Merge branch 'devel-stable' into for-linus

16 files changed, 474 insertions, 49 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 4728816..a4a756b 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
@@ -2060,6 +2061,25 @@ 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 3f9a9eb..4c23a68 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 0000000..9d5dc4f
--- /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 06e983f..af11c2f 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 2b60b84..81c4931 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 bd42530..16da638 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/efi.h b/arch/arm/include/asm/efi.h
new file mode 100644
index 0000000..e0eea72
--- /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 58cfe9f..5c17d2d 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/mach/map.h b/arch/arm/include/asm/mach/map.h
index f98c7f3..9b7c328 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 9b32f76..432ce81 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/kernel/Makefile b/arch/arm/kernel/Makefile
index 82bdac0..f729085 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -76,6 +76,7 @@ obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event_xscale.o perf_event_v6.o \
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(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
diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c
new file mode 100644
index 0000000..ff8a9d8
--- /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/setup.c b/arch/arm/kernel/setup.c
index e07f567..7d0cba6f 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>
@@ -1023,8 +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();
 
@@ -1032,9 +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/mm/init.c b/arch/arm/mm/init.c
index 7f8cd1b..49bd081 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 0c81056..66a978d 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 de9f892..a87f6cc 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);
@@ -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)