+	unsigned long flags = pgprot_val(prot);
+
+	if ((flags & _PAGE_NO_CACHE) ||
+	    (cpu_has_feature(CPU_FTR_NEED_COHERENT) == 0))
+		flags &= ~_PAGE_COHERENT;
+
+	bl = (size >> 17) - 1;
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_601)) {
+		/* 603, 604, etc. */
+		/* Do DBAT first */
+		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
+				   | _PAGE_COHERENT | _PAGE_GUARDED);
+		wimgxpp |= (flags & _PAGE_RW)? 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)
+			bat[1].batu |= 1; 	/* Vp = 1 */
+		if (flags & _PAGE_GUARDED) {
+			/* G bit must be zero in IBATs */
+			flags &= ~_PAGE_EXEC;
+		}
+		if (flags & _PAGE_EXEC)
+			bat[0] = bat[1];
+		else
+			bat[0].batu = bat[0].batl = 0;
+	} else {
+		/* 601 cpu */
+		if (bl > BL_8M)
+			bl = BL_8M;
+		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
+				   | _PAGE_COHERENT);
+		wimgxpp |= (flags & _PAGE_RW)?
+			((flags & _PAGE_USER)? PP_RWRW: PP_RWXX): PP_RXRX;
+		bat->batu = virt | wimgxpp | 4;	/* Ks=0, Ku=1 */
+		bat->batl = phys | bl | 0x40;	/* V=1 */
+	}
+
+	bat_addrs[index].start = virt;
+	bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1;
+	bat_addrs[index].phys = phys;
+}
+
+/*
+ * Preload a translation in the hash table
+ */
+void hash_preload(struct mm_struct *mm, unsigned long ea)
+{
+	pmd_t *pmd;
+
+	if (!Hash)
+		return;
+	pmd = pmd_offset(pud_offset(pgd_offset(mm, ea), ea), ea);
+	if (!pmd_none(*pmd))
+		add_hash_page(mm->context.id, ea, pmd_val(*pmd));
+}
+
+/*
+ * This is called at the end of handling a user page fault, when the
+ * fault has been handled by updating a PTE in the linux page tables.
+ * We use it to preload an HPTE into the hash table corresponding to
+ * the updated linux 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)
+{
+	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		return;
+	/*
+	 * We don't need to worry about _PAGE_PRESENT here because we are
+	 * called with either mm->page_table_lock held or ptl lock held
+	 */
+
+	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
+	if (!pte_young(*ptep) || address >= TASK_SIZE)
+		return;
+
+	/* We have to test for regs NULL since init will get here first thing at boot */
+	if (!current->thread.regs)
+		return;
+
+	/* We also avoid filling the hash if not coming from a fault */
+	if (TRAP(current->thread.regs) != 0x300 && TRAP(current->thread.regs) != 0x400)
+		return;
+
+	hash_preload(vma->vm_mm, address);
+}
+
+/*
+ * Initialize the hash table and patch the instructions in hashtable.S.
+ */
+void __init MMU_init_hw(void)
+{
+	unsigned int n_hpteg, lg_n_hpteg;
+
+	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		return;
+
+	if ( ppc_md.progress ) ppc_md.progress("hash:enter", 0x105);
+
+#define LG_HPTEG_SIZE	6		/* 64 bytes per HPTEG */
+#define SDR1_LOW_BITS	((n_hpteg - 1) >> 10)
+#define MIN_N_HPTEG	1024		/* min 64kB hash table */
+
+	/*
+	 * Allow 1 HPTE (1/8 HPTEG) for each page of memory.
+	 * This is less than the recommended amount, but then
+	 * Linux ain't AIX.
+	 */
+	n_hpteg = total_memory / (PAGE_SIZE * 8);
+	if (n_hpteg < MIN_N_HPTEG)
+		n_hpteg = MIN_N_HPTEG;
+	lg_n_hpteg = __ilog2(n_hpteg);
+	if (n_hpteg & (n_hpteg - 1)) {
+		++lg_n_hpteg;		/* round up if not power of 2 */
+		n_hpteg = 1 << lg_n_hpteg;
+	}
+	Hash_size = n_hpteg << LG_HPTEG_SIZE;
+
+	/*
+	 * 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);
+	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
+
+	pr_info("Total memory = %lldMB; using %ldkB for hash table\n",
+		(unsigned long long)(total_memory >> 20), Hash_size >> 10);
+
+
+	Hash_mask = n_hpteg - 1;
+	hash_mb2 = hash_mb = 32 - LG_HPTEG_SIZE - lg_n_hpteg;
+	if (lg_n_hpteg > 16)
+		hash_mb2 = 16 - LG_HPTEG_SIZE;
+
+	/*
+	 * When KASAN is selected, there is already an early temporary hash
+	 * table and the switch to the final hash table is done later.
+	 */
+	if (IS_ENABLED(CONFIG_KASAN))
+		return;
+
+	MMU_init_hw_patch();
+}
+
+void __init MMU_init_hw_patch(void)
+{
+	unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE);
+
+	if (ppc_md.progress)
+		ppc_md.progress("hash:patch", 0x345);
+	if (ppc_md.progress)
+		ppc_md.progress("hash:done", 0x205);
+
+	/* WARNING: Make sure nothing can trigger a KASAN check past this point */
+
+	/*
+	 * Patch up the instructions in hashtable.S:create_hpte
+	 */
+	modify_instruction_site(&patch__hash_page_A0, 0xffff,
+				((unsigned int)Hash - PAGE_OFFSET) >> 16);
+	modify_instruction_site(&patch__hash_page_A1, 0x7c0, hash_mb << 6);
+	modify_instruction_site(&patch__hash_page_A2, 0x7c0, hash_mb2 << 6);
+	modify_instruction_site(&patch__hash_page_B, 0xffff, hmask);
+	modify_instruction_site(&patch__hash_page_C, 0xffff, hmask);
+
+	/*
+	 * Patch up the instructions in hashtable.S:flush_hash_page
+	 */
+	modify_instruction_site(&patch__flush_hash_A0, 0xffff,
+				((unsigned int)Hash - PAGE_OFFSET) >> 16);
+	modify_instruction_site(&patch__flush_hash_A1, 0x7c0, hash_mb << 6);
+	modify_instruction_site(&patch__flush_hash_A2, 0x7c0, hash_mb2 << 6);
+	modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask);
+}
+
+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);
+
+	/* 601 can only access 16MB at the moment */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000));
+	else /* Anything else has 256M mapped */
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000));
+}
+
+void __init print_system_hash_info(void)
+{
+	pr_info("Hash_size         = 0x%lx\n", Hash_size);
+	if (Hash_mask)
+		pr_info("Hash_mask         = 0x%lx\n", Hash_mask);
+}
+
+#ifdef CONFIG_PPC_KUEP
+void __init setup_kuep(bool disabled)
+{
+	pr_info("Activating Kernel Userspace Execution Prevention\n");
+
+	if (disabled)
+		pr_warn("KUEP cannot be disabled yet on 6xx when compiled in\n");
+}
+#endif
+
+#ifdef CONFIG_PPC_KUAP
+void __init setup_kuap(bool disabled)
+{
+	pr_info("Activating Kernel Userspace Access Protection\n");
+
+	if (disabled)
+		pr_warn("KUAP cannot be disabled yet on 6xx when compiled in\n");
+}
+#endif
diff --git a/arch/powerpc/mm/mmu_context_hash32.c b/arch/powerpc/mm/book3s32/mmu_context.c
similarity index 91%
rename from arch/powerpc/mm/mmu_context_hash32.c
rename to arch/powerpc/mm/book3s32/mmu_context.c
index 921c1e3..218996e 100644
--- a/arch/powerpc/mm/mmu_context_hash32.c
+++ b/arch/powerpc/mm/book3s32/mmu_context.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file contains the routines for handling the MMU on those
  * PowerPC implementations where the MMU substantially follows the
@@ -14,12 +15,6 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/mm.h>
diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/book3s32/tlb.c
similarity index 92%
rename from arch/powerpc/mm/tlb_hash32.c
rename to arch/powerpc/mm/book3s32/tlb.c
index cf8472c..2fcd321 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/book3s32/tlb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file contains the routines for TLB flushing.
  * On machines where the MMU uses a hash table to store virtual to
@@ -14,12 +15,6 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/kernel.h>
@@ -32,7 +27,7 @@
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 /*
  * Called when unmapping pages to flush entries from the TLB/hash table.
diff --git a/arch/powerpc/mm/book3s64/Makefile b/arch/powerpc/mm/book3s64/Makefile
new file mode 100644
index 0000000..fd393b8
--- /dev/null
+++ b/arch/powerpc/mm/book3s64/Makefile
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ccflags-y	:= $(NO_MINIMAL_TOC)
+
+CFLAGS_REMOVE_slb.o = $(CC_FLAGS_FTRACE)
+
+obj-y				+= hash_pgtable.o hash_utils.o slb.o \
+				   mmu_context.o pgtable.o hash_tlb.o
+obj-$(CONFIG_PPC_NATIVE)	+= hash_native.o
+obj-$(CONFIG_PPC_RADIX_MMU)	+= radix_pgtable.o radix_tlb.o
+obj-$(CONFIG_PPC_4K_PAGES)	+= hash_4k.o
+obj-$(CONFIG_PPC_64K_PAGES)	+= hash_64k.o
+obj-$(CONFIG_HUGETLB_PAGE)	+= hash_hugetlbpage.o
+ifdef CONFIG_HUGETLB_PAGE
+obj-$(CONFIG_PPC_RADIX_MMU)	+= radix_hugetlbpage.o
+endif
+obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hash_hugepage.o
+obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage_prot.o
+obj-$(CONFIG_SPAPR_TCE_IOMMU)	+= iommu_api.o
+obj-$(CONFIG_PPC_MEM_KEYS)	+= pkeys.o
+
+# Instrumenting the SLB fault path can lead to duplicate SLB entries
+KCOV_INSTRUMENT_slb.o := n
diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/book3s64/hash_4k.c
similarity index 97%
rename from arch/powerpc/mm/hash64_4k.c
rename to arch/powerpc/mm/book3s64/hash_4k.c
index 6fa6765..22e7871 100644
--- a/arch/powerpc/mm/hash64_4k.c
+++ b/arch/powerpc/mm/book3s64/hash_4k.c
@@ -1,6 +1,6 @@
 /*
  * Copyright IBM Corporation, 2015
- * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of version 2 of the GNU Lesser General Public License
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/book3s64/hash_64k.c
similarity index 98%
rename from arch/powerpc/mm/hash64_64k.c
rename to arch/powerpc/mm/book3s64/hash_64k.c
index 3afa253..7084ce2 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/book3s64/hash_64k.c
@@ -1,6 +1,6 @@
 /*
  * Copyright IBM Corporation, 2015
- * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of version 2 of the GNU Lesser General Public License
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/book3s64/hash_hugepage.c
similarity index 95%
rename from arch/powerpc/mm/hugepage-hash64.c
rename to arch/powerpc/mm/book3s64/hash_hugepage.c
index 01f213d..4408237 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/book3s64/hash_hugepage.c
@@ -1,6 +1,6 @@
 /*
  * Copyright IBM Corporation, 2013
- * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of version 2.1 of the GNU Lesser General Public License
@@ -51,6 +51,12 @@
 			new_pmd |= _PAGE_DIRTY;
 	} while (!pmd_xchg(pmdp, __pmd(old_pmd), __pmd(new_pmd)));
 
+	/*
+	 * Make sure this is thp or devmap entry
+	 */
+	if (!(old_pmd & (H_PAGE_THP_HUGE | _PAGE_DEVMAP)))
+		return 0;
+
 	rflags = htab_convert_pte_flags(new_pmd);
 
 #if 0
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/book3s64/hash_hugetlbpage.c
similarity index 66%
rename from arch/powerpc/mm/hugetlbpage-hash64.c
rename to arch/powerpc/mm/book3s64/hash_hugetlbpage.c
index b320f50..eefa89c 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/book3s64/hash_hugetlbpage.c
@@ -15,6 +15,9 @@
 #include <asm/cacheflush.h>
 #include <asm/machdep.h>
 
+unsigned int hpage_shift;
+EXPORT_SYMBOL(hpage_shift);
+
 extern long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
 				  unsigned long pa, unsigned long rlags,
 				  unsigned long vflags, int psize, int ssize);
@@ -26,7 +29,7 @@
 	real_pte_t rpte;
 	unsigned long vpn;
 	unsigned long old_pte, new_pte;
-	unsigned long rflags, pa, sz;
+	unsigned long rflags, pa;
 	long slot, offset;
 
 	BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
@@ -34,7 +37,8 @@
 	/* Search the Linux page table for a match with va */
 	vpn = hpt_vpn(ea, vsid, ssize);
 
-	/* At this point, we have a pte (old_pte) which can be used to build
+	/*
+	 * At this point, we have a pte (old_pte) which can be used to build
 	 * or update an HPTE. There are 2 cases:
 	 *
 	 * 1. There is a valid (present) pte with no associated HPTE (this is
@@ -55,13 +59,19 @@
 		if (unlikely(!check_pte_access(access, old_pte)))
 			return 1;
 
-		/* Try to lock the PTE, add ACCESSED and DIRTY if it was
-		 * a write access */
+		/*
+		 * Try to lock the PTE, add ACCESSED and DIRTY if it was
+		 * a write access
+		 */
 		new_pte = old_pte | H_PAGE_BUSY | _PAGE_ACCESSED;
 		if (access & _PAGE_WRITE)
 			new_pte |= _PAGE_DIRTY;
 	} 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))
+		return 0;
+
 	rflags = htab_convert_pte_flags(new_pte);
 	if (unlikely(mmu_psize == MMU_PAGE_16G))
 		offset = PTRS_PER_PUD;
@@ -69,10 +79,11 @@
 		offset = PTRS_PER_PMD;
 	rpte = __real_pte(__pte(old_pte), ptep, offset);
 
-	sz = ((1UL) << shift);
 	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
-		/* No CPU has hugepages but lacks no execute, so we
-		 * don't need to worry about that case */
+		/*
+		 * 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);
 
 	/* Check if pte already has an hpte (case 2) */
@@ -117,3 +128,41 @@
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
 }
+
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+				  unsigned long addr, pte_t *ptep)
+{
+	unsigned long pte_val;
+	/*
+	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
+	 * possible. Also keep the pte_present true so that we don't take
+	 * wrong fault.
+	 */
+	pte_val = pte_update(vma->vm_mm, addr, ptep,
+			     _PAGE_PRESENT, _PAGE_INVALID, 1);
+
+	return __pte(pte_val);
+}
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+				  pte_t *ptep, pte_t old_pte, pte_t pte)
+{
+
+	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);
+}
+
+void hugetlbpage_init_default(void)
+{
+	/* Set default large page size. Currently, we pick 16M or 1M
+	 * depending on what is available
+	 */
+	if (mmu_psize_defs[MMU_PAGE_16M].shift)
+		hpage_shift = mmu_psize_defs[MMU_PAGE_16M].shift;
+	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
+		hpage_shift = mmu_psize_defs[MMU_PAGE_1M].shift;
+	else if (mmu_psize_defs[MMU_PAGE_2M].shift)
+		hpage_shift = mmu_psize_defs[MMU_PAGE_2M].shift;
+}
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/book3s64/hash_native.c
similarity index 95%
rename from arch/powerpc/mm/hash_native_64.c
rename to arch/powerpc/mm/book3s64/hash_native.c
index aaa28fd..523e42e 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/book3s64/hash_native.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * native hashtable management.
  *
  * SMP scalability work:
  *    Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
- * 
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG_LOW
@@ -45,7 +41,7 @@
 #define HPTE_LOCK_BIT (56+3)
 #endif
 
-DEFINE_RAW_SPINLOCK(native_tlbie_lock);
+static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
 static inline void tlbiel_hash_set_isa206(unsigned int set, unsigned int is)
 {
@@ -60,7 +56,7 @@
  * tlbiel instruction for hash, set invalidation
  * i.e., r=1 and is=01 or is=10 or is=11
  */
-static inline void tlbiel_hash_set_isa300(unsigned int set, unsigned int is,
+static __always_inline void tlbiel_hash_set_isa300(unsigned int set, unsigned int is,
 					unsigned int pid,
 					unsigned int ric, unsigned int prs)
 {
@@ -116,7 +112,7 @@
 
 	asm volatile("ptesync": : :"memory");
 
-	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+	asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory");
 }
 
 void hash__tlbiel_all(unsigned int action)
@@ -201,9 +197,32 @@
 	return va;
 }
 
-static inline void fixup_tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+static inline void fixup_tlbie_vpn(unsigned long vpn, int psize,
+				   int apsize, int ssize)
 {
-	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		/* Radix flush for a hash guest */
+
+		unsigned long rb,rs,prs,r,ric;
+
+		rb = PPC_BIT(52); /* IS = 2 */
+		rs = 0;  /* lpid = 0 */
+		prs = 0; /* partition scoped */
+		r = 1;   /* radix format */
+		ric = 0; /* RIC_FLSUH_TLB */
+
+		/*
+		 * Need the extra ptesync to make sure we don't
+		 * re-order the tlbie
+		 */
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+			     : : "r"(rb), "i"(r), "i"(prs),
+			       "i"(ric), "r"(rs) : "memory");
+	}
+
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
 		/* Need the extra ptesync to ensure we don't reorder tlbie*/
 		asm volatile("ptesync": : :"memory");
 		___tlbie(vpn, psize, apsize, ssize);
@@ -287,7 +306,7 @@
 		asm volatile("ptesync": : :"memory");
 	} else {
 		__tlbie(vpn, psize, apsize, ssize);
-		fixup_tlbie(vpn, psize, apsize, ssize);
+		fixup_tlbie_vpn(vpn, psize, apsize, ssize);
 		asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	}
 	if (lock_tlbie && !use_local)
@@ -860,7 +879,7 @@
 		/*
 		 * Just do one more with the last used values.
 		 */
-		fixup_tlbie(vpn, psize, psize, ssize);
+		fixup_tlbie_vpn(vpn, psize, psize, ssize);
 		asm volatile("eieio; tlbsync; ptesync":::"memory");
 
 		if (lock_tlbie)
diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/book3s64/hash_pgtable.c
similarity index 94%
rename from arch/powerpc/mm/pgtable-hash64.c
rename to arch/powerpc/mm/book3s64/hash_pgtable.c
index 692bfc9..64733b9 100644
--- a/arch/powerpc/mm/pgtable-hash64.c
+++ b/arch/powerpc/mm/book3s64/hash_pgtable.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2005, Paul Mackerras, IBM Corporation.
  * Copyright 2009, Benjamin Herrenschmidt, IBM Corporation.
  * Copyright 2015-2016, Aneesh Kumar K.V, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/sched.h>
@@ -19,7 +15,7 @@
 #include <asm/mmu.h>
 #include <asm/tlb.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/thp.h>
@@ -112,9 +108,16 @@
 				       unsigned long page_size,
 				       unsigned long phys)
 {
-	int rc = htab_bolt_mapping(start, start + page_size, phys,
-				   pgprot_val(PAGE_KERNEL),
-				   mmu_vmemmap_psize, mmu_kernel_ssize);
+	int rc;
+
+	if ((start + page_size) >= H_VMEMMAP_END) {
+		pr_warn("Outside the supported range\n");
+		return -1;
+	}
+
+	rc = htab_bolt_mapping(start, start + page_size, phys,
+			       pgprot_val(PAGE_KERNEL),
+			       mmu_vmemmap_psize, mmu_kernel_ssize);
 	if (rc < 0) {
 		int rc2 = htab_remove_mapping(start, start + page_size,
 					      mmu_vmemmap_psize,
@@ -142,7 +145,7 @@
  * map_kernel_page adds an entry to the ioremap page table
  * and adds an entry to the HPT, possibly bolting it
  */
-int hash__map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags)
+int hash__map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
 {
 	pgd_t *pgdp;
 	pud_t *pudp;
@@ -161,8 +164,7 @@
 		ptep = pte_alloc_kernel(pmdp, ea);
 		if (!ptep)
 			return -ENOMEM;
-		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
-							  __pgprot(flags)));
+		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, prot));
 	} else {
 		/*
 		 * If the mm subsystem is not fully up, we cannot create a
@@ -170,7 +172,7 @@
 		 * entry in the hardware page table.
 		 *
 		 */
-		if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags,
+		if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, pgprot_val(prot),
 				      mmu_io_psize, mmu_kernel_ssize)) {
 			printk(KERN_ERR "Failed to do bolted mapping IO "
 			       "memory at %016lx !\n", pa);
@@ -404,6 +406,8 @@
 
 	return 1;
 }
+EXPORT_SYMBOL_GPL(hash__has_transparent_hugepage);
+
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/book3s64/hash_tlb.c
similarity index 91%
rename from arch/powerpc/mm/tlb_hash64.c
rename to arch/powerpc/mm/book3s64/hash_tlb.c
index 87d71dd..4a70d8d 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/book3s64/hash_tlb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file contains the routines for flushing entries from the
  * TLB and MMU hash table.
@@ -14,11 +15,6 @@
  *
  *  Dave Engebretsen <engebret@us.ibm.com>
  *      Rework for PPC64 port.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -55,7 +51,8 @@
 
 	i = batch->index;
 
-	/* Get page size (maybe move back to caller).
+	/*
+	 * Get page size (maybe move back to caller).
 	 *
 	 * NOTE: when using special 64K mappings in 4K environment like
 	 * for SPEs, we obtain the page size from the slice, which thus
@@ -77,10 +74,12 @@
 #endif
 	} else {
 		psize = pte_pagesize_index(mm, addr, pte);
-		/* Mask the address for the standard page size.  If we
+		/*
+		 * Mask the address for the standard page size.  If we
 		 * have a 64k page kernel, but the hardware does not
 		 * support 64k pages, this might be different from the
-		 * hardware page size encoded in the slice table. */
+		 * hardware page size encoded in the slice table.
+		 */
 		addr &= PAGE_MASK;
 		offset = PTRS_PER_PTE;
 	}
@@ -161,7 +160,8 @@
 {
 	struct ppc64_tlb_batch *tlbbatch = &get_cpu_var(ppc64_tlb_batch);
 
-	/* If there's a TLB batch pending, then we must flush it because the
+	/*
+	 * If there's a TLB batch pending, then we must flush it because the
 	 * pages are going to be freed and we really don't want to have a CPU
 	 * access a freed page because it has a stale TLB
 	 */
@@ -201,7 +201,8 @@
 
 	BUG_ON(!mm->pgd);
 
-	/* Note: Normally, we should only ever use a batch within a
+	/*
+	 * Note: Normally, we should only ever use a batch within a
 	 * PTE locked section. This violates the rule, but will work
 	 * since we don't actually modify the PTEs, we just flush the
 	 * hash while leaving the PTEs intact (including their reference
@@ -238,7 +239,8 @@
 	unsigned long flags;
 
 	addr = _ALIGN_DOWN(addr, PMD_SIZE);
-	/* Note: Normally, we should only ever use a batch within a
+	/*
+	 * Note: Normally, we should only ever use a batch within a
 	 * PTE locked section. This violates the rule, but will work
 	 * since we don't actually modify the PTEs, we just flush the
 	 * hash while leaving the PTEs intact (including their reference
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/book3s64/hash_utils.c
similarity index 87%
rename from arch/powerpc/mm/hash_utils_64.c
rename to arch/powerpc/mm/book3s64/hash_utils.c
index f23a89d..6c12376 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerPC64 port by Mike Corrigan and Dave Engebretsen
  *   {mikejc|engebret}@us.ibm.com
@@ -11,11 +12,6 @@
  *
  *    Description:
  *      PowerPC Hashed Page Table functions
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
@@ -37,6 +33,8 @@
 #include <linux/context_tracking.h>
 #include <linux/libfdt.h>
 #include <linux/pkeys.h>
+#include <linux/hugetlb.h>
+#include <linux/cpu.h>
 
 #include <asm/debugfs.h>
 #include <asm/processor.h>
@@ -64,6 +62,9 @@
 #include <asm/ps3.h>
 #include <asm/pte-walk.h>
 #include <asm/asm-prototypes.h>
+#include <asm/ultravisor.h>
+
+#include <mm/mmu_decl.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -128,7 +129,8 @@
 struct mmu_hash_ops mmu_hash_ops;
 EXPORT_SYMBOL(mmu_hash_ops);
 
-/* There are definitions of page sizes arrays to be used when none
+/*
+ * These are definitions of page sizes arrays to be used when none
  * is provided by the firmware.
  */
 
@@ -145,7 +147,8 @@
 	},
 };
 
-/* POWER4, GPUL, POWER5
+/*
+ * POWER4, GPUL, POWER5
  *
  * Support for 16Mb large pages
  */
@@ -270,10 +273,6 @@
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
-		/* Make kvm guest trampolines executable */
-		if (overlaps_kvm_tmp(vaddr, vaddr + step))
-			tprot &= ~HPTE_R_N;
-
 		/*
 		 * If relocatable, check if it overlaps interrupt vectors that
 		 * are copied down to real 0. For relocatable kernel
@@ -479,7 +478,8 @@
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-/* Scan for 16G memory blocks that have been set aside for huge pages
+/*
+ * Scan for 16G memory blocks that have been set aside for huge pages
  * and reserve those blocks for 16G huge pages.
  */
 static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
@@ -496,8 +496,10 @@
 	if (type == NULL || strcmp(type, "memory") != 0)
 		return 0;
 
-	/* This property is the log base 2 of the number of virtual pages that
-	 * will represent this memory block. */
+	/*
+	 * This property is the log base 2 of the number of virtual pages that
+	 * will represent this memory block.
+	 */
 	page_count_prop = of_get_flat_dt_prop(node, "ibm,expected#pages", NULL);
 	if (page_count_prop == NULL)
 		return 0;
@@ -673,16 +675,15 @@
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-	/* We try to use 16M pages for vmemmap if that is supported
+	/*
+	 * We try to use 16M pages for vmemmap if that is supported
 	 * and we have at least 1G of RAM at boot
 	 */
 	if (mmu_psize_defs[MMU_PAGE_16M].shift &&
 	    memblock_phys_mem_size() >= 0x40000000)
 		mmu_vmemmap_psize = MMU_PAGE_16M;
-	else if (mmu_psize_defs[MMU_PAGE_64K].shift)
-		mmu_vmemmap_psize = MMU_PAGE_64K;
 	else
-		mmu_vmemmap_psize = MMU_PAGE_4K;
+		mmu_vmemmap_psize = mmu_virtual_psize;
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 	printk(KERN_DEBUG "Page orders: linear mapping = %d, "
@@ -742,7 +743,8 @@
 
 static unsigned long __init htab_get_table_size(void)
 {
-	/* If hash size isn't already provided by the platform, we try to
+	/*
+	 * If hash size isn't already provided by the platform, we try to
 	 * retrieve it from the device-tree. If it's not there neither, we
 	 * calculate it now based on the total RAM size
 	 */
@@ -755,12 +757,12 @@
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-void resize_hpt_for_hotplug(unsigned long new_mem_size)
+int resize_hpt_for_hotplug(unsigned long new_mem_size)
 {
 	unsigned target_hpt_shift;
 
 	if (!mmu_hash_ops.resize_hpt)
-		return;
+		return 0;
 
 	target_hpt_shift = htab_shift_for_mem_size(new_mem_size);
 
@@ -772,23 +774,25 @@
 	 * reduce unless the target shift is at least 2 below the
 	 * current shift
 	 */
-	if ((target_hpt_shift > ppc64_pft_size)
-	    || (target_hpt_shift < (ppc64_pft_size - 1))) {
-		int rc;
+	if (target_hpt_shift > ppc64_pft_size ||
+	    target_hpt_shift < ppc64_pft_size - 1)
+		return mmu_hash_ops.resize_hpt(target_hpt_shift);
 
-		rc = mmu_hash_ops.resize_hpt(target_hpt_shift);
-		if (rc && (rc != -ENODEV))
-			printk(KERN_WARNING
-			       "Unable to resize hash page table to target order %d: %d\n",
-			       target_hpt_shift, rc);
-	}
+	return 0;
 }
 
 int hash__create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
-	int rc = htab_bolt_mapping(start, end, __pa(start),
-				   pgprot_val(PAGE_KERNEL), mmu_linear_psize,
-				   mmu_kernel_ssize);
+	int rc;
+
+	if (end >= H_VMALLOC_START) {
+		pr_warn("Outside the supported range\n");
+		return -1;
+	}
+
+	rc = htab_bolt_mapping(start, end, __pa(start),
+			       pgprot_val(PAGE_KERNEL), mmu_linear_psize,
+			       mmu_kernel_ssize);
 
 	if (rc < 0) {
 		int rc2 = htab_remove_mapping(start, end, mmu_linear_psize,
@@ -817,7 +821,7 @@
 	 * For now, UPRT is 0 and we have no segment table.
 	 */
 	htab_size =  __ilog2(htab_size) - 18;
-	mmu_partition_table_set_entry(0, hash_table | htab_size, 0);
+	mmu_partition_table_set_entry(0, hash_table | htab_size, 0, false);
 	pr_info("Partition table %p\n", partition_tb);
 }
 
@@ -851,12 +855,6 @@
 		/* Using a hypervisor which owns the htab */
 		htab_address = NULL;
 		_SDR1 = 0; 
-		/*
-		 * On POWER9, we need to do a H_REGISTER_PROC_TBL hcall
-		 * to inform the hypervisor that we wish to use the HPT.
-		 */
-		if (cpu_has_feature(CPU_FTR_ARCH_300))
-			register_process_table(0, 0, 0);
 #ifdef CONFIG_FA_DUMP
 		/*
 		 * If firmware assisted dump is active firmware preserves
@@ -882,8 +880,12 @@
 		}
 #endif /* CONFIG_PPC_CELL */
 
-		table = memblock_alloc_base(htab_size_bytes, htab_size_bytes,
-					    limit);
+		table = memblock_phys_alloc_range(htab_size_bytes,
+						  htab_size_bytes,
+						  0, limit);
+		if (!table)
+			panic("ERROR: Failed to allocate %pa bytes below %pa\n",
+			      &htab_size_bytes, &limit);
 
 		DBG("Hash table allocated at %lx, size: %lx\n", table,
 		    htab_size_bytes);
@@ -908,9 +910,12 @@
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	if (debug_pagealloc_enabled()) {
 		linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
-		linear_map_hash_slots = __va(memblock_alloc_base(
-				linear_map_hash_count, 1, ppc64_rma_size));
-		memset(linear_map_hash_slots, 0, linear_map_hash_count);
+		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);
 	}
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
@@ -922,6 +927,11 @@
 		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
 		    base, size, prot);
 
+		if ((base + size) >= H_VMALLOC_START) {
+			pr_warn("Outside the supported range\n");
+			continue;
+		}
+
 		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
 				prot, mmu_linear_psize, mmu_kernel_ssize));
 	}
@@ -961,6 +971,7 @@
 	htab_scan_page_sizes();
 }
 
+static struct hash_mm_context init_hash_mm_context;
 void __init hash__early_init_mmu(void)
 {
 #ifndef CONFIG_PPC_64K_PAGES
@@ -1001,16 +1012,16 @@
 	 * 4k use hugepd format, so for hash set then to
 	 * zero
 	 */
-	__pmd_val_bits = 0;
-	__pud_val_bits = 0;
-	__pgd_val_bits = 0;
+	__pmd_val_bits = HASH_PMD_VAL_BITS;
+	__pud_val_bits = HASH_PUD_VAL_BITS;
+	__pgd_val_bits = HASH_PGD_VAL_BITS;
 
 	__kernel_virt_start = H_KERN_VIRT_START;
-	__kernel_virt_size = H_KERN_VIRT_SIZE;
 	__vmalloc_start = H_VMALLOC_START;
 	__vmalloc_end = H_VMALLOC_END;
 	__kernel_io_start = H_KERN_IO_START;
-	vmemmap = (struct page *)H_VMEMMAP_BASE;
+	__kernel_io_end = H_KERN_IO_END;
+	vmemmap = (struct page *)H_VMEMMAP_START;
 	ioremap_bot = IOREMAP_BASE;
 
 #ifdef CONFIG_PCI
@@ -1028,12 +1039,16 @@
 	if (!mmu_hash_ops.hpte_insert)
 		panic("hash__early_init_mmu: No MMU hash ops defined!\n");
 
-	/* Initialize the MMU Hash table and create the linear mapping
+	/*
+	 * Initialize the MMU Hash table and create the linear mapping
 	 * of memory. Has to be done before SLB initialization as this is
 	 * currently where the page size encoding is obtained.
 	 */
 	htab_initialize();
 
+	init_mm.context.hash_context = &init_hash_mm_context;
+	mm_ctx_set_slb_addr_limit(&init_mm.context, SLB_ADDR_LIMIT_DEFAULT);
+
 	pr_info("Initializing hash mmu with SLB\n");
 	/* Initialize SLB management */
 	slb_initialize();
@@ -1052,8 +1067,8 @@
 		if (!cpu_has_feature(CPU_FTR_ARCH_300))
 			mtspr(SPRN_SDR1, _SDR1);
 		else
-			mtspr(SPRN_PTCR,
-			      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+			set_ptcr_when_no_uv(__pa(partition_tb) |
+					    (PATB_SIZE_SHIFT - 12));
 	}
 	/* Initialize SLB */
 	slb_initialize();
@@ -1125,7 +1140,7 @@
 	if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {
 
 		copy_mm_to_paca(mm);
-		slb_flush_and_rebolt();
+		slb_flush_and_restore_bolted();
 	}
 }
 #endif /* CONFIG_PPC_64K_PAGES */
@@ -1140,10 +1155,13 @@
  */
 static int subpage_protection(struct mm_struct *mm, unsigned long ea)
 {
-	struct subpage_prot_table *spt = &mm->context.spt;
+	struct subpage_prot_table *spt = mm_ctx_subpage_prot(&mm->context);
 	u32 spp = 0;
 	u32 **sbpm, *sbpp;
 
+	if (!spt)
+		return 0;
+
 	if (ea >= spt->maxaddr)
 		return 0;
 	if (ea < 0x100000000UL) {
@@ -1197,7 +1215,7 @@
 	if (user_region) {
 		if (psize != get_paca_psize(ea)) {
 			copy_mm_to_paca(mm);
-			slb_flush_and_rebolt();
+			slb_flush_and_restore_bolted();
 		}
 	} else if (get_paca()->vmalloc_sllp !=
 		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
@@ -1207,7 +1225,8 @@
 	}
 }
 
-/* Result code is:
+/*
+ * Result code is:
  *  0 - handled
  *  1 - normal page fault
  * -1 - critical hash insertion error
@@ -1231,7 +1250,7 @@
 	trace_hash_fault(ea, access, trap);
 
 	/* Get region & vsid */
- 	switch (REGION_ID(ea)) {
+	switch (get_region_id(ea)) {
 	case USER_REGION_ID:
 		user_region = 1;
 		if (! mm) {
@@ -1245,15 +1264,19 @@
 		break;
 	case VMALLOC_REGION_ID:
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
-		if (ea < VMALLOC_END)
-			psize = mmu_vmalloc_psize;
-		else
-			psize = mmu_io_psize;
+		psize = mmu_vmalloc_psize;
+		ssize = mmu_kernel_ssize;
+		break;
+
+	case IO_REGION_ID:
+		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		psize = mmu_io_psize;
 		ssize = mmu_kernel_ssize;
 		break;
 	default:
-		/* Not a valid range
-		 * Send the problem up to do_page_fault 
+		/*
+		 * Not a valid range
+		 * Send the problem up to do_page_fault()
 		 */
 		rc = 1;
 		goto bail;
@@ -1278,7 +1301,8 @@
 		flags |= HPTE_LOCAL_UPDATE;
 
 #ifndef CONFIG_PPC_64K_PAGES
-	/* If we use 4K pages and our psize is not 4K, then we might
+	/*
+	 * If we use 4K pages and our psize is not 4K, then we might
 	 * be hitting a special driver mapping, and need to align the
 	 * address before we fetch the PTE.
 	 *
@@ -1300,7 +1324,8 @@
 	/* Add _PAGE_PRESENT to the required access perm */
 	access |= _PAGE_PRESENT;
 
-	/* Pre-check access permissions (will be re-checked atomically
+	/*
+	 * Pre-check access permissions (will be re-checked atomically
 	 * in __hash_page_XX but this pre-check is a fast path
 	 */
 	if (!check_pte_access(access, pte_val(*ptep))) {
@@ -1347,7 +1372,8 @@
 		psize = MMU_PAGE_4K;
 	}
 
-	/* If this PTE is non-cacheable and we have restrictions on
+	/*
+	 * If this PTE is non-cacheable and we have restrictions on
 	 * using non cacheable large pages, then we switch to 4k
 	 */
 	if (mmu_ci_restrictions && psize == MMU_PAGE_64K && pte_ci(*ptep)) {
@@ -1388,7 +1414,8 @@
 					    flags, ssize, spp);
 	}
 
-	/* Dump some info in case of hash insertion failure, they should
+	/*
+	 * Dump some info in case of hash insertion failure, they should
 	 * never happen so it is really useful to know if/when they do
 	 */
 	if (rc == -1)
@@ -1414,7 +1441,8 @@
 	unsigned long flags = 0;
 	struct mm_struct *mm = current->mm;
 
-	if (REGION_ID(ea) == VMALLOC_REGION_ID)
+	if ((get_region_id(ea) == VMALLOC_REGION_ID) ||
+	    (get_region_id(ea) == IO_REGION_ID))
 		mm = &init_mm;
 
 	if (dsisr & DSISR_NOHPTE)
@@ -1424,14 +1452,15 @@
 }
 EXPORT_SYMBOL_GPL(hash_page);
 
-int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap,
-		unsigned long dsisr)
+int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr,
+		unsigned long msr)
 {
 	unsigned long access = _PAGE_PRESENT | _PAGE_READ;
 	unsigned long flags = 0;
 	struct mm_struct *mm = current->mm;
+	unsigned int region_id = get_region_id(ea);
 
-	if (REGION_ID(ea) == VMALLOC_REGION_ID)
+	if ((region_id == VMALLOC_REGION_ID) || (region_id == IO_REGION_ID))
 		mm = &init_mm;
 
 	if (dsisr & DSISR_NOHPTE)
@@ -1448,7 +1477,7 @@
 	 * 2) user space access kernel space.
 	 */
 	access |= _PAGE_PRIVILEGED;
-	if ((msr & MSR_PR) || (REGION_ID(ea) == USER_REGION_ID))
+	if ((msr & MSR_PR) || (region_id == USER_REGION_ID))
 		access &= ~_PAGE_PRIVILEGED;
 
 	if (trap == 0x400)
@@ -1463,7 +1492,7 @@
 	int psize = get_slice_psize(mm, ea);
 
 	/* We only prefault standard pages for now */
-	if (unlikely(psize != mm->context.user_psize))
+	if (unlikely(psize != mm_ctx_user_psize(&mm->context)))
 		return false;
 
 	/*
@@ -1481,8 +1510,8 @@
 }
 #endif
 
-void hash_preload(struct mm_struct *mm, unsigned long ea,
-		  unsigned long access, unsigned long trap)
+static void hash_preload(struct mm_struct *mm, unsigned long ea,
+			 bool is_exec, unsigned long trap)
 {
 	int hugepage_shift;
 	unsigned long vsid;
@@ -1490,8 +1519,9 @@
 	pte_t *ptep;
 	unsigned long flags;
 	int rc, ssize, update_flags = 0;
+	unsigned long access = _PAGE_PRESENT | _PAGE_READ | (is_exec ? _PAGE_EXEC : 0);
 
-	BUG_ON(REGION_ID(ea) != USER_REGION_ID);
+	BUG_ON(get_region_id(ea) != USER_REGION_ID);
 
 	if (!should_hash_preload(mm, ea))
 		return;
@@ -1541,7 +1571,7 @@
 
 	/* Hash it in */
 #ifdef CONFIG_PPC_64K_PAGES
-	if (mm->context.user_psize == MMU_PAGE_64K)
+	if (mm_ctx_user_psize(&mm->context) == MMU_PAGE_64K)
 		rc = __hash_page_64K(ea, access, vsid, ptep, trap,
 				     update_flags, ssize);
 	else
@@ -1554,13 +1584,64 @@
 	 */
 	if (rc == -1)
 		hash_failure_debug(ea, access, vsid, trap, ssize,
-				   mm->context.user_psize,
-				   mm->context.user_psize,
+				   mm_ctx_user_psize(&mm->context),
+				   mm_ctx_user_psize(&mm->context),
 				   pte_val(*ptep));
 out_exit:
 	local_irq_restore(flags);
 }
 
+/*
+ * This is called at the end of handling a user page fault, when the
+ * fault has been handled by updating a PTE in the linux page tables.
+ * We use it to preload an HPTE into the hash table corresponding to
+ * the updated linux 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)
+{
+	/*
+	 * We don't need to worry about _PAGE_PRESENT here because we are
+	 * called with either mm->page_table_lock held or ptl lock held
+	 */
+	unsigned long trap;
+	bool is_exec;
+
+	if (radix_enabled()) {
+		prefetch((void *)address);
+		return;
+	}
+
+	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
+	if (!pte_young(*ptep) || address >= TASK_SIZE)
+		return;
+
+	/*
+	 * We try to figure out if we are coming from an instruction
+	 * access fault and pass that down to __hash_page so we avoid
+	 * double-faulting on execution of fresh text. We have to test
+	 * for regs NULL since init will get here first thing at boot.
+	 *
+	 * We also avoid filling the hash if not coming from a fault.
+	 */
+
+	trap = current->thread.regs ? TRAP(current->thread.regs) : 0UL;
+	switch (trap) {
+	case 0x300:
+		is_exec = false;
+		break;
+	case 0x400:
+		is_exec = true;
+		break;
+	default:
+		return;
+	}
+
+	hash_preload(vma->vm_mm, address, is_exec, trap);
+}
+
 #ifdef CONFIG_PPC_MEM_KEYS
 /*
  * Return the protection key associated with the given address and the
@@ -1626,7 +1707,8 @@
 	return gslot;
 }
 
-/* WARNING: This is called from hash_low_64.S, if you change this prototype,
+/*
+ * WARNING: This is called from hash_low_64.S, if you change this prototype,
  *          do not forget to update the assembly call site !
  */
 void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
@@ -1666,7 +1748,7 @@
 	/*
 	 * IF we try to do a HUGE PTE update after a withdraw is done.
 	 * we will find the below NULL. This happens when we do
-	 * split_huge_page_pmd
+	 * split_huge_pmd
 	 */
 	if (!hpte_slot_array)
 		return;
@@ -1847,7 +1929,8 @@
 void hash__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
+	/*
+	 * We don't currently support the first MEMBLOCK not mapping 0
 	 * physical on those processors
 	 */
 	BUG_ON(first_memblock_base != 0);
@@ -1859,11 +1942,20 @@
 	 *
 	 * For guests on platforms before POWER9, we clamp the it limit to 1G
 	 * to avoid some funky things such as RTAS bugs etc...
+	 *
+	 * On POWER9 we limit to 1TB in case the host erroneously told us that
+	 * the RMA was >1TB. Effective address bits 0:23 are treated as zero
+	 * (meaning the access is aliased to zero i.e. addr = addr % 1TB)
+	 * for virtual real mode addressing and so it doesn't make sense to
+	 * have an area larger than 1TB as it can't be addressed.
 	 */
 	if (!early_cpu_has_feature(CPU_FTR_HVMODE)) {
 		ppc64_rma_size = first_memblock_size;
 		if (!early_cpu_has_feature(CPU_FTR_ARCH_300))
 			ppc64_rma_size = min_t(u64, ppc64_rma_size, 0x40000000);
+		else
+			ppc64_rma_size = min_t(u64, ppc64_rma_size,
+					       1UL << SID_SHIFT_1T);
 
 		/* Finally limit subsequent allocations */
 		memblock_set_current_limit(ppc64_rma_size);
@@ -1882,18 +1974,24 @@
 
 static int hpt_order_set(void *data, u64 val)
 {
+	int ret;
+
 	if (!mmu_hash_ops.resize_hpt)
 		return -ENODEV;
 
-	return mmu_hash_ops.resize_hpt(val);
+	cpus_read_lock();
+	ret = mmu_hash_ops.resize_hpt(val);
+	cpus_read_unlock();
+
+	return ret;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n");
 
 static int __init hash64_debugfs(void)
 {
-	if (!debugfs_create_file("hpt_order", 0600, powerpc_debugfs_root,
-				 NULL, &fops_hpt_order)) {
+	if (!debugfs_create_file_unsafe("hpt_order", 0600, powerpc_debugfs_root,
+					NULL, &fops_hpt_order)) {
 		pr_err("lpar: unable to create hpt_order debugsfs file\n");
 	}
 
@@ -1901,3 +1999,11 @@
 }
 machine_device_initcall(pseries, hash64_debugfs);
 #endif /* CONFIG_DEBUG_FS */
+
+void __init print_system_hash_info(void)
+{
+	pr_info("ppc64_pft_size    = 0x%llx\n", ppc64_pft_size);
+
+	if (htab_hash_mask)
+		pr_info("htab_hash_mask    = 0x%lx\n", htab_hash_mask);
+}
diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
new file mode 100644
index 0000000..56cc845
--- /dev/null
+++ b/arch/powerpc/mm/book3s64/iommu_api.c
@@ -0,0 +1,461 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  IOMMU helpers in MMU context.
+ *
+ *  Copyright (C) 2015 IBM Corp. <aik@ozlabs.ru>
+ */
+
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+#include <linux/rculist.h>
+#include <linux/vmalloc.h>
+#include <linux/mutex.h>
+#include <linux/migrate.h>
+#include <linux/hugetlb.h>
+#include <linux/swap.h>
+#include <linux/sizes.h>
+#include <linux/mm.h>
+#include <asm/mmu_context.h>
+#include <asm/pte-walk.h>
+#include <linux/mm_inline.h>
+
+static DEFINE_MUTEX(mem_list_mutex);
+
+#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY	0x1
+#define MM_IOMMU_TABLE_GROUP_PAGE_MASK	~(SZ_4K - 1)
+
+struct mm_iommu_table_group_mem_t {
+	struct list_head next;
+	struct rcu_head rcu;
+	unsigned long used;
+	atomic64_t mapped;
+	unsigned int pageshift;
+	u64 ua;			/* userspace address */
+	u64 entries;		/* number of entries in hpas/hpages[] */
+	/*
+	 * in mm_iommu_get we temporarily use this to store
+	 * struct page address.
+	 *
+	 * We need to convert ua to hpa in real mode. Make it
+	 * simpler by storing physical address.
+	 */
+	union {
+		struct page **hpages;	/* vmalloc'ed */
+		phys_addr_t *hpas;
+	};
+#define MM_IOMMU_TABLE_INVALID_HPA	((uint64_t)-1)
+	u64 dev_hpa;		/* Device memory base address */
+};
+
+bool mm_iommu_preregistered(struct mm_struct *mm)
+{
+	return !list_empty(&mm->context.iommu_group_mem_list);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
+
+static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
+			      unsigned long entries, unsigned long dev_hpa,
+			      struct mm_iommu_table_group_mem_t **pmem)
+{
+	struct mm_iommu_table_group_mem_t *mem, *mem2;
+	long i, ret, locked_entries = 0, pinned = 0;
+	unsigned int pageshift;
+	unsigned long entry, chunk;
+
+	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
+		ret = account_locked_vm(mm, entries, true);
+		if (ret)
+			return ret;
+
+		locked_entries = entries;
+	}
+
+	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+	if (!mem) {
+		ret = -ENOMEM;
+		goto unlock_exit;
+	}
+
+	if (dev_hpa != MM_IOMMU_TABLE_INVALID_HPA) {
+		mem->pageshift = __ffs(dev_hpa | (entries << PAGE_SHIFT));
+		mem->dev_hpa = dev_hpa;
+		goto good_exit;
+	}
+	mem->dev_hpa = MM_IOMMU_TABLE_INVALID_HPA;
+
+	/*
+	 * For a starting point for a maximum page size calculation
+	 * we use @ua and @entries natural alignment to allow IOMMU pages
+	 * smaller than huge pages but still bigger than PAGE_SIZE.
+	 */
+	mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
+	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
+	if (!mem->hpas) {
+		kfree(mem);
+		ret = -ENOMEM;
+		goto unlock_exit;
+	}
+
+	down_read(&mm->mmap_sem);
+	chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) /
+			sizeof(struct vm_area_struct *);
+	chunk = min(chunk, entries);
+	for (entry = 0; entry < entries; entry += chunk) {
+		unsigned long n = min(entries - entry, chunk);
+
+		ret = get_user_pages(ua + (entry << PAGE_SHIFT), n,
+				FOLL_WRITE | FOLL_LONGTERM,
+				mem->hpages + entry, NULL);
+		if (ret == n) {
+			pinned += n;
+			continue;
+		}
+		if (ret > 0)
+			pinned += ret;
+		break;
+	}
+	up_read(&mm->mmap_sem);
+	if (pinned != entries) {
+		if (!ret)
+			ret = -EFAULT;
+		goto free_exit;
+	}
+
+	pageshift = PAGE_SHIFT;
+	for (i = 0; i < entries; ++i) {
+		struct page *page = mem->hpages[i];
+
+		/*
+		 * Allow to use larger than 64k IOMMU pages. Only do that
+		 * if we are backed by hugetlb.
+		 */
+		if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page))
+			pageshift = page_shift(compound_head(page));
+		mem->pageshift = min(mem->pageshift, pageshift);
+		/*
+		 * We don't need struct page reference any more, switch
+		 * to physical address.
+		 */
+		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
+	}
+
+good_exit:
+	atomic64_set(&mem->mapped, 1);
+	mem->used = 1;
+	mem->ua = ua;
+	mem->entries = entries;
+
+	mutex_lock(&mem_list_mutex);
+
+	list_for_each_entry_rcu(mem2, &mm->context.iommu_group_mem_list, next) {
+		/* Overlap? */
+		if ((mem2->ua < (ua + (entries << PAGE_SHIFT))) &&
+				(ua < (mem2->ua +
+				       (mem2->entries << PAGE_SHIFT)))) {
+			ret = -EINVAL;
+			mutex_unlock(&mem_list_mutex);
+			goto free_exit;
+		}
+	}
+
+	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
+
+	mutex_unlock(&mem_list_mutex);
+
+	*pmem = mem;
+
+	return 0;
+
+free_exit:
+	/* free the reference taken */
+	for (i = 0; i < pinned; i++)
+		put_page(mem->hpages[i]);
+
+	vfree(mem->hpas);
+	kfree(mem);
+
+unlock_exit:
+	account_locked_vm(mm, locked_entries, false);
+
+	return ret;
+}
+
+long mm_iommu_new(struct mm_struct *mm, unsigned long ua, unsigned long entries,
+		struct mm_iommu_table_group_mem_t **pmem)
+{
+	return mm_iommu_do_alloc(mm, ua, entries, MM_IOMMU_TABLE_INVALID_HPA,
+			pmem);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_new);
+
+long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua,
+		unsigned long entries, unsigned long dev_hpa,
+		struct mm_iommu_table_group_mem_t **pmem)
+{
+	return mm_iommu_do_alloc(mm, ua, entries, dev_hpa, pmem);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_newdev);
+
+static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
+{
+	long i;
+	struct page *page = NULL;
+
+	if (!mem->hpas)
+		return;
+
+	for (i = 0; i < mem->entries; ++i) {
+		if (!mem->hpas[i])
+			continue;
+
+		page = pfn_to_page(mem->hpas[i] >> PAGE_SHIFT);
+		if (!page)
+			continue;
+
+		if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
+			SetPageDirty(page);
+
+		put_page(page);
+		mem->hpas[i] = 0;
+	}
+}
+
+static void mm_iommu_do_free(struct mm_iommu_table_group_mem_t *mem)
+{
+
+	mm_iommu_unpin(mem);
+	vfree(mem->hpas);
+	kfree(mem);
+}
+
+static void mm_iommu_free(struct rcu_head *head)
+{
+	struct mm_iommu_table_group_mem_t *mem = container_of(head,
+			struct mm_iommu_table_group_mem_t, rcu);
+
+	mm_iommu_do_free(mem);
+}
+
+static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
+{
+	list_del_rcu(&mem->next);
+	call_rcu(&mem->rcu, mm_iommu_free);
+}
+
+long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
+{
+	long ret = 0;
+	unsigned long unlock_entries = 0;
+
+	mutex_lock(&mem_list_mutex);
+
+	if (mem->used == 0) {
+		ret = -ENOENT;
+		goto unlock_exit;
+	}
+
+	--mem->used;
+	/* There are still users, exit */
+	if (mem->used)
+		goto unlock_exit;
+
+	/* Are there still mappings? */
+	if (atomic_cmpxchg(&mem->mapped, 1, 0) != 1) {
+		++mem->used;
+		ret = -EBUSY;
+		goto unlock_exit;
+	}
+
+	if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+		unlock_entries = mem->entries;
+
+	/* @mapped became 0 so now mappings are disabled, release the region */
+	mm_iommu_release(mem);
+
+unlock_exit:
+	mutex_unlock(&mem_list_mutex);
+
+	account_locked_vm(mm, unlock_entries, false);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_put);
+
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
+		unsigned long ua, unsigned long size)
+{
+	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
+		if ((mem->ua <= ua) &&
+				(ua + size <= mem->ua +
+				 (mem->entries << PAGE_SHIFT))) {
+			ret = mem;
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_lookup);
+
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
+		unsigned long ua, unsigned long size)
+{
+	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+	list_for_each_entry_lockless(mem, &mm->context.iommu_group_mem_list,
+			next) {
+		if ((mem->ua <= ua) &&
+				(ua + size <= mem->ua +
+				 (mem->entries << PAGE_SHIFT))) {
+			ret = mem;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm,
+		unsigned long ua, unsigned long entries)
+{
+	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+	mutex_lock(&mem_list_mutex);
+
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
+		if ((mem->ua == ua) && (mem->entries == entries)) {
+			ret = mem;
+			++mem->used;
+			break;
+		}
+	}
+
+	mutex_unlock(&mem_list_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_get);
+
+long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
+{
+	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
+	u64 *va;
+
+	if (entry >= mem->entries)
+		return -EFAULT;
+
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
+	if (!mem->hpas) {
+		*hpa = mem->dev_hpa + (ua - mem->ua);
+		return 0;
+	}
+
+	va = &mem->hpas[entry];
+	*hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
+
+long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
+{
+	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
+	unsigned long *pa;
+
+	if (entry >= mem->entries)
+		return -EFAULT;
+
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
+	if (!mem->hpas) {
+		*hpa = mem->dev_hpa + (ua - mem->ua);
+		return 0;
+	}
+
+	pa = (void *) vmalloc_to_phys(&mem->hpas[entry]);
+	if (!pa)
+		return -EFAULT;
+
+	*hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
+
+	return 0;
+}
+
+extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua)
+{
+	struct mm_iommu_table_group_mem_t *mem;
+	long entry;
+	void *va;
+	unsigned long *pa;
+
+	mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE);
+	if (!mem)
+		return;
+
+	if (mem->dev_hpa != MM_IOMMU_TABLE_INVALID_HPA)
+		return;
+
+	entry = (ua - mem->ua) >> PAGE_SHIFT;
+	va = &mem->hpas[entry];
+
+	pa = (void *) vmalloc_to_phys(va);
+	if (!pa)
+		return;
+
+	*pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY;
+}
+
+bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa,
+		unsigned int pageshift, unsigned long *size)
+{
+	struct mm_iommu_table_group_mem_t *mem;
+	unsigned long end;
+
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
+		if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+			continue;
+
+		end = mem->dev_hpa + (mem->entries << PAGE_SHIFT);
+		if ((mem->dev_hpa <= hpa) && (hpa < end)) {
+			/*
+			 * Since the IOMMU page size might be bigger than
+			 * PAGE_SIZE, the amount of preregistered memory
+			 * starting from @hpa might be smaller than 1<<pageshift
+			 * and the caller needs to distinguish this situation.
+			 */
+			*size = min(1UL << pageshift, end - hpa);
+			return true;
+		}
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_is_devmem);
+
+long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
+{
+	if (atomic64_inc_not_zero(&mem->mapped))
+		return 0;
+
+	/* Last mm_iommu_put() has been called, no more mappings allowed() */
+	return -ENXIO;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_mapped_inc);
+
+void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem)
+{
+	atomic64_add_unless(&mem->mapped, -1, 1);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_mapped_dec);
+
+void mm_iommu_init(struct mm_struct *mm)
+{
+	INIT_LIST_HEAD_RCU(&mm->context.iommu_group_mem_list);
+}
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/book3s64/mmu_context.c
similarity index 63%
rename from arch/powerpc/mm/mmu_context_book3s64.c
rename to arch/powerpc/mm/book3s64/mmu_context.c
index dbd8f76..0ba30b8 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/book3s64/mmu_context.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  MMU context allocation for 64-bit kernels.
  *
  *  Copyright (C) 2004 Anton Blanchard, IBM Corp. <anton@samba.org>
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/sched.h>
@@ -53,13 +48,54 @@
 }
 EXPORT_SYMBOL_GPL(hash__alloc_context_id);
 
+void slb_setup_new_exec(void);
+
+static int realloc_context_ids(mm_context_t *ctx)
+{
+	int i, id;
+
+	/*
+	 * id 0 (aka. ctx->id) is special, we always allocate a new one, even if
+	 * there wasn't one allocated previously (which happens in the exec
+	 * case where ctx is newly allocated).
+	 *
+	 * We have to be a bit careful here. We must keep the existing ids in
+	 * the array, so that we can test if they're non-zero to decide if we
+	 * need to allocate a new one. However in case of error we must free the
+	 * ids we've allocated but *not* any of the existing ones (or risk a
+	 * UAF). That's why we decrement i at the start of the error handling
+	 * loop, to skip the id that we just tested but couldn't reallocate.
+	 */
+	for (i = 0; i < ARRAY_SIZE(ctx->extended_id); i++) {
+		if (i == 0 || ctx->extended_id[i]) {
+			id = hash__alloc_context_id();
+			if (id < 0)
+				goto error;
+
+			ctx->extended_id[i] = id;
+		}
+	}
+
+	/* The caller expects us to return id */
+	return ctx->id;
+
+error:
+	for (i--; i >= 0; i--) {
+		if (ctx->extended_id[i])
+			ida_free(&mmu_context_ida, ctx->extended_id[i]);
+	}
+
+	return id;
+}
+
 static int hash__init_new_context(struct mm_struct *mm)
 {
 	int index;
 
-	index = hash__alloc_context_id();
-	if (index < 0)
-		return index;
+	mm->context.hash_context = kmalloc(sizeof(struct hash_mm_context),
+					   GFP_KERNEL);
+	if (!mm->context.hash_context)
+		return -ENOMEM;
 
 	/*
 	 * The old code would re-promote on fork, we don't do that when using
@@ -75,15 +111,45 @@
 	 * We should not be calling init_new_context() on init_mm. Hence a
 	 * check against 0 is OK.
 	 */
-	if (mm->context.id == 0)
+	if (mm->context.id == 0) {
+		memset(mm->context.hash_context, 0, sizeof(struct hash_mm_context));
 		slice_init_new_context_exec(mm);
+	} else {
+		/* This is fork. Copy hash_context details from current->mm */
+		memcpy(mm->context.hash_context, current->mm->context.hash_context, sizeof(struct hash_mm_context));
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+		/* inherit subpage prot detalis if we have one. */
+		if (current->mm->context.hash_context->spt) {
+			mm->context.hash_context->spt = kmalloc(sizeof(struct subpage_prot_table),
+								GFP_KERNEL);
+			if (!mm->context.hash_context->spt) {
+				kfree(mm->context.hash_context);
+				return -ENOMEM;
+			}
+		}
+#endif
+	}
 
-	subpage_prot_init_new_context(mm);
+	index = realloc_context_ids(&mm->context);
+	if (index < 0) {
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+		kfree(mm->context.hash_context->spt);
+#endif
+		kfree(mm->context.hash_context);
+		return index;
+	}
 
 	pkey_mm_init(mm);
 	return index;
 }
 
+void hash__setup_new_exec(void)
+{
+	slice_setup_new_exec();
+
+	slb_setup_new_exec();
+}
+
 static int radix__init_new_context(struct mm_struct *mm)
 {
 	unsigned long rts_field;
@@ -108,7 +174,7 @@
 	 */
 	asm volatile("ptesync;isync" : : : "memory");
 
-	mm->context.npu_context = NULL;
+	mm->context.hash_context = NULL;
 
 	return index;
 }
@@ -153,21 +219,7 @@
 		if (context_id)
 			ida_free(&mmu_context_ida, context_id);
 	}
-}
-
-static void pte_frag_destroy(void *pte_frag)
-{
-	int count;
-	struct page *page;
-
-	page = virt_to_page(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_page_dtor(page);
-		__free_page(page);
-	}
+	kfree(ctx->hash_context);
 }
 
 static void pmd_frag_destroy(void *pmd_frag)
@@ -204,8 +256,21 @@
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 	WARN_ON_ONCE(!list_empty(&mm->context.iommu_group_mem_list));
 #endif
+	/*
+	 * For tasks which were successfully initialized we end up calling
+	 * arch_exit_mmap() which clears the process table entry. And
+	 * arch_exit_mmap() is called before the required fullmm TLB flush
+	 * which does a RIC=2 flush. Hence for an initialized task, we do clear
+	 * any cached process table entries.
+	 *
+	 * The condition below handles the error case during task init. We have
+	 * set the process table entry early and if we fail a task
+	 * initialization, we need to ensure the process table entry is zeroed.
+	 * We need not worry about process table entry caches because the task
+	 * never ran with the PID value.
+	 */
 	if (radix_enabled())
-		WARN_ON(process_tb[mm->context.id].prtb0 != 0);
+		process_tb[mm->context.id].prtb0 = 0;
 	else
 		subpage_prot_free(mm);
 	destroy_contexts(&mm->context);
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/book3s64/pgtable.c
similarity index 66%
rename from arch/powerpc/mm/pgtable-book3s64.c
rename to arch/powerpc/mm/book3s64/pgtable.c
index 01d7c0f..75483b4 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2015-2016, Aneesh Kumar K.V, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/sched.h>
@@ -12,12 +8,15 @@
 #include <linux/memblock.h>
 #include <misc/cxl-base.h>
 
+#include <asm/debugfs.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/trace.h>
 #include <asm/powernv.h>
+#include <asm/firmware.h>
+#include <asm/ultravisor.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 #include <trace/events/thp.h>
 
 unsigned long __pmd_frag_nr;
@@ -25,9 +24,6 @@
 unsigned long __pmd_frag_size_shift;
 EXPORT_SYMBOL(__pmd_frag_size_shift);
 
-int (*register_process_table)(unsigned long base, unsigned long page_size,
-			      unsigned long tbl_size);
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * This is called when relaxing access to a hugepage. It's also called in the page
@@ -69,9 +65,14 @@
 		pmd_t *pmdp, pmd_t pmd)
 {
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(pte_present(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
+	/*
+	 * Make sure hardware valid bit is not set. We don't do
+	 * tlb flush for this update.
+	 */
+
+	WARN_ON(pte_hw_valid(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
-	WARN_ON(!(pmd_trans_huge(pmd) || pmd_devmap(pmd)));
+	WARN_ON(!(pmd_large(pmd)));
 #endif
 	trace_hugepage_set_pmd(addr, pmd_val(pmd));
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
@@ -106,11 +107,14 @@
 {
 	unsigned long old_pmd;
 
-	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
+	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID);
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	/*
 	 * This ensures that generic code that rely on IRQ disabling
 	 * to prevent a parallel THP split work as expected.
+	 *
+	 * Marking the entry with _PAGE_INVALID && ~_PAGE_PRESENT requires
+	 * a special case check in pmd_access_permitted.
 	 */
 	serialize_against_pte_lookup(vma->vm_mm);
 	return __pmd(old_pmd);
@@ -190,48 +194,72 @@
 	unsigned long ptcr;
 
 	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large.");
-	partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
-						MEMBLOCK_ALLOC_ANYWHERE));
-
 	/* Initialize the Partition Table with no entries */
-	memset((void *)partition_tb, 0, patb_size);
+	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);
 
 	/*
 	 * update partition table control register,
 	 * 64 K size.
 	 */
 	ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12);
-	mtspr(SPRN_PTCR, ptcr);
+	set_ptcr_when_no_uv(ptcr);
 	powernv_set_nmmu_ptcr(ptcr);
 }
 
+static void flush_partition(unsigned int lpid, bool radix)
+{
+	if (radix) {
+		radix__flush_all_lpid(lpid);
+		radix__flush_all_lpid_guest(lpid);
+	} else {
+		asm volatile("ptesync" : : : "memory");
+		asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
+			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
+		/* do we need fixup here ?*/
+		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
+	}
+}
+
 void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
-				   unsigned long dw1)
+				  unsigned long dw1, bool flush)
 {
 	unsigned long old = be64_to_cpu(partition_tb[lpid].patb0);
 
+	/*
+	 * When ultravisor is enabled, the partition table is stored in secure
+	 * memory and can only be accessed doing an ultravisor call. However, we
+	 * maintain a copy of the partition table in normal memory to allow Nest
+	 * MMU translations to occur (for normal VMs).
+	 *
+	 * Therefore, here we always update partition_tb, regardless of whether
+	 * we are running under an ultravisor or not.
+	 */
 	partition_tb[lpid].patb0 = cpu_to_be64(dw0);
 	partition_tb[lpid].patb1 = cpu_to_be64(dw1);
 
 	/*
-	 * Global flush of TLBs and partition table caches for this lpid.
-	 * The type of flush (hash or radix) depends on what the previous
-	 * use of this partition ID was, not the new use.
+	 * If ultravisor is enabled, we do an ultravisor call to register the
+	 * partition table entry (PATE), which also do a global flush of TLBs
+	 * and partition table caches for the lpid. Otherwise, just do the
+	 * flush. The type of flush (hash or radix) depends on what the previous
+	 * use of the partition ID was, not the new use.
 	 */
-	asm volatile("ptesync" : : : "memory");
-	if (old & PATB_HR) {
-		asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : :
-			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
-		asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
-			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
-		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1);
-	} else {
-		asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
-			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
-		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
+	if (firmware_has_feature(FW_FEATURE_ULTRAVISOR)) {
+		uv_register_pate(lpid, dw0, dw1);
+		pr_info("PATE registered by ultravisor: dw0 = 0x%lx, dw1 = 0x%lx\n",
+			dw0, dw1);
+	} else if (flush) {
+		/*
+		 * Boot does not need to flush, because MMU is off and each
+		 * CPU does a tlbiel_all() before switching them on, which
+		 * flushes everything.
+		 */
+		flush_partition(lpid, (old & PATB_HR));
 	}
-	/* do we need fixup here ?*/
-	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
 
@@ -239,6 +267,9 @@
 {
 	void *pmd_frag, *ret;
 
+	if (PMD_FRAG_NR == 1)
+		return NULL;
+
 	spin_lock(&mm->page_table_lock);
 	ret = mm->context.pmd_frag;
 	if (ret) {
@@ -317,91 +348,6 @@
 	}
 }
 
-static pte_t *get_pte_from_cache(struct mm_struct *mm)
-{
-	void *pte_frag, *ret;
-
-	spin_lock(&mm->page_table_lock);
-	ret = mm->context.pte_frag;
-	if (ret) {
-		pte_frag = ret + PTE_FRAG_SIZE;
-		/*
-		 * If we have taken up all the fragments mark PTE page NULL
-		 */
-		if (((unsigned long)pte_frag & ~PAGE_MASK) == 0)
-			pte_frag = NULL;
-		mm->context.pte_frag = pte_frag;
-	}
-	spin_unlock(&mm->page_table_lock);
-	return (pte_t *)ret;
-}
-
-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_page_ctor(page)) {
-			__free_page(page);
-			return NULL;
-		}
-	} else {
-		page = alloc_page(PGALLOC_GFP);
-		if (!page)
-			return NULL;
-	}
-
-	atomic_set(&page->pt_frag_refcount, 1);
-
-	ret = page_address(page);
-	/*
-	 * if we support only one fragment just return the
-	 * allocated page.
-	 */
-	if (PTE_FRAG_NR == 1)
-		return ret;
-	spin_lock(&mm->page_table_lock);
-	/*
-	 * If we find pgtable_page set, we return
-	 * the allocated page with single fragement
-	 * count.
-	 */
-	if (likely(!mm->context.pte_frag)) {
-		atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR);
-		mm->context.pte_frag = ret + PTE_FRAG_SIZE;
-	}
-	spin_unlock(&mm->page_table_lock);
-
-	return (pte_t *)ret;
-}
-
-pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel)
-{
-	pte_t *pte;
-
-	pte = get_pte_from_cache(mm);
-	if (pte)
-		return pte;
-
-	return __alloc_for_ptecache(mm, kernel);
-}
-
-void pte_fragment_free(unsigned long *table, int kernel)
-{
-	struct page *page = virt_to_page(table);
-
-	BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0);
-	if (atomic_dec_and_test(&page->pt_frag_refcount)) {
-		if (!kernel)
-			pgtable_page_dtor(page);
-		__free_page(page);
-	}
-}
-
 static inline void pgtable_free(void *table, int index)
 {
 	switch (index) {
@@ -477,3 +423,96 @@
 		   atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20);
 }
 #endif /* CONFIG_PROC_FS */
+
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep)
+{
+	unsigned long pte_val;
+
+	/*
+	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
+	 * possible. Also keep the pte_present true so that we don't take
+	 * wrong fault.
+	 */
+	pte_val = pte_update(vma->vm_mm, addr, ptep, _PAGE_PRESENT, _PAGE_INVALID, 0);
+
+	return __pte(pte_val);
+
+}
+
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t *ptep, pte_t old_pte, pte_t pte)
+{
+	if (radix_enabled())
+		return radix__ptep_modify_prot_commit(vma, addr,
+						      ptep, old_pte, pte);
+	set_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+
+/*
+ * 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
+ * location. Hence a pmd move requires deposit and withdraw.
+ *
+ * For radix translation with split pmd ptl, we store the deposited table in the
+ * pmd page. Hence if we have different pmd page we need to withdraw during pmd
+ * move.
+ *
+ * With hash we use deposited table always irrespective of anon or not.
+ * With radix we use deposited table only for anonymous mapping.
+ */
+int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
+			   struct spinlock *old_pmd_ptl,
+			   struct vm_area_struct *vma)
+{
+	if (radix_enabled())
+		return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma);
+
+	return true;
+}
+
+/*
+ * Does the CPU support tlbie?
+ */
+bool tlbie_capable __read_mostly = true;
+EXPORT_SYMBOL(tlbie_capable);
+
+/*
+ * Should tlbie be used for management of CPU TLBs, for kernel and process
+ * address spaces? tlbie may still be used for nMMU accelerators, and for KVM
+ * guest address spaces.
+ */
+bool tlbie_enabled __read_mostly = true;
+
+static int __init setup_disable_tlbie(char *str)
+{
+	if (!radix_enabled()) {
+		pr_err("disable_tlbie: Unable to disable TLBIE with Hash MMU.\n");
+		return 1;
+	}
+
+	tlbie_capable = false;
+	tlbie_enabled = false;
+
+        return 1;
+}
+__setup("disable_tlbie", setup_disable_tlbie);
+
+static int __init pgtable_debugfs_setup(void)
+{
+	if (!tlbie_capable)
+		return 0;
+
+	/*
+	 * There is no locking vs tlb flushing when changing this value.
+	 * The tlb flushers will see one value or another, and use either
+	 * tlbie or tlbiel with IPIs. In both cases the TLBs will be
+	 * invalidated as expected.
+	 */
+	debugfs_create_bool("tlbie_enabled", 0600,
+			powerpc_debugfs_root,
+			&tlbie_enabled);
+
+	return 0;
+}
+arch_initcall(pgtable_debugfs_setup);
diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
similarity index 93%
rename from arch/powerpc/mm/pkeys.c
rename to arch/powerpc/mm/book3s64/pkeys.c
index b271b28..ae7fca4 100644
--- a/arch/powerpc/mm/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -6,20 +6,22 @@
  */
 
 #include <asm/mman.h>
+#include <asm/mmu_context.h>
+#include <asm/mmu.h>
 #include <asm/setup.h>
 #include <linux/pkeys.h>
 #include <linux/of_device.h>
 
 DEFINE_STATIC_KEY_TRUE(pkey_disabled);
-bool pkey_execute_disable_supported;
 int  pkeys_total;		/* Total pkeys as per device tree */
-bool pkeys_devtree_defined;	/* pkey property exported by device tree */
 u32  initial_allocation_mask;   /* Bits set for the initially allocated keys */
 u32  reserved_allocation_mask;  /* Bits set for reserved keys */
-u64  pkey_amr_mask;		/* Bits in AMR not to be touched */
-u64  pkey_iamr_mask;		/* Bits in AMR not to be touched */
-u64  pkey_uamor_mask;		/* Bits in UMOR not to be touched */
-int  execute_only_key = 2;
+static bool pkey_execute_disable_supported;
+static bool pkeys_devtree_defined;	/* property exported by device tree */
+static u64 pkey_amr_mask;		/* Bits in AMR not to be touched */
+static u64 pkey_iamr_mask;		/* Bits in AMR not to be touched */
+static u64 pkey_uamor_mask;		/* Bits in UMOR not to be touched */
+static int execute_only_key = 2;
 
 #define AMR_BITS_PER_PKEY 2
 #define AMR_RD_BIT 0x1UL
@@ -57,7 +59,7 @@
 		return cpu_has_feature(CPU_FTR_PKEY);
 }
 
-int pkey_initialize(void)
+static int pkey_initialize(void)
 {
 	int os_reserved, i;
 
@@ -414,3 +416,13 @@
 
 	return pkey_access_permitted(vma_pkey(vma), write, execute);
 }
+
+void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+	if (static_branch_likely(&pkey_disabled))
+		return;
+
+	/* Duplicate the oldmm pkey state in mm: */
+	mm_pkey_allocation_map(mm) = mm_pkey_allocation_map(oldmm);
+	mm->context.execute_only_pkey = oldmm->context.execute_only_pkey;
+}
diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
similarity index 78%
rename from arch/powerpc/mm/hugetlbpage-radix.c
rename to arch/powerpc/mm/book3s64/radix_hugetlbpage.c
index 2486bee..cab0633 100644
--- a/arch/powerpc/mm/hugetlbpage-radix.c
+++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
+#include <linux/security.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
@@ -73,7 +74,7 @@
 	if (addr) {
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
-		if (high_limit - len >= addr &&
+		if (high_limit - len >= addr && addr >= mmap_min_addr &&
 		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
@@ -83,10 +84,27 @@
 	 */
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
-	info.low_limit = PAGE_SIZE;
+	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
 	info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW);
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 
 	return vm_unmapped_area(&info);
 }
+
+void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t pte)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	/*
+	 * To avoid NMMU hang while relaxing access we need to flush the tlb before
+	 * we set the new value.
+	 */
+	if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		radix__flush_hugetlb_page(vma, addr);
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
similarity index 77%
rename from arch/powerpc/mm/pgtable-radix.c
rename to arch/powerpc/mm/book3s64/radix_pgtable.c
index c879979..6ee17d0 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1,16 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Page table handling routines for radix page table.
  *
  * Copyright 2015-2016, Aneesh Kumar K.V, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "radix-mmu: " fmt
 
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/sched/mm.h>
 #include <linux/memblock.h>
@@ -29,48 +26,33 @@
 #include <asm/powernv.h>
 #include <asm/sections.h>
 #include <asm/trace.h>
+#include <asm/uaccess.h>
+#include <asm/ultravisor.h>
 
 #include <trace/events/thp.h>
 
 unsigned int mmu_pid_bits;
 unsigned int mmu_base_pid;
 
-static int native_register_process_table(unsigned long base, unsigned long pg_sz,
-					 unsigned long table_size)
-{
-	unsigned long patb0, patb1;
-
-	patb0 = be64_to_cpu(partition_tb[0].patb0);
-	patb1 = base | table_size | PATB_GR;
-
-	mmu_partition_table_set_entry(0, patb0, patb1);
-
-	return 0;
-}
-
 static __ref void *early_alloc_pgtable(unsigned long size, int nid,
 			unsigned long region_start, unsigned long region_end)
 {
-	unsigned long pa = 0;
-	void *pt;
+	phys_addr_t min_addr = MEMBLOCK_LOW_LIMIT;
+	phys_addr_t max_addr = MEMBLOCK_ALLOC_ANYWHERE;
+	void *ptr;
 
-	if (region_start || region_end) /* has region hint */
-		pa = memblock_alloc_range(size, size, region_start, region_end,
-						MEMBLOCK_NONE);
-	else if (nid != -1) /* has node hint */
-		pa = memblock_alloc_base_nid(size, size,
-						MEMBLOCK_ALLOC_ANYWHERE,
-						nid, MEMBLOCK_NONE);
+	if (region_start)
+		min_addr = region_start;
+	if (region_end)
+		max_addr = region_end;
 
-	if (!pa)
-		pa = memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE);
+	ptr = memblock_alloc_try_nid(size, size, min_addr, max_addr, nid);
 
-	BUG_ON(!pa);
+	if (!ptr)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%pa max_addr=%pa\n",
+		      __func__, size, size, nid, &min_addr, &max_addr);
 
-	pt = __va(pa);
-	memset(pt, 0, size);
-
-	return pt;
+	return ptr;
 }
 
 static int early_map_kernel_page(unsigned long ea, unsigned long pa,
@@ -139,6 +121,10 @@
 	 */
 	BUILD_BUG_ON(TASK_SIZE_USER64 > RADIX_PGTABLE_RANGE);
 
+#ifdef CONFIG_PPC_64K_PAGES
+	BUILD_BUG_ON(RADIX_KERN_MAP_SIZE != (1UL << MAX_EA_BITS_PER_CONTEXT));
+#endif
+
 	if (unlikely(!slab_is_available()))
 		return early_map_kernel_page(ea, pa, flags, map_page_size,
 						nid, region_start, region_end);
@@ -201,14 +187,14 @@
 		pudp = pud_alloc(&init_mm, pgdp, idx);
 		if (!pudp)
 			continue;
-		if (pud_huge(*pudp)) {
+		if (pud_is_leaf(*pudp)) {
 			ptep = (pte_t *)pudp;
 			goto update_the_pte;
 		}
 		pmdp = pmd_alloc(&init_mm, pudp, idx);
 		if (!pmdp)
 			continue;
-		if (pmd_huge(*pmdp)) {
+		if (pmd_is_leaf(*pmdp)) {
 			ptep = pmdp_ptep(pmdp);
 			goto update_the_pte;
 		}
@@ -241,9 +227,8 @@
 }
 #endif /* CONFIG_STRICT_KERNEL_RWX */
 
-static inline void __meminit print_mapping(unsigned long start,
-					   unsigned long end,
-					   unsigned long size)
+static inline void __meminit
+print_mapping(unsigned long start, unsigned long end, unsigned long size, bool exec)
 {
 	char buf[10];
 
@@ -252,7 +237,17 @@
 
 	string_get_size(size, 1, STRING_UNITS_2, buf, sizeof(buf));
 
-	pr_info("Mapped 0x%016lx-0x%016lx with %s pages\n", start, end, buf);
+	pr_info("Mapped 0x%016lx-0x%016lx with %s pages%s\n", start, end, buf,
+		exec ? " (exec)" : "");
+}
+
+static unsigned long next_boundary(unsigned long addr, unsigned long end)
+{
+#ifdef CONFIG_STRICT_KERNEL_RWX
+	if (addr < __pa_symbol(__init_begin))
+		return __pa_symbol(__init_begin);
+#endif
+	return end;
 }
 
 static int __meminit create_physical_mapping(unsigned long start,
@@ -260,13 +255,8 @@
 					     int nid)
 {
 	unsigned long vaddr, addr, mapping_size = 0;
+	bool prev_exec, exec = false;
 	pgprot_t prot;
-	unsigned long max_mapping_size;
-#ifdef CONFIG_STRICT_KERNEL_RWX
-	int split_text_mapping = 1;
-#else
-	int split_text_mapping = 0;
-#endif
 	int psize;
 
 	start = _ALIGN_UP(start, PAGE_SIZE);
@@ -274,14 +264,12 @@
 		unsigned long gap, previous_size;
 		int rc;
 
-		gap = end - addr;
+		gap = next_boundary(addr, end) - addr;
 		previous_size = mapping_size;
-		max_mapping_size = PUD_SIZE;
+		prev_exec = exec;
 
-retry:
 		if (IS_ALIGNED(addr, PUD_SIZE) && gap >= PUD_SIZE &&
-		    mmu_psize_defs[MMU_PAGE_1G].shift &&
-		    PUD_SIZE <= max_mapping_size) {
+		    mmu_psize_defs[MMU_PAGE_1G].shift) {
 			mapping_size = PUD_SIZE;
 			psize = MMU_PAGE_1G;
 		} else if (IS_ALIGNED(addr, PMD_SIZE) && gap >= PMD_SIZE &&
@@ -293,32 +281,21 @@
 			psize = mmu_virtual_psize;
 		}
 
-		if (split_text_mapping && (mapping_size == PUD_SIZE) &&
-			(addr <= __pa_symbol(__init_begin)) &&
-			(addr + mapping_size) >= __pa_symbol(_stext)) {
-			max_mapping_size = PMD_SIZE;
-			goto retry;
-		}
-
-		if (split_text_mapping && (mapping_size == PMD_SIZE) &&
-		    (addr <= __pa_symbol(__init_begin)) &&
-		    (addr + mapping_size) >= __pa_symbol(_stext)) {
-			mapping_size = PAGE_SIZE;
-			psize = mmu_virtual_psize;
-		}
-
-		if (mapping_size != previous_size) {
-			print_mapping(start, addr, previous_size);
-			start = addr;
-		}
-
 		vaddr = (unsigned long)__va(addr);
 
 		if (overlaps_kernel_text(vaddr, vaddr + mapping_size) ||
-		    overlaps_interrupt_vector_text(vaddr, vaddr + mapping_size))
+		    overlaps_interrupt_vector_text(vaddr, vaddr + mapping_size)) {
 			prot = PAGE_KERNEL_X;
-		else
+			exec = true;
+		} else {
 			prot = PAGE_KERNEL;
+			exec = false;
+		}
+
+		if (mapping_size != previous_size || exec != prev_exec) {
+			print_mapping(start, addr, previous_size, prev_exec);
+			start = addr;
+		}
 
 		rc = __map_kernel_page(vaddr, addr, prot, mapping_size, nid, start, end);
 		if (rc)
@@ -327,11 +304,11 @@
 		update_page_count(psize, 1);
 	}
 
-	print_mapping(start, addr, mapping_size);
+	print_mapping(start, addr, mapping_size, exec);
 	return 0;
 }
 
-void __init radix_init_pgtable(void)
+static void __init radix_init_pgtable(void)
 {
 	unsigned long rts_field;
 	struct memblock_region *reg;
@@ -347,6 +324,12 @@
 		 * page tables will be allocated within the range. No
 		 * need or a node (which we don't have yet).
 		 */
+
+		if ((reg->base + reg->size) >= RADIX_VMALLOC_START) {
+			pr_warn("Outside the supported range\n");
+			continue;
+		}
+
 		WARN_ON(create_physical_mapping(reg->base,
 						reg->base + reg->size,
 						-1));
@@ -385,18 +368,6 @@
 	 */
 	rts_field = radix__get_tree_size();
 	process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE);
-	/*
-	 * Fill in the partition table. We are suppose to use effective address
-	 * of process table here. But our linear mapping also enable us to use
-	 * physical address here.
-	 */
-	register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
-	pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
-	asm volatile("ptesync" : : : "memory");
-	asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
-		     "r" (TLBIEL_INVAL_SET_LPID), "r" (0));
-	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-	trace_tlbie(0, 0, TLBIEL_INVAL_SET_LPID, 0, 2, 1, 1);
 
 	/*
 	 * The init_mm context is given the first available (non-zero) PID,
@@ -417,20 +388,15 @@
 
 static void __init radix_init_partition_table(void)
 {
-	unsigned long rts_field, dw0;
+	unsigned long rts_field, dw0, dw1;
 
 	mmu_partition_table_init();
 	rts_field = radix__get_tree_size();
 	dw0 = rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE | PATB_HR;
-	mmu_partition_table_set_entry(0, dw0, 0);
+	dw1 = __pa(process_tb) | (PRTB_SIZE_SHIFT - 12) | PATB_GR;
+	mmu_partition_table_set_entry(0, dw0, dw1, false);
 
 	pr_info("Initializing Radix MMU\n");
-	pr_info("Partition table %p\n", partition_tb);
-}
-
-void __init radix_init_native(void)
-{
-	register_process_table = native_register_process_table;
 }
 
 static int __init get_idx_from_shift(unsigned int shift)
@@ -521,14 +487,6 @@
 	mmu_psize_defs[MMU_PAGE_64K].shift = 16;
 	mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
 found:
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-	if (mmu_psize_defs[MMU_PAGE_2M].shift) {
-		/*
-		 * map vmemmap using 2M if available
-		 */
-		mmu_vmemmap_psize = MMU_PAGE_2M;
-	}
-#endif /* CONFIG_SPARSEMEM_VMEMMAP */
 	return;
 }
 
@@ -544,8 +502,15 @@
 	mtspr(SPRN_AMOR, (3ul << 62));
 }
 
-static void radix_init_iamr(void)
+#ifdef CONFIG_PPC_KUEP
+void setup_kuep(bool disabled)
 {
+	if (disabled || !early_radix_enabled())
+		return;
+
+	if (smp_processor_id() == boot_cpuid)
+		pr_info("Activating Kernel Userspace Execution Prevention\n");
+
 	/*
 	 * Radix always uses key0 of the IAMR to determine if an access is
 	 * allowed. We set bit 0 (IBM bit 1) of key0, to prevent instruction
@@ -553,6 +518,25 @@
 	 */
 	mtspr(SPRN_IAMR, (1ul << 62));
 }
+#endif
+
+#ifdef CONFIG_PPC_KUAP
+void setup_kuap(bool disabled)
+{
+	if (disabled || !early_radix_enabled())
+		return;
+
+	if (smp_processor_id() == boot_cpuid) {
+		pr_info("Activating Kernel Userspace Access Prevention\n");
+		cur_cpu_spec->mmu_features |= MMU_FTR_RADIX_KUAP;
+	}
+
+	/* Make sure userspace can't change the AMR */
+	mtspr(SPRN_UAMOR, 0);
+	mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
+	isync();
+}
+#endif
 
 void __init radix__early_init_mmu(void)
 {
@@ -567,7 +551,13 @@
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	/* vmemmap mapping */
-	mmu_vmemmap_psize = mmu_virtual_psize;
+	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
 	/*
 	 * initialize page table size
@@ -587,11 +577,11 @@
 	__pgd_val_bits = RADIX_PGD_VAL_BITS;
 
 	__kernel_virt_start = RADIX_KERN_VIRT_START;
-	__kernel_virt_size = RADIX_KERN_VIRT_SIZE;
 	__vmalloc_start = RADIX_VMALLOC_START;
 	__vmalloc_end = RADIX_VMALLOC_END;
 	__kernel_io_start = RADIX_KERN_IO_START;
-	vmemmap = (struct page *)RADIX_VMEMMAP_BASE;
+	__kernel_io_end = RADIX_KERN_IO_END;
+	vmemmap = (struct page *)RADIX_VMEMMAP_START;
 	ioremap_bot = IOREMAP_BASE;
 
 #ifdef CONFIG_PCI
@@ -602,8 +592,9 @@
 	__pmd_frag_nr = RADIX_PMD_FRAG_NR;
 	__pmd_frag_size_shift = RADIX_PMD_FRAG_SIZE_SHIFT;
 
+	radix_init_pgtable();
+
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
-		radix_init_native();
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 		radix_init_partition_table();
@@ -614,12 +605,9 @@
 
 	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 
-	radix_init_iamr();
-	radix_init_pgtable();
 	/* Switch to the guard PID before turning on MMU */
 	radix__switch_mmu_context(NULL, &init_mm);
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		tlbiel_all();
+	tlbiel_all();
 }
 
 void radix__early_init_mmu_secondary(void)
@@ -632,15 +620,14 @@
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 
-		mtspr(SPRN_PTCR,
-		      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+		set_ptcr_when_no_uv(__pa(partition_tb) |
+				    (PATB_SIZE_SHIFT - 12));
+
 		radix_init_amor();
 	}
-	radix_init_iamr();
 
 	radix__switch_mmu_context(NULL, &init_mm);
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		tlbiel_all();
+	tlbiel_all();
 }
 
 void radix__mmu_cleanup_all(void)
@@ -650,7 +637,7 @@
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr & ~LPCR_UPRT);
-		mtspr(SPRN_PTCR, 0);
+		set_ptcr_when_no_uv(0);
 		powernv_set_nmmu_ptcr(0);
 		radix__flush_tlb_all();
 	}
@@ -659,7 +646,8 @@
 void radix__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
+	/*
+	 * We don't currently support the first MEMBLOCK not mapping 0
 	 * physical on those processors
 	 */
 	BUG_ON(first_memblock_base != 0);
@@ -719,8 +707,8 @@
 
 	spin_unlock(&init_mm.page_table_lock);
 	pte_clear(&init_mm, params->aligned_start, params->pte);
-	create_physical_mapping(params->aligned_start, params->start, -1);
-	create_physical_mapping(params->end, params->aligned_end, -1);
+	create_physical_mapping(__pa(params->aligned_start), __pa(params->start), -1);
+	create_physical_mapping(__pa(params->end), __pa(params->aligned_end), -1);
 	spin_lock(&init_mm.page_table_lock);
 	return 0;
 }
@@ -813,7 +801,7 @@
 		if (!pmd_present(*pmd))
 			continue;
 
-		if (pmd_huge(*pmd)) {
+		if (pmd_is_leaf(*pmd)) {
 			split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd);
 			continue;
 		}
@@ -838,7 +826,7 @@
 		if (!pud_present(*pud))
 			continue;
 
-		if (pud_huge(*pud)) {
+		if (pud_is_leaf(*pud)) {
 			split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud);
 			continue;
 		}
@@ -864,7 +852,7 @@
 		if (!pgd_present(*pgd))
 			continue;
 
-		if (pgd_huge(*pgd)) {
+		if (pgd_is_leaf(*pgd)) {
 			split_kernel_mapping(addr, end, PGDIR_SIZE, (pte_t *)pgd);
 			continue;
 		}
@@ -879,7 +867,12 @@
 
 int __meminit radix__create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
-	return create_physical_mapping(start, end, nid);
+	if (end >= RADIX_VMALLOC_START) {
+		pr_warn("Outside the supported range\n");
+		return -1;
+	}
+
+	return create_physical_mapping(__pa(start), __pa(end), nid);
 }
 
 int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
@@ -906,6 +899,11 @@
 	int nid = early_pfn_to_nid(phys >> PAGE_SHIFT);
 	int ret;
 
+	if ((start + page_size) >= RADIX_VMEMMAP_END) {
+		pr_warn("Outside the supported range\n");
+		return -1;
+	}
+
 	ret = __map_kernel_page_nid(start, phys, __pgprot(flags), page_size, nid);
 	BUG_ON(ret);
 
@@ -971,45 +969,44 @@
 void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				 pgtable_t pgtable)
 {
-        struct list_head *lh = (struct list_head *) pgtable;
+	struct list_head *lh = (struct list_head *) pgtable;
 
-        assert_spin_locked(pmd_lockptr(mm, pmdp));
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
-        /* FIFO */
-        if (!pmd_huge_pte(mm, pmdp))
-                INIT_LIST_HEAD(lh);
-        else
-                list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
-        pmd_huge_pte(mm, pmdp) = pgtable;
+	/* FIFO */
+	if (!pmd_huge_pte(mm, pmdp))
+		INIT_LIST_HEAD(lh);
+	else
+		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
+	pmd_huge_pte(mm, pmdp) = pgtable;
 }
 
 pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
-        pte_t *ptep;
-        pgtable_t pgtable;
-        struct list_head *lh;
+	pte_t *ptep;
+	pgtable_t pgtable;
+	struct list_head *lh;
 
-        assert_spin_locked(pmd_lockptr(mm, pmdp));
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
-        /* FIFO */
-        pgtable = pmd_huge_pte(mm, pmdp);
-        lh = (struct list_head *) pgtable;
-        if (list_empty(lh))
-                pmd_huge_pte(mm, pmdp) = NULL;
-        else {
-                pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
-                list_del(lh);
-        }
-        ptep = (pte_t *) pgtable;
-        *ptep = __pte(0);
-        ptep++;
-        *ptep = __pte(0);
-        return pgtable;
+	/* FIFO */
+	pgtable = pmd_huge_pte(mm, pmdp);
+	lh = (struct list_head *) pgtable;
+	if (list_empty(lh))
+		pmd_huge_pte(mm, pmdp) = NULL;
+	else {
+		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
+		list_del(lh);
+	}
+	ptep = (pte_t *) pgtable;
+	*ptep = __pte(0);
+	ptep++;
+	*ptep = __pte(0);
+	return pgtable;
 }
 
-
 pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
-			       unsigned long addr, pmd_t *pmdp)
+				     unsigned long addr, pmd_t *pmdp)
 {
 	pmd_t old_pmd;
 	unsigned long old;
@@ -1030,13 +1027,6 @@
 	return old_pmd;
 }
 
-int radix__has_transparent_hugepage(void)
-{
-	/* For radix 2M at PMD level means thp */
-	if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT)
-		return 1;
-	return 0;
-}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
@@ -1072,3 +1062,126 @@
 	}
 	/* See ptesync comment in radix__set_pte_at */
 }
+
+void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep,
+				    pte_t old_pte, pte_t pte)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	/*
+	 * To avoid NMMU hang while relaxing access we need to flush the tlb before
+	 * we set the new value. We need to do this only for radix, because hash
+	 * translation does flush when updating the linux pte.
+	 */
+	if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
+	    (atomic_read(&mm->context.copros) > 0))
+		radix__flush_tlb_page(vma, addr);
+
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+int __init arch_ioremap_pud_supported(void)
+{
+	/* HPT does not cope with large pages in the vmalloc area */
+	return radix_enabled();
+}
+
+int __init arch_ioremap_pmd_supported(void)
+{
+	return radix_enabled();
+}
+
+int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
+{
+	return 0;
+}
+
+int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
+{
+	pte_t *ptep = (pte_t *)pud;
+	pte_t new_pud = pfn_pte(__phys_to_pfn(addr), prot);
+
+	if (!radix_enabled())
+		return 0;
+
+	set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pud);
+
+	return 1;
+}
+
+int pud_clear_huge(pud_t *pud)
+{
+	if (pud_huge(*pud)) {
+		pud_clear(pud);
+		return 1;
+	}
+
+	return 0;
+}
+
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
+{
+	pmd_t *pmd;
+	int i;
+
+	pmd = (pmd_t *)pud_page_vaddr(*pud);
+	pud_clear(pud);
+
+	flush_tlb_kernel_range(addr, addr + PUD_SIZE);
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(pmd[i])) {
+			pte_t *pte;
+			pte = (pte_t *)pmd_page_vaddr(pmd[i]);
+
+			pte_free_kernel(&init_mm, pte);
+		}
+	}
+
+	pmd_free(&init_mm, pmd);
+
+	return 1;
+}
+
+int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
+{
+	pte_t *ptep = (pte_t *)pmd;
+	pte_t new_pmd = pfn_pte(__phys_to_pfn(addr), prot);
+
+	if (!radix_enabled())
+		return 0;
+
+	set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pmd);
+
+	return 1;
+}
+
+int pmd_clear_huge(pmd_t *pmd)
+{
+	if (pmd_huge(*pmd)) {
+		pmd_clear(pmd);
+		return 1;
+	}
+
+	return 0;
+}
+
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+{
+	pte_t *pte;
+
+	pte = (pte_t *)pmd_page_vaddr(*pmd);
+	pmd_clear(pmd);
+
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+
+	pte_free_kernel(&init_mm, pte);
+
+	return 1;
+}
+
+int __init arch_ioremap_p4d_supported(void)
+{
+	return 0;
+}
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/book3s64/radix_tlb.c
similarity index 72%
rename from arch/powerpc/mm/tlb-radix.c
rename to arch/powerpc/mm/book3s64/radix_tlb.c
index fef3e1e..67af871 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * TLB flush routines for radix kernels.
  *
  * Copyright 2015-2016, Aneesh Kumar K.V, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/mm.h>
@@ -29,7 +25,7 @@
  * tlbiel instruction for radix, set invalidation
  * i.e., r=1 and is=01 or is=10 or is=11
  */
-static inline void tlbiel_radix_set_isa300(unsigned int set, unsigned int is,
+static __always_inline void tlbiel_radix_set_isa300(unsigned int set, unsigned int is,
 					unsigned int pid,
 					unsigned int ric, unsigned int prs)
 {
@@ -55,11 +51,15 @@
 	 * and partition table entries. Then flush the remaining sets of the
 	 * TLB.
 	 */
-	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0);
-	for (set = 1; set < num_sets; set++)
-		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0);
 
-	/* Do the same for process scoped entries. */
+	if (early_cpu_has_feature(CPU_FTR_HVMODE)) {
+		/* MSR[HV] should flush partition scope translations first. */
+		tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0);
+		for (set = 1; set < num_sets; set++)
+			tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0);
+	}
+
+	/* Flush process scoped entries. */
 	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 1);
 	for (set = 1; set < num_sets; set++)
 		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1);
@@ -87,10 +87,10 @@
 	else
 		WARN(1, "%s called on pre-POWER9 CPU\n", __func__);
 
-	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+	asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory");
 }
 
-static inline void __tlbiel_pid(unsigned long pid, int set,
+static __always_inline void __tlbiel_pid(unsigned long pid, int set,
 				unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
@@ -106,7 +106,7 @@
 	trace_tlbie(0, 1, rb, rs, ric, prs, r);
 }
 
-static inline void __tlbie_pid(unsigned long pid, unsigned long ric)
+static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
@@ -120,23 +120,7 @@
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
-static inline void __tlbiel_lpid(unsigned long lpid, int set,
-				unsigned long ric)
-{
-	unsigned long rb,rs,prs,r;
-
-	rb = PPC_BIT(52); /* IS = 2 */
-	rb |= set << PPC_BITLSHIFT(51);
-	rs = 0;  /* LPID comes from LPIDR */
-	prs = 0; /* partition scoped */
-	r = 1;   /* radix format */
-
-	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(lpid, 1, rb, rs, ric, prs, r);
-}
-
-static inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
+static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
@@ -150,25 +134,22 @@
 	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
 }
 
-static inline void __tlbiel_lpid_guest(unsigned long lpid, int set,
-				unsigned long ric)
+static __always_inline void __tlbie_lpid_guest(unsigned long lpid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(52); /* IS = 2 */
-	rb |= set << PPC_BITLSHIFT(51);
-	rs = 0;  /* LPID comes from LPIDR */
+	rs = lpid;
 	prs = 1; /* process scoped */
 	r = 1;   /* radix format */
 
-	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(lpid, 1, rb, rs, ric, prs, r);
+	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
 }
 
-
-static inline void __tlbiel_va(unsigned long va, unsigned long pid,
-			       unsigned long ap, unsigned long ric)
+static __always_inline void __tlbiel_va(unsigned long va, unsigned long pid,
+					unsigned long ap, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
@@ -183,8 +164,8 @@
 	trace_tlbie(0, 1, rb, rs, ric, prs, r);
 }
 
-static inline void __tlbie_va(unsigned long va, unsigned long pid,
-			      unsigned long ap, unsigned long ric)
+static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
+				       unsigned long ap, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
@@ -199,8 +180,8 @@
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
-static inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
-			      unsigned long ap, unsigned long ric)
+static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
+					    unsigned long ap, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
@@ -215,22 +196,83 @@
 	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
 }
 
-static inline void fixup_tlbie(void)
+
+static inline void fixup_tlbie_va(unsigned long va, unsigned long pid,
+				  unsigned long ap)
 {
-	unsigned long pid = 0;
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, 0, ap, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, pid, ap, RIC_FLUSH_TLB);
+	}
+}
+
+static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid,
+					unsigned long ap)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_pid(0, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_va(va, pid, ap, RIC_FLUSH_TLB);
+	}
+}
+
+static inline void fixup_tlbie_pid(unsigned long pid)
+{
+	/*
+	 * 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_BUG)) {
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_pid(0, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
 		asm volatile("ptesync": : :"memory");
 		__tlbie_va(va, pid, 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)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_lpid_va(va, 0, ap, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_lpid_va(va, lpid, ap, RIC_FLUSH_TLB);
+	}
+}
+
 static inline void fixup_tlbie_lpid(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_BUG)) {
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_lpid(0, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
 		asm volatile("ptesync": : :"memory");
 		__tlbie_lpid_va(va, lpid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
 	}
@@ -239,7 +281,7 @@
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
-static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
+static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 {
 	int set;
 
@@ -262,7 +304,7 @@
 		__tlbiel_pid(pid, set, RIC_FLUSH_TLB);
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+	asm volatile(PPC_RADIX_INVALIDATE_ERAT_USER "; isync" : : :"memory");
 }
 
 static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
@@ -277,6 +319,7 @@
 	switch (ric) {
 	case RIC_FLUSH_TLB:
 		__tlbie_pid(pid, RIC_FLUSH_TLB);
+		fixup_tlbie_pid(pid);
 		break;
 	case RIC_FLUSH_PWC:
 		__tlbie_pid(pid, RIC_FLUSH_PWC);
@@ -284,37 +327,42 @@
 	case RIC_FLUSH_ALL:
 	default:
 		__tlbie_pid(pid, RIC_FLUSH_ALL);
+		fixup_tlbie_pid(pid);
 	}
-	fixup_tlbie();
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-static inline void _tlbiel_lpid(unsigned long lpid, unsigned long ric)
+struct tlbiel_pid {
+	unsigned long pid;
+	unsigned long ric;
+};
+
+static void do_tlbiel_pid(void *info)
 {
-	int set;
+	struct tlbiel_pid *t = info;
 
-	VM_BUG_ON(mfspr(SPRN_LPID) != lpid);
+	if (t->ric == RIC_FLUSH_TLB)
+		_tlbiel_pid(t->pid, RIC_FLUSH_TLB);
+	else if (t->ric == RIC_FLUSH_PWC)
+		_tlbiel_pid(t->pid, RIC_FLUSH_PWC);
+	else
+		_tlbiel_pid(t->pid, RIC_FLUSH_ALL);
+}
 
-	asm volatile("ptesync": : :"memory");
+static inline void _tlbiel_pid_multicast(struct mm_struct *mm,
+				unsigned long pid, unsigned long ric)
+{
+	struct cpumask *cpus = mm_cpumask(mm);
+	struct tlbiel_pid t = { .pid = pid, .ric = ric };
 
+	on_each_cpu_mask(cpus, do_tlbiel_pid, &t, 1);
 	/*
-	 * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL,
-	 * also flush the entire Page Walk Cache.
+	 * Always want the CPU translations to be invalidated with tlbiel in
+	 * these paths, so while coprocessors must use tlbie, we can not
+	 * optimise away the tlbiel component.
 	 */
-	__tlbiel_lpid(lpid, 0, ric);
-
-	/* For PWC, only one flush is needed */
-	if (ric == RIC_FLUSH_PWC) {
-		asm volatile("ptesync": : :"memory");
-		return;
-	}
-
-	/* For the remaining sets, just flush the TLB */
-	for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
-		__tlbiel_lpid(lpid, set, RIC_FLUSH_TLB);
-
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+	if (atomic_read(&mm->context.copros) > 0)
+		_tlbie_pid(pid, RIC_FLUSH_ALL);
 }
 
 static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric)
@@ -329,6 +377,7 @@
 	switch (ric) {
 	case RIC_FLUSH_TLB:
 		__tlbie_lpid(lpid, RIC_FLUSH_TLB);
+		fixup_tlbie_lpid(lpid);
 		break;
 	case RIC_FLUSH_PWC:
 		__tlbie_lpid(lpid, RIC_FLUSH_PWC);
@@ -336,39 +385,33 @@
 	case RIC_FLUSH_ALL:
 	default:
 		__tlbie_lpid(lpid, RIC_FLUSH_ALL);
+		fixup_tlbie_lpid(lpid);
+	}
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+
+static __always_inline void _tlbie_lpid_guest(unsigned long lpid, unsigned long ric)
+{
+	/*
+	 * 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_lpid_guest(lpid, RIC_FLUSH_TLB);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_lpid_guest(lpid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_lpid_guest(lpid, RIC_FLUSH_ALL);
 	}
 	fixup_tlbie_lpid(lpid);
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-static inline void _tlbiel_lpid_guest(unsigned long lpid, unsigned long ric)
-{
-	int set;
-
-	VM_BUG_ON(mfspr(SPRN_LPID) != lpid);
-
-	asm volatile("ptesync": : :"memory");
-
-	/*
-	 * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL,
-	 * also flush the entire Page Walk Cache.
-	 */
-	__tlbiel_lpid_guest(lpid, 0, ric);
-
-	/* For PWC, only one flush is needed */
-	if (ric == RIC_FLUSH_PWC) {
-		asm volatile("ptesync": : :"memory");
-		return;
-	}
-
-	/* For the remaining sets, just flush the TLB */
-	for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
-		__tlbiel_lpid_guest(lpid, set, RIC_FLUSH_TLB);
-
-	asm volatile("ptesync": : :"memory");
-}
-
-
 static inline void __tlbiel_va_range(unsigned long start, unsigned long end,
 				    unsigned long pid, unsigned long page_size,
 				    unsigned long psize)
@@ -380,8 +423,8 @@
 		__tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB);
 }
 
-static inline void _tlbiel_va(unsigned long va, unsigned long pid,
-			      unsigned long psize, unsigned long ric)
+static __always_inline void _tlbiel_va(unsigned long va, unsigned long pid,
+				       unsigned long psize, unsigned long ric)
 {
 	unsigned long ap = mmu_get_ap(psize);
 
@@ -410,27 +453,76 @@
 
 	for (addr = start; addr < end; addr += page_size)
 		__tlbie_va(addr, pid, ap, RIC_FLUSH_TLB);
+
+	fixup_tlbie_va_range(addr - page_size, pid, ap);
 }
 
-static inline void _tlbie_va(unsigned long va, unsigned long pid,
-			      unsigned long psize, unsigned long ric)
+static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
+				      unsigned long psize, unsigned long ric)
 {
 	unsigned long ap = mmu_get_ap(psize);
 
 	asm volatile("ptesync": : :"memory");
 	__tlbie_va(va, pid, ap, ric);
-	fixup_tlbie();
+	fixup_tlbie_va(va, pid, ap);
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-static inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid,
+struct tlbiel_va {
+	unsigned long pid;
+	unsigned long va;
+	unsigned long psize;
+	unsigned long ric;
+};
+
+static void do_tlbiel_va(void *info)
+{
+	struct tlbiel_va *t = info;
+
+	if (t->ric == RIC_FLUSH_TLB)
+		_tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_TLB);
+	else if (t->ric == RIC_FLUSH_PWC)
+		_tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_PWC);
+	else
+		_tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_ALL);
+}
+
+static inline void _tlbiel_va_multicast(struct mm_struct *mm,
+				unsigned long va, unsigned long pid,
+				unsigned long psize, unsigned long ric)
+{
+	struct cpumask *cpus = mm_cpumask(mm);
+	struct tlbiel_va t = { .va = va, .pid = pid, .psize = psize, .ric = ric };
+	on_each_cpu_mask(cpus, do_tlbiel_va, &t, 1);
+	if (atomic_read(&mm->context.copros) > 0)
+		_tlbie_va(va, pid, psize, RIC_FLUSH_TLB);
+}
+
+struct tlbiel_va_range {
+	unsigned long pid;
+	unsigned long start;
+	unsigned long end;
+	unsigned long page_size;
+	unsigned long psize;
+	bool also_pwc;
+};
+
+static void do_tlbiel_va_range(void *info)
+{
+	struct tlbiel_va_range *t = info;
+
+	_tlbiel_va_range(t->start, t->end, t->pid, t->page_size,
+				    t->psize, t->also_pwc);
+}
+
+static __always_inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid,
 			      unsigned long psize, unsigned long ric)
 {
 	unsigned long ap = mmu_get_ap(psize);
 
 	asm volatile("ptesync": : :"memory");
 	__tlbie_lpid_va(va, lpid, ap, ric);
-	fixup_tlbie_lpid(lpid);
+	fixup_tlbie_lpid_va(va, lpid, ap);
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
@@ -442,10 +534,24 @@
 	if (also_pwc)
 		__tlbie_pid(pid, RIC_FLUSH_PWC);
 	__tlbie_va_range(start, end, pid, page_size, psize);
-	fixup_tlbie();
 	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,
+				unsigned long psize, bool also_pwc)
+{
+	struct cpumask *cpus = mm_cpumask(mm);
+	struct tlbiel_va_range t = { .start = start, .end = end,
+				.pid = pid, .page_size = page_size,
+				.psize = psize, .also_pwc = also_pwc };
+
+	on_each_cpu_mask(cpus, do_tlbiel_va_range, &t, 1);
+	if (atomic_read(&mm->context.copros) > 0)
+		_tlbie_va_range(start, end, pid, page_size, psize, also_pwc);
+}
+
 /*
  * Base TLB flushing operations:
  *
@@ -583,10 +689,14 @@
 			goto local;
 		}
 
-		if (mm_needs_flush_escalation(mm))
-			_tlbie_pid(pid, RIC_FLUSH_ALL);
-		else
-			_tlbie_pid(pid, RIC_FLUSH_TLB);
+		if (cputlb_use_tlbie()) {
+			if (mm_needs_flush_escalation(mm))
+				_tlbie_pid(pid, RIC_FLUSH_ALL);
+			else
+				_tlbie_pid(pid, RIC_FLUSH_TLB);
+		} else {
+			_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_TLB);
+		}
 	} else {
 local:
 		_tlbiel_pid(pid, RIC_FLUSH_TLB);
@@ -612,7 +722,10 @@
 				goto local;
 			}
 		}
-		_tlbie_pid(pid, RIC_FLUSH_ALL);
+		if (cputlb_use_tlbie())
+			_tlbie_pid(pid, RIC_FLUSH_ALL);
+		else
+			_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL);
 	} else {
 local:
 		_tlbiel_pid(pid, RIC_FLUSH_ALL);
@@ -647,7 +760,10 @@
 			exit_flush_lazy_tlbs(mm);
 			goto local;
 		}
-		_tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
+		if (cputlb_use_tlbie())
+			_tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
+		else
+			_tlbiel_va_multicast(mm, vmaddr, pid, psize, RIC_FLUSH_TLB);
 	} else {
 local:
 		_tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
@@ -669,9 +785,35 @@
 #define radix__flush_all_mm radix__local_flush_all_mm
 #endif /* CONFIG_SMP */
 
+static void do_tlbiel_kernel(void *info)
+{
+	_tlbiel_pid(0, RIC_FLUSH_ALL);
+}
+
+static inline void _tlbiel_kernel_broadcast(void)
+{
+	on_each_cpu(do_tlbiel_kernel, NULL, 1);
+	if (tlbie_capable) {
+		/*
+		 * Coherent accelerators don't refcount kernel memory mappings,
+		 * so have to always issue a tlbie for them. This is quite a
+		 * slow path anyway.
+		 */
+		_tlbie_pid(0, RIC_FLUSH_ALL);
+	}
+}
+
+/*
+ * If kernel TLBIs ever become local rather than global, then
+ * drivers/misc/ocxl/link.c:ocxl_link_add_pe will need some work, as it
+ * assumes kernel TLBIs are global.
+ */
 void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	_tlbie_pid(0, RIC_FLUSH_ALL);
+	if (cputlb_use_tlbie())
+		_tlbie_pid(0, RIC_FLUSH_ALL);
+	else
+		_tlbiel_kernel_broadcast();
 }
 EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
 
@@ -727,10 +869,14 @@
 		if (local) {
 			_tlbiel_pid(pid, RIC_FLUSH_TLB);
 		} else {
-			if (mm_needs_flush_escalation(mm))
-				_tlbie_pid(pid, RIC_FLUSH_ALL);
-			else
-				_tlbie_pid(pid, RIC_FLUSH_TLB);
+			if (cputlb_use_tlbie()) {
+				if (mm_needs_flush_escalation(mm))
+					_tlbie_pid(pid, RIC_FLUSH_ALL);
+				else
+					_tlbie_pid(pid, RIC_FLUSH_TLB);
+			} else {
+				_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_TLB);
+			}
 		}
 	} else {
 		bool hflush = flush_all_sizes;
@@ -755,8 +901,8 @@
 				gflush = false;
 		}
 
-		asm volatile("ptesync": : :"memory");
 		if (local) {
+			asm volatile("ptesync": : :"memory");
 			__tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize);
 			if (hflush)
 				__tlbiel_va_range(hstart, hend, pid,
@@ -765,7 +911,8 @@
 				__tlbiel_va_range(gstart, gend, pid,
 						PUD_SIZE, MMU_PAGE_1G);
 			asm volatile("ptesync": : :"memory");
-		} else {
+		} else if (cputlb_use_tlbie()) {
+			asm volatile("ptesync": : :"memory");
 			__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);
 			if (hflush)
 				__tlbie_va_range(hstart, hend, pid,
@@ -773,8 +920,17 @@
 			if (gflush)
 				__tlbie_va_range(gstart, gend, pid,
 						PUD_SIZE, MMU_PAGE_1G);
-			fixup_tlbie();
+
 			asm volatile("eieio; tlbsync; ptesync": : :"memory");
+		} else {
+			_tlbiel_va_range_multicast(mm,
+					start, end, pid, page_size, mmu_virtual_psize, false);
+			if (hflush)
+				_tlbiel_va_range_multicast(mm,
+					hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M, false);
+			if (gflush)
+				_tlbiel_va_range_multicast(mm,
+					gstart, gend, pid, PUD_SIZE, MMU_PAGE_1G, false);
 		}
 	}
 	preempt_enable();
@@ -833,23 +989,19 @@
 /*
  * Flush partition scoped translations from LPID (=LPIDR)
  */
-void radix__local_flush_tlb_lpid(unsigned int lpid)
+void radix__flush_all_lpid(unsigned int lpid)
 {
-	_tlbiel_lpid(lpid, RIC_FLUSH_ALL);
+	_tlbie_lpid(lpid, RIC_FLUSH_ALL);
 }
-EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid);
+EXPORT_SYMBOL_GPL(radix__flush_all_lpid);
 
 /*
- * Flush process scoped translations from LPID (=LPIDR).
- * Important difference, the guest normally manages its own translations,
- * but some cases e.g., vCPU CPU migration require KVM to flush.
+ * Flush process scoped translations from LPID (=LPIDR)
  */
-void radix__local_flush_tlb_lpid_guest(unsigned int lpid)
+void radix__flush_all_lpid_guest(unsigned int lpid)
 {
-	_tlbiel_lpid_guest(lpid, RIC_FLUSH_ALL);
+	_tlbie_lpid_guest(lpid, RIC_FLUSH_ALL);
 }
-EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid_guest);
-
 
 static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
 				  unsigned long end, int psize);
@@ -918,7 +1070,7 @@
 	tlb->need_flush_all = 0;
 }
 
-static inline void __radix__flush_tlb_range_psize(struct mm_struct *mm,
+static __always_inline void __radix__flush_tlb_range_psize(struct mm_struct *mm,
 				unsigned long start, unsigned long end,
 				int psize, bool also_pwc)
 {
@@ -955,16 +1107,26 @@
 		if (local) {
 			_tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
 		} else {
-			if (mm_needs_flush_escalation(mm))
-				also_pwc = true;
+			if (cputlb_use_tlbie()) {
+				if (mm_needs_flush_escalation(mm))
+					also_pwc = true;
 
-			_tlbie_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
+				_tlbie_pid(pid,
+					also_pwc ?  RIC_FLUSH_ALL : RIC_FLUSH_TLB);
+			} else {
+				_tlbiel_pid_multicast(mm, pid,
+					also_pwc ?  RIC_FLUSH_ALL : RIC_FLUSH_TLB);
+			}
+
 		}
 	} else {
 		if (local)
 			_tlbiel_va_range(start, end, pid, page_size, psize, also_pwc);
-		else
+		else if (cputlb_use_tlbie())
 			_tlbie_va_range(start, end, pid, page_size, psize, also_pwc);
+		else
+			_tlbiel_va_range_multicast(mm,
+					start, end, pid, page_size, psize, also_pwc);
 	}
 	preempt_enable();
 }
@@ -1006,8 +1168,11 @@
 			exit_flush_lazy_tlbs(mm);
 			goto local;
 		}
-		_tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
-		goto local;
+		if (cputlb_use_tlbie())
+			_tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
+		else
+			_tlbiel_va_range_multicast(mm,
+					addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
 	} else {
 local:
 		_tlbiel_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
new file mode 100644
index 0000000..716204a
--- /dev/null
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -0,0 +1,828 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PowerPC64 SLB support.
+ *
+ * Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM
+ * Based on earlier code written by:
+ * Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
+ *    Copyright (c) 2001 Dave Engebretsen
+ * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
+ */
+
+#include <asm/asm-prototypes.h>
+#include <asm/pgtable.h>
+#include <asm/mmu.h>
+#include <asm/mmu_context.h>
+#include <asm/paca.h>
+#include <asm/ppc-opcode.h>
+#include <asm/cputable.h>
+#include <asm/cacheflush.h>
+#include <asm/smp.h>
+#include <linux/compiler.h>
+#include <linux/context_tracking.h>
+#include <linux/mm_types.h>
+
+#include <asm/udbg.h>
+#include <asm/code-patching.h>
+
+enum slb_index {
+	LINEAR_INDEX	= 0, /* Kernel linear map  (0xc000000000000000) */
+	KSTACK_INDEX	= 1, /* Kernel stack map */
+};
+
+static long slb_allocate_user(struct mm_struct *mm, unsigned long ea);
+
+#define slb_esid_mask(ssize)	\
+	(((ssize) == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T)
+
+static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
+					 enum slb_index index)
+{
+	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | index;
+}
+
+static inline unsigned long __mk_vsid_data(unsigned long vsid, int ssize,
+					 unsigned long flags)
+{
+	return (vsid << slb_vsid_shift(ssize)) | flags |
+		((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
+}
+
+static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
+					 unsigned long flags)
+{
+	return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags);
+}
+
+static void assert_slb_presence(bool present, unsigned long ea)
+{
+#ifdef CONFIG_DEBUG_VM
+	unsigned long tmp;
+
+	WARN_ON_ONCE(mfmsr() & MSR_EE);
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_206))
+		return;
+
+	/*
+	 * slbfee. requires bit 24 (PPC bit 39) be clear in RB. Hardware
+	 * ignores all other bits from 0-27, so just clear them all.
+	 */
+	ea &= ~((1UL << 28) - 1);
+	asm volatile(__PPC_SLBFEE_DOT(%0, %1) : "=r"(tmp) : "r"(ea) : "cr0");
+
+	WARN_ON(present == (tmp == 0));
+#endif
+}
+
+static inline void slb_shadow_update(unsigned long ea, int ssize,
+				     unsigned long flags,
+				     enum slb_index index)
+{
+	struct slb_shadow *p = get_slb_shadow();
+
+	/*
+	 * Clear the ESID first so the entry is not valid while we are
+	 * updating it.  No write barriers are needed here, provided
+	 * we only update the current CPU's SLB shadow buffer.
+	 */
+	WRITE_ONCE(p->save_area[index].esid, 0);
+	WRITE_ONCE(p->save_area[index].vsid, cpu_to_be64(mk_vsid_data(ea, ssize, flags)));
+	WRITE_ONCE(p->save_area[index].esid, cpu_to_be64(mk_esid_data(ea, ssize, index)));
+}
+
+static inline void slb_shadow_clear(enum slb_index index)
+{
+	WRITE_ONCE(get_slb_shadow()->save_area[index].esid, cpu_to_be64(index));
+}
+
+static inline void create_shadowed_slbe(unsigned long ea, int ssize,
+					unsigned long flags,
+					enum slb_index index)
+{
+	/*
+	 * Updating the shadow buffer before writing the SLB ensures
+	 * we don't get a stale entry here if we get preempted by PHYP
+	 * between these two statements.
+	 */
+	slb_shadow_update(ea, ssize, flags, index);
+
+	assert_slb_presence(false, ea);
+	asm volatile("slbmte  %0,%1" :
+		     : "r" (mk_vsid_data(ea, ssize, flags)),
+		       "r" (mk_esid_data(ea, ssize, index))
+		     : "memory" );
+}
+
+/*
+ * Insert bolted entries into SLB (which may not be empty, so don't clear
+ * slb_cache_ptr).
+ */
+void __slb_restore_bolted_realmode(void)
+{
+	struct slb_shadow *p = get_slb_shadow();
+	enum slb_index index;
+
+	 /* No isync needed because realmode. */
+	for (index = 0; index < SLB_NUM_BOLTED; index++) {
+		asm volatile("slbmte  %0,%1" :
+		     : "r" (be64_to_cpu(p->save_area[index].vsid)),
+		       "r" (be64_to_cpu(p->save_area[index].esid)));
+	}
+
+	assert_slb_presence(true, local_paca->kstack);
+}
+
+/*
+ * Insert the bolted entries into an empty SLB.
+ */
+void slb_restore_bolted_realmode(void)
+{
+	__slb_restore_bolted_realmode();
+	get_paca()->slb_cache_ptr = 0;
+
+	get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1;
+	get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap;
+}
+
+/*
+ * This flushes all SLB entries including 0, so it must be realmode.
+ */
+void slb_flush_all_realmode(void)
+{
+	asm volatile("slbmte %0,%0; slbia" : : "r" (0));
+}
+
+/*
+ * This flushes non-bolted entries, it can be run in virtual mode. Must
+ * be called with interrupts disabled.
+ */
+void slb_flush_and_restore_bolted(void)
+{
+	struct slb_shadow *p = get_slb_shadow();
+
+	BUILD_BUG_ON(SLB_NUM_BOLTED != 2);
+
+	WARN_ON(!irqs_disabled());
+
+	/*
+	 * We can't take a PMU exception in the following code, so hard
+	 * disable interrupts.
+	 */
+	hard_irq_disable();
+
+	asm volatile("isync\n"
+		     "slbia\n"
+		     "slbmte  %0, %1\n"
+		     "isync\n"
+		     :: "r" (be64_to_cpu(p->save_area[KSTACK_INDEX].vsid)),
+			"r" (be64_to_cpu(p->save_area[KSTACK_INDEX].esid))
+		     : "memory");
+	assert_slb_presence(true, get_paca()->kstack);
+
+	get_paca()->slb_cache_ptr = 0;
+
+	get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1;
+	get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap;
+}
+
+void slb_save_contents(struct slb_entry *slb_ptr)
+{
+	int i;
+	unsigned long e, v;
+
+	/* Save slb_cache_ptr value. */
+	get_paca()->slb_save_cache_ptr = get_paca()->slb_cache_ptr;
+
+	if (!slb_ptr)
+		return;
+
+	for (i = 0; i < mmu_slb_size; i++) {
+		asm volatile("slbmfee  %0,%1" : "=r" (e) : "r" (i));
+		asm volatile("slbmfev  %0,%1" : "=r" (v) : "r" (i));
+		slb_ptr->esid = e;
+		slb_ptr->vsid = v;
+		slb_ptr++;
+	}
+}
+
+void slb_dump_contents(struct slb_entry *slb_ptr)
+{
+	int i, n;
+	unsigned long e, v;
+	unsigned long llp;
+
+	if (!slb_ptr)
+		return;
+
+	pr_err("SLB contents of cpu 0x%x\n", smp_processor_id());
+	pr_err("Last SLB entry inserted at slot %d\n", get_paca()->stab_rr);
+
+	for (i = 0; i < mmu_slb_size; i++) {
+		e = slb_ptr->esid;
+		v = slb_ptr->vsid;
+		slb_ptr++;
+
+		if (!e && !v)
+			continue;
+
+		pr_err("%02d %016lx %016lx\n", i, e, v);
+
+		if (!(e & SLB_ESID_V)) {
+			pr_err("\n");
+			continue;
+		}
+		llp = v & SLB_VSID_LLP;
+		if (v & SLB_VSID_B_1T) {
+			pr_err("  1T  ESID=%9lx  VSID=%13lx LLP:%3lx\n",
+			       GET_ESID_1T(e),
+			       (v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T, llp);
+		} else {
+			pr_err(" 256M ESID=%9lx  VSID=%13lx LLP:%3lx\n",
+			       GET_ESID(e),
+			       (v & ~SLB_VSID_B) >> SLB_VSID_SHIFT, llp);
+		}
+	}
+	pr_err("----------------------------------\n");
+
+	/* Dump slb cache entires as well. */
+	pr_err("SLB cache ptr value = %d\n", get_paca()->slb_save_cache_ptr);
+	pr_err("Valid SLB cache entries:\n");
+	n = min_t(int, get_paca()->slb_save_cache_ptr, SLB_CACHE_ENTRIES);
+	for (i = 0; i < n; i++)
+		pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]);
+	pr_err("Rest of SLB cache entries:\n");
+	for (i = n; i < SLB_CACHE_ENTRIES; i++)
+		pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]);
+}
+
+void slb_vmalloc_update(void)
+{
+	/*
+	 * vmalloc is not bolted, so just have to flush non-bolted.
+	 */
+	slb_flush_and_restore_bolted();
+}
+
+static bool preload_hit(struct thread_info *ti, unsigned long esid)
+{
+	unsigned char i;
+
+	for (i = 0; i < ti->slb_preload_nr; i++) {
+		unsigned char idx;
+
+		idx = (ti->slb_preload_tail + i) % SLB_PRELOAD_NR;
+		if (esid == ti->slb_preload_esid[idx])
+			return true;
+	}
+	return false;
+}
+
+static bool preload_add(struct thread_info *ti, unsigned long ea)
+{
+	unsigned char idx;
+	unsigned long esid;
+
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
+		/* EAs are stored >> 28 so 256MB segments don't need clearing */
+		if (ea & ESID_MASK_1T)
+			ea &= ESID_MASK_1T;
+	}
+
+	esid = ea >> SID_SHIFT;
+
+	if (preload_hit(ti, esid))
+		return false;
+
+	idx = (ti->slb_preload_tail + ti->slb_preload_nr) % SLB_PRELOAD_NR;
+	ti->slb_preload_esid[idx] = esid;
+	if (ti->slb_preload_nr == SLB_PRELOAD_NR)
+		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)
+{
+	if (!ti->slb_preload_nr)
+		return;
+	ti->slb_preload_nr--;
+	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 aleady 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();
+}
+
+
+/* Flush all user entries from the segment table of the current processor. */
+void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
+{
+	struct thread_info *ti = task_thread_info(tsk);
+	unsigned char i;
+
+	/*
+	 * We need interrupts hard-disabled here, not just soft-disabled,
+	 * so that a PMU interrupt can't occur, which might try to access
+	 * user memory (to get a stack trace) and possible cause an SLB miss
+	 * which would update the slb_cache/slb_cache_ptr fields in the PACA.
+	 */
+	hard_irq_disable();
+	asm volatile("isync" : : : "memory");
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		/*
+		 * SLBIA IH=3 invalidates all Class=1 SLBEs and their
+		 * associated lookaside structures, which matches what
+		 * switch_slb wants. So ARCH_300 does not use the slb
+		 * cache.
+		 */
+		asm volatile(PPC_SLBIA(3));
+	} else {
+		unsigned long offset = get_paca()->slb_cache_ptr;
+
+		if (!mmu_has_feature(MMU_FTR_NO_SLBIE_B) &&
+		    offset <= SLB_CACHE_ENTRIES) {
+			unsigned long slbie_data = 0;
+
+			for (i = 0; i < offset; i++) {
+				unsigned long ea;
+
+				ea = (unsigned long)
+					get_paca()->slb_cache[i] << SID_SHIFT;
+				/*
+				 * Could assert_slb_presence(true) here, but
+				 * hypervisor or machine check could have come
+				 * in and removed the entry at this point.
+				 */
+
+				slbie_data = ea;
+				slbie_data |= user_segment_size(slbie_data)
+						<< SLBIE_SSIZE_SHIFT;
+				slbie_data |= SLBIE_C; /* user slbs have C=1 */
+				asm volatile("slbie %0" : : "r" (slbie_data));
+			}
+
+			/* Workaround POWER5 < DD2.1 issue */
+			if (!cpu_has_feature(CPU_FTR_ARCH_207S) && offset == 1)
+				asm volatile("slbie %0" : : "r" (slbie_data));
+
+		} else {
+			struct slb_shadow *p = get_slb_shadow();
+			unsigned long ksp_esid_data =
+				be64_to_cpu(p->save_area[KSTACK_INDEX].esid);
+			unsigned long ksp_vsid_data =
+				be64_to_cpu(p->save_area[KSTACK_INDEX].vsid);
+
+			asm volatile(PPC_SLBIA(1) "\n"
+				     "slbmte	%0,%1\n"
+				     "isync"
+				     :: "r"(ksp_vsid_data),
+					"r"(ksp_esid_data));
+
+			get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1;
+		}
+
+		get_paca()->slb_cache_ptr = 0;
+	}
+	get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap;
+
+	copy_mm_to_paca(mm);
+
+	/*
+	 * We gradually age out SLBs after a number of context switches to
+	 * reduce reload overhead of unused entries (like we do with FP/VEC
+	 * reload). Each time we wrap 256 switches, take an entry out of the
+	 * SLB preload cache.
+	 */
+	tsk->thread.load_slb++;
+	if (!tsk->thread.load_slb) {
+		unsigned long pc = KSTK_EIP(tsk);
+
+		preload_age(ti);
+		preload_add(ti, pc);
+	}
+
+	for (i = 0; i < ti->slb_preload_nr; i++) {
+		unsigned char idx;
+		unsigned long ea;
+
+		idx = (ti->slb_preload_tail + i) % SLB_PRELOAD_NR;
+		ea = (unsigned long)ti->slb_preload_esid[idx] << SID_SHIFT;
+
+		slb_allocate_user(mm, ea);
+	}
+
+	/*
+	 * Synchronize slbmte preloads with possible subsequent user memory
+	 * address accesses by the kernel (user mode won't happen until
+	 * rfid, which is safe).
+	 */
+	asm volatile("isync" : : : "memory");
+}
+
+void slb_set_size(u16 size)
+{
+	mmu_slb_size = size;
+}
+
+void slb_initialize(void)
+{
+	unsigned long linear_llp, vmalloc_llp, io_llp;
+	unsigned long lflags;
+	static int slb_encoding_inited;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	unsigned long vmemmap_llp;
+#endif
+
+	/* Prepare our SLB miss handler based on our page size */
+	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
+	io_llp = mmu_psize_defs[mmu_io_psize].sllp;
+	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
+	get_paca()->vmalloc_sllp = SLB_VSID_KERNEL | vmalloc_llp;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	vmemmap_llp = mmu_psize_defs[mmu_vmemmap_psize].sllp;
+#endif
+	if (!slb_encoding_inited) {
+		slb_encoding_inited = 1;
+		pr_devel("SLB: linear  LLP = %04lx\n", linear_llp);
+		pr_devel("SLB: io      LLP = %04lx\n", io_llp);
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+		pr_devel("SLB: vmemmap LLP = %04lx\n", vmemmap_llp);
+#endif
+	}
+
+	get_paca()->stab_rr = SLB_NUM_BOLTED - 1;
+	get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1;
+	get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap;
+
+	lflags = SLB_VSID_KERNEL | linear_llp;
+
+	/* Invalidate the entire SLB (even entry 0) & all the ERATS */
+	asm volatile("isync":::"memory");
+	asm volatile("slbmte  %0,%0"::"r" (0) : "memory");
+	asm volatile("isync; slbia; isync":::"memory");
+	create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, LINEAR_INDEX);
+
+	/*
+	 * For the boot cpu, we're running on the stack in init_thread_union,
+	 * which is in the first segment of the linear mapping, and also
+	 * get_paca()->kstack hasn't been initialized yet.
+	 * For secondary cpus, we need to bolt the kernel stack entry now.
+	 */
+	slb_shadow_clear(KSTACK_INDEX);
+	if (raw_smp_processor_id() != boot_cpuid &&
+	    (get_paca()->kstack & slb_esid_mask(mmu_kernel_ssize)) > PAGE_OFFSET)
+		create_shadowed_slbe(get_paca()->kstack,
+				     mmu_kernel_ssize, lflags, KSTACK_INDEX);
+
+	asm volatile("isync":::"memory");
+}
+
+static void slb_cache_update(unsigned long esid_data)
+{
+	int slb_cache_index;
+
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		return; /* ISAv3.0B and later does not use slb_cache */
+
+	/*
+	 * Now update slb cache entries
+	 */
+	slb_cache_index = local_paca->slb_cache_ptr;
+	if (slb_cache_index < SLB_CACHE_ENTRIES) {
+		/*
+		 * We have space in slb cache for optimized switch_slb().
+		 * Top 36 bits from esid_data as per ISA
+		 */
+		local_paca->slb_cache[slb_cache_index++] = esid_data >> 28;
+		local_paca->slb_cache_ptr++;
+	} else {
+		/*
+		 * Our cache is full and the current cache content strictly
+		 * doesn't indicate the active SLB conents. Bump the ptr
+		 * so that switch_slb() will ignore the cache.
+		 */
+		local_paca->slb_cache_ptr = SLB_CACHE_ENTRIES + 1;
+	}
+}
+
+static enum slb_index alloc_slb_index(bool kernel)
+{
+	enum slb_index index;
+
+	/*
+	 * The allocation bitmaps can become out of synch with the SLB
+	 * when the _switch code does slbie when bolting a new stack
+	 * segment and it must not be anywhere else in the SLB. This leaves
+	 * a kernel allocated entry that is unused in the SLB. With very
+	 * large systems or small segment sizes, the bitmaps could slowly
+	 * fill with these entries. They will eventually be cleared out
+	 * by the round robin allocator in that case, so it's probably not
+	 * worth accounting for.
+	 */
+
+	/*
+	 * SLBs beyond 32 entries are allocated with stab_rr only
+	 * POWER7/8/9 have 32 SLB entries, this could be expanded if a
+	 * future CPU has more.
+	 */
+	if (local_paca->slb_used_bitmap != U32_MAX) {
+		index = ffz(local_paca->slb_used_bitmap);
+		local_paca->slb_used_bitmap |= 1U << index;
+		if (kernel)
+			local_paca->slb_kern_bitmap |= 1U << index;
+	} else {
+		/* round-robin replacement of slb starting at SLB_NUM_BOLTED. */
+		index = local_paca->stab_rr;
+		if (index < (mmu_slb_size - 1))
+			index++;
+		else
+			index = SLB_NUM_BOLTED;
+		local_paca->stab_rr = index;
+		if (index < 32) {
+			if (kernel)
+				local_paca->slb_kern_bitmap |= 1U << index;
+			else
+				local_paca->slb_kern_bitmap &= ~(1U << index);
+		}
+	}
+	BUG_ON(index < SLB_NUM_BOLTED);
+
+	return index;
+}
+
+static long slb_insert_entry(unsigned long ea, unsigned long context,
+				unsigned long flags, int ssize, bool kernel)
+{
+	unsigned long vsid;
+	unsigned long vsid_data, esid_data;
+	enum slb_index index;
+
+	vsid = get_vsid(context, ea, ssize);
+	if (!vsid)
+		return -EFAULT;
+
+	/*
+	 * There must not be a kernel SLB fault in alloc_slb_index or before
+	 * slbmte here or the allocation bitmaps could get out of whack with
+	 * the SLB.
+	 *
+	 * User SLB faults or preloads take this path which might get inlined
+	 * into the caller, so add compiler barriers here to ensure unsafe
+	 * memory accesses do not come between.
+	 */
+	barrier();
+
+	index = alloc_slb_index(kernel);
+
+	vsid_data = __mk_vsid_data(vsid, ssize, flags);
+	esid_data = mk_esid_data(ea, ssize, index);
+
+	/*
+	 * No need for an isync before or after this slbmte. The exception
+	 * we enter with and the rfid we exit with are context synchronizing.
+	 * User preloads should add isync afterwards in case the kernel
+	 * accesses user memory before it returns to userspace with rfid.
+	 */
+	assert_slb_presence(false, ea);
+	asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data));
+
+	barrier();
+
+	if (!kernel)
+		slb_cache_update(esid_data);
+
+	return 0;
+}
+
+static long slb_allocate_kernel(unsigned long ea, unsigned long id)
+{
+	unsigned long context;
+	unsigned long flags;
+	int ssize;
+
+	if (id == LINEAR_MAP_REGION_ID) {
+
+		/* We only support upto MAX_PHYSMEM_BITS */
+		if ((ea & EA_MASK) > (1UL << MAX_PHYSMEM_BITS))
+			return -EFAULT;
+
+		flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp;
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	} else if (id == VMEMMAP_REGION_ID) {
+
+		if (ea >= H_VMEMMAP_END)
+			return -EFAULT;
+
+		flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmemmap_psize].sllp;
+#endif
+	} else if (id == VMALLOC_REGION_ID) {
+
+		if (ea >= H_VMALLOC_END)
+			return -EFAULT;
+
+		flags = local_paca->vmalloc_sllp;
+
+	} else if (id == IO_REGION_ID) {
+
+		if (ea >= H_KERN_IO_END)
+			return -EFAULT;
+
+		flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp;
+
+	} else {
+		return -EFAULT;
+	}
+
+	ssize = MMU_SEGSIZE_1T;
+	if (!mmu_has_feature(MMU_FTR_1T_SEGMENT))
+		ssize = MMU_SEGSIZE_256M;
+
+	context = get_kernel_context(ea);
+
+	return slb_insert_entry(ea, context, flags, ssize, true);
+}
+
+static long slb_allocate_user(struct mm_struct *mm, unsigned long ea)
+{
+	unsigned long context;
+	unsigned long flags;
+	int bpsize;
+	int ssize;
+
+	/*
+	 * consider this as bad access if we take a SLB miss
+	 * on an address above addr limit.
+	 */
+	if (ea >= mm_ctx_slb_addr_limit(&mm->context))
+		return -EFAULT;
+
+	context = get_user_context(&mm->context, ea);
+	if (!context)
+		return -EFAULT;
+
+	if (unlikely(ea >= H_PGTABLE_RANGE)) {
+		WARN_ON(1);
+		return -EFAULT;
+	}
+
+	ssize = user_segment_size(ea);
+
+	bpsize = get_slice_psize(mm, ea);
+	flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp;
+
+	return slb_insert_entry(ea, context, flags, ssize, false);
+}
+
+long do_slb_fault(struct pt_regs *regs, unsigned long ea)
+{
+	unsigned long id = get_region_id(ea);
+
+	/* IRQs are not reconciled here, so can't check irqs_disabled */
+	VM_WARN_ON(mfmsr() & MSR_EE);
+
+	if (unlikely(!(regs->msr & MSR_RI)))
+		return -EINVAL;
+
+	/*
+	 * SLB kernel faults must be very careful not to touch anything
+	 * that is not bolted. E.g., PACA and global variables are okay,
+	 * mm->context stuff is not.
+	 *
+	 * SLB user faults can access all of kernel memory, but must be
+	 * careful not to touch things like IRQ state because it is not
+	 * "reconciled" here. The difficulty is that we must use
+	 * fast_exception_return to return from kernel SLB faults without
+	 * looking at possible non-bolted memory. We could test user vs
+	 * kernel faults in the interrupt handler asm and do a full fault,
+	 * reconcile, ret_from_except for user faults which would make them
+	 * first class kernel code. But for performance it's probably nicer
+	 * if they go via fast_exception_return too.
+	 */
+	if (id >= LINEAR_MAP_REGION_ID) {
+		long err;
+#ifdef CONFIG_DEBUG_VM
+		/* Catch recursive kernel SLB faults. */
+		BUG_ON(local_paca->in_kernel_slb_handler);
+		local_paca->in_kernel_slb_handler = 1;
+#endif
+		err = slb_allocate_kernel(ea, id);
+#ifdef CONFIG_DEBUG_VM
+		local_paca->in_kernel_slb_handler = 0;
+#endif
+		return err;
+	} else {
+		struct mm_struct *mm = current->mm;
+		long err;
+
+		if (unlikely(!mm))
+			return -EFAULT;
+
+		err = slb_allocate_user(mm, ea);
+		if (!err)
+			preload_add(current_thread_info(), ea);
+
+		return err;
+	}
+}
+
+void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err)
+{
+	if (err == -EFAULT) {
+		if (user_mode(regs))
+			_exception(SIGSEGV, regs, SEGV_BNDERR, ea);
+		else
+			bad_page_fault(regs, ea, SIGSEGV);
+	} else if (err == -EINVAL) {
+		unrecoverable_exception(regs);
+	} else {
+		BUG();
+	}
+}
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c
similarity index 87%
rename from arch/powerpc/mm/subpage-prot.c
rename to arch/powerpc/mm/book3s64/subpage_prot.c
index 3327551..2ef24a5 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/book3s64/subpage_prot.c
@@ -1,17 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2007-2008 Paul Mackerras, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/types.h>
-#include <linux/mm.h>
+#include <linux/pagewalk.h>
 #include <linux/hugetlb.h>
 #include <linux/syscalls.h>
 
@@ -25,10 +21,13 @@
  */
 void subpage_prot_free(struct mm_struct *mm)
 {
-	struct subpage_prot_table *spt = &mm->context.spt;
+	struct subpage_prot_table *spt = mm_ctx_subpage_prot(&mm->context);
 	unsigned long i, j, addr;
 	u32 **p;
 
+	if (!spt)
+		return;
+
 	for (i = 0; i < 4; ++i) {
 		if (spt->low_prot[i]) {
 			free_page((unsigned long)spt->low_prot[i]);
@@ -48,13 +47,7 @@
 		free_page((unsigned long)p);
 	}
 	spt->maxaddr = 0;
-}
-
-void subpage_prot_init_new_context(struct mm_struct *mm)
-{
-	struct subpage_prot_table *spt = &mm->context.spt;
-
-	memset(spt, 0, sizeof(*spt));
+	kfree(spt);
 }
 
 static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
@@ -93,13 +86,18 @@
 static void subpage_prot_clear(unsigned long addr, unsigned long len)
 {
 	struct mm_struct *mm = current->mm;
-	struct subpage_prot_table *spt = &mm->context.spt;
+	struct subpage_prot_table *spt;
 	u32 **spm, *spp;
 	unsigned long i;
 	size_t nw;
 	unsigned long next, limit;
 
 	down_write(&mm->mmap_sem);
+
+	spt = mm_ctx_subpage_prot(&mm->context);
+	if (!spt)
+		goto err_out;
+
 	limit = addr + len;
 	if (limit > spt->maxaddr)
 		limit = spt->maxaddr;
@@ -127,6 +125,8 @@
 		/* now flush any existing HPTEs for the range */
 		hpte_flush_range(mm, addr, nw);
 	}
+
+err_out:
 	up_write(&mm->mmap_sem);
 }
 
@@ -139,14 +139,14 @@
 	return 0;
 }
 
+static const struct mm_walk_ops subpage_walk_ops = {
+	.pmd_entry	= subpage_walk_pmd_entry,
+};
+
 static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
 				    unsigned long len)
 {
 	struct vm_area_struct *vma;
-	struct mm_walk subpage_proto_walk = {
-		.mm = mm,
-		.pmd_entry = subpage_walk_pmd_entry,
-	};
 
 	/*
 	 * We don't try too hard, we just mark all the vma in that range
@@ -163,7 +163,7 @@
 		if (vma->vm_start >= (addr + len))
 			break;
 		vma->vm_flags |= VM_NOHUGEPAGE;
-		walk_page_vma(vma, &subpage_proto_walk);
+		walk_page_vma(vma, &subpage_walk_ops, NULL);
 		vma = vma->vm_next;
 	}
 }
@@ -189,7 +189,7 @@
 		unsigned long, len, u32 __user *, map)
 {
 	struct mm_struct *mm = current->mm;
-	struct subpage_prot_table *spt = &mm->context.spt;
+	struct subpage_prot_table *spt;
 	u32 **spm, *spp;
 	unsigned long i;
 	size_t nw;
@@ -214,10 +214,25 @@
 		return 0;
 	}
 
-	if (!access_ok(VERIFY_READ, map, (len >> PAGE_SHIFT) * sizeof(u32)))
+	if (!access_ok(map, (len >> PAGE_SHIFT) * sizeof(u32)))
 		return -EFAULT;
 
 	down_write(&mm->mmap_sem);
+
+	spt = mm_ctx_subpage_prot(&mm->context);
+	if (!spt) {
+		/*
+		 * Allocate subpage prot table if not already done.
+		 * Do this with mmap_sem held
+		 */
+		spt = kzalloc(sizeof(struct subpage_prot_table), GFP_KERNEL);
+		if (!spt) {
+			err = -ENOMEM;
+			goto out;
+		}
+		mm->context.hash_context->spt = spt;
+	}
+
 	subpage_mark_vma_nohuge(mm, addr, len);
 	for (limit = addr + len; addr < limit; addr = next) {
 		next = pmd_addr_end(addr, limit);
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index c8da352..beb060b 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * CoProcessor (SPU/AFU) mm fault handler
  *
@@ -5,20 +6,6 @@
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
  * Author: Jeremy Kerr <jk@ozlabs.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/sched.h>
 #include <linux/mm.h>
@@ -105,7 +92,7 @@
 	u64 vsid, vsidkey;
 	int psize, ssize;
 
-	switch (REGION_ID(ea)) {
+	switch (get_region_id(ea)) {
 	case USER_REGION_ID:
 		pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
 		if (mm == NULL)
@@ -117,16 +104,20 @@
 		break;
 	case VMALLOC_REGION_ID:
 		pr_devel("%s: 0x%llx -- VMALLOC_REGION_ID\n", __func__, ea);
-		if (ea < VMALLOC_END)
-			psize = mmu_vmalloc_psize;
-		else
-			psize = mmu_io_psize;
+		psize = mmu_vmalloc_psize;
 		ssize = mmu_kernel_ssize;
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
 		vsidkey = SLB_VSID_KERNEL;
 		break;
-	case KERNEL_REGION_ID:
-		pr_devel("%s: 0x%llx -- KERNEL_REGION_ID\n", __func__, ea);
+	case IO_REGION_ID:
+		pr_devel("%s: 0x%llx -- IO_REGION_ID\n", __func__, ea);
+		psize = mmu_io_psize;
+		ssize = mmu_kernel_ssize;
+		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		vsidkey = SLB_VSID_KERNEL;
+		break;
+	case LINEAR_MAP_REGION_ID:
+		pr_devel("%s: 0x%llx -- LINEAR_MAP_REGION_ID\n", __func__, ea);
 		psize = mmu_linear_psize;
 		ssize = mmu_kernel_ssize;
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 3825284..2a82984 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -1,320 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PowerPC version derived from arch/arm/mm/consistent.c
  *    Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
  *
  *  Copyright (C) 2000 Russell King
- *
- * Consistent memory allocators.  Used for DMA devices that want to
- * share uncached memory with the processor core.  The function return
- * is the virtual address and 'dma_handle' is the physical address.
- * Mostly stolen from the ARM port, with some changes for PowerPC.
- *						-- Dan
- *
- * Reorganized to get rid of the arch-specific consistent_* functions
- * and provide non-coherent implementations for the DMA API. -Matt
- *
- * Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent()
- * implementation. This is pulled straight from ARM and barely
- * modified. -Matt
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
-#include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
-#include <linux/string.h>
 #include <linux/types.h>
 #include <linux/highmem.h>
-#include <linux/dma-mapping.h>
-#include <linux/export.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 
 #include <asm/tlbflush.h>
 #include <asm/dma.h>
 
-#include "mmu_decl.h"
-
-/*
- * This address range defaults to a value that is safe for all
- * platforms which currently set CONFIG_NOT_COHERENT_CACHE. It
- * can be further configured for specific applications under
- * the "Advanced Setup" menu. -Matt
- */
-#define CONSISTENT_BASE		(IOREMAP_TOP)
-#define CONSISTENT_END 		(CONSISTENT_BASE + CONFIG_CONSISTENT_SIZE)
-#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
-
-/*
- * This is the page table (2MB) covering uncached, DMA consistent allocations
- */
-static DEFINE_SPINLOCK(consistent_lock);
-
-/*
- * VM region handling support.
- *
- * This should become something generic, handling VM region allocations for
- * vmalloc and similar (ioremap, module space, etc).
- *
- * I envisage vmalloc()'s supporting vm_struct becoming:
- *
- *  struct vm_struct {
- *    struct vm_region	region;
- *    unsigned long	flags;
- *    struct page	**pages;
- *    unsigned int	nr_pages;
- *    unsigned long	phys_addr;
- *  };
- *
- * get_vm_area() would then call vm_region_alloc with an appropriate
- * struct vm_region head (eg):
- *
- *  struct vm_region vmalloc_head = {
- *	.vm_list	= LIST_HEAD_INIT(vmalloc_head.vm_list),
- *	.vm_start	= VMALLOC_START,
- *	.vm_end		= VMALLOC_END,
- *  };
- *
- * However, vmalloc_head.vm_start is variable (typically, it is dependent on
- * the amount of RAM found at boot time.)  I would imagine that get_vm_area()
- * would have to initialise this each time prior to calling vm_region_alloc().
- */
-struct ppc_vm_region {
-	struct list_head	vm_list;
-	unsigned long		vm_start;
-	unsigned long		vm_end;
-};
-
-static struct ppc_vm_region consistent_head = {
-	.vm_list	= LIST_HEAD_INIT(consistent_head.vm_list),
-	.vm_start	= CONSISTENT_BASE,
-	.vm_end		= CONSISTENT_END,
-};
-
-static struct ppc_vm_region *
-ppc_vm_region_alloc(struct ppc_vm_region *head, size_t size, gfp_t gfp)
-{
-	unsigned long addr = head->vm_start, end = head->vm_end - size;
-	unsigned long flags;
-	struct ppc_vm_region *c, *new;
-
-	new = kmalloc(sizeof(struct ppc_vm_region), gfp);
-	if (!new)
-		goto out;
-
-	spin_lock_irqsave(&consistent_lock, flags);
-
-	list_for_each_entry(c, &head->vm_list, vm_list) {
-		if ((addr + size) < addr)
-			goto nospc;
-		if ((addr + size) <= c->vm_start)
-			goto found;
-		addr = c->vm_end;
-		if (addr > end)
-			goto nospc;
-	}
-
- found:
-	/*
-	 * Insert this entry _before_ the one we found.
-	 */
-	list_add_tail(&new->vm_list, &c->vm_list);
-	new->vm_start = addr;
-	new->vm_end = addr + size;
-
-	spin_unlock_irqrestore(&consistent_lock, flags);
-	return new;
-
- nospc:
-	spin_unlock_irqrestore(&consistent_lock, flags);
-	kfree(new);
- out:
-	return NULL;
-}
-
-static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsigned long addr)
-{
-	struct ppc_vm_region *c;
-
-	list_for_each_entry(c, &head->vm_list, vm_list) {
-		if (c->vm_start == addr)
-			goto out;
-	}
-	c = NULL;
- out:
-	return c;
-}
-
-/*
- * Allocate DMA-coherent memory space and return both the kernel remapped
- * virtual and bus address for that space.
- */
-void *
-__dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
-{
-	struct page *page;
-	struct ppc_vm_region *c;
-	unsigned long order;
-	u64 mask = ISA_DMA_THRESHOLD, limit;
-
-	if (dev) {
-		mask = dev->coherent_dma_mask;
-
-		/*
-		 * Sanity check the DMA mask - it must be non-zero, and
-		 * must be able to be satisfied by a DMA allocation.
-		 */
-		if (mask == 0) {
-			dev_warn(dev, "coherent DMA mask is unset\n");
-			goto no_page;
-		}
-
-		if ((~mask) & ISA_DMA_THRESHOLD) {
-			dev_warn(dev, "coherent DMA mask %#llx is smaller "
-				 "than system GFP_DMA mask %#llx\n",
-				 mask, (unsigned long long)ISA_DMA_THRESHOLD);
-			goto no_page;
-		}
-	}
-
-
-	size = PAGE_ALIGN(size);
-	limit = (mask + 1) & ~mask;
-	if ((limit && size >= limit) ||
-	    size >= (CONSISTENT_END - CONSISTENT_BASE)) {
-		printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n",
-		       size, mask);
-		return NULL;
-	}
-
-	order = get_order(size);
-
-	/* Might be useful if we ever have a real legacy DMA zone... */
-	if (mask != 0xffffffff)
-		gfp |= GFP_DMA;
-
-	page = alloc_pages(gfp, order);
-	if (!page)
-		goto no_page;
-
-	/*
-	 * Invalidate any data that might be lurking in the
-	 * kernel direct-mapped region for device DMA.
-	 */
-	{
-		unsigned long kaddr = (unsigned long)page_address(page);
-		memset(page_address(page), 0, size);
-		flush_dcache_range(kaddr, kaddr + size);
-	}
-
-	/*
-	 * Allocate a virtual address in the consistent mapping region.
-	 */
-	c = ppc_vm_region_alloc(&consistent_head, size,
-			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
-	if (c) {
-		unsigned long vaddr = c->vm_start;
-		struct page *end = page + (1 << order);
-
-		split_page(page, order);
-
-		/*
-		 * Set the "dma handle"
-		 */
-		*handle = page_to_phys(page);
-
-		do {
-			SetPageReserved(page);
-			map_kernel_page(vaddr, page_to_phys(page),
-				 pgprot_val(pgprot_noncached(PAGE_KERNEL)));
-			page++;
-			vaddr += PAGE_SIZE;
-		} while (size -= PAGE_SIZE);
-
-		/*
-		 * Free the otherwise unused pages.
-		 */
-		while (page < end) {
-			__free_page(page);
-			page++;
-		}
-
-		return (void *)c->vm_start;
-	}
-
-	if (page)
-		__free_pages(page, order);
- no_page:
-	return NULL;
-}
-EXPORT_SYMBOL(__dma_alloc_coherent);
-
-/*
- * free a page as defined by the above mapping.
- */
-void __dma_free_coherent(size_t size, void *vaddr)
-{
-	struct ppc_vm_region *c;
-	unsigned long flags, addr;
-	
-	size = PAGE_ALIGN(size);
-
-	spin_lock_irqsave(&consistent_lock, flags);
-
-	c = ppc_vm_region_find(&consistent_head, (unsigned long)vaddr);
-	if (!c)
-		goto no_area;
-
-	if ((c->vm_end - c->vm_start) != size) {
-		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
-		       __func__, c->vm_end - c->vm_start, size);
-		dump_stack();
-		size = c->vm_end - c->vm_start;
-	}
-
-	addr = c->vm_start;
-	do {
-		pte_t *ptep;
-		unsigned long pfn;
-
-		ptep = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(addr),
-							       addr),
-						    addr),
-					 addr);
-		if (!pte_none(*ptep) && pte_present(*ptep)) {
-			pfn = pte_pfn(*ptep);
-			pte_clear(&init_mm, addr, ptep);
-			if (pfn_valid(pfn)) {
-				struct page *page = pfn_to_page(pfn);
-				__free_reserved_page(page);
-			}
-		}
-		addr += PAGE_SIZE;
-	} while (size -= PAGE_SIZE);
-
-	flush_tlb_kernel_range(c->vm_start, c->vm_end);
-
-	list_del(&c->vm_list);
-
-	spin_unlock_irqrestore(&consistent_lock, flags);
-
-	kfree(c);
-	return;
-
- no_area:
-	spin_unlock_irqrestore(&consistent_lock, flags);
-	printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
-	       __func__, vaddr);
-	dump_stack();
-}
-EXPORT_SYMBOL(__dma_free_coherent);
-
 /*
  * make an area consistent.
  */
-void __dma_sync(void *vaddr, size_t size, int direction)
+static void __dma_sync(void *vaddr, size_t size, int direction)
 {
 	unsigned long start = (unsigned long)vaddr;
 	unsigned long end   = start + size;
@@ -340,7 +45,6 @@
 		break;
 	}
 }
-EXPORT_SYMBOL(__dma_sync);
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -387,34 +91,34 @@
  * __dma_sync_page makes memory consistent. identical to __dma_sync, but
  * takes a struct page instead of a virtual address
  */
-void __dma_sync_page(struct page *page, unsigned long offset,
-	size_t size, int direction)
+static void __dma_sync_page(phys_addr_t paddr, size_t size, int dir)
 {
+	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	unsigned offset = paddr & ~PAGE_MASK;
+
 #ifdef CONFIG_HIGHMEM
-	__dma_sync_page_highmem(page, offset, size, direction);
+	__dma_sync_page_highmem(page, offset, size, dir);
 #else
 	unsigned long start = (unsigned long)page_address(page) + offset;
-	__dma_sync((void *)start, size, direction);
+	__dma_sync((void *)start, size, dir);
 #endif
 }
-EXPORT_SYMBOL(__dma_sync_page);
 
-/*
- * Return the PFN for a given cpu virtual address returned by
- * __dma_alloc_coherent. This is used by dma_mmap_coherent()
- */
-unsigned long __dma_get_coherent_pfn(unsigned long cpu_addr)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	/* This should always be populated, so we don't test every
-	 * level. If that fails, we'll have a nice crash which
-	 * will be as good as a BUG_ON()
-	 */
-	pgd_t *pgd = pgd_offset_k(cpu_addr);
-	pud_t *pud = pud_offset(pgd, cpu_addr);
-	pmd_t *pmd = pmd_offset(pud, cpu_addr);
-	pte_t *ptep = pte_offset_kernel(pmd, cpu_addr);
+	__dma_sync_page(paddr, size, dir);
+}
 
-	if (pte_none(*ptep) || !pte_present(*ptep))
-		return 0;
-	return pte_pfn(*ptep);
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_sync_page(paddr, size, dir);
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	unsigned long kaddr = (unsigned long)page_address(page);
+
+	flush_dcache_range(kaddr, kaddr + size);
 }
diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
index 3f18036..59327ce 100644
--- a/arch/powerpc/mm/drmem.c
+++ b/arch/powerpc/mm/drmem.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Dynamic reconfiguration memory support
  *
  * Copyright 2017 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "drmem: " fmt
@@ -366,8 +362,10 @@
 	if (!drmem_info->lmbs)
 		return;
 
-	for_each_drmem_lmb(lmb)
+	for_each_drmem_lmb(lmb) {
 		read_drconf_v1_cell(lmb, &prop);
+		lmb_set_nid(lmb);
+	}
 }
 
 static void __init init_drmem_v2_lmbs(const __be32 *prop)
@@ -412,6 +410,8 @@
 
 			lmb->aa_index = dr_cell.aa_index;
 			lmb->flags = dr_cell.flags;
+
+			lmb_set_nid(lmb);
 		}
 	}
 }
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index d51cf5f..8432c28 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -8,11 +9,6 @@
  *  Modified by Cort Dougan and Paul Mackerras.
  *
  *  Modified for PPC64 by Dave Engebretsen (engebret@ibm.com)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/signal.h>
@@ -44,26 +40,7 @@
 #include <asm/mmu_context.h>
 #include <asm/siginfo.h>
 #include <asm/debug.h>
-
-static inline bool notify_page_fault(struct pt_regs *regs)
-{
-	bool ret = false;
-
-#ifdef CONFIG_KPROBES
-	/* kprobe_running() needs smp_processor_id() */
-	if (!user_mode(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, 11))
-			ret = true;
-		preempt_enable();
-	}
-#endif /* CONFIG_KPROBES */
-
-	if (unlikely(debugger_fault_handler(regs)))
-		ret = true;
-
-	return ret;
-}
+#include <asm/kup.h>
 
 /*
  * Check whether the instruction inst is a store using
@@ -103,8 +80,7 @@
  */
 
 static int
-__bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code,
-		int pkey)
+__bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code)
 {
 	/*
 	 * If we are in kernel mode, bail out with a SEGV, this will
@@ -114,18 +90,17 @@
 	if (!user_mode(regs))
 		return SIGSEGV;
 
-	_exception_pkey(SIGSEGV, regs, si_code, address, pkey);
+	_exception(SIGSEGV, regs, si_code, address);
 
 	return 0;
 }
 
 static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long address)
 {
-	return __bad_area_nosemaphore(regs, address, SEGV_MAPERR, 0);
+	return __bad_area_nosemaphore(regs, address, SEGV_MAPERR);
 }
 
-static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code,
-			int pkey)
+static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code)
 {
 	struct mm_struct *mm = current->mm;
 
@@ -135,54 +110,60 @@
 	 */
 	up_read(&mm->mmap_sem);
 
-	return __bad_area_nosemaphore(regs, address, si_code, pkey);
+	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, 0);
+	return __bad_area(regs, address, SEGV_MAPERR);
 }
 
 static int bad_key_fault_exception(struct pt_regs *regs, unsigned long address,
 				    int pkey)
 {
-	return __bad_area_nosemaphore(regs, address, SEGV_PKUERR, pkey);
+	/*
+	 * If we are in kernel mode, bail out with a SEGV, this will
+	 * be caught by the assembly which will restore the non-volatile
+	 * registers before calling bad_page_fault()
+	 */
+	if (!user_mode(regs))
+		return SIGSEGV;
+
+	_exception_pkey(regs, address, pkey);
+
+	return 0;
 }
 
 static noinline int bad_access(struct pt_regs *regs, unsigned long address)
 {
-	return __bad_area(regs, address, SEGV_ACCERR, 0);
+	return __bad_area(regs, address, SEGV_ACCERR);
 }
 
 static int do_sigbus(struct pt_regs *regs, unsigned long address,
 		     vm_fault_t fault)
 {
-	siginfo_t info;
-	unsigned int lsb = 0;
-
 	if (!user_mode(regs))
 		return SIGBUS;
 
 	current->thread.trap_nr = BUS_ADRERR;
-	clear_siginfo(&info);
-	info.si_signo = SIGBUS;
-	info.si_errno = 0;
-	info.si_code = BUS_ADRERR;
-	info.si_addr = (void __user *)address;
 #ifdef CONFIG_MEMORY_FAILURE
 	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+		unsigned int lsb = 0; /* shutup gcc */
+
 		pr_err("MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
 			current->comm, current->pid, address);
-		info.si_code = BUS_MCEERR_AR;
+
+		if (fault & VM_FAULT_HWPOISON_LARGE)
+			lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+		if (fault & VM_FAULT_HWPOISON)
+			lsb = PAGE_SHIFT;
+
+		force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb);
+		return 0;
 	}
 
-	if (fault & VM_FAULT_HWPOISON_LARGE)
-		lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
-	if (fault & VM_FAULT_HWPOISON)
-		lsb = PAGE_SHIFT;
 #endif
-	info.si_addr_lsb = lsb;
-	force_sig_info(SIGBUS, &info, current);
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
 	return 0;
 }
 
@@ -218,17 +199,46 @@
 }
 
 /* Is this a bad kernel fault ? */
-static bool bad_kernel_fault(bool is_exec, unsigned long error_code,
-			     unsigned long address)
+static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
+			     unsigned long address, bool is_write)
 {
-	if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT))) {
-		printk_ratelimited(KERN_CRIT "kernel tried to execute"
-				   " exec-protected page (%lx) -"
-				   "exploit attempt? (uid: %d)\n",
-				   address, from_kuid(&init_user_ns,
-						      current_uid()));
+	int is_exec = TRAP(regs) == 0x400;
+
+	/* NX faults set DSISR_PROTFAULT on the 8xx, DSISR_NOEXEC_OR_G on others */
+	if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT |
+				      DSISR_PROTFAULT))) {
+		pr_crit_ratelimited("kernel tried to execute %s page (%lx) - exploit attempt? (uid: %d)\n",
+				    address >= TASK_SIZE ? "exec-protected" : "user",
+				    address,
+				    from_kuid(&init_user_ns, current_uid()));
+
+		// Kernel exec fault is always bad
+		return true;
 	}
-	return is_exec || (address >= TASK_SIZE);
+
+	if (!is_exec && address < TASK_SIZE && (error_code & DSISR_PROTFAULT) &&
+	    !search_exception_tables(regs->nip)) {
+		pr_crit_ratelimited("Kernel attempted to access user page (%lx) - exploit attempt? (uid: %d)\n",
+				    address,
+				    from_kuid(&init_user_ns, current_uid()));
+	}
+
+	// Kernel fault on kernel address is bad
+	if (address >= TASK_SIZE)
+		return true;
+
+	// Fault on user outside of certain regions (eg. copy_tofrom_user()) is bad
+	if (!search_exception_tables(regs->nip))
+		return true;
+
+	// Read/write fault in a valid region (the exception table search passed
+	// above), but blocked by KUAP is bad, it can never succeed.
+	if (bad_kuap_fault(regs, is_write))
+		return true;
+
+	// What's left? Kernel fault on user in well defined regions (extable
+	// matched), and allowed by KUAP in the faulting context.
+	return false;
 }
 
 static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
@@ -267,7 +277,7 @@
 			return false;
 
 		if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) &&
-		    access_ok(VERIFY_READ, nip, sizeof(*nip))) {
+		    access_ok(nip, sizeof(*nip))) {
 			unsigned int inst;
 			int res;
 
@@ -336,10 +346,21 @@
 static inline void cmo_account_page_fault(void) { }
 #endif /* CONFIG_PPC_SMLPAR */
 
-#ifdef CONFIG_PPC_STD_MMU
-static void sanity_check_fault(bool is_write, unsigned long error_code)
+#ifdef CONFIG_PPC_BOOK3S
+static void sanity_check_fault(bool is_write, bool is_user,
+			       unsigned long error_code, unsigned long address)
 {
 	/*
+	 * Userspace trying to access kernel address, we get PROTFAULT for that.
+	 */
+	if (is_user && address >= TASK_SIZE) {
+		pr_crit_ratelimited("%s[%d]: User access of kernel address (%lx) - exploit attempt? (uid: %d)\n",
+				   current->comm, current->pid, address,
+				   from_kuid(&init_user_ns, current_uid()));
+		return;
+	}
+
+	/*
 	 * For hash translation mode, we should never get a
 	 * PROTFAULT. Any update to pte to reduce access will result in us
 	 * removing the hash page table entry, thus resulting in a DSISR_NOHPTE
@@ -368,12 +389,15 @@
 	 * For radix, we can get prot fault for autonuma case, because radix
 	 * page table will have them marked noaccess for user.
 	 */
-	if (!radix_enabled() && !is_write)
-		WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
+	if (radix_enabled() || is_write)
+		return;
+
+	WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
 }
 #else
-static void sanity_check_fault(bool is_write, unsigned long error_code) { }
-#endif /* CONFIG_PPC_STD_MMU */
+static void sanity_check_fault(bool is_write, bool is_user,
+			       unsigned long error_code, unsigned long address) { }
+#endif /* CONFIG_PPC_BOOK3S */
 
 /*
  * Define the correct "is_write" bit in error_code based
@@ -417,8 +441,9 @@
 	int is_write = page_fault_is_write(error_code);
 	vm_fault_t fault, major = 0;
 	bool must_retry = false;
+	bool kprobe_fault = kprobe_page_fault(regs, 11);
 
-	if (notify_page_fault(regs))
+	if (unlikely(debugger_fault_handler(regs) || kprobe_fault))
 		return 0;
 
 	if (unlikely(page_fault_is_bad(error_code))) {
@@ -430,13 +455,14 @@
 	}
 
 	/* Additional sanity check(s) */
-	sanity_check_fault(is_write, error_code);
+	sanity_check_fault(is_write, is_user, error_code, address);
 
 	/*
 	 * The kernel should never take an execute fault nor should it
-	 * take a page fault to a kernel address.
+	 * take a page fault to a kernel address or a page fault to a user
+	 * address outside of dedicated places
 	 */
-	if (unlikely(!is_user && bad_kernel_fault(is_exec, error_code, address)))
+	if (unlikely(!is_user && bad_kernel_fault(regs, error_code, address, is_write)))
 		return SIGSEGV;
 
 	/*
@@ -631,21 +657,23 @@
 	switch (TRAP(regs)) {
 	case 0x300:
 	case 0x380:
-		printk(KERN_ALERT "Unable to handle kernel paging request for "
-			"data at address 0x%08lx\n", regs->dar);
+	case 0xe00:
+		pr_alert("BUG: %s at 0x%08lx\n",
+			 regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" :
+			 "Unable to handle kernel data access", regs->dar);
 		break;
 	case 0x400:
 	case 0x480:
-		printk(KERN_ALERT "Unable to handle kernel paging request for "
-			"instruction fetch\n");
+		pr_alert("BUG: Unable to handle kernel instruction fetch%s",
+			 regs->nip < PAGE_SIZE ? " (NULL pointer?)\n" : "\n");
 		break;
 	case 0x600:
-		printk(KERN_ALERT "Unable to handle kernel paging request for "
-			"unaligned access at address 0x%08lx\n", regs->dar);
+		pr_alert("BUG: Unable to handle kernel unaligned access at 0x%08lx\n",
+			 regs->dar);
 		break;
 	default:
-		printk(KERN_ALERT "Unable to handle kernel paging request for "
-			"unknown fault\n");
+		pr_alert("BUG: Unable to handle unknown paging fault at 0x%08lx\n",
+			 regs->dar);
 		break;
 	}
 	printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n",
diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c
index 82a0e37..320c167 100644
--- a/arch/powerpc/mm/highmem.c
+++ b/arch/powerpc/mm/highmem.c
@@ -43,9 +43,7 @@
 	type = kmap_atomic_idx_push();
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-#ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(kmap_pte-idx)));
-#endif
+	WARN_ON(IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !pte_none(*(kmap_pte - idx)));
 	__set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot), 1);
 	local_flush_tlb_page(NULL, vaddr);
 
@@ -56,7 +54,6 @@
 void __kunmap_atomic(void *kvaddr)
 {
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-	int type __maybe_unused;
 
 	if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
 		pagefault_enable();
@@ -64,14 +61,12 @@
 		return;
 	}
 
-	type = kmap_atomic_idx();
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-	{
+	if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM)) {
+		int type = kmap_atomic_idx();
 		unsigned int idx;
 
 		idx = type + KM_TYPE_NR * smp_processor_id();
-		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
+		WARN_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
 
 		/*
 		 * force other mappings to Oops if they'll try to access
@@ -80,7 +75,6 @@
 		pte_clear(&init_mm, vaddr, kmap_pte-idx);
 		local_flush_tlb_page(NULL, vaddr);
 	}
-#endif
 
 	kmap_atomic_idx_pop();
 	pagefault_enable();
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 7296a42..73d4873 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -15,7 +15,6 @@
 #include <linux/export.h>
 #include <linux/of_fdt.h>
 #include <linux/memblock.h>
-#include <linux/bootmem.h>
 #include <linux/moduleparam.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
@@ -27,22 +26,12 @@
 #include <asm/hugetlb.h>
 #include <asm/pte-walk.h>
 
-
-#ifdef CONFIG_HUGETLB_PAGE
-
-#define PAGE_SHIFT_64K	16
-#define PAGE_SHIFT_512K	19
-#define PAGE_SHIFT_8M	23
-#define PAGE_SHIFT_16M	24
-#define PAGE_SHIFT_16G	34
-
 bool hugetlb_disabled = false;
 
-unsigned int HPAGE_SHIFT;
-EXPORT_SYMBOL(HPAGE_SHIFT);
-
 #define hugepd_none(hpd)	(hpd_val(hpd) == 0)
 
+#define PTE_T_ORDER	(__builtin_ffs(sizeof(pte_t)) - __builtin_ffs(sizeof(void *)))
+
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
 	/*
@@ -62,19 +51,27 @@
 	int num_hugepd;
 
 	if (pshift >= pdshift) {
-		cachep = hugepte_cache;
+		cachep = PGT_CACHE(PTE_T_ORDER);
 		num_hugepd = 1 << (pshift - pdshift);
+	} else if (IS_ENABLED(CONFIG_PPC_8xx)) {
+		cachep = PGT_CACHE(PTE_INDEX_SIZE);
+		num_hugepd = 1;
 	} else {
 		cachep = PGT_CACHE(pdshift - pshift);
 		num_hugepd = 1;
 	}
 
-	new = kmem_cache_zalloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
+	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));
 
 	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
 	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
 
-	if (! new)
+	if (!new)
 		return -ENOMEM;
 
 	/*
@@ -94,19 +91,7 @@
 	for (i = 0; i < num_hugepd; i++, hpdp++) {
 		if (unlikely(!hugepd_none(*hpdp)))
 			break;
-		else {
-#ifdef CONFIG_PPC_BOOK3S_64
-			*hpdp = __hugepd(__pa(new) |
-					 (shift_to_mmu_psize(pshift) << 2));
-#elif defined(CONFIG_PPC_8xx)
-			*hpdp = __hugepd(__pa(new) | _PMD_USER |
-					 (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M :
-					  _PMD_PAGE_512K) | _PMD_PRESENT);
-#else
-			/* We use the old format for PPC_FSL_BOOK3E */
-			*hpdp = __hugepd(((unsigned long)new & ~PD_HUGE) | pshift);
-#endif
-		}
+		hugepd_populate(hpdp, new, pshift);
 	}
 	/* If we bailed from the for loop early, an error occurred, clean up */
 	if (i < num_hugepd) {
@@ -150,6 +135,8 @@
 	} else {
 		pdshift = PUD_SHIFT;
 		pu = pud_alloc(mm, pg, addr);
+		if (!pu)
+			return NULL;
 		if (pshift == PUD_SHIFT)
 			return (pte_t *)pu;
 		else if (pshift > PMD_SHIFT) {
@@ -158,6 +145,8 @@
 		} else {
 			pdshift = PMD_SHIFT;
 			pm = pmd_alloc(mm, pu, addr);
+			if (!pm)
+				return NULL;
 			if (pshift == PMD_SHIFT)
 				/* 16MB hugepage */
 				return (pte_t *)pm;
@@ -174,12 +163,16 @@
 	} else {
 		pdshift = PUD_SHIFT;
 		pu = pud_alloc(mm, pg, 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;
 		}
@@ -246,7 +239,7 @@
 	return __alloc_bootmem_huge_page(h);
 }
 
-#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
+#ifndef CONFIG_PPC_BOOK3S_64
 #define HUGEPD_FREELIST_SIZE \
 	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
 
@@ -265,7 +258,7 @@
 	unsigned int i;
 
 	for (i = 0; i < batch->index; i++)
-		kmem_cache_free(hugepte_cache, batch->ptes[i]);
+		kmem_cache_free(PGT_CACHE(PTE_T_ORDER), batch->ptes[i]);
 
 	free_page((unsigned long)batch);
 }
@@ -278,7 +271,7 @@
 
 	if (atomic_read(&tlb->mm->mm_users) < 2 ||
 	    mm_is_thread_local(tlb->mm)) {
-		kmem_cache_free(hugepte_cache, hugepte);
+		kmem_cache_free(PGT_CACHE(PTE_T_ORDER), hugepte);
 		put_cpu_var(hugepd_freelist_cur);
 		return;
 	}
@@ -290,7 +283,7 @@
 
 	(*batchp)->ptes[(*batchp)->index++] = hugepte;
 	if ((*batchp)->index == HUGEPD_FREELIST_SIZE) {
-		call_rcu_sched(&(*batchp)->rcu, hugepd_free_rcu_callback);
+		call_rcu(&(*batchp)->rcu, hugepd_free_rcu_callback);
 		*batchp = NULL;
 	}
 	put_cpu_var(hugepd_freelist_cur);
@@ -330,6 +323,9 @@
 
 	if (shift >= pdshift)
 		hugepd_free(tlb, hugepte);
+	else if (IS_ENABLED(CONFIG_PPC_8xx))
+		pgtable_free_tlb(tlb, hugepte,
+				 get_hugepd_cache_index(PTE_INDEX_SIZE));
 	else
 		pgtable_free_tlb(tlb, hugepte,
 				 get_hugepd_cache_index(pdshift - shift));
@@ -528,30 +524,6 @@
 	return page;
 }
 
-static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
-				      unsigned long sz)
-{
-	unsigned long __boundary = (addr + sz) & ~(sz-1);
-	return (__boundary - 1 < end - 1) ? __boundary : end;
-}
-
-int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned pdshift,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	pte_t *ptep;
-	unsigned long sz = 1UL << hugepd_shift(hugepd);
-	unsigned long next;
-
-	ptep = hugepte_offset(hugepd, addr, pdshift);
-	do {
-		next = hugepte_addr_end(addr, end, sz);
-		if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
-			return 0;
-	} while (ptep++, addr = next, addr != end);
-
-	return 1;
-}
-
 #ifdef CONFIG_PPC_MM_SLICES
 unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long len, unsigned long pgoff,
@@ -571,24 +543,15 @@
 
 unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 {
-#ifdef CONFIG_PPC_MM_SLICES
 	/* With radix we don't use slice, so derive it from vma*/
-	if (!radix_enabled()) {
+	if (IS_ENABLED(CONFIG_PPC_MM_SLICES) && !radix_enabled()) {
 		unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
 
 		return 1UL << mmu_psize_to_shift(psize);
 	}
-#endif
 	return vma_kernel_pagesize(vma);
 }
 
-static inline bool is_power_of_4(unsigned long x)
-{
-	if (is_power_of_2(x))
-		return (__ilog2(x) % 2) ? false : true;
-	return false;
-}
-
 static int __init add_huge_page_size(unsigned long long size)
 {
 	int shift = __ffs(size);
@@ -596,36 +559,12 @@
 
 	/* Check that it is a page size supported by the hardware and
 	 * that it fits within pagetable and slice limits. */
-	if (size <= PAGE_SIZE)
-		return -EINVAL;
-#if defined(CONFIG_PPC_FSL_BOOK3E)
-	if (!is_power_of_4(size))
-		return -EINVAL;
-#elif !defined(CONFIG_PPC_8xx)
-	if (!is_power_of_2(size) || (shift > SLICE_HIGH_SHIFT))
-		return -EINVAL;
-#endif
-
-	if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
+	if (size <= PAGE_SIZE || !is_power_of_2(size))
 		return -EINVAL;
 
-#ifdef CONFIG_PPC_BOOK3S_64
-	/*
-	 * We need to make sure that for different page sizes reported by
-	 * firmware we only add hugetlb support for page sizes that can be
-	 * supported by linux page table layout.
-	 * For now we have
-	 * Radix: 2M and 1G
-	 * Hash: 16M and 16G
-	 */
-	if (radix_enabled()) {
-		if (mmu_psize != MMU_PAGE_2M && mmu_psize != MMU_PAGE_1G)
-			return -EINVAL;
-	} else {
-		if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G)
-			return -EINVAL;
-	}
-#endif
+	mmu_psize = check_and_get_huge_psize(shift);
+	if (mmu_psize < 0)
+		return -EINVAL;
 
 	BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);
 
@@ -653,9 +592,9 @@
 }
 __setup("hugepagesz=", hugepage_setup_sz);
 
-struct kmem_cache *hugepte_cache;
 static int __init hugetlbpage_init(void)
 {
+	bool configured = false;
 	int psize;
 
 	if (hugetlb_disabled) {
@@ -663,10 +602,10 @@
 		return 0;
 	}
 
-#if !defined(CONFIG_PPC_FSL_BOOK3E) && !defined(CONFIG_PPC_8xx)
-	if (!radix_enabled() && !mmu_has_feature(MMU_FTR_16M_PAGE))
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled() &&
+	    !mmu_has_feature(MMU_FTR_16M_PAGE))
 		return -ENODEV;
-#endif
+
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 		unsigned shift;
 		unsigned pdshift;
@@ -700,44 +639,22 @@
 		 * if we have pdshift and shift value same, we don't
 		 * use pgt cache for hugepd.
 		 */
-		if (pdshift > shift)
-			pgtable_cache_add(pdshift - shift, NULL);
-#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
-		else if (!hugepte_cache) {
-			/*
-			 * Create a kmem cache for hugeptes.  The bottom bits in
-			 * the pte have size information encoded in them, so
-			 * align them to allow this
-			 */
-			hugepte_cache = kmem_cache_create("hugepte-cache",
-							  sizeof(pte_t),
-							  HUGEPD_SHIFT_MASK + 1,
-							  0, NULL);
-			if (hugepte_cache == NULL)
-				panic("%s: Unable to create kmem cache "
-				      "for hugeptes\n", __func__);
+		if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx))
+			pgtable_cache_add(PTE_INDEX_SIZE);
+		else if (pdshift > shift)
+			pgtable_cache_add(pdshift - shift);
+		else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx))
+			pgtable_cache_add(PTE_T_ORDER);
 
-		}
-#endif
+		configured = true;
 	}
 
-#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
-	/* Default hpage size = 4M on FSL_BOOK3E and 512k on 8xx */
-	if (mmu_psize_defs[MMU_PAGE_4M].shift)
-		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_4M].shift;
-	else if (mmu_psize_defs[MMU_PAGE_512K].shift)
-		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_512K].shift;
-#else
-	/* Set default large page size. Currently, we pick 16M or 1M
-	 * depending on what is available
-	 */
-	if (mmu_psize_defs[MMU_PAGE_16M].shift)
-		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_16M].shift;
-	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
-		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift;
-	else if (mmu_psize_defs[MMU_PAGE_2M].shift)
-		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_2M].shift;
-#endif
+	if (configured) {
+		if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE))
+			hugetlbpage_init_default();
+	} else
+		pr_info("Failed to initialize. Disabling HugeTLB");
+
 	return 0;
 }
 
@@ -750,7 +667,7 @@
 
 	BUG_ON(!PageCompound(page));
 
-	for (i = 0; i < (1UL << compound_order(page)); i++) {
+	for (i = 0; i < compound_nr(page); i++) {
 		if (!PageHighMem(page)) {
 			__flush_dcache_icache(page_address(page+i));
 		} else {
@@ -760,152 +677,3 @@
 		}
 	}
 }
-
-#endif /* CONFIG_HUGETLB_PAGE */
-
-/*
- * We have 4 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 the page and take a ref on it.
- * This function need to be called with interrupts disabled. We use this variant
- * when we have MSR[EE] = 0 but the paca->irq_soft_mask = IRQS_ENABLED
- */
-pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
-			bool *is_thp, unsigned *hpage_shift)
-{
-	pgd_t pgd, *pgdp;
-	pud_t pud, *pudp;
-	pmd_t pmd, *pmdp;
-	pte_t *ret_pte;
-	hugepd_t *hpdp = NULL;
-	unsigned pdshift = PGDIR_SHIFT;
-
-	if (hpage_shift)
-		*hpage_shift = 0;
-
-	if (is_thp)
-		*is_thp = false;
-
-	pgdp = pgdir + pgd_index(ea);
-	pgd  = READ_ONCE(*pgdp);
-	/*
-	 * Always operate on the local stack value. This make sure the
-	 * value don't get updated by a parallel THP split/collapse,
-	 * page fault or a page unmap. The return pte_t * is still not
-	 * stable. So should be checked there for above conditions.
-	 */
-	if (pgd_none(pgd))
-		return NULL;
-	else if (pgd_huge(pgd)) {
-		ret_pte = (pte_t *) pgdp;
-		goto out;
-	} else if (is_hugepd(__hugepd(pgd_val(pgd))))
-		hpdp = (hugepd_t *)&pgd;
-	else {
-		/*
-		 * Even if we end up with an unmap, the pgtable will not
-		 * be freed, because we do an rcu free and here we are
-		 * irq disabled
-		 */
-		pdshift = PUD_SHIFT;
-		pudp = pud_offset(&pgd, ea);
-		pud  = READ_ONCE(*pudp);
-
-		if (pud_none(pud))
-			return NULL;
-		else if (pud_huge(pud)) {
-			ret_pte = (pte_t *) pudp;
-			goto out;
-		} else if (is_hugepd(__hugepd(pud_val(pud))))
-			hpdp = (hugepd_t *)&pud;
-		else {
-			pdshift = PMD_SHIFT;
-			pmdp = pmd_offset(&pud, ea);
-			pmd  = READ_ONCE(*pmdp);
-			/*
-			 * A hugepage collapse is captured by pmd_none, because
-			 * it mark the pmd none and do a hpte invalidate.
-			 */
-			if (pmd_none(pmd))
-				return NULL;
-
-			if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
-				if (is_thp)
-					*is_thp = true;
-				ret_pte = (pte_t *) pmdp;
-				goto out;
-			}
-
-			if (pmd_huge(pmd)) {
-				ret_pte = (pte_t *) pmdp;
-				goto out;
-			} else if (is_hugepd(__hugepd(pmd_val(pmd))))
-				hpdp = (hugepd_t *)&pmd;
-			else
-				return pte_offset_kernel(&pmd, ea);
-		}
-	}
-	if (!hpdp)
-		return NULL;
-
-	ret_pte = hugepte_offset(*hpdp, ea, pdshift);
-	pdshift = hugepd_shift(*hpdp);
-out:
-	if (hpage_shift)
-		*hpage_shift = pdshift;
-	return ret_pte;
-}
-EXPORT_SYMBOL_GPL(__find_linux_pte);
-
-int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long pte_end;
-	struct page *head, *page;
-	pte_t pte;
-	int refs;
-
-	pte_end = (addr + sz) & ~(sz-1);
-	if (pte_end < end)
-		end = pte_end;
-
-	pte = READ_ONCE(*ptep);
-
-	if (!pte_access_permitted(pte, write))
-		return 0;
-
-	/* hugepages are never "special" */
-	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-	refs = 0;
-	head = pte_page(pte);
-
-	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index 2b656e6..a84da92 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -11,12 +12,6 @@
  *
  *  Dave Engebretsen <engebret@us.ibm.com>
  *      Rework for PPC64 port.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #undef DEBUG
@@ -24,23 +19,67 @@
 #include <linux/string.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
+#include <asm/kup.h>
 
-static void pgd_ctor(void *addr)
+static bool disable_kuep = !IS_ENABLED(CONFIG_PPC_KUEP);
+static bool disable_kuap = !IS_ENABLED(CONFIG_PPC_KUAP);
+
+static int __init parse_nosmep(char *p)
 {
-	memset(addr, 0, PGD_TABLE_SIZE);
+	disable_kuep = true;
+	pr_warn("Disabling Kernel Userspace Execution Prevention\n");
+	return 0;
+}
+early_param("nosmep", parse_nosmep);
+
+static int __init parse_nosmap(char *p)
+{
+	disable_kuap = true;
+	pr_warn("Disabling Kernel Userspace Access Protection\n");
+	return 0;
+}
+early_param("nosmap", parse_nosmap);
+
+void __ref setup_kup(void)
+{
+	setup_kuep(disable_kuep);
+	setup_kuap(disable_kuap);
 }
 
-static void pud_ctor(void *addr)
-{
-	memset(addr, 0, PUD_TABLE_SIZE);
+#define CTOR(shift) static void ctor_##shift(void *addr) \
+{							\
+	memset(addr, 0, sizeof(void *) << (shift));	\
 }
 
-static void pmd_ctor(void *addr)
+CTOR(0); CTOR(1); CTOR(2); CTOR(3); CTOR(4); CTOR(5); CTOR(6); CTOR(7);
+CTOR(8); CTOR(9); CTOR(10); CTOR(11); CTOR(12); CTOR(13); CTOR(14); CTOR(15);
+
+static inline void (*ctor(int shift))(void *)
 {
-	memset(addr, 0, PMD_TABLE_SIZE);
+	BUILD_BUG_ON(MAX_PGTABLE_INDEX_SIZE != 15);
+
+	switch (shift) {
+	case 0: return ctor_0;
+	case 1: return ctor_1;
+	case 2: return ctor_2;
+	case 3: return ctor_3;
+	case 4: return ctor_4;
+	case 5: return ctor_5;
+	case 6: return ctor_6;
+	case 7: return ctor_7;
+	case 8: return ctor_8;
+	case 9: return ctor_9;
+	case 10: return ctor_10;
+	case 11: return ctor_11;
+	case 12: return ctor_12;
+	case 13: return ctor_13;
+	case 14: return ctor_14;
+	case 15: return ctor_15;
+	}
+	return NULL;
 }
 
-struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
+struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE + 1];
 EXPORT_SYMBOL_GPL(pgtable_cache);	/* used by kvm_hv module */
 
 /*
@@ -50,7 +89,7 @@
  * everything else.  Caches created by this function are used for all
  * the higher level pagetables, and for hugepage pagetables.
  */
-void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
+void pgtable_cache_add(unsigned int shift)
 {
 	char *name;
 	unsigned long table_size = sizeof(void *) << shift;
@@ -71,19 +110,19 @@
 	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
 	 * constant expression, so so much for that. */
 	BUG_ON(!is_power_of_2(minalign));
-	BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
 
 	if (PGT_CACHE(shift))
 		return; /* Already have a cache of this size */
 
 	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);
+	new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
 	if (!new)
 		panic("Could not allocate pgtable cache for order %d", shift);
 
 	kfree(name);
-	pgtable_cache[shift - 1] = new;
+	pgtable_cache[shift] = new;
 
 	pr_debug("Allocated pgtable cache for order %d\n", shift);
 }
@@ -91,15 +130,15 @@
 
 void pgtable_cache_init(void)
 {
-	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
+	pgtable_cache_add(PGD_INDEX_SIZE);
 
-	if (PMD_CACHE_INDEX && !PGT_CACHE(PMD_CACHE_INDEX))
-		pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+	if (PMD_CACHE_INDEX)
+		pgtable_cache_add(PMD_CACHE_INDEX);
 	/*
 	 * In all current configs, when the PUD index exists it's the
 	 * same size as either the pgd or pmd index except with THP enabled
 	 * on book3s 64
 	 */
-	if (PUD_CACHE_INDEX && !PGT_CACHE(PUD_CACHE_INDEX))
-		pgtable_cache_add(PUD_CACHE_INDEX, pud_ctor);
+	if (PUD_CACHE_INDEX)
+		pgtable_cache_add(PUD_CACHE_INDEX);
 }
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 3e59e5d..b04896a 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -9,12 +10,6 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/module.h>
@@ -45,8 +40,10 @@
 #include <asm/tlb.h>
 #include <asm/sections.h>
 #include <asm/hugetlb.h>
+#include <asm/kup.h>
+#include <asm/kasan.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 #if defined(CONFIG_KERNEL_START_BOOL) || defined(CONFIG_LOWMEM_SIZE_BOOL)
 /* The amount of lowmem must be within 0xF0000000 - KERNELBASE. */
@@ -108,12 +105,8 @@
 		__map_without_bats = 1;
 		__map_without_ltlbs = 1;
 	}
-#ifdef CONFIG_STRICT_KERNEL_RWX
-	if (rodata_enabled) {
-		__map_without_bats = 1;
+	if (strict_kernel_rwx_enabled() && !IS_ENABLED(CONFIG_PPC_8xx))
 		__map_without_ltlbs = 1;
-	}
-#endif
 }
 
 /*
@@ -182,6 +175,10 @@
 	btext_unmap();
 #endif
 
+	kasan_mmu_init();
+
+	setup_kup();
+
 	/* 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 7a9886f..4e08246 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -11,12 +12,6 @@
  *
  *  Dave Engebretsen <engebret@us.ibm.com>
  *      Rework for PPC64 port.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #undef DEBUG
@@ -66,7 +61,7 @@
 #include <asm/iommu.h>
 #include <asm/vdso.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 phys_addr_t memstart_addr = ~0;
 EXPORT_SYMBOL_GPL(memstart_addr);
@@ -177,6 +172,21 @@
 	vmemmap_list = vmem_back;
 }
 
+static 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)
+		return true;
+
+	if (start_pfn < altmap->base_pfn)
+		return true;
+
+	return false;
+}
+
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
@@ -188,15 +198,23 @@
 	pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);
 
 	for (; start < end; start += page_size) {
-		void *p;
+		void *p = NULL;
 		int rc;
 
 		if (vmemmap_populated(start, page_size))
 			continue;
 
-		if (altmap)
+		/*
+		 * Allocate from the altmap first if we have one. This may
+		 * fail due to alignment issues when using 16MB hugepages, so
+		 * fall back to system memory if the altmap allocation fail.
+		 */
+		if (altmap && !altmap_cross_boundary(altmap, start, page_size)) {
 			p = altmap_alloc_block_buf(page_size, altmap);
-		else
+			if (!p)
+				pr_debug("altmap block allocation failed, falling back to system memory");
+		}
+		if (!p)
 			p = vmemmap_alloc_block_buf(page_size, node);
 		if (!p)
 			return -ENOMEM;
@@ -255,14 +273,20 @@
 {
 	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
 	unsigned long page_order = get_order(page_size);
+	unsigned long alt_start = ~0, alt_end = ~0;
+	unsigned long base_pfn;
 
 	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;
+	}
 
 	pr_debug("vmemmap_free %lx...%lx\n", start, end);
 
 	for (; start < end; start += page_size) {
 		unsigned long nr_pages, addr;
-		struct page *section_base;
 		struct page *page;
 
 		/*
@@ -278,10 +302,10 @@
 			continue;
 
 		page = pfn_to_page(addr >> PAGE_SHIFT);
-		section_base = pfn_to_page(vmemmap_section_start(start));
 		nr_pages = 1 << page_order;
+		base_pfn = PHYS_PFN(addr);
 
-		if (altmap) {
+		if (base_pfn >= alt_start && base_pfn < alt_end) {
 			vmem_altmap_free(altmap, nr_pages);
 		} else if (PageReserved(page)) {
 			/* allocated from bootmem */
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
new file mode 100644
index 0000000..fc66964
--- /dev/null
+++ b/arch/powerpc/mm/ioremap.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <asm/io-workarounds.h>
+
+unsigned long ioremap_bot;
+EXPORT_SYMBOL(ioremap_bot);
+
+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);
+
+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);
+
+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)
+{
+	pte_t pte = __pte(flags);
+	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);
+
+int early_ioremap_range(unsigned long ea, phys_addr_t pa,
+			unsigned long size, pgprot_t prot)
+{
+	unsigned long i;
+
+	for (i = 0; i < size; i += PAGE_SIZE) {
+		int err = map_kernel_page(ea + i, pa + i, prot);
+
+		if (WARN_ON_ONCE(err))  /* Should clean up */
+			return err;
+	}
+
+	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;
+
+	unmap_kernel_range(va, size);
+	free_vm_area(area);
+
+	return NULL;
+}
diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c
new file mode 100644
index 0000000..f36121f
--- /dev/null
+++ b/arch/powerpc/mm/ioremap_32.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+#include <mm/mmu_decl.h>
+
+void __iomem *ioremap_wt(phys_addr_t addr, unsigned long size)
+{
+	pgprot_t prot = pgprot_cached_wthru(PAGE_KERNEL);
+
+	return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wt);
+
+void __iomem *
+__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
+{
+	unsigned long v;
+	phys_addr_t p, offset;
+	int err;
+
+	/*
+	 * 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
+	 * (ioremap_bot records where we're up to).
+	 */
+	p = addr & PAGE_MASK;
+	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.
+	 * mem_init() sets high_memory so only do the check after that.
+	 */
+	if (slab_is_available() && p <= virt_to_phys(high_memory - 1) &&
+	    page_is_ram(__phys_to_pfn(p))) {
+		pr_warn("%s(): phys addr 0x%llx is RAM lr %ps\n", __func__,
+			(unsigned long long)p, __builtin_return_address(0));
+		return NULL;
+	}
+#endif
+
+	if (size == 0)
+		return NULL;
+
+	/*
+	 * Is it already mapped?  Perhaps overlapped by a previous
+	 * mapping.
+	 */
+	v = p_block_mapped(p);
+	if (v)
+		return (void __iomem *)v + offset;
+
+	if (slab_is_available())
+		return do_ioremap(p, offset, size, prot, caller);
+
+	/*
+	 * Should check if it is a candidate for a BAT mapping
+	 */
+
+	err = early_ioremap_range(ioremap_bot - size, p, size, prot);
+	if (err)
+		return NULL;
+	ioremap_bot -= size;
+
+	return (void __iomem *)ioremap_bot + offset;
+}
+
+void iounmap(volatile void __iomem *addr)
+{
+	/*
+	 * If mapped by BATs then there is nothing to do.
+	 * Calling vfree() generates a benign warning.
+	 */
+	if (v_block_mapped((unsigned long)addr))
+		return;
+
+	if (addr > high_memory && (unsigned long)addr < ioremap_bot)
+		vunmap((void *)(PAGE_MASK & (unsigned long)addr));
+}
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c
new file mode 100644
index 0000000..fd29e51
--- /dev/null
+++ b/arch/powerpc/mm/ioremap_64.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+/**
+ * Low level function to establish the page tables for an IO mapping
+ */
+void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot)
+{
+	int ret;
+	unsigned long va = (unsigned long)ea;
+
+	/* We don't support the 4K PFN hack with ioremap */
+	if (pgprot_val(prot) & H_PAGE_4K_PFN)
+		return NULL;
+
+	if ((ea + size) >= (void *)IOREMAP_END) {
+		pr_warn("Outside the supported range\n");
+		return NULL;
+	}
+
+	WARN_ON(pa & ~PAGE_MASK);
+	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
+	WARN_ON(size & ~PAGE_MASK);
+
+	if (slab_is_available()) {
+		ret = ioremap_page_range(va, va + size, pa, prot);
+		if (ret)
+			unmap_kernel_range(va, size);
+	} else {
+		ret = early_ioremap_range(va, pa, size, prot);
+	}
+
+	if (ret)
+		return NULL;
+
+	return (void __iomem *)ea;
+}
+EXPORT_SYMBOL(__ioremap_at);
+
+/**
+ * Low level function to tear down the page tables for an IO mapping. This is
+ * used for mappings that are manipulated manually, like partial unmapping of
+ * PCI IOs or ISA space.
+ */
+void __iounmap_at(void *ea, unsigned long size)
+{
+	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
+	WARN_ON(size & ~PAGE_MASK);
+
+	unmap_kernel_range((unsigned long)ea, size);
+}
+EXPORT_SYMBOL(__iounmap_at);
+
+void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
+			       pgprot_t prot, void *caller)
+{
+	phys_addr_t paligned, offset;
+	void __iomem *ret;
+	int err;
+
+	/* We don't support the 4K PFN hack with ioremap */
+	if (pgprot_val(prot) & H_PAGE_4K_PFN)
+		return NULL;
+
+	/*
+	 * Choose an address to map it to. Once the vmalloc system is running,
+	 * we use it. Before that, we map using addresses going up from
+	 * ioremap_bot.  vmalloc will use the addresses from IOREMAP_BASE
+	 * through ioremap_bot.
+	 */
+	paligned = addr & PAGE_MASK;
+	offset = addr & ~PAGE_MASK;
+	size = PAGE_ALIGN(addr + size) - paligned;
+
+	if (size == 0 || paligned == 0)
+		return NULL;
+
+	if (slab_is_available())
+		return do_ioremap(paligned, offset, size, prot, caller);
+
+	err = early_ioremap_range(ioremap_bot, paligned, size, prot);
+	if (err)
+		return NULL;
+
+	ret = (void __iomem *)ioremap_bot + offset;
+	ioremap_bot += size;
+
+	return ret;
+}
+
+/*
+ * Unmap an IO region and remove it from vmalloc'd list.
+ * Access to IO memory should be serialized by driver.
+ */
+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);
+}
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/kasan/Makefile b/arch/powerpc/mm/kasan/Makefile
new file mode 100644
index 0000000..6577897
--- /dev/null
+++ b/arch/powerpc/mm/kasan/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+KASAN_SANITIZE := n
+
+obj-$(CONFIG_PPC32)           += kasan_init_32.o
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
new file mode 100644
index 0000000..0e6ed44
--- /dev/null
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define DISABLE_BRANCH_PROFILING
+
+#include <linux/kasan.h>
+#include <linux/printk.h>
+#include <linux/memblock.h>
+#include <linux/moduleloader.h>
+#include <linux/sched/task.h>
+#include <linux/vmalloc.h>
+#include <asm/pgalloc.h>
+#include <asm/code-patching.h>
+#include <mm/mmu_decl.h>
+
+static pgprot_t kasan_prot_ro(void)
+{
+	if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		return PAGE_READONLY;
+
+	return PAGE_KERNEL_RO;
+}
+
+static void kasan_populate_pte(pte_t *ptep, pgprot_t prot)
+{
+	unsigned long va = (unsigned long)kasan_early_shadow_page;
+	phys_addr_t pa = __pa(kasan_early_shadow_page);
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++, ptep++)
+		__set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0);
+}
+
+static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end)
+{
+	pmd_t *pmd;
+	unsigned long k_cur, k_next;
+	pgprot_t prot = slab_is_available() ? kasan_prot_ro() : PAGE_KERNEL;
+
+	pmd = pmd_offset(pud_offset(pgd_offset_k(k_start), k_start), k_start);
+
+	for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd++) {
+		pte_t *new;
+
+		k_next = pgd_addr_end(k_cur, k_end);
+		if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte)
+			continue;
+
+		if (slab_is_available())
+			new = pte_alloc_one_kernel(&init_mm);
+		else
+			new = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE);
+
+		if (!new)
+			return -ENOMEM;
+		kasan_populate_pte(new, prot);
+
+		smp_wmb(); /* See comment in __pte_alloc */
+
+		spin_lock(&init_mm.page_table_lock);
+			/* Has another populated it ? */
+		if (likely((void *)pmd_page_vaddr(*pmd) == kasan_early_shadow_pte)) {
+			pmd_populate_kernel(&init_mm, pmd, new);
+			new = NULL;
+		}
+		spin_unlock(&init_mm.page_table_lock);
+
+		if (new && slab_is_available())
+			pte_free_kernel(&init_mm, new);
+	}
+	return 0;
+}
+
+static void __ref *kasan_get_one_page(void)
+{
+	if (slab_is_available())
+		return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+
+	return memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static int __ref kasan_init_region(void *start, size_t size)
+{
+	unsigned long k_start = (unsigned long)kasan_mem_to_shadow(start);
+	unsigned long k_end = (unsigned long)kasan_mem_to_shadow(start + size);
+	unsigned long k_cur;
+	int ret;
+	void *block = NULL;
+
+	ret = kasan_init_shadow_page_tables(k_start, k_end);
+	if (ret)
+		return ret;
+
+	if (!slab_is_available())
+		block = memblock_alloc(k_end - k_start, PAGE_SIZE);
+
+	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
+		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
+		void *va = block ? block + k_cur - k_start : kasan_get_one_page();
+		pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL);
+
+		if (!va)
+			return -ENOMEM;
+
+		__set_pte_at(&init_mm, k_cur, pte_offset_kernel(pmd, k_cur), pte, 0);
+	}
+	flush_tlb_kernel_range(k_start, k_end);
+	return 0;
+}
+
+static void __init kasan_remap_early_shadow_ro(void)
+{
+	pgprot_t prot = kasan_prot_ro();
+	unsigned long k_start = KASAN_SHADOW_START;
+	unsigned long k_end = KASAN_SHADOW_END;
+	unsigned long k_cur;
+	phys_addr_t pa = __pa(kasan_early_shadow_page);
+
+	kasan_populate_pte(kasan_early_shadow_pte, prot);
+
+	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
+		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
+		pte_t *ptep = pte_offset_kernel(pmd, k_cur);
+
+		if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
+			continue;
+
+		__set_pte_at(&init_mm, k_cur, ptep, pfn_pte(PHYS_PFN(pa), prot), 0);
+	}
+	flush_tlb_kernel_range(KASAN_SHADOW_START, KASAN_SHADOW_END);
+}
+
+void __init kasan_mmu_init(void)
+{
+	int ret;
+	struct memblock_region *reg;
+
+	if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) {
+		ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+		if (ret)
+			panic("kasan: kasan_init_shadow_page_tables() failed");
+	}
+
+	for_each_memblock(memory, reg) {
+		phys_addr_t base = reg->base;
+		phys_addr_t top = min(base + reg->size, total_lowmem);
+
+		if (base >= top)
+			continue;
+
+		ret = kasan_init_region(__va(base), top - base);
+		if (ret)
+			panic("kasan: kasan_init_region() failed");
+	}
+}
+
+void __init kasan_init(void)
+{
+	kasan_remap_early_shadow_ro();
+
+	clear_page(kasan_early_shadow_page);
+
+	/* At this point kasan is fully initialized. Enable error messages */
+	init_task.kasan_depth = 0;
+	pr_info("KASAN init done\n");
+}
+
+#ifdef CONFIG_MODULES
+void *module_alloc(unsigned long size)
+{
+	void *base;
+
+	base = __vmalloc_node_range(size, MODULE_ALIGN, VMALLOC_START, VMALLOC_END,
+				    GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+				    NUMA_NO_NODE, __builtin_return_address(0));
+
+	if (!base)
+		return NULL;
+
+	if (!kasan_init_region(base, size))
+		return base;
+
+	vfree(base);
+
+	return NULL;
+}
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_32
+u8 __initdata early_hash[256 << 10] __aligned(256 << 10) = {0};
+
+static void __init kasan_early_hash_table(void)
+{
+	modify_instruction_site(&patch__hash_page_A0, 0xffff, __pa(early_hash) >> 16);
+	modify_instruction_site(&patch__flush_hash_A0, 0xffff, __pa(early_hash) >> 16);
+
+	Hash = (struct hash_pte *)early_hash;
+}
+#else
+static void __init kasan_early_hash_table(void) {}
+#endif
+
+void __init kasan_early_init(void)
+{
+	unsigned long addr = KASAN_SHADOW_START;
+	unsigned long end = KASAN_SHADOW_END;
+	unsigned long next;
+	pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(addr), addr), addr);
+
+	BUILD_BUG_ON(KASAN_SHADOW_START & ~PGDIR_MASK);
+
+	kasan_populate_pte(kasan_early_shadow_pte, PAGE_KERNEL);
+
+	do {
+		next = pgd_addr_end(addr, end);
+		pmd_populate_kernel(&init_mm, pmd, kasan_early_shadow_pte);
+	} while (pmd++, addr = next, addr != end);
+
+	if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		kasan_early_hash_table();
+}
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 04ccb27..be941d3 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -9,12 +10,6 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/export.h>
@@ -27,12 +22,11 @@
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/highmem.h>
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
 #include <linux/suspend.h>
-#include <linux/memblock.h>
 #include <linux/hugetlb.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
@@ -55,7 +49,7 @@
 #include <asm/swiotlb.h>
 #include <asm/rtas.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 #ifndef CPU_FTR_COHERENT_ICACHE
 #define CPU_FTR_COHERENT_ICACHE	0	/* XXX for now */
@@ -70,22 +64,14 @@
 EXPORT_SYMBOL(kmap_pte);
 pgprot_t kmap_prot;
 EXPORT_SYMBOL(kmap_prot);
-#define TOP_ZONE ZONE_HIGHMEM
 
 static inline pte_t *virt_to_kpte(unsigned long vaddr)
 {
 	return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
 			vaddr), vaddr), vaddr);
 }
-#else
-#define TOP_ZONE ZONE_NORMAL
 #endif
 
-int page_is_ram(unsigned long pfn)
-{
-	return memblock_is_memory(__pfn_to_phys(pfn));
-}
-
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
@@ -118,8 +104,8 @@
 	return -ENODEV;
 }
 
-int __meminit arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
-		bool want_memblock)
+int __ref arch_add_memory(int nid, u64 start, u64 size,
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -134,75 +120,36 @@
 			start, start + size, rc);
 		return -EFAULT;
 	}
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 
-	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
-int __meminit arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(int nid, u64 start, u64 size,
+			     struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct page *page;
+	struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
 	int ret;
 
-	/*
-	 * If we have an altmap then we need to skip over any reserved PFNs
-	 * when querying the zone.
-	 */
-	page = pfn_to_page(start_pfn);
-	if (altmap)
-		page += vmem_altmap_offset(altmap);
-
-	ret = __remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
-	if (ret)
-		return ret;
+	__remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
 
 	/* Remove htab bolted mappings for this section of memory */
 	start = (unsigned long)__va(start);
-	flush_inval_dcache_range(start, start + size);
+	flush_dcache_range(start, start + size);
 	ret = remove_section_mapping(start, start + size);
+	WARN_ON_ONCE(ret);
 
 	/* Ensure all vmalloc mappings are flushed in case they also
 	 * hit that section of memory
 	 */
 	vm_unmap_aliases();
 
-	resize_hpt_for_hotplug(memblock_phys_mem_size());
-
-	return ret;
+	if (resize_hpt_for_hotplug(memblock_phys_mem_size()) == -ENOSPC)
+		pr_warn("Hash collision while resizing HPT\n");
 }
 #endif
-#endif /* CONFIG_MEMORY_HOTPLUG */
-
-/*
- * walk_memory_resource() needs to make sure there is no holes in a given
- * memory range.  PPC64 does not maintain the memory layout in /proc/iomem.
- * Instead it maintains it in memblock.memory structures.  Walk through the
- * memory regions, find holes and callback for contiguous regions.
- */
-int
-walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
-		void *arg, int (*func)(unsigned long, unsigned long, void *))
-{
-	struct memblock_region *reg;
-	unsigned long end_pfn = start_pfn + nr_pages;
-	unsigned long tstart, tend;
-	int ret = -1;
-
-	for_each_memblock(memory, reg) {
-		tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
-		tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
-		if (tstart >= tend)
-			continue;
-		ret = (*func)(tstart, tend - tstart, arg);
-		if (ret)
-			break;
-	}
-	return ret;
-}
-EXPORT_SYMBOL_GPL(walk_system_ram_range);
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 void __init mem_topology_setup(void)
@@ -247,54 +194,19 @@
 }
 #endif
 
-static bool zone_limits_final;
-
 /*
- * The memory zones past TOP_ZONE are managed by generic mm code.
- * These should be set to zero since that's what every other
- * architecture does.
- */
-static unsigned long max_zone_pfns[MAX_NR_ZONES] = {
-	[0            ... TOP_ZONE        ] = ~0UL,
-	[TOP_ZONE + 1 ... MAX_NR_ZONES - 1] = 0
-};
-
-/*
- * Restrict the specified zone and all more restrictive zones
- * to be below the specified pfn.  May not be called after
- * paging_init().
- */
-void __init limit_zone_pfn(enum zone_type zone, unsigned long pfn_limit)
-{
-	int i;
-
-	if (WARN_ON(zone_limits_final))
-		return;
-
-	for (i = zone; i >= 0; i--) {
-		if (max_zone_pfns[i] > pfn_limit)
-			max_zone_pfns[i] = pfn_limit;
-	}
-}
-
-/*
- * Find the least restrictive zone that is entirely below the
- * specified pfn limit.  Returns < 0 if no suitable zone is found.
+ * Zones usage:
  *
- * pfn_limit must be u64 because it can exceed 32 bits even on 32-bit
- * systems -- the DMA limit can be higher than any possible real pfn.
+ * We setup ZONE_DMA to be 31-bits on all platforms and ZONE_NORMAL to be
+ * everything else. GFP_DMA32 page allocations automatically fall back to
+ * ZONE_DMA.
+ *
+ * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS 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.
  */
-int dma_pfn_limit_to_zone(u64 pfn_limit)
-{
-	int i;
-
-	for (i = TOP_ZONE; i >= 0; i--) {
-		if (max_zone_pfns[i] <= pfn_limit)
-			return i;
-	}
-
-	return -EPERM;
-}
+static unsigned long max_zone_pfns[MAX_NR_ZONES];
 
 /*
  * paging_init() sets up the page tables - in fact we've already done this.
@@ -309,11 +221,11 @@
 	unsigned long end = __fix_to_virt(FIX_HOLE);
 
 	for (; v < end; v += PAGE_SIZE)
-		map_kernel_page(v, 0, 0); /* XXX gross */
+		map_kernel_page(v, 0, __pgprot(0)); /* XXX gross */
 #endif
 
 #ifdef CONFIG_HIGHMEM
-	map_kernel_page(PKMAP_BASE, 0, 0);	/* XXX gross */
+	map_kernel_page(PKMAP_BASE, 0, __pgprot(0));	/* XXX gross */
 	pkmap_page_table = virt_to_kpte(PKMAP_BASE);
 
 	kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
@@ -325,11 +237,15 @@
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (long int)((top_of_ram - total_ram) >> 20));
 
-#ifdef CONFIG_HIGHMEM
-	limit_zone_pfn(ZONE_NORMAL, lowmem_end_addr >> PAGE_SHIFT);
+#ifdef CONFIG_ZONE_DMA
+	max_zone_pfns[ZONE_DMA]	= min(max_low_pfn,
+				      1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT));
 #endif
-	limit_zone_pfn(TOP_ZONE, top_of_ram >> PAGE_SHIFT);
-	zone_limits_final = true;
+	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+#ifdef CONFIG_HIGHMEM
+	max_zone_pfns[ZONE_HIGHMEM] = max_pfn;
+#endif
+
 	free_area_init_nodes(max_zone_pfns);
 
 	mark_nonram_nosave();
@@ -349,7 +265,7 @@
 
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 	set_max_mapnr(max_pfn);
-	free_all_bootmem();
+	memblock_free_all();
 
 #ifdef CONFIG_HIGHMEM
 	{
@@ -377,17 +293,18 @@
 	mem_init_print_info(NULL);
 #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 */
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	pr_info("  * 0x%08lx..0x%08lx  : consistent mem\n",
-		IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE);
-#endif /* CONFIG_NOT_COHERENT_CACHE */
-	pr_info("  * 0x%08lx..0x%08lx  : early ioremap\n",
-		ioremap_bot, IOREMAP_TOP);
+	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);
 #endif /* CONFIG_PPC32 */
@@ -401,13 +318,6 @@
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
 /*
  * This is called when a page has been modified by the kernel.
  * It just marks the page as not i-cache clean.  We do the i-cache
@@ -494,62 +404,6 @@
 EXPORT_SYMBOL(flush_icache_user_range);
 
 /*
- * This is called at the end of handling a user page fault, when the
- * fault has been handled by updating a PTE in the linux page tables.
- * We use it to preload an HPTE into the hash table corresponding to
- * the updated linux 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)
-{
-#ifdef CONFIG_PPC_STD_MMU
-	/*
-	 * We don't need to worry about _PAGE_PRESENT here because we are
-	 * called with either mm->page_table_lock held or ptl lock held
-	 */
-	unsigned long access, trap;
-
-	if (radix_enabled()) {
-		prefetch((void *)address);
-		return;
-	}
-
-	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
-	if (!pte_young(*ptep) || address >= TASK_SIZE)
-		return;
-
-	/* We try to figure out if we are coming from an instruction
-	 * access fault and pass that down to __hash_page so we avoid
-	 * double-faulting on execution of fresh text. We have to test
-	 * for regs NULL since init will get here first thing at boot
-	 *
-	 * We also avoid filling the hash if not coming from a fault
-	 */
-
-	trap = current->thread.regs ? TRAP(current->thread.regs) : 0UL;
-	switch (trap) {
-	case 0x300:
-		access = 0UL;
-		break;
-	case 0x400:
-		access = _PAGE_EXEC;
-		break;
-	default:
-		return;
-	}
-
-	hash_preload(vma->vm_mm, address, access, trap);
-#endif /* CONFIG_PPC_STD_MMU */
-#if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \
-	&& defined(CONFIG_HUGETLB_PAGE)
-	if (is_vm_hugetlb_page(vma))
-		book3e_hugetlb_preload(vma, address, *ptep);
-#endif
-}
-
-/*
  * System memory should not be in /proc/iomem but various tools expect it
  * (eg kdump).
  */
@@ -597,3 +451,9 @@
 	return 0;
 }
 #endif /* CONFIG_STRICT_DEVMEM */
+
+/*
+ * This is defined in kernel/resource.c but only powerpc needs to export it, for
+ * the EHEA driver. Drop this when drivers/net/ethernet/ibm/ehea is removed.
+ */
+EXPORT_SYMBOL_GPL(walk_system_ram_range);
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index b24ce40..ae683fd 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -1,24 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  flexible mmap layout support
  *
  * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
  * All Rights Reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * Started by Ingo Molnar <mingo@elte.hu>
  */
 
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index f84e14f..18f20da 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Common implementation of switch_mm_irqs_off
  *
  *  Copyright IBM Corp. 2017
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/mm.h>
@@ -15,6 +10,7 @@
 #include <linux/sched/mm.h>
 
 #include <asm/mmu_context.h>
+#include <asm/pgalloc.h>
 
 #if defined(CONFIG_PPC32)
 static inline void switch_mm_pgdir(struct task_struct *tsk,
@@ -97,3 +93,12 @@
 	switch_mmu_context(prev, next, tsk);
 }
 
+#ifndef CONFIG_PPC_BOOK3S_64
+void arch_exit_mmap(struct mm_struct *mm)
+{
+	void *frag = pte_frag_get(&mm->context);
+
+	if (frag)
+		pte_frag_destroy(frag);
+}
+#endif
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
deleted file mode 100644
index 56c2234..0000000
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ /dev/null
@@ -1,467 +0,0 @@
-/*
- *  IOMMU helpers in MMU context.
- *
- *  Copyright (C) 2015 IBM Corp. <aik@ozlabs.ru>
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
- */
-
-#include <linux/sched/signal.h>
-#include <linux/slab.h>
-#include <linux/rculist.h>
-#include <linux/vmalloc.h>
-#include <linux/mutex.h>
-#include <linux/migrate.h>
-#include <linux/hugetlb.h>
-#include <linux/swap.h>
-#include <linux/sizes.h>
-#include <asm/mmu_context.h>
-#include <asm/pte-walk.h>
-
-static DEFINE_MUTEX(mem_list_mutex);
-
-#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY	0x1
-#define MM_IOMMU_TABLE_GROUP_PAGE_MASK	~(SZ_4K - 1)
-
-struct mm_iommu_table_group_mem_t {
-	struct list_head next;
-	struct rcu_head rcu;
-	unsigned long used;
-	atomic64_t mapped;
-	unsigned int pageshift;
-	u64 ua;			/* userspace address */
-	u64 entries;		/* number of entries in hpas[] */
-	u64 *hpas;		/* vmalloc'ed */
-};
-
-static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
-		unsigned long npages, bool incr)
-{
-	long ret = 0, locked, lock_limit;
-
-	if (!npages)
-		return 0;
-
-	down_write(&mm->mmap_sem);
-
-	if (incr) {
-		locked = mm->locked_vm + npages;
-		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			ret = -ENOMEM;
-		else
-			mm->locked_vm += npages;
-	} else {
-		if (WARN_ON_ONCE(npages > mm->locked_vm))
-			npages = mm->locked_vm;
-		mm->locked_vm -= npages;
-	}
-
-	pr_debug("[%d] RLIMIT_MEMLOCK HASH64 %c%ld %ld/%ld\n",
-			current ? current->pid : 0,
-			incr ? '+' : '-',
-			npages << PAGE_SHIFT,
-			mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK));
-	up_write(&mm->mmap_sem);
-
-	return ret;
-}
-
-bool mm_iommu_preregistered(struct mm_struct *mm)
-{
-	return !list_empty(&mm->context.iommu_group_mem_list);
-}
-EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
-
-/*
- * Taken from alloc_migrate_target with changes to remove CMA allocations
- */
-struct page *new_iommu_non_cma_page(struct page *page, unsigned long private)
-{
-	gfp_t gfp_mask = GFP_USER;
-	struct page *new_page;
-
-	if (PageCompound(page))
-		return NULL;
-
-	if (PageHighMem(page))
-		gfp_mask |= __GFP_HIGHMEM;
-
-	/*
-	 * We don't want the allocation to force an OOM if possibe
-	 */
-	new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);
-	return new_page;
-}
-
-static int mm_iommu_move_page_from_cma(struct page *page)
-{
-	int ret = 0;
-	LIST_HEAD(cma_migrate_pages);
-
-	/* Ignore huge pages for now */
-	if (PageCompound(page))
-		return -EBUSY;
-
-	lru_add_drain();
-	ret = isolate_lru_page(page);
-	if (ret)
-		return ret;
-
-	list_add(&page->lru, &cma_migrate_pages);
-	put_page(page); /* Drop the gup reference */
-
-	ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
-				NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE);
-	if (ret) {
-		if (!list_empty(&cma_migrate_pages))
-			putback_movable_pages(&cma_migrate_pages);
-	}
-
-	return 0;
-}
-
-long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
-		struct mm_iommu_table_group_mem_t **pmem)
-{
-	struct mm_iommu_table_group_mem_t *mem;
-	long i, j, ret = 0, locked_entries = 0;
-	unsigned int pageshift;
-	unsigned long flags;
-	unsigned long cur_ua;
-	struct page *page = NULL;
-
-	mutex_lock(&mem_list_mutex);
-
-	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
-			next) {
-		if ((mem->ua == ua) && (mem->entries == entries)) {
-			++mem->used;
-			*pmem = mem;
-			goto unlock_exit;
-		}
-
-		/* Overlap? */
-		if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
-				(ua < (mem->ua +
-				       (mem->entries << PAGE_SHIFT)))) {
-			ret = -EINVAL;
-			goto unlock_exit;
-		}
-
-	}
-
-	ret = mm_iommu_adjust_locked_vm(mm, entries, true);
-	if (ret)
-		goto unlock_exit;
-
-	locked_entries = entries;
-
-	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
-	if (!mem) {
-		ret = -ENOMEM;
-		goto unlock_exit;
-	}
-
-	/*
-	 * For a starting point for a maximum page size calculation
-	 * we use @ua and @entries natural alignment to allow IOMMU pages
-	 * smaller than huge pages but still bigger than PAGE_SIZE.
-	 */
-	mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
-	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
-	if (!mem->hpas) {
-		kfree(mem);
-		ret = -ENOMEM;
-		goto unlock_exit;
-	}
-
-	for (i = 0; i < entries; ++i) {
-		cur_ua = ua + (i << PAGE_SHIFT);
-		if (1 != get_user_pages_fast(cur_ua,
-					1/* pages */, 1/* iswrite */, &page)) {
-			ret = -EFAULT;
-			for (j = 0; j < i; ++j)
-				put_page(pfn_to_page(mem->hpas[j] >>
-						PAGE_SHIFT));
-			vfree(mem->hpas);
-			kfree(mem);
-			goto unlock_exit;
-		}
-		/*
-		 * If we get a page from the CMA zone, since we are going to
-		 * be pinning these entries, we might as well move them out
-		 * of the CMA zone if possible. NOTE: faulting in + migration
-		 * can be expensive. Batching can be considered later
-		 */
-		if (is_migrate_cma_page(page)) {
-			if (mm_iommu_move_page_from_cma(page))
-				goto populate;
-			if (1 != get_user_pages_fast(cur_ua,
-						1/* pages */, 1/* iswrite */,
-						&page)) {
-				ret = -EFAULT;
-				for (j = 0; j < i; ++j)
-					put_page(pfn_to_page(mem->hpas[j] >>
-								PAGE_SHIFT));
-				vfree(mem->hpas);
-				kfree(mem);
-				goto unlock_exit;
-			}
-		}
-populate:
-		pageshift = PAGE_SHIFT;
-		if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
-			pte_t *pte;
-			struct page *head = compound_head(page);
-			unsigned int compshift = compound_order(head);
-			unsigned int pteshift;
-
-			local_irq_save(flags); /* disables as well */
-			pte = find_linux_pte(mm->pgd, cur_ua, NULL, &pteshift);
-
-			/* Double check it is still the same pinned page */
-			if (pte && pte_page(*pte) == head &&
-			    pteshift == compshift + PAGE_SHIFT)
-				pageshift = max_t(unsigned int, pteshift,
-						PAGE_SHIFT);
-			local_irq_restore(flags);
-		}
-		mem->pageshift = min(mem->pageshift, pageshift);
-		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
-	}
-
-	atomic64_set(&mem->mapped, 1);
-	mem->used = 1;
-	mem->ua = ua;
-	mem->entries = entries;
-	*pmem = mem;
-
-	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
-
-unlock_exit:
-	if (locked_entries && ret)
-		mm_iommu_adjust_locked_vm(mm, locked_entries, false);
-
-	mutex_unlock(&mem_list_mutex);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(mm_iommu_get);
-
-static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
-{
-	long i;
-	struct page *page = NULL;
-
-	for (i = 0; i < mem->entries; ++i) {
-		if (!mem->hpas[i])
-			continue;
-
-		page = pfn_to_page(mem->hpas[i] >> PAGE_SHIFT);
-		if (!page)
-			continue;
-
-		if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
-			SetPageDirty(page);
-
-		put_page(page);
-		mem->hpas[i] = 0;
-	}
-}
-
-static void mm_iommu_do_free(struct mm_iommu_table_group_mem_t *mem)
-{
-
-	mm_iommu_unpin(mem);
-	vfree(mem->hpas);
-	kfree(mem);
-}
-
-static void mm_iommu_free(struct rcu_head *head)
-{
-	struct mm_iommu_table_group_mem_t *mem = container_of(head,
-			struct mm_iommu_table_group_mem_t, rcu);
-
-	mm_iommu_do_free(mem);
-}
-
-static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
-{
-	list_del_rcu(&mem->next);
-	call_rcu(&mem->rcu, mm_iommu_free);
-}
-
-long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
-{
-	long ret = 0;
-
-	mutex_lock(&mem_list_mutex);
-
-	if (mem->used == 0) {
-		ret = -ENOENT;
-		goto unlock_exit;
-	}
-
-	--mem->used;
-	/* There are still users, exit */
-	if (mem->used)
-		goto unlock_exit;
-
-	/* Are there still mappings? */
-	if (atomic_cmpxchg(&mem->mapped, 1, 0) != 1) {
-		++mem->used;
-		ret = -EBUSY;
-		goto unlock_exit;
-	}
-
-	/* @mapped became 0 so now mappings are disabled, release the region */
-	mm_iommu_release(mem);
-
-	mm_iommu_adjust_locked_vm(mm, mem->entries, false);
-
-unlock_exit:
-	mutex_unlock(&mem_list_mutex);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(mm_iommu_put);
-
-struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
-		unsigned long ua, unsigned long size)
-{
-	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
-
-	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
-		if ((mem->ua <= ua) &&
-				(ua + size <= mem->ua +
-				 (mem->entries << PAGE_SHIFT))) {
-			ret = mem;
-			break;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(mm_iommu_lookup);
-
-struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
-		unsigned long ua, unsigned long size)
-{
-	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
-
-	list_for_each_entry_lockless(mem, &mm->context.iommu_group_mem_list,
-			next) {
-		if ((mem->ua <= ua) &&
-				(ua + size <= mem->ua +
-				 (mem->entries << PAGE_SHIFT))) {
-			ret = mem;
-			break;
-		}
-	}
-
-	return ret;
-}
-
-struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
-		unsigned long ua, unsigned long entries)
-{
-	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
-
-	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
-		if ((mem->ua == ua) && (mem->entries == entries)) {
-			ret = mem;
-			break;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(mm_iommu_find);
-
-long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
-{
-	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
-	u64 *va = &mem->hpas[entry];
-
-	if (entry >= mem->entries)
-		return -EFAULT;
-
-	if (pageshift > mem->pageshift)
-		return -EFAULT;
-
-	*hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
-
-long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
-{
-	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
-	void *va = &mem->hpas[entry];
-	unsigned long *pa;
-
-	if (entry >= mem->entries)
-		return -EFAULT;
-
-	if (pageshift > mem->pageshift)
-		return -EFAULT;
-
-	pa = (void *) vmalloc_to_phys(va);
-	if (!pa)
-		return -EFAULT;
-
-	*hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
-
-	return 0;
-}
-
-extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua)
-{
-	struct mm_iommu_table_group_mem_t *mem;
-	long entry;
-	void *va;
-	unsigned long *pa;
-
-	mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE);
-	if (!mem)
-		return;
-
-	entry = (ua - mem->ua) >> PAGE_SHIFT;
-	va = &mem->hpas[entry];
-
-	pa = (void *) vmalloc_to_phys(va);
-	if (!pa)
-		return;
-
-	*pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY;
-}
-
-long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
-{
-	if (atomic64_inc_not_zero(&mem->mapped))
-		return 0;
-
-	/* Last mm_iommu_put() has been called, no more mappings allowed() */
-	return -ENXIO;
-}
-EXPORT_SYMBOL_GPL(mm_iommu_mapped_inc);
-
-void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem)
-{
-	atomic64_add_unless(&mem->mapped, -1, 1);
-}
-EXPORT_SYMBOL_GPL(mm_iommu_mapped_dec);
-
-void mm_iommu_init(struct mm_struct *mm)
-{
-	INIT_LIST_HEAD_RCU(&mm->context.iommu_group_mem_list);
-}
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index e5d779e..c750ac9 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Declarations of procedures and variables shared between files
  * in arch/ppc/mm/.
@@ -11,17 +12,12 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 #include <linux/mm.h>
 #include <asm/mmu.h>
 
 #ifdef CONFIG_PPC_MMU_NOHASH
+#include <asm/trace.h>
 
 /*
  * On 40x and 8xx, we directly inline tlbia and tlbivax
@@ -30,10 +26,12 @@
 static inline void _tlbil_all(void)
 {
 	asm volatile ("sync; tlbia; isync" : : : "memory");
+	trace_tlbia(MMU_NO_CONTEXT);
 }
 static inline void _tlbil_pid(unsigned int pid)
 {
 	asm volatile ("sync; tlbia; isync" : : : "memory");
+	trace_tlbia(pid);
 }
 #define _tlbil_pid_noind(pid)	_tlbil_pid(pid)
 
@@ -55,6 +53,7 @@
 			     unsigned int tsize, unsigned int ind)
 {
 	asm volatile ("tlbie %0; sync" : : "r" (address) : "memory");
+	trace_tlbie(0, 0, address, pid, 0, 0, 0);
 }
 #elif defined(CONFIG_PPC_BOOK3E)
 extern void _tlbil_va(unsigned long address, unsigned int pid,
@@ -79,19 +78,21 @@
 }
 #endif
 
+static inline void print_system_hash_info(void) {}
+
 #else /* CONFIG_PPC_MMU_NOHASH */
 
-extern void hash_preload(struct mm_struct *mm, unsigned long ea,
-			 unsigned long access, unsigned long trap);
-
-
 extern void _tlbie(unsigned long address);
 extern void _tlbia(void);
 
+void print_system_hash_info(void);
+
 #endif /* CONFIG_PPC_MMU_NOHASH */
 
 #ifdef CONFIG_PPC32
 
+void hash_preload(struct mm_struct *mm, unsigned long ea);
+
 extern void mapin_ram(void);
 extern void setbat(int index, unsigned long virt, phys_addr_t phys,
 		   unsigned int size, pgprot_t prot);
@@ -100,12 +101,11 @@
 extern unsigned int rtas_data, rtas_size;
 
 struct hash_pte;
-extern struct hash_pte *Hash, *Hash_end;
-extern unsigned long Hash_size, Hash_mask;
+extern struct hash_pte *Hash;
+extern u8 early_hash[];
 
 #endif /* CONFIG_PPC32 */
 
-extern unsigned long ioremap_bot;
 extern unsigned long __max_low_memory;
 extern phys_addr_t __initial_memory_limit_addr;
 extern phys_addr_t total_memory;
@@ -126,7 +126,8 @@
  */
 #ifdef CONFIG_PPC32
 extern void MMU_init_hw(void);
-extern unsigned long mmu_mapin_ram(unsigned long top);
+void MMU_init_hw_patch(void);
+unsigned long mmu_mapin_ram(unsigned long base, unsigned long top);
 #endif
 
 #ifdef CONFIG_PPC_FSL_BOOK3E
@@ -151,7 +152,7 @@
 };
 #endif
 
-#if defined(CONFIG_6xx) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx)
+#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx)
 /* 6xx have BATS */
 /* FSL_BOOKE have TLBCAM */
 /* 8xx have LTLB */
@@ -161,3 +162,11 @@
 static inline phys_addr_t v_block_mapped(unsigned long va) { return 0; }
 static inline unsigned long p_block_mapped(phys_addr_t pa) { return 0; }
 #endif
+
+#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_8xx)
+void mmu_mark_initmem_nx(void);
+void mmu_mark_rodata_ro(void);
+#else
+static inline void mmu_mark_initmem_nx(void) { }
+static inline void mmu_mark_rodata_ro(void) { }
+#endif
diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/nohash/40x.c
similarity index 91%
rename from arch/powerpc/mm/40x_mmu.c
rename to arch/powerpc/mm/nohash/40x.c
index 61ac468..f348104 100644
--- a/arch/powerpc/mm/40x_mmu.c
+++ b/arch/powerpc/mm/nohash/40x.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file contains the routines for initializing the MMU
  * on the 4xx series of chips.
@@ -12,12 +13,6 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/signal.h>
@@ -49,7 +44,7 @@
 #include <asm/machdep.h>
 #include <asm/setup.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 extern int __map_without_ltlbs;
 /*
@@ -93,7 +88,7 @@
 #define LARGE_PAGE_SIZE_16M	(1<<24)
 #define LARGE_PAGE_SIZE_4M	(1<<22)
 
-unsigned long __init mmu_mapin_ram(unsigned long top)
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 {
 	unsigned long v, s, mapped;
 	phys_addr_t p;
diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/nohash/44x.c
similarity index 87%
rename from arch/powerpc/mm/44x_mmu.c
rename to arch/powerpc/mm/nohash/44x.c
index 12d9251..3d6ae7c 100644
--- a/arch/powerpc/mm/44x_mmu.c
+++ b/arch/powerpc/mm/nohash/44x.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Modifications by Matt Porter (mporter@mvista.com) to support
  * PPC44x Book E processors.
@@ -15,12 +16,6 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/init.h>
@@ -29,8 +24,9 @@
 #include <asm/mmu.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
+#include <asm/code-patching.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 /* Used by the 44x TLB replacement exception handler.
  * Just needed it declared someplace.
@@ -43,22 +39,13 @@
 
 static void ppc44x_update_tlb_hwater(void)
 {
-	extern unsigned int tlb_44x_patch_hwater_D[];
-	extern unsigned int tlb_44x_patch_hwater_I[];
-
 	/* The TLB miss handlers hard codes the watermark in a cmpli
 	 * instruction to improve performances rather than loading it
 	 * from the global variable. Thus, we patch the instructions
 	 * in the 2 TLB miss handlers when updating the value
 	 */
-	tlb_44x_patch_hwater_D[0] = (tlb_44x_patch_hwater_D[0] & 0xffff0000) |
-		tlb_44x_hwater;
-	flush_icache_range((unsigned long)&tlb_44x_patch_hwater_D[0],
-			   (unsigned long)&tlb_44x_patch_hwater_D[1]);
-	tlb_44x_patch_hwater_I[0] = (tlb_44x_patch_hwater_I[0] & 0xffff0000) |
-		tlb_44x_hwater;
-	flush_icache_range((unsigned long)&tlb_44x_patch_hwater_I[0],
-			   (unsigned long)&tlb_44x_patch_hwater_I[1]);
+	modify_instruction_site(&patch__tlb_44x_hwater_D, 0xffff, tlb_44x_hwater);
+	modify_instruction_site(&patch__tlb_44x_hwater_I, 0xffff, tlb_44x_hwater);
 }
 
 /*
@@ -178,7 +165,7 @@
 	flush_instruction_cache();
 }
 
-unsigned long __init mmu_mapin_ram(unsigned long top)
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 {
 	unsigned long addr;
 	unsigned long memstart = memstart_addr & ~(PPC_PIN_SIZE - 1);
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
new file mode 100644
index 0000000..4a06cb3
--- /dev/null
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * This file contains the routines for initializing the MMU
+ * on the 8xx series of chips.
+ *  -- christophe
+ *
+ *  Derived from arch/powerpc/mm/40x_mmu.c:
+ */
+
+#include <linux/memblock.h>
+#include <linux/mmu_context.h>
+#include <asm/fixmap.h>
+#include <asm/code-patching.h>
+
+#include <mm/mmu_decl.h>
+
+#define IMMR_SIZE (FIX_IMMR_SIZE << PAGE_SHIFT)
+
+extern int __map_without_ltlbs;
+
+static unsigned long block_mapped_ram;
+
+/*
+ * Return PA for this VA if it is in an area mapped with LTLBs.
+ * Otherwise, returns 0
+ */
+phys_addr_t v_block_mapped(unsigned long va)
+{
+	unsigned long p = PHYS_IMMR_BASE;
+
+	if (__map_without_ltlbs)
+		return 0;
+	if (va >= VIRT_IMMR_BASE && va < VIRT_IMMR_BASE + IMMR_SIZE)
+		return p + va - VIRT_IMMR_BASE;
+	if (va >= PAGE_OFFSET && va < PAGE_OFFSET + block_mapped_ram)
+		return __pa(va);
+	return 0;
+}
+
+/*
+ * Return VA for a given PA mapped with LTLBs or 0 if not mapped
+ */
+unsigned long p_block_mapped(phys_addr_t pa)
+{
+	unsigned long p = PHYS_IMMR_BASE;
+
+	if (__map_without_ltlbs)
+		return 0;
+	if (pa >= p && pa < p + IMMR_SIZE)
+		return VIRT_IMMR_BASE + pa - p;
+	if (pa < block_mapped_ram)
+		return (unsigned long)__va(pa);
+	return 0;
+}
+
+#define LARGE_PAGE_SIZE_8M	(1<<23)
+
+/*
+ * MMU_init_hw does the chip-specific initialization of the MMU hardware.
+ */
+void __init MMU_init_hw(void)
+{
+	/* PIN up to the 3 first 8Mb after IMMR in DTLB table */
+	if (IS_ENABLED(CONFIG_PIN_TLB_DATA)) {
+		unsigned long ctr = mfspr(SPRN_MD_CTR) & 0xfe000000;
+		unsigned long flags = 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY;
+		int i = IS_ENABLED(CONFIG_PIN_TLB_IMMR) ? 29 : 28;
+		unsigned long addr = 0;
+		unsigned long mem = total_lowmem;
+
+		for (; i < 32 && mem >= LARGE_PAGE_SIZE_8M; i++) {
+			mtspr(SPRN_MD_CTR, ctr | (i << 8));
+			mtspr(SPRN_MD_EPN, (unsigned long)__va(addr) | MD_EVALID);
+			mtspr(SPRN_MD_TWC, MD_PS8MEG | MD_SVALID);
+			mtspr(SPRN_MD_RPN, addr | flags | _PAGE_PRESENT);
+			addr += LARGE_PAGE_SIZE_8M;
+			mem -= LARGE_PAGE_SIZE_8M;
+		}
+	}
+}
+
+static void __init mmu_mapin_immr(void)
+{
+	unsigned long p = PHYS_IMMR_BASE;
+	unsigned long v = VIRT_IMMR_BASE;
+	int offset;
+
+	for (offset = 0; offset < IMMR_SIZE; offset += PAGE_SIZE)
+		map_kernel_page(v + offset, p + offset, PAGE_KERNEL_NCG);
+}
+
+static void mmu_patch_cmp_limit(s32 *site, unsigned long mapped)
+{
+	modify_instruction_site(site, 0xffff, (unsigned long)__va(mapped) >> 16);
+}
+
+static void mmu_patch_addis(s32 *site, long simm)
+{
+	unsigned int instr = *(unsigned int *)patch_site_addr(site);
+
+	instr &= 0xffff0000;
+	instr |= ((unsigned long)simm) >> 16;
+	patch_instruction_site(site, instr);
+}
+
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
+{
+	unsigned long mapped;
+
+	if (__map_without_ltlbs) {
+		mapped = 0;
+		mmu_mapin_immr();
+		if (!IS_ENABLED(CONFIG_PIN_TLB_IMMR))
+			patch_instruction_site(&patch__dtlbmiss_immr_jmp, PPC_INST_NOP);
+		if (!IS_ENABLED(CONFIG_PIN_TLB_TEXT))
+			mmu_patch_cmp_limit(&patch__itlbmiss_linmem_top, 0);
+	} else {
+		mapped = top & ~(LARGE_PAGE_SIZE_8M - 1);
+		if (!IS_ENABLED(CONFIG_PIN_TLB_TEXT))
+			mmu_patch_cmp_limit(&patch__itlbmiss_linmem_top,
+					    _ALIGN(__pa(_einittext), 8 << 20));
+	}
+
+	mmu_patch_cmp_limit(&patch__dtlbmiss_linmem_top, mapped);
+	mmu_patch_cmp_limit(&patch__fixupdar_linmem_top, mapped);
+
+	/* If the size of RAM is not an exact power of two, we may not
+	 * have covered RAM in its entirety with 8 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.
+	 */
+	if (mapped)
+		memblock_set_current_limit(mapped);
+
+	block_mapped_ram = mapped;
+
+	return mapped;
+}
+
+void mmu_mark_initmem_nx(void)
+{
+	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && CONFIG_ETEXT_SHIFT < 23)
+		mmu_patch_addis(&patch__itlbmiss_linmem_top8,
+				-((long)_etext & ~(LARGE_PAGE_SIZE_8M - 1)));
+	if (!IS_ENABLED(CONFIG_PIN_TLB_TEXT))
+		mmu_patch_cmp_limit(&patch__itlbmiss_linmem_top, __pa(_etext));
+}
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+void mmu_mark_rodata_ro(void)
+{
+	if (CONFIG_DATA_SHIFT < 23)
+		mmu_patch_addis(&patch__dtlbmiss_romem_top8,
+				-__pa(((unsigned long)_sinittext) &
+				      ~(LARGE_PAGE_SIZE_8M - 1)));
+	mmu_patch_addis(&patch__dtlbmiss_romem_top, -__pa(_sinittext));
+}
+#endif
+
+void __init 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);
+
+	/* 8xx can only access 32MB at the moment */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x02000000));
+}
+
+/*
+ * Set up to use a given MMU context.
+ * id is context number, pgd is PGD pointer.
+ *
+ * We place the physical address of the new task page directory loaded
+ * into the MMU base register, and set the ASID compare register with
+ * the new "context."
+ */
+void set_context(unsigned long id, pgd_t *pgd)
+{
+	s16 offset = (s16)(__pa(swapper_pg_dir));
+
+	/* Context switch the PTE pointer for the Abatron BDI2000.
+	 * The PGDIR is passed as second argument.
+	 */
+	if (IS_ENABLED(CONFIG_BDI_SWITCH))
+		abatron_pteptrs[1] = pgd;
+
+	/* 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);
+
+	/* Update context */
+	mtspr(SPRN_M_CASID, id - 1);
+	/* sync */
+	mb();
+}
+
+void flush_instruction_cache(void)
+{
+	isync();
+	mtspr(SPRN_IC_CST, IDC_INVALL);
+	isync();
+}
+
+#ifdef CONFIG_PPC_KUEP
+void __init setup_kuep(bool disabled)
+{
+	if (disabled)
+		return;
+
+	pr_info("Activating Kernel Userspace Execution Prevention\n");
+
+	mtspr(SPRN_MI_AP, MI_APG_KUEP);
+}
+#endif
+
+#ifdef CONFIG_PPC_KUAP
+void __init setup_kuap(bool disabled)
+{
+	pr_info("Activating Kernel Userspace Access Protection\n");
+
+	if (disabled)
+		pr_warn("KUAP cannot be disabled yet on 8xx when compiled in\n");
+
+	mtspr(SPRN_MD_AP, MD_APG_KUAP);
+}
+#endif
diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile
new file mode 100644
index 0000000..33b6f6f
--- /dev/null
+++ b/arch/powerpc/mm/nohash/Makefile
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
+
+obj-y				+= mmu_context.o tlb.o tlb_low.o
+obj-$(CONFIG_PPC_BOOK3E_64)  	+= tlb_low_64e.o book3e_pgtable.o
+obj-$(CONFIG_40x)		+= 40x.o
+obj-$(CONFIG_44x)		+= 44x.o
+obj-$(CONFIG_PPC_8xx)		+= 8xx.o
+obj-$(CONFIG_PPC_FSL_BOOK3E)	+= fsl_booke.o
+ifdef CONFIG_HUGETLB_PAGE
+obj-$(CONFIG_PPC_FSL_BOOK3E)	+= book3e_hugetlbpage.o
+endif
+
+# Disable kcov instrumentation on sensitive code
+# This is necessary for booting with kcov enabled on book3e machines
+KCOV_INSTRUMENT_tlb.o := n
+KCOV_INSTRUMENT_fsl_booke.o := n
diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/nohash/book3e_hugetlbpage.c
similarity index 88%
rename from arch/powerpc/mm/hugetlbpage-book3e.c
rename to arch/powerpc/mm/nohash/book3e_hugetlbpage.c
index f84ec46..8b88be9 100644
--- a/arch/powerpc/mm/hugetlbpage-book3e.c
+++ b/arch/powerpc/mm/nohash/book3e_hugetlbpage.c
@@ -11,8 +11,9 @@
 
 #include <asm/mmu.h>
 
-#ifdef CONFIG_PPC_FSL_BOOK3E
 #ifdef CONFIG_PPC64
+#include <asm/paca.h>
+
 static inline int tlb1_next(void)
 {
 	struct paca_struct *paca = get_paca();
@@ -29,33 +30,6 @@
 	tcd->esel_next = next;
 	return this;
 }
-#else
-static inline int tlb1_next(void)
-{
-	int index, ncams;
-
-	ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
-
-	index = this_cpu_read(next_tlbcam_idx);
-
-	/* Just round-robin the entries and wrap when we hit the end */
-	if (unlikely(index == ncams - 1))
-		__this_cpu_write(next_tlbcam_idx, tlbcam_index);
-	else
-		__this_cpu_inc(next_tlbcam_idx);
-
-	return index;
-}
-#endif /* !PPC64 */
-#endif /* FSL */
-
-static inline int mmu_get_tsize(int psize)
-{
-	return mmu_psize_defs[psize].enc;
-}
-
-#if defined(CONFIG_PPC_FSL_BOOK3E) && defined(CONFIG_PPC64)
-#include <asm/paca.h>
 
 static inline void book3e_tlb_lock(void)
 {
@@ -98,6 +72,23 @@
 	paca->tcd_ptr->lock = 0;
 }
 #else
+static inline int tlb1_next(void)
+{
+	int index, ncams;
+
+	ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+	index = this_cpu_read(next_tlbcam_idx);
+
+	/* Just round-robin the entries and wrap when we hit the end */
+	if (unlikely(index == ncams - 1))
+		__this_cpu_write(next_tlbcam_idx, tlbcam_index);
+	else
+		__this_cpu_inc(next_tlbcam_idx);
+
+	return index;
+}
+
 static inline void book3e_tlb_lock(void)
 {
 }
@@ -131,18 +122,15 @@
 	return found;
 }
 
-void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
-			    pte_t pte)
+static void
+book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte)
 {
 	unsigned long mas1, mas2;
 	u64 mas7_3;
 	unsigned long psize, tsize, shift;
 	unsigned long flags;
 	struct mm_struct *mm;
-
-#ifdef CONFIG_PPC_FSL_BOOK3E
 	int index;
-#endif
 
 	if (unlikely(is_kernel_addr(ea)))
 		return;
@@ -166,11 +154,9 @@
 		return;
 	}
 
-#ifdef CONFIG_PPC_FSL_BOOK3E
 	/* We have to use the CAM(TLB1) on FSL parts for hugepages */
 	index = tlb1_next();
 	mtspr(SPRN_MAS0, MAS0_ESEL(index) | MAS0_TLBSEL(1));
-#endif
 
 	mas1 = MAS1_VALID | MAS1_TID(mm->context.id) | MAS1_TSIZE(tsize);
 	mas2 = ea & ~((1UL << shift) - 1);
@@ -197,6 +183,18 @@
 	local_irq_restore(flags);
 }
 
+/*
+ * This is called at the end of handling a user page fault, when the
+ * fault has been handled by updating a PTE in the linux page tables.
+ *
+ * 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)
+{
+	if (is_vm_hugetlb_page(vma))
+		book3e_hugetlb_preload(vma, address, *ptep);
+}
+
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
 	struct hstate *hstate = hstate_file(vma->vm_file);
diff --git a/arch/powerpc/mm/pgtable-book3e.c b/arch/powerpc/mm/nohash/book3e_pgtable.c
similarity index 74%
rename from arch/powerpc/mm/pgtable-book3e.c
rename to arch/powerpc/mm/nohash/book3e_pgtable.c
index a229893..4637fdd 100644
--- a/arch/powerpc/mm/pgtable-book3e.c
+++ b/arch/powerpc/mm/nohash/book3e_pgtable.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2005, Paul Mackerras, IBM Corporation.
  * Copyright 2009, Benjamin Herrenschmidt, IBM Corporation.
  * Copyright 2015-2016, Aneesh Kumar K.V, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/sched.h>
@@ -15,7 +11,7 @@
 #include <asm/tlb.h>
 #include <asm/dma.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
@@ -42,7 +38,7 @@
 	 * thus must have the low bits clear
 	 */
 	for (i = 0; i < page_size; i += PAGE_SIZE)
-		BUG_ON(map_kernel_page(start + i, phys, flags));
+		BUG_ON(map_kernel_page(start + i, phys, __pgprot(flags)));
 
 	return 0;
 }
@@ -55,14 +51,18 @@
 #endif
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
-static __ref void *early_alloc_pgtable(unsigned long size)
+static void __init *early_alloc_pgtable(unsigned long size)
 {
-	void *pt;
+	void *ptr;
 
-	pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS)));
-	memset(pt, 0, size);
+	ptr = memblock_alloc_try_nid(size, size, MEMBLOCK_LOW_LIMIT,
+				     __pa(MAX_DMA_ADDRESS), NUMA_NO_NODE);
 
-	return pt;
+	if (!ptr)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx max_addr=%lx\n",
+		      __func__, size, size, __pa(MAX_DMA_ADDRESS));
+
+	return ptr;
 }
 
 /*
@@ -70,7 +70,7 @@
  * map_kernel_page adds an entry to the ioremap page table
  * and adds an entry to the HPT, possibly bolting it
  */
-int map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags)
+int __ref map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
 {
 	pgd_t *pgdp;
 	pud_t *pudp;
@@ -89,33 +89,27 @@
 		ptep = pte_alloc_kernel(pmdp, ea);
 		if (!ptep)
 			return -ENOMEM;
-		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
-							  __pgprot(flags)));
 	} else {
 		pgdp = pgd_offset_k(ea);
 #ifndef __PAGETABLE_PUD_FOLDED
 		if (pgd_none(*pgdp)) {
 			pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
-			BUG_ON(pudp == NULL);
 			pgd_populate(&init_mm, pgdp, pudp);
 		}
 #endif /* !__PAGETABLE_PUD_FOLDED */
 		pudp = pud_offset(pgdp, ea);
 		if (pud_none(*pudp)) {
 			pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
-			BUG_ON(pmdp == NULL);
 			pud_populate(&init_mm, pudp, pmdp);
 		}
 		pmdp = pmd_offset(pudp, ea);
 		if (!pmd_present(*pmdp)) {
 			ptep = early_alloc_pgtable(PAGE_SIZE);
-			BUG_ON(ptep == NULL);
 			pmd_populate_kernel(&init_mm, pmdp, ptep);
 		}
 		ptep = pte_offset_kernel(pmdp, ea);
-		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
-							  __pgprot(flags)));
 	}
+	set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, prot));
 
 	smp_wmb();
 	return 0;
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/nohash/fsl_booke.c
similarity index 95%
rename from arch/powerpc/mm/fsl_booke_mmu.c
rename to arch/powerpc/mm/nohash/fsl_booke.c
index 080d49b..556e3cd 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/nohash/fsl_booke.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Modifications by Kumar Gala (galak@kernel.crashing.org) to support
  * E500 Book E processors.
@@ -17,12 +18,6 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/signal.h>
@@ -54,7 +49,7 @@
 #include <asm/setup.h>
 #include <asm/paca.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 unsigned int tlbcam_index;
 
@@ -221,7 +216,7 @@
 #error "LOWMEM_CAM_NUM must be less than NUM_TLBCAMS"
 #endif
 
-unsigned long __init mmu_mapin_ram(unsigned long top)
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 {
 	return tlbcam_addrs[tlbcam_index - 1].limit - PAGE_OFFSET + 1;
 }
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/nohash/mmu_context.c
similarity index 94%
rename from arch/powerpc/mm/mmu_context_nohash.c
rename to arch/powerpc/mm/nohash/mmu_context.c
index 4d80239..aac81c9 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/nohash/mmu_context.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file contains the routines for handling the MMU on those
  * PowerPC implementations where the MMU is not using the hash
@@ -9,11 +10,6 @@
  *  Derived from previous arch/powerpc/mm/mmu_context.c
  *  and arch/powerpc/include/asm/mmu_context.h
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  * TODO:
  *
  *   - The global context lock will not scale very well
@@ -44,7 +40,7 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/slab.h>
@@ -52,7 +48,7 @@
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 /*
  * The MPC8xx has only 16 contexts. We rotate through them on each task switch.
@@ -372,7 +368,6 @@
 {
 	pr_hard("initing context for mm @%p\n", mm);
 
-#ifdef	CONFIG_PPC_MM_SLICES
 	/*
 	 * We have MMU_NO_CONTEXT set to be ~0. Hence check
 	 * explicitly against context.id == 0. This ensures that we properly
@@ -382,9 +377,9 @@
 	 */
 	if (mm->context.id == 0)
 		slice_init_new_context_exec(mm);
-#endif
 	mm->context.id = MMU_NO_CONTEXT;
 	mm->context.active = 0;
+	pte_frag_set(&mm->context, NULL);
 	return 0;
 }
 
@@ -461,10 +456,20 @@
 	/*
 	 * Allocate the maps used by context management
 	 */
-	context_map = memblock_virt_alloc(CTX_MAP_SIZE, 0);
-	context_mm = memblock_virt_alloc(sizeof(void *) * (LAST_CONTEXT + 1), 0);
+	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),
+				    SMP_CACHE_BYTES);
+	if (!context_mm)
+		panic("%s: Failed to allocate %zu bytes\n", __func__,
+		      sizeof(void *) * (LAST_CONTEXT + 1));
 #ifdef CONFIG_SMP
-	stale_map[boot_cpuid] = memblock_virt_alloc(CTX_MAP_SIZE, 0);
+	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);
 
 	cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE,
 				  "powerpc/mmu/ctx:prepare",
@@ -486,4 +491,3 @@
 	next_context = FIRST_CONTEXT;
 	nr_free_contexts = LAST_CONTEXT - FIRST_CONTEXT + 1;
 }
-
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/nohash/tlb.c
similarity index 96%
rename from arch/powerpc/mm/tlb_nohash.c
rename to arch/powerpc/mm/nohash/tlb.c
index ae5d568..696f568 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file contains the routines for TLB flushing.
  * On machines where the MMU does not use a hash table to store virtual to
@@ -19,12 +20,6 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/kernel.h>
@@ -46,7 +41,7 @@
 #include <asm/hugetlb.h>
 #include <asm/paca.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 /*
  * This struct lists the sw-supported page sizes.  The hardawre MMU may support
@@ -302,7 +297,7 @@
 	 * This function as well as __local_flush_tlb_page() must only be called
 	 * for user contexts.
 	 */
-	if (unlikely(WARN_ON(!mm)))
+	if (WARN_ON(!mm))
 		return;
 
 	preempt_disable();
@@ -433,11 +428,7 @@
 		unsigned long rid = (address & rmask) | 0x1000000000000000ul;
 		unsigned long vpte = address & ~rmask;
 
-#ifdef CONFIG_PPC_64K_PAGES
-		vpte = (vpte >> (PAGE_SHIFT - 4)) & ~0xfffful;
-#else
 		vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
-#endif
 		vpte |= rid;
 		__flush_tlb_page(tlb->mm, vpte, tsize, 0);
 	}
@@ -625,21 +616,12 @@
 
 	case PPC_HTW_IBM:
 		mas4 |= MAS4_INDD;
-#ifdef CONFIG_PPC_64K_PAGES
-		mas4 |=	BOOK3E_PAGESZ_256M << MAS4_TSIZED_SHIFT;
-		mmu_pte_psize = MMU_PAGE_256M;
-#else
 		mas4 |=	BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT;
 		mmu_pte_psize = MMU_PAGE_1M;
-#endif
 		break;
 
 	case PPC_HTW_NONE:
-#ifdef CONFIG_PPC_64K_PAGES
-		mas4 |=	BOOK3E_PAGESZ_64K << MAS4_TSIZED_SHIFT;
-#else
 		mas4 |=	BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
-#endif
 		mmu_pte_psize = mmu_virtual_psize;
 		break;
 	}
@@ -648,7 +630,6 @@
 #ifdef CONFIG_PPC_FSL_BOOK3E
 	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
 		unsigned int num_cams;
-		int __maybe_unused cpu = smp_processor_id();
 		bool map = true;
 
 		/* use a quarter of the TLBCAM for bolted linear map */
@@ -722,6 +703,8 @@
 	 * 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)
@@ -800,5 +783,9 @@
 #ifdef CONFIG_PPC_47x
 	early_init_mmu_47x();
 #endif
+
+#ifdef CONFIG_PPC_MM_SLICES
+	mm_ctx_set_slb_addr_limit(&init_mm.context, SLB_ADDR_LIMIT_DEFAULT);
+#endif
 }
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/nohash/tlb_low.S
similarity index 96%
rename from arch/powerpc/mm/tlb_nohash_low.S
rename to arch/powerpc/mm/nohash/tlb_low.S
index e066a65..2ca407c 100644
--- a/arch/powerpc/mm/tlb_nohash_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains low-level functions for performing various
  * types of TLB invalidations on various processors with no hash
@@ -18,12 +19,6 @@
  *
  * Partially rewritten by Cort Dougan (cort@cs.nmt.edu)
  * Paul Mackerras, Kumar Gala and Benjamin Herrenschmidt.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/reg.h>
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S
similarity index 96%
rename from arch/powerpc/mm/tlb_low_64e.S
rename to arch/powerpc/mm/nohash/tlb_low_64e.S
index 7fd20c5..1f110c3 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/nohash/tlb_low_64e.S
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  Low level TLB miss handlers for Book3E
  *
  *  Copyright (C) 2008-2009
  *      Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <asm/processor.h>
@@ -24,11 +20,7 @@
 #include <asm/kvm_booke_hv_asm.h>
 #include <asm/feature-fixups.h>
 
-#ifdef CONFIG_PPC_64K_PAGES
-#define VPTE_PMD_SHIFT	(PTE_INDEX_SIZE+1)
-#else
 #define VPTE_PMD_SHIFT	(PTE_INDEX_SIZE)
-#endif
 #define VPTE_PUD_SHIFT	(VPTE_PMD_SHIFT + PMD_INDEX_SIZE)
 #define VPTE_PGD_SHIFT	(VPTE_PUD_SHIFT + PUD_INDEX_SIZE)
 #define VPTE_INDEX_SIZE (VPTE_PGD_SHIFT + PGD_INDEX_SIZE)
@@ -70,6 +62,13 @@
 	std	r15,EX_TLB_R15(r12)
 	std	r10,EX_TLB_CR(r12)
 #ifdef CONFIG_PPC_FSL_BOOK3E
+START_BTB_FLUSH_SECTION
+	mfspr r11, SPRN_SRR1
+	andi. r10,r11,MSR_PR
+	beq 1f
+	BTB_FLUSH(r10)
+1:
+END_BTB_FLUSH_SECTION
 	std	r7,EX_TLB_R7(r12)
 #endif
 	TLB_MISS_PROLOG_STATS
@@ -160,13 +159,11 @@
 	ldx	r14,r14,r15		/* grab pgd entry */
 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV)
 
-#ifndef CONFIG_PPC_64K_PAGES
 	rldicl	r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3
 	clrrdi	r15,r15,3
 	cmpdi	cr0,r14,0
 	bge	tlb_miss_fault_bolted	/* Bad pgd entry or hugepage; bail */
 	ldx	r14,r14,r15		/* grab pud entry */
-#endif /* CONFIG_PPC_64K_PAGES */
 
 	rldicl	r15,r16,64-PMD_SHIFT+3,64-PMD_INDEX_SIZE-3
 	clrrdi	r15,r15,3
@@ -675,18 +672,7 @@
 	 * order to handle the weird page table format used by linux
 	 */
 	ori	r10,r15,0x1
-#ifdef CONFIG_PPC_64K_PAGES
-	/* For the top bits, 16 bytes per PTE */
-	rldicl	r14,r16,64-(PAGE_SHIFT-4),PAGE_SHIFT-4+4
-	/* Now create the bottom bits as 0 in position 0x8000 and
-	 * the rest calculated for 8 bytes per PTE
-	 */
-	rldicl	r15,r16,64-(PAGE_SHIFT-3),64-15
-	/* Insert the bottom bits in */
-	rlwimi	r14,r15,0,16,31
-#else
 	rldicl	r14,r16,64-(PAGE_SHIFT-3),PAGE_SHIFT-3+4
-#endif
 	sldi	r15,r10,60
 	clrrdi	r14,r14,3
 	or	r10,r15,r14
@@ -725,11 +711,7 @@
 
 	/* Check page size, if not standard, update MAS1 */
 	rldicl	r11,r14,64-8,64-8
-#ifdef CONFIG_PPC_64K_PAGES
-	cmpldi	cr0,r11,BOOK3E_PAGESZ_64K
-#else
 	cmpldi	cr0,r11,BOOK3E_PAGESZ_4K
-#endif
 	beq-	1f
 	mfspr	r11,SPRN_MAS1
 	rlwimi	r11,r14,31,21,24
@@ -850,14 +832,12 @@
 	cmpdi	cr0,r15,0
 	bge	virt_page_table_tlb_miss_fault
 
-#ifndef CONFIG_PPC_64K_PAGES
 	/* Get to PUD entry */
 	rldicl	r11,r16,64-VPTE_PUD_SHIFT,64-PUD_INDEX_SIZE-3
 	clrrdi	r10,r11,3
 	ldx	r15,r10,r15
 	cmpdi	cr0,r15,0
 	bge	virt_page_table_tlb_miss_fault
-#endif /* CONFIG_PPC_64K_PAGES */
 
 	/* Get to PMD entry */
 	rldicl	r11,r16,64-VPTE_PMD_SHIFT,64-PMD_INDEX_SIZE-3
@@ -1099,14 +1079,12 @@
 	cmpdi	cr0,r15,0
 	bge	htw_tlb_miss_fault
 
-#ifndef CONFIG_PPC_64K_PAGES
 	/* 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
-#endif /* CONFIG_PPC_64K_PAGES */
 
 	/* Get to PMD entry */
 	rldicl	r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3
@@ -1125,9 +1103,7 @@
 	 * 4K page we need to extract a bit from the virtual address and
 	 * insert it into the "PA52" bit of the RPN.
 	 */
-#ifndef CONFIG_PPC_64K_PAGES
 	rlwimi	r15,r16,32-9,20,20
-#endif
 	/* Now we build the MAS:
 	 *
 	 * MAS 0   :	Fully setup with defaults in MAS4 and TLBnCFG
@@ -1137,11 +1113,7 @@
 	 * MAS 2   :	Use defaults
 	 * MAS 3+7 :	Needs to be done
 	 */
-#ifdef CONFIG_PPC_64K_PAGES
-	ori	r10,r15,(BOOK3E_PAGESZ_64K << MAS3_SPSIZE_SHIFT)
-#else
 	ori	r10,r15,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT)
-#endif
 
 BEGIN_MMU_FTR_SECTION
 	srdi	r16,r10,32
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 5500e4e..50d68d2 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1,17 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * pSeries NUMA support
  *
  * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #define pr_fmt(fmt) "numa: " fmt
 
 #include <linux/threads.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
@@ -19,7 +15,6 @@
 #include <linux/nodemask.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
-#include <linux/memblock.h>
 #include <linux/of.h>
 #include <linux/pfn.h>
 #include <linux/cpuset.h>
@@ -33,7 +28,6 @@
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
 #include <asm/smp.h>
-#include <asm/cputhreads.h>
 #include <asm/topology.h>
 #include <asm/firmware.h>
 #include <asm/paca.h>
@@ -85,7 +79,7 @@
 		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
 
 	/* cpumask_of_node() will now work */
-	dbg("Node to cpumask map for %d nodes\n", nr_node_ids);
+	dbg("Node to cpumask map for %u nodes\n", nr_node_ids);
 }
 
 static int __init fake_numa_create_new_node(unsigned long end_pfn,
@@ -169,6 +163,22 @@
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
+int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	int dist = 0;
+
+	int i, index;
+
+	for (i = 0; i < distance_ref_points_depth; i++) {
+		index = be32_to_cpu(distance_ref_points[i]);
+		if (cpu1_assoc[index] == cpu2_assoc[index])
+			break;
+		dist++;
+	}
+
+	return dist;
+}
+
 /* must hold reference to node during call */
 static const __be32 *of_get_associativity(struct device_node *dev)
 {
@@ -216,9 +226,9 @@
  */
 static int associativity_to_nid(const __be32 *associativity)
 {
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
-	if (min_common_depth == -1)
+	if (!numa_enabled)
 		goto out;
 
 	if (of_read_number(associativity, 1) >= min_common_depth)
@@ -226,7 +236,7 @@
 
 	/* POWER4 LPAR uses 0xffff as invalid node */
 	if (nid == 0xffff || nid >= MAX_NUMNODES)
-		nid = -1;
+		nid = NUMA_NO_NODE;
 
 	if (nid > 0 &&
 		of_read_number(associativity, 1) >= distance_ref_points_depth) {
@@ -245,7 +255,7 @@
  */
 static int of_node_to_nid_single(struct device_node *device)
 {
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 	const __be32 *tmp;
 
 	tmp = of_get_associativity(device);
@@ -257,7 +267,7 @@
 /* Walk the device tree upwards, looking for an associativity id */
 int of_node_to_nid(struct device_node *device)
 {
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	of_node_get(device);
 	while (device) {
@@ -422,17 +432,19 @@
 static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 {
 	struct assoc_arrays aa = { .arrays = NULL };
-	int default_nid = 0;
+	int default_nid = NUMA_NO_NODE;
 	int nid = default_nid;
 	int rc, index;
 
+	if ((min_common_depth < 0) || !numa_enabled)
+		return default_nid;
+
 	rc = of_get_assoc_arrays(&aa);
 	if (rc)
 		return default_nid;
 
-	if (min_common_depth > 0 && min_common_depth <= aa.array_sz &&
-	    !(lmb->flags & DRCONF_MEM_AI_INVALID) &&
-	    lmb->aa_index < aa.n_arrays) {
+	if (min_common_depth <= aa.array_sz &&
+	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
 		index = lmb->aa_index * aa.array_sz + min_common_depth - 1;
 		nid = of_read_number(&aa.arrays[index], 1);
 
@@ -455,7 +467,7 @@
  */
 static int numa_setup_cpu(unsigned long lcpu)
 {
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 	struct device_node *cpu;
 
 	/*
@@ -632,8 +644,14 @@
 
 	min_common_depth = find_min_common_depth();
 
-	if (min_common_depth < 0)
+	if (min_common_depth < 0) {
+		/*
+		 * if we fail to parse min_common_depth from device tree
+		 * mark the numa disabled, boot with numa disabled.
+		 */
+		numa_enabled = false;
 		return min_common_depth;
+	}
 
 	dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth);
 
@@ -749,7 +767,7 @@
 	unsigned int node;
 	unsigned int cpu, count;
 
-	if (min_common_depth == -1 || !numa_enabled)
+	if (!numa_enabled)
 		return;
 
 	for_each_online_node(node) {
@@ -788,7 +806,11 @@
 	void *nd;
 	int tnid;
 
-	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+	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 */
@@ -810,7 +832,7 @@
 	struct device_node *rtas;
 	u32 numnodes, i;
 
-	if (min_common_depth <= 0)
+	if (!numa_enabled)
 		return;
 
 	rtas = of_find_node_by_path("/rtas");
@@ -905,16 +927,22 @@
 }
 early_param("numa", early_numa);
 
-static bool topology_updates_enabled = true;
+/*
+ * The platform can inform us through one of several mechanisms
+ * (post-migration device tree updates, PRRN or VPHN) that the NUMA
+ * assignment of a resource has changed. This controls whether we act
+ * on that. Disabled by default.
+ */
+static bool topology_updates_enabled;
 
 static int __init early_topology_updates(char *p)
 {
 	if (!p)
 		return 0;
 
-	if (!strcmp(p, "off")) {
-		pr_info("Disabling topology updates\n");
-		topology_updates_enabled = false;
+	if (!strcmp(p, "on")) {
+		pr_warn("Caution: enabling topology updates\n");
+		topology_updates_enabled = true;
 	}
 
 	return 0;
@@ -931,7 +959,7 @@
 {
 	struct drmem_lmb *lmb;
 	unsigned long lmb_size;
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	lmb_size = drmem_lmb_size();
 
@@ -961,7 +989,7 @@
 static int hot_add_node_scn_to_nid(unsigned long scn_addr)
 {
 	struct device_node *memory;
-	int nid = -1;
+	int nid = NUMA_NO_NODE;
 
 	for_each_node_by_type(memory, "memory") {
 		unsigned long start, size;
@@ -1006,7 +1034,7 @@
 	struct device_node *memory = NULL;
 	int nid;
 
-	if (!numa_enabled || (min_common_depth < 0))
+	if (!numa_enabled)
 		return first_online_node;
 
 	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
@@ -1059,9 +1087,6 @@
 
 /* Virtual Processor Home Node (VPHN) support */
 #ifdef CONFIG_PPC_SPLPAR
-
-#include "vphn.h"
-
 struct topology_update_data {
 	struct topology_update_data *next;
 	unsigned int cpu;
@@ -1157,25 +1182,13 @@
  * Retrieve the new associativity information for a virtual processor's
  * home node.
  */
-static long hcall_vphn(unsigned long cpu, __be32 *associativity)
-{
-	long rc;
-	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
-	u64 flags = 1;
-	int hwcpu = get_hard_smp_processor_id(cpu);
-
-	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
-	vphn_unpack_associativity(retbuf, associativity);
-
-	return rc;
-}
-
 static long vphn_get_associativity(unsigned long cpu,
 					__be32 *associativity)
 {
 	long rc;
 
-	rc = hcall_vphn(cpu, associativity);
+	rc = hcall_vphn(get_hard_smp_processor_id(cpu),
+				VPHN_FLAG_VCPU, associativity);
 
 	switch (rc) {
 	case H_FUNCTION:
@@ -1461,13 +1474,6 @@
 
 #ifdef CONFIG_SMP
 
-static void stage_topology_update(int core_id)
-{
-	cpumask_or(&cpu_associativity_changes_mask,
-		&cpu_associativity_changes_mask, cpu_sibling_mask(core_id));
-	reset_topology_timer();
-}
-
 static int dt_update_callback(struct notifier_block *nb,
 				unsigned long action, void *data)
 {
@@ -1476,11 +1482,11 @@
 
 	switch (action) {
 	case OF_RECONFIG_UPDATE_PROPERTY:
-		if (!of_prop_cmp(update->dn->type, "cpu") &&
+		if (of_node_is_type(update->dn, "cpu") &&
 		    !of_prop_cmp(update->prop->name, "ibm,associativity")) {
 			u32 core_id;
 			of_property_read_u32(update->dn, "reg", &core_id);
-			stage_topology_update(core_id);
+			rc = dlpar_cpu_readd(core_id);
 			rc = NOTIFY_OK;
 		}
 		break;
@@ -1502,6 +1508,9 @@
 {
 	int rc = 0;
 
+	if (!topology_updates_enabled)
+		return 0;
+
 	if (firmware_has_feature(FW_FEATURE_PRRN)) {
 		if (!prrn_enabled) {
 			prrn_enabled = 1;
@@ -1521,6 +1530,10 @@
 		}
 	}
 
+	pr_info("Starting topology update%s%s\n",
+		(prrn_enabled ? " prrn_enabled" : ""),
+		(vphn_enabled ? " vphn_enabled" : ""));
+
 	return rc;
 }
 
@@ -1531,6 +1544,9 @@
 {
 	int rc = 0;
 
+	if (!topology_updates_enabled)
+		return 0;
+
 	if (prrn_enabled) {
 		prrn_enabled = 0;
 #ifdef CONFIG_SMP
@@ -1542,6 +1558,8 @@
 		rc = del_timer_sync(&topology_timer);
 	}
 
+	pr_info("Stopping topology update\n");
+
 	return rc;
 }
 
@@ -1586,11 +1604,13 @@
 
 	kbuf[read_len] = '\0';
 
-	if (!strncmp(kbuf, "on", 2))
+	if (!strncmp(kbuf, "on", 2)) {
+		topology_updates_enabled = true;
 		start_topology_update();
-	else if (!strncmp(kbuf, "off", 3))
+	} else if (!strncmp(kbuf, "off", 3)) {
 		stop_topology_update();
-	else
+		topology_updates_enabled = false;
+	} else
 		return -EINVAL;
 
 	return count;
@@ -1605,9 +1625,7 @@
 
 static int topology_update_init(void)
 {
-	/* Do not poll for changes if disabled at boot */
-	if (topology_updates_enabled)
-		start_topology_update();
+	start_topology_update();
 
 	if (vphn_enabled)
 		topology_schedule_update();
diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c
new file mode 100644
index 0000000..ee4bd6d
--- /dev/null
+++ b/arch/powerpc/mm/pgtable-frag.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ *  Handling Page Tables through page fragments
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/hugetlb.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+void pte_frag_destroy(void *pte_frag)
+{
+	int count;
+	struct page *page;
+
+	page = virt_to_page(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);
+	}
+}
+
+static pte_t *get_pte_from_cache(struct mm_struct *mm)
+{
+	void *pte_frag, *ret;
+
+	if (PTE_FRAG_NR == 1)
+		return NULL;
+
+	spin_lock(&mm->page_table_lock);
+	ret = pte_frag_get(&mm->context);
+	if (ret) {
+		pte_frag = ret + PTE_FRAG_SIZE;
+		/*
+		 * If we have taken up all the fragments mark PTE page NULL
+		 */
+		if (((unsigned long)pte_frag & ~PAGE_MASK) == 0)
+			pte_frag = NULL;
+		pte_frag_set(&mm->context, pte_frag);
+	}
+	spin_unlock(&mm->page_table_lock);
+	return (pte_t *)ret;
+}
+
+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;
+	}
+
+	atomic_set(&page->pt_frag_refcount, 1);
+
+	ret = page_address(page);
+	/*
+	 * if we support only one fragment just return the
+	 * allocated page.
+	 */
+	if (PTE_FRAG_NR == 1)
+		return ret;
+	spin_lock(&mm->page_table_lock);
+	/*
+	 * If we find pgtable_page set, we return
+	 * the allocated page with single fragement
+	 * count.
+	 */
+	if (likely(!pte_frag_get(&mm->context))) {
+		atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR);
+		pte_frag_set(&mm->context, ret + PTE_FRAG_SIZE);
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	return (pte_t *)ret;
+}
+
+pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel)
+{
+	pte_t *pte;
+
+	pte = get_pte_from_cache(mm);
+	if (pte)
+		return pte;
+
+	return __alloc_for_ptecache(mm, kernel);
+}
+
+void pte_fragment_free(unsigned long *table, int kernel)
+{
+	struct page *page = virt_to_page(table);
+
+	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);
+	}
+}
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index d71c777..e3759b6 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file contains common routines for dealing with free of page tables
  * Along with common page table handling code
@@ -14,11 +15,6 @@
  *
  *  Dave Engebretsen <engebret@us.ibm.com>
  *      Rework for PPC64 port.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -30,6 +26,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
+#include <asm/hugetlb.h>
 
 static inline int is_exec_fault(void)
 {
@@ -44,20 +41,13 @@
 static inline int pte_looks_normal(pte_t pte)
 {
 
-#if defined(CONFIG_PPC_BOOK3S_64)
-	if ((pte_val(pte) & (_PAGE_PRESENT | _PAGE_SPECIAL)) == _PAGE_PRESENT) {
+	if (pte_present(pte) && !pte_special(pte)) {
 		if (pte_ci(pte))
 			return 0;
 		if (pte_user(pte))
 			return 1;
 	}
 	return 0;
-#else
-	return (pte_val(pte) &
-		(_PAGE_PRESENT | _PAGE_SPECIAL | _PAGE_NO_CACHE | _PAGE_USER |
-		 _PAGE_PRIVILEGED)) ==
-		(_PAGE_PRESENT | _PAGE_USER);
-#endif
 }
 
 static struct page *maybe_pte_to_page(pte_t pte)
@@ -73,7 +63,7 @@
 	return page;
 }
 
-#if defined(CONFIG_PPC_STD_MMU) || _PAGE_EXEC == 0
+#ifdef CONFIG_PPC_BOOK3S
 
 /* Server-style MMU handles coherency when hashing if HW exec permission
  * is supposed per page (currently 64-bit only). If not, then, we always
@@ -81,7 +71,7 @@
  * support falls into the same category.
  */
 
-static pte_t set_pte_filter(pte_t pte)
+static pte_t set_pte_filter_hash(pte_t pte)
 {
 	if (radix_enabled())
 		return pte;
@@ -100,13 +90,11 @@
 	return pte;
 }
 
-static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
-				     int dirty)
-{
-	return pte;
-}
+#else /* CONFIG_PPC_BOOK3S */
 
-#else /* defined(CONFIG_PPC_STD_MMU) || _PAGE_EXEC == 0 */
+static pte_t set_pte_filter_hash(pte_t pte) { 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
@@ -116,8 +104,11 @@
 {
 	struct page *pg;
 
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		return set_pte_filter_hash(pte);
+
 	/* No exec permission in the first place, move on */
-	if (!(pte_val(pte) & _PAGE_EXEC) || !pte_looks_normal(pte))
+	if (!pte_exec(pte) || !pte_looks_normal(pte))
 		return pte;
 
 	/* If you set _PAGE_EXEC on weird pages you're on your own */
@@ -137,7 +128,7 @@
 	}
 
 	/* Else, we filter out _PAGE_EXEC */
-	return __pte(pte_val(pte) & ~_PAGE_EXEC);
+	return pte_exprotect(pte);
 }
 
 static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
@@ -145,12 +136,15 @@
 {
 	struct page *pg;
 
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		return pte;
+
 	/* So here, we only care about exec faults, as we use them
 	 * to recover lost _PAGE_EXEC and perform I$/D$ coherency
 	 * if necessary. Also if _PAGE_EXEC is already set, same deal,
 	 * we just bail out
 	 */
-	if (dirty || (pte_val(pte) & _PAGE_EXEC) || !is_exec_fault())
+	if (dirty || pte_exec(pte) || !is_exec_fault())
 		return pte;
 
 #ifdef CONFIG_DEBUG_VM
@@ -176,11 +170,9 @@
 	set_bit(PG_arch_1, &pg->flags);
 
  bail:
-	return __pte(pte_val(pte) | _PAGE_EXEC);
+	return pte_mkexec(pte);
 }
 
-#endif /* !(defined(CONFIG_PPC_STD_MMU) || _PAGE_EXEC == 0) */
-
 /*
  * set_pte stores a linux PTE into the linux page table.
  */
@@ -188,14 +180,13 @@
 		pte_t pte)
 {
 	/*
-	 * When handling numa faults, we already have the pte marked
-	 * _PAGE_PRESENT, but we can be sure that it is not in hpte.
-	 * Hence we can use set_pte_at for them.
+	 * Make sure hardware valid bit is not set. We don't do
+	 * tlb flush for this update.
 	 */
-	VM_WARN_ON(pte_present(*ptep) && !pte_protnone(*ptep));
+	VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
 
 	/* Add the pte bit when trying to set a pte */
-	pte = __pte(pte_val(pte) | _PAGE_PTE);
+	pte = pte_mkpte(pte);
 
 	/* Note: mm->context.id might not yet have been assigned as
 	 * this context might not have been activated yet when this
@@ -229,9 +220,9 @@
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-				      unsigned long addr, pte_t *ptep,
-				      pte_t pte, int dirty)
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+			       unsigned long addr, pte_t *ptep,
+			       pte_t pte, int dirty)
 {
 #ifdef HUGETLB_NEED_PRELOAD
 	/*
@@ -305,3 +296,128 @@
 	return __pa(pfn_to_kaddr(pfn)) + offset_in_page(va);
 }
 EXPORT_SYMBOL_GPL(vmalloc_to_phys);
+
+/*
+ * We have 4 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 the page and take a ref on it.
+ * This function need to be called with interrupts disabled. We use this variant
+ * when we have MSR[EE] = 0 but the paca->irq_soft_mask = IRQS_ENABLED
+ */
+pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
+			bool *is_thp, unsigned *hpage_shift)
+{
+	pgd_t pgd, *pgdp;
+	pud_t pud, *pudp;
+	pmd_t pmd, *pmdp;
+	pte_t *ret_pte;
+	hugepd_t *hpdp = NULL;
+	unsigned pdshift = PGDIR_SHIFT;
+
+	if (hpage_shift)
+		*hpage_shift = 0;
+
+	if (is_thp)
+		*is_thp = false;
+
+	pgdp = pgdir + pgd_index(ea);
+	pgd  = READ_ONCE(*pgdp);
+	/*
+	 * Always operate on the local stack value. This make sure the
+	 * value don't get updated by a parallel THP split/collapse,
+	 * page fault or a page unmap. The return pte_t * is still not
+	 * stable. So should be checked there for above conditions.
+	 */
+	if (pgd_none(pgd))
+		return NULL;
+
+	if (pgd_is_leaf(pgd)) {
+		ret_pte = (pte_t *)pgdp;
+		goto out;
+	}
+
+	if (is_hugepd(__hugepd(pgd_val(pgd)))) {
+		hpdp = (hugepd_t *)&pgd;
+		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
+	 * irq disabled
+	 */
+	pdshift = PUD_SHIFT;
+	pudp = pud_offset(&pgd, ea);
+	pud  = READ_ONCE(*pudp);
+
+	if (pud_none(pud))
+		return NULL;
+
+	if (pud_is_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);
+	pmd  = READ_ONCE(*pmdp);
+
+	/*
+	 * A hugepage collapse is captured by this condition, see
+	 * pmdp_collapse_flush.
+	 */
+	if (pmd_none(pmd))
+		return NULL;
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * A hugepage split is captured by this condition, see
+	 * pmdp_invalidate.
+	 *
+	 * Huge page modification can be caught here too.
+	 */
+	if (pmd_is_serializing(pmd))
+		return NULL;
+#endif
+
+	if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
+		if (is_thp)
+			*is_thp = true;
+		ret_pte = (pte_t *)pmdp;
+		goto out;
+	}
+
+	if (pmd_is_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;
+	return ret_pte;
+}
+EXPORT_SYMBOL_GPL(__find_linux_pte);
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 120a49b..8ec5dfb 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file contains the routines setting up the linux page tables.
  *  -- paulus
@@ -11,12 +12,6 @@
  *
  *  Derived from "arch/i386/mm/init.c"
  *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/kernel.h>
@@ -32,184 +27,36 @@
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
-#include <asm/io.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
 
-#include "mmu_decl.h"
-
-unsigned long ioremap_bot;
-EXPORT_SYMBOL(ioremap_bot);	/* aka VMALLOC_END */
+#include <mm/mmu_decl.h>
 
 extern char etext[], _stext[], _sinittext[], _einittext[];
 
-__ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
+static void __init *early_alloc_pgtable(unsigned long size)
 {
-	pte_t *pte;
+	void *ptr = memblock_alloc(size, size);
 
-	if (slab_is_available()) {
-		pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
-	} else {
-		pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
-		if (pte)
-			clear_page(pte);
+	if (!ptr)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+		      __func__, size, size);
+
+	return ptr;
+}
+
+static pte_t __init *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va)
+{
+	if (pmd_none(*pmdp)) {
+		pte_t *ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
+
+		pmd_populate_kernel(&init_mm, pmdp, ptep);
 	}
-	return pte;
+	return pte_offset_kernel(pmdp, va);
 }
 
-pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
-{
-	struct page *ptepage;
 
-	gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT;
-
-	ptepage = alloc_pages(flags, 0);
-	if (!ptepage)
-		return NULL;
-	if (!pgtable_page_ctor(ptepage)) {
-		__free_page(ptepage);
-		return NULL;
-	}
-	return ptepage;
-}
-
-void __iomem *
-ioremap(phys_addr_t addr, unsigned long size)
-{
-	return __ioremap_caller(addr, size, _PAGE_NO_CACHE | _PAGE_GUARDED,
-				__builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap);
-
-void __iomem *
-ioremap_wc(phys_addr_t addr, unsigned long size)
-{
-	return __ioremap_caller(addr, size, _PAGE_NO_CACHE,
-				__builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_wc);
-
-void __iomem *
-ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
-{
-	/* writeable implies dirty for kernel addresses */
-	if ((flags & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO)
-		flags |= _PAGE_DIRTY | _PAGE_HWWRITE;
-
-	/* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
-	flags &= ~(_PAGE_USER | _PAGE_EXEC);
-	flags |= _PAGE_PRIVILEGED;
-
-	return __ioremap_caller(addr, size, flags, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_prot);
-
-void __iomem *
-__ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
-{
-	return __ioremap_caller(addr, size, flags, __builtin_return_address(0));
-}
-
-void __iomem *
-__ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
-		 void *caller)
-{
-	unsigned long v, i;
-	phys_addr_t p;
-	int err;
-
-	/* Make sure we have the base flags */
-	if ((flags & _PAGE_PRESENT) == 0)
-		flags |= pgprot_val(PAGE_KERNEL);
-
-	/* Non-cacheable page cannot be coherent */
-	if (flags & _PAGE_NO_CACHE)
-		flags &= ~_PAGE_COHERENT;
-
-	/*
-	 * 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
-	 * (ioremap_bot records where we're up to).
-	 */
-	p = 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.
-	 * mem_init() sets high_memory so only do the check after that.
-	 */
-	if (slab_is_available() && (p < virt_to_phys(high_memory)) &&
-	    page_is_ram(__phys_to_pfn(p))) {
-		printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n",
-		       (unsigned long long)p, __builtin_return_address(0));
-		return NULL;
-	}
-#endif
-
-	if (size == 0)
-		return NULL;
-
-	/*
-	 * Is it already mapped?  Perhaps overlapped by a previous
-	 * mapping.
-	 */
-	v = p_block_mapped(p);
-	if (v)
-		goto out;
-
-	if (slab_is_available()) {
-		struct vm_struct *area;
-		area = get_vm_area_caller(size, VM_IOREMAP, caller);
-		if (area == 0)
-			return NULL;
-		area->phys_addr = p;
-		v = (unsigned long) area->addr;
-	} else {
-		v = (ioremap_bot -= size);
-	}
-
-	/*
-	 * Should check if it is a candidate for a BAT mapping
-	 */
-
-	err = 0;
-	for (i = 0; i < size && err == 0; i += PAGE_SIZE)
-		err = map_kernel_page(v+i, p+i, flags);
-	if (err) {
-		if (slab_is_available())
-			vunmap((void *)v);
-		return NULL;
-	}
-
-out:
-	return (void __iomem *) (v + ((unsigned long)addr & ~PAGE_MASK));
-}
-EXPORT_SYMBOL(__ioremap);
-
-void iounmap(volatile void __iomem *addr)
-{
-	/*
-	 * If mapped by BATs then there is nothing to do.
-	 * Calling vfree() generates a benign warning.
-	 */
-	if (v_block_mapped((unsigned long)addr))
-		return;
-
-	if (addr > high_memory && (unsigned long) addr < ioremap_bot)
-		vunmap((void *) (PAGE_MASK & (unsigned long)addr));
-}
-EXPORT_SYMBOL(iounmap);
-
-int map_kernel_page(unsigned long va, phys_addr_t pa, int flags)
+int __ref map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot)
 {
 	pmd_t *pd;
 	pte_t *pg;
@@ -218,16 +65,17 @@
 	/* Use upper 10 bits of VA to index the first level map */
 	pd = pmd_offset(pud_offset(pgd_offset_k(va), va), va);
 	/* Use middle 10 bits of VA to index the second-level map */
-	pg = pte_alloc_kernel(pd, va);
+	if (likely(slab_is_available()))
+		pg = pte_alloc_kernel(pd, va);
+	else
+		pg = early_pte_alloc_kernel(pd, va);
 	if (pg != 0) {
 		err = 0;
 		/* The PTE should never be already set nor present in the
 		 * hash table
 		 */
-		BUG_ON((pte_val(*pg) & (_PAGE_PRESENT | _PAGE_HASHPTE)) &&
-		       flags);
-		set_pte_at(&init_mm, va, pg, pfn_pte(pa >> PAGE_SHIFT,
-						     __pgprot(flags)));
+		BUG_ON((pte_present(*pg) | pte_hashpte(*pg)) && pgprot_val(prot));
+		set_pte_at(&init_mm, va, pg, pfn_pte(pa >> PAGE_SHIFT, prot));
 	}
 	smp_wmb();
 	return err;
@@ -238,7 +86,7 @@
  */
 static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
 {
-	unsigned long v, s, f;
+	unsigned long v, s;
 	phys_addr_t p;
 	int ktext;
 
@@ -248,11 +96,10 @@
 	for (; s < top; s += PAGE_SIZE) {
 		ktext = ((char *)v >= _stext && (char *)v < etext) ||
 			((char *)v >= _sinittext && (char *)v < _einittext);
-		f = ktext ? pgprot_val(PAGE_KERNEL_TEXT) : pgprot_val(PAGE_KERNEL);
-		map_kernel_page(v, p, f);
-#ifdef CONFIG_PPC_STD_MMU_32
+		map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL);
+#ifdef CONFIG_PPC_BOOK3S_32
 		if (ktext)
-			hash_preload(&init_mm, v, 0, 0x300);
+			hash_preload(&init_mm, v);
 #endif
 		v += PAGE_SIZE;
 		p += PAGE_SIZE;
@@ -261,26 +108,20 @@
 
 void __init mapin_ram(void)
 {
-	unsigned long s, top;
+	struct memblock_region *reg;
 
-#ifndef CONFIG_WII
-	top = total_lowmem;
-	s = mmu_mapin_ram(top);
-	__mapin_ram_chunk(s, top);
-#else
-	if (!wii_hole_size) {
-		s = mmu_mapin_ram(total_lowmem);
-		__mapin_ram_chunk(s, total_lowmem);
-	} else {
-		top = wii_hole_start;
-		s = mmu_mapin_ram(top);
-		__mapin_ram_chunk(s, top);
+	for_each_memblock(memory, reg) {
+		phys_addr_t base = reg->base;
+		phys_addr_t top = min(base + reg->size, total_lowmem);
 
-		top = memblock_end_of_DRAM();
-		s = wii_mmu_mapin_mem2(top);
-		__mapin_ram_chunk(s, top);
+		if (base >= top)
+			continue;
+		base = mmu_mapin_ram(base, top);
+		if (IS_ENABLED(CONFIG_BDI_SWITCH))
+			__mapin_ram_chunk(reg->base, top);
+		else
+			__mapin_ram_chunk(base, top);
 	}
-#endif
 }
 
 /* Scan the real Linux page tables and return a PTE pointer for
@@ -366,7 +207,10 @@
 	unsigned long numpages = PFN_UP((unsigned long)_einittext) -
 				 PFN_DOWN((unsigned long)_sinittext);
 
-	change_page_attr(page, numpages, PAGE_KERNEL);
+	if (v_block_mapped((unsigned long)_stext + 1))
+		mmu_mark_initmem_nx();
+	else
+		change_page_attr(page, numpages, PAGE_KERNEL);
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
@@ -375,6 +219,11 @@
 	struct page *page;
 	unsigned long numpages;
 
+	if (v_block_mapped((unsigned long)_sinittext)) {
+		mmu_mark_rodata_ro();
+		return;
+	}
+
 	page = virt_to_page(_stext);
 	numpages = PFN_UP((unsigned long)_etext) -
 		   PFN_DOWN((unsigned long)_stext);
@@ -389,6 +238,9 @@
 		   PFN_DOWN((unsigned long)__start_rodata);
 
 	change_page_attr(page, numpages, PAGE_KERNEL_RO);
+
+	// mark_initmem_nx() should have already run by now
+	ptdump_check_wx();
 }
 #endif
 
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 53e9eee..e78832d 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -1,5 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- *  This file contains ioremap and related functions for 64-bit machines.
+ *  This file contains pgtable related functions for 64-bit machines.
  *
  *  Derived from arch/ppc64/mm/init.c
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -13,12 +14,6 @@
  *
  *  Dave Engebretsen <engebret@us.ibm.com>
  *      Rework for PPC64 port.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/signal.h>
@@ -39,7 +34,6 @@
 #include <asm/pgalloc.h>
 #include <asm/page.h>
 #include <asm/prom.h>
-#include <asm/io.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
@@ -52,7 +46,7 @@
 #include <asm/firmware.h>
 #include <asm/dma.h>
 
-#include "mmu_decl.h"
+#include <mm/mmu_decl.h>
 
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -90,213 +84,39 @@
 EXPORT_SYMBOL(__pgd_val_bits);
 unsigned long __kernel_virt_start;
 EXPORT_SYMBOL(__kernel_virt_start);
-unsigned long __kernel_virt_size;
-EXPORT_SYMBOL(__kernel_virt_size);
 unsigned long __vmalloc_start;
 EXPORT_SYMBOL(__vmalloc_start);
 unsigned long __vmalloc_end;
 EXPORT_SYMBOL(__vmalloc_end);
 unsigned long __kernel_io_start;
 EXPORT_SYMBOL(__kernel_io_start);
+unsigned long __kernel_io_end;
 struct page *vmemmap;
 EXPORT_SYMBOL(vmemmap);
 unsigned long __pte_frag_nr;
 EXPORT_SYMBOL(__pte_frag_nr);
 unsigned long __pte_frag_size_shift;
 EXPORT_SYMBOL(__pte_frag_size_shift);
-unsigned long ioremap_bot;
-#else /* !CONFIG_PPC_BOOK3S_64 */
-unsigned long ioremap_bot = IOREMAP_BASE;
 #endif
 
-/**
- * __ioremap_at - Low level function to establish the page tables
- *                for an IO mapping
- */
-void __iomem * __ioremap_at(phys_addr_t pa, void *ea, unsigned long size,
-			    unsigned long flags)
-{
-	unsigned long i;
-
-	/* Make sure we have the base flags */
-	if ((flags & _PAGE_PRESENT) == 0)
-		flags |= pgprot_val(PAGE_KERNEL);
-
-	/* We don't support the 4K PFN hack with ioremap */
-	if (flags & H_PAGE_4K_PFN)
-		return NULL;
-
-	WARN_ON(pa & ~PAGE_MASK);
-	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
-	WARN_ON(size & ~PAGE_MASK);
-
-	for (i = 0; i < size; i += PAGE_SIZE)
-		if (map_kernel_page((unsigned long)ea+i, pa+i, flags))
-			return NULL;
-
-	return (void __iomem *)ea;
-}
-
-/**
- * __iounmap_from - Low level function to tear down the page tables
- *                  for an IO mapping. This is used for mappings that
- *                  are manipulated manually, like partial unmapping of
- *                  PCI IOs or ISA space.
- */
-void __iounmap_at(void *ea, unsigned long size)
-{
-	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
-	WARN_ON(size & ~PAGE_MASK);
-
-	unmap_kernel_range((unsigned long)ea, size);
-}
-
-void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
-				unsigned long flags, void *caller)
-{
-	phys_addr_t paligned;
-	void __iomem *ret;
-
-	/*
-	 * Choose an address to map it to.
-	 * Once the imalloc system is running, we use it.
-	 * Before that, we map using addresses going
-	 * up from ioremap_bot.  imalloc will use
-	 * the addresses from ioremap_bot through
-	 * IMALLOC_END
-	 * 
-	 */
-	paligned = addr & PAGE_MASK;
-	size = PAGE_ALIGN(addr + size) - paligned;
-
-	if ((size == 0) || (paligned == 0))
-		return NULL;
-
-	if (slab_is_available()) {
-		struct vm_struct *area;
-
-		area = __get_vm_area_caller(size, VM_IOREMAP,
-					    ioremap_bot, IOREMAP_END,
-					    caller);
-		if (area == NULL)
-			return NULL;
-
-		area->phys_addr = paligned;
-		ret = __ioremap_at(paligned, area->addr, size, flags);
-		if (!ret)
-			vunmap(area->addr);
-	} else {
-		ret = __ioremap_at(paligned, (void *)ioremap_bot, size, flags);
-		if (ret)
-			ioremap_bot += size;
-	}
-
-	if (ret)
-		ret += addr & ~PAGE_MASK;
-	return ret;
-}
-
-void __iomem * __ioremap(phys_addr_t addr, unsigned long size,
-			 unsigned long flags)
-{
-	return __ioremap_caller(addr, size, flags, __builtin_return_address(0));
-}
-
-void __iomem * ioremap(phys_addr_t addr, unsigned long size)
-{
-	unsigned long flags = pgprot_val(pgprot_noncached(__pgprot(0)));
-	void *caller = __builtin_return_address(0);
-
-	if (ppc_md.ioremap)
-		return ppc_md.ioremap(addr, size, flags, caller);
-	return __ioremap_caller(addr, size, flags, caller);
-}
-
-void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size)
-{
-	unsigned long flags = pgprot_val(pgprot_noncached_wc(__pgprot(0)));
-	void *caller = __builtin_return_address(0);
-
-	if (ppc_md.ioremap)
-		return ppc_md.ioremap(addr, size, flags, caller);
-	return __ioremap_caller(addr, size, flags, caller);
-}
-
-void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
-			     unsigned long flags)
-{
-	void *caller = __builtin_return_address(0);
-
-	/* writeable implies dirty for kernel addresses */
-	if (flags & _PAGE_WRITE)
-		flags |= _PAGE_DIRTY;
-
-	/* we don't want to let _PAGE_EXEC leak out */
-	flags &= ~_PAGE_EXEC;
-	/*
-	 * Force kernel mapping.
-	 */
-	flags &= ~_PAGE_USER;
-	flags |= _PAGE_PRIVILEGED;
-
-	if (ppc_md.ioremap)
-		return ppc_md.ioremap(addr, size, flags, caller);
-	return __ioremap_caller(addr, size, flags, caller);
-}
-
-
-/*  
- * Unmap an IO region and remove it from imalloc'd list.
- * Access to IO memory should be serialized by driver.
- */
-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) {
-		printk(KERN_WARNING "Attempt to iounmap early bolted mapping"
-		       " at 0x%p\n", addr);
-		return;
-	}
-	vunmap(addr);
-}
-
-void iounmap(volatile void __iomem *token)
-{
-	if (ppc_md.iounmap)
-		ppc_md.iounmap(token);
-	else
-		__iounmap(token);
-}
-
-EXPORT_SYMBOL(ioremap);
-EXPORT_SYMBOL(ioremap_wc);
-EXPORT_SYMBOL(ioremap_prot);
-EXPORT_SYMBOL(__ioremap);
-EXPORT_SYMBOL(__ioremap_at);
-EXPORT_SYMBOL(iounmap);
-EXPORT_SYMBOL(__iounmap);
-EXPORT_SYMBOL(__iounmap_at);
-
 #ifndef __PAGETABLE_PUD_FOLDED
 /* 4 level page table */
 struct page *pgd_page(pgd_t pgd)
 {
-	if (pgd_huge(pgd))
+	if (pgd_is_leaf(pgd)) {
+		VM_WARN_ON(!pgd_huge(pgd));
 		return pte_page(pgd_pte(pgd));
+	}
 	return virt_to_page(pgd_page_vaddr(pgd));
 }
 #endif
 
 struct page *pud_page(pud_t pud)
 {
-	if (pud_huge(pud))
+	if (pud_is_leaf(pud)) {
+		VM_WARN_ON(!pud_huge(pud));
 		return pte_page(pud_pte(pud));
+	}
 	return virt_to_page(pud_page_vaddr(pud));
 }
 
@@ -306,8 +126,10 @@
  */
 struct page *pmd_page(pmd_t pmd)
 {
-	if (pmd_trans_huge(pmd) || pmd_huge(pmd) || pmd_devmap(pmd))
+	if (pmd_is_leaf(pmd)) {
+		VM_WARN_ON(!(pmd_large(pmd) || pmd_huge(pmd)));
 		return pte_page(pmd_pte(pmd));
+	}
 	return virt_to_page(pmd_page_vaddr(pmd));
 }
 
@@ -323,6 +145,9 @@
 		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/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
deleted file mode 100644
index bea6c54..0000000
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ /dev/null
@@ -1,289 +0,0 @@
-/*
- * This file contains the routines for handling the MMU on those
- * PowerPC implementations where the MMU substantially follows the
- * architecture specification.  This includes the 6xx, 7xx, 7xxx,
- * and 8260 implementations but excludes the 8xx and 4xx.
- *  -- 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
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/init.h>
-#include <linux/highmem.h>
-#include <linux/memblock.h>
-
-#include <asm/prom.h>
-#include <asm/mmu.h>
-#include <asm/machdep.h>
-
-#include "mmu_decl.h"
-
-struct hash_pte *Hash, *Hash_end;
-unsigned long Hash_size, Hash_mask;
-unsigned long _SDR1;
-
-struct ppc_bat BATS[8][2];	/* 8 pairs of IBAT, DBAT */
-
-struct batrange {		/* stores address ranges mapped by BATs */
-	unsigned long start;
-	unsigned long limit;
-	phys_addr_t phys;
-} bat_addrs[8];
-
-/*
- * Return PA for this VA if it is mapped by a BAT, or 0
- */
-phys_addr_t v_block_mapped(unsigned long va)
-{
-	int b;
-	for (b = 0; b < 4; ++b)
-		if (va >= bat_addrs[b].start && va < bat_addrs[b].limit)
-			return bat_addrs[b].phys + (va - bat_addrs[b].start);
-	return 0;
-}
-
-/*
- * Return VA for a given PA or 0 if not mapped
- */
-unsigned long p_block_mapped(phys_addr_t pa)
-{
-	int b;
-	for (b = 0; b < 4; ++b)
-		if (pa >= bat_addrs[b].phys
-	    	    && pa < (bat_addrs[b].limit-bat_addrs[b].start)
-		              +bat_addrs[b].phys)
-			return bat_addrs[b].start+(pa-bat_addrs[b].phys);
-	return 0;
-}
-
-unsigned long __init mmu_mapin_ram(unsigned long top)
-{
-	unsigned long tot, bl, done;
-	unsigned long max_size = (256<<20);
-
-	if (__map_without_bats) {
-		printk(KERN_DEBUG "RAM mapped without BATs\n");
-		return 0;
-	}
-
-	/* Set up BAT2 and if necessary BAT3 to cover RAM. */
-
-	/* Make sure we don't map a block larger than the
-	   smallest alignment of the physical address. */
-	tot = top;
-	for (bl = 128<<10; bl < max_size; bl <<= 1) {
-		if (bl * 2 > tot)
-			break;
-	}
-
-	setbat(2, PAGE_OFFSET, 0, bl, PAGE_KERNEL_X);
-	done = (unsigned long)bat_addrs[2].limit - PAGE_OFFSET + 1;
-	if ((done < tot) && !bat_addrs[3].limit) {
-		/* use BAT3 to cover a bit more */
-		tot -= done;
-		for (bl = 128<<10; bl < max_size; bl <<= 1)
-			if (bl * 2 > tot)
-				break;
-		setbat(3, PAGE_OFFSET+done, done, bl, PAGE_KERNEL_X);
-		done = (unsigned long)bat_addrs[3].limit - PAGE_OFFSET + 1;
-	}
-
-	return done;
-}
-
-/*
- * Set up one of the I/D BAT (block address translation) register pairs.
- * The parameters are not checked; in particular size must be a power
- * of 2 between 128k and 256M.
- */
-void __init setbat(int index, unsigned long virt, phys_addr_t phys,
-		   unsigned int size, pgprot_t prot)
-{
-	unsigned int bl;
-	int wimgxpp;
-	struct ppc_bat *bat = BATS[index];
-	unsigned long flags = pgprot_val(prot);
-
-	if ((flags & _PAGE_NO_CACHE) ||
-	    (cpu_has_feature(CPU_FTR_NEED_COHERENT) == 0))
-		flags &= ~_PAGE_COHERENT;
-
-	bl = (size >> 17) - 1;
-	if (PVR_VER(mfspr(SPRN_PVR)) != 1) {
-		/* 603, 604, etc. */
-		/* Do DBAT first */
-		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
-				   | _PAGE_COHERENT | _PAGE_GUARDED);
-		wimgxpp |= (flags & _PAGE_RW)? 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)
-			bat[1].batu |= 1; 	/* Vp = 1 */
-		if (flags & _PAGE_GUARDED) {
-			/* G bit must be zero in IBATs */
-			bat[0].batu = bat[0].batl = 0;
-		} else {
-			/* make IBAT same as DBAT */
-			bat[0] = bat[1];
-		}
-	} else {
-		/* 601 cpu */
-		if (bl > BL_8M)
-			bl = BL_8M;
-		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
-				   | _PAGE_COHERENT);
-		wimgxpp |= (flags & _PAGE_RW)?
-			((flags & _PAGE_USER)? PP_RWRW: PP_RWXX): PP_RXRX;
-		bat->batu = virt | wimgxpp | 4;	/* Ks=0, Ku=1 */
-		bat->batl = phys | bl | 0x40;	/* V=1 */
-	}
-
-	bat_addrs[index].start = virt;
-	bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1;
-	bat_addrs[index].phys = phys;
-}
-
-/*
- * Preload a translation in the hash table
- */
-void hash_preload(struct mm_struct *mm, unsigned long ea,
-		  unsigned long access, unsigned long trap)
-{
-	pmd_t *pmd;
-
-	if (!Hash)
-		return;
-	pmd = pmd_offset(pud_offset(pgd_offset(mm, ea), ea), ea);
-	if (!pmd_none(*pmd))
-		add_hash_page(mm->context.id, ea, pmd_val(*pmd));
-}
-
-/*
- * Initialize the hash table and patch the instructions in hashtable.S.
- */
-void __init MMU_init_hw(void)
-{
-	unsigned int hmask, mb, mb2;
-	unsigned int n_hpteg, lg_n_hpteg;
-
-	extern unsigned int hash_page_patch_A[];
-	extern unsigned int hash_page_patch_B[], hash_page_patch_C[];
-	extern unsigned int hash_page[];
-	extern unsigned int flush_hash_patch_A[], flush_hash_patch_B[];
-
-	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) {
-		/*
-		 * Put a blr (procedure return) instruction at the
-		 * start of hash_page, since we can still get DSI
-		 * exceptions on a 603.
-		 */
-		hash_page[0] = 0x4e800020;
-		flush_icache_range((unsigned long) &hash_page[0],
-				   (unsigned long) &hash_page[1]);
-		return;
-	}
-
-	if ( ppc_md.progress ) ppc_md.progress("hash:enter", 0x105);
-
-#define LG_HPTEG_SIZE	6		/* 64 bytes per HPTEG */
-#define SDR1_LOW_BITS	((n_hpteg - 1) >> 10)
-#define MIN_N_HPTEG	1024		/* min 64kB hash table */
-
-	/*
-	 * Allow 1 HPTE (1/8 HPTEG) for each page of memory.
-	 * This is less than the recommended amount, but then
-	 * Linux ain't AIX.
-	 */
-	n_hpteg = total_memory / (PAGE_SIZE * 8);
-	if (n_hpteg < MIN_N_HPTEG)
-		n_hpteg = MIN_N_HPTEG;
-	lg_n_hpteg = __ilog2(n_hpteg);
-	if (n_hpteg & (n_hpteg - 1)) {
-		++lg_n_hpteg;		/* round up if not power of 2 */
-		n_hpteg = 1 << lg_n_hpteg;
-	}
-	Hash_size = n_hpteg << LG_HPTEG_SIZE;
-
-	/*
-	 * Find some memory for the hash table.
-	 */
-	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
-	Hash = __va(memblock_alloc(Hash_size, Hash_size));
-	memset(Hash, 0, Hash_size);
-	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
-
-	Hash_end = (struct hash_pte *) ((unsigned long)Hash + Hash_size);
-
-	printk("Total memory = %lldMB; using %ldkB for hash table (at %p)\n",
-	       (unsigned long long)(total_memory >> 20), Hash_size >> 10, Hash);
-
-
-	/*
-	 * Patch up the instructions in hashtable.S:create_hpte
-	 */
-	if ( ppc_md.progress ) ppc_md.progress("hash:patch", 0x345);
-	Hash_mask = n_hpteg - 1;
-	hmask = Hash_mask >> (16 - LG_HPTEG_SIZE);
-	mb2 = mb = 32 - LG_HPTEG_SIZE - lg_n_hpteg;
-	if (lg_n_hpteg > 16)
-		mb2 = 16 - LG_HPTEG_SIZE;
-
-	hash_page_patch_A[0] = (hash_page_patch_A[0] & ~0xffff)
-		| ((unsigned int)(Hash) >> 16);
-	hash_page_patch_A[1] = (hash_page_patch_A[1] & ~0x7c0) | (mb << 6);
-	hash_page_patch_A[2] = (hash_page_patch_A[2] & ~0x7c0) | (mb2 << 6);
-	hash_page_patch_B[0] = (hash_page_patch_B[0] & ~0xffff) | hmask;
-	hash_page_patch_C[0] = (hash_page_patch_C[0] & ~0xffff) | hmask;
-
-	/*
-	 * Ensure that the locations we've patched have been written
-	 * out from the data cache and invalidated in the instruction
-	 * cache, on those machines with split caches.
-	 */
-	flush_icache_range((unsigned long) &hash_page_patch_A[0],
-			   (unsigned long) &hash_page_patch_C[1]);
-
-	/*
-	 * Patch up the instructions in hashtable.S:flush_hash_page
-	 */
-	flush_hash_patch_A[0] = (flush_hash_patch_A[0] & ~0xffff)
-		| ((unsigned int)(Hash) >> 16);
-	flush_hash_patch_A[1] = (flush_hash_patch_A[1] & ~0x7c0) | (mb << 6);
-	flush_hash_patch_A[2] = (flush_hash_patch_A[2] & ~0x7c0) | (mb2 << 6);
-	flush_hash_patch_B[0] = (flush_hash_patch_B[0] & ~0xffff) | hmask;
-	flush_icache_range((unsigned long) &flush_hash_patch_A[0],
-			   (unsigned long) &flush_hash_patch_B[1]);
-
-	if ( ppc_md.progress ) ppc_md.progress("hash:done", 0x205);
-}
-
-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);
-
-	/* 601 can only access 16MB at the moment */
-	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
-		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000));
-	else /* Anything else has 256M mapped */
-		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000));
-}
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c
new file mode 100644
index 0000000..9e2d8e8
--- /dev/null
+++ b/arch/powerpc/mm/ptdump/8xx.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * From split of dump_linuxpagetables.c
+ * Copyright 2016, Rashmica Gupta, IBM Corp.
+ *
+ */
+#include <linux/kernel.h>
+#include <asm/pgtable.h>
+
+#include "ptdump.h"
+
+static const struct flag_info flag_array[] = {
+	{
+		.mask	= _PAGE_SH,
+		.val	= 0,
+		.set	= "user",
+		.clear	= "    ",
+	}, {
+		.mask	= _PAGE_RO | _PAGE_NA,
+		.val	= 0,
+		.set	= "rw",
+	}, {
+		.mask	= _PAGE_RO | _PAGE_NA,
+		.val	= _PAGE_RO,
+		.set	= "r ",
+	}, {
+		.mask	= _PAGE_RO | _PAGE_NA,
+		.val	= _PAGE_NA,
+		.set	= "  ",
+	}, {
+		.mask	= _PAGE_EXEC,
+		.val	= _PAGE_EXEC,
+		.set	= " X ",
+		.clear	= "   ",
+	}, {
+		.mask	= _PAGE_PRESENT,
+		.val	= _PAGE_PRESENT,
+		.set	= "present",
+		.clear	= "       ",
+	}, {
+		.mask	= _PAGE_GUARDED,
+		.val	= _PAGE_GUARDED,
+		.set	= "guarded",
+		.clear	= "       ",
+	}, {
+		.mask	= _PAGE_DIRTY,
+		.val	= _PAGE_DIRTY,
+		.set	= "dirty",
+		.clear	= "     ",
+	}, {
+		.mask	= _PAGE_ACCESSED,
+		.val	= _PAGE_ACCESSED,
+		.set	= "accessed",
+		.clear	= "        ",
+	}, {
+		.mask	= _PAGE_NO_CACHE,
+		.val	= _PAGE_NO_CACHE,
+		.set	= "no cache",
+		.clear	= "        ",
+	}, {
+		.mask	= _PAGE_SPECIAL,
+		.val	= _PAGE_SPECIAL,
+		.set	= "special",
+	}
+};
+
+struct pgtable_level pg_level[5] = {
+	{
+	}, { /* pgd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* pud */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* pmd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* pte */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	},
+};
diff --git a/arch/powerpc/mm/ptdump/Makefile b/arch/powerpc/mm/ptdump/Makefile
new file mode 100644
index 0000000..712762b
--- /dev/null
+++ b/arch/powerpc/mm/ptdump/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-y	+= ptdump.o
+
+obj-$(CONFIG_4xx)		+= shared.o
+obj-$(CONFIG_PPC_8xx)		+= 8xx.o
+obj-$(CONFIG_PPC_BOOK3E_MMU)	+= shared.o
+obj-$(CONFIG_PPC_BOOK3S_32)	+= shared.o bats.o segment_regs.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= book3s64.o hashpagetable.o
diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c
new file mode 100644
index 0000000..4154fea
--- /dev/null
+++ b/arch/powerpc/mm/ptdump/bats.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2018, Christophe Leroy CS S.I.
+ * <christophe.leroy@c-s.fr>
+ *
+ * This dumps the content of BATS
+ */
+
+#include <asm/debugfs.h>
+#include <asm/pgtable.h>
+#include <asm/cpu_has_feature.h>
+
+static char *pp_601(int k, int pp)
+{
+	if (pp == 0)
+		return k ? "NA" : "RWX";
+	if (pp == 1)
+		return k ? "ROX" : "RWX";
+	if (pp == 2)
+		return k ? "RWX" : "RWX";
+	return k ? "ROX" : "ROX";
+}
+
+static void bat_show_601(struct seq_file *m, int idx, u32 lower, u32 upper)
+{
+	u32 blpi = upper & 0xfffe0000;
+	u32 k = (upper >> 2) & 3;
+	u32 pp = upper & 3;
+	phys_addr_t pbn = PHYS_BAT_ADDR(lower);
+	u32 bsm = lower & 0x3ff;
+	u32 size = (bsm + 1) << 17;
+
+	seq_printf(m, "%d: ", idx);
+	if (!(lower & 0x40)) {
+		seq_puts(m, "        -\n");
+		return;
+	}
+
+	seq_printf(m, "0x%08x-0x%08x ", blpi, blpi + size - 1);
+#ifdef CONFIG_PHYS_64BIT
+	seq_printf(m, "0x%016llx ", pbn);
+#else
+	seq_printf(m, "0x%08x ", pbn);
+#endif
+
+	seq_printf(m, "Kernel %s User %s", pp_601(k & 2, pp), pp_601(k & 1, pp));
+
+	if (lower & _PAGE_WRITETHRU)
+		seq_puts(m, "write through ");
+	if (lower & _PAGE_NO_CACHE)
+		seq_puts(m, "no cache ");
+	if (lower & _PAGE_COHERENT)
+		seq_puts(m, "coherent ");
+	seq_puts(m, "\n");
+}
+
+#define BAT_SHOW_601(_m, _n, _l, _u) bat_show_601(_m, _n, mfspr(_l), mfspr(_u))
+
+static int bats_show_601(struct seq_file *m, void *v)
+{
+	seq_puts(m, "---[ Block Address Translation ]---\n");
+
+	BAT_SHOW_601(m, 0, SPRN_IBAT0L, SPRN_IBAT0U);
+	BAT_SHOW_601(m, 1, SPRN_IBAT1L, SPRN_IBAT1U);
+	BAT_SHOW_601(m, 2, SPRN_IBAT2L, SPRN_IBAT2U);
+	BAT_SHOW_601(m, 3, SPRN_IBAT3L, SPRN_IBAT3U);
+
+	return 0;
+}
+
+static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool is_d)
+{
+	u32 bepi = upper & 0xfffe0000;
+	u32 bl = (upper >> 2) & 0x7ff;
+	u32 k = upper & 3;
+	phys_addr_t brpn = PHYS_BAT_ADDR(lower);
+	u32 size = (bl + 1) << 17;
+
+	seq_printf(m, "%d: ", idx);
+	if (k == 0) {
+		seq_puts(m, "        -\n");
+		return;
+	}
+
+	seq_printf(m, "0x%08x-0x%08x ", bepi, bepi + size - 1);
+#ifdef CONFIG_PHYS_64BIT
+	seq_printf(m, "0x%016llx ", brpn);
+#else
+	seq_printf(m, "0x%08x ", brpn);
+#endif
+
+	if (k == 1)
+		seq_puts(m, "User ");
+	else if (k == 2)
+		seq_puts(m, "Kernel ");
+	else
+		seq_puts(m, "Kernel/User ");
+
+	if (lower & BPP_RX)
+		seq_puts(m, is_d ? "RO " : "EXEC ");
+	else if (lower & BPP_RW)
+		seq_puts(m, is_d ? "RW " : "EXEC ");
+	else
+		seq_puts(m, is_d ? "NA " : "NX   ");
+
+	if (lower & _PAGE_WRITETHRU)
+		seq_puts(m, "write through ");
+	if (lower & _PAGE_NO_CACHE)
+		seq_puts(m, "no cache ");
+	if (lower & _PAGE_COHERENT)
+		seq_puts(m, "coherent ");
+	if (lower & _PAGE_GUARDED)
+		seq_puts(m, "guarded ");
+	seq_puts(m, "\n");
+}
+
+#define BAT_SHOW_603(_m, _n, _l, _u, _d) bat_show_603(_m, _n, mfspr(_l), mfspr(_u), _d)
+
+static int bats_show_603(struct seq_file *m, void *v)
+{
+	seq_puts(m, "---[ Instruction Block Address Translation ]---\n");
+
+	BAT_SHOW_603(m, 0, SPRN_IBAT0L, SPRN_IBAT0U, false);
+	BAT_SHOW_603(m, 1, SPRN_IBAT1L, SPRN_IBAT1U, false);
+	BAT_SHOW_603(m, 2, SPRN_IBAT2L, SPRN_IBAT2U, false);
+	BAT_SHOW_603(m, 3, SPRN_IBAT3L, SPRN_IBAT3U, false);
+	if (mmu_has_feature(MMU_FTR_USE_HIGH_BATS)) {
+		BAT_SHOW_603(m, 4, SPRN_IBAT4L, SPRN_IBAT4U, false);
+		BAT_SHOW_603(m, 5, SPRN_IBAT5L, SPRN_IBAT5U, false);
+		BAT_SHOW_603(m, 6, SPRN_IBAT6L, SPRN_IBAT6U, false);
+		BAT_SHOW_603(m, 7, SPRN_IBAT7L, SPRN_IBAT7U, false);
+	}
+
+	seq_puts(m, "\n---[ Data Block Address Translation ]---\n");
+
+	BAT_SHOW_603(m, 0, SPRN_DBAT0L, SPRN_DBAT0U, true);
+	BAT_SHOW_603(m, 1, SPRN_DBAT1L, SPRN_DBAT1U, true);
+	BAT_SHOW_603(m, 2, SPRN_DBAT2L, SPRN_DBAT2U, true);
+	BAT_SHOW_603(m, 3, SPRN_DBAT3L, SPRN_DBAT3U, true);
+	if (mmu_has_feature(MMU_FTR_USE_HIGH_BATS)) {
+		BAT_SHOW_603(m, 4, SPRN_DBAT4L, SPRN_DBAT4U, true);
+		BAT_SHOW_603(m, 5, SPRN_DBAT5L, SPRN_DBAT5U, true);
+		BAT_SHOW_603(m, 6, SPRN_DBAT6L, SPRN_DBAT6U, true);
+		BAT_SHOW_603(m, 7, SPRN_DBAT7L, SPRN_DBAT7U, true);
+	}
+
+	return 0;
+}
+
+static int bats_open(struct inode *inode, struct file *file)
+{
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
+		return single_open(file, bats_show_601, NULL);
+
+	return single_open(file, bats_show_603, NULL);
+}
+
+static const struct file_operations bats_fops = {
+	.open		= bats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init bats_init(void)
+{
+	struct dentry *debugfs_file;
+
+	debugfs_file = debugfs_create_file("block_address_translation", 0400,
+					   powerpc_debugfs_root, NULL, &bats_fops);
+	return debugfs_file ? 0 : -ENOMEM;
+}
+device_initcall(bats_init);
diff --git a/arch/powerpc/mm/ptdump/book3s64.c b/arch/powerpc/mm/ptdump/book3s64.c
new file mode 100644
index 0000000..0dfca72
--- /dev/null
+++ b/arch/powerpc/mm/ptdump/book3s64.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * From split of dump_linuxpagetables.c
+ * Copyright 2016, Rashmica Gupta, IBM Corp.
+ *
+ */
+#include <linux/kernel.h>
+#include <asm/pgtable.h>
+
+#include "ptdump.h"
+
+static const struct flag_info flag_array[] = {
+	{
+		.mask	= _PAGE_PRIVILEGED,
+		.val	= 0,
+		.set	= "user",
+		.clear	= "    ",
+	}, {
+		.mask	= _PAGE_READ,
+		.val	= _PAGE_READ,
+		.set	= "r",
+		.clear	= " ",
+	}, {
+		.mask	= _PAGE_WRITE,
+		.val	= _PAGE_WRITE,
+		.set	= "w",
+		.clear	= " ",
+	}, {
+		.mask	= _PAGE_EXEC,
+		.val	= _PAGE_EXEC,
+		.set	= " X ",
+		.clear	= "   ",
+	}, {
+		.mask	= _PAGE_PTE,
+		.val	= _PAGE_PTE,
+		.set	= "pte",
+		.clear	= "   ",
+	}, {
+		.mask	= _PAGE_PRESENT,
+		.val	= _PAGE_PRESENT,
+		.set	= "valid",
+		.clear	= "     ",
+	}, {
+		.mask	= _PAGE_PRESENT | _PAGE_INVALID,
+		.val	= 0,
+		.set	= "       ",
+		.clear	= "present",
+	}, {
+		.mask	= H_PAGE_HASHPTE,
+		.val	= H_PAGE_HASHPTE,
+		.set	= "hpte",
+		.clear	= "    ",
+	}, {
+		.mask	= _PAGE_DIRTY,
+		.val	= _PAGE_DIRTY,
+		.set	= "dirty",
+		.clear	= "     ",
+	}, {
+		.mask	= _PAGE_ACCESSED,
+		.val	= _PAGE_ACCESSED,
+		.set	= "accessed",
+		.clear	= "        ",
+	}, {
+		.mask	= _PAGE_NON_IDEMPOTENT,
+		.val	= _PAGE_NON_IDEMPOTENT,
+		.set	= "non-idempotent",
+		.clear	= "              ",
+	}, {
+		.mask	= _PAGE_TOLERANT,
+		.val	= _PAGE_TOLERANT,
+		.set	= "tolerant",
+		.clear	= "        ",
+	}, {
+		.mask	= H_PAGE_BUSY,
+		.val	= H_PAGE_BUSY,
+		.set	= "busy",
+	}, {
+#ifdef CONFIG_PPC_64K_PAGES
+		.mask	= H_PAGE_COMBO,
+		.val	= H_PAGE_COMBO,
+		.set	= "combo",
+	}, {
+		.mask	= H_PAGE_4K_PFN,
+		.val	= H_PAGE_4K_PFN,
+		.set	= "4K_pfn",
+	}, {
+#else /* CONFIG_PPC_64K_PAGES */
+		.mask	= H_PAGE_F_GIX,
+		.val	= H_PAGE_F_GIX,
+		.set	= "f_gix",
+		.is_val	= true,
+		.shift	= H_PAGE_F_GIX_SHIFT,
+	}, {
+		.mask	= H_PAGE_F_SECOND,
+		.val	= H_PAGE_F_SECOND,
+		.set	= "f_second",
+	}, {
+#endif /* CONFIG_PPC_64K_PAGES */
+		.mask	= _PAGE_SPECIAL,
+		.val	= _PAGE_SPECIAL,
+		.set	= "special",
+	}
+};
+
+struct pgtable_level pg_level[5] = {
+	{
+	}, { /* pgd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* pud */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* pmd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* pte */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	},
+};
diff --git a/arch/powerpc/mm/dump_hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
similarity index 94%
rename from arch/powerpc/mm/dump_hashpagetable.c
rename to arch/powerpc/mm/ptdump/hashpagetable.c
index 8692946..a072780 100644
--- a/arch/powerpc/mm/dump_hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2016, Rashmica Gupta, IBM Corp.
  *
@@ -7,11 +8,6 @@
  *
  * If radix is enabled then there is no hash page table and so no debugfs file
  * is generated.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 #include <linux/debugfs.h>
 #include <linux/fs.h>
@@ -241,7 +237,6 @@
 	return -1;
 }
 
-#ifdef CONFIG_PPC_PSERIES
 static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *r)
 {
 	struct hash_pte ptes[4];
@@ -278,7 +273,6 @@
 	}
 	return -1;
 }
-#endif
 
 static void decode_r(int bps, unsigned long r, unsigned long *rpn, int *aps,
 		unsigned long *lp_bits)
@@ -320,10 +314,9 @@
 static int base_hpte_find(unsigned long ea, int psize, bool primary, u64 *v,
 			  u64 *r)
 {
-#ifdef CONFIG_PPC_PSERIES
-	if (firmware_has_feature(FW_FEATURE_LPAR))
+	if (IS_ENABLED(CONFIG_PPC_PSERIES) && firmware_has_feature(FW_FEATURE_LPAR))
 		return pseries_find(ea, psize, primary, v, r);
-#endif
+
 	return native_find(ea, psize, primary, v, r);
 }
 
@@ -342,7 +335,7 @@
 
 	/* Look in secondary table */
 	if (slot == -1)
-		slot = base_hpte_find(ea, psize, true, &v, &r);
+		slot = base_hpte_find(ea, psize, false, &v, &r);
 
 	/* No entry found */
 	if (slot == -1)
@@ -390,12 +383,13 @@
 			psize = mmu_vmalloc_psize;
 		else
 			psize = mmu_io_psize;
-#ifdef CONFIG_PPC_64K_PAGES
+
 		/* check for secret 4K mappings */
-		if (((pteval & H_PAGE_COMBO) == H_PAGE_COMBO) ||
-			((pteval & H_PAGE_4K_PFN) == H_PAGE_4K_PFN))
+		if (IS_ENABLED(CONFIG_PPC_64K_PAGES) &&
+		    ((pteval & H_PAGE_COMBO) == H_PAGE_COMBO ||
+		     (pteval & H_PAGE_4K_PFN) == H_PAGE_4K_PFN))
 			psize = mmu_io_psize;
-#endif
+
 		/* check for hashpte */
 		status = hpte_find(st, addr, psize);
 
@@ -473,9 +467,10 @@
 
 static void walk_vmemmap(struct pg_state *st)
 {
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
 	struct vmemmap_backing *ptr = vmemmap_list;
 
+	if (!IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP))
+		return;
 	/*
 	 * Traverse the vmemmaped memory and dump pages that are in the hash
 	 * pagetable.
@@ -485,7 +480,6 @@
 		ptr = ptr->list;
 	}
 	seq_puts(st->seq, "---[ vmemmap end ]---\n");
-#endif
 }
 
 static void populate_markers(void)
@@ -499,11 +493,7 @@
 	address_markers[6].start_address = PHB_IO_END;
 	address_markers[7].start_address = IOREMAP_BASE;
 	address_markers[8].start_address = IOREMAP_END;
-#ifdef CONFIG_PPC_BOOK3S_64
-	address_markers[9].start_address =  H_VMEMMAP_BASE;
-#else
-	address_markers[9].start_address =  VMEMMAP_BASE;
-#endif
+	address_markers[9].start_address =  H_VMEMMAP_START;
 }
 
 static int ptdump_show(struct seq_file *m, void *v)
diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/ptdump/ptdump.c
similarity index 64%
rename from arch/powerpc/mm/dump_linuxpagetables.c
rename to arch/powerpc/mm/ptdump/ptdump.c
index bdf33b9..2f9ddc2 100644
--- a/arch/powerpc/mm/dump_linuxpagetables.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2016, Rashmica Gupta, IBM Corp.
  *
@@ -8,17 +9,13 @@
  * Derived from the arm64 implementation:
  * Copyright (c) 2014, The Linux Foundation, Laura Abbott.
  * (C) Copyright 2008 Intel Corporation, Arjan van de Ven.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 #include <linux/debugfs.h>
 #include <linux/fs.h>
 #include <linux/hugetlb.h>
 #include <linux/io.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <asm/fixmap.h>
@@ -27,9 +24,7 @@
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 
-#ifdef CONFIG_PPC32
-#define KERN_VIRT_START	0
-#endif
+#include "ptdump.h"
 
 /*
  * To visualise what is happening,
@@ -65,6 +60,8 @@
 	unsigned long last_pa;
 	unsigned int level;
 	u64 current_flags;
+	bool check_wx;
+	unsigned long wx_pages;
 };
 
 struct addr_marker {
@@ -87,10 +84,6 @@
 #else
 	{ 0,	"Early I/O remap start" },
 	{ 0,	"Early I/O remap end" },
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	{ 0,	"Consistent mem start" },
-	{ 0,	"Consistent mem end" },
-#endif
 #ifdef CONFIG_HIGHMEM
 	{ 0,	"Highmem PTEs start" },
 	{ 0,	"Highmem PTEs end" },
@@ -98,161 +91,24 @@
 	{ 0,	"Fixmap start" },
 	{ 0,	"Fixmap end" },
 #endif
+#ifdef CONFIG_KASAN
+	{ 0,	"kasan shadow mem start" },
+	{ 0,	"kasan shadow mem end" },
+#endif
 	{ -1,	NULL },
 };
 
-struct flag_info {
-	u64		mask;
-	u64		val;
-	const char	*set;
-	const char	*clear;
-	bool		is_val;
-	int		shift;
-};
+#define pt_dump_seq_printf(m, fmt, args...)	\
+({						\
+	if (m)					\
+		seq_printf(m, fmt, ##args);	\
+})
 
-static const struct flag_info flag_array[] = {
-	{
-		.mask	= _PAGE_USER | _PAGE_PRIVILEGED,
-		.val	= _PAGE_USER,
-		.set	= "user",
-		.clear	= "    ",
-	}, {
-		.mask	= _PAGE_RW | _PAGE_RO | _PAGE_NA,
-		.val	= _PAGE_RW,
-		.set	= "rw",
-	}, {
-		.mask	= _PAGE_RW | _PAGE_RO | _PAGE_NA,
-		.val	= _PAGE_RO,
-		.set	= "ro",
-	}, {
-#if _PAGE_NA != 0
-		.mask	= _PAGE_RW | _PAGE_RO | _PAGE_NA,
-		.val	= _PAGE_RO,
-		.set	= "na",
-	}, {
-#endif
-		.mask	= _PAGE_EXEC,
-		.val	= _PAGE_EXEC,
-		.set	= " X ",
-		.clear	= "   ",
-	}, {
-		.mask	= _PAGE_PTE,
-		.val	= _PAGE_PTE,
-		.set	= "pte",
-		.clear	= "   ",
-	}, {
-		.mask	= _PAGE_PRESENT,
-		.val	= _PAGE_PRESENT,
-		.set	= "present",
-		.clear	= "       ",
-	}, {
-#ifdef CONFIG_PPC_BOOK3S_64
-		.mask	= H_PAGE_HASHPTE,
-		.val	= H_PAGE_HASHPTE,
-#else
-		.mask	= _PAGE_HASHPTE,
-		.val	= _PAGE_HASHPTE,
-#endif
-		.set	= "hpte",
-		.clear	= "    ",
-	}, {
-#ifndef CONFIG_PPC_BOOK3S_64
-		.mask	= _PAGE_GUARDED,
-		.val	= _PAGE_GUARDED,
-		.set	= "guarded",
-		.clear	= "       ",
-	}, {
-#endif
-		.mask	= _PAGE_DIRTY,
-		.val	= _PAGE_DIRTY,
-		.set	= "dirty",
-		.clear	= "     ",
-	}, {
-		.mask	= _PAGE_ACCESSED,
-		.val	= _PAGE_ACCESSED,
-		.set	= "accessed",
-		.clear	= "        ",
-	}, {
-#ifndef CONFIG_PPC_BOOK3S_64
-		.mask	= _PAGE_WRITETHRU,
-		.val	= _PAGE_WRITETHRU,
-		.set	= "write through",
-		.clear	= "             ",
-	}, {
-#endif
-#ifndef CONFIG_PPC_BOOK3S_64
-		.mask	= _PAGE_NO_CACHE,
-		.val	= _PAGE_NO_CACHE,
-		.set	= "no cache",
-		.clear	= "        ",
-	}, {
-#else
-		.mask	= _PAGE_NON_IDEMPOTENT,
-		.val	= _PAGE_NON_IDEMPOTENT,
-		.set	= "non-idempotent",
-		.clear	= "              ",
-	}, {
-		.mask	= _PAGE_TOLERANT,
-		.val	= _PAGE_TOLERANT,
-		.set	= "tolerant",
-		.clear	= "        ",
-	}, {
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
-		.mask	= H_PAGE_BUSY,
-		.val	= H_PAGE_BUSY,
-		.set	= "busy",
-	}, {
-#ifdef CONFIG_PPC_64K_PAGES
-		.mask	= H_PAGE_COMBO,
-		.val	= H_PAGE_COMBO,
-		.set	= "combo",
-	}, {
-		.mask	= H_PAGE_4K_PFN,
-		.val	= H_PAGE_4K_PFN,
-		.set	= "4K_pfn",
-	}, {
-#else /* CONFIG_PPC_64K_PAGES */
-		.mask	= H_PAGE_F_GIX,
-		.val	= H_PAGE_F_GIX,
-		.set	= "f_gix",
-		.is_val	= true,
-		.shift	= H_PAGE_F_GIX_SHIFT,
-	}, {
-		.mask	= H_PAGE_F_SECOND,
-		.val	= H_PAGE_F_SECOND,
-		.set	= "f_second",
-	}, {
-#endif /* CONFIG_PPC_64K_PAGES */
-#endif
-		.mask	= _PAGE_SPECIAL,
-		.val	= _PAGE_SPECIAL,
-		.set	= "special",
-	}
-};
-
-struct pgtable_level {
-	const struct flag_info *flag;
-	size_t num;
-	u64 mask;
-};
-
-static struct pgtable_level pg_level[] = {
-	{
-	}, { /* pgd */
-		.flag	= flag_array,
-		.num	= ARRAY_SIZE(flag_array),
-	}, { /* pud */
-		.flag	= flag_array,
-		.num	= ARRAY_SIZE(flag_array),
-	}, { /* pmd */
-		.flag	= flag_array,
-		.num	= ARRAY_SIZE(flag_array),
-	}, { /* pte */
-		.flag	= flag_array,
-		.num	= ARRAY_SIZE(flag_array),
-	},
-};
+#define pt_dump_seq_putc(m, c)		\
+({					\
+	if (m)				\
+		seq_putc(m, c);		\
+})
 
 static void dump_flag_info(struct pg_state *st, const struct flag_info
 		*flag, u64 pte, int num)
@@ -271,19 +127,19 @@
 			val = pte & flag->val;
 			if (flag->shift)
 				val = val >> flag->shift;
-			seq_printf(st->seq, "  %s:%llx", flag->set, val);
+			pt_dump_seq_printf(st->seq, "  %s:%llx", flag->set, val);
 		} else {
 			if ((pte & flag->mask) == flag->val)
 				s = flag->set;
 			else
 				s = flag->clear;
 			if (s)
-				seq_printf(st->seq, "  %s", s);
+				pt_dump_seq_printf(st->seq, "  %s", s);
 		}
 		st->current_flags &= ~flag->mask;
 	}
 	if (st->current_flags != 0)
-		seq_printf(st->seq, "  unknown flags:%llx", st->current_flags);
+		pt_dump_seq_printf(st->seq, "  unknown flags:%llx", st->current_flags);
 }
 
 static void dump_addr(struct pg_state *st, unsigned long addr)
@@ -293,23 +149,42 @@
 	unsigned long delta;
 
 #ifdef CONFIG_PPC64
-	seq_printf(st->seq, "0x%016lx-0x%016lx ", st->start_address, addr-1);
-	seq_printf(st->seq, "0x%016lx ", st->start_pa);
+#define REG		"0x%016lx"
 #else
-	seq_printf(st->seq, "0x%08lx-0x%08lx ", st->start_address, addr - 1);
-	seq_printf(st->seq, "0x%08lx ", st->start_pa);
+#define REG		"0x%08lx"
 #endif
 
-	delta = (addr - st->start_address) >> 10;
+	pt_dump_seq_printf(st->seq, REG "-" REG " ", st->start_address, addr - 1);
+	if (st->start_pa == st->last_pa && st->start_address + PAGE_SIZE != addr) {
+		pt_dump_seq_printf(st->seq, "[" REG "]", st->start_pa);
+		delta = PAGE_SIZE >> 10;
+	} else {
+		pt_dump_seq_printf(st->seq, " " REG " ", st->start_pa);
+		delta = (addr - st->start_address) >> 10;
+	}
 	/* Work out what appropriate unit to use */
 	while (!(delta & 1023) && unit[1]) {
 		delta >>= 10;
 		unit++;
 	}
-	seq_printf(st->seq, "%9lu%c", delta, *unit);
+	pt_dump_seq_printf(st->seq, "%9lu%c", delta, *unit);
 
 }
 
+static void note_prot_wx(struct pg_state *st, unsigned long addr)
+{
+	if (!IS_ENABLED(CONFIG_PPC_DEBUG_WX) || !st->check_wx)
+		return;
+
+	if (!((st->current_flags & pgprot_val(PAGE_KERNEL_X)) == pgprot_val(PAGE_KERNEL_X)))
+		return;
+
+	WARN_ONCE(1, "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;
+}
+
 static void note_page(struct pg_state *st, unsigned long addr,
 	       unsigned int level, u64 val)
 {
@@ -323,7 +198,7 @@
 		st->start_address = addr;
 		st->start_pa = pa;
 		st->last_pa = pa;
-		seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
 	/*
 	 * Dump the section of virtual memory when:
 	 *   - the PTE flags from one entry to the next differs.
@@ -334,10 +209,12 @@
 	 */
 	} else if (flag != st->current_flags || level != st->level ||
 		   addr >= st->marker[1].start_address ||
-		   pa != st->last_pa + PAGE_SIZE) {
+		   (pa != st->last_pa + PAGE_SIZE &&
+		    (pa != st->start_pa || st->start_pa != st->last_pa))) {
 
 		/* Check the PTE flags */
 		if (st->current_flags) {
+			note_prot_wx(st, addr);
 			dump_addr(st, addr);
 
 			/* Dump all the flags */
@@ -346,7 +223,7 @@
 					  st->current_flags,
 					  pg_level[st->level].num);
 
-			seq_putc(st->seq, '\n');
+			pt_dump_seq_putc(st->seq, '\n');
 		}
 
 		/*
@@ -355,7 +232,7 @@
 		 */
 		while (addr >= st->marker[1].start_address) {
 			st->marker++;
-			seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+			pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
 		}
 		st->start_address = addr;
 		st->start_pa = pa;
@@ -388,7 +265,7 @@
 
 	for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
 		addr = start + i * PMD_SIZE;
-		if (!pmd_none(*pmd) && !pmd_huge(*pmd))
+		if (!pmd_none(*pmd) && !pmd_is_leaf(*pmd))
 			/* pmd exists */
 			walk_pte(st, pmd, addr);
 		else
@@ -404,7 +281,7 @@
 
 	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
 		addr = start + i * PUD_SIZE;
-		if (!pud_none(*pud) && !pud_huge(*pud))
+		if (!pud_none(*pud) && !pud_is_leaf(*pud))
 			/* pud exists */
 			walk_pmd(st, pud, addr);
 		else
@@ -414,18 +291,16 @@
 
 static void walk_pagetables(struct pg_state *st)
 {
-	pgd_t *pgd = pgd_offset_k(0UL);
 	unsigned int i;
-	unsigned long addr;
-
-	addr = st->start_address;
+	unsigned long addr = st->start_address & PGDIR_MASK;
+	pgd_t *pgd = pgd_offset_k(addr);
 
 	/*
 	 * Traverse the linux pagetable structure and dump pages that are in
 	 * the hash pagetable.
 	 */
-	for (i = 0; i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) {
-		if (!pgd_none(*pgd) && !pgd_huge(*pgd))
+	for (i = pgd_index(addr); i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) {
+		if (!pgd_none(*pgd) && !pgd_is_leaf(*pgd))
 			/* pgd exists */
 			walk_pud(st, pgd, addr);
 		else
@@ -447,25 +322,25 @@
 	address_markers[i++].start_address = PHB_IO_END;
 	address_markers[i++].start_address = IOREMAP_BASE;
 	address_markers[i++].start_address = IOREMAP_END;
+	/* What is the ifdef about? */
 #ifdef CONFIG_PPC_BOOK3S_64
-	address_markers[i++].start_address =  H_VMEMMAP_BASE;
+	address_markers[i++].start_address =  H_VMEMMAP_START;
 #else
 	address_markers[i++].start_address =  VMEMMAP_BASE;
 #endif
 #else /* !CONFIG_PPC64 */
 	address_markers[i++].start_address = ioremap_bot;
 	address_markers[i++].start_address = IOREMAP_TOP;
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	address_markers[i++].start_address = IOREMAP_TOP;
-	address_markers[i++].start_address = IOREMAP_TOP +
-					     CONFIG_CONSISTENT_SIZE;
-#endif
 #ifdef CONFIG_HIGHMEM
 	address_markers[i++].start_address = PKMAP_BASE;
 	address_markers[i++].start_address = PKMAP_ADDR(LAST_PKMAP);
 #endif
 	address_markers[i++].start_address = FIXADDR_START;
 	address_markers[i++].start_address = FIXADDR_TOP;
+#ifdef CONFIG_KASAN
+	address_markers[i++].start_address = KASAN_SHADOW_START;
+	address_markers[i++].start_address = KASAN_SHADOW_END;
+#endif
 #endif /* CONFIG_PPC64 */
 }
 
@@ -474,12 +349,13 @@
 	struct pg_state st = {
 		.seq = m,
 		.marker = address_markers,
+		.start_address = PAGE_OFFSET,
 	};
 
-	if (radix_enabled())
-		st.start_address = PAGE_OFFSET;
-	else
+#ifdef CONFIG_PPC64
+	if (!radix_enabled())
 		st.start_address = KERN_VIRT_START;
+#endif
 
 	/* Traverse kernel page tables */
 	walk_pagetables(&st);
@@ -510,6 +386,31 @@
 				pg_level[i].mask |= pg_level[i].flag[j].mask;
 }
 
+#ifdef CONFIG_PPC_DEBUG_WX
+void ptdump_check_wx(void)
+{
+	struct pg_state st = {
+		.seq = NULL,
+		.marker = address_markers,
+		.check_wx = true,
+		.start_address = PAGE_OFFSET,
+	};
+
+#ifdef CONFIG_PPC64
+	if (!radix_enabled())
+		st.start_address = KERN_VIRT_START;
+#endif
+
+	walk_pagetables(&st);
+
+	if (st.wx_pages)
+		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n",
+			st.wx_pages);
+	else
+		pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+}
+#endif
+
 static int ptdump_init(void)
 {
 	struct dentry *debugfs_file;
diff --git a/arch/powerpc/mm/ptdump/ptdump.h b/arch/powerpc/mm/ptdump/ptdump.h
new file mode 100644
index 0000000..5d51363
--- /dev/null
+++ b/arch/powerpc/mm/ptdump/ptdump.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/types.h>
+
+struct flag_info {
+	u64		mask;
+	u64		val;
+	const char	*set;
+	const char	*clear;
+	bool		is_val;
+	int		shift;
+};
+
+struct pgtable_level {
+	const struct flag_info *flag;
+	size_t num;
+	u64 mask;
+};
+
+extern struct pgtable_level pg_level[5];
diff --git a/arch/powerpc/mm/ptdump/segment_regs.c b/arch/powerpc/mm/ptdump/segment_regs.c
new file mode 100644
index 0000000..5018436
--- /dev/null
+++ b/arch/powerpc/mm/ptdump/segment_regs.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2018, Christophe Leroy CS S.I.
+ * <christophe.leroy@c-s.fr>
+ *
+ * This dumps the content of Segment Registers
+ */
+
+#include <asm/debugfs.h>
+
+static void seg_show(struct seq_file *m, int i)
+{
+	u32 val = mfsrin(i << 28);
+
+	seq_printf(m, "0x%01x0000000-0x%01xfffffff ", i, i);
+	seq_printf(m, "Kern key %d ", (val >> 30) & 1);
+	seq_printf(m, "User key %d ", (val >> 29) & 1);
+	if (val & 0x80000000) {
+		seq_printf(m, "Device 0x%03x", (val >> 20) & 0x1ff);
+		seq_printf(m, "-0x%05x", val & 0xfffff);
+	} else {
+		if (val & 0x10000000)
+			seq_puts(m, "No Exec ");
+		seq_printf(m, "VSID 0x%06x", val & 0xffffff);
+	}
+	seq_puts(m, "\n");
+}
+
+static int sr_show(struct seq_file *m, void *v)
+{
+	int i;
+
+	seq_puts(m, "---[ User Segments ]---\n");
+	for (i = 0; i < TASK_SIZE >> 28; i++)
+		seg_show(m, i);
+
+	seq_puts(m, "\n---[ Kernel Segments ]---\n");
+	for (; i < 16; i++)
+		seg_show(m, i);
+
+	return 0;
+}
+
+static int sr_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sr_show, NULL);
+}
+
+static const struct file_operations sr_fops = {
+	.open		= sr_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init sr_init(void)
+{
+	struct dentry *debugfs_file;
+
+	debugfs_file = debugfs_create_file("segment_registers", 0400,
+					   powerpc_debugfs_root, NULL, &sr_fops);
+	return debugfs_file ? 0 : -ENOMEM;
+}
+device_initcall(sr_init);
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
new file mode 100644
index 0000000..f7ed2f1
--- /dev/null
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * From split of dump_linuxpagetables.c
+ * Copyright 2016, Rashmica Gupta, IBM Corp.
+ *
+ */
+#include <linux/kernel.h>
+#include <asm/pgtable.h>
+
+#include "ptdump.h"
+
+static const struct flag_info flag_array[] = {
+	{
+		.mask	= _PAGE_USER,
+		.val	= _PAGE_USER,
+		.set	= "user",
+		.clear	= "    ",
+	}, {
+		.mask	= _PAGE_RW,
+		.val	= _PAGE_RW,
+		.set	= "rw",
+		.clear	= "r ",
+	}, {
+		.mask	= _PAGE_EXEC,
+		.val	= _PAGE_EXEC,
+		.set	= " X ",
+		.clear	= "   ",
+	}, {
+		.mask	= _PAGE_PRESENT,
+		.val	= _PAGE_PRESENT,
+		.set	= "present",
+		.clear	= "       ",
+	}, {
+		.mask	= _PAGE_GUARDED,
+		.val	= _PAGE_GUARDED,
+		.set	= "guarded",
+		.clear	= "       ",
+	}, {
+		.mask	= _PAGE_DIRTY,
+		.val	= _PAGE_DIRTY,
+		.set	= "dirty",
+		.clear	= "     ",
+	}, {
+		.mask	= _PAGE_ACCESSED,
+		.val	= _PAGE_ACCESSED,
+		.set	= "accessed",
+		.clear	= "        ",
+	}, {
+		.mask	= _PAGE_WRITETHRU,
+		.val	= _PAGE_WRITETHRU,
+		.set	= "write through",
+		.clear	= "             ",
+	}, {
+		.mask	= _PAGE_NO_CACHE,
+		.val	= _PAGE_NO_CACHE,
+		.set	= "no cache",
+		.clear	= "        ",
+	}, {
+		.mask	= _PAGE_SPECIAL,
+		.val	= _PAGE_SPECIAL,
+		.set	= "special",
+	}
+};
+
+struct pgtable_level pg_level[5] = {
+	{
+	}, { /* pgd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* pud */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* pmd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* pte */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	},
+};
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
deleted file mode 100644
index 9f574e5..0000000
--- a/arch/powerpc/mm/slb.c
+++ /dev/null
@@ -1,502 +0,0 @@
-/*
- * PowerPC64 SLB support.
- *
- * Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM
- * Based on earlier code written by:
- * Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
- *    Copyright (c) 2001 Dave Engebretsen
- * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- */
-
-#include <asm/pgtable.h>
-#include <asm/mmu.h>
-#include <asm/mmu_context.h>
-#include <asm/paca.h>
-#include <asm/cputable.h>
-#include <asm/cacheflush.h>
-#include <asm/smp.h>
-#include <linux/compiler.h>
-#include <linux/context_tracking.h>
-#include <linux/mm_types.h>
-
-#include <asm/udbg.h>
-#include <asm/code-patching.h>
-
-enum slb_index {
-	LINEAR_INDEX	= 0, /* Kernel linear map  (0xc000000000000000) */
-	VMALLOC_INDEX	= 1, /* Kernel virtual map (0xd000000000000000) */
-	KSTACK_INDEX	= 2, /* Kernel stack map */
-};
-
-extern void slb_allocate(unsigned long ea);
-
-#define slb_esid_mask(ssize)	\
-	(((ssize) == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T)
-
-static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
-					 enum slb_index index)
-{
-	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | index;
-}
-
-static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
-					 unsigned long flags)
-{
-	return (get_kernel_vsid(ea, ssize) << slb_vsid_shift(ssize)) | flags |
-		((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
-}
-
-static inline void slb_shadow_update(unsigned long ea, int ssize,
-				     unsigned long flags,
-				     enum slb_index index)
-{
-	struct slb_shadow *p = get_slb_shadow();
-
-	/*
-	 * Clear the ESID first so the entry is not valid while we are
-	 * updating it.  No write barriers are needed here, provided
-	 * we only update the current CPU's SLB shadow buffer.
-	 */
-	WRITE_ONCE(p->save_area[index].esid, 0);
-	WRITE_ONCE(p->save_area[index].vsid, cpu_to_be64(mk_vsid_data(ea, ssize, flags)));
-	WRITE_ONCE(p->save_area[index].esid, cpu_to_be64(mk_esid_data(ea, ssize, index)));
-}
-
-static inline void slb_shadow_clear(enum slb_index index)
-{
-	WRITE_ONCE(get_slb_shadow()->save_area[index].esid, cpu_to_be64(index));
-}
-
-static inline void create_shadowed_slbe(unsigned long ea, int ssize,
-					unsigned long flags,
-					enum slb_index index)
-{
-	/*
-	 * Updating the shadow buffer before writing the SLB ensures
-	 * we don't get a stale entry here if we get preempted by PHYP
-	 * between these two statements.
-	 */
-	slb_shadow_update(ea, ssize, flags, index);
-
-	asm volatile("slbmte  %0,%1" :
-		     : "r" (mk_vsid_data(ea, ssize, flags)),
-		       "r" (mk_esid_data(ea, ssize, index))
-		     : "memory" );
-}
-
-/*
- * Insert bolted entries into SLB (which may not be empty, so don't clear
- * slb_cache_ptr).
- */
-void __slb_restore_bolted_realmode(void)
-{
-	struct slb_shadow *p = get_slb_shadow();
-	enum slb_index index;
-
-	 /* No isync needed because realmode. */
-	for (index = 0; index < SLB_NUM_BOLTED; index++) {
-		asm volatile("slbmte  %0,%1" :
-		     : "r" (be64_to_cpu(p->save_area[index].vsid)),
-		       "r" (be64_to_cpu(p->save_area[index].esid)));
-	}
-}
-
-/*
- * Insert the bolted entries into an empty SLB.
- * This is not the same as rebolt because the bolted segments are not
- * changed, just loaded from the shadow area.
- */
-void slb_restore_bolted_realmode(void)
-{
-	__slb_restore_bolted_realmode();
-	get_paca()->slb_cache_ptr = 0;
-}
-
-/*
- * This flushes all SLB entries including 0, so it must be realmode.
- */
-void slb_flush_all_realmode(void)
-{
-	/*
-	 * This flushes all SLB entries including 0, so it must be realmode.
-	 */
-	asm volatile("slbmte %0,%0; slbia" : : "r" (0));
-}
-
-static void __slb_flush_and_rebolt(void)
-{
-	/* If you change this make sure you change SLB_NUM_BOLTED
-	 * and PR KVM appropriately too. */
-	unsigned long linear_llp, vmalloc_llp, lflags, vflags;
-	unsigned long ksp_esid_data, ksp_vsid_data;
-
-	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
-	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
-	lflags = SLB_VSID_KERNEL | linear_llp;
-	vflags = SLB_VSID_KERNEL | vmalloc_llp;
-
-	ksp_esid_data = mk_esid_data(get_paca()->kstack, mmu_kernel_ssize, KSTACK_INDEX);
-	if ((ksp_esid_data & ~0xfffffffUL) <= PAGE_OFFSET) {
-		ksp_esid_data &= ~SLB_ESID_V;
-		ksp_vsid_data = 0;
-		slb_shadow_clear(KSTACK_INDEX);
-	} else {
-		/* Update stack entry; others don't change */
-		slb_shadow_update(get_paca()->kstack, mmu_kernel_ssize, lflags, KSTACK_INDEX);
-		ksp_vsid_data =
-			be64_to_cpu(get_slb_shadow()->save_area[KSTACK_INDEX].vsid);
-	}
-
-	/* We need to do this all in asm, so we're sure we don't touch
-	 * the stack between the slbia and rebolting it. */
-	asm volatile("isync\n"
-		     "slbia\n"
-		     /* Slot 1 - first VMALLOC segment */
-		     "slbmte	%0,%1\n"
-		     /* Slot 2 - kernel stack */
-		     "slbmte	%2,%3\n"
-		     "isync"
-		     :: "r"(mk_vsid_data(VMALLOC_START, mmu_kernel_ssize, vflags)),
-		        "r"(mk_esid_data(VMALLOC_START, mmu_kernel_ssize, VMALLOC_INDEX)),
-		        "r"(ksp_vsid_data),
-		        "r"(ksp_esid_data)
-		     : "memory");
-}
-
-void slb_flush_and_rebolt(void)
-{
-
-	WARN_ON(!irqs_disabled());
-
-	/*
-	 * We can't take a PMU exception in the following code, so hard
-	 * disable interrupts.
-	 */
-	hard_irq_disable();
-
-	__slb_flush_and_rebolt();
-	get_paca()->slb_cache_ptr = 0;
-}
-
-void slb_vmalloc_update(void)
-{
-	unsigned long vflags;
-
-	vflags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmalloc_psize].sllp;
-	slb_shadow_update(VMALLOC_START, mmu_kernel_ssize, vflags, VMALLOC_INDEX);
-	slb_flush_and_rebolt();
-}
-
-/* Helper function to compare esids.  There are four cases to handle.
- * 1. The system is not 1T segment size capable.  Use the GET_ESID compare.
- * 2. The system is 1T capable, both addresses are < 1T, use the GET_ESID compare.
- * 3. The system is 1T capable, only one of the two addresses is > 1T.  This is not a match.
- * 4. The system is 1T capable, both addresses are > 1T, use the GET_ESID_1T macro to compare.
- */
-static inline int esids_match(unsigned long addr1, unsigned long addr2)
-{
-	int esid_1t_count;
-
-	/* System is not 1T segment size capable. */
-	if (!mmu_has_feature(MMU_FTR_1T_SEGMENT))
-		return (GET_ESID(addr1) == GET_ESID(addr2));
-
-	esid_1t_count = (((addr1 >> SID_SHIFT_1T) != 0) +
-				((addr2 >> SID_SHIFT_1T) != 0));
-
-	/* both addresses are < 1T */
-	if (esid_1t_count == 0)
-		return (GET_ESID(addr1) == GET_ESID(addr2));
-
-	/* One address < 1T, the other > 1T.  Not a match */
-	if (esid_1t_count == 1)
-		return 0;
-
-	/* Both addresses are > 1T. */
-	return (GET_ESID_1T(addr1) == GET_ESID_1T(addr2));
-}
-
-/* Flush all user entries from the segment table of the current processor. */
-void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
-{
-	unsigned long offset;
-	unsigned long slbie_data = 0;
-	unsigned long pc = KSTK_EIP(tsk);
-	unsigned long stack = KSTK_ESP(tsk);
-	unsigned long exec_base;
-
-	/*
-	 * We need interrupts hard-disabled here, not just soft-disabled,
-	 * so that a PMU interrupt can't occur, which might try to access
-	 * user memory (to get a stack trace) and possible cause an SLB miss
-	 * which would update the slb_cache/slb_cache_ptr fields in the PACA.
-	 */
-	hard_irq_disable();
-	offset = get_paca()->slb_cache_ptr;
-	if (!mmu_has_feature(MMU_FTR_NO_SLBIE_B) &&
-	    offset <= SLB_CACHE_ENTRIES) {
-		int i;
-		asm volatile("isync" : : : "memory");
-		for (i = 0; i < offset; i++) {
-			slbie_data = (unsigned long)get_paca()->slb_cache[i]
-				<< SID_SHIFT; /* EA */
-			slbie_data |= user_segment_size(slbie_data)
-				<< SLBIE_SSIZE_SHIFT;
-			slbie_data |= SLBIE_C; /* C set for user addresses */
-			asm volatile("slbie %0" : : "r" (slbie_data));
-		}
-		asm volatile("isync" : : : "memory");
-	} else {
-		__slb_flush_and_rebolt();
-	}
-
-	/* Workaround POWER5 < DD2.1 issue */
-	if (offset == 1 || offset > SLB_CACHE_ENTRIES)
-		asm volatile("slbie %0" : : "r" (slbie_data));
-
-	get_paca()->slb_cache_ptr = 0;
-	copy_mm_to_paca(mm);
-
-	/*
-	 * 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.
-	 */
-	exec_base = 0x10000000;
-
-	if (is_kernel_addr(pc) || is_kernel_addr(stack) ||
-	    is_kernel_addr(exec_base))
-		return;
-
-	slb_allocate(pc);
-
-	if (!esids_match(pc, stack))
-		slb_allocate(stack);
-
-	if (!esids_match(pc, exec_base) &&
-	    !esids_match(stack, exec_base))
-		slb_allocate(exec_base);
-}
-
-static inline void patch_slb_encoding(unsigned int *insn_addr,
-				      unsigned int immed)
-{
-
-	/*
-	 * This function patches either an li or a cmpldi instruction with
-	 * a new immediate value. This relies on the fact that both li
-	 * (which is actually addi) and cmpldi both take a 16-bit immediate
-	 * value, and it is situated in the same location in the instruction,
-	 * ie. bits 16-31 (Big endian bit order) or the lower 16 bits.
-	 * The signedness of the immediate operand differs between the two
-	 * instructions however this code is only ever patching a small value,
-	 * much less than 1 << 15, so we can get away with it.
-	 * To patch the value we read the existing instruction, clear the
-	 * immediate value, and or in our new value, then write the instruction
-	 * back.
-	 */
-	unsigned int insn = (*insn_addr & 0xffff0000) | immed;
-	patch_instruction(insn_addr, insn);
-}
-
-extern u32 slb_miss_kernel_load_linear[];
-extern u32 slb_miss_kernel_load_io[];
-extern u32 slb_compare_rr_to_size[];
-extern u32 slb_miss_kernel_load_vmemmap[];
-
-void slb_set_size(u16 size)
-{
-	if (mmu_slb_size == size)
-		return;
-
-	mmu_slb_size = size;
-	patch_slb_encoding(slb_compare_rr_to_size, mmu_slb_size);
-}
-
-void slb_initialize(void)
-{
-	unsigned long linear_llp, vmalloc_llp, io_llp;
-	unsigned long lflags, vflags;
-	static int slb_encoding_inited;
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-	unsigned long vmemmap_llp;
-#endif
-
-	/* Prepare our SLB miss handler based on our page size */
-	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
-	io_llp = mmu_psize_defs[mmu_io_psize].sllp;
-	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
-	get_paca()->vmalloc_sllp = SLB_VSID_KERNEL | vmalloc_llp;
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-	vmemmap_llp = mmu_psize_defs[mmu_vmemmap_psize].sllp;
-#endif
-	if (!slb_encoding_inited) {
-		slb_encoding_inited = 1;
-		patch_slb_encoding(slb_miss_kernel_load_linear,
-				   SLB_VSID_KERNEL | linear_llp);
-		patch_slb_encoding(slb_miss_kernel_load_io,
-				   SLB_VSID_KERNEL | io_llp);
-		patch_slb_encoding(slb_compare_rr_to_size,
-				   mmu_slb_size);
-
-		pr_devel("SLB: linear  LLP = %04lx\n", linear_llp);
-		pr_devel("SLB: io      LLP = %04lx\n", io_llp);
-
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-		patch_slb_encoding(slb_miss_kernel_load_vmemmap,
-				   SLB_VSID_KERNEL | vmemmap_llp);
-		pr_devel("SLB: vmemmap LLP = %04lx\n", vmemmap_llp);
-#endif
-	}
-
-	get_paca()->stab_rr = SLB_NUM_BOLTED;
-
-	lflags = SLB_VSID_KERNEL | linear_llp;
-	vflags = SLB_VSID_KERNEL | vmalloc_llp;
-
-	/* Invalidate the entire SLB (even entry 0) & all the ERATS */
-	asm volatile("isync":::"memory");
-	asm volatile("slbmte  %0,%0"::"r" (0) : "memory");
-	asm volatile("isync; slbia; isync":::"memory");
-	create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, LINEAR_INDEX);
-	create_shadowed_slbe(VMALLOC_START, mmu_kernel_ssize, vflags, VMALLOC_INDEX);
-
-	/* For the boot cpu, we're running on the stack in init_thread_union,
-	 * which is in the first segment of the linear mapping, and also
-	 * get_paca()->kstack hasn't been initialized yet.
-	 * For secondary cpus, we need to bolt the kernel stack entry now.
-	 */
-	slb_shadow_clear(KSTACK_INDEX);
-	if (raw_smp_processor_id() != boot_cpuid &&
-	    (get_paca()->kstack & slb_esid_mask(mmu_kernel_ssize)) > PAGE_OFFSET)
-		create_shadowed_slbe(get_paca()->kstack,
-				     mmu_kernel_ssize, lflags, KSTACK_INDEX);
-
-	asm volatile("isync":::"memory");
-}
-
-static void insert_slb_entry(unsigned long vsid, unsigned long ea,
-			     int bpsize, int ssize)
-{
-	unsigned long flags, vsid_data, esid_data;
-	enum slb_index index;
-	int slb_cache_index;
-
-	/*
-	 * We are irq disabled, hence should be safe to access PACA.
-	 */
-	VM_WARN_ON(!irqs_disabled());
-
-	/*
-	 * We can't take a PMU exception in the following code, so hard
-	 * disable interrupts.
-	 */
-	hard_irq_disable();
-
-	index = get_paca()->stab_rr;
-
-	/*
-	 * simple round-robin replacement of slb starting at SLB_NUM_BOLTED.
-	 */
-	if (index < (mmu_slb_size - 1))
-		index++;
-	else
-		index = SLB_NUM_BOLTED;
-
-	get_paca()->stab_rr = index;
-
-	flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp;
-	vsid_data = (vsid << slb_vsid_shift(ssize)) | flags |
-		    ((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
-	esid_data = mk_esid_data(ea, ssize, index);
-
-	/*
-	 * No need for an isync before or after this slbmte. The exception
-	 * we enter with and the rfid we exit with are context synchronizing.
-	 * Also we only handle user segments here.
-	 */
-	asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data)
-		     : "memory");
-
-	/*
-	 * Now update slb cache entries
-	 */
-	slb_cache_index = get_paca()->slb_cache_ptr;
-	if (slb_cache_index < SLB_CACHE_ENTRIES) {
-		/*
-		 * We have space in slb cache for optimized switch_slb().
-		 * Top 36 bits from esid_data as per ISA
-		 */
-		get_paca()->slb_cache[slb_cache_index++] = esid_data >> 28;
-		get_paca()->slb_cache_ptr++;
-	} else {
-		/*
-		 * Our cache is full and the current cache content strictly
-		 * doesn't indicate the active SLB conents. Bump the ptr
-		 * so that switch_slb() will ignore the cache.
-		 */
-		get_paca()->slb_cache_ptr = SLB_CACHE_ENTRIES + 1;
-	}
-}
-
-static void handle_multi_context_slb_miss(int context_id, unsigned long ea)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long vsid;
-	int bpsize;
-
-	/*
-	 * We are always above 1TB, hence use high user segment size.
-	 */
-	vsid = get_vsid(context_id, ea, mmu_highuser_ssize);
-	bpsize = get_slice_psize(mm, ea);
-	insert_slb_entry(vsid, ea, bpsize, mmu_highuser_ssize);
-}
-
-void slb_miss_large_addr(struct pt_regs *regs)
-{
-	enum ctx_state prev_state = exception_enter();
-	unsigned long ea = regs->dar;
-	int context;
-
-	if (REGION_ID(ea) != USER_REGION_ID)
-		goto slb_bad_addr;
-
-	/*
-	 * Are we beyound what the page table layout supports ?
-	 */
-	if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
-		goto slb_bad_addr;
-
-	/* Lower address should have been handled by asm code */
-	if (ea < (1UL << MAX_EA_BITS_PER_CONTEXT))
-		goto slb_bad_addr;
-
-	/*
-	 * consider this as bad access if we take a SLB miss
-	 * on an address above addr limit.
-	 */
-	if (ea >= current->mm->context.slb_addr_limit)
-		goto slb_bad_addr;
-
-	context = get_ea_context(&current->mm->context, ea);
-	if (!context)
-		goto slb_bad_addr;
-
-	handle_multi_context_slb_miss(context, ea);
-	exception_exit(prev_state);
-	return;
-
-slb_bad_addr:
-	if (user_mode(regs))
-		_exception(SIGSEGV, regs, SEGV_BNDERR, ea);
-	else
-		bad_page_fault(regs, ea, SIGSEGV);
-	exception_exit(prev_state);
-}
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
deleted file mode 100644
index 4ac5057..0000000
--- a/arch/powerpc/mm/slb_low.S
+++ /dev/null
@@ -1,335 +0,0 @@
-/*
- * Low-level SLB routines
- *
- * Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM
- *
- * Based on earlier C version:
- * Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
- *    Copyright (c) 2001 Dave Engebretsen
- * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-
-#include <asm/processor.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/cputable.h>
-#include <asm/page.h>
-#include <asm/mmu.h>
-#include <asm/pgtable.h>
-#include <asm/firmware.h>
-#include <asm/feature-fixups.h>
-
-/*
- * This macro generates asm code to compute the VSID scramble
- * function.  Used in slb_allocate() and do_stab_bolted.  The function
- * computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS
- *
- *	rt = register containing the proto-VSID and into which the
- *		VSID will be stored
- *	rx = scratch register (clobbered)
- *	rf = flags
- *
- *	- rt and rx must be different registers
- *	- The answer will end up in the low VSID_BITS bits of rt.  The higher
- *	  bits may contain other garbage, so you may need to mask the
- *	  result.
- */
-#define ASM_VSID_SCRAMBLE(rt, rx, rf, size)				\
-	lis	rx,VSID_MULTIPLIER_##size@h;				\
-	ori	rx,rx,VSID_MULTIPLIER_##size@l;				\
-	mulld	rt,rt,rx;		/* rt = rt * MULTIPLIER */	\
-/*									\
- * powermac get slb fault before feature fixup, so make 65 bit part     \
- * the default part of feature fixup					\
- */									\
-BEGIN_MMU_FTR_SECTION							\
-	srdi	rx,rt,VSID_BITS_65_##size;				\
-	clrldi	rt,rt,(64-VSID_BITS_65_##size);				\
-	add	rt,rt,rx;						\
-	addi	rx,rt,1;						\
-	srdi	rx,rx,VSID_BITS_65_##size;				\
-	add	rt,rt,rx;						\
-	rldimi	rf,rt,SLB_VSID_SHIFT_##size,(64 - (SLB_VSID_SHIFT_##size + VSID_BITS_65_##size)); \
-MMU_FTR_SECTION_ELSE							\
-	srdi	rx,rt,VSID_BITS_##size;					\
-	clrldi	rt,rt,(64-VSID_BITS_##size);				\
-	add	rt,rt,rx;		/* add high and low bits */	\
-	addi	rx,rt,1;						\
-	srdi	rx,rx,VSID_BITS_##size;	/* extract 2^VSID_BITS bit */	\
-	add	rt,rt,rx;						\
-	rldimi	rf,rt,SLB_VSID_SHIFT_##size,(64 - (SLB_VSID_SHIFT_##size + VSID_BITS_##size)); \
-ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_68_BIT_VA)
-
-
-/* void slb_allocate(unsigned long ea);
- *
- * Create an SLB entry for the given EA (user or kernel).
- * 	r3 = faulting address, r13 = PACA
- *	r9, r10, r11 are clobbered by this function
- *	r3 is preserved.
- * No other registers are examined or changed.
- */
-_GLOBAL(slb_allocate)
-	/*
-	 * Check if the address falls within the range of the first context, or
-	 * if we may need to handle multi context. For the first context we
-	 * allocate the slb entry via the fast path below. For large address we
-	 * branch out to C-code and see if additional contexts have been
-	 * allocated.
-	 * The test here is:
-	 *   (ea & ~REGION_MASK) >= (1ull << MAX_EA_BITS_PER_CONTEXT)
-	 */
-	rldicr. r9,r3,4,(63 - MAX_EA_BITS_PER_CONTEXT - 4)
-	bne-	8f
-
-	srdi	r9,r3,60		/* get region */
-	srdi	r10,r3,SID_SHIFT	/* get esid */
-	cmpldi	cr7,r9,0xc		/* cmp PAGE_OFFSET for later use */
-
-	/* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */
-	blt	cr7,0f			/* user or kernel? */
-
-	/* Check if hitting the linear mapping or some other kernel space
-	*/
-	bne	cr7,1f
-
-	/* Linear mapping encoding bits, the "li" instruction below will
-	 * be patched by the kernel at boot
-	 */
-.globl slb_miss_kernel_load_linear
-slb_miss_kernel_load_linear:
-	li	r11,0
-	/*
-	 * context = (ea >> 60) - (0xc - 1)
-	 * r9 = region id.
-	 */
-	subi	r9,r9,KERNEL_REGION_CONTEXT_OFFSET
-
-BEGIN_FTR_SECTION
-	b	.Lslb_finish_load
-END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
-	b	.Lslb_finish_load_1T
-
-1:
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-	cmpldi	cr0,r9,0xf
-	bne	1f
-/* Check virtual memmap region. To be patched at kernel boot */
-.globl slb_miss_kernel_load_vmemmap
-slb_miss_kernel_load_vmemmap:
-	li	r11,0
-	b	6f
-1:
-#endif /* CONFIG_SPARSEMEM_VMEMMAP */
-
-	/*
-	 * r10 contains the ESID, which is the original faulting EA shifted
-	 * right by 28 bits. We need to compare that with (H_VMALLOC_END >> 28)
-	 * which is 0xd00038000. That can't be used as an immediate, even if we
-	 * ignored the 0xd, so we have to load it into a register, and we only
-	 * have one register free. So we must load all of (H_VMALLOC_END >> 28)
-	 * into a register and compare ESID against that.
-	 */
-	lis	r11,(H_VMALLOC_END >> 32)@h	// r11 = 0xffffffffd0000000
-	ori	r11,r11,(H_VMALLOC_END >> 32)@l	// r11 = 0xffffffffd0003800
-	// Rotate left 4, then mask with 0xffffffff0
-	rldic	r11,r11,4,28			// r11 = 0xd00038000
-	cmpld	r10,r11				// if r10 >= r11
-	bge	5f				//   goto io_mapping
-
-	/*
-	 * vmalloc mapping gets the encoding from the PACA as the mapping
-	 * can be demoted from 64K -> 4K dynamically on some machines.
-	 */
-	lhz	r11,PACAVMALLOCSLLP(r13)
-	b	6f
-5:
-	/* IO mapping */
-.globl slb_miss_kernel_load_io
-slb_miss_kernel_load_io:
-	li	r11,0
-6:
-	/*
-	 * context = (ea >> 60) - (0xc - 1)
-	 * r9 = region id.
-	 */
-	subi	r9,r9,KERNEL_REGION_CONTEXT_OFFSET
-
-BEGIN_FTR_SECTION
-	b	.Lslb_finish_load
-END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
-	b	.Lslb_finish_load_1T
-
-0:	/*
-	 * For userspace addresses, make sure this is region 0.
-	 */
-	cmpdi	r9, 0
-	bne-	8f
-        /*
-         * user space make sure we are within the allowed limit
-	 */
-	ld	r11,PACA_SLB_ADDR_LIMIT(r13)
-	cmpld	r3,r11
-	bge-	8f
-
-	/* when using slices, we extract the psize off the slice bitmaps
-	 * and then we need to get the sllp encoding off the mmu_psize_defs
-	 * array.
-	 *
-	 * XXX This is a bit inefficient especially for the normal case,
-	 * so we should try to implement a fast path for the standard page
-	 * size using the old sllp value so we avoid the array. We cannot
-	 * really do dynamic patching unfortunately as processes might flip
-	 * between 4k and 64k standard page size
-	 */
-#ifdef CONFIG_PPC_MM_SLICES
-	/* r10 have esid */
-	cmpldi	r10,16
-	/* below SLICE_LOW_TOP */
-	blt	5f
-	/*
-	 * Handle hpsizes,
-	 * r9 is get_paca()->context.high_slices_psize[index], r11 is mask_index
-	 */
-	srdi    r11,r10,(SLICE_HIGH_SHIFT - SLICE_LOW_SHIFT + 1) /* index */
-	addi	r9,r11,PACAHIGHSLICEPSIZE
-	lbzx	r9,r13,r9		/* r9 is hpsizes[r11] */
-	/* r11 = (r10 >> (SLICE_HIGH_SHIFT - SLICE_LOW_SHIFT)) & 0x1 */
-	rldicl	r11,r10,(64 - (SLICE_HIGH_SHIFT - SLICE_LOW_SHIFT)),63
-	b	6f
-
-5:
-	/*
-	 * Handle lpsizes
-	 * r9 is get_paca()->context.low_slices_psize[index], r11 is mask_index
-	 */
-	srdi    r11,r10,1 /* index */
-	addi	r9,r11,PACALOWSLICESPSIZE
-	lbzx	r9,r13,r9		/* r9 is lpsizes[r11] */
-	rldicl	r11,r10,0,63		/* r11 = r10 & 0x1 */
-6:
-	sldi	r11,r11,2  /* index * 4 */
-	/* Extract the psize and multiply to get an array offset */
-	srd	r9,r9,r11
-	andi.	r9,r9,0xf
-	mulli	r9,r9,MMUPSIZEDEFSIZE
-
-	/* Now get to the array and obtain the sllp
-	 */
-	ld	r11,PACATOC(r13)
-	ld	r11,mmu_psize_defs@got(r11)
-	add	r11,r11,r9
-	ld	r11,MMUPSIZESLLP(r11)
-	ori	r11,r11,SLB_VSID_USER
-#else
-	/* paca context sllp already contains the SLB_VSID_USER bits */
-	lhz	r11,PACACONTEXTSLLP(r13)
-#endif /* CONFIG_PPC_MM_SLICES */
-
-	ld	r9,PACACONTEXTID(r13)
-BEGIN_FTR_SECTION
-	cmpldi	r10,0x1000
-	bge	.Lslb_finish_load_1T
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
-	b	.Lslb_finish_load
-
-8:	/* invalid EA - return an error indication */
-	crset	4*cr0+eq		/* indicate failure */
-	blr
-
-/*
- * Finish loading of an SLB entry and return
- *
- * r3 = EA, r9 = context, r10 = ESID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET
- */
-.Lslb_finish_load:
-	rldimi  r10,r9,ESID_BITS,0
-	ASM_VSID_SCRAMBLE(r10,r9,r11,256M)
-	/* r3 = EA, r11 = VSID data */
-	/*
-	 * Find a slot, round robin. Previously we tried to find a
-	 * free slot first but that took too long. Unfortunately we
- 	 * dont have any LRU information to help us choose a slot.
- 	 */
-
-	mr	r9,r3
-
-	/* slb_finish_load_1T continues here. r9=EA with non-ESID bits clear */
-7:	ld	r10,PACASTABRR(r13)
-	addi	r10,r10,1
-	/* This gets soft patched on boot. */
-.globl slb_compare_rr_to_size
-slb_compare_rr_to_size:
-	cmpldi	r10,0
-
-	blt+	4f
-	li	r10,SLB_NUM_BOLTED
-
-4:
-	std	r10,PACASTABRR(r13)
-
-3:
-	rldimi	r9,r10,0,36		/* r9  = EA[0:35] | entry */
-	oris	r10,r9,SLB_ESID_V@h	/* r10 = r9 | SLB_ESID_V */
-
-	/* r9 = ESID data, r11 = VSID data */
-
-	/*
-	 * No need for an isync before or after this slbmte. The exception
-	 * we enter with and the rfid we exit with are context synchronizing.
-	 */
-	slbmte	r11,r10
-
-	/* we're done for kernel addresses */
-	crclr	4*cr0+eq		/* set result to "success" */
-	bgelr	cr7
-
-	/* Update the slb cache */
-	lhz	r9,PACASLBCACHEPTR(r13)	/* offset = paca->slb_cache_ptr */
-	cmpldi	r9,SLB_CACHE_ENTRIES
-	bge	1f
-
-	/* still room in the slb cache */
-	sldi	r11,r9,2		/* r11 = offset * sizeof(u32) */
-	srdi    r10,r10,28		/* get the 36 bits of the ESID */
-	add	r11,r11,r13		/* r11 = (u32 *)paca + offset */
-	stw	r10,PACASLBCACHE(r11)	/* paca->slb_cache[offset] = esid */
-	addi	r9,r9,1			/* offset++ */
-	b	2f
-1:					/* offset >= SLB_CACHE_ENTRIES */
-	li	r9,SLB_CACHE_ENTRIES+1
-2:
-	sth	r9,PACASLBCACHEPTR(r13)	/* paca->slb_cache_ptr = offset */
-	crclr	4*cr0+eq		/* set result to "success" */
-	blr
-
-/*
- * Finish loading of a 1T SLB entry (for the kernel linear mapping) and return.
- *
- * r3 = EA, r9 = context, r10 = ESID(256MB), r11 = flags, clobbers r9
- */
-.Lslb_finish_load_1T:
-	srdi	r10,r10,(SID_SHIFT_1T - SID_SHIFT)	/* get 1T ESID */
-	rldimi  r10,r9,ESID_BITS_1T,0
-	ASM_VSID_SCRAMBLE(r10,r9,r11,1T)
-
-	li	r10,MMU_SEGSIZE_1T
-	rldimi	r11,r10,SLB_VSID_SSIZE_SHIFT,0	/* insert segment size */
-
-	/* r3 = EA, r11 = VSID data */
-	clrrdi	r9,r3,SID_SHIFT_1T	/* clear out non-ESID bits */
-	b	7b
-
-
-_ASM_NOKPROBE_SYMBOL(slb_allocate)
-_ASM_NOKPROBE_SYMBOL(slb_miss_kernel_load_linear)
-_ASM_NOKPROBE_SYMBOL(slb_miss_kernel_load_io)
-_ASM_NOKPROBE_SYMBOL(slb_compare_rr_to_size)
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-_ASM_NOKPROBE_SYMBOL(slb_miss_kernel_load_vmemmap)
-#endif
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 4f213ba..42bbcd4 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * address space "slices" (meta-segments) support
  *
@@ -6,20 +7,6 @@
  * Based on hugetlb implementation
  *
  * Copyright (C) 2003 David Gibson, IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #undef DEBUG
@@ -31,6 +18,8 @@
 #include <linux/spinlock.h>
 #include <linux/export.h>
 #include <linux/hugetlb.h>
+#include <linux/sched/mm.h>
+#include <linux/security.h>
 #include <asm/mman.h>
 #include <asm/mmu.h>
 #include <asm/copro.h>
@@ -99,7 +88,7 @@
 {
 	struct vm_area_struct *vma;
 
-	if ((mm->context.slb_addr_limit - len) < addr)
+	if ((mm_ctx_slb_addr_limit(&mm->context) - len) < addr)
 		return 0;
 	vma = find_vma(mm, addr);
 	return (!vma || (addr + len) <= vm_start_gap(vma));
@@ -116,13 +105,11 @@
 	unsigned long start = slice << SLICE_HIGH_SHIFT;
 	unsigned long end = start + (1ul << SLICE_HIGH_SHIFT);
 
-#ifdef CONFIG_PPC64
 	/* Hack, so that each addresses is controlled by exactly one
 	 * of the high or low area bitmaps, the first high area starts
 	 * at 4GB, not 0 */
 	if (start == 0)
-		start = SLICE_LOW_TOP;
-#endif
+		start = (unsigned long)SLICE_LOW_TOP;
 
 	return !slice_area_is_free(mm, start, end - start);
 }
@@ -148,40 +135,6 @@
 			__set_bit(i, ret->high_slices);
 }
 
-#ifdef CONFIG_PPC_BOOK3S_64
-static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
-{
-#ifdef CONFIG_PPC_64K_PAGES
-	if (psize == MMU_PAGE_64K)
-		return &mm->context.mask_64k;
-#endif
-	if (psize == MMU_PAGE_4K)
-		return &mm->context.mask_4k;
-#ifdef CONFIG_HUGETLB_PAGE
-	if (psize == MMU_PAGE_16M)
-		return &mm->context.mask_16m;
-	if (psize == MMU_PAGE_16G)
-		return &mm->context.mask_16g;
-#endif
-	BUG();
-}
-#elif defined(CONFIG_PPC_8xx)
-static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
-{
-	if (psize == mmu_virtual_psize)
-		return &mm->context.mask_base_psize;
-#ifdef CONFIG_HUGETLB_PAGE
-	if (psize == MMU_PAGE_512K)
-		return &mm->context.mask_512k;
-	if (psize == MMU_PAGE_8M)
-		return &mm->context.mask_8m;
-#endif
-	BUG();
-}
-#else
-#error "Must define the slice masks for page sizes supported by the platform"
-#endif
-
 static bool slice_check_range_fits(struct mm_struct *mm,
 			   const struct slice_mask *available,
 			   unsigned long start, unsigned long len)
@@ -226,7 +179,7 @@
 	copy_mm_to_paca(current->active_mm);
 
 	local_irq_save(flags);
-	slb_flush_and_rebolt();
+	slb_flush_and_restore_bolted();
 	local_irq_restore(flags);
 #endif
 }
@@ -244,14 +197,14 @@
 	slice_dbg("slice_convert(mm=%p, psize=%d)\n", mm, psize);
 	slice_print_mask(" mask", mask);
 
-	psize_mask = slice_mask_for_size(mm, psize);
+	psize_mask = slice_mask_for_size(&mm->context, psize);
 
 	/* We need to use a spinlock here to protect against
 	 * concurrent 64k -> 4k demotion ...
 	 */
 	spin_lock_irqsave(&slice_convert_lock, flags);
 
-	lpsizes = mm->context.low_slices_psize;
+	lpsizes = mm_ctx_low_slices(&mm->context);
 	for (i = 0; i < SLICE_NUM_LOW; i++) {
 		if (!(mask->low_slices & (1u << i)))
 			continue;
@@ -261,7 +214,7 @@
 
 		/* Update the slice_mask */
 		old_psize = (lpsizes[index] >> (mask_index * 4)) & 0xf;
-		old_mask = slice_mask_for_size(mm, old_psize);
+		old_mask = slice_mask_for_size(&mm->context, old_psize);
 		old_mask->low_slices &= ~(1u << i);
 		psize_mask->low_slices |= 1u << i;
 
@@ -270,8 +223,8 @@
 				(((unsigned long)psize) << (mask_index * 4));
 	}
 
-	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit); i++) {
+	hpsizes = mm_ctx_high_slices(&mm->context);
+	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm_ctx_slb_addr_limit(&mm->context)); i++) {
 		if (!test_bit(i, mask->high_slices))
 			continue;
 
@@ -280,7 +233,7 @@
 
 		/* Update the slice_mask */
 		old_psize = (hpsizes[index] >> (mask_index * 4)) & 0xf;
-		old_mask = slice_mask_for_size(mm, old_psize);
+		old_mask = slice_mask_for_size(&mm->context, old_psize);
 		__clear_bit(i, old_mask->high_slices);
 		__set_bit(i, psize_mask->high_slices);
 
@@ -290,8 +243,8 @@
 	}
 
 	slice_dbg(" lsps=%lx, hsps=%lx\n",
-		  (unsigned long)mm->context.low_slices_psize,
-		  (unsigned long)mm->context.high_slices_psize);
+		  (unsigned long)mm_ctx_low_slices(&mm->context),
+		  (unsigned long)mm_ctx_high_slices(&mm->context));
 
 	spin_unlock_irqrestore(&slice_convert_lock, flags);
 
@@ -376,6 +329,7 @@
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 	unsigned long addr, found, prev;
 	struct vm_unmapped_area_info info;
+	unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr);
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
@@ -390,9 +344,9 @@
 	 * DEFAULT_MAP_WINDOW we should apply this.
 	 */
 	if (high_limit > DEFAULT_MAP_WINDOW)
-		addr += mm->context.slb_addr_limit - DEFAULT_MAP_WINDOW;
+		addr += mm_ctx_slb_addr_limit(&mm->context) - DEFAULT_MAP_WINDOW;
 
-	while (addr > PAGE_SIZE) {
+	while (addr > min_addr) {
 		info.high_limit = addr;
 		if (!slice_scan_available(addr - 1, available, 0, &addr))
 			continue;
@@ -404,8 +358,8 @@
 		 * Check if we need to reduce the range, or if we can
 		 * extend it to cover the previous available slice.
 		 */
-		if (addr < PAGE_SIZE)
-			addr = PAGE_SIZE;
+		if (addr < min_addr)
+			addr = min_addr;
 		else if (slice_scan_available(addr - 1, available, 0, &prev)) {
 			addr = prev;
 			goto prev_slice;
@@ -502,20 +456,20 @@
 			return -ENOMEM;
 	}
 
-	if (high_limit > mm->context.slb_addr_limit) {
+	if (high_limit > mm_ctx_slb_addr_limit(&mm->context)) {
 		/*
 		 * Increasing the slb_addr_limit does not require
 		 * slice mask cache to be recalculated because it should
 		 * be already initialised beyond the old address limit.
 		 */
-		mm->context.slb_addr_limit = high_limit;
+		mm_ctx_set_slb_addr_limit(&mm->context, high_limit);
 
 		on_each_cpu(slice_flush_segments, mm, 1);
 	}
 
 	/* Sanity checks */
 	BUG_ON(mm->task_size == 0);
-	BUG_ON(mm->context.slb_addr_limit == 0);
+	BUG_ON(mm_ctx_slb_addr_limit(&mm->context) == 0);
 	VM_BUG_ON(radix_enabled());
 
 	slice_dbg("slice_get_unmapped_area(mm=%p, psize=%d...\n", mm, psize);
@@ -527,7 +481,7 @@
 		addr = _ALIGN_UP(addr, page_size);
 		slice_dbg(" aligned addr=%lx\n", addr);
 		/* Ignore hint if it's too large or overlaps a VMA */
-		if (addr > high_limit - len ||
+		if (addr > high_limit - len || addr < mmap_min_addr ||
 		    !slice_area_is_free(mm, addr, len))
 			addr = 0;
 	}
@@ -535,7 +489,7 @@
 	/* First make up a "good" mask of slices that have the right size
 	 * already
 	 */
-	maskp = slice_mask_for_size(mm, psize);
+	maskp = slice_mask_for_size(&mm->context, psize);
 
 	/*
 	 * Here "good" means slices that are already the right page size,
@@ -562,7 +516,7 @@
 	 * a pointer to good mask for the next code to use.
 	 */
 	if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && psize == MMU_PAGE_64K) {
-		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
+		compat_maskp = slice_mask_for_size(&mm->context, MMU_PAGE_4K);
 		if (fixed)
 			slice_or_mask(&good_mask, maskp, compat_maskp);
 		else
@@ -639,14 +593,13 @@
 	newaddr = slice_find_area(mm, len, &potential_mask,
 				  psize, topdown, high_limit);
 
-#ifdef CONFIG_PPC_64K_PAGES
-	if (newaddr == -ENOMEM && psize == MMU_PAGE_64K) {
+	if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && newaddr == -ENOMEM &&
+	    psize == MMU_PAGE_64K) {
 		/* retry the search with 4k-page slices included */
 		slice_or_mask(&potential_mask, &potential_mask, compat_maskp);
 		newaddr = slice_find_area(mm, len, &potential_mask,
 					  psize, topdown, high_limit);
 	}
-#endif
 
 	if (newaddr == -ENOMEM)
 		return -ENOMEM;
@@ -693,7 +646,7 @@
 				     unsigned long flags)
 {
 	return slice_get_unmapped_area(addr, len, flags,
-				       current->mm->context.user_psize, 0);
+				       mm_ctx_user_psize(&current->mm->context), 0);
 }
 
 unsigned long arch_get_unmapped_area_topdown(struct file *filp,
@@ -703,7 +656,7 @@
 					     const unsigned long flags)
 {
 	return slice_get_unmapped_area(addr0, len, flags,
-				       current->mm->context.user_psize, 1);
+				       mm_ctx_user_psize(&current->mm->context), 1);
 }
 
 unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
@@ -714,10 +667,10 @@
 	VM_BUG_ON(radix_enabled());
 
 	if (slice_addr_is_low(addr)) {
-		psizes = mm->context.low_slices_psize;
+		psizes = mm_ctx_low_slices(&mm->context);
 		index = GET_LOW_SLICE_INDEX(addr);
 	} else {
-		psizes = mm->context.high_slices_psize;
+		psizes = mm_ctx_high_slices(&mm->context);
 		index = GET_HIGH_SLICE_INDEX(addr);
 	}
 	mask_index = index & 0x1;
@@ -738,32 +691,41 @@
 	 * case of fork it is just inherited from the mm being
 	 * duplicated.
 	 */
-#ifdef CONFIG_PPC64
-	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
-#else
-	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW;
-#endif
-
-	mm->context.user_psize = psize;
+	mm_ctx_set_slb_addr_limit(&mm->context, SLB_ADDR_LIMIT_DEFAULT);
+	mm_ctx_set_user_psize(&mm->context, psize);
 
 	/*
 	 * Set all slice psizes to the default.
 	 */
-	lpsizes = mm->context.low_slices_psize;
+	lpsizes = mm_ctx_low_slices(&mm->context);
 	memset(lpsizes, (psize << 4) | psize, SLICE_NUM_LOW >> 1);
 
-	hpsizes = mm->context.high_slices_psize;
+	hpsizes = mm_ctx_high_slices(&mm->context);
 	memset(hpsizes, (psize << 4) | psize, SLICE_NUM_HIGH >> 1);
 
 	/*
 	 * Slice mask cache starts zeroed, fill the default size cache.
 	 */
-	mask = slice_mask_for_size(mm, psize);
+	mask = slice_mask_for_size(&mm->context, psize);
 	mask->low_slices = ~0UL;
 	if (SLICE_NUM_HIGH)
 		bitmap_fill(mask->high_slices, SLICE_NUM_HIGH);
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+void slice_setup_new_exec(void)
+{
+	struct mm_struct *mm = current->mm;
+
+	slice_dbg("slice_setup_new_exec(mm=%p)\n", mm);
+
+	if (!is_32bit_task())
+		return;
+
+	mm_ctx_set_slb_addr_limit(&mm->context, DEFAULT_MAP_WINDOW);
+}
+#endif
+
 void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 			   unsigned long len, unsigned int psize)
 {
@@ -799,22 +761,21 @@
 			   unsigned long len)
 {
 	const struct slice_mask *maskp;
-	unsigned int psize = mm->context.user_psize;
+	unsigned int psize = mm_ctx_user_psize(&mm->context);
 
 	VM_BUG_ON(radix_enabled());
 
-	maskp = slice_mask_for_size(mm, psize);
-#ifdef CONFIG_PPC_64K_PAGES
+	maskp = slice_mask_for_size(&mm->context, psize);
+
 	/* We need to account for 4k slices too */
-	if (psize == MMU_PAGE_64K) {
+	if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && psize == MMU_PAGE_64K) {
 		const struct slice_mask *compat_maskp;
 		struct slice_mask available;
 
-		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
+		compat_maskp = slice_mask_for_size(&mm->context, MMU_PAGE_4K);
 		slice_or_mask(&available, maskp, compat_maskp);
 		return !slice_check_range_fits(mm, &available, addr, len);
 	}
-#endif
 
 	return !slice_check_range_fits(mm, maskp, addr, len);
 }
diff --git a/arch/powerpc/mm/vphn.h b/arch/powerpc/mm/vphn.h
deleted file mode 100644
index f9ffdb3..0000000
--- a/arch/powerpc/mm/vphn.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ARCH_POWERPC_MM_VPHN_H_
-#define _ARCH_POWERPC_MM_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)
-
-extern int vphn_unpack_associativity(const long *packed, __be32 *unpacked);
-
-#endif
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 47fc666..55d4377 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * bpf_jit.h: BPF JIT compiler for PPC
  *
  * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation
  * 	     2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 #ifndef _BPF_JIT_H
 #define _BPF_JIT_H
@@ -51,6 +47,8 @@
 #define PPC_LIS(r, i)		PPC_ADDIS(r, 0, i)
 #define PPC_STD(r, base, i)	EMIT(PPC_INST_STD | ___PPC_RS(r) |	      \
 				     ___PPC_RA(base) | ((i) & 0xfffc))
+#define PPC_STDX(r, base, b)	EMIT(PPC_INST_STDX | ___PPC_RS(r) |	      \
+				     ___PPC_RA(base) | ___PPC_RB(b))
 #define PPC_STDU(r, base, i)	EMIT(PPC_INST_STDU | ___PPC_RS(r) |	      \
 				     ___PPC_RA(base) | ((i) & 0xfffc))
 #define PPC_STW(r, base, i)	EMIT(PPC_INST_STW | ___PPC_RS(r) |	      \
@@ -65,7 +63,9 @@
 #define PPC_LBZ(r, base, i)	EMIT(PPC_INST_LBZ | ___PPC_RT(r) |	      \
 				     ___PPC_RA(base) | IMM_L(i))
 #define PPC_LD(r, base, i)	EMIT(PPC_INST_LD | ___PPC_RT(r) |	      \
-				     ___PPC_RA(base) | IMM_L(i))
+				     ___PPC_RA(base) | ((i) & 0xfffc))
+#define PPC_LDX(r, base, b)	EMIT(PPC_INST_LDX | ___PPC_RT(r) |	      \
+				     ___PPC_RA(base) | ___PPC_RB(b))
 #define PPC_LWZ(r, base, i)	EMIT(PPC_INST_LWZ | ___PPC_RT(r) |	      \
 				     ___PPC_RA(base) | IMM_L(i))
 #define PPC_LHZ(r, base, i)	EMIT(PPC_INST_LHZ | ___PPC_RT(r) |	      \
@@ -85,17 +85,6 @@
 					___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_BPF_STDCX(s, a, b)	EMIT(PPC_INST_STDCX | ___PPC_RS(s) |	      \
 					___PPC_RA(a) | ___PPC_RB(b))
-
-#ifdef CONFIG_PPC64
-#define PPC_BPF_LL(r, base, i) do { PPC_LD(r, base, i); } while(0)
-#define PPC_BPF_STL(r, base, i) do { PPC_STD(r, base, i); } while(0)
-#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0)
-#else
-#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0)
-#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0)
-#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0)
-#endif
-
 #define PPC_CMPWI(a, i)		EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i))
 #define PPC_CMPDI(a, i)		EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i))
 #define PPC_CMPW(a, b)		EMIT(PPC_INST_CMPW | ___PPC_RA(a) |	      \
@@ -123,7 +112,7 @@
 				     ___PPC_RA(a) | IMM_L(i))
 #define PPC_DIVWU(d, a, b)	EMIT(PPC_INST_DIVWU | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
-#define PPC_DIVD(d, a, b)	EMIT(PPC_INST_DIVD | ___PPC_RT(d) |	      \
+#define PPC_DIVDU(d, a, b)	EMIT(PPC_INST_DIVDU | ___PPC_RT(d) |	      \
 				     ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_AND(d, a, b)	EMIT(PPC_INST_AND | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(b))
@@ -152,6 +141,10 @@
 				     ___PPC_RS(a) | ___PPC_RB(s))
 #define PPC_SRW(d, a, s)	EMIT(PPC_INST_SRW | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRAW(d, a, s)	EMIT(PPC_INST_SRAW | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRAWI(d, a, i)	EMIT(PPC_INST_SRAWI | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | __PPC_SH(i))
 #define PPC_SRD(d, a, s)	EMIT(PPC_INST_SRD | ___PPC_RA(d) |	      \
 				     ___PPC_RS(a) | ___PPC_RB(s))
 #define PPC_SRAD(d, a, s)	EMIT(PPC_INST_SRAD | ___PPC_RA(d) |	      \
@@ -161,6 +154,10 @@
 #define PPC_RLWINM(d, a, i, mb, me)	EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \
 					___PPC_RS(a) | __PPC_SH(i) |	      \
 					__PPC_MB(mb) | __PPC_ME(me))
+#define PPC_RLWINM_DOT(d, a, i, mb, me)	EMIT(PPC_INST_RLWINM_DOT |	      \
+					___PPC_RA(d) | ___PPC_RS(a) |	      \
+					__PPC_SH(i) | __PPC_MB(mb) |	      \
+					__PPC_ME(me))
 #define PPC_RLWIMI(d, a, i, mb, me)	EMIT(PPC_INST_RLWIMI | ___PPC_RA(d) | \
 					___PPC_RS(a) | __PPC_SH(i) |	      \
 					__PPC_MB(mb) | __PPC_ME(me))
diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h
index 6f4daac..6e5a2a4 100644
--- a/arch/powerpc/net/bpf_jit32.h
+++ b/arch/powerpc/net/bpf_jit32.h
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * bpf_jit32.h: BPF JIT compiler for PPC
  *
  * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation
  *
  * Split from bpf_jit.h
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 #ifndef _BPF_JIT32_H
 #define _BPF_JIT32_H
@@ -106,9 +102,8 @@
 	} while (0)
 #else
 #define PPC_BPF_LOAD_CPU(r)     \
-	do { BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);		\
-		PPC_LHZ_OFFS(r, (1 & ~(THREAD_SIZE - 1)),			\
-				offsetof(struct thread_info, cpu));		\
+	do { BUILD_BUG_ON(FIELD_SIZEOF(struct task_struct, cpu) != 4);		\
+		PPC_LHZ_OFFS(r, 2, offsetof(struct task_struct, cpu));		\
 	} while(0)
 #endif
 #else
@@ -123,6 +118,10 @@
 #define PPC_NTOHS_OFFS(r, base, i)	PPC_LHZ_OFFS(r, base, i)
 #endif
 
+#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0)
+#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0)
+#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0)
+
 #define SEEN_DATAREF 0x10000 /* might call external helpers */
 #define SEEN_XREG    0x20000 /* X reg is used */
 #define SEEN_MEM     0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary
diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
index 3609be4..cf3a7e3 100644
--- a/arch/powerpc/net/bpf_jit64.h
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * bpf_jit64.h: BPF JIT compiler for PPC64
  *
  * Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
  *		  IBM 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.
  */
 #ifndef _BPF_JIT64_H
 #define _BPF_JIT64_H
@@ -68,6 +64,26 @@
 /* PPC NVR range -- update this if we ever use NVRs below r27 */
 #define BPF_PPC_NVR_MIN		27
 
+/*
+ * WARNING: These can use TMP_REG_2 if the offset is not at word boundary,
+ * so ensure that it isn't in use already.
+ */
+#define PPC_BPF_LL(r, base, i) do {					      \
+				if ((i) % 4) {				      \
+					PPC_LI(b2p[TMP_REG_2], (i));	      \
+					PPC_LDX(r, base, b2p[TMP_REG_2]);     \
+				} else					      \
+					PPC_LD(r, base, i);		      \
+				} while(0)
+#define PPC_BPF_STL(r, base, i) do {					      \
+				if ((i) % 4) {				      \
+					PPC_LI(b2p[TMP_REG_2], (i));	      \
+					PPC_STDX(r, base, b2p[TMP_REG_2]);    \
+				} else					      \
+					PPC_STD(r, base, i);		      \
+				} while(0)
+#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0)
+
 #define SEEN_FUNC	0x1000 /* might call external helpers */
 #define SEEN_STACK	0x2000 /* uses BPF stack */
 #define SEEN_TAILCALL	0x4000 /* uses tail calls */
diff --git a/arch/powerpc/net/bpf_jit_asm.S b/arch/powerpc/net/bpf_jit_asm.S
index c80280d..2f5030d 100644
--- a/arch/powerpc/net/bpf_jit_asm.S
+++ b/arch/powerpc/net/bpf_jit_asm.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* bpf_jit.S: Packet/header access helper functions
  * for PPC64 BPF compiler.
  *
  * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM 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.
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index d5bfe24..d57b46e 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* bpf_jit_comp.c: BPF JIT compiler
  *
  * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation
  *
  * Based on the x86 BPF compiler, by Eric Dumazet (eric.dumazet@gmail.com)
  * Ported to ppc32 by Denis Kirjanov <kda@linux-powerpc.org>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 #include <linux/moduleloader.h>
 #include <asm/cacheflush.h>
@@ -379,18 +375,17 @@
 							  hash));
 			break;
 		case BPF_ANC | SKF_AD_VLAN_TAG:
-		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
-			BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
 
 			PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  vlan_tci));
-			if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
-				PPC_ANDI(r_A, r_A, ~VLAN_TAG_PRESENT);
-			} else {
-				PPC_ANDI(r_A, r_A, VLAN_TAG_PRESENT);
-				PPC_SRWI(r_A, r_A, 12);
-			}
+			break;
+		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
+			PPC_LBZ_OFFS(r_A, r_skb, PKT_VLAN_PRESENT_OFFSET());
+			if (PKT_VLAN_PRESENT_BIT)
+				PPC_SRWI(r_A, r_A, PKT_VLAN_PRESENT_BIT);
+			if (PKT_VLAN_PRESENT_BIT < 7)
+				PPC_ANDI(r_A, r_A, 1);
 			break;
 		case BPF_ANC | SKF_AD_QUEUE:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 50b1297..be3517e 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * bpf_jit_comp64.c: eBPF JIT compiler
  *
@@ -5,11 +6,6 @@
  *		  IBM Corporation
  *
  * Based on the powerpc classic BPF JIT compiler by Matt Evans
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 #include <linux/moduleloader.h>
 #include <asm/cacheflush.h>
@@ -166,7 +162,33 @@
 	PPC_BLR();
 }
 
-static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func)
+static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx,
+				       u64 func)
+{
+#ifdef PPC64_ELF_ABI_v1
+	/* func points to the function descriptor */
+	PPC_LI64(b2p[TMP_REG_2], func);
+	/* Load actual entry point from function descriptor */
+	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
+	/* ... and move it to LR */
+	PPC_MTLR(b2p[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)
+	 * and since we don't use a TOC ourself.
+	 */
+	PPC_BPF_LL(2, b2p[TMP_REG_2], 8);
+#else
+	/* We can clobber r12 */
+	PPC_FUNC_ADDR(12, func);
+	PPC_MTLR(12);
+#endif
+	PPC_BLRL();
+}
+
+static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx,
+				       u64 func)
 {
 	unsigned int i, ctx_idx = ctx->idx;
 
@@ -226,7 +248,7 @@
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *   goto out;
 	 */
-	PPC_LD(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
+	PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
 	PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT);
 	PPC_BCC(COND_GT, out);
 
@@ -239,7 +261,7 @@
 	/* prog = array->ptrs[index]; */
 	PPC_MULI(b2p[TMP_REG_1], b2p_index, 8);
 	PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array);
-	PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs));
+	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs));
 
 	/*
 	 * if (prog == NULL)
@@ -249,7 +271,7 @@
 	PPC_BCC(COND_EQ, out);
 
 	/* goto *(prog->bpf_func + prologue_size); */
-	PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func));
+	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func));
 #ifdef PPC64_ELF_ABI_v1
 	/* skip past the function descriptor */
 	PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1],
@@ -273,7 +295,7 @@
 {
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
-	int i;
+	int i, ret;
 
 	/* Start of epilogue code - will only be valid 2nd pass onwards */
 	u32 exit_addr = addrs[flen];
@@ -284,8 +306,9 @@
 		u32 src_reg = b2p[insn[i].src_reg];
 		s16 off = insn[i].off;
 		s32 imm = insn[i].imm;
+		bool func_addr_fixed;
+		u64 func_addr;
 		u64 imm64;
-		u8 *func;
 		u32 true_cond;
 		u32 tmp_idx;
 
@@ -372,12 +395,12 @@
 		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
 		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
 			if (BPF_OP(code) == BPF_MOD) {
-				PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
+				PPC_DIVDU(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULD(b2p[TMP_REG_1], src_reg,
 						b2p[TMP_REG_1]);
 				PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
 			} else
-				PPC_DIVD(dst_reg, dst_reg, src_reg);
+				PPC_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 */
@@ -405,7 +428,7 @@
 				break;
 			case BPF_ALU64:
 				if (BPF_OP(code) == BPF_MOD) {
-					PPC_DIVD(b2p[TMP_REG_2], dst_reg,
+					PPC_DIVDU(b2p[TMP_REG_2], dst_reg,
 							b2p[TMP_REG_1]);
 					PPC_MULD(b2p[TMP_REG_1],
 							b2p[TMP_REG_1],
@@ -413,7 +436,7 @@
 					PPC_SUB(dst_reg, dst_reg,
 							b2p[TMP_REG_1]);
 				} else
-					PPC_DIVD(dst_reg, dst_reg,
+					PPC_DIVDU(dst_reg, dst_reg,
 							b2p[TMP_REG_1]);
 				break;
 			}
@@ -477,6 +500,9 @@
 		case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */
 			/* slw clears top 32 bits */
 			PPC_SLW(dst_reg, dst_reg, src_reg);
+			/* skip zero extension move, but set address map. */
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
 			PPC_SLD(dst_reg, dst_reg, src_reg);
@@ -484,6 +510,8 @@
 		case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<== (u32) imm */
 			/* with imm 0, we still need to clear top 32 bits */
 			PPC_SLWI(dst_reg, dst_reg, imm);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<== imm */
 			if (imm != 0)
@@ -491,20 +519,30 @@
 			break;
 		case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */
 			PPC_SRW(dst_reg, dst_reg, src_reg);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
 			PPC_SRD(dst_reg, dst_reg, src_reg);
 			break;
 		case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
 			PPC_SRWI(dst_reg, dst_reg, imm);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */
 			if (imm != 0)
 				PPC_SRDI(dst_reg, dst_reg, imm);
 			break;
+		case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */
+			PPC_SRAW(dst_reg, dst_reg, src_reg);
+			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
 			PPC_SRAD(dst_reg, dst_reg, src_reg);
 			break;
+		case BPF_ALU | BPF_ARSH | BPF_K: /* (s32) dst >>= imm */
+			PPC_SRAWI(dst_reg, dst_reg, imm);
+			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_ARSH | BPF_K: /* (s64) dst >>= imm */
 			if (imm != 0)
 				PPC_SRADI(dst_reg, dst_reg, imm);
@@ -515,6 +553,11 @@
 		 */
 		case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
 		case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
+			if (imm == 1) {
+				/* special mov32 for zext */
+				PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
+				break;
+			}
 			PPC_MR(dst_reg, src_reg);
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
@@ -522,11 +565,13 @@
 			PPC_LI32(dst_reg, imm);
 			if (imm < 0)
 				goto bpf_alu32_trunc;
+			else if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 
 bpf_alu32_trunc:
 		/* Truncate to 32-bits */
-		if (BPF_CLASS(code) == BPF_ALU)
+		if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext)
 			PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
 		break;
 
@@ -573,7 +618,7 @@
 				 * the instructions generated will remain the
 				 * same across all passes
 				 */
-				PPC_STD(dst_reg, 1, bpf_jit_stack_local(ctx));
+				PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx));
 				PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx));
 				PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]);
 				break;
@@ -585,10 +630,13 @@
 			case 16:
 				/* zero-extend 16 bits into 64 bits */
 				PPC_RLDICL(dst_reg, dst_reg, 0, 48);
+				if (insn_is_zext(&insn[i + 1]))
+					addrs[++i] = ctx->idx * 4;
 				break;
 			case 32:
-				/* zero-extend 32 bits into 64 bits */
-				PPC_RLDICL(dst_reg, dst_reg, 0, 32);
+				if (!fp->aux->verifier_zext)
+					/* zero-extend 32 bits into 64 bits */
+					PPC_RLDICL(dst_reg, dst_reg, 0, 32);
 				break;
 			case 64:
 				/* nop */
@@ -629,7 +677,7 @@
 				PPC_LI32(b2p[TMP_REG_1], imm);
 				src_reg = b2p[TMP_REG_1];
 			}
-			PPC_STD(src_reg, dst_reg, off);
+			PPC_BPF_STL(src_reg, dst_reg, off);
 			break;
 
 		/*
@@ -665,18 +713,24 @@
 		/* dst = *(u8 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
 			PPC_LBZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u16 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_H:
 			PPC_LHZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u32 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_W:
 			PPC_LWZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
-			PPC_LD(dst_reg, src_reg, off);
+			PPC_BPF_LL(dst_reg, src_reg, off);
 			break;
 
 		/*
@@ -711,23 +765,15 @@
 		case BPF_JMP | BPF_CALL:
 			ctx->seen |= SEEN_FUNC;
 
-			/* bpf function call */
-			if (insn[i].src_reg == BPF_PSEUDO_CALL)
-				if (!extra_pass)
-					func = NULL;
-				else if (fp->aux->func && off < fp->aux->func_cnt)
-					/* use the subprog id from the off
-					 * field to lookup the callee address
-					 */
-					func = (u8 *) fp->aux->func[off]->bpf_func;
-				else
-					return -EINVAL;
-			/* kernel helper call */
+			ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
+						    &func_addr, &func_addr_fixed);
+			if (ret < 0)
+				return ret;
+
+			if (func_addr_fixed)
+				bpf_jit_emit_func_call_hlp(image, ctx, func_addr);
 			else
-				func = (u8 *) __bpf_call_base + imm;
-
-			bpf_jit_emit_func_call(image, ctx, (u64)func);
-
+				bpf_jit_emit_func_call_rel(image, ctx, func_addr);
 			/* move return value from r3 to BPF_REG_0 */
 			PPC_MR(b2p[BPF_REG_0], 3);
 			break;
@@ -743,36 +789,58 @@
 		case BPF_JMP | BPF_JGT | BPF_X:
 		case BPF_JMP | BPF_JSGT | BPF_K:
 		case BPF_JMP | BPF_JSGT | BPF_X:
+		case BPF_JMP32 | BPF_JGT | BPF_K:
+		case BPF_JMP32 | BPF_JGT | BPF_X:
+		case BPF_JMP32 | BPF_JSGT | BPF_K:
+		case BPF_JMP32 | BPF_JSGT | BPF_X:
 			true_cond = COND_GT;
 			goto cond_branch;
 		case BPF_JMP | BPF_JLT | BPF_K:
 		case BPF_JMP | BPF_JLT | BPF_X:
 		case BPF_JMP | BPF_JSLT | BPF_K:
 		case BPF_JMP | BPF_JSLT | BPF_X:
+		case BPF_JMP32 | BPF_JLT | BPF_K:
+		case BPF_JMP32 | BPF_JLT | BPF_X:
+		case BPF_JMP32 | BPF_JSLT | BPF_K:
+		case BPF_JMP32 | BPF_JSLT | BPF_X:
 			true_cond = COND_LT;
 			goto cond_branch;
 		case BPF_JMP | BPF_JGE | BPF_K:
 		case BPF_JMP | BPF_JGE | BPF_X:
 		case BPF_JMP | BPF_JSGE | BPF_K:
 		case BPF_JMP | BPF_JSGE | BPF_X:
+		case BPF_JMP32 | BPF_JGE | BPF_K:
+		case BPF_JMP32 | BPF_JGE | BPF_X:
+		case BPF_JMP32 | BPF_JSGE | BPF_K:
+		case BPF_JMP32 | BPF_JSGE | BPF_X:
 			true_cond = COND_GE;
 			goto cond_branch;
 		case BPF_JMP | BPF_JLE | BPF_K:
 		case BPF_JMP | BPF_JLE | BPF_X:
 		case BPF_JMP | BPF_JSLE | BPF_K:
 		case BPF_JMP | BPF_JSLE | BPF_X:
+		case BPF_JMP32 | BPF_JLE | BPF_K:
+		case BPF_JMP32 | BPF_JLE | BPF_X:
+		case BPF_JMP32 | BPF_JSLE | BPF_K:
+		case BPF_JMP32 | BPF_JSLE | BPF_X:
 			true_cond = COND_LE;
 			goto cond_branch;
 		case BPF_JMP | BPF_JEQ | BPF_K:
 		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP32 | BPF_JEQ | BPF_K:
+		case BPF_JMP32 | BPF_JEQ | BPF_X:
 			true_cond = COND_EQ;
 			goto cond_branch;
 		case BPF_JMP | BPF_JNE | BPF_K:
 		case BPF_JMP | BPF_JNE | BPF_X:
+		case BPF_JMP32 | BPF_JNE | BPF_K:
+		case BPF_JMP32 | BPF_JNE | BPF_X:
 			true_cond = COND_NE;
 			goto cond_branch;
 		case BPF_JMP | BPF_JSET | BPF_K:
 		case BPF_JMP | BPF_JSET | BPF_X:
+		case BPF_JMP32 | BPF_JSET | BPF_K:
+		case BPF_JMP32 | BPF_JSET | BPF_X:
 			true_cond = COND_NE;
 			/* Fall through */
 
@@ -784,18 +852,44 @@
 			case BPF_JMP | BPF_JLE | BPF_X:
 			case BPF_JMP | BPF_JEQ | BPF_X:
 			case BPF_JMP | BPF_JNE | BPF_X:
+			case BPF_JMP32 | BPF_JGT | BPF_X:
+			case BPF_JMP32 | BPF_JLT | BPF_X:
+			case BPF_JMP32 | BPF_JGE | BPF_X:
+			case BPF_JMP32 | BPF_JLE | BPF_X:
+			case BPF_JMP32 | BPF_JEQ | BPF_X:
+			case BPF_JMP32 | BPF_JNE | BPF_X:
 				/* unsigned comparison */
-				PPC_CMPLD(dst_reg, src_reg);
+				if (BPF_CLASS(code) == BPF_JMP32)
+					PPC_CMPLW(dst_reg, src_reg);
+				else
+					PPC_CMPLD(dst_reg, src_reg);
 				break;
 			case BPF_JMP | BPF_JSGT | BPF_X:
 			case BPF_JMP | BPF_JSLT | BPF_X:
 			case BPF_JMP | BPF_JSGE | BPF_X:
 			case BPF_JMP | BPF_JSLE | BPF_X:
+			case BPF_JMP32 | BPF_JSGT | BPF_X:
+			case BPF_JMP32 | BPF_JSLT | BPF_X:
+			case BPF_JMP32 | BPF_JSGE | BPF_X:
+			case BPF_JMP32 | BPF_JSLE | BPF_X:
 				/* signed comparison */
-				PPC_CMPD(dst_reg, src_reg);
+				if (BPF_CLASS(code) == BPF_JMP32)
+					PPC_CMPW(dst_reg, src_reg);
+				else
+					PPC_CMPD(dst_reg, src_reg);
 				break;
 			case BPF_JMP | BPF_JSET | BPF_X:
-				PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, src_reg);
+			case BPF_JMP32 | BPF_JSET | BPF_X:
+				if (BPF_CLASS(code) == BPF_JMP) {
+					PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
+						    src_reg);
+				} else {
+					int tmp_reg = b2p[TMP_REG_1];
+
+					PPC_AND(tmp_reg, dst_reg, src_reg);
+					PPC_RLWINM_DOT(tmp_reg, tmp_reg, 0, 0,
+						       31);
+				}
 				break;
 			case BPF_JMP | BPF_JNE | BPF_K:
 			case BPF_JMP | BPF_JEQ | BPF_K:
@@ -803,43 +897,87 @@
 			case BPF_JMP | BPF_JLT | BPF_K:
 			case BPF_JMP | BPF_JGE | BPF_K:
 			case BPF_JMP | BPF_JLE | BPF_K:
+			case BPF_JMP32 | BPF_JNE | BPF_K:
+			case BPF_JMP32 | BPF_JEQ | BPF_K:
+			case BPF_JMP32 | BPF_JGT | BPF_K:
+			case BPF_JMP32 | BPF_JLT | BPF_K:
+			case BPF_JMP32 | BPF_JGE | BPF_K:
+			case BPF_JMP32 | BPF_JLE | BPF_K:
+			{
+				bool is_jmp32 = BPF_CLASS(code) == BPF_JMP32;
+
 				/*
 				 * Need sign-extended load, so only positive
 				 * values can be used as imm in cmpldi
 				 */
-				if (imm >= 0 && imm < 32768)
-					PPC_CMPLDI(dst_reg, imm);
-				else {
+				if (imm >= 0 && imm < 32768) {
+					if (is_jmp32)
+						PPC_CMPLWI(dst_reg, imm);
+					else
+						PPC_CMPLDI(dst_reg, imm);
+				} else {
 					/* sign-extending load */
 					PPC_LI32(b2p[TMP_REG_1], imm);
 					/* ... but unsigned comparison */
-					PPC_CMPLD(dst_reg, b2p[TMP_REG_1]);
+					if (is_jmp32)
+						PPC_CMPLW(dst_reg,
+							  b2p[TMP_REG_1]);
+					else
+						PPC_CMPLD(dst_reg,
+							  b2p[TMP_REG_1]);
 				}
 				break;
+			}
 			case BPF_JMP | BPF_JSGT | BPF_K:
 			case BPF_JMP | BPF_JSLT | BPF_K:
 			case BPF_JMP | BPF_JSGE | BPF_K:
 			case BPF_JMP | BPF_JSLE | BPF_K:
+			case BPF_JMP32 | BPF_JSGT | BPF_K:
+			case BPF_JMP32 | BPF_JSLT | BPF_K:
+			case BPF_JMP32 | BPF_JSGE | BPF_K:
+			case BPF_JMP32 | BPF_JSLE | BPF_K:
+			{
+				bool is_jmp32 = BPF_CLASS(code) == BPF_JMP32;
+
 				/*
 				 * signed comparison, so any 16-bit value
 				 * can be used in cmpdi
 				 */
-				if (imm >= -32768 && imm < 32768)
-					PPC_CMPDI(dst_reg, imm);
-				else {
+				if (imm >= -32768 && imm < 32768) {
+					if (is_jmp32)
+						PPC_CMPWI(dst_reg, imm);
+					else
+						PPC_CMPDI(dst_reg, imm);
+				} else {
 					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_CMPD(dst_reg, b2p[TMP_REG_1]);
+					if (is_jmp32)
+						PPC_CMPW(dst_reg,
+							 b2p[TMP_REG_1]);
+					else
+						PPC_CMPD(dst_reg,
+							 b2p[TMP_REG_1]);
 				}
 				break;
+			}
 			case BPF_JMP | BPF_JSET | BPF_K:
+			case BPF_JMP32 | BPF_JSET | BPF_K:
 				/* andi does not sign-extend the immediate */
 				if (imm >= 0 && imm < 32768)
 					/* PPC_ANDI is _only/always_ dot-form */
 					PPC_ANDI(b2p[TMP_REG_1], dst_reg, imm);
 				else {
-					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
-						    b2p[TMP_REG_1]);
+					int tmp_reg = b2p[TMP_REG_1];
+
+					PPC_LI32(tmp_reg, imm);
+					if (BPF_CLASS(code) == BPF_JMP) {
+						PPC_AND_DOT(tmp_reg, dst_reg,
+							    tmp_reg);
+					} else {
+						PPC_AND(tmp_reg, dst_reg,
+							tmp_reg);
+						PPC_RLWINM_DOT(tmp_reg, tmp_reg,
+							       0, 0, 31);
+					}
 				}
 				break;
 			}
@@ -872,6 +1010,55 @@
 	return 0;
 }
 
+/* Fix the branch target addresses for subprog calls */
+static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image,
+				       struct codegen_context *ctx, u32 *addrs)
+{
+	const struct bpf_insn *insn = fp->insnsi;
+	bool func_addr_fixed;
+	u64 func_addr;
+	u32 tmp_idx;
+	int i, ret;
+
+	for (i = 0; i < fp->len; i++) {
+		/*
+		 * During the extra pass, only the branch target addresses for
+		 * the subprog calls need to be fixed. All other instructions
+		 * can left untouched.
+		 *
+		 * The JITed image length does not change because we already
+		 * ensure that the JITed instruction sequence for these calls
+		 * are of fixed length by padding them with NOPs.
+		 */
+		if (insn[i].code == (BPF_JMP | BPF_CALL) &&
+		    insn[i].src_reg == BPF_PSEUDO_CALL) {
+			ret = bpf_jit_get_func_addr(fp, &insn[i], true,
+						    &func_addr,
+						    &func_addr_fixed);
+			if (ret < 0)
+				return ret;
+
+			/*
+			 * Save ctx->idx as this would currently point to the
+			 * end of the JITed image and set it to the offset of
+			 * the instruction sequence corresponding to the
+			 * subprog call temporarily.
+			 */
+			tmp_idx = ctx->idx;
+			ctx->idx = addrs[i] / 4;
+			bpf_jit_emit_func_call_rel(image, ctx, func_addr);
+
+			/*
+			 * Restore ctx->idx here. This is safe as the length
+			 * of the JITed sequence remains unchanged.
+			 */
+			ctx->idx = tmp_idx;
+		}
+	}
+
+	return 0;
+}
+
 struct powerpc64_jit_data {
 	struct bpf_binary_header *header;
 	u32 *addrs;
@@ -880,6 +1067,11 @@
 	struct codegen_context ctx;
 };
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 {
 	u32 proglen;
@@ -950,6 +1142,19 @@
 	}
 
 	/*
+	 * If we have seen a tail call, we need a second pass.
+	 * This is because bpf_jit_emit_common_epilogue() is called
+	 * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen.
+	 */
+	if (cgctx.seen & SEEN_TAILCALL) {
+		cgctx.idx = 0;
+		if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
+			fp = org_fp;
+			goto out_addrs;
+		}
+	}
+
+	/*
 	 * Pretend to build prologue, given the features we've seen.  This will
 	 * update ctgtx.idx as it pretends to output instructions, then we can
 	 * calculate total size from idx.
@@ -970,6 +1175,22 @@
 skip_init_ctx:
 	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
 
+	if (extra_pass) {
+		/*
+		 * Do not touch the prologue and epilogue as they will remain
+		 * unchanged. Only fix the branch target address for subprog
+		 * calls in the body.
+		 *
+		 * This does not change the offsets and lengths of the subprog
+		 * call instruction sequences and hence, the size of the JITed
+		 * image as well.
+		 */
+		bpf_jit_fixup_subprog_calls(fp, code_base, &cgctx, addrs);
+
+		/* There is no need to perform the usual passes. */
+		goto skip_codegen_passes;
+	}
+
 	/* Code generation passes 1-2 */
 	for (pass = 1; pass < 3; pass++) {
 		/* Now build the prologue, body code & epilogue for real. */
@@ -983,6 +1204,7 @@
 				proglen - (cgctx.idx * 4), cgctx.seen);
 	}
 
+skip_codegen_passes:
 	if (bpf_jit_enable > 1)
 		/*
 		 * Note that we output the base address of the code_base
@@ -1002,6 +1224,7 @@
 
 	bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE));
 	if (!fp->is_func || extra_pass) {
+		bpf_prog_fill_jited_linfo(fp, addrs);
 out_addrs:
 		kfree(addrs);
 		kfree(jit_data);
diff --git a/arch/powerpc/oprofile/Makefile b/arch/powerpc/oprofile/Makefile
index 7a7834c..bb2d94c 100644
--- a/arch/powerpc/oprofile/Makefile
+++ b/arch/powerpc/oprofile/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
@@ -17,4 +16,4 @@
 		cell/spu_task_sync.o
 oprofile-$(CONFIG_PPC_BOOK3S_64) += op_model_power4.o op_model_pa6t.o
 oprofile-$(CONFIG_FSL_EMB_PERFMON) += op_model_fsl_emb.o
-oprofile-$(CONFIG_6xx) += op_model_7450.o
+oprofile-$(CONFIG_PPC_BOOK3S_32) += op_model_7450.o
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index ad054dd..43245f4 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /**
  * Copyright (C) 2005 Brian Rogan <bcr6@cornell.edu>, IBM
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
 **/
 
-#include <linux/compat_time.h>
+#include <linux/time.h>
 #include <linux/oprofile.h>
 #include <linux/sched.h>
 #include <asm/processor.h>
@@ -31,7 +28,7 @@
 	unsigned int stack_frame[2];
 	void __user *p = compat_ptr(sp);
 
-	if (!access_ok(VERIFY_READ, p, sizeof(stack_frame)))
+	if (!access_ok(p, sizeof(stack_frame)))
 		return 0;
 
 	/*
@@ -57,7 +54,7 @@
 {
 	unsigned long stack_frame[3];
 
-	if (!access_ok(VERIFY_READ, (void __user *)sp, sizeof(stack_frame)))
+	if (!access_ok((void __user *)sp, sizeof(stack_frame)))
 		return 0;
 
 	if (__copy_from_user_inatomic(stack_frame, (void __user *)sp,
diff --git a/arch/powerpc/oprofile/cell/pr_util.h b/arch/powerpc/oprofile/cell/pr_util.h
index 964b939..e198efa 100644
--- a/arch/powerpc/oprofile/cell/pr_util.h
+++ b/arch/powerpc/oprofile/cell/pr_util.h
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
  /*
  * Cell Broadband Engine OProfile Support
  *
  * (C) Copyright IBM Corporation 2006
  *
  * Author: Maynard Johnson <maynardj@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef PR_UTIL_H
diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c
index 4e099e5..cdf8834 100644
--- a/arch/powerpc/oprofile/cell/spu_profiler.c
+++ b/arch/powerpc/oprofile/cell/spu_profiler.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Cell Broadband Engine OProfile Support
  *
@@ -5,11 +6,6 @@
  *
  * Authors: Maynard Johnson <maynardj@us.ibm.com>
  *	    Carl Love <carll@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/hrtimer.h>
diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c
index 2668cc4..0caec3d 100644
--- a/arch/powerpc/oprofile/cell/spu_task_sync.c
+++ b/arch/powerpc/oprofile/cell/spu_task_sync.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Cell Broadband Engine OProfile Support
  *
  * (C) Copyright IBM Corporation 2006
  *
  * Author: Maynard Johnson <maynardj@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /* The purpose of this file is to handle SPU event task switching
diff --git a/arch/powerpc/oprofile/cell/vma_map.c b/arch/powerpc/oprofile/cell/vma_map.c
index f40e373..7c4b19c 100644
--- a/arch/powerpc/oprofile/cell/vma_map.c
+++ b/arch/powerpc/oprofile/cell/vma_map.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Cell Broadband Engine OProfile Support
  *
  * (C) Copyright IBM Corporation 2006
  *
  * Author: Maynard Johnson <maynardj@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /* The code in this source file is responsible for generating
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
index bf094c5..0fb528c 100644
--- a/arch/powerpc/oprofile/common.c
+++ b/arch/powerpc/oprofile/common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PPC 64 oprofile support:
  * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
@@ -6,11 +7,6 @@
  *	Author: Andy Fleming
  *
  * Based on alpha version.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/oprofile.h>
@@ -212,7 +208,7 @@
 			model = &op_model_pa6t;
 			break;
 #endif
-#ifdef CONFIG_6xx
+#ifdef CONFIG_PPC_BOOK3S_32
 		case PPC_OPROFILE_G4:
 			model = &op_model_7450;
 			break;
diff --git a/arch/powerpc/oprofile/op_model_7450.c b/arch/powerpc/oprofile/op_model_7450.c
index d29b6e4..5ebc251 100644
--- a/arch/powerpc/oprofile/op_model_7450.c
+++ b/arch/powerpc/oprofile/op_model_7450.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/oprofile/op_model_7450.c
  *
@@ -8,11 +9,6 @@
  *
  * Author: Andy Fleming
  * Maintainer: Kumar Gala <galak@kernel.crashing.org>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/oprofile.h>
diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c
index b90a21b..7eb7307 100644
--- a/arch/powerpc/oprofile/op_model_cell.c
+++ b/arch/powerpc/oprofile/op_model_cell.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Cell Broadband Engine OProfile Support
  *
@@ -7,11 +8,6 @@
  * Modifications:
  *	   Carl Love <carll@us.ibm.com>
  *	   Maynard Johnson <maynardj@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/cpufreq.h>
diff --git a/arch/powerpc/oprofile/op_model_fsl_emb.c b/arch/powerpc/oprofile/op_model_fsl_emb.c
index 14cf86f..25dc681 100644
--- a/arch/powerpc/oprofile/op_model_fsl_emb.c
+++ b/arch/powerpc/oprofile/op_model_fsl_emb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Freescale Embedded oprofile support, based on ppc64 oprofile support
  * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
@@ -6,11 +7,6 @@
  *
  * Author: Andy Fleming
  * Maintainer: Kumar Gala <galak@kernel.crashing.org>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/oprofile.h>
diff --git a/arch/powerpc/oprofile/op_model_pa6t.c b/arch/powerpc/oprofile/op_model_pa6t.c
index a114a7c..d23061c 100644
--- a/arch/powerpc/oprofile/op_model_pa6t.c
+++ b/arch/powerpc/oprofile/op_model_pa6t.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2006-2007 PA Semi, Inc
  *
@@ -6,19 +7,6 @@
  * Maintained by: Olof Johansson <olof@lixom.net>
  *
  * Based on arch/powerpc/oprofile/op_model_power4.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/oprofile.h>
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index 4b32e94..2ae6b86 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
  * Added mmcra[slot] support:
  * Copyright (C) 2006-2007 Will Schmidt <willschm@us.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/oprofile.h>
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c
index 6c0020d..19124b0 100644
--- a/arch/powerpc/perf/8xx-pmu.c
+++ b/arch/powerpc/perf/8xx-pmu.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance event support - PPC 8xx
  *
  * Copyright 2016 Christophe Leroy, CS Systemes d'Information
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -31,9 +27,6 @@
 
 extern unsigned long itlb_miss_counter, dtlb_miss_counter;
 extern atomic_t instruction_counter;
-extern unsigned int itlb_miss_perf, dtlb_miss_perf;
-extern unsigned int itlb_miss_exit_1, itlb_miss_exit_2;
-extern unsigned int dtlb_miss_exit_1, dtlb_miss_exit_2, dtlb_miss_exit_3;
 
 static atomic_t insn_ctr_ref;
 static atomic_t itlb_miss_ref;
@@ -103,22 +96,22 @@
 		break;
 	case PERF_8xx_ID_ITLB_LOAD_MISS:
 		if (atomic_inc_return(&itlb_miss_ref) == 1) {
-			unsigned long target = (unsigned long)&itlb_miss_perf;
+			unsigned long target = patch_site_addr(&patch__itlbmiss_perf);
 
-			patch_branch(&itlb_miss_exit_1, target, 0);
+			patch_branch_site(&patch__itlbmiss_exit_1, target, 0);
 #ifndef CONFIG_PIN_TLB_TEXT
-			patch_branch(&itlb_miss_exit_2, target, 0);
+			patch_branch_site(&patch__itlbmiss_exit_2, target, 0);
 #endif
 		}
 		val = itlb_miss_counter;
 		break;
 	case PERF_8xx_ID_DTLB_LOAD_MISS:
 		if (atomic_inc_return(&dtlb_miss_ref) == 1) {
-			unsigned long target = (unsigned long)&dtlb_miss_perf;
+			unsigned long target = patch_site_addr(&patch__dtlbmiss_perf);
 
-			patch_branch(&dtlb_miss_exit_1, target, 0);
-			patch_branch(&dtlb_miss_exit_2, target, 0);
-			patch_branch(&dtlb_miss_exit_3, target, 0);
+			patch_branch_site(&patch__dtlbmiss_exit_1, target, 0);
+			patch_branch_site(&patch__dtlbmiss_exit_2, target, 0);
+			patch_branch_site(&patch__dtlbmiss_exit_3, target, 0);
 		}
 		val = dtlb_miss_counter;
 		break;
@@ -180,17 +173,17 @@
 		break;
 	case PERF_8xx_ID_ITLB_LOAD_MISS:
 		if (atomic_dec_return(&itlb_miss_ref) == 0) {
-			patch_instruction(&itlb_miss_exit_1, insn);
+			patch_instruction_site(&patch__itlbmiss_exit_1, insn);
 #ifndef CONFIG_PIN_TLB_TEXT
-			patch_instruction(&itlb_miss_exit_2, insn);
+			patch_instruction_site(&patch__itlbmiss_exit_2, insn);
 #endif
 		}
 		break;
 	case PERF_8xx_ID_DTLB_LOAD_MISS:
 		if (atomic_dec_return(&dtlb_miss_ref) == 0) {
-			patch_instruction(&dtlb_miss_exit_1, insn);
-			patch_instruction(&dtlb_miss_exit_2, insn);
-			patch_instruction(&dtlb_miss_exit_3, insn);
+			patch_instruction_site(&patch__dtlbmiss_exit_1, insn);
+			patch_instruction_site(&patch__dtlbmiss_exit_2, insn);
+			patch_instruction_site(&patch__dtlbmiss_exit_3, insn);
 		}
 		break;
 	}
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index 82986d2..c155dcb 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -1,12 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 obj-$(CONFIG_PERF_EVENTS)	+= callchain.o perf_regs.o
 
 obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o bhrb.o
 obj64-$(CONFIG_PPC_PERF_CTRS)	+= ppc970-pmu.o power5-pmu.o \
 				   power5+-pmu.o power6-pmu.o power7-pmu.o \
-				   isa207-common.o power8-pmu.o power9-pmu.o
+				   isa207-common.o power8-pmu.o power9-pmu.o \
+				   generic-compat-pmu.o
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_PPC_POWERNV)	+= imc-pmu.o
diff --git a/arch/powerpc/perf/bhrb.S b/arch/powerpc/perf/bhrb.S
index d85f9a5..1aa3259 100644
--- a/arch/powerpc/perf/bhrb.S
+++ b/arch/powerpc/perf/bhrb.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Basic assembly code to read BHRB entries
  *
  * Copyright 2013 Anshuman Khandual, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc_asm.h>
 #include <asm/ppc-opcode.h>
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 0af051a..c84bbd4 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter callchain support - powerpc architecture code
  *
  * Copyright © 2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/sched.h>
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 81f8a0c..ca92e01 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1,15 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance event support - powerpc architecture code
  *
  * Copyright 2008-2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/clock.h>
 #include <linux/perf_event.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
@@ -21,6 +18,10 @@
 #include <asm/ptrace.h>
 #include <asm/code-patching.h>
 
+#ifdef CONFIG_PPC64
+#include "internal.h"
+#endif
+
 #define BHRB_MAX_ENTRIES	32
 #define BHRB_TARGET		0x0000000000000002
 #define BHRB_PREDICTION		0x0000000000000001
@@ -130,6 +131,14 @@
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
 
+bool is_sier_available(void)
+{
+	if (ppmu->flags & PPMU_HAS_SIER)
+		return true;
+
+	return false;
+}
+
 static bool regs_use_siar(struct pt_regs *regs)
 {
 	/*
@@ -864,6 +873,8 @@
 	int i, j;
 	unsigned long addf = ppmu->add_fields;
 	unsigned long tadd = ppmu->test_adder;
+	unsigned long grp_mask = ppmu->group_constraint_mask;
+	unsigned long grp_val = ppmu->group_constraint_val;
 
 	if (n_ev > ppmu->n_counter)
 		return -1;
@@ -884,15 +895,23 @@
 	for (i = 0; i < n_ev; ++i) {
 		nv = (value | cpuhw->avalues[i][0]) +
 			(value & cpuhw->avalues[i][0] & addf);
-		if ((((nv + tadd) ^ value) & mask) != 0 ||
-		    (((nv + tadd) ^ cpuhw->avalues[i][0]) &
-		     cpuhw->amasks[i][0]) != 0)
+
+		if (((((nv + tadd) ^ value) & mask) & (~grp_mask)) != 0)
 			break;
+
+		if (((((nv + tadd) ^ cpuhw->avalues[i][0]) & cpuhw->amasks[i][0])
+			& (~grp_mask)) != 0)
+			break;
+
 		value = nv;
 		mask |= cpuhw->amasks[i][0];
 	}
-	if (i == n_ev)
-		return 0;	/* all OK */
+	if (i == n_ev) {
+		if ((value & mask & grp_mask) != (mask & grp_val))
+			return -1;
+		else
+			return 0;	/* all OK */
+	}
 
 	/* doesn't work, gather alternatives... */
 	if (!ppmu->get_alternatives)
@@ -1827,6 +1846,7 @@
 	int n;
 	int err;
 	struct cpu_hw_events *cpuhw;
+	u64 bhrb_filter;
 
 	if (!ppmu)
 		return -ENOENT;
@@ -1932,13 +1952,14 @@
 	err = power_check_constraints(cpuhw, events, cflags, n + 1);
 
 	if (has_branch_stack(event)) {
-		cpuhw->bhrb_filter = ppmu->bhrb_filter_map(
+		bhrb_filter = ppmu->bhrb_filter_map(
 					event->attr.branch_sample_type);
 
-		if (cpuhw->bhrb_filter == -1) {
+		if (bhrb_filter == -1) {
 			put_cpu_var(cpu_hw_events);
 			return -EOPNOTSUPP;
 		}
+		cpuhw->bhrb_filter = bhrb_filter;
 	}
 
 	put_cpu_var(cpu_hw_events);
@@ -2148,7 +2169,7 @@
 /*
  * Performance monitor interrupt stuff
  */
-static void perf_event_interrupt(struct pt_regs *regs)
+static void __perf_event_interrupt(struct pt_regs *regs)
 {
 	int i, j;
 	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
@@ -2232,6 +2253,14 @@
 		irq_exit();
 }
 
+static void perf_event_interrupt(struct pt_regs *regs)
+{
+	u64 start_clock = sched_clock();
+
+	__perf_event_interrupt(regs);
+	perf_sample_event_took(sched_clock() - start_clock);
+}
+
 static int power_pmu_prepare_cpu(unsigned int cpu)
 {
 	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
@@ -2267,3 +2296,27 @@
 			  power_pmu_prepare_cpu, NULL);
 	return 0;
 }
+
+#ifdef CONFIG_PPC64
+static int __init init_ppc64_pmu(void)
+{
+	/* run through all the pmu drivers one at a time */
+	if (!init_power5_pmu())
+		return 0;
+	else if (!init_power5p_pmu())
+		return 0;
+	else if (!init_power6_pmu())
+		return 0;
+	else if (!init_power7_pmu())
+		return 0;
+	else if (!init_power8_pmu())
+		return 0;
+	else if (!init_power9_pmu())
+		return 0;
+	else if (!init_ppc970_pmu())
+		return 0;
+	else
+		return init_generic_compat_pmu();
+}
+early_initcall(init_ppc64_pmu);
+#endif
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index ba48584..e0e7e27 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance event support - Freescale Embedded Performance Monitor
  *
  * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
  * Copyright 2010 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/sched.h>
diff --git a/arch/powerpc/perf/e500-pmu.c b/arch/powerpc/perf/e500-pmu.c
index fb66492..a59c33b 100644
--- a/arch/powerpc/perf/e500-pmu.c
+++ b/arch/powerpc/perf/e500-pmu.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for e500 family processors.
  *
  * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
  * Copyright 2010 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/string.h>
 #include <linux/perf_event.h>
diff --git a/arch/powerpc/perf/e6500-pmu.c b/arch/powerpc/perf/e6500-pmu.c
index 3d877aa..44ad65d 100644
--- a/arch/powerpc/perf/e6500-pmu.c
+++ b/arch/powerpc/perf/e6500-pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for e6500 family processors.
  *
@@ -5,11 +6,6 @@
  * Based on e500-pmu.c
  * Copyright 2013 Freescale Semiconductor, Inc.
  * Copyright 2008-2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/string.h>
diff --git a/arch/powerpc/perf/generic-compat-pmu.c b/arch/powerpc/perf/generic-compat-pmu.c
new file mode 100644
index 0000000..5e5a54d
--- /dev/null
+++ b/arch/powerpc/perf/generic-compat-pmu.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2019 Madhavan Srinivasan, IBM Corporation.
+
+#define pr_fmt(fmt)	"generic-compat-pmu: " fmt
+
+#include "isa207-common.h"
+
+/*
+ * Raw event encoding:
+ *
+ *        60        56        52        48        44        40        36        32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *
+ *        28        24        20        16        12         8         4         0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ *                                 [ pmc ]   [unit ]   [ ]   m   [    pmcxsel    ]
+ *                                                     |     |
+ *                                                     |     *- mark
+ *                                                     |
+ *                                                     |
+ *                                                     *- combine
+ *
+ * Below uses IBM bit numbering.
+ *
+ * MMCR1[x:y] = unit    (PMCxUNIT)
+ * MMCR1[24]   = pmc1combine[0]
+ * MMCR1[25]   = pmc1combine[1]
+ * MMCR1[26]   = pmc2combine[0]
+ * MMCR1[27]   = pmc2combine[1]
+ * MMCR1[28]   = pmc3combine[0]
+ * MMCR1[29]   = pmc3combine[1]
+ * MMCR1[30]   = pmc4combine[0]
+ * MMCR1[31]   = pmc4combine[1]
+ *
+ */
+
+/*
+ * Some power9 event codes.
+ */
+#define EVENT(_name, _code)	_name = _code,
+
+enum {
+EVENT(PM_CYC,					0x0001e)
+EVENT(PM_INST_CMPL,				0x00002)
+};
+
+#undef EVENT
+
+GENERIC_EVENT_ATTR(cpu-cycles,			PM_CYC);
+GENERIC_EVENT_ATTR(instructions,		PM_INST_CMPL);
+
+static struct attribute *generic_compat_events_attr[] = {
+	GENERIC_EVENT_PTR(PM_CYC),
+	GENERIC_EVENT_PTR(PM_INST_CMPL),
+	NULL
+};
+
+static struct attribute_group generic_compat_pmu_events_group = {
+	.name = "events",
+	.attrs = generic_compat_events_attr,
+};
+
+PMU_FORMAT_ATTR(event,		"config:0-19");
+PMU_FORMAT_ATTR(pmcxsel,	"config:0-7");
+PMU_FORMAT_ATTR(mark,		"config:8");
+PMU_FORMAT_ATTR(combine,	"config:10-11");
+PMU_FORMAT_ATTR(unit,		"config:12-15");
+PMU_FORMAT_ATTR(pmc,		"config:16-19");
+
+static struct attribute *generic_compat_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_pmcxsel.attr,
+	&format_attr_mark.attr,
+	&format_attr_combine.attr,
+	&format_attr_unit.attr,
+	&format_attr_pmc.attr,
+	NULL,
+};
+
+static struct attribute_group generic_compat_pmu_format_group = {
+	.name = "format",
+	.attrs = generic_compat_pmu_format_attr,
+};
+
+static const struct attribute_group *generic_compat_pmu_attr_groups[] = {
+	&generic_compat_pmu_format_group,
+	&generic_compat_pmu_events_group,
+	NULL,
+};
+
+static int compat_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES] =			PM_CYC,
+	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_CMPL,
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int generic_compat_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[ C(L1D) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(L1I) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(LL) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+	},
+	[ C(DTLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(ITLB) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(BPU) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+	[ C(NODE) ] = {
+		[ C(OP_READ) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_WRITE) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+		[ C(OP_PREFETCH) ] = {
+			[ C(RESULT_ACCESS) ] = -1,
+			[ C(RESULT_MISS)   ] = -1,
+		},
+	},
+};
+
+#undef C
+
+static struct power_pmu generic_compat_pmu = {
+	.name			= "GENERIC_COMPAT",
+	.n_counter		= MAX_PMU_COUNTERS,
+	.add_fields		= ISA207_ADD_FIELDS,
+	.test_adder		= ISA207_TEST_ADDER,
+	.compute_mmcr		= isa207_compute_mmcr,
+	.get_constraint		= isa207_get_constraint,
+	.disable_pmc		= isa207_disable_pmc,
+	.flags			= PPMU_HAS_SIER | PPMU_ARCH_207S,
+	.n_generic		= ARRAY_SIZE(compat_generic_events),
+	.generic_events		= compat_generic_events,
+	.cache_events		= &generic_compat_cache_events,
+	.attr_groups		= generic_compat_pmu_attr_groups,
+};
+
+int init_generic_compat_pmu(void)
+{
+	int rc = 0;
+
+	rc = register_power_pmu(&generic_compat_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/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 72238ee..573e0b3 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Hypervisor supplied "24x7" performance counter support
  *
  * Author: Cody P Schafer <cody@linux.vnet.ibm.com>
  * Copyright 2014 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "hv-24x7: " fmt
@@ -571,7 +567,7 @@
 		struct event_uniq *it;
 		int result;
 
-		it = container_of(*new, struct event_uniq, node);
+		it = rb_entry(*new, struct event_uniq, node);
 		result = ev_uniq_ord(name, nl, domain, it->name, it->nl,
 					it->domain);
 
@@ -1306,15 +1302,6 @@
 		return -EINVAL;
 	}
 
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	/* no branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
@@ -1577,6 +1564,7 @@
 	.start_txn   = h_24x7_event_start_txn,
 	.commit_txn  = h_24x7_event_commit_txn,
 	.cancel_txn  = h_24x7_event_cancel_txn,
+	.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static int hv_24x7_init(void)
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 43fabb3..6884d16 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Hypervisor supplied "gpci" ("get performance counter info") performance
  * counter support
  *
  * Author: Cody P Schafer <cody@linux.vnet.ibm.com>
  * Copyright 2014 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "hv-gpci: " fmt
@@ -232,15 +228,6 @@
 		return -EINVAL;
 	}
 
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	/* no branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
@@ -285,6 +272,7 @@
 	.start       = h_gpci_event_start,
 	.stop        = h_gpci_event_stop,
 	.read        = h_gpci_event_update,
+	.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 };
 
 static int hv_gpci_init(void)
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 1fafc32..cb50a9e 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * In-Memory Collection (IMC) Performance Monitor counter support.
  *
  * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation.
  *           (C) 2017 Anju T Sudhakar, IBM Corporation.
  *           (C) 2017 Hemant K Shaw, IBM 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; either version
- * 2 of the License, or later version.
  */
 #include <linux/perf_event.h>
 #include <linux/slab.h>
@@ -28,13 +24,13 @@
 static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc);
 static struct imc_pmu **per_nest_pmu_arr;
 static cpumask_t nest_imc_cpumask;
-struct imc_pmu_ref *nest_imc_refc;
+static struct imc_pmu_ref *nest_imc_refc;
 static int nest_pmus;
 
 /* Core IMC data structures and variables */
 
 static cpumask_t core_imc_cpumask;
-struct imc_pmu_ref *core_imc_refc;
+static struct imc_pmu_ref *core_imc_refc;
 static struct imc_pmu *core_imc_pmu;
 
 /* Thread IMC data structures and variables */
@@ -43,12 +39,17 @@
 static struct imc_pmu *thread_imc_pmu;
 static int thread_imc_mem_size;
 
-struct imc_pmu *imc_event_to_pmu(struct perf_event *event)
+/* Trace IMC data structures */
+static DEFINE_PER_CPU(u64 *, trace_imc_mem);
+static struct imc_pmu_ref *trace_imc_refc;
+static int trace_imc_mem_size;
+
+static struct imc_pmu *imc_event_to_pmu(struct perf_event *event)
 {
 	return container_of(event->pmu, struct imc_pmu, pmu);
 }
 
-PMU_FORMAT_ATTR(event, "config:0-40");
+PMU_FORMAT_ATTR(event, "config:0-61");
 PMU_FORMAT_ATTR(offset, "config:0-31");
 PMU_FORMAT_ATTR(rvalue, "config:32");
 PMU_FORMAT_ATTR(mode, "config:33-40");
@@ -65,6 +66,25 @@
 	.attrs = imc_format_attrs,
 };
 
+/* Format attribute for imc trace-mode */
+PMU_FORMAT_ATTR(cpmc_reserved, "config:0-19");
+PMU_FORMAT_ATTR(cpmc_event, "config:20-27");
+PMU_FORMAT_ATTR(cpmc_samplesel, "config:28-29");
+PMU_FORMAT_ATTR(cpmc_load, "config:30-61");
+static struct attribute *trace_imc_format_attrs[] = {
+	&format_attr_event.attr,
+	&format_attr_cpmc_reserved.attr,
+	&format_attr_cpmc_event.attr,
+	&format_attr_cpmc_samplesel.attr,
+	&format_attr_cpmc_load.attr,
+	NULL,
+};
+
+static struct attribute_group trace_imc_format_group = {
+.name = "format",
+.attrs = trace_imc_format_attrs,
+};
+
 /* Get the cpumask printed to a buffer "buf" */
 static ssize_t imc_pmu_cpumask_get_attr(struct device *dev,
 					struct device_attribute *attr,
@@ -342,7 +362,14 @@
 	 */
 	nid = cpu_to_node(cpu);
 	l_cpumask = cpumask_of_node(nid);
-	target = cpumask_any_but(l_cpumask, cpu);
+	target = cpumask_last(l_cpumask);
+
+	/*
+	 * If this(target) is the last cpu in the cpumask for this chip,
+	 * check for any possible online cpu in the chip.
+	 */
+	if (unlikely(target == cpu))
+		target = cpumask_any_but(l_cpumask, cpu);
 
 	/*
 	 * Update the cpumask with the target cpu and
@@ -473,15 +500,6 @@
 	if (event->hw.sample_period)
 		return -EINVAL;
 
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -496,6 +514,11 @@
 	 * Get the base memory addresss for this cpu.
 	 */
 	chip_id = cpu_to_chip_id(event->cpu);
+
+	/* Return, if chip_id is not valid */
+	if (chip_id < 0)
+		return -ENODEV;
+
 	pcni = pmu->mem_info;
 	do {
 		if (pcni->id == chip_id) {
@@ -503,7 +526,7 @@
 			break;
 		}
 		pcni++;
-	} while (pcni);
+	} while (pcni->vbase != 0);
 
 	if (!flag)
 		return -ENODEV;
@@ -554,6 +577,7 @@
 {
 	int nid, rc = 0, core_id = (cpu / threads_per_core);
 	struct imc_mem_info *mem_info;
+	struct page *page;
 
 	/*
 	 * alloc_pages_node() will allocate memory for core in the
@@ -564,11 +588,12 @@
 	mem_info->id = core_id;
 
 	/* We need only vbase for core counters */
-	mem_info->vbase = page_address(alloc_pages_node(nid,
-					  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
-					  __GFP_NOWARN, get_order(size)));
-	if (!mem_info->vbase)
+	page = alloc_pages_node(nid,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
+				__GFP_NOWARN, get_order(size));
+	if (!page)
 		return -ENOMEM;
+	mem_info->vbase = page_address(page);
 
 	/* Init the mutex */
 	core_imc_refc[core_id].id = core_id;
@@ -651,7 +676,10 @@
 		return 0;
 
 	/* Find any online cpu in that core except the current "cpu" */
-	ncpu = cpumask_any_but(cpu_sibling_mask(cpu), cpu);
+	ncpu = cpumask_last(cpu_sibling_mask(cpu));
+
+	if (unlikely(ncpu == cpu))
+		ncpu = cpumask_any_but(cpu_sibling_mask(cpu), cpu);
 
 	if (ncpu >= 0 && ncpu < nr_cpu_ids) {
 		cpumask_set_cpu(ncpu, &core_imc_cpumask);
@@ -748,15 +776,6 @@
 	if (event->hw.sample_period)
 		return -EINVAL;
 
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -806,8 +825,11 @@
 }
 
 /*
- * Allocates a page of memory for each of the online cpus, and write the
- * physical base address of that page to the LDBAR for that cpu.
+ * Allocates a page of memory for each of the online cpus, and load
+ * LDBAR with 0.
+ * The physical base address of the page allocated for a cpu will be
+ * written to the LDBAR for that cpu, when the thread-imc event
+ * is added.
  *
  * LDBAR Register Layout:
  *
@@ -825,26 +847,26 @@
  */
 static int thread_imc_mem_alloc(int cpu_id, int size)
 {
-	u64 ldbar_value, *local_mem = per_cpu(thread_imc_mem, cpu_id);
+	u64 *local_mem = per_cpu(thread_imc_mem, cpu_id);
 	int nid = cpu_to_node(cpu_id);
 
 	if (!local_mem) {
+		struct page *page;
 		/*
 		 * This case could happen only once at start, since we dont
 		 * free the memory in cpu offline path.
 		 */
-		local_mem = page_address(alloc_pages_node(nid,
+		page = alloc_pages_node(nid,
 				  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
-				  __GFP_NOWARN, get_order(size)));
-		if (!local_mem)
+				  __GFP_NOWARN, get_order(size));
+		if (!page)
 			return -ENOMEM;
+		local_mem = page_address(page);
 
 		per_cpu(thread_imc_mem, cpu_id) = local_mem;
 	}
 
-	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | THREAD_IMC_ENABLE;
-
-	mtspr(SPRN_LDBAR, ldbar_value);
+	mtspr(SPRN_LDBAR, 0);
 	return 0;
 }
 
@@ -876,6 +898,9 @@
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	/* Sampling not supported */
 	if (event->hw.sample_period)
 		return -EINVAL;
@@ -995,6 +1020,7 @@
 {
 	int core_id;
 	struct imc_pmu_ref *ref;
+	u64 ldbar_value, *local_mem = per_cpu(thread_imc_mem, smp_processor_id());
 
 	if (flags & PERF_EF_START)
 		imc_event_start(event, flags);
@@ -1003,6 +1029,9 @@
 		return -EINVAL;
 
 	core_id = smp_processor_id() / threads_per_core;
+	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | THREAD_IMC_ENABLE;
+	mtspr(SPRN_LDBAR, ldbar_value);
+
 	/*
 	 * imc pmus are enabled only when it is used.
 	 * See if this is triggered for the first time.
@@ -1034,11 +1063,7 @@
 	int core_id;
 	struct imc_pmu_ref *ref;
 
-	/*
-	 * Take a snapshot and calculate the delta and update
-	 * the event counter values.
-	 */
-	imc_event_update(event);
+	mtspr(SPRN_LDBAR, 0);
 
 	core_id = smp_processor_id() / threads_per_core;
 	ref = &core_imc_refc[core_id];
@@ -1057,6 +1082,243 @@
 		ref->refc = 0;
 	}
 	mutex_unlock(&ref->lock);
+	/*
+	 * Take a snapshot and calculate the delta and update
+	 * the event counter values.
+	 */
+	imc_event_update(event);
+}
+
+/*
+ * Allocate a page of memory for each cpu, and load LDBAR with 0.
+ */
+static int trace_imc_mem_alloc(int cpu_id, int size)
+{
+	u64 *local_mem = per_cpu(trace_imc_mem, cpu_id);
+	int phys_id = cpu_to_node(cpu_id), rc = 0;
+	int core_id = (cpu_id / threads_per_core);
+
+	if (!local_mem) {
+		struct page *page;
+
+		page = alloc_pages_node(phys_id,
+				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
+				__GFP_NOWARN, get_order(size));
+		if (!page)
+			return -ENOMEM;
+		local_mem = page_address(page);
+		per_cpu(trace_imc_mem, cpu_id) = local_mem;
+
+		/* Initialise the counters for trace mode */
+		rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_TRACE, __pa((void *)local_mem),
+					    get_hard_smp_processor_id(cpu_id));
+		if (rc) {
+			pr_info("IMC:opal init failed for trace imc\n");
+			return rc;
+		}
+	}
+
+	/* Init the mutex, if not already */
+	trace_imc_refc[core_id].id = core_id;
+	mutex_init(&trace_imc_refc[core_id].lock);
+
+	mtspr(SPRN_LDBAR, 0);
+	return 0;
+}
+
+static int ppc_trace_imc_cpu_online(unsigned int cpu)
+{
+	return trace_imc_mem_alloc(cpu, trace_imc_mem_size);
+}
+
+static int ppc_trace_imc_cpu_offline(unsigned int cpu)
+{
+	mtspr(SPRN_LDBAR, 0);
+	return 0;
+}
+
+static int trace_imc_cpu_init(void)
+{
+	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE,
+			  "perf/powerpc/imc_trace:online",
+			  ppc_trace_imc_cpu_online,
+			  ppc_trace_imc_cpu_offline);
+}
+
+static u64 get_trace_imc_event_base_addr(void)
+{
+	return (u64)per_cpu(trace_imc_mem, smp_processor_id());
+}
+
+/*
+ * Function to parse trace-imc data obtained
+ * and to prepare the perf sample.
+ */
+static int trace_imc_prepare_sample(struct trace_imc_data *mem,
+				    struct perf_sample_data *data,
+				    u64 *prev_tb,
+				    struct perf_event_header *header,
+				    struct perf_event *event)
+{
+	/* Sanity checks for a valid record */
+	if (be64_to_cpu(READ_ONCE(mem->tb1)) > *prev_tb)
+		*prev_tb = be64_to_cpu(READ_ONCE(mem->tb1));
+	else
+		return -EINVAL;
+
+	if ((be64_to_cpu(READ_ONCE(mem->tb1)) & IMC_TRACE_RECORD_TB1_MASK) !=
+			 be64_to_cpu(READ_ONCE(mem->tb2)))
+		return -EINVAL;
+
+	/* Prepare perf sample */
+	data->ip =  be64_to_cpu(READ_ONCE(mem->ip));
+	data->period = event->hw.last_period;
+
+	header->type = PERF_RECORD_SAMPLE;
+	header->size = sizeof(*header) + event->header_size;
+	header->misc = 0;
+
+	if (is_kernel_addr(data->ip))
+		header->misc |= PERF_RECORD_MISC_KERNEL;
+	else
+		header->misc |= PERF_RECORD_MISC_USER;
+
+	perf_event_header__init_id(header, data, event);
+
+	return 0;
+}
+
+static void dump_trace_imc_data(struct perf_event *event)
+{
+	struct trace_imc_data *mem;
+	int i, ret;
+	u64 prev_tb = 0;
+
+	mem = (struct trace_imc_data *)get_trace_imc_event_base_addr();
+	for (i = 0; i < (trace_imc_mem_size / sizeof(struct trace_imc_data));
+		i++, mem++) {
+		struct perf_sample_data data;
+		struct perf_event_header header;
+
+		ret = trace_imc_prepare_sample(mem, &data, &prev_tb, &header, event);
+		if (ret) /* Exit, if not a valid record */
+			break;
+		else {
+			/* If this is a valid record, create the sample */
+			struct perf_output_handle handle;
+
+			if (perf_output_begin(&handle, event, header.size))
+				return;
+
+			perf_output_sample(&handle, &header, &data, event);
+			perf_output_end(&handle);
+		}
+	}
+}
+
+static int trace_imc_event_add(struct perf_event *event, int flags)
+{
+	int core_id = smp_processor_id() / threads_per_core;
+	struct imc_pmu_ref *ref = NULL;
+	u64 local_mem, ldbar_value;
+
+	/* Set trace-imc bit in ldbar and load ldbar with per-thread memory address */
+	local_mem = get_trace_imc_event_base_addr();
+	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | TRACE_IMC_ENABLE;
+
+	if (core_imc_refc)
+		ref = &core_imc_refc[core_id];
+	if (!ref) {
+		/* If core-imc is not enabled, use trace-imc reference count */
+		if (trace_imc_refc)
+			ref = &trace_imc_refc[core_id];
+		if (!ref)
+			return -EINVAL;
+	}
+	mtspr(SPRN_LDBAR, ldbar_value);
+	mutex_lock(&ref->lock);
+	if (ref->refc == 0) {
+		if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE,
+				get_hard_smp_processor_id(smp_processor_id()))) {
+			mutex_unlock(&ref->lock);
+			pr_err("trace-imc: Unable to start the counters for core %d\n", core_id);
+			mtspr(SPRN_LDBAR, 0);
+			return -EINVAL;
+		}
+	}
+	++ref->refc;
+	mutex_unlock(&ref->lock);
+
+	return 0;
+}
+
+static void trace_imc_event_read(struct perf_event *event)
+{
+	return;
+}
+
+static void trace_imc_event_stop(struct perf_event *event, int flags)
+{
+	u64 local_mem = get_trace_imc_event_base_addr();
+	dump_trace_imc_data(event);
+	memset((void *)local_mem, 0, sizeof(u64));
+}
+
+static void trace_imc_event_start(struct perf_event *event, int flags)
+{
+	return;
+}
+
+static void trace_imc_event_del(struct perf_event *event, int flags)
+{
+	int core_id = smp_processor_id() / threads_per_core;
+	struct imc_pmu_ref *ref = NULL;
+
+	if (core_imc_refc)
+		ref = &core_imc_refc[core_id];
+	if (!ref) {
+		/* If core-imc is not enabled, use trace-imc reference count */
+		if (trace_imc_refc)
+			ref = &trace_imc_refc[core_id];
+		if (!ref)
+			return;
+	}
+	mtspr(SPRN_LDBAR, 0);
+	mutex_lock(&ref->lock);
+	ref->refc--;
+	if (ref->refc == 0) {
+		if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE,
+				get_hard_smp_processor_id(smp_processor_id()))) {
+			mutex_unlock(&ref->lock);
+			pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id);
+			return;
+		}
+	} else if (ref->refc < 0) {
+		ref->refc = 0;
+	}
+	mutex_unlock(&ref->lock);
+	trace_imc_event_stop(event, flags);
+}
+
+static int trace_imc_event_init(struct perf_event *event)
+{
+	struct task_struct *target;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	/* Return if this is a couting event */
+	if (event->attr.sample_period == 0)
+		return -ENOENT;
+
+	event->hw.idx = -1;
+	target = event->hw.target;
+
+	event->pmu->task_ctx_nr = perf_hw_context;
+	return 0;
 }
 
 /* update_pmu_ops : Populate the appropriate operations for "pmu" */
@@ -1069,6 +1331,7 @@
 	pmu->pmu.stop = imc_event_stop;
 	pmu->pmu.read = imc_event_update;
 	pmu->pmu.attr_groups = pmu->attr_groups;
+	pmu->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE;
 	pmu->attr_groups[IMC_FORMAT_ATTR] = &imc_format_group;
 
 	switch (pmu->domain) {
@@ -1088,6 +1351,14 @@
 		pmu->pmu.cancel_txn = thread_imc_pmu_cancel_txn;
 		pmu->pmu.commit_txn = thread_imc_pmu_commit_txn;
 		break;
+	case IMC_DOMAIN_TRACE:
+		pmu->pmu.event_init = trace_imc_event_init;
+		pmu->pmu.add = trace_imc_event_add;
+		pmu->pmu.del = trace_imc_event_del;
+		pmu->pmu.start = trace_imc_event_start;
+		pmu->pmu.stop = trace_imc_event_stop;
+		pmu->pmu.read = trace_imc_event_read;
+		pmu->attr_groups[IMC_FORMAT_ATTR] = &trace_imc_format_group;
 	default:
 		break;
 	}
@@ -1180,6 +1451,18 @@
 	}
 }
 
+static void cleanup_all_trace_imc_memory(void)
+{
+	int i, order = get_order(trace_imc_mem_size);
+
+	for_each_online_cpu(i) {
+		if (per_cpu(trace_imc_mem, i))
+			free_pages((u64)per_cpu(trace_imc_mem, i), order);
+
+	}
+	kfree(trace_imc_refc);
+}
+
 /* Function to free the attr_groups which are dynamically allocated */
 static void imc_common_mem_free(struct imc_pmu *pmu_ptr)
 {
@@ -1221,6 +1504,11 @@
 		cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE);
 		cleanup_all_thread_imc_memory();
 	}
+
+	if (pmu_ptr->domain == IMC_DOMAIN_TRACE) {
+		cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE);
+		cleanup_all_trace_imc_memory();
+	}
 }
 
 /*
@@ -1303,6 +1591,27 @@
 
 		thread_imc_pmu = pmu_ptr;
 		break;
+	case IMC_DOMAIN_TRACE:
+		/* Update the pmu name */
+		pmu_ptr->pmu.name = kasprintf(GFP_KERNEL, "%s%s", s, "_imc");
+		if (!pmu_ptr->pmu.name)
+			return -ENOMEM;
+
+		nr_cores = DIV_ROUND_UP(num_possible_cpus(), threads_per_core);
+		trace_imc_refc = kcalloc(nr_cores, sizeof(struct imc_pmu_ref),
+								GFP_KERNEL);
+		if (!trace_imc_refc)
+			return -ENOMEM;
+
+		trace_imc_mem_size = pmu_ptr->counter_mem_size;
+		for_each_online_cpu(cpu) {
+			res = trace_imc_mem_alloc(cpu, trace_imc_mem_size);
+			if (res) {
+				cleanup_all_trace_imc_memory();
+				goto err;
+			}
+		}
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1376,6 +1685,14 @@
 		}
 
 		break;
+	case IMC_DOMAIN_TRACE:
+		ret = trace_imc_cpu_init();
+		if (ret) {
+			cleanup_all_trace_imc_memory();
+			goto err_free_mem;
+		}
+
+		break;
 	default:
 		return  -EINVAL;	/* Unknown domain */
 	}
@@ -1392,7 +1709,7 @@
 	if (ret)
 		goto err_free_cpuhp_mem;
 
-	pr_info("%s performance monitor hardware support registered\n",
+	pr_debug("%s performance monitor hardware support registered\n",
 							pmu_ptr->pmu.name);
 
 	return 0;
diff --git a/arch/powerpc/perf/internal.h b/arch/powerpc/perf/internal.h
new file mode 100644
index 0000000..f755c64
--- /dev/null
+++ b/arch/powerpc/perf/internal.h
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2019 Madhavan Srinivasan, IBM Corporation.
+
+extern int init_ppc970_pmu(void);
+extern int init_power5_pmu(void);
+extern int init_power5p_pmu(void);
+extern int init_power6_pmu(void);
+extern int init_power7_pmu(void);
+extern int init_power8_pmu(void);
+extern int init_power9_pmu(void);
+extern int init_generic_compat_pmu(void);
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 177de81..4c86da5 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Common Performance counter support functions for PowerISA v2.07 processors.
  *
  * Copyright 2009 Paul Mackerras, IBM Corporation.
  * Copyright 2013 Michael Ellerman, IBM Corporation.
  * Copyright 2016 Madhavan Srinivasan, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include "isa207-common.h"
 
@@ -148,6 +144,14 @@
 	return true;
 }
 
+static unsigned int dc_ic_rld_quad_l1_sel(u64 event)
+{
+	unsigned int cache;
+
+	cache = (event >> EVENT_CACHE_SEL_SHIFT) & MMCR1_DC_IC_QUAL_MASK;
+	return cache;
+}
+
 static inline u64 isa207_find_source(u64 idx, u32 sub_idx)
 {
 	u64 ret = PERF_MEM_NA;
@@ -226,8 +230,13 @@
 	u64 mmcra = mfspr(SPRN_MMCRA);
 	u64 exp = MMCRA_THR_CTR_EXP(mmcra);
 	u64 mantissa = MMCRA_THR_CTR_MANT(mmcra);
+	u64 sier = mfspr(SPRN_SIER);
+	u64 val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT;
 
-	*weight = mantissa << (2 * exp);
+	if (val == 0 || val == 7)
+		*weight = 0;
+	else
+		*weight = mantissa << (2 * exp);
 }
 
 int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
@@ -274,19 +283,27 @@
 	}
 
 	if (unit >= 6 && unit <= 9) {
-		/*
-		 * L2/L3 events contain a cache selector field, which is
-		 * supposed to be programmed into MMCRC. However MMCRC is only
-		 * HV writable, and there is no API for guest kernels to modify
-		 * it. The solution is for the hypervisor to initialise the
-		 * field to zeroes, and for us to only ever allow events that
-		 * have a cache selector of zero. The bank selector (bit 3) is
-		 * irrelevant, as long as the rest of the value is 0.
-		 */
-		if (cache & 0x7)
-			return -1;
+		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+			mask  |= CNST_CACHE_GROUP_MASK;
+			value |= CNST_CACHE_GROUP_VAL(event & 0xff);
 
-	} else if (event & EVENT_IS_L1) {
+			mask |= CNST_CACHE_PMC4_MASK;
+			if (pmc == 4)
+				value |= CNST_CACHE_PMC4_VAL;
+		} else if (cache & 0x7) {
+			/*
+			 * L2/L3 events contain a cache selector field, which is
+			 * supposed to be programmed into MMCRC. However MMCRC is only
+			 * HV writable, and there is no API for guest kernels to modify
+			 * it. The solution is for the hypervisor to initialise the
+			 * field to zeroes, and for us to only ever allow events that
+			 * have a cache selector of zero. The bank selector (bit 3) is
+			 * irrelevant, as long as the rest of the value is 0.
+			 */
+			return -1;
+		}
+
+	} else if (cpu_has_feature(CPU_FTR_ARCH_300) || (event & EVENT_IS_L1)) {
 		mask  |= CNST_L1_QUAL_MASK;
 		value |= CNST_L1_QUAL_VAL(cache);
 	}
@@ -389,11 +406,14 @@
 		/* In continuous sampling mode, update SDAR on TLB miss */
 		mmcra_sdar_mode(event[i], &mmcra);
 
-		if (event[i] & EVENT_IS_L1) {
-			cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
-			mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT;
-			cache >>= 1;
-			mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
+		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+			cache = dc_ic_rld_quad_l1_sel(event[i]);
+			mmcr1 |= (cache) << MMCR1_DC_IC_QUAL_SHIFT;
+		} else {
+			if (event[i] & EVENT_IS_L1) {
+				cache = dc_ic_rld_quad_l1_sel(event[i]);
+				mmcr1 |= (cache) << MMCR1_DC_IC_QUAL_SHIFT;
+			}
 		}
 
 		if (is_event_marked(event[i])) {
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 0028f4b..63fd4f3 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2009 Paul Mackerras, IBM Corporation.
  * Copyright 2013 Michael Ellerman, IBM Corporation.
  * Copyright 2016 Madhavan Srinivasan, IBM 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; either version
- * 2 of the License, or any later version.
  */
 
 #ifndef _LINUX_POWERPC_PERF_ISA207_COMMON_H_
@@ -134,6 +130,11 @@
 #define CNST_SAMPLE_VAL(v)	(((v) & EVENT_SAMPLE_MASK) << 16)
 #define CNST_SAMPLE_MASK	CNST_SAMPLE_VAL(EVENT_SAMPLE_MASK)
 
+#define CNST_CACHE_GROUP_VAL(v)	(((v) & 0xffull) << 55)
+#define CNST_CACHE_GROUP_MASK	CNST_CACHE_GROUP_VAL(0xff)
+#define CNST_CACHE_PMC4_VAL	(1ull << 54)
+#define CNST_CACHE_PMC4_MASK	CNST_CACHE_PMC4_VAL
+
 /*
  * For NC we are counting up to 4 events. This requires three bits, and we need
  * the fifth event to overflow and set the 4th bit. To achieve that we bias the
@@ -163,8 +164,8 @@
 #define MMCR1_COMBINE_SHIFT(pmc)	(35 - ((pmc) - 1))
 #define MMCR1_PMCSEL_SHIFT(pmc)		(24 - (((pmc) - 1)) * 8)
 #define MMCR1_FAB_SHIFT			36
-#define MMCR1_DC_QUAL_SHIFT		47
-#define MMCR1_IC_QUAL_SHIFT		46
+#define MMCR1_DC_IC_QUAL_MASK		0x3
+#define MMCR1_DC_IC_QUAL_SHIFT		46
 
 /* MMCR1 Combine bits macro for power9 */
 #define p9_MMCR1_COMBINE_SHIFT(pmc)	(38 - ((pmc - 1) * 2))
diff --git a/arch/powerpc/perf/mpc7450-pmu.c b/arch/powerpc/perf/mpc7450-pmu.c
index d115c56..4d5ef92 100644
--- a/arch/powerpc/perf/mpc7450-pmu.c
+++ b/arch/powerpc/perf/mpc7450-pmu.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for MPC7450-family processors.
  *
  * Copyright 2008-2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/string.h>
 #include <linux/perf_event.h>
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index 09ceea6..a213a0a 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2016 Anju T, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/errno.h>
@@ -69,6 +65,8 @@
 	PT_REGS_OFFSET(PERF_REG_POWERPC_TRAP, trap),
 	PT_REGS_OFFSET(PERF_REG_POWERPC_DAR, dar),
 	PT_REGS_OFFSET(PERF_REG_POWERPC_DSISR, dsisr),
+	PT_REGS_OFFSET(PERF_REG_POWERPC_SIER, dar),
+	PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr),
 };
 
 u64 perf_reg_value(struct pt_regs *regs, int idx)
@@ -76,6 +74,17 @@
 	if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX))
 		return 0;
 
+	if (idx == PERF_REG_POWERPC_SIER &&
+	   (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) ||
+	    IS_ENABLED(CONFIG_PPC32) ||
+	    !is_sier_available()))
+		return 0;
+
+	if (idx == PERF_REG_POWERPC_MMCRA &&
+	   (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) ||
+	    IS_ENABLED(CONFIG_PPC32)))
+		return 0;
+
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c
index 0526dac..f857454 100644
--- a/arch/powerpc/perf/power5+-pmu.c
+++ b/arch/powerpc/perf/power5+-pmu.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for POWER5+/++ (not POWER5) processors.
  *
  * Copyright 2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
@@ -677,7 +673,7 @@
 	.cache_events		= &power5p_cache_events,
 };
 
-static int __init init_power5p_pmu(void)
+int init_power5p_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+")
@@ -686,5 +682,3 @@
 
 	return register_power_pmu(&power5p_pmu);
 }
-
-early_initcall(init_power5p_pmu);
diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c
index 4dc99f9..da52eca 100644
--- a/arch/powerpc/perf/power5-pmu.c
+++ b/arch/powerpc/perf/power5-pmu.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for POWER5 (not POWER5++) processors.
  *
  * Copyright 2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
@@ -618,7 +614,7 @@
 	.flags			= PPMU_HAS_SSLOT,
 };
 
-static int __init init_power5_pmu(void)
+int init_power5_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5"))
@@ -626,5 +622,3 @@
 
 	return register_power_pmu(&power5_pmu);
 }
-
-early_initcall(init_power5_pmu);
diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c
index 9c9d646..3929cac 100644
--- a/arch/powerpc/perf/power6-pmu.c
+++ b/arch/powerpc/perf/power6-pmu.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for POWER6 processors.
  *
  * Copyright 2008-2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
@@ -540,7 +536,7 @@
 	.cache_events		= &power6_cache_events,
 };
 
-static int __init init_power6_pmu(void)
+int init_power6_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6"))
@@ -548,5 +544,3 @@
 
 	return register_power_pmu(&power6_pmu);
 }
-
-early_initcall(init_power6_pmu);
diff --git a/arch/powerpc/perf/power7-events-list.h b/arch/powerpc/perf/power7-events-list.h
index 64f13d9..6c2b706 100644
--- a/arch/powerpc/perf/power7-events-list.h
+++ b/arch/powerpc/perf/power7-events-list.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Performance counter support for POWER7 processors.
  *
  * Copyright 2013 Runzhen Wang, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 EVENT(PM_IC_DEMAND_L2_BR_ALL,                 0x04898)
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 7963658..a137813 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for POWER7 processors.
  *
  * Copyright 2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
@@ -238,6 +234,7 @@
 	case 6:
 		if (psel == 0x64)
 			return pmc >= 3;
+		break;
 	case 8:
 		return unit == 0xd;
 	}
@@ -444,7 +441,7 @@
 	.cache_events		= &power7_cache_events,
 };
 
-static int __init init_power7_pmu(void)
+int init_power7_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7"))
@@ -455,5 +452,3 @@
 
 	return register_power_pmu(&power7_pmu);
 }
-
-early_initcall(init_power7_pmu);
diff --git a/arch/powerpc/perf/power8-events-list.h b/arch/powerpc/perf/power8-events-list.h
index 0f1d184..2e9b75d 100644
--- a/arch/powerpc/perf/power8-events-list.h
+++ b/arch/powerpc/perf/power8-events-list.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Performance counter support for POWER8 processors.
  *
  * Copyright 2014 Sukadev Bhattiprolu, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /*
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index d12a2db..3a5fcc2 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for POWER8 processors.
  *
  * Copyright 2009 Paul Mackerras, IBM Corporation.
  * Copyright 2013 Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)	"power8-pmu: " fmt
@@ -29,6 +25,7 @@
 #define	POWER8_MMCRA_IFM1		0x0000000040000000UL
 #define	POWER8_MMCRA_IFM2		0x0000000080000000UL
 #define	POWER8_MMCRA_IFM3		0x00000000C0000000UL
+#define	POWER8_MMCRA_BHRB_MASK		0x00000000C0000000UL
 
 /*
  * Raw event encoding for PowerISA v2.07 (Power8):
@@ -243,6 +240,8 @@
 
 static void power8_config_bhrb(u64 pmu_bhrb_filter)
 {
+	pmu_bhrb_filter &= POWER8_MMCRA_BHRB_MASK;
+
 	/* Enable BHRB filter in PMU */
 	mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
 }
@@ -379,7 +378,7 @@
 	.bhrb_nr		= 32,
 };
 
-static int __init init_power8_pmu(void)
+int init_power8_pmu(void)
 {
 	int rc;
 
@@ -399,4 +398,3 @@
 
 	return 0;
 }
-early_initcall(init_power8_pmu);
diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h
index 7de344b..7f4e6b5 100644
--- a/arch/powerpc/perf/power9-events-list.h
+++ b/arch/powerpc/perf/power9-events-list.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Performance counter support for POWER9 processors.
  *
  * Copyright 2016 Madhavan Srinivasan, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /*
@@ -63,8 +59,6 @@
 /* Instruction Dispatched */
 EVENT(PM_INST_DISP,				0x200f2)
 EVENT(PM_INST_DISP_ALT,				0x300f2)
-/* Alternate Branch event code */
-EVENT(PM_BR_CMPL_ALT,				0x10012)
 /* Branch event that are not strongly biased */
 EVENT(PM_BR_2PATH,				0x20036)
 /* ALternate branch event that are not strongly biased */
@@ -97,3 +91,27 @@
 EVENT(PM_DTLB_MISS_16M,				0x4c056)
 EVENT(PM_DTLB_MISS_1G,				0x4c05a)
 EVENT(PM_MRK_DTLB_MISS_16M,			0x4c15e)
+
+/*
+ * Memory Access Events
+ *
+ * Primary PMU event used here is PM_MRK_INST_CMPL (0x401e0)
+ * To enable capturing of memory profiling, these MMCRA bits
+ * needs to be programmed and corresponding raw event format
+ * encoding.
+ *
+ * MMCRA bits encoding needed are
+ *     SM (Sampling Mode)
+ *     EM (Eligibility for Random Sampling)
+ *     TECE (Threshold Event Counter Event)
+ *     TS (Threshold Start Event)
+ *     TE (Threshold End Event)
+ *
+ * Corresponding Raw Encoding bits:
+ *     sample [EM,SM]
+ *     thresh_sel (TECE)
+ *     thresh start (TS)
+ *     thresh end (TE)
+ */
+EVENT(MEM_LOADS,				0x34340401e0)
+EVENT(MEM_STORES,				0x343c0401e0)
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index e012b10..08c3ef7 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for POWER9 processors.
  *
  * Copyright 2009 Paul Mackerras, IBM Corporation.
  * Copyright 2013 Michael Ellerman, IBM Corporation.
  * Copyright 2016 Madhavan Srinivasan, IBM 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; either version
- * 2 of the License, or later version.
  */
 
 #define pr_fmt(fmt)	"power9-pmu: " fmt
@@ -63,16 +59,8 @@
  *	MMCRA[9:11] = thresh_cmp[0:2]
  *	MMCRA[12:18] = thresh_cmp[3:9]
  *
- * if unit == 6 or unit == 7
- *	MMCRC[53:55] = cache_sel[1:3]      (L2EVENT_SEL)
- * else if unit == 8 or unit == 9:
- *	if cache_sel[0] == 0: # L3 bank
- *		MMCRC[47:49] = cache_sel[1:3]  (L3EVENT_SEL0)
- *	else if cache_sel[0] == 1:
- *		MMCRC[50:51] = cache_sel[2:3]  (L3EVENT_SEL1)
- * else if cache_sel[1]: # L1 event
- *	MMCR1[16] = cache_sel[2]
- *	MMCR1[17] = cache_sel[3]
+ * MMCR1[16] = cache_sel[2]
+ * MMCR1[17] = cache_sel[3]
  *
  * if mark:
  *	MMCRA[63]    = 1		(SAMPLE_ENABLE)
@@ -100,6 +88,7 @@
 #define POWER9_MMCRA_IFM1		0x0000000040000000UL
 #define POWER9_MMCRA_IFM2		0x0000000080000000UL
 #define POWER9_MMCRA_IFM3		0x00000000C0000000UL
+#define POWER9_MMCRA_BHRB_MASK		0x00000000C0000000UL
 
 /* Nasty Power9 specific hack */
 #define PVR_POWER9_CUMULUS		0x00002000
@@ -168,6 +157,8 @@
 GENERIC_EVENT_ATTR(branch-misses,		PM_BR_MPRED_CMPL);
 GENERIC_EVENT_ATTR(cache-references,		PM_LD_REF_L1);
 GENERIC_EVENT_ATTR(cache-misses,		PM_LD_MISS_L1_FIN);
+GENERIC_EVENT_ATTR(mem-loads,			MEM_LOADS);
+GENERIC_EVENT_ATTR(mem-stores,			MEM_STORES);
 
 CACHE_EVENT_ATTR(L1-dcache-load-misses,		PM_LD_MISS_L1_FIN);
 CACHE_EVENT_ATTR(L1-dcache-loads,		PM_LD_REF_L1);
@@ -179,8 +170,6 @@
 CACHE_EVENT_ATTR(LLC-load-misses,		PM_DATA_FROM_L3MISS);
 CACHE_EVENT_ATTR(LLC-loads,			PM_DATA_FROM_L3);
 CACHE_EVENT_ATTR(LLC-prefetches,		PM_L3_PREF_ALL);
-CACHE_EVENT_ATTR(LLC-store-misses,		PM_L2_ST_MISS);
-CACHE_EVENT_ATTR(LLC-stores,			PM_L2_ST);
 CACHE_EVENT_ATTR(branch-load-misses,		PM_BR_MPRED_CMPL);
 CACHE_EVENT_ATTR(branch-loads,			PM_BR_CMPL);
 CACHE_EVENT_ATTR(dTLB-load-misses,		PM_DTLB_MISS);
@@ -195,6 +184,8 @@
 	GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL),
 	GENERIC_EVENT_PTR(PM_LD_REF_L1),
 	GENERIC_EVENT_PTR(PM_LD_MISS_L1_FIN),
+	GENERIC_EVENT_PTR(MEM_LOADS),
+	GENERIC_EVENT_PTR(MEM_STORES),
 	CACHE_EVENT_PTR(PM_LD_MISS_L1_FIN),
 	CACHE_EVENT_PTR(PM_LD_REF_L1),
 	CACHE_EVENT_PTR(PM_L1_PREF),
@@ -205,8 +196,6 @@
 	CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS),
 	CACHE_EVENT_PTR(PM_DATA_FROM_L3),
 	CACHE_EVENT_PTR(PM_L3_PREF_ALL),
-	CACHE_EVENT_PTR(PM_L2_ST_MISS),
-	CACHE_EVENT_PTR(PM_L2_ST),
 	CACHE_EVENT_PTR(PM_BR_MPRED_CMPL),
 	CACHE_EVENT_PTR(PM_BR_CMPL),
 	CACHE_EVENT_PTR(PM_DTLB_MISS),
@@ -308,6 +297,8 @@
 
 static void power9_config_bhrb(u64 pmu_bhrb_filter)
 {
+	pmu_bhrb_filter &= POWER9_MMCRA_BHRB_MASK;
+
 	/* Enable BHRB filter in PMU */
 	mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
 }
@@ -354,8 +345,8 @@
 			[ C(RESULT_MISS)   ] = PM_DATA_FROM_L3MISS,
 		},
 		[ C(OP_WRITE) ] = {
-			[ C(RESULT_ACCESS) ] = PM_L2_ST,
-			[ C(RESULT_MISS)   ] = PM_L2_ST_MISS,
+			[ C(RESULT_ACCESS) ] = 0,
+			[ C(RESULT_MISS)   ] = 0,
 		},
 		[ C(OP_PREFETCH) ] = {
 			[ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL,
@@ -427,6 +418,8 @@
 	.n_counter		= MAX_PMU_COUNTERS,
 	.add_fields		= ISA207_ADD_FIELDS,
 	.test_adder		= ISA207_TEST_ADDER,
+	.group_constraint_mask	= CNST_CACHE_PMC4_MASK,
+	.group_constraint_val	= CNST_CACHE_PMC4_VAL,
 	.compute_mmcr		= isa207_compute_mmcr,
 	.config_bhrb		= power9_config_bhrb,
 	.bhrb_filter_map	= power9_bhrb_filter_map,
@@ -443,7 +436,7 @@
 	.bhrb_nr		= 32,
 };
 
-static int __init init_power9_pmu(void)
+int init_power9_pmu(void)
 {
 	int rc = 0;
 	unsigned int pvr = mfspr(SPRN_PVR);
@@ -473,4 +466,3 @@
 
 	return 0;
 }
-early_initcall(init_power9_pmu);
diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c
index 8b6a8a3..4035d93 100644
--- a/arch/powerpc/perf/ppc970-pmu.c
+++ b/arch/powerpc/perf/ppc970-pmu.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Performance counter support for PPC970-family processors.
  *
  * Copyright 2008-2009 Paul Mackerras, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/string.h>
 #include <linux/perf_event.h>
@@ -490,7 +486,7 @@
 	.flags			= PPMU_NO_SIPR | PPMU_NO_CONT_SAMPLING,
 };
 
-static int __init init_ppc970_pmu(void)
+int init_ppc970_pmu(void)
 {
 	if (!cur_cpu_spec->oprofile_cpu_type ||
 	    (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970")
@@ -499,5 +495,3 @@
 
 	return register_power_pmu(&ppc970_pmu);
 }
-
-early_initcall(init_ppc970_pmu);
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig
index 60254a3..6da813b 100644
--- a/arch/powerpc/platforms/40x/Kconfig
+++ b/arch/powerpc/platforms/40x/Kconfig
@@ -2,7 +2,6 @@
 config ACADIA
 	bool "Acadia"
 	depends on 40x
-	default n
 	select PPC40x_SIMPLE
 	select 405EZ
 	help
@@ -11,28 +10,26 @@
 config EP405
 	bool "EP405/EP405PC"
 	depends on 40x
-	default n
 	select 405GP
-	select PCI
+	select FORCE_PCI
 	help
 	  This option enables support for the EP405/EP405PC boards.
 
 config HOTFOOT
-        bool "Hotfoot"
+	bool "Hotfoot"
 	depends on 40x
-	default n
 	select PPC40x_SIMPLE
-	select PCI
-        help
-	 This option enables support for the ESTEEM 195E Hotfoot board.
+	select FORCE_PCI
+	help
+	  This option enables support for the ESTEEM 195E Hotfoot board.
 
 config KILAUEA
 	bool "Kilauea"
 	depends on 40x
-	default n
 	select 405EX
 	select PPC40x_SIMPLE
 	select PPC4xx_PCI_EXPRESS
+	select FORCE_PCI
 	select PCI_MSI
 	select PPC4xx_MSI
 	help
@@ -41,9 +38,8 @@
 config MAKALU
 	bool "Makalu"
 	depends on 40x
-	default n
 	select 405EX
-	select PCI
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	select PPC40x_SIMPLE
 	help
@@ -54,7 +50,7 @@
 	depends on 40x
 	default y
 	select 405GP
-	select PCI
+	select FORCE_PCI
 	select OF_RTC
 	help
 	  This option enables support for the IBM PPC405GP evaluation board.
@@ -62,7 +58,6 @@
 config XILINX_VIRTEX_GENERIC_BOARD
 	bool "Generic Xilinx Virtex board"
 	depends on 40x
-	default n
 	select XILINX_VIRTEX_II_PRO
 	select XILINX_VIRTEX_4_FX
 	select XILINX_INTC
@@ -80,17 +75,14 @@
 config OBS600
 	bool "OpenBlockS 600"
 	depends on 40x
-	default n
 	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
-	default n
 	help
 	  This option enables the simple PowerPC 40x platform support.
 
@@ -156,7 +148,6 @@
 config APM8018X
 	bool "APM8018X"
 	depends on 40x
-	default n
 	select PPC40x_SIMPLE
 	help
 	  This option enables support for the AppliedMicro APM8018X evaluation
diff --git a/arch/powerpc/platforms/40x/Makefile b/arch/powerpc/platforms/40x/Makefile
index 88c22de..828d783 100644
--- a/arch/powerpc/platforms/40x/Makefile
+++ b/arch/powerpc/platforms/40x/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_WALNUT)				+= walnut.o
 obj-$(CONFIG_XILINX_VIRTEX_GENERIC_BOARD)	+= virtex.o
 obj-$(CONFIG_EP405)				+= ep405.o
diff --git a/arch/powerpc/platforms/40x/ppc40x_simple.c b/arch/powerpc/platforms/40x/ppc40x_simple.c
index 2a05000..e70b427 100644
--- a/arch/powerpc/platforms/40x/ppc40x_simple.c
+++ b/arch/powerpc/platforms/40x/ppc40x_simple.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Generic PowerPC 40x platform support
  *
  * Copyright 2008 IBM 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 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
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index a601142..25ebe63 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -2,7 +2,6 @@
 config PPC_47x
 	bool "Support for 47x variant"
 	depends on 44x
-	default n
 	select MPIC
 	help
 	  This option enables support for the 47x family of processors and is
@@ -11,19 +10,18 @@
 config BAMBOO
 	bool "Bamboo"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 440EP
-	select PCI
+	select FORCE_PCI
 	help
 	  This option enables support for the IBM PPC440EP evaluation board.
 
 config BLUESTONE
 	bool "Bluestone"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select APM821xx
+	select FORCE_PCI
 	select PCI_MSI
 	select PPC4xx_MSI
 	select PPC4xx_PCI_EXPRESS
@@ -36,24 +34,22 @@
 	depends on 44x
 	default y
 	select 440GP
-	select PCI
+	select FORCE_PCI
 	select OF_RTC
 	help
 	  This option enables support for the IBM PPC440GP evaluation board.
 
 config SAM440EP
-        bool "Sam440ep"
+	bool "Sam440ep"
 	depends on 44x
-        default n
-        select 440EP
-        select PCI
-        help
-          This option enables support for the ACube Sam440ep board.
+	select 440EP
+	select FORCE_PCI
+	help
+	  This option enables support for the ACube Sam440ep board.
 
 config SEQUOIA
 	bool "Sequoia"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 440EPX
 	help
@@ -62,10 +58,9 @@
 config TAISHAN
 	bool "Taishan"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 440GX
-	select PCI
+	select FORCE_PCI
 	help
 	  This option enables support for the AMCC PPC440GX "Taishan"
 	  evaluation board.
@@ -73,10 +68,9 @@
 config KATMAI
 	bool "Katmai"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 440SPe
-	select PCI
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	select PCI_MSI
 	select PPC4xx_MSI
@@ -86,17 +80,15 @@
 config RAINIER
 	bool "Rainier"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 440GRX
-	select PCI
+	select FORCE_PCI
 	help
 	  This option enables support for the AMCC PPC440GRX evaluation board.
 
 config WARP
 	bool "PIKA Warp"
 	depends on 44x
-	default n
 	select 440EP
 	help
 	  This option enables support for the PIKA Warp(tm) Appliance. The Warp
@@ -109,10 +101,9 @@
 config ARCHES
 	bool "Arches"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 460EX # Odd since it uses 460GT but the effects are the same
-	select PCI
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	help
 	  This option enables support for the AMCC Dual PPC460GT evaluation board.
@@ -120,9 +111,8 @@
 config CANYONLANDS
 	bool "Canyonlands"
 	depends on 44x
-	default n
 	select 460EX
-	select PCI
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	select PCI_MSI
 	select PPC4xx_MSI
@@ -134,10 +124,9 @@
 config GLACIER
 	bool "Glacier"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 460EX # Odd since it uses 460GT but the effects are the same
-	select PCI
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	select IBM_EMAC_RGMII if IBM_EMAC
 	select IBM_EMAC_ZMII if IBM_EMAC
@@ -147,10 +136,9 @@
 config REDWOOD
 	bool "Redwood"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 460SX
-	select PCI
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	select PCI_MSI
 	select PPC4xx_MSI
@@ -160,10 +148,9 @@
 config EIGER
 	bool "Eiger"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 460SX
-	select PCI
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	select IBM_EMAC_RGMII if IBM_EMAC
 	help
@@ -172,17 +159,15 @@
 config YOSEMITE
 	bool "Yosemite"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 440EP
-	select PCI
+	select FORCE_PCI
 	help
 	  This option enables support for the AMCC PPC440EP evaluation board.
 
 config ISS4xx
 	bool "ISS 4xx Simulator"
 	depends on (44x || 40x)
-	default n
 	select 405GP if 40x
 	select 440GP if 44x && !PPC_47x
 	select PPC_FPU
@@ -193,9 +178,9 @@
 config CURRITUCK
 	bool "IBM Currituck (476fpe) Support"
 	depends on PPC_47x
-	default n
 	select SWIOTLB
 	select 476FPE
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	help
 	  This option enables support for the IBM Currituck (476fpe) evaluation board
@@ -203,7 +188,6 @@
 config FSP2
 	bool "IBM FSP2 (476fpe) Support"
 	depends on PPC_47x
-	default n
 	select 476FPE
 	select IBM_EMAC_EMAC4 if IBM_EMAC
 	select IBM_EMAC_RGMII if IBM_EMAC
@@ -215,10 +199,10 @@
 config AKEBONO
 	bool "IBM Akebono (476gtr) Support"
 	depends on PPC_47x
-	default n
 	select SWIOTLB
 	select 476FPE
 	select PPC4xx_PCI_EXPRESS
+	select FORCE_PCI
 	select PCI_MSI
 	select PPC4xx_HSTA_MSI
 	select I2C
@@ -241,10 +225,9 @@
 config ICON
 	bool "Icon"
 	depends on 44x
-	default n
 	select PPC44x_SIMPLE
 	select 440SPe
-	select PCI
+	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	help
 	  This option enables support for the AMCC PPC440SPe evaluation board.
@@ -252,7 +235,6 @@
 config XILINX_VIRTEX440_GENERIC_BOARD
 	bool "Generic Xilinx Virtex 5 FXT board support"
 	depends on 44x
-	default n
 	select XILINX_VIRTEX_5_FXT
 	select XILINX_INTC
 	help
@@ -269,7 +251,7 @@
 config XILINX_ML510
 	bool "Xilinx ML510 extra support"
 	depends on XILINX_VIRTEX440_GENERIC_BOARD
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 	select XILINX_PCI if PCI
 	select PPC_INDIRECT_PCI if PCI
 	select PPC_I8259 if PCI
@@ -280,7 +262,6 @@
 config PPC44x_SIMPLE
 	bool "Simple PowerPC 44x board support"
 	depends on 44x
-	default n
 	help
 	  This option enables the simple PowerPC 44x platform support.
 
@@ -291,14 +272,6 @@
 	help
 	  Enable gpiolib support for ppc440 based boards
 
-config PPC4xx_OCM
-	bool "PPC4xx On Chip Memory (OCM) support"
-	depends on 4xx
-	select PPC_LIB_RHEAP
-	help
-	  Enable OCM support for PowerPC 4xx platforms with on chip memory,
-	  OCM provides the fast place for memory access to improve performance.
-
 # 44x specific CPU modules, selected based on the board above.
 config 440EP
 	bool
diff --git a/arch/powerpc/platforms/44x/canyonlands.c b/arch/powerpc/platforms/44x/canyonlands.c
index 157f4ce..807968a 100644
--- a/arch/powerpc/platforms/44x/canyonlands.c
+++ b/arch/powerpc/platforms/44x/canyonlands.c
@@ -1,25 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This contain platform specific code for APM PPC460EX based Canyonlands
  * board.
  *
  * Copyright (c) 2010, Applied Micro Circuits Corporation
  * Author: Rupjyoti Sarmah <rsarmah@apm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- *
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/arch/powerpc/platforms/44x/ebony.c b/arch/powerpc/platforms/44x/ebony.c
index 1070225..0d8f202 100644
--- a/arch/powerpc/platforms/44x/ebony.c
+++ b/arch/powerpc/platforms/44x/ebony.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Ebony board specific routines
  *
@@ -9,11 +10,6 @@
  *
  * Rewritten and ported to the merged powerpc tree:
  * Copyright 2007 David Gibson <dwg@au1.ibm.com>, IBM 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;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/platforms/44x/fsp2.c b/arch/powerpc/platforms/44x/fsp2.c
index 04f0c73..b299e43 100644
--- a/arch/powerpc/platforms/44x/fsp2.c
+++ b/arch/powerpc/platforms/44x/fsp2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * FSP-2 board specific routines
  *
@@ -10,11 +11,6 @@
  *
  *    Rewritten and ported to the merged powerpc tree:
  *    Copyright 2007 David Gibson <dwg@au1.ibm.com>, IBM 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;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
@@ -210,15 +206,15 @@
 	for_each_compatible_node(np, NULL, compat) {
 		irq = irq_of_parse_and_map(np, 0);
 		if (irq == NO_IRQ) {
-			pr_err("device tree node %s is missing a interrupt",
-			      np->name);
+			pr_err("device tree node %pOFn is missing a interrupt",
+			      np);
 			return;
 		}
 
 		rc = request_irq(irq, errirq_handler, 0, np->name, np);
 		if (rc) {
-			pr_err("fsp_of_probe: request_irq failed: np=%s rc=%d",
-			      np->full_name, rc);
+			pr_err("fsp_of_probe: request_irq failed: np=%pOF rc=%d",
+			      np, rc);
 			return;
 		}
 	}
diff --git a/arch/powerpc/platforms/44x/idle.c b/arch/powerpc/platforms/44x/idle.c
index 7a81f92..f533b49 100644
--- a/arch/powerpc/platforms/44x/idle.c
+++ b/arch/powerpc/platforms/44x/idle.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2008 IBM Corp. 
  *
@@ -5,20 +6,6 @@
  * Copyright (C) 2006-2007 PA Semi, Inc
  *
  * Added by: Jerone Young <jyoung5@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  */
 
 #include <linux/of.h>
diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c
index 5f296dd..c5f8259 100644
--- a/arch/powerpc/platforms/44x/iss4xx.c
+++ b/arch/powerpc/platforms/44x/iss4xx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PPC476 board specific routines
  *
@@ -12,11 +13,6 @@
  *
  *    Rewritten and ported to the merged powerpc tree:
  *    Copyright 2007 David Gibson <dwg@au1.ibm.com>, IBM 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;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/platforms/44x/machine_check.c b/arch/powerpc/platforms/44x/machine_check.c
index 034d70d..90ad6ac 100644
--- a/arch/powerpc/platforms/44x/machine_check.c
+++ b/arch/powerpc/platforms/44x/machine_check.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/44x/misc_44x.S b/arch/powerpc/platforms/44x/misc_44x.S
index dc12b80..3a0c4bd 100644
--- a/arch/powerpc/platforms/44x/misc_44x.S
+++ b/arch/powerpc/platforms/44x/misc_44x.S
@@ -1,12 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains miscellaneous low-level functions for PPC 44x.
  *    Copyright 2007 David Gibson <dwg@au1.ibm.com>, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/reg.h>
diff --git a/arch/powerpc/platforms/44x/ppc44x_simple.c b/arch/powerpc/platforms/44x/ppc44x_simple.c
index 8d6e4da..3dbd8dd 100644
--- a/arch/powerpc/platforms/44x/ppc44x_simple.c
+++ b/arch/powerpc/platforms/44x/ppc44x_simple.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Generic PowerPC 44x platform support
  *
  * Copyright 2008 IBM 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 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
diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c
index e55933f..cba83ee 100644
--- a/arch/powerpc/platforms/44x/ppc476.c
+++ b/arch/powerpc/platforms/44x/ppc476.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerPC 476FPE board specific routines
  *
@@ -14,11 +15,6 @@
  *    Rewritten and ported to the merged powerpc tree:
  *    Copyright 2007 David Gibson <dwg@au1.ibm.com>, IBM Corporation.
  *    Copyright © 2011 David Kliekamp IBM 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;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
@@ -34,6 +30,7 @@
 #include <asm/ppc4xx.h>
 #include <asm/mpic.h>
 #include <asm/mmu.h>
+#include <asm/swiotlb.h>
 
 #include <linux/pci.h>
 #include <linux/i2c.h>
diff --git a/arch/powerpc/platforms/44x/sam440ep.c b/arch/powerpc/platforms/44x/sam440ep.c
index 55fed5e..68ba4b0 100644
--- a/arch/powerpc/platforms/44x/sam440ep.c
+++ b/arch/powerpc/platforms/44x/sam440ep.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Sam440ep board specific routines based off bamboo.c code
  * original copyrights below
@@ -11,11 +12,6 @@
  *
  * Modified from bamboo.c for sam440ep:
  * Copyright 2008 Giuseppe Coviello <gicoviello@gmail.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #include <linux/init.h>
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index a886c2c..6620b64 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PIKA Warp(tm) board specific routines
  *
  * Copyright (c) 2008-2009 PIKA Technologies
  *   Sean MacLennan <smaclennan@pikatech.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #include <linux/init.h>
 #include <linux/of_platform.h>
@@ -47,7 +43,7 @@
 	if (!of_machine_is_compatible("pika,warp"))
 		return 0;
 
-	/* For __dma_alloc_coherent */
+	/* For arch_dma_alloc */
 	ISA_DMA_THRESHOLD = ~0L;
 
 	return 1;
@@ -179,9 +175,9 @@
 	}
 
 	for_each_child_of_node(np, child)
-		if (strcmp(child->name, "green") == 0)
+		if (of_node_name_eq(child, "green"))
 			green_led = of_get_gpio(child, 0);
-		else if (strcmp(child->name, "red") == 0)
+		else if (of_node_name_eq(child, "red"))
 			red_led = of_get_gpio(child, 0);
 
 	of_node_put(np);
diff --git a/arch/powerpc/platforms/4xx/Makefile b/arch/powerpc/platforms/4xx/Makefile
index 9779c32..d009d2e 100644
--- a/arch/powerpc/platforms/4xx/Makefile
+++ b/arch/powerpc/platforms/4xx/Makefile
@@ -1,5 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-y				+= uic.o machine_check.o
-obj-$(CONFIG_PPC4xx_OCM)	+= ocm.o
 obj-$(CONFIG_4xx_SOC)		+= soc.o
 obj-$(CONFIG_PCI)		+= pci.o
 obj-$(CONFIG_PPC4xx_HSTA_MSI)	+= hsta_msi.o
diff --git a/arch/powerpc/platforms/4xx/cpm.c b/arch/powerpc/platforms/4xx/cpm.c
index 53ff81c..ae8b812 100644
--- a/arch/powerpc/platforms/4xx/cpm.c
+++ b/arch/powerpc/platforms/4xx/cpm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerPC 4xx Clock and Power Management
  *
@@ -14,21 +15,6 @@
  *
  * See file CREDITS for list of people who contributed to this
  * project.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/4xx/gpio.c b/arch/powerpc/platforms/4xx/gpio.c
index 2238e36..49ee8d3 100644
--- a/arch/powerpc/platforms/4xx/gpio.c
+++ b/arch/powerpc/platforms/4xx/gpio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * PPC4xx gpio driver
  *
@@ -6,19 +7,6 @@
  * Copyright (c) MontaVista Software, Inc. 2008.
  *
  * Author: Steve Falco <sfalco@harris.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/4xx/hsta_msi.c b/arch/powerpc/platforms/4xx/hsta_msi.c
index 1c18f29..c950fed 100644
--- a/arch/powerpc/platforms/4xx/hsta_msi.c
+++ b/arch/powerpc/platforms/4xx/hsta_msi.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MSI support for PPC4xx SoCs using High Speed Transfer Assist (HSTA) for
  * generation of the interrupt.
  *
  * Copyright © 2013 Alistair Popple <alistair@popple.id.au> IBM 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;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/4xx/machine_check.c b/arch/powerpc/platforms/4xx/machine_check.c
index aa039df..a71c298 100644
--- a/arch/powerpc/platforms/4xx/machine_check.c
+++ b/arch/powerpc/platforms/4xx/machine_check.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/4xx/msi.c b/arch/powerpc/platforms/4xx/msi.c
index 7c324ef..1051564 100644
--- a/arch/powerpc/platforms/4xx/msi.c
+++ b/arch/powerpc/platforms/4xx/msi.c
@@ -1,24 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Adding PCI-E MSI support for PPC4XX SoCs.
  *
  * Copyright (c) 2010, Applied Micro Circuits Corporation
  * Authors:	Tirumala R Marri <tmarri@apm.com>
  *		Feng Kan <fkan@apm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
  */
 
 #include <linux/irq.h>
diff --git a/arch/powerpc/platforms/4xx/ocm.c b/arch/powerpc/platforms/4xx/ocm.c
deleted file mode 100644
index 69d9f60..0000000
--- a/arch/powerpc/platforms/4xx/ocm.c
+++ /dev/null
@@ -1,416 +0,0 @@
-/*
- * PowerPC 4xx OCM memory allocation support
- *
- * (C) Copyright 2009, Applied Micro Circuits Corporation
- * Victor Gallardo (vgallardo@amcc.com)
- *
- * See file CREDITS for list of people who contributed to this
- * project.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- */
-
-#include <linux/kernel.h>
-#include <linux/dma-mapping.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <asm/rheap.h>
-#include <asm/ppc4xx_ocm.h>
-#include <linux/slab.h>
-#include <linux/debugfs.h>
-
-#define OCM_DISABLED	0
-#define OCM_ENABLED		1
-
-struct ocm_block {
-	struct list_head	list;
-	void __iomem		*addr;
-	int					size;
-	const char			*owner;
-};
-
-/* non-cached or cached region */
-struct ocm_region {
-	phys_addr_t			phys;
-	void __iomem		*virt;
-
-	int					memtotal;
-	int					memfree;
-
-	rh_info_t			*rh;
-	struct list_head	list;
-};
-
-struct ocm_info {
-	int					index;
-	int					status;
-	int					ready;
-
-	phys_addr_t			phys;
-
-	int					alignment;
-	int					memtotal;
-	int					cache_size;
-
-	struct ocm_region	nc;	/* non-cached region */
-	struct ocm_region	c;	/* cached region */
-};
-
-static struct ocm_info *ocm_nodes;
-static int ocm_count;
-
-static struct ocm_info *ocm_get_node(unsigned int index)
-{
-	if (index >= ocm_count) {
-		printk(KERN_ERR "PPC4XX OCM: invalid index");
-		return NULL;
-	}
-
-	return &ocm_nodes[index];
-}
-
-static int ocm_free_region(struct ocm_region *ocm_reg, const void *addr)
-{
-	struct ocm_block *blk, *tmp;
-	unsigned long offset;
-
-	if (!ocm_reg->virt)
-		return 0;
-
-	list_for_each_entry_safe(blk, tmp, &ocm_reg->list, list) {
-		if (blk->addr == addr) {
-			offset = addr - ocm_reg->virt;
-			ocm_reg->memfree += blk->size;
-			rh_free(ocm_reg->rh, offset);
-			list_del(&blk->list);
-			kfree(blk);
-			return 1;
-		}
-	}
-
-	return 0;
-}
-
-static void __init ocm_init_node(int count, struct device_node *node)
-{
-	struct ocm_info *ocm;
-
-	const unsigned int *cell_index;
-	const unsigned int *cache_size;
-	int len;
-
-	struct resource rsrc;
-	int ioflags;
-
-	ocm = ocm_get_node(count);
-
-	cell_index = of_get_property(node, "cell-index", &len);
-	if (!cell_index) {
-		printk(KERN_ERR "PPC4XX OCM: missing cell-index property");
-		return;
-	}
-	ocm->index = *cell_index;
-
-	if (of_device_is_available(node))
-		ocm->status = OCM_ENABLED;
-
-	cache_size = of_get_property(node, "cached-region-size", &len);
-	if (cache_size)
-		ocm->cache_size = *cache_size;
-
-	if (of_address_to_resource(node, 0, &rsrc)) {
-		printk(KERN_ERR "PPC4XX OCM%d: could not get resource address\n",
-			ocm->index);
-		return;
-	}
-
-	ocm->phys = rsrc.start;
-	ocm->memtotal = (rsrc.end - rsrc.start + 1);
-
-	printk(KERN_INFO "PPC4XX OCM%d: %d Bytes (%s)\n",
-		ocm->index, ocm->memtotal,
-		(ocm->status == OCM_DISABLED) ? "disabled" : "enabled");
-
-	if (ocm->status == OCM_DISABLED)
-		return;
-
-	/* request region */
-
-	if (!request_mem_region(ocm->phys, ocm->memtotal, "ppc4xx_ocm")) {
-		printk(KERN_ERR "PPC4XX OCM%d: could not request region\n",
-			ocm->index);
-		return;
-	}
-
-	/* Configure non-cached and cached regions */
-
-	ocm->nc.phys = ocm->phys;
-	ocm->nc.memtotal = ocm->memtotal - ocm->cache_size;
-	ocm->nc.memfree = ocm->nc.memtotal;
-
-	ocm->c.phys = ocm->phys + ocm->nc.memtotal;
-	ocm->c.memtotal = ocm->cache_size;
-	ocm->c.memfree = ocm->c.memtotal;
-
-	if (ocm->nc.memtotal == 0)
-		ocm->nc.phys = 0;
-
-	if (ocm->c.memtotal == 0)
-		ocm->c.phys = 0;
-
-	printk(KERN_INFO "PPC4XX OCM%d: %d Bytes (non-cached)\n",
-		ocm->index, ocm->nc.memtotal);
-
-	printk(KERN_INFO "PPC4XX OCM%d: %d Bytes (cached)\n",
-		ocm->index, ocm->c.memtotal);
-
-	/* ioremap the non-cached region */
-	if (ocm->nc.memtotal) {
-		ioflags = _PAGE_NO_CACHE | _PAGE_GUARDED | _PAGE_EXEC;
-		ocm->nc.virt = __ioremap(ocm->nc.phys, ocm->nc.memtotal,
-					  ioflags);
-
-		if (!ocm->nc.virt) {
-			printk(KERN_ERR
-			       "PPC4XX OCM%d: failed to ioremap non-cached memory\n",
-			       ocm->index);
-			ocm->nc.memfree = 0;
-			return;
-		}
-	}
-
-	/* ioremap the cached region */
-
-	if (ocm->c.memtotal) {
-		ioflags = _PAGE_EXEC;
-		ocm->c.virt = __ioremap(ocm->c.phys, ocm->c.memtotal,
-					 ioflags);
-
-		if (!ocm->c.virt) {
-			printk(KERN_ERR
-			       "PPC4XX OCM%d: failed to ioremap cached memory\n",
-			       ocm->index);
-			ocm->c.memfree = 0;
-			return;
-		}
-	}
-
-	/* Create Remote Heaps */
-
-	ocm->alignment = 4; /* default 4 byte alignment */
-
-	if (ocm->nc.virt) {
-		ocm->nc.rh = rh_create(ocm->alignment);
-		rh_attach_region(ocm->nc.rh, 0, ocm->nc.memtotal);
-	}
-
-	if (ocm->c.virt) {
-		ocm->c.rh = rh_create(ocm->alignment);
-		rh_attach_region(ocm->c.rh, 0, ocm->c.memtotal);
-	}
-
-	INIT_LIST_HEAD(&ocm->nc.list);
-	INIT_LIST_HEAD(&ocm->c.list);
-
-	ocm->ready = 1;
-
-	return;
-}
-
-static int ocm_debugfs_show(struct seq_file *m, void *v)
-{
-	struct ocm_block *blk, *tmp;
-	unsigned int i;
-
-	for (i = 0; i < ocm_count; i++) {
-		struct ocm_info *ocm = ocm_get_node(i);
-
-		if (!ocm || !ocm->ready)
-			continue;
-
-		seq_printf(m, "PPC4XX OCM   : %d\n", ocm->index);
-		seq_printf(m, "PhysAddr     : 0x%llx\n", ocm->phys);
-		seq_printf(m, "MemTotal     : %d Bytes\n", ocm->memtotal);
-		seq_printf(m, "MemTotal(NC) : %d Bytes\n", ocm->nc.memtotal);
-		seq_printf(m, "MemTotal(C)  : %d Bytes\n", ocm->c.memtotal);
-
-		seq_printf(m, "\n");
-
-		seq_printf(m, "NC.PhysAddr  : 0x%llx\n", ocm->nc.phys);
-		seq_printf(m, "NC.VirtAddr  : 0x%p\n", ocm->nc.virt);
-		seq_printf(m, "NC.MemTotal  : %d Bytes\n", ocm->nc.memtotal);
-		seq_printf(m, "NC.MemFree   : %d Bytes\n", ocm->nc.memfree);
-
-		list_for_each_entry_safe(blk, tmp, &ocm->nc.list, list) {
-			seq_printf(m, "NC.MemUsed   : %d Bytes (%s)\n",
-							blk->size, blk->owner);
-		}
-
-		seq_printf(m, "\n");
-
-		seq_printf(m, "C.PhysAddr   : 0x%llx\n", ocm->c.phys);
-		seq_printf(m, "C.VirtAddr   : 0x%p\n", ocm->c.virt);
-		seq_printf(m, "C.MemTotal   : %d Bytes\n", ocm->c.memtotal);
-		seq_printf(m, "C.MemFree    : %d Bytes\n", ocm->c.memfree);
-
-		list_for_each_entry_safe(blk, tmp, &ocm->c.list, list) {
-			seq_printf(m, "C.MemUsed    : %d Bytes (%s)\n",
-						blk->size, blk->owner);
-		}
-
-		seq_printf(m, "\n");
-	}
-
-	return 0;
-}
-
-static int ocm_debugfs_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ocm_debugfs_show, NULL);
-}
-
-static const struct file_operations ocm_debugfs_fops = {
-	.open = ocm_debugfs_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static int ocm_debugfs_init(void)
-{
-	struct dentry *junk;
-
-	junk = debugfs_create_dir("ppc4xx_ocm", 0);
-	if (!junk) {
-		printk(KERN_ALERT "debugfs ppc4xx ocm: failed to create dir\n");
-		return -1;
-	}
-
-	if (debugfs_create_file("info", 0644, junk, NULL, &ocm_debugfs_fops)) {
-		printk(KERN_ALERT "debugfs ppc4xx ocm: failed to create file\n");
-		return -1;
-	}
-
-	return 0;
-}
-
-void *ppc4xx_ocm_alloc(phys_addr_t *phys, int size, int align,
-			int flags, const char *owner)
-{
-	void __iomem *addr = NULL;
-	unsigned long offset;
-	struct ocm_info *ocm;
-	struct ocm_region *ocm_reg;
-	struct ocm_block *ocm_blk;
-	int i;
-
-	for (i = 0; i < ocm_count; i++) {
-		ocm = ocm_get_node(i);
-
-		if (!ocm || !ocm->ready)
-			continue;
-
-		if (flags == PPC4XX_OCM_NON_CACHED)
-			ocm_reg = &ocm->nc;
-		else
-			ocm_reg = &ocm->c;
-
-		if (!ocm_reg->virt)
-			continue;
-
-		if (align < ocm->alignment)
-			align = ocm->alignment;
-
-		offset = rh_alloc_align(ocm_reg->rh, size, align, NULL);
-
-		if (IS_ERR_VALUE(offset))
-			continue;
-
-		ocm_blk = kzalloc(sizeof(*ocm_blk), GFP_KERNEL);
-		if (!ocm_blk) {
-			printk(KERN_ERR "PPC4XX OCM: could not allocate ocm block");
-			rh_free(ocm_reg->rh, offset);
-			break;
-		}
-
-		*phys = ocm_reg->phys + offset;
-		addr = ocm_reg->virt + offset;
-		size = ALIGN(size, align);
-
-		ocm_blk->addr = addr;
-		ocm_blk->size = size;
-		ocm_blk->owner = owner;
-		list_add_tail(&ocm_blk->list, &ocm_reg->list);
-
-		ocm_reg->memfree -= size;
-
-		break;
-	}
-
-	return addr;
-}
-
-void ppc4xx_ocm_free(const void *addr)
-{
-	int i;
-
-	if (!addr)
-		return;
-
-	for (i = 0; i < ocm_count; i++) {
-		struct ocm_info *ocm = ocm_get_node(i);
-
-		if (!ocm || !ocm->ready)
-			continue;
-
-		if (ocm_free_region(&ocm->nc, addr) ||
-			ocm_free_region(&ocm->c, addr))
-			return;
-	}
-}
-
-static int __init ppc4xx_ocm_init(void)
-{
-	struct device_node *np;
-	int count;
-
-	count = 0;
-	for_each_compatible_node(np, NULL, "ibm,ocm")
-		count++;
-
-	if (!count)
-		return 0;
-
-	ocm_nodes = kzalloc((count * sizeof(struct ocm_info)), GFP_KERNEL);
-	if (!ocm_nodes) {
-		printk(KERN_ERR "PPC4XX OCM: failed to allocate OCM nodes!\n");
-		return -ENOMEM;
-	}
-
-	ocm_count = count;
-	count = 0;
-
-	for_each_compatible_node(np, NULL, "ibm,ocm") {
-		ocm_init_node(count, np);
-		count++;
-	}
-
-	ocm_debugfs_init();
-
-	return 0;
-}
-
-arch_initcall(ppc4xx_ocm_init);
diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c
index 5aca523..e6e2adc 100644
--- a/arch/powerpc/platforms/4xx/pci.c
+++ b/arch/powerpc/platforms/4xx/pci.c
@@ -1399,7 +1399,6 @@
 		printk(KERN_WARNING "PCIE%d: Link up failed\n", port->index);
 
 	iounmap(mbase);
-	return;
 }
 
 static struct ppc4xx_pciex_hwops ppc_476fpe_pcie_hwops __initdata =
@@ -2081,7 +2080,6 @@
 	const u32 *pval;
 	int portno;
 	unsigned int dcrs;
-	const char *val;
 
 	/* First, proceed to core initialization as we assume there's
 	 * only one PCIe core in the system
@@ -2127,10 +2125,9 @@
 	 * Resulting from this setup this PCIe port will be configured
 	 * as root-complex or as endpoint.
 	 */
-	val = of_get_property(port->node, "device_type", NULL);
-	if (!strcmp(val, "pci-endpoint")) {
+	if (of_node_is_type(port->node, "pci-endpoint")) {
 		port->endpoint = 1;
-	} else if (!strcmp(val, "pci")) {
+	} else if (of_node_is_type(port->node, "pci")) {
 		port->endpoint = 0;
 	} else {
 		printk(KERN_ERR "PCIE: missing or incorrect device_type for %pOF\n",
diff --git a/arch/powerpc/platforms/4xx/soc.c b/arch/powerpc/platforms/4xx/soc.c
index 5e36508..ac1cd8b 100644
--- a/arch/powerpc/platforms/4xx/soc.c
+++ b/arch/powerpc/platforms/4xx/soc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * IBM/AMCC PPC4xx SoC setup code
  *
@@ -6,11 +7,6 @@
  * L2 cache routines cloned from arch/ppc/syslib/ibm440gx_common.c which is:
  *   Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
  *   Copyright (c) 2003 - 2006 Zultys Technologies
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -200,7 +196,7 @@
 	u32 reset_type = DBCR0_RST_SYSTEM;
 	const u32 *prop;
 
-	np = of_find_node_by_type(NULL, "cpu");
+	np = of_get_cpu_node(0, NULL);
 	if (np) {
 		prop = of_get_property(np, "reset-type", NULL);
 
diff --git a/arch/powerpc/platforms/4xx/uic.c b/arch/powerpc/platforms/4xx/uic.c
index 8b4dd0d..36fb66c 100644
--- a/arch/powerpc/platforms/4xx/uic.c
+++ b/arch/powerpc/platforms/4xx/uic.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/sysdev/uic.c
  *
  * IBM PowerPC 4xx Universal Interrupt Controller
  *
  * Copyright 2007 David Gibson <dwg@au1.ibm.com>, IBM 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;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -158,6 +154,7 @@
 
 	mtdcr(uic->dcrbase + UIC_PR, pr);
 	mtdcr(uic->dcrbase + UIC_TR, tr);
+	mtdcr(uic->dcrbase + UIC_SR, ~mask);
 
 	raw_spin_unlock_irqrestore(&uic->lock, flags);
 
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index b59eab6..deecede 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -1,11 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 config PPC_MPC512x
 	bool "512x-based boards"
-	depends on 6xx
+	depends on PPC_BOOK3S_32
 	select COMMON_CLK
 	select FSL_SOC
 	select IPIC
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 	select FSL_PCI if PCI
 	select USB_EHCI_BIG_ENDIAN_MMIO if USB_EHCI_HCD
 	select USB_EHCI_BIG_ENDIAN_DESC if USB_EHCI_HCD
diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c
index b3097fe..30342b6 100644
--- a/arch/powerpc/platforms/512x/clock-commonclk.c
+++ b/arch/powerpc/platforms/512x/clock-commonclk.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2013 DENX Software Engineering
  *
  * Gerhard Sittig, <gsi@denx.de>
  *
  * common clock driver support for the MPC512x platform
- *
- * This is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/bitops.h>
@@ -239,6 +235,7 @@
 	const char *name, const char *parent_name, u8 clkflags,
 	u32 __iomem *reg, u8 pos, u8 len, int divflags)
 {
+	divflags |= CLK_DIVIDER_BIG_ENDIAN;
 	return clk_register_divider(NULL, name, parent_name, clkflags,
 				    reg, pos, len, divflags, &clklock);
 }
@@ -250,7 +247,7 @@
 {
 	u8 divflags;
 
-	divflags = 0;
+	divflags = CLK_DIVIDER_BIG_ENDIAN;
 	return clk_register_divider_table(NULL, name, parent_name, 0,
 					  reg, pos, len, divflags,
 					  divtab, &clklock);
@@ -261,10 +258,12 @@
 	u32 __iomem *reg, u8 pos)
 {
 	int clkflags;
+	u8 gateflags;
 
 	clkflags = CLK_SET_RATE_PARENT;
+	gateflags = CLK_GATE_BIG_ENDIAN;
 	return clk_register_gate(NULL, name, parent_name, clkflags,
-				 reg, pos, 0, &clklock);
+				 reg, pos, gateflags, &clklock);
 }
 
 static inline struct clk *mpc512x_clk_muxed(const char *name,
@@ -275,7 +274,7 @@
 	u8 muxflags;
 
 	clkflags = CLK_SET_RATE_PARENT;
-	muxflags = 0;
+	muxflags = CLK_MUX_BIG_ENDIAN;
 	return clk_register_mux(NULL, name,
 				parent_names, parent_count, clkflags,
 				reg, pos, len, muxflags, &clklock);
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.c b/arch/powerpc/platforms/512x/mpc5121_ads.c
index f65d503..6303fbf 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2007, 2008 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -5,12 +6,6 @@
  *
  * Description:
  * MPC5121 ADS board setup
- *
- * This is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.h b/arch/powerpc/platforms/512x/mpc5121_ads.h
index 662076c..c88dea8 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads.h
+++ b/arch/powerpc/platforms/512x/mpc5121_ads.h
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Prototypes for ADS5121 specific code
  */
 
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index fe4d4ea..b298163 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -5,11 +6,6 @@
  *
  * Description:
  * MPC5121ADS CPLD irq handling
- *
- * This is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/512x/mpc512x.h b/arch/powerpc/platforms/512x/mpc512x.h
index 14ba49f..fff2259 100644
--- a/arch/powerpc/platforms/512x/mpc512x.h
+++ b/arch/powerpc/platforms/512x/mpc512x.h
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Prototypes for MPC512x shared code
  */
 
diff --git a/arch/powerpc/platforms/512x/mpc512x_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c
index bf884d3..303bc30 100644
--- a/arch/powerpc/platforms/512x/mpc512x_generic.c
+++ b/arch/powerpc/platforms/512x/mpc512x_generic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2007,2008 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -5,12 +6,6 @@
  *
  * Description:
  * MPC512x SoC setup
- *
- * This is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
index cec3f88..13631f3 100644
--- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
+++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * The driver for Freescale MPC512x LocalPlus Bus FIFO
  * (called SCLPC in the Reference Manual).
  *
  * Copyright (C) 2013-2015 Alexander Popov <alex.popov@linux.com>.
- *
- * This file is released under the GPLv2.
  */
 
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index 48abb4c..7a9ae95 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2007,2008 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -5,11 +6,6 @@
  *
  * Description:
  * MPC512x Shared code
- *
- * This is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/clk.h>
diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c
index dc81f05..1e911f4 100644
--- a/arch/powerpc/platforms/512x/pdm360ng.c
+++ b/arch/powerpc/platforms/512x/pdm360ng.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2010 DENX Software Engineering
  *
  * Anatolij Gustschin, <agust@denx.de>
  *
  * PDM360NG board setup
- *
- * This is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig
index 55a5870..99d60ac 100644
--- a/arch/powerpc/platforms/52xx/Kconfig
+++ b/arch/powerpc/platforms/52xx/Kconfig
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 config PPC_MPC52xx
 	bool "52xx-based boards"
-	depends on 6xx
+	depends on PPC_BOOK3S_32
 	select COMMON_CLK
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 
 config PPC_MPC5200_SIMPLE
 	bool "Generic support for simple MPC5200 based boards"
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index 1ecbf17..6153886 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -82,11 +82,9 @@
 		return;
 	}
 
-	for (pcictrl = NULL;;) {
-		pcictrl = of_get_next_child(root, pcictrl);
-		if ((pcictrl == NULL) || (strcmp(pcictrl->name, "pci") == 0))
+	for_each_child_of_node(root, pcictrl)
+		if (of_node_name_eq(pcictrl, "pci"))
 			break;
-	}
 
 	of_node_put(root);
 
diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c
index c94c385..3181aac 100644
--- a/arch/powerpc/platforms/52xx/lite5200.c
+++ b/arch/powerpc/platforms/52xx/lite5200.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Freescale Lite5200 board support
  *
@@ -7,10 +8,6 @@
  * Copyright 2006 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Description:
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 1fcab23..07c5bc4 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Support for 'media5200-platform' compatible boards.
  *
  * Copyright (C) 2008 Secret Lab Technologies Ltd.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Description:
  * This code implements support for the Freescape Media5200 platform
  * (built around the MPC5200 SoC).
@@ -17,7 +13,6 @@
  * a cascaded interrupt controller driver which attaches itself to the
  * Virtual IRQ subsystem after the primary mpc5200 interrupt controller
  * is initialized.
- *
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
index a80c627..2d01e9b 100644
--- a/arch/powerpc/platforms/52xx/mpc5200_simple.c
+++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Support for 'mpc5200-simple-platform' compatible boards.
  *
  * Written by Marian Balakowicz <m8@semihalf.com>
  * Copyright (C) 2007 Semihalf
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Description:
  * This code implements support for a simple MPC52xx based boards which
  * do not need a custom platform specific setup. Such boards are
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 17cf249..ba12dc1 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC5200 General Purpose Timer device driver
  *
  * Copyright (c) 2009 Secret Lab Technologies Ltd.
  * Copyright (c) 2008 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * This file is a driver for the the General Purpose Timer (gpt) devices
  * found on the MPC5200 SoC.  Each timer has an IO pin which can be used
  * for GPIO or can be used to raise interrupts.  The timer function can
@@ -628,7 +624,7 @@
 	}
 
 	file->private_data = mpc52xx_gpt_wdt;
-	return nonseekable_open(inode, file);
+	return stream_open(inode, file);
 }
 
 static int mpc52xx_wdt_release(struct inode *inode, struct file *file)
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
index 7bb42a0..05e1947 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * LocalPlus Bus FIFO driver for the Freescale MPC52xx.
  *
  * Copyright (C) 2009 Secret Lab Technologies Ltd.
  *
- * This file is released under the GPLv2
- *
  * Todo:
  * - Add support for multiple requests to be queued.
  */
diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig
index 6e04099..1af81de 100644
--- a/arch/powerpc/platforms/82xx/Kconfig
+++ b/arch/powerpc/platforms/82xx/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 menuconfig PPC_82xx
 	bool "82xx-based boards (PQ II)"
-	depends on 6xx
+	depends on PPC_BOOK3S_32
 
 if PPC_82xx
 
@@ -51,11 +51,10 @@
 
 config PQ2ADS
 	bool
-	default n
 
 config 8260
 	bool
-	depends on 6xx
+	depends on PPC_BOOK3S_32
 	select CPM2
 	help
 	  The MPC8260 is a typical embedded CPU made by Freescale.  Selecting
diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c
index 8fec050..369ebb1 100644
--- a/arch/powerpc/platforms/82xx/ep8248e.c
+++ b/arch/powerpc/platforms/82xx/ep8248e.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Embedded Planet EP8248E support
  *
  * Copyright 2007 Freescale Semiconductor, Inc.
  * Author: Scott Wood <scottwood@freescale.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c
index 28860e4..745ed61 100644
--- a/arch/powerpc/platforms/82xx/km82xx.c
+++ b/arch/powerpc/platforms/82xx/km82xx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Keymile km82xx support
  * Copyright 2008-2011 DENX Software Engineering GmbH
@@ -6,11 +7,6 @@
  * based on code from:
  * Copyright 2007 Freescale Semiconductor, Inc.
  * Author: Scott Wood <scottwood@freescale.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/platforms/82xx/m82xx_pci.h b/arch/powerpc/platforms/82xx/m82xx_pci.h
index 65e38a7..d07c4d7 100644
--- a/arch/powerpc/platforms/82xx/m82xx_pci.h
+++ b/arch/powerpc/platforms/82xx/m82xx_pci.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _PPC_KERNEL_M82XX_PCI_H
 #define _PPC_KERNEL_M82XX_PCI_H
 
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define SIU_INT_IRQ1   ((uint)0x13 + CPM_IRQ_OFFSET)
diff --git a/arch/powerpc/platforms/82xx/mpc8272_ads.c b/arch/powerpc/platforms/82xx/mpc8272_ads.c
index d23c10a..3fe1a65 100644
--- a/arch/powerpc/platforms/82xx/mpc8272_ads.c
+++ b/arch/powerpc/platforms/82xx/mpc8272_ads.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8272 ADS board support
  *
@@ -6,11 +7,6 @@
  *
  * Based on code by Vitaly Bordug <vbordug@ru.mvista.com>
  * Copyright (c) 2006 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/platforms/82xx/pq2.c b/arch/powerpc/platforms/82xx/pq2.c
index c4f7029..1cdd5ed 100644
--- a/arch/powerpc/platforms/82xx/pq2.c
+++ b/arch/powerpc/platforms/82xx/pq2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Common PowerQUICC II code.
  *
@@ -7,11 +8,6 @@
  * Based on code by Vitaly Bordug <vbordug@ru.mvista.com>
  * pq2_restart fix by Wade Farnsworth <wfarnsworth@mvista.com>
  * Copyright (c) 2006 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <asm/cpm2.h>
diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
index 8b065bd..096cc0d 100644
--- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
+++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * PQ2 ADS-style PCI interrupt controller
  *
@@ -6,10 +7,6 @@
  *
  * Loosely based on mpc82xx ADS support by Vitaly Bordug <vbordug@ru.mvista.com>
  * Copyright (c) 2006 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/platforms/82xx/pq2ads.h b/arch/powerpc/platforms/82xx/pq2ads.h
index 6cf0f97..9d0bf74 100644
--- a/arch/powerpc/platforms/82xx/pq2ads.h
+++ b/arch/powerpc/platforms/82xx/pq2ads.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * PQ2/mpc8260 board-specific stuff
  *
@@ -11,11 +12,6 @@
  *
  * Copyright (c) 2001 Dan Malek <dan@embeddedalley.com>
  * Copyright (c) 2006 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifdef __KERNEL__
diff --git a/arch/powerpc/platforms/82xx/pq2fads.c b/arch/powerpc/platforms/82xx/pq2fads.c
index 6c654dc..a740821 100644
--- a/arch/powerpc/platforms/82xx/pq2fads.c
+++ b/arch/powerpc/platforms/82xx/pq2fads.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * PQ2FADS board support
  *
@@ -6,10 +7,6 @@
  *
  * Loosely based on mp82xx ADS support by Vitaly Bordug <vbordug@ru.mvista.com>
  * Copyright (c) 2006 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig
index 071f53b..bee1197 100644
--- a/arch/powerpc/platforms/83xx/Kconfig
+++ b/arch/powerpc/platforms/83xx/Kconfig
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 menuconfig PPC_83xx
 	bool "83xx-based boards"
-	depends on 6xx
+	depends on PPC_BOOK3S_32
 	select PPC_UDBG_16550
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 	select FSL_PCI if PCI
 	select FSL_SOC
 	select IPIC
diff --git a/arch/powerpc/platforms/83xx/asp834x.c b/arch/powerpc/platforms/83xx/asp834x.c
index 575afd6..2847487 100644
--- a/arch/powerpc/platforms/83xx/asp834x.c
+++ b/arch/powerpc/platforms/83xx/asp834x.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/83xx/asp834x.c
  *
@@ -7,11 +8,6 @@
  * Copyright 2008 Codehermit
  *
  * Maintainer: Bryan O'Donoghue <bodonoghue@codhermit.ie>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/pci.h>
diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index d8642a4..273145a 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2008-2011 DENX Software Engineering GmbH
  * Author: Heiko Schocher <hs@denx.de>
  *
  * Description:
  * Keymile 83xx platform specific routines.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index d2ef39f..0967bdf 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Power Management and GPIO expander driver for MPC8349E-mITX-compatible MCU
  *
  * Copyright (c) 2008  MontaVista Software, Inc.
  *
  * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c
index d75c981..f46d7bf 100644
--- a/arch/powerpc/platforms/83xx/misc.c
+++ b/arch/powerpc/platforms/83xx/misc.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * misc setup functions for MPC83xx
  *
  * Maintainer: Kumar Gala <galak@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -14,6 +10,7 @@
 #include <linux/of_platform.h>
 #include <linux/pci.h>
 
+#include <asm/debug.h>
 #include <asm/io.h>
 #include <asm/hw_irq.h>
 #include <asm/ipic.h>
@@ -150,3 +147,19 @@
 
 	mpc83xx_setup_pci();
 }
+
+int machine_check_83xx(struct pt_regs *regs)
+{
+	u32 mask = 1 << (31 - IPIC_MCP_WDT);
+
+	if (!(regs->msr & SRR1_MCE_MCP) || !(ipic_get_mcp_status() & mask))
+		return machine_check_generic(regs);
+	ipic_clear_mcp_status(mask);
+
+	if (debugger_fault_handler(regs))
+		return 1;
+
+	die("Watchdog NMI Reset", regs, 0);
+
+	return 1;
+}
diff --git a/arch/powerpc/platforms/83xx/mpc830x_rdb.c b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
index 272c41c..51426e8 100644
--- a/arch/powerpc/platforms/83xx/mpc830x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/83xx/mpc830x_rdb.c
  *
@@ -6,11 +7,6 @@
  *
  * Copyright (C) Freescale Semiconductor, Inc. 2009. All rights reserved.
  * Copyright (C) 2010. Ilya Yanok, Emcraft Systems, yanok@emcraft.com
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/pci.h>
diff --git a/arch/powerpc/platforms/83xx/mpc831x_rdb.c b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
index fd80fd5..5ccd57a 100644
--- a/arch/powerpc/platforms/83xx/mpc831x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/83xx/mpc831x_rdb.c
  *
@@ -6,11 +7,6 @@
  * Author: Lo Wlison <r43300@freescale.com>
  *
  * Copyright (C) Freescale Semiconductor, Inc. 2006. All rights reserved.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/pci.h>
diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c
index 74c154e..b428835 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2006 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Description:
  * MPC832xE MDS board specific routines.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
index 4389865..4588ce6 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/83xx/mpc832x_rdb.c
  *
@@ -7,11 +8,6 @@
  * MPC832x RDB board specific routines.
  * This file is based on mpc832x_mds.c and mpc8313_rdb.c
  * Author: Michael Barkowski <michael.barkowski@freescale.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/pci.h>
diff --git a/arch/powerpc/platforms/83xx/mpc834x_itx.c b/arch/powerpc/platforms/83xx/mpc834x_itx.c
index 73a5267..ebfd139 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_itx.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_itx.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/83xx/mpc834x_itx.c
  *
  * MPC834x ITX board specific routines
  *
  * Maintainer: Kumar Gala <galak@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/83xx/mpc834x_mds.c b/arch/powerpc/platforms/83xx/mpc834x_mds.c
index 009cfc1..356228e 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_mds.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/83xx/mpc834x_mds.c
  *
  * MPC834x MDS board specific routines
  *
  * Maintainer: Kumar Gala <galak@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c
index fd44dd0..4a4efa9 100644
--- a/arch/powerpc/platforms/83xx/mpc836x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2006 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -9,11 +10,6 @@
  *
  * Changelog:
  * Jun 21, 2006	Initial version
- *
- * This program is free software; you can redistribute it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/83xx/mpc836x_rdk.c b/arch/powerpc/platforms/83xx/mpc836x_rdk.c
index 93f024f..9923059 100644
--- a/arch/powerpc/platforms/83xx/mpc836x_rdk.c
+++ b/arch/powerpc/platforms/83xx/mpc836x_rdk.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8360E-RDK board file.
  *
@@ -5,11 +6,6 @@
  * Copyright (c) 2007-2008  MontaVista Software, Inc.
  *
  * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/83xx/mpc837x_mds.c b/arch/powerpc/platforms/83xx/mpc837x_mds.c
index 3b34cc1..9d3721c 100644
--- a/arch/powerpc/platforms/83xx/mpc837x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_mds.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/83xx/mpc837x_mds.c
  *
  * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
  *
  * MPC837x MDS board specific routines
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation;  either version 2 of the License, or (at your
- * option) any later version.
  */
 
 #include <linux/pci.h>
diff --git a/arch/powerpc/platforms/83xx/mpc837x_rdb.c b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
index 0c55fa6..7c45f7a 100644
--- a/arch/powerpc/platforms/83xx/mpc837x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/83xx/mpc837x_rdb.c
  *
  * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
  *
  * MPC837x RDB board specific routines
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/pci.h>
diff --git a/arch/powerpc/platforms/83xx/suspend-asm.S b/arch/powerpc/platforms/83xx/suspend-asm.S
index 3d1ecd2..3acd747 100644
--- a/arch/powerpc/platforms/83xx/suspend-asm.S
+++ b/arch/powerpc/platforms/83xx/suspend-asm.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Enter and leave deep sleep state on MPC83xx
  *
  * Copyright (c) 2006-2008 Freescale Semiconductor, Inc.
  * Author: Scott Wood <scottwood@freescale.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include <asm/page.h>
@@ -26,13 +23,13 @@
 #define SS_MSR		0x74
 #define SS_SDR1		0x78
 #define SS_LR		0x7c
-#define SS_SPRG		0x80 /* 4 SPRGs */
-#define SS_DBAT		0x90 /* 8 DBATs */
-#define SS_IBAT		0xd0 /* 8 IBATs */
-#define SS_TB		0x110
-#define SS_CR		0x118
-#define SS_GPREG	0x11c /* r12-r31 */
-#define STATE_SAVE_SIZE 0x16c
+#define SS_SPRG		0x80 /* 8 SPRGs */
+#define SS_DBAT		0xa0 /* 8 DBATs */
+#define SS_IBAT		0xe0 /* 8 IBATs */
+#define SS_TB		0x120
+#define SS_CR		0x128
+#define SS_GPREG	0x12c /* r12-r31 */
+#define STATE_SAVE_SIZE 0x17c
 
 	.section .data
 	.align	5
@@ -103,6 +100,16 @@
 	stw	r7, SS_SPRG+12(r3)
 	stw	r8, SS_SDR1(r3)
 
+	mfspr	r4, SPRN_SPRG4
+	mfspr	r5, SPRN_SPRG5
+	mfspr	r6, SPRN_SPRG6
+	mfspr	r7, SPRN_SPRG7
+
+	stw	r4, SS_SPRG+16(r3)
+	stw	r5, SS_SPRG+20(r3)
+	stw	r6, SS_SPRG+24(r3)
+	stw	r7, SS_SPRG+28(r3)
+
 	mfspr	r4, SPRN_DBAT0U
 	mfspr	r5, SPRN_DBAT0L
 	mfspr	r6, SPRN_DBAT1U
@@ -493,6 +500,16 @@
 	mtspr	SPRN_IBAT7U, r6
 	mtspr	SPRN_IBAT7L, r7
 
+	lwz	r4, SS_SPRG+16(r3)
+	lwz	r5, SS_SPRG+20(r3)
+	lwz	r6, SS_SPRG+24(r3)
+	lwz	r7, SS_SPRG+28(r3)
+
+	mtspr	SPRN_SPRG4, r4
+	mtspr	SPRN_SPRG5, r5
+	mtspr	SPRN_SPRG6, r6
+	mtspr	SPRN_SPRG7, r7
+
 	lwz	r4, SS_SPRG+0(r3)
 	lwz	r5, SS_SPRG+4(r3)
 	lwz	r6, SS_SPRG+8(r3)
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 7fa3e19..bb147d3 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * MPC83xx suspend support
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2006-2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include <linux/pm.h>
diff --git a/arch/powerpc/platforms/83xx/usb.c b/arch/powerpc/platforms/83xx/usb.c
index 5c31d82..3d247d7 100644
--- a/arch/powerpc/platforms/83xx/usb.c
+++ b/arch/powerpc/platforms/83xx/usb.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Freescale 83xx USB SOC setup code
  *
  * Copyright (C) 2007 Freescale Semiconductor, Inc.
  * Author: Li Yang
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 
@@ -221,8 +217,10 @@
 	int ret = 0;
 
 	np = of_find_compatible_node(NULL, NULL, "fsl-usb2-dr");
-	if (!np || !of_device_is_available(np))
+	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"))) {
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 68920d4..fa3d29d 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -5,7 +5,7 @@
 	select FSL_SOC
 	select PPC_UDBG_16550
 	select MPIC
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 	select FSL_PCI if PCI
 	select SERIAL_8250_EXTENDED if SERIAL_8250
 	select SERIAL_8250_SHARE_IRQ if SERIAL_8250
@@ -66,7 +66,7 @@
 	bool "Freescale MPC85xx CDS"
 	select DEFAULT_UIMAGE
 	select PPC_I8259
-	select HAS_RAPIDIO
+	select HAVE_RAPIDIO
 	help
 	  This option enables support for the MPC85xx CDS board
 
@@ -74,7 +74,7 @@
 	bool "Freescale MPC85xx MDS"
 	select DEFAULT_UIMAGE
 	select PHYLIB if NETDEVICES
-	select HAS_RAPIDIO
+	select HAVE_RAPIDIO
 	select SWIOTLB
 	help
 	  This option enables support for the MPC85xx MDS board
@@ -147,10 +147,10 @@
 	  This option enables support for the Socrates board.
 
 config KSI8560
-        bool "Emerson KSI8560"
-        select DEFAULT_UIMAGE
-        help
-          This option enables support for the Emerson KSI8560 board
+	bool "Emerson KSI8560"
+	select DEFAULT_UIMAGE
+	help
+	  This option enables support for the Emerson KSI8560 board
 
 config XES_MPC85xx
 	bool "X-ES single-board computer"
@@ -219,7 +219,7 @@
 	help
 	  This option enables support for the Prodrive PPA8548 board.
 	select DEFAULT_UIMAGE
-	select HAS_RAPIDIO
+	select HAVE_RAPIDIO
 
 config GE_IMP3A
 	bool "GE Intelligent Platforms IMP3A"
@@ -277,7 +277,7 @@
 	select SWIOTLB
 	select GPIOLIB
 	select GPIO_MPC8XXX
-	select HAS_RAPIDIO
+	select HAVE_RAPIDIO
 	select PPC_EPAPR_HV_PIC
 	help
 	  This option enables support for the FSL CoreNet based boards.
diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c
index d2f4556..bcbbeb5 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_qds.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * BSC913xQDS Board Setup
  *
@@ -6,11 +7,6 @@
  *   Priyanka Jain <Priyanka.Jain@freescale.com>
  *
  * Copyright 2014 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
index 0ffdb4a..f78e5d3 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_rdb.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * BSC913xRDB Board Setup
  *
  * Author: Priyanka Jain <Priyanka.Jain@freescale.com>
  *
  * Copyright 2011-2012 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c
index 4df1b40..8d9a250 100644
--- a/arch/powerpc/platforms/85xx/c293pcie.c
+++ b/arch/powerpc/platforms/85xx/c293pcie.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * C293PCIE Board Setup
  *
  * Copyright 2013 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c
index 954e5e8..fe06064 100644
--- a/arch/powerpc/platforms/85xx/common.c
+++ b/arch/powerpc/platforms/85xx/common.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Routines common to most mpc85xx-based boards.
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/of_irq.h>
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index ac191a7..7ee2c66 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Corenet based SoC DS Setup
  *
  * Maintained by Kumar Gala (see MAINTAINERS for contact information)
  *
  * Copyright 2009-2011 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -27,6 +23,7 @@
 #include <asm/udbg.h>
 #include <asm/mpic.h>
 #include <asm/ehv_pic.h>
+#include <asm/swiotlb.h>
 #include <soc/fsl/qe/qe_ic.h>
 
 #include <linux/of_platform.h>
@@ -68,16 +65,6 @@
 
 	swiotlb_detect_4g();
 
-#if defined(CONFIG_FSL_PCI) && defined(CONFIG_ZONE_DMA32)
-	/*
-	 * Inbound windows don't cover the full lower 4 GiB
-	 * due to conflicts with PCICSRBAR and outbound windows,
-	 * so limit the DMA32 zone to 2 GiB, to allow consistent
-	 * allocations to succeed.
-	 */
-	limit_zone_pfn(ZONE_DMA32, 1UL << (31 - PAGE_SHIFT));
-#endif
-
 	pr_info("%s board\n", ppc_md.name);
 
 	mpc85xx_qe_init();
@@ -233,7 +220,3 @@
 };
 
 machine_arch_initcall(corenet_generic, corenet_gen_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(corenet_generic, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
index f29c6f0..83a0f7a 100644
--- a/arch/powerpc/platforms/85xx/ge_imp3a.c
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * GE IMP3A Board Setup
  *
@@ -5,11 +6,6 @@
  *
  * Copyright 2010 GE Intelligent Platforms Embedded Systems, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Based on: mpc85xx_ds.c (MPC85xx DS Board Setup)
  * Copyright 2007 Freescale Semiconductor Inc.
  */
@@ -202,8 +198,6 @@
 
 machine_arch_initcall(ge_imp3a, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(ge_imp3a, swiotlb_setup_bus_notifier);
-
 define_machine(ge_imp3a) {
 	.name			= "GE_IMP3A",
 	.probe			= ge_imp3a_probe,
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index 94a7f92..53bccb8 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8536 DS Board Setup
  *
  * Copyright 2008 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -57,8 +53,6 @@
 
 machine_arch_initcall(mpc8536_ds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(mpc8536_ds, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
index f3e055f..a34fc03 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
@@ -1,14 +1,10 @@
+// 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.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index 224db30..6b1436a 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -1,14 +1,10 @@
+// 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.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index dc9e035..2157a80 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC85xx DS Board Setup
  *
@@ -5,11 +6,6 @@
  * Roy Zang <tie-fei.zang@freescale.com>
  * 	- Add PCI/PCI Exprees support
  * Copyright 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -174,10 +170,6 @@
 machine_arch_initcall(mpc8572_ds, mpc85xx_common_publish_devices);
 machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(mpc8544_ds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(mpc8572_ds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(p2020_ds, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index d7e440e..5ca2542 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2006-2010, 2012-2013 Freescale Semiconductor, Inc.
  * All rights reserved.
@@ -10,11 +11,6 @@
  *
  * Description:
  * MPC85xx MDS board specific routines.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -367,10 +363,6 @@
 machine_arch_initcall(mpc8569_mds, mpc85xx_publish_devices);
 machine_arch_initcall(p1021_mds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(mpc8568_mds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(mpc8569_mds, swiotlb_setup_bus_notifier);
-machine_arch_initcall(p1021_mds, swiotlb_setup_bus_notifier);
-
 static void __init mpc85xx_mds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_pm_ops.c b/arch/powerpc/platforms/85xx/mpc85xx_pm_ops.c
index f05325f..7c0133f 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_pm_ops.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_pm_ops.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC85xx PM operators
  *
  * Copyright 2015 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #define pr_fmt(fmt) "%s: " fmt, __func__
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index 1006950..d3c540e 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC85xx RDB Board Setup
  *
  * Copyright 2009,2012-2013 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c
index d5af072..69d5aa0 100644
--- a/arch/powerpc/platforms/85xx/mvme2500.c
+++ b/arch/powerpc/platforms/85xx/mvme2500.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Board setup routines for the Emerson/Artesyn MVME2500
  *
@@ -9,13 +10,7 @@
  *	Tom Armistead (tom.armistead@emerson.com)
  *	Copyright 2012 Emerson
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Author Alessio Igor Bogani <alessio.bogani@elettra.eu>
- *
  */
 
 #include <linux/pci.h>
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 78d13b3..2485528 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * P1010RDB Board Setup
  *
  * Copyright 2011 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -55,7 +51,6 @@
 }
 
 machine_arch_initcall(p1010_rdb, mpc85xx_common_publish_devices);
-machine_arch_initcall(p1010_rdb, swiotlb_setup_bus_notifier);
 
 /*
  * Called very early, device-tree isn't unflattened
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 9fb57f7..1f1af05 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -548,8 +548,6 @@
 
 machine_arch_initcall(p1022_ds, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(p1022_ds, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
index 276e00a..fd9e3e7 100644
--- a/arch/powerpc/platforms/85xx/p1022_rdk.c
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -128,8 +128,6 @@
 
 machine_arch_initcall(p1022_rdk, mpc85xx_common_publish_devices);
 
-machine_arch_initcall(p1022_rdk, swiotlb_setup_bus_notifier);
-
 /*
  * Called very early, device-tree isn't unflattened
  */
diff --git a/arch/powerpc/platforms/85xx/p1023_rdb.c b/arch/powerpc/platforms/85xx/p1023_rdb.c
index 3e8cd03..3b9cc49 100644
--- a/arch/powerpc/platforms/85xx/p1023_rdb.c
+++ b/arch/powerpc/platforms/85xx/p1023_rdb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2010-2011, 2013 Freescale Semiconductor, Inc.
  *
@@ -5,11 +6,6 @@
  *
  * Description:
  * P1023 RDB Board Setup
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/85xx/ppa8548.c b/arch/powerpc/platforms/85xx/ppa8548.c
index 33c5ba6..0faf299 100644
--- a/arch/powerpc/platforms/85xx/ppa8548.c
+++ b/arch/powerpc/platforms/85xx/ppa8548.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * ppa8548 setup and early boot code.
  *
@@ -7,11 +8,6 @@
  *
  * Based on the SBC8548 support - Copyright 2007 Wind River Systems Inc.
  * Based on the MPC8548CDS support - Copyright 2005 Freescale Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c
index b63a854..a43b8c3 100644
--- a/arch/powerpc/platforms/85xx/qemu_e500.c
+++ b/arch/powerpc/platforms/85xx/qemu_e500.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Paravirt target for a generic QEMU e500 machine
  *
@@ -8,11 +9,6 @@
  * an interface contract with QEMU.
  *
  * Copyright 2012 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -22,6 +18,7 @@
 #include <asm/time.h>
 #include <asm/udbg.h>
 #include <asm/mpic.h>
+#include <asm/swiotlb.h>
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
 #include "smp.h"
@@ -45,15 +42,6 @@
 
 	fsl_pci_assign_primary();
 	swiotlb_detect_4g();
-#if defined(CONFIG_FSL_PCI) && defined(CONFIG_ZONE_DMA32)
-	/*
-	 * Inbound windows don't cover the full lower 4 GiB
-	 * due to conflicts with PCICSRBAR and outbound windows,
-	 * so limit the DMA32 zone to 2 GiB, to allow consistent
-	 * allocations to succeed.
-	 */
-	limit_zone_pfn(ZONE_DMA32, 1UL << (31 - PAGE_SHIFT));
-#endif
 	mpc85xx_smp_init();
 }
 
diff --git a/arch/powerpc/platforms/85xx/sbc8548.c b/arch/powerpc/platforms/85xx/sbc8548.c
index 2c67084..dd97ef2 100644
--- a/arch/powerpc/platforms/85xx/sbc8548.c
+++ b/arch/powerpc/platforms/85xx/sbc8548.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Wind River SBC8548 setup and early boot code.
  *
@@ -6,12 +7,6 @@
  * By Paul Gortmaker (see MAINTAINERS for contact information)
  *
  * Based largely on the MPC8548CDS support - Copyright 2005 Freescale Inc.
- *
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c
index 21d6aaa..98ae640 100644
--- a/arch/powerpc/platforms/85xx/sgy_cts1000.c
+++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Servergy CTS-1000 Setup
  *
  * Maintained by Ben Collins <ben.c@servergy.com>
  *
  * Copyright 2012 by Servergy, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/platform_device.h>
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 7e966f4..8c7ea24 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Author: Andy Fleming <afleming@freescale.com>
  * 	   Kumar Gala <galak@kernel.crashing.org>
  *
  * Copyright 2006-2008, 2011-2012, 2015 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -216,8 +212,8 @@
 
 	/* Map the spin table */
 	if (ioremappable)
-		spin_table = ioremap_prot(*cpu_rel_addr,
-			sizeof(struct epapr_spin_table), _PAGE_COHERENT);
+		spin_table = ioremap_coherent(*cpu_rel_addr,
+					      sizeof(struct epapr_spin_table));
 	else
 		spin_table = phys_to_virt(*cpu_rel_addr);
 
diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c
index 8da4ed9..166b351 100644
--- a/arch/powerpc/platforms/85xx/socrates.c
+++ b/arch/powerpc/platforms/85xx/socrates.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2008 Emcraft Systems
  * Sergei Poselenov <sposelenov@emcraft.com>
@@ -14,11 +15,6 @@
  * Based on original work by
  * 	Kumar Gala <kumar.gala@freescale.com>
  *      Copyright 2004 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 38d4ba9..199a137 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Copyright (C) 2008 Ilya Yanok, Emcraft Systems
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <linux/irq.h>
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.h b/arch/powerpc/platforms/85xx/socrates_fpga_pic.h
index 21d7d8e..c592b8b 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.h
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.h
@@ -1,11 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright (C) 2008 Ilya Yanok, Emcraft Systems
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #ifndef SOCRATES_FPGA_PIC_H
diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c
index 1a1d44e..69e917e 100644
--- a/arch/powerpc/platforms/85xx/stx_gp3.c
+++ b/arch/powerpc/platforms/85xx/stx_gp3.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Based on MPC8560 ADS and arch/ppc stx_gp3 ports
  *
@@ -13,11 +14,6 @@
  *
  * Ported to 2.6, Matt Porter <mporter@kernel.crashing.org>
  * Copyright 2004-2005 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/85xx/t1042rdb_diu.c b/arch/powerpc/platforms/85xx/t1042rdb_diu.c
index dac36ba..767eed9 100644
--- a/arch/powerpc/platforms/85xx/t1042rdb_diu.c
+++ b/arch/powerpc/platforms/85xx/t1042rdb_diu.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * T1042 platform DIU operation
  *
  * Copyright 2014 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
@@ -39,7 +35,7 @@
  */
 static void t1042rdb_set_monitor_port(enum fsl_diu_monitor_port port)
 {
-	static void __iomem *cpld_base;
+	void __iomem *cpld_base;
 
 	cpld_base = of_iomap(cpld_node, 0);
 	if (!cpld_base) {
diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c
index 9fc20a3..95a1a11 100644
--- a/arch/powerpc/platforms/85xx/tqm85xx.c
+++ b/arch/powerpc/platforms/85xx/tqm85xx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Based on MPC8560 ADS and arch/ppc tqm85xx ports
  *
@@ -11,11 +12,6 @@
  * Based on original work by
  * 	Kumar Gala <kumar.gala@freescale.com>
  *      Copyright 2004 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c
index 360f625..720b0c0 100644
--- a/arch/powerpc/platforms/85xx/twr_p102x.c
+++ b/arch/powerpc/platforms/85xx/twr_p102x.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2010-2011, 2013 Freescale Semiconductor, Inc.
  *
@@ -5,11 +6,6 @@
  *
  * Description:
  * TWR-P102x Board Setup
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 77e618d..d54e1ae 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2009 Extreme Engineering Solutions, Inc.
  *
@@ -6,10 +7,6 @@
  * Based on mpc85xx_ds code from Freescale Semiconductor, Inc.
  *
  * Author: Nate Case <ncase@xes-inc.com>
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index bcd179d..07a9d60 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -2,7 +2,7 @@
 config PPC_86xx
 menuconfig PPC_86xx
 	bool "86xx-based boards"
-	depends on 6xx
+	depends on PPC_BOOK3S_32
 	select FSL_SOC
 	select ALTIVEC
 	help
@@ -15,7 +15,7 @@
 	select PPC_I8259
 	select DEFAULT_UIMAGE
 	select FSL_ULI1575 if PCI
-	select HAS_RAPIDIO
+	select HAVE_RAPIDIO
 	select SWIOTLB
 	help
 	  This option enables support for the MPC8641 HPCN board.
@@ -57,20 +57,20 @@
 	select MMIO_NVRAM
 	select GPIOLIB
 	select GE_FPGA
-	select HAS_RAPIDIO
+	select HAVE_RAPIDIO
 	help
 	  This option enables support for the GE SBC610.
 
 config MVME7100
-        bool "Artesyn MVME7100"
-        help
-          This option enables support for the Emerson/Artesyn MVME7100 board.
+	bool "Artesyn MVME7100"
+	help
+	  This option enables support for the Emerson/Artesyn MVME7100 board.
 
 endif
 
 config MPC8641
 	bool
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 	select FSL_PCI if PCI
 	select PPC_UDBG_16550
 	select MPIC
@@ -79,7 +79,7 @@
 
 config MPC8610
 	bool
-	select PPC_PCI_CHOICE
+	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 0f7b7fc..0069d38 100644
--- a/arch/powerpc/platforms/86xx/common.c
+++ b/arch/powerpc/platforms/86xx/common.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Routines common to most mpc86xx-based boards.
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index 6b99300..44bbbc5 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * GE PPC9A board support
  *
@@ -5,11 +6,6 @@
  *
  * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Based on: mpc86xx_hpcn.c (MPC86xx HPCN board specific routines)
  * Copyright 2006 Freescale Semiconductor Inc.
  *
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 8cdeca0..46d6d3d 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * GE SBC310 board support
  *
@@ -5,11 +6,6 @@
  *
  * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Based on: mpc86xx_hpcn.c (MPC86xx HPCN board specific routines)
  * Copyright 2006 Freescale Semiconductor Inc.
  *
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index da8723a..acf2c6c 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * GE SBC610 board support
  *
@@ -5,11 +6,6 @@
  *
  * Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Based on: mpc86xx_hpcn.c (MPC86xx HPCN board specific routines)
  * Copyright 2006 Freescale Semiconductor Inc.
  *
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index a5d73fa..96b27f6 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC8610 HPCD board specific routines
  *
@@ -9,11 +10,6 @@
  * All the integrated device in ULI use sideband interrupt.
  *
  * Copyright 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/86xx/mpc86xx.h b/arch/powerpc/platforms/86xx/mpc86xx.h
index 53500db..61e52c7 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx.h
+++ b/arch/powerpc/platforms/86xx/mpc86xx.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2006 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef __MPC86XX_H__
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 17c6cd3..b697918 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC86xx HPCN board specific routines
  *
@@ -5,11 +6,6 @@
  * Initial author: Xianghua Xiao <x.xiao@freescale.com>
  *
  * Copyright 2006 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -121,7 +117,6 @@
 	return 0;
 }
 machine_arch_initcall(mpc86xx_hpcn, declare_of_platform_devices);
-machine_arch_initcall(mpc86xx_hpcn, swiotlb_setup_bus_notifier);
 
 define_machine(mpc86xx_hpcn) {
 	.name			= "MPC86xx HPCN",
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
index 020e84a..5b91ea5 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_smp.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Author: Xianghua Xiao <x.xiao@freescale.com>
  *         Zhang Wei <wei.zhang@freescale.com>
  *
  * Copyright 2006 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -86,8 +82,7 @@
 		mdelay(1);
 
 	/* Restore the exception vector */
-	*vector = save_vector;
-	flush_icache_range((unsigned long) vector, (unsigned long) vector + 4);
+	patch_instruction(vector, save_vector);
 
 	local_irq_restore(flags);
 
diff --git a/arch/powerpc/platforms/86xx/mvme7100.c b/arch/powerpc/platforms/86xx/mvme7100.c
index 835352e..ee98361 100644
--- a/arch/powerpc/platforms/86xx/mvme7100.c
+++ b/arch/powerpc/platforms/86xx/mvme7100.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Board setup routines for the Emerson/Artesyn MVME7100
  *
@@ -14,12 +15,6 @@
  *
  *	Martyn Welch <martyn.welch@ge.com>
  *	Copyright 2008 GE Intelligent Platforms Embedded Systems, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 #include <linux/pci.h>
diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c
index a6c695f..2c32c34 100644
--- a/arch/powerpc/platforms/86xx/pic.c
+++ b/arch/powerpc/platforms/86xx/pic.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2008 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/86xx/sbc8641d.c b/arch/powerpc/platforms/86xx/sbc8641d.c
index 93db35d..dc23dd3 100644
--- a/arch/powerpc/platforms/86xx/sbc8641d.c
+++ b/arch/powerpc/platforms/86xx/sbc8641d.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SBC8641D board specific routines
  *
@@ -6,11 +7,6 @@
  * By Paul Gortmaker (see MAINTAINERS for contact information)
  *
  * Based largely on the 8641 HPCN support by Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index d408162..e0fe670 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -157,6 +157,13 @@
 	help
 	  Help not implemented yet, coming soon.
 
+config SMC_UCODE_PATCH
+	bool "SMC relocation patch"
+	help
+	  This microcode relocates SMC1 and SMC2 parameter RAMs at
+	  offset 0x1ec0 and 0x1fc0 to allow extended parameter RAM
+	  for SCC3 and SCC4.
+
 endchoice
 
 config UCODE_PATCH
diff --git a/arch/powerpc/platforms/8xx/Makefile b/arch/powerpc/platforms/8xx/Makefile
index 708ab09..27a7c6f 100644
--- a/arch/powerpc/platforms/8xx/Makefile
+++ b/arch/powerpc/platforms/8xx/Makefile
@@ -3,6 +3,8 @@
 # Makefile for the PowerPC 8xx linux kernel.
 #
 obj-y			+= m8xx_setup.o machine_check.o pic.o
+obj-$(CONFIG_CPM1)		+= cpm1.o
+obj-$(CONFIG_UCODE_PATCH)	+= micropatch.o
 obj-$(CONFIG_MPC885ADS)   += mpc885ads_setup.o
 obj-$(CONFIG_MPC86XADS)   += mpc86xads_setup.o
 obj-$(CONFIG_PPC_EP88XC)  += ep88xc.o
diff --git a/arch/powerpc/platforms/8xx/adder875.c b/arch/powerpc/platforms/8xx/adder875.c
index bcef9f6..651486a 100644
--- a/arch/powerpc/platforms/8xx/adder875.c
+++ b/arch/powerpc/platforms/8xx/adder875.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Analogue & Micro Adder MPC875 board support
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c
similarity index 97%
rename from arch/powerpc/sysdev/cpm1.c
rename to arch/powerpc/platforms/8xx/cpm1.c
index 4f8dcf1..0f65c51 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/platforms/8xx/cpm1.c
@@ -88,7 +88,8 @@
 {
 	int cpm_vec;
 
-	/* Get the vector by setting the ACK bit and then reading
+	/*
+	 * Get the vector by setting the ACK bit and then reading
 	 * the register.
 	 */
 	out_be16(&cpic_reg->cpic_civr, 1);
@@ -108,7 +109,8 @@
 	return 0;
 }
 
-/* The CPM can generate the error interrupt when there is a race condition
+/*
+ * The CPM can generate the error interrupt when there is a race condition
  * between generating and masking interrupts.  All we have to do is ACK it
  * and return.  This is a no-op function so we don't need any special
  * tests in the interrupt handler.
@@ -208,12 +210,10 @@
 	cpmp = &mpc8xx_immr->im_cpm;
 
 #ifndef CONFIG_PPC_EARLY_DEBUG_CPM
-	/* Perform a reset.
-	*/
+	/* Perform a reset. */
 	out_be16(&cpmp->cp_cpcr, CPM_CR_RST | CPM_CR_FLG);
 
-	/* Wait for it.
-	*/
+	/* Wait for it. */
 	while (in_be16(&cpmp->cp_cpcr) & CPM_CR_FLG);
 #endif
 
@@ -221,7 +221,8 @@
 	cpm_load_patch(cpmp);
 #endif
 
-	/* Set SDMA Bus Request priority 5.
+	/*
+	 * Set SDMA Bus Request priority 5.
 	 * On 860T, this also enables FEC priority 6.  I am not sure
 	 * this is what we really want for some applications, but the
 	 * manual recommends it.
@@ -263,7 +264,8 @@
 }
 EXPORT_SYMBOL(cpm_command);
 
-/* Set a baud rate generator.  This needs lots of work.  There are
+/*
+ * Set a baud rate generator.  This needs lots of work.  There are
  * four BRGs, any of which can be wired to any channel.
  * The internal baud rate clock is the system clock divided by 16.
  * This assumes the baudrate is 16x oversampled by the uart.
@@ -277,11 +279,11 @@
 {
 	u32 __iomem *bp;
 
-	/* This is good enough to get SMCs running.....
-	*/
+	/* This is good enough to get SMCs running..... */
 	bp = &cpmp->cp_brgc1;
 	bp += brg;
-	/* The BRG has a 12-bit counter.  For really slow baud rates (or
+	/*
+	 * The BRG has a 12-bit counter.  For really slow baud rates (or
 	 * really fast processors), we may have to further divide by 16.
 	 */
 	if (((BRG_UART_CLK / rate) - 1) < 4096)
diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c
index 027c42d..f1c805c 100644
--- a/arch/powerpc/platforms/8xx/m8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/m8xx_setup.c
@@ -66,7 +66,7 @@
 	int found = 0;
 
 	/* The cpu node should have timebase and clock frequency properties */
-	cpu = of_find_node_by_type(NULL, "cpu");
+	cpu = of_get_cpu_node(0, NULL);
 
 	if (cpu) {
 		fp = of_get_property(cpu, name, NULL);
@@ -147,8 +147,9 @@
 	 * we have to enable the timebase).  The decrementer interrupt
 	 * is wired into the vector table, nothing to do here for that.
 	 */
-	cpu = of_find_node_by_type(NULL, "cpu");
+	cpu = of_get_cpu_node(0, NULL);
 	virq= irq_of_parse_and_map(cpu, 0);
+	of_node_put(cpu);
 	irq = virq_to_hw(virq);
 
 	sys_tmr2 = immr_map(im_sit);
diff --git a/arch/powerpc/platforms/8xx/machine_check.c b/arch/powerpc/platforms/8xx/machine_check.c
index 4020167..88dedf3 100644
--- a/arch/powerpc/platforms/8xx/machine_check.c
+++ b/arch/powerpc/platforms/8xx/machine_check.c
@@ -1,8 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -18,9 +15,9 @@
 	pr_err("Machine check in kernel mode.\n");
 	pr_err("Caused by (from SRR1=%lx): ", reason);
 	if (reason & 0x40000000)
-		pr_err("Fetch error at address %lx\n", regs->nip);
+		pr_cont("Fetch error at address %lx\n", regs->nip);
 	else
-		pr_err("Data access error at address %lx\n", regs->dar);
+		pr_cont("Data access error at address %lx\n", regs->dar);
 
 #ifdef CONFIG_PCI
 	/* the qspan pci read routines can cause machine checks -- Cort
diff --git a/arch/powerpc/platforms/8xx/micropatch.c b/arch/powerpc/platforms/8xx/micropatch.c
new file mode 100644
index 0000000..c80bd7a
--- /dev/null
+++ b/arch/powerpc/platforms/8xx/micropatch.c
@@ -0,0 +1,378 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Microcode patches for the CPM as supplied by Motorola.
+ * This is the one for IIC/SPI.  There is a newer one that
+ * also relocates SMC2, but this would require additional changes
+ * to uart.c, so I am holding off on that for a moment.
+ */
+#include <linux/init.h>
+#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/interrupt.h>
+#include <asm/irq.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/8xx_immap.h>
+#include <asm/cpm.h>
+#include <asm/cpm1.h>
+
+struct patch_params {
+	ushort rccr;
+	ushort cpmcr1;
+	ushort cpmcr2;
+	ushort cpmcr3;
+	ushort cpmcr4;
+};
+
+/*
+ * I2C/SPI relocation patch arrays.
+ */
+
+#ifdef CONFIG_I2C_SPI_UCODE_PATCH
+
+static char patch_name[] __initdata = "I2C/SPI";
+
+static struct patch_params patch_params __initdata = {
+	1, 0x802a, 0x8028, 0x802e, 0x802c,
+};
+
+static uint patch_2000[] __initdata = {
+	0x7FFFEFD9, 0x3FFD0000, 0x7FFB49F7, 0x7FF90000,
+	0x5FEFADF7, 0x5F89ADF7, 0x5FEFAFF7, 0x5F89AFF7,
+	0x3A9CFBC8, 0xE7C0EDF0, 0x77C1E1BB, 0xF4DC7F1D,
+	0xABAD932F, 0x4E08FDCF, 0x6E0FAFF8, 0x7CCF76CF,
+	0xFD1FF9CF, 0xABF88DC6, 0xAB5679F7, 0xB0937383,
+	0xDFCE79F7, 0xB091E6BB, 0xE5BBE74F, 0xB3FA6F0F,
+	0x6FFB76CE, 0xEE0DF9CF, 0x2BFBEFEF, 0xCFEEF9CF,
+	0x76CEAD24, 0x90B2DF9A, 0x7FDDD0BF, 0x4BF847FD,
+	0x7CCF76CE, 0xCFEF7E1F, 0x7F1D7DFD, 0xF0B6EF71,
+	0x7FC177C1, 0xFBC86079, 0xE722FBC8, 0x5FFFDFFF,
+	0x5FB2FFFB, 0xFBC8F3C8, 0x94A67F01, 0x7F1D5F39,
+	0xAFE85F5E, 0xFFDFDF96, 0xCB9FAF7D, 0x5FC1AFED,
+	0x8C1C5FC1, 0xAFDD5FC3, 0xDF9A7EFD, 0xB0B25FB2,
+	0xFFFEABAD, 0x5FB2FFFE, 0x5FCE600B, 0xE6BB600B,
+	0x5FCEDFC6, 0x27FBEFDF, 0x5FC8CFDE, 0x3A9CE7C0,
+	0xEDF0F3C8, 0x7F0154CD, 0x7F1D2D3D, 0x363A7570,
+	0x7E0AF1CE, 0x37EF2E68, 0x7FEE10EC, 0xADF8EFDE,
+	0xCFEAE52F, 0x7D0FE12B, 0xF1CE5F65, 0x7E0A4DF8,
+	0xCFEA5F72, 0x7D0BEFEE, 0xCFEA5F74, 0xE522EFDE,
+	0x5F74CFDA, 0x0B627385, 0xDF627E0A, 0x30D8145B,
+	0xBFFFF3C8, 0x5FFFDFFF, 0xA7F85F5E, 0xBFFE7F7D,
+	0x10D31450, 0x5F36BFFF, 0xAF785F5E, 0xBFFDA7F8,
+	0x5F36BFFE, 0x77FD30C0, 0x4E08FDCF, 0xE5FF6E0F,
+	0xAFF87E1F, 0x7E0FFD1F, 0xF1CF5F1B, 0xABF80D5E,
+	0x5F5EFFEF, 0x79F730A2, 0xAFDD5F34, 0x47F85F34,
+	0xAFED7FDD, 0x50B24978, 0x47FD7F1D, 0x7DFD70AD,
+	0xEF717EC1, 0x6BA47F01, 0x2D267EFD, 0x30DE5F5E,
+	0xFFFD5F5E, 0xFFEF5F5E, 0xFFDF0CA0, 0xAFED0A9E,
+	0xAFDD0C3A, 0x5F3AAFBD, 0x7FBDB082, 0x5F8247F8
+};
+
+static uint patch_2f00[] __initdata = {
+	0x3E303430, 0x34343737, 0xABF7BF9B, 0x994B4FBD,
+	0xBD599493, 0x349FFF37, 0xFB9B177D, 0xD9936956,
+	0xBBFDD697, 0xBDD2FD11, 0x31DB9BB3, 0x63139637,
+	0x93733693, 0x193137F7, 0x331737AF, 0x7BB9B999,
+	0xBB197957, 0x7FDFD3D5, 0x73B773F7, 0x37933B99,
+	0x1D115316, 0x99315315, 0x31694BF4, 0xFBDBD359,
+	0x31497353, 0x76956D69, 0x7B9D9693, 0x13131979,
+	0x79376935
+};
+
+static uint patch_2e00[] __initdata = {};
+#endif
+
+/*
+ * I2C/SPI/SMC1 relocation patch arrays.
+ */
+
+#ifdef CONFIG_I2C_SPI_SMC1_UCODE_PATCH
+
+static char patch_name[] __initdata = "I2C/SPI/SMC1";
+
+static struct patch_params patch_params __initdata = {
+	3, 0x8080, 0x808a, 0x8028, 0x802a,
+};
+
+static uint patch_2000[] __initdata = {
+	0x3fff0000, 0x3ffd0000, 0x3ffb0000, 0x3ff90000,
+	0x5f13eff8, 0x5eb5eff8, 0x5f88adf7, 0x5fefadf7,
+	0x3a9cfbc8, 0x77cae1bb, 0xf4de7fad, 0xabae9330,
+	0x4e08fdcf, 0x6e0faff8, 0x7ccf76cf, 0xfdaff9cf,
+	0xabf88dc8, 0xab5879f7, 0xb0925d8d, 0xdfd079f7,
+	0xb090e6bb, 0xe5bbe74f, 0x9e046f0f, 0x6ffb76ce,
+	0xee0cf9cf, 0x2bfbefef, 0xcfeef9cf, 0x76cead23,
+	0x90b3df99, 0x7fddd0c1, 0x4bf847fd, 0x7ccf76ce,
+	0xcfef77ca, 0x7eaf7fad, 0x7dfdf0b7, 0xef7a7fca,
+	0x77cafbc8, 0x6079e722, 0xfbc85fff, 0xdfff5fb3,
+	0xfffbfbc8, 0xf3c894a5, 0xe7c9edf9, 0x7f9a7fad,
+	0x5f36afe8, 0x5f5bffdf, 0xdf95cb9e, 0xaf7d5fc3,
+	0xafed8c1b, 0x5fc3afdd, 0x5fc5df99, 0x7efdb0b3,
+	0x5fb3fffe, 0xabae5fb3, 0xfffe5fd0, 0x600be6bb,
+	0x600b5fd0, 0xdfc827fb, 0xefdf5fca, 0xcfde3a9c,
+	0xe7c9edf9, 0xf3c87f9e, 0x54ca7fed, 0x2d3a3637,
+	0x756f7e9a, 0xf1ce37ef, 0x2e677fee, 0x10ebadf8,
+	0xefdecfea, 0xe52f7d9f, 0xe12bf1ce, 0x5f647e9a,
+	0x4df8cfea, 0x5f717d9b, 0xefeecfea, 0x5f73e522,
+	0xefde5f73, 0xcfda0b61, 0x5d8fdf61, 0xe7c9edf9,
+	0x7e9a30d5, 0x1458bfff, 0xf3c85fff, 0xdfffa7f8,
+	0x5f5bbffe, 0x7f7d10d0, 0x144d5f33, 0xbfffaf78,
+	0x5f5bbffd, 0xa7f85f33, 0xbffe77fd, 0x30bd4e08,
+	0xfdcfe5ff, 0x6e0faff8, 0x7eef7e9f, 0xfdeff1cf,
+	0x5f17abf8, 0x0d5b5f5b, 0xffef79f7, 0x309eafdd,
+	0x5f3147f8, 0x5f31afed, 0x7fdd50af, 0x497847fd,
+	0x7f9e7fed, 0x7dfd70a9, 0xef7e7ece, 0x6ba07f9e,
+	0x2d227efd, 0x30db5f5b, 0xfffd5f5b, 0xffef5f5b,
+	0xffdf0c9c, 0xafed0a9a, 0xafdd0c37, 0x5f37afbd,
+	0x7fbdb081, 0x5f8147f8, 0x3a11e710, 0xedf0ccdd,
+	0xf3186d0a, 0x7f0e5f06, 0x7fedbb38, 0x3afe7468,
+	0x7fedf4fc, 0x8ffbb951, 0xb85f77fd, 0xb0df5ddd,
+	0xdefe7fed, 0x90e1e74d, 0x6f0dcbf7, 0xe7decfed,
+	0xcb74cfed, 0xcfeddf6d, 0x91714f74, 0x5dd2deef,
+	0x9e04e7df, 0xefbb6ffb, 0xe7ef7f0e, 0x9e097fed,
+	0xebdbeffa, 0xeb54affb, 0x7fea90d7, 0x7e0cf0c3,
+	0xbffff318, 0x5fffdfff, 0xac59efea, 0x7fce1ee5,
+	0xe2ff5ee1, 0xaffbe2ff, 0x5ee3affb, 0xf9cc7d0f,
+	0xaef8770f, 0x7d0fb0c6, 0xeffbbfff, 0xcfef5ede,
+	0x7d0fbfff, 0x5ede4cf8, 0x7fddd0bf, 0x49f847fd,
+	0x7efdf0bb, 0x7fedfffd, 0x7dfdf0b7, 0xef7e7e1e,
+	0x5ede7f0e, 0x3a11e710, 0xedf0ccab, 0xfb18ad2e,
+	0x1ea9bbb8, 0x74283b7e, 0x73c2e4bb, 0x2ada4fb8,
+	0xdc21e4bb, 0xb2a1ffbf, 0x5e2c43f8, 0xfc87e1bb,
+	0xe74ffd91, 0x6f0f4fe8, 0xc7ba32e2, 0xf396efeb,
+	0x600b4f78, 0xe5bb760b, 0x53acaef8, 0x4ef88b0e,
+	0xcfef9e09, 0xabf8751f, 0xefef5bac, 0x741f4fe8,
+	0x751e760d, 0x7fdbf081, 0x741cafce, 0xefcc7fce,
+	0x751e70ac, 0x741ce7bb, 0x3372cfed, 0xafdbefeb,
+	0xe5bb760b, 0x53f2aef8, 0xafe8e7eb, 0x4bf8771e,
+	0x7e247fed, 0x4fcbe2cc, 0x7fbc30a9, 0x7b0f7a0f,
+	0x34d577fd, 0x308b5db7, 0xde553e5f, 0xaf78741f,
+	0x741f30f0, 0xcfef5e2c, 0x741f3eac, 0xafb8771e,
+	0x5e677fed, 0x0bd3e2cc, 0x741ccfec, 0xe5ca53cd,
+	0x6fcb4f74, 0x5dadde4b, 0x2ab63d38, 0x4bb3de30,
+	0x751f741c, 0x6c42effa, 0xefea7fce, 0x6ffc30be,
+	0xefec3fca, 0x30b3de2e, 0xadf85d9e, 0xaf7daefd,
+	0x5d9ede2e, 0x5d9eafdd, 0x761f10ac, 0x1da07efd,
+	0x30adfffe, 0x4908fb18, 0x5fffdfff, 0xafbb709b,
+	0x4ef85e67, 0xadf814ad, 0x7a0f70ad, 0xcfef50ad,
+	0x7a0fde30, 0x5da0afed, 0x3c12780f, 0xefef780f,
+	0xefef790f, 0xa7f85e0f, 0xffef790f, 0xefef790f,
+	0x14adde2e, 0x5d9eadfd, 0x5e2dfffb, 0xe79addfd,
+	0xeff96079, 0x607ae79a, 0xddfceff9, 0x60795dff,
+	0x607acfef, 0xefefefdf, 0xefbfef7f, 0xeeffedff,
+	0xebffe7ff, 0xafefafdf, 0xafbfaf7f, 0xaeffadff,
+	0xabffa7ff, 0x6fef6fdf, 0x6fbf6f7f, 0x6eff6dff,
+	0x6bff67ff, 0x2fef2fdf, 0x2fbf2f7f, 0x2eff2dff,
+	0x2bff27ff, 0x4e08fd1f, 0xe5ff6e0f, 0xaff87eef,
+	0x7e0ffdef, 0xf11f6079, 0xabf8f542, 0x7e0af11c,
+	0x37cfae3a, 0x7fec90be, 0xadf8efdc, 0xcfeae52f,
+	0x7d0fe12b, 0xf11c6079, 0x7e0a4df8, 0xcfea5dc4,
+	0x7d0befec, 0xcfea5dc6, 0xe522efdc, 0x5dc6cfda,
+	0x4e08fd1f, 0x6e0faff8, 0x7c1f761f, 0xfdeff91f,
+	0x6079abf8, 0x761cee24, 0xf91f2bfb, 0xefefcfec,
+	0xf91f6079, 0x761c27fb, 0xefdf5da7, 0xcfdc7fdd,
+	0xd09c4bf8, 0x47fd7c1f, 0x761ccfcf, 0x7eef7fed,
+	0x7dfdf093, 0xef7e7f1e, 0x771efb18, 0x6079e722,
+	0xe6bbe5bb, 0xae0ae5bb, 0x600bae85, 0xe2bbe2bb,
+	0xe2bbe2bb, 0xaf02e2bb, 0xe2bb2ff9, 0x6079e2bb
+};
+
+static uint patch_2f00[] __initdata = {
+	0x30303030, 0x3e3e3434, 0xabbf9b99, 0x4b4fbdbd,
+	0x59949334, 0x9fff37fb, 0x9b177dd9, 0x936956bb,
+	0xfbdd697b, 0xdd2fd113, 0x1db9f7bb, 0x36313963,
+	0x79373369, 0x3193137f, 0x7331737a, 0xf7bb9b99,
+	0x9bb19795, 0x77fdfd3d, 0x573b773f, 0x737933f7,
+	0xb991d115, 0x31699315, 0x31531694, 0xbf4fbdbd,
+	0x35931497, 0x35376956, 0xbd697b9d, 0x96931313,
+	0x19797937, 0x6935af78, 0xb9b3baa3, 0xb8788683,
+	0x368f78f7, 0x87778733, 0x3ffffb3b, 0x8e8f78b8,
+	0x1d118e13, 0xf3ff3f8b, 0x6bd8e173, 0xd1366856,
+	0x68d1687b, 0x3daf78b8, 0x3a3a3f87, 0x8f81378f,
+	0xf876f887, 0x77fd8778, 0x737de8d6, 0xbbf8bfff,
+	0xd8df87f7, 0xfd876f7b, 0x8bfff8bd, 0x8683387d,
+	0xb873d87b, 0x3b8fd7f8, 0xf7338883, 0xbb8ee1f8,
+	0xef837377, 0x3337b836, 0x817d11f8, 0x7378b878,
+	0xd3368b7d, 0xed731b7d, 0x833731f3, 0xf22f3f23
+};
+
+static uint patch_2e00[] __initdata = {
+	0x27eeeeee, 0xeeeeeeee, 0xeeeeeeee, 0xeeeeeeee,
+	0xee4bf4fb, 0xdbd259bb, 0x1979577f, 0xdfd2d573,
+	0xb773f737, 0x4b4fbdbd, 0x25b9b177, 0xd2d17376,
+	0x956bbfdd, 0x697bdd2f, 0xff9f79ff, 0xff9ff22f
+};
+#endif
+
+/*
+ *  USB SOF patch arrays.
+ */
+
+#ifdef CONFIG_USB_SOF_UCODE_PATCH
+
+static char patch_name[] __initdata = "USB SOF";
+
+static struct patch_params patch_params __initdata = {
+	9,
+};
+
+static uint patch_2000[] __initdata = {
+	0x7fff0000, 0x7ffd0000, 0x7ffb0000, 0x49f7ba5b,
+	0xba383ffb, 0xf9b8b46d, 0xe5ab4e07, 0xaf77bffe,
+	0x3f7bbf79, 0xba5bba38, 0xe7676076, 0x60750000
+};
+
+static uint patch_2f00[] __initdata = {
+	0x3030304c, 0xcab9e441, 0xa1aaf220
+};
+
+static uint patch_2e00[] __initdata = {};
+#endif
+
+/*
+ * SMC relocation patch arrays.
+ */
+
+#ifdef CONFIG_SMC_UCODE_PATCH
+
+static char patch_name[] __initdata = "SMC";
+
+static struct patch_params patch_params __initdata = {
+	2, 0x8080, 0x8088,
+};
+
+static uint patch_2000[] __initdata = {
+	0x3fff0000, 0x3ffd0000, 0x3ffb0000, 0x3ff90000,
+	0x5fefeff8, 0x5f91eff8, 0x3ff30000, 0x3ff10000,
+	0x3a11e710, 0xedf0ccb9, 0xf318ed66, 0x7f0e5fe2,
+	0x7fedbb38, 0x3afe7468, 0x7fedf4d8, 0x8ffbb92d,
+	0xb83b77fd, 0xb0bb5eb9, 0xdfda7fed, 0x90bde74d,
+	0x6f0dcbd3, 0xe7decfed, 0xcb50cfed, 0xcfeddf6d,
+	0x914d4f74, 0x5eaedfcb, 0x9ee0e7df, 0xefbb6ffb,
+	0xe7ef7f0e, 0x9ee57fed, 0xebb7effa, 0xeb30affb,
+	0x7fea90b3, 0x7e0cf09f, 0xbffff318, 0x5fffdfff,
+	0xac35efea, 0x7fce1fc1, 0xe2ff5fbd, 0xaffbe2ff,
+	0x5fbfaffb, 0xf9a87d0f, 0xaef8770f, 0x7d0fb0a2,
+	0xeffbbfff, 0xcfef5fba, 0x7d0fbfff, 0x5fba4cf8,
+	0x7fddd09b, 0x49f847fd, 0x7efdf097, 0x7fedfffd,
+	0x7dfdf093, 0xef7e7e1e, 0x5fba7f0e, 0x3a11e710,
+	0xedf0cc87, 0xfb18ad0a, 0x1f85bbb8, 0x74283b7e,
+	0x7375e4bb, 0x2ab64fb8, 0x5c7de4bb, 0x32fdffbf,
+	0x5f0843f8, 0x7ce3e1bb, 0xe74f7ded, 0x6f0f4fe8,
+	0xc7ba32be, 0x73f2efeb, 0x600b4f78, 0xe5bb760b,
+	0x5388aef8, 0x4ef80b6a, 0xcfef9ee5, 0xabf8751f,
+	0xefef5b88, 0x741f4fe8, 0x751e760d, 0x7fdb70dd,
+	0x741cafce, 0xefcc7fce, 0x751e7088, 0x741ce7bb,
+	0x334ecfed, 0xafdbefeb, 0xe5bb760b, 0x53ceaef8,
+	0xafe8e7eb, 0x4bf8771e, 0x7e007fed, 0x4fcbe2cc,
+	0x7fbc3085, 0x7b0f7a0f, 0x34b177fd, 0xb0e75e93,
+	0xdf313e3b, 0xaf78741f, 0x741f30cc, 0xcfef5f08,
+	0x741f3e88, 0xafb8771e, 0x5f437fed, 0x0bafe2cc,
+	0x741ccfec, 0xe5ca53a9, 0x6fcb4f74, 0x5e89df27,
+	0x2a923d14, 0x4b8fdf0c, 0x751f741c, 0x6c1eeffa,
+	0xefea7fce, 0x6ffc309a, 0xefec3fca, 0x308fdf0a,
+	0xadf85e7a, 0xaf7daefd, 0x5e7adf0a, 0x5e7aafdd,
+	0x761f1088, 0x1e7c7efd, 0x3089fffe, 0x4908fb18,
+	0x5fffdfff, 0xafbbf0f7, 0x4ef85f43, 0xadf81489,
+	0x7a0f7089, 0xcfef5089, 0x7a0fdf0c, 0x5e7cafed,
+	0xbc6e780f, 0xefef780f, 0xefef790f, 0xa7f85eeb,
+	0xffef790f, 0xefef790f, 0x1489df0a, 0x5e7aadfd,
+	0x5f09fffb, 0xe79aded9, 0xeff96079, 0x607ae79a,
+	0xded8eff9, 0x60795edb, 0x607acfef, 0xefefefdf,
+	0xefbfef7f, 0xeeffedff, 0xebffe7ff, 0xafefafdf,
+	0xafbfaf7f, 0xaeffadff, 0xabffa7ff, 0x6fef6fdf,
+	0x6fbf6f7f, 0x6eff6dff, 0x6bff67ff, 0x2fef2fdf,
+	0x2fbf2f7f, 0x2eff2dff, 0x2bff27ff, 0x4e08fd1f,
+	0xe5ff6e0f, 0xaff87eef, 0x7e0ffdef, 0xf11f6079,
+	0xabf8f51e, 0x7e0af11c, 0x37cfae16, 0x7fec909a,
+	0xadf8efdc, 0xcfeae52f, 0x7d0fe12b, 0xf11c6079,
+	0x7e0a4df8, 0xcfea5ea0, 0x7d0befec, 0xcfea5ea2,
+	0xe522efdc, 0x5ea2cfda, 0x4e08fd1f, 0x6e0faff8,
+	0x7c1f761f, 0xfdeff91f, 0x6079abf8, 0x761cee00,
+	0xf91f2bfb, 0xefefcfec, 0xf91f6079, 0x761c27fb,
+	0xefdf5e83, 0xcfdc7fdd, 0x50f84bf8, 0x47fd7c1f,
+	0x761ccfcf, 0x7eef7fed, 0x7dfd70ef, 0xef7e7f1e,
+	0x771efb18, 0x6079e722, 0xe6bbe5bb, 0x2e66e5bb,
+	0x600b2ee1, 0xe2bbe2bb, 0xe2bbe2bb, 0x2f5ee2bb,
+	0xe2bb2ff9, 0x6079e2bb,
+};
+
+static uint patch_2f00[] __initdata = {
+	0x30303030, 0x3e3e3030, 0xaf79b9b3, 0xbaa3b979,
+	0x9693369f, 0x79f79777, 0x97333fff, 0xfb3b9e9f,
+	0x79b91d11, 0x9e13f3ff, 0x3f9b6bd9, 0xe173d136,
+	0x695669d1, 0x697b3daf, 0x79b93a3a, 0x3f979f91,
+	0x379ff976, 0xf99777fd, 0x9779737d, 0xe9d6bbf9,
+	0xbfffd9df, 0x97f7fd97, 0x6f7b9bff, 0xf9bd9683,
+	0x397db973, 0xd97b3b9f, 0xd7f9f733, 0x9993bb9e,
+	0xe1f9ef93, 0x73773337, 0xb936917d, 0x11f87379,
+	0xb979d336, 0x8b7ded73, 0x1b7d9337, 0x31f3f22f,
+	0x3f2327ee, 0xeeeeeeee, 0xeeeeeeee, 0xeeeeeeee,
+	0xeeeeee4b, 0xf4fbdbd2, 0x58bb1878, 0x577fdfd2,
+	0xd573b773, 0xf7374b4f, 0xbdbd25b8, 0xb177d2d1,
+	0x7376856b, 0xbfdd687b, 0xdd2fff8f, 0x78ffff8f,
+	0xf22f0000,
+};
+
+static uint patch_2e00[] __initdata = {};
+#endif
+
+static void __init cpm_write_patch(cpm8xx_t *cp, int offset, uint *patch, int len)
+{
+	if (!len)
+		return;
+	memcpy_toio(cp->cp_dpmem + offset, patch, len);
+}
+
+void __init cpm_load_patch(cpm8xx_t *cp)
+{
+	out_be16(&cp->cp_rccr, 0);
+
+	cpm_write_patch(cp, 0, patch_2000, sizeof(patch_2000));
+	cpm_write_patch(cp, 0xf00, patch_2f00, sizeof(patch_2f00));
+	cpm_write_patch(cp, 0xe00, patch_2e00, sizeof(patch_2e00));
+
+	if (IS_ENABLED(CONFIG_I2C_SPI_UCODE_PATCH) ||
+	    IS_ENABLED(CONFIG_I2C_SPI_SMC1_UCODE_PATCH)) {
+		u16 rpbase = 0x500;
+		iic_t *iip;
+		struct spi_pram *spp;
+
+		iip = (iic_t *)&cp->cp_dparam[PROFF_IIC];
+		out_be16(&iip->iic_rpbase, rpbase);
+
+		/* Put SPI above the IIC, also 32-byte aligned. */
+		spp = (struct spi_pram *)&cp->cp_dparam[PROFF_SPI];
+		out_be16(&spp->rpbase, (rpbase + sizeof(iic_t) + 31) & ~31);
+
+		if (IS_ENABLED(CONFIG_I2C_SPI_SMC1_UCODE_PATCH)) {
+			smc_uart_t *smp;
+
+			smp = (smc_uart_t *)&cp->cp_dparam[PROFF_SMC1];
+			out_be16(&smp->smc_rpbase, 0x1FC0);
+		}
+	}
+
+	if (IS_ENABLED(CONFIG_SMC_UCODE_PATCH)) {
+		smc_uart_t *smp;
+
+		smp = (smc_uart_t *)&cp->cp_dparam[PROFF_SMC1];
+		out_be16(&smp->smc_rpbase, 0x1ec0);
+		smp = (smc_uart_t *)&cp->cp_dparam[PROFF_SMC2];
+		out_be16(&smp->smc_rpbase, 0x1fc0);
+	}
+
+	out_be16(&cp->cp_cpmcr1, patch_params.cpmcr1);
+	out_be16(&cp->cp_cpmcr2, patch_params.cpmcr2);
+	out_be16(&cp->cp_cpmcr3, patch_params.cpmcr3);
+	out_be16(&cp->cp_cpmcr4, patch_params.cpmcr4);
+
+	out_be16(&cp->cp_rccr, patch_params.rccr);
+
+	pr_info("%s microcode patch installed\n", patch_name);
+}
diff --git a/arch/powerpc/platforms/8xx/pic.c b/arch/powerpc/platforms/8xx/pic.c
index 8d5a25d..e9617d3 100644
--- a/arch/powerpc/platforms/8xx/pic.c
+++ b/arch/powerpc/platforms/8xx/pic.c
@@ -153,10 +153,9 @@
 	if (mpc8xx_pic_host == NULL) {
 		printk(KERN_ERR "MPC8xx PIC: failed to allocate irq host!\n");
 		ret = -ENOMEM;
-		goto out;
 	}
-	return 0;
 
+	ret = 0;
 out:
 	of_node_put(np);
 	return ret;
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 14ef17e..d82e366 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -23,7 +23,6 @@
 
 config KVM_GUEST
 	bool "KVM Guest support"
-	default n
 	select EPAPR_PARAVIRT
 	---help---
 	  This option enables various optimizations for running under the KVM
@@ -34,7 +33,6 @@
 
 config EPAPR_PARAVIRT
 	bool "ePAPR para-virtualization support"
-	default n
 	help
 	  Enables ePAPR para-virtualization support for guests.
 
@@ -42,7 +40,7 @@
 
 config PPC_NATIVE
 	bool
-	depends on 6xx || PPC64
+	depends on PPC_BOOK3S_32 || PPC64
 	help
 	  Support for running natively on the hardware, i.e. without
 	  a hypervisor. This option is not user-selectable but should
@@ -50,7 +48,7 @@
 
 config PPC_OF_BOOT_TRAMPOLINE
 	bool "Support booting from Open Firmware or yaboot"
-	depends on 6xx || PPC64
+	depends on PPC_BOOK3S_32 || PPC64
 	default y
 	help
 	  Support from booting from Open Firmware or yaboot using an
@@ -74,7 +72,6 @@
 config UDBG_RTAS_CONSOLE
 	bool "RTAS based debug console"
 	depends on PPC_RTAS
-	default n
 
 config PPC_SMP_MUXED_IPI
 	bool
@@ -86,16 +83,13 @@
 
 config IPIC
 	bool
-	default n
 
 config MPIC
 	bool
-	default n
 
 config MPIC_TIMER
 	bool "MPIC Global Timer"
 	depends on MPIC && FSL_SOC
-	default n
 	help
 	  The MPIC global timer is a hardware timer inside the
 	  Freescale PIC complying with OpenPIC standard. When the
@@ -107,7 +101,6 @@
 config FSL_MPIC_TIMER_WAKEUP
 	tristate "Freescale MPIC global timer wakeup driver"
 	depends on FSL_SOC &&  MPIC_TIMER && PM
-	default n
 	help
 	  The driver provides a way to wake up the system by MPIC
 	  timer.
@@ -115,43 +108,35 @@
 
 config PPC_EPAPR_HV_PIC
 	bool
-	default n
 	select EPAPR_PARAVIRT
 
 config MPIC_WEIRD
 	bool
-	default n
 
 config MPIC_MSGR
 	bool "MPIC message register support"
 	depends on MPIC
-	default n
 	help
 	  Enables support for the MPIC message registers.  These
 	  registers are used for inter-processor communication.
 
 config PPC_I8259
 	bool
-	default n
 
 config U3_DART
 	bool
 	depends on PPC64
-	default n
 
 config PPC_RTAS
 	bool
-	default n
 
 config RTAS_ERROR_LOGGING
 	bool
 	depends on PPC_RTAS
-	default n
 
 config PPC_RTAS_DAEMON
 	bool
 	depends on PPC_RTAS
-	default n
 
 config RTAS_PROC
 	bool "Proc interface to RTAS"
@@ -164,11 +149,9 @@
 
 config MMIO_NVRAM
 	bool
-	default n
 
 config MPIC_U3_HT_IRQS
 	bool
-	default n
 
 config MPIC_BROKEN_REGREAD
 	bool
@@ -187,15 +170,12 @@
 
 config PPC_MPC106
 	bool
-	default n
 
 config PPC_970_NAP
 	bool
-	default n
 
 config PPC_P7_NAP
 	bool
-	default n
 
 config PPC_INDIRECT_PIO
 	bool
@@ -217,7 +197,8 @@
 
 config PPC601_SYNC_FIX
 	bool "Workarounds for PPC601 bugs"
-	depends on 6xx && PPC_PMAC
+	depends on PPC_BOOK3S_601 && PPC_PMAC
+	default y
 	help
 	  Some versions of the PPC601 (the first PowerPC chip) have bugs which
 	  mean that extra synchronization instructions are required near
@@ -231,7 +212,7 @@
 
 config TAU
 	bool "On-chip CPU temperature sensor support"
-	depends on 6xx
+	depends on PPC_BOOK3S_32
 	help
 	  G3 and G4 processors have an on-chip temperature sensor called the
 	  'Thermal Assist Unit (TAU)', which, in theory, can measure the on-die
@@ -285,7 +266,7 @@
 	bool "Enable support for the CPM2 (Communications Processor Module)"
 	depends on (FSL_SOC_BOOKE && PPC32) || 8260
 	select CPM
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 	select GPIOLIB
 	help
 	  The CPM2 (Communications Processor Module) is a coprocessor on
@@ -295,7 +276,6 @@
 
 config FSL_ULI1575
 	bool
-	default n
 	select GENERIC_ISA_DMA
 	help
 	  Supports for the ULI1575 PCIe south bridge that exists on some
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 6c6a7c7..12543e5 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -1,12 +1,14 @@
 # SPDX-License-Identifier: GPL-2.0
 config PPC64
 	bool "64-bit kernel"
-	default n
 	select ZLIB_DEFLATE
 	help
 	  This option selects whether a 32-bit or a 64-bit kernel
 	  will be built.
 
+config PPC_BOOK3S_32
+	bool
+
 menu "Processor support"
 choice
 	prompt "Processor Type"
@@ -22,9 +24,19 @@
 
 	  If unsure, select 52xx/6xx/7xx/74xx/82xx/83xx/86xx.
 
-config PPC_BOOK3S_32
-	bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx"
+config PPC_BOOK3S_6xx
+	bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx except 601"
+	select PPC_BOOK3S_32
 	select PPC_FPU
+	select PPC_HAVE_PMU_SUPPORT
+	select PPC_HAVE_KUEP
+	select PPC_HAVE_KUAP
+
+config PPC_BOOK3S_601
+	bool "PowerPC 601"
+	select PPC_BOOK3S_32
+	select PPC_FPU
+	select PPC_HAVE_KUAP
 
 config PPC_85xx
 	bool "Freescale 85xx"
@@ -34,20 +46,23 @@
 	bool "Freescale 8xx"
 	select FSL_SOC
 	select SYS_SUPPORTS_HUGETLBFS
+	select PPC_HAVE_KUEP
+	select PPC_HAVE_KUAP
+	select PPC_MM_SLICES if HUGETLB_PAGE
 
 config 40x
 	bool "AMCC 40x"
 	select PPC_DCR_NATIVE
 	select PPC_UDBG_16550
 	select 4xx_SOC
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 
 config 44x
 	bool "AMCC 44x, 46x or 47x"
 	select PPC_DCR_NATIVE
 	select PPC_UDBG_16550
 	select 4xx_SOC
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 	select PHYS_64BIT
 
 config E200
@@ -72,8 +87,10 @@
 	select PPC_HAVE_PMU_SUPPORT
 	select SYS_SUPPORTS_HUGETLBFS
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select IRQ_WORK
+	select PPC_MM_SLICES
 
 config PPC_BOOK3E_64
 	bool "Embedded processors"
@@ -152,6 +169,11 @@
 	bool "e300c3 (831x)"
 	depends on PPC_BOOK3S_32
 
+config G4_CPU
+	bool "G4 (74xx)"
+	depends on PPC_BOOK3S_32
+	select ALTIVEC
+
 endchoice
 
 config TARGET_CPU_BOOL
@@ -170,6 +192,7 @@
 	default "860" if 860_CPU
 	default "e300c2" if E300C2_CPU
 	default "e300c3" if E300C3_CPU
+	default "G4" if G4_CPU
 
 config PPC_BOOK3S
 	def_bool y
@@ -179,11 +202,6 @@
 	def_bool y
 	depends on PPC_BOOK3E_64
 
-config 6xx
-	def_bool y
-	depends on PPC32 && PPC_BOOK3S
-	select PPC_HAVE_PMU_SUPPORT
-
 config E500
 	select FSL_EMB_PERFMON
 	select PPC_FSL_BOOK3E
@@ -266,7 +284,7 @@
 
 config ALTIVEC
 	bool "AltiVec Support"
-	depends on 6xx || PPC_BOOK3S_64 || (PPC_E500MC && PPC64)
+	depends on PPC_BOOK3S_32 || PPC_BOOK3S_64 || (PPC_E500MC && PPC64)
 	---help---
 	  This option enables kernel support for the Altivec extensions to the
 	  PowerPC processor. The kernel currently supports saving and restoring
@@ -316,14 +334,6 @@
 
 	  If in doubt, say Y here.
 
-config PPC_STD_MMU
-	def_bool y
-	depends on PPC_BOOK3S
-
-config PPC_STD_MMU_32
-	def_bool y
-	depends on PPC_STD_MMU && PPC32
-
 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	def_bool y
 	depends on PPC_BOOK3S_64
@@ -331,7 +341,9 @@
 config PPC_RADIX_MMU
 	bool "Radix MMU Support"
 	depends on PPC_BOOK3S_64
-	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+	select ARCH_HAS_GIGANTIC_PAGE
+	select PPC_HAVE_KUEP
+	select PPC_HAVE_KUAP
 	default y
 	help
 	  Enable support for the Power ISA 3.0 Radix style MMU. Currently this
@@ -351,6 +363,37 @@
 
 	  If you're unsure, say Y.
 
+config PPC_HAVE_KUEP
+	bool
+
+config PPC_KUEP
+	bool "Kernel Userspace Execution Prevention"
+	depends on PPC_HAVE_KUEP
+	default y
+	help
+	  Enable support for Kernel Userspace Execution Prevention (KUEP)
+
+	  If you're unsure, say Y.
+
+config PPC_HAVE_KUAP
+	bool
+
+config PPC_KUAP
+	bool "Kernel Userspace Access Protection"
+	depends on PPC_HAVE_KUAP
+	default y
+	help
+	  Enable support for Kernel Userspace Access Protection (KUAP)
+
+	  If you're unsure, say Y.
+
+config PPC_KUAP_DEBUG
+	bool "Extra debugging for Kernel Userspace Access Protection"
+	depends on PPC_HAVE_KUAP && (PPC_RADIX_MMU || PPC_32)
+	help
+	  Add extra debugging for Kernel Userspace Access Protection (KUAP)
+	  If you're unsure, say N.
+
 config ARCH_ENABLE_HUGEPAGE_MIGRATION
 	def_bool y
 	depends on PPC_BOOK3S_64 && HUGETLB_PAGE && MIGRATION
@@ -358,7 +401,11 @@
 
 config PPC_MMU_NOHASH
 	def_bool y
-	depends on !PPC_STD_MMU
+	depends on !PPC_BOOK3S
+
+config PPC_MMU_NOHASH_32
+	def_bool y
+	depends on PPC_MMU_NOHASH && PPC32
 
 config PPC_BOOK3E_MMU
 	def_bool y
@@ -366,9 +413,6 @@
 
 config PPC_MM_SLICES
 	bool
-	default y if PPC_BOOK3S_64
-	default y if PPC_8xx && HUGETLB_PAGE
-	default n
 
 config PPC_HAVE_PMU_SUPPORT
        bool
@@ -382,7 +426,6 @@
 config FORCE_SMP
 	# Allow platforms to force SMP=y by selecting this
 	bool
-	default n
 	select SMP
 
 config SMP
@@ -414,7 +457,13 @@
 
 config NOT_COHERENT_CACHE
 	bool
-	depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || GAMECUBE_COMMON
+	depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \
+		GAMECUBE_COMMON || AMIGAONE
+	select ARCH_HAS_DMA_COHERENT_TO_PFN
+	select ARCH_HAS_DMA_PREP_COHERENT
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select DMA_DIRECT_REMAP
 	default n if PPC_47x
 	default y
 
@@ -423,7 +472,6 @@
 
 config PPC_DOORBELL
 	bool
-	default n
 
 endmenu
 
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index e46bb7e..143d441 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -1,7 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
-
 obj-$(CONFIG_FSL_ULI1575)	+= fsl_uli1575.o
 
 obj-$(CONFIG_PPC_PMAC)		+= powermac/
diff --git a/arch/powerpc/platforms/amigaone/Kconfig b/arch/powerpc/platforms/amigaone/Kconfig
index 03dc1e3..0741edb 100644
--- a/arch/powerpc/platforms/amigaone/Kconfig
+++ b/arch/powerpc/platforms/amigaone/Kconfig
@@ -1,11 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 config AMIGAONE
 	bool "Eyetech AmigaOne/MAI Teron"
-	depends on 6xx && BROKEN_ON_SMP
+	depends on PPC_BOOK3S_32 && BROKEN_ON_SMP
 	select PPC_I8259
 	select PPC_INDIRECT_PCI
 	select PPC_UDBG_16550
-	select PCI
+	select FORCE_PCI
 	select NOT_COHERENT_CACHE
 	select CHECK_CACHE_COHERENCY
 	select DEFAULT_UIMAGE
diff --git a/arch/powerpc/platforms/amigaone/Makefile b/arch/powerpc/platforms/amigaone/Makefile
index e6885b3..e95e4e3 100644
--- a/arch/powerpc/platforms/amigaone/Makefile
+++ b/arch/powerpc/platforms/amigaone/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-y	+= setup.o
diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c
index b9d466c..ea5e45e 100644
--- a/arch/powerpc/platforms/amigaone/setup.c
+++ b/arch/powerpc/platforms/amigaone/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * AmigaOne platform setup
  *
@@ -5,11 +6,6 @@
  *
  *   Based on original amigaone_setup.c source code
  * Copyright 2003 by Hans-Joerg Frieden and Thomas Frieden
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 9f5958f..0f7c824 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 config PPC_CELL
 	bool
-	default n
 
 config PPC_CELL_COMMON
 	bool
@@ -22,14 +21,13 @@
 	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
-	default n
 
 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 PCI
+	select FORCE_PCI
 	select MMIO_NVRAM
 	select PPC_UDBG_16550
 	select UDBG_RTAS_CONSOLE
@@ -54,7 +52,6 @@
 
 config SPU_BASE
 	bool
-	default n
 	select PPC_COPRO_BASE
 
 config CBE_RAS
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 326d34e..57c4e0e 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2007, Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 
diff --git a/arch/powerpc/platforms/cell/cbe_powerbutton.c b/arch/powerpc/platforms/cell/cbe_powerbutton.c
index 2bb8031..bda589d 100644
--- a/arch/powerpc/platforms/cell/cbe_powerbutton.c
+++ b/arch/powerpc/platforms/cell/cbe_powerbutton.c
@@ -1,23 +1,10 @@
+// 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>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/input.h>
diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c
index b926438..0be212a 100644
--- a/arch/powerpc/platforms/cell/cbe_regs.c
+++ b/arch/powerpc/platforms/cell/cbe_regs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * cbe_regs.c
  *
@@ -53,7 +54,7 @@
 	int i;
 	struct device_node *tmp_np;
 
-	if (strcasecmp(np->type, "spe")) {
+	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)
@@ -70,8 +71,8 @@
 		tmp_np = tmp_np->parent;
 		/* on a correct devicetree we wont get up to root */
 		BUG_ON(!tmp_np);
-	} while (strcasecmp(tmp_np->type, "cpu") &&
-		 strcasecmp(tmp_np->type, "be"));
+	} while (!of_node_is_type(tmp_np, "cpu") ||
+		 !of_node_is_type(tmp_np, "be"));
 
 	np->data = cbe_find_map(tmp_np);
 
diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c
index 55aac74..2ece77f 100644
--- a/arch/powerpc/platforms/cell/cbe_thermal.c
+++ b/arch/powerpc/platforms/cell/cbe_thermal.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * thermal support for the cell processor
  *
@@ -29,20 +30,6 @@
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Christian Krafft <krafft@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/module.h>
diff --git a/arch/powerpc/platforms/cell/cell.h b/arch/powerpc/platforms/cell/cell.h
index ef143df..d5142e9 100644
--- a/arch/powerpc/platforms/cell/cell.h
+++ b/arch/powerpc/platforms/cell/cell.h
@@ -1,17 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Cell Platform common data structures
  *
  * Copyright 2015, Daniel Axtens, IBM 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; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
  */
 
 #ifndef CELL_H
diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
index 882944c..55b31ea 100644
--- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c
+++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
@@ -1,23 +1,10 @@
+// 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>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/cpufreq.h>
@@ -49,7 +36,7 @@
 	cpu = info->policy->cpu;
 	busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus);
 
-	CALC_LOAD(info->busy_spus, EXP, busy_spus * FIXED_1);
+	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);
 
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 5d4bf9a..5927ead 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Cell Internal Interrupt Controller
  *
@@ -8,20 +9,6 @@
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
  * TODO:
  * - Fix various assumptions related to HW CPU numbers vs. linux CPU numbers
  *   vs node numbers in the setup code
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 12352a5..ca9ffc1 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -1,23 +1,10 @@
+// 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>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #undef DEBUG
@@ -499,7 +486,7 @@
 	window->table.it_size = size >> window->table.it_page_shift;
 	window->table.it_ops = &cell_iommu_ops;
 
-	iommu_init_table(&window->table, iommu->nid);
+	iommu_init_table(&window->table, iommu->nid, 0, 0);
 
 	pr_debug("\tioid      %d\n", window->ioid);
 	pr_debug("\tblocksize %ld\n", window->table.it_blocksize);
@@ -544,9 +531,10 @@
 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 */
-static int iommu_fixed_is_weak;
+bool iommu_fixed_is_weak;
 
 static struct iommu_table *cell_get_iommu_table(struct device *dev)
 {
@@ -568,103 +556,19 @@
 	return &window->table;
 }
 
-/* A coherent allocation implies strong ordering */
-
-static void *dma_fixed_alloc_coherent(struct device *dev, size_t size,
-				      dma_addr_t *dma_handle, gfp_t flag,
-				      unsigned long attrs)
-{
-	if (iommu_fixed_is_weak)
-		return iommu_alloc_coherent(dev, cell_get_iommu_table(dev),
-					    size, dma_handle,
-					    device_to_mask(dev), flag,
-					    dev_to_node(dev));
-	else
-		return dma_nommu_ops.alloc(dev, size, dma_handle, flag,
-					    attrs);
-}
-
-static void dma_fixed_free_coherent(struct device *dev, size_t size,
-				    void *vaddr, dma_addr_t dma_handle,
-				    unsigned long attrs)
-{
-	if (iommu_fixed_is_weak)
-		iommu_free_coherent(cell_get_iommu_table(dev), size, vaddr,
-				    dma_handle);
-	else
-		dma_nommu_ops.free(dev, size, vaddr, dma_handle, attrs);
-}
-
-static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page,
-				     unsigned long offset, size_t size,
-				     enum dma_data_direction direction,
-				     unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		return dma_nommu_ops.map_page(dev, page, offset, size,
-					       direction, attrs);
-	else
-		return iommu_map_page(dev, cell_get_iommu_table(dev), page,
-				      offset, size, device_to_mask(dev),
-				      direction, attrs);
-}
-
-static void dma_fixed_unmap_page(struct device *dev, dma_addr_t dma_addr,
-				 size_t size, enum dma_data_direction direction,
-				 unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		dma_nommu_ops.unmap_page(dev, dma_addr, size, direction,
-					  attrs);
-	else
-		iommu_unmap_page(cell_get_iommu_table(dev), dma_addr, size,
-				 direction, attrs);
-}
-
-static int dma_fixed_map_sg(struct device *dev, struct scatterlist *sg,
-			   int nents, enum dma_data_direction direction,
-			   unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		return dma_nommu_ops.map_sg(dev, sg, nents, direction, attrs);
-	else
-		return ppc_iommu_map_sg(dev, cell_get_iommu_table(dev), sg,
-					nents, device_to_mask(dev),
-					direction, attrs);
-}
-
-static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg,
-			       int nents, enum dma_data_direction direction,
-			       unsigned long attrs)
-{
-	if (iommu_fixed_is_weak == (attrs & DMA_ATTR_WEAK_ORDERING))
-		dma_nommu_ops.unmap_sg(dev, sg, nents, direction, attrs);
-	else
-		ppc_iommu_unmap_sg(cell_get_iommu_table(dev), sg, nents,
-				   direction, attrs);
-}
-
-static int dma_suported_and_switch(struct device *dev, u64 dma_mask);
-
-static const struct dma_map_ops dma_iommu_fixed_ops = {
-	.alloc          = dma_fixed_alloc_coherent,
-	.free           = dma_fixed_free_coherent,
-	.map_sg         = dma_fixed_map_sg,
-	.unmap_sg       = dma_fixed_unmap_sg,
-	.dma_supported  = dma_suported_and_switch,
-	.map_page       = dma_fixed_map_page,
-	.unmap_page     = dma_fixed_unmap_page,
-	.mapping_error	= dma_iommu_mapping_error,
-};
+static u64 cell_iommu_get_fixed_address(struct device *dev);
 
 static void cell_dma_dev_setup(struct device *dev)
 {
-	if (get_pci_dma_ops() == &dma_iommu_ops)
+	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 if (get_pci_dma_ops() == &dma_nommu_ops)
-		set_dma_offset(dev, cell_dma_nommu_offset);
-	else
-		BUG();
+	} else {
+		dev->archdata.dma_offset = cell_dma_nommu_offset;
+	}
 }
 
 static void cell_pci_dma_dev_setup(struct pci_dev *dev)
@@ -681,11 +585,9 @@
 	if (action != BUS_NOTIFY_ADD_DEVICE)
 		return 0;
 
-	/* We use the PCI DMA ops */
-	dev->dma_ops = get_pci_dma_ops();
-
+	if (cell_iommu_enabled)
+		dev->dma_ops = &dma_iommu_ops;
 	cell_dma_dev_setup(dev);
-
 	return 0;
 }
 
@@ -810,7 +712,6 @@
 	unsigned long base = 0, size;
 
 	/* When no iommu is present, we use direct DMA ops */
-	set_pci_dma_ops(&dma_nommu_ops);
 
 	/* First make sure all IOC translation is turned off */
 	cell_disable_iommus();
@@ -895,7 +796,11 @@
 	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);
@@ -946,27 +851,10 @@
 	return dev_addr;
 }
 
-static int dma_suported_and_switch(struct device *dev, u64 dma_mask)
+static bool cell_pci_iommu_bypass_supported(struct pci_dev *pdev, u64 mask)
 {
-	if (dma_mask == DMA_BIT_MASK(64) &&
-	    cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR) {
-		u64 addr = cell_iommu_get_fixed_address(dev) +
-			dma_iommu_fixed_base;
-		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
-		dev_dbg(dev, "iommu: fixed addr = %llx\n", addr);
-		set_dma_ops(dev, &dma_iommu_fixed_ops);
-		set_dma_offset(dev, addr);
-		return 1;
-	}
-
-	if (dma_iommu_dma_supported(dev, dma_mask)) {
-		dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
-		set_dma_ops(dev, get_pci_dma_ops());
-		cell_dma_dev_setup(dev);
-		return 1;
-	}
-
-	return 0;
+	return mask == DMA_BIT_MASK(64) &&
+		cell_iommu_get_fixed_address(&pdev->dev) != OF_BAD_ADDR;
 }
 
 static void insert_16M_pte(unsigned long addr, unsigned long *ptab,
@@ -1120,9 +1008,8 @@
 		cell_iommu_setup_window(iommu, np, dbase, dsize, 0);
 	}
 
-	dma_iommu_ops.dma_supported = dma_suported_and_switch;
-	set_pci_dma_ops(&dma_iommu_ops);
-
+	cell_pci_controller_ops.iommu_bypass_supported =
+		cell_pci_iommu_bypass_supported;
 	return 0;
 }
 
@@ -1143,7 +1030,7 @@
 	pciep = of_find_node_by_type(NULL, "pcie-endpoint");
 
 	if (strcmp(str, "weak") == 0 || (pciep && strcmp(str, "strong") != 0))
-		iommu_fixed_is_weak = DMA_ATTR_WEAK_ORDERING;
+		iommu_fixed_is_weak = true;
 
 	of_node_put(pciep);
 
@@ -1151,26 +1038,6 @@
 }
 __setup("iommu_fixed=", setup_iommu_fixed);
 
-static u64 cell_dma_get_required_mask(struct device *dev)
-{
-	const struct dma_map_ops *dma_ops;
-
-	if (!dev->dma_mask)
-		return 0;
-
-	if (!iommu_fixed_disabled &&
-			cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR)
-		return DMA_BIT_MASK(64);
-
-	dma_ops = get_dma_ops(dev);
-	if (dma_ops->get_required_mask)
-		return dma_ops->get_required_mask(dev);
-
-	WARN_ONCE(1, "no get_required_mask in %p ops", dma_ops);
-
-	return DMA_BIT_MASK(64);
-}
-
 static int __init cell_iommu_init(void)
 {
 	struct device_node *np;
@@ -1187,10 +1054,9 @@
 
 	/* Setup various callbacks */
 	cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
-	ppc_md.dma_get_required_mask = cell_dma_get_required_mask;
 
 	if (!iommu_fixed_disabled && cell_iommu_fixed_mapping_init() == 0)
-		goto bail;
+		goto done;
 
 	/* Create an iommu for each /axon node.  */
 	for_each_node_by_name(np, "axon") {
@@ -1207,10 +1073,10 @@
 			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
diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c
index a88944d..6af3a6e 100644
--- a/arch/powerpc/platforms/cell/pervasive.c
+++ b/arch/powerpc/platforms/cell/pervasive.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * CBE Pervasive Monitor and Debug
  *
@@ -5,20 +6,6 @@
  *
  * Authors: Maximino Aguilar (maguilar@us.ibm.com)
  *          Michael N. Day (mnday@us.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/cell/pervasive.h b/arch/powerpc/platforms/cell/pervasive.h
index fd4d7b7..c6fccad 100644
--- a/arch/powerpc/platforms/cell/pervasive.h
+++ b/arch/powerpc/platforms/cell/pervasive.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Cell Pervasive Monitor and Debug interface and HW structures
  *
@@ -5,20 +6,6 @@
  *
  * Authors: Maximino Aguilar (maguilar@us.ibm.com)
  *          David J. Erb (djerb@us.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 
diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c
index e3ad0c3..35bbd15 100644
--- a/arch/powerpc/platforms/cell/pmu.c
+++ b/arch/powerpc/platforms/cell/pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Cell Broadband Engine Performance Monitor
  *
@@ -6,20 +7,6 @@
  * Author:
  *    David Erb (djerb@us.ibm.com)
  *    Kevin Corry (kevcorry@us.ibm.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 2f704af..6ea4805 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2006-2008, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index 7d31b8d..9680d76 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  linux/arch/powerpc/platforms/cell/cell_setup.c
  *
@@ -6,11 +7,6 @@
  *  Modified by Cort Dougan (cort@cs.nmt.edu)
  *  Modified by PPC64 Team, IBM Corp
  *  Modified by Cell Team, IBM Deutschland Entwicklung GmbH
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #undef DEBUG
 
@@ -131,7 +127,7 @@
 
 	np = phb->dn;
 	model = of_get_property(np, "model", NULL);
-	if (model == NULL || strcmp(np->name, "pci"))
+	if (model == NULL || !of_node_name_eq(np, "pci"))
 		return 0;
 
 	/* Setup workarounds for spider */
@@ -168,8 +164,7 @@
 	 * platform devices for the PCI host bridges
 	 */
 	for_each_child_of_node(root, np) {
-		if (np->type == NULL || (strcmp(np->type, "pci") != 0 &&
-					 strcmp(np->type, "pciex") != 0))
+		if (!of_node_is_type(np, "pci") && !of_node_is_type(np, "pciex"))
 			continue;
 		of_platform_device_create(np, NULL, NULL);
 	}
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index 1aeac57..85d795d 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SMP support for BPA machines.
  *
@@ -5,11 +6,6 @@
  * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
  *
  * Plus various changes from other IBM teams...
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c
index 1200d0d..93ea416 100644
--- a/arch/powerpc/platforms/cell/spider-pci.c
+++ b/arch/powerpc/platforms/cell/spider-pci.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * IO workarounds for PCI on Celleb/Cell platform
  *
  * (C) Copyright 2006-2007 TOSHIBA 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index c137f0c..026b72c 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -1,23 +1,10 @@
+// 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>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 0c45cdb..bc48234 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Low-level SPU handling
  *
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #undef DEBUG
@@ -50,11 +37,11 @@
 EXPORT_SYMBOL_GPL(cbe_spu_info);
 
 /*
- * The spufs fault-handling code needs to call force_sig_info to raise signals
+ * The spufs fault-handling code needs to call force_sig_fault to raise signals
  * on DMA errors. Export it here to avoid general kernel-wide access to this
  * function
  */
-EXPORT_SYMBOL_GPL(force_sig_info);
+EXPORT_SYMBOL_GPL(force_sig_fault);
 
 /*
  * Protects cbe_spu_info and spu->number.
@@ -194,7 +181,7 @@
 	 * faults need to be deferred to process context.
 	 */
 	if ((dsisr & MFC_DSISR_PTE_NOT_FOUND) &&
-	    (REGION_ID(ea) != USER_REGION_ID)) {
+	    (get_region_id(ea) != USER_REGION_ID)) {
 
 		spin_unlock(&spu->register_lock);
 		ret = hash_page(ea,
@@ -224,7 +211,7 @@
 	unsigned long ea = (unsigned long)addr;
 	u64 llp;
 
-	if (REGION_ID(ea) == KERNEL_REGION_ID)
+	if (get_region_id(ea) == LINEAR_MAP_REGION_ID)
 		llp = mmu_psize_defs[mmu_linear_psize].sllp;
 	else
 		llp = mmu_psize_defs[mmu_virtual_psize].sllp;
diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c
index 8ae8620..cbee366 100644
--- a/arch/powerpc/platforms/cell/spu_callbacks.c
+++ b/arch/powerpc/platforms/cell/spu_callbacks.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * System call callback functions for SPUs
  */
@@ -34,20 +35,9 @@
  */
 
 static void *spu_syscall_table[] = {
-#define SYSCALL(func)		sys_ni_syscall,
-#define COMPAT_SYS(func)	sys_ni_syscall,
-#define PPC_SYS(func)		sys_ni_syscall,
-#define OLDSYS(func)		sys_ni_syscall,
-#define SYS32ONLY(func)		sys_ni_syscall,
-#define PPC64ONLY(func)		sys_ni_syscall,
-#define SYSX(f, f3264, f32)	sys_ni_syscall,
-
-#define SYSCALL_SPU(func)	sys_##func,
-#define COMPAT_SYS_SPU(func)	sys_##func,
-#define COMPAT_SPU_NEW(func)	sys_##func,
-#define SYSX_SPU(f, f3264, f32)	f,
-
-#include <asm/systbl.h>
+#define __SYSCALL(nr, entry)	entry,
+#include <asm/syscall_table_spu.h>
+#undef __SYSCALL
 };
 
 long spu_sys_callback(struct spu_syscall_block *s)
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
index 5c409c9..8e9ef65 100644
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ b/arch/powerpc/platforms/cell/spu_manage.c
@@ -1,22 +1,10 @@
+// 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
- *
- * 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.
  */
 
 #include <linux/interrupt.h>
@@ -180,35 +168,22 @@
 
 static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
 {
-	struct of_phandle_args oirq;
-	int ret;
 	int i;
 
 	for (i=0; i < 3; i++) {
-		ret = of_irq_parse_one(np, i, &oirq);
-		if (ret) {
-			pr_debug("spu_new: failed to get irq %d\n", i);
+		spu->irqs[i] = irq_of_parse_and_map(np, i);
+		if (!spu->irqs[i])
 			goto err;
-		}
-		ret = -EINVAL;
-		pr_debug("  irq %d no 0x%x on %pOF\n", i, oirq.args[0],
-			 oirq.np);
-		spu->irqs[i] = irq_create_of_mapping(&oirq);
-		if (!spu->irqs[i]) {
-			pr_debug("spu_new: failed to map it !\n");
-			goto err;
-		}
 	}
 	return 0;
 
 err:
-	pr_debug("failed to map irq %x for spu %s\n", *oirq.args,
-		spu->name);
+	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 ret;
+	return -EINVAL;
 }
 
 static int spu_map_resource(struct spu *spu, int nr,
@@ -295,8 +270,8 @@
 	for_each_node_by_type(node, "spe") {
 		ret = fn(node);
 		if (ret) {
-			printk(KERN_WARNING "%s: Error initializing %s\n",
-				__func__, node->name);
+			printk(KERN_WARNING "%s: Error initializing %pOFn\n",
+				__func__, node);
 			of_node_put(node);
 			break;
 		}
@@ -471,7 +446,6 @@
 	struct device_node *vic_dn, *last_spu_dn;
 	phandle avoid_ph;
 	const phandle *vic_handles;
-	const char *name;
 	int lenp, i, added;
 
 	last_spu = list_first_entry(&cbe_spu_info[cbe].spus, struct spu,
@@ -493,12 +467,7 @@
 			if (!vic_dn)
 				continue;
 
-			/* a neighbour might be spe, mic-tm, or bif0 */
-			name = of_get_property(vic_dn, "name", NULL);
-			if (!name)
-				continue;
-
-			if (strcmp(name, "spe") == 0) {
+			if (of_node_name_eq(vic_dn, "spe") ) {
 				spu = devnode_spu(cbe, vic_dn);
 				avoid_ph = last_spu_dn->phandle;
 			} else {
@@ -511,7 +480,7 @@
 				spu = neighbour_spu(cbe, vic_dn, last_spu_dn);
 				if (!spu)
 					continue;
-				if (!strcmp(name, "mic-tm")) {
+				if (of_node_name_eq(vic_dn, "mic-tm")) {
 					last_spu->has_mem_affinity = 1;
 					spu->has_mem_affinity = 1;
 				}
diff --git a/arch/powerpc/platforms/cell/spu_notify.c b/arch/powerpc/platforms/cell/spu_notify.c
index afdf857..67870ab 100644
--- a/arch/powerpc/platforms/cell/spu_notify.c
+++ b/arch/powerpc/platforms/cell/spu_notify.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Move OProfile dependencies from spufs module to the kernel so it
  * can run on non-cell PPC.
  *
  * Copyright (C) IBM 2005
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.c b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
index 66d3372..0c2e6bb 100644
--- a/arch/powerpc/platforms/cell/spu_priv1_mmio.c
+++ b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
@@ -1,21 +1,9 @@
+// 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.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.h b/arch/powerpc/platforms/cell/spu_priv1_mmio.h
index 7b62bd1..04f0db3 100644
--- a/arch/powerpc/platforms/cell/spu_priv1_mmio.h
+++ b/arch/powerpc/platforms/cell/spu_priv1_mmio.h
@@ -1,21 +1,9 @@
+/* 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.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #ifndef SPU_PRIV1_MMIO_H
diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c
index 263413a..87ad7d5 100644
--- a/arch/powerpc/platforms/cell/spu_syscalls.c
+++ b/arch/powerpc/platforms/cell/spu_syscalls.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SPU file system -- system call stubs
  *
@@ -5,20 +6,6 @@
  * (C) Copyright 2006-2007, IBM Corporation
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/file.h>
 #include <linux/fs.h>
@@ -26,7 +13,6 @@
 #include <linux/syscalls.h>
 #include <linux/rcupdate.h>
 #include <linux/binfmts.h>
-#include <linux/syscalls.h>
 
 #include <asm/spu.h>
 
diff --git a/arch/powerpc/platforms/cell/spufs/backing_ops.c b/arch/powerpc/platforms/cell/spufs/backing_ops.c
index 857580a..28a34a2 100644
--- a/arch/powerpc/platforms/cell/spufs/backing_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/backing_ops.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* backing_ops.c - query/set operations on saved SPU context.
  *
  * Copyright (C) IBM 2005
@@ -5,20 +6,6 @@
  *
  * These register operations allow SPUFS to operate on saved
  * SPU contexts rather than hardware.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/errno.h>
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index b500b17..7a39cc4 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SPU file system -- SPU context management
  *
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/fs.h>
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 84b7ac9..8b3296b 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SPU core dump code
  *
  * (C) Copyright 2006 IBM Corp.
  *
  * Author: Dwayne Grant McConnell <decimal@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/elf.h>
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index 83cf58d..24adbe3 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Low-level SPU handling
  *
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/sched/signal.h>
 #include <linux/mm.h>
@@ -36,42 +23,31 @@
 static void spufs_handle_event(struct spu_context *ctx,
 				unsigned long ea, int type)
 {
-	siginfo_t info;
-
 	if (ctx->flags & SPU_CREATE_EVENTS_ENABLED) {
 		ctx->event_return |= type;
 		wake_up_all(&ctx->stop_wq);
 		return;
 	}
 
-	clear_siginfo(&info);
-
 	switch (type) {
 	case SPE_EVENT_INVALID_DMA:
-		info.si_signo = SIGBUS;
-		info.si_code = BUS_OBJERR;
+		force_sig_fault(SIGBUS, BUS_OBJERR, NULL);
 		break;
 	case SPE_EVENT_SPE_DATA_STORAGE:
-		info.si_signo = SIGSEGV;
-		info.si_addr = (void __user *)ea;
-		info.si_code = SEGV_ACCERR;
 		ctx->ops->restart_dma(ctx);
+		force_sig_fault(SIGSEGV, SEGV_ACCERR, (void __user *)ea);
 		break;
 	case SPE_EVENT_DMA_ALIGNMENT:
-		info.si_signo = SIGBUS;
 		/* DAR isn't set for an alignment fault :( */
-		info.si_code = BUS_ADRALN;
+		force_sig_fault(SIGBUS, BUS_ADRALN, NULL);
 		break;
 	case SPE_EVENT_SPE_ERROR:
-		info.si_signo = SIGILL;
-		info.si_addr = (void __user *)(unsigned long)
-			ctx->ops->npc_read(ctx) - 4;
-		info.si_code = ILL_ILLOPC;
+		force_sig_fault(
+			SIGILL, ILL_ILLOPC,
+			(void __user *)(unsigned long)
+			ctx->ops->npc_read(ctx) - 4);
 		break;
 	}
-
-	if (info.si_signo)
-		force_sig_info(info.si_signo, &info, current);
 }
 
 int spufs_handle_class0(struct spu_context *ctx)
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 43e7b93..c0f950a 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SPU file system -- file contents
  *
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #undef DEBUG
@@ -459,7 +446,7 @@
 	.release = spufs_cntl_release,
 	.read = simple_attr_read,
 	.write = simple_attr_write,
-	.llseek	= generic_file_llseek,
+	.llseek	= no_llseek,
 	.mmap = spufs_cntl_mmap,
 };
 
@@ -588,7 +575,7 @@
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	file->private_data = i->i_ctx;
 
-	return nonseekable_open(inode, file);
+	return stream_open(inode, file);
 }
 
 /*
@@ -609,7 +596,7 @@
 	if (len < 4)
 		return -EINVAL;
 
-	if (!access_ok(VERIFY_WRITE, buf, len))
+	if (!access_ok(buf, len))
 		return -EFAULT;
 
 	udata = (void __user *)buf;
@@ -717,7 +704,7 @@
 	if (len < 4)
 		return -EINVAL;
 
-	if (!access_ok(VERIFY_WRITE, buf, len))
+	if (!access_ok(buf, len))
 		return -EFAULT;
 
 	udata = (void __user *)buf;
@@ -856,7 +843,7 @@
 		return -EINVAL;
 
 	udata = (void __user *)buf;
-	if (!access_ok(VERIFY_READ, buf, len))
+	if (!access_ok(buf, len))
 		return -EFAULT;
 
 	if (__get_user(wbox_data, udata))
@@ -1994,7 +1981,7 @@
 	int ret;
 	struct spu_context *ctx = file->private_data;
 
-	if (!access_ok(VERIFY_WRITE, buf, len))
+	if (!access_ok(buf, len))
 		return -EFAULT;
 
 	ret = spu_acquire_saved(ctx);
@@ -2034,7 +2021,7 @@
 	struct spu_context *ctx = file->private_data;
 	int ret;
 
-	if (!access_ok(VERIFY_WRITE, buf, len))
+	if (!access_ok(buf, len))
 		return -EFAULT;
 
 	ret = spu_acquire_saved(ctx);
@@ -2077,7 +2064,7 @@
 	struct spu_context *ctx = file->private_data;
 	int ret;
 
-	if (!access_ok(VERIFY_WRITE, buf, len))
+	if (!access_ok(buf, len))
 		return -EFAULT;
 
 	ret = spu_acquire_saved(ctx);
@@ -2129,7 +2116,7 @@
 	struct spu_context *ctx = file->private_data;
 	int ret;
 
-	if (!access_ok(VERIFY_WRITE, buf, len))
+	if (!access_ok(buf, len))
 		return -EFAULT;
 
 	ret = spu_acquire_saved(ctx);
@@ -2160,7 +2147,7 @@
 	if (len < ret)
 		return -EINVAL;
 
-	if (!access_ok(VERIFY_WRITE, buf, len))
+	if (!access_ok(buf, len))
 		return -EFAULT;
 
 	info.proxydma_info_type = ctx->csa.prob.dma_querytype_RW;
@@ -2338,9 +2325,8 @@
 		goto out;
 	}
 
-	ctx->switch_log = kmalloc(sizeof(struct switch_log) +
-		SWITCH_LOG_BUFSIZE * sizeof(struct switch_log_entry),
-		GFP_KERNEL);
+	ctx->switch_log = kmalloc(struct_size(ctx->switch_log, log,
+				  SWITCH_LOG_BUFSIZE), GFP_KERNEL);
 
 	if (!ctx->switch_log) {
 		rc = -ENOMEM;
diff --git a/arch/powerpc/platforms/cell/spufs/gang.c b/arch/powerpc/platforms/cell/spufs/gang.c
index 71a4432..827d338 100644
--- a/arch/powerpc/platforms/cell/spufs/gang.c
+++ b/arch/powerpc/platforms/cell/spufs/gang.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SPU file system
  *
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/list.h>
diff --git a/arch/powerpc/platforms/cell/spufs/hw_ops.c b/arch/powerpc/platforms/cell/spufs/hw_ops.c
index ae9d24d..8deaf78 100644
--- a/arch/powerpc/platforms/cell/spufs/hw_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/hw_ops.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* hw_ops.c - query/set operations on active SPU context.
  *
  * Copyright (C) IBM 2005
  * Author: Mark Nutter <mnutter@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/errno.h>
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index db329d4..2dd452a 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 
 /*
  * SPU file system
@@ -5,24 +6,12 @@
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include <linux/fsnotify.h>
 #include <linux/backing-dev.h>
 #include <linux/init.h>
@@ -33,7 +22,6 @@
 #include <linux/pagemap.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
-#include <linux/parser.h>
 
 #include <asm/prom.h>
 #include <asm/spu.h>
@@ -43,7 +31,7 @@
 #include "spufs.h"
 
 struct spufs_sb_info {
-	int debug;
+	bool debug;
 };
 
 static struct kmem_cache *spufs_inode_cache;
@@ -71,17 +59,11 @@
 	return &ei->vfs_inode;
 }
 
-static void spufs_i_callback(struct rcu_head *head)
+static void spufs_free_inode(struct inode *inode)
 {
-	struct inode *inode = container_of(head, struct inode, i_rcu);
 	kmem_cache_free(spufs_inode_cache, SPUFS_I(inode));
 }
 
-static void spufs_destroy_inode(struct inode *inode)
-{
-	call_rcu(&inode->i_rcu, spufs_i_callback);
-}
-
 static void
 spufs_init_once(void *p)
 {
@@ -593,16 +575,27 @@
 }
 
 /* File system initialization */
-enum {
-	Opt_uid, Opt_gid, Opt_mode, Opt_debug, Opt_err,
+struct spufs_fs_context {
+	kuid_t	uid;
+	kgid_t	gid;
+	umode_t	mode;
 };
 
-static const match_table_t spufs_tokens = {
-	{ Opt_uid,   "uid=%d" },
-	{ Opt_gid,   "gid=%d" },
-	{ Opt_mode,  "mode=%o" },
-	{ Opt_debug, "debug" },
-	{ Opt_err,    NULL  },
+enum {
+	Opt_uid, Opt_gid, Opt_mode, Opt_debug,
+};
+
+static const struct fs_parameter_spec spufs_param_specs[] = {
+	fsparam_u32	("gid",				Opt_gid),
+	fsparam_u32oct	("mode",			Opt_mode),
+	fsparam_u32	("uid",				Opt_uid),
+	fsparam_flag	("debug",			Opt_debug),
+	{}
+};
+
+static const struct fs_parameter_description spufs_fs_parameters = {
+	.name		= "spufs",
+	.specs		= spufs_param_specs,
 };
 
 static int spufs_show_options(struct seq_file *m, struct dentry *root)
@@ -623,47 +616,41 @@
 	return 0;
 }
 
-static int
-spufs_parse_options(struct super_block *sb, char *options, struct inode *root)
+static int spufs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
-	char *p;
-	substring_t args[MAX_OPT_ARGS];
+	struct spufs_fs_context *ctx = fc->fs_private;
+	struct spufs_sb_info *sbi = fc->s_fs_info;
+	struct fs_parse_result result;
+	kuid_t uid;
+	kgid_t gid;
+	int opt;
 
-	while ((p = strsep(&options, ",")) != NULL) {
-		int token, option;
+	opt = fs_parse(fc, &spufs_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
 
-		if (!*p)
-			continue;
-
-		token = match_token(p, spufs_tokens, args);
-		switch (token) {
-		case Opt_uid:
-			if (match_int(&args[0], &option))
-				return 0;
-			root->i_uid = make_kuid(current_user_ns(), option);
-			if (!uid_valid(root->i_uid))
-				return 0;
-			break;
-		case Opt_gid:
-			if (match_int(&args[0], &option))
-				return 0;
-			root->i_gid = make_kgid(current_user_ns(), option);
-			if (!gid_valid(root->i_gid))
-				return 0;
-			break;
-		case Opt_mode:
-			if (match_octal(&args[0], &option))
-				return 0;
-			root->i_mode = option | S_IFDIR;
-			break;
-		case Opt_debug:
-			spufs_get_sb_info(sb)->debug = 1;
-			break;
-		default:
-			return 0;
-		}
+	switch (opt) {
+	case Opt_uid:
+		uid = make_kuid(current_user_ns(), result.uint_32);
+		if (!uid_valid(uid))
+			return invalf(fc, "Unknown uid");
+		ctx->uid = uid;
+		break;
+	case Opt_gid:
+		gid = make_kgid(current_user_ns(), result.uint_32);
+		if (!gid_valid(gid))
+			return invalf(fc, "Unknown gid");
+		ctx->gid = gid;
+		break;
+	case Opt_mode:
+		ctx->mode = result.uint_32 & S_IALLUGO;
+		break;
+	case Opt_debug:
+		sbi->debug = true;
+		break;
 	}
-	return 1;
+
+	return 0;
 }
 
 static void spufs_exit_isolated_loader(void)
@@ -697,79 +684,99 @@
 	printk(KERN_INFO "spufs: SPU isolation mode enabled\n");
 }
 
-static int
-spufs_create_root(struct super_block *sb, void *data)
+static int spufs_create_root(struct super_block *sb, struct fs_context *fc)
 {
+	struct spufs_fs_context *ctx = fc->fs_private;
 	struct inode *inode;
-	int ret;
 
-	ret = -ENODEV;
 	if (!spu_management_ops)
-		goto out;
+		return -ENODEV;
 
-	ret = -ENOMEM;
-	inode = spufs_new_inode(sb, S_IFDIR | 0775);
+	inode = spufs_new_inode(sb, S_IFDIR | ctx->mode);
 	if (!inode)
-		goto out;
+		return -ENOMEM;
 
+	inode->i_uid = ctx->uid;
+	inode->i_gid = ctx->gid;
 	inode->i_op = &simple_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 	SPUFS_I(inode)->i_ctx = NULL;
 	inc_nlink(inode);
 
-	ret = -EINVAL;
-	if (!spufs_parse_options(sb, data, inode))
-		goto out_iput;
-
-	ret = -ENOMEM;
 	sb->s_root = d_make_root(inode);
 	if (!sb->s_root)
-		goto out;
-
+		return -ENOMEM;
 	return 0;
-out_iput:
-	iput(inode);
-out:
-	return ret;
 }
 
-static int
-spufs_fill_super(struct super_block *sb, void *data, int silent)
+static const struct super_operations spufs_ops = {
+	.alloc_inode	= spufs_alloc_inode,
+	.free_inode	= spufs_free_inode,
+	.statfs		= simple_statfs,
+	.evict_inode	= spufs_evict_inode,
+	.show_options	= spufs_show_options,
+};
+
+static int spufs_fill_super(struct super_block *sb, struct fs_context *fc)
 {
-	struct spufs_sb_info *info;
-	static const struct super_operations s_ops = {
-		.alloc_inode = spufs_alloc_inode,
-		.destroy_inode = spufs_destroy_inode,
-		.statfs = simple_statfs,
-		.evict_inode = spufs_evict_inode,
-		.show_options = spufs_show_options,
-	};
-
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_blocksize = PAGE_SIZE;
 	sb->s_blocksize_bits = PAGE_SHIFT;
 	sb->s_magic = SPUFS_MAGIC;
-	sb->s_op = &s_ops;
-	sb->s_fs_info = info;
+	sb->s_op = &spufs_ops;
 
-	return spufs_create_root(sb, data);
+	return spufs_create_root(sb, fc);
 }
 
-static struct dentry *
-spufs_mount(struct file_system_type *fstype, int flags,
-		const char *name, void *data)
+static int spufs_get_tree(struct fs_context *fc)
 {
-	return mount_single(fstype, flags, data, spufs_fill_super);
+	return get_tree_single(fc, spufs_fill_super);
+}
+
+static void spufs_free_fc(struct fs_context *fc)
+{
+	kfree(fc->s_fs_info);
+}
+
+static const struct fs_context_operations spufs_context_ops = {
+	.free		= spufs_free_fc,
+	.parse_param	= spufs_parse_param,
+	.get_tree	= spufs_get_tree,
+};
+
+static int spufs_init_fs_context(struct fs_context *fc)
+{
+	struct spufs_fs_context *ctx;
+	struct spufs_sb_info *sbi;
+
+	ctx = kzalloc(sizeof(struct spufs_fs_context), GFP_KERNEL);
+	if (!ctx)
+		goto nomem;
+
+	sbi = kzalloc(sizeof(struct spufs_sb_info), GFP_KERNEL);
+	if (!sbi)
+		goto nomem_ctx;
+
+	ctx->uid = current_uid();
+	ctx->gid = current_gid();
+	ctx->mode = 0755;
+
+	fc->fs_private = ctx;
+	fc->s_fs_info = sbi;
+	fc->ops = &spufs_context_ops;
+	return 0;
+
+nomem_ctx:
+	kfree(ctx);
+nomem:
+	return -ENOMEM;
 }
 
 static struct file_system_type spufs_type = {
 	.owner = THIS_MODULE,
 	.name = "spufs",
-	.mount = spufs_mount,
+	.init_fs_context = spufs_init_fs_context,
+	.parameters	= &spufs_fs_parameters,
 	.kill_sb = kill_litter_super,
 };
 MODULE_ALIAS_FS("spufs");
diff --git a/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c b/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c
index d9de848..43b9dde 100644
--- a/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c
+++ b/arch/powerpc/platforms/cell/spufs/lscsa_alloc.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SPU local store allocation routines
  *
  * Copyright 2007 Benjamin Herrenschmidt, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c
index 07f82d7..3f2380f 100644
--- a/arch/powerpc/platforms/cell/spufs/run.c
+++ b/arch/powerpc/platforms/cell/spufs/run.c
@@ -443,7 +443,7 @@
 
 	else if (unlikely((status & SPU_STATUS_STOPPED_BY_STOP)
 	    && (status >> SPU_STOP_STATUS_SHIFT) == 0x3fff)) {
-		force_sig(SIGTRAP, current);
+		force_sig(SIGTRAP);
 		ret = -ERESTARTSYS;
 	}
 
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index c9ef3c5..f18d506 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* sched.c - SPU scheduler.
  *
  * Copyright (C) IBM 2005
  * Author: Mark Nutter <mnutter@us.ibm.com>
  *
  * 2006-03-31	NUMA domains added.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #undef DEBUG
@@ -141,7 +128,7 @@
 	 * runqueue. The context will be rescheduled on the proper node
 	 * if it is timesliced or preempted.
 	 */
-	cpumask_copy(&ctx->cpus_allowed, &current->cpus_allowed);
+	cpumask_copy(&ctx->cpus_allowed, current->cpus_ptr);
 
 	/* Save the current cpu id for spu interrupt routing. */
 	ctx->last_ran = raw_smp_processor_id();
@@ -987,9 +974,9 @@
 	unsigned long active_tasks; /* fixed-point */
 
 	active_tasks = count_active_contexts() * FIXED_1;
-	CALC_LOAD(spu_avenrun[0], EXP_1, active_tasks);
-	CALC_LOAD(spu_avenrun[1], EXP_5, active_tasks);
-	CALC_LOAD(spu_avenrun[2], EXP_15, active_tasks);
+	spu_avenrun[0] = calc_load(spu_avenrun[0], EXP_1, active_tasks);
+	spu_avenrun[1] = calc_load(spu_avenrun[1], EXP_5, active_tasks);
+	spu_avenrun[2] = calc_load(spu_avenrun[2], EXP_15, active_tasks);
 }
 
 static void spusched_wake(struct timer_list *unused)
@@ -1071,9 +1058,6 @@
 	}
 }
 
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
 static int show_spu_loadavg(struct seq_file *s, void *private)
 {
 	int a, b, c;
diff --git a/arch/powerpc/platforms/cell/spufs/spu_restore.c b/arch/powerpc/platforms/cell/spufs/spu_restore.c
index 72c905f..2cbb6ef 100644
--- a/arch/powerpc/platforms/cell/spufs/spu_restore.c
+++ b/arch/powerpc/platforms/cell/spufs/spu_restore.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * spu_restore.c
  *
@@ -7,21 +8,6 @@
  * Synergistic Processor Element Book IV
  *
  * Author: Mark Nutter <mnutter@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
  */
 
 
diff --git a/arch/powerpc/platforms/cell/spufs/spu_restore_crt0.S b/arch/powerpc/platforms/cell/spufs/spu_restore_crt0.S
index 2905949..6d799f8 100644
--- a/arch/powerpc/platforms/cell/spufs/spu_restore_crt0.S
+++ b/arch/powerpc/platforms/cell/spufs/spu_restore_crt0.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * crt0_r.S: Entry function for SPU-side context restore.
  *
@@ -7,21 +8,6 @@
  * sequence.  Sets up an initial stack frame, then branches to
  * 'main'.  On return, restores all 128 registers from the LSCSA
  * and exits.
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <asm/spu_csa.h>
diff --git a/arch/powerpc/platforms/cell/spufs/spu_save.c b/arch/powerpc/platforms/cell/spufs/spu_save.c
index ae95cc1..28c88e3 100644
--- a/arch/powerpc/platforms/cell/spufs/spu_save.c
+++ b/arch/powerpc/platforms/cell/spufs/spu_save.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * spu_save.c
  *
@@ -7,21 +8,6 @@
  * Synergistic Processor Element Book IV
  *
  * Author: Mark Nutter <mnutter@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
  */
 
 
diff --git a/arch/powerpc/platforms/cell/spufs/spu_save_crt0.S b/arch/powerpc/platforms/cell/spufs/spu_save_crt0.S
index 6659d6a..5ce32ef 100644
--- a/arch/powerpc/platforms/cell/spufs/spu_save_crt0.S
+++ b/arch/powerpc/platforms/cell/spufs/spu_save_crt0.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * crt0_s.S: Entry function for SPU-side context save.
  *
@@ -6,21 +7,6 @@
  * Entry function for SPU-side of the context save sequence.
  * Saves all 128 GPRs, sets up an initial stack frame, then
  * branches to 'main'.
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <asm/spu_csa.h>
diff --git a/arch/powerpc/platforms/cell/spufs/spu_utils.h b/arch/powerpc/platforms/cell/spufs/spu_utils.h
index 58359fe..4fc1ebb 100644
--- a/arch/powerpc/platforms/cell/spufs/spu_utils.h
+++ b/arch/powerpc/platforms/cell/spufs/spu_utils.h
@@ -1,21 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * utils.h: Utilities for SPU-side of the context switch operation.
  *
  * (C) Copyright IBM 2005
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef _SPU_CONTEXT_UTILS_H_
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index b5fc1b3..413c89a 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * SPU file system
  *
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2005
  *
  * Author: Arnd Bergmann <arndb@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef SPUFS_H
 #define SPUFS_H
diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c
index dde3555..5c3f5d0 100644
--- a/arch/powerpc/platforms/cell/spufs/switch.c
+++ b/arch/powerpc/platforms/cell/spufs/switch.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * spu_switch.c
  *
@@ -15,21 +16,6 @@
  * this is not possible, this sequence may be used to premptively
  * save, and then later (optionally) restore the context of a
  * program executing on an SPE.
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/export.h>
diff --git a/arch/powerpc/platforms/chrp/Kconfig b/arch/powerpc/platforms/chrp/Kconfig
index ead99ef..9b5c550 100644
--- a/arch/powerpc/platforms/chrp/Kconfig
+++ b/arch/powerpc/platforms/chrp/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config PPC_CHRP
 	bool "Common Hardware Reference Platform (CHRP) based machines"
-	depends on 6xx
+	depends on PPC_BOOK3S_32
 	select HAVE_PCSPKR_PLATFORM
 	select MPIC
 	select PPC_I8259
@@ -12,5 +12,5 @@
 	select PPC_MPC106
 	select PPC_UDBG_16550
 	select PPC_NATIVE
-	select PCI
+	select FORCE_PCI
 	default y
diff --git a/arch/powerpc/platforms/chrp/Makefile b/arch/powerpc/platforms/chrp/Makefile
index 4b3bfad..05639db 100644
--- a/arch/powerpc/platforms/chrp/Makefile
+++ b/arch/powerpc/platforms/chrp/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-y				+= setup.o time.o pegasos_eth.o pci.o
 obj-$(CONFIG_SMP)		+= smp.o
-obj-$(CONFIG_NVRAM)		+= nvram.o
+obj-$(CONFIG_NVRAM:m=y)		+= nvram.o
diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c
index 791b863..e820332 100644
--- a/arch/powerpc/platforms/chrp/nvram.c
+++ b/arch/powerpc/platforms/chrp/nvram.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  c 2001 PPC 64 Team, IBM Corp
  *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- *
  * /dev/nvram driver for PPC
- *
  */
 
 #include <linux/kernel.h>
@@ -24,7 +19,7 @@
 static unsigned char nvram_buf[4];
 static DEFINE_SPINLOCK(nvram_lock);
 
-static unsigned char chrp_nvram_read(int addr)
+static unsigned char chrp_nvram_read_val(int addr)
 {
 	unsigned int done;
 	unsigned long flags;
@@ -46,7 +41,7 @@
 	return ret;
 }
 
-static void chrp_nvram_write(int addr, unsigned char val)
+static void chrp_nvram_write_val(int addr, unsigned char val)
 {
 	unsigned int done;
 	unsigned long flags;
@@ -64,6 +59,11 @@
 	spin_unlock_irqrestore(&nvram_lock, flags);
 }
 
+static ssize_t chrp_nvram_size(void)
+{
+	return nvram_size;
+}
+
 void __init chrp_nvram_init(void)
 {
 	struct device_node *nvram;
@@ -85,8 +85,9 @@
 	printk(KERN_INFO "CHRP nvram contains %u bytes\n", nvram_size);
 	of_node_put(nvram);
 
-	ppc_md.nvram_read_val = chrp_nvram_read;
-	ppc_md.nvram_write_val = chrp_nvram_write;
+	ppc_md.nvram_read_val  = chrp_nvram_read_val;
+	ppc_md.nvram_write_val = chrp_nvram_write_val;
+	ppc_md.nvram_size      = chrp_nvram_size;
 
 	return;
 }
diff --git a/arch/powerpc/platforms/chrp/pci.c b/arch/powerpc/platforms/chrp/pci.c
index 5ddb57b..b020c75 100644
--- a/arch/powerpc/platforms/chrp/pci.c
+++ b/arch/powerpc/platforms/chrp/pci.c
@@ -230,8 +230,8 @@
 		else if (strncmp(machine, "Pegasos", 7) == 0)
 			is_pegasos = 1;
 	}
-	for (dev = root->child; dev != NULL; dev = dev->sibling) {
-		if (dev->type == NULL || strcmp(dev->type, "pci") != 0)
+	for_each_child_of_node(root, dev) {
+		if (!of_node_is_type(dev, "pci"))
 			continue;
 		++index;
 		/* The GG2 bridge on the LongTrail doesn't have an address */
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index d6d8ffc..fcf6f23 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -280,20 +280,14 @@
 	node = of_find_node_by_path(property);
 	if (!node)
 		return;
-	property = of_get_property(node, "device_type", NULL);
-	if (!property)
-		goto out_put;
-	if (strcmp(property, "serial"))
+	if (!of_node_is_type(node, "serial"))
 		goto out_put;
 	/*
 	 * The 9pin connector is either /failsafe
 	 * or /pci@80000000/isa@C/serial@i2F8
 	 * The optional graphics card has also type 'serial' in VGA mode.
 	 */
-	property = of_get_property(node, "name", NULL);
-	if (!property)
-		goto out_put;
-	if (!strcmp(property, "failsafe") || !strcmp(property, "serial"))
+	if (of_node_name_eq(node, "failsafe") || of_node_name_eq(node, "serial"))
 		add_preferred_console("ttyS", 0, NULL);
 out_put:
 	of_node_put(node);
@@ -544,8 +538,7 @@
 	/* see if there is a keyboard in the device tree
 	   with a parent of type "adb" */
 	for_each_node_by_name(kbd, "keyboard")
-		if (kbd->parent && kbd->parent->type
-		    && strcmp(kbd->parent->type, "adb") == 0)
+		if (of_node_is_type(kbd->parent, "adb"))
 			break;
 	of_node_put(kbd);
 	if (kbd)
@@ -556,7 +549,7 @@
 static void __init
 chrp_init2(void)
 {
-#ifdef CONFIG_NVRAM
+#if IS_ENABLED(CONFIG_NVRAM)
 	chrp_nvram_init();
 #endif
 
diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig
index 8ea16db..c192096 100644
--- a/arch/powerpc/platforms/embedded6xx/Kconfig
+++ b/arch/powerpc/platforms/embedded6xx/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config EMBEDDED6xx
 	bool "Embedded 6xx/7xx/7xxx-based boards"
-	depends on 6xx && BROKEN_ON_SMP
+	depends on PPC_BOOK3S_32 && BROKEN_ON_SMP
 
 config LINKSTATION
 	bool "Linkstation / Kurobox(HG) from Buffalo"
@@ -52,7 +52,7 @@
 	bool "Motorola/Emerson MVME5100"
 	depends on EMBEDDED6xx
 	select MPIC
-	select PCI
+	select FORCE_PCI
 	select PPC_INDIRECT_PCI
 	select PPC_I8259
 	select PPC_NATIVE
@@ -63,7 +63,7 @@
 
 config TSI108_BRIDGE
 	bool
-	select PCI
+	select FORCE_PCI
 	select MPIC
 	select MPIC_WEIRD
 
diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
index db0be00..d39a921 100644
--- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/embedded6xx/flipper-pic.c
  *
  * Nintendo GameCube/Wii "Flipper" interrupt controller support.
  * Copyright (C) 2004-2009 The GameCube Linux Team
  * Copyright (C) 2007,2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 #define DRV_MODULE_NAME "flipper-pic"
 #define pr_fmt(fmt) DRV_MODULE_NAME ": " fmt
diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.h b/arch/powerpc/platforms/embedded6xx/flipper-pic.h
index e339186..024ae70 100644
--- a/arch/powerpc/platforms/embedded6xx/flipper-pic.h
+++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.h
@@ -1,15 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * arch/powerpc/platforms/embedded6xx/flipper-pic.h
  *
  * Nintendo GameCube/Wii "Flipper" interrupt controller support.
  * Copyright (C) 2004-2009 The GameCube Linux Team
  * Copyright (C) 2007,2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #ifndef __FLIPPER_PIC_H
diff --git a/arch/powerpc/platforms/embedded6xx/gamecube.c b/arch/powerpc/platforms/embedded6xx/gamecube.c
index 36789ce..ade928f 100644
--- a/arch/powerpc/platforms/embedded6xx/gamecube.c
+++ b/arch/powerpc/platforms/embedded6xx/gamecube.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/embedded6xx/gamecube.c
  *
  * Nintendo GameCube board-specific support
  * Copyright (C) 2004-2009 The GameCube Linux Team
  * Copyright (C) 2007,2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index 8112b39..a1b7f79 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/embedded6xx/hlwd-pic.c
  *
  * Nintendo Wii "Hollywood" interrupt controller support.
  * Copyright (C) 2009 The GameCube Linux Team
  * Copyright (C) 2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 #define DRV_MODULE_NAME "hlwd-pic"
 #define pr_fmt(fmt) DRV_MODULE_NAME ": " fmt
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.h b/arch/powerpc/platforms/embedded6xx/hlwd-pic.h
index d2e5a09..f18eeee 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.h
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.h
@@ -1,15 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * arch/powerpc/platforms/embedded6xx/hlwd-pic.h
  *
  * Nintendo Wii "Hollywood" interrupt controller support.
  * Copyright (C) 2009 The GameCube Linux Team
  * Copyright (C) 2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #ifndef __HLWD_PIC_H
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index 0409714..d8f2e2c 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Board setup routines for the IBM 750GX/CL platform w/ TSI10x bridge
  *
@@ -7,10 +8,6 @@
  * Josh Boyer <jwboyer@linux.vnet.ibm.com>
  *
  * Based on code from mpc7448_hpc2.c
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
  */
 
 #include <linux/stddef.h>
@@ -44,7 +41,8 @@
 
 #define HOLLY_PCI_CFG_PHYS 0x7c000000
 
-int holly_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn)
+static int holly_exclude_device(struct pci_controller *hose, u_char bus,
+				u_char devfn)
 {
 	if (bus == 0 && PCI_SLOT(devfn) == 0)
 		return PCIBIOS_DEVICE_NOT_FOUND;
@@ -187,13 +185,13 @@
 	tsi108_write_reg(TSI108_MPIC_OFFSET + 0x30c, 0);
 }
 
-void holly_show_cpuinfo(struct seq_file *m)
+static void holly_show_cpuinfo(struct seq_file *m)
 {
 	seq_printf(m, "vendor\t\t: IBM\n");
 	seq_printf(m, "machine\t\t: PPC750 GX/CL\n");
 }
 
-void __noreturn holly_restart(char *cmd)
+static void __noreturn holly_restart(char *cmd)
 {
 	__be32 __iomem *ocn_bar1 = NULL;
 	unsigned long bar;
@@ -233,18 +231,6 @@
 	for (;;) ;
 }
 
-void holly_power_off(void)
-{
-	local_irq_disable();
-	/* No way to shut power off with software */
-	for (;;) ;
-}
-
-void holly_halt(void)
-{
-	holly_power_off();
-}
-
 /*
  * Called very early, device-tree isn't unflattened
  */
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index 9de100e..15437ab 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * mpc7448_hpc2.c
  *
@@ -11,11 +12,6 @@
  * 	Add Flat Device Tree support fot mpc7448hpc2 board
  *
  * Copyright 2004-2006 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c
index 273dfa3..1cd488d 100644
--- a/arch/powerpc/platforms/embedded6xx/mvme5100.c
+++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Board setup routines for the Motorola/Emerson MVME5100.
  *
@@ -8,13 +9,7 @@
  *    Matt Porter, MontaVista Software Inc.
  *    Copyright 2001 MontaVista Software Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * Author: Stephen Chivers <schivers@csc.com>
- *
  */
 
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c b/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c
index 5c7e7ce..ed45db7 100644
--- a/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c
+++ b/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c
  *
  * udbg serial input/output routines for the USB Gecko adapter.
  * Copyright (C) 2008-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #include <mm/mmu_decl.h>
diff --git a/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.h b/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.h
index bb6cde4..bceb119 100644
--- a/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.h
+++ b/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.h
@@ -1,15 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * arch/powerpc/platforms/embedded6xx/usbgecko_udbg.h
  *
  * udbg serial input/output routines for the USB Gecko adapter.
  * Copyright (C) 2008-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #ifndef __USBGECKO_UDBG_H
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 403523c..67e48b0 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -1,15 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/embedded6xx/wii.c
  *
  * Nintendo Wii board-specific support
  * Copyright (C) 2008-2009 The GameCube Linux Team
  * Copyright (C) 2008,2009 Albert Herranz
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 #define DRV_MODULE_NAME "wii"
 #define pr_fmt(fmt) DRV_MODULE_NAME ": " fmt
@@ -54,10 +49,6 @@
 static void __iomem *hw_ctrl;
 static void __iomem *hw_gpio;
 
-unsigned long wii_hole_start;
-unsigned long wii_hole_size;
-
-
 static int __init page_aligned(unsigned long x)
 {
 	return !(x & (PAGE_SIZE-1));
@@ -69,26 +60,6 @@
 
 	BUG_ON(memblock.memory.cnt != 2);
 	BUG_ON(!page_aligned(p[0].base) || !page_aligned(p[1].base));
-
-	/* determine hole */
-	wii_hole_start = ALIGN(p[0].base + p[0].size, PAGE_SIZE);
-	wii_hole_size = p[1].base - wii_hole_start;
-}
-
-unsigned long __init wii_mmu_mapin_mem2(unsigned long top)
-{
-	unsigned long delta, size, bl;
-	unsigned long max_size = (256<<20);
-
-	/* MEM2 64MB@0x10000000 */
-	delta = wii_hole_start + wii_hole_size;
-	size = top - delta;
-	for (bl = 128<<10; bl < max_size; bl <<= 1) {
-		if (bl * 2 > size)
-			break;
-	}
-	setbat(4, PAGE_OFFSET+delta, delta, bl, PAGE_KERNEL_X);
-	return delta + bl;
 }
 
 static void __noreturn wii_spin(void)
@@ -112,7 +83,7 @@
 	}
 	error = of_address_to_resource(np, 0, &res);
 	if (error) {
-		pr_err("no valid reg found for %s\n", np->name);
+		pr_err("no valid reg found for %pOFn\n", np);
 		goto out_put;
 	}
 
diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c
index b97f6f3..044a20c 100644
--- a/arch/powerpc/platforms/fsl_uli1575.c
+++ b/arch/powerpc/platforms/fsl_uli1575.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * ULI M1575 setup code - specific to Freescale boards
  *
  * Copyright 2007 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/platforms/maple/Kconfig b/arch/powerpc/platforms/maple/Kconfig
index 376d0be..86ae210 100644
--- a/arch/powerpc/platforms/maple/Kconfig
+++ b/arch/powerpc/platforms/maple/Kconfig
@@ -2,7 +2,7 @@
 config PPC_MAPLE
 	depends on PPC64 && PPC_BOOK3S && CPU_BIG_ENDIAN
 	bool "Maple 970FX Evaluation Board"
-	select PCI
+	select FORCE_PCI
 	select MPIC
 	select U3_DART
 	select MPIC_U3_HT_IRQS
@@ -13,7 +13,6 @@
 	select PPC_RTAS
 	select MMIO_NVRAM
 	select ATA_NONSTANDARD if ATA
-	default n
 	help
-          This option enables support for the Maple 970FX Evaluation Board.
+	  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/Makefile b/arch/powerpc/platforms/maple/Makefile
index 1be1a99..19f35ab 100644
--- a/arch/powerpc/platforms/maple/Makefile
+++ b/arch/powerpc/platforms/maple/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-y	+= setup.o pci.o time.o
diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c
index e382137..c86a66d 100644
--- a/arch/powerpc/platforms/maple/pci.c
+++ b/arch/powerpc/platforms/maple/pci.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org),
  *		      IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
@@ -604,10 +600,8 @@
 		printk(KERN_CRIT "maple_find_bridges: can't find root of device tree\n");
 		return;
 	}
-	for (np = NULL; (np = of_get_next_child(root, np)) != NULL;) {
-		if (!np->type)
-			continue;
-		if (strcmp(np->type, "pci") && strcmp(np->type, "ht"))
+	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")) &&
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index b7f9375..9cd6f3e 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -1,14 +1,9 @@
+// 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. 
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/maple/time.c b/arch/powerpc/platforms/maple/time.c
index becf2eb..701c4e0 100644
--- a/arch/powerpc/platforms/maple/time.c
+++ b/arch/powerpc/platforms/maple/time.c
@@ -1,12 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  (c) Copyright 2004 Benjamin Herrenschmidt (benh@kernel.crashing.org),
  *                     IBM Corp. 
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/pasemi/Kconfig b/arch/powerpc/platforms/pasemi/Kconfig
index d458a79..c52731a 100644
--- a/arch/powerpc/platforms/pasemi/Kconfig
+++ b/arch/powerpc/platforms/pasemi/Kconfig
@@ -2,9 +2,8 @@
 config PPC_PASEMI
 	depends on PPC64 && PPC_BOOK3S && CPU_BIG_ENDIAN
 	bool "PA Semi SoC-based platforms"
-	default n
 	select MPIC
-	select PCI
+	select FORCE_PCI
 	select PPC_UDBG_16550
 	select PPC_NATIVE
 	select MPIC_BROKEN_REGREAD
diff --git a/arch/powerpc/platforms/pasemi/Makefile b/arch/powerpc/platforms/pasemi/Makefile
index 60b4e0f..d2ce954 100644
--- a/arch/powerpc/platforms/pasemi/Makefile
+++ b/arch/powerpc/platforms/pasemi/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-y	+= setup.o pci.o time.o idle.o powersave.o iommu.o dma_lib.o misc.o
 obj-$(CONFIG_PPC_PASEMI_MDIO)	+= gpio_mdio.o
 obj-$(CONFIG_PCI_MSI)		+= msi.o
diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c
index c80f72c..270fa3c 100644
--- a/arch/powerpc/platforms/pasemi/dma_lib.c
+++ b/arch/powerpc/platforms/pasemi/dma_lib.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2006-2007 PA Semi, Inc
  *
  * Common functions for DMA access on PA Semi PWRficient
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/kernel.h>
@@ -262,8 +250,6 @@
 	if (!chan->ring_virt)
 		return -ENOMEM;
 
-	memset(chan->ring_virt, 0, ring_size * sizeof(u64));
-
 	return 0;
 }
 EXPORT_SYMBOL(pasemi_dma_alloc_ring);
@@ -576,7 +562,7 @@
 		res.start = 0xfd800000;
 		res.end = res.start + 0x1000;
 	}
-	dma_status = __ioremap(res.start, resource_size(&res), 0);
+	dma_status = ioremap_cache(res.start, resource_size(&res));
 	pci_dev_put(iob_pdev);
 
 	for (i = 0; i < MAX_TXCH; i++)
diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c
index 6f35a2a..bf30016 100644
--- a/arch/powerpc/platforms/pasemi/gpio_mdio.c
+++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2006-2007 PA Semi, Inc
  *
@@ -6,19 +7,6 @@
  * Maintained by: Olof Johansson <olof@lixom.net>
  *
  * Based on drivers/net/fs_enet/mii-bitbang.c.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/io.h>
diff --git a/arch/powerpc/platforms/pasemi/idle.c b/arch/powerpc/platforms/pasemi/idle.c
index 8bb4e80..1c954c9 100644
--- a/arch/powerpc/platforms/pasemi/idle.c
+++ b/arch/powerpc/platforms/pasemi/idle.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2006-2007 PA Semi, Inc
  *
  * Maintained by: Olof Johansson <olof@lixom.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index f06c83f..b500a6e 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2005-2008, PA Semi, Inc
  *
  * Maintained by: Olof Johansson <olof@lixom.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #undef DEBUG
@@ -158,7 +146,7 @@
 	 */
 	iommu_table_iobmap.it_blocksize = 4;
 	iommu_table_iobmap.it_ops = &iommu_table_iobmap_ops;
-	iommu_init_table(&iommu_table_iobmap, 0);
+	iommu_init_table(&iommu_table_iobmap, 0, 0, 0);
 	pr_debug(" <- %s\n", __func__);
 }
 
@@ -186,7 +174,7 @@
 	 */
 	if (dev->vendor == 0x1959 && dev->device == 0xa007 &&
 	    !firmware_has_feature(FW_FEATURE_LPAR)) {
-		dev->dev.dma_ops = &dma_nommu_ops;
+		dev->dev.dma_ops = NULL;
 		/*
 		 * Set the coherent DMA mask to prevent the iommu
 		 * being used unnecessarily
@@ -208,12 +196,17 @@
 	pr_debug(" -> %s\n", __func__);
 
 	/* For 2G space, 8x64 pages (2^21 bytes) is max total l2 size */
-	iob_l2_base = (u32 *)__va(memblock_alloc_base(1UL<<21, 1UL<<21, 0x80000000));
+	iob_l2_base = memblock_alloc_try_nid_raw(1UL << 21, 1UL << 21,
+					MEMBLOCK_LOW_LIMIT, 0x80000000,
+					NUMA_NO_NODE);
+	if (!iob_l2_base)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx max_addr=%x\n",
+		      __func__, 1UL << 21, 1UL << 21, 0x80000000);
 
 	pr_info("IOBMAP L2 allocated at: %p\n", iob_l2_base);
 
 	/* Allocate a spare page to map all invalid IOTLB pages. */
-	tmp = memblock_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE);
+	tmp = memblock_phys_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE);
 	if (!tmp)
 		panic("IOBMAP: Cannot allocate spare page!");
 	/* Empty l1 is marked invalid */
@@ -269,4 +262,3 @@
 	pasemi_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pasemi;
 	set_pci_dma_ops(&dma_iommu_ops);
 }
-
diff --git a/arch/powerpc/platforms/pasemi/misc.c b/arch/powerpc/platforms/pasemi/misc.c
index aa958a4..1cd4ca1 100644
--- a/arch/powerpc/platforms/pasemi/misc.c
+++ b/arch/powerpc/platforms/pasemi/misc.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2007 PA Semi, Inc
  *
  * Parts based on arch/powerpc/sysdev/fsl_soc.c:
  *
  * 2006 (c) MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/errno.h>
diff --git a/arch/powerpc/platforms/pasemi/msi.c b/arch/powerpc/platforms/pasemi/msi.c
index d9cd510..d38944a 100644
--- a/arch/powerpc/platforms/pasemi/msi.c
+++ b/arch/powerpc/platforms/pasemi/msi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2007, Olof Johansson, PA Semi
  *
@@ -5,12 +6,6 @@
  *
  * Copyright 2006, Segher Boessenkool, IBM Corporation.
  * Copyright 2006-2007, Michael Ellerman, IBM 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.
- *
  */
 
 #include <linux/irq.h>
diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c
index c3c6417..8779b10 100644
--- a/arch/powerpc/platforms/pasemi/pci.c
+++ b/arch/powerpc/platforms/pasemi/pci.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2006 PA Semi, Inc
  *
@@ -7,19 +8,6 @@
  * Maintained by: Olof Johansson <olof@lixom.net>
  *
  * Based on arch/powerpc/platforms/maple/pci.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 
@@ -27,6 +15,7 @@
 #include <linux/pci.h>
 
 #include <asm/pci-bridge.h>
+#include <asm/isa-bridge.h>
 #include <asm/machdep.h>
 
 #include <asm/ppc-pci.h>
@@ -108,6 +97,61 @@
 	return 1;
 }
 
+#ifdef CONFIG_PPC_PASEMI_NEMO
+#define PXP_ERR_CFG_REG	0x4
+#define PXP_IGNORE_PCIE_ERRORS	0x800
+#define SB600_BUS 5
+
+static void sb600_set_flag(int bus)
+{
+	static void __iomem *iob_mapbase = NULL;
+	struct resource res;
+	struct device_node *dn;
+	int err;
+
+	if (iob_mapbase == NULL) {
+		dn = of_find_compatible_node(NULL, "isa", "pasemi,1682m-iob");
+		if (!dn) {
+			pr_crit("NEMO SB600 missing iob node\n");
+			return;
+		}
+
+		err = of_address_to_resource(dn, 0, &res);
+		of_node_put(dn);
+
+		if (err) {
+			pr_crit("NEMO SB600 missing resource\n");
+			return;
+		}
+
+		pr_info("NEMO SB600 IOB base %08llx\n",res.start);
+
+		iob_mapbase = ioremap(res.start + 0x100, 0x94);
+	}
+
+	if (iob_mapbase != NULL) {
+		if (bus == SB600_BUS) {
+			/*
+			 * This is the SB600's bus, tell the PCI-e root port
+			 * to allow non-zero devices to enumerate.
+			 */
+			out_le32(iob_mapbase + PXP_ERR_CFG_REG, in_le32(iob_mapbase + PXP_ERR_CFG_REG) | PXP_IGNORE_PCIE_ERRORS);
+		} else {
+			/*
+			 * Only scan device 0 on other busses
+			 */
+			out_le32(iob_mapbase + PXP_ERR_CFG_REG, in_le32(iob_mapbase + PXP_ERR_CFG_REG) & ~PXP_IGNORE_PCIE_ERRORS);
+		}
+	}
+}
+
+#else
+
+static void sb600_set_flag(int bus)
+{
+}
+#endif
+
 static int pa_pxp_read_config(struct pci_bus *bus, unsigned int devfn,
 			      int offset, int len, u32 *val)
 {
@@ -126,6 +170,8 @@
 
 	addr = pa_pxp_cfg_addr(hose, bus->number, devfn, offset);
 
+	sb600_set_flag(bus->number);
+
 	/*
 	 * Note: the caller has already checked that offset is
 	 * suitably aligned and that len is 1, 2 or 4.
@@ -160,6 +206,8 @@
 
 	addr = pa_pxp_cfg_addr(hose, bus->number, devfn, offset);
 
+	sb600_set_flag(bus->number);
+
 	/*
 	 * Note: the caller has already checked that offset is
 	 * suitably aligned and that len is 1, 2 or 4.
@@ -210,6 +258,12 @@
 	/* Interpret the "ranges" property */
 	pci_process_bridge_OF_ranges(hose, dev, 1);
 
+	/*
+	 * Scan for an isa bridge. This is needed to find the SB600 on the nemo
+	 * and does nothing on machines without one.
+	 */
+	isa_bridge_find_early(hose);
+
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/pasemi/powersave.S b/arch/powerpc/platforms/pasemi/powersave.S
index 81ab555..d0215d5 100644
--- a/arch/powerpc/platforms/pasemi/powersave.S
+++ b/arch/powerpc/platforms/pasemi/powersave.S
@@ -1,21 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2006-2007 PA Semi, Inc
  *
  * Maintained by: Olof Johansson <olof@lixom.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  */
 
 #include <asm/processor.h>
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 9a6eb04..05a52f1 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2006-2007 PA Semi, Inc
  *
@@ -7,19 +8,6 @@
  * Maintained by: Olof Johansson <olof@lixom.net>
  *
  * Based on arch/powerpc/platforms/maple/setup.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/errno.h>
@@ -34,6 +22,7 @@
 #include <asm/prom.h>
 #include <asm/iommu.h>
 #include <asm/machdep.h>
+#include <asm/i8259.h>
 #include <asm/mpic.h>
 #include <asm/smp.h>
 #include <asm/time.h>
@@ -72,6 +61,40 @@
 		out_le32(reset_reg, 0x6000000);
 }
 
+#ifdef CONFIG_PPC_PASEMI_NEMO
+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);
+	while (1)
+		out_8(pld_map+7,0x01);
+}
+
+/* RTC platform device structure as is not in device tree */
+static struct resource rtc_resource[] = {{
+	.name = "rtc",
+	.start = 0x70,
+	.end = 0x71,
+	.flags = IORESOURCE_IO,
+}, {
+	.name = "rtc",
+	.start = 8,
+	.end = 8,
+	.flags = IORESOURCE_IRQ,
+}};
+
+static inline void nemo_init_rtc(void)
+{
+	platform_device_register_simple("rtc_cmos", -1, rtc_resource, 2);
+}
+
+#else
+
+static inline void nemo_init_rtc(void)
+{
+}
+#endif
+
 #ifdef CONFIG_SMP
 static arch_spinlock_t timebase_lock;
 static unsigned long timebase;
@@ -183,6 +206,42 @@
 }
 machine_device_initcall(pasemi, pas_setup_mce_regs);
 
+#ifdef CONFIG_PPC_PASEMI_NEMO
+static void sb600_8259_cascade(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned int cascade_irq = i8259_irq();
+
+	if (cascade_irq)
+		generic_handle_irq(cascade_irq);
+
+	chip->irq_eoi(&desc->irq_data);
+}
+
+static void nemo_init_IRQ(struct mpic *mpic)
+{
+	struct device_node *np;
+	int gpio_virq;
+	/* Connect the SB600's legacy i8259 controller */
+	np = of_find_node_by_path("/pxp@0,e0000000");
+	i8259_init(np, 0);
+	of_node_put(np);
+
+	gpio_virq = irq_create_mapping(NULL, 3);
+	irq_set_irq_type(gpio_virq, IRQ_TYPE_LEVEL_HIGH);
+	irq_set_chained_handler(gpio_virq, sb600_8259_cascade);
+	mpic_unmask_irq(irq_get_irq_data(gpio_virq));
+
+	irq_set_default_host(mpic->irqhost);
+}
+
+#else
+
+static inline void nemo_init_IRQ(struct mpic *mpic)
+{
+}
+#endif
+
 static __init void pas_init_IRQ(void)
 {
 	struct device_node *np;
@@ -243,6 +302,8 @@
 		mpic_unmask_irq(irq_get_irq_data(nmi_virq));
 	}
 
+	nemo_init_IRQ(mpic);
+
 	of_node_put(mpic_node);
 	of_node_put(root);
 }
@@ -338,55 +399,6 @@
 	return !!(srr1 & 0x2);
 }
 
-#ifdef CONFIG_PCMCIA
-static int pcmcia_notify(struct notifier_block *nb, unsigned long action,
-			 void *data)
-{
-	struct device *dev = data;
-	struct device *parent;
-	struct pcmcia_device *pdev = to_pcmcia_dev(dev);
-
-	/* We are only intereted in device addition */
-	if (action != BUS_NOTIFY_ADD_DEVICE)
-		return 0;
-
-	parent = pdev->socket->dev.parent;
-
-	/* We know electra_cf devices will always have of_node set, since
-	 * electra_cf is an of_platform driver.
-	 */
-	if (!parent->of_node)
-		return 0;
-
-	if (!of_device_is_compatible(parent->of_node, "electra-cf"))
-		return 0;
-
-	/* We use the direct ops for localbus */
-	dev->dma_ops = &dma_nommu_ops;
-
-	return 0;
-}
-
-static struct notifier_block pcmcia_notifier = {
-	.notifier_call = pcmcia_notify,
-};
-
-static inline void pasemi_pcmcia_init(void)
-{
-	extern struct bus_type pcmcia_bus_type;
-
-	bus_register_notifier(&pcmcia_bus_type, &pcmcia_notifier);
-}
-
-#else
-
-static inline void pasemi_pcmcia_init(void)
-{
-}
-
-#endif
-
-
 static const struct of_device_id pasemi_bus_ids[] = {
 	/* Unfortunately needed for legacy firmwares */
 	{ .type = "localbus", },
@@ -399,11 +411,11 @@
 
 static int __init pasemi_publish_devices(void)
 {
-	pasemi_pcmcia_init();
-
 	/* Publish OF platform devices for SDC and other non-PCI devices */
 	of_platform_bus_probe(NULL, pasemi_bus_ids, NULL);
 
+	nemo_init_rtc();
+
 	return 0;
 }
 machine_device_initcall(pasemi, pasemi_publish_devices);
@@ -418,6 +430,17 @@
 	    !of_machine_is_compatible("pasemi,pwrficient"))
 		return 0;
 
+#ifdef CONFIG_PPC_PASEMI_NEMO
+	/*
+	 * Check for the Nemo motherboard here, if we are running on one
+	 * change the machine definition to fit
+	 */
+	if (of_machine_is_compatible("pasemi,nemo")) {
+		pm_power_off		= pas_shutdown;
+		ppc_md.name		= "A-EON Amigaone X1000";
+	}
+#endif
+
 	iommu_init_early_pasemi();
 
 	return 1;
diff --git a/arch/powerpc/platforms/pasemi/time.c b/arch/powerpc/platforms/pasemi/time.c
index ea81525..ad72188 100644
--- a/arch/powerpc/platforms/pasemi/time.c
+++ b/arch/powerpc/platforms/pasemi/time.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2006 PA Semi, Inc
  *
  * Maintained by: Olof Johansson <olof@lixom.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/time.h>
diff --git a/arch/powerpc/platforms/powermac/Kconfig b/arch/powerpc/platforms/powermac/Kconfig
index fc90cb3..c02d8c5 100644
--- a/arch/powerpc/platforms/powermac/Kconfig
+++ b/arch/powerpc/platforms/powermac/Kconfig
@@ -3,10 +3,11 @@
 	bool "Apple PowerMac based machines"
 	depends on PPC_BOOK3S && CPU_BIG_ENDIAN
 	select MPIC
-	select PCI
+	select FORCE_PCI
 	select PPC_INDIRECT_PCI if PPC32
 	select PPC_MPC106 if PPC32
 	select PPC_NATIVE
+	select ZONE_DMA if PPC32
 	default y
 
 config PPC_PMAC64
diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile
index f2839ee..f4247ad 100644
--- a/arch/powerpc/platforms/powermac/Makefile
+++ b/arch/powerpc/platforms/powermac/Makefile
@@ -1,9 +1,16 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS_bootx_init.o  		+= -fPIC
+CFLAGS_bootx_init.o  		+= $(call cc-option, -fno-stack-protector)
+
+KASAN_SANITIZE_bootx_init.o := n
+
+ifdef CONFIG_KASAN
+CFLAGS_bootx_init.o  		+= -DDISABLE_BRANCH_PROFILING
+endif
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
-CFLAGS_REMOVE_bootx_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_bootx_init.o = $(CC_FLAGS_FTRACE)
 endif
 
 obj-y				+= pic.o setup.o time.o feature.o pci.o \
@@ -14,7 +21,5 @@
 # need this to be a bool.  Cheat here and pretend CONFIG_NVRAM=m is really
 # CONFIG_NVRAM=y
 obj-$(CONFIG_NVRAM:m=y)		+= nvram.o
-# ppc64 pmac doesn't define CONFIG_NVRAM but needs nvram stuff
-obj-$(CONFIG_PPC64)		+= nvram.o
 obj-$(CONFIG_PPC32)		+= bootx_init.o
 obj-$(CONFIG_SMP)		+= smp.o
diff --git a/arch/powerpc/platforms/powermac/backlight.c b/arch/powerpc/platforms/powermac/backlight.c
index 6b5dccc..32224cb 100644
--- a/arch/powerpc/platforms/powermac/backlight.c
+++ b/arch/powerpc/platforms/powermac/backlight.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Miscellaneous procedures for dealing with the PowerMac hardware.
  * Contains support for the backlight.
diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c
index 3b3b0b9..af309ee 100644
--- a/arch/powerpc/platforms/powermac/bootx_init.c
+++ b/arch/powerpc/platforms/powermac/bootx_init.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Early boot support code for BootX bootloader
  *
  *  Copyright (C) 2005 Ben. Herrenschmidt (benh@kernel.crashing.org)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/powermac/cache.S b/arch/powerpc/platforms/powermac/cache.S
index 27862fe..da69e0f 100644
--- a/arch/powerpc/platforms/powermac/cache.S
+++ b/arch/powerpc/platforms/powermac/cache.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains low-level cache management functions
  * used for sleep and CPU speed changes on Apple machines.
@@ -6,12 +7,6 @@
  *
  *    Copyright (C) 2004 Paul Mackerras (paulus@samba.org) and
  *                       Benjamin Herrenschmidt (benh@kernel.crashing.org)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/processor.h>
@@ -28,7 +23,7 @@
  */
 
 _GLOBAL(flush_disable_caches)
-#ifndef CONFIG_6xx
+#ifndef CONFIG_PPC_BOOK3S_32
 	blr
 #else
 BEGIN_FTR_SECTION
@@ -356,4 +351,4 @@
 	mtmsr	r11		/* restore DR and EE */
 	isync
 	blr
-#endif	/* CONFIG_6xx */
+#endif	/* CONFIG_PPC_BOOK3S_32 */
diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c
index 4eb8cb3..181caa3 100644
--- a/arch/powerpc/platforms/powermac/feature.c
+++ b/arch/powerpc/platforms/powermac/feature.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 1996-2001 Paul Mackerras (paulus@cs.anu.edu.au)
  *                          Ben. Herrenschmidt (benh@kernel.crashing.org)
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  *  TODO:
  *
  *   - Replace mdelay with some schedule loop if possible
@@ -14,7 +10,6 @@
  *     power)
  *   - Refcount some clocks (see darwin)
  *   - Split split split...
- *
  */
 #include <linux/types.h>
 #include <linux/init.h>
@@ -51,7 +46,7 @@
 #define DBG(fmt...)
 #endif
 
-#ifdef CONFIG_6xx
+#ifdef CONFIG_PPC_BOOK3S_32
 extern int powersave_lowspeed;
 #endif
 
@@ -173,9 +168,9 @@
 	macio = macio_find(node, 0);
 	if (!macio)
 		return -ENODEV;
-	if (!strcmp(node->name, "ch-a"))
+	if (of_node_name_eq(node, "ch-a"))
 		chan_mask = MACIO_FLAG_SCCA_ON;
-	else if (!strcmp(node->name, "ch-b"))
+	else if (of_node_name_eq(node, "ch-b"))
 		chan_mask = MACIO_FLAG_SCCB_ON;
 	else
 		return -ENODEV;
@@ -610,9 +605,9 @@
 	macio = macio_find(node, 0);
 	if (!macio)
 		return -ENODEV;
-	if (!strcmp(node->name, "ch-a"))
+	if (of_node_name_eq(node, "ch-a"))
 		chan_mask = MACIO_FLAG_SCCA_ON;
-	else if (!strcmp(node->name, "ch-b"))
+	else if (of_node_name_eq(node, "ch-b"))
 		chan_mask = MACIO_FLAG_SCCB_ON;
 	else
 		return -ENODEV;
@@ -1049,7 +1044,6 @@
 	unsigned long flags;
 	struct macio_chip *macio;
 	struct device_node *np;
-	struct device_node *cpus;
 	const int dflt_reset_lines[] = {	KL_GPIO_RESET_CPU0,
 						KL_GPIO_RESET_CPU1,
 						KL_GPIO_RESET_CPU2,
@@ -1059,10 +1053,7 @@
 	if (macio->type != macio_keylargo)
 		return -ENODEV;
 
-	cpus = of_find_node_by_path("/cpus");
-	if (cpus == NULL)
-		return -ENODEV;
-	for (np = cpus->child; np != NULL; np = np->sibling) {
+	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)
@@ -1072,7 +1063,6 @@
 			break;
 		}
 	}
-	of_node_put(cpus);
 	if (np == NULL || reset_io == 0)
 		reset_io = dflt_reset_lines[param];
 
@@ -1397,8 +1387,7 @@
 
 	if (parent == NULL)
 		return 0;
-	is_u3 = strcmp(parent->name, "u3") == 0 ||
-		strcmp(parent->name, "u4") == 0;
+	is_u3 = of_node_name_eq(parent, "u3") || of_node_name_eq(parent, "u4");
 	of_node_put(parent);
 	if (!is_u3)
 		return 0;
@@ -1476,6 +1465,7 @@
 	case 2:
 		if (macio->type == macio_shasta)
 			break;
+		/* fall through */
 	default:
 		return -ENODEV;
 	}
@@ -1504,16 +1494,12 @@
 	unsigned long flags;
 	struct macio_chip *macio;
 	struct device_node *np;
-	struct device_node *cpus;
 
 	macio = &macio_chips[0];
 	if (macio->type != macio_keylargo2 && macio->type != macio_shasta)
 		return -ENODEV;
 
-	cpus = of_find_node_by_path("/cpus");
-	if (cpus == NULL)
-		return -ENODEV;
-	for (np = cpus->child; np != NULL; np = np->sibling) {
+	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)
@@ -1523,7 +1509,6 @@
 			break;
 		}
 	}
-	of_node_put(cpus);
 	if (np == NULL || reset_io == 0)
 		return -ENODEV;
 
@@ -2515,31 +2500,26 @@
 	 * supposed to be set when not supported, but I'm not very confident
 	 * that all Apple OF revs did it properly, I do it the paranoid way.
 	 */
-	while (uninorth_base && uninorth_rev > 3) {
-		struct device_node *cpus = of_find_node_by_path("/cpus");
+	if (uninorth_base && uninorth_rev > 3) {
 		struct device_node *np;
 
-		if (!cpus || !cpus->child) {
-			printk(KERN_WARNING "Can't find CPU(s) in device tree !\n");
-			of_node_put(cpus);
-			break;
+		for_each_of_cpu_node(np) {
+			int cpu_count = 1;
+
+			/* Nap mode not supported on SMP */
+			if (of_get_property(np, "flush-on-lock", NULL) ||
+			    (cpu_count > 1)) {
+				powersave_nap = 0;
+				of_node_put(np);
+				break;
+			}
+
+			cpu_count++;
+			powersave_nap = 1;
 		}
-		np = cpus->child;
-		/* Nap mode not supported on SMP */
-		if (np->sibling) {
-			of_node_put(cpus);
-			break;
-		}
-		/* Nap mode not supported if flush-on-lock property is present */
-		if (of_get_property(np, "flush-on-lock", NULL)) {
-			of_node_put(cpus);
-			break;
-		}
-		of_node_put(cpus);
-		powersave_nap = 1;
-		printk(KERN_DEBUG "Processor NAP mode on idle enabled.\n");
-		break;
 	}
+	if (powersave_nap)
+		printk(KERN_DEBUG "Processor NAP mode on idle enabled.\n");
 
 	/* On CPUs that support it (750FX), lowspeed by default during
 	 * NAP mode
diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c
index d4d4118..bf4be4b 100644
--- a/arch/powerpc/platforms/powermac/low_i2c.c
+++ b/arch/powerpc/platforms/powermac/low_i2c.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/platforms/powermac/low_i2c.c
  *
  *  Copyright (C) 2003-2005 Ben. Herrenschmidt (benh@kernel.crashing.org)
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  * The linux i2c layer isn't completely suitable for our needs for various
  * reasons ranging from too late initialisation to semantics not perfectly
  * matching some requirements of the apple platform functions etc...
@@ -617,7 +613,7 @@
 		 * but not for now
 		 */
 		child = of_get_next_child(np, NULL);
-		multibus = !child || strcmp(child->name, "i2c-bus");
+		multibus = !of_node_name_eq(child, "i2c-bus");
 		of_node_put(child);
 
 		/* For a multibus setup, we get the bus count based on the
@@ -917,10 +913,9 @@
 	 * type as older device trees mix i2c busses and other things
 	 * at the same level
 	 */
-	for (busnode = NULL;
-	     (busnode = of_get_next_child(controller, busnode)) != NULL;) {
-		if (strcmp(busnode->type, "i2c") &&
-		    strcmp(busnode->type, "i2c-bus"))
+	for_each_child_of_node(controller, busnode) {
+		if (!of_node_is_type(busnode, "i2c") &&
+		    !of_node_is_type(busnode, "i2c-bus"))
 			continue;
 		reg = of_get_property(busnode, "reg", NULL);
 		if (reg == NULL)
@@ -1206,7 +1201,7 @@
 				if (bus != pmac_i2c_find_bus(np))
 					continue;
 			for (p = whitelist; p->name != NULL; p++) {
-				if (strcmp(np->name, p->name))
+				if (!of_node_name_eq(np, p->name))
 					continue;
 				if (p->compatible &&
 				    !of_device_is_compatible(np, p->compatible))
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index 60b03a1..dc7a5ba 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2002 Benjamin Herrenschmidt (benh@kernel.crashing.org)
  *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  *  Todo: - add support for the OF persistent properties
  */
 #include <linux/export.h>
@@ -18,7 +14,7 @@
 #include <linux/errno.h>
 #include <linux/adb.h>
 #include <linux/pmu.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/completion.h>
 #include <linux/spinlock.h>
 #include <asm/sections.h>
@@ -147,6 +143,11 @@
 static volatile unsigned char __iomem *nvram_addr;
 static int nvram_mult;
 
+static ssize_t ppc32_nvram_size(void)
+{
+	return NVRAM_SIZE;
+}
+
 static unsigned char direct_nvram_read_byte(int addr)
 {
 	return in_8(&nvram_data[(addr & (NVRAM_SIZE - 1)) * nvram_mult]);
@@ -513,7 +514,10 @@
 		printk(KERN_ERR "nvram: no address\n");
 		return -EINVAL;
 	}
-	nvram_image = memblock_virt_alloc(NVRAM_SIZE, 0);
+	nvram_image = memblock_alloc(NVRAM_SIZE, SMP_CACHE_BYTES);
+	if (!nvram_image)
+		panic("%s: Failed to allocate %u bytes\n", __func__,
+		      NVRAM_SIZE);
 	nvram_data = ioremap(addr, NVRAM_SIZE*2);
 	nvram_naddrs = 1; /* Make sure we get the correct case */
 
@@ -590,21 +594,25 @@
 		nvram_mult = 1;
 		ppc_md.nvram_read_val	= direct_nvram_read_byte;
 		ppc_md.nvram_write_val	= direct_nvram_write_byte;
+		ppc_md.nvram_size	= ppc32_nvram_size;
 	} else if (nvram_naddrs == 1) {
 		nvram_data = ioremap(r1.start, s1);
 		nvram_mult = (s1 + NVRAM_SIZE - 1) / NVRAM_SIZE;
 		ppc_md.nvram_read_val	= direct_nvram_read_byte;
 		ppc_md.nvram_write_val	= direct_nvram_write_byte;
+		ppc_md.nvram_size	= ppc32_nvram_size;
 	} else if (nvram_naddrs == 2) {
 		nvram_addr = ioremap(r1.start, s1);
 		nvram_data = ioremap(r2.start, s2);
 		ppc_md.nvram_read_val	= indirect_nvram_read_byte;
 		ppc_md.nvram_write_val	= indirect_nvram_write_byte;
+		ppc_md.nvram_size	= ppc32_nvram_size;
 	} else if (nvram_naddrs == 0 && sys_ctrler == SYS_CTRLER_PMU) {
 #ifdef CONFIG_ADB_PMU
 		nvram_naddrs = -1;
 		ppc_md.nvram_read_val	= pmu_nvram_read_byte;
 		ppc_md.nvram_write_val	= pmu_nvram_write_byte;
+		ppc_md.nvram_size	= ppc32_nvram_size;
 #endif /* CONFIG_ADB_PMU */
 	} else {
 		printk(KERN_ERR "Incompatible type of NVRAM\n");
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index 04527d1..e35eaa9 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Support for PCI bridges found on Power Macintoshes.
  *
  * Copyright (C) 2003-2005 Benjamin Herrenschmuidt (benh@kernel.crashing.org)
  * Copyright (C) 1997 Paul Mackerras (paulus@samba.org)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -501,9 +497,7 @@
 	/* XXX it would be better here to identify the specific
 	   PCI-PCI bridge chip we have. */
 	p2pbridge = of_find_node_by_name(NULL, "pci-bridge");
-	if (p2pbridge == NULL
-	    || p2pbridge->parent == NULL
-	    || strcmp(p2pbridge->parent->name, "pci") != 0)
+	if (p2pbridge == NULL || !of_node_name_eq(p2pbridge->parent, "pci"))
 		goto done;
 	if (pci_device_from_OF_node(p2pbridge, &bus, &devfn) < 0) {
 		DBG("Can't find PCI infos for PCI<->PCI bridge\n");
@@ -828,14 +822,14 @@
 	if (of_device_is_compatible(dev, "uni-north")) {
 		primary = setup_uninorth(hose, &rsrc);
 		disp_name = "UniNorth";
-	} else if (strcmp(dev->name, "pci") == 0) {
+	} else if (of_node_name_eq(dev, "pci")) {
 		/* XXX assume this is a mpc106 (grackle) */
 		setup_grackle(hose);
 		disp_name = "Grackle (MPC106)";
-	} else if (strcmp(dev->name, "bandit") == 0) {
+	} else if (of_node_name_eq(dev, "bandit")) {
 		setup_bandit(hose, &rsrc);
 		disp_name = "Bandit";
-	} else if (strcmp(dev->name, "chaos") == 0) {
+	} else if (of_node_name_eq(dev, "chaos")) {
 		setup_chaos(hose, &rsrc);
 		disp_name = "Chaos";
 		primary = 0;
@@ -914,16 +908,14 @@
 		       "of device tree\n");
 		return;
 	}
-	for (np = NULL; (np = of_get_next_child(root, np)) != NULL;) {
-		if (np->name == NULL)
-			continue;
-		if (strcmp(np->name, "bandit") == 0
-		    || strcmp(np->name, "chaos") == 0
-		    || strcmp(np->name, "pci") == 0) {
+	for_each_child_of_node(root, np) {
+		if (of_node_name_eq(np, "bandit")
+		    || of_node_name_eq(np, "chaos")
+		    || of_node_name_eq(np, "pci")) {
 			if (pmac_add_bridge(np) == 0)
 				of_node_get(np);
 		}
-		if (strcmp(np->name, "ht") == 0) {
+		if (of_node_name_eq(np, "ht")) {
 			of_node_get(np);
 			ht = np;
 		}
@@ -983,7 +975,7 @@
 	/* Firewire & GMAC were disabled after PCI probe, the driver is
 	 * claiming them, we must re-enable them now.
 	 */
-	if (uninorth_child && !strcmp(node->name, "firewire") &&
+	if (uninorth_child && of_node_name_eq(node, "firewire") &&
 	    (of_device_is_compatible(node, "pci106b,18") ||
 	     of_device_is_compatible(node, "pci106b,30") ||
 	     of_device_is_compatible(node, "pci11c1,5811"))) {
@@ -991,7 +983,7 @@
 		pmac_call_feature(PMAC_FTR_1394_ENABLE, node, 0, 1);
 		updatecfg = 1;
 	}
-	if (uninorth_child && !strcmp(node->name, "ethernet") &&
+	if (uninorth_child && of_node_name_eq(node, "ethernet") &&
 	    of_device_is_compatible(node, "gmac")) {
 		pmac_call_feature(PMAC_FTR_GMAC_ENABLE, node, 0, 1);
 		updatecfg = 1;
@@ -1262,4 +1254,3 @@
 	.enable_device_hook	= pmac_pci_enable_device_hook,
 #endif
 };
-
diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c
index fd2e210..62311e8 100644
--- a/arch/powerpc/platforms/powermac/pfunc_base.c
+++ b/arch/powerpc/platforms/powermac/pfunc_base.c
@@ -101,9 +101,8 @@
 	 * Find the "gpio" parent node
 	 */
 
-	for (gparent = NULL;
-	     (gparent = of_get_next_child(macio->of_node, gparent)) != NULL;)
-		if (strcmp(gparent->name, "gpio") == 0)
+	for_each_child_of_node(macio->of_node, gparent)
+		if (of_node_name_eq(gparent, "gpio"))
 			break;
 	if (gparent == NULL)
 		return;
@@ -313,7 +312,7 @@
 	 * Install handlers for the hwclock child if any
 	 */
 	for (np = NULL; (np = of_get_next_child(uninorth_node, np)) != NULL;)
-		if (strcmp(np->name, "hw-clock") == 0) {
+		if (of_node_name_eq(np, "hw-clock")) {
 			unin_hwclock = np;
 			break;
 		}
diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c
index e0462fe..94df0a9 100644
--- a/arch/powerpc/platforms/powermac/pfunc_core.c
+++ b/arch/powerpc/platforms/powermac/pfunc_core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *
  * FIXME: Properly make this race free with refcounting etc...
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 57bbff4..2e96907 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Support for the interrupt controllers found on Power Macintosh,
  *  currently Apple's "Grand Central" interrupt controller in all
@@ -7,12 +8,6 @@
  *  Copyright (C) 1997 Paul Mackerras (paulus@samba.org)
  *  Copyright (C) 2005 Benjamin Herrenschmidt (benh@kernel.crashing.org)
  *                     IBM, Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/stddef.h>
@@ -417,7 +412,7 @@
 		if (ints != NULL)
 			break;
 		device = device->parent;
-		if (device && strcmp(device->type, "pci") != 0)
+		if (!of_node_is_type(device, "pci"))
 			break;
 	}
 	if (ints == NULL)
@@ -553,13 +548,13 @@
 
 		for_each_node_with_property(np, "interrupt-controller") {
 			/* Skip /chosen/interrupt-controller */
-			if (strcmp(np->name, "chosen") == 0)
+			if (of_node_name_eq(np, "chosen"))
 				continue;
 			/* It seems like at least one person wants
 			 * to use BootX on a machine with an AppleKiwi
 			 * controller which happens to pretend to be an
 			 * interrupt controller too. */
-			if (strcmp(np->name, "AppleKiwi") == 0)
+			if (of_node_name_eq(np, "AppleKiwi"))
 				continue;
 			/* I think we found one ! */
 			of_irq_dflt_pic = np;
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 3a529fc..c6d5333 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Powermac setup and early boot code plus other random bits.
  *
@@ -11,12 +12,6 @@
  *    Copyright (C) 1995 Linus Torvalds
  *
  *  Maintained by Benjamin Herrenschmidt (benh@kernel.crashing.org)
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 /*
@@ -243,10 +238,9 @@
 {
 	/* Checks "l2cr-value" property in the registry */
 	if (cpu_has_feature(CPU_FTR_L2CR)) {
-		struct device_node *np = of_find_node_by_name(NULL, "cpus");
-		if (!np)
-			np = of_find_node_by_type(NULL, "cpu");
-		if (np) {
+		struct device_node *np;
+
+		for_each_of_cpu_node(np) {
 			const unsigned int *l2cr =
 				of_get_property(np, "l2cr-value", NULL);
 			if (l2cr) {
@@ -256,6 +250,7 @@
 				_set_L2CR(ppc_override_l2cr_value);
 			}
 			of_node_put(np);
+			break;
 		}
 	}
 
@@ -279,8 +274,8 @@
 	/* Set loops_per_jiffy to a half-way reasonable value,
 	   for use until calibrate_delay gets called. */
 	loops_per_jiffy = 50000000 / HZ;
-	cpu = of_find_node_by_type(NULL, "cpu");
-	if (cpu != NULL) {
+
+	for_each_of_cpu_node(cpu) {
 		fp = of_get_property(cpu, "clock-frequency", NULL);
 		if (fp != NULL) {
 			if (pvr >= 0x30 && pvr < 0x80)
@@ -292,8 +287,9 @@
 			else
 				/* 601, 603, etc. */
 				loops_per_jiffy = *fp / (2 * HZ);
+			of_node_put(cpu);
+			break;
 		}
-		of_node_put(cpu);
 	}
 
 	/* See if newworld or oldworld */
@@ -315,8 +311,7 @@
 	find_via_pmu();
 	smu_init();
 
-#if defined(CONFIG_NVRAM) || defined(CONFIG_NVRAM_MODULE) || \
-    defined(CONFIG_PPC64)
+#if IS_ENABLED(CONFIG_NVRAM)
 	pmac_nvram_init();
 #endif
 #ifdef CONFIG_PPC32
@@ -559,15 +554,9 @@
 	}
 	pr_debug("stdout is %pOF\n", prom_stdout);
 
-	name = of_get_property(prom_stdout, "name", NULL);
-	if (!name) {
-		pr_debug(" stdout package has no name !\n");
-		goto not_found;
-	}
-
-	if (strcmp(name, "ch-a") == 0)
+	if (of_node_name_eq(prom_stdout, "ch-a"))
 		offset = 0;
-	else if (strcmp(name, "ch-b") == 0)
+	else if (of_node_name_eq(prom_stdout, "ch-b"))
 		offset = 1;
 	else
 		goto not_found;
diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S
index f89808b..bd6085b 100644
--- a/arch/powerpc/platforms/powermac/sleep.S
+++ b/arch/powerpc/platforms/powermac/sleep.S
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains sleep low-level functions for PowerBook G3.
  *    Copyright (C) 1999 Benjamin Herrenschmidt (benh@kernel.crashing.org)
  *    and Paul Mackerras (paulus@samba.org).
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  */
 
 #include <asm/processor.h>
@@ -38,10 +33,18 @@
 #define SL_IBAT2	0x48
 #define SL_DBAT3	0x50
 #define SL_IBAT3	0x58
-#define SL_TB		0x60
-#define SL_R2		0x68
-#define SL_CR		0x6c
-#define SL_R12		0x70	/* r12 to r31 */
+#define SL_DBAT4	0x60
+#define SL_IBAT4	0x68
+#define SL_DBAT5	0x70
+#define SL_IBAT5	0x78
+#define SL_DBAT6	0x80
+#define SL_IBAT6	0x88
+#define SL_DBAT7	0x90
+#define SL_IBAT7	0x98
+#define SL_TB		0xa0
+#define SL_R2		0xa8
+#define SL_CR		0xac
+#define SL_R12		0xb0	/* r12 to r31 */
 #define SL_SIZE		(SL_R12 + 80)
 
 	.section .text
@@ -56,7 +59,7 @@
  * vector that will be called by the ROM on wakeup
  */
 _GLOBAL(low_sleep_handler)
-#ifndef CONFIG_6xx
+#ifndef CONFIG_PPC_BOOK3S_32
 	blr
 #else
 	mflr	r0
@@ -126,6 +129,41 @@
 	mfibatl	r4,3
 	stw	r4,SL_IBAT3+4(r1)
 
+BEGIN_MMU_FTR_SECTION
+	mfspr	r4,SPRN_DBAT4U
+	stw	r4,SL_DBAT4(r1)
+	mfspr	r4,SPRN_DBAT4L
+	stw	r4,SL_DBAT4+4(r1)
+	mfspr	r4,SPRN_DBAT5U
+	stw	r4,SL_DBAT5(r1)
+	mfspr	r4,SPRN_DBAT5L
+	stw	r4,SL_DBAT5+4(r1)
+	mfspr	r4,SPRN_DBAT6U
+	stw	r4,SL_DBAT6(r1)
+	mfspr	r4,SPRN_DBAT6L
+	stw	r4,SL_DBAT6+4(r1)
+	mfspr	r4,SPRN_DBAT7U
+	stw	r4,SL_DBAT7(r1)
+	mfspr	r4,SPRN_DBAT7L
+	stw	r4,SL_DBAT7+4(r1)
+	mfspr	r4,SPRN_IBAT4U
+	stw	r4,SL_IBAT4(r1)
+	mfspr	r4,SPRN_IBAT4L
+	stw	r4,SL_IBAT4+4(r1)
+	mfspr	r4,SPRN_IBAT5U
+	stw	r4,SL_IBAT5(r1)
+	mfspr	r4,SPRN_IBAT5L
+	stw	r4,SL_IBAT5+4(r1)
+	mfspr	r4,SPRN_IBAT6U
+	stw	r4,SL_IBAT6(r1)
+	mfspr	r4,SPRN_IBAT6L
+	stw	r4,SL_IBAT6+4(r1)
+	mfspr	r4,SPRN_IBAT7U
+	stw	r4,SL_IBAT7(r1)
+	mfspr	r4,SPRN_IBAT7L
+	stw	r4,SL_IBAT7+4(r1)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
 	/* Backup various CPU config stuffs */
 	bl	__save_cpu_setup
 
@@ -326,22 +364,37 @@
 	mtibatl	3,r4
 
 BEGIN_MMU_FTR_SECTION
-	li	r4,0
+	lwz	r4,SL_DBAT4(r1)
 	mtspr	SPRN_DBAT4U,r4
+	lwz	r4,SL_DBAT4+4(r1)
 	mtspr	SPRN_DBAT4L,r4
+	lwz	r4,SL_DBAT5(r1)
 	mtspr	SPRN_DBAT5U,r4
+	lwz	r4,SL_DBAT5+4(r1)
 	mtspr	SPRN_DBAT5L,r4
+	lwz	r4,SL_DBAT6(r1)
 	mtspr	SPRN_DBAT6U,r4
+	lwz	r4,SL_DBAT6+4(r1)
 	mtspr	SPRN_DBAT6L,r4
+	lwz	r4,SL_DBAT7(r1)
 	mtspr	SPRN_DBAT7U,r4
+	lwz	r4,SL_DBAT7+4(r1)
 	mtspr	SPRN_DBAT7L,r4
+	lwz	r4,SL_IBAT4(r1)
 	mtspr	SPRN_IBAT4U,r4
+	lwz	r4,SL_IBAT4+4(r1)
 	mtspr	SPRN_IBAT4L,r4
+	lwz	r4,SL_IBAT5(r1)
 	mtspr	SPRN_IBAT5U,r4
+	lwz	r4,SL_IBAT5+4(r1)
 	mtspr	SPRN_IBAT5L,r4
+	lwz	r4,SL_IBAT6(r1)
 	mtspr	SPRN_IBAT6U,r4
+	lwz	r4,SL_IBAT6+4(r1)
 	mtspr	SPRN_IBAT6L,r4
+	lwz	r4,SL_IBAT7(r1)
 	mtspr	SPRN_IBAT7U,r4
+	lwz	r4,SL_IBAT7+4(r1)
 	mtspr	SPRN_IBAT7L,r4
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 
@@ -394,5 +447,5 @@
 	.long 0
 	.balign	L1_CACHE_BYTES, 0
 
-#endif /* CONFIG_6xx */
+#endif /* CONFIG_PPC_BOOK3S_32 */
 	.section .text
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 447da6d..f95fbde 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SMP support for power macintosh.
  *
@@ -15,11 +16,6 @@
  *
  * Support for DayStar quad CPU cards
  * Copyright (C) XLR8, Inc. 1994-2000
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -832,8 +828,7 @@
 	mdelay(1);
 
 	/* Restore our exception vector */
-	*vector = save_vector;
-	flush_icache_range((unsigned long) vector, (unsigned long) vector + 4);
+	patch_instruction(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 f92c191..b36ddee 100644
--- a/arch/powerpc/platforms/powermac/time.c
+++ b/arch/powerpc/platforms/powermac/time.c
@@ -45,13 +45,6 @@
 #endif
 
 /*
- * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU
- * times wrap in 2040. If we need to handle later times, the read_time functions
- * need to be changed to interpret wrapped times as post-2040.
- */
-#define RTC_OFFSET	2082844800
-
-/*
  * Calibrate the decrementer frequency with the VIA timer 1.
  */
 #define VIA_TIMER_FREQ_6	4700000	/* time 1 frequency * 6 */
@@ -75,7 +68,7 @@
 long __init pmac_time_init(void)
 {
 	s32 delta = 0;
-#ifdef CONFIG_NVRAM
+#if defined(CONFIG_NVRAM) && defined(CONFIG_PPC32)
 	int dst;
 	
 	delta = ((s32)pmac_xpram_read(PMAC_XPRAM_MACHINE_LOC + 0x9)) << 16;
@@ -90,98 +83,6 @@
 	return delta;
 }
 
-#ifdef CONFIG_ADB_CUDA
-static time64_t cuda_get_time(void)
-{
-	struct adb_request req;
-	time64_t now;
-
-	if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0)
-		return 0;
-	while (!req.complete)
-		cuda_poll();
-	if (req.reply_len != 7)
-		printk(KERN_ERR "cuda_get_time: got %d byte reply\n",
-		       req.reply_len);
-	now = (u32)((req.reply[3] << 24) + (req.reply[4] << 16) +
-		    (req.reply[5] << 8) + req.reply[6]);
-	/* it's either after year 2040, or the RTC has gone backwards */
-	WARN_ON(now < RTC_OFFSET);
-
-	return now - RTC_OFFSET;
-}
-
-#define cuda_get_rtc_time(tm)	rtc_time64_to_tm(cuda_get_time(), (tm))
-
-static int cuda_set_rtc_time(struct rtc_time *tm)
-{
-	u32 nowtime;
-	struct adb_request req;
-
-	nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
-	if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME,
-			 nowtime >> 24, nowtime >> 16, nowtime >> 8,
-			 nowtime) < 0)
-		return -ENXIO;
-	while (!req.complete)
-		cuda_poll();
-	if ((req.reply_len != 3) && (req.reply_len != 7))
-		printk(KERN_ERR "cuda_set_rtc_time: got %d byte reply\n",
-		       req.reply_len);
-	return 0;
-}
-
-#else
-#define cuda_get_time()		0
-#define cuda_get_rtc_time(tm)
-#define cuda_set_rtc_time(tm)	0
-#endif
-
-#ifdef CONFIG_ADB_PMU
-static time64_t pmu_get_time(void)
-{
-	struct adb_request req;
-	time64_t now;
-
-	if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
-		return 0;
-	pmu_wait_complete(&req);
-	if (req.reply_len != 4)
-		printk(KERN_ERR "pmu_get_time: got %d byte reply from PMU\n",
-		       req.reply_len);
-	now = (u32)((req.reply[0] << 24) + (req.reply[1] << 16)	+
-		    (req.reply[2] << 8) + req.reply[3]);
-
-	/* it's either after year 2040, or the RTC has gone backwards */
-	WARN_ON(now < RTC_OFFSET);
-
-	return now - RTC_OFFSET;
-}
-
-#define pmu_get_rtc_time(tm)	rtc_time64_to_tm(pmu_get_time(), (tm))
-
-static int pmu_set_rtc_time(struct rtc_time *tm)
-{
-	u32 nowtime;
-	struct adb_request req;
-
-	nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
-	if (pmu_request(&req, NULL, 5, PMU_SET_RTC, nowtime >> 24,
-			nowtime >> 16, nowtime >> 8, nowtime) < 0)
-		return -ENXIO;
-	pmu_wait_complete(&req);
-	if (req.reply_len != 0)
-		printk(KERN_ERR "pmu_set_rtc_time: %d byte reply from PMU\n",
-		       req.reply_len);
-	return 0;
-}
-
-#else
-#define pmu_get_time()		0
-#define pmu_get_rtc_time(tm)
-#define pmu_set_rtc_time(tm)	0
-#endif
-
 #ifdef CONFIG_PMAC_SMU
 static time64_t smu_get_time(void)
 {
@@ -191,11 +92,6 @@
 		return 0;
 	return rtc_tm_to_time64(&tm);
 }
-
-#else
-#define smu_get_time()			0
-#define smu_get_rtc_time(tm, spin)
-#define smu_set_rtc_time(tm, spin)	0
 #endif
 
 /* Can't be __init, it's called when suspending and resuming */
@@ -203,12 +99,18 @@
 {
 	/* Get the time from the RTC, used only at boot time */
 	switch (sys_ctrler) {
+#ifdef CONFIG_ADB_CUDA
 	case SYS_CTRLER_CUDA:
 		return cuda_get_time();
+#endif
+#ifdef CONFIG_ADB_PMU
 	case SYS_CTRLER_PMU:
 		return pmu_get_time();
+#endif
+#ifdef CONFIG_PMAC_SMU
 	case SYS_CTRLER_SMU:
 		return smu_get_time();
+#endif
 	default:
 		return 0;
 	}
@@ -218,15 +120,21 @@
 {
 	/* Get the time from the RTC, used only at boot time */
 	switch (sys_ctrler) {
+#ifdef CONFIG_ADB_CUDA
 	case SYS_CTRLER_CUDA:
-		cuda_get_rtc_time(tm);
+		rtc_time64_to_tm(cuda_get_time(), tm);
 		break;
+#endif
+#ifdef CONFIG_ADB_PMU
 	case SYS_CTRLER_PMU:
-		pmu_get_rtc_time(tm);
+		rtc_time64_to_tm(pmu_get_time(), tm);
 		break;
+#endif
+#ifdef CONFIG_PMAC_SMU
 	case SYS_CTRLER_SMU:
 		smu_get_rtc_time(tm, 1);
 		break;
+#endif
 	default:
 		;
 	}
@@ -235,12 +143,18 @@
 int pmac_set_rtc_time(struct rtc_time *tm)
 {
 	switch (sys_ctrler) {
+#ifdef CONFIG_ADB_CUDA
 	case SYS_CTRLER_CUDA:
 		return cuda_set_rtc_time(tm);
+#endif
+#ifdef CONFIG_ADB_PMU
 	case SYS_CTRLER_PMU:
 		return pmu_set_rtc_time(tm);
+#endif
+#ifdef CONFIG_PMAC_SMU
 	case SYS_CTRLER_SMU:
 		return smu_set_rtc_time(tm, 1);
+#endif
 	default:
 		return -ENODEV;
 	}
diff --git a/arch/powerpc/platforms/powermac/udbg_adb.c b/arch/powerpc/platforms/powermac/udbg_adb.c
index 64f38f0..12158bb 100644
--- a/arch/powerpc/platforms/powermac/udbg_adb.c
+++ b/arch/powerpc/platforms/powermac/udbg_adb.c
@@ -194,7 +194,7 @@
 	 */
 	for_each_node_by_name(np, "keyboard") {
 		struct device_node *parent = of_get_parent(np);
-		int found = (parent && strcmp(parent->type, "adb") == 0);
+		int found = of_node_is_type(parent, "adb");
 		of_node_put(parent);
 		if (found)
 			break;
diff --git a/arch/powerpc/platforms/powermac/udbg_scc.c b/arch/powerpc/platforms/powermac/udbg_scc.c
index 8901973..6b61a18 100644
--- a/arch/powerpc/platforms/powermac/udbg_scc.c
+++ b/arch/powerpc/platforms/powermac/udbg_scc.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * udbg for zilog scc ports as found on Apple PowerMacs
  *
  * Copyright (C) 2001-2005 PPC 64 Team, IBM Corp
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 #include <linux/types.h>
 #include <asm/udbg.h>
@@ -87,7 +83,7 @@
 	for (ch = NULL; (ch = of_get_next_child(escc, ch)) != NULL;) {
 		if (ch == stdout)
 			ch_def = of_node_get(ch);
-		if (strcmp(ch->name, "ch-a") == 0)
+		if (of_node_name_eq(ch, "ch-a"))
 			ch_a = of_node_get(ch);
 	}
 	if (ch_def == NULL && !force_scc)
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index f8dc98d..938803e 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -7,19 +7,13 @@
 	select PPC_ICP_NATIVE
 	select PPC_XIVE_NATIVE
 	select PPC_P7_NAP
-	select PCI
+	select FORCE_PCI
 	select PCI_MSI
 	select EPAPR_BOOT
 	select PPC_INDIRECT_PIO
 	select PPC_UDBG_16550
-	select PPC_SCOM
 	select ARCH_RANDOM
 	select CPU_FREQ
-	select CPU_FREQ_GOV_PERFORMANCE
-	select CPU_FREQ_GOV_POWERSAVE
-	select CPU_FREQ_GOV_USERSPACE
-	select CPU_FREQ_GOV_ONDEMAND
-	select CPU_FREQ_GOV_CONSERVATIVE
 	select PPC_DOORBELL
 	select MMU_NOTIFIER
 	select FORCE_SMP
@@ -35,7 +29,6 @@
 config PPC_MEMTRACE
 	bool "Enable removal of RAM from kernel mappings for tracing"
 	depends on PPC_POWERNV && MEMORY_HOTREMOVE
-	default n
 	help
 	  Enabling this option allows for the removal of memory (RAM)
 	  from the kernel mappings to be used for hardware tracing.
@@ -53,3 +46,7 @@
 	  VAS adapters are found in POWER9 based systems.
 
 	  If unsure, say N.
+
+config SCOM_DEBUGFS
+	bool "Expose SCOM controllers via debugfs"
+	depends on DEBUG_FS
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index b540ce8..a3ac964 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,19 +1,22 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-y			+= setup.o opal-wrappers.o opal.o opal-async.o idle.o
-obj-y			+= opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
+obj-y			+= setup.o opal-call.o opal-wrappers.o opal.o opal-async.o
+obj-y			+= idle.o opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y			+= rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
 obj-y			+= opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o
 obj-y			+= opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o
+obj-y			+= ultravisor.o
 
 obj-$(CONFIG_SMP)	+= smp.o subcore.o subcore-asm.o
+obj-$(CONFIG_FA_DUMP)	+= opal-fadump.o
+obj-$(CONFIG_PRESERVE_FA_DUMP)	+= opal-fadump.o
+obj-$(CONFIG_OPAL_CORE)	+= opal-core.o
 obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o
 obj-$(CONFIG_CXL_BASE)	+= pci-cxl.o
 obj-$(CONFIG_EEH)	+= eeh-powernv.o
-obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
-obj-$(CONFIG_TRACEPOINTS)	+= opal-tracepoints.o
 obj-$(CONFIG_OPAL_PRD)	+= opal-prd.o
 obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
 obj-$(CONFIG_PPC_MEMTRACE)	+= memtrace.o
 obj-$(CONFIG_PPC_VAS)	+= vas.o vas-window.o vas-debug.o
 obj-$(CONFIG_OCXL_BASE)	+= ocxl.o
+obj-$(CONFIG_SCOM_DEBUGFS) += opal-xscom.o
diff --git a/arch/powerpc/platforms/powernv/copy-paste.h b/arch/powerpc/platforms/powernv/copy-paste.h
index cb36f9f..f063807 100644
--- a/arch/powerpc/platforms/powernv/copy-paste.h
+++ b/arch/powerpc/platforms/powernv/copy-paste.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2016-17 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc-opcode.h>
 #include <asm/reg.h>
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 3c1beae..6f300ab 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1,14 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * The file intends to implement the platform dependent EEH operations on
- * powernv platform. Actually, the powernv was created in order to fully
- * hypervisor support.
+ * PowerNV Platform dependent EEH operations
  *
  * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/atomic.h>
@@ -40,6 +34,7 @@
 
 #include "powernv.h"
 #include "pci.h"
+#include "../../../../drivers/pci/pci.h"
 
 static int eeh_event_irq = -EINVAL;
 
@@ -47,13 +42,10 @@
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 
-	if (!pdev->is_virtfn)
+	if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED))
 		return;
 
-	/*
-	 * The following operations will fail if VF's sysfs files
-	 * aren't created or its resources aren't finalized.
-	 */
+	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
 	eeh_add_device_early(pdn);
 	eeh_add_device_late(pdev);
 	eeh_sysfs_add_device(pdev);
@@ -205,6 +197,25 @@
 
 #endif /* CONFIG_DEBUG_FS */
 
+void pnv_eeh_enable_phbs(void)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		phb = hose->private_data;
+		/*
+		 * If EEH is enabled, we're going to rely on that.
+		 * Otherwise, we restore to conventional mechanism
+		 * to clear frozen PE during PCI config access.
+		 */
+		if (eeh_enabled())
+			phb->flags |= PNV_PHB_FLAG_EEH;
+		else
+			phb->flags &= ~PNV_PHB_FLAG_EEH;
+	}
+}
+
 /**
  * pnv_eeh_post_init - EEH platform dependent post initialization
  *
@@ -219,17 +230,7 @@
 	struct pnv_phb *phb;
 	int ret = 0;
 
-	/* Probe devices & build address cache */
-	eeh_probe_devices();
-	eeh_addr_cache_build();
-
-	if (eeh_has_flag(EEH_POSTPONED_PROBE)) {
-		eeh_clear_flag(EEH_POSTPONED_PROBE);
-		if (eeh_enabled())
-			pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
-		else
-			pr_info("EEH: No capable adapters found\n");
-	}
+	eeh_show_enabled();
 
 	/* Register OPAL event notifier */
 	eeh_event_irq = opal_event_request(ilog2(OPAL_EVENT_PCI_ERROR));
@@ -251,19 +252,11 @@
 	if (!eeh_enabled())
 		disable_irq(eeh_event_irq);
 
+	pnv_eeh_enable_phbs();
+
 	list_for_each_entry(hose, &hose_list, list_node) {
 		phb = hose->private_data;
 
-		/*
-		 * If EEH is enabled, we're going to rely on that.
-		 * Otherwise, we restore to conventional mechanism
-		 * to clear frozen PE during PCI config access.
-		 */
-		if (eeh_enabled())
-			phb->flags |= PNV_PHB_FLAG_EEH;
-		else
-			phb->flags &= ~PNV_PHB_FLAG_EEH;
-
 		/* Create debugfs entries */
 #ifdef CONFIG_DEBUG_FS
 		if (phb->has_dbgfs || !phb->dbgfs)
@@ -391,11 +384,7 @@
 	if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA)
 		return NULL;
 
-	/* Skip if we haven't probed yet */
-	if (phb->ioda.pe_rmap[config_addr] == IODA_INVALID_PE) {
-		eeh_add_flag(EEH_POSTPONED_PROBE);
-		return NULL;
-	}
+	eeh_edev_dbg(edev, "Probing device\n");
 
 	/* Initialize eeh device */
 	edev->class_code = pdn->class_code;
@@ -422,9 +411,7 @@
 	/* Create PE */
 	ret = eeh_add_to_parent_pe(edev);
 	if (ret) {
-		pr_warn("%s: Can't add PCI dev %04x:%02x:%02x.%01x to parent PE (%x)\n",
-			__func__, hose->global_number, pdn->busno,
-			PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn), ret);
+		eeh_edev_warn(edev, "Failed to add device to PE (code %d)\n", ret);
 		return NULL;
 	}
 
@@ -473,11 +460,17 @@
 	 * Enable EEH explicitly so that we will do EEH check
 	 * while accessing I/O stuff
 	 */
-	eeh_add_flag(EEH_ENABLED);
+	if (!eeh_has_flag(EEH_ENABLED)) {
+		enable_irq(eeh_event_irq);
+		pnv_eeh_enable_phbs();
+		eeh_add_flag(EEH_ENABLED);
+	}
 
 	/* Save memory bars */
 	eeh_save_bars(edev);
 
+	eeh_edev_dbg(edev, "EEH enabled on device\n");
+
 	return NULL;
 }
 
@@ -578,8 +571,8 @@
 static int pnv_eeh_get_phb_state(struct eeh_pe *pe)
 {
 	struct pnv_phb *phb = pe->phb->private_data;
-	u8 fstate;
-	__be16 pcierr;
+	u8 fstate = 0;
+	__be16 pcierr = 0;
 	s64 rc;
 	int result = 0;
 
@@ -604,7 +597,7 @@
 			  EEH_STATE_MMIO_ENABLED |
 			  EEH_STATE_DMA_ENABLED);
 	} else if (!(pe->state & EEH_PE_ISOLATED)) {
-		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+		eeh_pe_mark_isolated(pe);
 		pnv_eeh_get_phb_diag(pe);
 
 		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
@@ -617,8 +610,8 @@
 static int pnv_eeh_get_pe_state(struct eeh_pe *pe)
 {
 	struct pnv_phb *phb = pe->phb->private_data;
-	u8 fstate;
-	__be16 pcierr;
+	u8 fstate = 0;
+	__be16 pcierr = 0;
 	s64 rc;
 	int result;
 
@@ -706,7 +699,7 @@
 		if (phb->freeze_pe)
 			phb->freeze_pe(phb, pe->addr);
 
-		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+		eeh_pe_mark_isolated(pe);
 		pnv_eeh_get_phb_diag(pe);
 
 		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
@@ -857,7 +850,7 @@
 	int aer = edev ? edev->aer_cap : 0;
 	u32 ctrl;
 
-	pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n",
+	pr_debug("%s: Secondary Reset PCI bus %04x:%02x with option %d\n",
 		 __func__, pci_domain_nr(dev->bus),
 		 dev->bus->number, option);
 
@@ -915,6 +908,10 @@
 	if (!dn || !of_get_property(dn, "ibm,reset-by-firmware", NULL))
 		return __pnv_eeh_bridge_reset(pdev, option);
 
+	pr_debug("%s: FW reset PCI bus %04x:%02x with option %d\n",
+		 __func__, pci_domain_nr(pdev->bus),
+		 pdev->bus->number, option);
+
 	switch (option) {
 	case EEH_RESET_FUNDAMENTAL:
 		scope = OPAL_RESET_PCI_FUNDAMENTAL;
@@ -1054,7 +1051,7 @@
 	int ret;
 
 	/* The VF PE should have only one child device */
-	edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, list);
+	edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry);
 	pdn = eeh_dev_to_pdn(edev);
 	if (!pdn)
 		return -ENXIO;
@@ -1133,55 +1130,38 @@
 		return -EIO;
 	}
 
-	/*
-	 * If dealing with the root bus (or the bus underneath the
-	 * root port), we reset the bus underneath the root port.
-	 *
-	 * The cxl driver depends on this behaviour for bi-modal card
-	 * switching.
-	 */
-	if (pci_is_root_bus(bus) ||
-	    pci_is_root_bus(bus->parent))
+	if (pci_is_root_bus(bus))
 		return pnv_eeh_root_reset(hose, option);
 
-	return pnv_eeh_bridge_reset(bus->self, option);
-}
-
-/**
- * pnv_eeh_wait_state - Wait for PE state
- * @pe: EEH PE
- * @max_wait: maximal period in millisecond
- *
- * Wait for the state of associated PE. It might take some time
- * to retrieve the PE's state.
- */
-static int pnv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
-{
-	int ret;
-	int mwait;
-
-	while (1) {
-		ret = pnv_eeh_get_state(pe, &mwait);
-
+	/*
+	 * For hot resets try use the generic PCI error recovery reset
+	 * functions. These correctly handles the case where the secondary
+	 * bus is behind a hotplug slot and it will use the slot provided
+	 * reset methods to prevent spurious hotplug events during the reset.
+	 *
+	 * Fundemental resets need to be handled internally to EEH since the
+	 * PCI core doesn't really have a concept of a fundemental reset,
+	 * mainly because there's no standard way to generate one. Only a
+	 * few devices require an FRESET so it should be fine.
+	 */
+	if (option != EEH_RESET_FUNDAMENTAL) {
 		/*
-		 * If the PE's state is temporarily unavailable,
-		 * we have to wait for the specified time. Otherwise,
-		 * the PE's state will be returned immediately.
+		 * NB: Skiboot and pnv_eeh_bridge_reset() also no-op the
+		 *     de-assert step. It's like the OPAL reset API was
+		 *     poorly designed or something...
 		 */
-		if (ret != EEH_STATE_UNAVAILABLE)
-			return ret;
+		if (option == EEH_RESET_DEACTIVATE)
+			return 0;
 
-		if (max_wait <= 0) {
-			pr_warn("%s: Timeout getting PE#%x's state (%d)\n",
-				__func__, pe->addr, max_wait);
-			return EEH_STATE_NOT_SUPPORT;
-		}
-
-		max_wait -= mwait;
-		msleep(mwait);
+		rc = pci_bus_error_reset(bus->self);
+		if (!rc)
+			return 0;
 	}
 
-	return EEH_STATE_NOT_SUPPORT;
+	/* otherwise, use the generic bridge reset. this might call into FW */
+	if (pci_is_root_bus(bus->parent))
+		return pnv_eeh_root_reset(hose, option);
+	return pnv_eeh_bridge_reset(bus->self, option);
 }
 
 /**
@@ -1611,7 +1591,7 @@
 		if ((ret == EEH_NEXT_ERR_FROZEN_PE  ||
 		    ret == EEH_NEXT_ERR_FENCED_PHB) &&
 		    !((*pe)->state & EEH_PE_ISOLATED)) {
-			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+			eeh_pe_mark_isolated(*pe);
 			pnv_eeh_get_phb_diag(*pe);
 
 			if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
@@ -1640,7 +1620,7 @@
 			}
 
 			/* We possibly migrate to another PE */
-			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+			eeh_pe_mark_isolated(*pe);
 		}
 
 		/*
@@ -1702,7 +1682,6 @@
 	.get_pe_addr            = pnv_eeh_get_pe_addr,
 	.get_state              = pnv_eeh_get_state,
 	.reset                  = pnv_eeh_reset,
-	.wait_state             = pnv_eeh_wait_state,
 	.get_log                = pnv_eeh_get_log,
 	.configure_bridge       = pnv_eeh_configure_bridge,
 	.err_inject		= pnv_eeh_err_inject,
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 35f699e..78599bc 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV cpuidle code
  *
  * Copyright 2015 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/types.h>
@@ -16,6 +12,7 @@
 #include <linux/device.h>
 #include <linux/cpu.h>
 
+#include <asm/asm-prototypes.h>
 #include <asm/firmware.h>
 #include <asm/machdep.h>
 #include <asm/opal.h>
@@ -48,10 +45,10 @@
 static bool default_stop_found;
 
 /*
- * First deep stop state. Used to figure out when to save/restore
- * hypervisor context.
+ * First stop state levels when SPR and TB loss can occur.
  */
-u64 pnv_first_deep_stop_state = MAX_STOP_STATE;
+static u64 pnv_first_tb_loss_level = MAX_STOP_STATE + 1;
+static u64 pnv_first_spr_loss_level = MAX_STOP_STATE + 1;
 
 /*
  * psscr value and mask of the deepest stop idle state.
@@ -62,6 +59,8 @@
 static u64 pnv_deepest_stop_flag;
 static bool deepest_stop_found;
 
+static unsigned long power7_offline_type;
+
 static int pnv_save_sprs_for_deep_states(void)
 {
 	int cpu;
@@ -72,12 +71,12 @@
 	 * all cpus at boot. Get these reg values of current cpu and use the
 	 * same across all cpus.
 	 */
-	uint64_t lpcr_val = mfspr(SPRN_LPCR);
-	uint64_t hid0_val = mfspr(SPRN_HID0);
-	uint64_t hid1_val = mfspr(SPRN_HID1);
-	uint64_t hid4_val = mfspr(SPRN_HID4);
-	uint64_t hid5_val = mfspr(SPRN_HID5);
-	uint64_t hmeer_val = mfspr(SPRN_HMEER);
+	uint64_t lpcr_val	= mfspr(SPRN_LPCR);
+	uint64_t hid0_val	= mfspr(SPRN_HID0);
+	uint64_t hid1_val	= mfspr(SPRN_HID1);
+	uint64_t hid4_val	= mfspr(SPRN_HID4);
+	uint64_t hid5_val	= mfspr(SPRN_HID5);
+	uint64_t hmeer_val	= mfspr(SPRN_HMEER);
 	uint64_t msr_val = MSR_IDLE;
 	uint64_t psscr_val = pnv_deepest_stop_psscr_val;
 
@@ -137,89 +136,6 @@
 	return 0;
 }
 
-static void pnv_alloc_idle_core_states(void)
-{
-	int i, j;
-	int nr_cores = cpu_nr_cores();
-	u32 *core_idle_state;
-
-	/*
-	 * core_idle_state - The lower 8 bits track the idle state of
-	 * each thread of the core.
-	 *
-	 * The most significant bit is the lock bit.
-	 *
-	 * Initially all the bits corresponding to threads_per_core
-	 * are set. They are cleared when the thread enters deep idle
-	 * state like sleep and winkle/stop.
-	 *
-	 * Initially the lock bit is cleared.  The lock bit has 2
-	 * purposes:
-	 * 	a. While the first thread in the core waking up from
-	 * 	   idle is restoring core state, it prevents other
-	 * 	   threads in the core from switching to process
-	 * 	   context.
-	 * 	b. While the last thread in the core is saving the
-	 *	   core state, it prevents a different thread from
-	 *	   waking up.
-	 */
-	for (i = 0; i < nr_cores; i++) {
-		int first_cpu = i * threads_per_core;
-		int node = cpu_to_node(first_cpu);
-		size_t paca_ptr_array_size;
-
-		core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
-		*core_idle_state = (1 << threads_per_core) - 1;
-		paca_ptr_array_size = (threads_per_core *
-				       sizeof(struct paca_struct *));
-
-		for (j = 0; j < threads_per_core; j++) {
-			int cpu = first_cpu + j;
-
-			paca_ptrs[cpu]->core_idle_state_ptr = core_idle_state;
-			paca_ptrs[cpu]->thread_idle_state = PNV_THREAD_RUNNING;
-			paca_ptrs[cpu]->thread_mask = 1 << j;
-		}
-	}
-
-	update_subcore_sibling_mask();
-
-	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) {
-		int rc = pnv_save_sprs_for_deep_states();
-
-		if (likely(!rc))
-			return;
-
-		/*
-		 * The stop-api is unable to restore hypervisor
-		 * resources on wakeup from platform idle states which
-		 * lose full context. So disable such states.
-		 */
-		supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT;
-		pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n");
-		pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");
-
-		if (cpu_has_feature(CPU_FTR_ARCH_300) &&
-		    (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
-			/*
-			 * Use the default stop state for CPU-Hotplug
-			 * if available.
-			 */
-			if (default_stop_found) {
-				pnv_deepest_stop_psscr_val =
-					pnv_default_stop_val;
-				pnv_deepest_stop_psscr_mask =
-					pnv_default_stop_mask;
-				pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
-					pnv_deepest_stop_psscr_val);
-			} else { /* Fallback to snooze loop for CPU-Hotplug */
-				deepest_stop_found = false;
-				pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
-			}
-		}
-	}
-}
-
 u32 pnv_get_supported_cpuidle_states(void)
 {
 	return supported_cpuidle_states;
@@ -238,6 +154,9 @@
 		*err = 1;
 }
 
+static bool power7_fastsleep_workaround_entry = true;
+static bool power7_fastsleep_workaround_exit = true;
+
 /*
  * Used to store fastsleep workaround state
  * 0 - Workaround applied/undone at fastsleep entry/exit path (Default)
@@ -269,21 +188,15 @@
 	 * fastsleep_workaround_applyonce = 1 implies
 	 * fastsleep workaround needs to be left in 'applied' state on all
 	 * the cores. Do this by-
-	 * 1. Patching out the call to 'undo' workaround in fastsleep exit path
-	 * 2. Sending ipi to all the cores which have at least one online thread
-	 * 3. Patching out the call to 'apply' workaround in fastsleep entry
-	 * path
+	 * 1. Disable the 'undo' workaround in fastsleep exit path
+	 * 2. Sendi IPIs to all the cores which have at least one online thread
+	 * 3. Disable the 'apply' workaround in fastsleep entry path
+	 *
 	 * There is no need to send ipi to cores which have all threads
 	 * offlined, as last thread of the core entering fastsleep or deeper
 	 * state would have applied workaround.
 	 */
-	err = patch_instruction(
-		(unsigned int *)pnv_fastsleep_workaround_at_exit,
-		PPC_INST_NOP);
-	if (err) {
-		pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_exit");
-		goto fail;
-	}
+	power7_fastsleep_workaround_exit = false;
 
 	get_online_cpus();
 	primary_thread_mask = cpu_online_cores_map();
@@ -296,13 +209,7 @@
 		goto fail;
 	}
 
-	err = patch_instruction(
-		(unsigned int *)pnv_fastsleep_workaround_at_entry,
-		PPC_INST_NOP);
-	if (err) {
-		pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_entry");
-		goto fail;
-	}
+	power7_fastsleep_workaround_entry = false;
 
 	fastsleep_workaround_applyonce = 1;
 
@@ -315,27 +222,346 @@
 			show_fastsleep_workaround_applyonce,
 			store_fastsleep_workaround_applyonce);
 
-static unsigned long __power7_idle_type(unsigned long type)
+static inline void atomic_start_thread_idle(void)
 {
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	int thread_nr = cpu_thread_in_core(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+
+	clear_bit(thread_nr, state);
+}
+
+static inline void atomic_stop_thread_idle(void)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	int thread_nr = cpu_thread_in_core(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+
+	set_bit(thread_nr, state);
+}
+
+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;
+
+	while (unlikely(test_and_set_bit_lock(NR_PNV_CORE_IDLE_LOCK_BIT, state)))
+		barrier();
+}
+
+static inline void atomic_unlock_and_stop_thread_idle(void)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	unsigned long thread = 1UL << cpu_thread_in_core(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+	u64 s = READ_ONCE(*state);
+	u64 new, tmp;
+
+	BUG_ON(!(s & PNV_CORE_IDLE_LOCK_BIT));
+	BUG_ON(s & thread);
+
+again:
+	new = (s | thread) & ~PNV_CORE_IDLE_LOCK_BIT;
+	tmp = cmpxchg(state, s, new);
+	if (unlikely(tmp != s)) {
+		s = tmp;
+		goto again;
+	}
+}
+
+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;
+
+	BUG_ON(!test_bit(NR_PNV_CORE_IDLE_LOCK_BIT, state));
+	clear_bit_unlock(NR_PNV_CORE_IDLE_LOCK_BIT, state);
+}
+
+/* P7 and P8 */
+struct p7_sprs {
+	/* per core */
+	u64 tscr;
+	u64 worc;
+
+	/* per subcore */
+	u64 sdr1;
+	u64 rpr;
+
+	/* per thread */
+	u64 lpcr;
+	u64 hfscr;
+	u64 fscr;
+	u64 purr;
+	u64 spurr;
+	u64 dscr;
+	u64 wort;
+
+	/* per thread SPRs that get lost in shallow states */
+	u64 amr;
+	u64 iamr;
+	u64 amor;
+	u64 uamor;
+};
+
+static unsigned long power7_idle_insn(unsigned long type)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+	unsigned long thread = 1UL << cpu_thread_in_core(cpu);
+	unsigned long core_thread_mask = (1UL << threads_per_core) - 1;
 	unsigned long srr1;
+	bool full_winkle;
+	struct p7_sprs sprs = {}; /* avoid false use-uninitialised */
+	bool sprs_saved = false;
+	int rc;
 
-	if (!prep_irq_for_idle_irqsoff())
-		return 0;
+	if (unlikely(type != PNV_THREAD_NAP)) {
+		atomic_lock_thread_idle();
 
-	__ppc64_runlatch_off();
-	srr1 = power7_idle_insn(type);
-	__ppc64_runlatch_on();
+		BUG_ON(!(*state & thread));
+		*state &= ~thread;
 
-	fini_irq_for_idle_irqsoff();
+		if (power7_fastsleep_workaround_entry) {
+			if ((*state & core_thread_mask) == 0) {
+				rc = opal_config_cpu_idle_state(
+						OPAL_CONFIG_IDLE_FASTSLEEP,
+						OPAL_CONFIG_IDLE_APPLY);
+				BUG_ON(rc);
+			}
+		}
+
+		if (type == PNV_THREAD_WINKLE) {
+			sprs.tscr	= mfspr(SPRN_TSCR);
+			sprs.worc	= mfspr(SPRN_WORC);
+
+			sprs.sdr1	= mfspr(SPRN_SDR1);
+			sprs.rpr	= mfspr(SPRN_RPR);
+
+			sprs.lpcr	= mfspr(SPRN_LPCR);
+			if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+				sprs.hfscr	= mfspr(SPRN_HFSCR);
+				sprs.fscr	= mfspr(SPRN_FSCR);
+			}
+			sprs.purr	= mfspr(SPRN_PURR);
+			sprs.spurr	= mfspr(SPRN_SPURR);
+			sprs.dscr	= mfspr(SPRN_DSCR);
+			sprs.wort	= mfspr(SPRN_WORT);
+
+			sprs_saved = true;
+
+			/*
+			 * Increment winkle counter and set all winkle bits if
+			 * all threads are winkling. This allows wakeup side to
+			 * distinguish between fast sleep and winkle state
+			 * loss. Fast sleep still has to resync the timebase so
+			 * this may not be a really big win.
+			 */
+			*state += 1 << PNV_CORE_IDLE_WINKLE_COUNT_SHIFT;
+			if ((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS)
+					>> PNV_CORE_IDLE_WINKLE_COUNT_SHIFT
+					== threads_per_core)
+				*state |= PNV_CORE_IDLE_THREAD_WINKLE_BITS;
+			WARN_ON((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) == 0);
+		}
+
+		atomic_unlock_thread_idle();
+	}
+
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		sprs.amr	= mfspr(SPRN_AMR);
+		sprs.iamr	= mfspr(SPRN_IAMR);
+		sprs.amor	= mfspr(SPRN_AMOR);
+		sprs.uamor	= mfspr(SPRN_UAMOR);
+	}
+
+	local_paca->thread_idle_state = type;
+	srr1 = isa206_idle_insn_mayloss(type);		/* go idle */
+	local_paca->thread_idle_state = PNV_THREAD_RUNNING;
+
+	WARN_ON_ONCE(!srr1);
+	WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR));
+
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		if ((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS) {
+			/*
+			 * We don't need an isync after the mtsprs here because
+			 * the upcoming mtmsrd is execution synchronizing.
+			 */
+			mtspr(SPRN_AMR,		sprs.amr);
+			mtspr(SPRN_IAMR,	sprs.iamr);
+			mtspr(SPRN_AMOR,	sprs.amor);
+			mtspr(SPRN_UAMOR,	sprs.uamor);
+		}
+	}
+
+	if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI))
+		hmi_exception_realmode(NULL);
+
+	if (likely((srr1 & SRR1_WAKESTATE) != SRR1_WS_HVLOSS)) {
+		if (unlikely(type != PNV_THREAD_NAP)) {
+			atomic_lock_thread_idle();
+			if (type == PNV_THREAD_WINKLE) {
+				WARN_ON((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) == 0);
+				*state -= 1 << PNV_CORE_IDLE_WINKLE_COUNT_SHIFT;
+				*state &= ~(thread << PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT);
+			}
+			atomic_unlock_and_stop_thread_idle();
+		}
+		return srr1;
+	}
+
+	/* HV state loss */
+	BUG_ON(type == PNV_THREAD_NAP);
+
+	atomic_lock_thread_idle();
+
+	full_winkle = false;
+	if (type == PNV_THREAD_WINKLE) {
+		WARN_ON((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) == 0);
+		*state -= 1 << PNV_CORE_IDLE_WINKLE_COUNT_SHIFT;
+		if (*state & (thread << PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT)) {
+			*state &= ~(thread << PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT);
+			full_winkle = true;
+			BUG_ON(!sprs_saved);
+		}
+	}
+
+	WARN_ON(*state & thread);
+
+	if ((*state & core_thread_mask) != 0)
+		goto core_woken;
+
+	/* Per-core SPRs */
+	if (full_winkle) {
+		mtspr(SPRN_TSCR,	sprs.tscr);
+		mtspr(SPRN_WORC,	sprs.worc);
+	}
+
+	if (power7_fastsleep_workaround_exit) {
+		rc = opal_config_cpu_idle_state(OPAL_CONFIG_IDLE_FASTSLEEP,
+						OPAL_CONFIG_IDLE_UNDO);
+		BUG_ON(rc);
+	}
+
+	/* TB */
+	if (opal_resync_timebase() != OPAL_SUCCESS)
+		BUG();
+
+core_woken:
+	if (!full_winkle)
+		goto subcore_woken;
+
+	if ((*state & local_paca->subcore_sibling_mask) != 0)
+		goto subcore_woken;
+
+	/* Per-subcore SPRs */
+	mtspr(SPRN_SDR1,	sprs.sdr1);
+	mtspr(SPRN_RPR,		sprs.rpr);
+
+subcore_woken:
+	/*
+	 * isync after restoring shared SPRs and before unlocking. Unlock
+	 * only contains hwsync which does not necessarily do the right
+	 * thing for SPRs.
+	 */
+	isync();
+	atomic_unlock_and_stop_thread_idle();
+
+	/* Fast sleep does not lose SPRs */
+	if (!full_winkle)
+		return srr1;
+
+	/* Per-thread SPRs */
+	mtspr(SPRN_LPCR,	sprs.lpcr);
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		mtspr(SPRN_HFSCR,	sprs.hfscr);
+		mtspr(SPRN_FSCR,	sprs.fscr);
+	}
+	mtspr(SPRN_PURR,	sprs.purr);
+	mtspr(SPRN_SPURR,	sprs.spurr);
+	mtspr(SPRN_DSCR,	sprs.dscr);
+	mtspr(SPRN_WORT,	sprs.wort);
+
+	mtspr(SPRN_SPRG3,	local_paca->sprg_vdso);
+
+	/*
+	 * The SLB has to be restored here, but it sometimes still
+	 * contains entries, so the __ variant must be used to prevent
+	 * multi hits.
+	 */
+	__slb_restore_bolted_realmode();
 
 	return srr1;
 }
 
+extern unsigned long idle_kvm_start_guest(unsigned long srr1);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static unsigned long power7_offline(void)
+{
+	unsigned long srr1;
+
+	mtmsr(MSR_IDLE);
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* Tell KVM we're entering idle. */
+	/******************************************************/
+	/*  N O T E   W E L L    ! ! !    N O T E   W E L L   */
+	/* The following store to HSTATE_HWTHREAD_STATE(r13)  */
+	/* MUST occur in real mode, i.e. with the MMU off,    */
+	/* and the MMU must stay off until we clear this flag */
+	/* and test HSTATE_HWTHREAD_REQ(r13) in               */
+	/* pnv_powersave_wakeup in this file.                 */
+	/* The reason is that another thread can switch the   */
+	/* MMU to a guest context whenever this flag is set   */
+	/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on,    */
+	/* that would potentially cause this thread to start  */
+	/* executing instructions from guest memory in        */
+	/* hypervisor mode, leading to a host crash or data   */
+	/* corruption, or worse.                              */
+	/******************************************************/
+	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE;
+#endif
+
+	__ppc64_runlatch_off();
+	srr1 = power7_idle_insn(power7_offline_type);
+	__ppc64_runlatch_on();
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL;
+	/* Order setting hwthread_state vs. testing hwthread_req */
+	smp_mb();
+	if (local_paca->kvm_hstate.hwthread_req)
+		srr1 = idle_kvm_start_guest(srr1);
+#endif
+
+	mtmsr(MSR_KERNEL);
+
+	return srr1;
+}
+#endif
+
 void power7_idle_type(unsigned long type)
 {
 	unsigned long srr1;
 
-	srr1 = __power7_idle_type(type);
+	if (!prep_irq_for_idle_irqsoff())
+		return;
+
+	mtmsr(MSR_IDLE);
+	__ppc64_runlatch_off();
+	srr1 = power7_idle_insn(type);
+	__ppc64_runlatch_on();
+	mtmsr(MSR_KERNEL);
+
+	fini_irq_for_idle_irqsoff();
 	irq_set_pending_from_srr1(srr1);
 }
 
@@ -347,33 +573,294 @@
 	power7_idle_type(PNV_THREAD_NAP);
 }
 
-static unsigned long __power9_idle_type(unsigned long stop_psscr_val,
+struct p9_sprs {
+	/* per core */
+	u64 ptcr;
+	u64 rpr;
+	u64 tscr;
+	u64 ldbar;
+
+	/* per thread */
+	u64 lpcr;
+	u64 hfscr;
+	u64 fscr;
+	u64 pid;
+	u64 purr;
+	u64 spurr;
+	u64 dscr;
+	u64 wort;
+
+	u64 mmcra;
+	u32 mmcr0;
+	u32 mmcr1;
+	u64 mmcr2;
+
+	/* per thread SPRs that get lost in shallow states */
+	u64 amr;
+	u64 iamr;
+	u64 amor;
+	u64 uamor;
+};
+
+static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
+{
+	int cpu = raw_smp_processor_id();
+	int first = cpu_first_thread_sibling(cpu);
+	unsigned long *state = &paca_ptrs[first]->idle_state;
+	unsigned long core_thread_mask = (1UL << threads_per_core) - 1;
+	unsigned long srr1;
+	unsigned long pls;
+	unsigned long mmcr0 = 0;
+	struct p9_sprs sprs = {}; /* avoid false used-uninitialised */
+	bool sprs_saved = false;
+
+	if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
+		/* EC=ESL=0 case */
+
+		BUG_ON(!mmu_on);
+
+		/*
+		 * Wake synchronously. SRESET via xscom may still cause
+		 * a 0x100 powersave wakeup with SRR1 reason!
+		 */
+		srr1 = isa300_idle_stop_noloss(psscr);		/* go idle */
+		if (likely(!srr1))
+			return 0;
+
+		/*
+		 * Registers not saved, can't recover!
+		 * This would be a hardware bug
+		 */
+		BUG_ON((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS);
+
+		goto out;
+	}
+
+	/* EC=ESL=1 case */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	if (cpu_has_feature(CPU_FTR_P9_TM_XER_SO_BUG)) {
+		local_paca->requested_psscr = psscr;
+		/* order setting requested_psscr vs testing dont_stop */
+		smp_mb();
+		if (atomic_read(&local_paca->dont_stop)) {
+			local_paca->requested_psscr = 0;
+			return 0;
+		}
+	}
+#endif
+
+	if (!cpu_has_feature(CPU_FTR_POWER9_DD2_1)) {
+		 /*
+		  * POWER9 DD2 can incorrectly set PMAO when waking up
+		  * after a state-loss idle. Saving and restoring MMCR0
+		  * over idle is a workaround.
+		  */
+		mmcr0		= mfspr(SPRN_MMCR0);
+	}
+	if ((psscr & PSSCR_RL_MASK) >= pnv_first_spr_loss_level) {
+		sprs.lpcr	= mfspr(SPRN_LPCR);
+		sprs.hfscr	= mfspr(SPRN_HFSCR);
+		sprs.fscr	= mfspr(SPRN_FSCR);
+		sprs.pid	= mfspr(SPRN_PID);
+		sprs.purr	= mfspr(SPRN_PURR);
+		sprs.spurr	= mfspr(SPRN_SPURR);
+		sprs.dscr	= mfspr(SPRN_DSCR);
+		sprs.wort	= mfspr(SPRN_WORT);
+
+		sprs.mmcra	= mfspr(SPRN_MMCRA);
+		sprs.mmcr0	= mfspr(SPRN_MMCR0);
+		sprs.mmcr1	= mfspr(SPRN_MMCR1);
+		sprs.mmcr2	= mfspr(SPRN_MMCR2);
+
+		sprs.ptcr	= mfspr(SPRN_PTCR);
+		sprs.rpr	= mfspr(SPRN_RPR);
+		sprs.tscr	= mfspr(SPRN_TSCR);
+		if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
+			sprs.ldbar = mfspr(SPRN_LDBAR);
+
+		sprs_saved = true;
+
+		atomic_start_thread_idle();
+	}
+
+	sprs.amr	= mfspr(SPRN_AMR);
+	sprs.iamr	= mfspr(SPRN_IAMR);
+	sprs.amor	= mfspr(SPRN_AMOR);
+	sprs.uamor	= mfspr(SPRN_UAMOR);
+
+	srr1 = isa300_idle_stop_mayloss(psscr);		/* go idle */
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	local_paca->requested_psscr = 0;
+#endif
+
+	psscr = mfspr(SPRN_PSSCR);
+
+	WARN_ON_ONCE(!srr1);
+	WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR));
+
+	if ((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS) {
+		unsigned long mmcra;
+
+		/*
+		 * We don't need an isync after the mtsprs here because the
+		 * upcoming mtmsrd is execution synchronizing.
+		 */
+		mtspr(SPRN_AMR,		sprs.amr);
+		mtspr(SPRN_IAMR,	sprs.iamr);
+		mtspr(SPRN_AMOR,	sprs.amor);
+		mtspr(SPRN_UAMOR,	sprs.uamor);
+
+		/*
+		 * Workaround for POWER9 DD2.0, if we lost resources, the ERAT
+		 * might have been corrupted and needs flushing. We also need
+		 * to reload MMCR0 (see mmcr0 comment above).
+		 */
+		if (!cpu_has_feature(CPU_FTR_POWER9_DD2_1)) {
+			asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT);
+			mtspr(SPRN_MMCR0, mmcr0);
+		}
+
+		/*
+		 * DD2.2 and earlier need to set then clear bit 60 in MMCRA
+		 * to ensure the PMU starts running.
+		 */
+		mmcra = mfspr(SPRN_MMCRA);
+		mmcra |= PPC_BIT(60);
+		mtspr(SPRN_MMCRA, mmcra);
+		mmcra &= ~PPC_BIT(60);
+		mtspr(SPRN_MMCRA, mmcra);
+	}
+
+	if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI))
+		hmi_exception_realmode(NULL);
+
+	/*
+	 * On POWER9, SRR1 bits do not match exactly as expected.
+	 * SRR1_WS_GPRLOSS (10b) can also result in SPR loss, so
+	 * just always test PSSCR for SPR/TB state loss.
+	 */
+	pls = (psscr & PSSCR_PLS) >> PSSCR_PLS_SHIFT;
+	if (likely(pls < pnv_first_spr_loss_level)) {
+		if (sprs_saved)
+			atomic_stop_thread_idle();
+		goto out;
+	}
+
+	/* HV state loss */
+	BUG_ON(!sprs_saved);
+
+	atomic_lock_thread_idle();
+
+	if ((*state & core_thread_mask) != 0)
+		goto core_woken;
+
+	/* Per-core SPRs */
+	mtspr(SPRN_PTCR,	sprs.ptcr);
+	mtspr(SPRN_RPR,		sprs.rpr);
+	mtspr(SPRN_TSCR,	sprs.tscr);
+
+	if (pls >= pnv_first_tb_loss_level) {
+		/* TB loss */
+		if (opal_resync_timebase() != OPAL_SUCCESS)
+			BUG();
+	}
+
+	/*
+	 * isync after restoring shared SPRs and before unlocking. Unlock
+	 * only contains hwsync which does not necessarily do the right
+	 * thing for SPRs.
+	 */
+	isync();
+
+core_woken:
+	atomic_unlock_and_stop_thread_idle();
+
+	/* Per-thread SPRs */
+	mtspr(SPRN_LPCR,	sprs.lpcr);
+	mtspr(SPRN_HFSCR,	sprs.hfscr);
+	mtspr(SPRN_FSCR,	sprs.fscr);
+	mtspr(SPRN_PID,		sprs.pid);
+	mtspr(SPRN_PURR,	sprs.purr);
+	mtspr(SPRN_SPURR,	sprs.spurr);
+	mtspr(SPRN_DSCR,	sprs.dscr);
+	mtspr(SPRN_WORT,	sprs.wort);
+
+	mtspr(SPRN_MMCRA,	sprs.mmcra);
+	mtspr(SPRN_MMCR0,	sprs.mmcr0);
+	mtspr(SPRN_MMCR1,	sprs.mmcr1);
+	mtspr(SPRN_MMCR2,	sprs.mmcr2);
+	if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
+		mtspr(SPRN_LDBAR, sprs.ldbar);
+
+	mtspr(SPRN_SPRG3,	local_paca->sprg_vdso);
+
+	if (!radix_enabled())
+		__slb_restore_bolted_realmode();
+
+out:
+	if (mmu_on)
+		mtmsr(MSR_KERNEL);
+
+	return srr1;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static unsigned long power9_offline_stop(unsigned long psscr)
+{
+	unsigned long srr1;
+
+#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	__ppc64_runlatch_off();
+	srr1 = power9_idle_stop(psscr, true);
+	__ppc64_runlatch_on();
+#else
+	/*
+	 * Tell KVM we're entering idle.
+	 * This does not have to be done in real mode because the P9 MMU
+	 * is independent per-thread. Some steppings share radix/hash mode
+	 * between threads, but in that case KVM has a barrier sync in real
+	 * mode before and after switching between radix and hash.
+	 *
+	 * kvm_start_guest must still be called in real mode though, hence
+	 * the false argument.
+	 */
+	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE;
+
+	__ppc64_runlatch_off();
+	srr1 = power9_idle_stop(psscr, false);
+	__ppc64_runlatch_on();
+
+	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL;
+	/* Order setting hwthread_state vs. testing hwthread_req */
+	smp_mb();
+	if (local_paca->kvm_hstate.hwthread_req)
+		srr1 = idle_kvm_start_guest(srr1);
+	mtmsr(MSR_KERNEL);
+#endif
+
+	return srr1;
+}
+#endif
+
+void power9_idle_type(unsigned long stop_psscr_val,
 				      unsigned long stop_psscr_mask)
 {
 	unsigned long psscr;
 	unsigned long srr1;
 
 	if (!prep_irq_for_idle_irqsoff())
-		return 0;
+		return;
 
 	psscr = mfspr(SPRN_PSSCR);
 	psscr = (psscr & ~stop_psscr_mask) | stop_psscr_val;
 
 	__ppc64_runlatch_off();
-	srr1 = power9_idle_stop(psscr);
+	srr1 = power9_idle_stop(psscr, true);
 	__ppc64_runlatch_on();
 
 	fini_irq_for_idle_irqsoff();
 
-	return srr1;
-}
-
-void power9_idle_type(unsigned long stop_psscr_val,
-				      unsigned long stop_psscr_mask)
-{
-	unsigned long srr1;
-
-	srr1 = __power9_idle_type(stop_psscr_val, stop_psscr_mask);
 	irq_set_pending_from_srr1(srr1);
 }
 
@@ -409,7 +896,7 @@
 			atomic_inc(&paca_ptrs[cpu0+thr]->dont_stop);
 	}
 	/* order setting dont_stop vs testing requested_psscr */
-	mb();
+	smp_mb();
 	for (thr = 0; thr < threads_per_core; ++thr) {
 		if (!paca_ptrs[cpu0+thr]->requested_psscr)
 			++awake_threads;
@@ -458,7 +945,8 @@
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
+
+void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
 {
 	u64 pir = get_hard_smp_processor_id(cpu);
 
@@ -480,21 +968,6 @@
 unsigned long pnv_cpu_offline(unsigned int cpu)
 {
 	unsigned long srr1;
-	u32 idle_states = pnv_get_supported_cpuidle_states();
-	u64 lpcr_val;
-
-	/*
-	 * We don't want to take decrementer interrupts while we are
-	 * offline, so clear LPCR:PECE1. We keep PECE2 (and
-	 * LPCR_PECE_HVEE on P9) enabled as to let IPIs in.
-	 *
-	 * If the CPU gets woken up by a special wakeup, ensure that
-	 * the SLW engine sets LPCR with decrementer bit cleared, else
-	 * the CPU will come back to the kernel due to a spurious
-	 * wakeup.
-	 */
-	lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
-	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
 
 	__ppc64_runlatch_off();
 
@@ -505,15 +978,8 @@
 		psscr = (psscr & ~pnv_deepest_stop_psscr_mask) |
 						pnv_deepest_stop_psscr_val;
 		srr1 = power9_offline_stop(psscr);
-
-	} else if ((idle_states & OPAL_PM_WINKLE_ENABLED) &&
-		   (idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) {
-		srr1 = power7_idle_insn(PNV_THREAD_WINKLE);
-	} else if ((idle_states & OPAL_PM_SLEEP_ENABLED) ||
-		   (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
-		srr1 = power7_idle_insn(PNV_THREAD_SLEEP);
-	} else if (idle_states & OPAL_PM_NAP_ENABLED) {
-		srr1 = power7_idle_insn(PNV_THREAD_NAP);
+	} else if (cpu_has_feature(CPU_FTR_ARCH_206) && power7_offline_type) {
+		srr1 = power7_offline();
 	} else {
 		/* This is the fallback method. We emulate snooze */
 		while (!generic_check_cpu_restart(cpu)) {
@@ -526,16 +992,6 @@
 
 	__ppc64_runlatch_on();
 
-	/*
-	 * Re-enable decrementer interrupts in LPCR.
-	 *
-	 * Further, we want stop states to be woken up by decrementer
-	 * for non-hotplug cases. So program the LPCR via stop api as
-	 * well.
-	 */
-	lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
-	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
-
 	return srr1;
 }
 #endif
@@ -619,33 +1075,44 @@
  * @dt_idle_states: Number of idle state entries
  * Returns 0 on success
  */
-static int __init pnv_power9_idle_init(void)
+static void __init pnv_power9_idle_init(void)
 {
 	u64 max_residency_ns = 0;
 	int i;
 
 	/*
-	 * Set pnv_first_deep_stop_state, pnv_deepest_stop_psscr_{val,mask},
-	 * and the pnv_default_stop_{val,mask}.
-	 *
-	 * pnv_first_deep_stop_state should be set to the first stop
-	 * level to cause hypervisor state loss.
-	 *
 	 * pnv_deepest_stop_{val,mask} should be set to values corresponding to
 	 * the deepest stop state.
 	 *
 	 * pnv_default_stop_{val,mask} should be set to values corresponding to
-	 * the shallowest (OPAL_PM_STOP_INST_FAST) loss-less stop state.
+	 * the deepest loss-less (OPAL_PM_STOP_INST_FAST) stop state.
 	 */
-	pnv_first_deep_stop_state = MAX_STOP_STATE;
+	pnv_first_tb_loss_level = MAX_STOP_STATE + 1;
+	pnv_first_spr_loss_level = MAX_STOP_STATE + 1;
 	for (i = 0; i < nr_pnv_idle_states; i++) {
 		int err;
 		struct pnv_idle_states_t *state = &pnv_idle_states[i];
 		u64 psscr_rl = state->psscr_val & PSSCR_RL_MASK;
 
+		if ((state->flags & OPAL_PM_TIMEBASE_STOP) &&
+		     (pnv_first_tb_loss_level > psscr_rl))
+			pnv_first_tb_loss_level = psscr_rl;
+
 		if ((state->flags & OPAL_PM_LOSE_FULL_CONTEXT) &&
-		    pnv_first_deep_stop_state > psscr_rl)
-			pnv_first_deep_stop_state = psscr_rl;
+		     (pnv_first_spr_loss_level > psscr_rl))
+			pnv_first_spr_loss_level = psscr_rl;
+
+		/*
+		 * The idle code does not deal with TB loss occurring
+		 * in a shallower state than SPR loss, so force it to
+		 * behave like SPRs are lost if TB is lost. POWER9 would
+		 * never encouter this, but a POWER8 core would if it
+		 * implemented the stop instruction. So this is for forward
+		 * compatibility.
+		 */
+		if ((state->flags & OPAL_PM_TIMEBASE_STOP) &&
+		     (pnv_first_spr_loss_level > psscr_rl))
+			pnv_first_spr_loss_level = psscr_rl;
 
 		err = validate_psscr_val_mask(&state->psscr_val,
 					      &state->psscr_mask,
@@ -670,6 +1137,7 @@
 			pnv_default_stop_val = state->psscr_val;
 			pnv_default_stop_mask = state->psscr_mask;
 			default_stop_found = true;
+			WARN_ON(state->flags & OPAL_PM_LOSE_FULL_CONTEXT);
 		}
 	}
 
@@ -689,10 +1157,40 @@
 			pnv_deepest_stop_psscr_mask);
 	}
 
-	pr_info("cpuidle-powernv: Requested Level (RL) value of first deep stop = 0x%llx\n",
-		pnv_first_deep_stop_state);
+	pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%llx\n",
+		pnv_first_spr_loss_level);
 
-	return 0;
+	pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%llx\n",
+		pnv_first_tb_loss_level);
+}
+
+static void __init pnv_disable_deep_states(void)
+{
+	/*
+	 * The stop-api is unable to restore hypervisor
+	 * resources on wakeup from platform idle states which
+	 * lose full context. So disable such states.
+	 */
+	supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT;
+	pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n");
+	pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");
+
+	if (cpu_has_feature(CPU_FTR_ARCH_300) &&
+	    (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
+		/*
+		 * Use the default stop state for CPU-Hotplug
+		 * if available.
+		 */
+		if (default_stop_found) {
+			pnv_deepest_stop_psscr_val = pnv_default_stop_val;
+			pnv_deepest_stop_psscr_mask = pnv_default_stop_mask;
+			pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
+				pnv_deepest_stop_psscr_val);
+		} else { /* Fallback to snooze loop for CPU-Hotplug */
+			deepest_stop_found = false;
+			pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
+		}
+	}
 }
 
 /*
@@ -707,10 +1205,8 @@
 		return;
 	}
 
-	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
-		if (pnv_power9_idle_init())
-			return;
-	}
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		pnv_power9_idle_init();
 
 	for (i = 0; i < nr_pnv_idle_states; i++)
 		supported_cpuidle_states |= pnv_idle_states[i].flags;
@@ -830,11 +1326,33 @@
 
 static int __init pnv_init_idle_states(void)
 {
+	int cpu;
 	int rc = 0;
-	supported_cpuidle_states = 0;
+
+	/* Set up PACA fields */
+	for_each_present_cpu(cpu) {
+		struct paca_struct *p = paca_ptrs[cpu];
+
+		p->idle_state = 0;
+		if (cpu == cpu_first_thread_sibling(cpu))
+			p->idle_state = (1 << threads_per_core) - 1;
+
+		if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+			/* P7/P8 nap */
+			p->thread_idle_state = PNV_THREAD_RUNNING;
+		} else {
+			/* P9 stop */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+			p->requested_psscr = 0;
+			atomic_set(&p->dont_stop, 0);
+#endif
+		}
+	}
 
 	/* In case we error out nr_pnv_idle_states will be zero */
 	nr_pnv_idle_states = 0;
+	supported_cpuidle_states = 0;
+
 	if (cpuidle_disable != IDLE_NO_OVERRIDE)
 		goto out;
 	rc = pnv_parse_cpuidle_dt();
@@ -842,27 +1360,40 @@
 		return rc;
 	pnv_probe_idle_states();
 
-	if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
-		patch_instruction(
-			(unsigned int *)pnv_fastsleep_workaround_at_entry,
-			PPC_INST_NOP);
-		patch_instruction(
-			(unsigned int *)pnv_fastsleep_workaround_at_exit,
-			PPC_INST_NOP);
-	} else {
-		/*
-		 * OPAL_PM_SLEEP_ENABLED_ER1 is set. It indicates that
-		 * workaround is needed to use fastsleep. Provide sysfs
-		 * control to choose how this workaround has to be applied.
-		 */
-		device_create_file(cpu_subsys.dev_root,
+	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
+			power7_fastsleep_workaround_entry = false;
+			power7_fastsleep_workaround_exit = false;
+		} else {
+			/*
+			 * OPAL_PM_SLEEP_ENABLED_ER1 is set. It indicates that
+			 * workaround is needed to use fastsleep. Provide sysfs
+			 * control to choose how this workaround has to be
+			 * applied.
+			 */
+			device_create_file(cpu_subsys.dev_root,
 				&dev_attr_fastsleep_workaround_applyonce);
+		}
+
+		update_subcore_sibling_mask();
+
+		if (supported_cpuidle_states & OPAL_PM_NAP_ENABLED) {
+			ppc_md.power_save = power7_idle;
+			power7_offline_type = PNV_THREAD_NAP;
+		}
+
+		if ((supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED) &&
+			   (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT))
+			power7_offline_type = PNV_THREAD_WINKLE;
+		else if ((supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED) ||
+			   (supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1))
+			power7_offline_type = PNV_THREAD_SLEEP;
 	}
 
-	pnv_alloc_idle_core_states();
-
-	if (supported_cpuidle_states & OPAL_PM_NAP_ENABLED)
-		ppc_md.power_save = power7_idle;
+	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) {
+		if (pnv_save_sprs_for_deep_states())
+			pnv_disable_deep_states();
+	}
 
 out:
 	return 0;
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index a29fdf8..eb2e75d 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) IBM Corporation, 2014, 2017
  * Anton Blanchard, Rashmica Gupta.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "memtrace: " fmt
@@ -20,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
+#include <linux/numa.h>
 #include <asm/machdep.h>
 #include <asm/debugfs.h>
 
@@ -70,25 +67,26 @@
 	return 0;
 }
 
+/* called with device_hotplug_lock held */
 static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
 {
-	u64 end_pfn = start_pfn + nr_pages - 1;
+	const unsigned long start = PFN_PHYS(start_pfn);
+	const unsigned long size = PFN_PHYS(nr_pages);
 
-	if (walk_memory_range(start_pfn, end_pfn, NULL,
-	    check_memblock_online))
+	if (walk_memory_blocks(start, size, NULL, check_memblock_online))
 		return false;
 
-	walk_memory_range(start_pfn, end_pfn, (void *)MEM_GOING_OFFLINE,
-			  change_memblock_state);
+	walk_memory_blocks(start, size, (void *)MEM_GOING_OFFLINE,
+			   change_memblock_state);
 
 	if (offline_pages(start_pfn, nr_pages)) {
-		walk_memory_range(start_pfn, end_pfn, (void *)MEM_ONLINE,
-				  change_memblock_state);
+		walk_memory_blocks(start, size, (void *)MEM_ONLINE,
+				   change_memblock_state);
 		return false;
 	}
 
-	walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
-			  change_memblock_state);
+	walk_memory_blocks(start, size, (void *)MEM_OFFLINE,
+			   change_memblock_state);
 
 
 	return true;
@@ -110,6 +108,7 @@
 	/* Trace memory needs to be aligned to the size */
 	end_pfn = round_down(end_pfn - nr_pages, nr_pages);
 
+	lock_device_hotplug();
 	for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) {
 		if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true) {
 			/*
@@ -118,15 +117,15 @@
 			 * we never try to remove memory that spans two iomem
 			 * resources.
 			 */
-			lock_device_hotplug();
 			end_pfn = base_pfn + nr_pages;
 			for (pfn = base_pfn; pfn < end_pfn; pfn += bytes>> PAGE_SHIFT) {
-				remove_memory(nid, pfn << PAGE_SHIFT, bytes);
+				__remove_memory(nid, pfn << PAGE_SHIFT, bytes);
 			}
 			unlock_device_hotplug();
 			return base_pfn << PAGE_SHIFT;
 		}
 	}
+	unlock_device_hotplug();
 
 	return 0;
 }
@@ -221,7 +220,7 @@
 		ent = &memtrace_array[i];
 
 		/* We have onlined this chunk previously */
-		if (ent->nid == -1)
+		if (ent->nid == NUMA_NO_NODE)
 			continue;
 
 		/* Remove from io mappings */
@@ -242,9 +241,10 @@
 		 * we need to online the memory ourselves.
 		 */
 		if (!memhp_auto_online) {
-			walk_memory_range(PFN_DOWN(ent->start),
-					  PFN_UP(ent->start + ent->size - 1),
-					  NULL, online_mem_block);
+			lock_device_hotplug();
+			walk_memory_blocks(ent->start, ent->size, NULL,
+					   online_mem_block);
+			unlock_device_hotplug();
 		}
 
 		/*
@@ -253,7 +253,7 @@
 		 */
 		debugfs_remove_recursive(ent->dir);
 		pr_info("Added trace memory back to node %d\n", ent->nid);
-		ent->size = ent->start = ent->nid = -1;
+		ent->size = ent->start = ent->nid = NUMA_NO_NODE;
 	}
 	if (ret)
 		return ret;
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 8006c54..b95b9e3 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -1,64 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * This file implements the DMA operations for NVLink devices. The NPU
  * devices all point to the same iommu table as the parent PCI device.
  *
  * Copyright Alistair Popple, IBM Corporation 2015.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
  */
 
-#include <linux/slab.h>
 #include <linux/mmu_notifier.h>
 #include <linux/mmu_context.h>
 #include <linux/of.h>
-#include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/memblock.h>
-#include <linux/iommu.h>
-#include <linux/debugfs.h>
+#include <linux/sizes.h>
 
 #include <asm/debugfs.h>
-#include <asm/tlb.h>
 #include <asm/powernv.h>
-#include <asm/reg.h>
-#include <asm/opal.h>
-#include <asm/io.h>
-#include <asm/iommu.h>
-#include <asm/pnv-pci.h>
-#include <asm/msi_bitmap.h>
 #include <asm/opal.h>
 
-#include "powernv.h"
 #include "pci.h"
 
-#define npu_to_phb(x) container_of(x, struct pnv_phb, npu)
-
-/*
- * spinlock to protect initialisation of an npu_context for a particular
- * mm_struct.
- */
-static DEFINE_SPINLOCK(npu_context_lock);
-
-/*
- * When an address shootdown range exceeds this threshold we invalidate the
- * entire TLB on the GPU for the given PID rather than each specific address in
- * the range.
- */
-static uint64_t atsd_threshold = 2 * 1024 * 1024;
-static struct dentry *atsd_threshold_dentry;
-
-/*
- * Other types of TCE cache invalidation are not functional in the
- * hardware.
- */
 static struct pci_dev *get_pci_dev(struct device_node *dn)
 {
 	struct pci_dn *pdn = PCI_DN(dn);
+	struct pci_dev *pdev;
 
-	return pci_get_domain_bus_and_slot(pci_domain_nr(pdn->phb->bus),
+	pdev = pci_get_domain_bus_and_slot(pci_domain_nr(pdn->phb->bus),
 					   pdn->busno, pdn->devfn);
+
+	/*
+	 * pci_get_domain_bus_and_slot() increased the reference count of
+	 * the PCI device, but callers don't need that actually as the PE
+	 * already holds a reference to the device. Since callers aren't
+	 * aware of the reference count change, call pci_dev_put() now to
+	 * avoid leaks.
+	 */
+	if (pdev)
+		pci_dev_put(pdev);
+
+	return pdev;
 }
 
 /* Given a NPU device get the associated PCI device. */
@@ -110,63 +89,7 @@
 }
 EXPORT_SYMBOL(pnv_pci_get_npu_dev);
 
-#define NPU_DMA_OP_UNSUPPORTED()					\
-	dev_err_once(dev, "%s operation unsupported for NVLink devices\n", \
-		__func__)
-
-static void *dma_npu_alloc(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag,
-			   unsigned long attrs)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return NULL;
-}
-
-static void dma_npu_free(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle,
-			 unsigned long attrs)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-}
-
-static dma_addr_t dma_npu_map_page(struct device *dev, struct page *page,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction direction,
-				   unsigned long attrs)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return 0;
-}
-
-static int dma_npu_map_sg(struct device *dev, struct scatterlist *sglist,
-			  int nelems, enum dma_data_direction direction,
-			  unsigned long attrs)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return 0;
-}
-
-static int dma_npu_dma_supported(struct device *dev, u64 mask)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return 0;
-}
-
-static u64 dma_npu_get_required_mask(struct device *dev)
-{
-	NPU_DMA_OP_UNSUPPORTED();
-	return 0;
-}
-
-static const struct dma_map_ops dma_npu_ops = {
-	.map_page		= dma_npu_map_page,
-	.map_sg			= dma_npu_map_sg,
-	.alloc			= dma_npu_alloc,
-	.free			= dma_npu_free,
-	.dma_supported		= dma_npu_dma_supported,
-	.get_required_mask	= dma_npu_get_required_mask,
-};
-
+#ifdef CONFIG_IOMMU_API
 /*
  * Returns the PE assoicated with the PCI device of the given
  * NPU. Returns the linked pci device if pci_dev != NULL.
@@ -198,15 +121,25 @@
 	return pe;
 }
 
-long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
+static long pnv_npu_unset_window(struct iommu_table_group *table_group,
+		int num);
+
+static long pnv_npu_set_window(struct iommu_table_group *table_group, int num,
 		struct iommu_table *tbl)
 {
+	struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe,
+			table_group);
 	struct pnv_phb *phb = npe->phb;
 	int64_t rc;
 	const unsigned long size = tbl->it_indirect_levels ?
 		tbl->it_level_size : tbl->it_size;
 	const __u64 start_addr = tbl->it_offset << tbl->it_page_shift;
 	const __u64 win_size = tbl->it_size << tbl->it_page_shift;
+	int num2 = (num == 0) ? 1 : 0;
+
+	/* NPU has just one TVE so if there is another table, remove it first */
+	if (npe->table_group.tables[num2])
+		pnv_npu_unset_window(&npe->table_group, num2);
 
 	pe_info(npe, "Setting up window %llx..%llx pg=%lx\n",
 			start_addr, start_addr + win_size - 1,
@@ -232,11 +165,16 @@
 	return 0;
 }
 
-long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num)
+static long pnv_npu_unset_window(struct iommu_table_group *table_group, int num)
 {
+	struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe,
+			table_group);
 	struct pnv_phb *phb = npe->phb;
 	int64_t rc;
 
+	if (!npe->table_group.tables[num])
+		return 0;
+
 	pe_info(npe, "Removing DMA window\n");
 
 	rc = opal_pci_map_pe_dma_window(phb->opal_id, npe->pe_number,
@@ -255,108 +193,14 @@
 	return 0;
 }
 
-/*
- * Enables 32 bit DMA on NPU.
- */
-static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe)
-{
-	struct pci_dev *gpdev;
-	struct pnv_ioda_pe *gpe;
-	int64_t rc;
-
-	/*
-	 * Find the assoicated PCI devices and get the dma window
-	 * information from there.
-	 */
-	if (!npe->pdev || !(npe->flags & PNV_IODA_PE_DEV))
-		return;
-
-	gpe = get_gpu_pci_dev_and_pe(npe, &gpdev);
-	if (!gpe)
-		return;
-
-	rc = pnv_npu_set_window(npe, 0, gpe->table_group.tables[0]);
-
-	/*
-	 * We don't initialise npu_pe->tce32_table as we always use
-	 * dma_npu_ops which are nops.
-	 */
-	set_dma_ops(&npe->pdev->dev, &dma_npu_ops);
-}
-
-/*
- * Enables bypass mode on the NPU. The NPU only supports one
- * window per link, so bypass needs to be explicitly enabled or
- * disabled. Unlike for a PHB3 bypass and non-bypass modes can't be
- * active at the same time.
- */
-static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe)
-{
-	struct pnv_phb *phb = npe->phb;
-	int64_t rc = 0;
-	phys_addr_t top = memblock_end_of_DRAM();
-
-	if (phb->type != PNV_PHB_NPU_NVLINK || !npe->pdev)
-		return -EINVAL;
-
-	rc = pnv_npu_unset_window(npe, 0);
-	if (rc != OPAL_SUCCESS)
-		return rc;
-
-	/* Enable the bypass window */
-
-	top = roundup_pow_of_two(top);
-	dev_info(&npe->pdev->dev, "Enabling bypass for PE %x\n",
-			npe->pe_number);
-	rc = opal_pci_map_pe_dma_window_real(phb->opal_id,
-			npe->pe_number, npe->pe_number,
-			0 /* bypass base */, top);
-
-	if (rc == OPAL_SUCCESS)
-		pnv_pci_ioda2_tce_invalidate_entire(phb, false);
-
-	return rc;
-}
-
-void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass)
-{
-	int i;
-	struct pnv_phb *phb;
-	struct pci_dn *pdn;
-	struct pnv_ioda_pe *npe;
-	struct pci_dev *npdev;
-
-	for (i = 0; ; ++i) {
-		npdev = pnv_pci_get_npu_dev(gpdev, i);
-
-		if (!npdev)
-			break;
-
-		pdn = pci_get_pdn(npdev);
-		if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
-			return;
-
-		phb = pci_bus_to_host(npdev->bus)->private_data;
-
-		/* We only do bypass if it's enabled on the linked device */
-		npe = &phb->ioda.pe_array[pdn->pe_number];
-
-		if (bypass) {
-			dev_info(&npdev->dev,
-					"Using 64-bit DMA iommu bypass\n");
-			pnv_npu_dma_set_bypass(npe);
-		} else {
-			dev_info(&npdev->dev, "Using 32-bit DMA via iommu\n");
-			pnv_npu_dma_set_32(npe);
-		}
-	}
-}
-
 /* Switch ownership from platform code to external user (e.g. VFIO) */
-void pnv_npu_take_ownership(struct pnv_ioda_pe *npe)
+static void pnv_npu_take_ownership(struct iommu_table_group *table_group)
 {
+	struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe,
+			table_group);
 	struct pnv_phb *phb = npe->phb;
 	int64_t rc;
+	struct pci_dev *gpdev = NULL;
 
 	/*
 	 * Note: NPU has just a single TVE in the hardware which means that
@@ -365,7 +209,7 @@
 	 * if it was enabled at the moment of ownership change.
 	 */
 	if (npe->table_group.tables[0]) {
-		pnv_npu_unset_window(npe, 0);
+		pnv_npu_unset_window(&npe->table_group, 0);
 		return;
 	}
 
@@ -378,622 +222,409 @@
 		return;
 	}
 	pnv_pci_ioda2_tce_invalidate_entire(npe->phb, false);
+
+	get_gpu_pci_dev_and_pe(npe, &gpdev);
+	if (gpdev)
+		pnv_npu2_unmap_lpar_dev(gpdev);
 }
 
-struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe)
+static void pnv_npu_release_ownership(struct iommu_table_group *table_group)
 {
-	struct pnv_phb *phb = npe->phb;
-	struct pci_bus *pbus = phb->hose->bus;
-	struct pci_dev *npdev, *gpdev = NULL, *gptmp;
-	struct pnv_ioda_pe *gpe = get_gpu_pci_dev_and_pe(npe, &gpdev);
+	struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe,
+			table_group);
+	struct pci_dev *gpdev = NULL;
 
-	if (!gpe || !gpdev)
-		return NULL;
-
-	list_for_each_entry(npdev, &pbus->devices, bus_list) {
-		gptmp = pnv_pci_get_gpu_dev(npdev);
-
-		if (gptmp != gpdev)
-			continue;
-
-		pe_info(gpe, "Attached NPU %s\n", dev_name(&npdev->dev));
-		iommu_group_add_device(gpe->table_group.group, &npdev->dev);
-	}
-
-	return gpe;
+	get_gpu_pci_dev_and_pe(npe, &gpdev);
+	if (gpdev)
+		pnv_npu2_map_lpar_dev(gpdev, 0, MSR_DR | MSR_PR | MSR_HV);
 }
 
-/* Maximum number of nvlinks per npu */
-#define NV_MAX_LINKS 6
-
-/* Maximum index of npu2 hosts in the system. Always < NV_MAX_NPUS */
-static int max_npu2_index;
-
-struct npu_context {
-	struct mm_struct *mm;
-	struct pci_dev *npdev[NV_MAX_NPUS][NV_MAX_LINKS];
-	struct mmu_notifier mn;
-	struct kref kref;
-	bool nmmu_flush;
-
-	/* Callback to stop translation requests on a given GPU */
-	void (*release_cb)(struct npu_context *context, void *priv);
-
-	/*
-	 * Private pointer passed to the above callback for usage by
-	 * device drivers.
-	 */
-	void *priv;
+static struct iommu_table_group_ops pnv_pci_npu_ops = {
+	.set_window = pnv_npu_set_window,
+	.unset_window = pnv_npu_unset_window,
+	.take_ownership = pnv_npu_take_ownership,
+	.release_ownership = pnv_npu_release_ownership,
 };
-
-struct mmio_atsd_reg {
-	struct npu *npu;
-	int reg;
-};
+#endif /* !CONFIG_IOMMU_API */
 
 /*
- * Find a free MMIO ATSD register and mark it in use. Return -ENOSPC
- * if none are available.
+ * NPU2 ATS
  */
-static int get_mmio_atsd_reg(struct npu *npu)
-{
-	int i;
-
-	for (i = 0; i < npu->mmio_atsd_count; i++) {
-		if (!test_bit(i, &npu->mmio_atsd_usage))
-			if (!test_and_set_bit_lock(i, &npu->mmio_atsd_usage))
-				return i;
-	}
-
-	return -ENOSPC;
-}
-
-static void put_mmio_atsd_reg(struct npu *npu, int reg)
-{
-	clear_bit_unlock(reg, &npu->mmio_atsd_usage);
-}
-
-/* MMIO ATSD register offsets */
-#define XTS_ATSD_AVA  1
-#define XTS_ATSD_STAT 2
-
-static void mmio_launch_invalidate(struct mmio_atsd_reg *mmio_atsd_reg,
-				unsigned long launch, unsigned long va)
-{
-	struct npu *npu = mmio_atsd_reg->npu;
-	int reg = mmio_atsd_reg->reg;
-
-	__raw_writeq_be(va, npu->mmio_atsd_regs[reg] + XTS_ATSD_AVA);
-	eieio();
-	__raw_writeq_be(launch, npu->mmio_atsd_regs[reg]);
-}
-
-static void mmio_invalidate_pid(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS],
-				unsigned long pid, bool flush)
-{
-	int i;
-	unsigned long launch;
-
-	for (i = 0; i <= max_npu2_index; i++) {
-		if (mmio_atsd_reg[i].reg < 0)
-			continue;
-
-		/* IS set to invalidate matching PID */
-		launch = PPC_BIT(12);
-
-		/* PRS set to process-scoped */
-		launch |= PPC_BIT(13);
-
-		/* AP */
-		launch |= (u64)
-			mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17);
-
-		/* PID */
-		launch |= pid << PPC_BITLSHIFT(38);
-
-		/* No flush */
-		launch |= !flush << PPC_BITLSHIFT(39);
-
-		/* Invalidating the entire process doesn't use a va */
-		mmio_launch_invalidate(&mmio_atsd_reg[i], launch, 0);
-	}
-}
-
-static void mmio_invalidate_va(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS],
-			unsigned long va, unsigned long pid, bool flush)
-{
-	int i;
-	unsigned long launch;
-
-	for (i = 0; i <= max_npu2_index; i++) {
-		if (mmio_atsd_reg[i].reg < 0)
-			continue;
-
-		/* IS set to invalidate target VA */
-		launch = 0;
-
-		/* PRS set to process scoped */
-		launch |= PPC_BIT(13);
-
-		/* AP */
-		launch |= (u64)
-			mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17);
-
-		/* PID */
-		launch |= pid << PPC_BITLSHIFT(38);
-
-		/* No flush */
-		launch |= !flush << PPC_BITLSHIFT(39);
-
-		mmio_launch_invalidate(&mmio_atsd_reg[i], launch, va);
-	}
-}
-
-#define mn_to_npu_context(x) container_of(x, struct npu_context, mn)
-
-static void mmio_invalidate_wait(
-	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
-{
-	struct npu *npu;
-	int i, reg;
-
-	/* Wait for all invalidations to complete */
-	for (i = 0; i <= max_npu2_index; i++) {
-		if (mmio_atsd_reg[i].reg < 0)
-			continue;
-
-		/* Wait for completion */
-		npu = mmio_atsd_reg[i].npu;
-		reg = mmio_atsd_reg[i].reg;
-		while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
-			cpu_relax();
-	}
-}
+/* Maximum possible number of ATSD MMIO registers per NPU */
+#define NV_NMMU_ATSD_REGS 8
+#define NV_NPU_MAX_PE_NUM	16
 
 /*
- * Acquires all the address translation shootdown (ATSD) registers required to
- * launch an ATSD on all links this npu_context is active on.
+ * A compound NPU IOMMU group which might consist of 1 GPU + 2xNPUs (POWER8) or
+ * up to 3 x (GPU + 2xNPUs) (POWER9).
  */
-static void acquire_atsd_reg(struct npu_context *npu_context,
-			struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
+struct npu_comp {
+	struct iommu_table_group table_group;
+	int pe_num;
+	struct pnv_ioda_pe *pe[NV_NPU_MAX_PE_NUM];
+};
+
+/* An NPU descriptor, valid for POWER9 only */
+struct npu {
+	int index;
+	struct npu_comp npucomp;
+};
+
+#ifdef CONFIG_IOMMU_API
+static long pnv_npu_peers_create_table_userspace(
+		struct iommu_table_group *table_group,
+		int num, __u32 page_shift, __u64 window_size, __u32 levels,
+		struct iommu_table **ptbl)
+{
+	struct npu_comp *npucomp = container_of(table_group, struct npu_comp,
+			table_group);
+
+	if (!npucomp->pe_num || !npucomp->pe[0] ||
+			!npucomp->pe[0]->table_group.ops ||
+			!npucomp->pe[0]->table_group.ops->create_table)
+		return -EFAULT;
+
+	return npucomp->pe[0]->table_group.ops->create_table(
+			&npucomp->pe[0]->table_group, num, page_shift,
+			window_size, levels, ptbl);
+}
+
+static long pnv_npu_peers_set_window(struct iommu_table_group *table_group,
+		int num, struct iommu_table *tbl)
 {
 	int i, j;
-	struct npu *npu;
-	struct pci_dev *npdev;
-	struct pnv_phb *nphb;
+	long ret = 0;
+	struct npu_comp *npucomp = container_of(table_group, struct npu_comp,
+			table_group);
 
-	for (i = 0; i <= max_npu2_index; i++) {
-		mmio_atsd_reg[i].reg = -1;
-		for (j = 0; j < NV_MAX_LINKS; j++) {
-			/*
-			 * There are no ordering requirements with respect to
-			 * the setup of struct npu_context, but to ensure
-			 * consistent behaviour we need to ensure npdev[][] is
-			 * only read once.
-			 */
-			npdev = READ_ONCE(npu_context->npdev[i][j]);
-			if (!npdev)
+	for (i = 0; i < npucomp->pe_num; ++i) {
+		struct pnv_ioda_pe *pe = npucomp->pe[i];
+
+		if (!pe->table_group.ops->set_window)
+			continue;
+
+		ret = pe->table_group.ops->set_window(&pe->table_group,
+				num, tbl);
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		for (j = 0; j < i; ++j) {
+			struct pnv_ioda_pe *pe = npucomp->pe[j];
+
+			if (!pe->table_group.ops->unset_window)
 				continue;
 
-			nphb = pci_bus_to_host(npdev->bus)->private_data;
-			npu = &nphb->npu;
-			mmio_atsd_reg[i].npu = npu;
-			mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu);
-			while (mmio_atsd_reg[i].reg < 0) {
-				mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu);
-				cpu_relax();
-			}
-			break;
+			ret = pe->table_group.ops->unset_window(
+					&pe->table_group, num);
+			if (ret)
+				break;
 		}
+	} else {
+		table_group->tables[num] = iommu_tce_table_get(tbl);
 	}
+
+	return ret;
 }
 
-/*
- * Release previously acquired ATSD registers. To avoid deadlocks the registers
- * must be released in the same order they were acquired above in
- * acquire_atsd_reg.
- */
-static void release_atsd_reg(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
+static long pnv_npu_peers_unset_window(struct iommu_table_group *table_group,
+		int num)
+{
+	int i, j;
+	long ret = 0;
+	struct npu_comp *npucomp = container_of(table_group, struct npu_comp,
+			table_group);
+
+	for (i = 0; i < npucomp->pe_num; ++i) {
+		struct pnv_ioda_pe *pe = npucomp->pe[i];
+
+		WARN_ON(npucomp->table_group.tables[num] !=
+				table_group->tables[num]);
+		if (!npucomp->table_group.tables[num])
+			continue;
+
+		if (!pe->table_group.ops->unset_window)
+			continue;
+
+		ret = pe->table_group.ops->unset_window(&pe->table_group, num);
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		for (j = 0; j < i; ++j) {
+			struct pnv_ioda_pe *pe = npucomp->pe[j];
+
+			if (!npucomp->table_group.tables[num])
+				continue;
+
+			if (!pe->table_group.ops->set_window)
+				continue;
+
+			ret = pe->table_group.ops->set_window(&pe->table_group,
+					num, table_group->tables[num]);
+			if (ret)
+				break;
+		}
+	} else if (table_group->tables[num]) {
+		iommu_tce_table_put(table_group->tables[num]);
+		table_group->tables[num] = NULL;
+	}
+
+	return ret;
+}
+
+static void pnv_npu_peers_take_ownership(struct iommu_table_group *table_group)
 {
 	int i;
+	struct npu_comp *npucomp = container_of(table_group, struct npu_comp,
+			table_group);
 
-	for (i = 0; i <= max_npu2_index; i++) {
-		/*
-		 * We can't rely on npu_context->npdev[][] being the same here
-		 * as when acquire_atsd_reg() was called, hence we use the
-		 * values stored in mmio_atsd_reg during the acquire phase
-		 * rather than re-reading npdev[][].
-		 */
-		if (mmio_atsd_reg[i].reg < 0)
+	for (i = 0; i < npucomp->pe_num; ++i) {
+		struct pnv_ioda_pe *pe = npucomp->pe[i];
+
+		if (!pe->table_group.ops->take_ownership)
 			continue;
-
-		put_mmio_atsd_reg(mmio_atsd_reg[i].npu, mmio_atsd_reg[i].reg);
+		pe->table_group.ops->take_ownership(&pe->table_group);
 	}
 }
 
-/*
- * Invalidate either a single address or an entire PID depending on
- * the value of va.
- */
-static void mmio_invalidate(struct npu_context *npu_context, int va,
-			unsigned long address, bool flush)
+static void pnv_npu_peers_release_ownership(
+		struct iommu_table_group *table_group)
 {
-	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS];
-	unsigned long pid = npu_context->mm->context.id;
+	int i;
+	struct npu_comp *npucomp = container_of(table_group, struct npu_comp,
+			table_group);
 
-	if (npu_context->nmmu_flush)
-		/*
-		 * Unfortunately the nest mmu does not support flushing specific
-		 * addresses so we have to flush the whole mm once before
-		 * shooting down the GPU translation.
-		 */
-		flush_all_mm(npu_context->mm);
+	for (i = 0; i < npucomp->pe_num; ++i) {
+		struct pnv_ioda_pe *pe = npucomp->pe[i];
 
-	/*
-	 * Loop over all the NPUs this process is active on and launch
-	 * an invalidate.
-	 */
-	acquire_atsd_reg(npu_context, mmio_atsd_reg);
-	if (va)
-		mmio_invalidate_va(mmio_atsd_reg, address, pid, flush);
-	else
-		mmio_invalidate_pid(mmio_atsd_reg, pid, flush);
-
-	mmio_invalidate_wait(mmio_atsd_reg);
-	if (flush) {
-		/*
-		 * The GPU requires two flush ATSDs to ensure all entries have
-		 * been flushed. We use PID 0 as it will never be used for a
-		 * process on the GPU.
-		 */
-		mmio_invalidate_pid(mmio_atsd_reg, 0, true);
-		mmio_invalidate_wait(mmio_atsd_reg);
-		mmio_invalidate_pid(mmio_atsd_reg, 0, true);
-		mmio_invalidate_wait(mmio_atsd_reg);
-	}
-	release_atsd_reg(mmio_atsd_reg);
-}
-
-static void pnv_npu2_mn_release(struct mmu_notifier *mn,
-				struct mm_struct *mm)
-{
-	struct npu_context *npu_context = mn_to_npu_context(mn);
-
-	/* Call into device driver to stop requests to the NMMU */
-	if (npu_context->release_cb)
-		npu_context->release_cb(npu_context, npu_context->priv);
-
-	/*
-	 * There should be no more translation requests for this PID, but we
-	 * need to ensure any entries for it are removed from the TLB.
-	 */
-	mmio_invalidate(npu_context, 0, 0, true);
-}
-
-static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
-				struct mm_struct *mm,
-				unsigned long address,
-				pte_t pte)
-{
-	struct npu_context *npu_context = mn_to_npu_context(mn);
-
-	mmio_invalidate(npu_context, 1, address, true);
-}
-
-static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
-					struct mm_struct *mm,
-					unsigned long start, unsigned long end)
-{
-	struct npu_context *npu_context = mn_to_npu_context(mn);
-	unsigned long address;
-
-	if (end - start > atsd_threshold) {
-		/*
-		 * Just invalidate the entire PID if the address range is too
-		 * large.
-		 */
-		mmio_invalidate(npu_context, 0, 0, true);
-	} else {
-		for (address = start; address < end; address += PAGE_SIZE)
-			mmio_invalidate(npu_context, 1, address, false);
-
-		/* Do the flush only on the final addess == end */
-		mmio_invalidate(npu_context, 1, address, true);
+		if (!pe->table_group.ops->release_ownership)
+			continue;
+		pe->table_group.ops->release_ownership(&pe->table_group);
 	}
 }
 
-static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
-	.release = pnv_npu2_mn_release,
-	.change_pte = pnv_npu2_mn_change_pte,
-	.invalidate_range = pnv_npu2_mn_invalidate_range,
+static struct iommu_table_group_ops pnv_npu_peers_ops = {
+	.get_table_size = pnv_pci_ioda2_get_table_size,
+	.create_table = pnv_npu_peers_create_table_userspace,
+	.set_window = pnv_npu_peers_set_window,
+	.unset_window = pnv_npu_peers_unset_window,
+	.take_ownership = pnv_npu_peers_take_ownership,
+	.release_ownership = pnv_npu_peers_release_ownership,
 };
 
-/*
- * Call into OPAL to setup the nmmu context for the current task in
- * the NPU. This must be called to setup the context tables before the
- * GPU issues ATRs. pdev should be a pointed to PCIe GPU device.
- *
- * A release callback should be registered to allow a device driver to
- * be notified that it should not launch any new translation requests
- * as the final TLB invalidate is about to occur.
- *
- * Returns an error if there no contexts are currently available or a
- * npu_context which should be passed to pnv_npu2_handle_fault().
- *
- * mmap_sem must be held in write mode and must not be called from interrupt
- * context.
- */
-struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
-			unsigned long flags,
-			void (*cb)(struct npu_context *, void *),
-			void *priv)
+static void pnv_comp_attach_table_group(struct npu_comp *npucomp,
+		struct pnv_ioda_pe *pe)
 {
-	int rc;
-	u32 nvlink_index;
-	struct device_node *nvlink_dn;
-	struct mm_struct *mm = current->mm;
-	struct pnv_phb *nphb;
-	struct npu *npu;
-	struct npu_context *npu_context;
+	if (WARN_ON(npucomp->pe_num == NV_NPU_MAX_PE_NUM))
+		return;
 
-	/*
-	 * At present we don't support GPUs connected to multiple NPUs and I'm
-	 * not sure the hardware does either.
-	 */
-	struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
+	npucomp->pe[npucomp->pe_num] = pe;
+	++npucomp->pe_num;
+}
 
-	if (!firmware_has_feature(FW_FEATURE_OPAL))
-		return ERR_PTR(-ENODEV);
+struct iommu_table_group *pnv_try_setup_npu_table_group(struct pnv_ioda_pe *pe)
+{
+	struct iommu_table_group *table_group;
+	struct npu_comp *npucomp;
+	struct pci_dev *gpdev = NULL;
+	struct pci_controller *hose;
+	struct pci_dev *npdev = NULL;
+
+	list_for_each_entry(gpdev, &pe->pbus->devices, bus_list) {
+		npdev = pnv_pci_get_npu_dev(gpdev, 0);
+		if (npdev)
+			break;
+	}
 
 	if (!npdev)
-		/* No nvlink associated with this GPU device */
-		return ERR_PTR(-ENODEV);
+		/* It is not an NPU attached device, skip */
+		return NULL;
 
-	nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
-	if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
-							&nvlink_index)))
-		return ERR_PTR(-ENODEV);
+	hose = pci_bus_to_host(npdev->bus);
 
-	if (!mm || mm->context.id == 0) {
-		/*
-		 * Kernel thread contexts are not supported and context id 0 is
-		 * reserved on the GPU.
-		 */
-		return ERR_PTR(-EINVAL);
+	if (hose->npu) {
+		table_group = &hose->npu->npucomp.table_group;
+
+		if (!table_group->group) {
+			table_group->ops = &pnv_npu_peers_ops;
+			iommu_register_group(table_group,
+					hose->global_number,
+					pe->pe_number);
+		}
+	} else {
+		/* Create a group for 1 GPU and attached NPUs for POWER8 */
+		pe->npucomp = kzalloc(sizeof(*pe->npucomp), GFP_KERNEL);
+		table_group = &pe->npucomp->table_group;
+		table_group->ops = &pnv_npu_peers_ops;
+		iommu_register_group(table_group, hose->global_number,
+				pe->pe_number);
 	}
 
-	nphb = pci_bus_to_host(npdev->bus)->private_data;
-	npu = &nphb->npu;
+	/* Steal capabilities from a GPU PE */
+	table_group->max_dynamic_windows_supported =
+		pe->table_group.max_dynamic_windows_supported;
+	table_group->tce32_start = pe->table_group.tce32_start;
+	table_group->tce32_size = pe->table_group.tce32_size;
+	table_group->max_levels = pe->table_group.max_levels;
+	if (!table_group->pgsizes)
+		table_group->pgsizes = pe->table_group.pgsizes;
 
-	/*
-	 * Setup the NPU context table for a particular GPU. These need to be
-	 * per-GPU as we need the tables to filter ATSDs when there are no
-	 * active contexts on a particular GPU. It is safe for these to be
-	 * called concurrently with destroy as the OPAL call takes appropriate
-	 * locks and refcounts on init/destroy.
-	 */
-	rc = opal_npu_init_context(nphb->opal_id, mm->context.id, flags,
-				PCI_DEVID(gpdev->bus->number, gpdev->devfn));
-	if (rc < 0)
-		return ERR_PTR(-ENOSPC);
+	npucomp = container_of(table_group, struct npu_comp, table_group);
+	pnv_comp_attach_table_group(npucomp, pe);
 
-	/*
-	 * We store the npu pci device so we can more easily get at the
-	 * associated npus.
-	 */
-	spin_lock(&npu_context_lock);
-	npu_context = mm->context.npu_context;
-	if (npu_context) {
-		if (npu_context->release_cb != cb ||
-			npu_context->priv != priv) {
-			spin_unlock(&npu_context_lock);
-			opal_npu_destroy_context(nphb->opal_id, mm->context.id,
-						PCI_DEVID(gpdev->bus->number,
-							gpdev->devfn));
-			return ERR_PTR(-EINVAL);
-		}
-
-		WARN_ON(!kref_get_unless_zero(&npu_context->kref));
-	}
-	spin_unlock(&npu_context_lock);
-
-	if (!npu_context) {
-		/*
-		 * We can set up these fields without holding the
-		 * npu_context_lock as the npu_context hasn't been returned to
-		 * the caller meaning it can't be destroyed. Parallel allocation
-		 * is protected against by mmap_sem.
-		 */
-		rc = -ENOMEM;
-		npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL);
-		if (npu_context) {
-			kref_init(&npu_context->kref);
-			npu_context->mm = mm;
-			npu_context->mn.ops = &nv_nmmu_notifier_ops;
-			rc = __mmu_notifier_register(&npu_context->mn, mm);
-		}
-
-		if (rc) {
-			kfree(npu_context);
-			opal_npu_destroy_context(nphb->opal_id, mm->context.id,
-					PCI_DEVID(gpdev->bus->number,
-						gpdev->devfn));
-			return ERR_PTR(rc);
-		}
-
-		mm->context.npu_context = npu_context;
-	}
-
-	npu_context->release_cb = cb;
-	npu_context->priv = priv;
-
-	/*
-	 * npdev is a pci_dev pointer setup by the PCI code. We assign it to
-	 * npdev[][] to indicate to the mmu notifiers that an invalidation
-	 * should also be sent over this nvlink. The notifiers don't use any
-	 * other fields in npu_context, so we just need to ensure that when they
-	 * deference npu_context->npdev[][] it is either a valid pointer or
-	 * NULL.
-	 */
-	WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], npdev);
-
-	if (!nphb->npu.nmmu_flush) {
-		/*
-		 * If we're not explicitly flushing ourselves we need to mark
-		 * the thread for global flushes
-		 */
-		npu_context->nmmu_flush = false;
-		mm_context_add_copro(mm);
-	} else
-		npu_context->nmmu_flush = true;
-
-	return npu_context;
-}
-EXPORT_SYMBOL(pnv_npu2_init_context);
-
-static void pnv_npu2_release_context(struct kref *kref)
-{
-	struct npu_context *npu_context =
-		container_of(kref, struct npu_context, kref);
-
-	if (!npu_context->nmmu_flush)
-		mm_context_remove_copro(npu_context->mm);
-
-	npu_context->mm->context.npu_context = NULL;
+	return table_group;
 }
 
-/*
- * Destroy a context on the given GPU. May free the npu_context if it is no
- * longer active on any GPUs. Must not be called from interrupt context.
- */
-void pnv_npu2_destroy_context(struct npu_context *npu_context,
-			struct pci_dev *gpdev)
+struct iommu_table_group *pnv_npu_compound_attach(struct pnv_ioda_pe *pe)
 {
-	int removed;
-	struct pnv_phb *nphb;
+	struct iommu_table_group *table_group;
+	struct npu_comp *npucomp;
+	struct pci_dev *gpdev = NULL;
+	struct pci_dev *npdev;
+	struct pnv_ioda_pe *gpe = get_gpu_pci_dev_and_pe(pe, &gpdev);
+
+	WARN_ON(!(pe->flags & PNV_IODA_PE_DEV));
+	if (!gpe)
+		return NULL;
+
+	/*
+	 * IODA2 bridges get this set up from pci_controller_ops::setup_bridge
+	 * but NPU bridges do not have this hook defined so we do it here.
+	 * We do not setup other table group parameters as they won't be used
+	 * anyway - NVLink bridges are subordinate PEs.
+	 */
+	pe->table_group.ops = &pnv_pci_npu_ops;
+
+	table_group = iommu_group_get_iommudata(
+			iommu_group_get(&gpdev->dev));
+
+	/*
+	 * On P9 NPU PHB and PCI PHB support different page sizes,
+	 * keep only matching. We expect here that NVLink bridge PE pgsizes is
+	 * initialized by the caller.
+	 */
+	table_group->pgsizes &= pe->table_group.pgsizes;
+	npucomp = container_of(table_group, struct npu_comp, table_group);
+	pnv_comp_attach_table_group(npucomp, pe);
+
+	list_for_each_entry(npdev, &pe->phb->hose->bus->devices, bus_list) {
+		struct pci_dev *gpdevtmp = pnv_pci_get_gpu_dev(npdev);
+
+		if (gpdevtmp != gpdev)
+			continue;
+
+		iommu_add_device(table_group, &npdev->dev);
+	}
+
+	return table_group;
+}
+#endif /* CONFIG_IOMMU_API */
+
+int pnv_npu2_init(struct pci_controller *hose)
+{
+	static int npu_index;
 	struct npu *npu;
-	struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
-	struct device_node *nvlink_dn;
-	u32 nvlink_index;
+	int ret;
 
-	if (WARN_ON(!npdev))
-		return;
+	npu = kzalloc(sizeof(*npu), GFP_KERNEL);
+	if (!npu)
+		return -ENOMEM;
 
-	if (!firmware_has_feature(FW_FEATURE_OPAL))
-		return;
-
-	nphb = pci_bus_to_host(npdev->bus)->private_data;
-	npu = &nphb->npu;
-	nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
-	if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
-							&nvlink_index)))
-		return;
-	WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL);
-	opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id,
-				PCI_DEVID(gpdev->bus->number, gpdev->devfn));
-	spin_lock(&npu_context_lock);
-	removed = kref_put(&npu_context->kref, pnv_npu2_release_context);
-	spin_unlock(&npu_context_lock);
-
-	/*
-	 * We need to do this outside of pnv_npu2_release_context so that it is
-	 * outside the spinlock as mmu_notifier_destroy uses SRCU.
-	 */
-	if (removed) {
-		mmu_notifier_unregister(&npu_context->mn,
-					npu_context->mm);
-
-		kfree(npu_context);
+	npu_index++;
+	if (WARN_ON(npu_index >= NV_MAX_NPUS)) {
+		ret = -ENOSPC;
+		goto fail_exit;
 	}
+	npu->index = npu_index;
+	hose->npu = npu;
 
+	return 0;
+
+fail_exit:
+	kfree(npu);
+	return ret;
 }
-EXPORT_SYMBOL(pnv_npu2_destroy_context);
 
-/*
- * Assumes mmap_sem is held for the contexts associated mm.
- */
-int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea,
-			unsigned long *flags, unsigned long *status, int count)
+int pnv_npu2_map_lpar_dev(struct pci_dev *gpdev, unsigned int lparid,
+		unsigned long msr)
 {
-	u64 rc = 0, result = 0;
-	int i, is_write;
-	struct page *page[1];
+	int ret;
+	struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
+	struct pci_controller *hose;
+	struct pnv_phb *nphb;
 
-	/* mmap_sem should be held so the struct_mm must be present */
-	struct mm_struct *mm = context->mm;
-
-	if (!firmware_has_feature(FW_FEATURE_OPAL))
+	if (!npdev)
 		return -ENODEV;
 
-	WARN_ON(!rwsem_is_locked(&mm->mmap_sem));
+	hose = pci_bus_to_host(npdev->bus);
+	nphb = hose->private_data;
 
-	for (i = 0; i < count; i++) {
-		is_write = flags[i] & NPU2_WRITE;
-		rc = get_user_pages_remote(NULL, mm, ea[i], 1,
-					is_write ? FOLL_WRITE : 0,
-					page, NULL, NULL);
-
-		/*
-		 * To support virtualised environments we will have to do an
-		 * access to the page to ensure it gets faulted into the
-		 * hypervisor. For the moment virtualisation is not supported in
-		 * other areas so leave the access out.
-		 */
-		if (rc != 1) {
-			status[i] = rc;
-			result = -EFAULT;
-			continue;
-		}
-
-		status[i] = 0;
-		put_page(page[0]);
+	dev_dbg(&gpdev->dev, "Map LPAR opalid=%llu lparid=%u\n",
+			nphb->opal_id, lparid);
+	/*
+	 * Currently we only support radix and non-zero LPCR only makes sense
+	 * for hash tables so skiboot expects the LPCR parameter to be a zero.
+	 */
+	ret = opal_npu_map_lpar(nphb->opal_id, pci_dev_id(gpdev), lparid,
+				0 /* LPCR bits */);
+	if (ret) {
+		dev_err(&gpdev->dev, "Error %d mapping device to LPAR\n", ret);
+		return ret;
 	}
 
-	return result;
-}
-EXPORT_SYMBOL(pnv_npu2_handle_fault);
-
-int pnv_npu2_init(struct pnv_phb *phb)
-{
-	unsigned int i;
-	u64 mmio_atsd;
-	struct device_node *dn;
-	struct pci_dev *gpdev;
-	static int npu_index;
-	uint64_t rc = 0;
-
-	if (!atsd_threshold_dentry) {
-		atsd_threshold_dentry = debugfs_create_x64("atsd_threshold",
-				   0600, powerpc_debugfs_root, &atsd_threshold);
-	}
-
-	phb->npu.nmmu_flush =
-		of_property_read_bool(phb->hose->dn, "ibm,nmmu-flush");
-	for_each_child_of_node(phb->hose->dn, dn) {
-		gpdev = pnv_pci_get_gpu_dev(get_pci_dev(dn));
-		if (gpdev) {
-			rc = opal_npu_map_lpar(phb->opal_id,
-				PCI_DEVID(gpdev->bus->number, gpdev->devfn),
-				0, 0);
-			if (rc)
-				dev_err(&gpdev->dev,
-					"Error %lld mapping device to LPAR\n",
-					rc);
-		}
-	}
-
-	for (i = 0; !of_property_read_u64_index(phb->hose->dn, "ibm,mmio-atsd",
-							i, &mmio_atsd); i++)
-		phb->npu.mmio_atsd_regs[i] = ioremap(mmio_atsd, 32);
-
-	pr_info("NPU%lld: Found %d MMIO ATSD registers", phb->opal_id, i);
-	phb->npu.mmio_atsd_count = i;
-	phb->npu.mmio_atsd_usage = 0;
-	npu_index++;
-	if (WARN_ON(npu_index >= NV_MAX_NPUS))
-		return -ENOSPC;
-	max_npu2_index = npu_index;
-	phb->npu.index = npu_index;
+	dev_dbg(&gpdev->dev, "init context opalid=%llu msr=%lx\n",
+			nphb->opal_id, msr);
+	ret = opal_npu_init_context(nphb->opal_id, 0/*__unused*/, msr,
+				    pci_dev_id(gpdev));
+	if (ret < 0)
+		dev_err(&gpdev->dev, "Failed to init context: %d\n", ret);
+	else
+		ret = 0;
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pnv_npu2_map_lpar_dev);
+
+void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr)
+{
+	struct pci_dev *gpdev;
+
+	list_for_each_entry(gpdev, &gpe->pbus->devices, bus_list)
+		pnv_npu2_map_lpar_dev(gpdev, 0, msr);
+}
+
+int pnv_npu2_unmap_lpar_dev(struct pci_dev *gpdev)
+{
+	int ret;
+	struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
+	struct pci_controller *hose;
+	struct pnv_phb *nphb;
+
+	if (!npdev)
+		return -ENODEV;
+
+	hose = pci_bus_to_host(npdev->bus);
+	nphb = hose->private_data;
+
+	dev_dbg(&gpdev->dev, "destroy context opalid=%llu\n",
+			nphb->opal_id);
+	ret = opal_npu_destroy_context(nphb->opal_id, 0/*__unused*/,
+				       pci_dev_id(gpdev));
+	if (ret < 0) {
+		dev_err(&gpdev->dev, "Failed to destroy context: %d\n", ret);
+		return ret;
+	}
+
+	/* Set LPID to 0 anyway, just to be safe */
+	dev_dbg(&gpdev->dev, "Map LPAR opalid=%llu lparid=0\n", nphb->opal_id);
+	ret = opal_npu_map_lpar(nphb->opal_id, pci_dev_id(gpdev), 0 /*LPID*/,
+				0 /* LPCR bits */);
+	if (ret)
+		dev_err(&gpdev->dev, "Error %d mapping device to LPAR\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pnv_npu2_unmap_lpar_dev);
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
index 18a355f..1656e89 100644
--- a/arch/powerpc/platforms/powernv/opal-async.c
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV OPAL asynchronous completion interfaces
  *
  * Copyright 2013-2017 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c
new file mode 100644
index 0000000..a2aa5e4
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-call.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/percpu.h>
+#include <linux/jump_label.h>
+#include <asm/opal-api.h>
+#include <asm/trace.h>
+#include <asm/asm-prototypes.h>
+
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * Since the tracing code might execute OPAL calls we need to guard against
+ * recursion.
+ */
+static DEFINE_PER_CPU(unsigned int, opal_trace_depth);
+
+static void __trace_opal_entry(s64 a0, s64 a1, s64 a2, s64 a3,
+			       s64 a4, s64 a5, s64 a6, s64 a7,
+			       unsigned long opcode)
+{
+	unsigned int *depth;
+	unsigned long args[8];
+
+	depth = this_cpu_ptr(&opal_trace_depth);
+
+	if (*depth)
+		return;
+
+	args[0] = a0;
+	args[1] = a1;
+	args[2] = a2;
+	args[3] = a3;
+	args[4] = a4;
+	args[5] = a5;
+	args[6] = a6;
+	args[7] = a7;
+
+	(*depth)++;
+	trace_opal_entry(opcode, &args[0]);
+	(*depth)--;
+}
+
+static void __trace_opal_exit(unsigned long opcode, unsigned long retval)
+{
+	unsigned int *depth;
+
+	depth = this_cpu_ptr(&opal_trace_depth);
+
+	if (*depth)
+		return;
+
+	(*depth)++;
+	trace_opal_exit(opcode, retval);
+	(*depth)--;
+}
+
+static DEFINE_STATIC_KEY_FALSE(opal_tracepoint_key);
+
+int opal_tracepoint_regfunc(void)
+{
+	static_branch_inc(&opal_tracepoint_key);
+	return 0;
+}
+
+void opal_tracepoint_unregfunc(void)
+{
+	static_branch_dec(&opal_tracepoint_key);
+}
+
+static s64 __opal_call_trace(s64 a0, s64 a1, s64 a2, s64 a3,
+			     s64 a4, s64 a5, s64 a6, s64 a7,
+			      unsigned long opcode, unsigned long msr)
+{
+	s64 ret;
+
+	__trace_opal_entry(a0, a1, a2, a3, a4, a5, a6, a7, opcode);
+	ret = __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+	__trace_opal_exit(opcode, ret);
+
+	return ret;
+}
+
+#define DO_TRACE (static_branch_unlikely(&opal_tracepoint_key))
+
+#else /* CONFIG_TRACEPOINTS */
+
+static s64 __opal_call_trace(s64 a0, s64 a1, s64 a2, s64 a3,
+			     s64 a4, s64 a5, s64 a6, s64 a7,
+			      unsigned long opcode, unsigned long msr)
+{
+	return 0;
+}
+
+#define DO_TRACE false
+#endif /* CONFIG_TRACEPOINTS */
+
+static int64_t opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3,
+	     int64_t a4, int64_t a5, int64_t a6, int64_t a7, int64_t opcode)
+{
+	unsigned long flags;
+	unsigned long msr = mfmsr();
+	bool mmu = (msr & (MSR_IR|MSR_DR));
+	int64_t ret;
+
+	msr &= ~MSR_EE;
+
+	if (unlikely(!mmu))
+		return __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+
+	local_save_flags(flags);
+	hard_irq_disable();
+
+	if (DO_TRACE) {
+		ret = __opal_call_trace(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+	} else {
+		ret = __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr);
+	}
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+#define OPAL_CALL(name, opcode)					\
+int64_t name(int64_t a0, int64_t a1, int64_t a2, int64_t a3,	\
+	     int64_t a4, int64_t a5, int64_t a6, int64_t a7);	\
+int64_t name(int64_t a0, int64_t a1, int64_t a2, int64_t a3,	\
+	     int64_t a4, int64_t a5, int64_t a6, int64_t a7)	\
+{								\
+	return opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode); \
+}
+
+OPAL_CALL(opal_invalid_call,			OPAL_INVALID_CALL);
+OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
+OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
+OPAL_CALL(opal_console_write_buffer_space,	OPAL_CONSOLE_WRITE_BUFFER_SPACE);
+OPAL_CALL(opal_rtc_read,			OPAL_RTC_READ);
+OPAL_CALL(opal_rtc_write,			OPAL_RTC_WRITE);
+OPAL_CALL(opal_cec_power_down,			OPAL_CEC_POWER_DOWN);
+OPAL_CALL(opal_cec_reboot,			OPAL_CEC_REBOOT);
+OPAL_CALL(opal_cec_reboot2,			OPAL_CEC_REBOOT2);
+OPAL_CALL(opal_read_nvram,			OPAL_READ_NVRAM);
+OPAL_CALL(opal_write_nvram,			OPAL_WRITE_NVRAM);
+OPAL_CALL(opal_handle_interrupt,		OPAL_HANDLE_INTERRUPT);
+OPAL_CALL(opal_poll_events,			OPAL_POLL_EVENTS);
+OPAL_CALL(opal_pci_set_hub_tce_memory,		OPAL_PCI_SET_HUB_TCE_MEMORY);
+OPAL_CALL(opal_pci_set_phb_tce_memory,		OPAL_PCI_SET_PHB_TCE_MEMORY);
+OPAL_CALL(opal_pci_config_read_byte,		OPAL_PCI_CONFIG_READ_BYTE);
+OPAL_CALL(opal_pci_config_read_half_word,	OPAL_PCI_CONFIG_READ_HALF_WORD);
+OPAL_CALL(opal_pci_config_read_word,		OPAL_PCI_CONFIG_READ_WORD);
+OPAL_CALL(opal_pci_config_write_byte,		OPAL_PCI_CONFIG_WRITE_BYTE);
+OPAL_CALL(opal_pci_config_write_half_word,	OPAL_PCI_CONFIG_WRITE_HALF_WORD);
+OPAL_CALL(opal_pci_config_write_word,		OPAL_PCI_CONFIG_WRITE_WORD);
+OPAL_CALL(opal_set_xive,			OPAL_SET_XIVE);
+OPAL_CALL(opal_get_xive,			OPAL_GET_XIVE);
+OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER);
+OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
+OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
+OPAL_CALL(opal_pci_eeh_freeze_set,		OPAL_PCI_EEH_FREEZE_SET);
+OPAL_CALL(opal_pci_err_inject,			OPAL_PCI_ERR_INJECT);
+OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
+OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
+OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
+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);
+OPAL_CALL(opal_get_xive_source,			OPAL_GET_XIVE_SOURCE);
+OPAL_CALL(opal_get_msi_32,			OPAL_GET_MSI_32);
+OPAL_CALL(opal_get_msi_64,			OPAL_GET_MSI_64);
+OPAL_CALL(opal_start_cpu,			OPAL_START_CPU);
+OPAL_CALL(opal_query_cpu_status,		OPAL_QUERY_CPU_STATUS);
+OPAL_CALL(opal_write_oppanel,			OPAL_WRITE_OPPANEL);
+OPAL_CALL(opal_pci_map_pe_dma_window,		OPAL_PCI_MAP_PE_DMA_WINDOW);
+OPAL_CALL(opal_pci_map_pe_dma_window_real,	OPAL_PCI_MAP_PE_DMA_WINDOW_REAL);
+OPAL_CALL(opal_pci_reset,			OPAL_PCI_RESET);
+OPAL_CALL(opal_pci_get_hub_diag_data,		OPAL_PCI_GET_HUB_DIAG_DATA);
+OPAL_CALL(opal_pci_get_phb_diag_data,		OPAL_PCI_GET_PHB_DIAG_DATA);
+OPAL_CALL(opal_pci_fence_phb,			OPAL_PCI_FENCE_PHB);
+OPAL_CALL(opal_pci_reinit,			OPAL_PCI_REINIT);
+OPAL_CALL(opal_pci_mask_pe_error,		OPAL_PCI_MASK_PE_ERROR);
+OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
+OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
+OPAL_CALL(opal_get_dpo_status,			OPAL_GET_DPO_STATUS);
+OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
+OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
+OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
+OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
+OPAL_CALL(opal_pci_get_phb_diag_data2,		OPAL_PCI_GET_PHB_DIAG_DATA2);
+OPAL_CALL(opal_xscom_read,			OPAL_XSCOM_READ);
+OPAL_CALL(opal_xscom_write,			OPAL_XSCOM_WRITE);
+OPAL_CALL(opal_lpc_read,			OPAL_LPC_READ);
+OPAL_CALL(opal_lpc_write,			OPAL_LPC_WRITE);
+OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
+OPAL_CALL(opal_reinit_cpus,			OPAL_REINIT_CPUS);
+OPAL_CALL(opal_read_elog,			OPAL_ELOG_READ);
+OPAL_CALL(opal_send_ack_elog,			OPAL_ELOG_ACK);
+OPAL_CALL(opal_get_elog_size,			OPAL_ELOG_SIZE);
+OPAL_CALL(opal_resend_pending_logs,		OPAL_ELOG_RESEND);
+OPAL_CALL(opal_write_elog,			OPAL_ELOG_WRITE);
+OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
+OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
+OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
+OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
+OPAL_CALL(opal_check_token,			OPAL_CHECK_TOKEN);
+OPAL_CALL(opal_dump_init,			OPAL_DUMP_INIT);
+OPAL_CALL(opal_dump_info,			OPAL_DUMP_INFO);
+OPAL_CALL(opal_dump_info2,			OPAL_DUMP_INFO2);
+OPAL_CALL(opal_dump_read,			OPAL_DUMP_READ);
+OPAL_CALL(opal_dump_ack,			OPAL_DUMP_ACK);
+OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
+OPAL_CALL(opal_write_oppanel_async,		OPAL_WRITE_OPPANEL_ASYNC);
+OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
+OPAL_CALL(opal_dump_resend_notification,	OPAL_DUMP_RESEND);
+OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);
+OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
+OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
+OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
+OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
+OPAL_CALL(opal_handle_hmi2,			OPAL_HANDLE_HMI2);
+OPAL_CALL(opal_config_cpu_idle_state,		OPAL_CONFIG_CPU_IDLE_STATE);
+OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
+OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
+OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
+OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CAPI_MODE);
+OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
+OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
+OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
+OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
+OPAL_CALL(opal_i2c_request,			OPAL_I2C_REQUEST);
+OPAL_CALL(opal_flash_read,			OPAL_FLASH_READ);
+OPAL_CALL(opal_flash_write,			OPAL_FLASH_WRITE);
+OPAL_CALL(opal_flash_erase,			OPAL_FLASH_ERASE);
+OPAL_CALL(opal_prd_msg,				OPAL_PRD_MSG);
+OPAL_CALL(opal_leds_get_ind,			OPAL_LEDS_GET_INDICATOR);
+OPAL_CALL(opal_leds_set_ind,			OPAL_LEDS_SET_INDICATOR);
+OPAL_CALL(opal_console_flush,			OPAL_CONSOLE_FLUSH);
+OPAL_CALL(opal_get_device_tree,			OPAL_GET_DEVICE_TREE);
+OPAL_CALL(opal_pci_get_presence_state,		OPAL_PCI_GET_PRESENCE_STATE);
+OPAL_CALL(opal_pci_get_power_state,		OPAL_PCI_GET_POWER_STATE);
+OPAL_CALL(opal_pci_set_power_state,		OPAL_PCI_SET_POWER_STATE);
+OPAL_CALL(opal_int_get_xirr,			OPAL_INT_GET_XIRR);
+OPAL_CALL(opal_int_set_cppr,			OPAL_INT_SET_CPPR);
+OPAL_CALL(opal_int_eoi,				OPAL_INT_EOI);
+OPAL_CALL(opal_int_set_mfrr,			OPAL_INT_SET_MFRR);
+OPAL_CALL(opal_pci_tce_kill,			OPAL_PCI_TCE_KILL);
+OPAL_CALL(opal_nmmu_set_ptcr,			OPAL_NMMU_SET_PTCR);
+OPAL_CALL(opal_xive_reset,			OPAL_XIVE_RESET);
+OPAL_CALL(opal_xive_get_irq_info,		OPAL_XIVE_GET_IRQ_INFO);
+OPAL_CALL(opal_xive_get_irq_config,		OPAL_XIVE_GET_IRQ_CONFIG);
+OPAL_CALL(opal_xive_set_irq_config,		OPAL_XIVE_SET_IRQ_CONFIG);
+OPAL_CALL(opal_xive_get_queue_info,		OPAL_XIVE_GET_QUEUE_INFO);
+OPAL_CALL(opal_xive_set_queue_info,		OPAL_XIVE_SET_QUEUE_INFO);
+OPAL_CALL(opal_xive_donate_page,		OPAL_XIVE_DONATE_PAGE);
+OPAL_CALL(opal_xive_alloc_vp_block,		OPAL_XIVE_ALLOCATE_VP_BLOCK);
+OPAL_CALL(opal_xive_free_vp_block,		OPAL_XIVE_FREE_VP_BLOCK);
+OPAL_CALL(opal_xive_allocate_irq_raw,		OPAL_XIVE_ALLOCATE_IRQ);
+OPAL_CALL(opal_xive_free_irq,			OPAL_XIVE_FREE_IRQ);
+OPAL_CALL(opal_xive_get_vp_info,		OPAL_XIVE_GET_VP_INFO);
+OPAL_CALL(opal_xive_set_vp_info,		OPAL_XIVE_SET_VP_INFO);
+OPAL_CALL(opal_xive_sync,			OPAL_XIVE_SYNC);
+OPAL_CALL(opal_xive_dump,			OPAL_XIVE_DUMP);
+OPAL_CALL(opal_xive_get_queue_state,		OPAL_XIVE_GET_QUEUE_STATE);
+OPAL_CALL(opal_xive_set_queue_state,		OPAL_XIVE_SET_QUEUE_STATE);
+OPAL_CALL(opal_xive_get_vp_state,		OPAL_XIVE_GET_VP_STATE);
+OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
+OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
+OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);
+OPAL_CALL(opal_npu_map_lpar,			OPAL_NPU_MAP_LPAR);
+OPAL_CALL(opal_imc_counters_init,		OPAL_IMC_COUNTERS_INIT);
+OPAL_CALL(opal_imc_counters_start,		OPAL_IMC_COUNTERS_START);
+OPAL_CALL(opal_imc_counters_stop,		OPAL_IMC_COUNTERS_STOP);
+OPAL_CALL(opal_get_powercap,			OPAL_GET_POWERCAP);
+OPAL_CALL(opal_set_powercap,			OPAL_SET_POWERCAP);
+OPAL_CALL(opal_get_power_shift_ratio,		OPAL_GET_POWER_SHIFT_RATIO);
+OPAL_CALL(opal_set_power_shift_ratio,		OPAL_SET_POWER_SHIFT_RATIO);
+OPAL_CALL(opal_sensor_group_clear,		OPAL_SENSOR_GROUP_CLEAR);
+OPAL_CALL(opal_quiesce,				OPAL_QUIESCE);
+OPAL_CALL(opal_npu_spa_setup,			OPAL_NPU_SPA_SETUP);
+OPAL_CALL(opal_npu_spa_clear_cache,		OPAL_NPU_SPA_CLEAR_CACHE);
+OPAL_CALL(opal_npu_tl_set,			OPAL_NPU_TL_SET);
+OPAL_CALL(opal_pci_get_pbcq_tunnel_bar,		OPAL_PCI_GET_PBCQ_TUNNEL_BAR);
+OPAL_CALL(opal_pci_set_pbcq_tunnel_bar,		OPAL_PCI_SET_PBCQ_TUNNEL_BAR);
+OPAL_CALL(opal_sensor_read_u64,			OPAL_SENSOR_READ_U64);
+OPAL_CALL(opal_sensor_group_enable,		OPAL_SENSOR_GROUP_ENABLE);
+OPAL_CALL(opal_nx_coproc_init,			OPAL_NX_COPROC_INIT);
+OPAL_CALL(opal_mpipl_update,			OPAL_MPIPL_UPDATE);
+OPAL_CALL(opal_mpipl_register_tag,		OPAL_MPIPL_REGISTER_TAG);
+OPAL_CALL(opal_mpipl_query_tag,			OPAL_MPIPL_QUERY_TAG);
diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c
new file mode 100644
index 0000000..ed895d8
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-core.c
@@ -0,0 +1,636 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Interface for exporting the OPAL ELF core.
+ * Heavily inspired from fs/proc/vmcore.c
+ *
+ * Copyright 2019, Hari Bathini, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "opal core: " fmt
+
+#include <linux/memblock.h>
+#include <linux/uaccess.h>
+#include <linux/proc_fs.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/slab.h>
+#include <linux/crash_core.h>
+#include <linux/of.h>
+
+#include <asm/page.h>
+#include <asm/opal.h>
+#include <asm/fadump-internal.h>
+
+#include "opal-fadump.h"
+
+#define MAX_PT_LOAD_CNT		8
+
+/* NT_AUXV note related info */
+#define AUXV_CNT		1
+#define AUXV_DESC_SZ		(((2 * AUXV_CNT) + 1) * sizeof(Elf64_Off))
+
+struct opalcore_config {
+	u32			num_cpus;
+	/* PIR value of crashing CPU */
+	u32			crashing_cpu;
+
+	/* CPU state data info from F/W */
+	u64			cpu_state_destination_vaddr;
+	u64			cpu_state_data_size;
+	u64			cpu_state_entry_size;
+
+	/* OPAL memory to be exported as PT_LOAD segments */
+	u64			ptload_addr[MAX_PT_LOAD_CNT];
+	u64			ptload_size[MAX_PT_LOAD_CNT];
+	u64			ptload_cnt;
+
+	/* Pointer to the first PT_LOAD in the ELF core file */
+	Elf64_Phdr		*ptload_phdr;
+
+	/* Total size of opalcore file. */
+	size_t			opalcore_size;
+
+	/* Buffer for all the ELF core headers and the PT_NOTE */
+	size_t			opalcorebuf_sz;
+	char			*opalcorebuf;
+
+	/* NT_AUXV buffer */
+	char			auxv_buf[AUXV_DESC_SZ];
+};
+
+struct opalcore {
+	struct list_head	list;
+	u64			paddr;
+	size_t			size;
+	loff_t			offset;
+};
+
+static LIST_HEAD(opalcore_list);
+static struct opalcore_config *oc_conf;
+static const struct opal_mpipl_fadump *opalc_metadata;
+static const struct opal_mpipl_fadump *opalc_cpu_metadata;
+
+/*
+ * Set crashing CPU's signal to SIGUSR1. if the kernel is triggered
+ * by kernel, SIGTERM otherwise.
+ */
+bool kernel_initiated;
+
+static struct opalcore * __init get_new_element(void)
+{
+	return kzalloc(sizeof(struct opalcore), GFP_KERNEL);
+}
+
+static inline int is_opalcore_usable(void)
+{
+	return (oc_conf && oc_conf->opalcorebuf != NULL) ? 1 : 0;
+}
+
+static Elf64_Word *append_elf64_note(Elf64_Word *buf, char *name,
+				     u32 type, void *data,
+				     size_t data_len)
+{
+	Elf64_Nhdr *note = (Elf64_Nhdr *)buf;
+	Elf64_Word namesz = strlen(name) + 1;
+
+	note->n_namesz = cpu_to_be32(namesz);
+	note->n_descsz = cpu_to_be32(data_len);
+	note->n_type   = cpu_to_be32(type);
+	buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf64_Word));
+	memcpy(buf, name, namesz);
+	buf += DIV_ROUND_UP(namesz, sizeof(Elf64_Word));
+	memcpy(buf, data, data_len);
+	buf += DIV_ROUND_UP(data_len, sizeof(Elf64_Word));
+
+	return buf;
+}
+
+static void fill_prstatus(struct elf_prstatus *prstatus, int pir,
+			  struct pt_regs *regs)
+{
+	memset(prstatus, 0, sizeof(struct elf_prstatus));
+	elf_core_copy_kernel_regs(&(prstatus->pr_reg), regs);
+
+	/*
+	 * Overload PID with PIR value.
+	 * As a PIR value could also be '0', add an offset of '100'
+	 * to every PIR to avoid misinterpretations in GDB.
+	 */
+	prstatus->pr_pid  = cpu_to_be32(100 + pir);
+	prstatus->pr_ppid = cpu_to_be32(1);
+
+	/*
+	 * Indicate SIGUSR1 for crash initiated from kernel.
+	 * SIGTERM otherwise.
+	 */
+	if (pir == oc_conf->crashing_cpu) {
+		short sig;
+
+		sig = kernel_initiated ? SIGUSR1 : SIGTERM;
+		prstatus->pr_cursig = cpu_to_be16(sig);
+	}
+}
+
+static Elf64_Word *auxv_to_elf64_notes(Elf64_Word *buf,
+				       u64 opal_boot_entry)
+{
+	Elf64_Off *bufp = (Elf64_Off *)oc_conf->auxv_buf;
+	int idx = 0;
+
+	memset(bufp, 0, AUXV_DESC_SZ);
+
+	/* Entry point of OPAL */
+	bufp[idx++] = cpu_to_be64(AT_ENTRY);
+	bufp[idx++] = cpu_to_be64(opal_boot_entry);
+
+	/* end of vector */
+	bufp[idx++] = cpu_to_be64(AT_NULL);
+
+	buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_AUXV,
+				oc_conf->auxv_buf, AUXV_DESC_SZ);
+	return buf;
+}
+
+/*
+ * Read from the ELF header and then the crash dump.
+ * 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,
+			     loff_t pos, size_t count)
+{
+	struct opalcore *m;
+	ssize_t tsz, avail;
+	loff_t tpos = pos;
+
+	if (pos >= oc_conf->opalcore_size)
+		return 0;
+
+	/* Adjust count if it goes beyond opalcore size */
+	avail = oc_conf->opalcore_size - pos;
+	if (count > avail)
+		count = avail;
+
+	if (count == 0)
+		return 0;
+
+	/* Read ELF core header and/or PT_NOTE segment */
+	if (tpos < oc_conf->opalcorebuf_sz) {
+		tsz = min_t(size_t, oc_conf->opalcorebuf_sz - tpos, count);
+		memcpy(to, oc_conf->opalcorebuf + tpos, tsz);
+		to += tsz;
+		tpos += tsz;
+		count -= tsz;
+	}
+
+	list_for_each_entry(m, &opalcore_list, list) {
+		/* nothing more to read here */
+		if (count == 0)
+			break;
+
+		if (tpos < m->offset + m->size) {
+			void *addr;
+
+			tsz = min_t(size_t, m->offset + m->size - tpos, count);
+			addr = (void *)(m->paddr + tpos - m->offset);
+			memcpy(to, __va(addr), tsz);
+			to += tsz;
+			tpos += tsz;
+			count -= tsz;
+		}
+	}
+
+	return (tpos - pos);
+}
+
+static struct bin_attribute opal_core_attr = {
+	.attr = {.name = "core", .mode = 0400},
+	.read = read_opalcore
+};
+
+/*
+ * Read CPU state dump data and convert it into ELF notes.
+ *
+ * Each register entry is of 16 bytes, A numerical identifier along with
+ * a GPR/SPR flag in the first 8 bytes and the register value in the next
+ * 8 bytes. For more details refer to F/W documentation.
+ */
+static Elf64_Word * __init opalcore_append_cpu_notes(Elf64_Word *buf)
+{
+	u32 thread_pir, size_per_thread, regs_offset, regs_cnt, reg_esize;
+	struct hdat_fadump_thread_hdr *thdr;
+	struct elf_prstatus prstatus;
+	Elf64_Word *first_cpu_note;
+	struct pt_regs regs;
+	char *bufp;
+	int i;
+
+	size_per_thread = oc_conf->cpu_state_entry_size;
+	bufp = __va(oc_conf->cpu_state_destination_vaddr);
+
+	/*
+	 * Offset for register entries, entry size and registers count is
+	 * duplicated in every thread header in keeping with HDAT format.
+	 * Use these values from the first thread header.
+	 */
+	thdr = (struct hdat_fadump_thread_hdr *)bufp;
+	regs_offset = (offsetof(struct hdat_fadump_thread_hdr, offset) +
+		       be32_to_cpu(thdr->offset));
+	reg_esize = be32_to_cpu(thdr->esize);
+	regs_cnt  = be32_to_cpu(thdr->ecnt);
+
+	pr_debug("--------CPU State Data------------\n");
+	pr_debug("NumCpus     : %u\n", oc_conf->num_cpus);
+	pr_debug("\tOffset: %u, Entry size: %u, Cnt: %u\n",
+		 regs_offset, reg_esize, regs_cnt);
+
+	/*
+	 * Skip past the first CPU note. Fill this note with the
+	 * crashing CPU's prstatus.
+	 */
+	first_cpu_note = buf;
+	buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+				&prstatus, sizeof(prstatus));
+
+	for (i = 0; i < oc_conf->num_cpus; i++, bufp += size_per_thread) {
+		thdr = (struct hdat_fadump_thread_hdr *)bufp;
+		thread_pir = be32_to_cpu(thdr->pir);
+
+		pr_debug("[%04d] PIR: 0x%x, core state: 0x%02x\n",
+			 i, thread_pir, thdr->core_state);
+
+		/*
+		 * Register state data of MAX cores is provided by firmware,
+		 * but some of this cores may not be active. So, while
+		 * processing register state data, check core state and
+		 * skip threads that belong to inactive cores.
+		 */
+		if (thdr->core_state == HDAT_FADUMP_CORE_INACTIVE)
+			continue;
+
+		opal_fadump_read_regs((bufp + regs_offset), regs_cnt,
+				      reg_esize, false, &regs);
+
+		pr_debug("PIR 0x%x - R1 : 0x%llx, NIP : 0x%llx\n", thread_pir,
+			 be64_to_cpu(regs.gpr[1]), be64_to_cpu(regs.nip));
+		fill_prstatus(&prstatus, thread_pir, &regs);
+
+		if (thread_pir != oc_conf->crashing_cpu) {
+			buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME,
+						NT_PRSTATUS, &prstatus,
+						sizeof(prstatus));
+		} else {
+			/*
+			 * 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,
+					  NT_PRSTATUS, &prstatus,
+					  sizeof(prstatus));
+		}
+	}
+
+	return buf;
+}
+
+static int __init create_opalcore(void)
+{
+	u64 opal_boot_entry, opal_base_addr, paddr;
+	u32 hdr_size, cpu_notes_size, count;
+	struct device_node *dn;
+	struct opalcore *new;
+	loff_t opalcore_off;
+	struct page *page;
+	Elf64_Phdr *phdr;
+	Elf64_Ehdr *elf;
+	int i, ret;
+	char *bufp;
+
+	/* Get size of header & CPU notes for OPAL core */
+	hdr_size = (sizeof(Elf64_Ehdr) +
+		    ((oc_conf->ptload_cnt + 1) * sizeof(Elf64_Phdr)));
+	cpu_notes_size = ((oc_conf->num_cpus * (CRASH_CORE_NOTE_HEAD_BYTES +
+			  CRASH_CORE_NOTE_NAME_BYTES +
+			  CRASH_CORE_NOTE_DESC_BYTES)) +
+			  (CRASH_CORE_NOTE_HEAD_BYTES +
+			  CRASH_CORE_NOTE_NAME_BYTES + AUXV_DESC_SZ));
+
+	/* Allocate buffer to setup OPAL core */
+	oc_conf->opalcorebuf_sz = PAGE_ALIGN(hdr_size + cpu_notes_size);
+	oc_conf->opalcorebuf = alloc_pages_exact(oc_conf->opalcorebuf_sz,
+						 GFP_KERNEL | __GFP_ZERO);
+	if (!oc_conf->opalcorebuf) {
+		pr_err("Not enough memory to setup OPAL core (size: %lu)\n",
+		       oc_conf->opalcorebuf_sz);
+		oc_conf->opalcorebuf_sz = 0;
+		return -ENOMEM;
+	}
+	count = oc_conf->opalcorebuf_sz / PAGE_SIZE;
+	page = virt_to_page(oc_conf->opalcorebuf);
+	for (i = 0; i < count; i++)
+		mark_page_reserved(page + i);
+
+	pr_debug("opalcorebuf = 0x%llx\n", (u64)oc_conf->opalcorebuf);
+
+	/* Read OPAL related device-tree entries */
+	dn = of_find_node_by_name(NULL, "ibm,opal");
+	if (dn) {
+		ret = of_property_read_u64(dn, "opal-base-address",
+					   &opal_base_addr);
+		pr_debug("opal-base-address: %llx\n", opal_base_addr);
+		ret |= of_property_read_u64(dn, "opal-boot-address",
+					    &opal_boot_entry);
+		pr_debug("opal-boot-address: %llx\n", opal_boot_entry);
+	}
+	if (!dn || ret)
+		pr_warn("WARNING: Failed to read OPAL base & entry values\n");
+
+	/* Use count to keep track of the program headers */
+	count = 0;
+
+	bufp = oc_conf->opalcorebuf;
+	elf = (Elf64_Ehdr *)bufp;
+	bufp += sizeof(Elf64_Ehdr);
+	memcpy(elf->e_ident, ELFMAG, SELFMAG);
+	elf->e_ident[EI_CLASS] = ELF_CLASS;
+	elf->e_ident[EI_DATA] = ELFDATA2MSB;
+	elf->e_ident[EI_VERSION] = EV_CURRENT;
+	elf->e_ident[EI_OSABI] = ELF_OSABI;
+	memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
+	elf->e_type = cpu_to_be16(ET_CORE);
+	elf->e_machine = cpu_to_be16(ELF_ARCH);
+	elf->e_version = cpu_to_be32(EV_CURRENT);
+	elf->e_entry = 0;
+	elf->e_phoff = cpu_to_be64(sizeof(Elf64_Ehdr));
+	elf->e_shoff = 0;
+	elf->e_flags = 0;
+
+	elf->e_ehsize = cpu_to_be16(sizeof(Elf64_Ehdr));
+	elf->e_phentsize = cpu_to_be16(sizeof(Elf64_Phdr));
+	elf->e_phnum = 0;
+	elf->e_shentsize = 0;
+	elf->e_shnum = 0;
+	elf->e_shstrndx = 0;
+
+	phdr = (Elf64_Phdr *)bufp;
+	bufp += sizeof(Elf64_Phdr);
+	phdr->p_type	= cpu_to_be32(PT_NOTE);
+	phdr->p_flags	= 0;
+	phdr->p_align	= 0;
+	phdr->p_paddr	= phdr->p_vaddr = 0;
+	phdr->p_offset	= cpu_to_be64(hdr_size);
+	phdr->p_filesz	= phdr->p_memsz = cpu_to_be64(cpu_notes_size);
+	count++;
+
+	opalcore_off = oc_conf->opalcorebuf_sz;
+	oc_conf->ptload_phdr  = (Elf64_Phdr *)bufp;
+	paddr = 0;
+	for (i = 0; i < oc_conf->ptload_cnt; i++) {
+		phdr = (Elf64_Phdr *)bufp;
+		bufp += sizeof(Elf64_Phdr);
+		phdr->p_type	= cpu_to_be32(PT_LOAD);
+		phdr->p_flags	= cpu_to_be32(PF_R|PF_W|PF_X);
+		phdr->p_align	= 0;
+
+		new = get_new_element();
+		if (!new)
+			return -ENOMEM;
+		new->paddr  = oc_conf->ptload_addr[i];
+		new->size   = oc_conf->ptload_size[i];
+		new->offset = opalcore_off;
+		list_add_tail(&new->list, &opalcore_list);
+
+		phdr->p_paddr	= cpu_to_be64(paddr);
+		phdr->p_vaddr	= cpu_to_be64(opal_base_addr + paddr);
+		phdr->p_filesz	= phdr->p_memsz  =
+			cpu_to_be64(oc_conf->ptload_size[i]);
+		phdr->p_offset	= cpu_to_be64(opalcore_off);
+
+		count++;
+		opalcore_off += oc_conf->ptload_size[i];
+		paddr += oc_conf->ptload_size[i];
+	}
+
+	elf->e_phnum = cpu_to_be16(count);
+
+	bufp = (char *)opalcore_append_cpu_notes((Elf64_Word *)bufp);
+	bufp = (char *)auxv_to_elf64_notes((Elf64_Word *)bufp, opal_boot_entry);
+
+	oc_conf->opalcore_size = opalcore_off;
+	return 0;
+}
+
+static void opalcore_cleanup(void)
+{
+	if (oc_conf == NULL)
+		return;
+
+	/* Remove OPAL core sysfs file */
+	sysfs_remove_bin_file(opal_kobj, &opal_core_attr);
+	oc_conf->ptload_phdr = NULL;
+	oc_conf->ptload_cnt = 0;
+
+	/* free the buffer used for setting up OPAL core */
+	if (oc_conf->opalcorebuf) {
+		void *end = (void *)((u64)oc_conf->opalcorebuf +
+				     oc_conf->opalcorebuf_sz);
+
+		free_reserved_area(oc_conf->opalcorebuf, end, -1, NULL);
+		oc_conf->opalcorebuf = NULL;
+		oc_conf->opalcorebuf_sz = 0;
+	}
+
+	kfree(oc_conf);
+	oc_conf = NULL;
+}
+__exitcall(opalcore_cleanup);
+
+static void __init opalcore_config_init(void)
+{
+	u32 idx, cpu_data_version;
+	struct device_node *np;
+	const __be32 *prop;
+	u64 addr = 0;
+	int i, ret;
+
+	np = of_find_node_by_path("/ibm,opal/dump");
+	if (np == NULL)
+		return;
+
+	if (!of_device_is_compatible(np, "ibm,opal-dump")) {
+		pr_warn("Support missing for this f/w version!\n");
+		return;
+	}
+
+	/* Check if dump has been initiated on last reboot */
+	prop = of_get_property(np, "mpipl-boot", NULL);
+	if (!prop) {
+		of_node_put(np);
+		return;
+	}
+
+	/* Get OPAL metadata */
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_OPAL, &addr);
+	if ((ret != OPAL_SUCCESS) || !addr) {
+		pr_err("Failed to get OPAL metadata (%d)\n", ret);
+		goto error_out;
+	}
+
+	addr = be64_to_cpu(addr);
+	pr_debug("OPAL metadata addr: %llx\n", addr);
+	opalc_metadata = __va(addr);
+
+	/* Get OPAL CPU metadata */
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_CPU, &addr);
+	if ((ret != OPAL_SUCCESS) || !addr) {
+		pr_err("Failed to get OPAL CPU metadata (%d)\n", ret);
+		goto error_out;
+	}
+
+	addr = be64_to_cpu(addr);
+	pr_debug("CPU metadata addr: %llx\n", addr);
+	opalc_cpu_metadata = __va(addr);
+
+	/* Allocate memory for config buffer */
+	oc_conf = kzalloc(sizeof(struct opalcore_config), GFP_KERNEL);
+	if (oc_conf == NULL)
+		goto error_out;
+
+	/* Parse OPAL metadata */
+	if (opalc_metadata->version != OPAL_MPIPL_VERSION) {
+		pr_warn("Supported OPAL metadata version: %u, found: %u!\n",
+			OPAL_MPIPL_VERSION, opalc_metadata->version);
+		pr_warn("WARNING: F/W using newer OPAL metadata format!!\n");
+	}
+
+	oc_conf->ptload_cnt = 0;
+	idx = be32_to_cpu(opalc_metadata->region_cnt);
+	if (idx > MAX_PT_LOAD_CNT) {
+		pr_warn("WARNING: OPAL regions count (%d) adjusted to limit (%d)",
+			MAX_PT_LOAD_CNT, idx);
+		idx = MAX_PT_LOAD_CNT;
+	}
+	for (i = 0; i < idx; i++) {
+		oc_conf->ptload_addr[oc_conf->ptload_cnt] =
+				be64_to_cpu(opalc_metadata->region[i].dest);
+		oc_conf->ptload_size[oc_conf->ptload_cnt++] =
+				be64_to_cpu(opalc_metadata->region[i].size);
+	}
+	oc_conf->ptload_cnt = i;
+	oc_conf->crashing_cpu = be32_to_cpu(opalc_metadata->crashing_pir);
+
+	if (!oc_conf->ptload_cnt) {
+		pr_err("OPAL memory regions not found\n");
+		goto error_out;
+	}
+
+	/* Parse OPAL CPU metadata */
+	cpu_data_version = be32_to_cpu(opalc_cpu_metadata->cpu_data_version);
+	if (cpu_data_version != HDAT_FADUMP_CPU_DATA_VER) {
+		pr_warn("Supported CPU data version: %u, found: %u!\n",
+			HDAT_FADUMP_CPU_DATA_VER, cpu_data_version);
+		pr_warn("WARNING: F/W using newer CPU state data format!!\n");
+	}
+
+	addr = be64_to_cpu(opalc_cpu_metadata->region[0].dest);
+	if (!addr) {
+		pr_err("CPU state data not found!\n");
+		goto error_out;
+	}
+	oc_conf->cpu_state_destination_vaddr = (u64)__va(addr);
+
+	oc_conf->cpu_state_data_size =
+			be64_to_cpu(opalc_cpu_metadata->region[0].size);
+	oc_conf->cpu_state_entry_size =
+			be32_to_cpu(opalc_cpu_metadata->cpu_data_size);
+
+	if ((oc_conf->cpu_state_entry_size == 0) ||
+	    (oc_conf->cpu_state_entry_size > oc_conf->cpu_state_data_size)) {
+		pr_err("CPU state data is invalid.\n");
+		goto error_out;
+	}
+	oc_conf->num_cpus = (oc_conf->cpu_state_data_size /
+			     oc_conf->cpu_state_entry_size);
+
+	of_node_put(np);
+	return;
+
+error_out:
+	pr_err("Could not export /sys/firmware/opal/core\n");
+	opalcore_cleanup();
+	of_node_put(np);
+}
+
+static ssize_t fadump_release_opalcore_store(struct kobject *kobj,
+					     struct kobj_attribute *attr,
+					     const char *buf, size_t count)
+{
+	int input = -1;
+
+	if (kstrtoint(buf, 0, &input))
+		return -EINVAL;
+
+	if (input == 1) {
+		if (oc_conf == NULL) {
+			pr_err("'/sys/firmware/opal/core' file not accessible!\n");
+			return -EPERM;
+		}
+
+		/*
+		 * Take away '/sys/firmware/opal/core' and release all memory
+		 * used for exporting this file.
+		 */
+		opalcore_cleanup();
+	} else
+		return -EINVAL;
+
+	return count;
+}
+
+static struct kobj_attribute opalcore_rel_attr = __ATTR(fadump_release_opalcore,
+						0200, NULL,
+						fadump_release_opalcore_store);
+
+static int __init opalcore_init(void)
+{
+	int rc = -1;
+
+	opalcore_config_init();
+
+	if (oc_conf == NULL)
+		return rc;
+
+	create_opalcore();
+
+	/*
+	 * If oc_conf->opalcorebuf= is set in the 2nd kernel,
+	 * then capture the dump.
+	 */
+	if (!(is_opalcore_usable())) {
+		pr_err("Failed to export /sys/firmware/opal/core\n");
+		opalcore_cleanup();
+		return rc;
+	}
+
+	/* Set OPAL core file size */
+	opal_core_attr.size = oc_conf->opalcore_size;
+
+	/* Export OPAL core sysfs file */
+	rc = sysfs_create_bin_file(opal_kobj, &opal_core_attr);
+	if (rc != 0) {
+		pr_err("Failed to export /sys/firmware/opal/core\n");
+		opalcore_cleanup();
+		return rc;
+	}
+
+	rc = sysfs_create_file(kernel_kobj, &opalcore_rel_attr.attr);
+	if (rc) {
+		pr_warn("unable to create sysfs file fadump_release_opalcore (%d)\n",
+			rc);
+	}
+
+	return 0;
+}
+fs_initcall(opalcore_init);
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 1981438..543c816 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV OPAL Dump Interface
  *
  * Copyright 2013,2014 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kobject.h>
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index ba6e437..62ef7ad 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Error log support on PowerNV.
  *
  * Copyright 2013,2014 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
new file mode 100644
index 0000000..d361d37
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -0,0 +1,716 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Firmware-Assisted Dump support on POWER platform (OPAL).
+ *
+ * Copyright 2019, Hari Bathini, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "opal fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/seq_file.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/libfdt.h>
+#include <linux/mm.h>
+#include <linux/crash_dump.h>
+
+#include <asm/page.h>
+#include <asm/opal.h>
+#include <asm/fadump-internal.h>
+
+#include "opal-fadump.h"
+
+
+#ifdef CONFIG_PRESERVE_FA_DUMP
+/*
+ * When dump is active but PRESERVE_FA_DUMP is enabled on the kernel,
+ * ensure crash data is preserved in hope that the subsequent memory
+ * preserving kernel boot is going to process this crash data.
+ */
+void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
+{
+	const struct opal_fadump_mem_struct *opal_fdm_active;
+	const __be32 *prop;
+	unsigned long dn;
+	u64 addr = 0;
+	s64 ret;
+
+	dn = of_get_flat_dt_subnode_by_name(node, "dump");
+	if (dn == -FDT_ERR_NOTFOUND)
+		return;
+
+	/*
+	 * Check if dump has been initiated on last reboot.
+	 */
+	prop = of_get_flat_dt_prop(dn, "mpipl-boot", NULL);
+	if (!prop)
+		return;
+
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_KERNEL, &addr);
+	if ((ret != OPAL_SUCCESS) || !addr) {
+		pr_debug("Could not get Kernel metadata (%lld)\n", ret);
+		return;
+	}
+
+	/*
+	 * Preserve memory only if kernel memory regions are registered
+	 * with f/w for MPIPL.
+	 */
+	addr = be64_to_cpu(addr);
+	pr_debug("Kernel metadata addr: %llx\n", addr);
+	opal_fdm_active = (void *)addr;
+	if (opal_fdm_active->registered_regions == 0)
+		return;
+
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_BOOT_MEM, &addr);
+	if ((ret != OPAL_SUCCESS) || !addr) {
+		pr_err("Failed to get boot memory tag (%lld)\n", ret);
+		return;
+	}
+
+	/*
+	 * Memory below this address can be used for booting a
+	 * capture kernel or petitboot kernel. Preserve everything
+	 * above this address for processing crashdump.
+	 */
+	fadump_conf->boot_mem_top = be64_to_cpu(addr);
+	pr_debug("Preserve everything above %llx\n", fadump_conf->boot_mem_top);
+
+	pr_info("Firmware-assisted dump is active.\n");
+	fadump_conf->dump_active = 1;
+}
+
+#else /* CONFIG_PRESERVE_FA_DUMP */
+static const struct opal_fadump_mem_struct *opal_fdm_active;
+static const struct opal_mpipl_fadump *opal_cpu_metadata;
+static struct opal_fadump_mem_struct *opal_fdm;
+
+#ifdef CONFIG_OPAL_CORE
+extern bool kernel_initiated;
+#endif
+
+static int opal_fadump_unregister(struct fw_dump *fadump_conf);
+
+static void opal_fadump_update_config(struct fw_dump *fadump_conf,
+				      const struct opal_fadump_mem_struct *fdm)
+{
+	pr_debug("Boot memory regions count: %d\n", fdm->region_cnt);
+
+	/*
+	 * The destination address of the first boot memory region is the
+	 * destination address of boot memory regions.
+	 */
+	fadump_conf->boot_mem_dest_addr = fdm->rgn[0].dest;
+	pr_debug("Destination address of boot memory regions: %#016llx\n",
+		 fadump_conf->boot_mem_dest_addr);
+
+	fadump_conf->fadumphdr_addr = fdm->fadumphdr_addr;
+}
+
+/*
+ * This function is called in the capture kernel to get configuration details
+ * from metadata setup by the first kernel.
+ */
+static void opal_fadump_get_config(struct fw_dump *fadump_conf,
+				   const struct opal_fadump_mem_struct *fdm)
+{
+	unsigned long base, size, last_end, hole_size;
+	int i;
+
+	if (!fadump_conf->dump_active)
+		return;
+
+	last_end = 0;
+	hole_size = 0;
+	fadump_conf->boot_memory_size = 0;
+
+	pr_debug("Boot memory regions:\n");
+	for (i = 0; i < fdm->region_cnt; i++) {
+		base = fdm->rgn[i].src;
+		size = fdm->rgn[i].size;
+		pr_debug("\t[%03d] base: 0x%lx, size: 0x%lx\n", i, base, size);
+
+		fadump_conf->boot_mem_addr[i] = base;
+		fadump_conf->boot_mem_sz[i] = size;
+		fadump_conf->boot_memory_size += size;
+		hole_size += (base - last_end);
+
+		last_end = base + size;
+	}
+
+	/*
+	 * Start address of reserve dump area (permanent reservation) for
+	 * re-registering FADump after dump capture.
+	 */
+	fadump_conf->reserve_dump_area_start = fdm->rgn[0].dest;
+
+	/*
+	 * Rarely, but it can so happen that system crashes before all
+	 * boot memory regions are registered for MPIPL. In such
+	 * cases, warn that the vmcore may not be accurate and proceed
+	 * anyway as that is the best bet considering free pages, cache
+	 * pages, user pages, etc are usually filtered out.
+	 *
+	 * Hope the memory that could not be preserved only has pages
+	 * that are usually filtered out while saving the vmcore.
+	 */
+	if (fdm->region_cnt > fdm->registered_regions) {
+		pr_warn("Not all memory regions were saved!!!\n");
+		pr_warn("  Unsaved memory regions:\n");
+		i = fdm->registered_regions;
+		while (i < fdm->region_cnt) {
+			pr_warn("\t[%03d] base: 0x%llx, size: 0x%llx\n",
+				i, fdm->rgn[i].src, fdm->rgn[i].size);
+			i++;
+		}
+
+		pr_warn("If the unsaved regions only contain pages that are filtered out (eg. free/user pages), the vmcore should still be usable.\n");
+		pr_warn("WARNING: If the unsaved regions contain kernel pages, the vmcore will be corrupted.\n");
+	}
+
+	fadump_conf->boot_mem_top = (fadump_conf->boot_memory_size + hole_size);
+	fadump_conf->boot_mem_regs_cnt = fdm->region_cnt;
+	opal_fadump_update_config(fadump_conf, fdm);
+}
+
+/* Initialize kernel metadata */
+static void opal_fadump_init_metadata(struct opal_fadump_mem_struct *fdm)
+{
+	fdm->version = OPAL_FADUMP_VERSION;
+	fdm->region_cnt = 0;
+	fdm->registered_regions = 0;
+	fdm->fadumphdr_addr = 0;
+}
+
+static u64 opal_fadump_init_mem_struct(struct fw_dump *fadump_conf)
+{
+	u64 addr = fadump_conf->reserve_dump_area_start;
+	int i;
+
+	opal_fdm = __va(fadump_conf->kernel_metadata);
+	opal_fadump_init_metadata(opal_fdm);
+
+	/* Boot memory regions */
+	for (i = 0; i < fadump_conf->boot_mem_regs_cnt; i++) {
+		opal_fdm->rgn[i].src	= fadump_conf->boot_mem_addr[i];
+		opal_fdm->rgn[i].dest	= addr;
+		opal_fdm->rgn[i].size	= fadump_conf->boot_mem_sz[i];
+
+		opal_fdm->region_cnt++;
+		addr += fadump_conf->boot_mem_sz[i];
+	}
+
+	/*
+	 * Kernel metadata is passed to f/w and retrieved in capture kerenl.
+	 * So, use it to save fadump header address instead of calculating it.
+	 */
+	opal_fdm->fadumphdr_addr = (opal_fdm->rgn[0].dest +
+				    fadump_conf->boot_memory_size);
+
+	opal_fadump_update_config(fadump_conf, opal_fdm);
+
+	return addr;
+}
+
+static u64 opal_fadump_get_metadata_size(void)
+{
+	return PAGE_ALIGN(sizeof(struct opal_fadump_mem_struct));
+}
+
+static int opal_fadump_setup_metadata(struct fw_dump *fadump_conf)
+{
+	int err = 0;
+	s64 ret;
+
+	/*
+	 * Use the last page(s) in FADump memory reservation for
+	 * kernel metadata.
+	 */
+	fadump_conf->kernel_metadata = (fadump_conf->reserve_dump_area_start +
+					fadump_conf->reserve_dump_area_size -
+					opal_fadump_get_metadata_size());
+	pr_info("Kernel metadata addr: %llx\n", fadump_conf->kernel_metadata);
+
+	/* Initialize kernel metadata before registering the address with f/w */
+	opal_fdm = __va(fadump_conf->kernel_metadata);
+	opal_fadump_init_metadata(opal_fdm);
+
+	/*
+	 * Register metadata address with f/w. Can be retrieved in
+	 * the capture kernel.
+	 */
+	ret = opal_mpipl_register_tag(OPAL_MPIPL_TAG_KERNEL,
+				      fadump_conf->kernel_metadata);
+	if (ret != OPAL_SUCCESS) {
+		pr_err("Failed to set kernel metadata tag!\n");
+		err = -EPERM;
+	}
+
+	/*
+	 * Register boot memory top address with f/w. Should be retrieved
+	 * by a kernel that intends to preserve crash'ed kernel's memory.
+	 */
+	ret = opal_mpipl_register_tag(OPAL_MPIPL_TAG_BOOT_MEM,
+				      fadump_conf->boot_mem_top);
+	if (ret != OPAL_SUCCESS) {
+		pr_err("Failed to set boot memory tag!\n");
+		err = -EPERM;
+	}
+
+	return err;
+}
+
+static u64 opal_fadump_get_bootmem_min(void)
+{
+	return OPAL_FADUMP_MIN_BOOT_MEM;
+}
+
+static int opal_fadump_register(struct fw_dump *fadump_conf)
+{
+	s64 rc = OPAL_PARAMETER;
+	int i, err = -EIO;
+
+	for (i = 0; i < opal_fdm->region_cnt; i++) {
+		rc = opal_mpipl_update(OPAL_MPIPL_ADD_RANGE,
+				       opal_fdm->rgn[i].src,
+				       opal_fdm->rgn[i].dest,
+				       opal_fdm->rgn[i].size);
+		if (rc != OPAL_SUCCESS)
+			break;
+
+		opal_fdm->registered_regions++;
+	}
+
+	switch (rc) {
+	case OPAL_SUCCESS:
+		pr_info("Registration is successful!\n");
+		fadump_conf->dump_registered = 1;
+		err = 0;
+		break;
+	case OPAL_RESOURCE:
+		/* If MAX regions limit in f/w is hit, warn and proceed. */
+		pr_warn("%d regions could not be registered for MPIPL as MAX limit is reached!\n",
+			(opal_fdm->region_cnt - opal_fdm->registered_regions));
+		fadump_conf->dump_registered = 1;
+		err = 0;
+		break;
+	case OPAL_PARAMETER:
+		pr_err("Failed to register. Parameter Error(%lld).\n", rc);
+		break;
+	case OPAL_HARDWARE:
+		pr_err("Support not available.\n");
+		fadump_conf->fadump_supported = 0;
+		fadump_conf->fadump_enabled = 0;
+		break;
+	default:
+		pr_err("Failed to register. Unknown Error(%lld).\n", rc);
+		break;
+	}
+
+	/*
+	 * If some regions were registered before OPAL_MPIPL_ADD_RANGE
+	 * OPAL call failed, unregister all regions.
+	 */
+	if ((err < 0) && (opal_fdm->registered_regions > 0))
+		opal_fadump_unregister(fadump_conf);
+
+	return err;
+}
+
+static int opal_fadump_unregister(struct fw_dump *fadump_conf)
+{
+	s64 rc;
+
+	rc = opal_mpipl_update(OPAL_MPIPL_REMOVE_ALL, 0, 0, 0);
+	if (rc) {
+		pr_err("Failed to un-register - unexpected Error(%lld).\n", rc);
+		return -EIO;
+	}
+
+	opal_fdm->registered_regions = 0;
+	fadump_conf->dump_registered = 0;
+	return 0;
+}
+
+static int opal_fadump_invalidate(struct fw_dump *fadump_conf)
+{
+	s64 rc;
+
+	rc = opal_mpipl_update(OPAL_MPIPL_FREE_PRESERVED_MEMORY, 0, 0, 0);
+	if (rc) {
+		pr_err("Failed to invalidate - unexpected Error(%lld).\n", rc);
+		return -EIO;
+	}
+
+	fadump_conf->dump_active = 0;
+	opal_fdm_active = NULL;
+	return 0;
+}
+
+static void opal_fadump_cleanup(struct fw_dump *fadump_conf)
+{
+	s64 ret;
+
+	ret = opal_mpipl_register_tag(OPAL_MPIPL_TAG_KERNEL, 0);
+	if (ret != OPAL_SUCCESS)
+		pr_warn("Could not reset (%llu) kernel metadata tag!\n", ret);
+}
+
+/*
+ * Verify if CPU state data is available. If available, do a bit of sanity
+ * checking before processing this data.
+ */
+static bool __init is_opal_fadump_cpu_data_valid(struct fw_dump *fadump_conf)
+{
+	if (!opal_cpu_metadata)
+		return false;
+
+	fadump_conf->cpu_state_data_version =
+		be32_to_cpu(opal_cpu_metadata->cpu_data_version);
+	fadump_conf->cpu_state_entry_size =
+		be32_to_cpu(opal_cpu_metadata->cpu_data_size);
+	fadump_conf->cpu_state_dest_vaddr =
+		(u64)__va(be64_to_cpu(opal_cpu_metadata->region[0].dest));
+	fadump_conf->cpu_state_data_size =
+		be64_to_cpu(opal_cpu_metadata->region[0].size);
+
+	if (fadump_conf->cpu_state_data_version != HDAT_FADUMP_CPU_DATA_VER) {
+		pr_warn("Supported CPU state data version: %u, found: %d!\n",
+			HDAT_FADUMP_CPU_DATA_VER,
+			fadump_conf->cpu_state_data_version);
+		pr_warn("WARNING: F/W using newer CPU state data format!!\n");
+	}
+
+	if ((fadump_conf->cpu_state_dest_vaddr == 0) ||
+	    (fadump_conf->cpu_state_entry_size == 0) ||
+	    (fadump_conf->cpu_state_entry_size >
+	     fadump_conf->cpu_state_data_size)) {
+		pr_err("CPU state data is invalid. Ignoring!\n");
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Convert CPU state data saved at the time of crash into ELF notes.
+ *
+ * While the crashing CPU's register data is saved by the kernel, CPU state
+ * data for all CPUs is saved by f/w. In CPU state data provided by f/w,
+ * each register entry is of 16 bytes, a numerical identifier along with
+ * a GPR/SPR flag in the first 8 bytes and the register value in the next
+ * 8 bytes. For more details refer to F/W documentation. If this data is
+ * missing or in unsupported format, append crashing CPU's register data
+ * saved by the kernel in the PT_NOTE, to have something to work with in
+ * the vmcore file.
+ */
+static int __init
+opal_fadump_build_cpu_notes(struct fw_dump *fadump_conf,
+			    struct fadump_crash_info_header *fdh)
+{
+	u32 thread_pir, size_per_thread, regs_offset, regs_cnt, reg_esize;
+	struct hdat_fadump_thread_hdr *thdr;
+	bool is_cpu_data_valid = false;
+	u32 num_cpus = 1, *note_buf;
+	struct pt_regs regs;
+	char *bufp;
+	int rc, i;
+
+	if (is_opal_fadump_cpu_data_valid(fadump_conf)) {
+		size_per_thread = fadump_conf->cpu_state_entry_size;
+		num_cpus = (fadump_conf->cpu_state_data_size / size_per_thread);
+		bufp = __va(fadump_conf->cpu_state_dest_vaddr);
+		is_cpu_data_valid = true;
+	}
+
+	rc = fadump_setup_cpu_notes_buf(num_cpus);
+	if (rc != 0)
+		return rc;
+
+	note_buf = (u32 *)fadump_conf->cpu_notes_buf_vaddr;
+	if (!is_cpu_data_valid)
+		goto out;
+
+	/*
+	 * Offset for register entries, entry size and registers count is
+	 * duplicated in every thread header in keeping with HDAT format.
+	 * Use these values from the first thread header.
+	 */
+	thdr = (struct hdat_fadump_thread_hdr *)bufp;
+	regs_offset = (offsetof(struct hdat_fadump_thread_hdr, offset) +
+		       be32_to_cpu(thdr->offset));
+	reg_esize = be32_to_cpu(thdr->esize);
+	regs_cnt  = be32_to_cpu(thdr->ecnt);
+
+	pr_debug("--------CPU State Data------------\n");
+	pr_debug("NumCpus     : %u\n", num_cpus);
+	pr_debug("\tOffset: %u, Entry size: %u, Cnt: %u\n",
+		 regs_offset, reg_esize, regs_cnt);
+
+	for (i = 0; i < num_cpus; i++, bufp += size_per_thread) {
+		thdr = (struct hdat_fadump_thread_hdr *)bufp;
+
+		thread_pir = be32_to_cpu(thdr->pir);
+		pr_debug("[%04d] PIR: 0x%x, core state: 0x%02x\n",
+			 i, thread_pir, thdr->core_state);
+
+		/*
+		 * If this is kernel initiated crash, crashing_cpu would be set
+		 * appropriately and register data of the crashing CPU saved by
+		 * crashing kernel. Add this saved register data of crashing CPU
+		 * to elf notes and populate the pt_regs for the remaining CPUs
+		 * from register state data provided by firmware.
+		 */
+		if (fdh->crashing_cpu == thread_pir) {
+			note_buf = fadump_regs_to_elf_notes(note_buf,
+							    &fdh->regs);
+			pr_debug("Crashing CPU PIR: 0x%x - R1 : 0x%lx, NIP : 0x%lx\n",
+				 fdh->crashing_cpu, fdh->regs.gpr[1],
+				 fdh->regs.nip);
+			continue;
+		}
+
+		/*
+		 * Register state data of MAX cores is provided by firmware,
+		 * but some of this cores may not be active. So, while
+		 * processing register state data, check core state and
+		 * skip threads that belong to inactive cores.
+		 */
+		if (thdr->core_state == HDAT_FADUMP_CORE_INACTIVE)
+			continue;
+
+		opal_fadump_read_regs((bufp + regs_offset), regs_cnt,
+				      reg_esize, true, &regs);
+		note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
+		pr_debug("CPU PIR: 0x%x - R1 : 0x%lx, NIP : 0x%lx\n",
+			 thread_pir, regs.gpr[1], regs.nip);
+	}
+
+out:
+	/*
+	 * CPU state data is invalid/unsupported. Try appending crashing CPU's
+	 * register data, if it is saved by the kernel.
+	 */
+	if (fadump_conf->cpu_notes_buf_vaddr == (u64)note_buf) {
+		if (fdh->crashing_cpu == FADUMP_CPU_UNKNOWN) {
+			fadump_free_cpu_notes_buf();
+			return -ENODEV;
+		}
+
+		pr_warn("WARNING: appending only crashing CPU's register data\n");
+		note_buf = fadump_regs_to_elf_notes(note_buf, &(fdh->regs));
+	}
+
+	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));
+	return 0;
+}
+
+static int __init opal_fadump_process(struct fw_dump *fadump_conf)
+{
+	struct fadump_crash_info_header *fdh;
+	int rc = -EINVAL;
+
+	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
+	/*
+	 * If this is a kernel initiated crash, crashing_cpu would be set
+	 * appropriately and register data of the crashing CPU saved by
+	 * crashing kernel. Add this saved register data of crashing CPU
+	 * to elf notes and populate the pt_regs for the remaining CPUs
+	 * from register state data provided by firmware.
+	 */
+	if (fdh->crashing_cpu != FADUMP_CPU_UNKNOWN)
+		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;
+}
+
+static void opal_fadump_region_show(struct fw_dump *fadump_conf,
+				    struct seq_file *m)
+{
+	const struct opal_fadump_mem_struct *fdm_ptr;
+	u64 dumped_bytes = 0;
+	int i;
+
+	if (fadump_conf->dump_active)
+		fdm_ptr = opal_fdm_active;
+	else
+		fdm_ptr = opal_fdm;
+
+	for (i = 0; i < fdm_ptr->region_cnt; i++) {
+		/*
+		 * Only regions that are registered for MPIPL
+		 * would have dump data.
+		 */
+		if ((fadump_conf->dump_active) &&
+		    (i < fdm_ptr->registered_regions))
+			dumped_bytes = fdm_ptr->rgn[i].size;
+
+		seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ",
+			   fdm_ptr->rgn[i].src, fdm_ptr->rgn[i].dest);
+		seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n",
+			   fdm_ptr->rgn[i].size, dumped_bytes);
+	}
+
+	/* Dump is active. Show reserved area start address. */
+	if (fadump_conf->dump_active) {
+		seq_printf(m, "\nMemory above %#016lx is reserved for saving crash dump\n",
+			   fadump_conf->reserve_dump_area_start);
+	}
+}
+
+static void opal_fadump_trigger(struct fadump_crash_info_header *fdh,
+				const char *msg)
+{
+	int rc;
+
+	/*
+	 * Unlike on pSeries platform, logical CPU number is not provided
+	 * with architected register state data. So, store the crashing
+	 * CPU's PIR instead to plug the appropriate register data for
+	 * crashing CPU in the vmcore file.
+	 */
+	fdh->crashing_cpu = (u32)mfspr(SPRN_PIR);
+
+	rc = opal_cec_reboot2(OPAL_REBOOT_MPIPL, msg);
+	if (rc == OPAL_UNSUPPORTED) {
+		pr_emerg("Reboot type %d not supported.\n",
+			 OPAL_REBOOT_MPIPL);
+	} else if (rc == OPAL_HARDWARE)
+		pr_emerg("No backend support for MPIPL!\n");
+}
+
+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,
+	.fadump_setup_metadata		= opal_fadump_setup_metadata,
+	.fadump_get_bootmem_min		= opal_fadump_get_bootmem_min,
+	.fadump_register		= opal_fadump_register,
+	.fadump_unregister		= opal_fadump_unregister,
+	.fadump_invalidate		= opal_fadump_invalidate,
+	.fadump_cleanup			= opal_fadump_cleanup,
+	.fadump_process			= opal_fadump_process,
+	.fadump_region_show		= opal_fadump_region_show,
+	.fadump_trigger			= opal_fadump_trigger,
+};
+
+void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
+{
+	const __be32 *prop;
+	unsigned long dn;
+	u64 addr = 0;
+	int i, len;
+	s64 ret;
+
+	/*
+	 * Check if Firmware-Assisted Dump is supported. if yes, check
+	 * if dump has been initiated on last reboot.
+	 */
+	dn = of_get_flat_dt_subnode_by_name(node, "dump");
+	if (dn == -FDT_ERR_NOTFOUND) {
+		pr_debug("FADump support is missing!\n");
+		return;
+	}
+
+	if (!of_flat_dt_is_compatible(dn, "ibm,opal-dump")) {
+		pr_err("Support missing for this f/w version!\n");
+		return;
+	}
+
+	prop = of_get_flat_dt_prop(dn, "fw-load-area", &len);
+	if (prop) {
+		/*
+		 * Each f/w load area is an (address,size) pair,
+		 * 2 cells each, totalling 4 cells per range.
+		 */
+		for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+			u64 base, end;
+
+			base = of_read_number(prop + (i * 4) + 0, 2);
+			end = base;
+			end += of_read_number(prop + (i * 4) + 2, 2);
+			if (end > OPAL_FADUMP_MIN_BOOT_MEM) {
+				pr_err("F/W load area: 0x%llx-0x%llx\n",
+				       base, end);
+				pr_err("F/W version not supported!\n");
+				return;
+			}
+		}
+	}
+
+	fadump_conf->ops		= &opal_fadump_ops;
+	fadump_conf->fadump_supported	= 1;
+
+	/*
+	 * Firmware supports 32-bit field for size. Align it to PAGE_SIZE
+	 * and request firmware to copy multiple kernel boot memory regions.
+	 */
+	fadump_conf->max_copy_size = _ALIGN_DOWN(U32_MAX, PAGE_SIZE);
+
+	/*
+	 * Check if dump has been initiated on last reboot.
+	 */
+	prop = of_get_flat_dt_prop(dn, "mpipl-boot", NULL);
+	if (!prop)
+		return;
+
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_KERNEL, &addr);
+	if ((ret != OPAL_SUCCESS) || !addr) {
+		pr_err("Failed to get Kernel metadata (%lld)\n", ret);
+		return;
+	}
+
+	addr = be64_to_cpu(addr);
+	pr_debug("Kernel metadata addr: %llx\n", addr);
+
+	opal_fdm_active = __va(addr);
+	if (opal_fdm_active->version != OPAL_FADUMP_VERSION) {
+		pr_warn("Supported kernel metadata version: %u, found: %d!\n",
+			OPAL_FADUMP_VERSION, opal_fdm_active->version);
+		pr_warn("WARNING: Kernel metadata format mismatch identified! Core file maybe corrupted..\n");
+	}
+
+	/* Kernel regions not registered with f/w for MPIPL */
+	if (opal_fdm_active->registered_regions == 0) {
+		opal_fdm_active = NULL;
+		return;
+	}
+
+	ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_CPU, &addr);
+	if (addr) {
+		addr = be64_to_cpu(addr);
+		pr_debug("CPU metadata addr: %llx\n", addr);
+		opal_cpu_metadata = __va(addr);
+	}
+
+	pr_info("Firmware-assisted dump is active.\n");
+	fadump_conf->dump_active = 1;
+	opal_fadump_get_config(fadump_conf, opal_fdm_active);
+}
+#endif /* !CONFIG_PRESERVE_FA_DUMP */
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h
new file mode 100644
index 0000000..f1e9ecf
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-fadump.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Firmware-Assisted Dump support on POWER platform (OPAL).
+ *
+ * Copyright 2019, Hari Bathini, IBM Corporation.
+ */
+
+#ifndef _POWERNV_OPAL_FADUMP_H
+#define _POWERNV_OPAL_FADUMP_H
+
+#include <asm/reg.h>
+
+/*
+ * With kernel & initrd loaded at 512MB (with 256MB size), enforce a minimum
+ * boot memory size of 768MB to ensure f/w loading kernel and initrd doesn't
+ * mess with crash'ed kernel's memory during MPIPL.
+ */
+#define OPAL_FADUMP_MIN_BOOT_MEM		(0x30000000UL)
+
+/*
+ * OPAL FADump metadata structure format version
+ *
+ * OPAL FADump kernel metadata structure stores kernel metadata needed to
+ * register-for/process crash dump. Format version is used to keep a tab on
+ * the changes in the structure format. The changes, if any, to the format
+ * are expected to be minimal and backward compatible.
+ */
+#define OPAL_FADUMP_VERSION			0x1
+
+/*
+ * OPAL FADump kernel metadata
+ *
+ * The address of this structure will be registered with f/w for retrieving
+ * and processing during crash dump.
+ */
+struct opal_fadump_mem_struct {
+	u8	version;
+	u8	reserved[3];
+	u16	region_cnt;		/* number of regions */
+	u16	registered_regions;	/* Regions registered for MPIPL */
+	u64	fadumphdr_addr;
+	struct opal_mpipl_region	rgn[FADUMP_MAX_MEM_REGS];
+} __packed;
+
+/*
+ * CPU state data
+ *
+ * CPU state data information is provided by f/w. The format for this data
+ * is defined in the HDAT spec. Version is used to keep a tab on the changes
+ * in this CPU state data format. Changes to this format are unlikely, but
+ * if there are any changes, please refer to latest HDAT specification.
+ */
+#define HDAT_FADUMP_CPU_DATA_VER		1
+
+#define HDAT_FADUMP_CORE_INACTIVE		(0x0F)
+
+/* HDAT thread header for register entries */
+struct hdat_fadump_thread_hdr {
+	__be32  pir;
+	/* 0x00 - 0x0F - The corresponding stop state of the core */
+	u8      core_state;
+	u8      reserved[3];
+
+	__be32	offset;	/* Offset to Register Entries array */
+	__be32	ecnt;	/* Number of entries */
+	__be32	esize;	/* Alloc size of each array entry in bytes */
+	__be32	eactsz;	/* Actual size of each array entry in bytes */
+} __packed;
+
+/* Register types populated by f/w */
+#define HDAT_FADUMP_REG_TYPE_GPR		0x01
+#define HDAT_FADUMP_REG_TYPE_SPR		0x02
+
+/* ID numbers used by f/w while populating certain registers */
+#define HDAT_FADUMP_REG_ID_NIP			0x7D0
+#define HDAT_FADUMP_REG_ID_MSR			0x7D1
+#define HDAT_FADUMP_REG_ID_CCR			0x7D2
+
+/* HDAT register entry. */
+struct hdat_fadump_reg_entry {
+	__be32		reg_type;
+	__be32		reg_num;
+	__be64		reg_val;
+} __packed;
+
+static inline void opal_fadump_set_regval_regnum(struct pt_regs *regs,
+						 u32 reg_type, u32 reg_num,
+						 u64 reg_val)
+{
+	if (reg_type == HDAT_FADUMP_REG_TYPE_GPR) {
+		if (reg_num < 32)
+			regs->gpr[reg_num] = reg_val;
+		return;
+	}
+
+	switch (reg_num) {
+	case SPRN_CTR:
+		regs->ctr = reg_val;
+		break;
+	case SPRN_LR:
+		regs->link = reg_val;
+		break;
+	case SPRN_XER:
+		regs->xer = reg_val;
+		break;
+	case SPRN_DAR:
+		regs->dar = reg_val;
+		break;
+	case SPRN_DSISR:
+		regs->dsisr = reg_val;
+		break;
+	case HDAT_FADUMP_REG_ID_NIP:
+		regs->nip = reg_val;
+		break;
+	case HDAT_FADUMP_REG_ID_MSR:
+		regs->msr = reg_val;
+		break;
+	case HDAT_FADUMP_REG_ID_CCR:
+		regs->ccr = reg_val;
+		break;
+	}
+}
+
+static inline void opal_fadump_read_regs(char *bufp, unsigned int regs_cnt,
+					 unsigned int reg_entry_size,
+					 bool cpu_endian,
+					 struct pt_regs *regs)
+{
+	struct hdat_fadump_reg_entry *reg_entry;
+	u64 val;
+	int i;
+
+	memset(regs, 0, sizeof(struct pt_regs));
+
+	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) :
+		       reg_entry->reg_val);
+		opal_fadump_set_regval_regnum(regs,
+					      be32_to_cpu(reg_entry->reg_type),
+					      be32_to_cpu(reg_entry->reg_num),
+					      val);
+	}
+}
+
+#endif /* _POWERNV_OPAL_FADUMP_H */
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index b370151..7e7d38b 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV OPAL Firmware Update Interface
  *
  * Copyright 2013 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define DEBUG
diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c
index 586ec71..3e1f064 100644
--- a/arch/powerpc/platforms/powernv/opal-hmi.c
+++ b/arch/powerpc/platforms/powernv/opal-hmi.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * OPAL hypervisor Maintenance interrupt handling support in PowerNV.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; If not, see <http://www.gnu.org/licenses/>.
- *
  * Copyright 2014 IBM Corporation
  * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
  */
@@ -149,6 +137,43 @@
 					xstop_reason[i].description);
 }
 
+static void print_npu_checkstop_reason(const char *level,
+					struct OpalHMIEvent *hmi_evt)
+{
+	uint8_t reason, reason_count, i;
+
+	/*
+	 * We may not have a checkstop reason on some combination of
+	 * hardware and/or skiboot version
+	 */
+	if (!hmi_evt->u.xstop_error.xstop_reason) {
+		printk("%s	NPU checkstop on chip %x\n", level,
+			be32_to_cpu(hmi_evt->u.xstop_error.u.chip_id));
+		return;
+	}
+
+	/*
+	 * NPU2 has 3 FIRs. Reason encoded on a byte as:
+	 *   2 bits for the FIR number
+	 *   6 bits for the bit number
+	 * It may be possible to find several reasons.
+	 *
+	 * We don't display a specific message per FIR bit as there
+	 * are too many and most are meaningless without the workbook
+	 * and/or hw team help anyway.
+	 */
+	reason_count = sizeof(hmi_evt->u.xstop_error.xstop_reason) /
+		sizeof(reason);
+	for (i = 0; i < reason_count; i++) {
+		reason = (hmi_evt->u.xstop_error.xstop_reason >> (8 * i)) & 0xFF;
+		if (reason)
+			printk("%s	NPU checkstop on chip %x: FIR%d bit %d is set\n",
+				level,
+				be32_to_cpu(hmi_evt->u.xstop_error.u.chip_id),
+				reason >> 6, reason & 0x3F);
+	}
+}
+
 static void print_checkstop_reason(const char *level,
 					struct OpalHMIEvent *hmi_evt)
 {
@@ -160,6 +185,9 @@
 	case CHECKSTOP_TYPE_NX:
 		print_nx_checkstop_reason(level, hmi_evt);
 		break;
+	case CHECKSTOP_TYPE_NPU:
+		print_npu_checkstop_reason(level, hmi_evt);
+		break;
 	default:
 		printk("%s	Unknown Malfunction Alert of type %d\n",
 		       level, type);
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
index 58a0794..e04b206 100644
--- a/arch/powerpc/platforms/powernv/opal-imc.c
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * OPAL IMC interface detection driver
  * Supported on POWERNV platform
@@ -5,11 +6,6 @@
  * Copyright	(C) 2017 Madhavan Srinivasan, IBM Corporation.
  *		(C) 2017 Anju T Sudhakar, IBM Corporation.
  *		(C) 2017 Hemant K Shaw, IBM 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; either version
- * 2 of the License, or later version.
  */
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
@@ -57,9 +53,9 @@
 				    struct imc_pmu *pmu_ptr)
 {
 	static u64 loc, *imc_mode_addr, *imc_cmd_addr;
-	int chip = 0, nid;
 	char mode[16], cmd[16];
 	u32 cb_offset;
+	struct imc_mem_info *ptr = pmu_ptr->mem_info;
 
 	imc_debugfs_parent = debugfs_create_dir("imc", powerpc_debugfs_root);
 
@@ -73,20 +69,20 @@
 	if (of_property_read_u32(node, "cb_offset", &cb_offset))
 		cb_offset = IMC_CNTL_BLK_OFFSET;
 
-	for_each_node(nid) {
-		loc = (u64)(pmu_ptr->mem_info[chip].vbase) + cb_offset;
+	while (ptr->vbase != NULL) {
+		loc = (u64)(ptr->vbase) + cb_offset;
 		imc_mode_addr = (u64 *)(loc + IMC_CNTL_BLK_MODE_OFFSET);
-		sprintf(mode, "imc_mode_%d", nid);
+		sprintf(mode, "imc_mode_%d", (u32)(ptr->id));
 		if (!imc_debugfs_create_x64(mode, 0600, imc_debugfs_parent,
 					    imc_mode_addr))
 			goto err;
 
 		imc_cmd_addr = (u64 *)(loc + IMC_CNTL_BLK_CMD_OFFSET);
-		sprintf(cmd, "imc_cmd_%d", nid);
+		sprintf(cmd, "imc_cmd_%d", (u32)(ptr->id));
 		if (!imc_debugfs_create_x64(cmd, 0600, imc_debugfs_parent,
 					    imc_cmd_addr))
 			goto err;
-		chip++;
+		ptr++;
 	}
 	return;
 
@@ -127,7 +123,7 @@
 								nr_chips))
 		goto error;
 
-	pmu_ptr->mem_info = kcalloc(nr_chips, sizeof(*pmu_ptr->mem_info),
+	pmu_ptr->mem_info = kcalloc(nr_chips + 1, sizeof(*pmu_ptr->mem_info),
 				    GFP_KERNEL);
 	if (!pmu_ptr->mem_info)
 		goto error;
@@ -161,6 +157,10 @@
 	struct imc_pmu *pmu_ptr;
 	u32 offset;
 
+	/* Return for unknown domain */
+	if (domain < 0)
+		return -EINVAL;
+
 	/* memory for pmu */
 	pmu_ptr = kzalloc(sizeof(*pmu_ptr), GFP_KERNEL);
 	if (!pmu_ptr)
@@ -284,6 +284,9 @@
 		case IMC_TYPE_THREAD:
 			domain = IMC_DOMAIN_THREAD;
 			break;
+		case IMC_TYPE_TRACE:
+			domain = IMC_DOMAIN_TRACE;
+			break;
 		default:
 			pr_warn("IMC Unknown Device type \n");
 			domain = -1;
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index bc97770..c164419 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This file implements an irqchip for OPAL events. Whenever there is
  * an interrupt that is handled by OPAL we get passed a list of events
@@ -5,11 +6,6 @@
  * interrupts to Linux so we implement an irqchip to handle them.
  *
  * Copyright Alistair Popple, IBM Corporation 2014.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #include <linux/bitops.h>
 #include <linux/irq.h>
diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c
index 5569195..6c3bc4b 100644
--- a/arch/powerpc/platforms/powernv/opal-kmsg.c
+++ b/arch/powerpc/platforms/powernv/opal-kmsg.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * kmsg dumper that ensures the OPAL console fully flushes panic messages
  *
  * Author: Russell Currey <ruscur@russell.cc>
  *
  * Copyright 2015 IBM 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; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 #include <linux/kmsg_dump.h>
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index 6c7ad1d..6085690 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV LPC bus handling.
  *
  * Copyright 2013 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -192,7 +188,7 @@
 	u32 data, pos, len, todo;
 	int rc;
 
-	if (!access_ok(VERIFY_WRITE, ubuf, count))
+	if (!access_ok(ubuf, count))
 		return -EFAULT;
 
 	todo = count;
@@ -283,7 +279,7 @@
 	u32 data, pos, len, todo;
 	int rc;
 
-	if (!access_ok(VERIFY_READ, ubuf, count))
+	if (!access_ok(ubuf, count))
 		return -EFAULT;
 
 	todo = count;
diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c
index dcb42bc..1e8e17d 100644
--- a/arch/powerpc/platforms/powernv/opal-memory-errors.c
+++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * OPAL asynchronus Memory error handling support in PowerNV.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  * Copyright 2013 IBM Corporation
  * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
  */
diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c
index acd3206..d26da19 100644
--- a/arch/powerpc/platforms/powernv/opal-msglog.c
+++ b/arch/powerpc/platforms/powernv/opal-msglog.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV OPAL in-memory console interface
  *
  * Copyright 2014 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/io.h>
@@ -33,23 +29,23 @@
 
 static struct memcons *opal_memcons = NULL;
 
-ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
+ssize_t memcons_copy(struct memcons *mc, char *to, loff_t pos, size_t count)
 {
 	const char *conbuf;
 	ssize_t ret;
 	size_t first_read = 0;
 	uint32_t out_pos, avail;
 
-	if (!opal_memcons)
+	if (!mc)
 		return -ENODEV;
 
-	out_pos = be32_to_cpu(READ_ONCE(opal_memcons->out_pos));
+	out_pos = be32_to_cpu(READ_ONCE(mc->out_pos));
 
 	/* Now we've read out_pos, put a barrier in before reading the new
 	 * data it points to in conbuf. */
 	smp_rmb();
 
-	conbuf = phys_to_virt(be64_to_cpu(opal_memcons->obuf_phys));
+	conbuf = phys_to_virt(be64_to_cpu(mc->obuf_phys));
 
 	/* When the buffer has wrapped, read from the out_pos marker to the end
 	 * of the buffer, and then read the remaining data as in the un-wrapped
@@ -57,7 +53,7 @@
 	if (out_pos & MEMCONS_OUT_POS_WRAP) {
 
 		out_pos &= MEMCONS_OUT_POS_MASK;
-		avail = be32_to_cpu(opal_memcons->obuf_size) - out_pos;
+		avail = be32_to_cpu(mc->obuf_size) - out_pos;
 
 		ret = memory_read_from_buffer(to, count, &pos,
 				conbuf + out_pos, avail);
@@ -75,7 +71,7 @@
 	}
 
 	/* Sanity check. The firmware should not do this to us. */
-	if (out_pos > be32_to_cpu(opal_memcons->obuf_size)) {
+	if (out_pos > be32_to_cpu(mc->obuf_size)) {
 		pr_err("OPAL: memory console corruption. Aborting read.\n");
 		return -EINVAL;
 	}
@@ -90,6 +86,11 @@
 	return ret;
 }
 
+ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
+{
+	return memcons_copy(opal_memcons, to, pos, count);
+}
+
 static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj,
 				struct bin_attribute *bin_attr, char *to,
 				loff_t pos, size_t count)
@@ -98,36 +99,52 @@
 }
 
 static struct bin_attribute opal_msglog_attr = {
-	.attr = {.name = "msglog", .mode = 0444},
+	.attr = {.name = "msglog", .mode = 0400},
 	.read = opal_msglog_read
 };
 
-void __init opal_msglog_init(void)
+struct memcons *memcons_init(struct device_node *node, const char *mc_prop_name)
 {
 	u64 mcaddr;
 	struct memcons *mc;
 
-	if (of_property_read_u64(opal_node, "ibm,opal-memcons", &mcaddr)) {
-		pr_warn("OPAL: Property ibm,opal-memcons not found, no message log\n");
-		return;
+	if (of_property_read_u64(node, mc_prop_name, &mcaddr)) {
+		pr_warn("%s property not found, no message log\n",
+			mc_prop_name);
+		goto out_err;
 	}
 
 	mc = phys_to_virt(mcaddr);
 	if (!mc) {
-		pr_warn("OPAL: memory console address is invalid\n");
-		return;
+		pr_warn("memory console address is invalid\n");
+		goto out_err;
 	}
 
 	if (be64_to_cpu(mc->magic) != MEMCONS_MAGIC) {
-		pr_warn("OPAL: memory console version is invalid\n");
+		pr_warn("memory console version is invalid\n");
+		goto out_err;
+	}
+
+	return mc;
+
+out_err:
+	return NULL;
+}
+
+u32 memcons_get_size(struct memcons *mc)
+{
+	return be32_to_cpu(mc->ibuf_size) + be32_to_cpu(mc->obuf_size);
+}
+
+void __init opal_msglog_init(void)
+{
+	opal_memcons = memcons_init(opal_node, "ibm,opal-memcons");
+	if (!opal_memcons) {
+		pr_warn("OPAL: memcons failed to load from ibm,opal-memcons\n");
 		return;
 	}
 
-	/* Report maximum size */
-	opal_msglog_attr.size =  be32_to_cpu(mc->ibuf_size) +
-		be32_to_cpu(mc->obuf_size);
-
-	opal_memcons = mc;
+	opal_msglog_attr.size = memcons_get_size(opal_memcons);
 }
 
 void __init opal_msglog_sysfs_init(void)
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
index 5584247..380bc2d 100644
--- a/arch/powerpc/platforms/powernv/opal-nvram.c
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV nvram code.
  *
  * Copyright 2011 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define DEBUG
diff --git a/arch/powerpc/platforms/powernv/opal-power.c b/arch/powerpc/platforms/powernv/opal-power.c
index 58dc330..2a3717f 100644
--- a/arch/powerpc/platforms/powernv/opal-power.c
+++ b/arch/powerpc/platforms/powernv/opal-power.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV OPAL power control for graceful shutdown handling
  *
  * Copyright 2015 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)	"opal-power: "	fmt
@@ -138,7 +134,7 @@
 	.priority	= 0,
 };
 
-static int __init opal_power_control_init(void)
+int __init opal_power_control_init(void)
 {
 	int ret, supported = 0;
 	struct device_node *np;
@@ -176,4 +172,3 @@
 
 	return 0;
 }
-machine_subsys_initcall(powernv, opal_power_control_init);
diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c
index badb29b..dc599e7 100644
--- a/arch/powerpc/platforms/powernv/opal-powercap.c
+++ b/arch/powerpc/platforms/powernv/opal-powercap.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV OPAL Powercap interface
  *
  * Copyright 2017 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)     "opal-powercap: " fmt
@@ -199,7 +195,7 @@
 		}
 
 		j = 0;
-		pcaps[i].pg.name = node->name;
+		pcaps[i].pg.name = kasprintf(GFP_KERNEL, "%pOFn", node);
 		if (has_min) {
 			powercap_add_attr(min, "powercap-min",
 					  &pcaps[i].pattrs[j]);
@@ -237,6 +233,7 @@
 	while (--i >= 0) {
 		kfree(pcaps[i].pattrs);
 		kfree(pcaps[i].pg.attrs);
+		kfree(pcaps[i].pg.name);
 	}
 	kobject_put(powercap_kobj);
 out_pcaps:
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index 4070bb4..45f4223 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * OPAL Runtime Diagnostics interface driver
  * Supported on POWERNV platform
  *
  * Copyright IBM Corporation 2015
- *
- * 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.
  */
 
 #define pr_fmt(fmt) "opal-prd: " fmt
@@ -350,7 +342,7 @@
 	int msg_size, item_size;
 	unsigned long flags;
 
-	if (msg_type != OPAL_MSG_PRD)
+	if (msg_type != OPAL_MSG_PRD && msg_type != OPAL_MSG_PRD2)
 		return 0;
 
 	/* Calculate total size of the message and item we need to store. The
@@ -401,6 +393,12 @@
 		return rc;
 	}
 
+	rc = opal_message_notifier_register(OPAL_MSG_PRD2, &opal_prd_event_nb);
+	if (rc) {
+		pr_err("Couldn't register PRD2 event notifier\n");
+		return rc;
+	}
+
 	rc = misc_register(&opal_prd_dev);
 	if (rc) {
 		pr_err("failed to register miscdev\n");
diff --git a/arch/powerpc/platforms/powernv/opal-psr.c b/arch/powerpc/platforms/powernv/opal-psr.c
index 74986b3..b6ccb30 100644
--- a/arch/powerpc/platforms/powernv/opal-psr.c
+++ b/arch/powerpc/platforms/powernv/opal-psr.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV OPAL Power-Shift-Ratio interface
  *
  * Copyright 2017 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)     "opal-psr: " fmt
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index 42ec642..44d7dac 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV Real Time Clock.
  *
  * Copyright 2011 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 
diff --git a/arch/powerpc/platforms/powernv/opal-sensor-groups.c b/arch/powerpc/platforms/powernv/opal-sensor-groups.c
index f7d04b6..31f13c1 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor-groups.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor-groups.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV OPAL Sensor-groups interface
  *
  * Copyright 2017 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)     "opal-sensor-groups: " fmt
@@ -214,9 +210,9 @@
 		}
 
 		if (!of_property_read_u32(node, "ibm,chip-id", &chipid))
-			sprintf(sgs[i].name, "%s%d", node->name, chipid);
+			sprintf(sgs[i].name, "%pOFn%d", node, chipid);
 		else
-			sprintf(sgs[i].name, "%s", node->name);
+			sprintf(sgs[i].name, "%pOFn", node);
 
 		sgs[i].sg.name = sgs[i].name;
 		if (add_attr_group(ops, len, &sgs[i], sgid)) {
diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
index 35a5f4b..3192c61 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV sensor code
  *
  * Copyright (C) 2013 IBM
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/delay.h>
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index 9aa87df..a12312a 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV system parameter code
  *
  * Copyright (C) 2013 IBM
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kobject.h>
@@ -194,7 +181,7 @@
 	count = of_property_count_strings(sysparam, "param-name");
 	if (count < 0) {
 		pr_err("SYSPARAM: No string found of property param-name in "
-				"the node %s\n", sysparam->name);
+				"the node %pOFn\n", sysparam);
 		goto out_param_buf;
 	}
 
diff --git a/arch/powerpc/platforms/powernv/opal-tracepoints.c b/arch/powerpc/platforms/powernv/opal-tracepoints.c
index 1ab7d26..f16a435 100644
--- a/arch/powerpc/platforms/powernv/opal-tracepoints.c
+++ b/arch/powerpc/platforms/powernv/opal-tracepoints.c
@@ -4,7 +4,7 @@
 #include <asm/trace.h>
 #include <asm/asm-prototypes.h>
 
-#ifdef HAVE_JUMP_LABEL
+#ifdef CONFIG_JUMP_LABEL
 struct static_key opal_tracepoint_key = STATIC_KEY_INIT;
 
 int opal_tracepoint_regfunc(void)
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 2515282..e5acc33 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * PowerNV OPAL API wrappers
  *
  * Copyright 2011 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/jump_label.h>
@@ -17,317 +13,51 @@
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
-	.section	".text"
-
-#ifdef CONFIG_TRACEPOINTS
-#ifdef HAVE_JUMP_LABEL
-#define OPAL_BRANCH(LABEL)					\
-	ARCH_STATIC_BRANCH(LABEL, opal_tracepoint_key)
-#else
-
-	.section	".toc","aw"
-
-	.globl opal_tracepoint_refcount
-opal_tracepoint_refcount:
-	.8byte	0
-
-	.section	".text"
+	.section ".text"
 
 /*
- * We branch around this in early init by using an unconditional cpu
- * feature.
+ * r3-r10		- OPAL call arguments
+ * STK_PARAM(R11)	- OPAL opcode
+ * STK_PARAM(R12)	- MSR to restore
  */
-#define OPAL_BRANCH(LABEL)					\
-BEGIN_FTR_SECTION;						\
-	b	1f;						\
-END_FTR_SECTION(0, 1);						\
-	ld	r11,opal_tracepoint_refcount@toc(r2);		\
-	cmpdi	r11,0;						\
-	bne-	LABEL;						\
-1:
-
-#endif
-
-#else
-#define OPAL_BRANCH(LABEL)
-#endif
-
-/*
- * DO_OPAL_CALL assumes:
- * r0  = opal call token
- * r12 = msr
- * LR has been saved
- */
-#define DO_OPAL_CALL()			\
-	mfcr	r11;			\
-	stw	r11,8(r1);		\
-	li	r11,0;			\
-	ori	r11,r11,MSR_EE;		\
-	std	r12,PACASAVEDMSR(r13);	\
-	andc	r12,r12,r11;		\
-	mtmsrd	r12,1;			\
-	LOAD_REG_ADDR(r11,opal_return);	\
-	mtlr	r11;			\
-	li	r11,MSR_DR|MSR_IR|MSR_LE;\
-	andc	r12,r12,r11;		\
-	mtspr	SPRN_HSRR1,r12;		\
-	LOAD_REG_ADDR(r11,opal);	\
-	ld	r12,8(r11);		\
-	ld	r2,0(r11);		\
-	mtspr	SPRN_HSRR0,r12;		\
+_GLOBAL_TOC(__opal_call)
+	mflr	r0
+	std	r0,PPC_LR_STKOFF(r1)
+	ld	r12,STK_PARAM(R12)(r1)
+	li	r0,MSR_IR|MSR_DR|MSR_LE
+	andc	r12,r12,r0
+	LOAD_REG_ADDR(r11, opal_return)
+	mtlr	r11
+	LOAD_REG_ADDR(r11, opal)
+	ld	r2,0(r11)
+	ld	r11,8(r11)
+	mtspr	SPRN_HSRR0,r11
+	mtspr	SPRN_HSRR1,r12
+	/* set token to r0 */
+	ld	r0,STK_PARAM(R11)(r1)
 	hrfid
-
-#define OPAL_CALL(name, token)		\
- _GLOBAL_TOC(name);			\
-	mfmsr	r12;			\
-	mflr	r0;			\
-	andi.	r11,r12,MSR_IR|MSR_DR; 	\
-	std	r0,PPC_LR_STKOFF(r1);	\
-	li	r0,token;		\
-	beq	opal_real_call;         \
-	OPAL_BRANCH(opal_tracepoint_entry) \
-	DO_OPAL_CALL()
-
-
 opal_return:
 	/*
-	 * Fixup endian on OPAL return... we should be able to simplify
-	 * this by instead converting the below trampoline to a set of
-	 * bytes (always BE) since MSR:LE will end up fixed up as a side
-	 * effect of the rfid.
+	 * Restore MSR on OPAL return. The MSR is set to big-endian.
 	 */
-	FIXUP_ENDIAN_HV
-	ld	r2,PACATOC(r13);
-	lwz	r4,8(r1);
-	ld	r5,PPC_LR_STKOFF(r1);
-	ld	r6,PACASAVEDMSR(r13);
-	mtcr	r4;
-	mtspr	SPRN_HSRR0,r5;
-	mtspr	SPRN_HSRR1,r6;
-	hrfid
+#ifdef __BIG_ENDIAN__
+	ld	r11,STK_PARAM(R12)(r1)
+	mtmsrd	r11
+#else
+	/* Endian can only be switched with rfi, must byte reverse MSR load */
+	.short 0x4039	 /* li r10,STK_PARAM(R12)		*/
+	.byte (STK_PARAM(R12) >> 8) & 0xff
+	.byte STK_PARAM(R12) & 0xff
 
-opal_real_call:
-	mfcr	r11
-	stw	r11,8(r1)
-	/* Set opal return address */
-	LOAD_REG_ADDR(r11, opal_return_realmode)
-	mtlr	r11
-	li	r11,MSR_LE
-	andc	r12,r12,r11
-	mtspr	SPRN_HSRR1,r12
-	LOAD_REG_ADDR(r11,opal)
-	ld	r12,8(r11)
-	ld	r2,0(r11)
-	mtspr	SPRN_HSRR0,r12
-	hrfid
-
-opal_return_realmode:
-	FIXUP_ENDIAN_HV
-	ld	r2,PACATOC(r13);
-	lwz	r11,8(r1);
-	ld	r12,PPC_LR_STKOFF(r1)
-	mtcr	r11;
-	mtlr	r12
-	blr
-
-#ifdef CONFIG_TRACEPOINTS
-opal_tracepoint_entry:
-	stdu	r1,-STACKFRAMESIZE(r1)
-	std	r0,STK_REG(R23)(r1)
-	std	r3,STK_REG(R24)(r1)
-	std	r4,STK_REG(R25)(r1)
-	std	r5,STK_REG(R26)(r1)
-	std	r6,STK_REG(R27)(r1)
-	std	r7,STK_REG(R28)(r1)
-	std	r8,STK_REG(R29)(r1)
-	std	r9,STK_REG(R30)(r1)
-	std	r10,STK_REG(R31)(r1)
-	mr	r3,r0
-	addi	r4,r1,STK_REG(R24)
-	bl	__trace_opal_entry
-	ld	r0,STK_REG(R23)(r1)
-	ld	r3,STK_REG(R24)(r1)
-	ld	r4,STK_REG(R25)(r1)
-	ld	r5,STK_REG(R26)(r1)
-	ld	r6,STK_REG(R27)(r1)
-	ld	r7,STK_REG(R28)(r1)
-	ld	r8,STK_REG(R29)(r1)
-	ld	r9,STK_REG(R30)(r1)
-	ld	r10,STK_REG(R31)(r1)
-
-	/* setup LR so we return via tracepoint_return */
-	LOAD_REG_ADDR(r11,opal_tracepoint_return)
-	std	r11,16(r1)
-
-	mfmsr	r12
-	DO_OPAL_CALL()
-
-opal_tracepoint_return:
-	std	r3,STK_REG(R31)(r1)
-	mr	r4,r3
-	ld	r3,STK_REG(R23)(r1)
-	bl	__trace_opal_exit
-	ld	r3,STK_REG(R31)(r1)
-	addi	r1,r1,STACKFRAMESIZE
-	ld	r0,16(r1)
+	.long 0x280c6a7d /* ldbrx r11,r10,r1			*/
+	.long 0x05009f42 /* bcl 20,31,$+4			*/
+	.long 0xa602487d /* mflr r10				*/
+	.long 0x14004a39 /* addi r10,r10,20			*/
+	.long 0xa64b5a7d /* mthsrr0 r10				*/
+	.long 0xa64b7b7d /* mthsrr1 r11				*/
+	.long 0x2402004c /* hrfid				*/
+#endif
+	ld	r2,PACATOC(r13)
+	ld	r0,PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr
-#endif
-
-
-OPAL_CALL(opal_invalid_call,			OPAL_INVALID_CALL);
-OPAL_CALL(opal_console_write,			OPAL_CONSOLE_WRITE);
-OPAL_CALL(opal_console_read,			OPAL_CONSOLE_READ);
-OPAL_CALL(opal_console_write_buffer_space,	OPAL_CONSOLE_WRITE_BUFFER_SPACE);
-OPAL_CALL(opal_rtc_read,			OPAL_RTC_READ);
-OPAL_CALL(opal_rtc_write,			OPAL_RTC_WRITE);
-OPAL_CALL(opal_cec_power_down,			OPAL_CEC_POWER_DOWN);
-OPAL_CALL(opal_cec_reboot,			OPAL_CEC_REBOOT);
-OPAL_CALL(opal_cec_reboot2,			OPAL_CEC_REBOOT2);
-OPAL_CALL(opal_read_nvram,			OPAL_READ_NVRAM);
-OPAL_CALL(opal_write_nvram,			OPAL_WRITE_NVRAM);
-OPAL_CALL(opal_handle_interrupt,		OPAL_HANDLE_INTERRUPT);
-OPAL_CALL(opal_poll_events,			OPAL_POLL_EVENTS);
-OPAL_CALL(opal_pci_set_hub_tce_memory,		OPAL_PCI_SET_HUB_TCE_MEMORY);
-OPAL_CALL(opal_pci_set_phb_tce_memory,		OPAL_PCI_SET_PHB_TCE_MEMORY);
-OPAL_CALL(opal_pci_config_read_byte,		OPAL_PCI_CONFIG_READ_BYTE);
-OPAL_CALL(opal_pci_config_read_half_word,	OPAL_PCI_CONFIG_READ_HALF_WORD);
-OPAL_CALL(opal_pci_config_read_word,		OPAL_PCI_CONFIG_READ_WORD);
-OPAL_CALL(opal_pci_config_write_byte,		OPAL_PCI_CONFIG_WRITE_BYTE);
-OPAL_CALL(opal_pci_config_write_half_word,	OPAL_PCI_CONFIG_WRITE_HALF_WORD);
-OPAL_CALL(opal_pci_config_write_word,		OPAL_PCI_CONFIG_WRITE_WORD);
-OPAL_CALL(opal_set_xive,			OPAL_SET_XIVE);
-OPAL_CALL(opal_get_xive,			OPAL_GET_XIVE);
-OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER);
-OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
-OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
-OPAL_CALL(opal_pci_eeh_freeze_set,		OPAL_PCI_EEH_FREEZE_SET);
-OPAL_CALL(opal_pci_err_inject,			OPAL_PCI_ERR_INJECT);
-OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
-OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
-OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
-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);
-OPAL_CALL(opal_get_xive_source,			OPAL_GET_XIVE_SOURCE);
-OPAL_CALL(opal_get_msi_32,			OPAL_GET_MSI_32);
-OPAL_CALL(opal_get_msi_64,			OPAL_GET_MSI_64);
-OPAL_CALL(opal_start_cpu,			OPAL_START_CPU);
-OPAL_CALL(opal_query_cpu_status,		OPAL_QUERY_CPU_STATUS);
-OPAL_CALL(opal_write_oppanel,			OPAL_WRITE_OPPANEL);
-OPAL_CALL(opal_pci_map_pe_dma_window,		OPAL_PCI_MAP_PE_DMA_WINDOW);
-OPAL_CALL(opal_pci_map_pe_dma_window_real,	OPAL_PCI_MAP_PE_DMA_WINDOW_REAL);
-OPAL_CALL(opal_pci_reset,			OPAL_PCI_RESET);
-OPAL_CALL(opal_pci_get_hub_diag_data,		OPAL_PCI_GET_HUB_DIAG_DATA);
-OPAL_CALL(opal_pci_get_phb_diag_data,		OPAL_PCI_GET_PHB_DIAG_DATA);
-OPAL_CALL(opal_pci_fence_phb,			OPAL_PCI_FENCE_PHB);
-OPAL_CALL(opal_pci_reinit,			OPAL_PCI_REINIT);
-OPAL_CALL(opal_pci_mask_pe_error,		OPAL_PCI_MASK_PE_ERROR);
-OPAL_CALL(opal_set_slot_led_status,		OPAL_SET_SLOT_LED_STATUS);
-OPAL_CALL(opal_get_epow_status,			OPAL_GET_EPOW_STATUS);
-OPAL_CALL(opal_get_dpo_status,			OPAL_GET_DPO_STATUS);
-OPAL_CALL(opal_set_system_attention_led,	OPAL_SET_SYSTEM_ATTENTION_LED);
-OPAL_CALL(opal_pci_next_error,			OPAL_PCI_NEXT_ERROR);
-OPAL_CALL(opal_pci_poll,			OPAL_PCI_POLL);
-OPAL_CALL(opal_pci_msi_eoi,			OPAL_PCI_MSI_EOI);
-OPAL_CALL(opal_pci_get_phb_diag_data2,		OPAL_PCI_GET_PHB_DIAG_DATA2);
-OPAL_CALL(opal_xscom_read,			OPAL_XSCOM_READ);
-OPAL_CALL(opal_xscom_write,			OPAL_XSCOM_WRITE);
-OPAL_CALL(opal_lpc_read,			OPAL_LPC_READ);
-OPAL_CALL(opal_lpc_write,			OPAL_LPC_WRITE);
-OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
-OPAL_CALL(opal_reinit_cpus,			OPAL_REINIT_CPUS);
-OPAL_CALL(opal_read_elog,			OPAL_ELOG_READ);
-OPAL_CALL(opal_send_ack_elog,			OPAL_ELOG_ACK);
-OPAL_CALL(opal_get_elog_size,			OPAL_ELOG_SIZE);
-OPAL_CALL(opal_resend_pending_logs,		OPAL_ELOG_RESEND);
-OPAL_CALL(opal_write_elog,			OPAL_ELOG_WRITE);
-OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
-OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
-OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
-OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
-OPAL_CALL(opal_check_token,			OPAL_CHECK_TOKEN);
-OPAL_CALL(opal_dump_init,			OPAL_DUMP_INIT);
-OPAL_CALL(opal_dump_info,			OPAL_DUMP_INFO);
-OPAL_CALL(opal_dump_info2,			OPAL_DUMP_INFO2);
-OPAL_CALL(opal_dump_read,			OPAL_DUMP_READ);
-OPAL_CALL(opal_dump_ack,			OPAL_DUMP_ACK);
-OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
-OPAL_CALL(opal_write_oppanel_async,		OPAL_WRITE_OPPANEL_ASYNC);
-OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
-OPAL_CALL(opal_dump_resend_notification,	OPAL_DUMP_RESEND);
-OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);
-OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
-OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
-OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
-OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
-OPAL_CALL(opal_config_cpu_idle_state,		OPAL_CONFIG_CPU_IDLE_STATE);
-OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
-OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
-OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
-OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CAPI_MODE);
-OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
-OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
-OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
-OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
-OPAL_CALL(opal_i2c_request,			OPAL_I2C_REQUEST);
-OPAL_CALL(opal_flash_read,			OPAL_FLASH_READ);
-OPAL_CALL(opal_flash_write,			OPAL_FLASH_WRITE);
-OPAL_CALL(opal_flash_erase,			OPAL_FLASH_ERASE);
-OPAL_CALL(opal_prd_msg,				OPAL_PRD_MSG);
-OPAL_CALL(opal_leds_get_ind,			OPAL_LEDS_GET_INDICATOR);
-OPAL_CALL(opal_leds_set_ind,			OPAL_LEDS_SET_INDICATOR);
-OPAL_CALL(opal_console_flush,			OPAL_CONSOLE_FLUSH);
-OPAL_CALL(opal_get_device_tree,			OPAL_GET_DEVICE_TREE);
-OPAL_CALL(opal_pci_get_presence_state,		OPAL_PCI_GET_PRESENCE_STATE);
-OPAL_CALL(opal_pci_get_power_state,		OPAL_PCI_GET_POWER_STATE);
-OPAL_CALL(opal_pci_set_power_state,		OPAL_PCI_SET_POWER_STATE);
-OPAL_CALL(opal_int_get_xirr,			OPAL_INT_GET_XIRR);
-OPAL_CALL(opal_int_set_cppr,			OPAL_INT_SET_CPPR);
-OPAL_CALL(opal_int_eoi,				OPAL_INT_EOI);
-OPAL_CALL(opal_int_set_mfrr,			OPAL_INT_SET_MFRR);
-OPAL_CALL(opal_pci_tce_kill,			OPAL_PCI_TCE_KILL);
-OPAL_CALL(opal_nmmu_set_ptcr,			OPAL_NMMU_SET_PTCR);
-OPAL_CALL(opal_xive_reset,			OPAL_XIVE_RESET);
-OPAL_CALL(opal_xive_get_irq_info,		OPAL_XIVE_GET_IRQ_INFO);
-OPAL_CALL(opal_xive_get_irq_config,		OPAL_XIVE_GET_IRQ_CONFIG);
-OPAL_CALL(opal_xive_set_irq_config,		OPAL_XIVE_SET_IRQ_CONFIG);
-OPAL_CALL(opal_xive_get_queue_info,		OPAL_XIVE_GET_QUEUE_INFO);
-OPAL_CALL(opal_xive_set_queue_info,		OPAL_XIVE_SET_QUEUE_INFO);
-OPAL_CALL(opal_xive_donate_page,		OPAL_XIVE_DONATE_PAGE);
-OPAL_CALL(opal_xive_alloc_vp_block,		OPAL_XIVE_ALLOCATE_VP_BLOCK);
-OPAL_CALL(opal_xive_free_vp_block,		OPAL_XIVE_FREE_VP_BLOCK);
-OPAL_CALL(opal_xive_allocate_irq,		OPAL_XIVE_ALLOCATE_IRQ);
-OPAL_CALL(opal_xive_free_irq,			OPAL_XIVE_FREE_IRQ);
-OPAL_CALL(opal_xive_get_vp_info,		OPAL_XIVE_GET_VP_INFO);
-OPAL_CALL(opal_xive_set_vp_info,		OPAL_XIVE_SET_VP_INFO);
-OPAL_CALL(opal_xive_sync,			OPAL_XIVE_SYNC);
-OPAL_CALL(opal_xive_dump,			OPAL_XIVE_DUMP);
-OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
-OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
-OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);
-OPAL_CALL(opal_npu_map_lpar,			OPAL_NPU_MAP_LPAR);
-OPAL_CALL(opal_imc_counters_init,		OPAL_IMC_COUNTERS_INIT);
-OPAL_CALL(opal_imc_counters_start,		OPAL_IMC_COUNTERS_START);
-OPAL_CALL(opal_imc_counters_stop,		OPAL_IMC_COUNTERS_STOP);
-OPAL_CALL(opal_pci_set_p2p,			OPAL_PCI_SET_P2P);
-OPAL_CALL(opal_get_powercap,			OPAL_GET_POWERCAP);
-OPAL_CALL(opal_set_powercap,			OPAL_SET_POWERCAP);
-OPAL_CALL(opal_get_power_shift_ratio,		OPAL_GET_POWER_SHIFT_RATIO);
-OPAL_CALL(opal_set_power_shift_ratio,		OPAL_SET_POWER_SHIFT_RATIO);
-OPAL_CALL(opal_sensor_group_clear,		OPAL_SENSOR_GROUP_CLEAR);
-OPAL_CALL(opal_quiesce,				OPAL_QUIESCE);
-OPAL_CALL(opal_npu_spa_setup,			OPAL_NPU_SPA_SETUP);
-OPAL_CALL(opal_npu_spa_clear_cache,		OPAL_NPU_SPA_CLEAR_CACHE);
-OPAL_CALL(opal_npu_tl_set,			OPAL_NPU_TL_SET);
-OPAL_CALL(opal_pci_get_pbcq_tunnel_bar,		OPAL_PCI_GET_PBCQ_TUNNEL_BAR);
-OPAL_CALL(opal_pci_set_pbcq_tunnel_bar,		OPAL_PCI_SET_PBCQ_TUNNEL_BAR);
-OPAL_CALL(opal_sensor_read_u64,			OPAL_SENSOR_READ_U64);
-OPAL_CALL(opal_sensor_group_enable,		OPAL_SENSOR_GROUP_ENABLE);
-OPAL_CALL(opal_nx_coproc_init,			OPAL_NX_COPROC_INIT);
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 22d5e11..fd510d9 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -1,12 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * PowerNV LPC bus handling.
+ * PowerNV SCOM bus debugfs interface
  *
+ * Copyright 2010 Benjamin Herrenschmidt, IBM Corp
+ *                <benh@kernel.crashing.org>
+ *     and        David Gibson, IBM Corporation.
  * Copyright 2013 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -14,62 +13,13 @@
 #include <linux/bug.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/uaccess.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/opal.h>
-#include <asm/scom.h>
-
-/*
- * We could probably fit that inside the scom_map_t
- * which is a void* after all but it's really too ugly
- * so let's kmalloc it for now
- */
-struct opal_scom_map {
-	uint32_t chip;
-	uint64_t addr;
-};
-
-static scom_map_t opal_scom_map(struct device_node *dev, u64 reg, u64 count)
-{
-	struct opal_scom_map *m;
-	const __be32 *gcid;
-
-	if (!of_get_property(dev, "scom-controller", NULL)) {
-		pr_err("%s: device %pOF is not a SCOM controller\n",
-			__func__, dev);
-		return SCOM_MAP_INVALID;
-	}
-	gcid = of_get_property(dev, "ibm,chip-id", NULL);
-	if (!gcid) {
-		pr_err("%s: device %pOF has no ibm,chip-id\n",
-			__func__, dev);
-		return SCOM_MAP_INVALID;
-	}
-	m = kmalloc(sizeof(*m), GFP_KERNEL);
-	if (!m)
-		return NULL;
-	m->chip = be32_to_cpup(gcid);
-	m->addr = reg;
-
-	return (scom_map_t)m;
-}
-
-static void opal_scom_unmap(scom_map_t map)
-{
-	kfree(map);
-}
-
-static int opal_xscom_err_xlate(int64_t rc)
-{
-	switch(rc) {
-	case 0:
-		return 0;
-	/* Add more translations if necessary */
-	default:
-		return -EIO;
-	}
-}
+#include <asm/debugfs.h>
+#include <asm/prom.h>
 
 static u64 opal_scom_unmangle(u64 addr)
 {
@@ -102,39 +52,154 @@
 	return addr;
 }
 
-static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
+static int opal_scom_read(uint32_t chip, uint64_t addr, u64 reg, u64 *value)
 {
-	struct opal_scom_map *m = map;
 	int64_t rc;
 	__be64 v;
 
-	reg = opal_scom_unmangle(m->addr + reg);
-	rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v));
+	reg = opal_scom_unmangle(addr + reg);
+	rc = opal_xscom_read(chip, reg, (__be64 *)__pa(&v));
+	if (rc) {
+		*value = 0xfffffffffffffffful;
+		return -EIO;
+	}
 	*value = be64_to_cpu(v);
-	return opal_xscom_err_xlate(rc);
-}
-
-static int opal_scom_write(scom_map_t map, u64 reg, u64 value)
-{
-	struct opal_scom_map *m = map;
-	int64_t rc;
-
-	reg = opal_scom_unmangle(m->addr + reg);
-	rc = opal_xscom_write(m->chip, reg, value);
-	return opal_xscom_err_xlate(rc);
-}
-
-static const struct scom_controller opal_scom_controller = {
-	.map	= opal_scom_map,
-	.unmap	= opal_scom_unmap,
-	.read	= opal_scom_read,
-	.write	= opal_scom_write
-};
-
-static int opal_xscom_init(void)
-{
-	if (firmware_has_feature(FW_FEATURE_OPAL))
-		scom_init(&opal_scom_controller);
 	return 0;
 }
-machine_arch_initcall(powernv, opal_xscom_init);
+
+static int opal_scom_write(uint32_t chip, uint64_t addr, u64 reg, u64 value)
+{
+	int64_t rc;
+
+	reg = opal_scom_unmangle(addr + reg);
+	rc = opal_xscom_write(chip, reg, value);
+	if (rc)
+		return -EIO;
+	return 0;
+}
+
+struct scom_debug_entry {
+	u32 chip;
+	struct debugfs_blob_wrapper path;
+	char name[16];
+};
+
+static ssize_t scom_debug_read(struct file *filp, char __user *ubuf,
+			       size_t count, loff_t *ppos)
+{
+	struct scom_debug_entry *ent = filp->private_data;
+	u64 __user *ubuf64 = (u64 __user *)ubuf;
+	loff_t off = *ppos;
+	ssize_t done = 0;
+	u64 reg, reg_base, reg_cnt, val;
+	int rc;
+
+	if (off < 0 || (off & 7) || (count & 7))
+		return -EINVAL;
+	reg_base = off >> 3;
+	reg_cnt = count >> 3;
+
+	for (reg = 0; reg < reg_cnt; reg++) {
+		rc = opal_scom_read(ent->chip, reg_base, reg, &val);
+		if (!rc)
+			rc = put_user(val, ubuf64);
+		if (rc) {
+			if (!done)
+				done = rc;
+			break;
+		}
+		ubuf64++;
+		*ppos += 8;
+		done += 8;
+	}
+	return done;
+}
+
+static ssize_t scom_debug_write(struct file *filp, const char __user *ubuf,
+				size_t count, loff_t *ppos)
+{
+	struct scom_debug_entry *ent = filp->private_data;
+	u64 __user *ubuf64 = (u64 __user *)ubuf;
+	loff_t off = *ppos;
+	ssize_t done = 0;
+	u64 reg, reg_base, reg_cnt, val;
+	int rc;
+
+	if (off < 0 || (off & 7) || (count & 7))
+		return -EINVAL;
+	reg_base = off >> 3;
+	reg_cnt = count >> 3;
+
+	for (reg = 0; reg < reg_cnt; reg++) {
+		rc = get_user(val, ubuf64);
+		if (!rc)
+			rc = opal_scom_write(ent->chip, reg_base, reg,  val);
+		if (rc) {
+			if (!done)
+				done = rc;
+			break;
+		}
+		ubuf64++;
+		done += 8;
+	}
+	return done;
+}
+
+static const struct file_operations scom_debug_fops = {
+	.read =		scom_debug_read,
+	.write =	scom_debug_write,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+static int scom_debug_init_one(struct dentry *root, struct device_node *dn,
+			       int chip)
+{
+	struct scom_debug_entry *ent;
+	struct dentry *dir;
+
+	ent = kzalloc(sizeof(*ent), GFP_KERNEL);
+	if (!ent)
+		return -ENOMEM;
+
+	ent->chip = chip;
+	snprintf(ent->name, 16, "%08x", chip);
+	ent->path.data = (void *)kasprintf(GFP_KERNEL, "%pOF", dn);
+	ent->path.size = strlen((char *)ent->path.data);
+
+	dir = debugfs_create_dir(ent->name, root);
+	if (!dir) {
+		kfree(ent->path.data);
+		kfree(ent);
+		return -1;
+	}
+
+	debugfs_create_blob("devspec", 0400, dir, &ent->path);
+	debugfs_create_file("access", 0600, dir, ent, &scom_debug_fops);
+
+	return 0;
+}
+
+static int scom_debug_init(void)
+{
+	struct device_node *dn;
+	struct dentry *root;
+	int chip, rc;
+
+	if (!firmware_has_feature(FW_FEATURE_OPAL))
+		return 0;
+
+	root = debugfs_create_dir("scom", powerpc_debugfs_root);
+	if (!root)
+		return -1;
+
+	rc = 0;
+	for_each_node_with_property(dn, "scom-controller") {
+		chip = of_get_ibm_chip_id(dn);
+		WARN_ON(chip == -1);
+		rc |= scom_debug_init_one(root, dn, chip);
+	}
+
+	return rc;
+}
+device_initcall(scom_debug_init);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 38fe408..38e9027 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV OPAL high level interfaces
  *
  * Copyright 2011 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)	"opal: " fmt
@@ -26,7 +22,6 @@
 #include <linux/memblock.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
-#include <linux/printk.h>
 #include <linux/kmsg_dump.h>
 #include <linux/console.h>
 #include <linux/sched/debug.h>
@@ -63,6 +58,8 @@
 static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX];
 static uint32_t opal_heartbeat;
 static struct task_struct *kopald_tsk;
+static struct opal_msg *opal_msg;
+static u32 opal_msg_size __ro_after_init;
 
 void opal_configure_cores(void)
 {
@@ -171,8 +168,10 @@
 	/*
 	 * Allocate a buffer to hold the MC recoverable ranges.
 	 */
-	mc_recoverable_range =__va(memblock_alloc(size, __alignof__(u64)));
-	memset(mc_recoverable_range, 0, size);
+	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));
 
 	for (i = 0; i < mc_recoverable_range_len; i++) {
 		mc_recoverable_range[i].start_addr =
@@ -205,16 +204,18 @@
 	glue = 0x7000;
 
 	/*
-	 * Check if we are running on newer firmware that exports
-	 * OPAL_HANDLE_HMI token. If yes, then don't ask OPAL to patch
-	 * the HMI interrupt and we catch it directly in Linux.
+	 * Only ancient OPAL firmware requires this.
+	 * Specifically, firmware from FW810.00 (released June 2014)
+	 * through FW810.20 (Released October 2014).
 	 *
-	 * For older firmware (i.e currently released POWER8 System Firmware
-	 * as of today <= SV810_087), we fallback to old behavior and let OPAL
-	 * patch the HMI vector and handle it inside OPAL firmware.
+	 * Check if we are running on newer (post Oct 2014) firmware that
+	 * exports the OPAL_HANDLE_HMI token. If yes, then don't ask OPAL to
+	 * patch the HMI interrupt and we catch it directly in Linux.
 	 *
-	 * For newer firmware (in development/yet to be released) we will
-	 * start catching/handling HMI directly in Linux.
+	 * For older firmware (i.e < FW810.20), we fallback to old behavior and
+	 * let OPAL patch the HMI vector and handle it inside OPAL firmware.
+	 *
+	 * For newer firmware we catch/handle the HMI directly in Linux.
 	 */
 	if (!opal_check_token(OPAL_HANDLE_HMI)) {
 		pr_info("Old firmware detected, OPAL handles HMIs.\n");
@@ -224,6 +225,11 @@
 		glue += 128;
 	}
 
+	/*
+	 * Only applicable to ancient firmware, all modern
+	 * (post March 2015/skiboot 5.0) firmware will just return
+	 * OPAL_UNSUPPORTED.
+	 */
 	opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue);
 #endif
 
@@ -267,14 +273,9 @@
 static void opal_handle_message(void)
 {
 	s64 ret;
-	/*
-	 * TODO: pre-allocate a message buffer depending on opal-msg-size
-	 * value in /proc/device-tree.
-	 */
-	static struct opal_msg msg;
 	u32 type;
 
-	ret = opal_get_msg(__pa(&msg), sizeof(msg));
+	ret = opal_get_msg(__pa(opal_msg), opal_msg_size);
 	/* No opal message pending. */
 	if (ret == OPAL_RESOURCE)
 		return;
@@ -286,14 +287,14 @@
 		return;
 	}
 
-	type = be32_to_cpu(msg.msg_type);
+	type = be32_to_cpu(opal_msg->msg_type);
 
 	/* Sanity check */
 	if (type >= OPAL_MSG_TYPE_MAX) {
 		pr_warn_once("%s: Unknown message type: %u\n", __func__, type);
 		return;
 	}
-	opal_message_do_notify(type, (void *)&msg);
+	opal_message_do_notify(type, (void *)opal_msg);
 }
 
 static irqreturn_t opal_message_notify(int irq, void *data)
@@ -302,10 +303,24 @@
 	return IRQ_HANDLED;
 }
 
-static int __init opal_message_init(void)
+static int __init opal_message_init(struct device_node *opal_node)
 {
 	int ret, i, irq;
 
+	ret = of_property_read_u32(opal_node, "opal-msg-size", &opal_msg_size);
+	if (ret) {
+		pr_notice("Failed to read opal-msg-size property\n");
+		opal_msg_size = sizeof(struct opal_msg);
+	}
+
+	opal_msg = kmalloc(opal_msg_size, GFP_KERNEL);
+	if (!opal_msg) {
+		opal_msg_size = sizeof(struct opal_msg);
+		/* Try to allocate fixed message size */
+		opal_msg = kmalloc(opal_msg_size, GFP_KERNEL);
+		BUG_ON(opal_msg == NULL);
+	}
+
 	for (i = 0; i < OPAL_MSG_TYPE_MAX; i++)
 		ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]);
 
@@ -504,7 +519,7 @@
 		recovered = 0;
 	}
 
-	if (!recovered && evt->severity == MCE_SEV_ERROR_SYNC) {
+	if (!recovered && evt->sync_error) {
 		/*
 		 * Try to kill processes if we get a synchronous machine check
 		 * (e.g., one caused by execution of this instruction). This
@@ -535,7 +550,7 @@
 	return recovered;
 }
 
-void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg)
+void __noreturn pnv_platform_error_reboot(struct pt_regs *regs, const char *msg)
 {
 	panic_flush_kmsg_start();
 
@@ -587,7 +602,7 @@
 		       evt.version);
 		return 0;
 	}
-	machine_check_print_event_info(&evt, user_mode(regs));
+	machine_check_print_event_info(&evt, user_mode(regs), false);
 
 	if (opal_recover_mce(regs, &evt))
 		return 1;
@@ -613,6 +628,27 @@
 	return 0;
 }
 
+int opal_hmi_exception_early2(struct pt_regs *regs)
+{
+	s64 rc;
+	__be64 out_flags;
+
+	/*
+	 * call opal hmi handler.
+	 * Check 64-bit flag mask to find out if an event was generated,
+	 * and whether TB is still valid or not etc.
+	 */
+	rc = opal_handle_hmi2(&out_flags);
+	if (rc != OPAL_SUCCESS)
+		return 0;
+
+	if (be64_to_cpu(out_flags) & OPAL_HMI_FLAGS_NEW_EVENT)
+		local_paca->hmi_event_available = 1;
+	if (be64_to_cpu(out_flags) & OPAL_HMI_FLAGS_TOD_TB_FAIL)
+		tb_invalid = true;
+	return 1;
+}
+
 /* HMI exception handler called in virtual mode during check_irq_replay. */
 int opal_handle_hmi_exception(struct pt_regs *regs)
 {
@@ -680,7 +716,10 @@
 				       bin_attr->size);
 }
 
-static BIN_ATTR_RO(symbol_map, 0);
+static struct bin_attribute symbol_map_attr = {
+	.attr = {.name = "symbol_map", .mode = 0400},
+	.read = symbol_map_read
+};
 
 static void opal_export_symmap(void)
 {
@@ -697,10 +736,10 @@
 		return;
 
 	/* Setup attributes */
-	bin_attr_symbol_map.private = __va(be64_to_cpu(syms[0]));
-	bin_attr_symbol_map.size = be64_to_cpu(syms[1]);
+	symbol_map_attr.private = __va(be64_to_cpu(syms[0]));
+	symbol_map_attr.size = be64_to_cpu(syms[1]);
 
-	rc = sysfs_create_bin_file(opal_kobj, &bin_attr_symbol_map);
+	rc = sysfs_create_bin_file(opal_kobj, &symbol_map_attr);
 	if (rc)
 		pr_warn("Error %d creating OPAL symbols file\n", rc);
 }
@@ -877,7 +916,7 @@
 	consoles = of_find_node_by_path("/ibm,opal/consoles");
 	if (consoles) {
 		for_each_child_of_node(consoles, np) {
-			if (strcmp(np->name, "serial"))
+			if (!of_node_name_eq(np, "serial"))
 				continue;
 			of_platform_device_create(np, NULL, NULL);
 		}
@@ -885,7 +924,7 @@
 	}
 
 	/* Initialise OPAL messaging system */
-	opal_message_init();
+	opal_message_init(opal_node);
 
 	/* Initialise OPAL asynchronous completion interface */
 	opal_async_comp_init();
@@ -960,6 +999,9 @@
 	/* Initialise OPAL sensor groups */
 	opal_sensor_groups_init();
 
+	/* Initialise OPAL Power control interface */
+	opal_power_control_init();
+
 	return 0;
 }
 machine_subsys_initcall(powernv, opal_init);
diff --git a/arch/powerpc/platforms/powernv/pci-cxl.c b/arch/powerpc/platforms/powernv/pci-cxl.c
index 1b18111..8c739c9 100644
--- a/arch/powerpc/platforms/powernv/pci-cxl.c
+++ b/arch/powerpc/platforms/powernv/pci-cxl.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2014-2016 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/module.h>
diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
index fe96910..a0b9c0c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
@@ -36,7 +36,8 @@
 	struct page *tce_mem = NULL;
 	__be64 *addr;
 
-	tce_mem = alloc_pages_node(nid, GFP_KERNEL, shift - PAGE_SHIFT);
+	tce_mem = alloc_pages_node(nid, GFP_ATOMIC | __GFP_NOWARN,
+			shift - PAGE_SHIFT);
 	if (!tce_mem) {
 		pr_err("Failed to allocate a TCE memory, level shift=%d\n",
 				shift);
@@ -48,6 +49,9 @@
 	return addr;
 }
 
+static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr,
+		unsigned long size, unsigned int levels);
+
 static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc)
 {
 	__be64 *tmp = user ? tbl->it_userspace : (__be64 *) tbl->it_base;
@@ -57,9 +61,9 @@
 
 	while (level) {
 		int n = (idx & mask) >> (level * shift);
-		unsigned long tce;
+		unsigned long oldtce, tce = be64_to_cpu(READ_ONCE(tmp[n]));
 
-		if (tmp[n] == 0) {
+		if (!tce) {
 			__be64 *tmp2;
 
 			if (!alloc)
@@ -70,10 +74,15 @@
 			if (!tmp2)
 				return NULL;
 
-			tmp[n] = cpu_to_be64(__pa(tmp2) |
-					TCE_PCI_READ | TCE_PCI_WRITE);
+			tce = __pa(tmp2) | TCE_PCI_READ | TCE_PCI_WRITE;
+			oldtce = be64_to_cpu(cmpxchg(&tmp[n], 0,
+					cpu_to_be64(tce)));
+			if (oldtce) {
+				pnv_pci_ioda2_table_do_free_pages(tmp2,
+					ilog2(tbl->it_level_size) + 3, 1);
+				tce = oldtce;
+			}
 		}
-		tce = be64_to_cpu(tmp[n]);
 
 		tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE));
 		idx &= ~mask;
@@ -161,6 +170,9 @@
 
 		if (ptce)
 			*ptce = cpu_to_be64(0);
+		else
+			/* Skip the rest of the level */
+			i |= tbl->it_level_size - 1;
 	}
 }
 
@@ -260,7 +272,6 @@
 	unsigned int table_shift = max_t(unsigned int, entries_shift + 3,
 			PAGE_SHIFT);
 	const unsigned long tce_table_size = 1UL << table_shift;
-	unsigned int tmplevels = levels;
 
 	if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS))
 		return -EINVAL;
@@ -268,9 +279,6 @@
 	if (!is_power_of_2(window_size))
 		return -EINVAL;
 
-	if (alloc_userspace_copy && (window_size > (1ULL << 32)))
-		tmplevels = 1;
-
 	/* Adjust direct table size from window_size and levels */
 	entries_shift = (entries_shift + levels - 1) / levels;
 	level_shift = entries_shift + 3;
@@ -281,7 +289,7 @@
 
 	/* Allocate TCE table */
 	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
-			tmplevels, tce_table_size, &offset, &total_allocated);
+			1, tce_table_size, &offset, &total_allocated);
 
 	/* addr==NULL means that the first level allocation failed */
 	if (!addr)
@@ -292,18 +300,18 @@
 	 * we did not allocate as much as we wanted,
 	 * release partially allocated table.
 	 */
-	if (tmplevels == levels && offset < tce_table_size)
+	if (levels == 1 && offset < tce_table_size)
 		goto free_tces_exit;
 
 	/* Allocate userspace view of the TCE table */
 	if (alloc_userspace_copy) {
 		offset = 0;
 		uas = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
-				levels, tce_table_size, &offset,
+				1, tce_table_size, &offset,
 				&total_allocated_uas);
 		if (!uas)
 			goto free_tces_exit;
-		if (tmplevels == levels && (offset < tce_table_size ||
+		if (levels == 1 && (offset < tce_table_size ||
 				total_allocated_uas != total_allocated))
 			goto free_uas_exit;
 	}
@@ -313,13 +321,12 @@
 			page_shift);
 	tbl->it_level_size = 1ULL << (level_shift - 3);
 	tbl->it_indirect_levels = levels - 1;
-	tbl->it_allocated_size = total_allocated;
 	tbl->it_userspace = uas;
 	tbl->it_nid = nid;
 
 	pr_debug("Created TCE table: ws=%08llx ts=%lx @%08llx base=%lx uas=%p levels=%d/%d\n",
 			window_size, tce_table_size, bus_offset, tbl->it_base,
-			tbl->it_userspace, tmplevels, levels);
+			tbl->it_userspace, 1, levels);
 
 	return 0;
 
@@ -368,6 +375,7 @@
 	found = false;
 	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
 		if (table_group->tables[i] == tbl) {
+			iommu_tce_table_put(tbl);
 			table_group->tables[i] = NULL;
 			found = true;
 			break;
@@ -393,7 +401,7 @@
 	tgl->table_group = table_group;
 	list_add_rcu(&tgl->next, &tbl->it_group_list);
 
-	table_group->tables[num] = tbl;
+	table_group->tables[num] = iommu_tce_table_get(tbl);
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index cde7102..c28d0d9 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Support PCI/PCIe on PowerNV platforms
  *
  * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
@@ -17,11 +13,10 @@
 #include <linux/delay.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
-#include <linux/memblock.h>
 #include <linux/iommu.h>
 #include <linux/rculist.h>
 #include <linux/sizes.h>
@@ -55,6 +50,8 @@
 static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
 					      "NPU_OCAPI" };
 
+static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
+
 void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 			    const char *fmt, ...)
 {
@@ -191,7 +188,8 @@
 	unsigned int pe_num = pe->pe_number;
 
 	WARN_ON(pe->pdev);
-
+	WARN_ON(pe->npucomp); /* NPUs are not supposed to be freed */
+	kfree(pe->npucomp);
 	memset(pe, 0, sizeof(struct pnv_ioda_pe));
 	clear_bit(pe_num, phb->ioda.pe_alloc);
 }
@@ -518,8 +516,6 @@
 		phb->init_m64 = pnv_ioda1_init_m64;
 	else
 		phb->init_m64 = pnv_ioda2_init_m64;
-	phb->reserve_m64_pe = pnv_ioda_reserve_m64_pe;
-	phb->pick_m64_pe = pnv_ioda_pick_m64_pe;
 }
 
 static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no)
@@ -605,8 +601,8 @@
 static int pnv_ioda_get_pe_state(struct pnv_phb *phb, int pe_no)
 {
 	struct pnv_ioda_pe *slave, *pe;
-	u8 fstate, state;
-	__be16 pcierr;
+	u8 fstate = 0, state;
+	__be16 pcierr = 0;
 	s64 rc;
 
 	/* Sanity check on PE number */
@@ -664,10 +660,6 @@
 	return state;
 }
 
-/* Currently those 2 are only used when MSIs are enabled, this will change
- * but in the meantime, we need to protect them to avoid warnings
- */
-#ifdef CONFIG_PCI_MSI
 struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
@@ -680,7 +672,6 @@
 		return NULL;
 	return &phb->ioda.pe_array[pdn->pe_number];
 }
-#endif /* CONFIG_PCI_MSI */
 
 static int pnv_ioda_set_one_peltv(struct pnv_phb *phb,
 				  struct pnv_ioda_pe *parent,
@@ -854,11 +845,11 @@
 	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
 				pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
 	if (rc)
-		pe_warn(pe, "OPAL error %ld remove self from PELTV\n", rc);
+		pe_warn(pe, "OPAL error %lld remove self from PELTV\n", rc);
 	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
 			     bcomp, dcomp, fcomp, OPAL_UNMAP_PE);
 	if (rc)
-		pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
+		pe_err(pe, "OPAL error %lld trying to setup PELT table\n", rc);
 
 	pe->pbus = NULL;
 	pe->pdev = NULL;
@@ -1161,8 +1152,8 @@
 		pe = &phb->ioda.pe_array[phb->ioda.root_pe_idx];
 
 	/* Check if PE is determined by M64 */
-	if (!pe && phb->pick_m64_pe)
-		pe = phb->pick_m64_pe(bus, all);
+	if (!pe)
+		pe = pnv_ioda_pick_m64_pe(bus, all);
 
 	/* The PE number isn't pinned by M64 */
 	if (!pe)
@@ -1181,11 +1172,12 @@
 	pe->rid = bus->busn_res.start << 8;
 
 	if (all)
-		pe_info(pe, "Secondary bus %d..%d associated with PE#%x\n",
-			bus->busn_res.start, bus->busn_res.end, pe->pe_number);
+		pe_info(pe, "Secondary bus %pad..%pad associated with PE#%x\n",
+			&bus->busn_res.start, &bus->busn_res.end,
+			pe->pe_number);
 	else
-		pe_info(pe, "Secondary bus %d associated with PE#%x\n",
-			bus->busn_res.start, pe->pe_number);
+		pe_info(pe, "Secondary bus %pad associated with PE#%x\n",
+			&bus->busn_res.start, pe->pe_number);
 
 	if (pnv_ioda_configure_pe(phb, pe)) {
 		/* XXX What do we do here ? */
@@ -1274,19 +1266,20 @@
 
 static void pnv_pci_ioda_setup_PEs(void)
 {
-	struct pci_controller *hose, *tmp;
+	struct pci_controller *hose;
 	struct pnv_phb *phb;
 	struct pci_bus *bus;
 	struct pci_dev *pdev;
+	struct pnv_ioda_pe *pe;
 
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+	list_for_each_entry(hose, &hose_list, list_node) {
 		phb = hose->private_data;
 		if (phb->type == PNV_PHB_NPU_NVLINK) {
 			/* PE#0 is needed for error reporting */
 			pnv_ioda_reserve_pe(phb, 0);
 			pnv_ioda_setup_npu_PEs(hose->bus);
 			if (phb->model == PNV_PHB_MODEL_NPU2)
-				pnv_npu2_init(phb);
+				WARN_ON_ONCE(pnv_npu2_init(hose));
 		}
 		if (phb->type == PNV_PHB_NPU_OCAPI) {
 			bus = hose->bus;
@@ -1294,6 +1287,14 @@
 				pnv_ioda_setup_dev_PE(pdev);
 		}
 	}
+	list_for_each_entry(hose, &hose_list, list_node) {
+		phb = hose->private_data;
+		if (phb->type != PNV_PHB_IODA2)
+			continue;
+
+		list_for_each_entry(pe, &phb->ioda.pe_list, list)
+			pnv_npu2_map_lpar(pe, MSR_DR | MSR_PR | MSR_HV);
+	}
 }
 
 #ifdef CONFIG_PCI_IOV
@@ -1446,7 +1447,7 @@
 	tbl = pe->table_group.tables[0];
 	rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (rc)
-		pe_warn(pe, "OPAL error %ld release DMA window\n", rc);
+		pe_warn(pe, "OPAL error %lld release DMA window\n", rc);
 
 	pnv_pci_ioda2_set_bypass(pe, false);
 	if (pe->table_group.group) {
@@ -1532,6 +1533,11 @@
 
 static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 				       struct pnv_ioda_pe *pe);
+#ifdef CONFIG_IOMMU_API
+static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe,
+		struct iommu_table_group *table_group, struct pci_bus *bus);
+
+#endif
 static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 {
 	struct pci_bus        *bus;
@@ -1585,6 +1591,11 @@
 		mutex_unlock(&phb->ioda.pe_list_mutex);
 
 		pnv_pci_ioda2_setup_dma_pe(phb, pe);
+#ifdef CONFIG_IOMMU_API
+		iommu_register_group(&pe->table_group,
+				pe->phb->hose->global_number, pe->pe_number);
+		pnv_ioda_setup_bus_iommu_group(pe, &pe->table_group, NULL);
+#endif
 	}
 }
 
@@ -1736,7 +1747,7 @@
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
-	set_dma_offset(&pdev->dev, pe->tce_bypass_base);
+	pdev->dev.archdata.dma_offset = pe->tce_bypass_base;
 	set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
 	/*
 	 * Note: iommu_add_device() will fail here as
@@ -1746,31 +1757,6 @@
 	 */
 }
 
-static bool pnv_pci_ioda_pe_single_vendor(struct pnv_ioda_pe *pe)
-{
-	unsigned short vendor = 0;
-	struct pci_dev *pdev;
-
-	if (pe->device_count == 1)
-		return true;
-
-	/* pe->pdev should be set if it's a single device, pe->pbus if not */
-	if (!pe->pbus)
-		return true;
-
-	list_for_each_entry(pdev, &pe->pbus->devices, bus_list) {
-		if (!vendor) {
-			vendor = pdev->vendor;
-			continue;
-		}
-
-		if (pdev->vendor != vendor)
-			return false;
-	}
-
-	return true;
-}
-
 /*
  * Reconfigure TVE#0 to be usable as 64-bit DMA space.
  *
@@ -1840,105 +1826,57 @@
 	return -EIO;
 }
 
-static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev,
+		u64 dma_mask)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
-	uint64_t top;
-	bool bypass = false;
-	s64 rc;
 
 	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
-		return -ENODEV;
+		return false;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	if (pe->tce_bypass_enabled) {
-		top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
-		bypass = (dma_mask >= top);
+		u64 top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
+		if (dma_mask >= top)
+			return true;
 	}
 
-	if (bypass) {
-		dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
-		set_dma_ops(&pdev->dev, &dma_nommu_ops);
-	} else {
-		/*
-		 * If the device can't set the TCE bypass bit but still wants
-		 * to access 4GB or more, on PHB3 we can reconfigure TVE#0 to
-		 * bypass the 32-bit region and be usable for 64-bit DMAs.
-		 * The device needs to be able to address all of this space.
-		 */
-		if (dma_mask >> 32 &&
-		    dma_mask > (memory_hotplug_max() + (1ULL << 32)) &&
-		    pnv_pci_ioda_pe_single_vendor(pe) &&
-		    phb->model == PNV_PHB_MODEL_PHB3) {
-			/* Configure the bypass mode */
-			rc = pnv_pci_ioda_dma_64bit_bypass(pe);
-			if (rc)
-				return rc;
-			/* 4GB offset bypasses 32-bit space */
-			set_dma_offset(&pdev->dev, (1ULL << 32));
-			set_dma_ops(&pdev->dev, &dma_nommu_ops);
-		} else if (dma_mask >> 32 && dma_mask != DMA_BIT_MASK(64)) {
-			/*
-			 * Fail the request if a DMA mask between 32 and 64 bits
-			 * was requested but couldn't be fulfilled. Ideally we
-			 * would do this for 64-bits but historically we have
-			 * always fallen back to 32-bits.
-			 */
-			return -ENOMEM;
-		} else {
-			dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
-			set_dma_ops(&pdev->dev, &dma_iommu_ops);
-		}
+	/*
+	 * If the device can't set the TCE bypass bit but still wants
+	 * to access 4GB or more, on PHB3 we can reconfigure TVE#0 to
+	 * bypass the 32-bit region and be usable for 64-bit DMAs.
+	 * The device needs to be able to address all of this space.
+	 */
+	if (dma_mask >> 32 &&
+	    dma_mask > (memory_hotplug_max() + (1ULL << 32)) &&
+	    /* pe->pdev should be set if it's a single device, pe->pbus if not */
+	    (pe->device_count == 1 || !pe->pbus) &&
+	    phb->model == PNV_PHB_MODEL_PHB3) {
+		/* Configure the bypass mode */
+		s64 rc = pnv_pci_ioda_dma_64bit_bypass(pe);
+		if (rc)
+			return false;
+		/* 4GB offset bypasses 32-bit space */
+		pdev->dev.archdata.dma_offset = (1ULL << 32);
+		return true;
 	}
-	*pdev->dev.dma_mask = dma_mask;
 
-	/* Update peer npu devices */
-	pnv_npu_try_dma_set_bypass(pdev, bypass);
-
-	return 0;
+	return false;
 }
 
-static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-	struct pnv_ioda_pe *pe;
-	u64 end, mask;
-
-	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
-		return 0;
-
-	pe = &phb->ioda.pe_array[pdn->pe_number];
-	if (!pe->tce_bypass_enabled)
-		return __dma_get_required_mask(&pdev->dev);
-
-
-	end = pe->tce_bypass_base + memblock_end_of_DRAM();
-	mask = 1ULL << (fls64(end) - 1);
-	mask += mask - 1;
-
-	return mask;
-}
-
-static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
-				   struct pci_bus *bus,
-				   bool add_to_group)
+static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
-		set_dma_offset(&dev->dev, pe->tce_bypass_base);
-		if (add_to_group)
-			iommu_add_device(&dev->dev);
+		dev->dev.archdata.dma_offset = pe->tce_bypass_base;
 
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
-			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
-					add_to_group);
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
 	}
 }
 
@@ -2001,26 +1939,12 @@
 }
 
 #ifdef CONFIG_IOMMU_API
-static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction)
+/* Common for IODA1 and IODA2 */
+static int pnv_ioda_tce_xchg_no_kill(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction,
+		bool realmode)
 {
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);
-
-	if (!ret)
-		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, false);
-
-	return ret;
-}
-
-static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction)
-{
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);
-
-	if (!ret)
-		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);
-
-	return ret;
+	return pnv_tce_xchg(tbl, index, hpa, direction, !realmode);
 }
 #endif
 
@@ -2035,8 +1959,8 @@
 static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 	.set = pnv_ioda1_tce_build,
 #ifdef CONFIG_IOMMU_API
-	.exchange = pnv_ioda1_tce_xchg,
-	.exchange_rm = pnv_ioda1_tce_xchg_rm,
+	.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,
@@ -2165,30 +2089,6 @@
 	return ret;
 }
 
-#ifdef CONFIG_IOMMU_API
-static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction)
-{
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);
-
-	if (!ret)
-		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false);
-
-	return ret;
-}
-
-static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction)
-{
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);
-
-	if (!ret)
-		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);
-
-	return ret;
-}
-#endif
-
 static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 		long npages)
 {
@@ -2200,8 +2100,8 @@
 static struct iommu_table_ops pnv_ioda2_iommu_ops = {
 	.set = pnv_ioda2_tce_build,
 #ifdef CONFIG_IOMMU_API
-	.exchange = pnv_ioda2_tce_xchg,
-	.exchange_rm = pnv_ioda2_tce_xchg_rm,
+	.xchg_no_kill = pnv_ioda_tce_xchg_no_kill,
+	.tce_kill = pnv_pci_ioda2_tce_invalidate,
 	.useraddrptr = pnv_tce_useraddrptr,
 #endif
 	.clear = pnv_ioda2_tce_free,
@@ -2347,8 +2247,8 @@
 					      __pa(addr) + tce32_segsz * i,
 					      tce32_segsz, IOMMU_PAGE_SIZE_4K);
 		if (rc) {
-			pe_err(pe, " Failed to configure 32-bit TCE table,"
-			       " err %ld\n", rc);
+			pe_err(pe, " Failed to configure 32-bit TCE table, err %lld\n",
+			       rc);
 			goto fail;
 		}
 	}
@@ -2365,18 +2265,10 @@
 	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;
-	iommu_init_table(tbl, phb->hose->node);
+	iommu_init_table(tbl, phb->hose->node, 0, 0);
 
-	if (pe->flags & PNV_IODA_PE_DEV) {
-		/*
-		 * Setting table base here only for carrying iommu_group
-		 * further down to let iommu_add_device() do the job.
-		 * pnv_pci_ioda_dma_dev_setup will override it later anyway.
-		 */
-		set_iommu_table_base(&pe->pdev->dev, tbl);
-		iommu_add_device(&pe->pdev->dev);
-	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+	if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
 	return;
  fail:
@@ -2401,9 +2293,9 @@
 	const __u64 start_addr = tbl->it_offset << tbl->it_page_shift;
 	const __u64 win_size = tbl->it_size << tbl->it_page_shift;
 
-	pe_info(pe, "Setting up window#%d %llx..%llx pg=%x\n", num,
-			start_addr, start_addr + win_size - 1,
-			IOMMU_PAGE_SIZE(tbl));
+	pe_info(pe, "Setting up window#%d %llx..%llx pg=%lx\n",
+		num, start_addr, start_addr + win_size - 1,
+		IOMMU_PAGE_SIZE(tbl));
 
 	/*
 	 * Map TCE table through TVT. The TVE index is the PE number
@@ -2417,7 +2309,7 @@
 			size << 3,
 			IOMMU_PAGE_SIZE(tbl));
 	if (rc) {
-		pe_err(pe, "Failed to configure TCE table, err %ld\n", rc);
+		pe_err(pe, "Failed to configure TCE table, err %lld\n", rc);
 		return rc;
 	}
 
@@ -2428,7 +2320,7 @@
 	return 0;
 }
 
-void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
+static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
 {
 	uint16_t window_id = (pe->pe_number << 1 ) + 1;
 	int64_t rc;
@@ -2490,6 +2382,7 @@
 {
 	struct iommu_table *tbl = NULL;
 	long rc;
+	unsigned long res_start, res_end;
 
 	/*
 	 * crashkernel= specifies the kdump kernel's maximum memory at
@@ -2503,19 +2396,46 @@
 	 * DMA window can be larger than available memory, which will
 	 * cause errors later.
 	 */
-	const u64 window_size = min((u64)pe->table_group.tce32_size, max_memory);
+	const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_ORDER - 1);
 
-	rc = pnv_pci_ioda2_create_table(&pe->table_group, 0,
-			IOMMU_PAGE_SHIFT_4K,
-			window_size,
-			POWERNV_IOMMU_DEFAULT_LEVELS, false, &tbl);
+	/*
+	 * We create the default window as big as we can. The constraint is
+	 * the max order of allocation possible. The TCE table is likely to
+	 * end up being multilevel and with on-demand allocation in place,
+	 * the initial use is not going to be huge as the default window aims
+	 * to support crippled devices (i.e. not fully 64bit DMAble) only.
+	 */
+	/* iommu_table::it_map uses 1 bit per IOMMU page, hence 8 */
+	const u64 window_size = min((maxblock * 8) << PAGE_SHIFT, max_memory);
+	/* Each TCE level cannot exceed maxblock so go multilevel if needed */
+	unsigned long tces_order = ilog2(window_size >> PAGE_SHIFT);
+	unsigned long tcelevel_order = ilog2(maxblock >> 3);
+	unsigned int levels = tces_order / tcelevel_order;
+
+	if (tces_order % tcelevel_order)
+		levels += 1;
+	/*
+	 * We try to stick to default levels (which is >1 at the moment) in
+	 * order to save memory by relying on on-demain TCE level allocation.
+	 */
+	levels = max_t(unsigned int, levels, POWERNV_IOMMU_DEFAULT_LEVELS);
+
+	rc = pnv_pci_ioda2_create_table(&pe->table_group, 0, PAGE_SHIFT,
+			window_size, levels, false, &tbl);
 	if (rc) {
 		pe_err(pe, "Failed to create 32-bit TCE table, err %ld",
 				rc);
 		return rc;
 	}
 
-	iommu_init_table(tbl, pe->phb->hose->node);
+	/* We use top part of 32bit space for MMIO so exclude it from DMA */
+	res_start = 0;
+	res_end = 0;
+	if (window_size > pe->phb->ioda.m32_pci_base) {
+		res_start = pe->phb->ioda.m32_pci_base >> tbl->it_page_shift;
+		res_end = min(window_size, SZ_4G) >> tbl->it_page_shift;
+	}
+	iommu_init_table(tbl, pe->phb->hose->node, res_start, res_end);
 
 	rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
 	if (rc) {
@@ -2529,11 +2449,11 @@
 		pnv_pci_ioda2_set_bypass(pe, true);
 
 	/*
-	 * Setting table base here only for carrying iommu_group
-	 * further down to let iommu_add_device() do the job.
-	 * pnv_pci_ioda_dma_dev_setup will override it later anyway.
+	 * Set table base for the case of IOMMU DMA use. Usually this is done
+	 * from dma_dev_setup() which is not called when a device is returned
+	 * from VFIO so do it here.
 	 */
-	if (pe->flags & PNV_IODA_PE_DEV)
+	if (pe->pdev)
 		set_iommu_table_base(&pe->pdev->dev, tbl);
 
 	return 0;
@@ -2566,7 +2486,7 @@
 #endif
 
 #ifdef CONFIG_IOMMU_API
-static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
+unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
 		__u64 window_size, __u32 levels)
 {
 	unsigned long bytes = 0;
@@ -2603,8 +2523,13 @@
 		int num, __u32 page_shift, __u64 window_size, __u32 levels,
 		struct iommu_table **ptbl)
 {
-	return pnv_pci_ioda2_create_table(table_group,
+	long ret = pnv_pci_ioda2_create_table(table_group,
 			num, page_shift, window_size, levels, true, ptbl);
+
+	if (!ret)
+		(*ptbl)->it_allocated_size = pnv_pci_ioda2_get_table_size(
+				page_shift, window_size, levels);
+	return ret;
 }
 
 static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
@@ -2617,7 +2542,9 @@
 	pnv_pci_ioda2_set_bypass(pe, false);
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (pe->pbus)
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+	else if (pe->pdev)
+		set_iommu_table_base(&pe->pdev->dev, NULL);
 	iommu_tce_table_put(tbl);
 }
 
@@ -2628,7 +2555,7 @@
 
 	pnv_pci_ioda2_setup_default_config(pe);
 	if (pe->pbus)
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 }
 
 static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
@@ -2640,131 +2567,101 @@
 	.release_ownership = pnv_ioda2_release_ownership,
 };
 
-static int gpe_table_group_to_npe_cb(struct device *dev, void *opaque)
-{
-	struct pci_controller *hose;
-	struct pnv_phb *phb;
-	struct pnv_ioda_pe **ptmppe = opaque;
-	struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-
-	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
-		return 0;
-
-	hose = pci_bus_to_host(pdev->bus);
-	phb = hose->private_data;
-	if (phb->type != PNV_PHB_NPU_NVLINK)
-		return 0;
-
-	*ptmppe = &phb->ioda.pe_array[pdn->pe_number];
-
-	return 1;
-}
-
-/*
- * This returns PE of associated NPU.
- * This assumes that NPU is in the same IOMMU group with GPU and there is
- * no other PEs.
- */
-static struct pnv_ioda_pe *gpe_table_group_to_npe(
-		struct iommu_table_group *table_group)
-{
-	struct pnv_ioda_pe *npe = NULL;
-	int ret = iommu_group_for_each_dev(table_group->group, &npe,
-			gpe_table_group_to_npe_cb);
-
-	BUG_ON(!ret || !npe);
-
-	return npe;
-}
-
-static long pnv_pci_ioda2_npu_set_window(struct iommu_table_group *table_group,
-		int num, struct iommu_table *tbl)
-{
-	struct pnv_ioda_pe *npe = gpe_table_group_to_npe(table_group);
-	int num2 = (num == 0) ? 1 : 0;
-	long ret = pnv_pci_ioda2_set_window(table_group, num, tbl);
-
-	if (ret)
-		return ret;
-
-	if (table_group->tables[num2])
-		pnv_npu_unset_window(npe, num2);
-
-	ret = pnv_npu_set_window(npe, num, tbl);
-	if (ret) {
-		pnv_pci_ioda2_unset_window(table_group, num);
-		if (table_group->tables[num2])
-			pnv_npu_set_window(npe, num2,
-					table_group->tables[num2]);
-	}
-
-	return ret;
-}
-
-static long pnv_pci_ioda2_npu_unset_window(
+static void pnv_ioda_setup_bus_iommu_group_add_devices(struct pnv_ioda_pe *pe,
 		struct iommu_table_group *table_group,
-		int num)
+		struct pci_bus *bus)
 {
-	struct pnv_ioda_pe *npe = gpe_table_group_to_npe(table_group);
-	int num2 = (num == 0) ? 1 : 0;
-	long ret = pnv_pci_ioda2_unset_window(table_group, num);
+	struct pci_dev *dev;
 
-	if (ret)
-		return ret;
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		iommu_add_device(table_group, &dev->dev);
 
-	if (!npe->table_group.tables[num])
-		return 0;
-
-	ret = pnv_npu_unset_window(npe, num);
-	if (ret)
-		return ret;
-
-	if (table_group->tables[num2])
-		ret = pnv_npu_set_window(npe, num2, table_group->tables[num2]);
-
-	return ret;
+		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
+			pnv_ioda_setup_bus_iommu_group_add_devices(pe,
+					table_group, dev->subordinate);
+	}
 }
 
-static void pnv_ioda2_npu_take_ownership(struct iommu_table_group *table_group)
+static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe,
+		struct iommu_table_group *table_group, struct pci_bus *bus)
 {
-	/*
-	 * Detach NPU first as pnv_ioda2_take_ownership() will destroy
-	 * the iommu_table if 32bit DMA is enabled.
-	 */
-	pnv_npu_take_ownership(gpe_table_group_to_npe(table_group));
-	pnv_ioda2_take_ownership(table_group);
+
+	if (pe->flags & PNV_IODA_PE_DEV)
+		iommu_add_device(table_group, &pe->pdev->dev);
+
+	if ((pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) || bus)
+		pnv_ioda_setup_bus_iommu_group_add_devices(pe, table_group,
+				bus);
 }
 
-static struct iommu_table_group_ops pnv_pci_ioda2_npu_ops = {
-	.get_table_size = pnv_pci_ioda2_get_table_size,
-	.create_table = pnv_pci_ioda2_create_table_userspace,
-	.set_window = pnv_pci_ioda2_npu_set_window,
-	.unset_window = pnv_pci_ioda2_npu_unset_window,
-	.take_ownership = pnv_ioda2_npu_take_ownership,
-	.release_ownership = pnv_ioda2_release_ownership,
-};
+static unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb);
 
 static void pnv_pci_ioda_setup_iommu_api(void)
 {
-	struct pci_controller *hose, *tmp;
+	struct pci_controller *hose;
 	struct pnv_phb *phb;
-	struct pnv_ioda_pe *pe, *gpe;
+	struct pnv_ioda_pe *pe;
+
+	/*
+	 * There are 4 types of PEs:
+	 * - PNV_IODA_PE_BUS: a downstream port with an adapter,
+	 *   created from pnv_pci_setup_bridge();
+	 * - PNV_IODA_PE_BUS_ALL: a PCI-PCIX bridge with devices behind it,
+	 *   created from pnv_pci_setup_bridge();
+	 * - PNV_IODA_PE_VF: a SRIOV virtual function,
+	 *   created from pnv_pcibios_sriov_enable();
+	 * - PNV_IODA_PE_DEV: an NPU or OCAPI device,
+	 *   created from pnv_pci_ioda_fixup().
+	 *
+	 * Normally a PE is represented by an IOMMU group, however for
+	 * devices with side channels the groups need to be more strict.
+	 */
+	list_for_each_entry(hose, &hose_list, list_node) {
+		phb = hose->private_data;
+
+		if (phb->type == PNV_PHB_NPU_NVLINK ||
+		    phb->type == PNV_PHB_NPU_OCAPI)
+			continue;
+
+		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+			struct iommu_table_group *table_group;
+
+			table_group = pnv_try_setup_npu_table_group(pe);
+			if (!table_group) {
+				if (!pnv_pci_ioda_pe_dma_weight(pe))
+					continue;
+
+				table_group = &pe->table_group;
+				iommu_register_group(&pe->table_group,
+						pe->phb->hose->global_number,
+						pe->pe_number);
+			}
+			pnv_ioda_setup_bus_iommu_group(pe, table_group,
+					pe->pbus);
+		}
+	}
 
 	/*
 	 * Now we have all PHBs discovered, time to add NPU devices to
 	 * the corresponding IOMMU groups.
 	 */
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+	list_for_each_entry(hose, &hose_list, list_node) {
+		unsigned long  pgsizes;
+
 		phb = hose->private_data;
 
 		if (phb->type != PNV_PHB_NPU_NVLINK)
 			continue;
 
+		pgsizes = pnv_ioda_parse_tce_sizes(phb);
 		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
-			gpe = pnv_pci_npu_setup_iommu(pe);
-			if (gpe)
-				gpe->table_group.ops = &pnv_pci_ioda2_npu_ops;
+			/*
+			 * IODA2 bridges get this set up from
+			 * pci_controller_ops::setup_bridge but NPU bridges
+			 * do not have this hook defined so we do it here.
+			 */
+			pe->table_group.pgsizes = pgsizes;
+			pnv_npu_compound_attach(pe);
 		}
 	}
 }
@@ -2811,9 +2708,6 @@
 	/* TVE #1 is selected by PCI address bit 59 */
 	pe->tce_bypass_base = 1ull << 59;
 
-	iommu_register_group(&pe->table_group, phb->hose->global_number,
-			pe->pe_number);
-
 	/* The PE will reserve all possible 32-bits space */
 	pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
 		phb->ioda.m32_pci_base);
@@ -2834,10 +2728,9 @@
 		return;
 
 	if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 }
 
-#ifdef CONFIG_PCI_MSI
 int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq)
 {
 	struct pnv_phb *phb = container_of(chip, struct pnv_phb,
@@ -2983,9 +2876,6 @@
 	pr_info("  Allocated bitmap for %d MSIs (base IRQ 0x%x)\n",
 		count, phb->msi_base);
 }
-#else
-static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { }
-#endif /* CONFIG_PCI_MSI */
 
 #ifdef CONFIG_PCI_IOV
 static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
@@ -3403,8 +3293,7 @@
 		return;
 
 	/* Reserve PEs according to used M64 resources */
-	if (phb->reserve_m64_pe)
-		phb->reserve_m64_pe(bus, NULL, all);
+	pnv_ioda_reserve_m64_pe(bus, NULL, all);
 
 	/*
 	 * Assign PE. We might run here because of partial hotplug.
@@ -3560,7 +3449,7 @@
 #ifdef CONFIG_IOMMU_API
 	rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (rc)
-		pe_warn(pe, "OPAL error %ld release DMA window\n", rc);
+		pe_warn(pe, "OPAL error %lld release DMA window\n", rc);
 #endif
 
 	pnv_pci_ioda2_set_bypass(pe, false);
@@ -3594,7 +3483,7 @@
 					phb->ioda.reserved_pe_idx, win, 0, idx);
 
 		if (rc != OPAL_SUCCESS)
-			pe_warn(pe, "Error %ld unmapping (%d) segment#%d\n",
+			pe_warn(pe, "Error %lld unmapping (%d) segment#%d\n",
 				rc, win, idx);
 
 		map[idx] = IODA_INVALID_PE;
@@ -3688,6 +3577,15 @@
 		pnv_ioda_release_pe(pe);
 }
 
+static void pnv_npu_disable_device(struct pci_dev *pdev)
+{
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+	struct eeh_pe *eehpe = edev ? edev->pe : NULL;
+
+	if (eehpe && eeh_ops && eeh_ops->reset)
+		eeh_ops->reset(eehpe, EEH_RESET_HOT);
+}
+
 static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;
@@ -3699,39 +3597,26 @@
 static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_dma_dev_setup,
 	.dma_bus_setup		= pnv_pci_dma_bus_setup,
-#ifdef CONFIG_PCI_MSI
+	.iommu_bypass_supported	= pnv_pci_ioda_iommu_bypass_supported,
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
 	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
-#endif
 	.enable_device_hook	= pnv_pci_enable_device_hook,
 	.release_device		= pnv_pci_release_device,
 	.window_alignment	= pnv_pci_window_alignment,
 	.setup_bridge		= pnv_pci_setup_bridge,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
-	.dma_set_mask		= pnv_pci_ioda_dma_set_mask,
-	.dma_get_required_mask	= pnv_pci_ioda_dma_get_required_mask,
 	.shutdown		= pnv_pci_ioda_shutdown,
 };
 
-static int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask)
-{
-	dev_err_once(&npdev->dev,
-			"%s operation unsupported for NVLink devices\n",
-			__func__);
-	return -EPERM;
-}
-
 static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_dma_dev_setup,
-#ifdef CONFIG_PCI_MSI
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
 	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
-#endif
 	.enable_device_hook	= pnv_pci_enable_device_hook,
 	.window_alignment	= pnv_pci_window_alignment,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
-	.dma_set_mask		= pnv_npu_dma_set_mask,
 	.shutdown		= pnv_pci_ioda_shutdown,
+	.disable_device		= pnv_npu_disable_device,
 };
 
 static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
@@ -3770,7 +3655,10 @@
 	phb_id = be64_to_cpup(prop64);
 	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);
 
-	phb = memblock_virt_alloc(sizeof(*phb), 0);
+	phb = memblock_alloc(sizeof(*phb), SMP_CACHE_BYTES);
+	if (!phb)
+		panic("%s: Failed to allocate %zu bytes\n", __func__,
+		      sizeof(*phb));
 
 	/* Allocate PCI controller */
 	phb->hose = hose = pcibios_alloc_controller(np);
@@ -3816,7 +3704,10 @@
 	else
 		phb->diag_data_size = PNV_PCI_DIAG_BUF_SIZE;
 
-	phb->diag_data = memblock_virt_alloc(phb->diag_data_size, 0);
+	phb->diag_data = memblock_alloc(phb->diag_data_size, SMP_CACHE_BYTES);
+	if (!phb->diag_data)
+		panic("%s: Failed to allocate %u bytes\n", __func__,
+		      phb->diag_data_size);
 
 	/* Parse 32-bit and IO ranges (if any) */
 	pci_process_bridge_OF_ranges(hose, np, !hose->global_number);
@@ -3875,7 +3766,9 @@
 	}
 	pemap_off = size;
 	size += phb->ioda.total_pe_num * sizeof(struct pnv_ioda_pe);
-	aux = memblock_virt_alloc(size, 0);
+	aux = memblock_alloc(size, SMP_CACHE_BYTES);
+	if (!aux)
+		panic("%s: Failed to allocate %lu bytes\n", __func__, size);
 	phb->ioda.pe_alloc = aux;
 	phb->ioda.m64_segmap = aux + m64map_off;
 	phb->ioda.m32_segmap = aux + m32map_off;
@@ -3987,9 +3880,12 @@
 	 * shutdown PCI devices correctly. We already got IODA table
 	 * cleaned out. So we have to issue PHB reset to stop all PCI
 	 * transactions from previous kernel. The ppc_pci_reset_phbs
-	 * kernel parameter will force this reset too.
+	 * kernel parameter will force this reset too. Additionally,
+	 * if the IODA reset above failed then use a bigger hammer.
+	 * This can happen if we get a PHB fatal error in very early
+	 * boot.
 	 */
-	if (is_kdump_kernel() || pci_reset_phbs) {
+	if (is_kdump_kernel() || pci_reset_phbs || rc) {
 		pr_info("  Issue PHB reset ...\n");
 		pnv_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL);
 		pnv_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE);
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 13aef23..2825d00 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Support PCI/PCIe on PowerNV platforms
  *
  * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -38,7 +34,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-static DEFINE_MUTEX(p2p_mutex);
 static DEFINE_MUTEX(tunnel_mutex);
 
 int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
@@ -59,7 +54,8 @@
 			break;
 		}
 
-		if (!of_device_is_compatible(parent, "ibm,ioda2-phb")) {
+		if (!of_device_is_compatible(parent, "ibm,ioda2-phb") &&
+		    !of_device_is_compatible(parent, "ibm,ioda3-phb")) {
 			of_node_put(parent);
 			continue;
 		}
@@ -160,7 +156,6 @@
 }
 EXPORT_SYMBOL_GPL(pnv_pci_set_power_state);
 
-#ifdef CONFIG_PCI_MSI
 int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
@@ -229,7 +224,6 @@
 		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, 1);
 	}
 }
-#endif /* CONFIG_PCI_MSI */
 
 /* Nicely print the contents of the PE State Tables (PEST). */
 static void pnv_pci_dump_pest(__be64 pestA[], __be64 pestB[], int pest_size)
@@ -602,8 +596,8 @@
 static void pnv_pci_config_check_eeh(struct pci_dn *pdn)
 {
 	struct pnv_phb *phb = pdn->phb->private_data;
-	u8	fstate;
-	__be16	pcierr;
+	u8	fstate = 0;
+	__be16	pcierr = 0;
 	unsigned int pe_no;
 	s64	rc;
 
@@ -863,79 +857,6 @@
 	}
 }
 
-int pnv_pci_set_p2p(struct pci_dev *initiator, struct pci_dev *target, u64 desc)
-{
-	struct pci_controller *hose;
-	struct pnv_phb *phb_init, *phb_target;
-	struct pnv_ioda_pe *pe_init;
-	int rc;
-
-	if (!opal_check_token(OPAL_PCI_SET_P2P))
-		return -ENXIO;
-
-	hose = pci_bus_to_host(initiator->bus);
-	phb_init = hose->private_data;
-
-	hose = pci_bus_to_host(target->bus);
-	phb_target = hose->private_data;
-
-	pe_init = pnv_ioda_get_pe(initiator);
-	if (!pe_init)
-		return -ENODEV;
-
-	/*
-	 * Configuring the initiator's PHB requires to adjust its
-	 * TVE#1 setting. Since the same device can be an initiator
-	 * several times for different target devices, we need to keep
-	 * a reference count to know when we can restore the default
-	 * bypass setting on its TVE#1 when disabling. Opal is not
-	 * tracking PE states, so we add a reference count on the PE
-	 * in linux.
-	 *
-	 * For the target, the configuration is per PHB, so we keep a
-	 * target reference count on the PHB.
-	 */
-	mutex_lock(&p2p_mutex);
-
-	if (desc & OPAL_PCI_P2P_ENABLE) {
-		/* always go to opal to validate the configuration */
-		rc = opal_pci_set_p2p(phb_init->opal_id, phb_target->opal_id,
-				      desc, pe_init->pe_number);
-
-		if (rc != OPAL_SUCCESS) {
-			rc = -EIO;
-			goto out;
-		}
-
-		pe_init->p2p_initiator_count++;
-		phb_target->p2p_target_count++;
-	} else {
-		if (!pe_init->p2p_initiator_count ||
-			!phb_target->p2p_target_count) {
-			rc = -EINVAL;
-			goto out;
-		}
-
-		if (--pe_init->p2p_initiator_count == 0)
-			pnv_pci_ioda2_set_bypass(pe_init, true);
-
-		if (--phb_target->p2p_target_count == 0) {
-			rc = opal_pci_set_p2p(phb_init->opal_id,
-					      phb_target->opal_id, desc,
-					      pe_init->pe_number);
-			if (rc != OPAL_SUCCESS) {
-				rc = -EIO;
-				goto out;
-			}
-		}
-	}
-	rc = 0;
-out:
-	mutex_unlock(&p2p_mutex);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(pnv_pci_set_p2p);
-
 struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
@@ -944,54 +865,6 @@
 }
 EXPORT_SYMBOL(pnv_pci_get_phb_node);
 
-int pnv_pci_enable_tunnel(struct pci_dev *dev, u64 *asnind)
-{
-	struct device_node *np;
-	const __be32 *prop;
-	struct pnv_ioda_pe *pe;
-	uint16_t window_id;
-	int rc;
-
-	if (!radix_enabled())
-		return -ENXIO;
-
-	if (!(np = pnv_pci_get_phb_node(dev)))
-		return -ENXIO;
-
-	prop = of_get_property(np, "ibm,phb-indications", NULL);
-	of_node_put(np);
-
-	if (!prop || !prop[1])
-		return -ENXIO;
-
-	*asnind = (u64)be32_to_cpu(prop[1]);
-	pe = pnv_ioda_get_pe(dev);
-	if (!pe)
-		return -ENODEV;
-
-	/* Increase real window size to accept as_notify messages. */
-	window_id = (pe->pe_number << 1 ) + 1;
-	rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, pe->pe_number,
-					     window_id, pe->tce_bypass_base,
-					     (uint64_t)1 << 48);
-	return opal_error_code(rc);
-}
-EXPORT_SYMBOL_GPL(pnv_pci_enable_tunnel);
-
-int pnv_pci_disable_tunnel(struct pci_dev *dev)
-{
-	struct pnv_ioda_pe *pe;
-
-	pe = pnv_ioda_get_pe(dev);
-	if (!pe)
-		return -ENODEV;
-
-	/* Restore default real window size. */
-	pnv_pci_ioda2_set_bypass(pe, true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pnv_pci_disable_tunnel);
-
 int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable)
 {
 	__be64 val;
@@ -1046,29 +919,6 @@
 }
 EXPORT_SYMBOL_GPL(pnv_pci_set_tunnel_bar);
 
-#ifdef CONFIG_PPC64	/* for thread.tidr */
-int pnv_pci_get_as_notify_info(struct task_struct *task, u32 *lpid, u32 *pid,
-			       u32 *tid)
-{
-	struct mm_struct *mm = NULL;
-
-	if (task == NULL)
-		return -EINVAL;
-
-	mm = get_task_mm(task);
-	if (mm == NULL)
-		return -EINVAL;
-
-	*pid = mm->context.id;
-	mmput(mm);
-
-	*tid = task->thread.tidr;
-	*lpid = mfspr(SPRN_LPID);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pnv_pci_get_as_notify_info);
-#endif
-
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
@@ -1127,4 +977,47 @@
 	set_pci_dma_ops(&dma_iommu_ops);
 }
 
-machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init);
+static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb,
+		unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct pci_dev *pdev;
+	struct pci_dn *pdn;
+	struct pnv_ioda_pe *pe;
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		pdev = to_pci_dev(dev);
+		pdn = pci_get_pdn(pdev);
+		hose = pci_bus_to_host(pdev->bus);
+		phb = hose->private_data;
+
+		WARN_ON_ONCE(!phb);
+		if (!pdn || pdn->pe_number == IODA_INVALID_PE || !phb)
+			return 0;
+
+		pe = &phb->ioda.pe_array[pdn->pe_number];
+		if (!pe->table_group.group)
+			return 0;
+		iommu_add_device(&pe->table_group, dev);
+		return 0;
+	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 8b37b28..f914f0b 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -2,15 +2,13 @@
 #ifndef __POWERNV_PCI_H
 #define __POWERNV_PCI_H
 
+#include <linux/compiler.h>		/* for __printf */
 #include <linux/iommu.h>
 #include <asm/iommu.h>
 #include <asm/msi_bitmap.h>
 
 struct pci_dn;
 
-/* Maximum possible number of ATSD MMIO registers per NPU */
-#define NV_NMMU_ATSD_REGS 8
-
 enum pnv_phb_type {
 	PNV_PHB_IODA1		= 0,
 	PNV_PHB_IODA2		= 1,
@@ -65,6 +63,7 @@
 
 	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
 	struct iommu_table_group table_group;
+	struct npu_comp		*npucomp;
 
 	/* 64-bit TCE bypass region */
 	bool			tce_bypass_enabled;
@@ -80,9 +79,6 @@
 	struct pnv_ioda_pe	*master;
 	struct list_head	slaves;
 
-	/* PCI peer-to-peer*/
-	int			p2p_initiator_count;
-
 	/* Link in list of PE#s */
 	struct list_head	list;
 };
@@ -106,20 +102,14 @@
 	struct dentry		*dbgfs;
 #endif
 
-#ifdef CONFIG_PCI_MSI
 	unsigned int		msi_base;
 	unsigned int		msi32_support;
 	struct msi_bitmap	msi_bmp;
-#endif
 	int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev,
 			 unsigned int hwirq, unsigned int virq,
 			 unsigned int is_64, struct msi_msg *msg);
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
-	void (*fixup_phb)(struct pci_controller *hose);
 	int (*init_m64)(struct pnv_phb *phb);
-	void (*reserve_m64_pe)(struct pci_bus *bus,
-			       unsigned long *pe_bitmap, bool all);
-	struct pnv_ioda_pe *(*pick_m64_pe)(struct pci_bus *bus, bool all);
 	int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
 	void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
 	int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt);
@@ -179,21 +169,6 @@
 	/* PHB and hub diagnostics */
 	unsigned int		diag_data_size;
 	u8			*diag_data;
-
-	/* Nvlink2 data */
-	struct npu {
-		int index;
-		__be64 *mmio_atsd_regs[NV_NMMU_ATSD_REGS];
-		unsigned int mmio_atsd_count;
-
-		/* Bitmask for MMIO register usage */
-		unsigned long mmio_atsd_usage;
-
-		/* Do we need to explicitly flush the nest mmu? */
-		bool nmmu_flush;
-	} npu;
-
-	int p2p_target_count;
 };
 
 extern struct pci_ops pnv_pci_ops;
@@ -210,6 +185,7 @@
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_init_npu_phb(struct device_node *np);
 extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np);
+extern void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
@@ -219,9 +195,11 @@
 extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
 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 void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
+extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
+		__u64 window_size, __u32 levels);
 extern int pnv_eeh_post_init(void);
 
+__printf(3, 4)
 extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 			    const char *fmt, ...);
 #define pe_err(pe, fmt, ...)					\
@@ -235,15 +213,13 @@
 extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass);
 extern void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
 extern struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe);
-extern long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
-		struct iommu_table *tbl);
-extern long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num);
-extern void pnv_npu_take_ownership(struct pnv_ioda_pe *npe);
-extern void pnv_npu_release_ownership(struct pnv_ioda_pe *npe);
-extern int pnv_npu2_init(struct pnv_phb *phb);
+extern struct iommu_table_group *pnv_try_setup_npu_table_group(
+		struct pnv_ioda_pe *pe);
+extern struct iommu_table_group *pnv_npu_compound_attach(
+		struct pnv_ioda_pe *pe);
 
 /* pci-ioda-tce.c */
-#define POWERNV_IOMMU_DEFAULT_LEVELS	1
+#define POWERNV_IOMMU_DEFAULT_LEVELS	2
 #define POWERNV_IOMMU_MAX_LEVELS	5
 
 extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index fd4a1c5..1aa51c4 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -30,4 +30,9 @@
 
 bool cpu_core_split_required(void);
 
+struct memcons;
+ssize_t memcons_copy(struct memcons *mc, char *to, loff_t pos, size_t count);
+u32 memcons_get_size(struct memcons *mc);
+struct memcons *memcons_init(struct device_node *node, const char *mc_prop_name);
+
 #endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c
index 718f50e..8035caf 100644
--- a/arch/powerpc/platforms/powernv/rng.c
+++ b/arch/powerpc/platforms/powernv/rng.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2013, Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)	"powernv-rng: " fmt
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index adddde0..8349860 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerNV setup code.
  *
  * Copyright 2011 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
@@ -28,6 +24,7 @@
 #include <linux/bug.h>
 #include <linux/pci.h>
 #include <linux/cpufreq.h>
+#include <linux/memblock.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
@@ -170,6 +167,14 @@
 	else
 #endif
 		add_preferred_console("hvc", 0, NULL);
+
+	if (!radix_enabled()) {
+		int i;
+
+		/* Allocate per cpu area to save old slb contents during MCE */
+		for_each_possible_cpu(i)
+			paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i));
+	}
 }
 
 static void __init pnv_init_IRQ(void)
@@ -219,17 +224,41 @@
 
 static void  __noreturn pnv_restart(char *cmd)
 {
-	long rc = OPAL_BUSY;
+	long rc;
 
 	pnv_prepare_going_down();
 
-	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		rc = opal_cec_reboot();
-		if (rc == OPAL_BUSY_EVENT)
-			opal_poll_events(NULL);
+	do {
+		if (!cmd)
+			rc = opal_cec_reboot();
+		else if (strcmp(cmd, "full") == 0)
+			rc = opal_cec_reboot2(OPAL_REBOOT_FULL_IPL, NULL);
 		else
+			rc = OPAL_UNSUPPORTED;
+
+		if (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+			/* Opal is busy wait for some time and retry */
+			opal_poll_events(NULL);
 			mdelay(10);
-	}
+
+		} else	if (cmd && rc) {
+			/* Unknown error while issuing reboot */
+			if (rc == OPAL_UNSUPPORTED)
+				pr_err("Unsupported '%s' reboot.\n", cmd);
+			else
+				pr_err("Unable to issue '%s' reboot. Err=%ld\n",
+				       cmd, rc);
+			pr_info("Forcing a cec-reboot\n");
+			cmd = NULL;
+			rc = OPAL_BUSY;
+
+		} else if (rc != OPAL_SUCCESS) {
+			/* Unknown error while issuing cec-reboot */
+			pr_err("Unable to reboot. Err=%ld\n", rc);
+		}
+
+	} while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT);
+
 	for (;;)
 		opal_poll_events(NULL);
 }
@@ -377,7 +406,10 @@
 	/* ppc_md.system_reset_exception gets filled in by pnv_smp_init() */
 	ppc_md.machine_check_exception = opal_machine_check;
 	ppc_md.mce_check_early_recovery = opal_mce_check_early_recovery;
-	ppc_md.hmi_exception_early = opal_hmi_exception_early;
+	if (opal_check_token(OPAL_HANDLE_HMI2))
+		ppc_md.hmi_exception_early = opal_hmi_exception_early2;
+	else
+		ppc_md.hmi_exception_early = opal_hmi_exception_early;
 	ppc_md.handle_hmi_exception = opal_handle_hmi_exception;
 }
 
@@ -437,6 +469,16 @@
 	return ret_freq;
 }
 
+static long pnv_machine_check_early(struct pt_regs *regs)
+{
+	long handled = 0;
+
+	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
+		handled = cur_cpu_spec->machine_check_early(regs);
+
+	return handled;
+}
+
 define_machine(powernv) {
 	.name			= "PowerNV",
 	.probe			= pnv_probe,
@@ -448,6 +490,7 @@
 	.machine_shutdown	= pnv_shutdown,
 	.power_save             = NULL,
 	.calibrate_decr		= generic_calibrate_decr,
+	.machine_check_early	= pnv_machine_check_early,
 #ifdef CONFIG_KEXEC_CORE
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 0d354e1..13e2516 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SMP support for PowerNV machines.
  *
  * Copyright 2011 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -39,6 +35,7 @@
 #include <asm/cpuidle.h>
 #include <asm/kexec.h>
 #include <asm/reg.h>
+#include <asm/powernv.h>
 
 #include "powernv.h"
 
@@ -149,19 +146,25 @@
 	return 0;
 }
 
+static void pnv_flush_interrupts(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (xive_enabled())
+			xive_flush_interrupt();
+		else
+			icp_opal_flush_interrupt();
+	} else {
+		icp_native_flush_interrupt();
+	}
+}
+
 static void pnv_smp_cpu_kill_self(void)
 {
+	unsigned long srr1, unexpected_mask, wmask;
 	unsigned int cpu;
-	unsigned long srr1, wmask;
+	u64 lpcr_val;
 
 	/* Standard hot unplug procedure */
-	/*
-	 * This hard disables local interurpts, ensuring we have no lazy
-	 * irqs pending.
-	 */
-	WARN_ON(irqs_disabled());
-	hard_irq_disable();
-	WARN_ON(lazy_irq_pending());
 
 	idle_task_exit();
 	current->active_mm = NULL; /* for sanity */
@@ -174,6 +177,40 @@
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		wmask = SRR1_WAKEMASK_P8;
 
+	/*
+	 * This turns the irq soft-disabled state we're called with, into a
+	 * hard-disabled state with pending irq_happened interrupts cleared.
+	 *
+	 * PACA_IRQ_DEC   - Decrementer should be ignored.
+	 * PACA_IRQ_HMI   - Can be ignored, processing is done in real mode.
+	 * PACA_IRQ_DBELL, EE, PMI - Unexpected.
+	 */
+	hard_irq_disable();
+	if (generic_check_cpu_restart(cpu))
+		goto out;
+
+	unexpected_mask = ~(PACA_IRQ_DEC | PACA_IRQ_HMI | PACA_IRQ_HARD_DIS);
+	if (local_paca->irq_happened & unexpected_mask) {
+		if (local_paca->irq_happened & PACA_IRQ_EE)
+			pnv_flush_interrupts();
+		DBG("CPU%d Unexpected exit while offline irq_happened=%lx!\n",
+				cpu, local_paca->irq_happened);
+	}
+	local_paca->irq_happened = PACA_IRQ_HARD_DIS;
+
+	/*
+	 * We don't want to take decrementer interrupts while we are
+	 * offline, so clear LPCR:PECE1. We keep PECE2 (and
+	 * LPCR_PECE_HVEE on P9) enabled so as to let IPIs in.
+	 *
+	 * If the CPU gets woken up by a special wakeup, ensure that
+	 * the SLW engine sets LPCR with decrementer bit cleared, else
+	 * the CPU will come back to the kernel due to a spurious
+	 * wakeup.
+	 */
+	lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
+	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
+
 	while (!generic_check_cpu_restart(cpu)) {
 		/*
 		 * Clear IPI flag, since we don't handle IPIs while
@@ -182,10 +219,11 @@
 		 * for coming online, which are handled via
 		 * generic_check_cpu_restart() calls.
 		 */
-		kvmppc_set_host_ipi(cpu, 0);
+		kvmppc_clear_host_ipi(cpu);
 
 		srr1 = pnv_cpu_offline(cpu);
 
+		WARN_ON_ONCE(!irqs_disabled());
 		WARN_ON(lazy_irq_pending());
 
 		/*
@@ -201,13 +239,7 @@
 		 */
 		if (((srr1 & wmask) == SRR1_WAKEEE) ||
 		    ((srr1 & wmask) == SRR1_WAKEHVI)) {
-			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
-				if (xive_enabled())
-					xive_flush_interrupt();
-				else
-					icp_opal_flush_interrupt();
-			} else
-				icp_native_flush_interrupt();
+			pnv_flush_interrupts();
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
@@ -246,6 +278,16 @@
 
 	}
 
+	/*
+	 * Re-enable decrementer interrupts in LPCR.
+	 *
+	 * Further, we want stop states to be woken up by decrementer
+	 * for non-hotplug cases. So program the LPCR via stop api as
+	 * well.
+	 */
+	lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
+	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
+out:
 	DBG("CPU%d coming online...\n", cpu);
 }
 
diff --git a/arch/powerpc/platforms/powernv/subcore-asm.S b/arch/powerpc/platforms/powernv/subcore-asm.S
index 39bb24a..e038f67 100644
--- a/arch/powerpc/platforms/powernv/subcore-asm.S
+++ b/arch/powerpc/platforms/powernv/subcore-asm.S
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2013, Michael (Ellerman|Neuling), IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <asm/asm-offsets.h>
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 4556300..73207b5 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2013, Michael (Ellerman|Neuling), IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)	"powernv: " fmt
@@ -183,7 +179,7 @@
 	cpu = smp_processor_id();
 	if (cpu_thread_in_core(cpu) != 0) {
 		while (mfspr(SPRN_HID0) & mask)
-			power7_idle_insn(PNV_THREAD_NAP);
+			power7_idle_type(PNV_THREAD_NAP);
 
 		per_cpu(split_state, cpu).step = SYNC_STEP_UNSPLIT;
 		return;
diff --git a/arch/powerpc/platforms/powernv/subcore.h b/arch/powerpc/platforms/powernv/subcore.h
index 84e02ae..c8f574d 100644
--- a/arch/powerpc/platforms/powernv/subcore.h
+++ b/arch/powerpc/platforms/powernv/subcore.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2013, Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /* These are ordered and tested with <= */
diff --git a/arch/powerpc/platforms/powernv/ultravisor.c b/arch/powerpc/platforms/powernv/ultravisor.c
new file mode 100644
index 0000000..e4a00ad
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/ultravisor.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ultravisor high level interfaces
+ *
+ * Copyright 2019, IBM Corporation.
+ *
+ */
+#include <linux/init.h>
+#include <linux/printk.h>
+#include <linux/of_fdt.h>
+#include <linux/of.h>
+
+#include <asm/ultravisor.h>
+#include <asm/firmware.h>
+#include <asm/machdep.h>
+
+#include "powernv.h"
+
+static struct kobject *ultravisor_kobj;
+
+int __init early_init_dt_scan_ultravisor(unsigned long node, const char *uname,
+					 int depth, void *data)
+{
+	if (!of_flat_dt_is_compatible(node, "ibm,ultravisor"))
+		return 0;
+
+	powerpc_firmware_features |= FW_FEATURE_ULTRAVISOR;
+	pr_debug("Ultravisor detected!\n");
+	return 1;
+}
+
+static struct memcons *uv_memcons;
+
+static ssize_t uv_msglog_read(struct file *file, struct kobject *kobj,
+			      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 = {
+	.attr = {.name = "msglog", .mode = 0400},
+	.read = uv_msglog_read
+};
+
+static int __init uv_init(void)
+{
+	struct device_node *node;
+
+	if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
+		return 0;
+
+	node = of_find_compatible_node(NULL, NULL, "ibm,uv-firmware");
+	if (!node)
+		return -ENODEV;
+
+	uv_memcons = memcons_init(node, "memcons");
+	if (!uv_memcons)
+		return -ENOENT;
+
+	uv_msglog_attr.size = memcons_get_size(uv_memcons);
+
+	ultravisor_kobj = kobject_create_and_add("ultravisor", firmware_kobj);
+	if (!ultravisor_kobj)
+		return -ENOMEM;
+
+	return sysfs_create_bin_file(ultravisor_kobj, &uv_msglog_attr);
+}
+machine_subsys_initcall(powernv, uv_init);
diff --git a/arch/powerpc/platforms/powernv/vas-debug.c b/arch/powerpc/platforms/powernv/vas-debug.c
index 4f7276e..09e63df 100644
--- a/arch/powerpc/platforms/powernv/vas-debug.c
+++ b/arch/powerpc/platforms/powernv/vas-debug.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2016-17 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "vas: " fmt
@@ -30,7 +26,7 @@
 	}
 }
 
-static int info_dbg_show(struct seq_file *s, void *private)
+static int info_show(struct seq_file *s, void *private)
 {
 	struct vas_window *window = s->private;
 
@@ -49,17 +45,7 @@
 	return 0;
 }
 
-static int info_dbg_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, info_dbg_show, inode->i_private);
-}
-
-static const struct file_operations info_fops = {
-	.open		= info_dbg_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(info);
 
 static inline void print_reg(struct seq_file *s, struct vas_window *win,
 			char *name, u32 reg)
@@ -67,7 +53,7 @@
 	seq_printf(s, "0x%016llx %s\n", read_hvwc_reg(win, name, reg), name);
 }
 
-static int hvwc_dbg_show(struct seq_file *s, void *private)
+static int hvwc_show(struct seq_file *s, void *private)
 {
 	struct vas_window *window = s->private;
 
@@ -115,17 +101,7 @@
 	return 0;
 }
 
-static int hvwc_dbg_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hvwc_dbg_show, inode->i_private);
-}
-
-static const struct file_operations hvwc_fops = {
-	.open		= hvwc_dbg_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(hvwc);
 
 void vas_window_free_dbgdir(struct vas_window *window)
 {
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index e59e0e6..0c0d27d 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2016-17 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "vas: " fmt
@@ -44,16 +40,6 @@
 	pr_debug("Txwin #%d: Paste addr 0x%llx\n", winid, *addr);
 }
 
-u64 vas_win_paste_addr(struct vas_window *win)
-{
-	u64 addr;
-
-	compute_paste_address(win, &addr, NULL);
-
-	return addr;
-}
-EXPORT_SYMBOL(vas_win_paste_addr);
-
 static inline void get_hvwc_mmio_bar(struct vas_window *window,
 			u64 *start, int *len)
 {
@@ -1268,12 +1254,3 @@
 	return 0;
 }
 EXPORT_SYMBOL_GPL(vas_win_close);
-
-/*
- * Return a system-wide unique window id for the window @win.
- */
-u32 vas_win_id(struct vas_window *win)
-{
-	return encode_pswid(win->vinst->vas_id, win->winid);
-}
-EXPORT_SYMBOL_GPL(vas_win_id);
diff --git a/arch/powerpc/platforms/powernv/vas.c b/arch/powerpc/platforms/powernv/vas.c
index 5a2b24c..ed9cc6d 100644
--- a/arch/powerpc/platforms/powernv/vas.c
+++ b/arch/powerpc/platforms/powernv/vas.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2016-17 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "vas: " fmt
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
index f5493db..5574aec 100644
--- a/arch/powerpc/platforms/powernv/vas.h
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2016-17 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _VAS_H
@@ -448,26 +444,6 @@
 	return in_be64(win->hvwc_map+reg);
 }
 
-/*
- * Encode/decode the Partition Send Window ID (PSWID) for a window in
- * a way that we can uniquely identify any window in the system. i.e.
- * we should be able to locate the 'struct vas_window' given the PSWID.
- *
- *	Bits	Usage
- *	0:7	VAS id (8 bits)
- *	8:15	Unused, 0 (3 bits)
- *	16:31	Window id (16 bits)
- */
-static inline u32 encode_pswid(int vasid, int winid)
-{
-	u32 pswid = 0;
-
-	pswid |= vasid << (31 - 7);
-	pswid |= winid;
-
-	return pswid;
-}
-
 static inline void decode_pswid(u32 pswid, int *vasid, int *winid)
 {
 	if (vasid)
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index 6f75255..e32406e 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -6,7 +6,7 @@
 	select USB_OHCI_LITTLE_ENDIAN
 	select USB_OHCI_BIG_ENDIAN_MMIO
 	select USB_EHCI_BIG_ENDIAN_MMIO
-	select PPC_PCI_CHOICE
+	select HAVE_PCI
 	help
 	  This option enables support for the Sony PS3 game console
 	  and other platforms using the PS3 hypervisor.  Enabling this
@@ -49,7 +49,6 @@
 config PS3_DYNAMIC_DMA
 	depends on PPC_PS3
 	bool "PS3 Platform dynamic DMA page table management"
-	default n
 	help
 	  This option will enable kernel support to take advantage of the
 	  per device dynamic DMA page table management provided by the Cell
@@ -89,7 +88,6 @@
 config PS3_REPOSITORY_WRITE
 	bool "PS3 Repository write support" if PS3_ADVANCED
 	depends on PPC_PS3
-	default n
 	help
 	  Enables support for writing to the PS3 System Repository.
 
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index e7075aa..2735ec9 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 device registration routines.
  *
  *  Copyright (C) 2007 Sony Computer Entertainment Inc.
  *  Copyright 2007 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/delay.h>
@@ -354,9 +342,7 @@
 		 repo->dev_index, repo->dev_type, port, blk_size, num_blocks,
 		 num_regions);
 
-	p = kzalloc(sizeof(struct ps3_storage_device) +
-		    num_regions * sizeof(struct ps3_storage_region),
-		    GFP_KERNEL);
+	p = kzalloc(struct_size(p, regions, num_regions), GFP_KERNEL);
 	if (!p) {
 		result = -ENOMEM;
 		goto fail_malloc;
diff --git a/arch/powerpc/platforms/ps3/exports.c b/arch/powerpc/platforms/ps3/exports.c
index 7df5b7d..1ac31ab 100644
--- a/arch/powerpc/platforms/ps3/exports.c
+++ b/arch/powerpc/platforms/ps3/exports.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 hvcall exports for modules.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #define LV1_CALL(name, in, out, num)                          \
diff --git a/arch/powerpc/platforms/ps3/gelic_udbg.c b/arch/powerpc/platforms/ps3/gelic_udbg.c
index 09bf24d..cba4f8f 100644
--- a/arch/powerpc/platforms/ps3/gelic_udbg.c
+++ b/arch/powerpc/platforms/ps3/gelic_udbg.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * udbg debug output routine via GELIC UDP broadcasts
  *
@@ -5,12 +6,6 @@
  * Copyright 2006, 2007 Sony Corporation
  * Copyright (C) 2010 Hector Martin <hector@marcansoft.com>
  * Copyright (C) 2011 Andre Heider <a.heider@gmail.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/if_ether.h>
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index cc2b281..7ddc7ec 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 pagetable management routines.
  *
  *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/ps3/hvcall.S b/arch/powerpc/platforms/ps3/hvcall.S
index 54be652..509e30a 100644
--- a/arch/powerpc/platforms/ps3/hvcall.S
+++ b/arch/powerpc/platforms/ps3/hvcall.S
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  PS3 hvcall interface.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
  *  Copyright 2003, 2004 (c) MontaVista Software, Inc.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <asm/processor.h>
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 98f8c36..78f2339 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 interrupt routines.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index 8c7009d..423be34 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 address space management.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c
index cdbfc5c..cbddd63 100644
--- a/arch/powerpc/platforms/ps3/os-area.c
+++ b/arch/powerpc/platforms/ps3/os-area.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 flash memory os area.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
@@ -205,11 +193,11 @@
  *  3) The number of seconds from 1970 to 2000.
  */
 
-struct saved_params {
+static struct saved_params {
 	unsigned int valid;
 	s64 rtc_diff;
 	unsigned int av_multi_out;
-} static saved_params;
+} saved_params;
 
 static struct property property_rtc_diff = {
 	.name = "linux,rtc_diff",
@@ -664,7 +652,7 @@
 	db_set_64(db, &os_area_db_id_rtc_diff, saved_params.rtc_diff);
 
 	count = os_area_flash_write(db, sizeof(struct os_area_db), pos);
-	if (count < sizeof(struct os_area_db)) {
+	if (count < 0 || count < sizeof(struct os_area_db)) {
 		pr_debug("%s: os_area_flash_write failed %zd\n", __func__,
 			 count);
 		error = count < 0 ? count : -EIO;
diff --git a/arch/powerpc/platforms/ps3/platform.h b/arch/powerpc/platforms/ps3/platform.h
index 9bc68f9..07bd39e 100644
--- a/arch/powerpc/platforms/ps3/platform.h
+++ b/arch/powerpc/platforms/ps3/platform.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  PS3 platform declarations.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #if !defined(_PS3_PLATFORM_H)
diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c
index e49c887..2171296 100644
--- a/arch/powerpc/platforms/ps3/repository.c
+++ b/arch/powerpc/platforms/ps3/repository.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 repository routines.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <asm/lv1call.h>
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 77a3752..8108b9b 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 platform setup routines.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
@@ -24,7 +12,7 @@
 #include <linux/root_dev.h>
 #include <linux/console.h>
 #include <linux/export.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
@@ -126,7 +114,10 @@
 	if (!p->size)
 		return;
 
-	p->address = memblock_virt_alloc(p->size, p->align);
+	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);
 
 	printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size,
 	       p->address);
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index 1d1ad5d..93b1e73 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 SMP routines.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c
index b548508..1193c29 100644
--- a/arch/powerpc/platforms/ps3/spu.c
+++ b/arch/powerpc/platforms/ps3/spu.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 Platform spu routines.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
@@ -196,10 +184,7 @@
  * setup_areas - Map the spu regions into the address space.
  *
  * The current HV requires the spu shadow regs to be mapped with the
- * PTE page protection bits set as read-only (PP=3).  This implementation
- * uses the low level __ioremap() to bypass the page protection settings
- * inforced by ioremap_prot() to get the needed PTE bits set for the
- * shadow regs.
+ * PTE page protection bits set as read-only.
  */
 
 static int __init setup_areas(struct spu *spu)
@@ -207,16 +192,14 @@
 	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(spu_pdata(spu)->shadow_addr,
-					   sizeof(struct spe_shadow),
-					   shadow_flags);
+	spu_pdata(spu)->shadow = ioremap_prot(spu_pdata(spu)->shadow_addr,
+					      sizeof(struct spe_shadow), shadow_flags);
 	if (!spu_pdata(spu)->shadow) {
 		pr_debug("%s:%d: ioremap shadow failed\n", __func__, __LINE__);
 		goto fail_ioremap;
 	}
 
-	spu->local_store = (__force void *)ioremap_prot(spu->local_store_phys,
-		LS_SIZE, pgprot_val(pgprot_noncached_wc(__pgprot(0))));
+	spu->local_store = (__force void *)ioremap_wc(spu->local_store_phys, LS_SIZE);
 
 	if (!spu->local_store) {
 		pr_debug("%s:%d: ioremap local_store failed\n",
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 5cc35d6..3542b7b 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 system bus driver.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
@@ -37,12 +25,12 @@
 };
 
 /* FIXME: need device usage counters! */
-struct {
+static struct {
 	struct mutex mutex;
 	int sb_11; /* usb 0 */
 	int sb_12; /* usb 0 */
 	int gpu;
-} static usage_hack;
+} usage_hack;
 
 static int ps3_is_device(struct ps3_system_bus_device *dev, u64 bus_id,
 			 u64 dev_id)
@@ -698,20 +686,16 @@
 	return mask >= DMA_BIT_MASK(32);
 }
 
-static u64 ps3_dma_get_required_mask(struct device *_dev)
-{
-	return DMA_BIT_MASK(32);
-}
-
 static const struct dma_map_ops ps3_sb_dma_ops = {
 	.alloc = ps3_alloc_coherent,
 	.free = ps3_free_coherent,
 	.map_sg = ps3_sb_map_sg,
 	.unmap_sg = ps3_sb_unmap_sg,
 	.dma_supported = ps3_dma_supported,
-	.get_required_mask = ps3_dma_get_required_mask,
 	.map_page = ps3_sb_map_page,
 	.unmap_page = ps3_unmap_page,
+	.mmap = dma_common_mmap,
+	.get_sgtable = dma_common_get_sgtable,
 };
 
 static const struct dma_map_ops ps3_ioc0_dma_ops = {
@@ -720,9 +704,10 @@
 	.map_sg = ps3_ioc0_map_sg,
 	.unmap_sg = ps3_ioc0_unmap_sg,
 	.dma_supported = ps3_dma_supported,
-	.get_required_mask = ps3_dma_get_required_mask,
 	.map_page = ps3_ioc0_map_page,
 	.unmap_page = ps3_unmap_page,
+	.mmap = dma_common_mmap,
+	.get_sgtable = dma_common_get_sgtable,
 };
 
 /**
diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c
index 08ca76e..c9bfc11 100644
--- a/arch/powerpc/platforms/ps3/time.c
+++ b/arch/powerpc/platforms/ps3/time.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 time and rtc routines.
  *
  *  Copyright (C) 2006 Sony Computer Entertainment Inc.
  *  Copyright 2006 Sony Corp.
- *
- *  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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 0c698fd..9e35cdd 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -5,7 +5,7 @@
 	select HAVE_PCSPKR_PLATFORM
 	select MPIC
 	select OF_DYNAMIC
-	select PCI
+	select FORCE_PCI
 	select PCI_MSI
 	select PPC_XICS
 	select PPC_XIVE_SPAPR
@@ -23,12 +23,12 @@
 	select ARCH_RANDOM
 	select PPC_DOORBELL
 	select FORCE_SMP
+	select SWIOTLB
 	default y
 
 config PPC_SPLPAR
 	depends on PPC_PSERIES
 	bool "Support for shared-processor logical partitions"
-	default n
 	help
 	  Enabling this option will make the kernel run more efficiently
 	  on logically-partitioned pSeries systems which use shared
@@ -81,25 +81,24 @@
 	bool "LPAR Configuration Data"
 	depends on PPC_PSERIES
 	help
-	Provide system capacity information via human readable
-	<key word>=<value> pairs through a /proc/ppc64/lparcfg interface.
+	  Provide system capacity information via human readable
+	  <key word>=<value> pairs through a /proc/ppc64/lparcfg interface.
 
 config PPC_PSERIES_DEBUG
 	depends on PPC_PSERIES && PPC_EARLY_DEBUG
 	bool "Enable extra debug logging in platforms/pseries"
-        help
+	default y
+	help
 	  Say Y here if you want the pseries core to produce a bunch of
 	  debug messages to the system log. Select this if you are having a
 	  problem with the pseries core and want to see more of what is
 	  going on. This does not enable debugging in lpar.c, which must
 	  be manually done due to its verbosity.
-	default y
 
 config PPC_SMLPAR
 	bool "Support for shared-memory logical partitions"
 	depends on PPC_PSERIES
 	select LPARCFG
-	default n
 	help
 	  Select this option to enable shared memory partition support.
 	  With this option a system running in an LPAR can be given more
@@ -119,16 +118,16 @@
 	  balance memory across many LPARs.
 
 config HV_PERF_CTRS
-       bool "Hypervisor supplied PMU events (24x7 & GPCI)"
-       default y
-       depends on PERF_EVENTS && PPC_PSERIES
-       help
+	bool "Hypervisor supplied PMU events (24x7 & GPCI)"
+	default y
+	depends on PERF_EVENTS && PPC_PSERIES
+	help
 	  Enable access to hypervisor supplied counters in perf. Currently,
 	  this enables code that uses the hcall GetPerfCounterInfo and 24x7
 	  interfaces to retrieve counters. GPCI exists on Power 6 and later
 	  systems. 24x7 is available on Power 8 and later systems.
 
-          If unsure, select Y.
+	  If unsure, select Y.
 
 config IBMVIO
 	depends on PPC_PSERIES
@@ -140,3 +139,23 @@
 	bool "Support for GX bus based adapters"
 	help
 	  Bus device driver for GX bus based adapters.
+
+config PAPR_SCM
+	depends on PPC_PSERIES && MEMORY_HOTPLUG && LIBNVDIMM
+	tristate "Support for the PAPR Storage Class Memory interface"
+	help
+	  Enable access to hypervisor provided storage class memory.
+
+config PPC_SVM
+	bool "Secure virtual machine (SVM) support for POWER"
+	depends on PPC_PSERIES
+	select SWIOTLB
+	select ARCH_HAS_MEM_ENCRYPT
+	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
+	help
+	 There are certain POWER platforms which support secure guests using
+	 the Protected Execution Facility, with the help of an Ultravisor
+	 executing below the hypervisor layer. This enables support for
+	 those guests.
+
+	 If unsure, say "N".
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 7e89d5c..a3c74a5 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -13,7 +13,7 @@
 obj-$(CONFIG_PSERIES_ENERGY)	+= pseries_energy.o
 
 obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug-cpu.o
-obj-$(CONFIG_MEMORY_HOTPLUG)	+= hotplug-memory.o
+obj-$(CONFIG_MEMORY_HOTPLUG)	+= hotplug-memory.o pmem.o
 
 obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
 obj-$(CONFIG_HVCS)		+= hvcserver.o
@@ -24,6 +24,10 @@
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)		+= ibmebus.o
+obj-$(CONFIG_PAPR_SCM)		+= papr_scm.o
+obj-$(CONFIG_PPC_SPLPAR)	+= vphn.o
+obj-$(CONFIG_PPC_SVM)		+= svm.o
+obj-$(CONFIG_FA_DUMP)		+= rtas-fadump.o
 
 ifdef CONFIG_PPC_PSERIES
 obj-$(CONFIG_SUSPEND)		+= suspend.o
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 25427a4..b33251d 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -1,23 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Collaborative memory management interface.
  *
  * Copyright (C) 2008 IBM Corporation
  * Author(s): Brian King (brking@linux.vnet.ibm.com),
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
  */
 
 #include <linux/ctype.h>
@@ -208,7 +194,7 @@
 
 		pa->page[pa->index++] = addr;
 		loaned_pages++;
-		totalram_pages--;
+		totalram_pages_dec();
 		spin_unlock(&cmm_lock);
 		nr--;
 	}
@@ -247,7 +233,7 @@
 		free_page(addr);
 		loaned_pages--;
 		nr--;
-		totalram_pages++;
+		totalram_pages_inc();
 	}
 	spin_unlock(&cmm_lock);
 	cmm_dbg("End request with %ld pages unfulfilled\n", nr);
@@ -291,7 +277,7 @@
 	int rc;
 	struct hvcall_mpp_data mpp_data;
 	signed long active_pages_target, page_loan_request, target;
-	signed long total_pages = totalram_pages + loaned_pages;
+	signed long total_pages = totalram_pages() + loaned_pages;
 	signed long min_mem_pages = (min_mem_mb * 1024 * 1024) / PAGE_SIZE;
 
 	rc = h_get_mpp(&mpp_data);
@@ -322,7 +308,7 @@
 
 	cmm_dbg("delta = %ld, loaned = %lu, target = %lu, oom = %lu, totalram = %lu\n",
 		page_loan_request, loaned_pages, loaned_pages_target,
-		oom_freed_pages, totalram_pages);
+		oom_freed_pages, totalram_pages());
 }
 
 static struct notifier_block cmm_oom_nb = {
@@ -581,7 +567,7 @@
 			free_page(pa_curr->page[idx]);
 			freed++;
 			loaned_pages--;
-			totalram_pages++;
+			totalram_pages_inc();
 			pa_curr->page[idx] = pa_last->page[--pa_last->index];
 			if (pa_last->index == 0) {
 				if (pa_curr == pa_last)
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index a0b20c0..16e86ba 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Support for dynamic reconfiguration for PCI, Memory, and CPU
  * Hotplug and Dynamic Logical Partitioning on RPA platforms.
  *
  * Copyright (C) 2009 Nathan Fontenot
  * Copyright (C) 2009 IBM Corporation
- *
- * 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.
  */
 
 #define pr_fmt(fmt)	"dlpar: " fmt
@@ -32,8 +29,6 @@
 struct pseries_hp_work {
 	struct work_struct work;
 	struct pseries_hp_errorlog *errlog;
-	struct completion *hp_completion;
-	int *rc;
 };
 
 struct cc_workarea {
@@ -63,6 +58,10 @@
 
 	name = (char *)ccwa + be32_to_cpu(ccwa->name_offset);
 	prop->name = kstrdup(name, GFP_KERNEL);
+	if (!prop->name) {
+		dlpar_free_cc_property(prop);
+		return NULL;
+	}
 
 	prop->length = be32_to_cpu(ccwa->prop_length);
 	value = (char *)ccwa + be32_to_cpu(ccwa->prop_offset);
@@ -272,6 +271,8 @@
 	if (rc)
 		return rc;
 
+	of_node_put(dn);
+
 	return 0;
 }
 
@@ -329,7 +330,7 @@
 	return 0;
 }
 
-static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
+int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
 {
 	int rc;
 
@@ -357,6 +358,10 @@
 	case PSERIES_HP_ELOG_RESOURCE_CPU:
 		rc = dlpar_cpu(hp_elog);
 		break;
+	case PSERIES_HP_ELOG_RESOURCE_PMEM:
+		rc = dlpar_hp_pmem(hp_elog);
+		break;
+
 	default:
 		pr_warn_ratelimited("Invalid resource (%d) specified\n",
 				    hp_elog->resource);
@@ -371,39 +376,28 @@
 	struct pseries_hp_work *hp_work =
 			container_of(work, struct pseries_hp_work, work);
 
-	if (hp_work->rc)
-		*(hp_work->rc) = handle_dlpar_errorlog(hp_work->errlog);
-	else
-		handle_dlpar_errorlog(hp_work->errlog);
-
-	if (hp_work->hp_completion)
-		complete(hp_work->hp_completion);
+	handle_dlpar_errorlog(hp_work->errlog);
 
 	kfree(hp_work->errlog);
 	kfree((void *)work);
 }
 
-void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog,
-			 struct completion *hotplug_done, int *rc)
+void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog)
 {
 	struct pseries_hp_work *work;
 	struct pseries_hp_errorlog *hp_errlog_copy;
 
-	hp_errlog_copy = kmalloc(sizeof(struct pseries_hp_errorlog),
-				 GFP_KERNEL);
-	memcpy(hp_errlog_copy, hp_errlog, sizeof(struct pseries_hp_errorlog));
+	hp_errlog_copy = kmemdup(hp_errlog, sizeof(*hp_errlog), GFP_ATOMIC);
+	if (!hp_errlog_copy)
+		return;
 
-	work = kmalloc(sizeof(struct pseries_hp_work), GFP_KERNEL);
+	work = kmalloc(sizeof(struct pseries_hp_work), GFP_ATOMIC);
 	if (work) {
 		INIT_WORK((struct work_struct *)work, pseries_hp_work_fn);
 		work->errlog = hp_errlog_copy;
-		work->hp_completion = hotplug_done;
-		work->rc = rc;
 		queue_work(pseries_hp_wq, (struct work_struct *)work);
 	} else {
-		*rc = -ENOMEM;
 		kfree(hp_errlog_copy);
-		complete(hotplug_done);
 	}
 }
 
@@ -521,18 +515,15 @@
 static ssize_t dlpar_store(struct class *class, struct class_attribute *attr,
 			   const char *buf, size_t count)
 {
-	struct pseries_hp_errorlog *hp_elog;
-	struct completion hotplug_done;
+	struct pseries_hp_errorlog hp_elog;
 	char *argbuf;
 	char *args;
 	int rc;
 
 	args = argbuf = kstrdup(buf, GFP_KERNEL);
-	hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL);
-	if (!hp_elog || !argbuf) {
+	if (!argbuf) {
 		pr_info("Could not allocate resources for DLPAR operation\n");
 		kfree(argbuf);
-		kfree(hp_elog);
 		return -ENOMEM;
 	}
 
@@ -540,25 +531,22 @@
 	 * Parse out the request from the user, this will be in the form:
 	 * <resource> <action> <id_type> <id>
 	 */
-	rc = dlpar_parse_resource(&args, hp_elog);
+	rc = dlpar_parse_resource(&args, &hp_elog);
 	if (rc)
 		goto dlpar_store_out;
 
-	rc = dlpar_parse_action(&args, hp_elog);
+	rc = dlpar_parse_action(&args, &hp_elog);
 	if (rc)
 		goto dlpar_store_out;
 
-	rc = dlpar_parse_id_type(&args, hp_elog);
+	rc = dlpar_parse_id_type(&args, &hp_elog);
 	if (rc)
 		goto dlpar_store_out;
 
-	init_completion(&hotplug_done);
-	queue_hotplug_event(hp_elog, &hotplug_done, &rc);
-	wait_for_completion(&hotplug_done);
+	rc = handle_dlpar_errorlog(&hp_elog);
 
 dlpar_store_out:
 	kfree(argbuf);
-	kfree(hp_elog);
 
 	if (rc)
 		pr_err("Could not handle DLPAR request \"%s\"\n", buf);
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 18014cd..2b87480 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Virtual Processor Dispatch Trace Log
  *
  * (C) Copyright IBM Corporation 2009
  *
  * Author: Jeremy Kerr <jk@ozlabs.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/slab.h>
@@ -40,13 +27,7 @@
 };
 static DEFINE_PER_CPU(struct dtl, cpu_dtl);
 
-/*
- * Dispatch trace log event mask:
- * 0x7: 0x1: voluntary virtual processor waits
- *      0x2: time-slice preempts
- *      0x4: virtual partition memory page faults
- */
-static u8 dtl_event_mask = 0x7;
+static u8 dtl_event_mask = DTL_LOG_ALL;
 
 
 /*
@@ -61,7 +42,6 @@
 	struct dtl_entry *write_ptr;
 	struct dtl_entry *buf;
 	struct dtl_entry *buf_end;
-	u8	saved_dtl_mask;
 };
 
 static DEFINE_PER_CPU(struct dtl_ring, dtl_rings);
@@ -111,7 +91,6 @@
 	dtlr->write_ptr = dtl->buf;
 
 	/* enable event logging */
-	dtlr->saved_dtl_mask = lppaca_of(dtl->cpu).dtl_enable_mask;
 	lppaca_of(dtl->cpu).dtl_enable_mask |= dtl_event_mask;
 
 	dtl_consumer = consume_dtle;
@@ -129,7 +108,7 @@
 	dtlr->buf = NULL;
 
 	/* restore dtl_enable_mask */
-	lppaca_of(dtl->cpu).dtl_enable_mask = dtlr->saved_dtl_mask;
+	lppaca_of(dtl->cpu).dtl_enable_mask = DTL_LOG_PREEMPT;
 
 	if (atomic_dec_and_test(&dtl_count))
 		dtl_consumer = NULL;
@@ -149,7 +128,7 @@
 
 	/* Register our dtl buffer with the hypervisor. The HV expects the
 	 * buffer size to be passed in the second word of the buffer */
-	((u32 *)dtl->buf)[1] = DISPATCH_LOG_BYTES;
+	((u32 *)dtl->buf)[1] = cpu_to_be32(DISPATCH_LOG_BYTES);
 
 	hwcpu = get_hard_smp_processor_id(dtl->cpu);
 	addr = __pa(dtl->buf);
@@ -184,7 +163,7 @@
 
 static u64 dtl_current_index(struct dtl *dtl)
 {
-	return lppaca_of(dtl->cpu).dtl_idx;
+	return be64_to_cpu(lppaca_of(dtl->cpu).dtl_idx);
 }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
@@ -201,11 +180,16 @@
 	if (dtl->buf)
 		return -EBUSY;
 
+	/* ensure there are no other conflicting dtl users */
+	if (!read_trylock(&dtl_access_lock))
+		return -EBUSY;
+
 	n_entries = dtl_buf_entries;
 	buf = kmem_cache_alloc_node(dtl_cache, GFP_KERNEL, cpu_to_node(dtl->cpu));
 	if (!buf) {
 		printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
 				__func__, dtl->cpu);
+		read_unlock(&dtl_access_lock);
 		return -ENOMEM;
 	}
 
@@ -222,8 +206,11 @@
 	}
 	spin_unlock(&dtl->lock);
 
-	if (rc)
+	if (rc) {
+		read_unlock(&dtl_access_lock);
 		kmem_cache_free(dtl_cache, buf);
+	}
+
 	return rc;
 }
 
@@ -235,6 +222,7 @@
 	dtl->buf = NULL;
 	dtl->buf_entries = 0;
 	spin_unlock(&dtl->lock);
+	read_unlock(&dtl_access_lock);
 }
 
 /* file interface */
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 823cb27..893ba3f 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * The file intends to implement the platform dependent EEH operations on pseries.
  * Actually, the pseries platform is built based on RTAS heavily. That means the
@@ -9,20 +10,6 @@
  * Copyright IBM Corporation 2001, 2005, 2006
  * Copyright Dave Engebretsen & Todd Inglett 2001
  * Copyright Linas Vepstas 2005, 2006
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/atomic.h>
@@ -55,42 +42,44 @@
 static int ibm_get_config_addr_info2;
 static int ibm_configure_pe;
 
-#ifdef CONFIG_PCI_IOV
 void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);
-	struct pci_dn *physfn_pdn;
-	struct eeh_dev *edev;
 
-	if (!pdev->is_virtfn)
+	if (eeh_has_flag(EEH_FORCE_DISABLED))
 		return;
 
-	pdn->device_id  =  pdev->device;
-	pdn->vendor_id  =  pdev->vendor;
-	pdn->class_code =  pdev->class;
-	/*
-	 * Last allow unfreeze return code used for retrieval
-	 * by user space in eeh-sysfs to show the last command
-	 * completion from platform.
-	 */
-	pdn->last_allow_rc =  0;
-	physfn_pdn      =  pci_get_pdn(pdev->physfn);
-	pdn->pe_number  =  physfn_pdn->pe_num_map[pdn->vf_index];
-	edev = pdn_to_eeh_dev(pdn);
+	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
+#ifdef CONFIG_PCI_IOV
+	if (pdev->is_virtfn) {
+		struct pci_dn *physfn_pdn;
 
-	/*
-	 * The following operations will fail if VF's sysfs files
-	 * aren't created or its resources aren't finalized.
-	 */
+		pdn->device_id  =  pdev->device;
+		pdn->vendor_id  =  pdev->vendor;
+		pdn->class_code =  pdev->class;
+		/*
+		 * Last allow unfreeze return code used for retrieval
+		 * by user space in eeh-sysfs to show the last command
+		 * completion from platform.
+		 */
+		pdn->last_allow_rc =  0;
+		physfn_pdn      =  pci_get_pdn(pdev->physfn);
+		pdn->pe_number  =  physfn_pdn->pe_num_map[pdn->vf_index];
+	}
+#endif
 	eeh_add_device_early(pdn);
 	eeh_add_device_late(pdev);
-	edev->pe_config_addr =  (pdn->busno << 16) | (pdn->devfn << 8);
-	eeh_rmv_from_parent_pe(edev); /* Remove as it is adding to bus pe */
-	eeh_add_to_parent_pe(edev);   /* Add as VF PE type */
-	eeh_sysfs_add_device(pdev);
+#ifdef CONFIG_PCI_IOV
+	if (pdev->is_virtfn) {
+		struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 
-}
+		edev->pe_config_addr =  (pdn->busno << 16) | (pdn->devfn << 8);
+		eeh_rmv_from_parent_pe(edev); /* Remove as it is adding to bus pe */
+		eeh_add_to_parent_pe(edev);   /* Add as VF PE type */
+	}
 #endif
+	eeh_sysfs_add_device(pdev);
+}
 
 /*
  * Buffer for reporting slot-error-detail rtas calls. Its here
@@ -157,10 +146,8 @@
 	/* Set EEH probe mode */
 	eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG);
 
-#ifdef CONFIG_PCI_IOV
 	/* Set EEH machine dependent code */
 	ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device;
-#endif
 
 	return 0;
 }
@@ -264,6 +251,8 @@
         if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA)
 		return NULL;
 
+	eeh_edev_dbg(edev, "Probing device\n");
+
 	/*
 	 * Update class code and mode of eeh device. We need
 	 * correctly reflects that current device is root port
@@ -293,8 +282,11 @@
 	pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8);
 
 	/* Enable EEH on the device */
+	eeh_edev_dbg(edev, "Enabling EEH on device\n");
 	ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE);
-	if (!ret) {
+	if (ret) {
+		eeh_edev_dbg(edev, "EEH failed to enable on device (code %d)\n", ret);
+	} else {
 		/* Retrieve PE address */
 		edev->pe_config_addr = eeh_ops->get_pe_addr(&pe);
 		pe.addr = edev->pe_config_addr;
@@ -310,11 +302,6 @@
 		if (enable) {
 			eeh_add_flag(EEH_ENABLED);
 			eeh_add_to_parent_pe(edev);
-
-			pr_debug("%s: EEH enabled on %02x:%02x.%01x PHB#%x-PE#%x\n",
-				__func__, pdn->busno, PCI_SLOT(pdn->devfn),
-				PCI_FUNC(pdn->devfn), pe.phb->global_number,
-				pe.addr);
 		} else if (pdn->parent && pdn_to_eeh_dev(pdn->parent) &&
 			   (pdn_to_eeh_dev(pdn->parent))->pe) {
 			/* This device doesn't support EEH, but it may have an
@@ -323,6 +310,8 @@
 			edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr;
 			eeh_add_to_parent_pe(edev);
 		}
+		eeh_edev_dbg(edev, "EEH is %s on device (code %d)\n",
+			     (enable ? "enabled" : "unsupported"), ret);
 	}
 
 	/* Save memory bars */
@@ -438,7 +427,7 @@
 /**
  * pseries_eeh_get_state - Retrieve PE state
  * @pe: EEH PE
- * @state: return value
+ * @delay: suggested time to wait if state is unavailable
  *
  * Retrieve the state of the specified PE. On RTAS compliant
  * pseries platform, there already has one dedicated RTAS function
@@ -448,7 +437,7 @@
  * RTAS calls for the purpose, we need to try the new one and back
  * to the old one if the new one couldn't work properly.
  */
-static int pseries_eeh_get_state(struct eeh_pe *pe, int *state)
+static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay)
 {
 	int config_addr;
 	int ret;
@@ -499,7 +488,8 @@
 		break;
 	case 5:
 		if (rets[2]) {
-			if (state) *state = rets[2];
+			if (delay)
+				*delay = rets[2];
 			result = EEH_STATE_UNAVAILABLE;
 		} else {
 			result = EEH_STATE_NOT_SUPPORT;
@@ -554,64 +544,6 @@
 }
 
 /**
- * pseries_eeh_wait_state - Wait for PE state
- * @pe: EEH PE
- * @max_wait: maximal period in millisecond
- *
- * Wait for the state of associated PE. It might take some time
- * to retrieve the PE's state.
- */
-static int pseries_eeh_wait_state(struct eeh_pe *pe, int max_wait)
-{
-	int ret;
-	int mwait;
-
-	/*
-	 * According to PAPR, the state of PE might be temporarily
-	 * unavailable. Under the circumstance, we have to wait
-	 * for indicated time determined by firmware. The maximal
-	 * wait time is 5 minutes, which is acquired from the original
-	 * EEH implementation. Also, the original implementation
-	 * also defined the minimal wait time as 1 second.
-	 */
-#define EEH_STATE_MIN_WAIT_TIME	(1000)
-#define EEH_STATE_MAX_WAIT_TIME	(300 * 1000)
-
-	while (1) {
-		ret = pseries_eeh_get_state(pe, &mwait);
-
-		/*
-		 * If the PE's state is temporarily unavailable,
-		 * we have to wait for the specified time. Otherwise,
-		 * the PE's state will be returned immediately.
-		 */
-		if (ret != EEH_STATE_UNAVAILABLE)
-			return ret;
-
-		if (max_wait <= 0) {
-			pr_warn("%s: Timeout when getting PE's state (%d)\n",
-				__func__, max_wait);
-			return EEH_STATE_NOT_SUPPORT;
-		}
-
-		if (mwait <= 0) {
-			pr_warn("%s: Firmware returned bad wait value %d\n",
-				__func__, mwait);
-			mwait = EEH_STATE_MIN_WAIT_TIME;
-		} else if (mwait > EEH_STATE_MAX_WAIT_TIME) {
-			pr_warn("%s: Firmware returned too long wait value %d\n",
-				__func__, mwait);
-			mwait = EEH_STATE_MAX_WAIT_TIME;
-		}
-
-		max_wait -= mwait;
-		msleep(mwait);
-	}
-
-	return EEH_STATE_NOT_SUPPORT;
-}
-
-/**
  * pseries_eeh_get_log - Retrieve error log
  * @pe: EEH PE
  * @severity: temporary or permanent error log
@@ -849,7 +781,6 @@
 	.get_pe_addr		= pseries_eeh_get_pe_addr,
 	.get_state		= pseries_eeh_get_state,
 	.reset			= pseries_eeh_reset,
-	.wait_state		= pseries_eeh_wait_state,
 	.get_log		= pseries_eeh_get_log,
 	.configure_bridge       = pseries_eeh_configure_bridge,
 	.err_inject		= NULL,
diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c
index 6eeb0d4..be661e9 100644
--- a/arch/powerpc/platforms/pseries/event_sources.c
+++ b/arch/powerpc/platforms/pseries/event_sources.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2001 Dave Engebretsen IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#include <asm/prom.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
 
 #include "pseries.h"
 
@@ -24,34 +12,19 @@
 				irq_handler_t handler,
 				const char *name)
 {
-	int i, index, count = 0;
-	struct of_phandle_args oirq;
-	unsigned int virqs[16];
+	int i, virq, rc;
 
-	/* First try to do a proper OF tree parsing */
-	for (index = 0; of_irq_parse_one(np, index, &oirq) == 0;
-	     index++) {
-		if (count > 15)
-			break;
-		virqs[count] = irq_create_of_mapping(&oirq);
-		if (!virqs[count]) {
-			pr_err("event-sources: Unable to allocate "
-			       "interrupt number for %pOF\n",
-			       np);
-			WARN_ON(1);
-		} else {
-			count++;
-		}
-	}
-
-	/* Now request them */
-	for (i = 0; i < count; i++) {
-		if (request_irq(virqs[i], handler, 0, name, NULL)) {
-			pr_err("event-sources: Unable to request interrupt "
-			       "%d for %pOF\n", virqs[i], np);
-			WARN_ON(1);
+	for (i = 0; i < 16; i++) {
+		virq = of_irq_get(np, i);
+		if (virq < 0)
 			return;
-		}
+		if (WARN(!virq, "event-sources: Unable to allocate "
+			        "interrupt number for %pOF\n", np))
+			continue;
+
+		rc = request_irq(virq, handler, 0, name, NULL);
+		if (WARN(rc, "event-sources: Unable to request interrupt %d for %pOF\n",
+		    virq, np))
+			return;
 	}
 }
-
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index a3bbeb4..d4a8f17 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  pSeries firmware setup code.
  *
@@ -14,11 +15,6 @@
  *    Copyright (C) 2005 Stephen Rothwell, IBM Corporation
  *
  *  Copyright 2006 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 
@@ -65,6 +61,8 @@
 	{FW_FEATURE_SET_MODE,		"hcall-set-mode"},
 	{FW_FEATURE_BEST_ENERGY,	"hcall-best-energy-1*"},
 	{FW_FEATURE_HPT_RESIZE,		"hcall-hpt-resize"},
+	{FW_FEATURE_BLOCK_REMOVE,	"hcall-block-remove"},
+	{FW_FEATURE_PAPR_SCM,		"hcall-scm"},
 };
 
 /* Build up the firmware features bitmask using the contents of
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 6ef77ca..bbda646 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * pseries CPU Hotplug infrastructure.
  *
@@ -11,11 +12,6 @@
  * Plus various changes from other IBM teams...
  *
  * Copyright (C) 2006 Michael Ellerman, IBM 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; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)     "pseries-hotplug-cpu: " fmt
@@ -287,7 +283,7 @@
 
 	if (cpumask_empty(tmp)) {
 		printk(KERN_ERR "Unable to find space in cpu_present_mask for"
-		       " processor %s with %d thread(s)\n", np->name,
+		       " processor %pOFn with %d thread(s)\n", np,
 		       nthreads);
 		goto out_unlock;
 	}
@@ -481,8 +477,8 @@
 
 	if (rc) {
 		saved_rc = rc;
-		pr_warn("Failed to attach node %s, rc: %d, drc index: %x\n",
-			dn->name, rc, drc_index);
+		pr_warn("Failed to attach node %pOFn, rc: %d, drc index: %x\n",
+			dn, rc, drc_index);
 
 		rc = dlpar_release_drc(drc_index);
 		if (!rc)
@@ -494,8 +490,8 @@
 	rc = dlpar_online_cpu(dn);
 	if (rc) {
 		saved_rc = rc;
-		pr_warn("Failed to online cpu %s, rc: %d, drc index: %x\n",
-			dn->name, rc, drc_index);
+		pr_warn("Failed to online cpu %pOFn, rc: %d, drc index: %x\n",
+			dn, rc, drc_index);
 
 		rc = dlpar_detach_node(dn);
 		if (!rc)
@@ -504,7 +500,7 @@
 		return saved_rc;
 	}
 
-	pr_debug("Successfully added CPU %s, drc index: %x\n", dn->name,
+	pr_debug("Successfully added CPU %pOFn, drc index: %x\n", dn,
 		 drc_index);
 	return rc;
 }
@@ -570,19 +566,19 @@
 {
 	int rc;
 
-	pr_debug("Attempting to remove CPU %s, drc index: %x\n",
-		 dn->name, drc_index);
+	pr_debug("Attempting to remove CPU %pOFn, drc index: %x\n",
+		 dn, drc_index);
 
 	rc = dlpar_offline_cpu(dn);
 	if (rc) {
-		pr_warn("Failed to offline CPU %s, rc: %d\n", dn->name, rc);
+		pr_warn("Failed to offline CPU %pOFn, rc: %d\n", dn, rc);
 		return -EINVAL;
 	}
 
 	rc = dlpar_release_drc(drc_index);
 	if (rc) {
-		pr_warn("Failed to release drc (%x) for CPU %s, rc: %d\n",
-			drc_index, dn->name, rc);
+		pr_warn("Failed to release drc (%x) for CPU %pOFn, rc: %d\n",
+			drc_index, dn, rc);
 		dlpar_online_cpu(dn);
 		return rc;
 	}
@@ -591,7 +587,7 @@
 	if (rc) {
 		int saved_rc = rc;
 
-		pr_warn("Failed to detach CPU %s, rc: %d", dn->name, rc);
+		pr_warn("Failed to detach CPU %pOFn, rc: %d", dn, rc);
 
 		rc = dlpar_acquire_drc(drc_index);
 		if (!rc)
@@ -662,8 +658,8 @@
 		rc = of_property_read_u32(dn, "ibm,my-drc-index",
 					  &cpu_drcs[cpus_found - 1]);
 		if (rc) {
-			pr_warn("Error occurred getting drc-index for %s\n",
-				dn->name);
+			pr_warn("Error occurred getting drc-index for %pOFn\n",
+				dn);
 			of_node_put(dn);
 			return -1;
 		}
@@ -802,6 +798,25 @@
 	return rc;
 }
 
+int dlpar_cpu_readd(int cpu)
+{
+	struct device_node *dn;
+	struct device *dev;
+	u32 drc_index;
+	int rc;
+
+	dev = get_cpu_device(cpu);
+	dn = dev->of_node;
+
+	rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index);
+
+	rc = dlpar_cpu_remove_by_index(drc_index);
+	if (!rc)
+		rc = dlpar_cpu_add(drc_index);
+
+	return rc;
+}
+
 int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
 {
 	u32 count, drc_index;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index c1578f5..8e70039 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * pseries Memory Hotplug infrastructure.
  *
  * Copyright (C) 2008 Badari Pulavarty, IBM 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; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)	"pseries-hotplug-mem: " fmt
@@ -101,11 +97,12 @@
 	return new_prop;
 }
 
-static u32 find_aa_index(struct device_node *dr_node,
-			 struct property *ala_prop, const u32 *lmb_assoc)
+static bool find_aa_index(struct device_node *dr_node,
+			 struct property *ala_prop,
+			 const u32 *lmb_assoc, u32 *aa_index)
 {
-	u32 *assoc_arrays;
-	u32 aa_index;
+	u32 *assoc_arrays, new_prop_size;
+	struct property *new_prop;
 	int aa_arrays, aa_array_entries, aa_array_sz;
 	int i, index;
 
@@ -121,54 +118,48 @@
 	aa_array_entries = be32_to_cpu(assoc_arrays[1]);
 	aa_array_sz = aa_array_entries * sizeof(u32);
 
-	aa_index = -1;
 	for (i = 0; i < aa_arrays; i++) {
 		index = (i * aa_array_entries) + 2;
 
 		if (memcmp(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz))
 			continue;
 
-		aa_index = i;
-		break;
+		*aa_index = i;
+		return true;
 	}
 
-	if (aa_index == -1) {
-		struct property *new_prop;
-		u32 new_prop_size;
+	new_prop_size = ala_prop->length + aa_array_sz;
+	new_prop = dlpar_clone_property(ala_prop, new_prop_size);
+	if (!new_prop)
+		return false;
 
-		new_prop_size = ala_prop->length + aa_array_sz;
-		new_prop = dlpar_clone_property(ala_prop, new_prop_size);
-		if (!new_prop)
-			return -1;
+	assoc_arrays = new_prop->value;
 
-		assoc_arrays = new_prop->value;
+	/* increment the number of entries in the lookup array */
+	assoc_arrays[0] = cpu_to_be32(aa_arrays + 1);
 
-		/* increment the number of entries in the lookup array */
-		assoc_arrays[0] = cpu_to_be32(aa_arrays + 1);
+	/* copy the new associativity into the lookup array */
+	index = aa_arrays * aa_array_entries + 2;
+	memcpy(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz);
 
-		/* copy the new associativity into the lookup array */
-		index = aa_arrays * aa_array_entries + 2;
-		memcpy(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz);
+	of_update_property(dr_node, new_prop);
 
-		of_update_property(dr_node, new_prop);
-
-		/*
-		 * The associativity lookup array index for this lmb is
-		 * number of entries - 1 since we added its associativity
-		 * to the end of the lookup array.
-		 */
-		aa_index = be32_to_cpu(assoc_arrays[0]) - 1;
-	}
-
-	return aa_index;
+	/*
+	 * The associativity lookup array index for this lmb is
+	 * number of entries - 1 since we added its associativity
+	 * to the end of the lookup array.
+	 */
+	*aa_index = be32_to_cpu(assoc_arrays[0]) - 1;
+	return true;
 }
 
-static u32 lookup_lmb_associativity_index(struct drmem_lmb *lmb)
+static int update_lmb_associativity_index(struct drmem_lmb *lmb)
 {
 	struct device_node *parent, *lmb_node, *dr_node;
 	struct property *ala_prop;
 	const u32 *lmb_assoc;
 	u32 aa_index;
+	bool found;
 
 	parent = of_find_node_by_path("/");
 	if (!parent)
@@ -200,46 +191,18 @@
 		return -ENODEV;
 	}
 
-	aa_index = find_aa_index(dr_node, ala_prop, lmb_assoc);
+	found = find_aa_index(dr_node, ala_prop, lmb_assoc, &aa_index);
 
+	of_node_put(dr_node);
 	dlpar_free_cc_nodes(lmb_node);
-	return aa_index;
-}
 
-static int dlpar_add_device_tree_lmb(struct drmem_lmb *lmb)
-{
-	int rc, aa_index;
-
-	lmb->flags |= DRCONF_MEM_ASSIGNED;
-
-	aa_index = lookup_lmb_associativity_index(lmb);
-	if (aa_index < 0) {
-		pr_err("Couldn't find associativity index for drc index %x\n",
-		       lmb->drc_index);
-		return aa_index;
+	if (!found) {
+		pr_err("Could not find LMB associativity\n");
+		return -1;
 	}
 
 	lmb->aa_index = aa_index;
-
-	rtas_hp_event = true;
-	rc = drmem_update_dt();
-	rtas_hp_event = false;
-
-	return rc;
-}
-
-static int dlpar_remove_device_tree_lmb(struct drmem_lmb *lmb)
-{
-	int rc;
-
-	lmb->flags &= ~DRCONF_MEM_ASSIGNED;
-	lmb->aa_index = 0xffffffff;
-
-	rtas_hp_event = true;
-	rc = drmem_update_dt();
-	rtas_hp_event = false;
-
-	return rc;
+	return 0;
 }
 
 static struct memory_block *lmb_to_memblock(struct drmem_lmb *lmb)
@@ -334,7 +297,7 @@
 	nid = memory_add_physaddr_to_nid(base);
 
 	for (i = 0; i < sections_per_block; i++) {
-		remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE);
+		__remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE);
 		base += MIN_MEMORY_BLOCK_SIZE;
 	}
 
@@ -347,7 +310,6 @@
 
 static int pseries_remove_mem_node(struct device_node *np)
 {
-	const char *type;
 	const __be32 *regs;
 	unsigned long base;
 	unsigned int lmb_size;
@@ -356,8 +318,7 @@
 	/*
 	 * Check to see if we are actually removing memory
 	 */
-	type = of_get_property(np, "device_type", NULL);
-	if (type == NULL || strcmp(type, "memory") != 0)
+	if (!of_node_is_type(np, "memory"))
 		return 0;
 
 	/*
@@ -389,8 +350,11 @@
 	phys_addr = lmb->base_addr;
 
 #ifdef CONFIG_FA_DUMP
-	/* Don't hot-remove memory that falls in fadump boot memory area */
-	if (is_fadump_boot_memory_area(phys_addr, block_sz))
+	/*
+	 * Don't hot-remove memory that falls in fadump boot memory area
+	 * and memory that is reserved for capturing old kernel memory.
+	 */
+	if (is_fadump_memory_area(phys_addr, block_sz))
 		return false;
 #endif
 
@@ -411,7 +375,7 @@
 static int dlpar_remove_lmb(struct drmem_lmb *lmb)
 {
 	unsigned long block_sz;
-	int nid, rc;
+	int rc;
 
 	if (!lmb_is_removable(lmb))
 		return -EINVAL;
@@ -421,14 +385,16 @@
 		return rc;
 
 	block_sz = pseries_memory_block_size();
-	nid = memory_add_physaddr_to_nid(lmb->base_addr);
 
-	remove_memory(nid, lmb->base_addr, block_sz);
+	__remove_memory(lmb->nid, lmb->base_addr, block_sz);
 
 	/* Update memory regions for memory remove */
 	memblock_remove(lmb->base_addr, block_sz);
 
-	dlpar_remove_device_tree_lmb(lmb);
+	invalidate_lmb_associativity_index(lmb);
+	lmb_clear_nid(lmb);
+	lmb->flags &= ~DRCONF_MEM_ASSIGNED;
+
 	return 0;
 }
 
@@ -683,35 +649,32 @@
 static int dlpar_add_lmb(struct drmem_lmb *lmb)
 {
 	unsigned long block_sz;
-	int nid, rc;
+	int rc;
 
 	if (lmb->flags & DRCONF_MEM_ASSIGNED)
 		return -EINVAL;
 
-	rc = dlpar_add_device_tree_lmb(lmb);
+	rc = update_lmb_associativity_index(lmb);
 	if (rc) {
-		pr_err("Couldn't update device tree for drc index %x\n",
-		       lmb->drc_index);
 		dlpar_release_drc(lmb->drc_index);
 		return rc;
 	}
 
+	lmb_set_nid(lmb);
 	block_sz = memory_block_size_bytes();
 
-	/* Find the node id for this address */
-	nid = memory_add_physaddr_to_nid(lmb->base_addr);
-
 	/* Add the memory */
-	rc = add_memory(nid, lmb->base_addr, block_sz);
+	rc = __add_memory(lmb->nid, lmb->base_addr, block_sz);
 	if (rc) {
-		dlpar_remove_device_tree_lmb(lmb);
+		invalidate_lmb_associativity_index(lmb);
 		return rc;
 	}
 
 	rc = dlpar_online_lmb(lmb);
 	if (rc) {
-		remove_memory(nid, lmb->base_addr, block_sz);
-		dlpar_remove_device_tree_lmb(lmb);
+		__remove_memory(lmb->nid, lmb->base_addr, block_sz);
+		invalidate_lmb_associativity_index(lmb);
+		lmb_clear_nid(lmb);
 	} else {
 		lmb->flags |= DRCONF_MEM_ASSIGNED;
 	}
@@ -917,34 +880,44 @@
 
 	switch (hp_elog->action) {
 	case PSERIES_HP_ELOG_ACTION_ADD:
-		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) {
+		switch (hp_elog->id_type) {
+		case PSERIES_HP_ELOG_ID_DRC_COUNT:
 			count = hp_elog->_drc_u.drc_count;
 			rc = dlpar_memory_add_by_count(count);
-		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) {
+			break;
+		case PSERIES_HP_ELOG_ID_DRC_INDEX:
 			drc_index = hp_elog->_drc_u.drc_index;
 			rc = dlpar_memory_add_by_index(drc_index);
-		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_IC) {
+			break;
+		case PSERIES_HP_ELOG_ID_DRC_IC:
 			count = hp_elog->_drc_u.ic.count;
 			drc_index = hp_elog->_drc_u.ic.index;
 			rc = dlpar_memory_add_by_ic(count, drc_index);
-		} else {
+			break;
+		default:
 			rc = -EINVAL;
+			break;
 		}
 
 		break;
 	case PSERIES_HP_ELOG_ACTION_REMOVE:
-		if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) {
+		switch (hp_elog->id_type) {
+		case PSERIES_HP_ELOG_ID_DRC_COUNT:
 			count = hp_elog->_drc_u.drc_count;
 			rc = dlpar_memory_remove_by_count(count);
-		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) {
+			break;
+		case PSERIES_HP_ELOG_ID_DRC_INDEX:
 			drc_index = hp_elog->_drc_u.drc_index;
 			rc = dlpar_memory_remove_by_index(drc_index);
-		} else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_IC) {
+			break;
+		case PSERIES_HP_ELOG_ID_DRC_IC:
 			count = hp_elog->_drc_u.ic.count;
 			drc_index = hp_elog->_drc_u.ic.index;
 			rc = dlpar_memory_remove_by_ic(count, drc_index);
-		} else {
+			break;
+		default:
 			rc = -EINVAL;
+			break;
 		}
 
 		break;
@@ -958,13 +931,18 @@
 		break;
 	}
 
+	if (!rc) {
+		rtas_hp_event = true;
+		rc = drmem_update_dt();
+		rtas_hp_event = false;
+	}
+
 	unlock_device_hotplug();
 	return rc;
 }
 
 static int pseries_add_mem_node(struct device_node *np)
 {
-	const char *type;
 	const __be32 *regs;
 	unsigned long base;
 	unsigned int lmb_size;
@@ -973,8 +951,7 @@
 	/*
 	 * Check to see if we are actually adding memory
 	 */
-	type = of_get_property(np, "device_type", NULL);
-	if (type == NULL || strcmp(type, "memory") != 0)
+	if (!of_node_is_type(np, "memory"))
 		return 0;
 
 	/*
@@ -1009,6 +986,9 @@
 	if (!memblock_size)
 		return -EINVAL;
 
+	if (!pr->old_prop)
+		return 0;
+
 	p = (__be32 *) pr->old_prop->value;
 	if (!p)
 		return -EINVAL;
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index d91412c..2136e42 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * This file contains the generic code to perform a call to the
  * pSeries LPAR hypervisor.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/jump_label.h>
 #include <asm/hvcall.h>
@@ -19,7 +15,7 @@
 	
 #ifdef CONFIG_TRACEPOINTS
 
-#ifndef HAVE_JUMP_LABEL
+#ifndef CONFIG_JUMP_LABEL
 	.section	".toc","aw"
 
 	.globl hcall_tracepoint_refcount
@@ -79,7 +75,7 @@
 	mr	r5,BUFREG;					\
 	__HCALL_INST_POSTCALL
 
-#ifdef HAVE_JUMP_LABEL
+#ifdef CONFIG_JUMP_LABEL
 #define HCALL_BRANCH(LABEL)					\
 	ARCH_STATIC_BRANCH(LABEL, hcall_tracepoint_key)
 #else
diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c
index 6da320c..bcc1b67 100644
--- a/arch/powerpc/platforms/pseries/hvCall_inst.c
+++ b/arch/powerpc/platforms/pseries/hvCall_inst.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2006 Mike Kravetz IBM Corporation
  *
  * Hypervisor Call Instrumentation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c
index 74da18d..1ac5296 100644
--- a/arch/powerpc/platforms/pseries/hvconsole.c
+++ b/arch/powerpc/platforms/pseries/hvconsole.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * hvconsole.c
  * Copyright (C) 2004 Hollis Blanchard, IBM Corporation
@@ -7,20 +8,6 @@
  *  Ryan S. Arnold <rsa@us.ibm.com>
  *
  * LPAR console support.
- * 
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- * 
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- * 
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/kernel.h>
@@ -62,7 +49,7 @@
  * @vtermno: The vtermno or unit_address of the adapter from which the data
  *	originated.
  * @buf: The character buffer that contains the character data to send to
- *	firmware.
+ *	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)
diff --git a/arch/powerpc/platforms/pseries/hvcserver.c b/arch/powerpc/platforms/pseries/hvcserver.c
index 94a6e56..267139b 100644
--- a/arch/powerpc/platforms/pseries/hvcserver.c
+++ b/arch/powerpc/platforms/pseries/hvcserver.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * hvcserver.c
  * Copyright (C) 2004 Ryan S Arnold, IBM Corporation
  *
  * PPC64 virtual I/O console server support.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index c7c1140..b91eb09 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -147,13 +147,13 @@
 	.unmap_page         = ibmebus_unmap_page,
 };
 
-static int ibmebus_match_path(struct device *dev, void *data)
+static int ibmebus_match_path(struct device *dev, const void *data)
 {
 	struct device_node *dn = to_platform_device(dev)->dev.of_node;
 	return (of_find_node_by_path(data) == dn);
 }
 
-static int ibmebus_match_node(struct device *dev, void *data)
+static int ibmebus_match_node(struct device *dev, const void *data)
 {
 	return to_platform_device(dev)->dev.of_node == data;
 }
@@ -261,8 +261,7 @@
 	return out;
 }
 
-static ssize_t ibmebus_store_probe(struct bus_type *bus,
-				   const char *buf, size_t count)
+static ssize_t probe_store(struct bus_type *bus, const char *buf, size_t count)
 {
 	struct device_node *dn = NULL;
 	struct device *dev;
@@ -298,10 +297,9 @@
 		return rc;
 	return count;
 }
-static BUS_ATTR(probe, 0200, NULL, ibmebus_store_probe);
+static BUS_ATTR_WO(probe);
 
-static ssize_t ibmebus_store_remove(struct bus_type *bus,
-				    const char *buf, size_t count)
+static ssize_t remove_store(struct bus_type *bus, const char *buf, size_t count)
 {
 	struct device *dev;
 	char *path;
@@ -325,7 +323,7 @@
 		return -ENODEV;
 	}
 }
-static BUS_ATTR(remove, 0200, NULL, ibmebus_store_remove);
+static BUS_ATTR_WO(remove);
 
 static struct attribute *ibmbus_bus_attrs[] = {
 	&bus_attr_probe.attr,
@@ -404,7 +402,7 @@
 	struct platform_device *ofdev;
 
 	ofdev = to_platform_device(dev);
-	return sprintf(buf, "%s\n", ofdev->dev.of_node->name);
+	return sprintf(buf, "%pOFn\n", ofdev->dev.of_node);
 }
 static DEVICE_ATTR_RO(name);
 
diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c
index f053bda..7b74d4d 100644
--- a/arch/powerpc/platforms/pseries/io_event_irq.c
+++ b/arch/powerpc/platforms/pseries/io_event_irq.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2010 2011 Mark Nelson and Tseng-Hui (Frank) Lin, IBM 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; either version
- *  2 of the License, or (at your option) any later version.
  */
 
 #include <linux/errno.h>
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 06f0296..6ba081d 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
  *
@@ -7,21 +8,6 @@
  * Copyright (C) 2006 Olof Johansson <olof@lixom.net>
  *
  * Dynamic DMA mapping support, pSeries-specific parts, both SMP and LPAR.
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/init.h>
@@ -50,6 +36,7 @@
 #include <asm/udbg.h>
 #include <asm/mmzone.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/svm.h>
 
 #include "pseries.h"
 
@@ -57,7 +44,6 @@
 {
 	struct iommu_table_group *table_group;
 	struct iommu_table *tbl;
-	struct iommu_table_group_link *tgl;
 
 	table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL,
 			   node);
@@ -68,22 +54,13 @@
 	if (!tbl)
 		goto free_group;
 
-	tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL,
-			node);
-	if (!tgl)
-		goto free_table;
-
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
 	kref_init(&tbl->it_kref);
-	tgl->table_group = table_group;
-	list_add_rcu(&tgl->next, &tbl->it_group_list);
 
 	table_group->tables[0] = tbl;
 
 	return table_group;
 
-free_table:
-	kfree(tbl);
 free_group:
 	kfree(table_group);
 	return NULL;
@@ -93,23 +70,12 @@
 		const char *node_name)
 {
 	struct iommu_table *tbl;
-#ifdef CONFIG_IOMMU_API
-	struct iommu_table_group_link *tgl;
-#endif
 
 	if (!table_group)
 		return;
 
 	tbl = table_group->tables[0];
 #ifdef CONFIG_IOMMU_API
-	tgl = list_first_entry_or_null(&tbl->it_group_list,
-			struct iommu_table_group_link, next);
-
-	WARN_ON_ONCE(!tgl);
-	if (tgl) {
-		list_del_rcu(&tgl->next);
-		kfree(tgl);
-	}
 	if (table_group->group) {
 		iommu_group_put(table_group->group);
 		BUG_ON(table_group->group);
@@ -126,7 +92,7 @@
 			      unsigned long attrs)
 {
 	u64 proto_tce;
-	__be64 *tcep, *tces;
+	__be64 *tcep;
 	u64 rpn;
 
 	proto_tce = TCE_PCI_READ; // Read allowed
@@ -134,7 +100,7 @@
 	if (direction != DMA_TO_DEVICE)
 		proto_tce |= TCE_PCI_WRITE;
 
-	tces = tcep = ((__be64 *)tbl->it_base) + index;
+	tcep = ((__be64 *)tbl->it_base) + index;
 
 	while (npages--) {
 		/* can't move this out since we might cross MEMBLOCK boundary */
@@ -150,9 +116,9 @@
 
 static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
 {
-	__be64 *tcep, *tces;
+	__be64 *tcep;
 
-	tces = tcep = ((__be64 *)tbl->it_base) + index;
+	tcep = ((__be64 *)tbl->it_base) + index;
 
 	while (npages--)
 		*(tcep++) = 0;
@@ -644,8 +610,7 @@
 
 	iommu_table_setparms(pci->phb, dn, tbl);
 	tbl->it_ops = &iommu_table_pseries_ops;
-	iommu_init_table(tbl, pci->phb->node);
-	iommu_register_group(pci->table_group, pci_domain_nr(bus), 0);
+	iommu_init_table(tbl, pci->phb->node, 0, 0);
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
@@ -657,7 +622,8 @@
 
 #ifdef CONFIG_IOMMU_API
 static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
-				long *tce, enum dma_data_direction *direction)
+				long *tce, enum dma_data_direction *direction,
+				bool realmode)
 {
 	long rc;
 	unsigned long ioba = (unsigned long) index << tbl->it_page_shift;
@@ -685,7 +651,7 @@
 struct iommu_table_ops iommu_table_lpar_multi_ops = {
 	.set = tce_buildmulti_pSeriesLP,
 #ifdef CONFIG_IOMMU_API
-	.exchange = tce_exchange_pseries,
+	.xchg_no_kill = tce_exchange_pseries,
 #endif
 	.clear = tce_freemulti_pSeriesLP,
 	.get = tce_get_pSeriesLP
@@ -726,7 +692,7 @@
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
 				ppci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
-		iommu_init_table(tbl, ppci->phb->node);
+		iommu_init_table(tbl, ppci->phb->node, 0, 0);
 		iommu_register_group(ppci->table_group,
 				pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->table_group);
@@ -755,11 +721,8 @@
 		tbl = PCI_DN(dn)->table_group->tables[0];
 		iommu_table_setparms(phb, dn, tbl);
 		tbl->it_ops = &iommu_table_pseries_ops;
-		iommu_init_table(tbl, phb->node);
-		iommu_register_group(PCI_DN(dn)->table_group,
-				pci_domain_nr(phb->bus), 0);
+		iommu_init_table(tbl, phb->node, 0, 0);
 		set_iommu_table_base(&dev->dev, tbl);
-		iommu_add_device(&dev->dev);
 		return;
 	}
 
@@ -770,11 +733,10 @@
 	while (dn && PCI_DN(dn) && PCI_DN(dn)->table_group == NULL)
 		dn = dn->parent;
 
-	if (dn && PCI_DN(dn)) {
+	if (dn && PCI_DN(dn))
 		set_iommu_table_base(&dev->dev,
 				PCI_DN(dn)->table_group->tables[0]);
-		iommu_add_device(&dev->dev);
-	} else
+	else
 		printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
 		       pci_name(dev));
 }
@@ -964,6 +926,34 @@
 
 static LIST_HEAD(failed_ddw_pdn_list);
 
+static phys_addr_t ddw_memory_hotplug_max(void)
+{
+	phys_addr_t max_addr = memory_hotplug_max();
+	struct device_node *memory;
+
+	for_each_node_by_type(memory, "memory") {
+		unsigned long start, size;
+		int n_mem_addr_cells, n_mem_size_cells, len;
+		const __be32 *memcell_buf;
+
+		memcell_buf = of_get_property(memory, "reg", &len);
+		if (!memcell_buf || len <= 0)
+			continue;
+
+		n_mem_addr_cells = of_n_addr_cells(memory);
+		n_mem_size_cells = of_n_size_cells(memory);
+
+		start = of_read_number(memcell_buf, n_mem_addr_cells);
+		memcell_buf += n_mem_addr_cells;
+		size = of_read_number(memcell_buf, n_mem_size_cells);
+		memcell_buf += n_mem_size_cells;
+
+		max_addr = max_t(phys_addr_t, max_addr, start + size);
+	}
+
+	return max_addr;
+}
+
 /*
  * If the PE supports dynamic dma windows, and there is space for a table
  * that can map all pages in a linear offset, then setup such a table,
@@ -973,7 +963,7 @@
  * pdn: the parent pe node with the ibm,dma_window property
  * Future: also check if we can remap the base window for our base page size
  *
- * returns the dma offset for use by dma_set_mask
+ * returns the dma offset for use by the direct mapped DMA code.
  */
 static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 {
@@ -1053,7 +1043,7 @@
 	}
 	/* verify the window * number of ptes will map the partition */
 	/* check largest block * page size > max memory hotplug addr */
-	max_addr = memory_hotplug_max();
+	max_addr = ddw_memory_hotplug_max();
 	if (query.largest_available_block < (max_addr >> page_shift)) {
 		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %u "
 			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
@@ -1181,7 +1171,7 @@
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
 				pci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
-		iommu_init_table(tbl, pci->phb->node);
+		iommu_init_table(tbl, pci->phb->node, 0, 0);
 		iommu_register_group(pci->table_group,
 				pci_domain_nr(pci->phb->bus), 0);
 		pr_debug("  created table: %p\n", pci->table_group);
@@ -1190,90 +1180,40 @@
 	}
 
 	set_iommu_table_base(&dev->dev, pci->table_group->tables[0]);
-	iommu_add_device(&dev->dev);
+	iommu_add_device(pci->table_group, &dev->dev);
 }
 
-static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
+static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 {
-	bool ddw_enabled = false;
-	struct device_node *pdn, *dn;
-	struct pci_dev *pdev;
+	struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
 	const __be32 *dma_window = NULL;
-	u64 dma_offset;
-
-	if (!dev->dma_mask)
-		return -EIO;
-
-	if (!dev_is_pci(dev))
-		goto check_mask;
-
-	pdev = to_pci_dev(dev);
 
 	/* only attempt to use a new window if 64-bit DMA is requested */
-	if (!disable_ddw && dma_mask == DMA_BIT_MASK(64)) {
-		dn = pci_device_to_OF_node(pdev);
-		dev_dbg(dev, "node is %pOF\n", dn);
+	if (dma_mask < DMA_BIT_MASK(64))
+		return false;
 
-		/*
-		 * the device tree might contain the dma-window properties
-		 * per-device and not necessarily for the bus. So we need to
-		 * search upwards in the tree until we either hit a dma-window
-		 * property, OR find a parent with a table already allocated.
-		 */
-		for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
-				pdn = pdn->parent) {
-			dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
-			if (dma_window)
-				break;
-		}
-		if (pdn && PCI_DN(pdn)) {
-			dma_offset = enable_ddw(pdev, pdn);
-			if (dma_offset != 0) {
-				dev_info(dev, "Using 64-bit direct DMA at offset %llx\n", dma_offset);
-				set_dma_offset(dev, dma_offset);
-				set_dma_ops(dev, &dma_nommu_ops);
-				ddw_enabled = true;
-			}
-		}
+	dev_dbg(&pdev->dev, "node is %pOF\n", dn);
+
+	/*
+	 * the device tree might contain the dma-window properties
+	 * per-device and not necessarily for the bus. So we need to
+	 * search upwards in the tree until we either hit a dma-window
+	 * property, OR find a parent with a table already allocated.
+	 */
+	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
+			pdn = pdn->parent) {
+		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
+		if (dma_window)
+			break;
 	}
 
-	/* fall back on iommu ops */
-	if (!ddw_enabled && get_dma_ops(dev) != &dma_iommu_ops) {
-		dev_info(dev, "Restoring 32-bit DMA via iommu\n");
-		set_dma_ops(dev, &dma_iommu_ops);
+	if (pdn && PCI_DN(pdn)) {
+		pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn);
+		if (pdev->dev.archdata.dma_offset)
+			return true;
 	}
 
-check_mask:
-	if (!dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
-
-static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
-{
-	if (!dev->dma_mask)
-		return 0;
-
-	if (!disable_ddw && dev_is_pci(dev)) {
-		struct pci_dev *pdev = to_pci_dev(dev);
-		struct device_node *dn;
-
-		dn = pci_device_to_OF_node(pdev);
-
-		/* search upwards for ibm,dma-window */
-		for (; dn && PCI_DN(dn) && !PCI_DN(dn)->table_group;
-				dn = dn->parent)
-			if (of_get_property(dn, "ibm,dma-window", NULL))
-				break;
-		/* if there is a ibm,ddw-applicable property require 64 bits */
-		if (dn && PCI_DN(dn) &&
-				of_get_property(dn, "ibm,ddw-applicable", NULL))
-			return DMA_BIT_MASK(64);
-	}
-
-	return dma_iommu_ops.get_required_mask(dev);
+	return false;
 }
 
 static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
@@ -1368,8 +1308,9 @@
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
-		ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
-		ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
+		if (!disable_ddw)
+			pseries_pci_controller_ops.iommu_bypass_supported =
+				iommu_bypass_supported_pSeriesLP;
 	} else {
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries;
@@ -1379,7 +1320,15 @@
 	of_reconfig_notifier_register(&iommu_reconfig_nb);
 	register_memory_notifier(&iommu_mem_nb);
 
-	set_pci_dma_ops(&dma_iommu_ops);
+	/*
+	 * Secure guest memory is inacessible to devices so regular DMA isn't
+	 * possible.
+	 *
+	 * In that case keep devices' dma_map_ops as NULL so that the generic
+	 * DMA code path will use SWIOTLB to bounce buffers for DMA.
+	 */
+	if (!is_secure_guest())
+		set_pci_dma_ops(&dma_iommu_ops);
 }
 
 static int __init disable_multitce(char *str)
@@ -1395,4 +1344,27 @@
 
 __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);
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 23f5422..145fcfb 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright 2006 Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index d3992ce..f87a5c6 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * pSeries_lpar.c
  * Copyright (C) 2001 Todd Inglett, IBM Corporation
  *
  * pSeries LPAR support.
- * 
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- * 
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- * 
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 /* Enables debugging of low-level hash table routines - careful! */
@@ -30,6 +17,10 @@
 #include <linux/jump_label.h>
 #include <linux/delay.h>
 #include <linux/stop_machine.h>
+#include <linux/spinlock.h>
+#include <linux/cpuhotplug.h>
+#include <linux/workqueue.h>
+#include <linux/proc_fs.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/page.h>
@@ -48,6 +39,7 @@
 #include <asm/kexec.h>
 #include <asm/fadump.h>
 #include <asm/asm-prototypes.h>
+#include <asm/debugfs.h>
 
 #include "pseries.h"
 
@@ -64,13 +56,607 @@
 EXPORT_SYMBOL(plpar_hcall9);
 EXPORT_SYMBOL(plpar_hcall_norets);
 
+/*
+ * H_BLOCK_REMOVE supported block size for this page size in segment who's base
+ * page size is that page size.
+ *
+ * The first index is the segment base page size, the second one is the actual
+ * page size.
+ */
+static int hblkrm_size[MMU_PAGE_COUNT][MMU_PAGE_COUNT] __ro_after_init;
+
+/*
+ * Due to the involved complexity, and that the current hypervisor is only
+ * returning this value or 0, we are limiting the support of the H_BLOCK_REMOVE
+ * buffer size to 8 size block.
+ */
+#define HBLKRM_SUPPORTED_BLOCK_SIZE 8
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+static u8 dtl_mask = DTL_LOG_PREEMPT;
+#else
+static u8 dtl_mask;
+#endif
+
+void alloc_dtl_buffers(unsigned long *time_limit)
+{
+	int cpu;
+	struct paca_struct *pp;
+	struct dtl_entry *dtl;
+
+	for_each_possible_cpu(cpu) {
+		pp = paca_ptrs[cpu];
+		if (pp->dispatch_log)
+			continue;
+		dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL);
+		if (!dtl) {
+			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
+				cpu);
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+			pr_warn("Stolen time statistics will be unreliable\n");
+#endif
+			break;
+		}
+
+		pp->dtl_ridx = 0;
+		pp->dispatch_log = dtl;
+		pp->dispatch_log_end = dtl + N_DISPATCH_LOG;
+		pp->dtl_curr = dtl;
+
+		if (time_limit && time_after(jiffies, *time_limit)) {
+			cond_resched();
+			*time_limit = jiffies + HZ;
+		}
+	}
+}
+
+void register_dtl_buffer(int cpu)
+{
+	long ret;
+	struct paca_struct *pp;
+	struct dtl_entry *dtl;
+	int hwcpu = get_hard_smp_processor_id(cpu);
+
+	pp = paca_ptrs[cpu];
+	dtl = pp->dispatch_log;
+	if (dtl && dtl_mask) {
+		pp->dtl_ridx = 0;
+		pp->dtl_curr = dtl;
+		lppaca_of(cpu).dtl_idx = 0;
+
+		/* hypervisor reads buffer length from this field */
+		dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
+		ret = register_dtl(hwcpu, __pa(dtl));
+		if (ret)
+			pr_err("WARNING: DTL registration of cpu %d (hw %d) failed with %ld\n",
+			       cpu, hwcpu, ret);
+
+		lppaca_of(cpu).dtl_enable_mask = dtl_mask;
+	}
+}
+
+#ifdef CONFIG_PPC_SPLPAR
+struct dtl_worker {
+	struct delayed_work work;
+	int cpu;
+};
+
+struct vcpu_dispatch_data {
+	int last_disp_cpu;
+
+	int total_disp;
+
+	int same_cpu_disp;
+	int same_chip_disp;
+	int diff_chip_disp;
+	int far_chip_disp;
+
+	int numa_home_disp;
+	int numa_remote_disp;
+	int numa_far_disp;
+};
+
+/*
+ * This represents the number of cpus in the hypervisor. Since there is no
+ * architected way to discover the number of processors in the host, we
+ * provision for dealing with NR_CPUS. This is currently 2048 by default, and
+ * is sufficient for our purposes. This will need to be tweaked if
+ * CONFIG_NR_CPUS is changed.
+ */
+#define NR_CPUS_H	NR_CPUS
+
+DEFINE_RWLOCK(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);
+static enum cpuhp_state dtl_worker_state;
+static DEFINE_MUTEX(dtl_enable_mutex);
+static int vcpudispatch_stats_on __read_mostly;
+static int vcpudispatch_stats_freq = 50;
+static __be32 *vcpu_associativity, *pcpu_associativity;
+
+
+static void free_dtl_buffers(unsigned long *time_limit)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	int cpu;
+	struct paca_struct *pp;
+
+	for_each_possible_cpu(cpu) {
+		pp = paca_ptrs[cpu];
+		if (!pp->dispatch_log)
+			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;
+
+		if (time_limit && time_after(jiffies, *time_limit)) {
+			cond_resched();
+			*time_limit = jiffies + HZ;
+		}
+	}
+#endif
+}
+
+static int init_cpu_associativity(void)
+{
+	vcpu_associativity = kcalloc(num_possible_cpus() / threads_per_core,
+			VPHN_ASSOC_BUFSIZE * sizeof(__be32), GFP_KERNEL);
+	pcpu_associativity = kcalloc(NR_CPUS_H / threads_per_core,
+			VPHN_ASSOC_BUFSIZE * sizeof(__be32), GFP_KERNEL);
+
+	if (!vcpu_associativity || !pcpu_associativity) {
+		pr_err("error allocating memory for associativity information\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void destroy_cpu_associativity(void)
+{
+	kfree(vcpu_associativity);
+	kfree(pcpu_associativity);
+	vcpu_associativity = pcpu_associativity = 0;
+}
+
+static __be32 *__get_cpu_associativity(int cpu, __be32 *cpu_assoc, int flag)
+{
+	__be32 *assoc;
+	int rc = 0;
+
+	assoc = &cpu_assoc[(int)(cpu / threads_per_core) * VPHN_ASSOC_BUFSIZE];
+	if (!assoc[0]) {
+		rc = hcall_vphn(cpu, flag, &assoc[0]);
+		if (rc)
+			return NULL;
+	}
+
+	return assoc;
+}
+
+static __be32 *get_pcpu_associativity(int cpu)
+{
+	return __get_cpu_associativity(cpu, pcpu_associativity, VPHN_FLAG_PCPU);
+}
+
+static __be32 *get_vcpu_associativity(int cpu)
+{
+	return __get_cpu_associativity(cpu, vcpu_associativity, VPHN_FLAG_VCPU);
+}
+
+static int cpu_relative_dispatch_distance(int last_disp_cpu, int cur_disp_cpu)
+{
+	__be32 *last_disp_cpu_assoc, *cur_disp_cpu_assoc;
+
+	if (last_disp_cpu >= NR_CPUS_H || cur_disp_cpu >= NR_CPUS_H)
+		return -EINVAL;
+
+	last_disp_cpu_assoc = get_pcpu_associativity(last_disp_cpu);
+	cur_disp_cpu_assoc = get_pcpu_associativity(cur_disp_cpu);
+
+	if (!last_disp_cpu_assoc || !cur_disp_cpu_assoc)
+		return -EIO;
+
+	return cpu_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc);
+}
+
+static int cpu_home_node_dispatch_distance(int disp_cpu)
+{
+	__be32 *disp_cpu_assoc, *vcpu_assoc;
+	int vcpu_id = smp_processor_id();
+
+	if (disp_cpu >= NR_CPUS_H) {
+		pr_debug_ratelimited("vcpu dispatch cpu %d > %d\n",
+						disp_cpu, NR_CPUS_H);
+		return -EINVAL;
+	}
+
+	disp_cpu_assoc = get_pcpu_associativity(disp_cpu);
+	vcpu_assoc = get_vcpu_associativity(vcpu_id);
+
+	if (!disp_cpu_assoc || !vcpu_assoc)
+		return -EIO;
+
+	return cpu_distance(disp_cpu_assoc, vcpu_assoc);
+}
+
+static void update_vcpu_disp_stat(int disp_cpu)
+{
+	struct vcpu_dispatch_data *disp;
+	int distance;
+
+	disp = this_cpu_ptr(&vcpu_disp_data);
+	if (disp->last_disp_cpu == -1) {
+		disp->last_disp_cpu = disp_cpu;
+		return;
+	}
+
+	disp->total_disp++;
+
+	if (disp->last_disp_cpu == disp_cpu ||
+		(cpu_first_thread_sibling(disp->last_disp_cpu) ==
+					cpu_first_thread_sibling(disp_cpu)))
+		disp->same_cpu_disp++;
+	else {
+		distance = cpu_relative_dispatch_distance(disp->last_disp_cpu,
+								disp_cpu);
+		if (distance < 0)
+			pr_debug_ratelimited("vcpudispatch_stats: cpu %d: error determining associativity\n",
+					smp_processor_id());
+		else {
+			switch (distance) {
+			case 0:
+				disp->same_chip_disp++;
+				break;
+			case 1:
+				disp->diff_chip_disp++;
+				break;
+			case 2:
+				disp->far_chip_disp++;
+				break;
+			default:
+				pr_debug_ratelimited("vcpudispatch_stats: cpu %d (%d -> %d): unexpected relative dispatch distance %d\n",
+						 smp_processor_id(),
+						 disp->last_disp_cpu,
+						 disp_cpu,
+						 distance);
+			}
+		}
+	}
+
+	distance = cpu_home_node_dispatch_distance(disp_cpu);
+	if (distance < 0)
+		pr_debug_ratelimited("vcpudispatch_stats: cpu %d: error determining associativity\n",
+				smp_processor_id());
+	else {
+		switch (distance) {
+		case 0:
+			disp->numa_home_disp++;
+			break;
+		case 1:
+			disp->numa_remote_disp++;
+			break;
+		case 2:
+			disp->numa_far_disp++;
+			break;
+		default:
+			pr_debug_ratelimited("vcpudispatch_stats: cpu %d on %d: unexpected numa dispatch distance %d\n",
+						 smp_processor_id(),
+						 disp_cpu,
+						 distance);
+		}
+	}
+
+	disp->last_disp_cpu = disp_cpu;
+}
+
+static void process_dtl_buffer(struct work_struct *work)
+{
+	struct dtl_entry dtle;
+	u64 i = __this_cpu_read(dtl_entry_ridx);
+	struct dtl_entry *dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
+	struct dtl_entry *dtl_end = local_paca->dispatch_log_end;
+	struct lppaca *vpa = local_paca->lppaca_ptr;
+	struct dtl_worker *d = container_of(work, struct dtl_worker, work.work);
+
+	if (!local_paca->dispatch_log)
+		return;
+
+	/* if we have been migrated away, we cancel ourself */
+	if (d->cpu != smp_processor_id()) {
+		pr_debug("vcpudispatch_stats: cpu %d worker migrated -- canceling worker\n",
+						smp_processor_id());
+		return;
+	}
+
+	if (i == be64_to_cpu(vpa->dtl_idx))
+		goto out;
+
+	while (i < be64_to_cpu(vpa->dtl_idx)) {
+		dtle = *dtl;
+		barrier();
+		if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {
+			/* buffer has overflowed */
+			pr_debug_ratelimited("vcpudispatch_stats: cpu %d lost %lld DTL samples\n",
+				d->cpu,
+				be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG - i);
+			i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;
+			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
+			continue;
+		}
+		update_vcpu_disp_stat(be16_to_cpu(dtle.processor_id));
+		++i;
+		++dtl;
+		if (dtl == dtl_end)
+			dtl = local_paca->dispatch_log;
+	}
+
+	__this_cpu_write(dtl_entry_ridx, i);
+
+out:
+	schedule_delayed_work_on(d->cpu, to_delayed_work(work),
+					HZ / vcpudispatch_stats_freq);
+}
+
+static int dtl_worker_online(unsigned int cpu)
+{
+	struct dtl_worker *d = &per_cpu(dtl_workers, cpu);
+
+	memset(d, 0, sizeof(*d));
+	INIT_DELAYED_WORK(&d->work, process_dtl_buffer);
+	d->cpu = cpu;
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	per_cpu(dtl_entry_ridx, cpu) = 0;
+	register_dtl_buffer(cpu);
+#else
+	per_cpu(dtl_entry_ridx, cpu) = be64_to_cpu(lppaca_of(cpu).dtl_idx);
+#endif
+
+	schedule_delayed_work_on(cpu, &d->work, HZ / vcpudispatch_stats_freq);
+	return 0;
+}
+
+static int dtl_worker_offline(unsigned int cpu)
+{
+	struct dtl_worker *d = &per_cpu(dtl_workers, cpu);
+
+	cancel_delayed_work_sync(&d->work);
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	unregister_dtl(get_hard_smp_processor_id(cpu));
+#endif
+
+	return 0;
+}
+
+static void set_global_dtl_mask(u8 mask)
+{
+	int cpu;
+
+	dtl_mask = mask;
+	for_each_present_cpu(cpu)
+		lppaca_of(cpu).dtl_enable_mask = dtl_mask;
+}
+
+static void reset_global_dtl_mask(void)
+{
+	int cpu;
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	dtl_mask = DTL_LOG_PREEMPT;
+#else
+	dtl_mask = 0;
+#endif
+	for_each_present_cpu(cpu)
+		lppaca_of(cpu).dtl_enable_mask = dtl_mask;
+}
+
+static int dtl_worker_enable(unsigned long *time_limit)
+{
+	int rc = 0, state;
+
+	if (!write_trylock(&dtl_access_lock)) {
+		rc = -EBUSY;
+		goto out;
+	}
+
+	set_global_dtl_mask(DTL_LOG_ALL);
+
+	/* Setup dtl buffers and register those */
+	alloc_dtl_buffers(time_limit);
+
+	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/dtl:online",
+					dtl_worker_online, dtl_worker_offline);
+	if (state < 0) {
+		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);
+		rc = -EINVAL;
+		goto out;
+	}
+	dtl_worker_state = state;
+
+out:
+	return rc;
+}
+
+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);
+}
+
+static ssize_t vcpudispatch_stats_write(struct file *file, const char __user *p,
+		size_t count, loff_t *ppos)
+{
+	unsigned long time_limit = jiffies + HZ;
+	struct vcpu_dispatch_data *disp;
+	int rc, cmd, cpu;
+	char buf[16];
+
+	if (count > 15)
+		return -EINVAL;
+
+	if (copy_from_user(buf, p, count))
+		return -EFAULT;
+
+	buf[count] = 0;
+	rc = kstrtoint(buf, 0, &cmd);
+	if (rc || cmd < 0 || cmd > 1) {
+		pr_err("vcpudispatch_stats: please use 0 to disable or 1 to enable dispatch statistics\n");
+		return rc ? rc : -EINVAL;
+	}
+
+	mutex_lock(&dtl_enable_mutex);
+
+	if ((cmd == 0 && !vcpudispatch_stats_on) ||
+			(cmd == 1 && vcpudispatch_stats_on))
+		goto out;
+
+	if (cmd) {
+		rc = init_cpu_associativity();
+		if (rc)
+			goto out;
+
+		for_each_possible_cpu(cpu) {
+			disp = per_cpu_ptr(&vcpu_disp_data, cpu);
+			memset(disp, 0, sizeof(*disp));
+			disp->last_disp_cpu = -1;
+		}
+
+		rc = dtl_worker_enable(&time_limit);
+		if (rc) {
+			destroy_cpu_associativity();
+			goto out;
+		}
+	} else {
+		dtl_worker_disable(&time_limit);
+		destroy_cpu_associativity();
+	}
+
+	vcpudispatch_stats_on = cmd;
+
+out:
+	mutex_unlock(&dtl_enable_mutex);
+	if (rc)
+		return rc;
+	return count;
+}
+
+static int vcpudispatch_stats_display(struct seq_file *p, void *v)
+{
+	int cpu;
+	struct vcpu_dispatch_data *disp;
+
+	if (!vcpudispatch_stats_on) {
+		seq_puts(p, "off\n");
+		return 0;
+	}
+
+	for_each_online_cpu(cpu) {
+		disp = per_cpu_ptr(&vcpu_disp_data, cpu);
+		seq_printf(p, "cpu%d", cpu);
+		seq_put_decimal_ull(p, " ", disp->total_disp);
+		seq_put_decimal_ull(p, " ", disp->same_cpu_disp);
+		seq_put_decimal_ull(p, " ", disp->same_chip_disp);
+		seq_put_decimal_ull(p, " ", disp->diff_chip_disp);
+		seq_put_decimal_ull(p, " ", disp->far_chip_disp);
+		seq_put_decimal_ull(p, " ", disp->numa_home_disp);
+		seq_put_decimal_ull(p, " ", disp->numa_remote_disp);
+		seq_put_decimal_ull(p, " ", disp->numa_far_disp);
+		seq_puts(p, "\n");
+	}
+
+	return 0;
+}
+
+static int vcpudispatch_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, vcpudispatch_stats_display, NULL);
+}
+
+static const struct file_operations vcpudispatch_stats_proc_ops = {
+	.open		= vcpudispatch_stats_open,
+	.read		= seq_read,
+	.write		= vcpudispatch_stats_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static ssize_t vcpudispatch_stats_freq_write(struct file *file,
+		const char __user *p, size_t count, loff_t *ppos)
+{
+	int rc, freq;
+	char buf[16];
+
+	if (count > 15)
+		return -EINVAL;
+
+	if (copy_from_user(buf, p, count))
+		return -EFAULT;
+
+	buf[count] = 0;
+	rc = kstrtoint(buf, 0, &freq);
+	if (rc || freq < 1 || freq > HZ) {
+		pr_err("vcpudispatch_stats_freq: please specify a frequency between 1 and %d\n",
+				HZ);
+		return rc ? rc : -EINVAL;
+	}
+
+	vcpudispatch_stats_freq = freq;
+
+	return count;
+}
+
+static int vcpudispatch_stats_freq_display(struct seq_file *p, void *v)
+{
+	seq_printf(p, "%d\n", vcpudispatch_stats_freq);
+	return 0;
+}
+
+static int vcpudispatch_stats_freq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, vcpudispatch_stats_freq_display, NULL);
+}
+
+static const struct file_operations vcpudispatch_stats_freq_proc_ops = {
+	.open		= vcpudispatch_stats_freq_open,
+	.read		= seq_read,
+	.write		= vcpudispatch_stats_freq_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init vcpudispatch_stats_procfs_init(void)
+{
+	if (!lppaca_shared_proc(get_lppaca()))
+		return 0;
+
+	if (!proc_create("powerpc/vcpudispatch_stats", 0600, NULL,
+					&vcpudispatch_stats_proc_ops))
+		pr_err("vcpudispatch_stats: error creating procfs file\n");
+	else if (!proc_create("powerpc/vcpudispatch_stats_freq", 0600, NULL,
+					&vcpudispatch_stats_freq_proc_ops))
+		pr_err("vcpudispatch_stats_freq: error creating procfs file\n");
+
+	return 0;
+}
+
+machine_device_initcall(pseries, vcpudispatch_stats_procfs_init);
+#endif /* CONFIG_PPC_SPLPAR */
+
 void vpa_init(int cpu)
 {
 	int hwcpu = get_hard_smp_processor_id(cpu);
 	unsigned long addr;
 	long ret;
-	struct paca_struct *pp;
-	struct dtl_entry *dtl;
 
 	/*
 	 * The spec says it "may be problematic" if CPU x registers the VPA of
@@ -111,22 +697,7 @@
 	/*
 	 * Register dispatch trace log, if one has been allocated.
 	 */
-	pp = paca_ptrs[cpu];
-	dtl = pp->dispatch_log;
-	if (dtl) {
-		pp->dtl_ridx = 0;
-		pp->dtl_curr = dtl;
-		lppaca_of(cpu).dtl_idx = 0;
-
-		/* hypervisor reads buffer length from this field */
-		dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
-		ret = register_dtl(hwcpu, __pa(dtl));
-		if (ret)
-			pr_err("WARNING: DTL registration of cpu %d (hw %d) "
-			       "failed with %ld\n", smp_processor_id(),
-			       hwcpu, ret);
-		lppaca_of(cpu).dtl_enable_mask = 2;
-	}
+	register_dtl_buffer(cpu);
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -417,6 +988,90 @@
 	BUG_ON(lpar_rc != H_SUCCESS);
 }
 
+
+/*
+ * As defined in the PAPR's section 14.5.4.1.8
+ * The control mask doesn't include the returned reference and change bit from
+ * the processed PTE.
+ */
+#define HBLKR_AVPN		0x0100000000000000UL
+#define HBLKR_CTRL_MASK		0xf800000000000000UL
+#define HBLKR_CTRL_SUCCESS	0x8000000000000000UL
+#define HBLKR_CTRL_ERRNOTFOUND	0x8800000000000000UL
+#define HBLKR_CTRL_ERRBUSY	0xa000000000000000UL
+
+/*
+ * Returned true if we are supporting this block size for the specified segment
+ * base page size and actual page size.
+ *
+ * Currently, we only support 8 size block.
+ */
+static inline bool is_supported_hlbkrm(int bpsize, int psize)
+{
+	return (hblkrm_size[bpsize][psize] == HBLKRM_SUPPORTED_BLOCK_SIZE);
+}
+
+/**
+ * H_BLOCK_REMOVE caller.
+ * @idx should point to the latest @param entry set with a PTEX.
+ * If PTE cannot be processed because another CPUs has already locked that
+ * group, those entries are put back in @param starting at index 1.
+ * If entries has to be retried and @retry_busy is set to true, these entries
+ * are retried until success. If @retry_busy is set to false, the returned
+ * is the number of entries yet to process.
+ */
+static unsigned long call_block_remove(unsigned long idx, unsigned long *param,
+				       bool retry_busy)
+{
+	unsigned long i, rc, new_idx;
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+	if (idx < 2) {
+		pr_warn("Unexpected empty call to H_BLOCK_REMOVE");
+		return 0;
+	}
+again:
+	new_idx = 0;
+	if (idx > PLPAR_HCALL9_BUFSIZE) {
+		pr_err("Too many PTEs (%lu) for H_BLOCK_REMOVE", idx);
+		idx = PLPAR_HCALL9_BUFSIZE;
+	} else if (idx < PLPAR_HCALL9_BUFSIZE)
+		param[idx] = HBR_END;
+
+	rc = plpar_hcall9(H_BLOCK_REMOVE, retbuf,
+			  param[0], /* AVA */
+			  param[1],  param[2],  param[3],  param[4], /* TS0-7 */
+			  param[5],  param[6],  param[7],  param[8]);
+	if (rc == H_SUCCESS)
+		return 0;
+
+	BUG_ON(rc != H_PARTIAL);
+
+	/* Check that the unprocessed entries were 'not found' or 'busy' */
+	for (i = 0; i < idx-1; i++) {
+		unsigned long ctrl = retbuf[i] & HBLKR_CTRL_MASK;
+
+		if (ctrl == HBLKR_CTRL_ERRBUSY) {
+			param[++new_idx] = param[i+1];
+			continue;
+		}
+
+		BUG_ON(ctrl != HBLKR_CTRL_SUCCESS
+		       && ctrl != HBLKR_CTRL_ERRNOTFOUND);
+	}
+
+	/*
+	 * If there were entries found busy, retry these entries if requested,
+	 * of if all the entries have to be retried.
+	 */
+	if (new_idx && (retry_busy || new_idx == (PLPAR_HCALL9_BUFSIZE-1))) {
+		idx = new_idx + 1;
+		goto again;
+	}
+
+	return new_idx;
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need
@@ -424,17 +1079,57 @@
  */
 #define PPC64_HUGE_HPTE_BATCH 12
 
-static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
-					     unsigned long *vpn, int count,
-					     int psize, int ssize)
+static void hugepage_block_invalidate(unsigned long *slot, unsigned long *vpn,
+				      int count, int psize, int ssize)
+{
+	unsigned long param[PLPAR_HCALL9_BUFSIZE];
+	unsigned long shift, current_vpgb, vpgb;
+	int i, pix = 0;
+
+	shift = mmu_psize_defs[psize].shift;
+
+	for (i = 0; i < count; i++) {
+		/*
+		 * Shifting 3 bits more on the right to get a
+		 * 8 pages aligned virtual addresse.
+		 */
+		vpgb = (vpn[i] >> (shift - VPN_SHIFT + 3));
+		if (!pix || vpgb != current_vpgb) {
+			/*
+			 * Need to start a new 8 pages block, flush
+			 * the current one if needed.
+			 */
+			if (pix)
+				(void)call_block_remove(pix, param, true);
+			current_vpgb = vpgb;
+			param[0] = hpte_encode_avpn(vpn[i], psize, ssize);
+			pix = 1;
+		}
+
+		param[pix++] = HBR_REQUEST | HBLKR_AVPN | slot[i];
+		if (pix == PLPAR_HCALL9_BUFSIZE) {
+			pix = call_block_remove(pix, param, false);
+			/*
+			 * pix = 0 means that all the entries were
+			 * removed, we can start a new block.
+			 * Otherwise, this means that there are entries
+			 * to retry, and pix points to latest one, so
+			 * we should increment it and try to continue
+			 * the same block.
+			 */
+			if (pix)
+				pix++;
+		}
+	}
+	if (pix)
+		(void)call_block_remove(pix, param, true);
+}
+
+static void hugepage_bulk_invalidate(unsigned long *slot, unsigned long *vpn,
+				     int count, int psize, int ssize)
 {
 	unsigned long param[PLPAR_HCALL9_BUFSIZE];
 	int i = 0, pix = 0, rc;
-	unsigned long flags = 0;
-	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
-
-	if (lock_tlbie)
-		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
 
 	for (i = 0; i < count; i++) {
 
@@ -462,6 +1157,24 @@
 				  param[6], param[7]);
 		BUG_ON(rc != H_SUCCESS);
 	}
+}
+
+static inline void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
+						      unsigned long *vpn,
+						      int count, int psize,
+						      int ssize)
+{
+	unsigned long flags = 0;
+	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+	if (lock_tlbie)
+		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
+
+	/* Assuming THP size is 16M */
+	if (is_supported_hlbkrm(psize, MMU_PAGE_16M))
+		hugepage_block_invalidate(slot, vpn, count, psize, ssize);
+	else
+		hugepage_bulk_invalidate(slot, vpn, count, psize, ssize);
 
 	if (lock_tlbie)
 		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
@@ -546,6 +1259,220 @@
 	return 0;
 }
 
+
+static inline unsigned long compute_slot(real_pte_t pte,
+					 unsigned long vpn,
+					 unsigned long index,
+					 unsigned long shift,
+					 int ssize)
+{
+	unsigned long slot, hash, hidx;
+
+	hash = hpt_hash(vpn, shift, ssize);
+	hidx = __rpte_to_hidx(pte, index);
+	if (hidx & _PTEIDX_SECONDARY)
+		hash = ~hash;
+	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+	slot += hidx & _PTEIDX_GROUP_IX;
+	return slot;
+}
+
+/**
+ * The hcall H_BLOCK_REMOVE implies that the virtual pages to processed are
+ * "all within the same naturally aligned 8 page virtual address block".
+ */
+static void do_block_remove(unsigned long number, struct ppc64_tlb_batch *batch,
+			    unsigned long *param)
+{
+	unsigned long vpn;
+	unsigned long i, pix = 0;
+	unsigned long index, shift, slot, current_vpgb, vpgb;
+	real_pte_t pte;
+	int psize, ssize;
+
+	psize = batch->psize;
+	ssize = batch->ssize;
+
+	for (i = 0; i < number; i++) {
+		vpn = batch->vpn[i];
+		pte = batch->pte[i];
+		pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
+			/*
+			 * Shifting 3 bits more on the right to get a
+			 * 8 pages aligned virtual addresse.
+			 */
+			vpgb = (vpn >> (shift - VPN_SHIFT + 3));
+			if (!pix || vpgb != current_vpgb) {
+				/*
+				 * Need to start a new 8 pages block, flush
+				 * the current one if needed.
+				 */
+				if (pix)
+					(void)call_block_remove(pix, param,
+								true);
+				current_vpgb = vpgb;
+				param[0] = hpte_encode_avpn(vpn, psize,
+							    ssize);
+				pix = 1;
+			}
+
+			slot = compute_slot(pte, vpn, index, shift, ssize);
+			param[pix++] = HBR_REQUEST | HBLKR_AVPN | slot;
+
+			if (pix == PLPAR_HCALL9_BUFSIZE) {
+				pix = call_block_remove(pix, param, false);
+				/*
+				 * pix = 0 means that all the entries were
+				 * removed, we can start a new block.
+				 * Otherwise, this means that there are entries
+				 * to retry, and pix points to latest one, so
+				 * we should increment it and try to continue
+				 * the same block.
+				 */
+				if (pix)
+					pix++;
+			}
+		} pte_iterate_hashed_end();
+	}
+
+	if (pix)
+		(void)call_block_remove(pix, param, true);
+}
+
+/*
+ * TLB Block Invalidate Characteristics
+ *
+ * These characteristics define the size of the block the hcall H_BLOCK_REMOVE
+ * is able to process for each couple segment base page size, actual page size.
+ *
+ * The ibm,get-system-parameter properties is returning a buffer with the
+ * following layout:
+ *
+ * [ 2 bytes size of the RTAS buffer (excluding these 2 bytes) ]
+ * -----------------
+ * TLB Block Invalidate Specifiers:
+ * [ 1 byte LOG base 2 of the TLB invalidate block size being specified ]
+ * [ 1 byte Number of page sizes (N) that are supported for the specified
+ *          TLB invalidate block size ]
+ * [ 1 byte Encoded segment base page size and actual page size
+ *          MSB=0 means 4k segment base page size and actual page size
+ *          MSB=1 the penc value in mmu_psize_def ]
+ * ...
+ * -----------------
+ * Next TLB Block Invalidate Specifiers...
+ * -----------------
+ * [ 0 ]
+ */
+static inline void set_hblkrm_bloc_size(int bpsize, int psize,
+					unsigned int block_size)
+{
+	if (block_size > hblkrm_size[bpsize][psize])
+		hblkrm_size[bpsize][psize] = block_size;
+}
+
+/*
+ * Decode the Encoded segment base page size and actual page size.
+ * PAPR specifies:
+ *   - bit 7 is the L bit
+ *   - bits 0-5 are the penc value
+ * If the L bit is 0, this means 4K segment base page size and actual page size
+ * otherwise the penc value should be read.
+ */
+#define HBLKRM_L_MASK		0x80
+#define HBLKRM_PENC_MASK	0x3f
+static inline void __init check_lp_set_hblkrm(unsigned int lp,
+					      unsigned int block_size)
+{
+	unsigned int bpsize, psize;
+
+	/* First, check the L bit, if not set, this means 4K */
+	if ((lp & HBLKRM_L_MASK) == 0) {
+		set_hblkrm_bloc_size(MMU_PAGE_4K, MMU_PAGE_4K, block_size);
+		return;
+	}
+
+	lp &= HBLKRM_PENC_MASK;
+	for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++) {
+		struct mmu_psize_def *def = &mmu_psize_defs[bpsize];
+
+		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+			if (def->penc[psize] == lp) {
+				set_hblkrm_bloc_size(bpsize, psize, block_size);
+				return;
+			}
+		}
+	}
+}
+
+#define SPLPAR_TLB_BIC_TOKEN		50
+
+/*
+ * The size of the TLB Block Invalidate Characteristics is variable. But at the
+ * maximum it will be the number of possible page sizes *2 + 10 bytes.
+ * Currently MMU_PAGE_COUNT is 16, which means 42 bytes. Use a cache line size
+ * (128 bytes) for the buffer to get plenty of space.
+ */
+#define SPLPAR_TLB_BIC_MAXLENGTH	128
+
+void __init pseries_lpar_read_hblkrm_characteristics(void)
+{
+	unsigned char local_buffer[SPLPAR_TLB_BIC_MAXLENGTH];
+	int call_status, len, idx, bpsize;
+
+	if (!firmware_has_feature(FW_FEATURE_BLOCK_REMOVE))
+		return;
+
+	spin_lock(&rtas_data_buf_lock);
+	memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE);
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				SPLPAR_TLB_BIC_TOKEN,
+				__pa(rtas_data_buf),
+				RTAS_DATA_BUF_SIZE);
+	memcpy(local_buffer, rtas_data_buf, SPLPAR_TLB_BIC_MAXLENGTH);
+	local_buffer[SPLPAR_TLB_BIC_MAXLENGTH - 1] = '\0';
+	spin_unlock(&rtas_data_buf_lock);
+
+	if (call_status != 0) {
+		pr_warn("%s %s Error calling get-system-parameter (0x%x)\n",
+			__FILE__, __func__, call_status);
+		return;
+	}
+
+	/*
+	 * The first two (2) bytes of the data in the buffer are the length of
+	 * the returned data, not counting these first two (2) bytes.
+	 */
+	len = be16_to_cpu(*((u16 *)local_buffer)) + 2;
+	if (len > SPLPAR_TLB_BIC_MAXLENGTH) {
+		pr_warn("%s too large returned buffer %d", __func__, len);
+		return;
+	}
+
+	idx = 2;
+	while (idx < len) {
+		u8 block_shift = local_buffer[idx++];
+		u32 block_size;
+		unsigned int npsize;
+
+		if (!block_shift)
+			break;
+
+		block_size = 1 << block_shift;
+
+		for (npsize = local_buffer[idx++];
+		     npsize > 0 && idx < len; npsize--)
+			check_lp_set_hblkrm((unsigned int) local_buffer[idx++],
+					    block_size);
+	}
+
+	for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++)
+		for (idx = 0; idx < MMU_PAGE_COUNT; idx++)
+			if (hblkrm_size[bpsize][idx])
+				pr_info("H_BLOCK_REMOVE supports base psize:%d psize:%d block size:%d",
+					bpsize, idx, hblkrm_size[bpsize][idx]);
+}
+
 /*
  * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
  * lock.
@@ -558,13 +1485,18 @@
 	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 	unsigned long param[PLPAR_HCALL9_BUFSIZE];
-	unsigned long hash, index, shift, hidx, slot;
+	unsigned long index, shift, slot;
 	real_pte_t pte;
 	int psize, ssize;
 
 	if (lock_tlbie)
 		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
 
+	if (is_supported_hlbkrm(batch->psize, batch->psize)) {
+		do_block_remove(number, batch, param);
+		goto out;
+	}
+
 	psize = batch->psize;
 	ssize = batch->ssize;
 	pix = 0;
@@ -572,12 +1504,7 @@
 		vpn = batch->vpn[i];
 		pte = batch->pte[i];
 		pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
-			hash = hpt_hash(vpn, shift, ssize);
-			hidx = __rpte_to_hidx(pte, index);
-			if (hidx & _PTEIDX_SECONDARY)
-				hash = ~hash;
-			slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-			slot += hidx & _PTEIDX_GROUP_IX;
+			slot = compute_slot(pte, vpn, index, shift, ssize);
 			if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
 				/*
 				 * lpar doesn't use the passed actual page size
@@ -608,6 +1535,7 @@
 		BUG_ON(rc != H_SUCCESS);
 	}
 
+out:
 	if (lock_tlbie)
 		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
 }
@@ -647,7 +1575,10 @@
 	return 0;
 }
 
-/* Must be called in user context */
+/*
+ * Must be called in process context. The caller must hold the
+ * cpus_lock.
+ */
 static int pseries_lpar_resize_hpt(unsigned long shift)
 {
 	struct hpt_resize_state state = {
@@ -689,8 +1620,10 @@
 		break;
 
 	case H_PARAMETER:
+		pr_warn("Invalid argument from H_RESIZE_HPT_PREPARE\n");
 		return -EINVAL;
 	case H_RESOURCE:
+		pr_warn("Operation not permitted from H_RESIZE_HPT_PREPARE\n");
 		return -EPERM;
 	default:
 		pr_warn("Unexpected error %d from H_RESIZE_HPT_PREPARE\n", rc);
@@ -699,14 +1632,14 @@
 
 	t1 = ktime_get();
 
-	rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL);
+	rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit,
+				     &state, NULL);
 
 	t2 = ktime_get();
 
 	if (rc != 0) {
 		switch (state.commit_rc) {
 		case H_PTEG_FULL:
-			pr_warn("Hash collision while resizing HPT\n");
 			return -ENOSPC;
 
 		default:
@@ -760,16 +1693,24 @@
 	mmu_hash_ops.flush_hash_range	 = pSeries_lpar_flush_hash_range;
 	mmu_hash_ops.hpte_clear_all      = pseries_hpte_clear_all;
 	mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
-	register_process_table		 = pseries_lpar_register_process_table;
 
 	if (firmware_has_feature(FW_FEATURE_HPT_RESIZE))
 		mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;
+
+	/*
+	 * On POWER9, we need to do a H_REGISTER_PROC_TBL hcall
+	 * to inform the hypervisor that we wish to use the HPT.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		pseries_lpar_register_process_table(0, 0, 0);
 }
 
 void radix_init_pseries(void)
 {
 	pr_info("Using radix MMU under hypervisor\n");
-	register_process_table = pseries_lpar_register_process_table;
+
+	pseries_lpar_register_process_table(__pa(process_tb),
+						0, PRTB_SIZE_SHIFT - 12);
 }
 
 #ifdef CONFIG_PPC_SMLPAR
@@ -828,7 +1769,7 @@
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 #ifdef CONFIG_TRACEPOINTS
-#ifdef HAVE_JUMP_LABEL
+#ifdef CONFIG_JUMP_LABEL
 struct static_key hcall_tracepoint_key = STATIC_KEY_INIT;
 
 int hcall_tracepoint_regfunc(void)
@@ -1028,3 +1969,56 @@
 	return 0;
 }
 machine_device_initcall(pseries, reserve_vrma_context_id);
+
+#ifdef CONFIG_DEBUG_FS
+/* debugfs file interface for vpa data */
+static ssize_t vpa_file_read(struct file *filp, char __user *buf, size_t len,
+			      loff_t *pos)
+{
+	int cpu = (long)filp->private_data;
+	struct lppaca *lppaca = &lppaca_of(cpu);
+
+	return simple_read_from_buffer(buf, len, pos, lppaca,
+				sizeof(struct lppaca));
+}
+
+static const struct file_operations vpa_fops = {
+	.open		= simple_open,
+	.read		= vpa_file_read,
+	.llseek		= default_llseek,
+};
+
+static int __init vpa_debugfs_init(void)
+{
+	char name[16];
+	long i;
+	static struct dentry *vpa_dir;
+
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return 0;
+
+	vpa_dir = debugfs_create_dir("vpa", powerpc_debugfs_root);
+	if (!vpa_dir) {
+		pr_warn("%s: can't create vpa root dir\n", __func__);
+		return -ENOMEM;
+	}
+
+	/* set up the per-cpu vpa file*/
+	for_each_possible_cpu(i) {
+		struct dentry *d;
+
+		sprintf(name, "cpu-%ld", i);
+
+		d = debugfs_create_file(name, 0400, vpa_dir, (void *)i,
+					&vpa_fops);
+		if (!d) {
+			pr_warn("%s: can't create per-cpu vpa file\n",
+					__func__);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+machine_arch_initcall(pseries, vpa_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 7c872dc..e33e8bc 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PowerPC64 LPAR Configuration Information Driver
  *
@@ -9,11 +10,6 @@
  * Nathan Lynch nathanl@austin.ibm.com
  *    Added lparcfg_write, Copyright (C) 2004 Nathan Lynch IBM 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; either version
- *      2 of the License, or (at your option) any later version.
- *
  * This driver creates a proc file at /proc/ppc64/lparcfg which contains
  * keyword - value pairs that specify the configuration of the partition.
  */
@@ -26,6 +22,7 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/hugetlb.h>
 #include <asm/lppaca.h>
 #include <asm/hvcall.h>
 #include <asm/firmware.h>
@@ -36,6 +33,7 @@
 #include <asm/vio.h>
 #include <asm/mmu.h>
 #include <asm/machdep.h>
+#include <asm/drmem.h>
 
 #include "pseries.h"
 
@@ -433,6 +431,16 @@
 		seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
 }
 
+static void maxmem_data(struct seq_file *m)
+{
+	unsigned long maxmem = 0;
+
+	maxmem += drmem_info->n_lmbs * drmem_info->lmb_size;
+	maxmem += hugetlb_total_pages() * PAGE_SIZE;
+
+	seq_printf(m, "MaxMem=%ld\n", maxmem);
+}
+
 static int pseries_lparcfg_data(struct seq_file *m, void *v)
 {
 	int partition_potential_processors;
@@ -463,6 +471,7 @@
 		splpar_dispatch_data(m);
 
 		seq_printf(m, "purr=%ld\n", get_purr());
+		seq_printf(m, "tbr=%ld\n", mftb());
 	} else {		/* non SPLPAR case */
 
 		seq_printf(m, "system_active_processors=%d\n",
@@ -491,6 +500,7 @@
 	seq_printf(m, "slb_size=%d\n", mmu_slb_size);
 #endif
 	parse_em_data(m);
+	maxmem_data(m);
 
 	return 0;
 }
@@ -585,8 +595,7 @@
 static ssize_t lparcfg_write(struct file *file, const char __user * buf,
 			     size_t count, loff_t * off)
 {
-	int kbuf_sz = 64;
-	char kbuf[kbuf_sz];
+	char kbuf[64];
 	char *tmp;
 	u64 new_entitled, *new_entitled_ptr = &new_entitled;
 	u8 new_weight, *new_weight_ptr = &new_weight;
@@ -595,7 +604,7 @@
 	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
 		return -EINVAL;
 
-	if (count > kbuf_sz)
+	if (count > sizeof(kbuf))
 		return -EINVAL;
 
 	if (copy_from_user(kbuf, buf, count))
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index f0e30dc..b571285 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -1,16 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Support for Partition Mobility/Migration
  *
  * Copyright (C) 2010 Nathan Fontenot
  * Copyright (C) 2010 IBM Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/kobject.h>
+#include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/stat.h>
 #include <linux/completion.h>
@@ -22,6 +21,7 @@
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include "pseries.h"
+#include "../../kernel/cacheinfo.h"
 
 static struct kobject *mobility_kobj;
 
@@ -208,7 +208,11 @@
 
 				prop_data += vd;
 			}
+
+			cond_resched();
 		}
+
+		cond_resched();
 	} while (rtas_rc == 1);
 
 	of_node_put(dn);
@@ -242,7 +246,7 @@
 
 static void prrn_update_node(__be32 phandle)
 {
-	struct pseries_hp_errorlog *hp_elog;
+	struct pseries_hp_errorlog hp_elog;
 	struct device_node *dn;
 
 	/*
@@ -255,18 +259,12 @@
 		return;
 	}
 
-	hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL);
-	if(!hp_elog)
-		return;
+	hp_elog.resource = PSERIES_HP_ELOG_RESOURCE_MEM;
+	hp_elog.action = PSERIES_HP_ELOG_ACTION_READD;
+	hp_elog.id_type = PSERIES_HP_ELOG_ID_DRC_INDEX;
+	hp_elog._drc_u.drc_index = phandle;
 
-	hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM;
-	hp_elog->action = PSERIES_HP_ELOG_ACTION_READD;
-	hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_INDEX;
-	hp_elog->_drc_u.drc_index = phandle;
-
-	queue_hotplug_event(hp_elog, NULL, NULL);
-
-	kfree(hp_elog);
+	handle_dlpar_errorlog(&hp_elog);
 }
 
 int pseries_devicetree_update(s32 scope)
@@ -317,8 +315,12 @@
 					add_dt_node(phandle, drc_index);
 					break;
 				}
+
+				cond_resched();
 			}
 		}
+
+		cond_resched();
 	} while (rc == 1);
 
 	kfree(rtas_buf);
@@ -344,11 +346,28 @@
 	if (rc)
 		printk(KERN_ERR "Post-mobility activate-fw failed: %d\n", rc);
 
+	/*
+	 * We don't want CPUs to go online/offline while the device
+	 * tree is being updated.
+	 */
+	cpus_read_lock();
+
+	/*
+	 * It's common for the destination firmware to replace cache
+	 * nodes.  Release all of the cacheinfo hierarchy's references
+	 * before updating the device tree.
+	 */
+	cacheinfo_teardown();
+
 	rc = pseries_devicetree_update(MIGRATION_SCOPE);
 	if (rc)
 		printk(KERN_ERR "Post-mobility device tree update "
 			"failed: %d\n", rc);
 
+	cacheinfo_rebuild();
+
+	cpus_read_unlock();
+
 	/* Possibly switch to a new RFI flush type */
 	pseries_setup_rfi_flush();
 
@@ -366,6 +385,8 @@
 	if (rc)
 		return rc;
 
+	stop_topology_update();
+
 	do {
 		rc = rtas_ibm_suspend_me(streamid);
 		if (rc == -EAGAIN)
@@ -376,6 +397,9 @@
 		return rc;
 
 	post_mobility_fixup();
+
+	start_topology_update();
+
 	return count;
 }
 
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index b749694..133f6ad 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -1,12 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2006 Jake Moilanen <moilanen@austin.ibm.com>, IBM Corp.
  * Copyright 2006-2007 Michael Ellerman, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2 of the
- * License.
- *
  */
 
 #include <linux/device.h>
@@ -203,7 +198,8 @@
 	/* Get the top level device in the PE */
 	edev = pdn_to_eeh_dev(PCI_DN(dn));
 	if (edev->pe)
-		edev = list_first_entry(&edev->pe->edevs, struct eeh_dev, list);
+		edev = list_first_entry(&edev->pe->edevs, struct eeh_dev,
+					entry);
 	dn = pci_device_to_OF_node(edev->pdev);
 	if (!dn)
 		return NULL;
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 69cedc1..69db2ec 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -1,14 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  c 2001 PPC 64 Team, IBM Corp
  *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- *
  * /dev/nvram driver for PPC64
- *
- * This perhaps should live in drivers/char
  */
 
 
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
new file mode 100644
index 0000000..6188329
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -0,0 +1,524 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define pr_fmt(fmt)	"papr-scm: " fmt
+
+#include <linux/of.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/ndctl.h>
+#include <linux/sched.h>
+#include <linux/libnvdimm.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+
+#include <asm/plpar_wrappers.h>
+
+#define BIND_ANY_ADDR (~0ul)
+
+#define PAPR_SCM_DIMM_CMD_MASK \
+	((1ul << ND_CMD_GET_CONFIG_SIZE) | \
+	 (1ul << ND_CMD_GET_CONFIG_DATA) | \
+	 (1ul << ND_CMD_SET_CONFIG_DATA))
+
+struct papr_scm_priv {
+	struct platform_device *pdev;
+	struct device_node *dn;
+	uint32_t drc_index;
+	uint64_t blocks;
+	uint64_t block_size;
+	int metadata_size;
+	bool is_volatile;
+
+	uint64_t bound_addr;
+
+	struct nvdimm_bus_descriptor bus_desc;
+	struct nvdimm_bus *bus;
+	struct nvdimm *nvdimm;
+	struct resource res;
+	struct nd_region *region;
+	struct nd_interleave_set nd_set;
+};
+
+static int drc_pmem_bind(struct papr_scm_priv *p)
+{
+	unsigned long ret[PLPAR_HCALL_BUFSIZE];
+	uint64_t saved = 0;
+	uint64_t token;
+	int64_t rc;
+
+	/*
+	 * When the hypervisor cannot map all the requested memory in a single
+	 * hcall it returns H_BUSY and we call again with the token until
+	 * we get H_SUCCESS. Aborting the retry loop before getting H_SUCCESS
+	 * leave the system in an undefined state, so we wait.
+	 */
+	token = 0;
+
+	do {
+		rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0,
+				p->blocks, BIND_ANY_ADDR, token);
+		token = ret[0];
+		if (!saved)
+			saved = ret[1];
+		cond_resched();
+	} while (rc == H_BUSY);
+
+	if (rc)
+		return rc;
+
+	p->bound_addr = saved;
+	dev_dbg(&p->pdev->dev, "bound drc 0x%x to %pR\n", p->drc_index, &p->res);
+	return rc;
+}
+
+static void drc_pmem_unbind(struct papr_scm_priv *p)
+{
+	unsigned long ret[PLPAR_HCALL_BUFSIZE];
+	uint64_t token = 0;
+	int64_t rc;
+
+	dev_dbg(&p->pdev->dev, "unbind drc 0x%x\n", p->drc_index);
+
+	/* NB: unbind has the same retry requirements as drc_pmem_bind() */
+	do {
+
+		/* Unbind of all SCM resources associated with drcIndex */
+		rc = plpar_hcall(H_SCM_UNBIND_ALL, ret, H_UNBIND_SCOPE_DRC,
+				 p->drc_index, token);
+		token = ret[0];
+
+		/* Check if we are stalled for some time */
+		if (H_IS_LONG_BUSY(rc)) {
+			msleep(get_longbusy_msecs(rc));
+			rc = H_BUSY;
+		} else if (rc == H_BUSY) {
+			cond_resched();
+		}
+
+	} while (rc == H_BUSY);
+
+	if (rc)
+		dev_err(&p->pdev->dev, "unbind error: %lld\n", rc);
+	else
+		dev_dbg(&p->pdev->dev, "unbind drc 0x%x complete\n",
+			p->drc_index);
+
+	return;
+}
+
+static int drc_pmem_query_n_bind(struct papr_scm_priv *p)
+{
+	unsigned long start_addr;
+	unsigned long end_addr;
+	unsigned long ret[PLPAR_HCALL_BUFSIZE];
+	int64_t rc;
+
+
+	rc = plpar_hcall(H_SCM_QUERY_BLOCK_MEM_BINDING, ret,
+			 p->drc_index, 0);
+	if (rc)
+		goto err_out;
+	start_addr = ret[0];
+
+	/* Make sure the full region is bound. */
+	rc = plpar_hcall(H_SCM_QUERY_BLOCK_MEM_BINDING, ret,
+			 p->drc_index, p->blocks - 1);
+	if (rc)
+		goto err_out;
+	end_addr = ret[0];
+
+	if ((end_addr - start_addr) != ((p->blocks - 1) * p->block_size))
+		goto err_out;
+
+	p->bound_addr = start_addr;
+	dev_dbg(&p->pdev->dev, "bound drc 0x%x to %pR\n", p->drc_index, &p->res);
+	return rc;
+
+err_out:
+	dev_info(&p->pdev->dev,
+		 "Failed to query, trying an unbind followed by bind");
+	drc_pmem_unbind(p);
+	return drc_pmem_bind(p);
+}
+
+
+static int papr_scm_meta_get(struct papr_scm_priv *p,
+			     struct nd_cmd_get_config_data_hdr *hdr)
+{
+	unsigned long data[PLPAR_HCALL_BUFSIZE];
+	unsigned long offset, data_offset;
+	int len, read;
+	int64_t ret;
+
+	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+		return -EINVAL;
+
+	for (len = hdr->in_length; len; len -= read) {
+
+		data_offset = hdr->in_length - len;
+		offset = hdr->in_offset + data_offset;
+
+		if (len >= 8)
+			read = 8;
+		else if (len >= 4)
+			read = 4;
+		else if (len >= 2)
+			read = 2;
+		else
+			read = 1;
+
+		ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index,
+				  offset, read);
+
+		if (ret == H_PARAMETER) /* bad DRC index */
+			return -ENODEV;
+		if (ret)
+			return -EINVAL; /* other invalid parameter */
+
+		switch (read) {
+		case 8:
+			*(uint64_t *)(hdr->out_buf + data_offset) = be64_to_cpu(data[0]);
+			break;
+		case 4:
+			*(uint32_t *)(hdr->out_buf + data_offset) = be32_to_cpu(data[0] & 0xffffffff);
+			break;
+
+		case 2:
+			*(uint16_t *)(hdr->out_buf + data_offset) = be16_to_cpu(data[0] & 0xffff);
+			break;
+
+		case 1:
+			*(uint8_t *)(hdr->out_buf + data_offset) = (data[0] & 0xff);
+			break;
+		}
+	}
+	return 0;
+}
+
+static int papr_scm_meta_set(struct papr_scm_priv *p,
+			     struct nd_cmd_set_config_hdr *hdr)
+{
+	unsigned long offset, data_offset;
+	int len, wrote;
+	unsigned long data;
+	__be64 data_be;
+	int64_t ret;
+
+	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+		return -EINVAL;
+
+	for (len = hdr->in_length; len; len -= wrote) {
+
+		data_offset = hdr->in_length - len;
+		offset = hdr->in_offset + data_offset;
+
+		if (len >= 8) {
+			data = *(uint64_t *)(hdr->in_buf + data_offset);
+			data_be = cpu_to_be64(data);
+			wrote = 8;
+		} else if (len >= 4) {
+			data = *(uint32_t *)(hdr->in_buf + data_offset);
+			data &= 0xffffffff;
+			data_be = cpu_to_be32(data);
+			wrote = 4;
+		} else if (len >= 2) {
+			data = *(uint16_t *)(hdr->in_buf + data_offset);
+			data &= 0xffff;
+			data_be = cpu_to_be16(data);
+			wrote = 2;
+		} else {
+			data_be = *(uint8_t *)(hdr->in_buf + data_offset);
+			data_be &= 0xff;
+			wrote = 1;
+		}
+
+		ret = plpar_hcall_norets(H_SCM_WRITE_METADATA, p->drc_index,
+					 offset, data_be, wrote);
+		if (ret == H_PARAMETER) /* bad DRC index */
+			return -ENODEV;
+		if (ret)
+			return -EINVAL; /* other invalid parameter */
+	}
+
+	return 0;
+}
+
+int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
+		unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc)
+{
+	struct nd_cmd_get_config_size *get_size_hdr;
+	struct papr_scm_priv *p;
+
+	/* Only dimm-specific calls are supported atm */
+	if (!nvdimm)
+		return -EINVAL;
+
+	p = nvdimm_provider_data(nvdimm);
+
+	switch (cmd) {
+	case ND_CMD_GET_CONFIG_SIZE:
+		get_size_hdr = buf;
+
+		get_size_hdr->status = 0;
+		get_size_hdr->max_xfer = 8;
+		get_size_hdr->config_size = p->metadata_size;
+		*cmd_rc = 0;
+		break;
+
+	case ND_CMD_GET_CONFIG_DATA:
+		*cmd_rc = papr_scm_meta_get(p, buf);
+		break;
+
+	case ND_CMD_SET_CONFIG_DATA:
+		*cmd_rc = papr_scm_meta_set(p, buf);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	dev_dbg(&p->pdev->dev, "returned with cmd_rc = %d\n", *cmd_rc);
+
+	return 0;
+}
+
+static const struct attribute_group *region_attr_groups[] = {
+	&nd_region_attribute_group,
+	&nd_device_attribute_group,
+	&nd_mapping_attribute_group,
+	&nd_numa_attribute_group,
+	NULL,
+};
+
+static const struct attribute_group *bus_attr_groups[] = {
+	&nvdimm_bus_attribute_group,
+	NULL,
+};
+
+static const struct attribute_group *papr_scm_dimm_groups[] = {
+	&nvdimm_attribute_group,
+	&nd_device_attribute_group,
+	NULL,
+};
+
+static inline int papr_scm_node(int node)
+{
+	int min_dist = INT_MAX, dist;
+	int nid, min_node;
+
+	if ((node == NUMA_NO_NODE) || node_online(node))
+		return node;
+
+	min_node = first_online_node;
+	for_each_online_node(nid) {
+		dist = node_distance(node, nid);
+		if (dist < min_dist) {
+			min_dist = dist;
+			min_node = nid;
+		}
+	}
+	return min_node;
+}
+
+static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
+{
+	struct device *dev = &p->pdev->dev;
+	struct nd_mapping_desc mapping;
+	struct nd_region_desc ndr_desc;
+	unsigned long dimm_flags;
+	int target_nid, online_nid;
+
+	p->bus_desc.ndctl = papr_scm_ndctl;
+	p->bus_desc.module = THIS_MODULE;
+	p->bus_desc.of_node = p->pdev->dev.of_node;
+	p->bus_desc.attr_groups = bus_attr_groups;
+	p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL);
+
+	if (!p->bus_desc.provider_name)
+		return -ENOMEM;
+
+	p->bus = nvdimm_bus_register(NULL, &p->bus_desc);
+	if (!p->bus) {
+		dev_err(dev, "Error creating nvdimm bus %pOF\n", p->dn);
+		return -ENXIO;
+	}
+
+	dimm_flags = 0;
+	set_bit(NDD_ALIASING, &dimm_flags);
+
+	p->nvdimm = nvdimm_create(p->bus, p, papr_scm_dimm_groups,
+				dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL);
+	if (!p->nvdimm) {
+		dev_err(dev, "Error creating DIMM object for %pOF\n", p->dn);
+		goto err;
+	}
+
+	if (nvdimm_bus_check_dimm_count(p->bus, 1))
+		goto err;
+
+	/* now add the region */
+
+	memset(&mapping, 0, sizeof(mapping));
+	mapping.nvdimm = p->nvdimm;
+	mapping.start = 0;
+	mapping.size = p->blocks * p->block_size; // XXX: potential overflow?
+
+	memset(&ndr_desc, 0, sizeof(ndr_desc));
+	ndr_desc.attr_groups = region_attr_groups;
+	target_nid = dev_to_node(&p->pdev->dev);
+	online_nid = papr_scm_node(target_nid);
+	ndr_desc.numa_node = online_nid;
+	ndr_desc.target_node = target_nid;
+	ndr_desc.res = &p->res;
+	ndr_desc.of_node = p->dn;
+	ndr_desc.provider_data = p;
+	ndr_desc.mapping = &mapping;
+	ndr_desc.num_mappings = 1;
+	ndr_desc.nd_set = &p->nd_set;
+	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
+
+	if (p->is_volatile)
+		p->region = nvdimm_volatile_region_create(p->bus, &ndr_desc);
+	else
+		p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc);
+	if (!p->region) {
+		dev_err(dev, "Error registering region %pR from %pOF\n",
+				ndr_desc.res, p->dn);
+		goto err;
+	}
+	if (target_nid != online_nid)
+		dev_info(dev, "Region registered with target node %d and online node %d",
+			 target_nid, online_nid);
+
+	return 0;
+
+err:	nvdimm_bus_unregister(p->bus);
+	kfree(p->bus_desc.provider_name);
+	return -ENXIO;
+}
+
+static int papr_scm_probe(struct platform_device *pdev)
+{
+	struct device_node *dn = pdev->dev.of_node;
+	u32 drc_index, metadata_size;
+	u64 blocks, block_size;
+	struct papr_scm_priv *p;
+	const char *uuid_str;
+	u64 uuid[2];
+	int rc;
+
+	/* check we have all the required DT properties */
+	if (of_property_read_u32(dn, "ibm,my-drc-index", &drc_index)) {
+		dev_err(&pdev->dev, "%pOF: missing drc-index!\n", dn);
+		return -ENODEV;
+	}
+
+	if (of_property_read_u64(dn, "ibm,block-size", &block_size)) {
+		dev_err(&pdev->dev, "%pOF: missing block-size!\n", dn);
+		return -ENODEV;
+	}
+
+	if (of_property_read_u64(dn, "ibm,number-of-blocks", &blocks)) {
+		dev_err(&pdev->dev, "%pOF: missing number-of-blocks!\n", dn);
+		return -ENODEV;
+	}
+
+	if (of_property_read_string(dn, "ibm,unit-guid", &uuid_str)) {
+		dev_err(&pdev->dev, "%pOF: missing unit-guid!\n", dn);
+		return -ENODEV;
+	}
+
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	/* optional DT properties */
+	of_property_read_u32(dn, "ibm,metadata-size", &metadata_size);
+
+	p->dn = dn;
+	p->drc_index = drc_index;
+	p->block_size = block_size;
+	p->blocks = blocks;
+	p->is_volatile = !of_property_read_bool(dn, "ibm,cache-flush-required");
+
+	/* We just need to ensure that set cookies are unique across */
+	uuid_parse(uuid_str, (uuid_t *) uuid);
+	/*
+	 * cookie1 and cookie2 are not really little endian
+	 * we store a little endian representation of the
+	 * uuid str so that we can compare this with the label
+	 * area cookie irrespective of the endian config with which
+	 * the kernel is built.
+	 */
+	p->nd_set.cookie1 = cpu_to_le64(uuid[0]);
+	p->nd_set.cookie2 = cpu_to_le64(uuid[1]);
+
+	/* might be zero */
+	p->metadata_size = metadata_size;
+	p->pdev = pdev;
+
+	/* request the hypervisor to bind this region to somewhere in memory */
+	rc = drc_pmem_bind(p);
+
+	/* If phyp says drc memory still bound then force unbound and retry */
+	if (rc == H_OVERLAP)
+		rc = drc_pmem_query_n_bind(p);
+
+	if (rc != H_SUCCESS) {
+		dev_err(&p->pdev->dev, "bind err: %d\n", rc);
+		rc = -ENXIO;
+		goto err;
+	}
+
+	/* setup the resource for the newly bound range */
+	p->res.start = p->bound_addr;
+	p->res.end   = p->bound_addr + p->blocks * p->block_size - 1;
+	p->res.name  = pdev->name;
+	p->res.flags = IORESOURCE_MEM;
+
+	rc = papr_scm_nvdimm_init(p);
+	if (rc)
+		goto err2;
+
+	platform_set_drvdata(pdev, p);
+
+	return 0;
+
+err2:	drc_pmem_unbind(p);
+err:	kfree(p);
+	return rc;
+}
+
+static int papr_scm_remove(struct platform_device *pdev)
+{
+	struct papr_scm_priv *p = platform_get_drvdata(pdev);
+
+	nvdimm_bus_unregister(p->bus);
+	drc_pmem_unbind(p);
+	kfree(p);
+
+	return 0;
+}
+
+static const struct of_device_id papr_scm_match[] = {
+	{ .compatible = "ibm,pmemory" },
+	{ },
+};
+
+static struct platform_driver papr_scm_driver = {
+	.probe = papr_scm_probe,
+	.remove = papr_scm_remove,
+	.driver = {
+		.name = "papr_scm",
+		.owner = THIS_MODULE,
+		.of_match_table = papr_scm_match,
+	},
+};
+
+module_platform_driver(papr_scm_driver);
+MODULE_DEVICE_TABLE(of, papr_scm_match);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("IBM Corporation");
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index eab9663..7228309 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2001 Dave Engebretsen, IBM Corporation
  * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
  *
  * pSeries specific routines for PCI.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/init.h>
@@ -29,6 +16,7 @@
 #include <asm/pci-bridge.h>
 #include <asm/prom.h>
 #include <asm/ppc-pci.h>
+#include <asm/pci.h>
 #include "pseries.h"
 
 #if 0
@@ -237,14 +225,37 @@
 
 void __init pSeries_final_fixup(void)
 {
+	struct pci_controller *hose;
+
 	pSeries_request_regions();
 
-	eeh_addr_cache_build();
+	eeh_show_enabled();
 
 #ifdef CONFIG_PCI_IOV
 	ppc_md.pcibios_sriov_enable = pseries_pcibios_sriov_enable;
 	ppc_md.pcibios_sriov_disable = pseries_pcibios_sriov_disable;
 #endif
+	list_for_each_entry(hose, &hose_list, list_node) {
+		struct device_node *dn = hose->dn, *nvdn;
+
+		while (1) {
+			dn = of_find_all_nodes(dn);
+			if (!dn)
+				break;
+			nvdn = of_parse_phandle(dn, "ibm,nvlink", 0);
+			if (!nvdn)
+				continue;
+			if (!of_device_is_compatible(nvdn, "ibm,npu-link"))
+				continue;
+			if (!of_device_is_compatible(nvdn->parent,
+						"ibm,power9-npu"))
+				continue;
+#ifdef CONFIG_PPC_POWERNV
+			WARN_ON_ONCE(pnv_npu2_init(hose));
+#endif
+			break;
+		}
+	}
 }
 
 /*
diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c
new file mode 100644
index 0000000..f860a89
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/pmem.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Handles hot and cold plug of persistent memory regions on pseries.
+ */
+
+#define pr_fmt(fmt)     "pseries-pmem: " fmt
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/sched.h>	/* for idle_task_exit */
+#include <linux/sched/hotplug.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/slab.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/firmware.h>
+#include <asm/machdep.h>
+#include <asm/vdso_datapage.h>
+#include <asm/plpar_wrappers.h>
+#include <asm/topology.h>
+
+#include "pseries.h"
+#include "offline_states.h"
+
+static struct device_node *pmem_node;
+
+static ssize_t pmem_drc_add_node(u32 drc_index)
+{
+	struct device_node *dn;
+	int rc;
+
+	pr_debug("Attempting to add pmem node, drc index: %x\n", drc_index);
+
+	rc = dlpar_acquire_drc(drc_index);
+	if (rc) {
+		pr_err("Failed to acquire DRC, rc: %d, drc index: %x\n",
+			rc, drc_index);
+		return -EINVAL;
+	}
+
+	dn = dlpar_configure_connector(cpu_to_be32(drc_index), pmem_node);
+	if (!dn) {
+		pr_err("configure-connector failed for drc %x\n", drc_index);
+		dlpar_release_drc(drc_index);
+		return -EINVAL;
+	}
+
+	/* NB: The of reconfig notifier creates platform device from the node */
+	rc = dlpar_attach_node(dn, pmem_node);
+	if (rc) {
+		pr_err("Failed to attach node %pOF, rc: %d, drc index: %x\n",
+			dn, rc, drc_index);
+
+		if (dlpar_release_drc(drc_index))
+			dlpar_free_cc_nodes(dn);
+
+		return rc;
+	}
+
+	pr_info("Successfully added %pOF, drc index: %x\n", dn, drc_index);
+
+	return 0;
+}
+
+static ssize_t pmem_drc_remove_node(u32 drc_index)
+{
+	struct device_node *dn;
+	uint32_t index;
+	int rc;
+
+	for_each_child_of_node(pmem_node, dn) {
+		if (of_property_read_u32(dn, "ibm,my-drc-index", &index))
+			continue;
+		if (index == drc_index)
+			break;
+	}
+
+	if (!dn) {
+		pr_err("Attempting to remove unused DRC index %x\n", drc_index);
+		return -ENODEV;
+	}
+
+	pr_debug("Attempting to remove %pOF, drc index: %x\n", dn, drc_index);
+
+	/* * NB: tears down the ibm,pmemory device as a side-effect */
+	rc = dlpar_detach_node(dn);
+	if (rc)
+		return rc;
+
+	rc = dlpar_release_drc(drc_index);
+	if (rc) {
+		pr_err("Failed to release drc (%x) for CPU %pOFn, rc: %d\n",
+			drc_index, dn, rc);
+		dlpar_attach_node(dn, pmem_node);
+		return rc;
+	}
+
+	pr_info("Successfully removed PMEM with drc index: %x\n", drc_index);
+
+	return 0;
+}
+
+int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog)
+{
+	u32 drc_index;
+	int rc;
+
+	/* slim chance, but we might get a hotplug event while booting */
+	if (!pmem_node)
+		pmem_node = of_find_node_by_type(NULL, "ibm,persistent-memory");
+	if (!pmem_node) {
+		pr_err("Hotplug event for a pmem device, but none exists\n");
+		return -ENODEV;
+	}
+
+	if (hp_elog->id_type != PSERIES_HP_ELOG_ID_DRC_INDEX) {
+		pr_err("Unsupported hotplug event type %d\n",
+				hp_elog->id_type);
+		return -EINVAL;
+	}
+
+	drc_index = hp_elog->_drc_u.drc_index;
+
+	lock_device_hotplug();
+
+	if (hp_elog->action == PSERIES_HP_ELOG_ACTION_ADD) {
+		rc = pmem_drc_add_node(drc_index);
+	} else if (hp_elog->action == PSERIES_HP_ELOG_ACTION_REMOVE) {
+		rc = pmem_drc_remove_node(drc_index);
+	} else {
+		pr_err("Unsupported hotplug action (%d)\n", hp_elog->action);
+		rc = -EINVAL;
+	}
+
+	unlock_device_hotplug();
+	return rc;
+}
+
+const struct of_device_id drc_pmem_match[] = {
+	{ .type = "ibm,persistent-memory", },
+	{}
+};
+
+static int pseries_pmem_init(void)
+{
+	pmem_node = of_find_node_by_type(NULL, "ibm,persistent-memory");
+	if (!pmem_node)
+		return 0;
+
+	/*
+	 * The generic OF bus probe/populate handles creating platform devices
+	 * from the child (ibm,pmemory) nodes. The generic code registers an of
+	 * reconfig notifier to handle the hot-add/remove cases too.
+	 */
+	of_platform_bus_probe(pmem_node, drc_pmem_match, NULL);
+
+	return 0;
+}
+machine_arch_initcall(pseries, pseries_pmem_init);
diff --git a/arch/powerpc/platforms/pseries/power.c b/arch/powerpc/platforms/pseries/power.c
index a4a0b57..ee343ec 100644
--- a/arch/powerpc/platforms/pseries/power.c
+++ b/arch/powerpc/platforms/pseries/power.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Interface for power-management for ppc64 compliant platform
  *
@@ -6,19 +7,6 @@
  *  Feb 2007
  *
  *  Copyright (C) 2007 IBM 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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kobject.h>
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 60db2ee..13fa370 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2006 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #ifndef _PSERIES_PSERIES_H
@@ -24,6 +20,7 @@
 
 extern int pSeries_system_reset_exception(struct pt_regs *regs);
 extern int pSeries_machine_check_exception(struct pt_regs *regs);
+extern long pseries_machine_check_realmode(struct pt_regs *regs);
 
 #ifdef CONFIG_SMP
 extern void smp_init_pseries(void);
@@ -59,15 +56,21 @@
 extern int dlpar_acquire_drc(u32 drc_index);
 extern int dlpar_release_drc(u32 drc_index);
 
-void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog,
-			 struct completion *hotplug_done, int *rc);
+void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog);
+int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_errlog);
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 int dlpar_memory(struct pseries_hp_errorlog *hp_elog);
+int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog);
 #else
 static inline int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
 {
 	return -EOPNOTSUPP;
 }
+static inline int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -109,5 +112,6 @@
 int dlpar_workqueue_init(void);
 
 void pseries_setup_rfi_flush(void);
+void pseries_lpar_read_hblkrm_characteristics(void);
 
 #endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c
index 6ed2212..a96874f 100644
--- a/arch/powerpc/platforms/pseries/pseries_energy.c
+++ b/arch/powerpc/platforms/pseries/pseries_energy.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * POWER platform energy management driver
  * Copyright (C) 2010 IBM Corporation
  *
- * 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 pseries platform device driver provides access to
  * platform energy management capabilities.
  */
@@ -77,18 +74,27 @@
 
 		ret = drc.drc_index_start + (thread_index * drc.sequential_inc);
 	} else {
-		const __be32 *indexes;
-
-		indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
-		if (indexes == NULL)
-			goto err_of_node_put;
+		u32 nr_drc_indexes, thread_drc_index;
 
 		/*
-		 * The first element indexes[0] is the number of drc_indexes
-		 * returned in the list.  Hence thread_index+1 will get the
-		 * drc_index corresponding to core number thread_index.
+		 * The first element of ibm,drc-indexes array is the
+		 * number of drc_indexes returned in the list.  Hence
+		 * thread_index+1 will get the drc_index corresponding
+		 * to core number thread_index.
 		 */
-		ret = indexes[thread_index + 1];
+		rc = of_property_read_u32_index(dn, "ibm,drc-indexes",
+						0, &nr_drc_indexes);
+		if (rc)
+			goto err_of_node_put;
+
+		WARN_ON_ONCE(thread_index > nr_drc_indexes);
+		rc = of_property_read_u32_index(dn, "ibm,drc-indexes",
+						thread_index + 1,
+						&thread_drc_index);
+		if (rc)
+			goto err_of_node_put;
+
+		ret = thread_drc_index;
 	}
 
 	rc = 0;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 851ce32..3acdcc3 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -1,19 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2001 Dave Engebretsen IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/sched.h>
@@ -27,6 +14,7 @@
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include <asm/firmware.h>
+#include <asm/mce.h>
 
 #include "pseries.h"
 
@@ -50,6 +38,84 @@
 static irqreturn_t ras_epow_interrupt(int irq, void *dev_id);
 static irqreturn_t ras_error_interrupt(int irq, void *dev_id);
 
+/* RTAS pseries MCE errorlog section. */
+struct pseries_mc_errorlog {
+	__be32	fru_id;
+	__be32	proc_id;
+	u8	error_type;
+	/*
+	 * sub_err_type (1 byte). Bit fields depends on error_type
+	 *
+	 *   MSB0
+	 *   |
+	 *   V
+	 *   01234567
+	 *   XXXXXXXX
+	 *
+	 * For error_type == MC_ERROR_TYPE_UE
+	 *   XXXXXXXX
+	 *   X		1: Permanent or Transient UE.
+	 *    X		1: Effective address provided.
+	 *     X	1: Logical address provided.
+	 *      XX	2: Reserved.
+	 *        XXX	3: Type of UE error.
+	 *
+	 * For error_type != MC_ERROR_TYPE_UE
+	 *   XXXXXXXX
+	 *   X		1: Effective address provided.
+	 *    XXXXX	5: Reserved.
+	 *         XX	2: Type of SLB/ERAT/TLB error.
+	 */
+	u8	sub_err_type;
+	u8	reserved_1[6];
+	__be64	effective_address;
+	__be64	logical_address;
+} __packed;
+
+/* RTAS pseries MCE error types */
+#define MC_ERROR_TYPE_UE		0x00
+#define MC_ERROR_TYPE_SLB		0x01
+#define MC_ERROR_TYPE_ERAT		0x02
+#define MC_ERROR_TYPE_UNKNOWN		0x03
+#define MC_ERROR_TYPE_TLB		0x04
+#define MC_ERROR_TYPE_D_CACHE		0x05
+#define MC_ERROR_TYPE_I_CACHE		0x07
+
+/* RTAS pseries MCE error sub types */
+#define MC_ERROR_UE_INDETERMINATE		0
+#define MC_ERROR_UE_IFETCH			1
+#define MC_ERROR_UE_PAGE_TABLE_WALK_IFETCH	2
+#define MC_ERROR_UE_LOAD_STORE			3
+#define MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE	4
+
+#define UE_EFFECTIVE_ADDR_PROVIDED		0x40
+#define UE_LOGICAL_ADDR_PROVIDED		0x20
+
+#define MC_ERROR_SLB_PARITY		0
+#define MC_ERROR_SLB_MULTIHIT		1
+#define MC_ERROR_SLB_INDETERMINATE	2
+
+#define MC_ERROR_ERAT_PARITY		1
+#define MC_ERROR_ERAT_MULTIHIT		2
+#define MC_ERROR_ERAT_INDETERMINATE	3
+
+#define MC_ERROR_TLB_PARITY		1
+#define MC_ERROR_TLB_MULTIHIT		2
+#define MC_ERROR_TLB_INDETERMINATE	3
+
+static inline u8 rtas_mc_error_sub_type(const struct pseries_mc_errorlog *mlog)
+{
+	switch (mlog->error_type) {
+	case	MC_ERROR_TYPE_UE:
+		return (mlog->sub_err_type & 0x07);
+	case	MC_ERROR_TYPE_SLB:
+	case	MC_ERROR_TYPE_ERAT:
+	case	MC_ERROR_TYPE_TLB:
+		return (mlog->sub_err_type & 0x03);
+	default:
+		return 0;
+	}
+}
 
 /*
  * Enable the hotplug interrupt late because processing them may touch other
@@ -237,8 +303,9 @@
 	 * hotplug events on the ras_log_buf to be handled by rtas_errd.
 	 */
 	if (hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_MEM ||
-	    hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_CPU)
-		queue_hotplug_event(hp_elog, NULL, NULL);
+	    hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_CPU ||
+	    hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_PMEM)
+		queue_hotplug_event(hp_elog);
 	else
 		log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, 0);
 
@@ -427,6 +494,201 @@
 	return 0; /* need to perform reset */
 }
 
+
+static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp)
+{
+	struct mce_error_info mce_err = { 0 };
+	unsigned long eaddr = 0, paddr = 0;
+	struct pseries_errorlog *pseries_log;
+	struct pseries_mc_errorlog *mce_log;
+	int disposition = rtas_error_disposition(errp);
+	int initiator = rtas_error_initiator(errp);
+	int severity = rtas_error_severity(errp);
+	u8 error_type, err_sub_type;
+
+	if (initiator == RTAS_INITIATOR_UNKNOWN)
+		mce_err.initiator = MCE_INITIATOR_UNKNOWN;
+	else if (initiator == RTAS_INITIATOR_CPU)
+		mce_err.initiator = MCE_INITIATOR_CPU;
+	else if (initiator == RTAS_INITIATOR_PCI)
+		mce_err.initiator = MCE_INITIATOR_PCI;
+	else if (initiator == RTAS_INITIATOR_ISA)
+		mce_err.initiator = MCE_INITIATOR_ISA;
+	else if (initiator == RTAS_INITIATOR_MEMORY)
+		mce_err.initiator = MCE_INITIATOR_MEMORY;
+	else if (initiator == RTAS_INITIATOR_POWERMGM)
+		mce_err.initiator = MCE_INITIATOR_POWERMGM;
+	else
+		mce_err.initiator = MCE_INITIATOR_UNKNOWN;
+
+	if (severity == RTAS_SEVERITY_NO_ERROR)
+		mce_err.severity = MCE_SEV_NO_ERROR;
+	else if (severity == RTAS_SEVERITY_EVENT)
+		mce_err.severity = MCE_SEV_WARNING;
+	else if (severity == RTAS_SEVERITY_WARNING)
+		mce_err.severity = MCE_SEV_WARNING;
+	else if (severity == RTAS_SEVERITY_ERROR_SYNC)
+		mce_err.severity = MCE_SEV_SEVERE;
+	else if (severity == RTAS_SEVERITY_ERROR)
+		mce_err.severity = MCE_SEV_SEVERE;
+	else if (severity == RTAS_SEVERITY_FATAL)
+		mce_err.severity = MCE_SEV_FATAL;
+	else
+		mce_err.severity = MCE_SEV_FATAL;
+
+	if (severity <= RTAS_SEVERITY_ERROR_SYNC)
+		mce_err.sync_error = true;
+	else
+		mce_err.sync_error = false;
+
+	mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN;
+	mce_err.error_class = MCE_ECLASS_UNKNOWN;
+
+	if (!rtas_error_extended(errp))
+		goto out;
+
+	pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
+	if (pseries_log == NULL)
+		goto out;
+
+	mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
+	error_type = mce_log->error_type;
+	err_sub_type = rtas_mc_error_sub_type(mce_log);
+
+	switch (mce_log->error_type) {
+	case MC_ERROR_TYPE_UE:
+		mce_err.error_type = MCE_ERROR_TYPE_UE;
+		switch (err_sub_type) {
+		case MC_ERROR_UE_IFETCH:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_IFETCH;
+			break;
+		case MC_ERROR_UE_PAGE_TABLE_WALK_IFETCH:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+			break;
+		case MC_ERROR_UE_LOAD_STORE:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+			break;
+		case MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+			break;
+		case MC_ERROR_UE_INDETERMINATE:
+		default:
+			mce_err.u.ue_error_type = MCE_UE_ERROR_INDETERMINATE;
+			break;
+		}
+		if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED)
+			eaddr = be64_to_cpu(mce_log->effective_address);
+
+		if (mce_log->sub_err_type & UE_LOGICAL_ADDR_PROVIDED) {
+			paddr = be64_to_cpu(mce_log->logical_address);
+		} else if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) {
+			unsigned long pfn;
+
+			pfn = addr_to_pfn(regs, eaddr);
+			if (pfn != ULONG_MAX)
+				paddr = pfn << PAGE_SHIFT;
+		}
+
+		break;
+	case MC_ERROR_TYPE_SLB:
+		mce_err.error_type = MCE_ERROR_TYPE_SLB;
+		switch (err_sub_type) {
+		case MC_ERROR_SLB_PARITY:
+			mce_err.u.slb_error_type = MCE_SLB_ERROR_PARITY;
+			break;
+		case MC_ERROR_SLB_MULTIHIT:
+			mce_err.u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+			break;
+		case MC_ERROR_SLB_INDETERMINATE:
+		default:
+			mce_err.u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+			break;
+		}
+		if (mce_log->sub_err_type & 0x80)
+			eaddr = be64_to_cpu(mce_log->effective_address);
+		break;
+	case MC_ERROR_TYPE_ERAT:
+		mce_err.error_type = MCE_ERROR_TYPE_ERAT;
+		switch (err_sub_type) {
+		case MC_ERROR_ERAT_PARITY:
+			mce_err.u.erat_error_type = MCE_ERAT_ERROR_PARITY;
+			break;
+		case MC_ERROR_ERAT_MULTIHIT:
+			mce_err.u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+			break;
+		case MC_ERROR_ERAT_INDETERMINATE:
+		default:
+			mce_err.u.erat_error_type = MCE_ERAT_ERROR_INDETERMINATE;
+			break;
+		}
+		if (mce_log->sub_err_type & 0x80)
+			eaddr = be64_to_cpu(mce_log->effective_address);
+		break;
+	case MC_ERROR_TYPE_TLB:
+		mce_err.error_type = MCE_ERROR_TYPE_TLB;
+		switch (err_sub_type) {
+		case MC_ERROR_TLB_PARITY:
+			mce_err.u.tlb_error_type = MCE_TLB_ERROR_PARITY;
+			break;
+		case MC_ERROR_TLB_MULTIHIT:
+			mce_err.u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+			break;
+		case MC_ERROR_TLB_INDETERMINATE:
+		default:
+			mce_err.u.tlb_error_type = MCE_TLB_ERROR_INDETERMINATE;
+			break;
+		}
+		if (mce_log->sub_err_type & 0x80)
+			eaddr = be64_to_cpu(mce_log->effective_address);
+		break;
+	case MC_ERROR_TYPE_D_CACHE:
+		mce_err.error_type = MCE_ERROR_TYPE_DCACHE;
+		break;
+	case MC_ERROR_TYPE_I_CACHE:
+		mce_err.error_type = MCE_ERROR_TYPE_DCACHE;
+		break;
+	case MC_ERROR_TYPE_UNKNOWN:
+	default:
+		mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN;
+		break;
+	}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (disposition == RTAS_DISP_NOT_RECOVERED) {
+		switch (error_type) {
+		case	MC_ERROR_TYPE_SLB:
+		case	MC_ERROR_TYPE_ERAT:
+			/*
+			 * Store the old slb content in paca before flushing.
+			 * Print this when we go to virtual mode.
+			 * There are chances that we may hit MCE again if there
+			 * is a parity error on the SLB entry we trying to read
+			 * for saving. Hence limit the slb saving to single
+			 * level of recursion.
+			 */
+			if (local_paca->in_mce == 1)
+				slb_save_contents(local_paca->mce_faulty_slbs);
+			flush_and_reload_slb();
+			disposition = RTAS_DISP_FULLY_RECOVERED;
+			break;
+		default:
+			break;
+		}
+	} else if (disposition == RTAS_DISP_LIMITED_RECOVERY) {
+		/* Platform corrected itself but could be degraded */
+		printk(KERN_ERR "MCE: limited recovery, system may "
+		       "be degraded\n");
+		disposition = RTAS_DISP_FULLY_RECOVERED;
+	}
+#endif
+
+out:
+	save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED,
+			&mce_err, regs->nip, eaddr, paddr);
+
+	return disposition;
+}
+
 /*
  * Process MCE rtas errlog event.
  */
@@ -447,43 +709,50 @@
  * Return 1 if corrected (or delivered a signal).
  * Return 0 if there is nothing we can do.
  */
-static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
+static int recover_mce(struct pt_regs *regs, struct machine_check_event *evt)
 {
 	int recovered = 0;
-	int disposition = rtas_error_disposition(err);
 
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */
+		pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
 		recovered = 0;
-
-	} else if (disposition == RTAS_DISP_FULLY_RECOVERED) {
+	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
 		/* Platform corrected itself */
 		recovered = 1;
-
-	} else if (disposition == RTAS_DISP_LIMITED_RECOVERY) {
-		/* Platform corrected itself but could be degraded */
-		printk(KERN_ERR "MCE: limited recovery, system may "
-		       "be degraded\n");
-		recovered = 1;
-
-	} else if (user_mode(regs) && !is_global_init(current) &&
-		   rtas_error_severity(err) == RTAS_SEVERITY_ERROR_SYNC) {
-
-		/*
-		 * If we received a synchronous error when in userspace
-		 * kill the task. Firmware may report details of the fail
-		 * asynchronously, so we can't rely on the target and type
-		 * fields being valid here.
-		 */
-		printk(KERN_ERR "MCE: uncorrectable error, killing task "
-		       "%s:%d\n", current->comm, current->pid);
-
-		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
-		recovered = 1;
+	} else if (evt->severity == MCE_SEV_FATAL) {
+		/* Fatal machine check */
+		pr_err("Machine check interrupt is fatal\n");
+		recovered = 0;
 	}
 
-	/* Queue irq work to log this rtas event later. */
-	irq_work_queue(&mce_errlog_process_work);
+	if (!recovered && evt->sync_error) {
+		/*
+		 * Try to kill processes if we get a synchronous machine check
+		 * (e.g., one caused by execution of this instruction). This
+		 * will devolve into a panic if we try to kill init or are in
+		 * an interrupt etc.
+		 *
+		 * TODO: Queue up this address for hwpoisioning later.
+		 * TODO: This is not quite right for d-side machine
+		 *       checks ->nip is not necessarily the important
+		 *       address.
+		 */
+		if ((user_mode(regs))) {
+			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+			recovered = 1;
+		} else if (die_will_crash()) {
+			/*
+			 * die() would kill the kernel, so better to go via
+			 * the platform reboot code that will log the
+			 * machine check.
+			 */
+			recovered = 0;
+		} else {
+			die("Machine check", regs, SIGBUS);
+			recovered = 1;
+		}
+	}
 
 	return recovered;
 }
@@ -500,12 +769,44 @@
  */
 int pSeries_machine_check_exception(struct pt_regs *regs)
 {
+	struct machine_check_event evt;
+
+	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+		return 0;
+
+	/* Print things out */
+	if (evt.version != MCE_V1) {
+		pr_err("Machine Check Exception, Unknown event version %d !\n",
+		       evt.version);
+		return 0;
+	}
+	machine_check_print_event_info(&evt, user_mode(regs), false);
+
+	if (recover_mce(regs, &evt))
+		return 1;
+
+	return 0;
+}
+
+long pseries_machine_check_realmode(struct pt_regs *regs)
+{
 	struct rtas_error_log *errp;
+	int disposition;
 
 	if (fwnmi_active) {
 		errp = fwnmi_get_errinfo(regs);
+		/*
+		 * Call to fwnmi_release_errinfo() in real mode causes kernel
+		 * to panic. Hence we will call it as soon as we go into
+		 * virtual mode.
+		 */
+		disposition = mce_handle_error(regs, errp);
 		fwnmi_release_errinfo();
-		if (errp && recover_mce(regs, errp))
+
+		/* Queue irq work to log this rtas event later. */
+		irq_work_queue(&mce_errlog_process_work);
+
+		if (disposition == RTAS_DISP_FULLY_RECOVERED)
 			return 1;
 	}
 
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 0e02081..8a9c4fb 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * pSeries_reconfig.c - support for dynamic reconfiguration (including PCI
  * Hotplug and Dynamic Logical Partitioning on RPA platforms).
  *
  * Copyright (C) 2005 Nathan Lynch
  * Copyright (C) 2005 IBM Corporation
- *
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License version
- *	2 as published by the Free Software Foundation.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c
index 31ca557..bbb9716 100644
--- a/arch/powerpc/platforms/pseries/rng.c
+++ b/arch/powerpc/platforms/pseries/rng.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2013, Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt)	"pseries-rng: " fmt
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c
new file mode 100644
index 0000000..70c3013
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.c
@@ -0,0 +1,550 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Firmware-Assisted Dump support on POWERVM platform.
+ *
+ * Copyright 2011, Mahesh Salgaonkar, IBM Corporation.
+ * Copyright 2019, Hari Bathini, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "rtas fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+#include <linux/delay.h>
+#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/fadump.h>
+#include <asm/fadump-internal.h>
+
+#include "rtas-fadump.h"
+
+static struct rtas_fadump_mem_struct fdm;
+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);
+}
+
+/*
+ * This function is called in the capture kernel to get configuration details
+ * setup in the first kernel and passed to the f/w.
+ */
+static void 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];
+
+	fadump_conf->boot_mem_top = fadump_conf->boot_memory_size;
+	fadump_conf->boot_mem_regs_cnt = 1;
+
+	/*
+	 * 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);
+
+	rtas_fadump_update_config(fadump_conf, fdm);
+}
+
+static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
+{
+	u64 addr = fadump_conf->reserve_dump_area_start;
+
+	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));
+
+	/*
+	 * Fields for disk dump option.
+	 * We are not using disk dump option, hence set these fields to 0.
+	 */
+	fdm.header.dd_block_size = 0;
+	fdm.header.dd_block_offset = 0;
+	fdm.header.dd_num_blocks = 0;
+	fdm.header.dd_offset_disk_path = 0;
+
+	/* set 0 to disable an automatic dump-reboot. */
+	fdm.header.max_time_auto = 0;
+
+	/* 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);
+	addr += fadump_conf->cpu_state_data_size;
+
+	/* 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);
+	addr += fadump_conf->hpte_region_size;
+
+	/* 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;
+
+	rtas_fadump_update_config(fadump_conf, &fdm);
+
+	return addr;
+}
+
+static u64 rtas_fadump_get_bootmem_min(void)
+{
+	return RTAS_FADUMP_MIN_BOOT_MEM;
+}
+
+static int rtas_fadump_register(struct fw_dump *fadump_conf)
+{
+	unsigned int wait_time;
+	int rc, err = -EIO;
+
+	/* 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));
+
+		wait_time = rtas_busy_delay_time(rc);
+		if (wait_time)
+			mdelay(wait_time);
+
+	} while (wait_time);
+
+	switch (rc) {
+	case 0:
+		pr_info("Registration is successful!\n");
+		fadump_conf->dump_registered = 1;
+		err = 0;
+		break;
+	case -1:
+		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())
+			pr_err("Can't have holes in reserved memory area.\n");
+
+		pr_err("Failed to register. Parameter Error(%d).\n", rc);
+		err = -EINVAL;
+		break;
+	case -9:
+		pr_err("Already registered!\n");
+		fadump_conf->dump_registered = 1;
+		err = -EEXIST;
+		break;
+	default:
+		pr_err("Failed to register. Unknown Error(%d).\n", rc);
+		break;
+	}
+
+	return err;
+}
+
+static int rtas_fadump_unregister(struct fw_dump *fadump_conf)
+{
+	unsigned int wait_time;
+	int rc;
+
+	/* TODO: Add upper time limit for the delay */
+	do {
+		rc =  rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1,
+				NULL, FADUMP_UNREGISTER, &fdm,
+				sizeof(struct rtas_fadump_mem_struct));
+
+		wait_time = rtas_busy_delay_time(rc);
+		if (wait_time)
+			mdelay(wait_time);
+	} while (wait_time);
+
+	if (rc) {
+		pr_err("Failed to un-register - unexpected error(%d).\n", rc);
+		return -EIO;
+	}
+
+	fadump_conf->dump_registered = 0;
+	return 0;
+}
+
+static int rtas_fadump_invalidate(struct fw_dump *fadump_conf)
+{
+	unsigned int wait_time;
+	int rc;
+
+	/* TODO: Add upper time limit for the delay */
+	do {
+		rc =  rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1,
+				NULL, FADUMP_INVALIDATE, fdm_active,
+				sizeof(struct rtas_fadump_mem_struct));
+
+		wait_time = rtas_busy_delay_time(rc);
+		if (wait_time)
+			mdelay(wait_time);
+	} while (wait_time);
+
+	if (rc) {
+		pr_err("Failed to invalidate - unexpected error (%d).\n", rc);
+		return -EIO;
+	}
+
+	fadump_conf->dump_active = 0;
+	fdm_active = NULL;
+	return 0;
+}
+
+#define RTAS_FADUMP_GPR_MASK		0xffffff0000000000
+static inline int rtas_fadump_gpr_index(u64 id)
+{
+	char str[3];
+	int i = -1;
+
+	if ((id & RTAS_FADUMP_GPR_MASK) == fadump_str_to_u64("GPR")) {
+		/* get the digits at the end */
+		id &= ~RTAS_FADUMP_GPR_MASK;
+		id >>= 24;
+		str[2] = '\0';
+		str[1] = id & 0xff;
+		str[0] = (id >> 8) & 0xff;
+		if (kstrtoint(str, 10, &i))
+			i = -EINVAL;
+		if (i > 31)
+			i = -1;
+	}
+	return i;
+}
+
+void rtas_fadump_set_regval(struct pt_regs *regs, u64 reg_id, u64 reg_val)
+{
+	int i;
+
+	i = rtas_fadump_gpr_index(reg_id);
+	if (i >= 0)
+		regs->gpr[i] = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("NIA"))
+		regs->nip = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("MSR"))
+		regs->msr = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("CTR"))
+		regs->ctr = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("LR"))
+		regs->link = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("XER"))
+		regs->xer = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("CR"))
+		regs->ccr = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("DAR"))
+		regs->dar = (unsigned long)reg_val;
+	else if (reg_id == fadump_str_to_u64("DSISR"))
+		regs->dsisr = (unsigned long)reg_val;
+}
+
+static struct rtas_fadump_reg_entry*
+rtas_fadump_read_regs(struct rtas_fadump_reg_entry *reg_entry,
+		      struct pt_regs *regs)
+{
+	memset(regs, 0, sizeof(struct pt_regs));
+
+	while (be64_to_cpu(reg_entry->reg_id) != fadump_str_to_u64("CPUEND")) {
+		rtas_fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id),
+				       be64_to_cpu(reg_entry->reg_value));
+		reg_entry++;
+	}
+	reg_entry++;
+	return reg_entry;
+}
+
+/*
+ * Read CPU state dump data and convert it into ELF notes.
+ * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
+ * used to access the data to allow for additional fields to be added without
+ * affecting compatibility. Each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
+ * 8 Byte ASCII identifier and 8 Byte register value. The register entry
+ * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
+ * of register value. For more details refer to PAPR document.
+ *
+ * Only for the crashing cpu we ignore the CPU dump data and get exact
+ * state from fadump crash info structure populated by first kernel at the
+ * time of crash.
+ */
+static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf)
+{
+	struct rtas_fadump_reg_save_area_header *reg_header;
+	struct fadump_crash_info_header *fdh = NULL;
+	struct rtas_fadump_reg_entry *reg_entry;
+	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);
+
+	reg_header = vaddr;
+	if (be64_to_cpu(reg_header->magic_number) !=
+	    fadump_str_to_u64("REGSAVE")) {
+		pr_err("Unable to read register save area.\n");
+		return -ENOENT;
+	}
+
+	pr_debug("--------CPU State Data------------\n");
+	pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number));
+	pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset));
+
+	vaddr += be32_to_cpu(reg_header->num_cpu_offset);
+	num_cpus = be32_to_cpu(*((__be32 *)(vaddr)));
+	pr_debug("NumCpus     : %u\n", num_cpus);
+	vaddr += sizeof(u32);
+	reg_entry = (struct rtas_fadump_reg_entry *)vaddr;
+
+	rc = fadump_setup_cpu_notes_buf(num_cpus);
+	if (rc != 0)
+		return rc;
+
+	note_buf = (u32 *)fadump_conf->cpu_notes_buf_vaddr;
+
+	if (fadump_conf->fadumphdr_addr)
+		fdh = __va(fadump_conf->fadumphdr_addr);
+
+	for (i = 0; i < num_cpus; i++) {
+		if (be64_to_cpu(reg_entry->reg_id) !=
+		    fadump_str_to_u64("CPUSTRT")) {
+			pr_err("Unable to read CPU state data\n");
+			rc = -ENOENT;
+			goto error_out;
+		}
+		/* Lower 4 bytes of reg_value contains logical cpu id */
+		cpu = (be64_to_cpu(reg_entry->reg_value) &
+		       RTAS_FADUMP_CPU_ID_MASK);
+		if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) {
+			RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
+			continue;
+		}
+		pr_debug("Reading register data for cpu %d...\n", cpu);
+		if (fdh && fdh->crashing_cpu == cpu) {
+			regs = fdh->regs;
+			note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
+			RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
+		} else {
+			reg_entry++;
+			reg_entry = rtas_fadump_read_regs(reg_entry, &regs);
+			note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
+		}
+	}
+	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));
+	}
+	return 0;
+
+error_out:
+	fadump_free_cpu_notes_buf();
+	return rc;
+
+}
+
+/*
+ * Validate and process the dump data stored by firmware before exporting
+ * it through '/proc/vmcore'.
+ */
+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;
+	}
+
+	/* 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;
+	}
+
+	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;
+}
+
+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)
+		fdm_ptr = fdm_active;
+	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));
+
+	/* Dump is active. Show reserved area start address. */
+	if (fdm_active) {
+		seq_printf(m, "\nMemory above %#016lx is reserved for saving crash dump\n",
+			   fadump_conf->reserve_dump_area_start);
+	}
+}
+
+static void rtas_fadump_trigger(struct fadump_crash_info_header *fdh,
+				const char *msg)
+{
+	/* Call ibm,os-term rtas call to trigger firmware assisted dump */
+	rtas_os_term((char *)msg);
+}
+
+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,
+	.fadump_register		= rtas_fadump_register,
+	.fadump_unregister		= rtas_fadump_unregister,
+	.fadump_invalidate		= rtas_fadump_invalidate,
+	.fadump_process			= rtas_fadump_process,
+	.fadump_region_show		= rtas_fadump_region_show,
+	.fadump_trigger			= rtas_fadump_trigger,
+};
+
+void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
+{
+	int i, size, num_sections;
+	const __be32 *sections;
+	const __be32 *token;
+
+	/*
+	 * Check if Firmware Assisted dump is supported. if yes, check
+	 * if dump has been initiated on last reboot.
+	 */
+	token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
+	if (!token)
+		return;
+
+	fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token);
+	fadump_conf->ops		= &rtas_fadump_ops;
+	fadump_conf->fadump_supported	= 1;
+
+	/* Firmware supports 64-bit value for size, align it to pagesize. */
+	fadump_conf->max_copy_size = _ALIGN_DOWN(U64_MAX, PAGE_SIZE);
+
+	/*
+	 * The 'ibm,kernel-dump' rtas node is present only if there is
+	 * dump data waiting for us.
+	 */
+	fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
+	if (fdm_active) {
+		pr_info("Firmware-assisted dump is active.\n");
+		fadump_conf->dump_active = 1;
+		rtas_fadump_get_config(fadump_conf, (void *)__pa(fdm_active));
+	}
+
+	/* Get the sizes required to store dump data for the firmware provided
+	 * dump sections.
+	 * For each dump section type supported, a 32bit cell which defines
+	 * the ID of a supported section followed by two 32 bit cells which
+	 * gives the size of the section in bytes.
+	 */
+	sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
+					&size);
+
+	if (!sections)
+		return;
+
+	num_sections = size / (3 * sizeof(u32));
+
+	for (i = 0; i < num_sections; i++, sections += 3) {
+		u32 type = (u32)of_read_number(sections, 1);
+
+		switch (type) {
+		case RTAS_FADUMP_CPU_STATE_DATA:
+			fadump_conf->cpu_state_data_size =
+					of_read_ulong(&sections[1], 2);
+			break;
+		case RTAS_FADUMP_HPTE_REGION:
+			fadump_conf->hpte_region_size =
+					of_read_ulong(&sections[1], 2);
+			break;
+		}
+	}
+}
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.h b/arch/powerpc/platforms/pseries/rtas-fadump.h
new file mode 100644
index 0000000..fd59bd7
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Firmware-Assisted Dump support on POWERVM platform.
+ *
+ * Copyright 2011, Mahesh Salgaonkar, IBM Corporation.
+ * Copyright 2019, Hari Bathini, IBM Corporation.
+ */
+
+#ifndef _PSERIES_RTAS_FADUMP_H
+#define _PSERIES_RTAS_FADUMP_H
+
+/*
+ * On some Power systems where RMO is 128MB, it still requires minimum of
+ * 256MB for kernel to boot successfully. When kdump infrastructure is
+ * configured to save vmcore over network, we run into OOM issue while
+ * loading modules related to network setup. Hence we need additional 64M
+ * of memory to avoid OOM issue.
+ */
+#define RTAS_FADUMP_MIN_BOOT_MEM	((0x1UL << 28) + (0x1UL << 26))
+
+/* Firmware provided dump sections */
+#define RTAS_FADUMP_CPU_STATE_DATA	0x0001
+#define RTAS_FADUMP_HPTE_REGION		0x0002
+#define RTAS_FADUMP_REAL_MODE_REGION	0x0011
+
+/* Dump request flag */
+#define RTAS_FADUMP_REQUEST_FLAG	0x00000001
+
+/* Dump status flag */
+#define RTAS_FADUMP_ERROR_FLAG		0x2000
+
+/* Kernel Dump section info */
+struct rtas_fadump_section {
+	__be32	request_flag;
+	__be16	source_data_type;
+	__be16	error_flags;
+	__be64	source_address;
+	__be64	source_len;
+	__be64	bytes_dumped;
+	__be64	destination_address;
+};
+
+/* ibm,configure-kernel-dump header. */
+struct rtas_fadump_section_header {
+	__be32	dump_format_version;
+	__be16	dump_num_sections;
+	__be16	dump_status_flag;
+	__be32	offset_first_dump_section;
+
+	/* Fields for disk dump option. */
+	__be32	dd_block_size;
+	__be64	dd_block_offset;
+	__be64	dd_num_blocks;
+	__be32	dd_offset_disk_path;
+
+	/* Maximum time allowed to prevent an automatic dump-reboot. */
+	__be32	max_time_auto;
+};
+
+/*
+ * 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.
+ */
+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;
+};
+
+/*
+ * The firmware-assisted dump format.
+ *
+ * The register save area is an area in the partition's memory used to preserve
+ * the register contents (CPU state data) for the active CPUs during a firmware
+ * assisted dump. The dump format contains register save area header followed
+ * by register entries. Each list of registers for a CPU starts with "CPUSTRT"
+ * and ends with "CPUEND".
+ */
+
+/* Register save area header. */
+struct rtas_fadump_reg_save_area_header {
+	__be64		magic_number;
+	__be32		version;
+	__be32		num_cpu_offset;
+};
+
+/* Register entry. */
+struct rtas_fadump_reg_entry {
+	__be64		reg_id;
+	__be64		reg_value;
+};
+
+/* Utility macros */
+#define RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry)				\
+({									\
+	while (be64_to_cpu(reg_entry->reg_id) !=			\
+	       fadump_str_to_u64("CPUEND"))				\
+		reg_entry++;						\
+	reg_entry++;							\
+})
+
+#define RTAS_FADUMP_CPU_ID_MASK			((1UL << 32) - 1)
+
+#endif /* _PSERIES_RTAS_FADUMP_H */
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
index 054ce7a..a000128 100644
--- a/arch/powerpc/platforms/pseries/scanlog.c
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  c 2001 PPC 64 Team, IBM Corp
  *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- *
  * scan-log-data driver for PPC64  Todd Inglett <tinglett@vnet.ibm.com>
  *
  * When ppc64 hardware fails the service processor dumps internal state
@@ -63,7 +59,7 @@
 		return -EINVAL;
 	}
 
-	if (!access_ok(VERIFY_WRITE, buf, count))
+	if (!access_ok(buf, count))
 		return -EFAULT;
 
 	for (;;) {
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index ba1791f..0a40201 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  64-bit pSeries and RS/6000 setup code.
  *
@@ -5,11 +6,6 @@
  *  Adapted from 'alpha' version by Gary Thomas
  *  Modified by Cort Dougan (cort@cs.nmt.edu)
  *  Modified by PPC64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /*
@@ -42,6 +38,7 @@
 #include <linux/of.h>
 #include <linux/of_pci.h>
 #include <linux/memblock.h>
+#include <linux/swiotlb.h>
 
 #include <asm/mmu.h>
 #include <asm/processor.h>
@@ -71,6 +68,8 @@
 #include <asm/isa-bridge.h>
 #include <asm/security_features.h>
 #include <asm/asm-const.h>
+#include <asm/swiotlb.h>
+#include <asm/svm.h>
 
 #include "pseries.h"
 #include "../../../../drivers/pci/pci.h"
@@ -107,6 +106,10 @@
 	u8 *mce_data_buf;
 	unsigned int i;
 	int nr_cpus = num_possible_cpus();
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct slb_entry *slb_ptr;
+	size_t size;
+#endif
 
 	int ibm_nmi_register = rtas_token("ibm,nmi-register");
 	if (ibm_nmi_register == RTAS_UNKNOWN_SERVICE)
@@ -126,12 +129,33 @@
 	 * It will be used in real mode mce handler, hence it needs to be
 	 * below RMA.
 	 */
-	mce_data_buf = __va(memblock_alloc_base(RTAS_ERROR_LOG_MAX * nr_cpus,
-					RTAS_ERROR_LOG_MAX, ppc64_rma_size));
+	mce_data_buf = memblock_alloc_try_nid_raw(RTAS_ERROR_LOG_MAX * nr_cpus,
+					RTAS_ERROR_LOG_MAX, MEMBLOCK_LOW_LIMIT,
+					ppc64_rma_size, NUMA_NO_NODE);
+	if (!mce_data_buf)
+		panic("Failed to allocate %d bytes below %pa for MCE buffer\n",
+		      RTAS_ERROR_LOG_MAX * nr_cpus, &ppc64_rma_size);
+
 	for_each_possible_cpu(i) {
 		paca_ptrs[i]->mce_data_buf = mce_data_buf +
 						(RTAS_ERROR_LOG_MAX * i);
 	}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (!radix_enabled()) {
+		/* Allocate per cpu area to save old slb contents during MCE */
+		size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus;
+		slb_ptr = memblock_alloc_try_nid_raw(size,
+				sizeof(struct slb_entry), MEMBLOCK_LOW_LIMIT,
+				ppc64_rma_size, NUMA_NO_NODE);
+		if (!slb_ptr)
+			panic("Failed to allocate %zu bytes below %pa for slb area\n",
+			      size, &ppc64_rma_size);
+
+		for_each_possible_cpu(i)
+			paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i);
+	}
+#endif
 }
 
 static void pseries_8259_cascade(struct irq_desc *desc)
@@ -177,7 +201,7 @@
 		of_node_put(old);
 		if (np == NULL)
 			break;
-		if (strcmp(np->name, "pci") != 0)
+		if (!of_node_name_eq(np, "pci"))
 			continue;
 		addrp = of_get_property(np, "8259-interrupt-acknowledge", NULL);
 		if (addrp == NULL)
@@ -254,46 +278,16 @@
  */
 static int alloc_dispatch_logs(void)
 {
-	int cpu, ret;
-	struct paca_struct *pp;
-	struct dtl_entry *dtl;
-
 	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
 		return 0;
 
 	if (!dtl_cache)
 		return 0;
 
-	for_each_possible_cpu(cpu) {
-		pp = paca_ptrs[cpu];
-		dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL);
-		if (!dtl) {
-			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
-				cpu);
-			pr_warn("Stolen time statistics will be unreliable\n");
-			break;
-		}
-
-		pp->dtl_ridx = 0;
-		pp->dispatch_log = dtl;
-		pp->dispatch_log_end = dtl + N_DISPATCH_LOG;
-		pp->dtl_curr = dtl;
-	}
+	alloc_dtl_buffers(0);
 
 	/* Register the DTL for the current (boot) cpu */
-	dtl = get_paca()->dispatch_log;
-	get_paca()->dtl_ridx = 0;
-	get_paca()->dtl_curr = dtl;
-	get_paca()->lppaca_ptr->dtl_idx = 0;
-
-	/* hypervisor reads buffer length from this field */
-	dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
-	ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
-	if (ret)
-		pr_err("WARNING: DTL registration of cpu %d (hw %d) failed "
-		       "with %d\n", smp_processor_id(),
-		       hard_smp_processor_id(), ret);
-	get_paca()->lppaca_ptr->dtl_enable_mask = 2;
+	register_dtl_buffer(smp_processor_id());
 
 	return 0;
 }
@@ -306,8 +300,10 @@
 
 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, NULL);
+						DISPATCH_LOG_BYTES, 0, ctor);
 	if (!dtl_cache) {
 		pr_warn("Failed to create dispatch trace log buffer cache\n");
 		pr_warn("Stolen time statistics will be unreliable\n");
@@ -325,6 +321,9 @@
 	 * low power mode by ceding processor to hypervisor
 	 */
 
+	if (!prep_irq_for_idle())
+		return;
+
 	/* Indicate to hypervisor that we are idle. */
 	get_lppaca()->idle = 1;
 
@@ -456,8 +455,8 @@
 	struct device_node *root = of_find_node_by_path("/");
 
 	for_each_child_of_node(root, node) {
-		if (node->type == NULL || (strcmp(node->type, "pci") != 0 &&
-					   strcmp(node->type, "pciex") != 0))
+		if (!of_node_is_type(node, "pci") &&
+		    !of_node_is_type(node, "pciex"))
 			continue;
 
 		phb = pcibios_alloc_controller(node);
@@ -745,6 +744,7 @@
 
 	pseries_setup_rfi_flush();
 	setup_stf_barrier();
+	pseries_lpar_read_hblkrm_characteristics();
 
 	/* By default, only probe PCI (can be overridden by rtas_pci) */
 	pci_add_flags(PCI_PROBE_ONLY);
@@ -774,6 +774,9 @@
 	}
 
 	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
+
+	if (swiotlb_force == SWIOTLB_FORCE)
+		ppc_swiotlb_enable = 1;
 }
 
 static void pseries_panic(char *str)
@@ -965,11 +968,7 @@
 
 static int __init pSeries_probe(void)
 {
-	const char *dtype = of_get_property(of_root, "device_type", NULL);
-
- 	if (dtype == NULL)
- 		return 0;
- 	if (strcmp(dtype, "chrp"))
+	if (!of_node_is_type(of_root, "chrp"))
 		return 0;
 
 	/* Cell blades firmware claims to be chrp while it's not. Until this
@@ -1017,6 +1016,7 @@
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= rtas_progress,
 	.system_reset_exception = pSeries_system_reset_exception,
+	.machine_check_early	= pseries_machine_check_realmode,
 	.machine_check_exception = pSeries_machine_check_exception,
 #ifdef CONFIG_KEXEC_CORE
 	.machine_kexec          = pSeries_machine_kexec,
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 3df4612..ad61e90 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * SMP support for pSeries machines.
  *
@@ -5,11 +6,6 @@
  * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
  *
  * Plus various changes from other IBM teams...
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 
@@ -45,6 +41,7 @@
 #include <asm/dbell.h>
 #include <asm/plpar_wrappers.h>
 #include <asm/code-patching.h>
+#include <asm/svm.h>
 
 #include "pseries.h"
 #include "offline_states.h"
@@ -225,7 +222,7 @@
 {
 	xics_smp_probe();
 
-	if (cpu_has_feature(CPU_FTR_DBELL))
+	if (cpu_has_feature(CPU_FTR_DBELL) && !is_secure_guest())
 		smp_ops->cause_ipi = smp_pseries_cause_ipi;
 	else
 		smp_ops->cause_ipi = icp_ops->cause_ipi;
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 52a021e..0a24a5a 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -1,19 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
   * Copyright (C) 2010 Brian King IBM 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; either version 2 of the License, or
-  * (at your option) any later version.
-  *
-  * This program is distributed in the hope that it will be useful,
-  * but WITHOUT ANY WARRANTY; without even the implied warranty of
-  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-  * GNU General Public License for more details.
-  *
-  * You should have received a copy of the GNU General Public License
-  * along with this program; if not, write to the Free Software
-  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
   */
 
 #include <linux/cpu.h>
diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c
new file mode 100644
index 0000000..40c0637
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/svm.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Secure VM platform
+ *
+ * Copyright 2018 IBM Corporation
+ * Author: Anshuman Khandual <khandual@linux.vnet.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <asm/machdep.h>
+#include <asm/svm.h>
+#include <asm/swiotlb.h>
+#include <asm/ultravisor.h>
+
+static int __init init_svm(void)
+{
+	if (!is_secure_guest())
+		return 0;
+
+	/* Don't release the SWIOTLB buffer. */
+	ppc_swiotlb_enable = 1;
+
+	/*
+	 * Since the guest memory is inaccessible to the host, devices always
+	 * need to use the SWIOTLB buffer for DMA even if dma_capable() says
+	 * otherwise.
+	 */
+	swiotlb_force = SWIOTLB_FORCE;
+
+	/* Share the SWIOTLB buffer with the host. */
+	swiotlb_update_mem_attributes();
+
+	return 0;
+}
+machine_early_initcall(pseries, init_svm);
+
+int set_memory_encrypted(unsigned long addr, int numpages)
+{
+	if (!PAGE_ALIGNED(addr))
+		return -EINVAL;
+
+	uv_unshare_page(PHYS_PFN(__pa(addr)), numpages);
+
+	return 0;
+}
+
+int set_memory_decrypted(unsigned long addr, int numpages)
+{
+	if (!PAGE_ALIGNED(addr))
+		return -EINVAL;
+
+	uv_share_page(PHYS_PFN(__pa(addr)), numpages);
+
+	return 0;
+}
+
+/* There's one dispatch log per CPU. */
+#define NR_DTL_PAGE (DISPATCH_LOG_BYTES * CONFIG_NR_CPUS / PAGE_SIZE)
+
+static struct page *dtl_page_store[NR_DTL_PAGE];
+static long dtl_nr_pages;
+
+static bool is_dtl_page_shared(struct page *page)
+{
+	long i;
+
+	for (i = 0; i < dtl_nr_pages; i++)
+		if (dtl_page_store[i] == page)
+			return true;
+
+	return false;
+}
+
+void dtl_cache_ctor(void *addr)
+{
+	unsigned long pfn = PHYS_PFN(__pa(addr));
+	struct page *page = pfn_to_page(pfn);
+
+	if (!is_dtl_page_shared(page)) {
+		dtl_page_store[dtl_nr_pages] = page;
+		dtl_nr_pages++;
+		WARN_ON(dtl_nr_pages >= NR_DTL_PAGE);
+		uv_share_page(pfn, 1);
+	}
+}
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 49e04ec..79e2287 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * IBM PowerPC Virtual I/O Infrastructure Support.
  *
@@ -7,11 +8,6 @@
  *     Hollis Blanchard <hollisb@us.ibm.com>
  *     Stephen Rothwell
  *     Robert Jennings <rcjenn@us.ibm.com>
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <linux/cpu.h>
@@ -492,7 +488,9 @@
 		return NULL;
 	}
 
-	ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs);
+	ret = iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
+				    dma_handle, dev->coherent_dma_mask, flag,
+				    dev_to_node(dev));
 	if (unlikely(ret == NULL)) {
 		vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 		atomic_inc(&viodev->cmo.allocs_failed);
@@ -507,8 +505,7 @@
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 
-	dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs);
-
+	iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
 	vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE));
 }
 
@@ -518,22 +515,22 @@
                                          unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
-	dma_addr_t ret = IOMMU_MAPPING_ERROR;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
+	dma_addr_t ret = DMA_MAPPING_ERROR;
 
-	tbl = get_iommu_table_base(dev);
-	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) {
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return ret;
-	}
-
-	ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs);
-	if (unlikely(dma_mapping_error(dev, ret))) {
-		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
-		atomic_inc(&viodev->cmo.allocs_failed);
-	}
-
+	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),
+			direction, attrs);
+	if (unlikely(ret == DMA_MAPPING_ERROR))
+		goto out_deallocate;
 	return ret;
+
+out_deallocate:
+	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
+out_fail:
+	atomic_inc(&viodev->cmo.allocs_failed);
+	return DMA_MAPPING_ERROR;
 }
 
 static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
@@ -542,11 +539,9 @@
 				     unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 
-	tbl = get_iommu_table_base(dev);
-	dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs);
-
+	iommu_unmap_page(tbl, dma_handle, size, direction, attrs);
 	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
 }
 
@@ -555,34 +550,32 @@
                                 unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	struct scatterlist *sgl;
 	int ret, count;
 	size_t alloc_size = 0;
 
-	tbl = get_iommu_table_base(dev);
 	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl));
 
-	if (vio_cmo_alloc(viodev, alloc_size)) {
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return 0;
-	}
-
-	ret = dma_iommu_ops.map_sg(dev, sglist, nelems, direction, attrs);
-
-	if (unlikely(!ret)) {
-		vio_cmo_dealloc(viodev, alloc_size);
-		atomic_inc(&viodev->cmo.allocs_failed);
-		return ret;
-	}
+	if (vio_cmo_alloc(viodev, alloc_size))
+		goto out_fail;
+	ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, dma_get_mask(dev),
+			direction, attrs);
+	if (unlikely(!ret))
+		goto out_deallocate;
 
 	for_each_sg(sglist, sgl, ret, count)
 		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 	if (alloc_size)
 		vio_cmo_dealloc(viodev, alloc_size);
-
 	return ret;
+
+out_deallocate:
+	vio_cmo_dealloc(viodev, alloc_size);
+out_fail:
+	atomic_inc(&viodev->cmo.allocs_failed);
+	return 0;
 }
 
 static void vio_dma_iommu_unmap_sg(struct device *dev,
@@ -591,41 +584,29 @@
 		unsigned long attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
-	struct iommu_table *tbl;
+	struct iommu_table *tbl = get_iommu_table_base(dev);
 	struct scatterlist *sgl;
 	size_t alloc_size = 0;
 	int count;
 
-	tbl = get_iommu_table_base(dev);
 	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 
-	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);
-
+	ppc_iommu_unmap_sg(tbl, sglist, nelems, direction, attrs);
 	vio_cmo_dealloc(viodev, alloc_size);
 }
 
-static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask)
-{
-        return dma_iommu_ops.dma_supported(dev, mask);
-}
-
-static u64 vio_dma_get_required_mask(struct device *dev)
-{
-        return dma_iommu_ops.get_required_mask(dev);
-}
-
 static const struct dma_map_ops vio_dma_mapping_ops = {
 	.alloc             = vio_dma_iommu_alloc_coherent,
 	.free              = vio_dma_iommu_free_coherent,
-	.mmap		   = dma_nommu_mmap_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,
-	.dma_supported     = vio_dma_iommu_dma_supported,
-	.get_required_mask = vio_dma_get_required_mask,
-	.mapping_error	   = dma_iommu_mapping_error,
+	.dma_supported     = dma_iommu_dma_supported,
+	.get_required_mask = dma_iommu_get_required_mask,
+	.mmap		   = dma_common_mmap,
+	.get_sgtable	   = dma_common_get_sgtable,
 };
 
 /**
@@ -1212,7 +1193,7 @@
 	else
 		tbl->it_ops = &iommu_table_pseries_ops;
 
-	return iommu_init_table(tbl, -1);
+	return iommu_init_table(tbl, -1, 0, 0);
 }
 
 /**
@@ -1349,7 +1330,6 @@
 	struct device_node *parent_node;
 	const __be32 *prop;
 	enum vio_dev_family family;
-	const char *of_node_name = of_node->name ? of_node->name : "<unknown>";
 
 	/*
 	 * Determine if this node is a under the /vdevice node or under the
@@ -1357,29 +1337,29 @@
 	 */
 	parent_node = of_get_parent(of_node);
 	if (parent_node) {
-		if (!strcmp(parent_node->type, "ibm,platform-facilities"))
+		if (of_node_is_type(parent_node, "ibm,platform-facilities"))
 			family = PFO;
-		else if (!strcmp(parent_node->type, "vdevice"))
+		else if (of_node_is_type(parent_node, "vdevice"))
 			family = VDEVICE;
 		else {
-			pr_warn("%s: parent(%pOF) of %s not recognized.\n",
+			pr_warn("%s: parent(%pOF) of %pOFn not recognized.\n",
 					__func__,
 					parent_node,
-					of_node_name);
+					of_node);
 			of_node_put(parent_node);
 			return NULL;
 		}
 		of_node_put(parent_node);
 	} else {
-		pr_warn("%s: could not determine the parent of node %s.\n",
-				__func__, of_node_name);
+		pr_warn("%s: could not determine the parent of node %pOFn.\n",
+				__func__, of_node);
 		return NULL;
 	}
 
 	if (family == PFO) {
 		if (of_get_property(of_node, "interrupt-controller", NULL)) {
-			pr_debug("%s: Skipping the interrupt controller %s.\n",
-					__func__, of_node_name);
+			pr_debug("%s: Skipping the interrupt controller %pOFn.\n",
+					__func__, of_node);
 			return NULL;
 		}
 	}
@@ -1396,18 +1376,17 @@
 	if (viodev->family == VDEVICE) {
 		unsigned int unit_address;
 
-		if (of_node->type != NULL)
-			viodev->type = of_node->type;
-		else {
-			pr_warn("%s: node %s is missing the 'device_type' "
-					"property.\n", __func__, of_node_name);
+		viodev->type = of_node_get_device_type(of_node);
+		if (!viodev->type) {
+			pr_warn("%s: node %pOFn is missing the 'device_type' "
+					"property.\n", __func__, of_node);
 			goto out;
 		}
 
 		prop = of_get_property(of_node, "reg", NULL);
 		if (prop == NULL) {
-			pr_warn("%s: node %s missing 'reg'\n",
-					__func__, of_node_name);
+			pr_warn("%s: node %pOFn missing 'reg'\n",
+					__func__, of_node);
 			goto out;
 		}
 		unit_address = of_read_number(prop, 1);
@@ -1422,8 +1401,8 @@
 		if (prop != NULL)
 			viodev->resource_id = of_read_number(prop, 1);
 
-		dev_set_name(&viodev->dev, "%s", of_node_name);
-		viodev->type = of_node_name;
+		dev_set_name(&viodev->dev, "%pOFn", of_node);
+		viodev->type = dev_name(&viodev->dev);
 		viodev->irq = 0;
 	}
 
@@ -1673,32 +1652,30 @@
 {
 	char kobj_name[20];
 	struct device_node *vnode_parent;
-	const char *dev_type;
 
 	vnode_parent = of_get_parent(vnode);
 	if (!vnode_parent)
 		return NULL;
 
-	dev_type = of_get_property(vnode_parent, "device_type", NULL);
-	of_node_put(vnode_parent);
-	if (!dev_type)
-		return NULL;
-
 	/* construct the kobject name from the device node */
-	if (!strcmp(dev_type, "vdevice")) {
+	if (of_node_is_type(vnode_parent, "vdevice")) {
 		const __be32 *prop;
 		
 		prop = of_get_property(vnode, "reg", NULL);
 		if (!prop)
-			return NULL;
+			goto out;
 		snprintf(kobj_name, sizeof(kobj_name), "%x",
 			 (uint32_t)of_read_number(prop, 1));
-	} else if (!strcmp(dev_type, "ibm,platform-facilities"))
-		snprintf(kobj_name, sizeof(kobj_name), "%s", vnode->name);
+	} else if (of_node_is_type(vnode_parent, "ibm,platform-facilities"))
+		snprintf(kobj_name, sizeof(kobj_name), "%pOFn", vnode);
 	else
-		return NULL;
+		goto out;
 
+	of_node_put(vnode_parent);
 	return vio_find_name(kobj_name);
+out:
+	of_node_put(vnode_parent);
+	return NULL;
 }
 EXPORT_SYMBOL(vio_find_node);
 
@@ -1720,3 +1697,10 @@
 }
 EXPORT_SYMBOL(vio_disable_interrupts);
 #endif /* CONFIG_PPC_PSERIES */
+
+static int __init vio_init(void)
+{
+	dma_debug_add_bus(&vio_bus_type);
+	return 0;
+}
+fs_initcall(vio_init);
diff --git a/arch/powerpc/mm/vphn.c b/arch/powerpc/platforms/pseries/vphn.c
similarity index 75%
rename from arch/powerpc/mm/vphn.c
rename to arch/powerpc/platforms/pseries/vphn.c
index f83044f..3f07bf6 100644
--- a/arch/powerpc/mm/vphn.c
+++ b/arch/powerpc/platforms/pseries/vphn.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <asm/byteorder.h>
-#include "vphn.h"
+#include <asm/lppaca.h>
 
 /*
  * The associativity domain numbers are returned from the hypervisor as a
@@ -22,7 +22,7 @@
  *
  * Convert to the sequence they would appear in the ibm,associativity property.
  */
-int vphn_unpack_associativity(const long *packed, __be32 *unpacked)
+static int vphn_unpack_associativity(const long *packed, __be32 *unpacked)
 {
 	__be64 be_packed[VPHN_REGISTER_COUNT];
 	int i, nr_assoc_doms = 0;
@@ -42,7 +42,8 @@
 		u16 new = be16_to_cpup(field++);
 
 		if (is_32bit) {
-			/* Let's concatenate the 16 bits of this field to the
+			/*
+			 * Let's concatenate the 16 bits of this field to the
 			 * 15 lower bits of the previous field
 			 */
 			unpacked[++nr_assoc_doms] =
@@ -56,7 +57,8 @@
 			unpacked[++nr_assoc_doms] =
 				cpu_to_be32(new & VPHN_FIELD_MASK);
 		} else {
-			/* Data is in the lower 15 bits of this field
+			/*
+			 * Data is in the lower 15 bits of this field
 			 * concatenated with the next 16 bit field
 			 */
 			last = new;
@@ -69,3 +71,19 @@
 
 	return nr_assoc_doms;
 }
+
+/* NOTE: This file is included by a selftest and built in userspace. */
+#ifdef __KERNEL__
+#include <asm/hvcall.h>
+
+long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity)
+{
+	long rc;
+	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+
+	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, cpu);
+	vphn_unpack_associativity(retbuf, associativity);
+
+	return rc;
+}
+#endif
diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile
index 4314ba5..7c6d8b1 100644
--- a/arch/powerpc/purgatory/Makefile
+++ b/arch/powerpc/purgatory/Makefile
@@ -1,4 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
+
+KASAN_SANITIZE := n
+
 targets += trampoline.o purgatory.ro kexec-purgatory.c
 
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined
diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S
index 1e11295..a5a83c3 100644
--- a/arch/powerpc/purgatory/trampoline.S
+++ b/arch/powerpc/purgatory/trampoline.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * kexec trampoline
  *
@@ -6,10 +7,6 @@
  * Copyright (C) 2004 - 2005, Milton D Miller II, IBM Corporation
  * Copyright (C) 2006, Mohan Kumar M, IBM Corporation
  * Copyright (C) 2013, Anton Blanchard, IBM 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).
  */
 
 #include <asm/asm-compat.h>
diff --git a/arch/powerpc/sysdev/6xx-suspend.S b/arch/powerpc/sysdev/6xx-suspend.S
index cf48e9c..e882524 100644
--- a/arch/powerpc/sysdev/6xx-suspend.S
+++ b/arch/powerpc/sysdev/6xx-suspend.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Enter and leave sleep state on chips with 6xx-style HID0
  * power management bits, which don't leave sleep state via reset.
@@ -5,10 +6,6 @@
  * Author: Scott Wood <scottwood@freescale.com>
  *
  * Copyright (c) 2006-2007 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
  */
 
 #include <asm/ppc_asm.h>
@@ -29,10 +26,9 @@
 	ori	r5, r5, ret_from_standby@l
 	mtlr	r5
 
-	CURRENT_THREAD_INFO(r5, r1)
-	lwz	r6, TI_LOCAL_FLAGS(r5)
+	lwz	r6, TI_LOCAL_FLAGS(r2)
 	ori	r6, r6, _TLF_SLEEPING
-	stw	r6, TI_LOCAL_FLAGS(r5)
+	stw	r6, TI_LOCAL_FLAGS(r2)
 
 	mfmsr	r5
 	ori	r5, r5, MSR_EE
diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig
index bcef2ac..9ebcc13 100644
--- a/arch/powerpc/sysdev/Kconfig
+++ b/arch/powerpc/sysdev/Kconfig
@@ -1,24 +1,21 @@
 # SPDX-License-Identifier: GPL-2.0
 # For a description of the syntax of this configuration file,
-# see Documentation/kbuild/kconfig-language.txt.
+# see Documentation/kbuild/kconfig-language.rst.
 #
 
 config PPC4xx_PCI_EXPRESS
 	bool
 	depends on PCI && 4xx
-	default n
 
 config PPC4xx_HSTA_MSI
 	bool
 	depends on PCI_MSI
 	depends on PCI && 4xx
-	default n
 
 config PPC4xx_MSI
 	bool
 	depends on PCI_MSI
 	depends on PCI && 4xx
-	default n
 
 config PPC_MSI_BITMAP
 	bool
@@ -31,17 +28,8 @@
 source "arch/powerpc/sysdev/xics/Kconfig"
 source "arch/powerpc/sysdev/xive/Kconfig"
 
-config PPC_SCOM
-	bool
-
-config SCOM_DEBUGFS
-	bool "Expose SCOM controllers via debugfs"
-	depends on PPC_SCOM && DEBUG_FS
-	default n
-
 config GE_FPGA
 	bool
-	default n
 
 config FSL_CORENET_RCPM
 	bool
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index f730539..603b3c6 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-$(CONFIG_PPC64)		:= $(NO_MINIMAL_TOC)
 
@@ -38,26 +37,20 @@
 obj-$(CONFIG_OF_RTC)		+= of_rtc.o
 
 obj-$(CONFIG_CPM)		+= cpm_common.o
-obj-$(CONFIG_CPM1)		+= cpm1.o
 obj-$(CONFIG_CPM2)		+= cpm2.o cpm2_pic.o cpm_gpio.o
 obj-$(CONFIG_8xx_GPIO)		+= cpm_gpio.o
 obj-$(CONFIG_QUICC_ENGINE)	+= cpm_common.o
 obj-$(CONFIG_PPC_DCR)		+= dcr.o
-obj-$(CONFIG_UCODE_PATCH)	+= micropatch.o
 
 obj-$(CONFIG_PPC_MPC512x)	+= mpc5xxx_clocks.o
 obj-$(CONFIG_PPC_MPC52xx)	+= mpc5xxx_clocks.o
 
 ifdef CONFIG_SUSPEND
-obj-$(CONFIG_6xx)		+= 6xx-suspend.o
+obj-$(CONFIG_PPC_BOOK3S_32)	+= 6xx-suspend.o
 endif
 
-obj-$(CONFIG_PPC_SCOM)		+= scom.o
-
 obj-$(CONFIG_PPC_EARLY_DEBUG_MEMCONS)	+= udbg_memcons.o
 
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
-
 obj-$(CONFIG_PPC_XICS)		+= xics/
 obj-$(CONFIG_PPC_XIVE)		+= xive/
 
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index b745081..71660ba 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Common CPM code
  *
@@ -11,10 +12,6 @@
  * Copyright (c) 2000 MontaVista Software, Inc (source@mvista.com)
  * 2006 (c) MontaVista Software, Inc.
  * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/sysdev/dart.h b/arch/powerpc/sysdev/dart.h
index ff202ed..7f5df03 100644
--- a/arch/powerpc/sysdev/dart.h
+++ b/arch/powerpc/sysdev/dart.h
@@ -1,19 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM 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; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #ifndef _POWERPC_SYSDEV_DART_H
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 5ca3e22..6b4a34b 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/sysdev/dart_iommu.c
  *
@@ -10,21 +11,6 @@
  * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation
  *
  * Dynamic DMA mapping support, Apple U3, U4 & IBM CPC925 "DART" iommu.
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
 #include <linux/init.h>
@@ -158,7 +144,7 @@
 	unsigned int tmp;
 
 	/* Perform a standard cache flush */
-	flush_inval_dcache_range(start, end);
+	flush_dcache_range(start, end);
 
 	/*
 	 * Perform the sequence described in the CPC925 manual to
@@ -251,8 +237,11 @@
 	 * 16MB (1 << 24) alignment. We allocate a full 16Mb chuck since we
 	 * will blow up an entire large page anyway in the kernel mapping.
 	 */
-	dart_tablebase = __va(memblock_alloc_base(1UL<<24,
-						  1UL<<24, 0x80000000L));
+	dart_tablebase = memblock_alloc_try_nid_raw(SZ_16M, SZ_16M,
+					MEMBLOCK_LOW_LIMIT, SZ_2G,
+					NUMA_NO_NODE);
+	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);
@@ -261,7 +250,10 @@
 	 * that to work around what looks like a problem with the HT bridge
 	 * prefetching into invalid pages and corrupting data
 	 */
-	tmp = memblock_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE);
+	tmp = memblock_phys_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE);
+	if (!tmp)
+		panic("DART: table allocation failed\n");
+
 	dart_emptyval = DARTMAP_VALID | ((tmp >> DART_PAGE_SHIFT) &
 					 DARTMAP_RPNMASK);
 
@@ -352,7 +344,7 @@
 	iommu_table_dart.it_index = 0;
 	iommu_table_dart.it_blocksize = 1;
 	iommu_table_dart.it_ops = &iommu_dart_ops;
-	iommu_init_table(&iommu_table_dart, -1);
+	iommu_init_table(&iommu_table_dart, -1, 0, 0);
 
 	/* Reserve the last page of the DART to avoid possible prefetch
 	 * past the DART mapped area
@@ -360,13 +352,6 @@
 	set_bit(iommu_table_dart.it_size - 1, iommu_table_dart.it_map);
 }
 
-static void pci_dma_dev_setup_dart(struct pci_dev *dev)
-{
-	if (dart_is_u4)
-		set_dma_offset(&dev->dev, DART_U4_BYPASS_BASE);
-	set_iommu_table_base(&dev->dev, &iommu_table_dart);
-}
-
 static void pci_dma_bus_setup_dart(struct pci_bus *bus)
 {
 	if (!iommu_table_dart_inited) {
@@ -390,27 +375,18 @@
 	return false;
 }
 
-static int dart_dma_set_mask(struct device *dev, u64 dma_mask)
+static void pci_dma_dev_setup_dart(struct pci_dev *dev)
 {
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
+	if (dart_is_u4 && dart_device_on_pcie(&dev->dev))
+		dev->dev.archdata.dma_offset = DART_U4_BYPASS_BASE;
+	set_iommu_table_base(&dev->dev, &iommu_table_dart);
+}
 
-	/* U4 supports a DART bypass, we use it for 64-bit capable
-	 * devices to improve performances. However, that only works
-	 * for devices connected to U4 own PCIe interface, not bridged
-	 * through hypertransport. We need the device to support at
-	 * least 40 bits of addresses.
-	 */
-	if (dart_device_on_pcie(dev) && dma_mask >= DMA_BIT_MASK(40)) {
-		dev_info(dev, "Using 64-bit DMA iommu bypass\n");
-		set_dma_ops(dev, &dma_nommu_ops);
-	} else {
-		dev_info(dev, "Using 32-bit DMA via iommu\n");
-		set_dma_ops(dev, &dma_iommu_ops);
-	}
-
-	*dev->dma_mask = dma_mask;
-	return 0;
+static bool iommu_bypass_supported_dart(struct pci_dev *dev, u64 mask)
+{
+	return dart_is_u4 &&
+		dart_device_on_pcie(&dev->dev) &&
+		mask >= DMA_BIT_MASK(40);
 }
 
 void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
@@ -428,26 +404,20 @@
 
 	/* Initialize the DART HW */
 	if (dart_init(dn) != 0)
-		goto bail;
+		return;
 
-	/* Setup bypass if supported */
-	if (dart_is_u4)
-		ppc_md.dma_set_mask = dart_dma_set_mask;
-
+	/*
+	 * U4 supports a DART bypass, we use it for 64-bit capable devices to
+	 * improve performance.  However, that only works for devices connected
+	 * to the U4 own PCIe interface, not bridged through hypertransport.
+	 * We need the device to support at least 40 bits of addresses.
+	 */
 	controller_ops->dma_dev_setup = pci_dma_dev_setup_dart;
 	controller_ops->dma_bus_setup = pci_dma_bus_setup_dart;
+	controller_ops->iommu_bypass_supported = iommu_bypass_supported_dart;
 
 	/* Setup pci_dma ops */
 	set_pci_dma_ops(&dma_iommu_ops);
-	return;
-
- bail:
-	/* If init failed, use direct iommu and null setup functions */
-	controller_ops->dma_dev_setup = NULL;
-	controller_ops->dma_bus_setup = NULL;
-
-	/* Setup pci_dma ops */
-	set_pci_dma_ops(&dma_nommu_ops);
 }
 
 #ifdef CONFIG_PM
diff --git a/arch/powerpc/sysdev/dcr-low.S b/arch/powerpc/sysdev/dcr-low.S
index e687bb2..efeeb1b 100644
--- a/arch/powerpc/sysdev/dcr-low.S
+++ b/arch/powerpc/sysdev/dcr-low.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * "Indirect" DCR access
  *
  * Copyright (c) 2004 Eugene Surovegin <ebs@ebshome.net>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under  the terms of  the GNU General Public License as published by the
- * Free Software Foundation;  either version 2 of the License, or (at your
- * option) any later version.
  */
 
 #include <asm/ppc_asm.h>
diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c
index d72eda5..22991e1 100644
--- a/arch/powerpc/sysdev/dcr.c
+++ b/arch/powerpc/sysdev/dcr.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
  *                    <benh@kernel.crashing.org>
- *
- *   This program is free software;  you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
- *   the GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program;  if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h b/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h
index 2aa97dd..ce37074 100644
--- a/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h
+++ b/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2009-2010, 2012 Freescale Semiconductor, Inc
  *
  * QorIQ based Cache Controller Memory Mapped Registers
  *
  * Author: Vivek Mahajan <vivek.mahajan@freescale.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __FSL_85XX_CACHE_CTLR_H__
diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
index 00ccf3e..f6c665d 100644
--- a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
+++ b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2009-2010 Freescale Semiconductor, Inc.
  *
@@ -7,20 +8,6 @@
  *
  * This file is derived from the original work done
  * by Sylvain Munaut for the Bestcomm SRAM allocator.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/kernel.h>
@@ -107,11 +94,11 @@
 		goto out_free;
 	}
 
-	cache_sram->base_virt = ioremap_prot(cache_sram->base_phys,
-				cache_sram->size, _PAGE_COHERENT | PAGE_KERNEL);
+	cache_sram->base_virt = ioremap_coherent(cache_sram->base_phys,
+						 cache_sram->size);
 	if (!cache_sram->base_virt) {
-		dev_err(&dev->dev, "%pOF: ioremap_prot failed\n",
-				dev->dev.of_node);
+		dev_err(&dev->dev, "%pOF: ioremap_coherent failed\n",
+			dev->dev.of_node);
 		ret = -ENOMEM;
 		goto out_release;
 	}
diff --git a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
index c27058e..2d0af0c 100644
--- a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
+++ b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2009-2010, 2012 Freescale Semiconductor, Inc.
  *
  * QorIQ (P1/P2) L2 controller init for Cache-SRAM instantiation
  *
  * Author: Vivek Mahajan <vivek.mahajan@freescale.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c
index d902306..8963eaf 100644
--- a/arch/powerpc/sysdev/fsl_gtm.c
+++ b/arch/powerpc/sysdev/fsl_gtm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Freescale General-purpose Timers Module
  *
@@ -6,11 +7,6 @@
  *               Jerry Huang <Chang-Ming.Huang@freescale.com>
  * Copyright (c) MontaVista Software, Inc. 2008.
  *               Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c
index 5340a48..1985e06 100644
--- a/arch/powerpc/sysdev/fsl_lbc.c
+++ b/arch/powerpc/sysdev/fsl_lbc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Freescale LBC and UPM routines.
  *
@@ -7,11 +8,6 @@
  * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
  * Author: Jack Lan <Jack.Lan@freescale.com>
  * Author: Roy Zang <tie-fei.zang@freescale.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/sysdev/fsl_mpic_err.c b/arch/powerpc/sysdev/fsl_mpic_err.c
index 2a98837..13583bb 100644
--- a/arch/powerpc/sysdev/fsl_mpic_err.c
+++ b/arch/powerpc/sysdev/fsl_mpic_err.c
@@ -1,13 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2012 Freescale Semiconductor, Inc.
  *
  * Author: Varun Sethi <varun.sethi@freescale.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2 of the
- * License.
- *
  */
 
 #include <linux/irq.h>
diff --git a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
index 94278e8..c2baa28 100644
--- a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
+++ b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPIC timer wakeup driver
  *
  * Copyright 2013 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index df95102..808e711 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2007-2011 Freescale Semiconductor, Inc.
  *
@@ -5,12 +6,6 @@
  *	   Jason Jin <Jason.jin@freescale.com>
  *
  * The hwirq alloc and free code reuse from sysdev/mpic_msi.c
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2 of the
- * License.
- *
  */
 #include <linux/irq.h>
 #include <linux/msi.h>
diff --git a/arch/powerpc/sysdev/fsl_msi.h b/arch/powerpc/sysdev/fsl_msi.h
index a67359d..e2a1bfc 100644
--- a/arch/powerpc/sysdev/fsl_msi.h
+++ b/arch/powerpc/sysdev/fsl_msi.h
@@ -1,14 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2007-2008 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Tony Li <tony.li@freescale.com>
  *	   Jason Jin <Jason.jin@freescale.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2 of the
- * License.
- *
  */
 #ifndef _POWERPC_SYSDEV_FSL_MSI_H
 #define _POWERPC_SYSDEV_FSL_MSI_H
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 918be81..ff0e2b1 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPC83xx/85xx/86xx PCI/PCIE support routing.
  *
@@ -11,11 +12,6 @@
  * MPC83xx PCI-Express support:
  * 	Tony Li <tony.li@freescale.com>
  * 	Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/pci.h>
@@ -40,6 +36,7 @@
 #include <asm/mpc85xx.h>
 #include <asm/disassemble.h>
 #include <asm/ppc-opcode.h>
+#include <asm/swiotlb.h>
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
 
@@ -114,33 +111,33 @@
 static u64 pci64_dma_offset;
 
 #ifdef CONFIG_SWIOTLB
+static void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+
+	pdev->dev.bus_dma_mask =
+		hose->dma_window_base_cur + hose->dma_window_size;
+}
+
 static void setup_swiotlb_ops(struct pci_controller *hose)
 {
-	if (ppc_swiotlb_enable) {
+	if (ppc_swiotlb_enable)
 		hose->controller_ops.dma_dev_setup = pci_dma_dev_setup_swiotlb;
-		set_pci_dma_ops(&powerpc_swiotlb_dma_ops);
-	}
 }
 #else
 static inline void setup_swiotlb_ops(struct pci_controller *hose) {}
 #endif
 
-static int fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask)
+static void fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask)
 {
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
 	/*
 	 * Fix up PCI devices that are able to DMA to the large inbound
 	 * mapping that allows addressing any RAM address from across PCI.
 	 */
 	if (dev_is_pci(dev) && dma_mask >= pci64_dma_offset * 2 - 1) {
-		set_dma_ops(dev, &dma_nommu_ops);
-		set_dma_offset(dev, pci64_dma_offset);
+		dev->bus_dma_mask = 0;
+		dev->archdata.dma_offset = pci64_dma_offset;
 	}
-
-	*dev->dma_mask = dma_mask;
-	return 0;
 }
 
 static int setup_one_atmu(struct ccsr_pci __iomem *pci,
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index 1515885..1d7a412 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -1,13 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * MPC85xx/86xx PCI Express structure define
  *
  * Copyright 2007,2011 Freescale Semiconductor, Inc
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 #ifdef __KERNEL__
diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c
index 232225e..76896de 100644
--- a/arch/powerpc/sysdev/fsl_pmc.c
+++ b/arch/powerpc/sysdev/fsl_pmc.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Suspend/resume support
  *
  * Copyright 2009  MontaVista Software, Inc.
  *
  * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/sysdev/fsl_rcpm.c b/arch/powerpc/sysdev/fsl_rcpm.c
index 9259a94..aacd0be 100644
--- a/arch/powerpc/sysdev/fsl_rcpm.c
+++ b/arch/powerpc/sysdev/fsl_rcpm.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * RCPM(Run Control/Power Management) support
  *
  * Copyright 2012-2015 Freescale Semiconductor Inc.
  *
  * Author: Chenhui Zhao <chenhui.zhao@freescale.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #define pr_fmt(fmt) "%s: " fmt, __func__
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 5011ffe..07c164f 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Freescale MPC85xx/MPC86xx RapidIO support
  *
@@ -15,11 +16,6 @@
  *
  * Copyright 2005 MontaVista Software, Inc.
  * Matt Porter <mporter@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/sysdev/fsl_rio.h b/arch/powerpc/sysdev/fsl_rio.h
index 12dd18f..c526b72 100644
--- a/arch/powerpc/sysdev/fsl_rio.h
+++ b/arch/powerpc/sysdev/fsl_rio.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Freescale MPC85xx/MPC86xx RapidIO support
  *
@@ -17,11 +18,6 @@
  *
  * Copyright 2005 MontaVista Software, Inc.
  * Matt Porter <mporter@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef __FSL_RIO_H
@@ -41,7 +37,7 @@
 #define DOORBELL_ROWAR_PCI	0x02000000 /* PCI window */
 #define DOORBELL_ROWAR_NREAD	0x00040000 /* NREAD */
 #define DOORBELL_ROWAR_MAINTRD	0x00070000  /* maintenance read */
-#define DOORBELL_ROWAR_RES	0x00002000 /* wrtpy: reserverd */
+#define DOORBELL_ROWAR_RES	0x00002000 /* wrtpy: reserved */
 #define DOORBELL_ROWAR_MAINTWD	0x00007000
 #define DOORBELL_ROWAR_SIZE	0x0000000b /* window size is 4k */
 
diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c
index 88b35a3..7a5e2e2 100644
--- a/arch/powerpc/sysdev/fsl_rmu.c
+++ b/arch/powerpc/sysdev/fsl_rmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Freescale MPC85xx/MPC86xx RapidIO RMU support
  *
@@ -17,11 +18,6 @@
  *
  * Copyright 2005 MontaVista Software, Inc.
  * Matt Porter <mporter@kernel.crashing.org>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/types.h>
@@ -757,14 +753,13 @@
 
 	/* Initialize outbound message descriptor ring */
 	rmu->msg_tx_ring.virt = dma_alloc_coherent(priv->dev,
-				rmu->msg_tx_ring.size * RIO_MSG_DESC_SIZE,
-				&rmu->msg_tx_ring.phys, GFP_KERNEL);
+						   rmu->msg_tx_ring.size * RIO_MSG_DESC_SIZE,
+						   &rmu->msg_tx_ring.phys,
+						   GFP_KERNEL);
 	if (!rmu->msg_tx_ring.virt) {
 		rc = -ENOMEM;
 		goto out_dma;
 	}
-	memset(rmu->msg_tx_ring.virt, 0,
-			rmu->msg_tx_ring.size * RIO_MSG_DESC_SIZE);
 	rmu->msg_tx_ring.tx_slot = 0;
 
 	/* Point dequeue/enqueue pointers at first entry in ring */
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index 1f614fb..90ad161 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * FSL SoC setup code
  *
@@ -5,11 +6,6 @@
  *
  * 2006 (c) MontaVista Software, Inc.
  * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
diff --git a/arch/powerpc/sysdev/ge/Makefile b/arch/powerpc/sysdev/ge/Makefile
index 8731ffc..a63fdb3 100644
--- a/arch/powerpc/sysdev/ge/Makefile
+++ b/arch/powerpc/sysdev/ge/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_GE_FPGA)		+= ge_pic.o
diff --git a/arch/powerpc/sysdev/grackle.c b/arch/powerpc/sysdev/grackle.c
index 08abe91..aaba0b8 100644
--- a/arch/powerpc/sysdev/grackle.c
+++ b/arch/powerpc/sysdev/grackle.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Functions for setting up and using a MPC106 northbridge
  * Extracted from arch/powerpc/platforms/powermac/pci.c.
  *
  * Copyright (C) 2003 Benjamin Herrenschmuidt (benh@kernel.crashing.org)
  * Copyright (C) 1997 Paul Mackerras (paulus@samba.org)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/pci.h>
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index cb9a8b7..c1d76c3 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * i8259 interrupt controller driver.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 #undef DEBUG
 
diff --git a/arch/powerpc/sysdev/indirect_pci.c b/arch/powerpc/sysdev/indirect_pci.c
index 692de9d..09b3661 100644
--- a/arch/powerpc/sysdev/indirect_pci.c
+++ b/arch/powerpc/sysdev/indirect_pci.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Support for indirect PCI bridges.
  *
  * Copyright (C) 1998 Gabriel Paubert.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index 535cf1f..7638a50 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * arch/powerpc/sysdev/ipic.c
  *
  * IPIC routines implementations.
  *
  * Copyright 2005 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -771,49 +767,6 @@
 	return ipic;
 }
 
-int ipic_set_priority(unsigned int virq, unsigned int priority)
-{
-	struct ipic *ipic = ipic_from_irq(virq);
-	unsigned int src = virq_to_hw(virq);
-	u32 temp;
-
-	if (priority > 7)
-		return -EINVAL;
-	if (src > 127)
-		return -EINVAL;
-	if (ipic_info[src].prio == 0)
-		return -EINVAL;
-
-	temp = ipic_read(ipic->regs, ipic_info[src].prio);
-
-	if (priority < 4) {
-		temp &= ~(0x7 << (20 + (3 - priority) * 3));
-		temp |= ipic_info[src].prio_mask << (20 + (3 - priority) * 3);
-	} else {
-		temp &= ~(0x7 << (4 + (7 - priority) * 3));
-		temp |= ipic_info[src].prio_mask << (4 + (7 - priority) * 3);
-	}
-
-	ipic_write(ipic->regs, ipic_info[src].prio, temp);
-
-	return 0;
-}
-
-void ipic_set_highest_priority(unsigned int virq)
-{
-	struct ipic *ipic = ipic_from_irq(virq);
-	unsigned int src = virq_to_hw(virq);
-	u32 temp;
-
-	temp = ipic_read(ipic->regs, IPIC_SICFR);
-
-	/* clear and set HPI */
-	temp &= 0x7f000000;
-	temp |= (src & 0x7f) << 24;
-
-	ipic_write(ipic->regs, IPIC_SICFR, temp);
-}
-
 void ipic_set_default_priority(void)
 {
 	ipic_write(primary_ipic->regs, IPIC_SIPRR_A, IPIC_PRIORITY_DEFAULT);
@@ -824,29 +777,9 @@
 	ipic_write(primary_ipic->regs, IPIC_SMPRR_B, IPIC_PRIORITY_DEFAULT);
 }
 
-void ipic_enable_mcp(enum ipic_mcp_irq mcp_irq)
-{
-	struct ipic *ipic = primary_ipic;
-	u32 temp;
-
-	temp = ipic_read(ipic->regs, IPIC_SERMR);
-	temp |= (1 << (31 - mcp_irq));
-	ipic_write(ipic->regs, IPIC_SERMR, temp);
-}
-
-void ipic_disable_mcp(enum ipic_mcp_irq mcp_irq)
-{
-	struct ipic *ipic = primary_ipic;
-	u32 temp;
-
-	temp = ipic_read(ipic->regs, IPIC_SERMR);
-	temp &= (1 << (31 - mcp_irq));
-	ipic_write(ipic->regs, IPIC_SERMR, temp);
-}
-
 u32 ipic_get_mcp_status(void)
 {
-	return ipic_read(primary_ipic->regs, IPIC_SERSR);
+	return primary_ipic ? ipic_read(primary_ipic->regs, IPIC_SERSR) : 0;
 }
 
 void ipic_clear_mcp_status(u32 mask)
diff --git a/arch/powerpc/sysdev/ipic.h b/arch/powerpc/sysdev/ipic.h
index 90031d1..45ab614 100644
--- a/arch/powerpc/sysdev/ipic.h
+++ b/arch/powerpc/sysdev/ipic.h
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * IPIC private definitions and structure.
  *
  * Maintainer: Kumar Gala <galak@kernel.crashing.org>
  *
  * Copyright 2005 Freescale Semiconductor, Inc
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #ifndef __IPIC_H__
 #define __IPIC_H__
diff --git a/arch/powerpc/sysdev/micropatch.c b/arch/powerpc/sysdev/micropatch.c
deleted file mode 100644
index 33a9042..0000000
--- a/arch/powerpc/sysdev/micropatch.c
+++ /dev/null
@@ -1,749 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-/* Microcode patches for the CPM as supplied by Motorola.
- * This is the one for IIC/SPI.  There is a newer one that
- * also relocates SMC2, but this would require additional changes
- * to uart.c, so I am holding off on that for a moment.
- */
-#include <linux/init.h>
-#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/interrupt.h>
-#include <asm/irq.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/8xx_immap.h>
-#include <asm/cpm.h>
-#include <asm/cpm1.h>
-
-/*
- * I2C/SPI relocation patch arrays.
- */
-
-#ifdef CONFIG_I2C_SPI_UCODE_PATCH
-
-static uint patch_2000[] __initdata = {
-	0x7FFFEFD9,
-	0x3FFD0000,
-	0x7FFB49F7,
-	0x7FF90000,
-	0x5FEFADF7,
-	0x5F89ADF7,
-	0x5FEFAFF7,
-	0x5F89AFF7,
-	0x3A9CFBC8,
-	0xE7C0EDF0,
-	0x77C1E1BB,
-	0xF4DC7F1D,
-	0xABAD932F,
-	0x4E08FDCF,
-	0x6E0FAFF8,
-	0x7CCF76CF,
-	0xFD1FF9CF,
-	0xABF88DC6,
-	0xAB5679F7,
-	0xB0937383,
-	0xDFCE79F7,
-	0xB091E6BB,
-	0xE5BBE74F,
-	0xB3FA6F0F,
-	0x6FFB76CE,
-	0xEE0DF9CF,
-	0x2BFBEFEF,
-	0xCFEEF9CF,
-	0x76CEAD24,
-	0x90B2DF9A,
-	0x7FDDD0BF,
-	0x4BF847FD,
-	0x7CCF76CE,
-	0xCFEF7E1F,
-	0x7F1D7DFD,
-	0xF0B6EF71,
-	0x7FC177C1,
-	0xFBC86079,
-	0xE722FBC8,
-	0x5FFFDFFF,
-	0x5FB2FFFB,
-	0xFBC8F3C8,
-	0x94A67F01,
-	0x7F1D5F39,
-	0xAFE85F5E,
-	0xFFDFDF96,
-	0xCB9FAF7D,
-	0x5FC1AFED,
-	0x8C1C5FC1,
-	0xAFDD5FC3,
-	0xDF9A7EFD,
-	0xB0B25FB2,
-	0xFFFEABAD,
-	0x5FB2FFFE,
-	0x5FCE600B,
-	0xE6BB600B,
-	0x5FCEDFC6,
-	0x27FBEFDF,
-	0x5FC8CFDE,
-	0x3A9CE7C0,
-	0xEDF0F3C8,
-	0x7F0154CD,
-	0x7F1D2D3D,
-	0x363A7570,
-	0x7E0AF1CE,
-	0x37EF2E68,
-	0x7FEE10EC,
-	0xADF8EFDE,
-	0xCFEAE52F,
-	0x7D0FE12B,
-	0xF1CE5F65,
-	0x7E0A4DF8,
-	0xCFEA5F72,
-	0x7D0BEFEE,
-	0xCFEA5F74,
-	0xE522EFDE,
-	0x5F74CFDA,
-	0x0B627385,
-	0xDF627E0A,
-	0x30D8145B,
-	0xBFFFF3C8,
-	0x5FFFDFFF,
-	0xA7F85F5E,
-	0xBFFE7F7D,
-	0x10D31450,
-	0x5F36BFFF,
-	0xAF785F5E,
-	0xBFFDA7F8,
-	0x5F36BFFE,
-	0x77FD30C0,
-	0x4E08FDCF,
-	0xE5FF6E0F,
-	0xAFF87E1F,
-	0x7E0FFD1F,
-	0xF1CF5F1B,
-	0xABF80D5E,
-	0x5F5EFFEF,
-	0x79F730A2,
-	0xAFDD5F34,
-	0x47F85F34,
-	0xAFED7FDD,
-	0x50B24978,
-	0x47FD7F1D,
-	0x7DFD70AD,
-	0xEF717EC1,
-	0x6BA47F01,
-	0x2D267EFD,
-	0x30DE5F5E,
-	0xFFFD5F5E,
-	0xFFEF5F5E,
-	0xFFDF0CA0,
-	0xAFED0A9E,
-	0xAFDD0C3A,
-	0x5F3AAFBD,
-	0x7FBDB082,
-	0x5F8247F8
-};
-
-static uint patch_2f00[] __initdata = {
-	0x3E303430,
-	0x34343737,
-	0xABF7BF9B,
-	0x994B4FBD,
-	0xBD599493,
-	0x349FFF37,
-	0xFB9B177D,
-	0xD9936956,
-	0xBBFDD697,
-	0xBDD2FD11,
-	0x31DB9BB3,
-	0x63139637,
-	0x93733693,
-	0x193137F7,
-	0x331737AF,
-	0x7BB9B999,
-	0xBB197957,
-	0x7FDFD3D5,
-	0x73B773F7,
-	0x37933B99,
-	0x1D115316,
-	0x99315315,
-	0x31694BF4,
-	0xFBDBD359,
-	0x31497353,
-	0x76956D69,
-	0x7B9D9693,
-	0x13131979,
-	0x79376935
-};
-#endif
-
-/*
- * I2C/SPI/SMC1 relocation patch arrays.
- */
-
-#ifdef CONFIG_I2C_SPI_SMC1_UCODE_PATCH
-
-static uint patch_2000[] __initdata = {
-	0x3fff0000,
-	0x3ffd0000,
-	0x3ffb0000,
-	0x3ff90000,
-	0x5f13eff8,
-	0x5eb5eff8,
-	0x5f88adf7,
-	0x5fefadf7,
-	0x3a9cfbc8,
-	0x77cae1bb,
-	0xf4de7fad,
-	0xabae9330,
-	0x4e08fdcf,
-	0x6e0faff8,
-	0x7ccf76cf,
-	0xfdaff9cf,
-	0xabf88dc8,
-	0xab5879f7,
-	0xb0925d8d,
-	0xdfd079f7,
-	0xb090e6bb,
-	0xe5bbe74f,
-	0x9e046f0f,
-	0x6ffb76ce,
-	0xee0cf9cf,
-	0x2bfbefef,
-	0xcfeef9cf,
-	0x76cead23,
-	0x90b3df99,
-	0x7fddd0c1,
-	0x4bf847fd,
-	0x7ccf76ce,
-	0xcfef77ca,
-	0x7eaf7fad,
-	0x7dfdf0b7,
-	0xef7a7fca,
-	0x77cafbc8,
-	0x6079e722,
-	0xfbc85fff,
-	0xdfff5fb3,
-	0xfffbfbc8,
-	0xf3c894a5,
-	0xe7c9edf9,
-	0x7f9a7fad,
-	0x5f36afe8,
-	0x5f5bffdf,
-	0xdf95cb9e,
-	0xaf7d5fc3,
-	0xafed8c1b,
-	0x5fc3afdd,
-	0x5fc5df99,
-	0x7efdb0b3,
-	0x5fb3fffe,
-	0xabae5fb3,
-	0xfffe5fd0,
-	0x600be6bb,
-	0x600b5fd0,
-	0xdfc827fb,
-	0xefdf5fca,
-	0xcfde3a9c,
-	0xe7c9edf9,
-	0xf3c87f9e,
-	0x54ca7fed,
-	0x2d3a3637,
-	0x756f7e9a,
-	0xf1ce37ef,
-	0x2e677fee,
-	0x10ebadf8,
-	0xefdecfea,
-	0xe52f7d9f,
-	0xe12bf1ce,
-	0x5f647e9a,
-	0x4df8cfea,
-	0x5f717d9b,
-	0xefeecfea,
-	0x5f73e522,
-	0xefde5f73,
-	0xcfda0b61,
-	0x5d8fdf61,
-	0xe7c9edf9,
-	0x7e9a30d5,
-	0x1458bfff,
-	0xf3c85fff,
-	0xdfffa7f8,
-	0x5f5bbffe,
-	0x7f7d10d0,
-	0x144d5f33,
-	0xbfffaf78,
-	0x5f5bbffd,
-	0xa7f85f33,
-	0xbffe77fd,
-	0x30bd4e08,
-	0xfdcfe5ff,
-	0x6e0faff8,
-	0x7eef7e9f,
-	0xfdeff1cf,
-	0x5f17abf8,
-	0x0d5b5f5b,
-	0xffef79f7,
-	0x309eafdd,
-	0x5f3147f8,
-	0x5f31afed,
-	0x7fdd50af,
-	0x497847fd,
-	0x7f9e7fed,
-	0x7dfd70a9,
-	0xef7e7ece,
-	0x6ba07f9e,
-	0x2d227efd,
-	0x30db5f5b,
-	0xfffd5f5b,
-	0xffef5f5b,
-	0xffdf0c9c,
-	0xafed0a9a,
-	0xafdd0c37,
-	0x5f37afbd,
-	0x7fbdb081,
-	0x5f8147f8,
-	0x3a11e710,
-	0xedf0ccdd,
-	0xf3186d0a,
-	0x7f0e5f06,
-	0x7fedbb38,
-	0x3afe7468,
-	0x7fedf4fc,
-	0x8ffbb951,
-	0xb85f77fd,
-	0xb0df5ddd,
-	0xdefe7fed,
-	0x90e1e74d,
-	0x6f0dcbf7,
-	0xe7decfed,
-	0xcb74cfed,
-	0xcfeddf6d,
-	0x91714f74,
-	0x5dd2deef,
-	0x9e04e7df,
-	0xefbb6ffb,
-	0xe7ef7f0e,
-	0x9e097fed,
-	0xebdbeffa,
-	0xeb54affb,
-	0x7fea90d7,
-	0x7e0cf0c3,
-	0xbffff318,
-	0x5fffdfff,
-	0xac59efea,
-	0x7fce1ee5,
-	0xe2ff5ee1,
-	0xaffbe2ff,
-	0x5ee3affb,
-	0xf9cc7d0f,
-	0xaef8770f,
-	0x7d0fb0c6,
-	0xeffbbfff,
-	0xcfef5ede,
-	0x7d0fbfff,
-	0x5ede4cf8,
-	0x7fddd0bf,
-	0x49f847fd,
-	0x7efdf0bb,
-	0x7fedfffd,
-	0x7dfdf0b7,
-	0xef7e7e1e,
-	0x5ede7f0e,
-	0x3a11e710,
-	0xedf0ccab,
-	0xfb18ad2e,
-	0x1ea9bbb8,
-	0x74283b7e,
-	0x73c2e4bb,
-	0x2ada4fb8,
-	0xdc21e4bb,
-	0xb2a1ffbf,
-	0x5e2c43f8,
-	0xfc87e1bb,
-	0xe74ffd91,
-	0x6f0f4fe8,
-	0xc7ba32e2,
-	0xf396efeb,
-	0x600b4f78,
-	0xe5bb760b,
-	0x53acaef8,
-	0x4ef88b0e,
-	0xcfef9e09,
-	0xabf8751f,
-	0xefef5bac,
-	0x741f4fe8,
-	0x751e760d,
-	0x7fdbf081,
-	0x741cafce,
-	0xefcc7fce,
-	0x751e70ac,
-	0x741ce7bb,
-	0x3372cfed,
-	0xafdbefeb,
-	0xe5bb760b,
-	0x53f2aef8,
-	0xafe8e7eb,
-	0x4bf8771e,
-	0x7e247fed,
-	0x4fcbe2cc,
-	0x7fbc30a9,
-	0x7b0f7a0f,
-	0x34d577fd,
-	0x308b5db7,
-	0xde553e5f,
-	0xaf78741f,
-	0x741f30f0,
-	0xcfef5e2c,
-	0x741f3eac,
-	0xafb8771e,
-	0x5e677fed,
-	0x0bd3e2cc,
-	0x741ccfec,
-	0xe5ca53cd,
-	0x6fcb4f74,
-	0x5dadde4b,
-	0x2ab63d38,
-	0x4bb3de30,
-	0x751f741c,
-	0x6c42effa,
-	0xefea7fce,
-	0x6ffc30be,
-	0xefec3fca,
-	0x30b3de2e,
-	0xadf85d9e,
-	0xaf7daefd,
-	0x5d9ede2e,
-	0x5d9eafdd,
-	0x761f10ac,
-	0x1da07efd,
-	0x30adfffe,
-	0x4908fb18,
-	0x5fffdfff,
-	0xafbb709b,
-	0x4ef85e67,
-	0xadf814ad,
-	0x7a0f70ad,
-	0xcfef50ad,
-	0x7a0fde30,
-	0x5da0afed,
-	0x3c12780f,
-	0xefef780f,
-	0xefef790f,
-	0xa7f85e0f,
-	0xffef790f,
-	0xefef790f,
-	0x14adde2e,
-	0x5d9eadfd,
-	0x5e2dfffb,
-	0xe79addfd,
-	0xeff96079,
-	0x607ae79a,
-	0xddfceff9,
-	0x60795dff,
-	0x607acfef,
-	0xefefefdf,
-	0xefbfef7f,
-	0xeeffedff,
-	0xebffe7ff,
-	0xafefafdf,
-	0xafbfaf7f,
-	0xaeffadff,
-	0xabffa7ff,
-	0x6fef6fdf,
-	0x6fbf6f7f,
-	0x6eff6dff,
-	0x6bff67ff,
-	0x2fef2fdf,
-	0x2fbf2f7f,
-	0x2eff2dff,
-	0x2bff27ff,
-	0x4e08fd1f,
-	0xe5ff6e0f,
-	0xaff87eef,
-	0x7e0ffdef,
-	0xf11f6079,
-	0xabf8f542,
-	0x7e0af11c,
-	0x37cfae3a,
-	0x7fec90be,
-	0xadf8efdc,
-	0xcfeae52f,
-	0x7d0fe12b,
-	0xf11c6079,
-	0x7e0a4df8,
-	0xcfea5dc4,
-	0x7d0befec,
-	0xcfea5dc6,
-	0xe522efdc,
-	0x5dc6cfda,
-	0x4e08fd1f,
-	0x6e0faff8,
-	0x7c1f761f,
-	0xfdeff91f,
-	0x6079abf8,
-	0x761cee24,
-	0xf91f2bfb,
-	0xefefcfec,
-	0xf91f6079,
-	0x761c27fb,
-	0xefdf5da7,
-	0xcfdc7fdd,
-	0xd09c4bf8,
-	0x47fd7c1f,
-	0x761ccfcf,
-	0x7eef7fed,
-	0x7dfdf093,
-	0xef7e7f1e,
-	0x771efb18,
-	0x6079e722,
-	0xe6bbe5bb,
-	0xae0ae5bb,
-	0x600bae85,
-	0xe2bbe2bb,
-	0xe2bbe2bb,
-	0xaf02e2bb,
-	0xe2bb2ff9,
-	0x6079e2bb
-};
-
-static uint patch_2f00[] __initdata = {
-	0x30303030,
-	0x3e3e3434,
-	0xabbf9b99,
-	0x4b4fbdbd,
-	0x59949334,
-	0x9fff37fb,
-	0x9b177dd9,
-	0x936956bb,
-	0xfbdd697b,
-	0xdd2fd113,
-	0x1db9f7bb,
-	0x36313963,
-	0x79373369,
-	0x3193137f,
-	0x7331737a,
-	0xf7bb9b99,
-	0x9bb19795,
-	0x77fdfd3d,
-	0x573b773f,
-	0x737933f7,
-	0xb991d115,
-	0x31699315,
-	0x31531694,
-	0xbf4fbdbd,
-	0x35931497,
-	0x35376956,
-	0xbd697b9d,
-	0x96931313,
-	0x19797937,
-	0x6935af78,
-	0xb9b3baa3,
-	0xb8788683,
-	0x368f78f7,
-	0x87778733,
-	0x3ffffb3b,
-	0x8e8f78b8,
-	0x1d118e13,
-	0xf3ff3f8b,
-	0x6bd8e173,
-	0xd1366856,
-	0x68d1687b,
-	0x3daf78b8,
-	0x3a3a3f87,
-	0x8f81378f,
-	0xf876f887,
-	0x77fd8778,
-	0x737de8d6,
-	0xbbf8bfff,
-	0xd8df87f7,
-	0xfd876f7b,
-	0x8bfff8bd,
-	0x8683387d,
-	0xb873d87b,
-	0x3b8fd7f8,
-	0xf7338883,
-	0xbb8ee1f8,
-	0xef837377,
-	0x3337b836,
-	0x817d11f8,
-	0x7378b878,
-	0xd3368b7d,
-	0xed731b7d,
-	0x833731f3,
-	0xf22f3f23
-};
-
-static uint patch_2e00[] __initdata = {
-	0x27eeeeee,
-	0xeeeeeeee,
-	0xeeeeeeee,
-	0xeeeeeeee,
-	0xee4bf4fb,
-	0xdbd259bb,
-	0x1979577f,
-	0xdfd2d573,
-	0xb773f737,
-	0x4b4fbdbd,
-	0x25b9b177,
-	0xd2d17376,
-	0x956bbfdd,
-	0x697bdd2f,
-	0xff9f79ff,
-	0xff9ff22f
-};
-#endif
-
-/*
- *  USB SOF patch arrays.
- */
-
-#ifdef CONFIG_USB_SOF_UCODE_PATCH
-
-static uint patch_2000[] __initdata = {
-	0x7fff0000,
-	0x7ffd0000,
-	0x7ffb0000,
-	0x49f7ba5b,
-	0xba383ffb,
-	0xf9b8b46d,
-	0xe5ab4e07,
-	0xaf77bffe,
-	0x3f7bbf79,
-	0xba5bba38,
-	0xe7676076,
-	0x60750000
-};
-
-static uint patch_2f00[] __initdata = {
-	0x3030304c,
-	0xcab9e441,
-	0xa1aaf220
-};
-#endif
-
-void __init cpm_load_patch(cpm8xx_t *cp)
-{
-	volatile uint		*dp;		/* Dual-ported RAM. */
-	volatile cpm8xx_t	*commproc;
-#if defined(CONFIG_I2C_SPI_UCODE_PATCH) || \
-    defined(CONFIG_I2C_SPI_SMC1_UCODE_PATCH)
-	volatile iic_t		*iip;
-	volatile struct spi_pram *spp;
-#ifdef CONFIG_I2C_SPI_SMC1_UCODE_PATCH
-	volatile smc_uart_t	*smp;
-#endif
-#endif
-	int	i;
-
-	commproc = cp;
-
-#ifdef CONFIG_USB_SOF_UCODE_PATCH
-	commproc->cp_rccr = 0;
-
-	dp = (uint *)(commproc->cp_dpmem);
-	for (i=0; i<(sizeof(patch_2000)/4); i++)
-		*dp++ = patch_2000[i];
-
-	dp = (uint *)&(commproc->cp_dpmem[0x0f00]);
-	for (i=0; i<(sizeof(patch_2f00)/4); i++)
-		*dp++ = patch_2f00[i];
-
-	commproc->cp_rccr = 0x0009;
-
-	printk("USB SOF microcode patch installed\n");
-#endif /* CONFIG_USB_SOF_UCODE_PATCH */
-
-#if defined(CONFIG_I2C_SPI_UCODE_PATCH) || \
-    defined(CONFIG_I2C_SPI_SMC1_UCODE_PATCH)
-
-	commproc->cp_rccr = 0;
-
-	dp = (uint *)(commproc->cp_dpmem);
-	for (i=0; i<(sizeof(patch_2000)/4); i++)
-		*dp++ = patch_2000[i];
-
-	dp = (uint *)&(commproc->cp_dpmem[0x0f00]);
-	for (i=0; i<(sizeof(patch_2f00)/4); i++)
-		*dp++ = patch_2f00[i];
-
-	iip = (iic_t *)&commproc->cp_dparam[PROFF_IIC];
-# define RPBASE 0x0500
-	iip->iic_rpbase = RPBASE;
-
-	/* Put SPI above the IIC, also 32-byte aligned.
-	*/
-	i = (RPBASE + sizeof(iic_t) + 31) & ~31;
-	spp = (struct spi_pram *)&commproc->cp_dparam[PROFF_SPI];
-	spp->rpbase = i;
-
-# if defined(CONFIG_I2C_SPI_UCODE_PATCH)
-	commproc->cp_cpmcr1 = 0x802a;
-	commproc->cp_cpmcr2 = 0x8028;
-	commproc->cp_cpmcr3 = 0x802e;
-	commproc->cp_cpmcr4 = 0x802c;
-	commproc->cp_rccr = 1;
-
-	printk("I2C/SPI microcode patch installed.\n");
-# endif /* CONFIG_I2C_SPI_UCODE_PATCH */
-
-# if defined(CONFIG_I2C_SPI_SMC1_UCODE_PATCH)
-
-	dp = (uint *)&(commproc->cp_dpmem[0x0e00]);
-	for (i=0; i<(sizeof(patch_2e00)/4); i++)
-		*dp++ = patch_2e00[i];
-
-	commproc->cp_cpmcr1 = 0x8080;
-	commproc->cp_cpmcr2 = 0x808a;
-	commproc->cp_cpmcr3 = 0x8028;
-	commproc->cp_cpmcr4 = 0x802a;
-	commproc->cp_rccr = 3;
-
-	smp = (smc_uart_t *)&commproc->cp_dparam[PROFF_SMC1];
-	smp->smc_rpbase = 0x1FC0;
-
-	printk("I2C/SPI/SMC1 microcode patch installed.\n");
-# endif /* CONFIG_I2C_SPI_SMC1_UCODE_PATCH) */
-
-#endif /* some variation of the I2C/SPI patch was selected */
-}
-
-/*
- *  Take this entire routine out, since no one calls it and its
- * logic is suspect.
- */
-
-#if 0
-void
-verify_patch(volatile immap_t *immr)
-{
-	volatile uint		*dp;
-	volatile cpm8xx_t	*commproc;
-	int i;
-
-	commproc = (cpm8xx_t *)&immr->im_cpm;
-
-	printk("cp_rccr %x\n", commproc->cp_rccr);
-	commproc->cp_rccr = 0;
-
-	dp = (uint *)(commproc->cp_dpmem);
-	for (i=0; i<(sizeof(patch_2000)/4); i++)
-		if (*dp++ != patch_2000[i]) {
-			printk("patch_2000 bad at %d\n", i);
-			dp--;
-			printk("found 0x%X, wanted 0x%X\n", *dp, patch_2000[i]);
-			break;
-		}
-
-	dp = (uint *)&(commproc->cp_dpmem[0x0f00]);
-	for (i=0; i<(sizeof(patch_2f00)/4); i++)
-		if (*dp++ != patch_2f00[i]) {
-			printk("patch_2f00 bad at %d\n", i);
-			dp--;
-			printk("found 0x%X, wanted 0x%X\n", *dp, patch_2f00[i]);
-			break;
-		}
-
-	commproc->cp_rccr = 0x0009;
-}
-#endif
diff --git a/arch/powerpc/sysdev/mmio_nvram.c b/arch/powerpc/sysdev/mmio_nvram.c
index c31f634..628f9b7 100644
--- a/arch/powerpc/sysdev/mmio_nvram.c
+++ b/arch/powerpc/sysdev/mmio_nvram.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * memory mapped NVRAM
  *
  * (C) Copyright IBM Corp. 2005
  *
  * Authors : Utz Bacher <utz.bacher@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/fs.h>
diff --git a/arch/powerpc/sysdev/mpic.h b/arch/powerpc/sysdev/mpic.h
index 32971a4..73a31a4 100644
--- a/arch/powerpc/sysdev/mpic.h
+++ b/arch/powerpc/sysdev/mpic.h
@@ -1,14 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 #ifndef _POWERPC_SYSDEV_MPIC_H
 #define _POWERPC_SYSDEV_MPIC_H
 
 /*
  * Copyright 2006-2007, Michael Ellerman, IBM 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.
- *
  */
 
 #ifdef CONFIG_PCI_MSI
diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c
index 280e964..f6b253e 100644
--- a/arch/powerpc/sysdev/mpic_msgr.c
+++ b/arch/powerpc/sysdev/mpic_msgr.c
@@ -1,14 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2011-2012, Meador Inge, Mentor Graphics Corporation.
  *
  * Some ideas based on un-pushed work done by Vivek Mahajan, Jason Jin, and
  * Mingkai Hu from Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2 of the
- * License.
- *
  */
 
 #include <linux/list.h>
diff --git a/arch/powerpc/sysdev/mpic_msi.c b/arch/powerpc/sysdev/mpic_msi.c
index 9ed860a..4695c04 100644
--- a/arch/powerpc/sysdev/mpic_msi.c
+++ b/arch/powerpc/sysdev/mpic_msi.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2006-2007, Michael Ellerman, IBM 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.
- *
  */
 
 #include <linux/irq.h>
diff --git a/arch/powerpc/sysdev/mpic_timer.c b/arch/powerpc/sysdev/mpic_timer.c
index 87e7c42..a42a202 100644
--- a/arch/powerpc/sysdev/mpic_timer.c
+++ b/arch/powerpc/sysdev/mpic_timer.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * MPIC timer driver
  *
  * Copyright 2013 Freescale Semiconductor, Inc.
  * Author: Dongsheng Wang <Dongsheng.Wang@freescale.com>
  *	   Li Yang <leoli@freescale.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index cfc1c57..3861023 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -1,12 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2006, Segher Boessenkool, IBM Corporation.
  * Copyright 2006-2007, Michael Ellerman, IBM 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.
- *
  */
 
 #include <linux/irq.h>
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index e64a411..fdd3e17 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -1,18 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2006-2008, Michael Ellerman, IBM 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.
- *
  */
 
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/kmemleak.h>
 #include <linux/bitmap.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <asm/msi_bitmap.h>
 #include <asm/setup.h>
 
@@ -128,7 +123,10 @@
 	if (bmp->bitmap_from_slab)
 		bmp->bitmap = kzalloc(size, GFP_KERNEL);
 	else {
-		bmp->bitmap = memblock_virt_alloc(size, 0);
+		bmp->bitmap = memblock_alloc(size, SMP_CACHE_BYTES);
+		if (!bmp->bitmap)
+			panic("%s: Failed to allocate %u bytes\n", __func__,
+			      size);
 		/* 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 153fdac..1f408d3 100644
--- a/arch/powerpc/sysdev/of_rtc.c
+++ b/arch/powerpc/sysdev/of_rtc.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Instantiate mmio-mapped RTC chips based on device tree information
  *
  * Copyright 2007 David Gibson <dwg@au1.ibm.com>, IBM 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;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #include <linux/kernel.h>
 #include <linux/of.h>
diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c
index 9ea6a22..9c8744e 100644
--- a/arch/powerpc/sysdev/pmi.c
+++ b/arch/powerpc/sysdev/pmi.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * pmi driver
  *
@@ -8,20 +9,6 @@
  * Unlike IPMI it is bidirectional and has a low latency.
  *
  * Author: Christian Krafft <krafft@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c
deleted file mode 100644
index 0f6fd5d..0000000
--- a/arch/powerpc/sysdev/scom.c
+++ /dev/null
@@ -1,236 +0,0 @@
-/*
- * Copyright 2010 Benjamin Herrenschmidt, IBM Corp
- *                <benh@kernel.crashing.org>
- *     and        David Gibson, IBM 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; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
- *   the GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program;  if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include <asm/debugfs.h>
-#include <asm/prom.h>
-#include <asm/scom.h>
-#include <linux/uaccess.h>
-
-const struct scom_controller *scom_controller;
-EXPORT_SYMBOL_GPL(scom_controller);
-
-struct device_node *scom_find_parent(struct device_node *node)
-{
-	struct device_node *par, *tmp;
-	const u32 *p;
-
-	for (par = of_node_get(node); par;) {
-		if (of_get_property(par, "scom-controller", NULL))
-			break;
-		p = of_get_property(par, "scom-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;
-}
-EXPORT_SYMBOL_GPL(scom_find_parent);
-
-scom_map_t scom_map_device(struct device_node *dev, int index)
-{
-	struct device_node *parent;
-	unsigned int cells, size;
-	const __be32 *prop, *sprop;
-	u64 reg, cnt;
-	scom_map_t ret;
-
-	parent = scom_find_parent(dev);
-
-	if (parent == NULL)
-		return 0;
-
-	/*
-	 * We support "scom-reg" properties for adding scom registers
-	 * to a random device-tree node with an explicit scom-parent
-	 *
-	 * We also support the simple "reg" property if the device is
-	 * a direct child of a scom controller.
-	 *
-	 * In case both exist, "scom-reg" takes precedence.
-	 */
-	prop = of_get_property(dev, "scom-reg", &size);
-	sprop = of_get_property(parent, "#scom-cells", NULL);
-	if (!prop && parent == dev->parent) {
-		prop = of_get_property(dev, "reg", &size);
-		sprop = of_get_property(parent, "#address-cells", NULL);
-	}
-	if (!prop)
-		return NULL;
-	cells = sprop ? be32_to_cpup(sprop) : 1;
-	size >>= 2;
-
-	if (index >= (size / (2*cells)))
-		return 0;
-
-	reg = of_read_number(&prop[index * cells * 2], cells);
-	cnt = of_read_number(&prop[index * cells * 2 + cells], cells);
-
-	ret = scom_map(parent, reg, cnt);
-	of_node_put(parent);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(scom_map_device);
-
-#ifdef CONFIG_SCOM_DEBUGFS
-struct scom_debug_entry {
-	struct device_node *dn;
-	struct debugfs_blob_wrapper path;
-	char name[16];
-};
-
-static ssize_t scom_debug_read(struct file *filp, char __user *ubuf,
-			       size_t count, loff_t *ppos)
-{
-	struct scom_debug_entry *ent = filp->private_data;
-	u64 __user *ubuf64 = (u64 __user *)ubuf;
-	loff_t off = *ppos;
-	ssize_t done = 0; 
-	u64 reg, reg_cnt, val;
-	scom_map_t map;
-	int rc;
-
-	if (off < 0 || (off & 7) || (count & 7))
-		return -EINVAL;
-	reg = off >> 3;
-	reg_cnt = count >> 3;
-
-	map = scom_map(ent->dn, reg, reg_cnt);
-	if (!scom_map_ok(map))
-		return -ENXIO;
-
-	for (reg = 0; reg < reg_cnt; reg++) {
-		rc = scom_read(map, reg, &val);
-		if (!rc)
-			rc = put_user(val, ubuf64);
-		if (rc) {
-			if (!done)
-				done = rc;
-			break;
-		}
-		ubuf64++;
-		*ppos += 8;
-		done += 8;
-	}
-	scom_unmap(map);
-	return done;
-}
-
-static ssize_t scom_debug_write(struct file* filp, const char __user *ubuf,
-				size_t count, loff_t *ppos)
-{
-	struct scom_debug_entry *ent = filp->private_data;
-	u64 __user *ubuf64 = (u64 __user *)ubuf;
-	loff_t off = *ppos;
-	ssize_t done = 0; 
-	u64 reg, reg_cnt, val;
-	scom_map_t map;
-	int rc;
-
-	if (off < 0 || (off & 7) || (count & 7))
-		return -EINVAL;
-	reg = off >> 3;
-	reg_cnt = count >> 3;
-
-	map = scom_map(ent->dn, reg, reg_cnt);
-	if (!scom_map_ok(map))
-		return -ENXIO;
-
-	for (reg = 0; reg < reg_cnt; reg++) {
-		rc = get_user(val, ubuf64);
-		if (!rc)
-			rc = scom_write(map, reg,  val);
-		if (rc) {
-			if (!done)
-				done = rc;
-			break;
-		}
-		ubuf64++;
-		done += 8;
-	}
-	scom_unmap(map);
-	return done;
-}
-
-static const struct file_operations scom_debug_fops = {
-	.read =		scom_debug_read,
-	.write =	scom_debug_write,
-	.open =		simple_open,
-	.llseek =	default_llseek,
-};
-
-static int scom_debug_init_one(struct dentry *root, struct device_node *dn,
-			       int i)
-{
-	struct scom_debug_entry *ent;
-	struct dentry *dir;
-
-	ent = kzalloc(sizeof(*ent), GFP_KERNEL);
-	if (!ent)
-		return -ENOMEM;
-
-	ent->dn = of_node_get(dn);
-	snprintf(ent->name, 16, "%08x", i);
-	ent->path.data = (void*)kasprintf(GFP_KERNEL, "%pOF", dn);
-	ent->path.size = strlen((char *)ent->path.data);
-
-	dir = debugfs_create_dir(ent->name, root);
-	if (!dir) {
-		of_node_put(dn);
-		kfree(ent->path.data);
-		kfree(ent);
-		return -1;
-	}
-
-	debugfs_create_blob("devspec", 0400, dir, &ent->path);
-	debugfs_create_file("access", 0600, dir, ent, &scom_debug_fops);
-
-	return 0;
-}
-
-static int scom_debug_init(void)
-{
-	struct device_node *dn;
-	struct dentry *root;
-	int i, rc;
-
-	root = debugfs_create_dir("scom", powerpc_debugfs_root);
-	if (!root)
-		return -1;
-
-	i = rc = 0;
-	for_each_node_with_property(dn, "scom-controller") {
-		int id = of_get_ibm_chip_id(dn);
-		if (id == -1)
-			id = i;
-		rc |= scom_debug_init_one(root, dn, id);
-		i++;
-	}
-
-	return rc;
-}
-device_initcall(scom_debug_init);
-#endif /* CONFIG_SCOM_DEBUGFS */
diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c
index f02d457..dc1740c 100644
--- a/arch/powerpc/sysdev/simple_gpio.c
+++ b/arch/powerpc/sysdev/simple_gpio.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Simple Memory-Mapped GPIOs
  *
  * Copyright (c) MontaVista Software, Inc. 2008.
  *
  * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/init.h>
diff --git a/arch/powerpc/sysdev/tsi108_dev.c b/arch/powerpc/sysdev/tsi108_dev.c
index 1fd0717..0baec82 100644
--- a/arch/powerpc/sysdev/tsi108_dev.c
+++ b/arch/powerpc/sysdev/tsi108_dev.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * tsi108/109 device setup code
  *
  * Maintained by Roy Zang < tie-fei.zang@freescale.com >
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/stddef.h>
@@ -18,6 +14,7 @@
 #include <linux/irq.h>
 #include <linux/export.h>
 #include <linux/device.h>
+#include <linux/etherdevice.h>
 #include <linux/platform_device.h>
 #include <linux/of_net.h>
 #include <asm/tsi108.h>
@@ -51,7 +48,7 @@
 		const void *prop = of_get_property(tsi, "reg", &size);
 		tsi108_csr_base = of_translate_address(tsi, prop);
 		of_node_put(tsi);
-	};
+	}
 	return tsi108_csr_base;
 }
 
@@ -105,8 +102,8 @@
 		}
 
 		mac_addr = of_get_mac_address(np);
-		if (mac_addr)
-			memcpy(tsi_eth_data.mac_addr, mac_addr, 6);
+		if (!IS_ERR(mac_addr))
+			ether_addr_copy(tsi_eth_data.mac_addr, mac_addr);
 
 		ph = of_get_property(np, "mdio-handle", NULL);
 		mdio = of_find_node_by_phandle(*ph);
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 28ff1f5..49f9541 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Common routines for Tundra Semiconductor TSI108 host bridge.
  *
@@ -5,20 +6,6 @@
  * Author: Alex Bounine (alexandreb@tundra.com)
  * Author: Roy Zang (tie-fei.zang@freescale.com)
  * 	   Add pci interrupt router host
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c
index 9998c0d..d38bbee 100644
--- a/arch/powerpc/sysdev/udbg_memcons.c
+++ b/arch/powerpc/sysdev/udbg_memcons.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * A udbg backend which logs messages and reads input from in memory
  * buffers.
@@ -11,11 +12,6 @@
  *
  * Copyright (C) 2003-2005 Anton Blanchard and Milton Miller, IBM Corp
  * Copyright (C) 2013 Alistair Popple, IBM Corp
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig
index 86fee42..304614c 100644
--- a/arch/powerpc/sysdev/xics/Kconfig
+++ b/arch/powerpc/sysdev/xics/Kconfig
@@ -1,15 +1,14 @@
 # SPDX-License-Identifier: GPL-2.0
 config PPC_XICS
-       def_bool n
-       select PPC_SMP_MUXED_IPI
-       select HARDIRQS_SW_RESEND
+	def_bool n
+	select PPC_SMP_MUXED_IPI
+	select HARDIRQS_SW_RESEND
 
 config PPC_ICP_NATIVE
-       def_bool n
+	def_bool n
 
 config PPC_ICP_HV
-       def_bool n
+	def_bool n
 
 config PPC_ICS_RTAS
-       def_bool n
-
+	def_bool n
diff --git a/arch/powerpc/sysdev/xics/Makefile b/arch/powerpc/sysdev/xics/Makefile
index 5d438d9..ba1e311 100644
--- a/arch/powerpc/sysdev/xics/Makefile
+++ b/arch/powerpc/sysdev/xics/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 obj-y				+= xics-common.o
 obj-$(CONFIG_PPC_ICP_NATIVE)	+= icp-native.o
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index bbc839a..ad81171 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2011 IBM 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; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 37bfbc5..7d13d2e 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2011 IBM 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; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 
 #include <linux/types.h>
@@ -145,7 +140,7 @@
 
 static void icp_native_cause_ipi(int cpu)
 {
-	kvmppc_set_host_ipi(cpu, 1);
+	kvmppc_set_host_ipi(cpu);
 	icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
@@ -184,7 +179,7 @@
 	if (vec == XICS_IPI) {
 		/* Clear pending IPI */
 		int cpu = smp_processor_id();
-		kvmppc_set_host_ipi(cpu, 0);
+		kvmppc_clear_host_ipi(cpu);
 		icp_native_set_qirr(cpu, 0xff);
 	} else {
 		pr_err("XICS: hw interrupt 0x%x to offline cpu, disabling\n",
@@ -205,7 +200,7 @@
 {
 	int cpu = smp_processor_id();
 
-	kvmppc_set_host_ipi(cpu, 0);
+	kvmppc_clear_host_ipi(cpu);
 	icp_native_set_qirr(cpu, 0xff);
 
 	return smp_ipi_demux();
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index c71d2ea..68fd254 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2016 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -130,7 +126,7 @@
 {
 	int hw_cpu = get_hard_smp_processor_id(cpu);
 
-	kvmppc_set_host_ipi(cpu, 1);
+	kvmppc_set_host_ipi(cpu);
 	opal_int_set_mfrr(hw_cpu, IPI_PRIORITY);
 }
 
@@ -138,7 +134,7 @@
 {
 	int cpu = smp_processor_id();
 
-	kvmppc_set_host_ipi(cpu, 0);
+	kvmppc_clear_host_ipi(cpu);
 	opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff);
 
 	return smp_ipi_demux();
@@ -161,7 +157,7 @@
 		if (vec == XICS_IPI) {
 			/* Clear pending IPI */
 			int cpu = smp_processor_id();
-			kvmppc_set_host_ipi(cpu, 0);
+			kvmppc_clear_host_ipi(cpu);
 			opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff);
 		} else {
 			pr_err("XICS: hw interrupt 0x%x to offline cpu, "
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
index f85f916..823f6c9 100644
--- a/arch/powerpc/sysdev/xics/ics-opal.c
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * ICS backend for OPAL managed interrupts.
  *
  * Copyright 2011 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #undef DEBUG
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index f874703..7e4305c 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -1,11 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2011 IBM 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; either version
- *  2 of the License, or (at your option) any later version.
- *
  */
 #include <linux/types.h>
 #include <linux/threads.h>
diff --git a/arch/powerpc/sysdev/xive/Kconfig b/arch/powerpc/sysdev/xive/Kconfig
index 70ee976..785c292 100644
--- a/arch/powerpc/sysdev/xive/Kconfig
+++ b/arch/powerpc/sysdev/xive/Kconfig
@@ -1,17 +1,14 @@
 # SPDX-License-Identifier: GPL-2.0
 config PPC_XIVE
 	bool
-	default n
 	select PPC_SMP_MUXED_IPI
 	select HARDIRQS_SW_RESEND
 
 config PPC_XIVE_NATIVE
 	bool
-	default n
 	select PPC_XIVE
 	depends on PPC_POWERNV
 
 config PPC_XIVE_SPAPR
 	bool
-	default n
 	select PPC_XIVE
diff --git a/arch/powerpc/sysdev/xive/Makefile b/arch/powerpc/sysdev/xive/Makefile
index 536d6e5..e510888 100644
--- a/arch/powerpc/sysdev/xive/Makefile
+++ b/arch/powerpc/sysdev/xive/Makefile
@@ -1,4 +1,4 @@
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+# SPDX-License-Identifier: GPL-2.0-only
 
 obj-y				+= common.o
 obj-$(CONFIG_PPC_XIVE_NATIVE)	+= native.o
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index 959a2a6..df832b0 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2016,2017 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "xive: " fmt
@@ -139,7 +135,7 @@
 static u32 xive_scan_interrupts(struct xive_cpu *xc, bool just_peek)
 {
 	u32 irq = 0;
-	u8 prio;
+	u8 prio = 0;
 
 	/* Find highest pending priority */
 	while (xc->pending_prio != 0) {
@@ -152,8 +148,19 @@
 		irq = xive_read_eq(&xc->queue[prio], just_peek);
 
 		/* Found something ? That's it */
-		if (irq)
-			break;
+		if (irq) {
+			if (just_peek || irq_to_desc(irq))
+				break;
+			/*
+			 * We should never get here; if we do then we must
+			 * have failed to synchronize the interrupt properly
+			 * when shutting it down.
+			 */
+			pr_crit("xive: got interrupt %d without descriptor, dropping\n",
+				irq);
+			WARN_ON(1);
+			continue;
+		}
 
 		/* Clear pending bits */
 		xc->pending_prio &= ~(1 << prio);
@@ -189,7 +196,7 @@
 
 /*
  * This is used to perform the magic loads from an ESB
- * described in xive.h
+ * described in xive-regs.h
  */
 static notrace u8 xive_esb_read(struct xive_irq_data *xd, u32 offset)
 {
@@ -230,26 +237,61 @@
 	i0 = be32_to_cpup(q->qpage + idx);
 	idx = (idx + 1) & q->msk;
 	i1 = be32_to_cpup(q->qpage + idx);
-	xmon_printf("  %s Q T=%d %08x %08x ...\n", name,
-		    q->toggle, i0, i1);
+	xmon_printf("%s idx=%d T=%d %08x %08x ...", name,
+		     q->idx, q->toggle, i0, i1);
 }
 
 notrace void xmon_xive_do_dump(int cpu)
 {
 	struct xive_cpu *xc = per_cpu(xive_cpu, cpu);
 
-	xmon_printf("XIVE state for CPU %d:\n", cpu);
-	xmon_printf("  pp=%02x cppr=%02x\n", xc->pending_prio, xc->cppr);
-	xive_dump_eq("IRQ", &xc->queue[xive_irq_priority]);
+	xmon_printf("CPU %d:", cpu);
+	if (xc) {
+		xmon_printf("pp=%02x CPPR=%02x ", xc->pending_prio, xc->cppr);
+
 #ifdef CONFIG_SMP
-	{
-		u64 val = xive_esb_read(&xc->ipi_data, XIVE_ESB_GET);
-		xmon_printf("  IPI state: %x:%c%c\n", xc->hw_ipi,
-			val & XIVE_ESB_VAL_P ? 'P' : 'p',
-			val & XIVE_ESB_VAL_Q ? 'Q' : 'q');
-	}
+		{
+			u64 val = xive_esb_read(&xc->ipi_data, XIVE_ESB_GET);
+
+			xmon_printf("IPI=0x%08x PQ=%c%c ", xc->hw_ipi,
+				    val & XIVE_ESB_VAL_P ? 'P' : '-',
+				    val & XIVE_ESB_VAL_Q ? 'Q' : '-');
+		}
 #endif
+		xive_dump_eq("EQ", &xc->queue[xive_irq_priority]);
+	}
+	xmon_printf("\n");
 }
+
+int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d)
+{
+	int rc;
+	u32 target;
+	u8 prio;
+	u32 lirq;
+
+	rc = xive_ops->get_irq_config(hw_irq, &target, &prio, &lirq);
+	if (rc) {
+		xmon_printf("IRQ 0x%08x : no config rc=%d\n", hw_irq, rc);
+		return rc;
+	}
+
+	xmon_printf("IRQ 0x%08x : target=0x%x prio=%02x lirq=0x%x ",
+		    hw_irq, target, prio, lirq);
+
+	if (d) {
+		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+		u64 val = xive_esb_read(xd, XIVE_ESB_GET);
+
+		xmon_printf("PQ=%c%c",
+			    val & XIVE_ESB_VAL_P ? 'P' : '-',
+			    val & XIVE_ESB_VAL_Q ? 'Q' : '-');
+	}
+
+	xmon_printf("\n");
+	return 0;
+}
+
 #endif /* CONFIG_XMON */
 
 static unsigned int xive_get_irq(void)
@@ -309,8 +351,9 @@
  * EOI an interrupt at the source. There are several methods
  * to do this depending on the HW version and source type
  */
-void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd)
+static void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd)
 {
+	xd->stale_p = false;
 	/* If the XIVE supports the new "store EOI facility, use it */
 	if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI)
 		xive_esb_write(xd, XIVE_ESB_STORE_EOI, 0);
@@ -354,7 +397,7 @@
 	}
 }
 
-/* irq_chip eoi callback */
+/* 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);
@@ -370,6 +413,8 @@
 	if (!irqd_irq_disabled(d) && !irqd_is_forwarded_to_vcpu(d) &&
 	    !(xd->flags & XIVE_IRQ_NO_EOI))
 		xive_do_source_eoi(irqd_to_hwirq(d), xd);
+	else
+		xd->stale_p = true;
 
 	/*
 	 * Clear saved_p to indicate that it's no longer occupying
@@ -401,11 +446,16 @@
 	 */
 	if (mask) {
 		val = xive_esb_read(xd, XIVE_ESB_SET_PQ_01);
-		xd->saved_p = !!(val & XIVE_ESB_VAL_P);
-	} else if (xd->saved_p)
+		if (!xd->stale_p && !!(val & XIVE_ESB_VAL_P))
+			xd->saved_p = true;
+		xd->stale_p = false;
+	} else if (xd->saved_p) {
 		xive_esb_read(xd, XIVE_ESB_SET_PQ_10);
-	else
+		xd->saved_p = false;
+	} else {
 		xive_esb_read(xd, XIVE_ESB_SET_PQ_00);
+		xd->stale_p = false;
+	}
 }
 
 /*
@@ -442,7 +492,7 @@
 	struct xive_cpu *xc = per_cpu(xive_cpu, cpu);
 	struct xive_q *q = &xc->queue[xive_irq_priority];
 
-	if (unlikely(WARN_ON(cpu < 0 || !xc))) {
+	if (WARN_ON(cpu < 0 || !xc)) {
 		pr_err("%s: cpu=%d xc=%p\n", __func__, cpu, xc);
 		return;
 	}
@@ -483,7 +533,7 @@
 	 * Now go through the entire mask until we find a valid
 	 * target.
 	 */
-	for (;;) {
+	do {
 		/*
 		 * We re-check online as the fallback case passes us
 		 * an untested affinity mask
@@ -491,12 +541,11 @@
 		if (cpu_online(cpu) && xive_try_pick_target(cpu))
 			return cpu;
 		cpu = cpumask_next(cpu, mask);
-		if (cpu == first)
-			break;
 		/* Wrap around */
 		if (cpu >= nr_cpu_ids)
 			cpu = cpumask_first(mask);
-	}
+	} while (cpu != first);
+
 	return -1;
 }
 
@@ -546,6 +595,8 @@
 	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 	int target, rc;
 
+	xd->saved_p = false;
+	xd->stale_p = false;
 	pr_devel("xive_irq_startup: irq %d [0x%x] data @%p\n",
 		 d->irq, hw_irq, d);
 
@@ -592,6 +643,7 @@
 	return 0;
 }
 
+/* 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);
@@ -607,16 +659,6 @@
 	xive_do_source_set_mask(xd, true);
 
 	/*
-	 * The above may have set saved_p. We clear it otherwise it
-	 * will prevent re-enabling later on. It is ok to forget the
-	 * fact that the interrupt might be in a queue because we are
-	 * accounting that already in xive_dec_target_count() and will
-	 * be re-routing it to a new queue with proper accounting when
-	 * it's started up again
-	 */
-	xd->saved_p = false;
-
-	/*
 	 * Mask the interrupt in HW in the IVT/EAS and set the number
 	 * to be the "bad" IRQ number
 	 */
@@ -802,6 +844,10 @@
 	return 1;
 }
 
+/*
+ * Caller holds the irq descriptor lock, so this won't be called
+ * concurrently with xive_get_irqchip_state on the same interrupt.
+ */
 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);
@@ -825,6 +871,10 @@
 
 		/* Set it to PQ=10 state to prevent further sends */
 		pq = xive_esb_read(xd, XIVE_ESB_SET_PQ_10);
+		if (!xd->stale_p) {
+			xd->saved_p = !!(pq & XIVE_ESB_VAL_P);
+			xd->stale_p = !xd->saved_p;
+		}
 
 		/* No target ? nothing to do */
 		if (xd->target == XIVE_INVALID_TARGET) {
@@ -832,7 +882,7 @@
 			 * An untargetted interrupt should have been
 			 * also masked at the source
 			 */
-			WARN_ON(pq & 2);
+			WARN_ON(xd->saved_p);
 
 			return 0;
 		}
@@ -852,9 +902,8 @@
 		 * This saved_p is cleared by the host EOI, when we know
 		 * for sure the queue slot is no longer in use.
 		 */
-		if (pq & 2) {
-			pq = xive_esb_read(xd, XIVE_ESB_SET_PQ_11);
-			xd->saved_p = true;
+		if (xd->saved_p) {
+			xive_esb_read(xd, XIVE_ESB_SET_PQ_11);
 
 			/*
 			 * Sync the XIVE source HW to ensure the interrupt
@@ -867,8 +916,7 @@
 			 */
 			if (xive_ops->sync_source)
 				xive_ops->sync_source(hw_irq);
-		} else
-			xd->saved_p = false;
+		}
 	} else {
 		irqd_clr_forwarded_to_vcpu(d);
 
@@ -919,6 +967,23 @@
 	return 0;
 }
 
+/* Called with irq descriptor lock held. */
+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);
+
+	switch (which) {
+	case IRQCHIP_STATE_ACTIVE:
+		*state = !xd->stale_p &&
+			 (xd->saved_p ||
+			  !!(xive_esb_read(xd, XIVE_ESB_GET) & XIVE_ESB_VAL_P));
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static struct irq_chip xive_irq_chip = {
 	.name = "XIVE-IRQ",
 	.irq_startup = xive_irq_startup,
@@ -930,6 +995,7 @@
 	.irq_set_type = xive_irq_set_type,
 	.irq_retrigger = xive_irq_retrigger,
 	.irq_set_vcpu_affinity = xive_irq_set_vcpu_affinity,
+	.irq_get_irqchip_state = xive_get_irqchip_state,
 };
 
 bool is_xive_irq(struct irq_chip *chip)
@@ -1010,12 +1076,13 @@
 {
 	struct xive_cpu *xc = __this_cpu_read(xive_cpu);
 
-	DBG_VERBOSE("IPI eoi: irq=%d [0x%lx] (HW IRQ 0x%x) pending=%02x\n",
-		    d->irq, irqd_to_hwirq(d), xc->hw_ipi, xc->pending_prio);
-
 	/* Handle possible race with unplug and drop stale IPIs */
 	if (!xc)
 		return;
+
+	DBG_VERBOSE("IPI eoi: irq=%d [0x%lx] (HW IRQ 0x%x) pending=%02x\n",
+		    d->irq, irqd_to_hwirq(d), xc->hw_ipi, xc->pending_prio);
+
 	xive_do_source_eoi(xc->hw_ipi, &xc->ipi_data);
 	xive_do_queue_eoi(xc);
 }
@@ -1342,6 +1409,11 @@
 		xd = irq_desc_get_handler_data(desc);
 
 		/*
+		 * Clear saved_p to indicate that it's no longer pending
+		 */
+		xd->saved_p = false;
+
+		/*
 		 * For LSIs, we EOI, this will cause a resend if it's
 		 * still asserted. Otherwise do an MSI retrigger.
 		 */
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 5b20a67..0ff6b73 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2016,2017 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "xive: " fmt
@@ -115,6 +111,20 @@
 }
 EXPORT_SYMBOL_GPL(xive_native_configure_irq);
 
+static int xive_native_get_irq_config(u32 hw_irq, u32 *target, u8 *prio,
+				      u32 *sw_irq)
+{
+	s64 rc;
+	__be64 vp;
+	__be32 lirq;
+
+	rc = opal_xive_get_irq_config(hw_irq, &vp, prio, &lirq);
+
+	*target = be64_to_cpu(vp);
+	*sw_irq = be32_to_cpu(lirq);
+
+	return rc == 0 ? 0 : -ENXIO;
+}
 
 /* This can be called multiple time to change a queue configuration */
 int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
@@ -235,23 +245,25 @@
 	return of_device_is_compatible(node, "ibm,opal-xive-vc");
 }
 
+static s64 opal_xive_allocate_irq(u32 chip_id)
+{
+	s64 irq = opal_xive_allocate_irq_raw(chip_id);
+
+	/*
+	 * Old versions of skiboot can incorrectly return 0xffffffff to
+	 * indicate no space, fix it up here.
+	 */
+	return irq == 0xffffffff ? OPAL_RESOURCE : irq;
+}
+
 #ifdef CONFIG_SMP
 static int xive_native_get_ipi(unsigned int cpu, struct xive_cpu *xc)
 {
-	struct device_node *np;
-	unsigned int chip_id;
 	s64 irq;
 
-	/* Find the chip ID */
-	np = of_get_cpu_node(cpu, NULL);
-	if (np) {
-		if (of_property_read_u32(np, "ibm,chip-id", &chip_id) < 0)
-			chip_id = 0;
-	}
-
 	/* Allocate an IPI and populate info about it */
 	for (;;) {
-		irq = opal_xive_allocate_irq(chip_id);
+		irq = opal_xive_allocate_irq(xc->chip_id);
 		if (irq == OPAL_BUSY) {
 			msleep(OPAL_BUSY_DELAY_MS);
 			continue;
@@ -446,9 +458,16 @@
 }
 EXPORT_SYMBOL_GPL(xive_native_sync_source);
 
+void xive_native_sync_queue(u32 hw_irq)
+{
+	opal_xive_sync(XIVE_SYNC_QUEUE, hw_irq);
+}
+EXPORT_SYMBOL_GPL(xive_native_sync_queue);
+
 static const struct xive_ops xive_native_ops = {
 	.populate_irq_data	= xive_native_populate_irq_data,
 	.configure_irq		= xive_native_configure_irq,
+	.get_irq_config		= xive_native_get_irq_config,
 	.setup_queue		= xive_native_setup_queue,
 	.cleanup_queue		= xive_native_cleanup_queue,
 	.match			= xive_native_match,
@@ -524,6 +543,9 @@
 }
 EXPORT_SYMBOL_GPL(xive_native_default_eq_shift);
 
+unsigned long xive_tima_os;
+EXPORT_SYMBOL_GPL(xive_tima_os);
+
 bool __init xive_native_init(void)
 {
 	struct device_node *np;
@@ -576,6 +598,14 @@
 	for_each_possible_cpu(cpu)
 		kvmppc_set_xive_tima(cpu, r.start, tima);
 
+	/* Resource 2 is OS window */
+	if (of_address_to_resource(np, 2, &r)) {
+		pr_err("Failed to get thread mgmnt area resource\n");
+		return false;
+	}
+
+	xive_tima_os = r.start;
+
 	/* Grab size of provisionning pages */
 	xive_parse_provisioning(np);
 
@@ -720,3 +750,103 @@
 	return xive_has_single_esc;
 }
 EXPORT_SYMBOL_GPL(xive_native_has_single_escalation);
+
+int xive_native_get_queue_info(u32 vp_id, u32 prio,
+			       u64 *out_qpage,
+			       u64 *out_qsize,
+			       u64 *out_qeoi_page,
+			       u32 *out_escalate_irq,
+			       u64 *out_qflags)
+{
+	__be64 qpage;
+	__be64 qsize;
+	__be64 qeoi_page;
+	__be32 escalate_irq;
+	__be64 qflags;
+	s64 rc;
+
+	rc = opal_xive_get_queue_info(vp_id, prio, &qpage, &qsize,
+				      &qeoi_page, &escalate_irq, &qflags);
+	if (rc) {
+		pr_err("OPAL failed to get queue info for VCPU %d/%d : %lld\n",
+		       vp_id, prio, rc);
+		return -EIO;
+	}
+
+	if (out_qpage)
+		*out_qpage = be64_to_cpu(qpage);
+	if (out_qsize)
+		*out_qsize = be32_to_cpu(qsize);
+	if (out_qeoi_page)
+		*out_qeoi_page = be64_to_cpu(qeoi_page);
+	if (out_escalate_irq)
+		*out_escalate_irq = be32_to_cpu(escalate_irq);
+	if (out_qflags)
+		*out_qflags = be64_to_cpu(qflags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_queue_info);
+
+int xive_native_get_queue_state(u32 vp_id, u32 prio, u32 *qtoggle, u32 *qindex)
+{
+	__be32 opal_qtoggle;
+	__be32 opal_qindex;
+	s64 rc;
+
+	rc = opal_xive_get_queue_state(vp_id, prio, &opal_qtoggle,
+				       &opal_qindex);
+	if (rc) {
+		pr_err("OPAL failed to get queue state for VCPU %d/%d : %lld\n",
+		       vp_id, prio, rc);
+		return -EIO;
+	}
+
+	if (qtoggle)
+		*qtoggle = be32_to_cpu(opal_qtoggle);
+	if (qindex)
+		*qindex = be32_to_cpu(opal_qindex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_queue_state);
+
+int xive_native_set_queue_state(u32 vp_id, u32 prio, u32 qtoggle, u32 qindex)
+{
+	s64 rc;
+
+	rc = opal_xive_set_queue_state(vp_id, prio, qtoggle, qindex);
+	if (rc) {
+		pr_err("OPAL failed to set queue state for VCPU %d/%d : %lld\n",
+		       vp_id, prio, rc);
+		return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_set_queue_state);
+
+bool xive_native_has_queue_state_support(void)
+{
+	return opal_check_token(OPAL_XIVE_GET_QUEUE_STATE) &&
+		opal_check_token(OPAL_XIVE_SET_QUEUE_STATE);
+}
+EXPORT_SYMBOL_GPL(xive_native_has_queue_state_support);
+
+int xive_native_get_vp_state(u32 vp_id, u64 *out_state)
+{
+	__be64 state;
+	s64 rc;
+
+	rc = opal_xive_get_vp_state(vp_id, &state);
+	if (rc) {
+		pr_err("OPAL failed to get vp state for VCPU %d : %lld\n",
+		       vp_id, rc);
+		return -EIO;
+	}
+
+	if (out_state)
+		*out_state = be64_to_cpu(state);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_vp_state);
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index 575db3b..33c1074 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright 2016,2017 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) "xive: " fmt
@@ -20,6 +16,7 @@
 #include <linux/cpumask.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
+#include <linux/libfdt.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -48,7 +45,7 @@
 {
 	struct xive_irq_bitmap *xibm;
 
-	xibm = kzalloc(sizeof(*xibm), GFP_ATOMIC);
+	xibm = kzalloc(sizeof(*xibm), GFP_KERNEL);
 	if (!xibm)
 		return -ENOMEM;
 
@@ -56,6 +53,10 @@
 	xibm->base = base;
 	xibm->count = count;
 	xibm->bitmap = kzalloc(xibm->count, GFP_KERNEL);
+	if (!xibm->bitmap) {
+		kfree(xibm);
+		return -ENOMEM;
+	}
 	list_add(&xibm->list, &xive_irq_bitmaps);
 
 	pr_info("Using IRQ range [%x-%x]", xibm->base,
@@ -214,6 +215,38 @@
 	return 0;
 }
 
+static long plpar_int_get_source_config(unsigned long flags,
+					unsigned long lisn,
+					unsigned long *target,
+					unsigned long *prio,
+					unsigned long *sw_irq)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	pr_devel("H_INT_GET_SOURCE_CONFIG flags=%lx lisn=%lx\n", flags, lisn);
+
+	do {
+		rc = plpar_hcall(H_INT_GET_SOURCE_CONFIG, retbuf, flags, lisn,
+				 target, prio, sw_irq);
+	} while (plpar_busy_delay(rc));
+
+	if (rc) {
+		pr_err("H_INT_GET_SOURCE_CONFIG lisn=%ld failed %ld\n",
+		       lisn, rc);
+		return rc;
+	}
+
+	*target = retbuf[0];
+	*prio   = retbuf[1];
+	*sw_irq = retbuf[2];
+
+	pr_devel("H_INT_GET_SOURCE_CONFIG target=%lx prio=%lx sw_irq=%lx\n",
+		retbuf[0], retbuf[1], retbuf[2]);
+
+	return 0;
+}
+
 static long plpar_int_get_queue_info(unsigned long flags,
 				     unsigned long target,
 				     unsigned long priority,
@@ -397,6 +430,24 @@
 	return rc == 0 ? 0 : -ENXIO;
 }
 
+static int xive_spapr_get_irq_config(u32 hw_irq, u32 *target, u8 *prio,
+				     u32 *sw_irq)
+{
+	long rc;
+	unsigned long h_target;
+	unsigned long h_prio;
+	unsigned long h_sw_irq;
+
+	rc = plpar_int_get_source_config(0, hw_irq, &h_target, &h_prio,
+					 &h_sw_irq);
+
+	*target = h_target;
+	*prio = h_prio;
+	*sw_irq = h_sw_irq;
+
+	return rc == 0 ? 0 : -ENXIO;
+}
+
 /* This can be called multiple time to change a queue configuration */
 static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio,
 				   __be32 *qpage, u32 order)
@@ -589,6 +640,7 @@
 static const struct xive_ops xive_spapr_ops = {
 	.populate_irq_data	= xive_spapr_populate_irq_data,
 	.configure_irq		= xive_spapr_configure_irq,
+	.get_irq_config		= xive_spapr_get_irq_config,
 	.setup_queue		= xive_spapr_setup_queue,
 	.cleanup_queue		= xive_spapr_cleanup_queue,
 	.match			= xive_spapr_match,
@@ -663,6 +715,55 @@
 	return true;
 }
 
+static const u8 *get_vec5_feature(unsigned int index)
+{
+	unsigned long root, chosen;
+	int size;
+	const u8 *vec5;
+
+	root = of_get_flat_dt_root();
+	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
+	if (chosen == -FDT_ERR_NOTFOUND)
+		return NULL;
+
+	vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
+	if (!vec5)
+		return NULL;
+
+	if (size <= index)
+		return NULL;
+
+	return vec5 + index;
+}
+
+static bool xive_spapr_disabled(void)
+{
+	const u8 *vec5_xive;
+
+	vec5_xive = get_vec5_feature(OV5_INDX(OV5_XIVE_SUPPORT));
+	if (vec5_xive) {
+		u8 val;
+
+		val = *vec5_xive & OV5_FEAT(OV5_XIVE_SUPPORT);
+		switch (val) {
+		case OV5_FEAT(OV5_XIVE_EITHER):
+		case OV5_FEAT(OV5_XIVE_LEGACY):
+			break;
+		case OV5_FEAT(OV5_XIVE_EXPLOIT):
+			/* Hypervisor only supports XIVE */
+			if (xive_cmdline_disabled)
+				pr_warn("WARNING: Ignoring cmdline option xive=off\n");
+			return false;
+		default:
+			pr_warn("%s: Unknown xive support option: 0x%x\n",
+				__func__, val);
+			break;
+		}
+	}
+
+	return xive_cmdline_disabled;
+}
+
 bool __init xive_spapr_init(void)
 {
 	struct device_node *np;
@@ -675,7 +776,7 @@
 	const __be32 *reg;
 	int i;
 
-	if (xive_cmdline_disabled)
+	if (xive_spapr_disabled())
 		return false;
 
 	pr_devel("%s()\n", __func__);
diff --git a/arch/powerpc/sysdev/xive/xive-internal.h b/arch/powerpc/sysdev/xive/xive-internal.h
index f34abed..59cd366 100644
--- a/arch/powerpc/sysdev/xive/xive-internal.h
+++ b/arch/powerpc/sysdev/xive/xive-internal.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright 2016,2017 IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 #ifndef __XIVE_INTERNAL_H
 #define __XIVE_INTERNAL_H
@@ -37,6 +33,8 @@
 struct xive_ops {
 	int	(*populate_irq_data)(u32 hw_irq, struct xive_irq_data *data);
 	int 	(*configure_irq)(u32 hw_irq, u32 target, u8 prio, u32 sw_irq);
+	int	(*get_irq_config)(u32 hw_irq, u32 *target, u8 *prio,
+				  u32 *sw_irq);
 	int	(*setup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio);
 	void	(*cleanup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio);
 	void	(*setup_cpu)(unsigned int cpu, struct xive_cpu *xc);
diff --git a/arch/powerpc/tools/checkpatch.sh b/arch/powerpc/tools/checkpatch.sh
index 1fad3fb..3ce5c09 100755
--- a/arch/powerpc/tools/checkpatch.sh
+++ b/arch/powerpc/tools/checkpatch.sh
@@ -19,4 +19,5 @@
 	--ignore GLOBAL_INITIALISERS \
 	--ignore LINE_SPACING \
 	--ignore MULTIPLE_ASSIGNMENTS \
+	--ignore DT_SPLIT_BINDING_PATCH \
 	$@
diff --git a/arch/powerpc/tools/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh
index ec2d5c8..2b4e959 100755
--- a/arch/powerpc/tools/relocs_check.sh
+++ b/arch/powerpc/tools/relocs_check.sh
@@ -1,11 +1,8 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
 
 # Copyright © 2015 IBM 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; either version
-# 2 of the License, or (at your option) any later version.
 
 # This script checks the relocations of a vmlinux for "suspicious"
 # relocations.
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index 1bc3abb..f142570 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -1,14 +1,23 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for xmon
 
-subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+# Disable clang warning for using setjmp without setjmp.h header
+subdir-ccflags-y := $(call cc-disable-warning, builtin-requires-header)
 
 GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
 UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
 
 # Disable ftrace for the entire directory
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst -mno-sched-epilog,,$(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS)))
+KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))
+
+ifdef CONFIG_CC_IS_CLANG
+# 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)
 
diff --git a/arch/powerpc/xmon/ansidecl.h b/arch/powerpc/xmon/ansidecl.h
index c9b9f09..17a85a5 100644
--- a/arch/powerpc/xmon/ansidecl.h
+++ b/arch/powerpc/xmon/ansidecl.h
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* ANSI and traditional C compatibility macros
    Copyright 1991, 1992 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
 
-This program is free software; you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 2 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program; if not, write to the Free Software
-Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  */
+ */
 
 /* ANSI and traditional C compatibility macros
 
diff --git a/arch/powerpc/xmon/dis-asm.h b/arch/powerpc/xmon/dis-asm.h
index be3533b..c4d246e 100644
--- a/arch/powerpc/xmon/dis-asm.h
+++ b/arch/powerpc/xmon/dis-asm.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _POWERPC_XMON_DIS_ASM_H
 #define _POWERPC_XMON_DIS_ASM_H
 /*
  * Copyright (C) 2006 Michael Ellerman, IBM 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; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 extern void print_address (unsigned long memaddr);
diff --git a/arch/powerpc/xmon/nonstdio.c b/arch/powerpc/xmon/nonstdio.c
index d001234..5c1a509 100644
--- a/arch/powerpc/xmon/nonstdio.c
+++ b/arch/powerpc/xmon/nonstdio.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 1996-2005 Paul Mackerras.
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 #include <linux/string.h>
 #include <asm/udbg.h>
diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c
index 9deea5e..75fa982 100644
--- a/arch/powerpc/xmon/ppc-dis.c
+++ b/arch/powerpc/xmon/ppc-dis.c
@@ -1,22 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* ppc-dis.c -- Disassemble PowerPC instructions
    Copyright (C) 1994-2016 Free Software Foundation, Inc.
    Written by Ian Lance Taylor, Cygnus Support
 
 This file is part of GDB, GAS, and the GNU binutils.
 
-GDB, GAS, and the GNU binutils are free software; you can redistribute
-them and/or modify them under the terms of the GNU General Public
-License as published by the Free Software Foundation; either version
-2, or (at your option) any later version.
-
-GDB, GAS, and the GNU binutils are distributed in the hope that they
-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 file; see the file COPYING.  If not, write to the Free
-Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
+ */
 
 #include <asm/cputable.h>
 #include <asm/cpu_has_feature.h>
@@ -158,7 +147,7 @@
     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),
+		| 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 ac2b55b..dfb8081 100644
--- a/arch/powerpc/xmon/ppc-opc.c
+++ b/arch/powerpc/xmon/ppc-opc.c
@@ -1,23 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* ppc-opc.c -- PowerPC opcode list
    Copyright (C) 1994-2016 Free Software Foundation, Inc.
    Written by Ian Lance Taylor, Cygnus Support
 
    This file is part of GDB, GAS, and the GNU binutils.
 
-   GDB, GAS, and the GNU binutils are free software; you can redistribute
-   them and/or modify them under the terms of the GNU General Public
-   License as published by the Free Software Foundation; either version
-   2, or (at your option) any later version.
-
-   GDB, GAS, and the GNU binutils are distributed in the hope that they
-   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 file; see the file COPYING.  If not, write to the Free
-   Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA
-   02110-1301, USA.  */
+ */
 
 #include <linux/stddef.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/xmon/spu-dis.c b/arch/powerpc/xmon/spu-dis.c
index 4cbc7da..4b0a4e6 100644
--- a/arch/powerpc/xmon/spu-dis.c
+++ b/arch/powerpc/xmon/spu-dis.c
@@ -1,22 +1,11 @@
+// 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.
 
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 2 of the License, or
-   (at your option) any later version.
-
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-
-   You should have received a copy of the GNU General Public License along
-   with this program; if not, write to the Free Software Foundation, Inc.,
-   51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
+ */
 
 #include <linux/string.h>
 #include "nonstdio.h"
diff --git a/arch/powerpc/xmon/spu-insns.h b/arch/powerpc/xmon/spu-insns.h
index 99dc452..7e1126a 100644
--- a/arch/powerpc/xmon/spu-insns.h
+++ b/arch/powerpc/xmon/spu-insns.h
@@ -1,22 +1,11 @@
+/* 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.
 
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 2 of the License, or
-   (at your option) any later version.
-
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-
-   You should have received a copy of the GNU General Public License
-   along with this program; if not, write to the Free Software Foundation,
-   Inc., 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
+ */
 
 /* SPU Opcode Table
 
diff --git a/arch/powerpc/xmon/spu-opc.c b/arch/powerpc/xmon/spu-opc.c
index 7d37597..6d8197c 100644
--- a/arch/powerpc/xmon/spu-opc.c
+++ b/arch/powerpc/xmon/spu-opc.c
@@ -1,22 +1,11 @@
+// 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.
 
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 2 of the License, or
-   (at your option) any later version.
-
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-
-   You should have received a copy of the GNU General Public License along
-   with this program; if not, write to the Free Software Foundation, Inc.,
-   51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
+ */
 
 #include <linux/kernel.h>
 #include <linux/bug.h>
diff --git a/arch/powerpc/xmon/spu.h b/arch/powerpc/xmon/spu.h
index c761fc8..2d13b1a 100644
--- a/arch/powerpc/xmon/spu.h
+++ b/arch/powerpc/xmon/spu.h
@@ -1,22 +1,11 @@
+/* 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.
 
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 2 of the License, or
-   (at your option) any later version.
-
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-
-   You should have received a copy of the GNU General Public License
-   along with this program; if not, write to the Free Software Foundation,
-   Inc., 51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
+ */
 
 
 /* These two enums are from rel_apu/common/spu_asm_format.h */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 4264aed..d83364e 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Routines providing a simple monitor for use on the PowerMac.
  *
  * Copyright (C) 1996-2005 Paul Mackerras.
  * Copyright (C) 2001 PPC64 Team, IBM Corp
  * Copyrignt (C) 2006 Michael Ellerman, IBM Corp
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -75,8 +71,12 @@
 #define xmon_owner 0
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_PPC_PSERIES
+static int set_indicator_token = RTAS_UNKNOWN_SERVICE;
+#endif
 static unsigned long in_xmon __read_mostly = 0;
 static int xmon_on = IS_ENABLED(CONFIG_XMON_DEFAULT);
+static bool xmon_is_ro = IS_ENABLED(CONFIG_XMON_DEFAULT_RO_MODE);
 
 static unsigned long adrs;
 static int size = 1;
@@ -199,6 +199,8 @@
 #define GETWORD(v)	(((v)[0] << 24) + ((v)[1] << 16) + ((v)[2] << 8) + (v)[3])
 #endif
 
+static const char *xmon_ro_msg = "Operation disabled: xmon in read-only mode\n";
+
 static char *help_string = "\
 Commands:\n\
   b	show breakpoints\n\
@@ -273,7 +275,7 @@
   X	exit monitor and don't recover\n"
 #if defined(CONFIG_PPC64) && !defined(CONFIG_PPC_BOOK3E)
 "  u	dump segment table or SLB\n"
-#elif defined(CONFIG_PPC_STD_MMU_32)
+#elif defined(CONFIG_PPC_BOOK3S_32)
 "  u	dump segment registers\n"
 #elif defined(CONFIG_44x) || defined(CONFIG_PPC_BOOK3E)
 "  u	dump TLB\n"
@@ -358,7 +360,6 @@
 #ifdef CONFIG_PPC_PSERIES
 	/* Since this can't be a module, args should end up below 4GB. */
 	static struct rtas_args args;
-	int token;
 
 	/*
 	 * At this point we have got all the cpus we can into
@@ -367,11 +368,11 @@
 	 * If we did try to take rtas.lock there would be a
 	 * real possibility of deadlock.
 	 */
-	token = rtas_token("set-indicator");
-	if (token == RTAS_UNKNOWN_SERVICE)
+	if (set_indicator_token == RTAS_UNKNOWN_SERVICE)
 		return;
 
-	rtas_call_unlocked(&args, token, 3, 1, NULL, SURVEILLANCE_TOKEN, 0, 0);
+	rtas_call_unlocked(&args, set_indicator_token, 3, 1, NULL,
+			   SURVEILLANCE_TOKEN, 0, 0);
 
 #endif /* CONFIG_PPC_PSERIES */
 }
@@ -464,8 +465,10 @@
 	local_irq_save(flags);
 	hard_irq_disable();
 
-	tracing_enabled = tracing_is_on();
-	tracing_off();
+	if (!fromipi) {
+		tracing_enabled = tracing_is_on();
+		tracing_off();
+	}
 
 	bp = in_breakpoint_table(regs->nip, &offset);
 	if (bp != NULL) {
@@ -987,6 +990,10 @@
 				memlocate();
 				break;
 			case 'z':
+				if (xmon_is_ro) {
+					printf(xmon_ro_msg);
+					break;
+				}
 				memzcan();
 				break;
 			case 'i':
@@ -1040,6 +1047,10 @@
 			set_lpp_cmd();
 			break;
 		case 'b':
+			if (xmon_is_ro) {
+				printf(xmon_ro_msg);
+				break;
+			}
 			bpt_cmds();
 			break;
 		case 'C':
@@ -1053,12 +1064,16 @@
 			bootcmds();
 			break;
 		case 'p':
+			if (xmon_is_ro) {
+				printf(xmon_ro_msg);
+				break;
+			}
 			proccall();
 			break;
 		case 'P':
 			show_tasks();
 			break;
-#ifdef CONFIG_PPC_STD_MMU
+#ifdef CONFIG_PPC_BOOK3S
 		case 'u':
 			dump_segments();
 			break;
@@ -1775,6 +1790,11 @@
 static void
 write_spr(int n, unsigned long val)
 {
+	if (xmon_is_ro) {
+		printf(xmon_ro_msg);
+		return;
+	}
+
 	if (setjmp(bus_error_jmp) == 0) {
 		catch_spr_faults = 1;
 		sync();
@@ -2014,6 +2034,12 @@
 	char *p, *q;
 
 	n = 0;
+
+	if (xmon_is_ro) {
+		printf(xmon_ro_msg);
+		return n;
+	}
+
 	if (setjmp(bus_error_jmp) == 0) {
 		catch_memory_errors = 1;
 		sync();
@@ -2378,25 +2404,33 @@
 	DUMP(p, cpu_start, "%#-*x");
 	DUMP(p, kexec_state, "%#-*x");
 #ifdef CONFIG_PPC_BOOK3S_64
-	for (i = 0; i < SLB_NUM_BOLTED; i++) {
-		u64 esid, vsid;
+	if (!early_radix_enabled()) {
+		for (i = 0; i < SLB_NUM_BOLTED; i++) {
+			u64 esid, vsid;
 
-		if (!p->slb_shadow_ptr)
-			continue;
+			if (!p->slb_shadow_ptr)
+				continue;
 
-		esid = be64_to_cpu(p->slb_shadow_ptr->save_area[i].esid);
-		vsid = be64_to_cpu(p->slb_shadow_ptr->save_area[i].vsid);
+			esid = be64_to_cpu(p->slb_shadow_ptr->save_area[i].esid);
+			vsid = be64_to_cpu(p->slb_shadow_ptr->save_area[i].vsid);
 
-		if (esid || vsid) {
-			printf(" %-*s[%d] = 0x%016llx 0x%016llx\n",
-			       22, "slb_shadow", i, esid, vsid);
+			if (esid || vsid) {
+				printf(" %-*s[%d] = 0x%016llx 0x%016llx\n",
+				       22, "slb_shadow", i, esid, vsid);
+			}
+		}
+		DUMP(p, vmalloc_sllp, "%#-*x");
+		DUMP(p, stab_rr, "%#-*x");
+		DUMP(p, slb_used_bitmap, "%#-*x");
+		DUMP(p, slb_kern_bitmap, "%#-*x");
+
+		if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) {
+			DUMP(p, slb_cache_ptr, "%#-*x");
+			for (i = 0; i < SLB_CACHE_ENTRIES; i++)
+				printf(" %-*s[%d] = 0x%016x\n",
+				       22, "slb_cache", i, p->slb_cache[i]);
 		}
 	}
-	DUMP(p, vmalloc_sllp, "%#-*x");
-	DUMP(p, slb_cache_ptr, "%#-*x");
-	for (i = 0; i < SLB_CACHE_ENTRIES; i++)
-		printf(" %-*s[%d] = 0x%016x\n",
-		       22, "slb_cache", i, p->slb_cache[i]);
 
 	DUMP(p, rfi_flush_fallback_area, "%-*px");
 #endif
@@ -2412,14 +2446,20 @@
 	DUMP(p, __current, "%-*px");
 	DUMP(p, kstack, "%#-*llx");
 	printf(" %-*s = 0x%016llx\n", 25, "kstack_base", p->kstack & ~(THREAD_SIZE - 1));
-	DUMP(p, stab_rr, "%#-*llx");
+#ifdef CONFIG_STACKPROTECTOR
+	DUMP(p, canary, "%#-*lx");
+#endif
 	DUMP(p, saved_r1, "%#-*llx");
+#ifdef CONFIG_PPC_BOOK3E
 	DUMP(p, trap_save, "%#-*x");
+#endif
 	DUMP(p, irq_soft_mask, "%#-*x");
 	DUMP(p, irq_happened, "%#-*x");
-	DUMP(p, io_sync, "%#-*x");
+#ifdef CONFIG_MMIOWB
+	DUMP(p, mmiowb_state.nesting_count, "%#-*x");
+	DUMP(p, mmiowb_state.mmiowb_pending, "%#-*x");
+#endif
 	DUMP(p, irq_work_pending, "%#-*x");
-	DUMP(p, nap_state_lost, "%#-*x");
 	DUMP(p, sprg_vdso, "%#-*llx");
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -2427,28 +2467,29 @@
 #endif
 
 #ifdef CONFIG_PPC_POWERNV
-	DUMP(p, core_idle_state_ptr, "%-*px");
-	DUMP(p, thread_idle_state, "%#-*x");
-	DUMP(p, thread_mask, "%#-*x");
-	DUMP(p, subcore_sibling_mask, "%#-*x");
-	DUMP(p, requested_psscr, "%#-*llx");
-	DUMP(p, stop_sprs.pid, "%#-*llx");
-	DUMP(p, stop_sprs.ldbar, "%#-*llx");
-	DUMP(p, stop_sprs.fscr, "%#-*llx");
-	DUMP(p, stop_sprs.hfscr, "%#-*llx");
-	DUMP(p, stop_sprs.mmcr1, "%#-*llx");
-	DUMP(p, stop_sprs.mmcr2, "%#-*llx");
-	DUMP(p, stop_sprs.mmcra, "%#-*llx");
-	DUMP(p, dont_stop.counter, "%#-*x");
+	DUMP(p, idle_state, "%#-*lx");
+	if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) {
+		DUMP(p, thread_idle_state, "%#-*x");
+		DUMP(p, subcore_sibling_mask, "%#-*x");
+	} else {
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		DUMP(p, requested_psscr, "%#-*llx");
+		DUMP(p, dont_stop.counter, "%#-*x");
+#endif
+	}
 #endif
 
 	DUMP(p, accounting.utime, "%#-*lx");
 	DUMP(p, accounting.stime, "%#-*lx");
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 	DUMP(p, accounting.utime_scaled, "%#-*lx");
+#endif
 	DUMP(p, accounting.starttime, "%#-*lx");
 	DUMP(p, accounting.starttime_user, "%#-*lx");
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 	DUMP(p, accounting.startspurr, "%#-*lx");
 	DUMP(p, accounting.utime_sspurr, "%#-*lx");
+#endif
 	DUMP(p, accounting.steal_time, "%#-*lx");
 #undef DUMP
 
@@ -2493,13 +2534,16 @@
 static void dump_one_xive(int cpu)
 {
 	unsigned int hwid = get_hard_smp_processor_id(cpu);
+	bool hv = cpu_has_feature(CPU_FTR_HVMODE);
 
-	opal_xive_dump(XIVE_DUMP_TM_HYP, hwid);
-	opal_xive_dump(XIVE_DUMP_TM_POOL, hwid);
-	opal_xive_dump(XIVE_DUMP_TM_OS, hwid);
-	opal_xive_dump(XIVE_DUMP_TM_USER, hwid);
-	opal_xive_dump(XIVE_DUMP_VP, hwid);
-	opal_xive_dump(XIVE_DUMP_EMU_STATE, hwid);
+	if (hv) {
+		opal_xive_dump(XIVE_DUMP_TM_HYP, hwid);
+		opal_xive_dump(XIVE_DUMP_TM_POOL, hwid);
+		opal_xive_dump(XIVE_DUMP_TM_OS, hwid);
+		opal_xive_dump(XIVE_DUMP_TM_USER, hwid);
+		opal_xive_dump(XIVE_DUMP_VP, hwid);
+		opal_xive_dump(XIVE_DUMP_EMU_STATE, hwid);
+	}
 
 	if (setjmp(bus_error_jmp) != 0) {
 		catch_memory_errors = 0;
@@ -2528,16 +2572,28 @@
 		dump_one_xive(cpu);
 }
 
-static void dump_one_xive_irq(u32 num)
+static void dump_one_xive_irq(u32 num, struct irq_data *d)
 {
-	s64 rc;
-	__be64 vp;
-	u8 prio;
-	__be32 lirq;
+	xmon_xive_get_irq_config(num, d);
+}
 
-	rc = opal_xive_get_irq_config(num, &vp, &prio, &lirq);
-	xmon_printf("IRQ 0x%x config: vp=0x%llx prio=%d lirq=0x%x (rc=%lld)\n",
-		    num, be64_to_cpu(vp), prio, be32_to_cpu(lirq), rc);
+static void dump_all_xive_irq(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_data *d = irq_desc_get_irq_data(desc);
+		unsigned int hwirq;
+
+		if (!d)
+			continue;
+
+		hwirq = (unsigned int)irqd_to_hwirq(d);
+		/* IPIs are special (HW number 0) */
+		if (hwirq)
+			dump_one_xive_irq(hwirq, d);
+	}
 }
 
 static void dump_xives(void)
@@ -2556,7 +2612,9 @@
 		return;
 	} else if (c == 'i') {
 		if (scanhex(&num))
-			dump_one_xive_irq(num);
+			dump_one_xive_irq(num, NULL);
+		else
+			dump_all_xive_irq();
 		return;
 	}
 
@@ -2779,7 +2837,7 @@
 	xmon_print_symbol(addr, "\t# ", "");
 }
 
-void
+static void
 dump_log_buf(void)
 {
 	struct kmsg_dumper dumper = { .active = 1 };
@@ -2868,9 +2926,17 @@
 	scanhex((void *)&mcount);
 	switch( cmd ){
 	case 'm':
+		if (xmon_is_ro) {
+			printf(xmon_ro_msg);
+			break;
+		}
 		memmove((void *)mdest, (void *)msrc, mcount);
 		break;
 	case 's':
+		if (xmon_is_ro) {
+			printf(xmon_ro_msg);
+			break;
+		}
 		memset((void *)mdest, mval, mcount);
 		break;
 	case 'd':
@@ -2980,23 +3046,25 @@
 
 	printf("%px %016lx %6d %6d %c %2d %s\n", tsk,
 		tsk->thread.ksp,
-		tsk->pid, tsk->parent->pid,
-		state, task_thread_info(tsk)->cpu,
+		tsk->pid, rcu_dereference(tsk->parent)->pid,
+		state, task_cpu(tsk),
 		tsk->comm);
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
-void format_pte(void *ptep, unsigned long pte)
+static void format_pte(void *ptep, unsigned long pte)
 {
+	pte_t entry = __pte(pte);
+
 	printf("ptep @ 0x%016lx = 0x%016lx\n", (unsigned long)ptep, pte);
 	printf("Maps physical address = 0x%016lx\n", pte & PTE_RPN_MASK);
 
 	printf("Flags = %s%s%s%s%s\n",
-	       (pte & _PAGE_ACCESSED) ? "Accessed " : "",
-	       (pte & _PAGE_DIRTY)    ? "Dirty " : "",
-	       (pte & _PAGE_READ)     ? "Read " : "",
-	       (pte & _PAGE_WRITE)    ? "Write " : "",
-	       (pte & _PAGE_EXEC)     ? "Exec " : "");
+	       pte_young(entry) ? "Accessed " : "",
+	       pte_dirty(entry) ? "Dirty " : "",
+	       pte_read(entry)  ? "Read " : "",
+	       pte_write(entry) ? "Write " : "",
+	       pte_exec(entry)  ? "Exec " : "");
 }
 
 static void show_pte(unsigned long addr)
@@ -3043,7 +3111,7 @@
 
 	printf("pgd  @ 0x%px\n", pgdir);
 
-	if (pgd_huge(*pgdp)) {
+	if (pgd_is_leaf(*pgdp)) {
 		format_pte(pgdp, pgd_val(*pgdp));
 		return;
 	}
@@ -3056,7 +3124,7 @@
 		return;
 	}
 
-	if (pud_huge(*pudp)) {
+	if (pud_is_leaf(*pudp)) {
 		format_pte(pudp, pud_val(*pudp));
 		return;
 	}
@@ -3070,7 +3138,7 @@
 		return;
 	}
 
-	if (pmd_huge(*pmdp)) {
+	if (pmd_is_leaf(*pmdp)) {
 		format_pte(pmdp, pmd_val(*pmdp));
 		return;
 	}
@@ -3479,14 +3547,14 @@
 }
 #endif
 
-#ifdef CONFIG_PPC_STD_MMU_32
+#ifdef CONFIG_PPC_BOOK3S_32
 void dump_segments(void)
 {
 	int i;
 
 	printf("sr0-15 =");
 	for (i = 0; i < 16; ++i)
-		printf(" %x", mfsrin(i));
+		printf(" %x", mfsrin(i << 28));
 	printf("\n");
 }
 #endif
@@ -3672,6 +3740,14 @@
 		__debugger_iabr_match = xmon_iabr_match;
 		__debugger_break_match = xmon_break_match;
 		__debugger_fault_handler = xmon_fault_handler;
+
+#ifdef CONFIG_PPC_PSERIES
+		/*
+		 * Get the token here to avoid trying to get a lock
+		 * during the crash, causing a deadlock.
+		 */
+		set_indicator_token = rtas_token("set-indicator");
+#endif
 	} else {
 		__debugger = NULL;
 		__debugger_ipi = NULL;
@@ -3770,6 +3846,14 @@
 	} else if (strncmp(p, "on", 2) == 0) {
 		xmon_init(1);
 		xmon_on = 1;
+	} else if (strncmp(p, "rw", 2) == 0) {
+		xmon_init(1);
+		xmon_on = 1;
+		xmon_is_ro = false;
+	} else if (strncmp(p, "ro", 2) == 0) {
+		xmon_init(1);
+		xmon_on = 1;
+		xmon_is_ro = true;
 	} else if (strncmp(p, "off", 3) == 0)
 		xmon_on = 0;
 	else
@@ -4017,6 +4101,7 @@
 		subcmd = inchar();
 		if (isxdigit(subcmd) || subcmd == '\n')
 			termch = subcmd;
+		/* fall through */
 	case 'f':
 		scanhex(&num);
 		if (num >= XMON_NUM_SPUS || !spu_info[num].spu) {