Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:

 - UEFI boot and runtime services support for ARM from Ard Biesheuvel
   and Roy Franz.

 - DT compatibility with old atags booting protocol for Nokia N900
   devices from Ivaylo Dimitrov.

 - PSCI firmware interface using new arm-smc calling convention from
   Jens Wiklander.

 - Runtime patching for udiv/sdiv instructions for ARMv7 CPUs that
   support these instructions from Nicolas Pitre.

 - L2x0 cache updates from Dirk B and Linus Walleij.

 - Randconfig fixes from Arnd Bergmann.

 - ARMv7M (nommu) updates from Ezequiel Garcia

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (34 commits)
  ARM: 8481/2: drivers: psci: replace psci firmware calls
  ARM: 8480/2: arm64: add implementation for arm-smccc
  ARM: 8479/2: add implementation for arm-smccc
  ARM: 8478/2: arm/arm64: add arm-smccc
  ARM: 8494/1: mm: Enable PXN when running non-LPAE kernel on LPAE processor
  ARM: 8496/1: OMAP: RX51: save ATAGS data in the early boot stage
  ARM: 8495/1: ATAGS: move save_atags() to arch/arm/include/asm/setup.h
  ARM: 8452/3: PJ4: make coprocessor access sequences buildable in Thumb2 mode
  ARM: 8482/1: l2x0: make it possible to disable outer sync from DT
  ARM: 8488/1: Make IPI_CPU_BACKTRACE a "non-secure" SGI
  ARM: 8487/1: Remove IPI_CALL_FUNC_SINGLE
  ARM: 8485/1: cpuidle: remove cpu parameter from the cpuidle_ops suspend hook
  ARM: 8484/1: Documentation: l2c2x0: Mention separate controllers explicitly
  ARM: 8483/1: Documentation: l2c: Rename l2cc to l2c2x0
  ARM: 8477/1: runtime patch udiv/sdiv instructions into __aeabi_{u}idiv()
  ARM: 8476/1: VDSO: use PTR_ERR_OR_ZERO for vma check
  ARM: 8453/2: proc-v7.S: don't locate temporary stack space in .text section
  ARM: add UEFI stub support
  ARM: wire up UEFI init and runtime support
  ARM: only consider memblocks with NOMAP cleared for linear mapping
  ...

42 files changed, 786 insertions, 176 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 688dc7b0d951..b0e7ff176028 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -20,6 +20,7 @@ config ARM
 	select GENERIC_ALLOCATOR
 	select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -33,10 +34,11 @@ config ARM
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
-	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32
-	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
+	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARM_SMCCC if CPU_V7
 	select HAVE_BPF_JIT
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CONTEXT_TRACKING
@@ -45,7 +47,7 @@ config ARM
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS if MMU
-	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32
+	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
 	select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
 	select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL)
@@ -802,6 +804,7 @@ config ARCH_VIRT
 	bool "Dummy Virtual Machine" if ARCH_MULTI_V7
 	select ARM_AMBA
 	select ARM_GIC
+	select ARM_GIC_V2M if PCI_MSI
 	select ARM_GIC_V3
 	select ARM_PSCI
 	select HAVE_ARM_ARCH_TIMER
@@ -1425,7 +1428,7 @@ config BIG_LITTLE
 
 config BL_SWITCHER
 	bool "big.LITTLE switcher support"
-	depends on BIG_LITTLE && MCPM && HOTPLUG_CPU
+	depends on BIG_LITTLE && MCPM && HOTPLUG_CPU && ARM_GIC
 	select ARM_CPU_SUSPEND
 	select CPU_PM
 	help
@@ -1484,7 +1487,7 @@ config HOTPLUG_CPU
 
 config ARM_PSCI
 	bool "Support for the ARM Power State Coordination Interface (PSCI)"
-	depends on CPU_V7
+	depends on HAVE_ARM_SMCCC
 	select ARM_PSCI_FW
 	help
 	  Say Y here if you want Linux to communicate with system firmware
@@ -1607,6 +1610,24 @@ config THUMB2_AVOID_R_ARM_THM_JUMP11
 config ARM_ASM_UNIFIED
 	bool
 
+config ARM_PATCH_IDIV
+	bool "Runtime patch udiv/sdiv instructions into __aeabi_{u}idiv()"
+	depends on CPU_32v7 && !XIP_KERNEL
+	default y
+	help
+	  The ARM compiler inserts calls to __aeabi_idiv() and
+	  __aeabi_uidiv() when it needs to perform division on signed
+	  and unsigned integers. Some v7 CPUs have support for the sdiv
+	  and udiv instructions that can be used to implement those
+	  functions.
+
+	  Enabling this option allows the kernel to modify itself to
+	  replace the first two instructions of these library functions
+	  with the sdiv or udiv plus "bx lr" instructions when the CPU
+	  it is running on supports them. Typically this will be faster
+	  and less power intensive than running the original library
+	  code to do integer division.
+
 config AEABI
 	bool "Use the ARM EABI to compile the kernel"
 	help
@@ -2043,6 +2064,25 @@ config AUTO_ZRELADDR
 	  0xf8000000. This assumes the zImage being placed in the first 128MB
 	  from start of memory.
 
+config EFI_STUB
+	bool
+
+config EFI
+	bool "UEFI runtime support"
+	depends on OF && !CPU_BIG_ENDIAN && MMU && AUTO_ZRELADDR && !XIP_KERNEL
+	select UCS2_STRING
+	select EFI_PARAMS_FROM_FDT
+	select EFI_STUB
+	select EFI_ARMSTUB
+	select EFI_RUNTIME_WRAPPERS
+	---help---
+	  This option provides support for runtime services provided
+	  by UEFI firmware (such as non-volatile variables, realtime
+	  clock, and platform reset). A UEFI stub is also provided to
+	  allow the kernel to be booted as an EFI application. This
+	  is only useful for kernels that may run on systems that have
+	  UEFI firmware.
+
 endmenu
 
 menu "CPU Power Management"
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 3f9a9ebc77c3..4c23a68a0917 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -167,9 +167,11 @@ if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \
 	false; \
 fi
 
+efi-obj-$(CONFIG_EFI_STUB) := $(objtree)/drivers/firmware/efi/libstub/lib.a
+
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
 		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) \
-		$(bswapsdi2) FORCE
+		$(bswapsdi2) $(efi-obj-y) FORCE
 	@$(check_for_multiple_zreladdr)
 	$(call if_changed,ld)
 	@$(check_for_bad_syms)
diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S
new file mode 100644
index 000000000000..9d5dc4fda3c1
--- /dev/null
+++ b/arch/arm/boot/compressed/efi-header.S
@@ -0,0 +1,130 @@
+/*
+ * Copyright (C) 2013-2015 Linaro Ltd
+ * Authors: Roy Franz <roy.franz@linaro.org>
+ *          Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+		.macro	__nop
+#ifdef CONFIG_EFI_STUB
+		@ This is almost but not quite a NOP, since it does clobber the
+		@ condition flags. But it is the best we can do for EFI, since
+		@ PE/COFF expects the magic string "MZ" at offset 0, while the
+		@ ARM/Linux boot protocol expects an executable instruction
+		@ there.
+		.inst	'M' | ('Z' << 8) | (0x1310 << 16)   @ tstne r0, #0x4d000
+#else
+		mov	r0, r0
+#endif
+		.endm
+
+		.macro	__EFI_HEADER
+#ifdef CONFIG_EFI_STUB
+		b	__efi_start
+
+		.set	start_offset, __efi_start - start
+		.org	start + 0x3c
+		@
+		@ The PE header can be anywhere in the file, but for
+		@ simplicity we keep it together with the MSDOS header
+		@ The offset to the PE/COFF header needs to be at offset
+		@ 0x3C in the MSDOS header.
+		@ The only 2 fields of the MSDOS header that are used are this
+		@ PE/COFF offset, and the "MZ" bytes at offset 0x0.
+		@
+		.long	pe_header - start	@ Offset to the PE header.
+
+pe_header:
+		.ascii	"PE\0\0"
+
+coff_header:
+		.short	0x01c2			@ ARM or Thumb
+		.short	2			@ nr_sections
+		.long	0 			@ TimeDateStamp
+		.long	0			@ PointerToSymbolTable
+		.long	1			@ NumberOfSymbols
+		.short	section_table - optional_header
+						@ SizeOfOptionalHeader
+		.short	0x306			@ Characteristics.
+						@ IMAGE_FILE_32BIT_MACHINE |
+						@ IMAGE_FILE_DEBUG_STRIPPED |
+						@ IMAGE_FILE_EXECUTABLE_IMAGE |
+						@ IMAGE_FILE_LINE_NUMS_STRIPPED
+
+optional_header:
+		.short	0x10b			@ PE32 format
+		.byte	0x02			@ MajorLinkerVersion
+		.byte	0x14			@ MinorLinkerVersion
+		.long	_end - __efi_start	@ SizeOfCode
+		.long	0			@ SizeOfInitializedData
+		.long	0			@ SizeOfUninitializedData
+		.long	efi_stub_entry - start	@ AddressOfEntryPoint
+		.long	start_offset		@ BaseOfCode
+		.long	0			@ data
+
+extra_header_fields:
+		.long	0			@ ImageBase
+		.long	0x200			@ SectionAlignment
+		.long	0x200			@ FileAlignment
+		.short	0			@ MajorOperatingSystemVersion
+		.short	0			@ MinorOperatingSystemVersion
+		.short	0			@ MajorImageVersion
+		.short	0			@ MinorImageVersion
+		.short	0			@ MajorSubsystemVersion
+		.short	0			@ MinorSubsystemVersion
+		.long	0			@ Win32VersionValue
+
+		.long	_end - start		@ SizeOfImage
+		.long	start_offset		@ SizeOfHeaders
+		.long	0			@ CheckSum
+		.short	0xa			@ Subsystem (EFI application)
+		.short	0			@ DllCharacteristics
+		.long	0			@ SizeOfStackReserve
+		.long	0			@ SizeOfStackCommit
+		.long	0			@ SizeOfHeapReserve
+		.long	0			@ SizeOfHeapCommit
+		.long	0			@ LoaderFlags
+		.long	0x6			@ NumberOfRvaAndSizes
+
+		.quad	0			@ ExportTable
+		.quad	0			@ ImportTable
+		.quad	0			@ ResourceTable
+		.quad	0			@ ExceptionTable
+		.quad	0			@ CertificationTable
+		.quad	0			@ BaseRelocationTable
+
+section_table:
+		@
+		@ The EFI application loader requires a relocation section
+		@ because EFI applications must be relocatable. This is a
+		@ dummy section as far as we are concerned.
+		@
+		.ascii	".reloc\0\0"
+		.long	0			@ VirtualSize
+		.long	0			@ VirtualAddress
+		.long	0			@ SizeOfRawData
+		.long	0			@ PointerToRawData
+		.long	0			@ PointerToRelocations
+		.long	0			@ PointerToLineNumbers
+		.short	0			@ NumberOfRelocations
+		.short	0			@ NumberOfLineNumbers
+		.long	0x42100040		@ Characteristics
+
+		.ascii	".text\0\0\0"
+		.long	_end - __efi_start	@ VirtualSize
+		.long	__efi_start		@ VirtualAddress
+		.long	_edata - __efi_start	@ SizeOfRawData
+		.long	__efi_start		@ PointerToRawData
+		.long	0			@ PointerToRelocations
+		.long	0			@ PointerToLineNumbers
+		.short	0			@ NumberOfRelocations
+		.short	0			@ NumberOfLineNumbers
+		.long	0xe0500020		@ Characteristics
+
+		.align	9
+__efi_start:
+#endif
+		.endm
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 06e983f59980..af11c2f8f3b7 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -12,6 +12,8 @@
 #include <asm/assembler.h>
 #include <asm/v7m.h>
 
+#include "efi-header.S"
+
  AR_CLASS(	.arch	armv7-a	)
  M_CLASS(	.arch	armv7-m	)
 
@@ -126,7 +128,7 @@
 start:
 		.type	start,#function
 		.rept	7
-		mov	r0, r0
+		__nop
 		.endr
    ARM(		mov	r0, r0		)
    ARM(		b	1f		)
@@ -139,7 +141,8 @@ start:
 		.word	0x04030201	@ endianness flag
 
  THUMB(		.thumb			)
-1:
+1:		__EFI_HEADER
+
  ARM_BE8(	setend	be		)	@ go BE8 if compiled for BE8
  AR_CLASS(	mrs	r9, cpsr	)
 #ifdef CONFIG_ARM_VIRT_EXT
@@ -1353,6 +1356,53 @@ __enter_kernel:
 
 reloc_code_end:
 
+#ifdef CONFIG_EFI_STUB
+		.align	2
+_start:		.long	start - .
+
+ENTRY(efi_stub_entry)
+		@ allocate space on stack for passing current zImage address
+		@ and for the EFI stub to return of new entry point of
+		@ zImage, as EFI stub may copy the kernel. Pointer address
+		@ is passed in r2. r0 and r1 are passed through from the
+		@ EFI firmware to efi_entry
+		adr	ip, _start
+		ldr	r3, [ip]
+		add	r3, r3, ip
+		stmfd	sp!, {r3, lr}
+		mov	r2, sp			@ pass zImage address in r2
+		bl	efi_entry
+
+		@ Check for error return from EFI stub. r0 has FDT address
+		@ or error code.
+		cmn	r0, #1
+		beq	efi_load_fail
+
+		@ Preserve return value of efi_entry() in r4
+		mov	r4, r0
+		bl	cache_clean_flush
+		bl	cache_off
+
+		@ Set parameters for booting zImage according to boot protocol
+		@ put FDT address in r2, it was returned by efi_entry()
+		@ r1 is the machine type, and r0 needs to be 0
+		mov	r0, #0
+		mov	r1, #0xFFFFFFFF
+		mov	r2, r4
+
+		@ Branch to (possibly) relocated zImage that is in [sp]
+		ldr	lr, [sp]
+		ldr	ip, =start_offset
+		add	lr, lr, ip
+		mov	pc, lr				@ no mode switch
+
+efi_load_fail:
+		@ Return EFI_LOAD_ERROR to EFI firmware on error.
+		ldr	r0, =0x80000001
+		ldmfd	sp!, {ip, pc}
+ENDPROC(efi_stub_entry)
+#endif
+
 		.align
 		.section ".stack", "aw", %nobits
 .L_user_stack:	.space	4096
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index 2b60b843ac5e..81c493156ce8 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -48,6 +48,13 @@ SECTIONS
     *(.rodata)
     *(.rodata.*)
   }
+  .data : {
+    /*
+     * The EFI stub always executes from RAM, and runs strictly before the
+     * decompressor, so we can make an exception for its r/w data, and keep it
+     */
+    *(.data.efistub)
+  }
   .piggydata : {
     *(.piggydata)
   }
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index bd425302c97a..16da6380eb85 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -3,6 +3,7 @@
 generic-y += bitsperlong.h
 generic-y += cputime.h
 generic-y += current.h
+generic-y += early_ioremap.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index e7335a92144e..4e6e88a6b2f4 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -5,8 +5,6 @@
 #include <linux/types.h>
 #include <asm/opcodes.h>
 
-#ifdef CONFIG_BUG
-
 /*
  * Use a suitable undefined instruction to use for ARM/Thumb2 bug handling.
  * We need to be careful not to conflict with those used by other modules and
@@ -47,7 +45,7 @@ do {								\
 	unreachable();						\
 } while (0)
 
-#else  /* not CONFIG_DEBUG_BUGVERBOSE */
+#else
 
 #define __BUG(__file, __line, __value)				\
 do {								\
@@ -57,7 +55,6 @@ do {								\
 #endif  /* CONFIG_DEBUG_BUGVERBOSE */
 
 #define HAVE_ARCH_BUG
-#endif  /* CONFIG_BUG */
 
 #include <asm-generic/bug.h>
 
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
index 0f8424924902..3848259bebf8 100644
--- a/arch/arm/include/asm/cpuidle.h
+++ b/arch/arm/include/asm/cpuidle.h
@@ -30,7 +30,7 @@ static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
 struct device_node;
 
 struct cpuidle_ops {
-	int (*suspend)(int cpu, unsigned long arg);
+	int (*suspend)(unsigned long arg);
 	int (*init)(struct device_node *, int cpu);
 };
 
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
new file mode 100644
index 000000000000..e0eea72deb87
--- /dev/null
+++ b/arch/arm/include/asm/efi.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can 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_ARM_EFI_H
+#define __ASM_ARM_EFI_H
+
+#include <asm/cacheflush.h>
+#include <asm/cachetype.h>
+#include <asm/early_ioremap.h>
+#include <asm/fixmap.h>
+#include <asm/highmem.h>
+#include <asm/mach/map.h>
+#include <asm/mmu_context.h>
+#include <asm/pgtable.h>
+
+#ifdef CONFIG_EFI
+void efi_init(void);
+
+int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
+
+#define efi_call_virt(f, ...)						\
+({									\
+	efi_##f##_t *__f;						\
+	efi_status_t __s;						\
+									\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
+	__s = __f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
+	__s;								\
+})
+
+#define __efi_call_virt(f, ...)						\
+({									\
+	efi_##f##_t *__f;						\
+									\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
+	__f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
+})
+
+static inline void efi_set_pgd(struct mm_struct *mm)
+{
+	check_and_switch_context(mm, NULL);
+}
+
+void efi_virtmap_load(void);
+void efi_virtmap_unload(void);
+
+#else
+#define efi_init()
+#endif /* CONFIG_EFI */
+
+/* arch specific definitions used by the stub code */
+
+#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
+
+/*
+ * A reasonable upper bound for the uncompressed kernel size is 32 MBytes,
+ * so we will reserve that amount of memory. We have no easy way to tell what
+ * the actuall size of code + data the uncompressed kernel will use.
+ * If this is insufficient, the decompressor will relocate itself out of the
+ * way before performing the decompression.
+ */
+#define MAX_UNCOMP_KERNEL_SIZE	SZ_32M
+
+/*
+ * The kernel zImage should preferably be located between 32 MB and 128 MB
+ * from the base of DRAM. The min address leaves space for a maximal size
+ * uncompressed image, and the max address is due to how the zImage decompressor
+ * picks a destination address.
+ */
+#define ZIMAGE_OFFSET_LIMIT	SZ_128M
+#define MIN_ZIMAGE_OFFSET	MAX_UNCOMP_KERNEL_SIZE
+#define MAX_FDT_OFFSET		ZIMAGE_OFFSET_LIMIT
+
+#endif /* _ASM_ARM_EFI_H */
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index 58cfe9f1a687..5c17d2dec777 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -19,20 +19,47 @@ enum fixed_addresses {
 	FIX_TEXT_POKE0,
 	FIX_TEXT_POKE1,
 
-	__end_of_fixed_addresses
+	__end_of_fixmap_region,
+
+	/*
+	 * Share the kmap() region with early_ioremap(): this is guaranteed
+	 * not to clash since early_ioremap() is only available before
+	 * paging_init(), and kmap() only after.
+	 */
+#define NR_FIX_BTMAPS		32
+#define FIX_BTMAPS_SLOTS	7
+#define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
+	__end_of_early_ioremap_region
 };
 
+static const enum fixed_addresses __end_of_fixed_addresses =
+	__end_of_fixmap_region > __end_of_early_ioremap_region ?
+	__end_of_fixmap_region : __end_of_early_ioremap_region;
+
 #define FIXMAP_PAGE_COMMON	(L_PTE_YOUNG | L_PTE_PRESENT | L_PTE_XN | L_PTE_DIRTY)
 
 #define FIXMAP_PAGE_NORMAL	(FIXMAP_PAGE_COMMON | L_PTE_MT_WRITEBACK)
+#define FIXMAP_PAGE_RO		(FIXMAP_PAGE_NORMAL | L_PTE_RDONLY)
 
 /* Used by set_fixmap_(io|nocache), both meant for mapping a device */
 #define FIXMAP_PAGE_IO		(FIXMAP_PAGE_COMMON | L_PTE_MT_DEV_SHARED | L_PTE_SHARED)
 #define FIXMAP_PAGE_NOCACHE	FIXMAP_PAGE_IO
 
+#define __early_set_fixmap	__set_fixmap
+
+#ifdef CONFIG_MMU
+
 void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
 void __init early_fixmap_init(void);
 
 #include <asm-generic/fixmap.h>
 
+#else
+
+static inline void early_fixmap_init(void) { }
+
+#endif
 #endif
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index fe3ea776dc34..3d7351c844aa 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,7 +5,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	8
+#define NR_IPI	7
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h
index f98c7f32c9c8..9b7c328fb207 100644
--- a/arch/arm/include/asm/mach/map.h
+++ b/arch/arm/include/asm/mach/map.h
@@ -42,6 +42,8 @@ enum {
 extern void iotable_init(struct map_desc *, int);
 extern void vm_reserve_area_early(unsigned long addr, unsigned long size,
 				  void *caller);
+extern void create_mapping_late(struct mm_struct *mm, struct map_desc *md,
+				bool ng);
 
 #ifdef CONFIG_DEBUG_LL
 extern void debug_ll_addr(unsigned long *paddr, unsigned long *vaddr);
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 9b32f76bb0dd..432ce8176498 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -26,7 +26,7 @@ void __check_vmalloc_seq(struct mm_struct *mm);
 #ifdef CONFIG_CPU_HAS_ASID
 
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
-#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
 #ifdef CONFIG_ARM_ERRATA_798181
 void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index 68ee3ce17b82..b4c6d99364f1 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -16,7 +16,7 @@
 
 extern struct smp_operations psci_smp_ops;
 
-#ifdef CONFIG_ARM_PSCI
+#if defined(CONFIG_SMP) && defined(CONFIG_ARM_PSCI)
 bool psci_smp_available(void);
 #else
 static inline bool psci_smp_available(void) { return false; }
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index e0adb9f1bf94..3613d7e9fc40 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -25,4 +25,10 @@ extern int arm_add_memory(u64 start, u64 size);
 extern void early_print(const char *str, ...);
 extern void dump_machine_table(void);
 
+#ifdef CONFIG_ATAGS_PROC
+extern void save_atags(const struct tag *tags);
+#else
+static inline void save_atags(const struct tag *tags) { }
+#endif
+
 #endif
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index af9e59bf3831..f729085ece28 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -73,10 +73,10 @@ obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o perf_callchain.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event_xscale.o perf_event_v6.o \
 				   perf_event_v7.o
-CFLAGS_pj4-cp0.o		:= -marm
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
 obj-$(CONFIG_VDSO)		+= vdso.o
+obj-$(CONFIG_EFI)		+= efi.o
 
 ifneq ($(CONFIG_ARCH_EBSA110),y)
   obj-y		+= io.o
@@ -88,8 +88,9 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
 ifeq ($(CONFIG_ARM_PSCI),y)
-obj-y				+= psci-call.o
 obj-$(CONFIG_SMP)		+= psci_smp.o
 endif
 
+obj-$(CONFIG_HAVE_ARM_SMCCC)	+= smccc-call.o
+
 extra-y := $(head-y) vmlinux.lds
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index f89811fb9a55..7e45f69a0ddc 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -16,6 +16,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/arm-smccc.h>
 
 #include <asm/checksum.h>
 #include <asm/ftrace.h>
@@ -175,3 +176,8 @@ EXPORT_SYMBOL(__gnu_mcount_nc);
 EXPORT_SYMBOL(__pv_phys_pfn_offset);
 EXPORT_SYMBOL(__pv_offset);
 #endif
+
+#ifdef CONFIG_HAVE_ARM_SMCCC
+EXPORT_SYMBOL(arm_smccc_smc);
+EXPORT_SYMBOL(arm_smccc_hvc);
+#endif
diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h
index ec4164da6e30..edfa2268c127 100644
--- a/arch/arm/kernel/atags.h
+++ b/arch/arm/kernel/atags.h
@@ -1,9 +1,3 @@
-#ifdef CONFIG_ATAGS_PROC
-extern void save_atags(struct tag *tags);
-#else
-static inline void save_atags(struct tag *tags) { }
-#endif
-
 void convert_to_tag_list(struct tag *tags);
 
 #ifdef CONFIG_ATAGS
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
index 318da33465f4..703926e7007b 100644
--- a/arch/arm/kernel/cpuidle.c
+++ b/arch/arm/kernel/cpuidle.c
@@ -56,7 +56,7 @@ int arm_cpuidle_suspend(int index)
 	int cpu = smp_processor_id();
 
 	if (cpuidle_ops[cpu].suspend)
-		ret = cpuidle_ops[cpu].suspend(cpu, index);
+		ret = cpuidle_ops[cpu].suspend(index);
 
 	return ret;
 }
diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c
new file mode 100644
index 000000000000..ff8a9d8acfac
--- /dev/null
+++ b/arch/arm/kernel/efi.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can 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/efi.h>
+#include <asm/efi.h>
+#include <asm/mach/map.h>
+#include <asm/mmu_context.h>
+
+int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
+{
+	struct map_desc desc = {
+		.virtual	= md->virt_addr,
+		.pfn		= __phys_to_pfn(md->phys_addr),
+		.length		= md->num_pages * EFI_PAGE_SIZE,
+	};
+
+	/*
+	 * Order is important here: memory regions may have all of the
+	 * bits below set (and usually do), so we check them in order of
+	 * preference.
+	 */
+	if (md->attribute & EFI_MEMORY_WB)
+		desc.type = MT_MEMORY_RWX;
+	else if (md->attribute & EFI_MEMORY_WT)
+		desc.type = MT_MEMORY_RWX_NONCACHED;
+	else if (md->attribute & EFI_MEMORY_WC)
+		desc.type = MT_DEVICE_WC;
+	else
+		desc.type = MT_DEVICE;
+
+	create_mapping_late(mm, &desc, true);
+	return 0;
+}
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index b6c8bb9315e7..907534f97053 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -88,7 +88,7 @@ __pendsv_entry:
 	@ execute the pending work, including reschedule
 	get_thread_info tsk
 	mov	why, #0
-	b	ret_to_user
+	b	ret_to_user_from_irq
 ENDPROC(__pendsv_entry)
 
 /*
diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c
index 8153e36b2491..7c9248b74d3f 100644
--- a/arch/arm/kernel/pj4-cp0.c
+++ b/arch/arm/kernel/pj4-cp0.c
@@ -66,9 +66,13 @@ static void __init pj4_cp_access_write(u32 value)
 
 	__asm__ __volatile__ (
 		"mcr	p15, 0, %1, c1, c0, 2\n\t"
+#ifdef CONFIG_THUMB2_KERNEL
+		"isb\n\t"
+#else
 		"mrc	p15, 0, %0, c1, c0, 2\n\t"
 		"mov	%0, %0\n\t"
 		"sub	pc, pc, #4\n\t"
+#endif
 		: "=r" (temp) : "r" (value));
 }
 
diff --git a/arch/arm/kernel/psci-call.S b/arch/arm/kernel/psci-call.S
deleted file mode 100644
index a78e9e1e206d..000000000000
--- a/arch/arm/kernel/psci-call.S
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * This program is free software; you can 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 (C) 2015 ARM Limited
- *
- * Author: Mark Rutland <mark.rutland@arm.com>
- */
-
-#include <linux/linkage.h>
-
-#include <asm/opcodes-sec.h>
-#include <asm/opcodes-virt.h>
-
-/* int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */
-ENTRY(__invoke_psci_fn_hvc)
-	__HVC(0)
-	bx	lr
-ENDPROC(__invoke_psci_fn_hvc)
-
-/* int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */
-ENTRY(__invoke_psci_fn_smc)
-	__SMC(0)
-	bx	lr
-ENDPROC(__invoke_psci_fn_smc)
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 20edd349d379..7d0cba6f1cc5 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -7,6 +7,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/efi.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/stddef.h>
@@ -37,7 +38,9 @@
 #include <asm/cp15.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
+#include <asm/efi.h>
 #include <asm/elf.h>
+#include <asm/early_ioremap.h>
 #include <asm/fixmap.h>
 #include <asm/procinfo.h>
 #include <asm/psci.h>
@@ -375,6 +378,72 @@ void __init early_print(const char *str, ...)
 	printk("%s", buf);
 }
 
+#ifdef CONFIG_ARM_PATCH_IDIV
+
+static inline u32 __attribute_const__ sdiv_instruction(void)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* "sdiv r0, r0, r1" */
+		u32 insn = __opcode_thumb32_compose(0xfb90, 0xf0f1);
+		return __opcode_to_mem_thumb32(insn);
+	}
+
+	/* "sdiv r0, r0, r1" */
+	return __opcode_to_mem_arm(0xe710f110);
+}
+
+static inline u32 __attribute_const__ udiv_instruction(void)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* "udiv r0, r0, r1" */
+		u32 insn = __opcode_thumb32_compose(0xfbb0, 0xf0f1);
+		return __opcode_to_mem_thumb32(insn);
+	}
+
+	/* "udiv r0, r0, r1" */
+	return __opcode_to_mem_arm(0xe730f110);
+}
+
+static inline u32 __attribute_const__ bx_lr_instruction(void)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* "bx lr; nop" */
+		u32 insn = __opcode_thumb32_compose(0x4770, 0x46c0);
+		return __opcode_to_mem_thumb32(insn);
+	}
+
+	/* "bx lr" */
+	return __opcode_to_mem_arm(0xe12fff1e);
+}
+
+static void __init patch_aeabi_idiv(void)
+{
+	extern void __aeabi_uidiv(void);
+	extern void __aeabi_idiv(void);
+	uintptr_t fn_addr;
+	unsigned int mask;
+
+	mask = IS_ENABLED(CONFIG_THUMB2_KERNEL) ? HWCAP_IDIVT : HWCAP_IDIVA;
+	if (!(elf_hwcap & mask))
+		return;
+
+	pr_info("CPU: div instructions available: patching division code\n");
+
+	fn_addr = ((uintptr_t)&__aeabi_uidiv) & ~1;
+	((u32 *)fn_addr)[0] = udiv_instruction();
+	((u32 *)fn_addr)[1] = bx_lr_instruction();
+	flush_icache_range(fn_addr, fn_addr + 8);
+
+	fn_addr = ((uintptr_t)&__aeabi_idiv) & ~1;
+	((u32 *)fn_addr)[0] = sdiv_instruction();
+	((u32 *)fn_addr)[1] = bx_lr_instruction();
+	flush_icache_range(fn_addr, fn_addr + 8);
+}
+
+#else
+static inline void patch_aeabi_idiv(void) { }
+#endif
+
 static void __init cpuid_init_hwcaps(void)
 {
 	int block;
@@ -642,6 +711,7 @@ static void __init setup_processor(void)
 	elf_hwcap = list->elf_hwcap;
 
 	cpuid_init_hwcaps();
+	patch_aeabi_idiv();
 
 #ifndef CONFIG_ARM_THUMB
 	elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
@@ -956,8 +1026,8 @@ void __init setup_arch(char **cmdline_p)
 	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = cmd_line;
 
-	if (IS_ENABLED(CONFIG_FIX_EARLYCON_MEM))
-		early_fixmap_init();
+	early_fixmap_init();
+	early_ioremap_init();
 
 	parse_early_param();
 
@@ -965,9 +1035,12 @@ void __init setup_arch(char **cmdline_p)
 	early_paging_init(mdesc);
 #endif
 	setup_dma_zone(mdesc);
+	efi_init();
 	sanity_check_meminfo();
 	arm_memblock_init(mdesc);
 
+	early_ioremap_reset();
+
 	paging_init(mdesc);
 	request_standard_resources(mdesc);
 
diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S
new file mode 100644
index 000000000000..2e48b674aab1
--- /dev/null
+++ b/arch/arm/kernel/smccc-call.S
@@ -0,0 +1,62 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/linkage.h>
+
+#include <asm/opcodes-sec.h>
+#include <asm/opcodes-virt.h>
+#include <asm/unwind.h>
+
+	/*
+	 * Wrap c macros in asm macros to delay expansion until after the
+	 * SMCCC asm macro is expanded.
+	 */
+	.macro SMCCC_SMC
+	__SMC(0)
+	.endm
+
+	.macro SMCCC_HVC
+	__HVC(0)
+	.endm
+
+	.macro SMCCC instr
+UNWIND(	.fnstart)
+	mov	r12, sp
+	push	{r4-r7}
+UNWIND(	.save	{r4-r7})
+	ldm	r12, {r4-r7}
+	\instr
+	pop	{r4-r7}
+	ldr	r12, [sp, #(4 * 4)]
+	stm	r12, {r0-r3}
+	bx	lr
+UNWIND(	.fnend)
+	.endm
+
+/*
+ * void smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_smc)
+	SMCCC SMCCC_SMC
+ENDPROC(arm_smccc_smc)
+
+/*
+ * void smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_hvc)
+	SMCCC SMCCC_HVC
+ENDPROC(arm_smccc_hvc)
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index b26361355dae..37312f6749f3 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -69,11 +69,15 @@ enum ipi_msg_type {
 	IPI_TIMER,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
-	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
 	IPI_IRQ_WORK,
 	IPI_COMPLETION,
-	IPI_CPU_BACKTRACE = 15,
+	IPI_CPU_BACKTRACE,
+	/*
+	 * SGI8-15 can be reserved by secure firmware, and thus may
+	 * not be usable by the kernel. Please keep the above limited
+	 * to at most 8 entries.
+	 */
 };
 
 static DECLARE_COMPLETION(cpu_running);
@@ -475,7 +479,6 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_TIMER, "Timer broadcast interrupts"),
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
 	S(IPI_CALL_FUNC, "Function call interrupts"),
-	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
 	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 	S(IPI_COMPLETION, "completion interrupts"),
@@ -525,7 +528,7 @@ void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC);
 }
 
 #ifdef CONFIG_IRQ_WORK
@@ -620,12 +623,6 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
-	case IPI_CALL_FUNC_SINGLE:
-		irq_enter();
-		generic_smp_call_function_single_interrupt();
-		irq_exit();
-		break;
-
 	case IPI_CPU_STOP:
 		irq_enter();
 		ipi_cpu_stop(cpu);
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 54a5aeab988d..994e971a8538 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -224,7 +224,7 @@ static int install_vvar(struct mm_struct *mm, unsigned long addr)
 				       VM_READ | VM_MAYREAD,
 				       &vdso_data_mapping);
 
-	return IS_ERR(vma) ? PTR_ERR(vma) : 0;
+	return PTR_ERR_OR_ZERO(vma);
 }
 
 /* assumes mmap_sem is write-locked */
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index af2267f6a529..9397b2e532af 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -205,6 +205,10 @@ Boston, MA 02111-1307, USA.  */
 .endm
 
 
+#ifdef CONFIG_ARM_PATCH_IDIV
+	.align	3
+#endif
+
 ENTRY(__udivsi3)
 ENTRY(__aeabi_uidiv)
 UNWIND(.fnstart)
@@ -253,6 +257,10 @@ UNWIND(.fnstart)
 UNWIND(.fnend)
 ENDPROC(__umodsi3)
 
+#ifdef CONFIG_ARM_PATCH_IDIV
+	.align 3
+#endif
+
 ENTRY(__divsi3)
 ENTRY(__aeabi_idiv)
 UNWIND(.fnstart)
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 04a56cc04dfa..809827265fb3 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -16,6 +16,7 @@
 #include <linux/of_platform.h>
 #include <linux/irqdomain.h>
 
+#include <asm/setup.h>
 #include <asm/mach/arch.h>
 
 #include "common.h"
@@ -76,8 +77,17 @@ static const char *const n900_boards_compat[] __initconst = {
 	NULL,
 };
 
+/* Legacy userspace on Nokia N900 needs ATAGS exported in /proc/atags,
+ * save them while the data is still not overwritten
+ */
+static void __init rx51_reserve(void)
+{
+	save_atags((const struct tag *)(PAGE_OFFSET + 0x100));
+	omap_reserve();
+}
+
 DT_MACHINE_START(OMAP3_N900_DT, "Nokia RX-51 board")
-	.reserve	= omap_reserve,
+	.reserve	= rx51_reserve,
 	.map_io		= omap3_map_io,
 	.init_early	= omap3430_init_early,
 	.init_machine	= omap_generic_init,
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 493692d838c6..9f9d54271aad 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -790,7 +790,7 @@ static const struct l2c_init_data l2c310_init_fns __initconst = {
 };
 
 static int __init __l2c_init(const struct l2c_init_data *data,
-			     u32 aux_val, u32 aux_mask, u32 cache_id)
+			     u32 aux_val, u32 aux_mask, u32 cache_id, bool nosync)
 {
 	struct outer_cache_fns fns;
 	unsigned way_size_bits, ways;
@@ -866,6 +866,10 @@ static int __init __l2c_init(const struct l2c_init_data *data,
 	fns.configure = outer_cache.configure;
 	if (data->fixup)
 		data->fixup(l2x0_base, cache_id, &fns);
+	if (nosync) {
+		pr_info("L2C: disabling outer sync\n");
+		fns.sync = NULL;
+	}
 
 	/*
 	 * Check if l2x0 controller is already enabled.  If we are booting
@@ -925,7 +929,7 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	if (data->save)
 		data->save(l2x0_base);
 
-	__l2c_init(data, aux_val, aux_mask, cache_id);
+	__l2c_init(data, aux_val, aux_mask, cache_id, false);
 }
 
 #ifdef CONFIG_OF
@@ -1060,6 +1064,18 @@ static void __init l2x0_of_parse(const struct device_node *np,
 		val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT;
 	}
 
+	if (of_property_read_bool(np, "arm,parity-enable")) {
+		mask &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+		val |= L2C_AUX_CTRL_PARITY_ENABLE;
+	} else if (of_property_read_bool(np, "arm,parity-disable")) {
+		mask &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+	}
+
+	if (of_property_read_bool(np, "arm,shared-override")) {
+		mask &= ~L2C_AUX_CTRL_SHARED_OVERRIDE;
+		val |= L2C_AUX_CTRL_SHARED_OVERRIDE;
+	}
+
 	ret = l2x0_cache_size_of_parse(np, aux_val, aux_mask, &assoc, SZ_256K);
 	if (ret)
 		return;
@@ -1176,6 +1192,14 @@ static void __init l2c310_of_parse(const struct device_node *np,
 		*aux_mask &= ~L2C_AUX_CTRL_SHARED_OVERRIDE;
 	}
 
+	if (of_property_read_bool(np, "arm,parity-enable")) {
+		*aux_val |= L2C_AUX_CTRL_PARITY_ENABLE;
+		*aux_mask &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+	} else if (of_property_read_bool(np, "arm,parity-disable")) {
+		*aux_val &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+		*aux_mask &= ~L2C_AUX_CTRL_PARITY_ENABLE;
+	}
+
 	prefetch = l2x0_saved_regs.prefetch_ctrl;
 
 	ret = of_property_read_u32(np, "arm,double-linefill", &val);
@@ -1704,6 +1728,7 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 	struct resource res;
 	u32 cache_id, old_aux;
 	u32 cache_level = 2;
+	bool nosync = false;
 
 	np = of_find_matching_node(NULL, l2x0_ids);
 	if (!np)
@@ -1742,6 +1767,8 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 	if (cache_level != 2)
 		pr_err("L2C: device tree specifies invalid cache level\n");
 
+	nosync = of_property_read_bool(np, "arm,outer-sync-disable");
+
 	/* Read back current (default) hardware configuration */
 	if (data->save)
 		data->save(l2x0_base);
@@ -1756,6 +1783,6 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 	else
 		cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
 
-	return __l2c_init(data, aux_val, aux_mask, cache_id);
+	return __l2c_init(data, aux_val, aux_mask, cache_id, nosync);
 }
 #endif
diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c
index 0502ba17a3ab..a6fa7b73fbe0 100644
--- a/arch/arm/mm/cache-uniphier.c
+++ b/arch/arm/mm/cache-uniphier.c
@@ -377,17 +377,6 @@ static const struct of_device_id uniphier_cache_match[] __initconst = {
 	{ /* sentinel */ }
 };
 
-static struct device_node * __init uniphier_cache_get_next_level_node(
-							struct device_node *np)
-{
-	u32 phandle;
-
-	if (of_property_read_u32(np, "next-level-cache", &phandle))
-		return NULL;
-
-	return of_find_node_by_phandle(phandle);
-}
-
 static int __init __uniphier_cache_init(struct device_node *np,
 					unsigned int *cache_level)
 {
@@ -491,7 +480,7 @@ static int __init __uniphier_cache_init(struct device_node *np,
 	 * next level cache fails because we want to continue with available
 	 * cache levels.
 	 */
-	next_np = uniphier_cache_get_next_level_node(np);
+	next_np = of_find_next_cache_node(np);
 	if (next_np) {
 		(*cache_level)++;
 		ret = __uniphier_cache_init(next_np, cache_level);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 7f8cd1b3557f..49bd08178008 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -192,7 +192,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
-	return memblock_is_memory(__pfn_to_phys(pfn));
+	return memblock_is_map_memory(__pfn_to_phys(pfn));
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
@@ -433,6 +433,9 @@ static void __init free_highpages(void)
 		if (end <= max_low)
 			continue;
 
+		if (memblock_is_nomap(mem))
+			continue;
+
 		/* Truncate partial highmem entries */
 		if (start < max_low)
 			start = max_low;
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 0c81056c1dd7..66a978d05958 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -30,6 +30,7 @@
 #include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/cacheflush.h>
+#include <asm/early_ioremap.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
@@ -469,3 +470,11 @@ int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr)
 }
 EXPORT_SYMBOL_GPL(pci_ioremap_io);
 #endif
+
+/*
+ * Must be called after early_fixmap_init
+ */
+void __init early_ioremap_init(void)
+{
+	early_ioremap_setup();
+}
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4867f5daf82c..a87f6cc3fa2b 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -390,7 +390,7 @@ void __init early_fixmap_init(void)
 	 * The early fixmap range spans multiple pmds, for which
 	 * we are not prepared:
 	 */
-	BUILD_BUG_ON((__fix_to_virt(__end_of_permanent_fixed_addresses) >> PMD_SHIFT)
+	BUILD_BUG_ON((__fix_to_virt(__end_of_early_ioremap_region) >> PMD_SHIFT)
 		     != FIXADDR_TOP >> PMD_SHIFT);
 
 	pmd = fixmap_pmd(FIXADDR_TOP);
@@ -572,7 +572,7 @@ static void __init build_mem_type_table(void)
 	 * in the Short-descriptor translation table format descriptors.
 	 */
 	if (cpu_arch == CPU_ARCH_ARMv7 &&
-		(read_cpuid_ext(CPUID_EXT_MMFR0) & 0xF) == 4) {
+		(read_cpuid_ext(CPUID_EXT_MMFR0) & 0xF) >= 4) {
 		user_pmd_table |= PMD_PXNTABLE;
 	}
 #endif
@@ -724,30 +724,49 @@ static void __init *early_alloc(unsigned long sz)
 	return early_alloc_aligned(sz, sz);
 }
 
-static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, unsigned long prot)
+static void *__init late_alloc(unsigned long sz)
+{
+	void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz));
+
+	BUG_ON(!ptr);
+	return ptr;
+}
+
+static pte_t * __init pte_alloc(pmd_t *pmd, unsigned long addr,
+				unsigned long prot,
+				void *(*alloc)(unsigned long sz))
 {
 	if (pmd_none(*pmd)) {
-		pte_t *pte = early_alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE);
+		pte_t *pte = alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE);
 		__pmd_populate(pmd, __pa(pte), prot);
 	}
 	BUG_ON(pmd_bad(*pmd));
 	return pte_offset_kernel(pmd, addr);
 }
 
+static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr,
+				      unsigned long prot)
+{
+	return pte_alloc(pmd, addr, prot, early_alloc);
+}
+
 static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 				  unsigned long end, unsigned long pfn,
-				  const struct mem_type *type)
+				  const struct mem_type *type,
+				  void *(*alloc)(unsigned long sz),
+				  bool ng)
 {
-	pte_t *pte = early_pte_alloc(pmd, addr, type->prot_l1);
+	pte_t *pte = pte_alloc(pmd, addr, type->prot_l1, alloc);
 	do {
-		set_pte_ext(pte, pfn_pte(pfn, __pgprot(type->prot_pte)), 0);
+		set_pte_ext(pte, pfn_pte(pfn, __pgprot(type->prot_pte)),
+			    ng ? PTE_EXT_NG : 0);
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
 static void __init __map_init_section(pmd_t *pmd, unsigned long addr,
 			unsigned long end, phys_addr_t phys,
-			const struct mem_type *type)
+			const struct mem_type *type, bool ng)
 {
 	pmd_t *p = pmd;
 
@@ -765,7 +784,7 @@ static void __init __map_init_section(pmd_t *pmd, unsigned long addr,
 		pmd++;
 #endif
 	do {
-		*pmd = __pmd(phys | type->prot_sect);
+		*pmd = __pmd(phys | type->prot_sect | (ng ? PMD_SECT_nG : 0));
 		phys += SECTION_SIZE;
 	} while (pmd++, addr += SECTION_SIZE, addr != end);
 
@@ -774,7 +793,8 @@ static void __init __map_init_section(pmd_t *pmd, unsigned long addr,
 
 static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 				      unsigned long end, phys_addr_t phys,
-				      const struct mem_type *type)
+				      const struct mem_type *type,
+				      void *(*alloc)(unsigned long sz), bool ng)
 {
 	pmd_t *pmd = pmd_offset(pud, addr);
 	unsigned long next;
@@ -792,10 +812,10 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 		 */
 		if (type->prot_sect &&
 				((addr | next | phys) & ~SECTION_MASK) == 0) {
-			__map_init_section(pmd, addr, next, phys, type);
+			__map_init_section(pmd, addr, next, phys, type, ng);
 		} else {
 			alloc_init_pte(pmd, addr, next,
-						__phys_to_pfn(phys), type);
+				       __phys_to_pfn(phys), type, alloc, ng);
 		}
 
 		phys += next - addr;
@@ -805,21 +825,24 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 
 static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
 				  unsigned long end, phys_addr_t phys,
-				  const struct mem_type *type)
+				  const struct mem_type *type,
+				  void *(*alloc)(unsigned long sz), bool ng)
 {
 	pud_t *pud = pud_offset(pgd, addr);
 	unsigned long next;
 
 	do {
 		next = pud_addr_end(addr, end);
-		alloc_init_pmd(pud, addr, next, phys, type);
+		alloc_init_pmd(pud, addr, next, phys, type, alloc, ng);
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
 }
 
 #ifndef CONFIG_ARM_LPAE
-static void __init create_36bit_mapping(struct map_desc *md,
-					const struct mem_type *type)
+static void __init create_36bit_mapping(struct mm_struct *mm,
+					struct map_desc *md,
+					const struct mem_type *type,
+					bool ng)
 {
 	unsigned long addr, length, end;
 	phys_addr_t phys;
@@ -859,7 +882,7 @@ static void __init create_36bit_mapping(struct map_desc *md,
 	 */
 	phys |= (((md->pfn >> (32 - PAGE_SHIFT)) & 0xF) << 20);
 
-	pgd = pgd_offset_k(addr);
+	pgd = pgd_offset(mm, addr);
 	end = addr + length;
 	do {
 		pud_t *pud = pud_offset(pgd, addr);
@@ -867,7 +890,8 @@ static void __init create_36bit_mapping(struct map_desc *md,
 		int i;
 
 		for (i = 0; i < 16; i++)
-			*pmd++ = __pmd(phys | type->prot_sect | PMD_SECT_SUPER);
+			*pmd++ = __pmd(phys | type->prot_sect | PMD_SECT_SUPER |
+				       (ng ? PMD_SECT_nG : 0));
 
 		addr += SUPERSECTION_SIZE;
 		phys += SUPERSECTION_SIZE;
@@ -876,33 +900,15 @@ static void __init create_36bit_mapping(struct map_desc *md,
 }
 #endif	/* !CONFIG_ARM_LPAE */
 
-/*
- * Create the page directory entries and any necessary
- * page tables for the mapping specified by `md'.  We
- * are able to cope here with varying sizes and address
- * offsets, and we take full advantage of sections and
- * supersections.
- */
-static void __init create_mapping(struct map_desc *md)
+static void __init __create_mapping(struct mm_struct *mm, struct map_desc *md,
+				    void *(*alloc)(unsigned long sz),
+				    bool ng)
 {
 	unsigned long addr, length, end;
 	phys_addr_t phys;
 	const struct mem_type *type;
 	pgd_t *pgd;
 
-	if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) {
-		pr_warn("BUG: not creating mapping for 0x%08llx at 0x%08lx in user region\n",
-			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
-		return;
-	}
-
-	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
-	    md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START &&
-	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
-		pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n",
-			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
-	}
-
 	type = &mem_types[md->type];
 
 #ifndef CONFIG_ARM_LPAE
@@ -910,7 +916,7 @@ static void __init create_mapping(struct map_desc *md)
 	 * Catch 36-bit addresses
 	 */
 	if (md->pfn >= 0x100000) {
-		create_36bit_mapping(md, type);
+		create_36bit_mapping(mm, md, type, ng);
 		return;
 	}
 #endif
@@ -925,12 +931,12 @@ static void __init create_mapping(struct map_desc *md)
 		return;
 	}
 
-	pgd = pgd_offset_k(addr);
+	pgd = pgd_offset(mm, addr);
 	end = addr + length;
 	do {
 		unsigned long next = pgd_addr_end(addr, end);
 
-		alloc_init_pud(pgd, addr, next, phys, type);
+		alloc_init_pud(pgd, addr, next, phys, type, alloc, ng);
 
 		phys += next - addr;
 		addr = next;
@@ -938,6 +944,43 @@ static void __init create_mapping(struct map_desc *md)
 }
 
 /*
+ * Create the page directory entries and any necessary
+ * page tables for the mapping specified by `md'.  We
+ * are able to cope here with varying sizes and address
+ * offsets, and we take full advantage of sections and
+ * supersections.
+ */
+static void __init create_mapping(struct map_desc *md)
+{
+	if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) {
+		pr_warn("BUG: not creating mapping for 0x%08llx at 0x%08lx in user region\n",
+			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
+		return;
+	}
+
+	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
+	    md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START &&
+	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
+		pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n",
+			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
+	}
+
+	__create_mapping(&init_mm, md, early_alloc, false);
+}
+
+void __init create_mapping_late(struct mm_struct *mm, struct map_desc *md,
+				bool ng)
+{
+#ifdef CONFIG_ARM_LPAE
+	pud_t *pud = pud_alloc(mm, pgd_offset(mm, md->virtual), md->virtual);
+	if (WARN_ON(!pud))
+		return;
+	pmd_alloc(mm, pud, 0);
+#endif
+	__create_mapping(mm, md, late_alloc, ng);
+}
+
+/*
  * Create the architecture specific mappings
  */
 void __init iotable_init(struct map_desc *io_desc, int nr)
@@ -1392,6 +1435,9 @@ static void __init map_lowmem(void)
 		phys_addr_t end = start + reg->size;
 		struct map_desc map;
 
+		if (memblock_is_nomap(reg))
+			continue;
+
 		if (end > arm_lowmem_limit)
 			end = arm_lowmem_limit;
 		if (start >= end)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 8e1ea433c3f1..0f92d575a304 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -274,10 +274,12 @@ __v7_ca15mp_setup:
 __v7_b15mp_setup:
 __v7_ca17mp_setup:
 	mov	r10, #0
-1:	adr	r12, __v7_setup_stack		@ the local stack
-	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
+1:	adr	r0, __v7_setup_stack_ptr
+	ldr	r12, [r0]
+	add	r12, r12, r0			@ the local stack
+	stmia	r12, {r1-r6, lr}		@ v7_invalidate_l1 touches r0-r6
 	bl      v7_invalidate_l1
-	ldmia	r12, {r0-r5, lr}
+	ldmia	r12, {r1-r6, lr}
 #ifdef CONFIG_SMP
 	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)
 	ALT_UP(mov	r0, #(1 << 6))		@ fake it for UP
@@ -415,10 +417,12 @@ __v7_pj4b_setup:
 #endif /* CONFIG_CPU_PJ4B */
 
 __v7_setup:
-	adr	r12, __v7_setup_stack		@ the local stack
-	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
+	adr	r0, __v7_setup_stack_ptr
+	ldr	r12, [r0]
+	add	r12, r12, r0			@ the local stack
+	stmia	r12, {r1-r6, lr}		@ v7_invalidate_l1 touches r0-r6
 	bl      v7_invalidate_l1
-	ldmia	r12, {r0-r5, lr}
+	ldmia	r12, {r1-r6, lr}
 
 __v7_setup_cont:
 	and	r0, r9, #0xff000000		@ ARM?
@@ -480,11 +484,16 @@ __errata_finish:
 	orr	r0, r0, r6			@ set them
  THUMB(	orr	r0, r0, #1 << 30	)	@ Thumb exceptions
 	ret	lr				@ return to head.S:__ret
+
+	.align	2
+__v7_setup_stack_ptr:
+	.word	__v7_setup_stack - .
 ENDPROC(__v7_setup)
 
+	.bss
 	.align	2
 __v7_setup_stack:
-	.space	4 * 7				@ 12 registers
+	.space	4 * 7				@ 7 registers
 
 	__INITDATA
 
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 67d9209077c6..7229d8d0be1a 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -12,6 +12,7 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/memory.h>
 #include <asm/v7m.h>
 #include "proc-macros.S"
 
@@ -97,19 +98,19 @@ __v7m_setup:
 	mov	r5, #0x00800000
 	str	r5, [r0, V7M_SCB_SHPR3]	@ set PendSV priority
 
-	@ SVC to run the kernel in this mode
+	@ SVC to switch to handler mode. Notice that this requires sp to
+	@ point to writeable memory because the processor saves
+	@ some registers to the stack.
 	badr	r1, 1f
 	ldr	r5, [r12, #11 * 4]	@ read the SVC vector entry
 	str	r1, [r12, #11 * 4]	@ write the temporary SVC vector entry
 	mov	r6, lr			@ save LR
-	mov	r7, sp			@ save SP
-	ldr	sp, =__v7m_setup_stack_top
+	ldr	sp, =init_thread_union + THREAD_START_SP
 	cpsie	i
 	svc	#0
 1:	cpsid	i
 	str	r5, [r12, #11 * 4]	@ restore the original SVC vector entry
 	mov	lr, r6			@ restore LR
-	mov	sp, r7			@ restore SP
 
 	@ Special-purpose control register
 	mov	r1, #1
@@ -123,11 +124,6 @@ __v7m_setup:
 	ret	lr
 ENDPROC(__v7m_setup)
 
-	.align 2
-__v7m_setup_stack:
-	.space	4 * 8				@ 8 registers
-__v7m_setup_stack_top:
-
 	define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1
 
 	.section ".rodata"
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index ffa3c549a4ba..bf82ffe895bf 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -93,6 +93,7 @@ config ARM64
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_CONTEXT_TRACKING
+	select HAVE_ARM_SMCCC
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 474691f8b13a..27bf1e5180a1 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -14,10 +14,10 @@ CFLAGS_REMOVE_return_address.o = -pg
 arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o	\
+			   hyp-stub.o psci.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
-			   smp.o smp_spin_table.o topology.o
+			   smp.o smp_spin_table.o topology.o smccc-call.o
 
 extra-$(CONFIG_EFI)			:= efi-entry.o
 
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 3b6d8cc9dfe0..678f30b05a45 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -26,6 +26,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/arm-smccc.h>
 
 #include <asm/checksum.h>
 
@@ -68,3 +69,7 @@ EXPORT_SYMBOL(test_and_change_bit);
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
 #endif
+
+	/* arm-smccc */
+EXPORT_SYMBOL(arm_smccc_smc);
+EXPORT_SYMBOL(arm_smccc_hvc);
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 25de8b244961..bb493d44445f 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -28,6 +28,7 @@
 #include <asm/suspend.h>
 #include <asm/vdso_datapage.h>
 #include <linux/kbuild.h>
+#include <linux/arm-smccc.h>
 
 int main(void)
 {
@@ -161,5 +162,7 @@ int main(void)
   DEFINE(SLEEP_SAVE_SP_PHYS,	offsetof(struct sleep_save_sp, save_ptr_stash_phys));
   DEFINE(SLEEP_SAVE_SP_VIRT,	offsetof(struct sleep_save_sp, save_ptr_stash));
 #endif
+  DEFINE(ARM_SMCCC_RES_X0_OFFS,	offsetof(struct arm_smccc_res, a0));
+  DEFINE(ARM_SMCCC_RES_X2_OFFS,	offsetof(struct arm_smccc_res, a2));
   return 0;
 }
diff --git a/arch/arm64/kernel/psci-call.S b/arch/arm64/kernel/psci-call.S
deleted file mode 100644
index cf83e61cd3b5..000000000000
--- a/arch/arm64/kernel/psci-call.S
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * This program is free software; you can 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 (C) 2015 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#include <linux/linkage.h>
-
-/* int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
-ENTRY(__invoke_psci_fn_hvc)
-	hvc	#0
-	ret
-ENDPROC(__invoke_psci_fn_hvc)
-
-/* int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
-ENTRY(__invoke_psci_fn_smc)
-	smc	#0
-	ret
-ENDPROC(__invoke_psci_fn_smc)
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
new file mode 100644
index 000000000000..ae0496fa4235
--- /dev/null
+++ b/arch/arm64/kernel/smccc-call.S
@@ -0,0 +1,43 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This program is free software; you can 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.
+ *
+ */
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+
+	.macro SMCCC instr
+	.cfi_startproc
+	\instr	#0
+	ldr	x4, [sp]
+	stp	x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]
+	stp	x2, x3, [x4, #ARM_SMCCC_RES_X2_OFFS]
+	ret
+	.cfi_endproc
+	.endm
+
+/*
+ * void arm_smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_smc)
+	SMCCC	smc
+ENDPROC(arm_smccc_smc)
+
+/*
+ * void arm_smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_hvc)
+	SMCCC	hvc
+ENDPROC(arm_smccc_hvc)